diff --git a/Documentation/ABI/testing/configfs-usb-gadget-loopback b/Documentation/ABI/testing/configfs-usb-gadget-loopback index 9aae5bf..06beefb 100644 --- a/Documentation/ABI/testing/configfs-usb-gadget-loopback +++ b/Documentation/ABI/testing/configfs-usb-gadget-loopback @@ -5,4 +5,4 @@ Description: The attributes: qlen - depth of loopback queue - bulk_buflen - buffer length + buflen - buffer length diff --git a/Documentation/ABI/testing/configfs-usb-gadget-sourcesink b/Documentation/ABI/testing/configfs-usb-gadget-sourcesink index 29477c3..bc7ff73 100644 --- a/Documentation/ABI/testing/configfs-usb-gadget-sourcesink +++ b/Documentation/ABI/testing/configfs-usb-gadget-sourcesink @@ -9,4 +9,4 @@ Description: isoc_maxpacket - 0 - 1023 (fs), 0 - 1024 (hs/ss) isoc_mult - 0..2 (hs/ss only) isoc_maxburst - 0..15 (ss only) - qlen - buffer length + buflen - buffer length diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy index 4c3efe4..750ab97 100644 --- a/Documentation/ABI/testing/ima_policy +++ b/Documentation/ABI/testing/ima_policy @@ -20,16 +20,18 @@ Description: action: measure | dont_measure | appraise | dont_appraise | audit condition:= base | lsm [option] base: [[func=] [mask=] [fsmagic=] [fsuuid=] [uid=] - [fowner]] + [euid=] [fowner=]] lsm: [[subj_user=] [subj_role=] [subj_type=] [obj_user=] [obj_role=] [obj_type=]] option: [[appraise_type=]] [permit_directio] base: func:= [BPRM_CHECK][MMAP_CHECK][FILE_CHECK][MODULE_CHECK] - mask:= [MAY_READ] [MAY_WRITE] [MAY_APPEND] [MAY_EXEC] + mask:= [[^]MAY_READ] [[^]MAY_WRITE] [[^]MAY_APPEND] + [[^]MAY_EXEC] fsmagic:= hex value fsuuid:= file system UUID (e.g 8bcbe394-4f13-4144-be8e-5aa9ea2ce2f6) uid:= decimal value + euid:= decimal value fowner:=decimal value lsm: are LSM specific option: appraise_type:= [imasig] diff --git a/Documentation/devicetree/bindings/ata/sata_rcar.txt b/Documentation/devicetree/bindings/ata/sata_rcar.txt index 1e61113..7dd32d3 100644 --- a/Documentation/devicetree/bindings/ata/sata_rcar.txt +++ b/Documentation/devicetree/bindings/ata/sata_rcar.txt @@ -3,7 +3,8 @@ Required properties: - compatible : should contain one of the following: - "renesas,sata-r8a7779" for R-Car H1 - - "renesas,sata-r8a7790" for R-Car H2 + - "renesas,sata-r8a7790-es1" for R-Car H2 ES1 + - "renesas,sata-r8a7790" for R-Car H2 other than ES1 - "renesas,sata-r8a7791" for R-Car M2 - reg : address and length of the SATA registers; - interrupts : must consist of one interrupt specifier. diff --git a/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt b/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt index a4873e5..e30e184 100644 --- a/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt +++ b/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt @@ -38,7 +38,7 @@ dma_apbx: dma-apbx@80024000 { 80 81 68 69 70 71 72 73 74 75 76 77>; - interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty", + interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty", "saif0", "saif1", "i2c0", "i2c1", "auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx", "auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx"; diff --git a/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt b/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt index 1486497..8a3c408 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt @@ -4,11 +4,13 @@ Specifying interrupt information for devices 1) Interrupt client nodes ------------------------- -Nodes that describe devices which generate interrupts must contain an either an -"interrupts" property or an "interrupts-extended" property. These properties -contain a list of interrupt specifiers, one per output interrupt. The format of -the interrupt specifier is determined by the interrupt controller to which the -interrupts are routed; see section 2 below for details. +Nodes that describe devices which generate interrupts must contain an +"interrupts" property, an "interrupts-extended" property, or both. If both are +present, the latter should take precedence; the former may be provided simply +for compatibility with software that does not recognize the latter. These +properties contain a list of interrupt specifiers, one per output interrupt. The +format of the interrupt specifier is determined by the interrupt controller to +which the interrupts are routed; see section 2 below for details. Example: interrupt-parent = <&intc1>; @@ -28,10 +30,6 @@ should only be used when a device has multiple interrupt parents. Example: interrupts-extended = <&intc1 5 1>, <&intc2 1 0>; -A device node may contain either "interrupts" or "interrupts-extended", but not -both. If both properties are present, then the operating system should log an -error and use only the data in "interrupts". - 2) Interrupt controller nodes ----------------------------- diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-370-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-370-pinctrl.txt index 01ef408..8faff12 100644 --- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-370-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-370-pinctrl.txt @@ -91,5 +91,5 @@ mpp61 61 gpo, dev(wen1), uart1(txd), audio(rclk) mpp62 62 gpio, dev(a2), uart1(cts), tdm(drx), pcie(clkreq0), audio(mclk), uart0(cts) mpp63 63 gpo, spi0(sck), tclk -mpp64 64 gpio, spi0(miso), spi0-1(cs1) -mpp65 65 gpio, spi0(mosi), spi0-1(cs2) +mpp64 64 gpio, spi0(miso), spi0(cs1) +mpp65 65 gpio, spi0(mosi), spi0(cs2) diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-xp-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-xp-pinctrl.txt index bfa0a2e..86dec67 100644 --- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-xp-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-xp-pinctrl.txt @@ -41,15 +41,15 @@ mpp20 20 gpio, ge0(rxd4), ge1(rxd2), lcd(d20), ptp(clk) mpp21 21 gpio, ge0(rxd5), ge1(rxd3), lcd(d21), mem(bat) mpp22 22 gpio, ge0(rxd6), ge1(rxctl), lcd(d22), sata0(prsnt) mpp23 23 gpio, ge0(rxd7), ge1(rxclk), lcd(d23), sata1(prsnt) -mpp24 24 gpio, lcd(hsync), sata1(prsnt), nf(bootcs-re), tdm(rst) -mpp25 25 gpio, lcd(vsync), sata0(prsnt), nf(bootcs-we), tdm(pclk) -mpp26 26 gpio, lcd(clk), tdm(fsync), vdd(cpu1-pd) +mpp24 24 gpio, lcd(hsync), sata1(prsnt), tdm(rst) +mpp25 25 gpio, lcd(vsync), sata0(prsnt), tdm(pclk) +mpp26 26 gpio, lcd(clk), tdm(fsync) mpp27 27 gpio, lcd(e), tdm(dtx), ptp(trig) mpp28 28 gpio, lcd(pwm), tdm(drx), ptp(evreq) -mpp29 29 gpio, lcd(ref-clk), tdm(int0), ptp(clk), vdd(cpu0-pd) +mpp29 29 gpio, lcd(ref-clk), tdm(int0), ptp(clk) mpp30 30 gpio, tdm(int1), sd0(clk) -mpp31 31 gpio, tdm(int2), sd0(cmd), vdd(cpu0-pd) -mpp32 32 gpio, tdm(int3), sd0(d0), vdd(cpu1-pd) +mpp31 31 gpio, tdm(int2), sd0(cmd) +mpp32 32 gpio, tdm(int3), sd0(d0) mpp33 33 gpio, tdm(int4), sd0(d1), mem(bat) mpp34 34 gpio, tdm(int5), sd0(d2), sata0(prsnt) mpp35 35 gpio, tdm(int6), sd0(d3), sata1(prsnt) @@ -57,21 +57,18 @@ mpp36 36 gpio, spi(mosi) mpp37 37 gpio, spi(miso) mpp38 38 gpio, spi(sck) mpp39 39 gpio, spi(cs0) -mpp40 40 gpio, spi(cs1), uart2(cts), lcd(vga-hsync), vdd(cpu1-pd), - pcie(clkreq0) +mpp40 40 gpio, spi(cs1), uart2(cts), lcd(vga-hsync), pcie(clkreq0) mpp41 41 gpio, spi(cs2), uart2(rts), lcd(vga-vsync), sata1(prsnt), pcie(clkreq1) -mpp42 42 gpio, uart2(rxd), uart0(cts), tdm(int7), tdm-1(timer), - vdd(cpu0-pd) -mpp43 43 gpio, uart2(txd), uart0(rts), spi(cs3), pcie(rstout), - vdd(cpu2-3-pd){1} +mpp42 42 gpio, uart2(rxd), uart0(cts), tdm(int7), tdm-1(timer) +mpp43 43 gpio, uart2(txd), uart0(rts), spi(cs3), pcie(rstout) mpp44 44 gpio, uart2(cts), uart3(rxd), spi(cs4), pcie(clkreq2), mem(bat) mpp45 45 gpio, uart2(rts), uart3(txd), spi(cs5), sata1(prsnt) mpp46 46 gpio, uart3(rts), uart1(rts), spi(cs6), sata0(prsnt) mpp47 47 gpio, uart3(cts), uart1(cts), spi(cs7), pcie(clkreq3), ref(clkout) -mpp48 48 gpio, tclk, dev(burst/last) +mpp48 48 gpio, dev(clkout), dev(burst/last) * Marvell Armada XP (mv78260 and mv78460 only) @@ -83,9 +80,9 @@ mpp51 51 gpio, dev(ad16) mpp52 52 gpio, dev(ad17) mpp53 53 gpio, dev(ad18) mpp54 54 gpio, dev(ad19) -mpp55 55 gpio, dev(ad20), vdd(cpu0-pd) -mpp56 56 gpio, dev(ad21), vdd(cpu1-pd) -mpp57 57 gpio, dev(ad22), vdd(cpu2-3-pd){1} +mpp55 55 gpio, dev(ad20) +mpp56 56 gpio, dev(ad21) +mpp57 57 gpio, dev(ad22) mpp58 58 gpio, dev(ad23) mpp59 59 gpio, dev(ad24) mpp60 60 gpio, dev(ad25) @@ -95,6 +92,3 @@ mpp63 63 gpio, dev(ad28) mpp64 64 gpio, dev(ad29) mpp65 65 gpio, dev(ad30) mpp66 66 gpio, dev(ad31) - -Notes: -* {1} vdd(cpu2-3-pd) only available on mv78460. diff --git a/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt b/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt index 46f3449..4eb7997 100644 --- a/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt +++ b/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt @@ -1,7 +1,7 @@ ADI AXI-SPDIF controller Required properties: - - compatible : Must be "adi,axi-spdif-1.00.a" + - compatible : Must be "adi,axi-spdif-tx-1.00.a" - reg : Must contain SPDIF core's registers location and length - clocks : Pairs of phandle and specifier referencing the controller's clocks. The controller expects two clocks, the clock used for the AXI interface and diff --git a/Documentation/devicetree/bindings/spi/spi_pl022.txt b/Documentation/devicetree/bindings/spi/spi_pl022.txt index 22ed679..4d1673c 100644 --- a/Documentation/devicetree/bindings/spi/spi_pl022.txt +++ b/Documentation/devicetree/bindings/spi/spi_pl022.txt @@ -4,9 +4,9 @@ Required properties: - compatible : "arm,pl022", "arm,primecell" - reg : Offset and length of the register set for the device - interrupts : Should contain SPI controller interrupt +- num-cs : total number of chipselects Optional properties: -- num-cs : total number of chipselects - cs-gpios : should specify GPIOs used for chipselects. The gpios will be referred to as reg = in the SPI child nodes. If unspecified, a single SPI device without a chip select can be used. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index cef2e7d..a666fd8 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1175,6 +1175,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. i8042.notimeout [HW] Ignore timeout condition signalled by controller i8042.reset [HW] Reset the controller during init and cleanup i8042.unlock [HW] Unlock (ignore) the keylock + i8042.kbdreset [HW] Reset device connected to KBD port i810= [HW,DRM] diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt index 69b3cac..5d86756 100644 --- a/Documentation/ramoops.txt +++ b/Documentation/ramoops.txt @@ -14,11 +14,19 @@ survive after a restart. 1. Ramoops concepts -Ramoops uses a predefined memory area to store the dump. The start and size of -the memory area are set using two variables: +Ramoops uses a predefined memory area to store the dump. The start and size +and type of the memory area are set using three variables: * "mem_address" for the start * "mem_size" for the size. The memory size will be rounded down to a power of two. + * "mem_type" to specifiy if the memory type (default is pgprot_writecombine). + +Typically the default value of mem_type=0 should be used as that sets the pstore +mapping to pgprot_writecombine. Setting mem_type=1 attempts to use +pgprot_noncached, which only works on some platforms. This is because pstore +depends on atomic operations. At least on ARM, pgprot_noncached causes the +memory to be mapped strongly ordered, and atomic operations on strongly ordered +memory are implementation defined, and won't work on many ARMs such as omaps. The memory area is divided into "record_size" chunks (also rounded down to power of two) and each oops/panic writes a "record_size" chunk of @@ -55,6 +63,7 @@ Setting the ramoops parameters can be done in 2 different manners: static struct ramoops_platform_data ramoops_data = { .mem_size = <...>, .mem_address = <...>, + .mem_type = <...>, .record_size = <...>, .dump_oops = <...>, .ecc = <...>, diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt index b8dd0df..0fd40b1 100644 --- a/Documentation/sound/alsa/ALSA-Configuration.txt +++ b/Documentation/sound/alsa/ALSA-Configuration.txt @@ -2026,8 +2026,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. ------------------- Module for sound cards based on the Asus AV66/AV100/AV200 chips, - i.e., Xonar D1, DX, D2, D2X, DS, Essence ST (Deluxe), Essence STX, - HDAV1.3 (Deluxe), and HDAV1.3 Slim. + i.e., Xonar D1, DX, D2, D2X, DS, DSX, Essence ST (Deluxe), + Essence STX (II), HDAV1.3 (Deluxe), and HDAV1.3 Slim. This module supports autoprobe and multiple cards. diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt index b0714d8..8dfb6a5 100644 --- a/Documentation/stable_kernel_rules.txt +++ b/Documentation/stable_kernel_rules.txt @@ -29,6 +29,9 @@ Rules on what kind of patches are accepted, and which ones are not, into the Procedure for submitting patches to the -stable tree: + - If the patch covers files in net/ or drivers/net please follow netdev stable + submission guidelines as described in + Documentation/networking/netdev-FAQ.txt - Send the patch, after verifying that it follows the above rules, to stable@vger.kernel.org. You must note the upstream commit ID in the changelog of your submission, as well as the kernel version you wish diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 6cd63a9..bc6d617 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -2344,7 +2344,8 @@ should be created before this ioctl is invoked. Possible features: - KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state. - Depends on KVM_CAP_ARM_PSCI. + Depends on KVM_CAP_ARM_PSCI. If not set, the CPU will be powered on + and execute guest code when KVM_RUN is called. - KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode. Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only). diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index 2908941..53838d9 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -425,6 +425,20 @@ fault through the slow path. Since only 19 bits are used to store generation-number on mmio spte, all pages are zapped when there is an overflow. +Unfortunately, a single memory access might access kvm_memslots(kvm) multiple +times, the last one happening when the generation number is retrieved and +stored into the MMIO spte. Thus, the MMIO spte might be created based on +out-of-date information, but with an up-to-date generation number. + +To avoid this, the generation number is incremented again after synchronize_srcu +returns; thus, the low bit of kvm_memslots(kvm)->generation is only 1 during a +memslot update, while some SRCU readers might be using the old copy. We do not +want to use an MMIO sptes created with an odd generation number, and we can do +this without losing a bit in the MMIO spte. The low bit of the generation +is not stored in MMIO spte, and presumed zero when it is extracted out of the +spte. If KVM is unlucky and creates an MMIO spte while the low bit is 1, +the next access to the spte will always be a cache miss. + Further reading =============== diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index c584a51..afe68dd 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt @@ -12,6 +12,8 @@ ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB) ... unused hole ... +ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks +... unused hole ... ffffffff80000000 - ffffffffa0000000 (=512 MB) kernel text mapping, from phys 0 ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls diff --git a/Makefile b/Makefile index 230c7f6..86d2277 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 14 -SUBLEVEL = 14 +SUBLEVEL = 53 EXTRAVERSION = NAME = Remembering Coco @@ -244,7 +244,7 @@ CONFIG_SHELL := $(shell if [ -x "$$BASH" ]; then echo $$BASH; \ HOSTCC = gcc HOSTCXX = g++ -HOSTCFLAGS = -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 -fomit-frame-pointer +HOSTCFLAGS = -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 -fomit-frame-pointer -std=gnu89 HOSTCXXFLAGS = -O2 # Decide whether to build built-in, modular, or both. @@ -382,7 +382,9 @@ KBUILD_CFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -fno-common \ -Werror-implicit-function-declaration \ -Wno-format-security \ - -fno-delete-null-pointer-checks + -fno-delete-null-pointer-checks \ + -std=gnu89 + KBUILD_AFLAGS_KERNEL := KBUILD_CFLAGS_KERNEL := KBUILD_AFLAGS := -D__ASSEMBLY__ @@ -639,6 +641,8 @@ KBUILD_CFLAGS += -fomit-frame-pointer endif endif +KBUILD_CFLAGS += $(call cc-option, -fno-var-tracking-assignments) + ifdef CONFIG_DEBUG_INFO KBUILD_CFLAGS += -g KBUILD_AFLAGS += -Wa,--gdwarf-2 diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 98838a0..9d0ac09 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -156,6 +156,8 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts index 4f31b2e..4c169d8 100644 --- a/arch/arc/boot/dts/nsimosci.dts +++ b/arch/arc/boot/dts/nsimosci.dts @@ -20,7 +20,7 @@ /* this is for console on PGU */ /* bootargs = "console=tty0 consoleblank=0"; */ /* this is for console on serial */ - bootargs = "earlycon=uart8250,mmio32,0xc0000000,115200n8 console=ttyS0,115200n8 consoleblank=0 debug"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug"; }; aliases { @@ -46,9 +46,9 @@ #interrupt-cells = <1>; }; - uart0: serial@c0000000 { + uart0: serial@f0000000 { compatible = "ns8250"; - reg = <0xc0000000 0x2000>; + reg = <0xf0000000 0x2000>; interrupts = <11>; clock-frequency = <3686400>; baud = <115200>; @@ -57,21 +57,21 @@ no-loopback-test = <1>; }; - pgu0: pgu@c9000000 { + pgu0: pgu@f9000000 { compatible = "snps,arcpgufb"; - reg = <0xc9000000 0x400>; + reg = <0xf9000000 0x400>; }; - ps2: ps2@c9001000 { + ps2: ps2@f9001000 { compatible = "snps,arc_ps2"; - reg = <0xc9000400 0x14>; + reg = <0xf9000400 0x14>; interrupts = <13>; interrupt-names = "arc_ps2_irq"; }; - eth0: ethernet@c0003000 { + eth0: ethernet@f0003000 { compatible = "snps,oscilan"; - reg = <0xc0003000 0x44>; + reg = <0xf0003000 0x44>; interrupts = <7>, <8>; interrupt-names = "rx", "tx"; }; diff --git a/arch/arc/include/asm/barrier.h b/arch/arc/include/asm/barrier.h deleted file mode 100644 index c32245c..0000000 --- a/arch/arc/include/asm/barrier.h +++ /dev/null @@ -1,37 +0,0 @@ -/* - * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef __ASM_BARRIER_H -#define __ASM_BARRIER_H - -#ifndef __ASSEMBLY__ - -/* TODO-vineetg: Need to see what this does, don't we need sync anywhere */ -#define mb() __asm__ __volatile__ ("" : : : "memory") -#define rmb() mb() -#define wmb() mb() -#define set_mb(var, value) do { var = value; mb(); } while (0) -#define set_wmb(var, value) do { var = value; wmb(); } while (0) -#define read_barrier_depends() mb() - -/* TODO-vineetg verify the correctness of macros here */ -#ifdef CONFIG_SMP -#define smp_mb() mb() -#define smp_rmb() rmb() -#define smp_wmb() wmb() -#else -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#endif - -#define smp_read_barrier_depends() do { } while (0) - -#endif - -#endif diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index 2fd3162..c1d3d2d 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -55,4 +55,31 @@ extern void read_decode_cache_bcr(void); #endif /* !__ASSEMBLY__ */ +/* Instruction cache related Auxiliary registers */ +#define ARC_REG_IC_BCR 0x77 /* Build Config reg */ +#define ARC_REG_IC_IVIC 0x10 +#define ARC_REG_IC_CTRL 0x11 +#define ARC_REG_IC_IVIL 0x19 +#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4) +#define ARC_REG_IC_PTAG 0x1E +#endif + +/* Bit val in IC_CTRL */ +#define IC_CTRL_CACHE_DISABLE 0x1 + +/* Data cache related Auxiliary registers */ +#define ARC_REG_DC_BCR 0x72 /* Build Config reg */ +#define ARC_REG_DC_IVDC 0x47 +#define ARC_REG_DC_CTRL 0x48 +#define ARC_REG_DC_IVDL 0x4A +#define ARC_REG_DC_FLSH 0x4B +#define ARC_REG_DC_FLDL 0x4C +#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4) +#define ARC_REG_DC_PTAG 0x5C +#endif + +/* Bit val in DC_CTRL */ +#define DC_CTRL_INV_MODE_FLUSH 0x40 +#define DC_CTRL_FLUSH_STATUS 0x100 + #endif /* _ASM_CACHE_H */ diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h index 03cd689..90de5c5 100644 --- a/arch/arc/include/asm/cmpxchg.h +++ b/arch/arc/include/asm/cmpxchg.h @@ -25,10 +25,11 @@ __cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new) " scond %3, [%1] \n" " bnz 1b \n" "2: \n" - : "=&r"(prev) - : "r"(ptr), "ir"(expected), - "r"(new) /* can't be "ir". scond can't take limm for "b" */ - : "cc"); + : "=&r"(prev) /* Early clobber, to prevent reg reuse */ + : "r"(ptr), /* Not "m": llock only supports reg direct addr mode */ + "ir"(expected), + "r"(new) /* can't be "ir". scond can't take LIMM for "b" */ + : "cc", "memory"); /* so that gcc knows memory is being written here */ return prev; } diff --git a/arch/arc/include/asm/kgdb.h b/arch/arc/include/asm/kgdb.h index b65fca7..fea9316 100644 --- a/arch/arc/include/asm/kgdb.h +++ b/arch/arc/include/asm/kgdb.h @@ -19,7 +19,7 @@ * register API yet */ #undef DBG_MAX_REG_NUM -#define GDB_MAX_REGS 39 +#define GDB_MAX_REGS 87 #define BREAK_INSTR_SIZE 2 #define CACHE_FLUSH_IS_SAFE 1 @@ -33,23 +33,27 @@ static inline void arch_kgdb_breakpoint(void) extern void kgdb_trap(struct pt_regs *regs); -enum arc700_linux_regnums { +/* This is the numbering of registers according to the GDB. See GDB's + * arc-tdep.h for details. + * + * Registers are ordered for GDB 7.5. It is incompatible with GDB 6.8. */ +enum arc_linux_regnums { _R0 = 0, _R1, _R2, _R3, _R4, _R5, _R6, _R7, _R8, _R9, _R10, _R11, _R12, _R13, _R14, _R15, _R16, _R17, _R18, _R19, _R20, _R21, _R22, _R23, _R24, _R25, _R26, - _BTA = 27, - _LP_START = 28, - _LP_END = 29, - _LP_COUNT = 30, - _STATUS32 = 31, - _BLINK = 32, - _FP = 33, - __SP = 34, - _EFA = 35, - _RET = 36, - _ORIG_R8 = 37, - _STOP_PC = 38 + _FP = 27, + __SP = 28, + _R30 = 30, + _BLINK = 31, + _LP_COUNT = 60, + _STOP_PC = 64, + _RET = 64, + _LP_START = 65, + _LP_END = 66, + _STATUS32 = 67, + _ECR = 76, + _BTA = 82, }; #else diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h index 66ee552..5faad17 100644 --- a/arch/arc/include/asm/linkage.h +++ b/arch/arc/include/asm/linkage.h @@ -13,20 +13,6 @@ #define ASM_NL ` /* use '`' to mark new line in macro */ -/* Can't use the ENTRY macro in linux/linkage.h - * gas considers ';' as comment vs. newline - */ -.macro ARC_ENTRY name - .global \name - .align 4 - \name: -.endm - -.macro ARC_EXIT name -#define ASM_PREV_SYM_ADDR(name) .-##name - .size \ name, ASM_PREV_SYM_ADDR(\name) -.endm - /* annotation for data we want in DCCM - if enabled in .config */ .macro ARCFP_DATA nm #ifdef CONFIG_ARC_HAS_DCCM diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 6b0b7f7e..7670f33 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -259,7 +259,8 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) #define pmd_clear(xp) do { pmd_val(*(xp)) = 0; } while (0) #define pte_page(x) (mem_map + \ - (unsigned long)(((pte_val(x) - PAGE_OFFSET) >> PAGE_SHIFT))) + (unsigned long)(((pte_val(x) - CONFIG_LINUX_LINK_BASE) >> \ + PAGE_SHIFT))) #define mk_pte(page, pgprot) \ ({ \ diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index 15334ab..fb95aa8 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -69,18 +69,19 @@ unsigned long thread_saved_pc(struct task_struct *t); #define release_segments(mm) do { } while (0) #define KSTK_EIP(tsk) (task_pt_regs(tsk)->ret) +#define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp) /* * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode. * Look in process.c for details of kernel stack layout */ -#define KSTK_ESP(tsk) (tsk->thread.ksp) +#define TSK_K_ESP(tsk) (tsk->thread.ksp) -#define KSTK_REG(tsk, off) (*((unsigned int *)(KSTK_ESP(tsk) + \ +#define TSK_K_REG(tsk, off) (*((unsigned int *)(TSK_K_ESP(tsk) + \ sizeof(struct callee_regs) + off))) -#define KSTK_BLINK(tsk) KSTK_REG(tsk, 4) -#define KSTK_FP(tsk) KSTK_REG(tsk, 0) +#define TSK_K_BLINK(tsk) TSK_K_REG(tsk, 4) +#define TSK_K_FP(tsk) TSK_K_REG(tsk, 0) /* * Do necessary setup to start up a newly executed thread. diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h index 1bfeec2..2a58af7 100644 --- a/arch/arc/include/asm/ptrace.h +++ b/arch/arc/include/asm/ptrace.h @@ -63,7 +63,7 @@ struct callee_regs { long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13; }; -#define instruction_pointer(regs) ((regs)->ret) +#define instruction_pointer(regs) (unsigned long)((regs)->ret) #define profile_pc(regs) instruction_pointer(regs) /* return 1 if user mode or 0 if kernel mode */ diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S index 65690e7..e248594 100644 --- a/arch/arc/kernel/ctx_sw_asm.S +++ b/arch/arc/kernel/ctx_sw_asm.S @@ -10,9 +10,9 @@ * -This is the more "natural" hand written assembler */ +#include #include /* For the SAVE_* macros */ #include -#include #define KSP_WORD_OFF ((TASK_THREAD + THREAD_KSP) / 4) @@ -62,4 +62,4 @@ __switch_to: ld.ab blink, [sp, 4] j [blink] -ARC_EXIT __switch_to +END(__switch_to) diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 6e8f83a..29b82ad 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -141,7 +141,7 @@ VECTOR EV_Extension ; 0x130, Extn Intruction Excp (0x26) VECTOR reserved ; Reserved Exceptions .endr -#include /* ARC_{EXTRY,EXIT} */ +#include /* {EXTRY,EXIT} */ #include /* SAVE_ALL_{INT1,INT2,SYS...} */ #include #include @@ -184,7 +184,7 @@ reserved: ; processor restart ; --------------------------------------------- ; Level 2 ISR: Can interrupt a Level 1 ISR ; --------------------------------------------- -ARC_ENTRY handle_interrupt_level2 +ENTRY(handle_interrupt_level2) ; TODO-vineetg for SMP this wont work ; free up r9 as scratchpad @@ -225,14 +225,14 @@ ARC_ENTRY handle_interrupt_level2 b ret_from_exception -ARC_EXIT handle_interrupt_level2 +END(handle_interrupt_level2) #endif ; --------------------------------------------- ; Level 1 ISR ; --------------------------------------------- -ARC_ENTRY handle_interrupt_level1 +ENTRY(handle_interrupt_level1) /* free up r9 as scratchpad */ #ifdef CONFIG_SMP @@ -265,7 +265,7 @@ ARC_ENTRY handle_interrupt_level1 sr r8, [AUX_IRQ_LV12] ; clear bit in Sticky Status Reg b ret_from_exception -ARC_EXIT handle_interrupt_level1 +END(handle_interrupt_level1) ;################### Non TLB Exception Handling ############################# @@ -273,7 +273,7 @@ ARC_EXIT handle_interrupt_level1 ; Instruction Error Exception Handler ; --------------------------------------------- -ARC_ENTRY instr_service +ENTRY(instr_service) EXCEPTION_PROLOGUE @@ -284,13 +284,13 @@ ARC_ENTRY instr_service bl do_insterror_or_kprobe b ret_from_exception -ARC_EXIT instr_service +END(instr_service) ; --------------------------------------------- ; Memory Error Exception Handler ; --------------------------------------------- -ARC_ENTRY mem_service +ENTRY(mem_service) EXCEPTION_PROLOGUE @@ -301,13 +301,13 @@ ARC_ENTRY mem_service bl do_memory_error b ret_from_exception -ARC_EXIT mem_service +END(mem_service) ; --------------------------------------------- ; Machine Check Exception Handler ; --------------------------------------------- -ARC_ENTRY EV_MachineCheck +ENTRY(EV_MachineCheck) EXCEPTION_PROLOGUE @@ -331,13 +331,13 @@ ARC_ENTRY EV_MachineCheck j do_machine_check_fault -ARC_EXIT EV_MachineCheck +END(EV_MachineCheck) ; --------------------------------------------- ; Protection Violation Exception Handler ; --------------------------------------------- -ARC_ENTRY EV_TLBProtV +ENTRY(EV_TLBProtV) EXCEPTION_PROLOGUE @@ -385,12 +385,12 @@ ARC_ENTRY EV_TLBProtV b ret_from_exception -ARC_EXIT EV_TLBProtV +END(EV_TLBProtV) ; --------------------------------------------- ; Privilege Violation Exception Handler ; --------------------------------------------- -ARC_ENTRY EV_PrivilegeV +ENTRY(EV_PrivilegeV) EXCEPTION_PROLOGUE @@ -401,12 +401,12 @@ ARC_ENTRY EV_PrivilegeV bl do_privilege_fault b ret_from_exception -ARC_EXIT EV_PrivilegeV +END(EV_PrivilegeV) ; --------------------------------------------- ; Extension Instruction Exception Handler ; --------------------------------------------- -ARC_ENTRY EV_Extension +ENTRY(EV_Extension) EXCEPTION_PROLOGUE @@ -417,7 +417,7 @@ ARC_ENTRY EV_Extension bl do_extension_fault b ret_from_exception -ARC_EXIT EV_Extension +END(EV_Extension) ;######################### System Call Tracing ######################### @@ -504,7 +504,7 @@ trap_with_param: ; (2) Break Points ;------------------------------------------------------------------ -ARC_ENTRY EV_Trap +ENTRY(EV_Trap) EXCEPTION_PROLOGUE @@ -534,9 +534,9 @@ ARC_ENTRY EV_Trap jl [r9] ; Entry into Sys Call Handler ; fall through to ret_from_system_call -ARC_EXIT EV_Trap +END(EV_Trap) -ARC_ENTRY ret_from_system_call +ENTRY(ret_from_system_call) st r0, [sp, PT_r0] ; sys call return value in pt_regs @@ -546,7 +546,7 @@ ARC_ENTRY ret_from_system_call ; ; If ret to user mode do we need to handle signals, schedule() et al. -ARC_ENTRY ret_from_exception +ENTRY(ret_from_exception) ; Pre-{IRQ,Trap,Exception} K/U mode from pt_regs->status32 ld r8, [sp, PT_status32] ; returning to User/Kernel Mode @@ -728,9 +728,9 @@ not_level1_interrupt: debug_marker_syscall: rtie -ARC_EXIT ret_from_exception +END(ret_from_exception) -ARC_ENTRY ret_from_fork +ENTRY(ret_from_fork) ; when the forked child comes here from the __switch_to function ; r0 has the last task pointer. ; put last task in scheduler queue @@ -747,11 +747,11 @@ ARC_ENTRY ret_from_fork ; special case of kernel_thread entry point returning back due to ; kernel_execve() - pretend return from syscall to ret to userland b ret_from_exception -ARC_EXIT ret_from_fork +END(ret_from_fork) ;################### Special Sys Call Wrappers ########################## -ARC_ENTRY sys_clone_wrapper +ENTRY(sys_clone_wrapper) SAVE_CALLEE_SAVED_USER bl @sys_clone DISCARD_CALLEE_SAVED_USER @@ -761,7 +761,7 @@ ARC_ENTRY sys_clone_wrapper bnz tracesys_exit b ret_from_system_call -ARC_EXIT sys_clone_wrapper +END(sys_clone_wrapper) #ifdef CONFIG_ARC_DW2_UNWIND ; Workaround for bug 94179 (STAR ): diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 9919972..07a58f2 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -12,10 +12,42 @@ * to skip certain things during boot on simulator */ +#include #include #include -#include #include +#include + +.macro CPU_EARLY_SETUP + + ; Setting up Vectror Table (in case exception happens in early boot + sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + + ; Disable I-cache/D-cache if kernel so configured + lr r5, [ARC_REG_IC_BCR] + breq r5, 0, 1f ; I$ doesn't exist + lr r5, [ARC_REG_IC_CTRL] +#ifdef CONFIG_ARC_HAS_ICACHE + bclr r5, r5, 0 ; 0 - Enable, 1 is Disable +#else + bset r5, r5, 0 ; I$ exists, but is not used +#endif + sr r5, [ARC_REG_IC_CTRL] + +1: + lr r5, [ARC_REG_DC_BCR] + breq r5, 0, 1f ; D$ doesn't exist + lr r5, [ARC_REG_DC_CTRL] + bclr r5, r5, 6 ; Invalidate (discard w/o wback) +#ifdef CONFIG_ARC_HAS_DCACHE + bclr r5, r5, 0 ; Enable (+Inv) +#else + bset r5, r5, 0 ; Disable (+Inv) +#endif + sr r5, [ARC_REG_DC_CTRL] + +1: +.endm .cpu A7 @@ -24,13 +56,13 @@ .globl stext stext: ;------------------------------------------------------------------- - ; Don't clobber r0-r4 yet. It might have bootloader provided info + ; Don't clobber r0-r2 yet. It might have bootloader provided info ;------------------------------------------------------------------- - sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + CPU_EARLY_SETUP #ifdef CONFIG_SMP - ; Only Boot (Master) proceeds. Others wait in platform dependent way + ; Ensure Boot (Master) proceeds. Others wait in platform dependent way ; IDENTITY Reg [ 3 2 1 0 ] ; (cpu-id) ^^^ => Zero for UP ARC700 ; => #Core-ID if SMP (Master 0) @@ -39,7 +71,8 @@ stext: ; need to make sure only boot cpu takes this path. GET_CPU_ID r5 cmp r5, 0 - jnz arc_platform_smp_wait_to_boot + mov.ne r0, r5 + jne arc_platform_smp_wait_to_boot #endif ; Clear BSS before updating any globals ; XXX: use ZOL here @@ -89,7 +122,7 @@ stext: first_lines_of_secondary: - sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + CPU_EARLY_SETUP ; setup per-cpu idle task as "current" on this CPU ld r0, [@secondary_idle_tsk] diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 7e95e1a..a0c63fc 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -67,7 +67,7 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, sigset_t *set) { int err; - err = __copy_to_user(&(sf->uc.uc_mcontext.regs), regs, + err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), regs, sizeof(sf->uc.uc_mcontext.regs.scratch)); err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t)); @@ -83,7 +83,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) if (!err) set_current_blocked(&set); - err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs), + err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs.scratch), sizeof(sf->uc.uc_mcontext.regs.scratch)); return err; @@ -131,6 +131,15 @@ SYSCALL_DEFINE0(rt_sigreturn) /* Don't restart from sigreturn */ syscall_wont_restart(regs); + /* + * Ensure that sigreturn always returns to user mode (in case the + * regs saved on user stack got fudged between save and sigreturn) + * Otherwise it is easy to panic the kernel with a custom + * signal handler and/or restorer which clobberes the status32/ret + * to return to a bogus location in kernel mode. + */ + regs->status32 |= STATUS_U_MASK; + return regs->r0; badframe: @@ -234,8 +243,11 @@ setup_rt_frame(int signo, struct k_sigaction *ka, siginfo_t *info, /* * handler returns using sigreturn stub provided already by userpsace + * If not, nuke the process right away */ - BUG_ON(!(ka->sa.sa_flags & SA_RESTORER)); + if(!(ka->sa.sa_flags & SA_RESTORER)) + return 1; + regs->blink = (unsigned long)ka->sa.sa_restorer; /* User Stack for signal handler will be above the frame just carved */ @@ -302,12 +314,12 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, struct pt_regs *regs) { sigset_t *oldset = sigmask_to_save(); - int ret; + int failed; /* Set up the stack frame */ - ret = setup_rt_frame(sig, ka, info, oldset, regs); + failed = setup_rt_frame(sig, ka, info, oldset, regs); - if (ret) + if (failed) force_sigsegv(sig, current); else signal_delivered(sig, info, ka, regs, 0); diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index 9ce47cf..fb98769 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -64,9 +64,9 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->task = tsk; - frame_info->regs.r27 = KSTK_FP(tsk); - frame_info->regs.r28 = KSTK_ESP(tsk); - frame_info->regs.r31 = KSTK_BLINK(tsk); + frame_info->regs.r27 = TSK_K_FP(tsk); + frame_info->regs.r28 = TSK_K_ESP(tsk); + frame_info->regs.r31 = TSK_K_BLINK(tsk); frame_info->regs.r63 = (unsigned int)__switch_to; /* In the prologue of __switch_to, first FP is saved on stack diff --git a/arch/arc/lib/memcmp.S b/arch/arc/lib/memcmp.S index bc813d5..978bf83 100644 --- a/arch/arc/lib/memcmp.S +++ b/arch/arc/lib/memcmp.S @@ -6,7 +6,7 @@ * published by the Free Software Foundation. */ -#include +#include #ifdef __LITTLE_ENDIAN__ #define WORD2 r2 @@ -16,7 +16,7 @@ #define SHIFT r2 #endif -ARC_ENTRY memcmp +ENTRY(memcmp) or r12,r0,r1 asl_s r12,r12,30 sub r3,r2,1 @@ -121,4 +121,4 @@ ARC_ENTRY memcmp .Lnil: j_s.d [blink] mov r0,0 -ARC_EXIT memcmp +END(memcmp) diff --git a/arch/arc/lib/memcpy-700.S b/arch/arc/lib/memcpy-700.S index b64cc10..3222573 100644 --- a/arch/arc/lib/memcpy-700.S +++ b/arch/arc/lib/memcpy-700.S @@ -6,9 +6,9 @@ * published by the Free Software Foundation. */ -#include +#include -ARC_ENTRY memcpy +ENTRY(memcpy) or r3,r0,r1 asl_s r3,r3,30 mov_s r5,r0 @@ -63,4 +63,4 @@ ARC_ENTRY memcpy .Lendbloop: j_s.d [blink] stb r12,[r5,0] -ARC_EXIT memcpy +END(memcpy) diff --git a/arch/arc/lib/memset.S b/arch/arc/lib/memset.S index 9b2d88d..d36bd43 100644 --- a/arch/arc/lib/memset.S +++ b/arch/arc/lib/memset.S @@ -6,11 +6,11 @@ * published by the Free Software Foundation. */ -#include +#include #define SMALL 7 /* Must be at least 6 to deal with alignment/loop issues. */ -ARC_ENTRY memset +ENTRY(memset) mov_s r4,r0 or r12,r0,r2 bmsk.f r12,r12,1 @@ -46,14 +46,14 @@ ARC_ENTRY memset stb.ab r1,[r4,1] .Ltiny_end: j_s [blink] -ARC_EXIT memset +END(memset) ; memzero: @r0 = mem, @r1 = size_t ; memset: @r0 = mem, @r1 = char, @r2 = size_t -ARC_ENTRY memzero +ENTRY(memzero) ; adjust bzero args to memset args mov r2, r1 mov r1, 0 b memset ;tail call so need to tinker with blink -ARC_EXIT memzero +END(memzero) diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S index 9c548c7..b725d58 100644 --- a/arch/arc/lib/strchr-700.S +++ b/arch/arc/lib/strchr-700.S @@ -11,9 +11,9 @@ presence of the norm instruction makes it easier to operate on whole words branch-free. */ -#include +#include -ARC_ENTRY strchr +ENTRY(strchr) extb_s r1,r1 asl r5,r1,8 bmsk r2,r0,1 @@ -130,4 +130,4 @@ ARC_ENTRY strchr j_s.d [blink] mov.mi r0,0 #endif /* ENDIAN */ -ARC_EXIT strchr +END(strchr) diff --git a/arch/arc/lib/strcmp.S b/arch/arc/lib/strcmp.S index 5dc802b..3544600 100644 --- a/arch/arc/lib/strcmp.S +++ b/arch/arc/lib/strcmp.S @@ -13,9 +13,9 @@ source 1; however, that would increase the overhead for loop setup / finish, and strcmp might often terminate early. */ -#include +#include -ARC_ENTRY strcmp +ENTRY(strcmp) or r2,r0,r1 bmsk_s r2,r2,1 brne r2,0,.Lcharloop @@ -93,4 +93,4 @@ ARC_ENTRY strcmp .Lcmpend: j_s.d [blink] sub r0,r2,r3 -ARC_EXIT strcmp +END(strcmp) diff --git a/arch/arc/lib/strcpy-700.S b/arch/arc/lib/strcpy-700.S index b7ca4ae..8422f38 100644 --- a/arch/arc/lib/strcpy-700.S +++ b/arch/arc/lib/strcpy-700.S @@ -16,9 +16,9 @@ there, but the it is not likely to be taken often, and it would also be likey to cost an unaligned mispredict at the next call. */ -#include +#include -ARC_ENTRY strcpy +ENTRY(strcpy) or r2,r0,r1 bmsk_s r2,r2,1 brne.d r2,0,charloop @@ -67,4 +67,4 @@ charloop: brne.d r3,0,charloop stb.ab r3,[r10,1] j [blink] -ARC_EXIT strcpy +END(strcpy) diff --git a/arch/arc/lib/strlen.S b/arch/arc/lib/strlen.S index 39759e0..53cfd56 100644 --- a/arch/arc/lib/strlen.S +++ b/arch/arc/lib/strlen.S @@ -6,9 +6,9 @@ * published by the Free Software Foundation. */ -#include +#include -ARC_ENTRY strlen +ENTRY(strlen) or r3,r0,7 ld r2,[r3,-7] ld.a r6,[r3,-3] @@ -80,4 +80,4 @@ ARC_ENTRY strlen .Learly_end: b.d .Lend sub_s.ne r1,r1,r1 -ARC_EXIT strlen +END(strlen) diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c index 400c663..1f676c4 100644 --- a/arch/arc/mm/cache_arc700.c +++ b/arch/arc/mm/cache_arc700.c @@ -73,37 +73,9 @@ #include #include -/* Instruction cache related Auxiliary registers */ -#define ARC_REG_IC_BCR 0x77 /* Build Config reg */ -#define ARC_REG_IC_IVIC 0x10 -#define ARC_REG_IC_CTRL 0x11 -#define ARC_REG_IC_IVIL 0x19 -#if (CONFIG_ARC_MMU_VER > 2) -#define ARC_REG_IC_PTAG 0x1E -#endif - -/* Bit val in IC_CTRL */ -#define IC_CTRL_CACHE_DISABLE 0x1 - -/* Data cache related Auxiliary registers */ -#define ARC_REG_DC_BCR 0x72 /* Build Config reg */ -#define ARC_REG_DC_IVDC 0x47 -#define ARC_REG_DC_CTRL 0x48 -#define ARC_REG_DC_IVDL 0x4A -#define ARC_REG_DC_FLSH 0x4B -#define ARC_REG_DC_FLDL 0x4C -#if (CONFIG_ARC_MMU_VER > 2) -#define ARC_REG_DC_PTAG 0x5C -#endif - -/* Bit val in DC_CTRL */ -#define DC_CTRL_INV_MODE_FLUSH 0x40 -#define DC_CTRL_FLUSH_STATUS 0x100 - -char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len) +char *arc_cache_mumbojumbo(int c, char *buf, int len) { int n = 0; - unsigned int c = smp_processor_id(); #define PR_CACHE(p, enb, str) \ { \ @@ -169,72 +141,43 @@ void read_decode_cache_bcr(void) */ void arc_cache_init(void) { - unsigned int cpu = smp_processor_id(); - struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; - struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache; - unsigned int dcache_does_alias, temp; + unsigned int __maybe_unused cpu = smp_processor_id(); + struct cpuinfo_arc_cache __maybe_unused *ic, __maybe_unused *dc; char str[256]; printk(arc_cache_mumbojumbo(0, str, sizeof(str))); - if (!ic->ver) - goto chk_dc; - -#ifdef CONFIG_ARC_HAS_ICACHE - /* 1. Confirm some of I-cache params which Linux assumes */ - if (ic->line_len != L1_CACHE_BYTES) - panic("Cache H/W doesn't match kernel Config"); - - if (ic->ver != CONFIG_ARC_MMU_VER) - panic("Cache ver doesn't match MMU ver\n"); -#endif - - /* Enable/disable I-Cache */ - temp = read_aux_reg(ARC_REG_IC_CTRL); - #ifdef CONFIG_ARC_HAS_ICACHE - temp &= ~IC_CTRL_CACHE_DISABLE; -#else - temp |= IC_CTRL_CACHE_DISABLE; + ic = &cpuinfo_arc700[cpu].icache; + if (ic->ver) { + if (ic->line_len != L1_CACHE_BYTES) + panic("ICache line [%d] != kernel Config [%d]", + ic->line_len, L1_CACHE_BYTES); + + if (ic->ver != CONFIG_ARC_MMU_VER) + panic("Cache ver [%d] doesn't match MMU ver [%d]\n", + ic->ver, CONFIG_ARC_MMU_VER); + } #endif - write_aux_reg(ARC_REG_IC_CTRL, temp); - -chk_dc: - if (!dc->ver) - return; - #ifdef CONFIG_ARC_HAS_DCACHE - if (dc->line_len != L1_CACHE_BYTES) - panic("Cache H/W doesn't match kernel Config"); + dc = &cpuinfo_arc700[cpu].dcache; + if (dc->ver) { + unsigned int dcache_does_alias; - /* check for D-Cache aliasing */ - dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE; + if (dc->line_len != L1_CACHE_BYTES) + panic("DCache line [%d] != kernel Config [%d]", + dc->line_len, L1_CACHE_BYTES); - if (dcache_does_alias && !cache_is_vipt_aliasing()) - panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); - else if (!dcache_does_alias && cache_is_vipt_aliasing()) - panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n"); -#endif - - /* Set the default Invalidate Mode to "simpy discard dirty lines" - * as this is more frequent then flush before invalidate - * Ofcourse we toggle this default behviour when desired - */ - temp = read_aux_reg(ARC_REG_DC_CTRL); - temp &= ~DC_CTRL_INV_MODE_FLUSH; + /* check for D-Cache aliasing */ + dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE; -#ifdef CONFIG_ARC_HAS_DCACHE - /* Enable D-Cache: Clear Bit 0 */ - write_aux_reg(ARC_REG_DC_CTRL, temp & ~IC_CTRL_CACHE_DISABLE); -#else - /* Flush D cache */ - write_aux_reg(ARC_REG_DC_FLSH, 0x1); - /* Disable D cache */ - write_aux_reg(ARC_REG_DC_CTRL, temp | IC_CTRL_CACHE_DISABLE); + if (dcache_does_alias && !cache_is_vipt_aliasing()) + panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + else if (!dcache_does_alias && cache_is_vipt_aliasing()) + panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + } #endif - - return; } #define OP_INV 0x1 @@ -254,12 +197,16 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr, if (cacheop == OP_INV_IC) { aux_cmd = ARC_REG_IC_IVIL; +#if (CONFIG_ARC_MMU_VER > 2) aux_tag = ARC_REG_IC_PTAG; +#endif } else { /* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */ aux_cmd = cacheop & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL; +#if (CONFIG_ARC_MMU_VER > 2) aux_tag = ARC_REG_DC_PTAG; +#endif } /* Ensure we properly floor/ceil the non-line aligned/sized requests diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 9c69552..01e18b5 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -162,6 +162,8 @@ good_area: /* TBD: switch to pagefault_out_of_memory() */ if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S index 3fcfdb3..79bfc81 100644 --- a/arch/arc/mm/tlbex.S +++ b/arch/arc/mm/tlbex.S @@ -260,7 +260,7 @@ ARCFP_CODE ;Fast Path Code, candidate for ICCM ; I-TLB Miss Exception Handler ;----------------------------------------------------------------------------- -ARC_ENTRY EV_TLBMissI +ENTRY(EV_TLBMissI) TLBMISS_FREEUP_REGS @@ -293,13 +293,13 @@ ARC_ENTRY EV_TLBMissI TLBMISS_RESTORE_REGS rtie -ARC_EXIT EV_TLBMissI +END(EV_TLBMissI) ;----------------------------------------------------------------------------- ; D-TLB Miss Exception Handler ;----------------------------------------------------------------------------- -ARC_ENTRY EV_TLBMissD +ENTRY(EV_TLBMissD) TLBMISS_FREEUP_REGS @@ -381,6 +381,4 @@ do_slow_path_pf: bl do_page_fault b ret_from_exception -ARC_EXIT EV_TLBMissD - -ARC_ENTRY EV_TLBMissB ; Bogus entry to measure sz of DTLBMiss hdlr +END(EV_TLBMissD) diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 066b034..8017cde 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -400,8 +400,7 @@ dtb_check_done: add sp, sp, r6 #endif - tst r4, #1 - bleq cache_clean_flush + bl cache_clean_flush adr r0, BSYM(restart) add r0, r0, r6 @@ -1050,6 +1049,8 @@ cache_clean_flush: b call_cache_fn __armv4_mpu_cache_flush: + tst r4, #1 + movne pc, lr mov r2, #1 mov r3, #0 mcr p15, 0, ip, c7, c6, 0 @ invalidate D cache @@ -1067,6 +1068,8 @@ __armv4_mpu_cache_flush: mov pc, lr __fa526_cache_flush: + tst r4, #1 + movne pc, lr mov r1, #0 mcr p15, 0, r1, c7, c14, 0 @ clean and invalidate D cache mcr p15, 0, r1, c7, c5, 0 @ flush I cache @@ -1075,13 +1078,16 @@ __fa526_cache_flush: __armv6_mmu_cache_flush: mov r1, #0 - mcr p15, 0, r1, c7, c14, 0 @ clean+invalidate D + tst r4, #1 + mcreq p15, 0, r1, c7, c14, 0 @ clean+invalidate D mcr p15, 0, r1, c7, c5, 0 @ invalidate I+BTB - mcr p15, 0, r1, c7, c15, 0 @ clean+invalidate unified + mcreq p15, 0, r1, c7, c15, 0 @ clean+invalidate unified mcr p15, 0, r1, c7, c10, 4 @ drain WB mov pc, lr __armv7_mmu_cache_flush: + tst r4, #1 + bne iflush mrc p15, 0, r10, c0, c1, 5 @ read ID_MMFR1 tst r10, #0xf << 16 @ hierarchical cache (ARMv7) mov r10, #0 @@ -1142,6 +1148,8 @@ iflush: mov pc, lr __armv5tej_mmu_cache_flush: + tst r4, #1 + movne pc, lr 1: mrc p15, 0, r15, c7, c14, 3 @ test,clean,invalidate D cache bne 1b mcr p15, 0, r0, c7, c5, 0 @ flush I cache @@ -1149,6 +1157,8 @@ __armv5tej_mmu_cache_flush: mov pc, lr __armv4_mmu_cache_flush: + tst r4, #1 + movne pc, lr mov r2, #64*1024 @ default: 32K dcache size (*2) mov r11, #32 @ default: 32 byte line size mrc p15, 0, r3, c0, c0, 1 @ read cache type @@ -1182,6 +1192,8 @@ no_cache_id: __armv3_mmu_cache_flush: __armv3_mpu_cache_flush: + tst r4, #1 + movne pc, lr mov r1, #0 mcr p15, 0, r1, c7, c0, 0 @ invalidate whole cache v3 mov pc, lr diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi index 2e7d932..b3eff40 100644 --- a/arch/arm/boot/dts/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/am335x-bone-common.dtsi @@ -197,6 +197,7 @@ usb@47401000 { status = "okay"; + dr_mode = "peripheral"; }; usb@47401800 { diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index c6bd4d9..8775681 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -161,9 +161,6 @@ ti,hwmods = "mailbox"; ti,mbox-num-users = <4>; ti,mbox-num-fifos = <8>; - ti,mbox-names = "wkup_m3"; - ti,mbox-data = <0 0 0 0>; - status = "disabled"; }; timer1: timer@44e31000 { diff --git a/arch/arm/boot/dts/armada-370-netgear-rn102.dts b/arch/arm/boot/dts/armada-370-netgear-rn102.dts index 651aeb5..f3188e9 100644 --- a/arch/arm/boot/dts/armada-370-netgear-rn102.dts +++ b/arch/arm/boot/dts/armada-370-netgear-rn102.dts @@ -144,6 +144,10 @@ marvell,nand-enable-arbiter; nand-on-flash-bbt; + /* Use Hardware BCH ECC */ + nand-ecc-strength = <4>; + nand-ecc-step-size = <512>; + partition@0 { label = "u-boot"; reg = <0x0000000 0x180000>; /* 1.5MB */ diff --git a/arch/arm/boot/dts/armada-370-netgear-rn104.dts b/arch/arm/boot/dts/armada-370-netgear-rn104.dts index 4e27587..da406c1 100644 --- a/arch/arm/boot/dts/armada-370-netgear-rn104.dts +++ b/arch/arm/boot/dts/armada-370-netgear-rn104.dts @@ -146,6 +146,10 @@ marvell,nand-enable-arbiter; nand-on-flash-bbt; + /* Use Hardware BCH ECC */ + nand-ecc-strength = <4>; + nand-ecc-step-size = <512>; + partition@0 { label = "u-boot"; reg = <0x0000000 0x180000>; /* 1.5MB */ diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi index 0d8530c..34841fc 100644 --- a/arch/arm/boot/dts/armada-370.dtsi +++ b/arch/arm/boot/dts/armada-370.dtsi @@ -106,11 +106,6 @@ reg = <0x11100 0x20>; }; - system-controller@18200 { - compatible = "marvell,armada-370-xp-system-controller"; - reg = <0x18200 0x100>; - }; - pinctrl { compatible = "marvell,mv88f6710-pinctrl"; reg = <0x18000 0x38>; @@ -167,6 +162,11 @@ interrupts = <91>; }; + system-controller@18200 { + compatible = "marvell,armada-370-xp-system-controller"; + reg = <0x18200 0x100>; + }; + gateclk: clock-gating-control@18220 { compatible = "marvell,armada-370-gating-clock"; reg = <0x18220 0x4>; diff --git a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts index ff049ee..b4aba09 100644 --- a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts +++ b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts @@ -224,6 +224,10 @@ marvell,nand-enable-arbiter; nand-on-flash-bbt; + /* Use Hardware BCH ECC */ + nand-ecc-strength = <4>; + nand-ecc-step-size = <512>; + partition@0 { label = "u-boot"; reg = <0x0000000 0x180000>; /* 1.5MB */ diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts index 1c6bd83..2ade357 100644 --- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts +++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts @@ -69,6 +69,10 @@ }; internal-regs { + rtc@10300 { + /* No crystal connected to the internal RTC */ + status = "disabled"; + }; serial@12000 { clock-frequency = <250000000>; status = "okay"; diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi index fece866..b8f234b 100644 --- a/arch/arm/boot/dts/at91sam9263.dtsi +++ b/arch/arm/boot/dts/at91sam9263.dtsi @@ -535,6 +535,7 @@ compatible = "atmel,hsmci"; reg = <0xfff80000 0x600>; interrupts = <10 IRQ_TYPE_LEVEL_HIGH 0>; + pinctrl-names = "default"; #address-cells = <1>; #size-cells = <0>; status = "disabled"; @@ -544,6 +545,7 @@ compatible = "atmel,hsmci"; reg = <0xfff84000 0x600>; interrupts = <11 IRQ_TYPE_LEVEL_HIGH 0>; + pinctrl-names = "default"; #address-cells = <1>; #size-cells = <0>; status = "disabled"; diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi index 187fd46..355117c 100644 --- a/arch/arm/boot/dts/dove.dtsi +++ b/arch/arm/boot/dts/dove.dtsi @@ -154,7 +154,7 @@ uart2: serial@12200 { compatible = "ns16550a"; - reg = <0x12000 0x100>; + reg = <0x12200 0x100>; reg-shift = <2>; interrupts = <9>; clocks = <&core_clk 0>; @@ -163,7 +163,7 @@ uart3: serial@12300 { compatible = "ns16550a"; - reg = <0x12100 0x100>; + reg = <0x12300 0x100>; reg-shift = <2>; interrupts = <10>; clocks = <&core_clk 0>; diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts index 5babba0..9381754 100644 --- a/arch/arm/boot/dts/dra7-evm.dts +++ b/arch/arm/boot/dts/dra7-evm.dts @@ -50,13 +50,13 @@ mcspi1_pins: pinmux_mcspi1_pins { pinctrl-single,pins = < - 0x3a4 (PIN_INPUT | MUX_MODE0) /* spi2_clk */ - 0x3a8 (PIN_INPUT | MUX_MODE0) /* spi2_d1 */ - 0x3ac (PIN_INPUT | MUX_MODE0) /* spi2_d0 */ - 0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs0 */ - 0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs1 */ - 0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs2 */ - 0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs3 */ + 0x3a4 (PIN_INPUT | MUX_MODE0) /* spi1_sclk */ + 0x3a8 (PIN_INPUT | MUX_MODE0) /* spi1_d1 */ + 0x3ac (PIN_INPUT | MUX_MODE0) /* spi1_d0 */ + 0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs0 */ + 0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs1 */ + 0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs2.hdmi1_hpd */ + 0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs3.hdmi1_cec */ >; }; @@ -182,6 +182,7 @@ regulator-name = "ldo3"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-always-on; regulator-boot-on; }; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 1fd75aa..f60aeee 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -178,7 +178,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio2: gpio@48055000 { @@ -189,7 +189,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio3: gpio@48057000 { @@ -200,7 +200,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio4: gpio@48059000 { @@ -211,7 +211,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio5: gpio@4805b000 { @@ -222,7 +222,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio6: gpio@4805d000 { @@ -233,7 +233,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio7: gpio@48051000 { @@ -244,7 +244,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio8: gpio@48053000 { @@ -255,7 +255,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; uart1: serial@4806a000 { @@ -458,7 +458,7 @@ }; wdt2: wdt@4ae14000 { - compatible = "ti,omap4-wdt"; + compatible = "ti,omap3-wdt"; reg = <0x4ae14000 0x80>; interrupts = ; ti,hwmods = "wd_timer2"; diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi index e96da9a..f2512e1 100644 --- a/arch/arm/boot/dts/dra7xx-clocks.dtsi +++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi @@ -243,10 +243,18 @@ ti,invert-autoidle-bit; }; + dpll_core_byp_mux: dpll_core_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x012c>; + }; + dpll_core_ck: dpll_core_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-core-clock"; - clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin1>, <&dpll_core_byp_mux>; reg = <0x0120>, <0x0124>, <0x012c>, <0x0128>; }; @@ -309,10 +317,18 @@ clock-div = <1>; }; + dpll_dsp_byp_mux: dpll_dsp_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dsp_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x0240>; + }; + dpll_dsp_ck: dpll_dsp_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&dsp_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_dsp_byp_mux>; reg = <0x0234>, <0x0238>, <0x0240>, <0x023c>; }; @@ -335,10 +351,18 @@ clock-div = <1>; }; + dpll_iva_byp_mux: dpll_iva_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&iva_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x01ac>; + }; + dpll_iva_ck: dpll_iva_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&iva_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_iva_byp_mux>; reg = <0x01a0>, <0x01a4>, <0x01ac>, <0x01a8>; }; @@ -361,10 +385,18 @@ clock-div = <1>; }; + dpll_gpu_byp_mux: dpll_gpu_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x02e4>; + }; + dpll_gpu_ck: dpll_gpu_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin1>, <&dpll_gpu_byp_mux>; reg = <0x02d8>, <0x02dc>, <0x02e4>, <0x02e0>; }; @@ -398,10 +430,18 @@ clock-div = <1>; }; + dpll_ddr_byp_mux: dpll_ddr_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x021c>; + }; + dpll_ddr_ck: dpll_ddr_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin1>, <&dpll_ddr_byp_mux>; reg = <0x0210>, <0x0214>, <0x021c>, <0x0218>; }; @@ -416,10 +456,18 @@ ti,invert-autoidle-bit; }; + dpll_gmac_byp_mux: dpll_gmac_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x02b4>; + }; + dpll_gmac_ck: dpll_gmac_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin1>, <&dpll_gmac_byp_mux>; reg = <0x02a8>, <0x02ac>, <0x02b4>, <0x02b0>; }; @@ -482,10 +530,18 @@ clock-div = <1>; }; + dpll_eve_byp_mux: dpll_eve_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&eve_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x0290>; + }; + dpll_eve_ck: dpll_eve_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&eve_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_eve_byp_mux>; reg = <0x0284>, <0x0288>, <0x0290>, <0x028c>; }; @@ -1214,10 +1270,18 @@ clock-div = <1>; }; + dpll_per_byp_mux: dpll_per_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&per_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x014c>; + }; + dpll_per_ck: dpll_per_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&per_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_per_byp_mux>; reg = <0x0140>, <0x0144>, <0x014c>, <0x0148>; }; @@ -1240,10 +1304,18 @@ clock-div = <1>; }; + dpll_usb_byp_mux: dpll_usb_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&usb_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x018c>; + }; + dpll_usb_ck: dpll_usb_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-j-type-clock"; - clocks = <&sys_clkin1>, <&usb_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_usb_byp_mux>; reg = <0x0180>, <0x0184>, <0x018c>, <0x0188>; }; diff --git a/arch/arm/boot/dts/hi3620.dtsi b/arch/arm/boot/dts/hi3620.dtsi index ab1116d..83a5b86 100644 --- a/arch/arm/boot/dts/hi3620.dtsi +++ b/arch/arm/boot/dts/hi3620.dtsi @@ -73,7 +73,7 @@ L2: l2-cache { compatible = "arm,pl310-cache"; - reg = <0xfc10000 0x100000>; + reg = <0x100000 0x100000>; interrupts = <0 15 4>; cache-unified; cache-level = <2>; diff --git a/arch/arm/boot/dts/imx23-olinuxino.dts b/arch/arm/boot/dts/imx23-olinuxino.dts index 526bfdb..f8922fb 100644 --- a/arch/arm/boot/dts/imx23-olinuxino.dts +++ b/arch/arm/boot/dts/imx23-olinuxino.dts @@ -12,6 +12,7 @@ */ /dts-v1/; +#include #include "imx23.dtsi" / { @@ -93,6 +94,7 @@ ahb@80080000 { usb0: usb@80080000 { + dr_mode = "host"; vbus-supply = <®_usb0_vbus>; status = "okay"; }; @@ -119,7 +121,7 @@ user { label = "green"; - gpios = <&gpio2 1 1>; + gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>; }; }; }; diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi index 904416e..3fd539b 100644 --- a/arch/arm/boot/dts/imx25.dtsi +++ b/arch/arm/boot/dts/imx25.dtsi @@ -160,7 +160,7 @@ #size-cells = <0>; compatible = "fsl,imx25-cspi", "fsl,imx35-cspi"; reg = <0x43fa4000 0x4000>; - clocks = <&clks 62>, <&clks 62>; + clocks = <&clks 78>, <&clks 78>; clock-names = "ipg", "per"; interrupts = <14>; status = "disabled"; @@ -354,7 +354,7 @@ compatible = "fsl,imx25-pwm", "fsl,imx27-pwm"; #pwm-cells = <2>; reg = <0x53fa0000 0x4000>; - clocks = <&clks 106>, <&clks 36>; + clocks = <&clks 106>, <&clks 52>; clock-names = "ipg", "per"; interrupts = <36>; }; @@ -373,7 +373,7 @@ compatible = "fsl,imx25-pwm", "fsl,imx27-pwm"; #pwm-cells = <2>; reg = <0x53fa8000 0x4000>; - clocks = <&clks 107>, <&clks 36>; + clocks = <&clks 107>, <&clks 52>; clock-names = "ipg", "per"; interrupts = <41>; }; @@ -413,8 +413,9 @@ pwm4: pwm@53fc8000 { compatible = "fsl,imx25-pwm", "fsl,imx27-pwm"; + #pwm-cells = <2>; reg = <0x53fc8000 0x4000>; - clocks = <&clks 108>, <&clks 36>; + clocks = <&clks 108>, <&clks 52>; clock-names = "ipg", "per"; interrupts = <42>; }; @@ -460,7 +461,7 @@ compatible = "fsl,imx25-pwm", "fsl,imx27-pwm"; #pwm-cells = <2>; reg = <0x53fe0000 0x4000>; - clocks = <&clks 105>, <&clks 36>; + clocks = <&clks 105>, <&clks 52>; clock-names = "ipg", "per"; interrupts = <26>; }; diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi index 3f1f2c8..78be5c2 100644 --- a/arch/arm/boot/dts/imx27.dtsi +++ b/arch/arm/boot/dts/imx27.dtsi @@ -430,7 +430,7 @@ fec: ethernet@1002b000 { compatible = "fsl,imx27-fec"; - reg = <0x1002b000 0x4000>; + reg = <0x1002b000 0x1000>; interrupts = <50>; clocks = <&clks 48>, <&clks 67>; clock-names = "ipg", "ahb"; diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi index f34d469..6f776ab 100644 --- a/arch/arm/boot/dts/imx28.dtsi +++ b/arch/arm/boot/dts/imx28.dtsi @@ -803,7 +803,7 @@ 80 81 68 69 70 71 72 73 74 75 76 77>; - interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty", + interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty", "saif0", "saif1", "i2c0", "i2c1", "auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx", "auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx"; diff --git a/arch/arm/boot/dts/s3c6410-mini6410.dts b/arch/arm/boot/dts/s3c6410-mini6410.dts index 57e00f9..a25debb 100644 --- a/arch/arm/boot/dts/s3c6410-mini6410.dts +++ b/arch/arm/boot/dts/s3c6410-mini6410.dts @@ -198,10 +198,6 @@ status = "okay"; }; -&pwm { - status = "okay"; -}; - &pinctrl0 { gpio_leds: gpio-leds { samsung,pins = "gpk-4", "gpk-5", "gpk-6", "gpk-7"; diff --git a/arch/arm/boot/dts/s3c64xx.dtsi b/arch/arm/boot/dts/s3c64xx.dtsi index 4e3be4d..4f1eff3 100644 --- a/arch/arm/boot/dts/s3c64xx.dtsi +++ b/arch/arm/boot/dts/s3c64xx.dtsi @@ -168,7 +168,6 @@ clocks = <&clocks PCLK_PWM>; samsung,pwm-outputs = <0>, <1>; #pwm-cells = <3>; - status = "disabled"; }; pinctrl0: pinctrl@7f008000 { diff --git a/arch/arm/boot/dts/sama5d3_can.dtsi b/arch/arm/boot/dts/sama5d3_can.dtsi index a077585..eaf4145 100644 --- a/arch/arm/boot/dts/sama5d3_can.dtsi +++ b/arch/arm/boot/dts/sama5d3_can.dtsi @@ -40,7 +40,7 @@ atmel,clk-output-range = <0 66000000>; }; - can1_clk: can0_clk { + can1_clk: can1_clk { #clock-cells = <0>; reg = <41>; atmel,clk-output-range = <0 66000000>; diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi index e0853ea..75e748e 100644 --- a/arch/arm/boot/dts/ste-dbx5x0.dtsi +++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi @@ -985,23 +985,6 @@ status = "disabled"; }; - vmmci: regulator-gpio { - compatible = "regulator-gpio"; - - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <2900000>; - regulator-name = "mmci-reg"; - regulator-type = "voltage"; - - startup-delay-us = <100>; - enable-active-high; - - states = <1800000 0x1 - 2900000 0x0>; - - status = "disabled"; - }; - mcde@a0350000 { compatible = "stericsson,mcde"; reg = <0xa0350000 0x1000>, /* MCDE */ diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi index 6cb9b68..0b668f8 100644 --- a/arch/arm/boot/dts/ste-href.dtsi +++ b/arch/arm/boot/dts/ste-href.dtsi @@ -111,6 +111,21 @@ pinctrl-1 = <&i2c3_sleep_mode>; }; + vmmci: regulator-gpio { + compatible = "regulator-gpio"; + + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2900000>; + regulator-name = "mmci-reg"; + regulator-type = "voltage"; + + startup-delay-us = <100>; + enable-active-high; + + states = <1800000 0x1 + 2900000 0x0>; + }; + // External Micro SD slot sdi0_per1@80126000 { arm,primecell-periphid = <0x10480180>; diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts index 97d5d21..5deaf3c 100644 --- a/arch/arm/boot/dts/ste-snowball.dts +++ b/arch/arm/boot/dts/ste-snowball.dts @@ -146,8 +146,21 @@ }; vmmci: regulator-gpio { + compatible = "regulator-gpio"; + gpios = <&gpio7 4 0x4>; enable-gpio = <&gpio6 25 0x4>; + + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2900000>; + regulator-name = "mmci-reg"; + regulator-type = "voltage"; + + startup-delay-us = <100>; + enable-active-high; + + states = <1800000 0x1 + 2900000 0x0>; }; // External Micro SD slot diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi index 48d2a7f..ce978bc 100644 --- a/arch/arm/boot/dts/tegra20.dtsi +++ b/arch/arm/boot/dts/tegra20.dtsi @@ -76,9 +76,9 @@ reset-names = "2d"; }; - gr3d@54140000 { + gr3d@54180000 { compatible = "nvidia,tegra20-gr3d"; - reg = <0x54140000 0x00040000>; + reg = <0x54180000 0x00040000>; clocks = <&tegra_car TEGRA20_CLK_GR3D>; resets = <&tegra_car 24>; reset-names = "3d"; @@ -138,9 +138,9 @@ status = "disabled"; }; - dsi@542c0000 { + dsi@54300000 { compatible = "nvidia,tegra20-dsi"; - reg = <0x542c0000 0x00040000>; + reg = <0x54300000 0x00040000>; clocks = <&tegra_car TEGRA20_CLK_DSI>; resets = <&tegra_car 48>; reset-names = "dsi"; diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index ee69829..cf4823b 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -235,6 +235,7 @@ CONFIG_SND_SOC_TEGRA_MAX98090=y CONFIG_USB=y CONFIG_USB_XHCI_HCD=y CONFIG_USB_EHCI_HCD=y +CONFIG_USB_EHCI_EXYNOS=y CONFIG_USB_EHCI_TEGRA=y CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_ISP1760_HCD=y diff --git a/arch/arm/crypto/aes_glue.c b/arch/arm/crypto/aes_glue.c index 3003fa1..0409b8f 100644 --- a/arch/arm/crypto/aes_glue.c +++ b/arch/arm/crypto/aes_glue.c @@ -93,6 +93,6 @@ module_exit(aes_fini); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm (ASM)"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("aes"); -MODULE_ALIAS("aes-asm"); +MODULE_ALIAS_CRYPTO("aes"); +MODULE_ALIAS_CRYPTO("aes-asm"); MODULE_AUTHOR("David McCullough "); diff --git a/arch/arm/crypto/aesbs-core.S_shipped b/arch/arm/crypto/aesbs-core.S_shipped index 71e5fc7..1d1800f 100644 --- a/arch/arm/crypto/aesbs-core.S_shipped +++ b/arch/arm/crypto/aesbs-core.S_shipped @@ -58,14 +58,18 @@ # define VFP_ABI_FRAME 0 # define BSAES_ASM_EXTENDED_KEY # define XTS_CHAIN_TWEAK -# define __ARM_ARCH__ 7 +# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +# define __ARM_MAX_ARCH__ 7 #endif #ifdef __thumb__ # define adrl adr #endif -#if __ARM_ARCH__>=7 +#if __ARM_MAX_ARCH__>=7 +.arch armv7-a +.fpu neon + .text .syntax unified @ ARMv7-capable assembler is expected to handle this #ifdef __thumb2__ @@ -74,8 +78,6 @@ .code 32 #endif -.fpu neon - .type _bsaes_decrypt8,%function .align 4 _bsaes_decrypt8: @@ -2095,9 +2097,11 @@ bsaes_xts_decrypt: vld1.8 {q8}, [r0] @ initial tweak adr r2, .Lxts_magic +#ifndef XTS_CHAIN_TWEAK tst r9, #0xf @ if not multiple of 16 it ne @ Thumb2 thing, sanity check in ARM subne r9, #0x10 @ subtract another 16 bytes +#endif subs r9, #0x80 blo .Lxts_dec_short diff --git a/arch/arm/crypto/aesbs-glue.c b/arch/arm/crypto/aesbs-glue.c index 4522366..15468fb 100644 --- a/arch/arm/crypto/aesbs-glue.c +++ b/arch/arm/crypto/aesbs-glue.c @@ -137,7 +137,7 @@ static int aesbs_cbc_encrypt(struct blkcipher_desc *desc, dst += AES_BLOCK_SIZE; } while (--blocks); } - err = blkcipher_walk_done(desc, &walk, 0); + err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } return err; } @@ -158,7 +158,7 @@ static int aesbs_cbc_decrypt(struct blkcipher_desc *desc, bsaes_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr, walk.nbytes, &ctx->dec, walk.iv); kernel_neon_end(); - err = blkcipher_walk_done(desc, &walk, 0); + err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } while (walk.nbytes) { u32 blocks = walk.nbytes / AES_BLOCK_SIZE; @@ -182,7 +182,7 @@ static int aesbs_cbc_decrypt(struct blkcipher_desc *desc, dst += AES_BLOCK_SIZE; src += AES_BLOCK_SIZE; } while (--blocks); - err = blkcipher_walk_done(desc, &walk, 0); + err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } return err; } @@ -268,7 +268,7 @@ static int aesbs_xts_encrypt(struct blkcipher_desc *desc, bsaes_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr, walk.nbytes, &ctx->enc, walk.iv); kernel_neon_end(); - err = blkcipher_walk_done(desc, &walk, 0); + err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } return err; } @@ -292,7 +292,7 @@ static int aesbs_xts_decrypt(struct blkcipher_desc *desc, bsaes_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr, walk.nbytes, &ctx->dec, walk.iv); kernel_neon_end(); - err = blkcipher_walk_done(desc, &walk, 0); + err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } return err; } diff --git a/arch/arm/crypto/bsaes-armv7.pl b/arch/arm/crypto/bsaes-armv7.pl index be068db..a4d3856 100644 --- a/arch/arm/crypto/bsaes-armv7.pl +++ b/arch/arm/crypto/bsaes-armv7.pl @@ -701,14 +701,18 @@ $code.=<<___; # define VFP_ABI_FRAME 0 # define BSAES_ASM_EXTENDED_KEY # define XTS_CHAIN_TWEAK -# define __ARM_ARCH__ 7 +# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +# define __ARM_MAX_ARCH__ 7 #endif #ifdef __thumb__ # define adrl adr #endif -#if __ARM_ARCH__>=7 +#if __ARM_MAX_ARCH__>=7 +.arch armv7-a +.fpu neon + .text .syntax unified @ ARMv7-capable assembler is expected to handle this #ifdef __thumb2__ @@ -717,8 +721,6 @@ $code.=<<___; .code 32 #endif -.fpu neon - .type _bsaes_decrypt8,%function .align 4 _bsaes_decrypt8: @@ -2076,9 +2078,11 @@ bsaes_xts_decrypt: vld1.8 {@XMM[8]}, [r0] @ initial tweak adr $magic, .Lxts_magic +#ifndef XTS_CHAIN_TWEAK tst $len, #0xf @ if not multiple of 16 it ne @ Thumb2 thing, sanity check in ARM subne $len, #0x10 @ subtract another 16 bytes +#endif subs $len, #0x80 blo .Lxts_dec_short diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c index 76cd976..ace4cd6 100644 --- a/arch/arm/crypto/sha1_glue.c +++ b/arch/arm/crypto/sha1_glue.c @@ -175,5 +175,5 @@ module_exit(sha1_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm (ARM)"); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); MODULE_AUTHOR("David McCullough "); diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h index f4b46d3..051b726 100644 --- a/arch/arm/include/asm/elf.h +++ b/arch/arm/include/asm/elf.h @@ -114,7 +114,7 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs); the loader. We need to make sure that it is out of the way of the program that it will "exec", and that there is sufficient room for the brk. */ -#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3) +#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2) /* When the program starts, a1 contains a pointer to a function to be registered with atexit, as per the SVR4 ABI. A value of 0 means we diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index 1d3153c..816db0b 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -55,6 +55,7 @@ * The bits we set in HCR: * TAC: Trap ACTLR * TSC: Trap SMC + * TVM: Trap VM ops (until MMU and caches are on) * TSW: Trap cache operations by set/way * TWI: Trap WFI * TWE: Trap WFE @@ -68,8 +69,7 @@ */ #define HCR_GUEST_MASK (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \ HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \ - HCR_TWE | HCR_SWIO | HCR_TIDCP) -#define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF) + HCR_TVM | HCR_TWE | HCR_SWIO | HCR_TIDCP) /* System Control Register (SCTLR) bits */ #define SCTLR_TE (1 << 30) diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h index 661da11..53b3c4a 100644 --- a/arch/arm/include/asm/kvm_asm.h +++ b/arch/arm/include/asm/kvm_asm.h @@ -48,7 +48,9 @@ #define c13_TID_URO 26 /* Thread ID, User R/O */ #define c13_TID_PRIV 27 /* Thread ID, Privileged */ #define c14_CNTKCTL 28 /* Timer Control Register (PL1) */ -#define NR_CP15_REGS 29 /* Number of regs (incl. invalid) */ +#define c10_AMAIR0 29 /* Auxilary Memory Attribute Indirection Reg0 */ +#define c10_AMAIR1 30 /* Auxilary Memory Attribute Indirection Reg1 */ +#define NR_CP15_REGS 31 /* Number of regs (incl. invalid) */ #define ARM_EXCEPTION_RESET 0 #define ARM_EXCEPTION_UNDEFINED 1 diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 0fa90c9..853e2be 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -33,6 +33,11 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) +{ + vcpu->arch.hcr = HCR_GUEST_MASK; +} + static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu) { return 1; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 098f7dd..530f56e 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -42,7 +42,7 @@ struct kvm_vcpu; u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode); -int kvm_target_cpu(void); +int __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); void kvm_reset_coprocs(struct kvm_vcpu *vcpu); @@ -101,6 +101,12 @@ struct kvm_vcpu_arch { /* The CPU type we expose to the VM */ u32 midr; + /* HYP trapping configuration */ + u32 hcr; + + /* Interrupt related fields */ + u32 irq_lines; /* IRQ and FIQ levels */ + /* Exception Information */ struct kvm_vcpu_fault_info fault; @@ -128,9 +134,6 @@ struct kvm_vcpu_arch { /* IO related fields */ struct kvm_decode mmio_decode; - /* Interrupt related fields */ - u32 irq_lines; /* IRQ and FIQ levels */ - /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 2d122ad..7d35af3 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -47,6 +47,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t); void free_boot_hyp_pgd(void); void free_hyp_pgds(void); +void stage2_unmap_vm(struct kvm *kvm); int kvm_alloc_stage2_pgd(struct kvm *kvm); void kvm_free_stage2_pgd(struct kvm *kvm); int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, @@ -78,17 +79,6 @@ static inline void kvm_set_pte(pte_t *pte, pte_t new_pte) flush_pmd_entry(pte); } -static inline bool kvm_is_write_fault(unsigned long hsr) -{ - unsigned long hsr_ec = hsr >> HSR_EC_SHIFT; - if (hsr_ec == HSR_EC_IABT) - return false; - else if ((hsr & HSR_ISV) && !(hsr & HSR_WNR)) - return false; - else - return true; -} - static inline void kvm_clean_pgd(pgd_t *pgd) { clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t)); @@ -114,11 +104,47 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd) pmd_val(*pmd) |= L_PMD_S2_RDWR; } +/* Open coded p*d_addr_end that can deal with 64bit addresses */ +#define kvm_pgd_addr_end(addr, end) \ +({ u64 __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) + +#define kvm_pud_addr_end(addr,end) (end) + +#define kvm_pmd_addr_end(addr, end) \ +({ u64 __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) + +#define kvm_pgd_index(addr) pgd_index(addr) + +static inline bool kvm_page_empty(void *ptr) +{ + struct page *ptr_page = virt_to_page(ptr); + return page_count(ptr_page) == 1; +} + +#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep) +#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp) +#define kvm_pud_table_empty(pudp) (0) + + struct kvm; -static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva, - unsigned long size) +#define kvm_flush_dcache_to_poc(a,l) __cpuc_flush_dcache_area((a), (l)) + +static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101; +} + +static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, + unsigned long size) { + if (!vcpu_has_cache_enabled(vcpu)) + kvm_flush_dcache_to_poc((void *)hva, size); + /* * If we are going to insert an instruction page and the icache is * either VIPT or PIPT, there is a potential problem where the host @@ -139,9 +165,10 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva, } } -#define kvm_flush_dcache_to_poc(a,l) __cpuc_flush_dcache_area((a), (l)) #define kvm_virt_to_phys(x) virt_to_idmap((unsigned long)(x)) +void stage2_flush_vm(struct kvm *kvm); + #endif /* !__ASSEMBLY__ */ #endif /* __ARM_KVM_MMU_H__ */ diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h index 626989f..9fd61c7 100644 --- a/arch/arm/include/asm/pgtable-3level-hwdef.h +++ b/arch/arm/include/asm/pgtable-3level-hwdef.h @@ -43,7 +43,7 @@ #define PMD_SECT_BUFFERABLE (_AT(pmdval_t, 1) << 2) #define PMD_SECT_CACHEABLE (_AT(pmdval_t, 1) << 3) #define PMD_SECT_USER (_AT(pmdval_t, 1) << 6) /* AP[1] */ -#define PMD_SECT_RDONLY (_AT(pmdval_t, 1) << 7) /* AP[2] */ +#define PMD_SECT_AP2 (_AT(pmdval_t, 1) << 7) /* read only */ #define PMD_SECT_S (_AT(pmdval_t, 3) << 8) #define PMD_SECT_AF (_AT(pmdval_t, 1) << 10) #define PMD_SECT_nG (_AT(pmdval_t, 1) << 11) @@ -72,6 +72,7 @@ #define PTE_TABLE_BIT (_AT(pteval_t, 1) << 1) #define PTE_BUFFERABLE (_AT(pteval_t, 1) << 2) /* AttrIndx[0] */ #define PTE_CACHEABLE (_AT(pteval_t, 1) << 3) /* AttrIndx[1] */ +#define PTE_AP2 (_AT(pteval_t, 1) << 7) /* AP[2] */ #define PTE_EXT_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */ #define PTE_EXT_AF (_AT(pteval_t, 1) << 10) /* Access Flag */ #define PTE_EXT_NG (_AT(pteval_t, 1) << 11) /* nG */ diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 85c60ad..06e0bc0 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -79,18 +79,19 @@ #define L_PTE_PRESENT (_AT(pteval_t, 3) << 0) /* Present */ #define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */ #define L_PTE_USER (_AT(pteval_t, 1) << 6) /* AP[1] */ -#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7) /* AP[2] */ #define L_PTE_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */ #define L_PTE_YOUNG (_AT(pteval_t, 1) << 10) /* AF */ #define L_PTE_XN (_AT(pteval_t, 1) << 54) /* XN */ -#define L_PTE_DIRTY (_AT(pteval_t, 1) << 55) /* unused */ -#define L_PTE_SPECIAL (_AT(pteval_t, 1) << 56) /* unused */ +#define L_PTE_DIRTY (_AT(pteval_t, 1) << 55) +#define L_PTE_SPECIAL (_AT(pteval_t, 1) << 56) #define L_PTE_NONE (_AT(pteval_t, 1) << 57) /* PROT_NONE */ +#define L_PTE_RDONLY (_AT(pteval_t, 1) << 58) /* READ ONLY */ -#define PMD_SECT_VALID (_AT(pmdval_t, 1) << 0) -#define PMD_SECT_DIRTY (_AT(pmdval_t, 1) << 55) -#define PMD_SECT_SPLITTING (_AT(pmdval_t, 1) << 56) -#define PMD_SECT_NONE (_AT(pmdval_t, 1) << 57) +#define L_PMD_SECT_VALID (_AT(pmdval_t, 1) << 0) +#define L_PMD_SECT_DIRTY (_AT(pmdval_t, 1) << 55) +#define L_PMD_SECT_SPLITTING (_AT(pmdval_t, 1) << 56) +#define L_PMD_SECT_NONE (_AT(pmdval_t, 1) << 57) +#define L_PMD_SECT_RDONLY (_AT(pteval_t, 1) << 58) /* * To be used in assembly code with the upper page attributes. @@ -207,27 +208,32 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define pte_huge(pte) (pte_val(pte) && !(pte_val(pte) & PTE_TABLE_BIT)) #define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT)) -#define pmd_young(pmd) (pmd_val(pmd) & PMD_SECT_AF) +#define pmd_isset(pmd, val) ((u32)(val) == (val) ? pmd_val(pmd) & (val) \ + : !!(pmd_val(pmd) & (val))) +#define pmd_isclear(pmd, val) (!(pmd_val(pmd) & (val))) + +#define pmd_young(pmd) (pmd_isset((pmd), PMD_SECT_AF)) #define __HAVE_ARCH_PMD_WRITE -#define pmd_write(pmd) (!(pmd_val(pmd) & PMD_SECT_RDONLY)) +#define pmd_write(pmd) (pmd_isclear((pmd), L_PMD_SECT_RDONLY)) +#define pmd_dirty(pmd) (pmd_isset((pmd), L_PMD_SECT_DIRTY)) #define pmd_hugewillfault(pmd) (!pmd_young(pmd) || !pmd_write(pmd)) #define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define pmd_trans_huge(pmd) (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT)) -#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING) +#define pmd_trans_huge(pmd) (pmd_val(pmd) && !pmd_table(pmd)) +#define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING)) #endif #define PMD_BIT_FUNC(fn,op) \ static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; } -PMD_BIT_FUNC(wrprotect, |= PMD_SECT_RDONLY); +PMD_BIT_FUNC(wrprotect, |= L_PMD_SECT_RDONLY); PMD_BIT_FUNC(mkold, &= ~PMD_SECT_AF); -PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING); -PMD_BIT_FUNC(mkwrite, &= ~PMD_SECT_RDONLY); -PMD_BIT_FUNC(mkdirty, |= PMD_SECT_DIRTY); +PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING); +PMD_BIT_FUNC(mkwrite, &= ~L_PMD_SECT_RDONLY); +PMD_BIT_FUNC(mkdirty, |= L_PMD_SECT_DIRTY); PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF); #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) @@ -241,8 +247,8 @@ PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF); static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | PMD_SECT_RDONLY | - PMD_SECT_VALID | PMD_SECT_NONE; + const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | L_PMD_SECT_RDONLY | + L_PMD_SECT_VALID | L_PMD_SECT_NONE; pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask); return pmd; } @@ -253,8 +259,13 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, BUG_ON(addr >= TASK_SIZE); /* create a faulting entry if PROT_NONE protected */ - if (pmd_val(pmd) & PMD_SECT_NONE) - pmd_val(pmd) &= ~PMD_SECT_VALID; + if (pmd_val(pmd) & L_PMD_SECT_NONE) + pmd_val(pmd) &= ~L_PMD_SECT_VALID; + + if (pmd_write(pmd) && pmd_dirty(pmd)) + pmd_val(pmd) &= ~PMD_SECT_AP2; + else + pmd_val(pmd) |= PMD_SECT_AP2; *pmdp = __pmd(pmd_val(pmd) | PMD_SECT_nG); flush_pmd_entry(pmdp); diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 7d59b52..89dba13 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -214,12 +214,16 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd) #define pte_clear(mm,addr,ptep) set_pte_ext(ptep, __pte(0), 0) +#define pte_isset(pte, val) ((u32)(val) == (val) ? pte_val(pte) & (val) \ + : !!(pte_val(pte) & (val))) +#define pte_isclear(pte, val) (!(pte_val(pte) & (val))) + #define pte_none(pte) (!pte_val(pte)) -#define pte_present(pte) (pte_val(pte) & L_PTE_PRESENT) -#define pte_write(pte) (!(pte_val(pte) & L_PTE_RDONLY)) -#define pte_dirty(pte) (pte_val(pte) & L_PTE_DIRTY) -#define pte_young(pte) (pte_val(pte) & L_PTE_YOUNG) -#define pte_exec(pte) (!(pte_val(pte) & L_PTE_XN)) +#define pte_present(pte) (pte_isset((pte), L_PTE_PRESENT)) +#define pte_write(pte) (pte_isclear((pte), L_PTE_RDONLY)) +#define pte_dirty(pte) (pte_isset((pte), L_PTE_DIRTY)) +#define pte_young(pte) (pte_isset((pte), L_PTE_YOUNG)) +#define pte_exec(pte) (pte_isclear((pte), L_PTE_XN)) #define pte_special(pte) (0) #define pte_present_user(pte) (pte_present(pte) && (pte_val(pte) & L_PTE_USER)) diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h index 22a3b9b..4157aec 100644 --- a/arch/arm/include/asm/smp.h +++ b/arch/arm/include/asm/smp.h @@ -74,6 +74,7 @@ struct secondary_data { }; extern struct secondary_data secondary_data; extern volatile int pen_release; +extern void secondary_startup(void); extern int __cpu_disable(void); diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 71a06b2..3e635ee 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -43,16 +43,6 @@ struct cpu_context_save { __u32 extra[2]; /* Xscale 'acc' register, etc */ }; -struct arm_restart_block { - union { - /* For user cache flushing */ - struct { - unsigned long start; - unsigned long end; - } cache; - }; -}; - /* * low level task data that entry.S needs immediate access to. * __switch_to() assumes cpu_context follows immediately after cpu_domain. @@ -78,7 +68,6 @@ struct thread_info { unsigned long thumbee_state; /* ThumbEE Handler Base register */ #endif struct restart_block restart_block; - struct arm_restart_block arm_restart_block; }; #define INIT_THREAD_INFO(tsk) \ diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h index 83259b8..5f833f7 100644 --- a/arch/arm/include/asm/tls.h +++ b/arch/arm/include/asm/tls.h @@ -1,6 +1,9 @@ #ifndef __ASMARM_TLS_H #define __ASMARM_TLS_H +#include +#include + #ifdef __ASSEMBLY__ #include .macro switch_tls_none, base, tp, tpuser, tmp1, tmp2 @@ -50,6 +53,49 @@ #endif #ifndef __ASSEMBLY__ + +static inline void set_tls(unsigned long val) +{ + struct thread_info *thread; + + thread = current_thread_info(); + + thread->tp_value[0] = val; + + /* + * This code runs with preemption enabled and therefore must + * be reentrant with respect to switch_tls. + * + * We need to ensure ordering between the shadow state and the + * hardware state, so that we don't corrupt the hardware state + * with a stale shadow state during context switch. + * + * If we're preempted here, switch_tls will load TPIDRURO from + * thread_info upon resuming execution and the following mcr + * is merely redundant. + */ + barrier(); + + if (!tls_emu) { + if (has_tls_reg) { + asm("mcr p15, 0, %0, c13, c0, 3" + : : "r" (val)); + } else { +#ifdef CONFIG_KUSER_HELPERS + /* + * User space must never try to access this + * directly. Expect your app to break + * eventually if you do so. The user helper + * at 0xffff0fe0 must be used instead. (see + * entry-armv.S for details) + */ + *((unsigned int *)0xffff0ff0) = val; +#endif + } + + } +} + static inline unsigned long get_tpuser(void) { unsigned long reg = 0; @@ -59,5 +105,23 @@ static inline unsigned long get_tpuser(void) return reg; } + +static inline void set_tpuser(unsigned long val) +{ + /* Since TPIDRURW is fully context-switched (unlike TPIDRURO), + * we need not update thread_info. + */ + if (has_tls_reg && !tls_emu) { + asm("mcr p15, 0, %0, c13, c0, 2" + : : "r" (val)); + } +} + +static inline void flush_tls(void) +{ + set_tls(0); + set_tpuser(0); +} + #endif #endif /* __ASMARM_TLS_H */ diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h index 4387624..21ca0ce 100644 --- a/arch/arm/include/asm/unistd.h +++ b/arch/arm/include/asm/unistd.h @@ -15,7 +15,17 @@ #include +/* + * This may need to be greater than __NR_last_syscall+1 in order to + * account for the padding in the syscall table + */ #define __NR_syscalls (384) + +/* + * *NOTE*: This is a ghost syscall private to the kernel. Only the + * __kuser_cmpxchg code in entry-armv.S should be aware of its + * existence. Don't ever use this from user code. + */ #define __ARM_NR_cmpxchg (__ARM_NR_BASE+0x00fff0) #define __ARCH_WANT_STAT64 diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h index fb5584d..c377633 100644 --- a/arch/arm/include/uapi/asm/unistd.h +++ b/arch/arm/include/uapi/asm/unistd.h @@ -410,11 +410,6 @@ #define __NR_sched_getattr (__NR_SYSCALL_BASE+381) /* - * This may need to be greater than __NR_last_syscall+1 in order to - * account for the padding in the syscall table - */ - -/* * The following SWIs are ARM private. */ #define __ARM_NR_BASE (__NR_SYSCALL_BASE+0x0f0000) @@ -425,12 +420,6 @@ #define __ARM_NR_set_tls (__ARM_NR_BASE+5) /* - * *NOTE*: This is a ghost syscall private to the kernel. Only the - * __kuser_cmpxchg code in entry-armv.S should be aware of its - * existence. Don't ever use this from user code. - */ - -/* * The following syscalls are obsolete and no longer available for EABI. */ #if !defined(__KERNEL__) diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index ded0417..85598b5 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -174,6 +174,7 @@ int main(void) DEFINE(VCPU_FIQ_REGS, offsetof(struct kvm_vcpu, arch.regs.fiq_regs)); DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc)); DEFINE(VCPU_CPSR, offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr)); + DEFINE(VCPU_HCR, offsetof(struct kvm_vcpu, arch.hcr)); DEFINE(VCPU_IRQ_LINES, offsetof(struct kvm_vcpu, arch.irq_lines)); DEFINE(VCPU_HSR, offsetof(struct kvm_vcpu, arch.fault.hsr)); DEFINE(VCPU_HxFAR, offsetof(struct kvm_vcpu, arch.fault.hxfar)); diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index a2dcafd..98dd389 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -32,7 +32,9 @@ ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) disable_irq @ disable interrupts - ldr r1, [tsk, #TI_FLAGS] + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing + tst r1, #_TIF_SYSCALL_WORK + bne __sys_trace_return tst r1, #_TIF_WORK_MASK bne fast_work_pending asm_trace_hardirqs_on diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S index 797b1a6..7e666cf 100644 --- a/arch/arm/kernel/hyp-stub.S +++ b/arch/arm/kernel/hyp-stub.S @@ -134,9 +134,7 @@ ENTRY(__hyp_stub_install_secondary) mcr p15, 4, r7, c1, c1, 3 @ HSTR THUMB( orr r7, #(1 << 30) ) @ HSCTLR.TE -#ifdef CONFIG_CPU_BIG_ENDIAN - orr r7, #(1 << 9) @ HSCTLR.EE -#endif +ARM_BE8(orr r7, r7, #(1 << 25)) @ HSCTLR.EE mcr p15, 4, r7, c1, c0, 0 @ HSCTLR mrc p15, 4, r7, c1, c1, 1 @ HDCR diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 9723d17..1e782bd 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -163,7 +163,7 @@ static bool migrate_one_irq(struct irq_desc *desc) c = irq_data_get_irq_chip(d); if (!c->irq_set_affinity) pr_debug("IRQ%u: unable to set affinity\n", d->irq); - else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret) + else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret) cpumask_copy(d->affinity, affinity); return ret; diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c index 18a7628..380c20f 100644 --- a/arch/arm/kernel/kprobes-common.c +++ b/arch/arm/kernel/kprobes-common.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "kprobes.h" @@ -305,7 +306,8 @@ kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) if (handler) { /* We can emulate the instruction in (possibly) modified form */ - asi->insn[0] = (insn & 0xfff00000) | (rn << 16) | reglist; + asi->insn[0] = __opcode_to_mem_arm((insn & 0xfff00000) | + (rn << 16) | reglist); asi->insn_handler = handler; return INSN_GOOD; } @@ -334,13 +336,14 @@ prepare_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, #ifdef CONFIG_THUMB2_KERNEL if (thumb) { u16 *thumb_insn = (u16 *)asi->insn; - thumb_insn[1] = 0x4770; /* Thumb bx lr */ - thumb_insn[2] = 0x4770; /* Thumb bx lr */ + /* Thumb bx lr */ + thumb_insn[1] = __opcode_to_mem_thumb16(0x4770); + thumb_insn[2] = __opcode_to_mem_thumb16(0x4770); return insn; } - asi->insn[1] = 0xe12fff1e; /* ARM bx lr */ + asi->insn[1] = __opcode_to_mem_arm(0xe12fff1e); /* ARM bx lr */ #else - asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */ + asi->insn[1] = __opcode_to_mem_arm(0xe1a0f00e); /* mov pc, lr */ #endif /* Make an ARM instruction unconditional */ if (insn < 0xe0000000) @@ -360,12 +363,12 @@ set_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, if (thumb) { u16 *ip = (u16 *)asi->insn; if (is_wide_instruction(insn)) - *ip++ = insn >> 16; - *ip++ = insn; + *ip++ = __opcode_to_mem_thumb16(insn >> 16); + *ip++ = __opcode_to_mem_thumb16(insn); return; } #endif - asi->insn[0] = insn; + asi->insn[0] = __opcode_to_mem_arm(insn); } /* diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 6123daf..241222c 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "kprobes.h" @@ -163,9 +164,9 @@ t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) enum kprobe_insn ret = kprobe_decode_ldmstm(insn, asi); /* Fixup modified instruction to have halfwords in correct order...*/ - insn = asi->insn[0]; - ((u16 *)asi->insn)[0] = insn >> 16; - ((u16 *)asi->insn)[1] = insn & 0xffff; + insn = __mem_to_opcode_arm(asi->insn[0]); + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn >> 16); + ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0xffff); return ret; } @@ -1153,7 +1154,7 @@ t16_decode_hiregs(kprobe_opcode_t insn, struct arch_specific_insn *asi) { insn &= ~0x00ff; insn |= 0x001; /* Set Rdn = R1 and Rm = R0 */ - ((u16 *)asi->insn)[0] = insn; + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn); asi->insn_handler = t16_emulate_hiregs; return INSN_GOOD; } @@ -1182,8 +1183,10 @@ t16_decode_push(kprobe_opcode_t insn, struct arch_specific_insn *asi) * and call it with R9=SP and LR in the register list represented * by R8. */ - ((u16 *)asi->insn)[0] = 0xe929; /* 1st half STMDB R9!,{} */ - ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */ + /* 1st half STMDB R9!,{} */ + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe929); + /* 2nd half (register list) */ + ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff); asi->insn_handler = t16_emulate_push; return INSN_GOOD; } @@ -1232,8 +1235,10 @@ t16_decode_pop(kprobe_opcode_t insn, struct arch_specific_insn *asi) * and call it with R9=SP and PC in the register list represented * by R8. */ - ((u16 *)asi->insn)[0] = 0xe8b9; /* 1st half LDMIA R9!,{} */ - ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */ + /* 1st half LDMIA R9!,{} */ + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe8b9); + /* 2nd half (register list) */ + ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff); asi->insn_handler = insn & 0x100 ? t16_emulate_pop_pc : t16_emulate_pop_nopc; return INSN_GOOD; diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index a7b621e..49a87b6 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include "kprobes.h" @@ -62,10 +63,10 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) #ifdef CONFIG_THUMB2_KERNEL thumb = true; addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */ - insn = ((u16 *)addr)[0]; + insn = __mem_to_opcode_thumb16(((u16 *)addr)[0]); if (is_wide_instruction(insn)) { - insn <<= 16; - insn |= ((u16 *)addr)[1]; + u16 inst2 = __mem_to_opcode_thumb16(((u16 *)addr)[1]); + insn = __opcode_thumb32_compose(insn, inst2); decode_insn = thumb32_kprobe_decode_insn; } else decode_insn = thumb16_kprobe_decode_insn; @@ -73,7 +74,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) thumb = false; if (addr & 0x3) return -EINVAL; - insn = *p->addr; + insn = __mem_to_opcode_arm(*p->addr); decode_insn = arm_kprobe_decode_insn; #endif diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 1bdd78b..dd6553b 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -336,6 +336,8 @@ void flush_thread(void) memset(&tsk->thread.debug, 0, sizeof(struct debug_info)); memset(&thread->fpstate, 0, sizeof(union fp_state)); + flush_tls(); + thread_notify(THREAD_NOTIFY_FLUSH, thread); } diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 4a5e943..a4ef472 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -1034,6 +1034,15 @@ static int c_show(struct seq_file *m, void *v) seq_printf(m, "model name\t: %s rev %d (%s)\n", cpu_name, cpuid & 15, elf_platform); +#if defined(CONFIG_SMP) + seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", + per_cpu(cpu_data, i).loops_per_jiffy / (500000UL/HZ), + (per_cpu(cpu_data, i).loops_per_jiffy / (5000UL/HZ)) % 100); +#else + seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", + loops_per_jiffy / (500000/HZ), + (loops_per_jiffy / (5000/HZ)) % 100); +#endif /* dump out the processor features */ seq_puts(m, "Features\t: "); diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index b7b4c86..8cd3724 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -388,8 +388,17 @@ asmlinkage void secondary_start_kernel(void) void __init smp_cpus_done(unsigned int max_cpus) { - printk(KERN_INFO "SMP: Total of %d processors activated.\n", - num_online_cpus()); + int cpu; + unsigned long bogosum = 0; + + for_each_online_cpu(cpu) + bogosum += per_cpu(cpu_data, cpu).loops_per_jiffy; + + printk(KERN_INFO "SMP: Total of %d processors activated " + "(%lu.%02lu BogoMIPS).\n", + num_online_cpus(), + bogosum / (500000/HZ), + (bogosum / (5000/HZ)) % 100); hyp_mode_check(); } diff --git a/arch/arm/kernel/thumbee.c b/arch/arm/kernel/thumbee.c index 7b8403b..80f0d69 100644 --- a/arch/arm/kernel/thumbee.c +++ b/arch/arm/kernel/thumbee.c @@ -45,7 +45,7 @@ static int thumbee_notifier(struct notifier_block *self, unsigned long cmd, void switch (cmd) { case THREAD_NOTIFY_FLUSH: - thread->thumbee_state = 0; + teehbr_write(0); break; case THREAD_NOTIFY_SWITCH: current_thread_info()->thumbee_state = teehbr_read(); diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 172ee18..3f31443 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -510,8 +510,6 @@ static int bad_syscall(int n, struct pt_regs *regs) return regs->ARM_r0; } -static long do_cache_op_restart(struct restart_block *); - static inline int __do_cache_op(unsigned long start, unsigned long end) { @@ -520,24 +518,8 @@ __do_cache_op(unsigned long start, unsigned long end) do { unsigned long chunk = min(PAGE_SIZE, end - start); - if (signal_pending(current)) { - struct thread_info *ti = current_thread_info(); - - ti->restart_block = (struct restart_block) { - .fn = do_cache_op_restart, - }; - - ti->arm_restart_block = (struct arm_restart_block) { - { - .cache = { - .start = start, - .end = end, - }, - }, - }; - - return -ERESTART_RESTARTBLOCK; - } + if (fatal_signal_pending(current)) + return 0; ret = flush_cache_user_range(start, start + chunk); if (ret) @@ -550,15 +532,6 @@ __do_cache_op(unsigned long start, unsigned long end) return 0; } -static long do_cache_op_restart(struct restart_block *unused) -{ - struct arm_restart_block *restart_block; - - restart_block = ¤t_thread_info()->arm_restart_block; - return __do_cache_op(restart_block->cache.start, - restart_block->cache.end); -} - static inline int do_cache_op(unsigned long start, unsigned long end, int flags) { @@ -578,7 +551,6 @@ do_cache_op(unsigned long start, unsigned long end, int flags) #define NR(x) ((__ARM_NR_##x) - __ARM_NR_BASE) asmlinkage int arm_syscall(int no, struct pt_regs *regs) { - struct thread_info *thread = current_thread_info(); siginfo_t info; if ((no >> 16) != (__ARM_NR_BASE>> 16)) @@ -629,21 +601,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs) return regs->ARM_r0; case NR(set_tls): - thread->tp_value[0] = regs->ARM_r0; - if (tls_emu) - return 0; - if (has_tls_reg) { - asm ("mcr p15, 0, %0, c13, c0, 3" - : : "r" (regs->ARM_r0)); - } else { - /* - * User space must never try to access this directly. - * Expect your app to break eventually if you do so. - * The user helper at 0xffff0fe0 must be used instead. - * (see entry-armv.S for details) - */ - *((unsigned int *)0xffff0ff0) = regs->ARM_r0; - } + set_tls(regs->ARM_r0); return 0; #ifdef CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index bd18bb8..f6a52a2 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -82,7 +82,7 @@ struct kvm_vcpu *kvm_arm_get_running_vcpu(void) /** * kvm_arm_get_running_vcpus - get the per-CPU array of currently running vcpus. */ -struct kvm_vcpu __percpu **kvm_get_running_vcpus(void) +struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void) { return &kvm_arm_running_vcpu; } @@ -155,16 +155,6 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } -void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) -{ -} - -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) -{ - return 0; -} /** * kvm_arch_destroy_vm - destroy the VM data structure @@ -224,39 +214,17 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -void kvm_arch_memslots_updated(struct kvm *kvm) -{ -} - -int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) -{ - return 0; -} - -void kvm_arch_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, - enum kvm_mr_change change) -{ -} - -void kvm_arch_flush_shadow_all(struct kvm *kvm) -{ -} - -void kvm_arch_flush_shadow_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ -} struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) { int err; struct kvm_vcpu *vcpu; + if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) { + err = -EBUSY; + goto out; + } + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); if (!vcpu) { err = -ENOMEM; @@ -464,15 +432,16 @@ static void update_vttbr(struct kvm *kvm) /* update vttbr to be used with the new vmid */ pgd_phys = virt_to_phys(kvm->arch.pgd); + BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK); vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK; - kvm->arch.vttbr = pgd_phys & VTTBR_BADDR_MASK; - kvm->arch.vttbr |= vmid; + kvm->arch.vttbr = pgd_phys | vmid; spin_unlock(&kvm_vmid_lock); } static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) { + struct kvm *kvm = vcpu->kvm; int ret; if (likely(vcpu->arch.has_run_once)) @@ -484,12 +453,20 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) * Initialize the VGIC before running a vcpu the first time on * this VM. */ - if (unlikely(!vgic_initialized(vcpu->kvm))) { - ret = kvm_vgic_init(vcpu->kvm); + if (unlikely(!vgic_initialized(kvm))) { + ret = kvm_vgic_init(kvm); if (ret) return ret; } + /* + * Enable the arch timers only if we have an in-kernel VGIC + * and it has been properly initialized, since we cannot handle + * interrupts from the virtual timer with a userspace gic. + */ + if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) + kvm_timer_enable(kvm); + return 0; } @@ -713,10 +690,21 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, return ret; /* + * Ensure a rebooted VM will fault in RAM pages and detect if the + * guest MMU is turned off and flush the caches as needed. + */ + if (vcpu->arch.has_run_once) + stage2_unmap_vm(vcpu->kvm); + + vcpu_reset_hcr(vcpu); + + /* * Handle the "start in power-off" case by marking the VCPU as paused. */ - if (__test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) + if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) vcpu->arch.pause = true; + else + vcpu->arch.pause = false; return 0; } @@ -862,7 +850,8 @@ static int hyp_init_cpu_notify(struct notifier_block *self, switch (action) { case CPU_STARTING: case CPU_STARTING_FROZEN: - cpu_init_hyp_mode(NULL); + if (__hyp_get_vectors() == hyp_default_vectors) + cpu_init_hyp_mode(NULL); break; } diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 78c0885..7c73290 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -205,6 +206,44 @@ done: } /* + * Generic accessor for VM registers. Only called as long as HCR_TVM + * is set. + */ +static bool access_vm_reg(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + BUG_ON(!p->is_write); + + vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1); + if (p->is_64bit) + vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2); + + return true; +} + +/* + * SCTLR accessor. Only called as long as HCR_TVM is set. If the + * guest enables the MMU, we stop trapping the VM sys_regs and leave + * it in complete control of the caches. + * + * Used by the cpu-specific code. + */ +bool access_sctlr(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + access_vm_reg(vcpu, p, r); + + if (vcpu_has_cache_enabled(vcpu)) { /* MMU+Caches enabled? */ + vcpu->arch.hcr &= ~HCR_TVM; + stage2_flush_vm(vcpu->kvm); + } + + return true; +} + +/* * We could trap ID_DFR0 and tell the guest we don't support performance * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was * NAKed, so it will read the PMCR anyway. @@ -261,33 +300,36 @@ static const struct coproc_reg cp15_regs[] = { { CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32, NULL, reset_val, c1_CPACR, 0x00000000 }, - /* TTBR0/TTBR1: swapped by interrupt.S. */ - { CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 }, - { CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 }, - - /* TTBCR: swapped by interrupt.S. */ + /* TTBR0/TTBR1/TTBCR: swapped by interrupt.S. */ + { CRm64( 2), Op1( 0), is64, access_vm_reg, reset_unknown64, c2_TTBR0 }, + { CRn(2), CRm( 0), Op1( 0), Op2( 0), is32, + access_vm_reg, reset_unknown, c2_TTBR0 }, + { CRn(2), CRm( 0), Op1( 0), Op2( 1), is32, + access_vm_reg, reset_unknown, c2_TTBR1 }, { CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32, - NULL, reset_val, c2_TTBCR, 0x00000000 }, + access_vm_reg, reset_val, c2_TTBCR, 0x00000000 }, + { CRm64( 2), Op1( 1), is64, access_vm_reg, reset_unknown64, c2_TTBR1 }, + /* DACR: swapped by interrupt.S. */ { CRn( 3), CRm( 0), Op1( 0), Op2( 0), is32, - NULL, reset_unknown, c3_DACR }, + access_vm_reg, reset_unknown, c3_DACR }, /* DFSR/IFSR/ADFSR/AIFSR: swapped by interrupt.S. */ { CRn( 5), CRm( 0), Op1( 0), Op2( 0), is32, - NULL, reset_unknown, c5_DFSR }, + access_vm_reg, reset_unknown, c5_DFSR }, { CRn( 5), CRm( 0), Op1( 0), Op2( 1), is32, - NULL, reset_unknown, c5_IFSR }, + access_vm_reg, reset_unknown, c5_IFSR }, { CRn( 5), CRm( 1), Op1( 0), Op2( 0), is32, - NULL, reset_unknown, c5_ADFSR }, + access_vm_reg, reset_unknown, c5_ADFSR }, { CRn( 5), CRm( 1), Op1( 0), Op2( 1), is32, - NULL, reset_unknown, c5_AIFSR }, + access_vm_reg, reset_unknown, c5_AIFSR }, /* DFAR/IFAR: swapped by interrupt.S. */ { CRn( 6), CRm( 0), Op1( 0), Op2( 0), is32, - NULL, reset_unknown, c6_DFAR }, + access_vm_reg, reset_unknown, c6_DFAR }, { CRn( 6), CRm( 0), Op1( 0), Op2( 2), is32, - NULL, reset_unknown, c6_IFAR }, + access_vm_reg, reset_unknown, c6_IFAR }, /* PAR swapped by interrupt.S */ { CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR }, @@ -324,9 +366,15 @@ static const struct coproc_reg cp15_regs[] = { /* PRRR/NMRR (aka MAIR0/MAIR1): swapped by interrupt.S. */ { CRn(10), CRm( 2), Op1( 0), Op2( 0), is32, - NULL, reset_unknown, c10_PRRR}, + access_vm_reg, reset_unknown, c10_PRRR}, { CRn(10), CRm( 2), Op1( 0), Op2( 1), is32, - NULL, reset_unknown, c10_NMRR}, + access_vm_reg, reset_unknown, c10_NMRR}, + + /* AMAIR0/AMAIR1: swapped by interrupt.S. */ + { CRn(10), CRm( 3), Op1( 0), Op2( 0), is32, + access_vm_reg, reset_unknown, c10_AMAIR0}, + { CRn(10), CRm( 3), Op1( 0), Op2( 1), is32, + access_vm_reg, reset_unknown, c10_AMAIR1}, /* VBAR: swapped by interrupt.S. */ { CRn(12), CRm( 0), Op1( 0), Op2( 0), is32, @@ -334,7 +382,7 @@ static const struct coproc_reg cp15_regs[] = { /* CONTEXTIDR/TPIDRURW/TPIDRURO/TPIDRPRW: swapped by interrupt.S. */ { CRn(13), CRm( 0), Op1( 0), Op2( 1), is32, - NULL, reset_val, c13_CID, 0x00000000 }, + access_vm_reg, reset_val, c13_CID, 0x00000000 }, { CRn(13), CRm( 0), Op1( 0), Op2( 2), is32, NULL, reset_unknown, c13_TID_URW }, { CRn(13), CRm( 0), Op1( 0), Op2( 3), is32, @@ -443,7 +491,7 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct coproc_params params; - params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf; + params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf; params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf; params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0); params.is_64bit = true; @@ -451,7 +499,7 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run) params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 16) & 0xf; params.Op2 = 0; params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf; - params.CRn = 0; + params.CRm = 0; return emulate_cp15(vcpu, ¶ms); } @@ -694,7 +742,7 @@ static bool is_valid_cache(u32 val) u32 level, ctype; if (val >= CSSELR_MAX) - return -ENOENT; + return false; /* Bottom bit is Instruction or Data bit. Next 3 bits are level. */ level = (val >> 1); diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h index 0461d5c..1a44bbe 100644 --- a/arch/arm/kvm/coproc.h +++ b/arch/arm/kvm/coproc.h @@ -58,8 +58,8 @@ static inline void print_cp_instr(const struct coproc_params *p) { /* Look, we even formatted it for you to paste into the table! */ if (p->is_64bit) { - kvm_pr_unimpl(" { CRm(%2lu), Op1(%2lu), is64, func_%s },\n", - p->CRm, p->Op1, p->is_write ? "write" : "read"); + kvm_pr_unimpl(" { CRm64(%2lu), Op1(%2lu), is64, func_%s },\n", + p->CRn, p->Op1, p->is_write ? "write" : "read"); } else { kvm_pr_unimpl(" { CRn(%2lu), CRm(%2lu), Op1(%2lu), Op2(%2lu), is32," " func_%s },\n", @@ -135,13 +135,13 @@ static inline int cmp_reg(const struct coproc_reg *i1, return -1; if (i1->CRn != i2->CRn) return i1->CRn - i2->CRn; - if (i1->is_64 != i2->is_64) - return i2->is_64 - i1->is_64; if (i1->CRm != i2->CRm) return i1->CRm - i2->CRm; if (i1->Op1 != i2->Op1) return i1->Op1 - i2->Op1; - return i1->Op2 - i2->Op2; + if (i1->Op2 != i2->Op2) + return i1->Op2 - i2->Op2; + return i2->is_64 - i1->is_64; } @@ -153,4 +153,8 @@ static inline int cmp_reg(const struct coproc_reg *i1, #define is64 .is_64 = true #define is32 .is_64 = false +bool access_sctlr(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r); + #endif /* __ARM_KVM_COPROC_LOCAL_H__ */ diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c index bb0cac1..e6f4ae4 100644 --- a/arch/arm/kvm/coproc_a15.c +++ b/arch/arm/kvm/coproc_a15.c @@ -34,7 +34,7 @@ static const struct coproc_reg a15_regs[] = { /* SCTLR: swapped by interrupt.S. */ { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, - NULL, reset_val, c1_SCTLR, 0x00C50078 }, + access_sctlr, reset_val, c1_SCTLR, 0x00C50078 }, }; static struct kvm_coproc_target_table a15_target_table = { diff --git a/arch/arm/kvm/coproc_a7.c b/arch/arm/kvm/coproc_a7.c index 1df7673..17fc7cd 100644 --- a/arch/arm/kvm/coproc_a7.c +++ b/arch/arm/kvm/coproc_a7.c @@ -37,7 +37,7 @@ static const struct coproc_reg a7_regs[] = { /* SCTLR: swapped by interrupt.S. */ { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, - NULL, reset_val, c1_SCTLR, 0x00C50878 }, + access_sctlr, reset_val, c1_SCTLR, 0x00C50878 }, }; static struct kvm_coproc_target_table a7_target_table = { diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index 0de91fc..ec4fa86 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -89,6 +89,8 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) else kvm_vcpu_block(vcpu); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + return 1; } diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S index 1b9844d..ee4f744 100644 --- a/arch/arm/kvm/init.S +++ b/arch/arm/kvm/init.S @@ -98,6 +98,10 @@ __do_hyp_init: mrc p15, 0, r0, c10, c2, 1 mcr p15, 4, r0, c10, c2, 1 + @ Invalidate the stale TLBs from Bootloader + mcr p15, 4, r0, c8, c7, 0 @ TLBIALLH + dsb ish + @ Set the HSCTLR to: @ - ARM/THUMB exceptions: Kernel config (Thumb-2 kernel) @ - Endianness: Kernel config diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index 0d68d40..a1467e7 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -159,13 +159,9 @@ __kvm_vcpu_return: @ Don't trap coprocessor accesses for host kernel set_hstr vmexit set_hdcr vmexit - set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore #ifdef CONFIG_VFPv3 - @ Save floating point registers we if let guest use them. - tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) - bne after_vfp_restore - @ Switch VFP/NEON hardware state to the host's add r7, vcpu, #VCPU_VFP_GUEST store_vfp_state r7 @@ -177,6 +173,8 @@ after_vfp_restore: @ Restore FPEXC_EN which we clobbered on entry pop {r2} VFPFMXR FPEXC, r2 +#else +after_vfp_restore: #endif @ Reset Hyp-role @@ -467,7 +465,7 @@ switch_to_guest_vfp: push {r3-r7} @ NEON/VFP used. Turn on VFP access. - set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11)) @ Switch VFP/NEON hardware state to the guest's add r7, r0, #VCPU_VFP_HOST diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 6f18695..2973b2d 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -303,13 +303,17 @@ vcpu .req r0 @ vcpu pointer always in r0 mrc p15, 0, r2, c14, c1, 0 @ CNTKCTL mrrc p15, 0, r4, r5, c7 @ PAR + mrc p15, 0, r6, c10, c3, 0 @ AMAIR0 + mrc p15, 0, r7, c10, c3, 1 @ AMAIR1 .if \store_to_vcpu == 0 - push {r2,r4-r5} + push {r2,r4-r7} .else str r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)] add r12, vcpu, #CP15_OFFSET(c7_PAR) strd r4, r5, [r12] + str r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)] + str r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)] .endif .endm @@ -322,15 +326,19 @@ vcpu .req r0 @ vcpu pointer always in r0 */ .macro write_cp15_state read_from_vcpu .if \read_from_vcpu == 0 - pop {r2,r4-r5} + pop {r2,r4-r7} .else ldr r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)] add r12, vcpu, #CP15_OFFSET(c7_PAR) ldrd r4, r5, [r12] + ldr r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)] + ldr r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)] .endif mcr p15, 0, r2, c14, c1, 0 @ CNTKCTL mcrr p15, 0, r4, r5, c7 @ PAR + mcr p15, 0, r6, c10, c3, 0 @ AMAIR0 + mcr p15, 0, r7, c10, c3, 1 @ AMAIR1 .if \read_from_vcpu == 0 pop {r2-r12} @@ -570,8 +578,13 @@ vcpu .req r0 @ vcpu pointer always in r0 .endm /* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return - * (hardware reset value is 0). Keep previous value in r2. */ -.macro set_hcptr operation, mask + * (hardware reset value is 0). Keep previous value in r2. + * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if + * VFP wasn't already enabled (always executed on vmtrap). + * If a label is specified with vmexit, it is branched to if VFP wasn't + * enabled. + */ +.macro set_hcptr operation, mask, label = none mrc p15, 4, r2, c1, c1, 2 ldr r3, =\mask .if \operation == vmentry @@ -580,6 +593,17 @@ vcpu .req r0 @ vcpu pointer always in r0 bic r3, r2, r3 @ Don't trap defined coproc-accesses .endif mcr p15, 4, r3, c1, c1, 2 + .if \operation != vmentry + .if \operation == vmexit + tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) + beq 1f + .endif + isb + .if \label != none + b \label + .endif +1: + .endif .endm /* Configures the HDCR (Hyp Debug Configuration Register) on entry/return @@ -597,17 +621,14 @@ vcpu .req r0 @ vcpu pointer always in r0 /* Enable/Disable: stage-2 trans., trap interrupts, trap wfi, trap smc */ .macro configure_hyp_role operation - mrc p15, 4, r2, c1, c1, 0 @ HCR - bic r2, r2, #HCR_VIRT_EXCP_MASK - ldr r3, =HCR_GUEST_MASK .if \operation == vmentry - orr r2, r2, r3 + ldr r2, [vcpu, #VCPU_HCR] ldr r3, [vcpu, #VCPU_IRQ_LINES] orr r2, r2, r3 .else - bic r2, r2, r3 + mov r2, #0 .endif - mcr p15, 4, r2, c1, c1, 0 + mcr p15, 4, r2, c1, c1, 0 @ HCR .endm .macro load_vcpu diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 575d790..c612e37 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -90,103 +90,209 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) return p; } -static bool page_empty(void *ptr) +static void clear_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr) { - struct page *ptr_page = virt_to_page(ptr); - return page_count(ptr_page) == 1; + pud_t *pud_table __maybe_unused = pud_offset(pgd, 0); + pgd_clear(pgd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + pud_free(NULL, pud_table); + put_page(virt_to_page(pgd)); } static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr) { - if (pud_huge(*pud)) { - pud_clear(pud); - kvm_tlb_flush_vmid_ipa(kvm, addr); - } else { - pmd_t *pmd_table = pmd_offset(pud, 0); - pud_clear(pud); - kvm_tlb_flush_vmid_ipa(kvm, addr); - pmd_free(NULL, pmd_table); - } + pmd_t *pmd_table = pmd_offset(pud, 0); + VM_BUG_ON(pud_huge(*pud)); + pud_clear(pud); + kvm_tlb_flush_vmid_ipa(kvm, addr); + pmd_free(NULL, pmd_table); put_page(virt_to_page(pud)); } static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr) { - if (kvm_pmd_huge(*pmd)) { - pmd_clear(pmd); - kvm_tlb_flush_vmid_ipa(kvm, addr); - } else { - pte_t *pte_table = pte_offset_kernel(pmd, 0); - pmd_clear(pmd); - kvm_tlb_flush_vmid_ipa(kvm, addr); - pte_free_kernel(NULL, pte_table); - } + pte_t *pte_table = pte_offset_kernel(pmd, 0); + VM_BUG_ON(kvm_pmd_huge(*pmd)); + pmd_clear(pmd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + pte_free_kernel(NULL, pte_table); put_page(virt_to_page(pmd)); } -static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr) +static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, + phys_addr_t addr, phys_addr_t end) { - if (pte_present(*pte)) { - kvm_set_pte(pte, __pte(0)); - put_page(virt_to_page(pte)); - kvm_tlb_flush_vmid_ipa(kvm, addr); + phys_addr_t start_addr = addr; + pte_t *pte, *start_pte; + + start_pte = pte = pte_offset_kernel(pmd, addr); + do { + if (!pte_none(*pte)) { + kvm_set_pte(pte, __pte(0)); + put_page(virt_to_page(pte)); + kvm_tlb_flush_vmid_ipa(kvm, addr); + } + } while (pte++, addr += PAGE_SIZE, addr != end); + + if (kvm_pte_table_empty(start_pte)) + clear_pmd_entry(kvm, pmd, start_addr); } + +static void unmap_pmds(struct kvm *kvm, pud_t *pud, + phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t next, start_addr = addr; + pmd_t *pmd, *start_pmd; + + start_pmd = pmd = pmd_offset(pud, addr); + do { + next = kvm_pmd_addr_end(addr, end); + if (!pmd_none(*pmd)) { + if (kvm_pmd_huge(*pmd)) { + pmd_clear(pmd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + put_page(virt_to_page(pmd)); + } else { + unmap_ptes(kvm, pmd, addr, next); + } + } + } while (pmd++, addr = next, addr != end); + + if (kvm_pmd_table_empty(start_pmd)) + clear_pud_entry(kvm, pud, start_addr); +} + +static void unmap_puds(struct kvm *kvm, pgd_t *pgd, + phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t next, start_addr = addr; + pud_t *pud, *start_pud; + + start_pud = pud = pud_offset(pgd, addr); + do { + next = kvm_pud_addr_end(addr, end); + if (!pud_none(*pud)) { + if (pud_huge(*pud)) { + pud_clear(pud); + kvm_tlb_flush_vmid_ipa(kvm, addr); + put_page(virt_to_page(pud)); + } else { + unmap_pmds(kvm, pud, addr, next); + } + } + } while (pud++, addr = next, addr != end); + + if (kvm_pud_table_empty(start_pud)) + clear_pgd_entry(kvm, pgd, start_addr); } + static void unmap_range(struct kvm *kvm, pgd_t *pgdp, - unsigned long long start, u64 size) + phys_addr_t start, u64 size) { pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + phys_addr_t addr = start, end = start + size; + phys_addr_t next; + + pgd = pgdp + kvm_pgd_index(addr); + do { + next = kvm_pgd_addr_end(addr, end); + if (!pgd_none(*pgd)) + unmap_puds(kvm, pgd, addr, next); + } while (pgd++, addr = next, addr != end); +} + +static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, + phys_addr_t addr, phys_addr_t end) +{ pte_t *pte; - unsigned long long addr = start, end = start + size; - u64 next; - while (addr < end) { - pgd = pgdp + pgd_index(addr); - pud = pud_offset(pgd, addr); - if (pud_none(*pud)) { - addr = pud_addr_end(addr, end); - continue; + pte = pte_offset_kernel(pmd, addr); + do { + if (!pte_none(*pte)) { + hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); + kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE); } + } while (pte++, addr += PAGE_SIZE, addr != end); +} - if (pud_huge(*pud)) { - /* - * If we are dealing with a huge pud, just clear it and - * move on. - */ - clear_pud_entry(kvm, pud, addr); - addr = pud_addr_end(addr, end); - continue; - } +static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud, + phys_addr_t addr, phys_addr_t end) +{ + pmd_t *pmd; + phys_addr_t next; - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) { - addr = pmd_addr_end(addr, end); - continue; + pmd = pmd_offset(pud, addr); + do { + next = kvm_pmd_addr_end(addr, end); + if (!pmd_none(*pmd)) { + if (kvm_pmd_huge(*pmd)) { + hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); + kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE); + } else { + stage2_flush_ptes(kvm, pmd, addr, next); + } } + } while (pmd++, addr = next, addr != end); +} - if (!kvm_pmd_huge(*pmd)) { - pte = pte_offset_kernel(pmd, addr); - clear_pte_entry(kvm, pte, addr); - next = addr + PAGE_SIZE; - } +static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd, + phys_addr_t addr, phys_addr_t end) +{ + pud_t *pud; + phys_addr_t next; - /* - * If the pmd entry is to be cleared, walk back up the ladder - */ - if (kvm_pmd_huge(*pmd) || page_empty(pte)) { - clear_pmd_entry(kvm, pmd, addr); - next = pmd_addr_end(addr, end); - if (page_empty(pmd) && !page_empty(pud)) { - clear_pud_entry(kvm, pud, addr); - next = pud_addr_end(addr, end); + pud = pud_offset(pgd, addr); + do { + next = kvm_pud_addr_end(addr, end); + if (!pud_none(*pud)) { + if (pud_huge(*pud)) { + hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); + kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE); + } else { + stage2_flush_pmds(kvm, pud, addr, next); } } + } while (pud++, addr = next, addr != end); +} - addr = next; - } +static void stage2_flush_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t end = addr + PAGE_SIZE * memslot->npages; + phys_addr_t next; + pgd_t *pgd; + + pgd = kvm->arch.pgd + kvm_pgd_index(addr); + do { + next = kvm_pgd_addr_end(addr, end); + stage2_flush_puds(kvm, pgd, addr, next); + } while (pgd++, addr = next, addr != end); +} + +/** + * stage2_flush_vm - Invalidate cache for pages mapped in stage 2 + * @kvm: The struct kvm pointer + * + * Go through the stage 2 page tables and invalidate any cache lines + * backing memory already mapped to the VM. + */ +void stage2_flush_vm(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) + stage2_flush_memslot(kvm, memslot); + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); } /** @@ -450,6 +556,71 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) unmap_range(kvm, kvm->arch.pgd, start, size); } +static void stage2_unmap_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + hva_t hva = memslot->userspace_addr; + phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t size = PAGE_SIZE * memslot->npages; + hva_t reg_end = hva + size; + + /* + * A memory region could potentially cover multiple VMAs, and any holes + * between them, so iterate over all of them to find out if we should + * unmap any of them. + * + * +--------------------------------------------+ + * +---------------+----------------+ +----------------+ + * | : VMA 1 | VMA 2 | | VMA 3 : | + * +---------------+----------------+ +----------------+ + * | memory region | + * +--------------------------------------------+ + */ + do { + struct vm_area_struct *vma = find_vma(current->mm, hva); + hva_t vm_start, vm_end; + + if (!vma || vma->vm_start >= reg_end) + break; + + /* + * Take the intersection of this VMA with the memory region + */ + vm_start = max(hva, vma->vm_start); + vm_end = min(reg_end, vma->vm_end); + + if (!(vma->vm_flags & VM_PFNMAP)) { + gpa_t gpa = addr + (vm_start - memslot->userspace_addr); + unmap_stage2_range(kvm, gpa, vm_end - vm_start); + } + hva = vm_end; + } while (hva < reg_end); +} + +/** + * stage2_unmap_vm - Unmap Stage-2 RAM mappings + * @kvm: The struct kvm pointer + * + * Go through the memregions and unmap any reguler RAM + * backing memory already mapped to the VM. + */ +void stage2_unmap_vm(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) + stage2_unmap_memslot(kvm, memslot); + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); +} + /** * kvm_free_stage2_pgd - free all stage-2 tables * @kvm: The KVM struct pointer for the VM. @@ -478,7 +649,7 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache pud_t *pud; pmd_t *pmd; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); pud = pud_offset(pgd, addr); if (pud_none(*pud)) { if (!cache) @@ -641,6 +812,19 @@ static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap) return false; } +static bool kvm_is_write_fault(struct kvm_vcpu *vcpu) +{ + if (kvm_vcpu_trap_is_iabt(vcpu)) + return false; + + return kvm_vcpu_dabt_iswrite(vcpu); +} + +static bool kvm_is_device_pfn(unsigned long pfn) +{ + return !pfn_valid(pfn); +} + static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_memory_slot *memslot, unsigned long fault_status) @@ -654,8 +838,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; struct vm_area_struct *vma; pfn_t pfn; + pgprot_t mem_type = PAGE_S2; - write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu)); + write_fault = kvm_is_write_fault(vcpu); if (fault_status == FSC_PERM && !write_fault) { kvm_err("Unexpected L2 read permission error\n"); return -EFAULT; @@ -664,6 +849,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, /* Let's check if we will get back a huge page backed by hugetlbfs */ down_read(¤t->mm->mmap_sem); vma = find_vma_intersection(current->mm, hva, hva + 1); + if (unlikely(!vma)) { + kvm_err("Failed to find VMA for hva 0x%lx\n", hva); + up_read(¤t->mm->mmap_sem); + return -EFAULT; + } + if (is_vm_hugetlb_page(vma)) { hugetlb = true; gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT; @@ -704,6 +895,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (is_error_pfn(pfn)) return -EFAULT; + if (kvm_is_device_pfn(pfn)) + mem_type = PAGE_S2_DEVICE; + spin_lock(&kvm->mmu_lock); if (mmu_notifier_retry(kvm, mmu_seq)) goto out_unlock; @@ -711,22 +905,23 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa); if (hugetlb) { - pmd_t new_pmd = pfn_pmd(pfn, PAGE_S2); + pmd_t new_pmd = pfn_pmd(pfn, mem_type); new_pmd = pmd_mkhuge(new_pmd); if (writable) { kvm_set_s2pmd_writable(&new_pmd); kvm_set_pfn_dirty(pfn); } - coherent_icache_guest_page(kvm, hva & PMD_MASK, PMD_SIZE); + coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE); ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); } else { - pte_t new_pte = pfn_pte(pfn, PAGE_S2); + pte_t new_pte = pfn_pte(pfn, mem_type); if (writable) { kvm_set_s2pte_writable(&new_pte); kvm_set_pfn_dirty(pfn); } - coherent_icache_guest_page(kvm, hva, PAGE_SIZE); - ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, false); + coherent_cache_guest_page(vcpu, hva, PAGE_SIZE); + ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, + pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE)); } @@ -802,6 +997,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) memslot = gfn_to_memslot(vcpu->kvm, gfn); + /* Userspace should not be able to register out-of-bounds IPAs */ + VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE); + ret = user_mem_abort(vcpu, fault_ipa, memslot, fault_status); if (ret == 0) ret = 1; @@ -1006,3 +1204,57 @@ out: free_hyp_pgds(); return err; } + +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + enum kvm_mr_change change) +{ + gpa_t gpa = old->base_gfn << PAGE_SHIFT; + phys_addr_t size = old->npages << PAGE_SHIFT; + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { + spin_lock(&kvm->mmu_lock); + unmap_stage2_range(kvm, gpa, size); + spin_unlock(&kvm->mmu_lock); + } +} + +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) +{ + /* + * Prevent userspace from creating a memory region outside of the IPA + * space addressable by the KVM guest IPA space. + */ + if (memslot->base_gfn + memslot->npages >= + (KVM_PHYS_SIZE >> PAGE_SHIFT)) + return -EFAULT; + + return 0; +} + +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) +{ +} + +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) +{ + return 0; +} + +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + +void kvm_arch_flush_shadow_all(struct kvm *kvm) +{ +} + +void kvm_arch_flush_shadow_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ +} diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c index 034529d..d66f102 100644 --- a/arch/arm/mach-at91/clock.c +++ b/arch/arm/mach-at91/clock.c @@ -962,6 +962,7 @@ static int __init at91_clock_reset(void) } at91_pmc_write(AT91_PMC_SCDR, scdr); + at91_pmc_write(AT91_PMC_PCDR, pcdr); if (cpu_is_sama5d3()) at91_pmc_write(AT91_PMC_PCDR1, pcdr1); diff --git a/arch/arm/mach-at91/pm.h b/arch/arm/mach-at91/pm.h index c5101dc..1d4df3b 100644 --- a/arch/arm/mach-at91/pm.h +++ b/arch/arm/mach-at91/pm.h @@ -45,7 +45,7 @@ static inline void at91rm9200_standby(void) " mcr p15, 0, %0, c7, c0, 4\n\t" " str %5, [%1, %2]" : - : "r" (0), "r" (AT91_BASE_SYS), "r" (AT91RM9200_SDRAMC_LPR), + : "r" (0), "r" (at91_ramc_base[0]), "r" (AT91RM9200_SDRAMC_LPR), "r" (1), "r" (AT91RM9200_SDRAMC_SRR), "r" (lpr)); } diff --git a/arch/arm/mach-dove/board-dt.c b/arch/arm/mach-dove/board-dt.c index 49fa9ab..7a7a09a5 100644 --- a/arch/arm/mach-dove/board-dt.c +++ b/arch/arm/mach-dove/board-dt.c @@ -26,7 +26,7 @@ static void __init dove_dt_init(void) #ifdef CONFIG_CACHE_TAUROS2 tauros2_init(0); #endif - BUG_ON(mvebu_mbus_dt_init()); + BUG_ON(mvebu_mbus_dt_init(false)); of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); } diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index 3c27907..fdabccd 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -283,8 +283,8 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node) post_div_table[1].div = 1; post_div_table[2].div = 1; video_div_table[1].div = 1; - video_div_table[2].div = 1; - }; + video_div_table[3].div = 1; + } /* type name parent_name base div_mask */ clk[pll1_sys] = imx_clk_pllv3(IMX_PLLV3_SYS, "pll1_sys", "osc", base, 0x7f, false); @@ -536,7 +536,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node) clk[gpmi_io] = imx_clk_gate2("gpmi_io", "enfc", base + 0x78, 28); clk[gpmi_apb] = imx_clk_gate2("gpmi_apb", "usdhc3", base + 0x78, 30); clk[rom] = imx_clk_gate2("rom", "ahb", base + 0x7c, 0); - clk[sata] = imx_clk_gate2("sata", "ipg", base + 0x7c, 4); + clk[sata] = imx_clk_gate2("sata", "ahb", base + 0x7c, 4); clk[sdma] = imx_clk_gate2("sdma", "ahb", base + 0x7c, 6); clk[spba] = imx_clk_gate2("spba", "ipg", base + 0x7c, 12); clk[spdif] = imx_clk_gate2("spdif", "spdif_podf", base + 0x7c, 14); diff --git a/arch/arm/mach-kirkwood/board-dt.c b/arch/arm/mach-kirkwood/board-dt.c index 7818815..79e629d 100644 --- a/arch/arm/mach-kirkwood/board-dt.c +++ b/arch/arm/mach-kirkwood/board-dt.c @@ -116,7 +116,7 @@ static void __init kirkwood_dt_init(void) */ writel(readl(CPU_CONFIG) & ~CPU_CONFIG_ERROR_PROP, CPU_CONFIG); - BUG_ON(mvebu_mbus_dt_init()); + BUG_ON(mvebu_mbus_dt_init(false)); kirkwood_l2_init(); diff --git a/arch/arm/mach-mvebu/armada-370-xp.c b/arch/arm/mach-mvebu/armada-370-xp.c index f6c9d1d..79c3766 100644 --- a/arch/arm/mach-mvebu/armada-370-xp.c +++ b/arch/arm/mach-mvebu/armada-370-xp.c @@ -41,7 +41,7 @@ static void __init armada_370_xp_timer_and_clk_init(void) of_clk_init(NULL); clocksource_of_init(); coherency_init(); - BUG_ON(mvebu_mbus_dt_init()); + BUG_ON(mvebu_mbus_dt_init(coherency_available())); #ifdef CONFIG_CACHE_L2X0 l2x0_of_init(0, ~0UL); #endif diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c index 4e9d581..49bad4d 100644 --- a/arch/arm/mach-mvebu/coherency.c +++ b/arch/arm/mach-mvebu/coherency.c @@ -121,10 +121,47 @@ static struct notifier_block mvebu_hwcc_platform_nb = { .notifier_call = mvebu_hwcc_platform_notifier, }; +/* + * Keep track of whether we have IO hardware coherency enabled or not. + * On Armada 370's we will not be using it for example. We need to make + * that available [through coherency_available()] so the mbus controller + * doesn't enable the IO coherency bit in the attribute bits of the + * chip selects. + */ +static int coherency_enabled; + +int coherency_available(void) +{ + return coherency_enabled; +} + int __init coherency_init(void) { struct device_node *np; + /* + * The coherency fabric is needed: + * - For coherency between processors on Armada XP, so only + * when SMP is enabled. + * - For coherency between the processor and I/O devices, but + * this coherency requires many pre-requisites (write + * allocate cache policy, shareable pages, SMP bit set) that + * are only meant in SMP situations. + * + * Note that this means that on Armada 370, there is currently + * no way to use hardware I/O coherency, because even when + * CONFIG_SMP is enabled, is_smp() returns false due to the + * Armada 370 being a single-core processor. To lift this + * limitation, we would have to find a way to make the cache + * policy set to write-allocate (on all Armada SoCs), and to + * set the shareable attribute in page tables (on all Armada + * SoCs except the Armada 370). Unfortunately, such decisions + * are taken very early in the kernel boot process, at a point + * where we don't know yet on which SoC we are running. + */ + if (!is_smp()) + return 0; + np = of_find_matching_node(NULL, of_coherency_table); if (np) { struct resource res; @@ -141,6 +178,7 @@ int __init coherency_init(void) coherency_base = of_iomap(np, 0); coherency_cpu_base = of_iomap(np, 1); set_cpu_coherent(cpu_logical_map(smp_processor_id()), 0); + coherency_enabled = 1; of_node_put(np); } @@ -151,6 +189,9 @@ static int __init coherency_late_init(void) { struct device_node *np; + if (!is_smp()) + return 0; + np = of_find_matching_node(NULL, of_coherency_table); if (np) { bus_register_notifier(&platform_bus_type, diff --git a/arch/arm/mach-mvebu/coherency.h b/arch/arm/mach-mvebu/coherency.h index 760226c..63e18c6 100644 --- a/arch/arm/mach-mvebu/coherency.h +++ b/arch/arm/mach-mvebu/coherency.h @@ -17,6 +17,7 @@ extern unsigned long coherency_phys_base; int set_cpu_coherent(unsigned int cpu_id, int smp_group_id); +int coherency_available(void); int coherency_init(void); #endif /* __MACH_370_XP_COHERENCY_H */ diff --git a/arch/arm/mach-omap2/clockdomains7xx_data.c b/arch/arm/mach-omap2/clockdomains7xx_data.c index 57d5df0..7581e03 100644 --- a/arch/arm/mach-omap2/clockdomains7xx_data.c +++ b/arch/arm/mach-omap2/clockdomains7xx_data.c @@ -331,7 +331,7 @@ static struct clockdomain l4per2_7xx_clkdm = { .dep_bit = DRA7XX_L4PER2_STATDEP_SHIFT, .wkdep_srcs = l4per2_wkup_sleep_deps, .sleepdep_srcs = l4per2_wkup_sleep_deps, - .flags = CLKDM_CAN_HWSUP_SWSUP, + .flags = CLKDM_CAN_SWSUP, }; static struct clockdomain mpu0_7xx_clkdm = { diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c index 44bb4d5..89cde07 100644 --- a/arch/arm/mach-omap2/control.c +++ b/arch/arm/mach-omap2/control.c @@ -314,7 +314,8 @@ void omap3_save_scratchpad_contents(void) scratchpad_contents.public_restore_ptr = virt_to_phys(omap3_restore_3630); else if (omap_rev() != OMAP3430_REV_ES3_0 && - omap_rev() != OMAP3430_REV_ES3_1) + omap_rev() != OMAP3430_REV_ES3_1 && + omap_rev() != OMAP3430_REV_ES3_1_2) scratchpad_contents.public_restore_ptr = virt_to_phys(omap3_restore); else diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 66c60fe..399af1e 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -2185,6 +2185,8 @@ static int _enable(struct omap_hwmod *oh) oh->mux->pads_dynamic))) { omap_hwmod_mux(oh->mux, _HWMOD_STATE_ENABLED); _reconfigure_io_chain(); + } else if (oh->flags & HWMOD_FORCE_MSTANDBY) { + _reconfigure_io_chain(); } _add_initiator_dep(oh, mpu_oh); @@ -2291,6 +2293,8 @@ static int _idle(struct omap_hwmod *oh) if (oh->mux && oh->mux->pads_dynamic) { omap_hwmod_mux(oh->mux, _HWMOD_STATE_IDLE); _reconfigure_io_chain(); + } else if (oh->flags & HWMOD_FORCE_MSTANDBY) { + _reconfigure_io_chain(); } oh->_state = _HWMOD_STATE_IDLE; @@ -2448,6 +2452,9 @@ static int of_dev_hwmod_lookup(struct device_node *np, * registers. This address is needed early so the OCP registers that * are part of the device's address space can be ioremapped properly. * + * If SYSC access is not needed, the registers will not be remapped + * and non-availability of MPU access is not treated as an error. + * * Returns 0 on success, -EINVAL if an invalid hwmod is passed, and * -ENXIO on absent or invalid register target address space. */ @@ -2462,6 +2469,11 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data, _save_mpu_port_index(oh); + /* if we don't need sysc access we don't need to ioremap */ + if (!oh->class->sysc) + return 0; + + /* we can't continue without MPU PORT if we need sysc access */ if (oh->_int_flags & _HWMOD_NO_MPU_PORT) return -ENXIO; @@ -2471,8 +2483,10 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data, oh->name); /* Extract the IO space from device tree blob */ - if (!np) + if (!np) { + pr_err("omap_hwmod: %s: no dt node\n", oh->name); return -ENXIO; + } va_start = of_iomap(np, index + oh->mpu_rt_idx); } else { @@ -2531,13 +2545,11 @@ static int __init _init(struct omap_hwmod *oh, void *data) oh->name, np->name); } - if (oh->class->sysc) { - r = _init_mpu_rt_base(oh, NULL, index, np); - if (r < 0) { - WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n", - oh->name); - return 0; - } + r = _init_mpu_rt_base(oh, NULL, index, np); + if (r < 0) { + WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n", + oh->name); + return 0; } r = _init_clocks(oh, NULL); @@ -3345,6 +3357,9 @@ int __init omap_hwmod_register_links(struct omap_hwmod_ocp_if **ois) if (!ois) return 0; + if (ois[0] == NULL) /* Empty list */ + return 0; + if (!linkspace) { if (_alloc_linkspace(ois)) { pr_err("omap_hwmod: could not allocate link space\n"); diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c index 810c205..d3ac4c6 100644 --- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c @@ -35,6 +35,7 @@ #include "i2c.h" #include "mmc.h" #include "wd_timer.h" +#include "soc.h" /* Base offset for all DRA7XX interrupts external to MPUSS */ #define DRA7XX_IRQ_GIC_START 32 @@ -1668,7 +1669,7 @@ static struct omap_hwmod dra7xx_uart3_hwmod = { .class = &dra7xx_uart_hwmod_class, .clkdm_name = "l4per_clkdm", .main_clk = "uart3_gfclk_mux", - .flags = HWMOD_SWSUP_SIDLE_ACT, + .flags = HWMOD_SWSUP_SIDLE_ACT | DEBUG_OMAP4UART3_FLAGS, .prcm = { .omap4 = { .clkctrl_offs = DRA7XX_CM_L4PER_UART3_CLKCTRL_OFFSET, @@ -2707,7 +2708,6 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = { &dra7xx_l4_per3__usb_otg_ss1, &dra7xx_l4_per3__usb_otg_ss2, &dra7xx_l4_per3__usb_otg_ss3, - &dra7xx_l4_per3__usb_otg_ss4, &dra7xx_l3_main_1__vcp1, &dra7xx_l4_per2__vcp1, &dra7xx_l3_main_1__vcp2, @@ -2716,8 +2716,26 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = { NULL, }; +static struct omap_hwmod_ocp_if *dra74x_hwmod_ocp_ifs[] __initdata = { + &dra7xx_l4_per3__usb_otg_ss4, + NULL, +}; + +static struct omap_hwmod_ocp_if *dra72x_hwmod_ocp_ifs[] __initdata = { + NULL, +}; + int __init dra7xx_hwmod_init(void) { + int ret; + omap_hwmod_init(); - return omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs); + ret = omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs); + + if (!ret && soc_is_dra74x()) + return omap_hwmod_register_links(dra74x_hwmod_ocp_ifs); + else if (!ret && soc_is_dra72x()) + return omap_hwmod_register_links(dra72x_hwmod_ocp_ifs); + + return ret; } diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c index eefb30c..2b9cff9 100644 --- a/arch/arm/mach-omap2/pm44xx.c +++ b/arch/arm/mach-omap2/pm44xx.c @@ -148,26 +148,6 @@ static inline int omap4_init_static_deps(void) struct clockdomain *ducati_clkdm, *l3_2_clkdm; int ret = 0; - if (omap_rev() == OMAP4430_REV_ES1_0) { - WARN(1, "Power Management not supported on OMAP4430 ES1.0\n"); - return -ENODEV; - } - - pr_err("Power Management for TI OMAP4.\n"); - /* - * OMAP4 chip PM currently works only with certain (newer) - * versions of bootloaders. This is due to missing code in the - * kernel to properly reset and initialize some devices. - * http://www.spinics.net/lists/arm-kernel/msg218641.html - */ - pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n"); - - ret = pwrdm_for_each(pwrdms_setup, NULL); - if (ret) { - pr_err("Failed to setup powerdomains\n"); - return ret; - } - /* * The dynamic dependency between MPUSS -> MEMIF and * MPUSS -> L4_PER/L3_* and DUCATI -> L3_* doesn't work as @@ -231,6 +211,15 @@ int __init omap4_pm_init(void) pr_info("Power Management for TI OMAP4+ devices.\n"); + /* + * OMAP4 chip PM currently works only with certain (newer) + * versions of bootloaders. This is due to missing code in the + * kernel to properly reset and initialize some devices. + * http://www.spinics.net/lists/arm-kernel/msg218641.html + */ + if (cpu_is_omap44xx()) + pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n"); + ret = pwrdm_for_each(pwrdms_setup, NULL); if (ret) { pr_err("Failed to setup powerdomains.\n"); diff --git a/arch/arm/mach-omap2/soc.h b/arch/arm/mach-omap2/soc.h index 076bd90..8a9be09 100644 --- a/arch/arm/mach-omap2/soc.h +++ b/arch/arm/mach-omap2/soc.h @@ -245,6 +245,8 @@ IS_AM_SUBCLASS(437x, 0x437) #define soc_is_omap54xx() 0 #define soc_is_omap543x() 0 #define soc_is_dra7xx() 0 +#define soc_is_dra74x() 0 +#define soc_is_dra72x() 0 #if defined(MULTI_OMAP2) # if defined(CONFIG_ARCH_OMAP2) @@ -393,7 +395,11 @@ IS_OMAP_TYPE(3430, 0x3430) #if defined(CONFIG_SOC_DRA7XX) #undef soc_is_dra7xx +#undef soc_is_dra74x +#undef soc_is_dra72x #define soc_is_dra7xx() (of_machine_is_compatible("ti,dra7")) +#define soc_is_dra74x() (of_machine_is_compatible("ti,dra74")) +#define soc_is_dra72x() (of_machine_is_compatible("ti,dra72")) #endif /* Various silicon revisions for omap2 */ diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index 74044aa..73d80b8 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -513,11 +513,11 @@ static void __init realtime_counter_init(void) rate = clk_get_rate(sys_clk); /* Numerator/denumerator values refer TRM Realtime Counter section */ switch (rate) { - case 1200000: + case 12000000: num = 64; den = 125; break; - case 1300000: + case 13000000: num = 768; den = 1625; break; @@ -529,11 +529,11 @@ static void __init realtime_counter_init(void) num = 192; den = 625; break; - case 2600000: + case 26000000: num = 384; den = 1625; break; - case 2700000: + case 27000000: num = 256; den = 1125; break; diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c index f162f1b..82fd9dd 100644 --- a/arch/arm/mach-pxa/corgi.c +++ b/arch/arm/mach-pxa/corgi.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -711,6 +712,8 @@ static void __init corgi_init(void) sharpsl_nand_partitions[1].size = 53 * 1024 * 1024; platform_add_devices(devices, ARRAY_SIZE(devices)); + + regulator_has_full_constraints(); } static void __init fixup_corgi(struct tag *tags, char **cmdline, diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c index a7c30eb..007fd8a 100644 --- a/arch/arm/mach-pxa/hx4700.c +++ b/arch/arm/mach-pxa/hx4700.c @@ -892,6 +892,8 @@ static void __init hx4700_init(void) mdelay(10); gpio_set_value(GPIO71_HX4700_ASIC3_nRESET, 1); mdelay(10); + + regulator_has_full_constraints(); } MACHINE_START(H4700, "HP iPAQ HX4700") diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c index aedf053..b4fff29 100644 --- a/arch/arm/mach-pxa/poodle.c +++ b/arch/arm/mach-pxa/poodle.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -454,6 +455,7 @@ static void __init poodle_init(void) pxa_set_i2c_info(NULL); i2c_register_board_info(0, ARRAY_AND_SIZE(poodle_i2c_devices)); poodle_init_spi(); + regulator_has_full_constraints(); } static void __init fixup_poodle(struct tag *tags, char **cmdline, diff --git a/arch/arm/mach-realview/include/mach/memory.h b/arch/arm/mach-realview/include/mach/memory.h index 2022e09..db09170 100644 --- a/arch/arm/mach-realview/include/mach/memory.h +++ b/arch/arm/mach-realview/include/mach/memory.h @@ -56,6 +56,8 @@ #define PAGE_OFFSET1 (PAGE_OFFSET + 0x10000000) #define PAGE_OFFSET2 (PAGE_OFFSET + 0x30000000) +#define PHYS_OFFSET PLAT_PHYS_OFFSET + #define __phys_to_virt(phys) \ ((phys) >= 0x80000000 ? (phys) - 0x80000000 + PAGE_OFFSET2 : \ (phys) >= 0x20000000 ? (phys) - 0x20000000 + PAGE_OFFSET1 : \ diff --git a/arch/arm/mach-s3c64xx/crag6410.h b/arch/arm/mach-s3c64xx/crag6410.h index 7bc6668..dcbe17f 100644 --- a/arch/arm/mach-s3c64xx/crag6410.h +++ b/arch/arm/mach-s3c64xx/crag6410.h @@ -14,6 +14,7 @@ #include #define GLENFARCLAS_PMIC_IRQ_BASE IRQ_BOARD_START +#define BANFF_PMIC_IRQ_BASE (IRQ_BOARD_START + 64) #define PCA935X_GPIO_BASE GPIO_BOARD_START #define CODEC_GPIO_BASE (GPIO_BOARD_START + 8) diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c index 3df3c37..66b95c4 100644 --- a/arch/arm/mach-s3c64xx/mach-crag6410.c +++ b/arch/arm/mach-s3c64xx/mach-crag6410.c @@ -555,6 +555,7 @@ static struct wm831x_touch_pdata touch_pdata = { static struct wm831x_pdata crag_pmic_pdata = { .wm831x_num = 1, + .irq_base = BANFF_PMIC_IRQ_BASE, .gpio_base = BANFF_PMIC_GPIO_BASE, .soft_shutdown = true, diff --git a/arch/arm/mach-sa1100/pm.c b/arch/arm/mach-sa1100/pm.c index 6645d1e..34853d5 100644 --- a/arch/arm/mach-sa1100/pm.c +++ b/arch/arm/mach-sa1100/pm.c @@ -81,6 +81,7 @@ static int sa11x0_pm_enter(suspend_state_t state) /* * Ensure not to come back here if it wasn't intended */ + RCSR = RCSR_SMR; PSPR = 0; /* diff --git a/arch/arm/mach-shmobile/setup-sh73a0.c b/arch/arm/mach-shmobile/setup-sh73a0.c index f74ab53..2b73c8a 100644 --- a/arch/arm/mach-shmobile/setup-sh73a0.c +++ b/arch/arm/mach-shmobile/setup-sh73a0.c @@ -617,6 +617,7 @@ static struct platform_device ipmmu_device = { static struct renesas_intc_irqpin_config irqpin0_platform_data = { .irq_base = irq_pin(0), /* IRQ0 -> IRQ7 */ + .control_parent = true, }; static struct resource irqpin0_resources[] = { @@ -678,6 +679,7 @@ static struct platform_device irqpin1_device = { static struct renesas_intc_irqpin_config irqpin2_platform_data = { .irq_base = irq_pin(16), /* IRQ16 -> IRQ23 */ + .control_parent = true, }; static struct resource irqpin2_resources[] = { @@ -708,6 +710,7 @@ static struct platform_device irqpin2_device = { static struct renesas_intc_irqpin_config irqpin3_platform_data = { .irq_base = irq_pin(24), /* IRQ24 -> IRQ31 */ + .control_parent = true, }; static struct resource irqpin3_resources[] = { diff --git a/arch/arm/mach-sunxi/Makefile b/arch/arm/mach-sunxi/Makefile index d939720..27b168f 100644 --- a/arch/arm/mach-sunxi/Makefile +++ b/arch/arm/mach-sunxi/Makefile @@ -1,2 +1,2 @@ obj-$(CONFIG_ARCH_SUNXI) += sunxi.o -obj-$(CONFIG_SMP) += platsmp.o headsmp.o +obj-$(CONFIG_SMP) += platsmp.o diff --git a/arch/arm/mach-sunxi/headsmp.S b/arch/arm/mach-sunxi/headsmp.S deleted file mode 100644 index a10d494..0000000 --- a/arch/arm/mach-sunxi/headsmp.S +++ /dev/null @@ -1,9 +0,0 @@ -#include -#include - - .section ".text.head", "ax" - -ENTRY(sun6i_secondary_startup) - msr cpsr_fsxc, #0xd3 - b secondary_startup -ENDPROC(sun6i_secondary_startup) diff --git a/arch/arm/mach-sunxi/platsmp.c b/arch/arm/mach-sunxi/platsmp.c index 7b141d8..0c7dbce 100644 --- a/arch/arm/mach-sunxi/platsmp.c +++ b/arch/arm/mach-sunxi/platsmp.c @@ -82,7 +82,7 @@ static int sun6i_smp_boot_secondary(unsigned int cpu, spin_lock(&cpu_lock); /* Set CPU boot address */ - writel(virt_to_phys(sun6i_secondary_startup), + writel(virt_to_phys(secondary_startup), cpucfg_membase + CPUCFG_PRIVATE0_REG); /* Assert the CPU core in reset */ diff --git a/arch/arm/mach-tegra/reset-handler.S b/arch/arm/mach-tegra/reset-handler.S index 578d4d1..6448324 100644 --- a/arch/arm/mach-tegra/reset-handler.S +++ b/arch/arm/mach-tegra/reset-handler.S @@ -50,6 +50,7 @@ ENTRY(tegra_resume) THUMB( it ne ) bne cpu_resume @ no + tegra_get_soc_id TEGRA_APB_MISC_BASE, r6 /* Are we on Tegra20? */ cmp r6, #TEGRA20 beq 1f @ Yes diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 118d691..57b9650 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -798,6 +798,7 @@ config NEED_KUSER_HELPERS config KUSER_HELPERS bool "Enable kuser helpers in vector page" if !NEED_KUSER_HELPERS + depends on MMU default y help Warning: disabling this option may break user programs. diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index 3815a82..8c48c5c 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -17,12 +17,6 @@ */ .align 5 ENTRY(v6_early_abort) -#ifdef CONFIG_CPU_V6 - sub r1, sp, #4 @ Get unused stack location - strex r0, r1, [r1] @ Clear the exclusive monitor -#elif defined(CONFIG_CPU_32v6K) - clrex -#endif mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR /* diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S index 7033752..4812ad0 100644 --- a/arch/arm/mm/abort-ev7.S +++ b/arch/arm/mm/abort-ev7.S @@ -13,12 +13,6 @@ */ .align 5 ENTRY(v7_early_abort) - /* - * The effect of data aborts on on the exclusive access monitor are - * UNPREDICTABLE. Do a CLREX to clear the state - */ - clrex - mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 9240364..d301662 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -40,6 +40,7 @@ * This code is not portable to processors with late data abort handling. */ #define CODING_BITS(i) (i & 0x0e000000) +#define COND_BITS(i) (i & 0xf0000000) #define LDST_I_BIT(i) (i & (1 << 26)) /* Immediate constant */ #define LDST_P_BIT(i) (i & (1 << 24)) /* Preindex */ @@ -817,6 +818,8 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) break; case 0x04000000: /* ldr or str immediate */ + if (COND_BITS(instr) == 0xf0000000) /* NEON VLDn, VSTn */ + goto bad; offset.un = OFFSET_BITS(instr); handler = do_alignment_ldrstr; break; diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 6eb97b3..4370933 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -144,21 +144,17 @@ static void flush_context(unsigned int cpu) /* Update the list of reserved ASIDs and the ASID bitmap. */ bitmap_clear(asid_map, 0, NUM_USER_ASIDS); for_each_possible_cpu(i) { - if (i == cpu) { - asid = 0; - } else { - asid = atomic64_xchg(&per_cpu(active_asids, i), 0); - /* - * If this CPU has already been through a - * rollover, but hasn't run another task in - * the meantime, we must preserve its reserved - * ASID, as this is the only trace we have of - * the process it is still running. - */ - if (asid == 0) - asid = per_cpu(reserved_asids, i); - __set_bit(asid & ~ASID_MASK, asid_map); - } + asid = atomic64_xchg(&per_cpu(active_asids, i), 0); + /* + * If this CPU has already been through a + * rollover, but hasn't run another task in + * the meantime, we must preserve its reserved + * ASID, as this is the only trace we have of + * the process it is still running. + */ + if (asid == 0) + asid = per_cpu(reserved_asids, i); + __set_bit(asid & ~ASID_MASK, asid_map); per_cpu(reserved_asids, i) = asid; } diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index a810425..fae192b 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -465,12 +465,21 @@ void __init dma_contiguous_remap(void) map.type = MT_MEMORY_DMA_READY; /* - * Clear previous low-memory mapping + * Clear previous low-memory mapping to ensure that the + * TLB does not see any conflicting entries, then flush + * the TLB of the old entries before creating new mappings. + * + * This ensures that any speculatively loaded TLB entries + * (even though they may be rare) can not cause any problems, + * and ensures that this code is architecturally compliant. */ for (addr = __phys_to_virt(start); addr < __phys_to_virt(end); addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); + flush_tlb_kernel_range(__phys_to_virt(start), + __phys_to_virt(end)); + iotable_init(&map, 1); } } diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c index 8e0e52e..d7a0ee8 100644 --- a/arch/arm/mm/idmap.c +++ b/arch/arm/mm/idmap.c @@ -25,6 +25,13 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end, pr_warning("Failed to allocate identity pmd.\n"); return; } + /* + * Copy the original PMD to ensure that the PMD entries for + * the kernel image are preserved. + */ + if (!pud_none(*pud)) + memcpy(pmd, pmd_offset(pud, 0), + PTRS_PER_PMD * sizeof(pmd_t)); pud_populate(&init_mm, pud, pmd); pmd += pmd_index(addr); } else diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index b68c6b2..f15c22e 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1436,8 +1436,8 @@ void __init early_paging_init(const struct machine_desc *mdesc, return; /* remap kernel code and data */ - map_start = init_mm.start_code; - map_end = init_mm.brk; + map_start = init_mm.start_code & PMD_MASK; + map_end = ALIGN(init_mm.brk, PMD_SIZE); /* get a handle on things... */ pgd0 = pgd_offset_k(0); @@ -1472,7 +1472,7 @@ void __init early_paging_init(const struct machine_desc *mdesc, } /* remap pmds for kernel mapping */ - phys = __pa(map_start) & PMD_MASK; + phys = __pa(map_start); do { *pmdk++ = __pmd(phys | pmdprot); phys += PMD_SIZE; diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S index 22e3ad6..eb81123 100644 --- a/arch/arm/mm/proc-v7-3level.S +++ b/arch/arm/mm/proc-v7-3level.S @@ -86,8 +86,13 @@ ENTRY(cpu_v7_set_pte_ext) tst rh, #1 << (57 - 32) @ L_PTE_NONE bicne rl, #L_PTE_VALID bne 1f - tst rh, #1 << (55 - 32) @ L_PTE_DIRTY - orreq rl, #L_PTE_RDONLY + + eor ip, rh, #1 << (55 - 32) @ toggle L_PTE_DIRTY in temp reg to + @ test for !L_PTE_DIRTY || L_PTE_RDONLY + tst ip, #1 << (55 - 32) | 1 << (58 - 32) + orrne rl, #PTE_AP2 + biceq rl, #PTE_AP2 + 1: strd r2, r3, [r0] ALT_SMP(W(nop)) ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 158b875..bf7487d 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -211,7 +211,6 @@ __v7_pj4b_setup: /* Auxiliary Debug Modes Control 1 Register */ #define PJ4B_STATIC_BP (1 << 2) /* Enable Static BP */ #define PJ4B_INTER_PARITY (1 << 8) /* Disable Internal Parity Handling */ -#define PJ4B_BCK_OFF_STREX (1 << 5) /* Enable the back off of STREX instr */ #define PJ4B_CLEAN_LINE (1 << 16) /* Disable data transfer for clean line */ /* Auxiliary Debug Modes Control 2 Register */ @@ -234,7 +233,6 @@ __v7_pj4b_setup: /* Auxiliary Debug Modes Control 1 Register */ mrc p15, 1, r0, c15, c1, 1 orr r0, r0, #PJ4B_CLEAN_LINE - orr r0, r0, #PJ4B_BCK_OFF_STREX orr r0, r0, #PJ4B_INTER_PARITY bic r0, r0, #PJ4B_STATIC_BP mcr p15, 1, r0, c15, c1, 1 diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index d19b1cf..b34b95f 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -535,7 +535,7 @@ ENTRY(cpu_xscale_do_suspend) mrc p15, 0, r5, c15, c1, 0 @ CP access reg mrc p15, 0, r6, c13, c0, 0 @ PID mrc p15, 0, r7, c3, c0, 0 @ domain ID - mrc p15, 0, r8, c1, c1, 0 @ auxiliary control reg + mrc p15, 0, r8, c1, c0, 1 @ auxiliary control reg mrc p15, 0, r9, c1, c0, 0 @ control reg bic r4, r4, #2 @ clear frequency change bit stmia r0, {r4 - r9} @ store cp regs @@ -552,7 +552,7 @@ ENTRY(cpu_xscale_do_resume) mcr p15, 0, r6, c13, c0, 0 @ PID mcr p15, 0, r7, c3, c0, 0 @ domain ID mcr p15, 0, r1, c2, c0, 0 @ translation table base addr - mcr p15, 0, r8, c1, c1, 0 @ auxiliary control reg + mcr p15, 0, r8, c1, c0, 1 @ auxiliary control reg mov r0, r9 @ control register b cpu_resume_mmu ENDPROC(cpu_xscale_do_resume) diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 271b5e9..6adf591 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -449,10 +449,21 @@ static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx) return; } #endif - if (rm != ARM_R0) - emit(ARM_MOV_R(ARM_R0, rm), ctx); + + /* + * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4 + * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into + * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm + * before using it as a source for ARM_R1. + * + * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is + * ARM_R5 (r_X) so there is no particular register overlap + * issues. + */ if (rn != ARM_R1) emit(ARM_MOV_R(ARM_R1, rn), ctx); + if (rm != ARM_R0) + emit(ARM_MOV_R(ARM_R0, rm), ctx); ctx->seen |= SEEN_CALL; emit_mov_i(ARM_R3, (u32)jit_udiv, ctx); diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index 253e33b..56de5aa 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -37,8 +37,8 @@ typedef s32 compat_ssize_t; typedef s32 compat_time_t; typedef s32 compat_clock_t; typedef s32 compat_pid_t; -typedef u32 __compat_uid_t; -typedef u32 __compat_gid_t; +typedef u16 __compat_uid_t; +typedef u16 __compat_gid_t; typedef u16 __compat_uid16_t; typedef u16 __compat_gid16_t; typedef u32 __compat_uid32_t; diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index c404fb0..64bc6c6 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -77,6 +77,8 @@ static inline u32 __attribute_const__ read_cpuid_cachetype(void) return read_cpuid(CTR_EL0); } +void cpuinfo_store_cpu(void); + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index d064047..52b484b 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -79,7 +79,6 @@ static inline void decode_ctrl_reg(u32 reg, */ #define ARM_MAX_BRP 16 #define ARM_MAX_WRP 16 -#define ARM_MAX_HBP_SLOTS (ARM_MAX_BRP + ARM_MAX_WRP) /* Virtual debug register bases. */ #define AARCH64_DBG_REG_BVR 0 diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 024c461..0ad7351 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -30,6 +30,7 @@ #define COMPAT_HWCAP_IDIVA (1 << 17) #define COMPAT_HWCAP_IDIVT (1 << 18) #define COMPAT_HWCAP_IDIV (COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT) +#define COMPAT_HWCAP_LPAE (1 << 20) #define COMPAT_HWCAP_EVTSTRM (1 << 21) #define COMPAT_HWCAP2_AES (1 << 0) diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 0eb3986..ea68925 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -18,6 +18,7 @@ #ifndef __ARM64_KVM_ARM_H__ #define __ARM64_KVM_ARM_H__ +#include #include /* Hyp Configuration Register (HCR) bits */ @@ -62,6 +63,7 @@ * RW: 64bit by default, can be overriden for 32bit VMs * TAC: Trap ACTLR * TSC: Trap SMC + * TVM: Trap VM ops (until M+C set in SCTLR_EL1) * TSW: Trap cache operations by set/way * TWE: Trap WFE * TWI: Trap WFI @@ -74,7 +76,7 @@ * SWIO: Turn set/way invalidates into set/way clean+invalidate */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ - HCR_BSU_IS | HCR_FB | HCR_TAC | \ + HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \ HCR_AMO | HCR_IMO | HCR_FMO | \ HCR_SWIO | HCR_TIDCP | HCR_RW) #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF) @@ -121,6 +123,17 @@ #define VTCR_EL2_T0SZ_MASK 0x3f #define VTCR_EL2_T0SZ_40B 24 +/* + * We configure the Stage-2 page tables to always restrict the IPA space to be + * 40 bits wide (T0SZ = 24). Systems with a PARange smaller than 40 bits are + * not known to exist and will break with this configuration. + * + * Note that when using 4K pages, we concatenate two first level page tables + * together. + * + * The magic numbers used for VTTBR_X in this patch can be found in Tables + * D4-23 and D4-25 in ARM DDI 0487A.b. + */ #ifdef CONFIG_ARM64_64K_PAGES /* * Stage2 translation configuration: @@ -150,9 +163,9 @@ #endif #define VTTBR_BADDR_SHIFT (VTTBR_X - 1) -#define VTTBR_BADDR_MASK (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) -#define VTTBR_VMID_SHIFT (48LLU) -#define VTTBR_VMID_MASK (0xffLLU << VTTBR_VMID_SHIFT) +#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) +#define VTTBR_VMID_SHIFT (UL(48)) +#define VTTBR_VMID_MASK (UL(0xFF) << VTTBR_VMID_SHIFT) /* Hyp System Trap Register */ #define HSTR_EL2_TTEE (1 << 16) @@ -175,13 +188,13 @@ /* Exception Syndrome Register (ESR) bits */ #define ESR_EL2_EC_SHIFT (26) -#define ESR_EL2_EC (0x3fU << ESR_EL2_EC_SHIFT) -#define ESR_EL2_IL (1U << 25) +#define ESR_EL2_EC (UL(0x3f) << ESR_EL2_EC_SHIFT) +#define ESR_EL2_IL (UL(1) << 25) #define ESR_EL2_ISS (ESR_EL2_IL - 1) #define ESR_EL2_ISV_SHIFT (24) -#define ESR_EL2_ISV (1U << ESR_EL2_ISV_SHIFT) +#define ESR_EL2_ISV (UL(1) << ESR_EL2_ISV_SHIFT) #define ESR_EL2_SAS_SHIFT (22) -#define ESR_EL2_SAS (3U << ESR_EL2_SAS_SHIFT) +#define ESR_EL2_SAS (UL(3) << ESR_EL2_SAS_SHIFT) #define ESR_EL2_SSE (1 << 21) #define ESR_EL2_SRT_SHIFT (16) #define ESR_EL2_SRT_MASK (0x1f << ESR_EL2_SRT_SHIFT) @@ -195,16 +208,16 @@ #define ESR_EL2_FSC_TYPE (0x3c) #define ESR_EL2_CV_SHIFT (24) -#define ESR_EL2_CV (1U << ESR_EL2_CV_SHIFT) +#define ESR_EL2_CV (UL(1) << ESR_EL2_CV_SHIFT) #define ESR_EL2_COND_SHIFT (20) -#define ESR_EL2_COND (0xfU << ESR_EL2_COND_SHIFT) +#define ESR_EL2_COND (UL(0xf) << ESR_EL2_COND_SHIFT) #define FSC_FAULT (0x04) #define FSC_PERM (0x0c) /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ -#define HPFAR_MASK (~0xFUL) +#define HPFAR_MASK (~UL(0xf)) #define ESR_EL2_EC_UNKNOWN (0x00) #define ESR_EL2_EC_WFI (0x01) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index b25763b..9fcd54b 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -79,7 +79,8 @@ #define c13_TID_URW (TPIDR_EL0 * 2) /* Thread ID, User R/W */ #define c13_TID_URO (TPIDRRO_EL0 * 2)/* Thread ID, User R/O */ #define c13_TID_PRIV (TPIDR_EL1 * 2) /* Thread ID, Privileged */ -#define c10_AMAIR (AMAIR_EL1 * 2) /* Aux Memory Attr Indirection Reg */ +#define c10_AMAIR0 (AMAIR_EL1 * 2) /* Aux Memory Attr Indirection Reg */ +#define c10_AMAIR1 (c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */ #define c14_CNTKCTL (CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */ #define NR_CP15_REGS (NR_SYS_REGS * 2) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index dd8ecfc..91f33c2 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -38,6 +38,13 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) +{ + vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS; + if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) + vcpu->arch.hcr_el2 &= ~HCR_RW; +} + static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) { return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 0a1d697..3fb0946 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -42,7 +42,7 @@ #define KVM_VCPU_MAX_FEATURES 2 struct kvm_vcpu; -int kvm_target_cpu(void); +int __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); int kvm_arch_dev_ioctl_check_extension(long ext); @@ -177,7 +177,7 @@ static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) } struct kvm_vcpu *kvm_arm_get_running_vcpu(void); -struct kvm_vcpu __percpu **kvm_get_running_vcpus(void); +struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); u64 kvm_call_hyp(void *hypfn, ...); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 7f1f940..15a8a86 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -59,10 +59,9 @@ #define KERN_TO_HYP(kva) ((unsigned long)kva - PAGE_OFFSET + HYP_PAGE_OFFSET) /* - * Align KVM with the kernel's view of physical memory. Should be - * 40bit IPA, with PGD being 8kB aligned in the 4KB page configuration. + * We currently only support a 40bit IPA. */ -#define KVM_PHYS_SHIFT PHYS_MASK_SHIFT +#define KVM_PHYS_SHIFT (40) #define KVM_PHYS_SIZE (1UL << KVM_PHYS_SHIFT) #define KVM_PHYS_MASK (KVM_PHYS_SIZE - 1UL) @@ -70,11 +69,14 @@ #define PTRS_PER_S2_PGD (1 << (KVM_PHYS_SHIFT - PGDIR_SHIFT)) #define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t)) +#define kvm_pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1)) + int create_hyp_mappings(void *from, void *to); int create_hyp_io_mappings(void *from, void *to, phys_addr_t); void free_boot_hyp_pgd(void); void free_hyp_pgds(void); +void stage2_unmap_vm(struct kvm *kvm); int kvm_alloc_stage2_pgd(struct kvm *kvm); void kvm_free_stage2_pgd(struct kvm *kvm); int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, @@ -93,20 +95,6 @@ void kvm_clear_hyp_idmap(void); #define kvm_set_pte(ptep, pte) set_pte(ptep, pte) #define kvm_set_pmd(pmdp, pmd) set_pmd(pmdp, pmd) -static inline bool kvm_is_write_fault(unsigned long esr) -{ - unsigned long esr_ec = esr >> ESR_EL2_EC_SHIFT; - - if (esr_ec == ESR_EL2_EC_IABT) - return false; - - if ((esr & ESR_EL2_ISV) && !(esr & ESR_EL2_WNR)) - return false; - - return true; -} - -static inline void kvm_clean_dcache_area(void *addr, size_t size) {} static inline void kvm_clean_pgd(pgd_t *pgd) {} static inline void kvm_clean_pmd_entry(pmd_t *pmd) {} static inline void kvm_clean_pte(pte_t *pte) {} @@ -122,11 +110,40 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd) pmd_val(*pmd) |= PMD_S2_RDWR; } +#define kvm_pgd_addr_end(addr, end) pgd_addr_end(addr, end) +#define kvm_pud_addr_end(addr, end) pud_addr_end(addr, end) +#define kvm_pmd_addr_end(addr, end) pmd_addr_end(addr, end) + +static inline bool kvm_page_empty(void *ptr) +{ + struct page *ptr_page = virt_to_page(ptr); + return page_count(ptr_page) == 1; +} + +#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep) +#ifndef CONFIG_ARM64_64K_PAGES +#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp) +#else +#define kvm_pmd_table_empty(pmdp) (0) +#endif +#define kvm_pud_table_empty(pudp) (0) + + struct kvm; -static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva, - unsigned long size) +#define kvm_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l)) + +static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) { + return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; +} + +static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, + unsigned long size) +{ + if (!vcpu_has_cache_enabled(vcpu)) + kvm_flush_dcache_to_poc((void *)hva, size); + if (!icache_is_aliasing()) { /* PIPT */ flush_icache_range(hva, hva + size); } else if (!icache_is_aivivt()) { /* non ASID-tagged VIVT */ @@ -135,8 +152,9 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva, } } -#define kvm_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l)) #define kvm_virt_to_phys(x) __virt_to_phys((unsigned long)(x)) +void stage2_flush_vm(struct kvm *kvm); + #endif /* __ASSEMBLY__ */ #endif /* __ARM64_KVM_MMU_H__ */ diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index a9eee33..101a42b 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -151,6 +151,15 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, { unsigned int cpu = smp_processor_id(); + /* + * init_mm.pgd does not contain any user mappings and it is always + * active for kernel addresses in TTBR1. Just set the reserved TTBR0. + */ + if (next == &init_mm) { + cpu_set_reserved_ttbr0(); + return; + } + if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) check_and_switch_context(next, tsk); } diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h index e9c149c..456d67c 100644 --- a/arch/arm64/include/asm/suspend.h +++ b/arch/arm64/include/asm/suspend.h @@ -21,6 +21,7 @@ struct sleep_save_sp { phys_addr_t save_ptr_stash_phys; }; +extern int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)); extern void cpu_resume(void); extern int cpu_suspend(unsigned long); diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 92f3683..565e26f 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -156,9 +156,10 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) * which ends with "dsb; isb" pair guaranteeing global * visibility. */ - atomic_set(&pp->cpu_count, -1); + /* Notify other processors with an additional increment. */ + atomic_inc(&pp->cpu_count); } else { - while (atomic_read(&pp->cpu_count) != -1) + while (atomic_read(&pp->cpu_count) <= num_online_cpus()) cpu_relax(); isb(); } diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 0f08dfd..dfa6e3e 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -97,19 +97,15 @@ static bool migrate_one_irq(struct irq_desc *desc) if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity)) return false; - if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) + if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { + affinity = cpu_online_mask; ret = true; + } - /* - * when using forced irq_set_affinity we must ensure that the cpu - * being offlined is not present in the affinity mask, it may be - * selected as the target CPU otherwise - */ - affinity = cpu_online_mask; c = irq_data_get_irq_chip(d); if (!c->irq_set_affinity) pr_debug("IRQ%u: unable to set affinity\n", d->irq); - else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret) + else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret) cpumask_copy(d->affinity, affinity); return ret; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index fc8a387..98861d3 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -188,9 +188,27 @@ void exit_thread(void) { } +static void tls_thread_flush(void) +{ + asm ("msr tpidr_el0, xzr"); + + if (is_compat_task()) { + current->thread.tp_value = 0; + + /* + * We need to ensure ordering between the shadow state and the + * hardware state, so that we don't corrupt the hardware state + * with a stale shadow state during context switch. + */ + barrier(); + asm ("msr tpidrro_el0, xzr"); + } +} + void flush_thread(void) { fpsimd_flush_thread(); + tls_thread_flush(); flush_ptrace_hw_breakpoint(current); } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 7c8e809..8ba6b0f 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -85,7 +85,8 @@ static void ptrace_hbptriggered(struct perf_event *bp, break; } } - for (i = ARM_MAX_BRP; i < ARM_MAX_HBP_SLOTS && !bp; ++i) { + + for (i = 0; i < ARM_MAX_WRP; ++i) { if (current->thread.debug.hbp_watch[i] == bp) { info.si_errno = -((i << 1) + 1); break; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index e633c5e..4bc8d27 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -67,13 +68,13 @@ EXPORT_SYMBOL_GPL(elf_hwcap); COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\ COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\ COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\ - COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV) + COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\ + COMPAT_HWCAP_LPAE) unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT; unsigned int compat_elf_hwcap2 __read_mostly; #endif static const char *cpu_name; -static const char *machine_name; phys_addr_t __fdt_pointer __initdata; /* @@ -193,6 +194,19 @@ static void __init smp_build_mpidr_hash(void) } #endif +struct cpuinfo_arm64 { + struct cpu cpu; + u32 reg_midr; +}; + +static DEFINE_PER_CPU(struct cpuinfo_arm64, cpu_data); + +void cpuinfo_store_cpu(void) +{ + struct cpuinfo_arm64 *info = this_cpu_ptr(&cpu_data); + info->reg_midr = read_cpuid_id(); +} + static void __init setup_processor(void) { struct cpu_info *cpu_info; @@ -213,6 +227,8 @@ static void __init setup_processor(void) sprintf(init_utsname()->machine, ELF_PLATFORM); elf_hwcap = 0; + cpuinfo_store_cpu(); + /* * ID_AA64ISAR0_EL1 contains 4-bit wide signed feature blocks. * The blocks we test below represent incremental functionality @@ -289,8 +305,6 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys) while (true) cpu_relax(); } - - machine_name = of_flat_dt_get_machine_name(); } /* @@ -395,14 +409,12 @@ static int __init arm64_device_init(void) } arch_initcall_sync(arm64_device_init); -static DEFINE_PER_CPU(struct cpu, cpu_data); - static int __init topology_init(void) { int i; for_each_possible_cpu(i) { - struct cpu *cpu = &per_cpu(cpu_data, i); + struct cpu *cpu = &per_cpu(cpu_data.cpu, i); cpu->hotpluggable = 1; register_cpu(cpu, i); } @@ -423,14 +435,41 @@ static const char *hwcap_str[] = { NULL }; +#ifdef CONFIG_COMPAT +static const char *compat_hwcap_str[] = { + "swp", + "half", + "thumb", + "26bit", + "fastmult", + "fpa", + "vfp", + "edsp", + "java", + "iwmmxt", + "crunch", + "thumbee", + "neon", + "vfpv3", + "vfpv3d16", + "tls", + "vfpv4", + "idiva", + "idivt", + "vfpd32", + "lpae", + "evtstrm" +}; +#endif /* CONFIG_COMPAT */ + static int c_show(struct seq_file *m, void *v) { - int i; - - seq_printf(m, "Processor\t: %s rev %d (%s)\n", - cpu_name, read_cpuid_id() & 15, ELF_PLATFORM); + int i, j; for_each_online_cpu(i) { + struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i); + u32 midr = cpuinfo->reg_midr; + /* * glibc reads /proc/cpuinfo to determine the number of * online processors, looking for lines beginning with @@ -439,24 +478,33 @@ static int c_show(struct seq_file *m, void *v) #ifdef CONFIG_SMP seq_printf(m, "processor\t: %d\n", i); #endif - } - - /* dump out the processor features */ - seq_puts(m, "Features\t: "); - - for (i = 0; hwcap_str[i]; i++) - if (elf_hwcap & (1 << i)) - seq_printf(m, "%s ", hwcap_str[i]); - seq_printf(m, "\nCPU implementer\t: 0x%02x\n", read_cpuid_id() >> 24); - seq_printf(m, "CPU architecture: AArch64\n"); - seq_printf(m, "CPU variant\t: 0x%x\n", (read_cpuid_id() >> 20) & 15); - seq_printf(m, "CPU part\t: 0x%03x\n", (read_cpuid_id() >> 4) & 0xfff); - seq_printf(m, "CPU revision\t: %d\n", read_cpuid_id() & 15); - - seq_puts(m, "\n"); + /* + * Dump out the common processor features in a single line. + * Userspace should read the hwcaps with getauxval(AT_HWCAP) + * rather than attempting to parse this, but there's a body of + * software which does already (at least for 32-bit). + */ + seq_puts(m, "Features\t:"); + if (personality(current->personality) == PER_LINUX32) { +#ifdef CONFIG_COMPAT + for (j = 0; compat_hwcap_str[j]; j++) + if (compat_elf_hwcap & (1 << j)) + seq_printf(m, " %s", compat_hwcap_str[j]); +#endif /* CONFIG_COMPAT */ + } else { + for (j = 0; hwcap_str[j]; j++) + if (elf_hwcap & (1 << j)) + seq_printf(m, " %s", hwcap_str[j]); + } + seq_puts(m, "\n"); - seq_printf(m, "Hardware\t: %s\n", machine_name); + seq_printf(m, "CPU implementer\t: 0x%02x\n", (midr >> 24)); + seq_printf(m, "CPU architecture: 8\n"); + seq_printf(m, "CPU variant\t: 0x%x\n", ((midr >> 20) & 0xf)); + seq_printf(m, "CPU part\t: 0x%03x\n", ((midr >> 4) & 0xfff)); + seq_printf(m, "CPU revision\t: %d\n\n", (midr & 0xf)); + } return 0; } diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index b3fc9f5..a966bac 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -151,8 +151,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) case __SI_TIMER: err |= __put_user(from->si_tid, &to->si_tid); err |= __put_user(from->si_overrun, &to->si_overrun); - err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr, - &to->si_ptr); + err |= __put_user(from->si_int, &to->si_int); break; case __SI_POLL: err |= __put_user(from->si_band, &to->si_band); @@ -166,7 +165,8 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) * Other callers might not initialize the si_lsb field, * so check explicitely for the right codes here. */ - if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO) + if (from->si_signo == SIGBUS && + (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)) err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); #endif break; @@ -181,7 +181,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) case __SI_MESGQ: /* But this is */ err |= __put_user(from->si_pid, &to->si_pid); err |= __put_user(from->si_uid, &to->si_uid); - err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr, &to->si_ptr); + err |= __put_user(from->si_int, &to->si_int); break; default: /* this is just in case for now ... */ err |= __put_user(from->si_pid, &to->si_pid); @@ -193,8 +193,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) { - memset(to, 0, sizeof *to); - if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) || copy_from_user(to->_sifields._pad, from->_sifields._pad, SI_PAD_SIZE)) diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index b192572..ede186c 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -49,28 +49,39 @@ orr \dst, \dst, \mask // dst|=(aff3>>rs3) .endm /* - * Save CPU state for a suspend. This saves callee registers, and allocates - * space on the kernel stack to save the CPU specific registers + some - * other data for resume. + * Save CPU state for a suspend and execute the suspend finisher. + * On success it will return 0 through cpu_resume - ie through a CPU + * soft/hard reboot from the reset vector. + * On failure it returns the suspend finisher return value or force + * -EOPNOTSUPP if the finisher erroneously returns 0 (the suspend finisher + * is not allowed to return, if it does this must be considered failure). + * It saves callee registers, and allocates space on the kernel stack + * to save the CPU specific registers + some other data for resume. * * x0 = suspend finisher argument + * x1 = suspend finisher function pointer */ -ENTRY(__cpu_suspend) +ENTRY(__cpu_suspend_enter) stp x29, lr, [sp, #-96]! stp x19, x20, [sp,#16] stp x21, x22, [sp,#32] stp x23, x24, [sp,#48] stp x25, x26, [sp,#64] stp x27, x28, [sp,#80] + /* + * Stash suspend finisher and its argument in x20 and x19 + */ + mov x19, x0 + mov x20, x1 mov x2, sp sub sp, sp, #CPU_SUSPEND_SZ // allocate cpu_suspend_ctx - mov x1, sp + mov x0, sp /* - * x1 now points to struct cpu_suspend_ctx allocated on the stack + * x0 now points to struct cpu_suspend_ctx allocated on the stack */ - str x2, [x1, #CPU_CTX_SP] - ldr x2, =sleep_save_sp - ldr x2, [x2, #SLEEP_SAVE_SP_VIRT] + str x2, [x0, #CPU_CTX_SP] + ldr x1, =sleep_save_sp + ldr x1, [x1, #SLEEP_SAVE_SP_VIRT] #ifdef CONFIG_SMP mrs x7, mpidr_el1 ldr x9, =mpidr_hash @@ -82,11 +93,21 @@ ENTRY(__cpu_suspend) ldp w3, w4, [x9, #MPIDR_HASH_SHIFTS] ldp w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)] compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10 - add x2, x2, x8, lsl #3 + add x1, x1, x8, lsl #3 #endif - bl __cpu_suspend_finisher + bl __cpu_suspend_save + /* + * Grab suspend finisher in x20 and its argument in x19 + */ + mov x0, x19 + mov x1, x20 + /* + * We are ready for power down, fire off the suspend finisher + * in x1, with argument in x0 + */ + blr x1 /* - * Never gets here, unless suspend fails. + * Never gets here, unless suspend finisher fails. * Successful cpu_suspend should return from cpu_resume, returning * through this code path is considered an error * If the return value is set to 0 force x0 = -EOPNOTSUPP @@ -103,7 +124,7 @@ ENTRY(__cpu_suspend) ldp x27, x28, [sp, #80] ldp x29, lr, [sp], #96 ret -ENDPROC(__cpu_suspend) +ENDPROC(__cpu_suspend_enter) .ltorg /* @@ -126,14 +147,12 @@ cpu_resume_after_mmu: ret ENDPROC(cpu_resume_after_mmu) - .data ENTRY(cpu_resume) bl el2_setup // if in EL2 drop to EL1 cleanly #ifdef CONFIG_SMP mrs x1, mpidr_el1 - adr x4, mpidr_hash_ptr - ldr x5, [x4] - add x8, x4, x5 // x8 = struct mpidr_hash phys address + adrp x8, mpidr_hash + add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address /* retrieve mpidr_hash members to compute the hash */ ldr x2, [x8, #MPIDR_HASH_MASK] ldp w3, w4, [x8, #MPIDR_HASH_SHIFTS] @@ -143,14 +162,15 @@ ENTRY(cpu_resume) #else mov x7, xzr #endif - adr x0, sleep_save_sp + adrp x0, sleep_save_sp + add x0, x0, #:lo12:sleep_save_sp ldr x0, [x0, #SLEEP_SAVE_SP_PHYS] ldr x0, [x0, x7, lsl #3] /* load sp from context */ ldr x2, [x0, #CPU_CTX_SP] - adr x1, sleep_idmap_phys + adrp x1, sleep_idmap_phys /* load physical address of identity map page table in x1 */ - ldr x1, [x1] + ldr x1, [x1, #:lo12:sleep_idmap_phys] mov sp, x2 /* * cpu_do_resume expects x0 to contain context physical address @@ -159,26 +179,3 @@ ENTRY(cpu_resume) bl cpu_do_resume // PC relative jump, MMU off b cpu_resume_mmu // Resume MMU, never returns ENDPROC(cpu_resume) - - .align 3 -mpidr_hash_ptr: - /* - * offset of mpidr_hash symbol from current location - * used to obtain run-time mpidr_hash address with MMU off - */ - .quad mpidr_hash - . -/* - * physical address of identity mapped page tables - */ - .type sleep_idmap_phys, #object -ENTRY(sleep_idmap_phys) - .quad 0 -/* - * struct sleep_save_sp { - * phys_addr_t *save_ptr_stash; - * phys_addr_t save_ptr_stash_phys; - * }; - */ - .type sleep_save_sp, #object -ENTRY(sleep_save_sp) - .space SLEEP_SAVE_SP_SZ // struct sleep_save_sp diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 9660750..665049d 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -153,6 +153,11 @@ asmlinkage void secondary_start_kernel(void) cpu_ops[cpu]->cpu_postboot(); /* + * Log the CPU info before it is marked online and might get read. + */ + cpuinfo_store_cpu(); + + /* * Enable GIC and timers. */ notify_cpu_starting(cpu); diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 1fa9ce4..2d6b606 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -5,26 +5,24 @@ #include #include #include +#include #include #include #include -extern int __cpu_suspend(unsigned long); +extern int __cpu_suspend_enter(unsigned long arg, int (*fn)(unsigned long)); /* - * This is called by __cpu_suspend() to save the state, and do whatever + * This is called by __cpu_suspend_enter() to save the state, and do whatever * flushing is required to ensure that when the CPU goes to sleep we have * the necessary data available when the caches are not searched. * - * @arg: Argument to pass to suspend operations - * @ptr: CPU context virtual address - * @save_ptr: address of the location where the context physical address - * must be saved + * ptr: CPU context virtual address + * save_ptr: address of the location where the context physical address + * must be saved */ -int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr, - phys_addr_t *save_ptr) +void notrace __cpu_suspend_save(struct cpu_suspend_ctx *ptr, + phys_addr_t *save_ptr) { - int cpu = smp_processor_id(); - *save_ptr = virt_to_phys(ptr); cpu_do_suspend(ptr); @@ -35,8 +33,6 @@ int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr, */ __flush_dcache_area(ptr, sizeof(*ptr)); __flush_dcache_area(save_ptr, sizeof(*save_ptr)); - - return cpu_ops[cpu]->cpu_suspend(arg); } /* @@ -56,15 +52,15 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) } /** - * cpu_suspend + * cpu_suspend() - function to enter a low-power state + * @arg: argument to pass to CPU suspend operations * - * @arg: argument to pass to the finisher function + * Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU + * operations back-end error code otherwise. */ int cpu_suspend(unsigned long arg) { - struct mm_struct *mm = current->active_mm; - int ret, cpu = smp_processor_id(); - unsigned long flags; + int cpu = smp_processor_id(); /* * If cpu_ops have not been registered or suspend @@ -72,6 +68,21 @@ int cpu_suspend(unsigned long arg) */ if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend) return -EOPNOTSUPP; + return cpu_ops[cpu]->cpu_suspend(arg); +} + +/* + * __cpu_suspend + * + * arg: argument to pass to the finisher function + * fn: finisher function pointer + * + */ +int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) +{ + struct mm_struct *mm = current->active_mm; + int ret; + unsigned long flags; /* * From this point debug exceptions are disabled to prevent @@ -86,16 +97,27 @@ int cpu_suspend(unsigned long arg) * page tables, so that the thread address space is properly * set-up on function return. */ - ret = __cpu_suspend(arg); + ret = __cpu_suspend_enter(arg, fn); if (ret == 0) { - cpu_switch_mm(mm->pgd, mm); + /* + * We are resuming from reset with TTBR0_EL1 set to the + * idmap to enable the MMU; restore the active_mm mappings in + * TTBR0_EL1 unless the active_mm == &init_mm, in which case + * the thread entered __cpu_suspend with TTBR0_EL1 set to + * reserved TTBR0 page tables and should be restored as such. + */ + if (mm == &init_mm) + cpu_set_reserved_ttbr0(); + else + cpu_switch_mm(mm->pgd, mm); + flush_tlb_all(); /* * Restore per-cpu offset before any kernel * subsystem relying on it has a chance to run. */ - set_my_cpu_offset(per_cpu_offset(cpu)); + set_my_cpu_offset(per_cpu_offset(smp_processor_id())); /* * Restore HW breakpoint registers to sane values @@ -116,10 +138,10 @@ int cpu_suspend(unsigned long arg) return ret; } -extern struct sleep_save_sp sleep_save_sp; -extern phys_addr_t sleep_idmap_phys; +struct sleep_save_sp sleep_save_sp; +phys_addr_t sleep_idmap_phys; -static int cpu_suspend_init(void) +static int __init cpu_suspend_init(void) { void *ctx_ptr; diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 26e9c4e..7803992 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -79,6 +79,12 @@ long compat_arm_syscall(struct pt_regs *regs) case __ARM_NR_compat_set_tls: current->thread.tp_value = regs->regs[0]; + + /* + * Protect against register corruption from context switch. + * See comment in tls_thread_flush. + */ + barrier(); asm ("msr tpidrro_el0, %0" : : "r" (regs->regs[0])); return 0; diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 84b9426..f6fe17d 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -15,6 +15,10 @@ ccflags-y := -shared -fno-common -fno-builtin ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \ $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) +# Workaround for bare-metal (ELF) toolchains that neglect to pass -shared +# down to collect2, resulting in silent corruption of the vDSO image. +ccflags-y += -Wl,-shared + obj-y += vdso.o extra-y += vdso.lds vdso-offsets.h CPPFLAGS_vdso.lds += -P -C -U$(ARCH) @@ -43,7 +47,7 @@ $(obj)/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE $(call if_changed,vdsosym) # Assembly rules for the .S files -$(obj-vdso): %.o: %.S +$(obj-vdso): %.o: %.S FORCE $(call if_changed_dep,vdsoas) # Actual build commands diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 0874557..a8d81fa 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -38,7 +38,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { - vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS; return 0; } diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 7bc41ea..fd9aeba 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -62,6 +62,8 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) else kvm_vcpu_block(vcpu); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + return 1; } diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index 2b0244d..12e26f3 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -74,6 +74,10 @@ __do_hyp_init: msr mair_el2, x4 isb + /* Invalidate the stale TLBs from Bootloader */ + tlbi alle2 + dsb sy + mrs x4, sctlr_el2 and x4, x4, #SCTLR_EL2_EE // preserve endianness of EL2 ldr x5, =SCTLR_EL2_FLAGS diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 2c56012..3aaf3bc 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -629,10 +629,17 @@ ENTRY(__kvm_tlb_flush_vmid_ipa) * Instead, we invalidate Stage-2 for this IPA, and the * whole of Stage-1. Weep... */ + lsr x1, x1, #12 tlbi ipas2e1is, x1 - dsb sy + /* + * We have to ensure completion of the invalidation at Stage-2, + * since a table walk on another CPU could refill a TLB with a + * complete (S1 + S2) walk based on the old Stage-2 mapping if + * the Stage-1 invalidation happened first. + */ + dsb ish tlbi vmalle1is - dsb sy + dsb ish isb msr vttbr_el2, xzr @@ -643,7 +650,7 @@ ENTRY(__kvm_flush_vm_context) dsb ishst tlbi alle1is ic ialluis - dsb sy + dsb ish ret ENDPROC(__kvm_flush_vm_context) @@ -824,7 +831,7 @@ el1_trap: mrs x2, far_el2 2: mrs x0, tpidr_el2 - str x1, [x0, #VCPU_ESR_EL2] + str w1, [x0, #VCPU_ESR_EL2] str x2, [x0, #VCPU_FAR_EL2] str x3, [x0, #VCPU_HPFAR_EL2] diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 81a02a8..86825f8 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -168,8 +168,8 @@ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr) { if (!(vcpu->arch.hcr_el2 & HCR_RW)) inject_abt32(vcpu, false, addr); - - inject_abt64(vcpu, false, addr); + else + inject_abt64(vcpu, false, addr); } /** @@ -184,8 +184,8 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) { if (!(vcpu->arch.hcr_el2 & HCR_RW)) inject_abt32(vcpu, true, addr); - - inject_abt64(vcpu, true, addr); + else + inject_abt64(vcpu, true, addr); } /** @@ -198,6 +198,6 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu) { if (!(vcpu->arch.hcr_el2 & HCR_RW)) inject_undef32(vcpu); - - inject_undef64(vcpu); + else + inject_undef64(vcpu); } diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 70a7816..0b43265 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -90,7 +90,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) if (!cpu_has_32bit_el1()) return -EINVAL; cpu_reset = &default_regs_reset32; - vcpu->arch.hcr_el2 &= ~HCR_RW; } else { cpu_reset = &default_regs_reset; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 02e9d09..7691b25 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -121,6 +122,48 @@ done: } /* + * Generic accessor for VM registers. Only called as long as HCR_TVM + * is set. + */ +static bool access_vm_reg(struct kvm_vcpu *vcpu, + const struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + unsigned long val; + + BUG_ON(!p->is_write); + + val = *vcpu_reg(vcpu, p->Rt); + if (!p->is_aarch32) { + vcpu_sys_reg(vcpu, r->reg) = val; + } else { + vcpu_cp15(vcpu, r->reg) = val & 0xffffffffUL; + if (!p->is_32bit) + vcpu_cp15(vcpu, r->reg + 1) = val >> 32; + } + return true; +} + +/* + * SCTLR_EL1 accessor. Only called as long as HCR_TVM is set. If the + * guest enables the MMU, we stop trapping the VM sys_regs and leave + * it in complete control of the caches. + */ +static bool access_sctlr(struct kvm_vcpu *vcpu, + const struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + access_vm_reg(vcpu, p, r); + + if (vcpu_has_cache_enabled(vcpu)) { /* MMU+Caches enabled? */ + vcpu->arch.hcr_el2 &= ~HCR_TVM; + stage2_flush_vm(vcpu->kvm); + } + + return true; +} + +/* * We could trap ID_DFR0 and tell the guest we don't support performance * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was * NAKed, so it will read the PMCR anyway. @@ -185,32 +228,32 @@ static const struct sys_reg_desc sys_reg_descs[] = { NULL, reset_mpidr, MPIDR_EL1 }, /* SCTLR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000), - NULL, reset_val, SCTLR_EL1, 0x00C50078 }, + access_sctlr, reset_val, SCTLR_EL1, 0x00C50078 }, /* CPACR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010), NULL, reset_val, CPACR_EL1, 0 }, /* TTBR0_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b000), - NULL, reset_unknown, TTBR0_EL1 }, + access_vm_reg, reset_unknown, TTBR0_EL1 }, /* TTBR1_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b001), - NULL, reset_unknown, TTBR1_EL1 }, + access_vm_reg, reset_unknown, TTBR1_EL1 }, /* TCR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b010), - NULL, reset_val, TCR_EL1, 0 }, + access_vm_reg, reset_val, TCR_EL1, 0 }, /* AFSR0_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b000), - NULL, reset_unknown, AFSR0_EL1 }, + access_vm_reg, reset_unknown, AFSR0_EL1 }, /* AFSR1_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b001), - NULL, reset_unknown, AFSR1_EL1 }, + access_vm_reg, reset_unknown, AFSR1_EL1 }, /* ESR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0010), Op2(0b000), - NULL, reset_unknown, ESR_EL1 }, + access_vm_reg, reset_unknown, ESR_EL1 }, /* FAR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000), - NULL, reset_unknown, FAR_EL1 }, + access_vm_reg, reset_unknown, FAR_EL1 }, /* PAR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000), NULL, reset_unknown, PAR_EL1 }, @@ -224,17 +267,17 @@ static const struct sys_reg_desc sys_reg_descs[] = { /* MAIR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000), - NULL, reset_unknown, MAIR_EL1 }, + access_vm_reg, reset_unknown, MAIR_EL1 }, /* AMAIR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0011), Op2(0b000), - NULL, reset_amair_el1, AMAIR_EL1 }, + access_vm_reg, reset_amair_el1, AMAIR_EL1 }, /* VBAR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000), NULL, reset_val, VBAR_EL1, 0 }, /* CONTEXTIDR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001), - NULL, reset_val, CONTEXTIDR_EL1, 0 }, + access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 }, /* TPIDR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b100), NULL, reset_unknown, TPIDR_EL1 }, @@ -305,14 +348,32 @@ static const struct sys_reg_desc sys_reg_descs[] = { NULL, reset_val, FPEXC32_EL2, 0x70 }, }; -/* Trapped cp15 registers */ +/* + * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding, + * depending on the way they are accessed (as a 32bit or a 64bit + * register). + */ static const struct sys_reg_desc cp15_regs[] = { + { Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 }, + { Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_sctlr, NULL, c1_SCTLR }, + { Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 }, + { Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 }, + { Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR }, + { Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR }, + { Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR }, + { Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR }, + { Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, c5_ADFSR }, + { Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, c5_AIFSR }, + { Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, c6_DFAR }, + { Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, c6_IFAR }, + /* * DC{C,I,CI}SW operations: */ { Op1( 0), CRn( 7), CRm( 6), Op2( 2), access_dcsw }, { Op1( 0), CRn( 7), CRm(10), Op2( 2), access_dcsw }, { Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw }, + { Op1( 0), CRn( 9), CRm(12), Op2( 0), pm_fake }, { Op1( 0), CRn( 9), CRm(12), Op2( 1), pm_fake }, { Op1( 0), CRn( 9), CRm(12), Op2( 2), pm_fake }, @@ -326,6 +387,14 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn( 9), CRm(14), Op2( 0), pm_fake }, { Op1( 0), CRn( 9), CRm(14), Op2( 1), pm_fake }, { Op1( 0), CRn( 9), CRm(14), Op2( 2), pm_fake }, + + { Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR }, + { Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR }, + { Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 }, + { Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 }, + { Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID }, + + { Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 }, }; /* Target specific emulation tables */ @@ -437,6 +506,8 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run) u32 hsr = kvm_vcpu_get_hsr(vcpu); int Rt2 = (hsr >> 10) & 0xf; + params.is_aarch32 = true; + params.is_32bit = false; params.CRm = (hsr >> 1) & 0xf; params.Rt = (hsr >> 5) & 0xf; params.is_write = ((hsr & 1) == 0); @@ -480,6 +551,8 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run) struct sys_reg_params params; u32 hsr = kvm_vcpu_get_hsr(vcpu); + params.is_aarch32 = true; + params.is_32bit = true; params.CRm = (hsr >> 1) & 0xf; params.Rt = (hsr >> 5) & 0xf; params.is_write = ((hsr & 1) == 0); @@ -549,6 +622,8 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run) struct sys_reg_params params; unsigned long esr = kvm_vcpu_get_hsr(vcpu); + params.is_aarch32 = false; + params.is_32bit = false; params.Op0 = (esr >> 20) & 3; params.Op1 = (esr >> 14) & 0x7; params.CRn = (esr >> 10) & 0xf; @@ -761,7 +836,7 @@ static bool is_valid_cache(u32 val) u32 level, ctype; if (val >= CSSELR_MAX) - return -ENOENT; + return false; /* Bottom bit is Instruction or Data bit. Next 3 bits are level. */ level = (val >> 1); @@ -887,7 +962,7 @@ static unsigned int num_demux_regs(void) static int write_demux_regids(u64 __user *uindices) { - u64 val = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX; + u64 val = KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX; unsigned int i; val |= KVM_REG_ARM_DEMUX_ID_CCSIDR; diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index d50d372..d411e25 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -30,6 +30,8 @@ struct sys_reg_params { u8 Op2; u8 Rt; bool is_write; + bool is_aarch32; + bool is_32bit; /* Only valid if is_aarch32 is true */ }; struct sys_reg_desc { diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 6e0ed93..c17967f 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -46,7 +46,7 @@ USER(9f, strh wzr, [x0], #2 ) sub x1, x1, #2 4: adds x1, x1, #1 b.mi 5f - strb wzr, [x0] +USER(9f, strb wzr, [x0] ) 5: mov x0, #0 ret ENDPROC(__clear_user) diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index baa758d..76c1e6c 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -92,6 +92,14 @@ static void reset_context(void *info) unsigned int cpu = smp_processor_id(); struct mm_struct *mm = current->active_mm; + /* + * current->active_mm could be init_mm for the idle thread immediately + * after secondary CPU boot or hotplug. TTBR0_EL1 is already set to + * the reserved value, so no need to reset any context. + */ + if (mm == &init_mm) + return; + smp_rmb(); asid = cpu_last_asid + cpu; diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 9337524..05d9815 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -57,6 +57,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, flags |= GFP_DMA; if (IS_ENABLED(CONFIG_DMA_CMA)) { struct page *page; + void *addr; size = PAGE_ALIGN(size); page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, @@ -65,7 +66,9 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, return NULL; *dma_handle = phys_to_dma(dev, page_to_phys(page)); - return page_address(page); + addr = page_address(page); + memset(addr, 0, size); + return addr; } else { return swiotlb_alloc_coherent(dev, size, dma_handle, flags); } diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 023747b..e3a24b7 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -46,13 +46,13 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int pmd_huge(pmd_t pmd) { - return !(pmd_val(pmd) & PMD_TABLE_BIT); + return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); } int pud_huge(pud_t pud) { #ifndef __PAGETABLE_PMD_FOLDED - return !(pud_val(pud) & PUD_TABLE_BIT); + return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT); #else return 0; #endif diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index c872988..6ca4285 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -240,7 +240,7 @@ static void __init free_unused_memmap(void) * memmap entries are valid from the bank end aligned to * MAX_ORDER_NR_PAGES. */ - prev_end = ALIGN(start + __phys_to_pfn(reg->size), + prev_end = ALIGN(__phys_to_pfn(reg->base + reg->size), MAX_ORDER_NR_PAGES); } diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 8ed6cb1..8f7ffff 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -47,22 +47,14 @@ static int mmap_is_legacy(void) return sysctl_legacy_va_layout; } -/* - * Since get_random_int() returns the same value within a 1 jiffy window, we - * will almost always get the same randomisation for the stack and mmap - * region. This will mean the relative distance between stack and mmap will be - * the same. - * - * To avoid this we can shift the randomness by 1 bit. - */ static unsigned long mmap_rnd(void) { unsigned long rnd = 0; if (current->flags & PF_RANDOMIZE) - rnd = (long)get_random_int() & (STACK_RND_MASK >> 1); + rnd = (long)get_random_int() & STACK_RND_MASK; - return rnd << (PAGE_SHIFT + 1); + return rnd << PAGE_SHIFT; } static unsigned long mmap_base(void) diff --git a/arch/avr32/mach-at32ap/clock.c b/arch/avr32/mach-at32ap/clock.c index 23b1a97..52c179b 100644 --- a/arch/avr32/mach-at32ap/clock.c +++ b/arch/avr32/mach-at32ap/clock.c @@ -80,6 +80,9 @@ int clk_enable(struct clk *clk) { unsigned long flags; + if (!clk) + return 0; + spin_lock_irqsave(&clk_lock, flags); __clk_enable(clk); spin_unlock_irqrestore(&clk_lock, flags); @@ -106,6 +109,9 @@ void clk_disable(struct clk *clk) { unsigned long flags; + if (IS_ERR_OR_NULL(clk)) + return; + spin_lock_irqsave(&clk_lock, flags); __clk_disable(clk); spin_unlock_irqrestore(&clk_lock, flags); @@ -117,6 +123,9 @@ unsigned long clk_get_rate(struct clk *clk) unsigned long flags; unsigned long rate; + if (!clk) + return 0; + spin_lock_irqsave(&clk_lock, flags); rate = clk->get_rate(clk); spin_unlock_irqrestore(&clk_lock, flags); @@ -129,6 +138,9 @@ long clk_round_rate(struct clk *clk, unsigned long rate) { unsigned long flags, actual_rate; + if (!clk) + return 0; + if (!clk->set_rate) return -ENOSYS; @@ -145,6 +157,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate) unsigned long flags; long ret; + if (!clk) + return 0; + if (!clk->set_rate) return -ENOSYS; @@ -161,6 +176,9 @@ int clk_set_parent(struct clk *clk, struct clk *parent) unsigned long flags; int ret; + if (!clk) + return 0; + if (!clk->set_parent) return -ENOSYS; @@ -174,7 +192,7 @@ EXPORT_SYMBOL(clk_set_parent); struct clk *clk_get_parent(struct clk *clk) { - return clk->parent; + return !clk ? NULL : clk->parent; } EXPORT_SYMBOL(clk_get_parent); diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index 0eca933..d223a8b 100644 --- a/arch/avr32/mm/fault.c +++ b/arch/avr32/mm/fault.c @@ -142,6 +142,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/c6x/kernel/time.c b/arch/c6x/kernel/time.c index 356ee84..04845aa 100644 --- a/arch/c6x/kernel/time.c +++ b/arch/c6x/kernel/time.c @@ -49,7 +49,7 @@ u64 sched_clock(void) return (tsc * sched_clock_multiplier) >> SCHED_CLOCK_SHIFT; } -void time_init(void) +void __init time_init(void) { u64 tmp = (u64)NSEC_PER_SEC << SCHED_CLOCK_SHIFT; diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c index 1790f22..2686a7a 100644 --- a/arch/cris/mm/fault.c +++ b/arch/cris/mm/fault.c @@ -176,6 +176,8 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c index 9a66372..ec4917d 100644 --- a/arch/frv/mm/fault.c +++ b/arch/frv/mm/fault.c @@ -168,6 +168,8 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 7225dad..ba5ba7a 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -172,6 +172,8 @@ retry: */ if (fault & VM_FAULT_OOM) { goto out_of_memory; + } else if (fault & VM_FAULT_SIGSEGV) { + goto bad_area; } else if (fault & VM_FAULT_SIGBUS) { signal = SIGBUS; goto bad_area; diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c index e9c6a80..e3d4d48901 100644 --- a/arch/m32r/mm/fault.c +++ b/arch/m32r/mm/fault.c @@ -200,6 +200,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 2bd7487..b2f04ae 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -145,6 +145,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto map_err; else if (fault & VM_FAULT_SIGBUS) goto bus_err; BUG(); diff --git a/arch/m68k/mm/hwtest.c b/arch/m68k/mm/hwtest.c index 2c7dde3..2a5259f 100644 --- a/arch/m68k/mm/hwtest.c +++ b/arch/m68k/mm/hwtest.c @@ -28,9 +28,11 @@ int hwreg_present( volatile void *regp ) { int ret = 0; + unsigned long flags; long save_sp, save_vbr; long tmp_vectors[3]; + local_irq_save(flags); __asm__ __volatile__ ( "movec %/vbr,%2\n\t" "movel #Lberr1,%4@(8)\n\t" @@ -46,6 +48,7 @@ int hwreg_present( volatile void *regp ) : "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr) : "a" (regp), "a" (tmp_vectors) ); + local_irq_restore(flags); return( ret ); } @@ -58,9 +61,11 @@ EXPORT_SYMBOL(hwreg_present); int hwreg_write( volatile void *regp, unsigned short val ) { int ret; + unsigned long flags; long save_sp, save_vbr; long tmp_vectors[3]; + local_irq_save(flags); __asm__ __volatile__ ( "movec %/vbr,%2\n\t" "movel #Lberr2,%4@(8)\n\t" @@ -78,6 +83,7 @@ int hwreg_write( volatile void *regp, unsigned short val ) : "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr) : "a" (regp), "a" (tmp_vectors), "g" (val) ); + local_irq_restore(flags); return( ret ); } diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h index a8a3747..eb2005b 100644 --- a/arch/metag/include/asm/processor.h +++ b/arch/metag/include/asm/processor.h @@ -149,8 +149,8 @@ extern void exit_thread(void); unsigned long get_wchan(struct task_struct *p); -#define KSTK_EIP(tsk) ((tsk)->thread.kernel_context->CurrPC) -#define KSTK_ESP(tsk) ((tsk)->thread.kernel_context->AX[0].U0) +#define KSTK_EIP(tsk) (task_pt_regs(tsk)->ctx.CurrPC) +#define KSTK_ESP(tsk) (task_pt_regs(tsk)->ctx.AX[0].U0) #define user_stack_pointer(regs) ((regs)->ctx.AX[0].U0) diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c index 332680e..2de5dc6 100644 --- a/arch/metag/mm/fault.c +++ b/arch/metag/mm/fault.c @@ -141,6 +141,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index fa4cf52..d46a5eb 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -224,6 +224,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index c00c4dd..5244cec 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -13,6 +13,7 @@ #include #include +#include #include diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index 331b837..270cb3c 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -458,6 +458,18 @@ static void octeon_halt(void) octeon_kill_core(NULL); } +static char __read_mostly octeon_system_type[80]; + +static int __init init_octeon_system_type(void) +{ + snprintf(octeon_system_type, sizeof(octeon_system_type), "%s (%s)", + cvmx_board_type_to_string(octeon_bootinfo->board_type), + octeon_model_get_string(read_c0_prid())); + + return 0; +} +early_initcall(init_octeon_system_type); + /** * Return a string representing the system type * @@ -465,11 +477,7 @@ static void octeon_halt(void) */ const char *octeon_board_type_string(void) { - static char name[80]; - sprintf(name, "%s (%s)", - cvmx_board_type_to_string(octeon_bootinfo->board_type), - octeon_model_get_string(read_c0_prid())); - return name; + return octeon_system_type; } const char *get_system_type(void) diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 67a078f..34467ac 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -263,9 +263,7 @@ static int octeon_cpu_disable(void) set_cpu_online(cpu, false); cpu_clear(cpu, cpu_callin_map); - local_irq_disable(); octeon_fixup_irqs(); - local_irq_enable(); flush_cache_all(); local_flush_tlb_all(); diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h index 992aaba..b463f2a 100644 --- a/arch/mips/include/asm/ftrace.h +++ b/arch/mips/include/asm/ftrace.h @@ -24,7 +24,7 @@ do { \ asm volatile ( \ "1: " load " %[tmp_dst], 0(%[tmp_src])\n" \ " li %[tmp_err], 0\n" \ - "2:\n" \ + "2: .insn\n" \ \ ".section .fixup, \"ax\"\n" \ "3: li %[tmp_err], 1\n" \ @@ -46,7 +46,7 @@ do { \ asm volatile ( \ "1: " store " %[tmp_src], 0(%[tmp_dst])\n"\ " li %[tmp_err], 0\n" \ - "2:\n" \ + "2: .insn\n" \ \ ".section .fixup, \"ax\"\n" \ "3: li %[tmp_err], 1\n" \ diff --git a/arch/mips/include/asm/mach-generic/spaces.h b/arch/mips/include/asm/mach-generic/spaces.h index 9488fa5..afc96ec 100644 --- a/arch/mips/include/asm/mach-generic/spaces.h +++ b/arch/mips/include/asm/mach-generic/spaces.h @@ -94,7 +94,11 @@ #endif #ifndef FIXADDR_TOP +#ifdef CONFIG_KVM_GUEST +#define FIXADDR_TOP ((unsigned long)(long)(int)0x7ffe0000) +#else #define FIXADDR_TOP ((unsigned long)(long)(int)0xfffe0000) #endif +#endif #endif /* __ASM_MACH_GENERIC_SPACES_H */ diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 008324d..b154953 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -150,8 +150,39 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) * Make sure the buddy is global too (if it's !none, * it better already be global) */ +#ifdef CONFIG_SMP + /* + * For SMP, multiple CPUs can race, so we need to do + * this atomically. + */ +#ifdef CONFIG_64BIT +#define LL_INSN "lld" +#define SC_INSN "scd" +#else /* CONFIG_32BIT */ +#define LL_INSN "ll" +#define SC_INSN "sc" +#endif + unsigned long page_global = _PAGE_GLOBAL; + unsigned long tmp; + + __asm__ __volatile__ ( + " .set push\n" + " .set noreorder\n" + "1: " LL_INSN " %[tmp], %[buddy]\n" + " bnez %[tmp], 2f\n" + " or %[tmp], %[tmp], %[global]\n" + " " SC_INSN " %[tmp], %[buddy]\n" + " beqz %[tmp], 1b\n" + " nop\n" + "2:\n" + " .set pop" + : [buddy] "+m" (buddy->pte), + [tmp] "=&r" (tmp) + : [global] "r" (page_global)); +#else /* !CONFIG_SMP */ if (pte_none(*buddy)) pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL; +#endif /* CONFIG_SMP */ } #endif } diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index 7bba9da..6d019ca 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -23,7 +23,7 @@ struct pt_regs { #ifdef CONFIG_32BIT /* Pad bytes for argument save space on the stack. */ - unsigned long pad0[6]; + unsigned long pad0[8]; #endif /* Saved main processor registers. */ diff --git a/arch/mips/include/asm/reg.h b/arch/mips/include/asm/reg.h index 910e71a..b8343cc 100644 --- a/arch/mips/include/asm/reg.h +++ b/arch/mips/include/asm/reg.h @@ -12,116 +12,194 @@ #ifndef __ASM_MIPS_REG_H #define __ASM_MIPS_REG_H - -#if defined(CONFIG_32BIT) || defined(WANT_COMPAT_REG_H) - -#define EF_R0 6 -#define EF_R1 7 -#define EF_R2 8 -#define EF_R3 9 -#define EF_R4 10 -#define EF_R5 11 -#define EF_R6 12 -#define EF_R7 13 -#define EF_R8 14 -#define EF_R9 15 -#define EF_R10 16 -#define EF_R11 17 -#define EF_R12 18 -#define EF_R13 19 -#define EF_R14 20 -#define EF_R15 21 -#define EF_R16 22 -#define EF_R17 23 -#define EF_R18 24 -#define EF_R19 25 -#define EF_R20 26 -#define EF_R21 27 -#define EF_R22 28 -#define EF_R23 29 -#define EF_R24 30 -#define EF_R25 31 +#define MIPS32_EF_R0 6 +#define MIPS32_EF_R1 7 +#define MIPS32_EF_R2 8 +#define MIPS32_EF_R3 9 +#define MIPS32_EF_R4 10 +#define MIPS32_EF_R5 11 +#define MIPS32_EF_R6 12 +#define MIPS32_EF_R7 13 +#define MIPS32_EF_R8 14 +#define MIPS32_EF_R9 15 +#define MIPS32_EF_R10 16 +#define MIPS32_EF_R11 17 +#define MIPS32_EF_R12 18 +#define MIPS32_EF_R13 19 +#define MIPS32_EF_R14 20 +#define MIPS32_EF_R15 21 +#define MIPS32_EF_R16 22 +#define MIPS32_EF_R17 23 +#define MIPS32_EF_R18 24 +#define MIPS32_EF_R19 25 +#define MIPS32_EF_R20 26 +#define MIPS32_EF_R21 27 +#define MIPS32_EF_R22 28 +#define MIPS32_EF_R23 29 +#define MIPS32_EF_R24 30 +#define MIPS32_EF_R25 31 /* * k0/k1 unsaved */ -#define EF_R26 32 -#define EF_R27 33 +#define MIPS32_EF_R26 32 +#define MIPS32_EF_R27 33 -#define EF_R28 34 -#define EF_R29 35 -#define EF_R30 36 -#define EF_R31 37 +#define MIPS32_EF_R28 34 +#define MIPS32_EF_R29 35 +#define MIPS32_EF_R30 36 +#define MIPS32_EF_R31 37 /* * Saved special registers */ -#define EF_LO 38 -#define EF_HI 39 - -#define EF_CP0_EPC 40 -#define EF_CP0_BADVADDR 41 -#define EF_CP0_STATUS 42 -#define EF_CP0_CAUSE 43 -#define EF_UNUSED0 44 - -#define EF_SIZE 180 - -#endif - -#if defined(CONFIG_64BIT) && !defined(WANT_COMPAT_REG_H) - -#define EF_R0 0 -#define EF_R1 1 -#define EF_R2 2 -#define EF_R3 3 -#define EF_R4 4 -#define EF_R5 5 -#define EF_R6 6 -#define EF_R7 7 -#define EF_R8 8 -#define EF_R9 9 -#define EF_R10 10 -#define EF_R11 11 -#define EF_R12 12 -#define EF_R13 13 -#define EF_R14 14 -#define EF_R15 15 -#define EF_R16 16 -#define EF_R17 17 -#define EF_R18 18 -#define EF_R19 19 -#define EF_R20 20 -#define EF_R21 21 -#define EF_R22 22 -#define EF_R23 23 -#define EF_R24 24 -#define EF_R25 25 +#define MIPS32_EF_LO 38 +#define MIPS32_EF_HI 39 + +#define MIPS32_EF_CP0_EPC 40 +#define MIPS32_EF_CP0_BADVADDR 41 +#define MIPS32_EF_CP0_STATUS 42 +#define MIPS32_EF_CP0_CAUSE 43 +#define MIPS32_EF_UNUSED0 44 + +#define MIPS32_EF_SIZE 180 + +#define MIPS64_EF_R0 0 +#define MIPS64_EF_R1 1 +#define MIPS64_EF_R2 2 +#define MIPS64_EF_R3 3 +#define MIPS64_EF_R4 4 +#define MIPS64_EF_R5 5 +#define MIPS64_EF_R6 6 +#define MIPS64_EF_R7 7 +#define MIPS64_EF_R8 8 +#define MIPS64_EF_R9 9 +#define MIPS64_EF_R10 10 +#define MIPS64_EF_R11 11 +#define MIPS64_EF_R12 12 +#define MIPS64_EF_R13 13 +#define MIPS64_EF_R14 14 +#define MIPS64_EF_R15 15 +#define MIPS64_EF_R16 16 +#define MIPS64_EF_R17 17 +#define MIPS64_EF_R18 18 +#define MIPS64_EF_R19 19 +#define MIPS64_EF_R20 20 +#define MIPS64_EF_R21 21 +#define MIPS64_EF_R22 22 +#define MIPS64_EF_R23 23 +#define MIPS64_EF_R24 24 +#define MIPS64_EF_R25 25 /* * k0/k1 unsaved */ -#define EF_R26 26 -#define EF_R27 27 +#define MIPS64_EF_R26 26 +#define MIPS64_EF_R27 27 -#define EF_R28 28 -#define EF_R29 29 -#define EF_R30 30 -#define EF_R31 31 +#define MIPS64_EF_R28 28 +#define MIPS64_EF_R29 29 +#define MIPS64_EF_R30 30 +#define MIPS64_EF_R31 31 /* * Saved special registers */ -#define EF_LO 32 -#define EF_HI 33 - -#define EF_CP0_EPC 34 -#define EF_CP0_BADVADDR 35 -#define EF_CP0_STATUS 36 -#define EF_CP0_CAUSE 37 - -#define EF_SIZE 304 /* size in bytes */ +#define MIPS64_EF_LO 32 +#define MIPS64_EF_HI 33 + +#define MIPS64_EF_CP0_EPC 34 +#define MIPS64_EF_CP0_BADVADDR 35 +#define MIPS64_EF_CP0_STATUS 36 +#define MIPS64_EF_CP0_CAUSE 37 + +#define MIPS64_EF_SIZE 304 /* size in bytes */ + +#if defined(CONFIG_32BIT) + +#define EF_R0 MIPS32_EF_R0 +#define EF_R1 MIPS32_EF_R1 +#define EF_R2 MIPS32_EF_R2 +#define EF_R3 MIPS32_EF_R3 +#define EF_R4 MIPS32_EF_R4 +#define EF_R5 MIPS32_EF_R5 +#define EF_R6 MIPS32_EF_R6 +#define EF_R7 MIPS32_EF_R7 +#define EF_R8 MIPS32_EF_R8 +#define EF_R9 MIPS32_EF_R9 +#define EF_R10 MIPS32_EF_R10 +#define EF_R11 MIPS32_EF_R11 +#define EF_R12 MIPS32_EF_R12 +#define EF_R13 MIPS32_EF_R13 +#define EF_R14 MIPS32_EF_R14 +#define EF_R15 MIPS32_EF_R15 +#define EF_R16 MIPS32_EF_R16 +#define EF_R17 MIPS32_EF_R17 +#define EF_R18 MIPS32_EF_R18 +#define EF_R19 MIPS32_EF_R19 +#define EF_R20 MIPS32_EF_R20 +#define EF_R21 MIPS32_EF_R21 +#define EF_R22 MIPS32_EF_R22 +#define EF_R23 MIPS32_EF_R23 +#define EF_R24 MIPS32_EF_R24 +#define EF_R25 MIPS32_EF_R25 +#define EF_R26 MIPS32_EF_R26 +#define EF_R27 MIPS32_EF_R27 +#define EF_R28 MIPS32_EF_R28 +#define EF_R29 MIPS32_EF_R29 +#define EF_R30 MIPS32_EF_R30 +#define EF_R31 MIPS32_EF_R31 +#define EF_LO MIPS32_EF_LO +#define EF_HI MIPS32_EF_HI +#define EF_CP0_EPC MIPS32_EF_CP0_EPC +#define EF_CP0_BADVADDR MIPS32_EF_CP0_BADVADDR +#define EF_CP0_STATUS MIPS32_EF_CP0_STATUS +#define EF_CP0_CAUSE MIPS32_EF_CP0_CAUSE +#define EF_UNUSED0 MIPS32_EF_UNUSED0 +#define EF_SIZE MIPS32_EF_SIZE + +#elif defined(CONFIG_64BIT) + +#define EF_R0 MIPS64_EF_R0 +#define EF_R1 MIPS64_EF_R1 +#define EF_R2 MIPS64_EF_R2 +#define EF_R3 MIPS64_EF_R3 +#define EF_R4 MIPS64_EF_R4 +#define EF_R5 MIPS64_EF_R5 +#define EF_R6 MIPS64_EF_R6 +#define EF_R7 MIPS64_EF_R7 +#define EF_R8 MIPS64_EF_R8 +#define EF_R9 MIPS64_EF_R9 +#define EF_R10 MIPS64_EF_R10 +#define EF_R11 MIPS64_EF_R11 +#define EF_R12 MIPS64_EF_R12 +#define EF_R13 MIPS64_EF_R13 +#define EF_R14 MIPS64_EF_R14 +#define EF_R15 MIPS64_EF_R15 +#define EF_R16 MIPS64_EF_R16 +#define EF_R17 MIPS64_EF_R17 +#define EF_R18 MIPS64_EF_R18 +#define EF_R19 MIPS64_EF_R19 +#define EF_R20 MIPS64_EF_R20 +#define EF_R21 MIPS64_EF_R21 +#define EF_R22 MIPS64_EF_R22 +#define EF_R23 MIPS64_EF_R23 +#define EF_R24 MIPS64_EF_R24 +#define EF_R25 MIPS64_EF_R25 +#define EF_R26 MIPS64_EF_R26 +#define EF_R27 MIPS64_EF_R27 +#define EF_R28 MIPS64_EF_R28 +#define EF_R29 MIPS64_EF_R29 +#define EF_R30 MIPS64_EF_R30 +#define EF_R31 MIPS64_EF_R31 +#define EF_LO MIPS64_EF_LO +#define EF_HI MIPS64_EF_HI +#define EF_CP0_EPC MIPS64_EF_CP0_EPC +#define EF_CP0_BADVADDR MIPS64_EF_CP0_BADVADDR +#define EF_CP0_STATUS MIPS64_EF_CP0_STATUS +#define EF_CP0_CAUSE MIPS64_EF_CP0_CAUSE +#define EF_SIZE MIPS64_EF_SIZE #endif /* CONFIG_64BIT */ diff --git a/arch/mips/include/asm/suspend.h b/arch/mips/include/asm/suspend.h deleted file mode 100644 index 3adac3b..0000000 --- a/arch/mips/include/asm/suspend.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef __ASM_SUSPEND_H -#define __ASM_SUSPEND_H - -/* References to section boundaries */ -extern const void __nosave_begin, __nosave_end; - -#endif /* __ASM_SUSPEND_H */ diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index 7faf5f2..71df942 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -72,12 +72,6 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; #include -/* - * When this file is selected, we are definitely running a 64bit kernel. - * So using the right regs define in asm/reg.h - */ -#define WANT_COMPAT_REG_H - /* These MUST be defined before elf.h gets included */ extern void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs); #define ELF_CORE_COPY_REGS(_dest, _regs) elf32_core_copy_regs(_dest, _regs); @@ -149,21 +143,21 @@ void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs) { int i; - for (i = 0; i < EF_R0; i++) + for (i = 0; i < MIPS32_EF_R0; i++) grp[i] = 0; - grp[EF_R0] = 0; + grp[MIPS32_EF_R0] = 0; for (i = 1; i <= 31; i++) - grp[EF_R0 + i] = (elf_greg_t) regs->regs[i]; - grp[EF_R26] = 0; - grp[EF_R27] = 0; - grp[EF_LO] = (elf_greg_t) regs->lo; - grp[EF_HI] = (elf_greg_t) regs->hi; - grp[EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc; - grp[EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr; - grp[EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status; - grp[EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause; -#ifdef EF_UNUSED0 - grp[EF_UNUSED0] = 0; + grp[MIPS32_EF_R0 + i] = (elf_greg_t) regs->regs[i]; + grp[MIPS32_EF_R26] = 0; + grp[MIPS32_EF_R27] = 0; + grp[MIPS32_EF_LO] = (elf_greg_t) regs->lo; + grp[MIPS32_EF_HI] = (elf_greg_t) regs->hi; + grp[MIPS32_EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc; + grp[MIPS32_EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr; + grp[MIPS32_EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status; + grp[MIPS32_EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause; +#ifdef MIPS32_EF_UNUSED0 + grp[MIPS32_EF_UNUSED0] = 0; #endif } diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c index 5b5ddb2..78f1843 100644 --- a/arch/mips/kernel/irq-gic.c +++ b/arch/mips/kernel/irq-gic.c @@ -255,11 +255,13 @@ static void __init gic_setup_intr(unsigned int intr, unsigned int cpu, /* Setup Intr to Pin mapping */ if (pin & GIC_MAP_TO_NMI_MSK) { + int i; + GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_PIN(intr)), pin); /* FIXME: hack to route NMI to all cpu's */ - for (cpu = 0; cpu < NR_CPUS; cpu += 32) { + for (i = 0; i < NR_CPUS; i += 32) { GICWRITE(GIC_REG_ADDR(SHARED, - GIC_SH_MAP_TO_VPE_REG_OFF(intr, cpu)), + GIC_SH_MAP_TO_VPE_REG_OFF(intr, i)), 0xffffffff); } } else { diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c index d1fea7a..7479d8d 100644 --- a/arch/mips/kernel/irq.c +++ b/arch/mips/kernel/irq.c @@ -110,7 +110,7 @@ void __init init_IRQ(void) #endif } -#ifdef DEBUG_STACKOVERFLOW +#ifdef CONFIG_DEBUG_STACKOVERFLOW static inline void check_stack_overflow(void) { unsigned long sp; diff --git a/arch/mips/kernel/irq_cpu.c b/arch/mips/kernel/irq_cpu.c index e498f2b..f5598e2 100644 --- a/arch/mips/kernel/irq_cpu.c +++ b/arch/mips/kernel/irq_cpu.c @@ -56,6 +56,8 @@ static struct irq_chip mips_cpu_irq_controller = { .irq_mask_ack = mask_mips_irq, .irq_unmask = unmask_mips_irq, .irq_eoi = unmask_mips_irq, + .irq_disable = mask_mips_irq, + .irq_enable = unmask_mips_irq, }; /* @@ -92,6 +94,8 @@ static struct irq_chip mips_mt_cpu_irq_controller = { .irq_mask_ack = mips_mt_cpu_irq_ack, .irq_unmask = unmask_mips_irq, .irq_eoi = unmask_mips_irq, + .irq_disable = mask_mips_irq, + .irq_enable = unmask_mips_irq, }; void __init mips_cpu_irq_init(void) diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S index 539b629..8f89ff4 100644 --- a/arch/mips/kernel/mcount.S +++ b/arch/mips/kernel/mcount.S @@ -123,7 +123,11 @@ NESTED(_mcount, PT_SIZE, ra) nop #endif b ftrace_stub +#ifdef CONFIG_32BIT + addiu sp, sp, 8 +#else nop +#endif static_trace: MCOUNT_SAVE_REGS @@ -133,6 +137,9 @@ static_trace: move a1, AT /* arg2: parent's return address */ MCOUNT_RESTORE_REGS +#ifdef CONFIG_32BIT + addiu sp, sp, 8 +#endif .globl ftrace_stub ftrace_stub: RETURN_BACK @@ -177,6 +184,11 @@ NESTED(ftrace_graph_caller, PT_SIZE, ra) jal prepare_ftrace_return nop MCOUNT_RESTORE_REGS +#ifndef CONFIG_DYNAMIC_FTRACE +#ifdef CONFIG_32BIT + addiu sp, sp, 8 +#endif +#endif RETURN_BACK END(ftrace_graph_caller) diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c index cb09862..ca16964 100644 --- a/arch/mips/kernel/mips-mt-fpaff.c +++ b/arch/mips/kernel/mips-mt-fpaff.c @@ -154,7 +154,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, unsigned long __user *user_mask_ptr) { unsigned int real_len; - cpumask_t mask; + cpumask_t allowed, mask; int retval; struct task_struct *p; @@ -173,7 +173,8 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, if (retval) goto out_unlock; - cpumask_and(&mask, &p->thread.user_cpus_allowed, cpu_possible_mask); + cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed); + cpumask_and(&mask, &allowed, cpu_active_mask); out_unlock: read_unlock(&tasklist_lock); diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c index 6e58e97..cedeb56 100644 --- a/arch/mips/kernel/mips_ksyms.c +++ b/arch/mips/kernel/mips_ksyms.c @@ -14,6 +14,7 @@ #include #include #include +#include extern void *__bzero(void *__s, size_t __count); extern long __strncpy_from_user_nocheck_asm(char *__to, @@ -26,6 +27,13 @@ extern long __strnlen_user_nocheck_asm(const char *s); extern long __strnlen_user_asm(const char *s); /* + * Core architecture code + */ +#ifdef CONFIG_CPU_R4K_FPU +EXPORT_SYMBOL_GPL(_save_fp); +#endif + +/* * String functions */ EXPORT_SYMBOL(memset); diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 7da9b76..60f48fe 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -170,6 +170,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data) __get_user(fregs[i], i + (__u64 __user *) data); __get_user(child->thread.fpu.fcr31, data + 64); + child->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; /* FIR may not be written. */ @@ -265,36 +266,160 @@ int ptrace_set_watch_regs(struct task_struct *child, /* regset get/set implementations */ -static int gpr_get(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) +#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32) + +static int gpr32_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) { struct pt_regs *regs = task_pt_regs(target); + u32 uregs[ELF_NGREG] = {}; + unsigned i; - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - regs, 0, sizeof(*regs)); + for (i = MIPS32_EF_R1; i <= MIPS32_EF_R31; i++) { + /* k0/k1 are copied as zero. */ + if (i == MIPS32_EF_R26 || i == MIPS32_EF_R27) + continue; + + uregs[i] = regs->regs[i - MIPS32_EF_R0]; + } + + uregs[MIPS32_EF_LO] = regs->lo; + uregs[MIPS32_EF_HI] = regs->hi; + uregs[MIPS32_EF_CP0_EPC] = regs->cp0_epc; + uregs[MIPS32_EF_CP0_BADVADDR] = regs->cp0_badvaddr; + uregs[MIPS32_EF_CP0_STATUS] = regs->cp0_status; + uregs[MIPS32_EF_CP0_CAUSE] = regs->cp0_cause; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0, + sizeof(uregs)); } -static int gpr_set(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) +static int gpr32_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) { - struct pt_regs newregs; - int ret; + struct pt_regs *regs = task_pt_regs(target); + u32 uregs[ELF_NGREG]; + unsigned start, num_regs, i; + int err; - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &newregs, - 0, sizeof(newregs)); - if (ret) - return ret; + start = pos / sizeof(u32); + num_regs = count / sizeof(u32); - *task_pt_regs(target) = newregs; + if (start + num_regs > ELF_NGREG) + return -EIO; + + err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0, + sizeof(uregs)); + if (err) + return err; + + for (i = start; i < num_regs; i++) { + /* + * Cast all values to signed here so that if this is a 64-bit + * kernel, the supplied 32-bit values will be sign extended. + */ + switch (i) { + case MIPS32_EF_R1 ... MIPS32_EF_R25: + /* k0/k1 are ignored. */ + case MIPS32_EF_R28 ... MIPS32_EF_R31: + regs->regs[i - MIPS32_EF_R0] = (s32)uregs[i]; + break; + case MIPS32_EF_LO: + regs->lo = (s32)uregs[i]; + break; + case MIPS32_EF_HI: + regs->hi = (s32)uregs[i]; + break; + case MIPS32_EF_CP0_EPC: + regs->cp0_epc = (s32)uregs[i]; + break; + } + } return 0; } +#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */ + +#ifdef CONFIG_64BIT + +static int gpr64_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct pt_regs *regs = task_pt_regs(target); + u64 uregs[ELF_NGREG] = {}; + unsigned i; + + for (i = MIPS64_EF_R1; i <= MIPS64_EF_R31; i++) { + /* k0/k1 are copied as zero. */ + if (i == MIPS64_EF_R26 || i == MIPS64_EF_R27) + continue; + + uregs[i] = regs->regs[i - MIPS64_EF_R0]; + } + + uregs[MIPS64_EF_LO] = regs->lo; + uregs[MIPS64_EF_HI] = regs->hi; + uregs[MIPS64_EF_CP0_EPC] = regs->cp0_epc; + uregs[MIPS64_EF_CP0_BADVADDR] = regs->cp0_badvaddr; + uregs[MIPS64_EF_CP0_STATUS] = regs->cp0_status; + uregs[MIPS64_EF_CP0_CAUSE] = regs->cp0_cause; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0, + sizeof(uregs)); +} + +static int gpr64_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct pt_regs *regs = task_pt_regs(target); + u64 uregs[ELF_NGREG]; + unsigned start, num_regs, i; + int err; + + start = pos / sizeof(u64); + num_regs = count / sizeof(u64); + + if (start + num_regs > ELF_NGREG) + return -EIO; + + err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0, + sizeof(uregs)); + if (err) + return err; + + for (i = start; i < num_regs; i++) { + switch (i) { + case MIPS64_EF_R1 ... MIPS64_EF_R25: + /* k0/k1 are ignored. */ + case MIPS64_EF_R28 ... MIPS64_EF_R31: + regs->regs[i - MIPS64_EF_R0] = uregs[i]; + break; + case MIPS64_EF_LO: + regs->lo = uregs[i]; + break; + case MIPS64_EF_HI: + regs->hi = uregs[i]; + break; + case MIPS64_EF_CP0_EPC: + regs->cp0_epc = uregs[i]; + break; + } + } + + return 0; +} + +#endif /* CONFIG_64BIT */ + static int fpr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, @@ -322,14 +447,16 @@ enum mips_regset { REGSET_FPR, }; +#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32) + static const struct user_regset mips_regsets[] = { [REGSET_GPR] = { .core_note_type = NT_PRSTATUS, .n = ELF_NGREG, .size = sizeof(unsigned int), .align = sizeof(unsigned int), - .get = gpr_get, - .set = gpr_set, + .get = gpr32_get, + .set = gpr32_set, }, [REGSET_FPR] = { .core_note_type = NT_PRFPREG, @@ -349,14 +476,18 @@ static const struct user_regset_view user_mips_view = { .n = ARRAY_SIZE(mips_regsets), }; +#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */ + +#ifdef CONFIG_64BIT + static const struct user_regset mips64_regsets[] = { [REGSET_GPR] = { .core_note_type = NT_PRSTATUS, .n = ELF_NGREG, .size = sizeof(unsigned long), .align = sizeof(unsigned long), - .get = gpr_get, - .set = gpr_set, + .get = gpr64_get, + .set = gpr64_set, }, [REGSET_FPR] = { .core_note_type = NT_PRFPREG, @@ -369,25 +500,26 @@ static const struct user_regset mips64_regsets[] = { }; static const struct user_regset_view user_mips64_view = { - .name = "mips", + .name = "mips64", .e_machine = ELF_ARCH, .ei_osabi = ELF_OSABI, .regsets = mips64_regsets, - .n = ARRAY_SIZE(mips_regsets), + .n = ARRAY_SIZE(mips64_regsets), }; +#endif /* CONFIG_64BIT */ + const struct user_regset_view *task_user_regset_view(struct task_struct *task) { #ifdef CONFIG_32BIT return &user_mips_view; -#endif - +#else #ifdef CONFIG_MIPS32_O32 - if (test_thread_flag(TIF_32BIT_REGS)) - return &user_mips_view; + if (test_tsk_thread_flag(task, TIF_32BIT_REGS)) + return &user_mips_view; #endif - return &user_mips64_view; +#endif } long arch_ptrace(struct task_struct *child, long request, @@ -593,7 +725,7 @@ long arch_ptrace(struct task_struct *child, long request, break; #endif case FPC_CSR: - child->thread.fpu.fcr31 = data; + child->thread.fpu.fcr31 = data & ~FPU_CSR_ALL_X; break; case DSP_BASE ... DSP_BASE + 5: { dspreg_t *dregs; diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c index 3d60f77..ea585cf 100644 --- a/arch/mips/kernel/signal32.c +++ b/arch/mips/kernel/signal32.c @@ -370,8 +370,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) { - memset(to, 0, sizeof *to); - if (copy_from_user(to, from, 3*sizeof(int)) || copy_from_user(to->_sifields._pad, from->_sifields._pad, SI_PAD_SIZE32)) diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 0a022ee..18ed112 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -109,10 +109,10 @@ asmlinkage void start_secondary(void) else #endif /* CONFIG_MIPS_MT_SMTC */ cpu_probe(); - cpu_report(); per_cpu_trap_init(false); mips_clockevent_init(); mp_ops->init_secondary(); + cpu_report(); /* * XXX parity protection should be folded in here when it's converted diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index c369a5d..b897dde 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -605,7 +605,6 @@ static void emulate_load_store_insn(struct pt_regs *regs, case sdc1_op: die_if_kernel("Unaligned FP access in kernel code", regs); BUG_ON(!used_math()); - BUG_ON(!is_fpu_owner()); lose_fpu(1); /* Save FPU state for the emulator. */ res = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1, diff --git a/arch/mips/kvm/kvm_locore.S b/arch/mips/kvm/kvm_locore.S index bbace09..03a2db5 100644 --- a/arch/mips/kvm/kvm_locore.S +++ b/arch/mips/kvm/kvm_locore.S @@ -428,7 +428,7 @@ __kvm_mips_return_to_guest: /* Setup status register for running guest in UM */ .set at or v1, v1, (ST0_EXL | KSU_USER | ST0_IE) - and v1, v1, ~ST0_CU0 + and v1, v1, ~(ST0_CU0 | ST0_MX) .set noat mtc0 v1, CP0_STATUS ehb diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c index 3e0ff8d..897c605 100644 --- a/arch/mips/kvm/kvm_mips.c +++ b/arch/mips/kvm/kvm_mips.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -418,11 +419,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) vcpu->mmio_needed = 0; } + lose_fpu(1); + + local_irq_disable(); /* Check if we have any exceptions/interrupts pending */ kvm_mips_deliver_interrupts(vcpu, kvm_read_c0_guest_cause(vcpu->arch.cop0)); - local_irq_disable(); kvm_guest_enter(); r = __kvm_mips_vcpu_run(run, vcpu); @@ -1021,9 +1024,6 @@ void kvm_mips_set_c0_status(void) { uint32_t status = read_c0_status(); - if (cpu_has_fpu) - status |= (ST0_CU1); - if (cpu_has_dsp) status |= (ST0_MX); diff --git a/arch/mips/kvm/kvm_mips_emul.c b/arch/mips/kvm/kvm_mips_emul.c index e75ef82..c76f297 100644 --- a/arch/mips/kvm/kvm_mips_emul.c +++ b/arch/mips/kvm/kvm_mips_emul.c @@ -1626,7 +1626,7 @@ kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run) if (vcpu->mmio_needed == 2) *gpr = *(int16_t *) run->mmio.data; else - *gpr = *(int16_t *) run->mmio.data; + *gpr = *(uint16_t *)run->mmio.data; break; case 1: diff --git a/arch/mips/kvm/trace.h b/arch/mips/kvm/trace.h index bc9e0f4..e51621e 100644 --- a/arch/mips/kvm/trace.h +++ b/arch/mips/kvm/trace.h @@ -26,18 +26,18 @@ TRACE_EVENT(kvm_exit, TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason), TP_ARGS(vcpu, reason), TP_STRUCT__entry( - __field(struct kvm_vcpu *, vcpu) + __field(unsigned long, pc) __field(unsigned int, reason) ), TP_fast_assign( - __entry->vcpu = vcpu; + __entry->pc = vcpu->arch.pc; __entry->reason = reason; ), TP_printk("[%s]PC: 0x%08lx", kvm_mips_exit_types_str[__entry->reason], - __entry->vcpu->arch.pc) + __entry->pc) ); #endif /* _TRACE_KVM_H */ diff --git a/arch/mips/loongson/common/Makefile b/arch/mips/loongson/common/Makefile index 9e4484c..9005a8d6 100644 --- a/arch/mips/loongson/common/Makefile +++ b/arch/mips/loongson/common/Makefile @@ -11,7 +11,8 @@ obj-$(CONFIG_PCI) += pci.o # Serial port support # obj-$(CONFIG_EARLY_PRINTK) += early_printk.o -obj-$(CONFIG_SERIAL_8250) += serial.o +loongson-serial-$(CONFIG_SERIAL_8250) := serial.o +obj-y += $(loongson-serial-m) $(loongson-serial-y) obj-$(CONFIG_LOONGSON_UART_BASE) += uart_base.o obj-$(CONFIG_LOONGSON_MC146818) += rtc.o diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index becc42b..70ab5d6 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -158,6 +158,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index b234b1b..dd012c5 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -1057,6 +1057,7 @@ static void build_update_entries(u32 **p, unsigned int tmp, unsigned int ptep) struct mips_huge_tlb_info { int huge_pte; int restore_scratch; + bool need_reload_pte; }; static struct mips_huge_tlb_info @@ -1071,6 +1072,7 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l, rv.huge_pte = scratch; rv.restore_scratch = 0; + rv.need_reload_pte = false; if (check_for_high_segbits) { UASM_i_MFC0(p, tmp, C0_BADVADDR); @@ -1259,6 +1261,7 @@ static void build_r4000_tlb_refill_handler(void) } else { htlb_info.huge_pte = K0; htlb_info.restore_scratch = 0; + htlb_info.need_reload_pte = true; vmalloc_mode = refill_noscratch; /* * create the plain linear handler @@ -1295,6 +1298,8 @@ static void build_r4000_tlb_refill_handler(void) } #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT uasm_l_tlb_huge_update(&l, p); + if (htlb_info.need_reload_pte) + UASM_i_LW(&p, htlb_info.huge_pte, 0, K1); build_huge_update_entries(&p, htlb_info.huge_pte, K1); build_huge_tlb_write_entry(&p, &l, &r, K0, tlb_random, htlb_info.restore_scratch); diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c index 3190099..d4ab447 100644 --- a/arch/mips/mti-malta/malta-time.c +++ b/arch/mips/mti-malta/malta-time.c @@ -168,14 +168,17 @@ unsigned int get_c0_compare_int(void) static void __init init_rtc(void) { - /* stop the clock whilst setting it up */ - CMOS_WRITE(RTC_SET | RTC_24H, RTC_CONTROL); + unsigned char freq, ctrl; - /* 32KHz time base */ - CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT); + /* Set 32KHz time base if not already set */ + freq = CMOS_READ(RTC_FREQ_SELECT); + if ((freq & RTC_DIV_CTL) != RTC_REF_CLCK_32KHZ) + CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT); - /* start the clock */ - CMOS_WRITE(RTC_24H, RTC_CONTROL); + /* Ensure SET bit is clear so RTC can run */ + ctrl = CMOS_READ(RTC_CONTROL); + if (ctrl & RTC_SET) + CMOS_WRITE(ctrl & ~RTC_SET, RTC_CONTROL); } void __init plat_time_init(void) diff --git a/arch/mips/oprofile/backtrace.c b/arch/mips/oprofile/backtrace.c index 6854ed5..83a1dfd 100644 --- a/arch/mips/oprofile/backtrace.c +++ b/arch/mips/oprofile/backtrace.c @@ -92,7 +92,7 @@ static inline int unwind_user_frame(struct stackframe *old_frame, /* This marks the end of the previous function, which means we overran. */ break; - stack_size = (unsigned) stack_adjustment; + stack_size = (unsigned long) stack_adjustment; } else if (is_ra_save_ins(&ip)) { int ra_slot = ip.i_format.simmediate; if (ra_slot < 0) diff --git a/arch/mips/power/cpu.c b/arch/mips/power/cpu.c index 521e596..2129e67 100644 --- a/arch/mips/power/cpu.c +++ b/arch/mips/power/cpu.c @@ -7,7 +7,7 @@ * Author: Hu Hongbing * Wu Zhangjin */ -#include +#include #include #include diff --git a/arch/mips/power/hibernate.S b/arch/mips/power/hibernate.S index 32a7c82..e7567c8 100644 --- a/arch/mips/power/hibernate.S +++ b/arch/mips/power/hibernate.S @@ -30,6 +30,8 @@ LEAF(swsusp_arch_suspend) END(swsusp_arch_suspend) LEAF(swsusp_arch_resume) + /* Avoid TLB mismatch during and after kernel resume */ + jal local_flush_tlb_all PTR_L t0, restore_pblist 0: PTR_L t1, PBE_ADDRESS(t0) /* source */ @@ -43,7 +45,6 @@ LEAF(swsusp_arch_resume) bne t1, t3, 1b PTR_L t0, PBE_NEXT(t0) bnez t0, 0b - jal local_flush_tlb_all /* Avoid TLB mismatch after kernel resume */ PTR_LA t0, saved_regs PTR_L ra, PT_R31(t0) PTR_L sp, PT_R29(t0) diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c index 3516cbd..0c2cc5d 100644 --- a/arch/mn10300/mm/fault.c +++ b/arch/mn10300/mm/fault.c @@ -262,6 +262,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 0703acf..230ac20 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -171,6 +171,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 7187664..5db8882 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -48,7 +48,12 @@ cflags-y := -pipe # These flags should be implied by an hppa-linux configuration, but they # are not in gcc 3.2. -cflags-y += -mno-space-regs -mfast-indirect-calls +cflags-y += -mno-space-regs + +# -mfast-indirect-calls is only relevant for 32-bit kernels. +ifndef CONFIG_64BIT +cflags-y += -mfast-indirect-calls +endif # Currently we save and restore fpregs on all kernel entry/interruption paths. # If that gets optimized, we might need to disable the use of fpregs in the diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h index d2d11b7..8121aa6 100644 --- a/arch/parisc/include/asm/ldcw.h +++ b/arch/parisc/include/asm/ldcw.h @@ -33,11 +33,18 @@ #endif /*!CONFIG_PA20*/ -/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*. */ +/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*. + We don't explicitly expose that "*a" may be written as reload + fails to find a register in class R1_REGS when "a" needs to be + reloaded when generating 64-bit PIC code. Instead, we clobber + memory to indicate to the compiler that the assembly code reads + or writes to items other than those listed in the input and output + operands. This may pessimize the code somewhat but __ldcw is + usually used within code blocks surrounded by memory barriors. */ #define __ldcw(a) ({ \ unsigned __ret; \ - __asm__ __volatile__(__LDCW " 0(%2),%0" \ - : "=r" (__ret), "+m" (*(a)) : "r" (a)); \ + __asm__ __volatile__(__LDCW " 0(%1),%0" \ + : "=r" (__ret) : "r" (a) : "memory"); \ __ret; \ }) diff --git a/arch/parisc/include/uapi/asm/shmbuf.h b/arch/parisc/include/uapi/asm/shmbuf.h index 0a3eada..f395cde 100644 --- a/arch/parisc/include/uapi/asm/shmbuf.h +++ b/arch/parisc/include/uapi/asm/shmbuf.h @@ -36,23 +36,16 @@ struct shmid64_ds { unsigned int __unused2; }; -#ifdef CONFIG_64BIT -/* The 'unsigned int' (formerly 'unsigned long') data types below will - * ensure that a 32-bit app calling shmctl(*,IPC_INFO,*) will work on - * a wide kernel, but if some of these values are meant to contain pointers - * they may need to be 'long long' instead. -PB XXX FIXME - */ -#endif struct shminfo64 { - unsigned int shmmax; - unsigned int shmmin; - unsigned int shmmni; - unsigned int shmseg; - unsigned int shmall; - unsigned int __unused1; - unsigned int __unused2; - unsigned int __unused3; - unsigned int __unused4; + unsigned long shmmax; + unsigned long shmmin; + unsigned long shmmni; + unsigned long shmseg; + unsigned long shmall; + unsigned long __unused1; + unsigned long __unused2; + unsigned long __unused3; + unsigned long __unused4; }; #endif /* _PARISC_SHMBUF_H */ diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h index a2fa2971..f5645d6 100644 --- a/arch/parisc/include/uapi/asm/signal.h +++ b/arch/parisc/include/uapi/asm/signal.h @@ -69,8 +69,6 @@ #define SA_NOMASK SA_NODEFER #define SA_ONESHOT SA_RESETHAND -#define SA_RESTORER 0x04000000 /* obsolete -- ignored */ - #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 8387860..7ef22e3 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -74,7 +74,7 @@ ENTRY(linux_gateway_page) /* ADDRESS 0xb0 to 0xb8, lws uses two insns for entry */ /* Light-weight-syscall entry must always be located at 0xb0 */ /* WARNING: Keep this number updated with table size changes */ -#define __NR_lws_entries (2) +#define __NR_lws_entries (3) lws_entry: gate lws_start, %r0 /* increase privilege */ @@ -502,7 +502,7 @@ lws_exit: /*************************************************** - Implementing CAS as an atomic operation: + Implementing 32bit CAS as an atomic operation: %r26 - Address to examine %r25 - Old value to check (old) @@ -659,6 +659,230 @@ cas_action: ASM_EXCEPTIONTABLE_ENTRY(2b-linux_gateway_page, 3b-linux_gateway_page) + /*************************************************** + New CAS implementation which uses pointers and variable size + information. The value pointed by old and new MUST NOT change + while performing CAS. The lock only protect the value at %r26. + + %r26 - Address to examine + %r25 - Pointer to the value to check (old) + %r24 - Pointer to the value to set (new) + %r23 - Size of the variable (0/1/2/3 for 8/16/32/64 bit) + %r28 - Return non-zero on failure + %r21 - Kernel error code + + %r21 has the following meanings: + + EAGAIN - CAS is busy, ldcw failed, try again. + EFAULT - Read or write failed. + + Scratch: r20, r22, r28, r29, r1, fr4 (32bit for 64bit CAS only) + + ****************************************************/ + + /* ELF32 Process entry path */ +lws_compare_and_swap_2: +#ifdef CONFIG_64BIT + /* Clip the input registers */ + depdi 0, 31, 32, %r26 + depdi 0, 31, 32, %r25 + depdi 0, 31, 32, %r24 + depdi 0, 31, 32, %r23 +#endif + + /* Check the validity of the size pointer */ + subi,>>= 4, %r23, %r0 + b,n lws_exit_nosys + + /* Jump to the functions which will load the old and new values into + registers depending on the their size */ + shlw %r23, 2, %r29 + blr %r29, %r0 + nop + + /* 8bit load */ +4: ldb 0(%sr3,%r25), %r25 + b cas2_lock_start +5: ldb 0(%sr3,%r24), %r24 + nop + nop + nop + nop + nop + + /* 16bit load */ +6: ldh 0(%sr3,%r25), %r25 + b cas2_lock_start +7: ldh 0(%sr3,%r24), %r24 + nop + nop + nop + nop + nop + + /* 32bit load */ +8: ldw 0(%sr3,%r25), %r25 + b cas2_lock_start +9: ldw 0(%sr3,%r24), %r24 + nop + nop + nop + nop + nop + + /* 64bit load */ +#ifdef CONFIG_64BIT +10: ldd 0(%sr3,%r25), %r25 +11: ldd 0(%sr3,%r24), %r24 +#else + /* Load new value into r22/r23 - high/low */ +10: ldw 0(%sr3,%r25), %r22 +11: ldw 4(%sr3,%r25), %r23 + /* Load new value into fr4 for atomic store later */ +12: flddx 0(%sr3,%r24), %fr4 +#endif + +cas2_lock_start: + /* Load start of lock table */ + ldil L%lws_lock_start, %r20 + ldo R%lws_lock_start(%r20), %r28 + + /* Extract four bits from r26 and hash lock (Bits 4-7) */ + extru %r26, 27, 4, %r20 + + /* Find lock to use, the hash is either one of 0 to + 15, multiplied by 16 (keep it 16-byte aligned) + and add to the lock table offset. */ + shlw %r20, 4, %r20 + add %r20, %r28, %r20 + + rsm PSW_SM_I, %r0 /* Disable interrupts */ + /* COW breaks can cause contention on UP systems */ + LDCW 0(%sr2,%r20), %r28 /* Try to acquire the lock */ + cmpb,<>,n %r0, %r28, cas2_action /* Did we get it? */ +cas2_wouldblock: + ldo 2(%r0), %r28 /* 2nd case */ + ssm PSW_SM_I, %r0 + b lws_exit /* Contended... */ + ldo -EAGAIN(%r0), %r21 /* Spin in userspace */ + + /* + prev = *addr; + if ( prev == old ) + *addr = new; + return prev; + */ + + /* NOTES: + This all works becuse intr_do_signal + and schedule both check the return iasq + and see that we are on the kernel page + so this process is never scheduled off + or is ever sent any signal of any sort, + thus it is wholly atomic from usrspaces + perspective + */ +cas2_action: + /* Jump to the correct function */ + blr %r29, %r0 + /* Set %r28 as non-zero for now */ + ldo 1(%r0),%r28 + + /* 8bit CAS */ +13: ldb,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r25, %r0 + b,n cas2_end +14: stb,ma %r24, 0(%sr3,%r26) + b cas2_end + copy %r0, %r28 + nop + nop + + /* 16bit CAS */ +15: ldh,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r25, %r0 + b,n cas2_end +16: sth,ma %r24, 0(%sr3,%r26) + b cas2_end + copy %r0, %r28 + nop + nop + + /* 32bit CAS */ +17: ldw,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r25, %r0 + b,n cas2_end +18: stw,ma %r24, 0(%sr3,%r26) + b cas2_end + copy %r0, %r28 + nop + nop + + /* 64bit CAS */ +#ifdef CONFIG_64BIT +19: ldd,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r25, %r0 + b,n cas2_end +20: std,ma %r24, 0(%sr3,%r26) + copy %r0, %r28 +#else + /* Compare first word */ +19: ldw,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r22, %r0 + b,n cas2_end + /* Compare second word */ +20: ldw,ma 4(%sr3,%r26), %r29 + sub,= %r29, %r23, %r0 + b,n cas2_end + /* Perform the store */ +21: fstdx %fr4, 0(%sr3,%r26) + copy %r0, %r28 +#endif + +cas2_end: + /* Free lock */ + stw,ma %r20, 0(%sr2,%r20) + /* Enable interrupts */ + ssm PSW_SM_I, %r0 + /* Return to userspace, set no error */ + b lws_exit + copy %r0, %r21 + +22: + /* Error occurred on load or store */ + /* Free lock */ + stw %r20, 0(%sr2,%r20) + ssm PSW_SM_I, %r0 + ldo 1(%r0),%r28 + b lws_exit + ldo -EFAULT(%r0),%r21 /* set errno */ + nop + nop + nop + + /* Exception table entries, for the load and store, return EFAULT. + Each of the entries must be relocated. */ + ASM_EXCEPTIONTABLE_ENTRY(4b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(5b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(6b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(7b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(8b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(9b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(10b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(11b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(13b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(14b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(15b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(16b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(17b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(18b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(19b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(20b-linux_gateway_page, 22b-linux_gateway_page) +#ifndef CONFIG_64BIT + ASM_EXCEPTIONTABLE_ENTRY(12b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(21b-linux_gateway_page, 22b-linux_gateway_page) +#endif + /* Make sure nothing else is placed on this page */ .align PAGE_SIZE END(linux_gateway_page) @@ -675,8 +899,9 @@ ENTRY(end_linux_gateway_page) /* Light-weight-syscall table */ /* Start of lws table. */ ENTRY(lws_table) - LWS_ENTRY(compare_and_swap32) /* 0 - ELF32 Atomic compare and swap */ - LWS_ENTRY(compare_and_swap64) /* 1 - ELF64 Atomic compare and swap */ + LWS_ENTRY(compare_and_swap32) /* 0 - ELF32 Atomic 32bit CAS */ + LWS_ENTRY(compare_and_swap64) /* 1 - ELF64 Atomic 32bit CAS */ + LWS_ENTRY(compare_and_swap_2) /* 2 - ELF32 Atomic 64bit CAS */ END(lws_table) /* End of lws table */ diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 7dd8a3b..fc77d53 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -286,11 +286,11 @@ ENTRY_COMP(msgsnd) ENTRY_COMP(msgrcv) ENTRY_SAME(msgget) /* 190 */ - ENTRY_SAME(msgctl) - ENTRY_SAME(shmat) + ENTRY_COMP(msgctl) + ENTRY_COMP(shmat) ENTRY_SAME(shmdt) ENTRY_SAME(shmget) - ENTRY_SAME(shmctl) /* 195 */ + ENTRY_COMP(shmctl) /* 195 */ ENTRY_SAME(ni_syscall) /* streams1 */ ENTRY_SAME(ni_syscall) /* streams2 */ ENTRY_SAME(lstat64) @@ -323,7 +323,7 @@ ENTRY_SAME(epoll_ctl) /* 225 */ ENTRY_SAME(epoll_wait) ENTRY_SAME(remap_file_pages) - ENTRY_SAME(semtimedop) + ENTRY_COMP(semtimedop) ENTRY_COMP(mq_open) ENTRY_SAME(mq_unlink) /* 230 */ ENTRY_COMP(mq_timedsend) diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index d72197f..d27e388 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -256,6 +256,8 @@ good_area: */ if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto bad_area; BUG(); diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi index 1382fec..7fcb1ac 100644 --- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi @@ -50,6 +50,7 @@ ethernet@b0000 { fsl,num_tx_queues = <0x8>; fsl,magic-packet; local-mac-address = [ 00 00 00 00 00 00 ]; + ranges; queue-group@b0000 { #address-cells = <1>; diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi index 221cd2e..9f25427 100644 --- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi @@ -50,6 +50,7 @@ ethernet@b1000 { fsl,num_tx_queues = <0x8>; fsl,magic-packet; local-mac-address = [ 00 00 00 00 00 00 ]; + ranges; queue-group@b1000 { #address-cells = <1>; diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi index 61456c3..cd7c318 100644 --- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi +++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi @@ -49,6 +49,7 @@ ethernet@b2000 { fsl,num_tx_queues = <0x8>; fsl,magic-packet; local-mac-address = [ 00 00 00 00 00 00 ]; + ranges; queue-group@b2000 { #address-cells = <1>; diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c index f9e8b94..b51da91 100644 --- a/arch/powerpc/crypto/sha1.c +++ b/arch/powerpc/crypto/sha1.c @@ -154,4 +154,5 @@ module_exit(sha1_powerpc_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm"); -MODULE_ALIAS("sha1-powerpc"); +MODULE_ALIAS_CRYPTO("sha1"); +MODULE_ALIAS_CRYPTO("sha1-powerpc"); diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index ad3025d..f207868 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -57,10 +57,10 @@ struct machdep_calls { void (*hpte_removebolted)(unsigned long ea, int psize, int ssize); void (*flush_hash_range)(unsigned long number, int local); - void (*hugepage_invalidate)(struct mm_struct *mm, + void (*hugepage_invalidate)(unsigned long vsid, + unsigned long addr, unsigned char *hpte_slot_array, - unsigned long addr, int psize); - + int psize, int ssize); /* special for kexec, to be called in real mode, linear mapping is * destroyed as well */ void (*hpte_clear_all)(void); diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index eb92610..7b3d54f 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -413,7 +413,7 @@ static inline char *get_hpte_slot_array(pmd_t *pmdp) } extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp); + pmd_t *pmdp, unsigned long old_pmd); #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot); diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h index d836d94..9ecede1 100644 --- a/arch/powerpc/include/asm/pte-hash64-64k.h +++ b/arch/powerpc/include/asm/pte-hash64-64k.h @@ -46,11 +46,31 @@ * in order to deal with 64K made of 4K HW pages. Thus we override the * generic accessors and iterators here */ -#define __real_pte(e,p) ((real_pte_t) { \ - (e), (pte_val(e) & _PAGE_COMBO) ? \ - (pte_val(*((p) + PTRS_PER_PTE))) : 0 }) -#define __rpte_to_hidx(r,index) ((pte_val((r).pte) & _PAGE_COMBO) ? \ - (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf)) +#define __real_pte __real_pte +static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) +{ + real_pte_t rpte; + + rpte.pte = pte; + rpte.hidx = 0; + if (pte_val(pte) & _PAGE_COMBO) { + /* + * Make sure we order the hidx load against the _PAGE_COMBO + * check. The store side ordering is done in __hash_page_4K + */ + smp_rmb(); + rpte.hidx = pte_val(*((ptep) + PTRS_PER_PTE)); + } + return rpte; +} + +static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) +{ + if ((pte_val(rpte.pte) & _PAGE_COMBO)) + return (rpte.hidx >> (index<<2)) & 0xf; + return (pte_val(rpte.pte) >> 12) & 0xf; +} + #define __rpte_to_pte(r) ((r).pte) #define __rpte_sub_valid(rpte, index) \ (pte_val(rpte.pte) & (_PAGE_HPTE_SUB0 >> (index))) diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 279b80f..c0c61fa 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -47,6 +47,12 @@ STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE) #define STACK_FRAME_MARKER 12 +#if defined(_CALL_ELF) && _CALL_ELF == 2 +#define STACK_FRAME_MIN_SIZE 32 +#else +#define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD +#endif + /* Size of dummy stack frame allocated when calling signal handler. */ #define __SIGNAL_FRAMESIZE 128 #define __SIGNAL_FRAMESIZE32 64 @@ -60,6 +66,7 @@ #define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773) #define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD) #define STACK_FRAME_MARKER 2 +#define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD /* Size of stack frame allocated when calling signal handler. */ #define __SIGNAL_FRAMESIZE 64 diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 35aa339..4dbe072 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -61,6 +61,7 @@ static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) static inline int arch_spin_is_locked(arch_spinlock_t *lock) { + smp_mb(); return !arch_spin_value_unlocked(*lock); } diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 2912b87..3eb36ce 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -61,12 +61,22 @@ struct cache_type_info { }; /* These are used to index the cache_type_info array. */ -#define CACHE_TYPE_UNIFIED 0 -#define CACHE_TYPE_INSTRUCTION 1 -#define CACHE_TYPE_DATA 2 +#define CACHE_TYPE_UNIFIED 0 /* cache-size, cache-block-size, etc. */ +#define CACHE_TYPE_UNIFIED_D 1 /* d-cache-size, d-cache-block-size, etc */ +#define CACHE_TYPE_INSTRUCTION 2 +#define CACHE_TYPE_DATA 3 static const struct cache_type_info cache_type_info[] = { { + /* Embedded systems that use cache-size, cache-block-size, + * etc. for the Unified (typically L2) cache. */ + .name = "Unified", + .size_prop = "cache-size", + .line_size_props = { "cache-line-size", + "cache-block-size", }, + .nr_sets_prop = "cache-sets", + }, + { /* PowerPC Processor binding says the [di]-cache-* * must be equal on unified caches, so just use * d-cache properties. */ @@ -293,7 +303,8 @@ static struct cache *cache_find_first_sibling(struct cache *cache) { struct cache *iter; - if (cache->type == CACHE_TYPE_UNIFIED) + if (cache->type == CACHE_TYPE_UNIFIED || + cache->type == CACHE_TYPE_UNIFIED_D) return cache; list_for_each_entry(iter, &cache_list, list) @@ -324,16 +335,29 @@ static bool cache_node_is_unified(const struct device_node *np) return of_get_property(np, "cache-unified", NULL); } -static struct cache *cache_do_one_devnode_unified(struct device_node *node, - int level) +/* + * Unified caches can have two different sets of tags. Most embedded + * use cache-size, etc. for the unified cache size, but open firmware systems + * use d-cache-size, etc. Check on initialization for which type we have, and + * return the appropriate structure type. Assume it's embedded if it isn't + * open firmware. If it's yet a 3rd type, then there will be missing entries + * in /sys/devices/system/cpu/cpu0/cache/index2/, and this code will need + * to be extended further. + */ +static int cache_is_unified_d(const struct device_node *np) { - struct cache *cache; + return of_get_property(np, + cache_type_info[CACHE_TYPE_UNIFIED_D].size_prop, NULL) ? + CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED; +} +/* + */ +static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level) +{ pr_debug("creating L%d ucache for %s\n", level, node->full_name); - cache = new_cache(CACHE_TYPE_UNIFIED, level, node); - - return cache; + return new_cache(cache_is_unified_d(node), level, node); } static struct cache *cache_do_one_devnode_split(struct device_node *node, diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 38d5073..5193116 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1422,7 +1422,7 @@ machine_check_handle_early: bne 9f /* continue in V mode if we are. */ 5: -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER /* * We are coming from kernel context. Check if we are coming from * guest. if yes, then we can continue. We will fall through diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index 27c93f4..fc0927a 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -78,7 +78,7 @@ static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits) } if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) { if (cur_cpu_spec && cur_cpu_spec->flush_tlb) - cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE); + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET); /* reset error bits */ dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB; } @@ -109,7 +109,7 @@ static long mce_handle_common_ierror(uint64_t srr1) break; case P7_SRR1_MC_IFETCH_TLB_MULTIHIT: if (cur_cpu_spec && cur_cpu_spec->flush_tlb) { - cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE); + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET); handled = 1; } break; diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 4e47db6..e881e3f 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -967,8 +967,6 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s) int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from) { - memset(to, 0, sizeof *to); - if (copy_from_user(to, from, 3*sizeof(int)) || copy_from_user(to->_sifields._pad, from->_sifields._pad, SI_PAD_SIZE32)) diff --git a/arch/powerpc/kernel/suspend.c b/arch/powerpc/kernel/suspend.c index 0167d53..a531154 100644 --- a/arch/powerpc/kernel/suspend.c +++ b/arch/powerpc/kernel/suspend.c @@ -9,9 +9,7 @@ #include #include - -/* References to section boundaries */ -extern const void __nosave_begin, __nosave_end; +#include /* * pfn_is_nosave - check if given pfn is in the 'nosave' section diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index 75702e2..f7089fc 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -69,8 +69,12 @@ static void udbg_uart_putc(char c) static int udbg_uart_getc_poll(void) { - if (!udbg_uart_in || !(udbg_uart_in(UART_LSR) & LSR_DR)) + if (!udbg_uart_in) + return -1; + + if (!(udbg_uart_in(UART_LSR) & LSR_DR)) return udbg_uart_in(UART_RBR); + return -1; } diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S index 47afd08..fe7e97a 100644 --- a/arch/powerpc/kernel/vdso32/getcpu.S +++ b/arch/powerpc/kernel/vdso32/getcpu.S @@ -30,8 +30,8 @@ V_FUNCTION_BEGIN(__kernel_getcpu) .cfi_startproc mfspr r5,SPRN_USPRG3 - cmpdi cr0,r3,0 - cmpdi cr1,r4,0 + cmpwi cr0,r3,0 + cmpwi cr1,r4,0 clrlwi r6,r5,16 rlwinm r7,r5,16,31-15,31-0 beq cr0,1f diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index f096e72..1db6851 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -213,6 +213,7 @@ SECTIONS *(.opd) } + . = ALIGN(256); .got : AT(ADDR(.got) - LOAD_OFFSET) { __toc_start = .; #ifndef CONFIG_RELOCATABLE diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c index 0c9c8d7..170a034 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -70,12 +70,16 @@ void __rw_yield(arch_rwlock_t *rw) void arch_spin_unlock_wait(arch_spinlock_t *lock) { + smp_mb(); + while (lock->slock) { HMT_low(); if (SHARED_PROCESSOR) __spin_yield(lock); } HMT_medium(); + + smp_mb(); } EXPORT_SYMBOL(arch_spin_unlock_wait); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 51ab9e7..010fabf 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -432,6 +432,8 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, flags); if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { + if (fault & VM_FAULT_SIGSEGV) + goto bad_area; rc = mm_fault_error(regs, address, fault); if (rc >= MM_FAULT_RETURN) goto bail; diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 3ea26c2..838de8e 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -418,18 +418,18 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn, local_irq_restore(flags); } -static void native_hugepage_invalidate(struct mm_struct *mm, +static void native_hugepage_invalidate(unsigned long vsid, + unsigned long addr, unsigned char *hpte_slot_array, - unsigned long addr, int psize) + int psize, int ssize) { - int ssize = 0, i; - int lock_tlbie; + int i; struct hash_pte *hptep; int actual_psize = MMU_PAGE_16M; unsigned int max_hpte_count, valid; unsigned long flags, s_addr = addr; unsigned long hpte_v, want_v, shift; - unsigned long hidx, vpn = 0, vsid, hash, slot; + unsigned long hidx, vpn = 0, hash, slot; shift = mmu_psize_defs[psize].shift; max_hpte_count = 1U << (PMD_SHIFT - shift); @@ -443,15 +443,6 @@ static void native_hugepage_invalidate(struct mm_struct *mm, /* get the vpn */ addr = s_addr + (i * (1ul << shift)); - if (!is_kernel_addr(addr)) { - ssize = user_segment_size(addr); - vsid = get_vsid(mm->context.id, addr, ssize); - WARN_ON(vsid == 0); - } else { - vsid = get_kernel_vsid(addr, mmu_kernel_ssize); - ssize = mmu_kernel_ssize; - } - vpn = hpt_vpn(addr, vsid, ssize); hash = hpt_hash(vpn, shift, ssize); if (hidx & _PTEIDX_SECONDARY) @@ -471,22 +462,13 @@ static void native_hugepage_invalidate(struct mm_struct *mm, else /* Invalidate the hpte. NOTE: this also unlocks it */ hptep->v = 0; + /* + * We need to do tlb invalidate for all the address, tlbie + * instruction compares entry_VA in tlb with the VA specified + * here + */ + tlbie(vpn, psize, actual_psize, ssize, 0); } - /* - * Since this is a hugepage, we just need a single tlbie. - * use the last vpn. - */ - lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); - if (lock_tlbie) - raw_spin_lock(&native_tlbie_lock); - - asm volatile("ptesync":::"memory"); - __tlbie(vpn, psize, actual_psize, ssize); - asm volatile("eieio; tlbsync; ptesync":::"memory"); - - if (lock_tlbie) - raw_spin_unlock(&native_tlbie_lock); - local_irq_restore(flags); } diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index 826893f..5f5e632 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -18,6 +18,57 @@ #include #include +static void invalidate_old_hpte(unsigned long vsid, unsigned long addr, + pmd_t *pmdp, unsigned int psize, int ssize) +{ + int i, max_hpte_count, valid; + unsigned long s_addr; + unsigned char *hpte_slot_array; + unsigned long hidx, shift, vpn, hash, slot; + + s_addr = addr & HPAGE_PMD_MASK; + hpte_slot_array = get_hpte_slot_array(pmdp); + /* + * IF we try to do a HUGE PTE update after a withdraw is done. + * we will find the below NULL. This happens when we do + * split_huge_page_pmd + */ + if (!hpte_slot_array) + return; + + if (ppc_md.hugepage_invalidate) + return ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array, + psize, ssize); + /* + * No bluk hpte removal support, invalidate each entry + */ + shift = mmu_psize_defs[psize].shift; + max_hpte_count = HPAGE_PMD_SIZE >> shift; + for (i = 0; i < max_hpte_count; i++) { + /* + * 8 bits per each hpte entries + * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit] + */ + valid = hpte_valid(hpte_slot_array, i); + if (!valid) + continue; + hidx = hpte_hash_index(hpte_slot_array, i); + + /* get the vpn */ + addr = s_addr + (i * (1ul << shift)); + vpn = hpt_vpn(addr, vsid, ssize); + hash = hpt_hash(vpn, shift, ssize); + if (hidx & _PTEIDX_SECONDARY) + hash = ~hash; + + slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; + slot += hidx & _PTEIDX_GROUP_IX; + ppc_md.hpte_invalidate(slot, vpn, psize, + MMU_PAGE_16M, ssize, 0); + } +} + + int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, pmd_t *pmdp, unsigned long trap, int local, int ssize, unsigned int psize) @@ -33,7 +84,9 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, * atomically mark the linux large page PMD busy and dirty */ do { - old_pmd = pmd_val(*pmdp); + pmd_t pmd = ACCESS_ONCE(*pmdp); + + old_pmd = pmd_val(pmd); /* If PMD busy, retry the access */ if (unlikely(old_pmd & _PAGE_BUSY)) return 0; @@ -85,6 +138,15 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, vpn = hpt_vpn(ea, vsid, ssize); hash = hpt_hash(vpn, shift, ssize); hpte_slot_array = get_hpte_slot_array(pmdp); + if (psize == MMU_PAGE_4K) { + /* + * invalidate the old hpte entry if we have that mapped via 64K + * base page size. This is because demote_segment won't flush + * hash page table entries. + */ + if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO)) + invalidate_old_hpte(vsid, ea, pmdp, MMU_PAGE_64K, ssize); + } valid = hpte_valid(hpte_slot_array, index); if (valid) { @@ -107,11 +169,8 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, * safely update this here. */ valid = 0; - new_pmd &= ~_PAGE_HPTEFLAGS; hpte_slot_array[index] = 0; - } else - /* clear the busy bits and set the hash pte bits */ - new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE; + } } if (!valid) { @@ -119,11 +178,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, /* insert new entry */ pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT; -repeat: - hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; - - /* clear the busy bits and set the hash pte bits */ - new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE; + new_pmd |= _PAGE_HASHPTE; /* Add in WIMG bits */ rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | @@ -132,6 +187,8 @@ repeat: * enable the memory coherence always */ rflags |= HPTE_R_M; +repeat: + hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; /* Insert into the hash table, primary slot */ slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0, @@ -172,8 +229,17 @@ repeat: mark_hpte_slot_valid(hpte_slot_array, index, slot); } /* - * No need to use ldarx/stdcx here + * Mark the pte with _PAGE_COMBO, if we are trying to hash it with + * base page size 4k. + */ + if (psize == MMU_PAGE_4K) + new_pmd |= _PAGE_COMBO; + /* + * The hpte valid is stored in the pgtable whose address is in the + * second half of the PMD. Order this against clearing of the busy bit in + * huge pmd. */ + smp_wmb(); *pmdp = __pmd(new_pmd & ~_PAGE_BUSY); return 0; } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 30a42e2..a5fff17 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -610,8 +610,8 @@ static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action, case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: unmap_cpu_from_node(lcpu); - break; ret = NOTIFY_OK; + break; #endif } return ret; diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 62bf5e8..c64da56 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -538,7 +538,7 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, *pmdp = __pmd((old & ~clr) | set); #endif if (old & _PAGE_HASHPTE) - hpte_do_hugepage_flush(mm, addr, pmdp); + hpte_do_hugepage_flush(mm, addr, pmdp, old); return old; } @@ -645,7 +645,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, if (!(old & _PAGE_SPLITTING)) { /* We need to flush the hpte */ if (old & _PAGE_HASHPTE) - hpte_do_hugepage_flush(vma->vm_mm, address, pmdp); + hpte_do_hugepage_flush(vma->vm_mm, address, pmdp, old); } } @@ -718,7 +718,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, * neesd to be flushed. */ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp) + pmd_t *pmdp, unsigned long old_pmd) { int ssize, i; unsigned long s_addr; @@ -740,12 +740,29 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, if (!hpte_slot_array) return; - /* get the base page size */ + /* get the base page size,vsid and segment size */ +#ifdef CONFIG_DEBUG_VM psize = get_slice_psize(mm, s_addr); + BUG_ON(psize == MMU_PAGE_16M); +#endif + if (old_pmd & _PAGE_COMBO) + psize = MMU_PAGE_4K; + else + psize = MMU_PAGE_64K; + + if (!is_kernel_addr(s_addr)) { + ssize = user_segment_size(s_addr); + vsid = get_vsid(mm->context.id, s_addr, ssize); + WARN_ON(vsid == 0); + } else { + vsid = get_kernel_vsid(s_addr, mmu_kernel_ssize); + ssize = mmu_kernel_ssize; + } if (ppc_md.hugepage_invalidate) - return ppc_md.hugepage_invalidate(mm, hpte_slot_array, - s_addr, psize); + return ppc_md.hugepage_invalidate(vsid, s_addr, + hpte_slot_array, + psize, ssize); /* * No bluk hpte removal support, invalidate each entry */ @@ -763,15 +780,6 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, /* get the vpn */ addr = s_addr + (i * (1ul << shift)); - if (!is_kernel_addr(addr)) { - ssize = user_segment_size(addr); - vsid = get_vsid(mm->context.id, addr, ssize); - WARN_ON(vsid == 0); - } else { - vsid = get_kernel_vsid(addr, mmu_kernel_ssize); - ssize = mmu_kernel_ssize; - } - vpn = hpt_vpn(addr, vsid, ssize); hash = hpt_hash(vpn, shift, ssize); if (hidx & _PTEIDX_SECONDARY) diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index c99f651..9adda57 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -216,7 +216,7 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start, if (!(pte & _PAGE_HASHPTE)) continue; if (unlikely(hugepage_shift && pmd_trans_huge(*(pmd_t *)pte))) - hpte_do_hugepage_flush(mm, start, (pmd_t *)pte); + hpte_do_hugepage_flush(mm, start, (pmd_t *)ptep, pte); else hpte_need_flush(mm, start, ptep, pte, 0); } diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index 74d1e78..ead5535 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -35,7 +35,7 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp) return 0; /* must be 16-byte aligned */ if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD)) return 0; - if (sp >= prev_sp + STACK_FRAME_OVERHEAD) + if (sp >= prev_sp + STACK_FRAME_MIN_SIZE) return 1; /* * sp could decrease when we jump off an interrupt stack @@ -243,7 +243,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry, sp = regs->gpr[1]; perf_callchain_store(entry, next_ip); - for (;;) { + while (entry->nr < PERF_MAX_STACK_DEPTH) { fp = (unsigned long __user *) sp; if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp)) return; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 38265dc..65dfbd0 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -124,7 +124,16 @@ static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {} static bool regs_use_siar(struct pt_regs *regs) { - return !!regs->result; + /* + * When we take a performance monitor exception the regs are setup + * using perf_read_regs() which overloads some fields, in particular + * regs->result to tell us whether to use SIAR. + * + * However if the regs are from another exception, eg. a syscall, then + * they have not been setup using perf_read_regs() and so regs->result + * is something random. + */ + return ((TRAP(regs) == 0xf00) && regs->result); } /* diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 2b90ff8..59ef76c 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -197,7 +197,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages, io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset); - for (i = 0; i < npages; i++, uaddr += tbl->it_page_shift) + for (i = 0; i < npages; i++, uaddr += (1 << tbl->it_page_shift)) io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask); mb(); diff --git a/arch/powerpc/platforms/cell/spu_fault.c b/arch/powerpc/platforms/cell/spu_fault.c index 641e727..62f3e4e 100644 --- a/arch/powerpc/platforms/cell/spu_fault.c +++ b/arch/powerpc/platforms/cell/spu_fault.c @@ -75,7 +75,7 @@ int spu_handle_mm_fault(struct mm_struct *mm, unsigned long ea, if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; goto out_unlock; - } else if (*flt & VM_FAULT_SIGBUS) { + } else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) { ret = -EFAULT; goto out_unlock; } diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 87ba7cf..65d633f 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -164,7 +164,7 @@ static void spufs_prune_dir(struct dentry *dir) struct dentry *dentry, *tmp; mutex_lock(&dir->d_inode->i_mutex); - list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_u.d_child) { + list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) { spin_lock(&dentry->d_lock); if (!(d_unhashed(dentry)) && dentry->d_inode) { dget_dlock(dentry); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 3b2b4fb..d558b85 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -491,6 +491,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, set_dma_ops(&pdev->dev, &dma_iommu_ops); set_iommu_table_base(&pdev->dev, &pe->tce32_table); } + *pdev->dev.dma_mask = dma_mask; return 0; } @@ -901,7 +902,6 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, unsigned int is_64, struct msi_msg *msg) { struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev); - struct pci_dn *pdn = pci_get_pdn(dev); struct irq_data *idata; struct irq_chip *ichip; unsigned int xive_num = hwirq - phb->msi_base; @@ -917,7 +917,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, return -ENXIO; /* Force 32-bit MSI on some broken devices */ - if (pdn && pdn->force_32bit_msi) + if (dev->no_64bit_msi) is_64 = 0; /* Assign XIVE to PE */ diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 8518817..52c1162 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -1,3 +1,4 @@ + /* * Support PCI/PCIe on PowerNV platforms * @@ -50,9 +51,8 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); struct pnv_phb *phb = hose->private_data; - struct pci_dn *pdn = pci_get_pdn(pdev); - if (pdn && pdn->force_32bit_msi && !phb->msi32_support) + if (pdev->no_64bit_msi && !phb->msi32_support) return -ENODEV; return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV; diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index a8fe5aa..3b46eed 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -380,7 +380,7 @@ static int dlpar_online_cpu(struct device_node *dn) BUG_ON(get_cpu_current_state(cpu) != CPU_STATE_OFFLINE); cpu_maps_update_done(); - rc = cpu_up(cpu); + rc = device_online(get_cpu_device(cpu)); if (rc) goto out; cpu_maps_update_begin(); @@ -463,7 +463,7 @@ static int dlpar_offline_cpu(struct device_node *dn) if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); cpu_maps_update_done(); - rc = cpu_down(cpu); + rc = device_offline(get_cpu_device(cpu)); if (rc) goto out; cpu_maps_update_begin(); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 9590dbb..b9a8204 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -160,7 +160,7 @@ static int pseries_remove_memory(struct device_node *np) static inline int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { - return -EOPNOTSUPP; + return 0; } static inline int pseries_remove_memory(struct device_node *np) { diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 33b552f..de1ec54 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -329,16 +329,16 @@ struct direct_window { /* Dynamic DMA Window support */ struct ddw_query_response { - __be32 windows_available; - __be32 largest_available_block; - __be32 page_size; - __be32 migration_capable; + u32 windows_available; + u32 largest_available_block; + u32 page_size; + u32 migration_capable; }; struct ddw_create_response { - __be32 liobn; - __be32 addr_hi; - __be32 addr_lo; + u32 liobn; + u32 addr_hi; + u32 addr_lo; }; static LIST_HEAD(direct_window_list); @@ -721,20 +721,22 @@ static int __init disable_ddw_setup(char *str) early_param("disable_ddw", disable_ddw_setup); -static void remove_ddw(struct device_node *np) +static void remove_ddw(struct device_node *np, bool remove_prop) { struct dynamic_dma_window_prop *dwp; struct property *win64; - const u32 *ddw_avail; + u32 ddw_avail[3]; u64 liobn; - int len, ret; + int ret = 0; + + ret = of_property_read_u32_array(np, "ibm,ddw-applicable", + &ddw_avail[0], 3); - ddw_avail = of_get_property(np, "ibm,ddw-applicable", &len); win64 = of_find_property(np, DIRECT64_PROPNAME, NULL); if (!win64) return; - if (!ddw_avail || len < 3 * sizeof(u32) || win64->length < sizeof(*dwp)) + if (ret || win64->length < sizeof(*dwp)) goto delprop; dwp = win64->value; @@ -761,7 +763,8 @@ static void remove_ddw(struct device_node *np) np->full_name, ret, ddw_avail[2], liobn); delprop: - ret = of_remove_property(np, win64); + if (remove_prop) + ret = of_remove_property(np, win64); if (ret) pr_warning("%s: failed to remove direct window property: %d\n", np->full_name, ret); @@ -805,7 +808,7 @@ static int find_existing_ddw_windows(void) window = kzalloc(sizeof(*window), GFP_KERNEL); if (!window || len < sizeof(struct dynamic_dma_window_prop)) { kfree(window); - remove_ddw(pdn); + remove_ddw(pdn, true); continue; } @@ -871,8 +874,9 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ - ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, cfg_addr, - BUID_HI(buid), BUID_LO(buid), page_shift, window_shift); + ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, + cfg_addr, BUID_HI(buid), BUID_LO(buid), + page_shift, window_shift); } while (rtas_busy_delay(ret)); dev_info(&dev->dev, "ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d " @@ -909,7 +913,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) int page_shift; u64 dma_addr, max_addr; struct device_node *dn; - const u32 *uninitialized_var(ddw_avail); + u32 ddw_avail[3]; struct direct_window *window; struct property *win64; struct dynamic_dma_window_prop *ddwprop; @@ -941,8 +945,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * for the given node in that order. * the property is actually in the parent, not the PE */ - ddw_avail = of_get_property(pdn, "ibm,ddw-applicable", &len); - if (!ddw_avail || len < 3 * sizeof(u32)) + ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable", + &ddw_avail[0], 3); + if (ret) goto out_failed; /* @@ -965,11 +970,11 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) dev_dbg(&dev->dev, "no free dynamic windows"); goto out_failed; } - if (be32_to_cpu(query.page_size) & 4) { + if (query.page_size & 4) { page_shift = 24; /* 16MB */ - } else if (be32_to_cpu(query.page_size) & 2) { + } else if (query.page_size & 2) { page_shift = 16; /* 64kB */ - } else if (be32_to_cpu(query.page_size) & 1) { + } else if (query.page_size & 1) { page_shift = 12; /* 4kB */ } else { dev_dbg(&dev->dev, "no supported direct page size in mask %x", @@ -979,7 +984,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) /* verify the window * number of ptes will map the partition */ /* check largest block * page size > max memory hotplug addr */ max_addr = memory_hotplug_max(); - if (be32_to_cpu(query.largest_available_block) < (max_addr >> page_shift)) { + if (query.largest_available_block < (max_addr >> page_shift)) { dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u " "%llu-sized pages\n", max_addr, query.largest_available_block, 1ULL << page_shift); @@ -1005,8 +1010,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) if (ret != 0) goto out_free_prop; - ddwprop->liobn = create.liobn; - ddwprop->dma_base = cpu_to_be64(of_read_number(&create.addr_hi, 2)); + ddwprop->liobn = cpu_to_be32(create.liobn); + ddwprop->dma_base = cpu_to_be64(((u64)create.addr_hi << 32) | + create.addr_lo); ddwprop->tce_shift = cpu_to_be32(page_shift); ddwprop->window_shift = cpu_to_be32(len); @@ -1038,14 +1044,14 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) list_add(&window->list, &direct_window_list); spin_unlock(&direct_window_list_lock); - dma_addr = of_read_number(&create.addr_hi, 2); + dma_addr = be64_to_cpu(ddwprop->dma_base); goto out_unlock; out_free_window: kfree(window); out_clear_window: - remove_ddw(pdn); + remove_ddw(pdn, true); out_free_prop: kfree(win64->name); @@ -1255,7 +1261,14 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti switch (action) { case OF_RECONFIG_DETACH_NODE: - remove_ddw(np); + /* + * Removing the property will invoke the reconfig + * notifier again, which causes dead-lock on the + * read-write semaphore of the notifier chain. So + * we have to remove the property when releasing + * the device node. + */ + remove_ddw(np, false); if (pci && pci->iommu_table) iommu_free_table(pci->iommu_table, np->full_name); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index b02af9e..ccf6f16 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -430,16 +430,17 @@ static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot, spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags); } -static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm, - unsigned char *hpte_slot_array, - unsigned long addr, int psize) +static void pSeries_lpar_hugepage_invalidate(unsigned long vsid, + unsigned long addr, + unsigned char *hpte_slot_array, + int psize, int ssize) { - int ssize = 0, i, index = 0; + int i, index = 0; unsigned long s_addr = addr; unsigned int max_hpte_count, valid; unsigned long vpn_array[PPC64_HUGE_HPTE_BATCH]; unsigned long slot_array[PPC64_HUGE_HPTE_BATCH]; - unsigned long shift, hidx, vpn = 0, vsid, hash, slot; + unsigned long shift, hidx, vpn = 0, hash, slot; shift = mmu_psize_defs[psize].shift; max_hpte_count = 1U << (PMD_SHIFT - shift); @@ -452,15 +453,6 @@ static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm, /* get the vpn */ addr = s_addr + (i * (1ul << shift)); - if (!is_kernel_addr(addr)) { - ssize = user_segment_size(addr); - vsid = get_vsid(mm->context.id, addr, ssize); - WARN_ON(vsid == 0); - } else { - vsid = get_kernel_vsid(addr, mmu_kernel_ssize); - ssize = mmu_kernel_ssize; - } - vpn = hpt_vpn(addr, vsid, ssize); hash = hpt_hash(vpn, shift, ssize); if (hidx & _PTEIDX_SECONDARY) diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index cde4e0a..bf38292 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -24,10 +24,10 @@ static struct kobject *mobility_kobj; struct update_props_workarea { - u32 phandle; - u32 state; - u64 reserved; - u32 nprops; + __be32 phandle; + __be32 state; + __be64 reserved; + __be32 nprops; } __packed; #define NODE_ACTION_MASK 0xff000000 @@ -53,11 +53,11 @@ static int mobility_rtas_call(int token, char *buf, s32 scope) return rc; } -static int delete_dt_node(u32 phandle) +static int delete_dt_node(__be32 phandle) { struct device_node *dn; - dn = of_find_node_by_phandle(phandle); + dn = of_find_node_by_phandle(be32_to_cpu(phandle)); if (!dn) return -ENOENT; @@ -126,7 +126,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop, return 0; } -static int update_dt_node(u32 phandle, s32 scope) +static int update_dt_node(__be32 phandle, s32 scope) { struct update_props_workarea *upwa; struct device_node *dn; @@ -135,6 +135,7 @@ static int update_dt_node(u32 phandle, s32 scope) char *prop_data; char *rtas_buf; int update_properties_token; + u32 nprops; u32 vd; update_properties_token = rtas_token("ibm,update-properties"); @@ -145,7 +146,7 @@ static int update_dt_node(u32 phandle, s32 scope) if (!rtas_buf) return -ENOMEM; - dn = of_find_node_by_phandle(phandle); + dn = of_find_node_by_phandle(be32_to_cpu(phandle)); if (!dn) { kfree(rtas_buf); return -ENOENT; @@ -161,6 +162,7 @@ static int update_dt_node(u32 phandle, s32 scope) break; prop_data = rtas_buf + sizeof(*upwa); + nprops = be32_to_cpu(upwa->nprops); /* On the first call to ibm,update-properties for a node the * the first property value descriptor contains an empty @@ -169,17 +171,17 @@ static int update_dt_node(u32 phandle, s32 scope) */ if (*prop_data == 0) { prop_data++; - vd = *(u32 *)prop_data; + vd = be32_to_cpu(*(__be32 *)prop_data); prop_data += vd + sizeof(vd); - upwa->nprops--; + nprops--; } - for (i = 0; i < upwa->nprops; i++) { + for (i = 0; i < nprops; i++) { char *prop_name; prop_name = prop_data; prop_data += strlen(prop_name) + 1; - vd = *(u32 *)prop_data; + vd = be32_to_cpu(*(__be32 *)prop_data); prop_data += sizeof(vd); switch (vd) { @@ -211,13 +213,13 @@ static int update_dt_node(u32 phandle, s32 scope) return 0; } -static int add_dt_node(u32 parent_phandle, u32 drc_index) +static int add_dt_node(__be32 parent_phandle, __be32 drc_index) { struct device_node *dn; struct device_node *parent_dn; int rc; - parent_dn = of_find_node_by_phandle(parent_phandle); + parent_dn = of_find_node_by_phandle(be32_to_cpu(parent_phandle)); if (!parent_dn) return -ENOENT; @@ -236,7 +238,7 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index) int pseries_devicetree_update(s32 scope) { char *rtas_buf; - u32 *data; + __be32 *data; int update_nodes_token; int rc; @@ -253,17 +255,17 @@ int pseries_devicetree_update(s32 scope) if (rc && rc != 1) break; - data = (u32 *)rtas_buf + 4; - while (*data & NODE_ACTION_MASK) { + data = (__be32 *)rtas_buf + 4; + while (be32_to_cpu(*data) & NODE_ACTION_MASK) { int i; - u32 action = *data & NODE_ACTION_MASK; - int node_count = *data & NODE_COUNT_MASK; + u32 action = be32_to_cpu(*data) & NODE_ACTION_MASK; + u32 node_count = be32_to_cpu(*data) & NODE_COUNT_MASK; data++; for (i = 0; i < node_count; i++) { - u32 phandle = *data++; - u32 drc_index; + __be32 phandle = *data++; + __be32 drc_index; switch (action) { case DELETE_DT_NODE: diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 0c882e8..6849d85 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -428,7 +428,7 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) */ again: if (type == PCI_CAP_ID_MSI) { - if (pdn->force_32bit_msi) { + if (pdev->no_64bit_msi) { rc = rtas_change_msi(pdn, RTAS_CHANGE_32MSI_FN, nvec); if (rc < 0) { /* diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index efe6137..e68922b 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -118,10 +118,10 @@ int remove_phb_dynamic(struct pci_controller *phb) } } - /* Unregister the bridge device from sysfs and remove the PCI bus */ - device_unregister(b->bridge); + /* Remove the PCI bus and unregister the bridge device from sysfs */ phb->bus = NULL; pci_remove_bus(b); + device_unregister(b->bridge); /* Now release the IO resource */ if (res->flags & IORESOURCE_IO) diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 47b6b9f..830edc8 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -156,7 +156,7 @@ axon_ram_direct_access(struct block_device *device, sector_t sector, } *kaddr = (void *)(bank->ph_addr + offset); - *pfn = virt_to_phys(kaddr) >> PAGE_SHIFT; + *pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT; return 0; } diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index b079098..f89389f 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -288,10 +288,11 @@ static inline void disable_surveillance(void) args.token = rtas_token("set-indicator"); if (args.token == RTAS_UNKNOWN_SERVICE) return; - args.nargs = 3; - args.nret = 1; + args.token = cpu_to_be32(args.token); + args.nargs = cpu_to_be32(3); + args.nret = cpu_to_be32(1); args.rets = &args.args[3]; - args.args[0] = SURVEILLANCE_TOKEN; + args.args[0] = cpu_to_be32(SURVEILLANCE_TOKEN); args.args[1] = 0; args.args[2] = 0; enter_rtas(__pa(&args)); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index bb74b21..a0a3bed 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -93,6 +93,7 @@ config S390 select ARCH_INLINE_WRITE_UNLOCK_IRQ select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE select ARCH_SAVE_PAGE_KEYS if HIBERNATION + select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 23223cd..1f272b2 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -979,7 +979,7 @@ static void __exit aes_s390_fini(void) module_init(aes_s390_init); module_exit(aes_s390_fini); -MODULE_ALIAS("aes-all"); +MODULE_ALIAS_CRYPTO("aes-all"); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm"); MODULE_LICENSE("GPL"); diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index 7acb77f..9e05cc4 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -619,8 +619,8 @@ static void __exit des_s390_exit(void) module_init(des_s390_init); module_exit(des_s390_exit); -MODULE_ALIAS("des"); -MODULE_ALIAS("des3_ede"); +MODULE_ALIAS_CRYPTO("des"); +MODULE_ALIAS_CRYPTO("des3_ede"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms"); diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c index d43485d..b258110 100644 --- a/arch/s390/crypto/ghash_s390.c +++ b/arch/s390/crypto/ghash_s390.c @@ -16,11 +16,12 @@ #define GHASH_DIGEST_SIZE 16 struct ghash_ctx { - u8 icv[16]; - u8 key[16]; + u8 key[GHASH_BLOCK_SIZE]; }; struct ghash_desc_ctx { + u8 icv[GHASH_BLOCK_SIZE]; + u8 key[GHASH_BLOCK_SIZE]; u8 buffer[GHASH_BLOCK_SIZE]; u32 bytes; }; @@ -28,8 +29,10 @@ struct ghash_desc_ctx { static int ghash_init(struct shash_desc *desc) { struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); memset(dctx, 0, sizeof(*dctx)); + memcpy(dctx->key, ctx->key, GHASH_BLOCK_SIZE); return 0; } @@ -45,7 +48,6 @@ static int ghash_setkey(struct crypto_shash *tfm, } memcpy(ctx->key, key, GHASH_BLOCK_SIZE); - memset(ctx->icv, 0, GHASH_BLOCK_SIZE); return 0; } @@ -54,7 +56,6 @@ static int ghash_update(struct shash_desc *desc, const u8 *src, unsigned int srclen) { struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); - struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); unsigned int n; u8 *buf = dctx->buffer; int ret; @@ -70,7 +71,7 @@ static int ghash_update(struct shash_desc *desc, src += n; if (!dctx->bytes) { - ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf, + ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE); if (ret != GHASH_BLOCK_SIZE) return -EIO; @@ -79,7 +80,7 @@ static int ghash_update(struct shash_desc *desc, n = srclen & ~(GHASH_BLOCK_SIZE - 1); if (n) { - ret = crypt_s390_kimd(KIMD_GHASH, ctx, src, n); + ret = crypt_s390_kimd(KIMD_GHASH, dctx, src, n); if (ret != n) return -EIO; src += n; @@ -94,7 +95,7 @@ static int ghash_update(struct shash_desc *desc, return 0; } -static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx) +static int ghash_flush(struct ghash_desc_ctx *dctx) { u8 *buf = dctx->buffer; int ret; @@ -104,24 +105,24 @@ static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx) memset(pos, 0, dctx->bytes); - ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf, GHASH_BLOCK_SIZE); + ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE); if (ret != GHASH_BLOCK_SIZE) return -EIO; + + dctx->bytes = 0; } - dctx->bytes = 0; return 0; } static int ghash_final(struct shash_desc *desc, u8 *dst) { struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); - struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); int ret; - ret = ghash_flush(ctx, dctx); + ret = ghash_flush(dctx); if (!ret) - memcpy(dst, ctx->icv, GHASH_BLOCK_SIZE); + memcpy(dst, dctx->icv, GHASH_BLOCK_SIZE); return ret; } @@ -160,7 +161,7 @@ static void __exit ghash_mod_exit(void) module_init(ghash_mod_init); module_exit(ghash_mod_exit); -MODULE_ALIAS("ghash"); +MODULE_ALIAS_CRYPTO("ghash"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("GHASH Message Digest Algorithm, s390 implementation"); diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c index a1b3a9d..5b2bee3 100644 --- a/arch/s390/crypto/sha1_s390.c +++ b/arch/s390/crypto/sha1_s390.c @@ -103,6 +103,6 @@ static void __exit sha1_s390_fini(void) module_init(sha1_s390_init); module_exit(sha1_s390_fini); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm"); diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c index 9b85380..b74ff15 100644 --- a/arch/s390/crypto/sha256_s390.c +++ b/arch/s390/crypto/sha256_s390.c @@ -143,7 +143,7 @@ static void __exit sha256_s390_fini(void) module_init(sha256_s390_init); module_exit(sha256_s390_fini); -MODULE_ALIAS("sha256"); -MODULE_ALIAS("sha224"); +MODULE_ALIAS_CRYPTO("sha256"); +MODULE_ALIAS_CRYPTO("sha224"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA256 and SHA224 Secure Hash Algorithm"); diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c index 32a8138..0c36989 100644 --- a/arch/s390/crypto/sha512_s390.c +++ b/arch/s390/crypto/sha512_s390.c @@ -86,7 +86,7 @@ static struct shash_alg sha512_alg = { } }; -MODULE_ALIAS("sha512"); +MODULE_ALIAS_CRYPTO("sha512"); static int sha384_init(struct shash_desc *desc) { @@ -126,7 +126,7 @@ static struct shash_alg sha384_alg = { } }; -MODULE_ALIAS("sha384"); +MODULE_ALIAS_CRYPTO("sha384"); static int __init init(void) { diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index db02052..5426c9e 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -245,7 +245,7 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist) struct group_info *group_info; int retval; - if (!capable(CAP_SETGID)) + if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index a48bc79..184d305 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -323,9 +323,14 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) unsigned long mask = PSW_MASK_USER; mask |= is_ri_task(child) ? PSW_MASK_RI : 0; - if ((data & ~mask) != PSW_USER_BITS) + if ((data ^ PSW_USER_BITS) & ~mask) + /* Invalid psw mask. */ + return -EINVAL; + if ((data & PSW_MASK_ASC) == PSW_ASC_HOME) + /* Invalid address-space-control bits */ return -EINVAL; if ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA)) + /* Invalid addressing mode bits */ return -EINVAL; } *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data; @@ -661,9 +666,12 @@ static int __poke_user_compat(struct task_struct *child, mask |= is_ri_task(child) ? PSW32_MASK_RI : 0; /* Build a 64 bit psw mask from 31 bit mask. */ - if ((tmp & ~mask) != PSW32_USER_BITS) + if ((tmp ^ PSW32_USER_BITS) & ~mask) /* Invalid psw mask. */ return -EINVAL; + if ((data & PSW32_MASK_ASC) == PSW32_ASC_HOME) + /* Invalid address-space-control bits */ + return -EINVAL; regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | (regs->psw.mask & PSW_MASK_BA) | (__u64)(tmp & mask) << 32; diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S index 29bd7be..1ecd47b 100644 --- a/arch/s390/kernel/sclp.S +++ b/arch/s390/kernel/sclp.S @@ -276,6 +276,8 @@ ENTRY(_sclp_print_early) jno .Lesa2 ahi %r15,-80 stmh %r6,%r15,96(%r15) # store upper register halves + basr %r13,0 + lmh %r0,%r15,.Lzeroes-.(%r13) # clear upper register halves .Lesa2: #endif lr %r10,%r2 # save string pointer @@ -299,6 +301,8 @@ ENTRY(_sclp_print_early) #endif lm %r6,%r15,120(%r15) # restore registers br %r14 +.Lzeroes: + .fill 64,4,0 .LwritedataS4: .long 0x00760005 # SCLP command for write data diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c index a7a7537..d3236c9 100644 --- a/arch/s390/kernel/suspend.c +++ b/arch/s390/kernel/suspend.c @@ -13,14 +13,10 @@ #include #include #include +#include #include "entry.h" /* - * References to section boundaries - */ -extern const void __nosave_begin, __nosave_end; - -/* * The restore of the saved pages in an hibernation image will set * the change and referenced bits in the storage key for each page. * Overindication of the referenced bits after an hibernation cycle @@ -142,6 +138,8 @@ int pfn_is_nosave(unsigned long pfn) { unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin)); unsigned long nosave_end_pfn = PFN_DOWN(__pa(&__nosave_end)); + unsigned long eshared_pfn = PFN_DOWN(__pa(&_eshared)) - 1; + unsigned long stext_pfn = PFN_DOWN(__pa(&_stext)); /* Always save lowcore pages (LC protection might be enabled). */ if (pfn <= LC_PAGES) @@ -149,6 +147,8 @@ int pfn_is_nosave(unsigned long pfn) if (pfn >= nosave_begin_pfn && pfn < nosave_end_pfn) return 1; /* Skip memory holes and read-only pages (NSS, DCSS, ...). */ + if (pfn >= stext_pfn && pfn <= eshared_pfn) + return ipl_info.type == IPL_TYPE_NSS ? 1 : 0; if (tprot(PFN_PHYS(pfn))) return 1; return 0; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 5f79d2d..f1ba119 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -71,6 +71,7 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu, return 0; if (vcpu->arch.sie_block->gcr[0] & 0x2000ul) return 1; + return 0; case KVM_S390_INT_EMERGENCY: if (psw_extint_disabled(vcpu)) return 0; diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 75beea6..3588f2f 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -414,6 +414,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) for (n = mem->count - 1; n > 0 ; n--) memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0])); + memset(&mem->vm[0], 0, sizeof(mem->vm[0])); mem->vm[0].cpus_total = cpus; mem->vm[0].cpus_configured = cpus; mem->vm[0].cpus_standby = 0; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index d95265b2..8e95432 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -239,6 +239,12 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault) do_no_context(regs); else pagefault_out_of_memory(); + } else if (fault & VM_FAULT_SIGSEGV) { + /* Kernel mode? Handle exceptions or die */ + if (!user_mode(regs)) + do_no_context(regs); + else + do_sigsegv(regs, SEGV_MAPERR); } else if (fault & VM_FAULT_SIGBUS) { /* Kernel mode? Handle exceptions or die */ if (!user_mode(regs)) diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 3584ed9..e309c5c 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -810,11 +810,21 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep; down_read(&mm->mmap_sem); +retry: ptep = get_locked_pte(current->mm, addr, &ptl); if (unlikely(!ptep)) { up_read(&mm->mmap_sem); return -EFAULT; } + if (!(pte_val(*ptep) & _PAGE_INVALID) && + (pte_val(*ptep) & _PAGE_PROTECT)) { + pte_unmap_unlock(*ptep, ptl); + if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE)) { + up_read(&mm->mmap_sem); + return -EFAULT; + } + goto retry; + } new = old = pgste_get_lock(ptep); pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT | diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c index 52238983..6860beb 100644 --- a/arch/score/mm/fault.c +++ b/arch/score/mm/fault.c @@ -114,6 +114,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/sh/include/asm/sections.h b/arch/sh/include/asm/sections.h index 1b61997..7a99e6a 100644 --- a/arch/sh/include/asm/sections.h +++ b/arch/sh/include/asm/sections.h @@ -3,7 +3,6 @@ #include -extern long __nosave_begin, __nosave_end; extern long __machvec_start, __machvec_end; extern char __uncached_start, __uncached_end; extern char __start_eh_frame[], __stop_eh_frame[]; diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c index ff1465c..5acf89c 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c @@ -118,7 +118,7 @@ static struct plat_sci_port scif0_platform_data = { }; static struct resource scif0_resources[] = { - DEFINE_RES_MEM(0xfffffe80, 0x100), + DEFINE_RES_MEM(0xfffffe80, 0x10), DEFINE_RES_IRQ(evt2irq(0x4e0)), }; @@ -143,7 +143,7 @@ static struct plat_sci_port scif1_platform_data = { }; static struct resource scif1_resources[] = { - DEFINE_RES_MEM(0xa4000150, 0x100), + DEFINE_RES_MEM(0xa4000150, 0x10), DEFINE_RES_IRQ(evt2irq(0x900)), }; @@ -169,7 +169,7 @@ static struct plat_sci_port scif2_platform_data = { }; static struct resource scif2_resources[] = { - DEFINE_RES_MEM(0xa4000140, 0x100), + DEFINE_RES_MEM(0xa4000140, 0x10), DEFINE_RES_IRQ(evt2irq(0x880)), }; diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 541dc61..a58fec9 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -353,6 +353,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, } else { if (fault & VM_FAULT_SIGBUS) do_sigbus(regs, error_code, address); + else if (fault & VM_FAULT_SIGSEGV) + bad_area(regs, error_code, address); else BUG(); } diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index b398c68..a38513c 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -67,6 +67,7 @@ config SPARC64 select HAVE_SYSCALL_TRACEPOINTS select HAVE_CONTEXT_TRACKING select HAVE_DEBUG_KMEMLEAK + select SPARSE_IRQ select RTC_DRV_CMOS select RTC_DRV_BQ4802 select RTC_DRV_SUN4V diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c index 503e6d9..ded4cee3 100644 --- a/arch/sparc/crypto/aes_glue.c +++ b/arch/sparc/crypto/aes_glue.c @@ -499,6 +499,6 @@ module_exit(aes_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("AES Secure Hash Algorithm, sparc64 aes opcode accelerated"); -MODULE_ALIAS("aes"); +MODULE_ALIAS_CRYPTO("aes"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/camellia_glue.c b/arch/sparc/crypto/camellia_glue.c index 888f6260..641f55c 100644 --- a/arch/sparc/crypto/camellia_glue.c +++ b/arch/sparc/crypto/camellia_glue.c @@ -322,6 +322,6 @@ module_exit(camellia_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, sparc64 camellia opcode accelerated"); -MODULE_ALIAS("aes"); +MODULE_ALIAS_CRYPTO("aes"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/crc32c_glue.c b/arch/sparc/crypto/crc32c_glue.c index 5162fad..d1064e4 100644 --- a/arch/sparc/crypto/crc32c_glue.c +++ b/arch/sparc/crypto/crc32c_glue.c @@ -176,6 +176,6 @@ module_exit(crc32c_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CRC32c (Castagnoli), sparc64 crc32c opcode accelerated"); -MODULE_ALIAS("crc32c"); +MODULE_ALIAS_CRYPTO("crc32c"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c index 3065bc6..d115009 100644 --- a/arch/sparc/crypto/des_glue.c +++ b/arch/sparc/crypto/des_glue.c @@ -532,6 +532,6 @@ module_exit(des_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms, sparc64 des opcode accelerated"); -MODULE_ALIAS("des"); +MODULE_ALIAS_CRYPTO("des"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c index 09a9ea1..64c7ff5 100644 --- a/arch/sparc/crypto/md5_glue.c +++ b/arch/sparc/crypto/md5_glue.c @@ -185,6 +185,6 @@ module_exit(md5_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MD5 Secure Hash Algorithm, sparc64 md5 opcode accelerated"); -MODULE_ALIAS("md5"); +MODULE_ALIAS_CRYPTO("md5"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/sha1_glue.c b/arch/sparc/crypto/sha1_glue.c index 6cd5f29..1b3e47a 100644 --- a/arch/sparc/crypto/sha1_glue.c +++ b/arch/sparc/crypto/sha1_glue.c @@ -180,6 +180,6 @@ module_exit(sha1_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, sparc64 sha1 opcode accelerated"); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c index 04f555a..41f27cc 100644 --- a/arch/sparc/crypto/sha256_glue.c +++ b/arch/sparc/crypto/sha256_glue.c @@ -237,7 +237,7 @@ module_exit(sha256_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm, sparc64 sha256 opcode accelerated"); -MODULE_ALIAS("sha224"); -MODULE_ALIAS("sha256"); +MODULE_ALIAS_CRYPTO("sha224"); +MODULE_ALIAS_CRYPTO("sha256"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/sha512_glue.c b/arch/sparc/crypto/sha512_glue.c index f04d199..9fff885 100644 --- a/arch/sparc/crypto/sha512_glue.c +++ b/arch/sparc/crypto/sha512_glue.c @@ -222,7 +222,7 @@ module_exit(sha512_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA-384 and SHA-512 Secure Hash Algorithm, sparc64 sha512 opcode accelerated"); -MODULE_ALIAS("sha384"); -MODULE_ALIAS("sha512"); +MODULE_ALIAS_CRYPTO("sha384"); +MODULE_ALIAS_CRYPTO("sha512"); #include "crop_devid.c" diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index 905832a..a0ed182 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -21,7 +21,7 @@ extern int __atomic_add_return(int, atomic_t *); extern int atomic_cmpxchg(atomic_t *, int, int); -#define atomic_xchg(v, new) (xchg(&((v)->counter), new)) +extern int atomic_xchg(atomic_t *, int); extern int __atomic_add_unless(atomic_t *, int, int); extern void atomic_set(atomic_t *, int); diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h index 1fae1a0..ae0f9a7 100644 --- a/arch/sparc/include/asm/cmpxchg_32.h +++ b/arch/sparc/include/asm/cmpxchg_32.h @@ -11,22 +11,14 @@ #ifndef __ARCH_SPARC_CMPXCHG__ #define __ARCH_SPARC_CMPXCHG__ -static inline unsigned long xchg_u32(__volatile__ unsigned long *m, unsigned long val) -{ - __asm__ __volatile__("swap [%2], %0" - : "=&r" (val) - : "0" (val), "r" (m) - : "memory"); - return val; -} - +extern unsigned long __xchg_u32(volatile u32 *m, u32 new); extern void __xchg_called_with_bad_pointer(void); static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size) { switch (size) { case 4: - return xchg_u32(ptr, x); + return __xchg_u32(ptr, x); } __xchg_called_with_bad_pointer(); return x; diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h index ca121f0..17be9d6 100644 --- a/arch/sparc/include/asm/hypervisor.h +++ b/arch/sparc/include/asm/hypervisor.h @@ -2944,6 +2944,16 @@ extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num, unsigned long reg_val); #endif +#define HV_FAST_T5_GET_PERFREG 0x1a8 +#define HV_FAST_T5_SET_PERFREG 0x1a9 + +#ifndef __ASSEMBLY__ +unsigned long sun4v_t5_get_perfreg(unsigned long reg_num, + unsigned long *reg_val); +unsigned long sun4v_t5_set_perfreg(unsigned long reg_num, + unsigned long reg_val); +#endif + /* Function numbers for HV_CORE_TRAP. */ #define HV_CORE_SET_VER 0x00 #define HV_CORE_PUTCHAR 0x01 @@ -2975,6 +2985,7 @@ extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num, #define HV_GRP_VF_CPU 0x0205 #define HV_GRP_KT_CPU 0x0209 #define HV_GRP_VT_CPU 0x020c +#define HV_GRP_T5_CPU 0x0211 #define HV_GRP_DIAG 0x0300 #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h index abf6afe..3deb07f 100644 --- a/arch/sparc/include/asm/irq_64.h +++ b/arch/sparc/include/asm/irq_64.h @@ -37,7 +37,7 @@ * * ino_bucket->irq allocation is made during {sun4v_,}build_irq(). */ -#define NR_IRQS 255 +#define NR_IRQS (2048) extern void irq_install_pre_handler(int irq, void (*func)(unsigned int, void *, void *), @@ -57,11 +57,8 @@ extern unsigned int sun4u_build_msi(u32 portid, unsigned int *irq_p, unsigned long iclr_base); extern void sun4u_destroy_msi(unsigned int irq); -extern unsigned char irq_alloc(unsigned int dev_handle, - unsigned int dev_ino); -#ifdef CONFIG_PCI_MSI -extern void irq_free(unsigned int irq); -#endif +unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino); +void irq_free(unsigned int irq); extern void __init init_IRQ(void); extern void fixup_irqs(void); diff --git a/arch/sparc/include/asm/ldc.h b/arch/sparc/include/asm/ldc.h index bdb524a..8732ed3 100644 --- a/arch/sparc/include/asm/ldc.h +++ b/arch/sparc/include/asm/ldc.h @@ -53,13 +53,14 @@ struct ldc_channel; /* Allocate state for a channel. */ extern struct ldc_channel *ldc_alloc(unsigned long id, const struct ldc_channel_config *cfgp, - void *event_arg); + void *event_arg, + const char *name); /* Shut down and free state for a channel. */ extern void ldc_free(struct ldc_channel *lp); /* Register TX and RX queues of the link with the hypervisor. */ -extern int ldc_bind(struct ldc_channel *lp, const char *name); +extern int ldc_bind(struct ldc_channel *lp); /* For non-RAW protocols we need to complete a handshake before * communication can proceed. ldc_connect() does that, if the diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h index a12dbe3..e48fdf4 100644 --- a/arch/sparc/include/asm/oplib_64.h +++ b/arch/sparc/include/asm/oplib_64.h @@ -62,7 +62,8 @@ struct linux_mem_p1275 { /* You must call prom_init() before using any of the library services, * preferably as early as possible. Pass it the romvec pointer. */ -extern void prom_init(void *cif_handler, void *cif_stack); +extern void prom_init(void *cif_handler); +extern void prom_init_report(void); /* Boot argument acquisition, returns the boot command line string. */ extern char *prom_getbootargs(void); diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h index aac53fc..b18e602 100644 --- a/arch/sparc/include/asm/page_64.h +++ b/arch/sparc/include/asm/page_64.h @@ -57,18 +57,21 @@ extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct pag typedef struct { unsigned long pte; } pte_t; typedef struct { unsigned long iopte; } iopte_t; typedef struct { unsigned long pmd; } pmd_t; +typedef struct { unsigned long pud; } pud_t; typedef struct { unsigned long pgd; } pgd_t; typedef struct { unsigned long pgprot; } pgprot_t; #define pte_val(x) ((x).pte) #define iopte_val(x) ((x).iopte) #define pmd_val(x) ((x).pmd) +#define pud_val(x) ((x).pud) #define pgd_val(x) ((x).pgd) #define pgprot_val(x) ((x).pgprot) #define __pte(x) ((pte_t) { (x) } ) #define __iopte(x) ((iopte_t) { (x) } ) #define __pmd(x) ((pmd_t) { (x) } ) +#define __pud(x) ((pud_t) { (x) } ) #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) @@ -77,18 +80,21 @@ typedef struct { unsigned long pgprot; } pgprot_t; typedef unsigned long pte_t; typedef unsigned long iopte_t; typedef unsigned long pmd_t; +typedef unsigned long pud_t; typedef unsigned long pgd_t; typedef unsigned long pgprot_t; #define pte_val(x) (x) #define iopte_val(x) (x) #define pmd_val(x) (x) +#define pud_val(x) (x) #define pgd_val(x) (x) #define pgprot_val(x) (x) #define __pte(x) (x) #define __iopte(x) (x) #define __pmd(x) (x) +#define __pud(x) (x) #define __pgd(x) (x) #define __pgprot(x) (x) @@ -96,21 +102,14 @@ typedef unsigned long pgprot_t; typedef pte_t *pgtable_t; -/* These two values define the virtual address space range in which we - * must forbid 64-bit user processes from making mappings. It used to - * represent precisely the virtual address space hole present in most - * early sparc64 chips including UltraSPARC-I. But now it also is - * further constrained by the limits of our page tables, which is - * 43-bits of virtual address. - */ -#define SPARC64_VA_HOLE_TOP _AC(0xfffffc0000000000,UL) -#define SPARC64_VA_HOLE_BOTTOM _AC(0x0000040000000000,UL) +extern unsigned long sparc64_va_hole_top; +extern unsigned long sparc64_va_hole_bottom; /* The next two defines specify the actual exclusion region we * enforce, wherein we use a 4GB red zone on each side of the VA hole. */ -#define VA_EXCLUDE_START (SPARC64_VA_HOLE_BOTTOM - (1UL << 32UL)) -#define VA_EXCLUDE_END (SPARC64_VA_HOLE_TOP + (1UL << 32UL)) +#define VA_EXCLUDE_START (sparc64_va_hole_bottom - (1UL << 32UL)) +#define VA_EXCLUDE_END (sparc64_va_hole_top + (1UL << 32UL)) #define TASK_UNMAPPED_BASE (test_thread_flag(TIF_32BIT) ? \ _AC(0x0000000070000000,UL) : \ @@ -118,20 +117,16 @@ typedef pte_t *pgtable_t; #include -#define PAGE_OFFSET_BY_BITS(X) (-(_AC(1,UL) << (X))) extern unsigned long PAGE_OFFSET; #endif /* !(__ASSEMBLY__) */ -/* The maximum number of physical memory address bits we support, this - * is used to size various tables used to manage kernel TLB misses and - * also the sparsemem code. +/* The maximum number of physical memory address bits we support. The + * largest value we can support is whatever "KPGD_SHIFT + KPTE_BITS" + * evaluates to. */ -#define MAX_PHYS_ADDRESS_BITS 47 +#define MAX_PHYS_ADDRESS_BITS 53 -/* These two shift counts are used when indexing sparc64_valid_addr_bitmap - * and kpte_linear_bitmap. - */ #define ILOG2_4MB 22 #define ILOG2_256MB 28 diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h index bcfe063..2c8d41f 100644 --- a/arch/sparc/include/asm/pgalloc_64.h +++ b/arch/sparc/include/asm/pgalloc_64.h @@ -15,6 +15,13 @@ extern struct kmem_cache *pgtable_cache; +static inline void __pgd_populate(pgd_t *pgd, pud_t *pud) +{ + pgd_set(pgd, pud); +} + +#define pgd_populate(MM, PGD, PUD) __pgd_populate(PGD, PUD) + static inline pgd_t *pgd_alloc(struct mm_struct *mm) { return kmem_cache_alloc(pgtable_cache, GFP_KERNEL); @@ -25,7 +32,23 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) kmem_cache_free(pgtable_cache, pgd); } -#define pud_populate(MM, PUD, PMD) pud_set(PUD, PMD) +static inline void __pud_populate(pud_t *pud, pmd_t *pmd) +{ + pud_set(pud, pmd); +} + +#define pud_populate(MM, PUD, PMD) __pud_populate(PUD, PMD) + +static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + return kmem_cache_alloc(pgtable_cache, + GFP_KERNEL|__GFP_REPEAT); +} + +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + kmem_cache_free(pgtable_cache, pud); +} static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { @@ -91,4 +114,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pte_t *pte, #define __pmd_free_tlb(tlb, pmd, addr) \ pgtable_free_tlb(tlb, pmd, false) +#define __pud_free_tlb(tlb, pud, addr) \ + pgtable_free_tlb(tlb, pud, false) + #endif /* _SPARC64_PGALLOC_H */ diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 0f9e945..e8dfabf 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -20,11 +20,10 @@ #include #include -#include - /* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB). * The page copy blockops can use 0x6000000 to 0x8000000. - * The TSB is mapped in the 0x8000000 to 0xa000000 range. + * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range. + * The 4M TSB is mapped in the 0x8400000 to 0x8800000 range. * The PROM resides in an area spanning 0xf0000000 to 0x100000000. * The vmalloc area spans 0x100000000 to 0x200000000. * Since modules need to be in the lowest 32-bits of the address space, @@ -33,17 +32,15 @@ * 0x400000000. */ #define TLBTEMP_BASE _AC(0x0000000006000000,UL) -#define TSBMAP_BASE _AC(0x0000000008000000,UL) +#define TSBMAP_8K_BASE _AC(0x0000000008000000,UL) +#define TSBMAP_4M_BASE _AC(0x0000000008400000,UL) #define MODULES_VADDR _AC(0x0000000010000000,UL) #define MODULES_LEN _AC(0x00000000e0000000,UL) #define MODULES_END _AC(0x00000000f0000000,UL) #define LOW_OBP_ADDRESS _AC(0x00000000f0000000,UL) #define HI_OBP_ADDRESS _AC(0x0000000100000000,UL) #define VMALLOC_START _AC(0x0000000100000000,UL) -#define VMALLOC_END _AC(0x0000010000000000,UL) -#define VMEMMAP_BASE _AC(0x0000010000000000,UL) - -#define vmemmap ((struct page *)VMEMMAP_BASE) +#define VMEMMAP_BASE VMALLOC_END /* PMD_SHIFT determines the size of the area a second-level page * table can map @@ -53,13 +50,25 @@ #define PMD_MASK (~(PMD_SIZE-1)) #define PMD_BITS (PAGE_SHIFT - 3) -/* PGDIR_SHIFT determines what a third-level page table entry can map */ -#define PGDIR_SHIFT (PAGE_SHIFT + (PAGE_SHIFT-3) + PMD_BITS) +/* PUD_SHIFT determines the size of the area a third-level page + * table can map + */ +#define PUD_SHIFT (PMD_SHIFT + PMD_BITS) +#define PUD_SIZE (_AC(1,UL) << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE-1)) +#define PUD_BITS (PAGE_SHIFT - 3) + +/* PGDIR_SHIFT determines what a fourth-level page table entry can map */ +#define PGDIR_SHIFT (PUD_SHIFT + PUD_BITS) #define PGDIR_SIZE (_AC(1,UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) #define PGDIR_BITS (PAGE_SHIFT - 3) -#if (PGDIR_SHIFT + PGDIR_BITS) != 43 +#if (MAX_PHYS_ADDRESS_BITS > PGDIR_SHIFT + PGDIR_BITS) +#error MAX_PHYS_ADDRESS_BITS exceeds what kernel page tables can support +#endif + +#if (PGDIR_SHIFT + PGDIR_BITS) != 53 #error Page table parameters do not cover virtual address space properly. #endif @@ -69,19 +78,32 @@ #ifndef __ASSEMBLY__ +extern unsigned long VMALLOC_END; + +#define vmemmap ((struct page *)VMEMMAP_BASE) + #include +bool kern_addr_valid(unsigned long addr); + /* Entries per page directory level. */ #define PTRS_PER_PTE (1UL << (PAGE_SHIFT-3)) #define PTRS_PER_PMD (1UL << PMD_BITS) +#define PTRS_PER_PUD (1UL << PUD_BITS) #define PTRS_PER_PGD (1UL << PGDIR_BITS) /* Kernel has a separate 44bit address space. */ #define FIRST_USER_ADDRESS 0 -#define pte_ERROR(e) __builtin_trap() -#define pmd_ERROR(e) __builtin_trap() -#define pgd_ERROR(e) __builtin_trap() +#define pmd_ERROR(e) \ + pr_err("%s:%d: bad pmd %p(%016lx) seen at (%pS)\n", \ + __FILE__, __LINE__, &(e), pmd_val(e), __builtin_return_address(0)) +#define pud_ERROR(e) \ + pr_err("%s:%d: bad pud %p(%016lx) seen at (%pS)\n", \ + __FILE__, __LINE__, &(e), pud_val(e), __builtin_return_address(0)) +#define pgd_ERROR(e) \ + pr_err("%s:%d: bad pgd %p(%016lx) seen at (%pS)\n", \ + __FILE__, __LINE__, &(e), pgd_val(e), __builtin_return_address(0)) #endif /* !(__ASSEMBLY__) */ @@ -90,6 +112,7 @@ #define _PAGE_R _AC(0x8000000000000000,UL) /* Keep ref bit uptodate*/ #define _PAGE_SPECIAL _AC(0x0200000000000000,UL) /* Special page */ #define _PAGE_PMD_HUGE _AC(0x0100000000000000,UL) /* Huge page */ +#define _PAGE_PUD_HUGE _PAGE_PMD_HUGE /* Advertise support for _PAGE_SPECIAL */ #define __HAVE_ARCH_PTE_SPECIAL @@ -258,8 +281,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot) { unsigned long mask, tmp; - /* SUN4U: 0x600307ffffffecb8 (negated == 0x9ffcf80000001347) - * SUN4V: 0x30ffffffffffee17 (negated == 0xcf000000000011e8) + /* SUN4U: 0x630107ffffffec38 (negated == 0x9cfef800000013c7) + * SUN4V: 0x33ffffffffffee07 (negated == 0xcc000000000011f8) * * Even if we use negation tricks the result is still a 6 * instruction sequence, so don't try to play fancy and just @@ -289,10 +312,10 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot) " .previous\n" : "=r" (mask), "=r" (tmp) : "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U | - _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U | _PAGE_PRESENT_4U | + _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U | _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U), "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V | - _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V | _PAGE_PRESENT_4V | + _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V | _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V)); return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask)); @@ -633,29 +656,29 @@ static inline unsigned long pmd_large(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return (pte_val(pte) & _PAGE_PMD_HUGE) && pte_present(pte); + return pte_val(pte) & _PAGE_PMD_HUGE; } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline unsigned long pmd_young(pmd_t pmd) +static inline unsigned long pmd_pfn(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_young(pte); + return pte_pfn(pte); } -static inline unsigned long pmd_write(pmd_t pmd) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline unsigned long pmd_young(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_write(pte); + return pte_young(pte); } -static inline unsigned long pmd_pfn(pmd_t pmd) +static inline unsigned long pmd_write(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_pfn(pte); + return pte_write(pte); } static inline unsigned long pmd_trans_huge(pmd_t pmd) @@ -719,20 +742,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd) return __pmd(pte_val(pte)); } -static inline pmd_t pmd_mknotpresent(pmd_t pmd) -{ - unsigned long mask; - - if (tlb_type == hypervisor) - mask = _PAGE_PRESENT_4V; - else - mask = _PAGE_PRESENT_4U; - - pmd_val(pmd) &= ~mask; - - return pmd; -} - static inline pmd_t pmd_mksplitting(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); @@ -757,6 +766,22 @@ static inline int pmd_present(pmd_t pmd) #define pmd_none(pmd) (!pmd_val(pmd)) +/* pmd_bad() is only called on non-trans-huge PMDs. Our encoding is + * very simple, it's just the physical address. PTE tables are of + * size PAGE_SIZE so make sure the sub-PAGE_SIZE bits are clear and + * the top bits outside of the range of any physical address size we + * support are clear as well. We also validate the physical itself. + */ +#define pmd_bad(pmd) (pmd_val(pmd) & ~PAGE_MASK) + +#define pud_none(pud) (!pud_val(pud)) + +#define pud_bad(pud) (pud_val(pud) & ~PAGE_MASK) + +#define pgd_none(pgd) (!pgd_val(pgd)) + +#define pgd_bad(pgd) (pgd_val(pgd) & ~PAGE_MASK) + #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); @@ -790,16 +815,34 @@ static inline unsigned long __pmd_page(pmd_t pmd) #define pud_page_vaddr(pud) \ ((unsigned long) __va(pud_val(pud))) #define pud_page(pud) virt_to_page((void *)pud_page_vaddr(pud)) -#define pmd_bad(pmd) (0) #define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0UL) -#define pud_none(pud) (!pud_val(pud)) -#define pud_bad(pud) (0) #define pud_present(pud) (pud_val(pud) != 0U) #define pud_clear(pudp) (pud_val(*(pudp)) = 0UL) +#define pgd_page_vaddr(pgd) \ + ((unsigned long) __va(pgd_val(pgd))) +#define pgd_present(pgd) (pgd_val(pgd) != 0U) +#define pgd_clear(pgdp) (pgd_val(*(pgd)) = 0UL) + +static inline unsigned long pud_large(pud_t pud) +{ + pte_t pte = __pte(pud_val(pud)); + + return pte_val(pte) & _PAGE_PMD_HUGE; +} + +static inline unsigned long pud_pfn(pud_t pud) +{ + pte_t pte = __pte(pud_val(pud)); + + return pte_pfn(pte); +} /* Same in both SUN4V and SUN4U. */ #define pte_none(pte) (!pte_val(pte)) +#define pgd_set(pgdp, pudp) \ + (pgd_val(*(pgdp)) = (__pa((unsigned long) (pudp)))) + /* to find an entry in a page-table-directory. */ #define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) #define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) @@ -807,6 +850,11 @@ static inline unsigned long __pmd_page(pmd_t pmd) /* to find an entry in a kernel page-table-directory */ #define pgd_offset_k(address) pgd_offset(&init_mm, address) +/* Find an entry in the third-level page table.. */ +#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) +#define pud_offset(pgdp, address) \ + ((pud_t *) pgd_page_vaddr(*(pgdp)) + pud_index(address)) + /* Find an entry in the second-level page table.. */ #define pmd_offset(pudp, address) \ ((pmd_t *) pud_page_vaddr(*(pudp)) + \ @@ -879,7 +927,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, #endif extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; -extern pmd_t swapper_low_pmd_dir[PTRS_PER_PMD]; extern void paging_init(void); extern unsigned long find_ecache_flush_span(unsigned long size); @@ -893,6 +940,10 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *); extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd); +#define __HAVE_ARCH_PMDP_INVALIDATE +extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp); + #define __HAVE_ARCH_PGTABLE_DEPOSIT extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable); @@ -919,18 +970,6 @@ extern unsigned long pte_file(pte_t); extern pte_t pgoff_to_pte(unsigned long); #define PTE_FILE_MAX_BITS (64UL - PAGE_SHIFT - 1UL) -extern unsigned long sparc64_valid_addr_bitmap[]; - -/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */ -static inline bool kern_addr_valid(unsigned long addr) -{ - unsigned long paddr = __pa(addr); - - if ((paddr >> 41UL) != 0UL) - return false; - return test_bit(paddr >> 22, sparc64_valid_addr_bitmap); -} - extern int page_in_phys_avail(unsigned long paddr); /* diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h index 5e35e05..acd6146 100644 --- a/arch/sparc/include/asm/setup.h +++ b/arch/sparc/include/asm/setup.h @@ -24,6 +24,10 @@ static inline int con_is_present(void) } #endif +#ifdef CONFIG_SPARC64 +extern void __init start_early_boot(void); +#endif + extern void sun_do_break(void); extern int stop_a_enabled; extern int scons_pwroff; diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h index 6b67e50..69424d4 100644 --- a/arch/sparc/include/asm/spitfire.h +++ b/arch/sparc/include/asm/spitfire.h @@ -45,6 +45,8 @@ #define SUN4V_CHIP_NIAGARA3 0x03 #define SUN4V_CHIP_NIAGARA4 0x04 #define SUN4V_CHIP_NIAGARA5 0x05 +#define SUN4V_CHIP_SPARC_M6 0x06 +#define SUN4V_CHIP_SPARC_M7 0x07 #define SUN4V_CHIP_SPARC64X 0x8a #define SUN4V_CHIP_UNKNOWN 0xff diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h index a5f01ac..cc6275c 100644 --- a/arch/sparc/include/asm/thread_info_64.h +++ b/arch/sparc/include/asm/thread_info_64.h @@ -63,7 +63,8 @@ struct thread_info { struct pt_regs *kern_una_regs; unsigned int kern_una_insn; - unsigned long fpregs[0] __attribute__ ((aligned(64))); + unsigned long fpregs[(7 * 256) / sizeof(unsigned long)] + __attribute__ ((aligned(64))); }; #endif /* !(__ASSEMBLY__) */ @@ -102,6 +103,7 @@ struct thread_info { #define FAULT_CODE_ITLB 0x04 /* Miss happened in I-TLB */ #define FAULT_CODE_WINFIXUP 0x08 /* Miss happened during spill/fill */ #define FAULT_CODE_BLKCOMMIT 0x10 /* Use blk-commit ASI in copy_page */ +#define FAULT_CODE_BAD_RA 0x20 /* Bad RA for sun4v */ #if PAGE_SHIFT == 13 #define THREAD_SIZE (2*PAGE_SIZE) diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h index 3c3c89f..7f9bab2 100644 --- a/arch/sparc/include/asm/tlbflush_64.h +++ b/arch/sparc/include/asm/tlbflush_64.h @@ -34,6 +34,8 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, { } +void flush_tlb_kernel_range(unsigned long start, unsigned long end); + #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE extern void flush_tlb_pending(void); @@ -48,11 +50,6 @@ extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end); #ifndef CONFIG_SMP -#define flush_tlb_kernel_range(start,end) \ -do { flush_tsb_kernel_range(start,end); \ - __flush_tlb_kernel_range(start,end); \ -} while (0) - static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) { __flush_tlb_page(CTX_HWBITS(mm->context), vaddr); @@ -63,11 +60,6 @@ static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vad extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end); extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr); -#define flush_tlb_kernel_range(start, end) \ -do { flush_tsb_kernel_range(start,end); \ - smp_flush_tlb_kernel_range(start, end); \ -} while (0) - #define global_flush_tlb_page(mm, vaddr) \ smp_flush_tlb_page(mm, vaddr) diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h index 2230f80..ecb49cf 100644 --- a/arch/sparc/include/asm/tsb.h +++ b/arch/sparc/include/asm/tsb.h @@ -133,9 +133,24 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; sub TSB, 0x8, TSB; \ TSB_STORE(TSB, TAG); - /* Do a kernel page table walk. Leaves physical PTE pointer in - * REG1. Jumps to FAIL_LABEL on early page table walk termination. - * VADDR will not be clobbered, but REG2 will. + /* Do a kernel page table walk. Leaves valid PTE value in + * REG1. Jumps to FAIL_LABEL on early page table walk + * termination. VADDR will not be clobbered, but REG2 will. + * + * There are two masks we must apply to propagate bits from + * the virtual address into the PTE physical address field + * when dealing with huge pages. This is because the page + * table boundaries do not match the huge page size(s) the + * hardware supports. + * + * In these cases we propagate the bits that are below the + * page table level where we saw the huge page mapping, but + * are still within the relevant physical bits for the huge + * page size in question. So for PMD mappings (which fall on + * bit 23, for 8MB per PMD) we must propagate bit 22 for a + * 4MB huge page. For huge PUDs (which fall on bit 33, for + * 8GB per PUD), we have to accomodate 256MB and 2GB huge + * pages. So for those we propagate bits 32 to 28. */ #define KERN_PGTABLE_WALK(VADDR, REG1, REG2, FAIL_LABEL) \ sethi %hi(swapper_pg_dir), REG1; \ @@ -145,15 +160,40 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; andn REG2, 0x7, REG2; \ ldx [REG1 + REG2], REG1; \ brz,pn REG1, FAIL_LABEL; \ - sllx VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \ + sllx VADDR, 64 - (PUD_SHIFT + PUD_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ andn REG2, 0x7, REG2; \ ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ brz,pn REG1, FAIL_LABEL; \ - sllx VADDR, 64 - PMD_SHIFT, REG2; \ + sethi %uhi(_PAGE_PUD_HUGE), REG2; \ + brz,pn REG1, FAIL_LABEL; \ + sllx REG2, 32, REG2; \ + andcc REG1, REG2, %g0; \ + sethi %hi(0xf8000000), REG2; \ + bne,pt %xcc, 697f; \ + sllx REG2, 1, REG2; \ + sllx VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ andn REG2, 0x7, REG2; \ - add REG1, REG2, REG1; + ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ + sethi %uhi(_PAGE_PMD_HUGE), REG2; \ + brz,pn REG1, FAIL_LABEL; \ + sllx REG2, 32, REG2; \ + andcc REG1, REG2, %g0; \ + be,pn %xcc, 698f; \ + sethi %hi(0x400000), REG2; \ +697: brgez,pn REG1, FAIL_LABEL; \ + andn REG1, REG2, REG1; \ + and VADDR, REG2, REG2; \ + ba,pt %xcc, 699f; \ + or REG1, REG2, REG1; \ +698: sllx VADDR, 64 - PMD_SHIFT, REG2; \ + srlx REG2, 64 - PAGE_SHIFT, REG2; \ + andn REG2, 0x7, REG2; \ + ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ + brgez,pn REG1, FAIL_LABEL; \ + nop; \ +699: /* PMD has been loaded into REG1, interpret the value, seeing * if it is a HUGE PMD or a normal one. If it is not valid @@ -171,7 +211,8 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; andcc REG1, REG2, %g0; \ be,pt %xcc, 700f; \ sethi %hi(4 * 1024 * 1024), REG2; \ - andn REG1, REG2, REG1; \ + brgez,pn REG1, FAIL_LABEL; \ + andn REG1, REG2, REG1; \ and VADDR, REG2, REG2; \ brlz,pt REG1, PTE_LABEL; \ or REG1, REG2, REG1; \ @@ -197,6 +238,11 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; andn REG2, 0x7, REG2; \ ldxa [PHYS_PGD + REG2] ASI_PHYS_USE_EC, REG1; \ brz,pn REG1, FAIL_LABEL; \ + sllx VADDR, 64 - (PUD_SHIFT + PUD_BITS), REG2; \ + srlx REG2, 64 - PAGE_SHIFT, REG2; \ + andn REG2, 0x7, REG2; \ + ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ + brz,pn REG1, FAIL_LABEL; \ sllx VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ andn REG2, 0x7, REG2; \ @@ -245,8 +291,6 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; (KERNEL_TSB_SIZE_BYTES / 16) #define KERNEL_TSB4M_NENTRIES 4096 -#define KTSB_PHYS_SHIFT 15 - /* Do a kernel TSB lookup at tl>0 on VADDR+TAG, branch to OK_LABEL * on TSB hit. REG1, REG2, REG3, and REG4 are used as temporaries * and the found TTE will be left in REG1. REG3 and REG4 must @@ -255,17 +299,15 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; * VADDR and TAG will be preserved and not clobbered by this macro. */ #define KERN_TSB_LOOKUP_TL1(VADDR, TAG, REG1, REG2, REG3, REG4, OK_LABEL) \ -661: sethi %hi(swapper_tsb), REG1; \ - or REG1, %lo(swapper_tsb), REG1; \ +661: sethi %uhi(swapper_tsb), REG1; \ + sethi %hi(swapper_tsb), REG2; \ + or REG1, %ulo(swapper_tsb), REG1; \ + or REG2, %lo(swapper_tsb), REG2; \ .section .swapper_tsb_phys_patch, "ax"; \ .word 661b; \ .previous; \ -661: nop; \ - .section .tsb_ldquad_phys_patch, "ax"; \ - .word 661b; \ - sllx REG1, KTSB_PHYS_SHIFT, REG1; \ - sllx REG1, KTSB_PHYS_SHIFT, REG1; \ - .previous; \ + sllx REG1, 32, REG1; \ + or REG1, REG2, REG1; \ srlx VADDR, PAGE_SHIFT, REG2; \ and REG2, (KERNEL_TSB_NENTRIES - 1), REG2; \ sllx REG2, 4, REG2; \ @@ -280,17 +322,15 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; * we can make use of that for the index computation. */ #define KERN_TSB4M_LOOKUP_TL1(TAG, REG1, REG2, REG3, REG4, OK_LABEL) \ -661: sethi %hi(swapper_4m_tsb), REG1; \ - or REG1, %lo(swapper_4m_tsb), REG1; \ +661: sethi %uhi(swapper_4m_tsb), REG1; \ + sethi %hi(swapper_4m_tsb), REG2; \ + or REG1, %ulo(swapper_4m_tsb), REG1; \ + or REG2, %lo(swapper_4m_tsb), REG2; \ .section .swapper_4m_tsb_phys_patch, "ax"; \ .word 661b; \ .previous; \ -661: nop; \ - .section .tsb_ldquad_phys_patch, "ax"; \ - .word 661b; \ - sllx REG1, KTSB_PHYS_SHIFT, REG1; \ - sllx REG1, KTSB_PHYS_SHIFT, REG1; \ - .previous; \ + sllx REG1, 32, REG1; \ + or REG1, REG2, REG1; \ and TAG, (KERNEL_TSB4M_NENTRIES - 1), REG2; \ sllx REG2, 4, REG2; \ add REG1, REG2, REG2; \ diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h index 432afa8..55841c1 100644 --- a/arch/sparc/include/asm/vio.h +++ b/arch/sparc/include/asm/vio.h @@ -118,12 +118,18 @@ struct vio_disk_attr_info { u8 vdisk_type; #define VD_DISK_TYPE_SLICE 0x01 /* Slice in block device */ #define VD_DISK_TYPE_DISK 0x02 /* Entire block device */ - u16 resv1; + u8 vdisk_mtype; /* v1.1 */ +#define VD_MEDIA_TYPE_FIXED 0x01 /* Fixed device */ +#define VD_MEDIA_TYPE_CD 0x02 /* CD Device */ +#define VD_MEDIA_TYPE_DVD 0x03 /* DVD Device */ + u8 resv1; u32 vdisk_block_size; u64 operations; - u64 vdisk_size; + u64 vdisk_size; /* v1.1 */ u64 max_xfer_size; - u64 resv2[2]; + u32 phys_block_size; /* v1.2 */ + u32 resv2; + u64 resv3[1]; }; struct vio_disk_desc { @@ -259,7 +265,7 @@ static inline u32 vio_dring_avail(struct vio_dring_state *dr, unsigned int ring_size) { return (dr->pending - - ((dr->prod - dr->cons) & (ring_size - 1))); + ((dr->prod - dr->cons) & (ring_size - 1)) - 1); } #define VIO_MAX_TYPE_LEN 32 diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h index 39ca301..50d6f16 100644 --- a/arch/sparc/include/asm/visasm.h +++ b/arch/sparc/include/asm/visasm.h @@ -28,18 +28,20 @@ * Must preserve %o5 between VISEntryHalf and VISExitHalf */ #define VISEntryHalf \ + VISEntry + +#define VISExitHalf \ + VISExit + +#define VISEntryHalfFast(fail_label) \ rd %fprs, %o5; \ andcc %o5, FPRS_FEF, %g0; \ be,pt %icc, 297f; \ - sethi %hi(298f), %g7; \ - sethi %hi(VISenterhalf), %g1; \ - jmpl %g1 + %lo(VISenterhalf), %g0; \ - or %g7, %lo(298f), %g7; \ - clr %o5; \ -297: wr %o5, FPRS_FEF, %fprs; \ -298: + nop; \ + ba,a,pt %xcc, fail_label; \ +297: wr %o5, FPRS_FEF, %fprs; -#define VISExitHalf \ +#define VISExitHalfFast \ wr %o5, 0, %fprs; #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/uapi/asm/swab.h b/arch/sparc/include/uapi/asm/swab.h index a34ad07..4c7c12d 100644 --- a/arch/sparc/include/uapi/asm/swab.h +++ b/arch/sparc/include/uapi/asm/swab.h @@ -9,9 +9,9 @@ static inline __u16 __arch_swab16p(const __u16 *addr) { __u16 ret; - __asm__ __volatile__ ("lduha [%1] %2, %0" + __asm__ __volatile__ ("lduha [%2] %3, %0" : "=r" (ret) - : "r" (addr), "i" (ASI_PL)); + : "m" (*addr), "r" (addr), "i" (ASI_PL)); return ret; } #define __arch_swab16p __arch_swab16p @@ -20,9 +20,9 @@ static inline __u32 __arch_swab32p(const __u32 *addr) { __u32 ret; - __asm__ __volatile__ ("lduwa [%1] %2, %0" + __asm__ __volatile__ ("lduwa [%2] %3, %0" : "=r" (ret) - : "r" (addr), "i" (ASI_PL)); + : "m" (*addr), "r" (addr), "i" (ASI_PL)); return ret; } #define __arch_swab32p __arch_swab32p @@ -31,9 +31,9 @@ static inline __u64 __arch_swab64p(const __u64 *addr) { __u64 ret; - __asm__ __volatile__ ("ldxa [%1] %2, %0" + __asm__ __volatile__ ("ldxa [%2] %3, %0" : "=r" (ret) - : "r" (addr), "i" (ASI_PL)); + : "m" (*addr), "r" (addr), "i" (ASI_PL)); return ret; } #define __arch_swab64p __arch_swab64p diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c index 5c51258..52e10de 100644 --- a/arch/sparc/kernel/cpu.c +++ b/arch/sparc/kernel/cpu.c @@ -493,6 +493,18 @@ static void __init sun4v_cpu_probe(void) sparc_pmu_type = "niagara5"; break; + case SUN4V_CHIP_SPARC_M6: + sparc_cpu_type = "SPARC-M6"; + sparc_fpu_type = "SPARC-M6 integrated FPU"; + sparc_pmu_type = "sparc-m6"; + break; + + case SUN4V_CHIP_SPARC_M7: + sparc_cpu_type = "SPARC-M7"; + sparc_fpu_type = "SPARC-M7 integrated FPU"; + sparc_pmu_type = "sparc-m7"; + break; + case SUN4V_CHIP_SPARC64X: sparc_cpu_type = "SPARC64-X"; sparc_fpu_type = "SPARC64-X integrated FPU"; diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c index de1c844..e69ec0e 100644 --- a/arch/sparc/kernel/cpumap.c +++ b/arch/sparc/kernel/cpumap.c @@ -326,6 +326,8 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index) case SUN4V_CHIP_NIAGARA3: case SUN4V_CHIP_NIAGARA4: case SUN4V_CHIP_NIAGARA5: + case SUN4V_CHIP_SPARC_M6: + case SUN4V_CHIP_SPARC_M7: case SUN4V_CHIP_SPARC64X: rover_inc_table = niagara_iterate_method; break; diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c index dff60ab..f87a55d 100644 --- a/arch/sparc/kernel/ds.c +++ b/arch/sparc/kernel/ds.c @@ -1200,14 +1200,14 @@ static int ds_probe(struct vio_dev *vdev, const struct vio_device_id *id) ds_cfg.tx_irq = vdev->tx_irq; ds_cfg.rx_irq = vdev->rx_irq; - lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp); + lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp, "DS"); if (IS_ERR(lp)) { err = PTR_ERR(lp); goto out_free_ds_states; } dp->lp = lp; - err = ldc_bind(lp, "DS"); + err = ldc_bind(lp); if (err) goto out_free_ldc; diff --git a/arch/sparc/kernel/dtlb_prot.S b/arch/sparc/kernel/dtlb_prot.S index b2c2c5b..d668ca14 100644 --- a/arch/sparc/kernel/dtlb_prot.S +++ b/arch/sparc/kernel/dtlb_prot.S @@ -24,11 +24,11 @@ mov TLB_TAG_ACCESS, %g4 ! For reload of vaddr /* PROT ** ICACHE line 2: More real fault processing */ + ldxa [%g4] ASI_DMMU, %g5 ! Put tagaccess in %g5 bgu,pn %xcc, winfix_trampoline ! Yes, perform winfixup - ldxa [%g4] ASI_DMMU, %g5 ! Put tagaccess in %g5 - ba,pt %xcc, sparc64_realfault_common ! Nope, normal fault mov FAULT_CODE_DTLB | FAULT_CODE_WRITE, %g4 - nop + ba,pt %xcc, sparc64_realfault_common ! Nope, normal fault + nop nop nop nop diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h index 140966f..c88ffb9 100644 --- a/arch/sparc/kernel/entry.h +++ b/arch/sparc/kernel/entry.h @@ -66,13 +66,10 @@ struct pause_patch_entry { extern struct pause_patch_entry __pause_3insn_patch, __pause_3insn_patch_end; -extern void __init per_cpu_patch(void); extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *, struct sun4v_1insn_patch_entry *); extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *, struct sun4v_2insn_patch_entry *); -extern void __init sun4v_patch(void); -extern void __init boot_cpu_id_too_large(int cpu); extern unsigned int dcache_parity_tl1_occurred; extern unsigned int icache_parity_tl1_occurred; diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 26b706a..3d61fca 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -282,8 +282,8 @@ sun4v_chip_type: stx %l2, [%l4 + 0x0] ldx [%sp + 2047 + 128 + 0x50], %l3 ! physaddr low /* 4MB align */ - srlx %l3, 22, %l3 - sllx %l3, 22, %l3 + srlx %l3, ILOG2_4MB, %l3 + sllx %l3, ILOG2_4MB, %l3 stx %l3, [%l4 + 0x8] /* Leave service as-is, "call-method" */ @@ -427,6 +427,12 @@ sun4v_chip_type: cmp %g2, '5' be,pt %xcc, 5f mov SUN4V_CHIP_NIAGARA5, %g4 + cmp %g2, '6' + be,pt %xcc, 5f + mov SUN4V_CHIP_SPARC_M6, %g4 + cmp %g2, '7' + be,pt %xcc, 5f + mov SUN4V_CHIP_SPARC_M7, %g4 ba,pt %xcc, 49f nop @@ -585,6 +591,12 @@ niagara_tlb_fixup: cmp %g1, SUN4V_CHIP_NIAGARA5 be,pt %xcc, niagara4_patch nop + cmp %g1, SUN4V_CHIP_SPARC_M6 + be,pt %xcc, niagara4_patch + nop + cmp %g1, SUN4V_CHIP_SPARC_M7 + be,pt %xcc, niagara4_patch + nop call generic_patch_copyops nop @@ -660,14 +672,12 @@ tlb_fixup_done: sethi %hi(init_thread_union), %g6 or %g6, %lo(init_thread_union), %g6 ldx [%g6 + TI_TASK], %g4 - mov %sp, %l6 wr %g0, ASI_P, %asi mov 1, %g1 sllx %g1, THREAD_SHIFT, %g1 sub %g1, (STACKFRAME_SZ + STACK_BIAS), %g1 add %g6, %g1, %sp - mov 0, %fp /* Set per-cpu pointer initially to zero, this makes * the boot-cpu use the in-kernel-image per-cpu areas @@ -694,44 +704,14 @@ tlb_fixup_done: nop #endif - mov %l6, %o1 ! OpenPROM stack call prom_init mov %l7, %o0 ! OpenPROM cif handler - /* Initialize current_thread_info()->cpu as early as possible. - * In order to do that accurately we have to patch up the get_cpuid() - * assembler sequences. And that, in turn, requires that we know - * if we are on a Starfire box or not. While we're here, patch up - * the sun4v sequences as well. + /* To create a one-register-window buffer between the kernel's + * initial stack and the last stack frame we use from the firmware, + * do the rest of the boot from a C helper function. */ - call check_if_starfire - nop - call per_cpu_patch - nop - call sun4v_patch - nop - -#ifdef CONFIG_SMP - call hard_smp_processor_id - nop - cmp %o0, NR_CPUS - blu,pt %xcc, 1f - nop - call boot_cpu_id_too_large - nop - /* Not reached... */ - -1: -#else - mov 0, %o0 -#endif - sth %o0, [%g6 + TI_CPU] - - call prom_init_report - nop - - /* Off we go.... */ - call start_kernel + call start_early_boot nop /* Not reached... */ diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c index c0a2de0..5c55145 100644 --- a/arch/sparc/kernel/hvapi.c +++ b/arch/sparc/kernel/hvapi.c @@ -46,6 +46,7 @@ static struct api_info api_table[] = { { .group = HV_GRP_VF_CPU, }, { .group = HV_GRP_KT_CPU, }, { .group = HV_GRP_VT_CPU, }, + { .group = HV_GRP_T5_CPU, }, { .group = HV_GRP_DIAG, .flags = FLAG_PRE_API }, }; diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S index f3ab509..caedf83 100644 --- a/arch/sparc/kernel/hvcalls.S +++ b/arch/sparc/kernel/hvcalls.S @@ -821,3 +821,19 @@ ENTRY(sun4v_vt_set_perfreg) retl nop ENDPROC(sun4v_vt_set_perfreg) + +ENTRY(sun4v_t5_get_perfreg) + mov %o1, %o4 + mov HV_FAST_T5_GET_PERFREG, %o5 + ta HV_FAST_TRAP + stx %o1, [%o4] + retl + nop +ENDPROC(sun4v_t5_get_perfreg) + +ENTRY(sun4v_t5_set_perfreg) + mov HV_FAST_T5_SET_PERFREG, %o5 + ta HV_FAST_TRAP + retl + nop +ENDPROC(sun4v_t5_set_perfreg) diff --git a/arch/sparc/kernel/hvtramp.S b/arch/sparc/kernel/hvtramp.S index b7ddcdd..cdbfec2 100644 --- a/arch/sparc/kernel/hvtramp.S +++ b/arch/sparc/kernel/hvtramp.S @@ -109,7 +109,6 @@ hv_cpu_startup: sllx %g5, THREAD_SHIFT, %g5 sub %g5, (STACKFRAME_SZ + STACK_BIAS), %g5 add %g6, %g5, %sp - mov 0, %fp call init_irqwork_curcpu nop diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index e7e215d..c2d81ad 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -278,7 +278,8 @@ static void *sbus_alloc_coherent(struct device *dev, size_t len, } order = get_order(len_total); - if ((va = __get_free_pages(GFP_KERNEL|__GFP_COMP, order)) == 0) + va = __get_free_pages(gfp, order); + if (va == 0) goto err_nopages; if ((res = kzalloc(sizeof(struct resource), GFP_KERNEL)) == NULL) @@ -443,7 +444,7 @@ static void *pci32_alloc_coherent(struct device *dev, size_t len, } order = get_order(len_total); - va = (void *) __get_free_pages(GFP_KERNEL, order); + va = (void *) __get_free_pages(gfp, order); if (va == NULL) { printk("pci_alloc_consistent: no %ld pages\n", len_total>>PAGE_SHIFT); goto err_nopages; diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 666193f..4033c23 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -47,8 +47,6 @@ #include "cpumap.h" #include "kstack.h" -#define NUM_IVECS (IMAP_INR + 1) - struct ino_bucket *ivector_table; unsigned long ivector_table_pa; @@ -107,55 +105,196 @@ static void bucket_set_irq(unsigned long bucket_pa, unsigned int irq) #define irq_work_pa(__cpu) &(trap_block[(__cpu)].irq_worklist_pa) -static struct { - unsigned int dev_handle; - unsigned int dev_ino; - unsigned int in_use; -} irq_table[NR_IRQS]; -static DEFINE_SPINLOCK(irq_alloc_lock); +static unsigned long hvirq_major __initdata; +static int __init early_hvirq_major(char *p) +{ + int rc = kstrtoul(p, 10, &hvirq_major); + + return rc; +} +early_param("hvirq", early_hvirq_major); + +static int hv_irq_version; + +/* Major version 2.0 of HV_GRP_INTR added support for the VIRQ cookie + * based interfaces, but: + * + * 1) Several OSs, Solaris and Linux included, use them even when only + * negotiating version 1.0 (or failing to negotiate at all). So the + * hypervisor has a workaround that provides the VIRQ interfaces even + * when only verion 1.0 of the API is in use. + * + * 2) Second, and more importantly, with major version 2.0 these VIRQ + * interfaces only were actually hooked up for LDC interrupts, even + * though the Hypervisor specification clearly stated: + * + * The new interrupt API functions will be available to a guest + * when it negotiates version 2.0 in the interrupt API group 0x2. When + * a guest negotiates version 2.0, all interrupt sources will only + * support using the cookie interface, and any attempt to use the + * version 1.0 interrupt APIs numbered 0xa0 to 0xa6 will result in the + * ENOTSUPPORTED error being returned. + * + * with an emphasis on "all interrupt sources". + * + * To correct this, major version 3.0 was created which does actually + * support VIRQs for all interrupt sources (not just LDC devices). So + * if we want to move completely over the cookie based VIRQs we must + * negotiate major version 3.0 or later of HV_GRP_INTR. + */ +static bool sun4v_cookie_only_virqs(void) +{ + if (hv_irq_version >= 3) + return true; + return false; +} -unsigned char irq_alloc(unsigned int dev_handle, unsigned int dev_ino) +static void __init irq_init_hv(void) { - unsigned long flags; - unsigned char ent; + unsigned long hv_error, major, minor = 0; + + if (tlb_type != hypervisor) + return; - BUILD_BUG_ON(NR_IRQS >= 256); + if (hvirq_major) + major = hvirq_major; + else + major = 3; - spin_lock_irqsave(&irq_alloc_lock, flags); + hv_error = sun4v_hvapi_register(HV_GRP_INTR, major, &minor); + if (!hv_error) + hv_irq_version = major; + else + hv_irq_version = 1; - for (ent = 1; ent < NR_IRQS; ent++) { - if (!irq_table[ent].in_use) + pr_info("SUN4V: Using IRQ API major %d, cookie only virqs %s\n", + hv_irq_version, + sun4v_cookie_only_virqs() ? "enabled" : "disabled"); +} + +/* This function is for the timer interrupt.*/ +int __init arch_probe_nr_irqs(void) +{ + return 1; +} + +#define DEFAULT_NUM_IVECS (0xfffU) +static unsigned int nr_ivec = DEFAULT_NUM_IVECS; +#define NUM_IVECS (nr_ivec) + +static unsigned int __init size_nr_ivec(void) +{ + if (tlb_type == hypervisor) { + switch (sun4v_chip_type) { + /* Athena's devhandle|devino is large.*/ + case SUN4V_CHIP_SPARC64X: + nr_ivec = 0xffff; break; + } } - if (ent >= NR_IRQS) { - printk(KERN_ERR "IRQ: Out of virtual IRQs.\n"); - ent = 0; - } else { - irq_table[ent].dev_handle = dev_handle; - irq_table[ent].dev_ino = dev_ino; - irq_table[ent].in_use = 1; - } + return nr_ivec; +} + +struct irq_handler_data { + union { + struct { + unsigned int dev_handle; + unsigned int dev_ino; + }; + unsigned long sysino; + }; + struct ino_bucket bucket; + unsigned long iclr; + unsigned long imap; +}; + +static inline unsigned int irq_data_to_handle(struct irq_data *data) +{ + struct irq_handler_data *ihd = data->handler_data; + + return ihd->dev_handle; +} + +static inline unsigned int irq_data_to_ino(struct irq_data *data) +{ + struct irq_handler_data *ihd = data->handler_data; - spin_unlock_irqrestore(&irq_alloc_lock, flags); + return ihd->dev_ino; +} + +static inline unsigned long irq_data_to_sysino(struct irq_data *data) +{ + struct irq_handler_data *ihd = data->handler_data; - return ent; + return ihd->sysino; } -#ifdef CONFIG_PCI_MSI void irq_free(unsigned int irq) { - unsigned long flags; + void *data = irq_get_handler_data(irq); - if (irq >= NR_IRQS) - return; + kfree(data); + irq_set_handler_data(irq, NULL); + irq_free_descs(irq, 1); +} - spin_lock_irqsave(&irq_alloc_lock, flags); +unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino) +{ + int irq; - irq_table[irq].in_use = 0; + irq = __irq_alloc_descs(-1, 1, 1, numa_node_id(), NULL); + if (irq <= 0) + goto out; - spin_unlock_irqrestore(&irq_alloc_lock, flags); + return irq; +out: + return 0; +} + +static unsigned int cookie_exists(u32 devhandle, unsigned int devino) +{ + unsigned long hv_err, cookie; + struct ino_bucket *bucket; + unsigned int irq = 0U; + + hv_err = sun4v_vintr_get_cookie(devhandle, devino, &cookie); + if (hv_err) { + pr_err("HV get cookie failed hv_err = %ld\n", hv_err); + goto out; + } + + if (cookie & ((1UL << 63UL))) { + cookie = ~cookie; + bucket = (struct ino_bucket *) __va(cookie); + irq = bucket->__irq; + } +out: + return irq; +} + +static unsigned int sysino_exists(u32 devhandle, unsigned int devino) +{ + unsigned long sysino = sun4v_devino_to_sysino(devhandle, devino); + struct ino_bucket *bucket; + unsigned int irq; + + bucket = &ivector_table[sysino]; + irq = bucket_get_irq(__pa(bucket)); + + return irq; +} + +void ack_bad_irq(unsigned int irq) +{ + pr_crit("BAD IRQ ack %d\n", irq); +} + +void irq_install_pre_handler(int irq, + void (*func)(unsigned int, void *, void *), + void *arg1, void *arg2) +{ + pr_warn("IRQ pre handler NOT supported.\n"); } -#endif /* * /proc/interrupts printing: @@ -206,15 +345,6 @@ static unsigned int sun4u_compute_tid(unsigned long imap, unsigned long cpuid) return tid; } -struct irq_handler_data { - unsigned long iclr; - unsigned long imap; - - void (*pre_handler)(unsigned int, void *, void *); - void *arg1; - void *arg2; -}; - #ifdef CONFIG_SMP static int irq_choose_cpu(unsigned int irq, const struct cpumask *affinity) { @@ -316,8 +446,8 @@ static void sun4u_irq_eoi(struct irq_data *data) static void sun4v_irq_enable(struct irq_data *data) { - unsigned int ino = irq_table[data->irq].dev_ino; unsigned long cpuid = irq_choose_cpu(data->irq, data->affinity); + unsigned int ino = irq_data_to_sysino(data); int err; err = sun4v_intr_settarget(ino, cpuid); @@ -337,8 +467,8 @@ static void sun4v_irq_enable(struct irq_data *data) static int sun4v_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - unsigned int ino = irq_table[data->irq].dev_ino; unsigned long cpuid = irq_choose_cpu(data->irq, mask); + unsigned int ino = irq_data_to_sysino(data); int err; err = sun4v_intr_settarget(ino, cpuid); @@ -351,7 +481,7 @@ static int sun4v_set_affinity(struct irq_data *data, static void sun4v_irq_disable(struct irq_data *data) { - unsigned int ino = irq_table[data->irq].dev_ino; + unsigned int ino = irq_data_to_sysino(data); int err; err = sun4v_intr_setenabled(ino, HV_INTR_DISABLED); @@ -362,7 +492,7 @@ static void sun4v_irq_disable(struct irq_data *data) static void sun4v_irq_eoi(struct irq_data *data) { - unsigned int ino = irq_table[data->irq].dev_ino; + unsigned int ino = irq_data_to_sysino(data); int err; err = sun4v_intr_setstate(ino, HV_INTR_STATE_IDLE); @@ -373,14 +503,13 @@ static void sun4v_irq_eoi(struct irq_data *data) static void sun4v_virq_enable(struct irq_data *data) { - unsigned long cpuid, dev_handle, dev_ino; + unsigned long dev_handle = irq_data_to_handle(data); + unsigned long dev_ino = irq_data_to_ino(data); + unsigned long cpuid; int err; cpuid = irq_choose_cpu(data->irq, data->affinity); - dev_handle = irq_table[data->irq].dev_handle; - dev_ino = irq_table[data->irq].dev_ino; - err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid); if (err != HV_EOK) printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): " @@ -403,14 +532,13 @@ static void sun4v_virq_enable(struct irq_data *data) static int sun4v_virt_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - unsigned long cpuid, dev_handle, dev_ino; + unsigned long dev_handle = irq_data_to_handle(data); + unsigned long dev_ino = irq_data_to_ino(data); + unsigned long cpuid; int err; cpuid = irq_choose_cpu(data->irq, mask); - dev_handle = irq_table[data->irq].dev_handle; - dev_ino = irq_table[data->irq].dev_ino; - err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid); if (err != HV_EOK) printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): " @@ -422,11 +550,10 @@ static int sun4v_virt_set_affinity(struct irq_data *data, static void sun4v_virq_disable(struct irq_data *data) { - unsigned long dev_handle, dev_ino; + unsigned long dev_handle = irq_data_to_handle(data); + unsigned long dev_ino = irq_data_to_ino(data); int err; - dev_handle = irq_table[data->irq].dev_handle; - dev_ino = irq_table[data->irq].dev_ino; err = sun4v_vintr_set_valid(dev_handle, dev_ino, HV_INTR_DISABLED); @@ -438,12 +565,10 @@ static void sun4v_virq_disable(struct irq_data *data) static void sun4v_virq_eoi(struct irq_data *data) { - unsigned long dev_handle, dev_ino; + unsigned long dev_handle = irq_data_to_handle(data); + unsigned long dev_ino = irq_data_to_ino(data); int err; - dev_handle = irq_table[data->irq].dev_handle; - dev_ino = irq_table[data->irq].dev_ino; - err = sun4v_vintr_set_state(dev_handle, dev_ino, HV_INTR_STATE_IDLE); if (err != HV_EOK) @@ -479,31 +604,10 @@ static struct irq_chip sun4v_virq = { .flags = IRQCHIP_EOI_IF_HANDLED, }; -static void pre_flow_handler(struct irq_data *d) -{ - struct irq_handler_data *handler_data = irq_data_get_irq_handler_data(d); - unsigned int ino = irq_table[d->irq].dev_ino; - - handler_data->pre_handler(ino, handler_data->arg1, handler_data->arg2); -} - -void irq_install_pre_handler(int irq, - void (*func)(unsigned int, void *, void *), - void *arg1, void *arg2) -{ - struct irq_handler_data *handler_data = irq_get_handler_data(irq); - - handler_data->pre_handler = func; - handler_data->arg1 = arg1; - handler_data->arg2 = arg2; - - __irq_set_preflow_handler(irq, pre_flow_handler); -} - unsigned int build_irq(int inofixup, unsigned long iclr, unsigned long imap) { - struct ino_bucket *bucket; struct irq_handler_data *handler_data; + struct ino_bucket *bucket; unsigned int irq; int ino; @@ -537,119 +641,166 @@ out: return irq; } -static unsigned int sun4v_build_common(unsigned long sysino, - struct irq_chip *chip) +static unsigned int sun4v_build_common(u32 devhandle, unsigned int devino, + void (*handler_data_init)(struct irq_handler_data *data, + u32 devhandle, unsigned int devino), + struct irq_chip *chip) { - struct ino_bucket *bucket; - struct irq_handler_data *handler_data; + struct irq_handler_data *data; unsigned int irq; - BUG_ON(tlb_type != hypervisor); + irq = irq_alloc(devhandle, devino); + if (!irq) + goto out; - bucket = &ivector_table[sysino]; - irq = bucket_get_irq(__pa(bucket)); - if (!irq) { - irq = irq_alloc(0, sysino); - bucket_set_irq(__pa(bucket), irq); - irq_set_chip_and_handler_name(irq, chip, handle_fasteoi_irq, - "IVEC"); + data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC); + if (unlikely(!data)) { + pr_err("IRQ handler data allocation failed.\n"); + irq_free(irq); + irq = 0; + goto out; } - handler_data = irq_get_handler_data(irq); - if (unlikely(handler_data)) - goto out; + irq_set_handler_data(irq, data); + handler_data_init(data, devhandle, devino); + irq_set_chip_and_handler_name(irq, chip, handle_fasteoi_irq, "IVEC"); + data->imap = ~0UL; + data->iclr = ~0UL; +out: + return irq; +} - handler_data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC); - if (unlikely(!handler_data)) { - prom_printf("IRQ: kzalloc(irq_handler_data) failed.\n"); - prom_halt(); - } - irq_set_handler_data(irq, handler_data); +static unsigned long cookie_assign(unsigned int irq, u32 devhandle, + unsigned int devino) +{ + struct irq_handler_data *ihd = irq_get_handler_data(irq); + unsigned long hv_error, cookie; - /* Catch accidental accesses to these things. IMAP/ICLR handling - * is done by hypervisor calls on sun4v platforms, not by direct - * register accesses. + /* handler_irq needs to find the irq. cookie is seen signed in + * sun4v_dev_mondo and treated as a non ivector_table delivery. */ - handler_data->imap = ~0UL; - handler_data->iclr = ~0UL; + ihd->bucket.__irq = irq; + cookie = ~__pa(&ihd->bucket); -out: - return irq; + hv_error = sun4v_vintr_set_cookie(devhandle, devino, cookie); + if (hv_error) + pr_err("HV vintr set cookie failed = %ld\n", hv_error); + + return hv_error; } -unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino) +static void cookie_handler_data(struct irq_handler_data *data, + u32 devhandle, unsigned int devino) { - unsigned long sysino = sun4v_devino_to_sysino(devhandle, devino); + data->dev_handle = devhandle; + data->dev_ino = devino; +} - return sun4v_build_common(sysino, &sun4v_irq); +static unsigned int cookie_build_irq(u32 devhandle, unsigned int devino, + struct irq_chip *chip) +{ + unsigned long hv_error; + unsigned int irq; + + irq = sun4v_build_common(devhandle, devino, cookie_handler_data, chip); + + hv_error = cookie_assign(irq, devhandle, devino); + if (hv_error) { + irq_free(irq); + irq = 0; + } + + return irq; } -unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino) +static unsigned int sun4v_build_cookie(u32 devhandle, unsigned int devino) { - struct irq_handler_data *handler_data; - unsigned long hv_err, cookie; - struct ino_bucket *bucket; unsigned int irq; - bucket = kzalloc(sizeof(struct ino_bucket), GFP_ATOMIC); - if (unlikely(!bucket)) - return 0; + irq = cookie_exists(devhandle, devino); + if (irq) + goto out; - /* The only reference we store to the IRQ bucket is - * by physical address which kmemleak can't see, tell - * it that this object explicitly is not a leak and - * should be scanned. - */ - kmemleak_not_leak(bucket); + irq = cookie_build_irq(devhandle, devino, &sun4v_virq); - __flush_dcache_range((unsigned long) bucket, - ((unsigned long) bucket + - sizeof(struct ino_bucket))); +out: + return irq; +} - irq = irq_alloc(devhandle, devino); +static void sysino_set_bucket(unsigned int irq) +{ + struct irq_handler_data *ihd = irq_get_handler_data(irq); + struct ino_bucket *bucket; + unsigned long sysino; + + sysino = sun4v_devino_to_sysino(ihd->dev_handle, ihd->dev_ino); + BUG_ON(sysino >= nr_ivec); + bucket = &ivector_table[sysino]; bucket_set_irq(__pa(bucket), irq); +} - irq_set_chip_and_handler_name(irq, &sun4v_virq, handle_fasteoi_irq, - "IVEC"); +static void sysino_handler_data(struct irq_handler_data *data, + u32 devhandle, unsigned int devino) +{ + unsigned long sysino; - handler_data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC); - if (unlikely(!handler_data)) - return 0; + sysino = sun4v_devino_to_sysino(devhandle, devino); + data->sysino = sysino; +} - /* In order to make the LDC channel startup sequence easier, - * especially wrt. locking, we do not let request_irq() enable - * the interrupt. - */ - irq_set_status_flags(irq, IRQ_NOAUTOEN); - irq_set_handler_data(irq, handler_data); +static unsigned int sysino_build_irq(u32 devhandle, unsigned int devino, + struct irq_chip *chip) +{ + unsigned int irq; - /* Catch accidental accesses to these things. IMAP/ICLR handling - * is done by hypervisor calls on sun4v platforms, not by direct - * register accesses. - */ - handler_data->imap = ~0UL; - handler_data->iclr = ~0UL; + irq = sun4v_build_common(devhandle, devino, sysino_handler_data, chip); + if (!irq) + goto out; - cookie = ~__pa(bucket); - hv_err = sun4v_vintr_set_cookie(devhandle, devino, cookie); - if (hv_err) { - prom_printf("IRQ: Fatal, cannot set cookie for [%x:%x] " - "err=%lu\n", devhandle, devino, hv_err); - prom_halt(); - } + sysino_set_bucket(irq); +out: + return irq; +} +static int sun4v_build_sysino(u32 devhandle, unsigned int devino) +{ + int irq; + + irq = sysino_exists(devhandle, devino); + if (irq) + goto out; + + irq = sysino_build_irq(devhandle, devino, &sun4v_irq); +out: return irq; } -void ack_bad_irq(unsigned int irq) +unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino) { - unsigned int ino = irq_table[irq].dev_ino; + unsigned int irq; - if (!ino) - ino = 0xdeadbeef; + if (sun4v_cookie_only_virqs()) + irq = sun4v_build_cookie(devhandle, devino); + else + irq = sun4v_build_sysino(devhandle, devino); - printk(KERN_CRIT "Unexpected IRQ from ino[%x] irq[%u]\n", - ino, irq); + return irq; +} + +unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino) +{ + int irq; + + irq = cookie_build_irq(devhandle, devino, &sun4v_virq); + if (!irq) + goto out; + + /* This is borrowed from the original function. + */ + irq_set_status_flags(irq, IRQ_NOAUTOEN); + +out: + return irq; } void *hardirq_stack[NR_CPUS]; @@ -720,9 +871,12 @@ void fixup_irqs(void) for (irq = 0; irq < NR_IRQS; irq++) { struct irq_desc *desc = irq_to_desc(irq); - struct irq_data *data = irq_desc_get_irq_data(desc); + struct irq_data *data; unsigned long flags; + if (!desc) + continue; + data = irq_desc_get_irq_data(desc); raw_spin_lock_irqsave(&desc->lock, flags); if (desc->action && !irqd_is_per_cpu(data)) { if (data->chip->irq_set_affinity) @@ -922,16 +1076,22 @@ static struct irqaction timer_irq_action = { .name = "timer", }; -/* Only invoked on boot processor. */ -void __init init_IRQ(void) +static void __init irq_ivector_init(void) { - unsigned long size; + unsigned long size, order; + unsigned int ivecs; - map_prom_timers(); - kill_prom_timer(); + /* If we are doing cookie only VIRQs then we do not need the ivector + * table to process interrupts. + */ + if (sun4v_cookie_only_virqs()) + return; - size = sizeof(struct ino_bucket) * NUM_IVECS; - ivector_table = kzalloc(size, GFP_KERNEL); + ivecs = size_nr_ivec(); + size = sizeof(struct ino_bucket) * ivecs; + order = get_order(size); + ivector_table = (struct ino_bucket *) + __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); if (!ivector_table) { prom_printf("Fatal error, cannot allocate ivector_table\n"); prom_halt(); @@ -940,6 +1100,15 @@ void __init init_IRQ(void) ((unsigned long) ivector_table) + size); ivector_table_pa = __pa(ivector_table); +} + +/* Only invoked on boot processor.*/ +void __init init_IRQ(void) +{ + irq_init_hv(); + irq_ivector_init(); + map_prom_timers(); + kill_prom_timer(); if (tlb_type == hypervisor) sun4v_init_mondo_queues(); diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S index 542e96a..ef0d8e9 100644 --- a/arch/sparc/kernel/ktlb.S +++ b/arch/sparc/kernel/ktlb.S @@ -47,14 +47,6 @@ kvmap_itlb_vmalloc_addr: KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath) TSB_LOCK_TAG(%g1, %g2, %g7) - - /* Load and check PTE. */ - ldxa [%g5] ASI_PHYS_USE_EC, %g5 - mov 1, %g7 - sllx %g7, TSB_TAG_INVALID_BIT, %g7 - brgez,a,pn %g5, kvmap_itlb_longpath - TSB_STORE(%g1, %g7) - TSB_WRITE(%g1, %g5, %g6) /* fallthrough to TLB load */ @@ -118,6 +110,12 @@ kvmap_dtlb_obp: ba,pt %xcc, kvmap_dtlb_load nop +kvmap_linear_early: + sethi %hi(kern_linear_pte_xor), %g7 + ldx [%g7 + %lo(kern_linear_pte_xor)], %g2 + ba,pt %xcc, kvmap_dtlb_tsb4m_load + xor %g2, %g4, %g5 + .align 32 kvmap_dtlb_tsb4m_load: TSB_LOCK_TAG(%g1, %g2, %g7) @@ -146,105 +144,17 @@ kvmap_dtlb_4v: /* Correct TAG_TARGET is already in %g6, check 4mb TSB. */ KERN_TSB4M_LOOKUP_TL1(%g6, %g5, %g1, %g2, %g3, kvmap_dtlb_load) #endif - /* TSB entry address left in %g1, lookup linear PTE. - * Must preserve %g1 and %g6 (TAG). - */ -kvmap_dtlb_tsb4m_miss: - /* Clear the PAGE_OFFSET top virtual bits, shift - * down to get PFN, and make sure PFN is in range. - */ -661: sllx %g4, 0, %g5 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - /* Check to see if we know about valid memory at the 4MB - * chunk this physical address will reside within. + /* Linear mapping TSB lookup failed. Fallthrough to kernel + * page table based lookup. */ -661: srlx %g5, MAX_PHYS_ADDRESS_BITS, %g2 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - brnz,pn %g2, kvmap_dtlb_longpath - nop - - /* This unconditional branch and delay-slot nop gets patched - * by the sethi sequence once the bitmap is properly setup. - */ - .globl valid_addr_bitmap_insn -valid_addr_bitmap_insn: - ba,pt %xcc, 2f - nop - .subsection 2 - .globl valid_addr_bitmap_patch -valid_addr_bitmap_patch: - sethi %hi(sparc64_valid_addr_bitmap), %g7 - or %g7, %lo(sparc64_valid_addr_bitmap), %g7 - .previous - -661: srlx %g5, ILOG2_4MB, %g2 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - srlx %g2, 6, %g5 - and %g2, 63, %g2 - sllx %g5, 3, %g5 - ldx [%g7 + %g5], %g5 - mov 1, %g7 - sllx %g7, %g2, %g7 - andcc %g5, %g7, %g0 - be,pn %xcc, kvmap_dtlb_longpath - -2: sethi %hi(kpte_linear_bitmap), %g2 - - /* Get the 256MB physical address index. */ -661: sllx %g4, 0, %g5 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - or %g2, %lo(kpte_linear_bitmap), %g2 - -661: srlx %g5, ILOG2_256MB, %g5 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - and %g5, (32 - 1), %g7 - - /* Divide by 32 to get the offset into the bitmask. */ - srlx %g5, 5, %g5 - add %g7, %g7, %g7 - sllx %g5, 3, %g5 - - /* kern_linear_pte_xor[(mask >> shift) & 3)] */ - ldx [%g2 + %g5], %g2 - srlx %g2, %g7, %g7 - sethi %hi(kern_linear_pte_xor), %g5 - and %g7, 3, %g7 - or %g5, %lo(kern_linear_pte_xor), %g5 - sllx %g7, 3, %g7 - ldx [%g5 + %g7], %g2 - .globl kvmap_linear_patch kvmap_linear_patch: - ba,pt %xcc, kvmap_dtlb_tsb4m_load - xor %g2, %g4, %g5 + ba,a,pt %xcc, kvmap_linear_early kvmap_dtlb_vmalloc_addr: KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath) TSB_LOCK_TAG(%g1, %g2, %g7) - - /* Load and check PTE. */ - ldxa [%g5] ASI_PHYS_USE_EC, %g5 - mov 1, %g7 - sllx %g7, TSB_TAG_INVALID_BIT, %g7 - brgez,a,pn %g5, kvmap_dtlb_longpath - TSB_STORE(%g1, %g7) - TSB_WRITE(%g1, %g5, %g6) /* fallthrough to TLB load */ @@ -276,13 +186,8 @@ kvmap_dtlb_load: #ifdef CONFIG_SPARSEMEM_VMEMMAP kvmap_vmemmap: - sub %g4, %g5, %g5 - srlx %g5, 22, %g5 - sethi %hi(vmemmap_table), %g1 - sllx %g5, 3, %g5 - or %g1, %lo(vmemmap_table), %g1 - ba,pt %xcc, kvmap_dtlb_load - ldx [%g1 + %g5], %g5 + KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath) + ba,a,pt %xcc, kvmap_dtlb_load #endif kvmap_dtlb_nonlinear: @@ -294,8 +199,8 @@ kvmap_dtlb_nonlinear: #ifdef CONFIG_SPARSEMEM_VMEMMAP /* Do not use the TSB for vmemmap. */ - mov (VMEMMAP_BASE >> 40), %g5 - sllx %g5, 40, %g5 + sethi %hi(VMEMMAP_BASE), %g5 + ldx [%g5 + %lo(VMEMMAP_BASE)], %g5 cmp %g4,%g5 bgeu,pn %xcc, kvmap_vmemmap nop @@ -307,8 +212,8 @@ kvmap_dtlb_tsbmiss: sethi %hi(MODULES_VADDR), %g5 cmp %g4, %g5 blu,pn %xcc, kvmap_dtlb_longpath - mov (VMALLOC_END >> 40), %g5 - sllx %g5, 40, %g5 + sethi %hi(VMALLOC_END), %g5 + ldx [%g5 + %lo(VMALLOC_END)], %g5 cmp %g4, %g5 bgeu,pn %xcc, kvmap_dtlb_longpath nop diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c index e01d75d..7ef2862 100644 --- a/arch/sparc/kernel/ldc.c +++ b/arch/sparc/kernel/ldc.c @@ -1078,7 +1078,8 @@ static void ldc_iommu_release(struct ldc_channel *lp) struct ldc_channel *ldc_alloc(unsigned long id, const struct ldc_channel_config *cfgp, - void *event_arg) + void *event_arg, + const char *name) { struct ldc_channel *lp; const struct ldc_mode_ops *mops; @@ -1093,6 +1094,8 @@ struct ldc_channel *ldc_alloc(unsigned long id, err = -EINVAL; if (!cfgp) goto out_err; + if (!name) + goto out_err; switch (cfgp->mode) { case LDC_MODE_RAW: @@ -1185,6 +1188,21 @@ struct ldc_channel *ldc_alloc(unsigned long id, INIT_HLIST_HEAD(&lp->mh_list); + snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name); + snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name); + + err = request_irq(lp->cfg.rx_irq, ldc_rx, 0, + lp->rx_irq_name, lp); + if (err) + goto out_free_txq; + + err = request_irq(lp->cfg.tx_irq, ldc_tx, 0, + lp->tx_irq_name, lp); + if (err) { + free_irq(lp->cfg.rx_irq, lp); + goto out_free_txq; + } + return lp; out_free_txq: @@ -1237,31 +1255,14 @@ EXPORT_SYMBOL(ldc_free); * state. This does not initiate a handshake, ldc_connect() does * that. */ -int ldc_bind(struct ldc_channel *lp, const char *name) +int ldc_bind(struct ldc_channel *lp) { unsigned long hv_err, flags; int err = -EINVAL; - if (!name || - (lp->state != LDC_STATE_INIT)) + if (lp->state != LDC_STATE_INIT) return -EINVAL; - snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name); - snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name); - - err = request_irq(lp->cfg.rx_irq, ldc_rx, 0, - lp->rx_irq_name, lp); - if (err) - return err; - - err = request_irq(lp->cfg.tx_irq, ldc_tx, 0, - lp->tx_irq_name, lp); - if (err) { - free_irq(lp->cfg.rx_irq, lp); - return err; - } - - spin_lock_irqsave(&lp->lock, flags); enable_irq(lp->cfg.rx_irq); @@ -1336,7 +1337,7 @@ int ldc_connect(struct ldc_channel *lp) if (!(lp->flags & LDC_FLAG_ALLOCED_QUEUES) || !(lp->flags & LDC_FLAG_REGISTERED_QUEUES) || lp->hs_state != LDC_HS_OPEN) - err = -EINVAL; + err = ((lp->hs_state > LDC_HS_OPEN) ? 0 : -EINVAL); else err = start_handshake(lp); @@ -2306,7 +2307,7 @@ void *ldc_alloc_exp_dring(struct ldc_channel *lp, unsigned int len, if (len & (8UL - 1)) return ERR_PTR(-EINVAL); - buf = kzalloc(len, GFP_KERNEL); + buf = kzalloc(len, GFP_ATOMIC); if (!buf) return ERR_PTR(-ENOMEM); diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 6479256..fce8ab1 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -141,7 +141,6 @@ static inline unsigned int get_nmi_count(int cpu) static __init void nmi_cpu_busy(void *data) { - local_irq_enable_in_hardirq(); while (endflag == 0) mb(); } diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c index 8f76f23..f9c6813 100644 --- a/arch/sparc/kernel/pci_schizo.c +++ b/arch/sparc/kernel/pci_schizo.c @@ -581,7 +581,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm) { unsigned long csr_reg, csr, csr_error_bits; irqreturn_t ret = IRQ_NONE; - u16 stat; + u32 stat; csr_reg = pbm->pbm_regs + SCHIZO_PCI_CTRL; csr = upa_readq(csr_reg); @@ -617,7 +617,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm) pbm->name); ret = IRQ_HANDLED; } - pci_read_config_word(pbm->pci_bus->self, PCI_STATUS, &stat); + pbm->pci_ops->read(pbm->pci_bus, 0, PCI_STATUS, 2, &stat); if (stat & (PCI_STATUS_PARITY | PCI_STATUS_SIG_TARGET_ABORT | PCI_STATUS_REC_TARGET_ABORT | @@ -625,7 +625,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm) PCI_STATUS_SIG_SYSTEM_ERROR)) { printk("%s: PCI bus error, PCI_STATUS[%04x]\n", pbm->name, stat); - pci_write_config_word(pbm->pci_bus->self, PCI_STATUS, 0xffff); + pbm->pci_ops->write(pbm->pci_bus, 0, PCI_STATUS, 2, 0xffff); ret = IRQ_HANDLED; } return ret; diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index 269af58..7e967c8 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -191,12 +191,41 @@ static const struct pcr_ops n4_pcr_ops = { .pcr_nmi_disable = PCR_N4_PICNPT, }; +static u64 n5_pcr_read(unsigned long reg_num) +{ + unsigned long val; + + (void) sun4v_t5_get_perfreg(reg_num, &val); + + return val; +} + +static void n5_pcr_write(unsigned long reg_num, u64 val) +{ + (void) sun4v_t5_set_perfreg(reg_num, val); +} + +static const struct pcr_ops n5_pcr_ops = { + .read_pcr = n5_pcr_read, + .write_pcr = n5_pcr_write, + .read_pic = n4_pic_read, + .write_pic = n4_pic_write, + .nmi_picl_value = n4_picl_value, + .pcr_nmi_enable = (PCR_N4_PICNPT | PCR_N4_STRACE | + PCR_N4_UTRACE | PCR_N4_TOE | + (26 << PCR_N4_SL_SHIFT)), + .pcr_nmi_disable = PCR_N4_PICNPT, +}; + + static unsigned long perf_hsvc_group; static unsigned long perf_hsvc_major; static unsigned long perf_hsvc_minor; static int __init register_perf_hsvc(void) { + unsigned long hverror; + if (tlb_type == hypervisor) { switch (sun4v_chip_type) { case SUN4V_CHIP_NIAGARA1: @@ -215,6 +244,10 @@ static int __init register_perf_hsvc(void) perf_hsvc_group = HV_GRP_VT_CPU; break; + case SUN4V_CHIP_NIAGARA5: + perf_hsvc_group = HV_GRP_T5_CPU; + break; + default: return -ENODEV; } @@ -222,10 +255,12 @@ static int __init register_perf_hsvc(void) perf_hsvc_major = 1; perf_hsvc_minor = 0; - if (sun4v_hvapi_register(perf_hsvc_group, - perf_hsvc_major, - &perf_hsvc_minor)) { - printk("perfmon: Could not register hvapi.\n"); + hverror = sun4v_hvapi_register(perf_hsvc_group, + perf_hsvc_major, + &perf_hsvc_minor); + if (hverror) { + pr_err("perfmon: Could not register hvapi(0x%lx).\n", + hverror); return -ENODEV; } } @@ -254,6 +289,10 @@ static int __init setup_sun4v_pcr_ops(void) pcr_ops = &n4_pcr_ops; break; + case SUN4V_CHIP_NIAGARA5: + pcr_ops = &n5_pcr_ops; + break; + default: ret = -ENODEV; break; diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index b5c38fa..3ccb677 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -960,6 +960,8 @@ out: cpuc->pcr[0] |= cpuc->event[0]->hw.config_base; } +static void sparc_pmu_start(struct perf_event *event, int flags); + /* On this PMU each PIC has it's own PCR control register. */ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc) { @@ -972,20 +974,13 @@ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc) struct perf_event *cp = cpuc->event[i]; struct hw_perf_event *hwc = &cp->hw; int idx = hwc->idx; - u64 enc; if (cpuc->current_idx[i] != PIC_NO_INDEX) continue; - sparc_perf_event_set_period(cp, hwc, idx); cpuc->current_idx[i] = idx; - enc = perf_event_get_enc(cpuc->events[i]); - cpuc->pcr[idx] &= ~mask_for_index(idx); - if (hwc->state & PERF_HES_STOPPED) - cpuc->pcr[idx] |= nop_for_index(idx); - else - cpuc->pcr[idx] |= event_encoding(enc, idx); + sparc_pmu_start(cp, PERF_EF_RELOAD); } out: for (i = 0; i < cpuc->n_events; i++) { @@ -1101,7 +1096,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags) int i; local_irq_save(flags); - perf_pmu_disable(event->pmu); for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event[i]) { @@ -1127,7 +1121,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags) } } - perf_pmu_enable(event->pmu); local_irq_restore(flags); } @@ -1361,7 +1354,6 @@ static int sparc_pmu_add(struct perf_event *event, int ef_flags) unsigned long flags; local_irq_save(flags); - perf_pmu_disable(event->pmu); n0 = cpuc->n_events; if (n0 >= sparc_pmu->max_hw_events) @@ -1394,7 +1386,6 @@ nocheck: ret = 0; out: - perf_pmu_enable(event->pmu); local_irq_restore(flags); return ret; } @@ -1662,7 +1653,8 @@ static bool __init supported_pmu(void) sparc_pmu = &niagara2_pmu; return true; } - if (!strcmp(sparc_pmu_type, "niagara4")) { + if (!strcmp(sparc_pmu_type, "niagara4") || + !strcmp(sparc_pmu_type, "niagara5")) { sparc_pmu = &niagara4_pmu; return true; } @@ -1671,9 +1663,12 @@ static bool __init supported_pmu(void) int __init init_hw_perf_events(void) { + int err; + pr_info("Performance events: "); - if (!supported_pmu()) { + err = pcr_arch_init(); + if (err || !supported_pmu()) { pr_cont("No support for PMU type '%s'\n", sparc_pmu_type); return 0; } @@ -1685,7 +1680,7 @@ int __init init_hw_perf_events(void) return 0; } -early_initcall(init_hw_perf_events); +pure_initcall(init_hw_perf_events); void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index d7b4967..1a79d68 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -281,6 +281,8 @@ void arch_trigger_all_cpu_backtrace(void) printk(" TPC[%lx] O7[%lx] I7[%lx] RPC[%lx]\n", gp->tpc, gp->o7, gp->i7, gp->rpc); } + + touch_nmi_watchdog(); } memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); @@ -306,6 +308,9 @@ static void __global_pmu_self(int this_cpu) struct global_pmu_snapshot *pp; int i, num; + if (!pcr_ops) + return; + pp = &global_cpu_snapshot[this_cpu].pmu; num = 1; @@ -353,6 +358,8 @@ static void pmu_snapshot_all_cpus(void) (cpu == this_cpu ? '*' : ' '), cpu, pp->pcr[0], pp->pcr[1], pp->pcr[2], pp->pcr[3], pp->pic[0], pp->pic[1], pp->pic[2], pp->pic[3]); + + touch_nmi_watchdog(); } memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 3fdb455..61a5198 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -174,7 +175,7 @@ char reboot_command[COMMAND_LINE_SIZE]; static struct pt_regs fake_swapper_regs = { { 0, }, 0, 0, 0, 0 }; -void __init per_cpu_patch(void) +static void __init per_cpu_patch(void) { struct cpuid_patch_entry *p; unsigned long ver; @@ -266,7 +267,7 @@ void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start, } } -void __init sun4v_patch(void) +static void __init sun4v_patch(void) { extern void sun4v_hvapi_init(void); @@ -335,14 +336,25 @@ static void __init pause_patch(void) } } -#ifdef CONFIG_SMP -void __init boot_cpu_id_too_large(int cpu) +void __init start_early_boot(void) { - prom_printf("Serious problem, boot cpu id (%d) >= NR_CPUS (%d)\n", - cpu, NR_CPUS); - prom_halt(); + int cpu; + + check_if_starfire(); + per_cpu_patch(); + sun4v_patch(); + + cpu = hard_smp_processor_id(); + if (cpu >= NR_CPUS) { + prom_printf("Serious problem, boot cpu id (%d) >= NR_CPUS (%d)\n", + cpu, NR_CPUS); + prom_halt(); + } + current_thread_info()->cpu = cpu; + + prom_init_report(); + start_kernel(); } -#endif /* On Ultra, we support all of the v8 capabilities. */ unsigned long sparc64_elf_hwcap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR | @@ -500,12 +512,16 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= HWCAP_SPARC_BLKINIT; if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= HWCAP_SPARC_N2; } @@ -533,6 +549,8 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 | AV_SPARC_ASI_BLK_INIT | @@ -540,6 +558,8 @@ static void __init init_sparc64_elf_hwcap(void) if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC | AV_SPARC_FMAF); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index b085311..9af0a5d 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -151,7 +151,7 @@ void cpu_panic(void) #define NUM_ROUNDS 64 /* magic value */ #define NUM_ITERS 5 /* likewise */ -static DEFINE_SPINLOCK(itc_sync_lock); +static DEFINE_RAW_SPINLOCK(itc_sync_lock); static unsigned long go[SLAVE + 1]; #define DEBUG_TICK_SYNC 0 @@ -259,7 +259,7 @@ static void smp_synchronize_one_tick(int cpu) go[MASTER] = 0; membar_safe("#StoreLoad"); - spin_lock_irqsave(&itc_sync_lock, flags); + raw_spin_lock_irqsave(&itc_sync_lock, flags); { for (i = 0; i < NUM_ROUNDS*NUM_ITERS; i++) { while (!go[MASTER]) @@ -270,7 +270,7 @@ static void smp_synchronize_one_tick(int cpu) membar_safe("#StoreLoad"); } } - spin_unlock_irqrestore(&itc_sync_lock, flags); + raw_spin_unlock_irqrestore(&itc_sync_lock, flags); } #if defined(CONFIG_SUN_LDOMS) && defined(CONFIG_HOTPLUG_CPU) @@ -823,13 +823,17 @@ void arch_send_call_function_single_ipi(int cpu) void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); + irq_enter(); generic_smp_call_function_interrupt(); + irq_exit(); } void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); + irq_enter(); generic_smp_call_function_single_interrupt(); + irq_exit(); } static void tsb_sync(void *info) @@ -1395,7 +1399,6 @@ void __cpu_die(unsigned int cpu) void __init smp_cpus_done(unsigned int max_cpus) { - pcr_arch_init(); } void smp_send_reschedule(int cpu) @@ -1480,6 +1483,13 @@ static void __init pcpu_populate_pte(unsigned long addr) pud_t *pud; pmd_t *pmd; + if (pgd_none(*pgd)) { + pud_t *new; + + new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + pgd_populate(&init_mm, pgd, new); + } + pud = pud_offset(pgd, addr); if (pud_none(*pud)) { pmd_t *new; diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S index e0c09bf8..6179e19 100644 --- a/arch/sparc/kernel/sun4v_tlb_miss.S +++ b/arch/sparc/kernel/sun4v_tlb_miss.S @@ -195,6 +195,11 @@ sun4v_tsb_miss_common: ldx [%g2 + TRAP_PER_CPU_PGD_PADDR], %g7 sun4v_itlb_error: + rdpr %tl, %g1 + cmp %g1, 1 + ble,pt %icc, sun4v_bad_ra + or %g0, FAULT_CODE_BAD_RA | FAULT_CODE_ITLB, %g1 + sethi %hi(sun4v_err_itlb_vaddr), %g1 stx %g4, [%g1 + %lo(sun4v_err_itlb_vaddr)] sethi %hi(sun4v_err_itlb_ctx), %g1 @@ -206,15 +211,10 @@ sun4v_itlb_error: sethi %hi(sun4v_err_itlb_error), %g1 stx %o0, [%g1 + %lo(sun4v_err_itlb_error)] + sethi %hi(1f), %g7 rdpr %tl, %g4 - cmp %g4, 1 - ble,pt %icc, 1f - sethi %hi(2f), %g7 ba,pt %xcc, etraptl1 - or %g7, %lo(2f), %g7 - -1: ba,pt %xcc, etrap -2: or %g7, %lo(2b), %g7 +1: or %g7, %lo(1f), %g7 mov %l4, %o1 call sun4v_itlb_error_report add %sp, PTREGS_OFF, %o0 @@ -222,6 +222,11 @@ sun4v_itlb_error: /* NOTREACHED */ sun4v_dtlb_error: + rdpr %tl, %g1 + cmp %g1, 1 + ble,pt %icc, sun4v_bad_ra + or %g0, FAULT_CODE_BAD_RA | FAULT_CODE_DTLB, %g1 + sethi %hi(sun4v_err_dtlb_vaddr), %g1 stx %g4, [%g1 + %lo(sun4v_err_dtlb_vaddr)] sethi %hi(sun4v_err_dtlb_ctx), %g1 @@ -233,21 +238,23 @@ sun4v_dtlb_error: sethi %hi(sun4v_err_dtlb_error), %g1 stx %o0, [%g1 + %lo(sun4v_err_dtlb_error)] + sethi %hi(1f), %g7 rdpr %tl, %g4 - cmp %g4, 1 - ble,pt %icc, 1f - sethi %hi(2f), %g7 ba,pt %xcc, etraptl1 - or %g7, %lo(2f), %g7 - -1: ba,pt %xcc, etrap -2: or %g7, %lo(2b), %g7 +1: or %g7, %lo(1f), %g7 mov %l4, %o1 call sun4v_dtlb_error_report add %sp, PTREGS_OFF, %o0 /* NOTREACHED */ +sun4v_bad_ra: + or %g0, %g4, %g5 + ba,pt %xcc, sparc64_realfault_common + or %g1, %g0, %g4 + + /* NOTREACHED */ + /* Instruction Access Exception, tl0. */ sun4v_iacc: ldxa [%g0] ASI_SCRATCHPAD, %g2 diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S index f7c72b6..d066eb1 100644 --- a/arch/sparc/kernel/sys32.S +++ b/arch/sparc/kernel/sys32.S @@ -44,7 +44,7 @@ SIGN1(sys32_timer_settime, compat_sys_timer_settime, %o1) SIGN1(sys32_io_submit, compat_sys_io_submit, %o1) SIGN1(sys32_mq_open, compat_sys_mq_open, %o1) SIGN1(sys32_select, compat_sys_select, %o0) -SIGN3(sys32_futex, compat_sys_futex, %o1, %o2, %o5) +SIGN1(sys32_futex, compat_sys_futex, %o1) SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0) SIGN1(sys32_recvmsg, compat_sys_recvmsg, %o0) SIGN1(sys32_sendmsg, compat_sys_sendmsg, %o0) diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index beb0b5a..25db14a 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -332,7 +332,7 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second long err; /* No need for backward compatibility. We can start fresh... */ - if (call <= SEMCTL) { + if (call <= SEMTIMEDOP) { switch (call) { case SEMOP: err = sys_semtimedop(first, ptr, diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S index 737f8cb..88ede1d 100644 --- a/arch/sparc/kernel/trampoline_64.S +++ b/arch/sparc/kernel/trampoline_64.S @@ -109,10 +109,13 @@ startup_continue: brnz,pn %g1, 1b nop - sethi %hi(p1275buf), %g2 - or %g2, %lo(p1275buf), %g2 - ldx [%g2 + 0x10], %l2 - add %l2, -(192 + 128), %sp + /* Get onto temporary stack which will be in the locked + * kernel image. + */ + sethi %hi(tramp_stack), %g1 + or %g1, %lo(tramp_stack), %g1 + add %g1, TRAMP_STACK_SIZE, %g1 + sub %g1, STACKFRAME_SZ + STACK_BIAS + 256, %sp flushw /* Setup the loop variables: @@ -394,7 +397,6 @@ after_lock_tlb: sllx %g5, THREAD_SHIFT, %g5 sub %g5, (STACKFRAME_SZ + STACK_BIAS), %g5 add %g6, %g5, %sp - mov 0, %fp rdpr %pstate, %o1 or %o1, PSTATE_IE, %o1 diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 4ced92f..25d0c7e 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2102,6 +2102,11 @@ void sun4v_nonresum_overflow(struct pt_regs *regs) atomic_inc(&sun4v_nonresum_oflow_cnt); } +static void sun4v_tlb_error(struct pt_regs *regs) +{ + die_if_kernel("TLB/TSB error", regs); +} + unsigned long sun4v_err_itlb_vaddr; unsigned long sun4v_err_itlb_ctx; unsigned long sun4v_err_itlb_pte; @@ -2109,8 +2114,7 @@ unsigned long sun4v_err_itlb_error; void sun4v_itlb_error_report(struct pt_regs *regs, int tl) { - if (tl > 1) - dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); + dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); printk(KERN_EMERG "SUN4V-ITLB: Error at TPC[%lx], tl %d\n", regs->tpc, tl); @@ -2123,7 +2127,7 @@ void sun4v_itlb_error_report(struct pt_regs *regs, int tl) sun4v_err_itlb_vaddr, sun4v_err_itlb_ctx, sun4v_err_itlb_pte, sun4v_err_itlb_error); - prom_halt(); + sun4v_tlb_error(regs); } unsigned long sun4v_err_dtlb_vaddr; @@ -2133,8 +2137,7 @@ unsigned long sun4v_err_dtlb_error; void sun4v_dtlb_error_report(struct pt_regs *regs, int tl) { - if (tl > 1) - dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); + dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); printk(KERN_EMERG "SUN4V-DTLB: Error at TPC[%lx], tl %d\n", regs->tpc, tl); @@ -2147,7 +2150,7 @@ void sun4v_dtlb_error_report(struct pt_regs *regs, int tl) sun4v_err_dtlb_vaddr, sun4v_err_dtlb_ctx, sun4v_err_dtlb_pte, sun4v_err_dtlb_error); - prom_halt(); + sun4v_tlb_error(regs); } void hypervisor_tlbop_error(unsigned long err, unsigned long op) diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S index 14158d4..be98685 100644 --- a/arch/sparc/kernel/tsb.S +++ b/arch/sparc/kernel/tsb.S @@ -162,10 +162,10 @@ tsb_miss_page_table_walk_sun4v_fastpath: nop .previous - rdpr %tl, %g3 - cmp %g3, 1 + rdpr %tl, %g7 + cmp %g7, 1 bne,pn %xcc, winfix_trampoline - nop + mov %g3, %g4 ba,pt %xcc, etrap rd %pc, %g7 call hugetlb_setup diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c index 3c1a7cb..35ab8b6 100644 --- a/arch/sparc/kernel/unaligned_64.c +++ b/arch/sparc/kernel/unaligned_64.c @@ -166,17 +166,23 @@ static unsigned long *fetch_reg_addr(unsigned int reg, struct pt_regs *regs) unsigned long compute_effective_address(struct pt_regs *regs, unsigned int insn, unsigned int rd) { + int from_kernel = (regs->tstate & TSTATE_PRIV) != 0; unsigned int rs1 = (insn >> 14) & 0x1f; unsigned int rs2 = insn & 0x1f; - int from_kernel = (regs->tstate & TSTATE_PRIV) != 0; + unsigned long addr; if (insn & 0x2000) { maybe_flush_windows(rs1, 0, rd, from_kernel); - return (fetch_reg(rs1, regs) + sign_extend_imm13(insn)); + addr = (fetch_reg(rs1, regs) + sign_extend_imm13(insn)); } else { maybe_flush_windows(rs1, rs2, rd, from_kernel); - return (fetch_reg(rs1, regs) + fetch_reg(rs2, regs)); + addr = (fetch_reg(rs1, regs) + fetch_reg(rs2, regs)); } + + if (!from_kernel && test_thread_flag(TIF_32BIT)) + addr &= 0xffffffff; + + return addr; } /* This is just to make gcc think die_if_kernel does return... */ diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c index f8e7dd5..9c5fbd0 100644 --- a/arch/sparc/kernel/viohs.c +++ b/arch/sparc/kernel/viohs.c @@ -714,7 +714,7 @@ int vio_ldc_alloc(struct vio_driver_state *vio, cfg.tx_irq = vio->vdev->tx_irq; cfg.rx_irq = vio->vdev->rx_irq; - lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg); + lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg, vio->name); if (IS_ERR(lp)) return PTR_ERR(lp); @@ -746,7 +746,7 @@ void vio_port_up(struct vio_driver_state *vio) err = 0; if (state == LDC_STATE_INIT) { - err = ldc_bind(vio->lp, vio->name); + err = ldc_bind(vio->lp); if (err) printk(KERN_WARNING "%s: Port %lu bind failed, " "err=%d\n", diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index 932ff90..0924305 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -35,8 +35,9 @@ jiffies = jiffies_64; SECTIONS { - /* swapper_low_pmd_dir is sparc64 only */ - swapper_low_pmd_dir = 0x0000000000402000; +#ifdef CONFIG_SPARC64 + swapper_pg_dir = 0x0000000000402000; +#endif . = INITIAL_ADDRESS; .text TEXTSTART : { @@ -122,11 +123,6 @@ SECTIONS *(.swapper_4m_tsb_phys_patch) __swapper_4m_tsb_phys_patch_end = .; } - .page_offset_shift_patch : { - __page_offset_shift_patch = .; - *(.page_offset_shift_patch) - __page_offset_shift_patch_end = .; - } .popc_3insn_patch : { __popc_3insn_patch = .; *(.popc_3insn_patch) diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S index 2c20ad6..30eee6e 100644 --- a/arch/sparc/lib/NG2memcpy.S +++ b/arch/sparc/lib/NG2memcpy.S @@ -236,6 +236,7 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ */ VISEntryHalf + membar #Sync alignaddr %o1, %g0, %g0 add %o1, (64 - 1), %o4 diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S index 9cf2ee0..83aeeb1 100644 --- a/arch/sparc/lib/NG4memcpy.S +++ b/arch/sparc/lib/NG4memcpy.S @@ -41,6 +41,10 @@ #endif #endif +#if !defined(EX_LD) && !defined(EX_ST) +#define NON_USER_COPY +#endif + #ifndef EX_LD #define EX_LD(x) x #endif @@ -197,9 +201,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ mov EX_RETVAL(%o3), %o0 .Llarge_src_unaligned: +#ifdef NON_USER_COPY + VISEntryHalfFast(.Lmedium_vis_entry_fail) +#else + VISEntryHalf +#endif andn %o2, 0x3f, %o4 sub %o2, %o4, %o2 - VISEntryHalf alignaddr %o1, %g0, %g1 add %o1, %o4, %o1 EX_LD(LOAD(ldd, %g1 + 0x00, %f0)) @@ -232,14 +240,21 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ add %o0, 0x40, %o0 bne,pt %icc, 1b LOAD(prefetch, %g1 + 0x200, #n_reads_strong) +#ifdef NON_USER_COPY + VISExitHalfFast +#else VISExitHalf - +#endif brz,pn %o2, .Lexit cmp %o2, 19 ble,pn %icc, .Lsmall_unaligned nop ba,a,pt %icc, .Lmedium_unaligned +#ifdef NON_USER_COPY +.Lmedium_vis_entry_fail: + or %o0, %o1, %g2 +#endif .Lmedium: LOAD(prefetch, %o1 + 0x40, #n_reads_strong) andcc %g2, 0x7, %g0 diff --git a/arch/sparc/lib/VISsave.S b/arch/sparc/lib/VISsave.S index b320ae9..a063d84 100644 --- a/arch/sparc/lib/VISsave.S +++ b/arch/sparc/lib/VISsave.S @@ -44,9 +44,8 @@ vis1: ldub [%g6 + TI_FPSAVED], %g3 stx %g3, [%g6 + TI_GSR] 2: add %g6, %g1, %g3 - cmp %o5, FPRS_DU - be,pn %icc, 6f - sll %g1, 3, %g1 + mov FPRS_DU | FPRS_DL | FPRS_FEF, %o5 + sll %g1, 3, %g1 stb %o5, [%g3 + TI_FPSAVED] rd %gsr, %g2 add %g6, %g1, %g3 @@ -80,65 +79,3 @@ vis1: ldub [%g6 + TI_FPSAVED], %g3 .align 32 80: jmpl %g7 + %g0, %g0 nop - -6: ldub [%g3 + TI_FPSAVED], %o5 - or %o5, FPRS_DU, %o5 - add %g6, TI_FPREGS+0x80, %g2 - stb %o5, [%g3 + TI_FPSAVED] - - sll %g1, 5, %g1 - add %g6, TI_FPREGS+0xc0, %g3 - wr %g0, FPRS_FEF, %fprs - membar #Sync - stda %f32, [%g2 + %g1] ASI_BLK_P - stda %f48, [%g3 + %g1] ASI_BLK_P - membar #Sync - ba,pt %xcc, 80f - nop - - .align 32 -80: jmpl %g7 + %g0, %g0 - nop - - .align 32 -VISenterhalf: - ldub [%g6 + TI_FPDEPTH], %g1 - brnz,a,pn %g1, 1f - cmp %g1, 1 - stb %g0, [%g6 + TI_FPSAVED] - stx %fsr, [%g6 + TI_XFSR] - clr %o5 - jmpl %g7 + %g0, %g0 - wr %g0, FPRS_FEF, %fprs - -1: bne,pn %icc, 2f - srl %g1, 1, %g1 - ba,pt %xcc, vis1 - sub %g7, 8, %g7 -2: addcc %g6, %g1, %g3 - sll %g1, 3, %g1 - andn %o5, FPRS_DU, %g2 - stb %g2, [%g3 + TI_FPSAVED] - - rd %gsr, %g2 - add %g6, %g1, %g3 - stx %g2, [%g3 + TI_GSR] - add %g6, %g1, %g2 - stx %fsr, [%g2 + TI_XFSR] - sll %g1, 5, %g1 -3: andcc %o5, FPRS_DL, %g0 - be,pn %icc, 4f - add %g6, TI_FPREGS, %g2 - - add %g6, TI_FPREGS+0x40, %g3 - membar #Sync - stda %f0, [%g2 + %g1] ASI_BLK_P - stda %f16, [%g3 + %g1] ASI_BLK_P - membar #Sync - ba,pt %xcc, 4f - nop - - .align 32 -4: and %o5, FPRS_DU, %o5 - jmpl %g7 + %g0, %g0 - wr %o5, FPRS_FEF, %fprs diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c index 1d32b54..8f2f94d 100644 --- a/arch/sparc/lib/atomic32.c +++ b/arch/sparc/lib/atomic32.c @@ -40,6 +40,19 @@ int __atomic_add_return(int i, atomic_t *v) } EXPORT_SYMBOL(__atomic_add_return); +int atomic_xchg(atomic_t *v, int new) +{ + int ret; + unsigned long flags; + + spin_lock_irqsave(ATOMIC_HASH(v), flags); + ret = v->counter; + v->counter = new; + spin_unlock_irqrestore(ATOMIC_HASH(v), flags); + return ret; +} +EXPORT_SYMBOL(atomic_xchg); + int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; @@ -132,3 +145,17 @@ unsigned long __cmpxchg_u32(volatile u32 *ptr, u32 old, u32 new) return (unsigned long)prev; } EXPORT_SYMBOL(__cmpxchg_u32); + +unsigned long __xchg_u32(volatile u32 *ptr, u32 new) +{ + unsigned long flags; + u32 prev; + + spin_lock_irqsave(ATOMIC_HASH(ptr), flags); + prev = *ptr; + *ptr = new; + spin_unlock_irqrestore(ATOMIC_HASH(ptr), flags); + + return (unsigned long)prev; +} +EXPORT_SYMBOL(__xchg_u32); diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c index 323335b..ac094de 100644 --- a/arch/sparc/lib/ksyms.c +++ b/arch/sparc/lib/ksyms.c @@ -126,10 +126,6 @@ EXPORT_SYMBOL(copy_user_page); void VISenter(void); EXPORT_SYMBOL(VISenter); -/* CRYPTO code needs this */ -void VISenterhalf(void); -EXPORT_SYMBOL(VISenterhalf); - extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *); extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *, unsigned long *); diff --git a/arch/sparc/lib/memmove.S b/arch/sparc/lib/memmove.S index b7f6334..857ad4f 100644 --- a/arch/sparc/lib/memmove.S +++ b/arch/sparc/lib/memmove.S @@ -8,9 +8,11 @@ .text ENTRY(memmove) /* o0=dst o1=src o2=len */ - mov %o0, %g1 + brz,pn %o2, 99f + mov %o0, %g1 + cmp %o0, %o1 - bleu,pt %xcc, memcpy + bleu,pt %xcc, 2f add %o1, %o2, %g7 cmp %g7, %o0 bleu,pt %xcc, memcpy @@ -24,7 +26,34 @@ ENTRY(memmove) /* o0=dst o1=src o2=len */ stb %g7, [%o0] bne,pt %icc, 1b sub %o0, 1, %o0 - +99: retl mov %g1, %o0 + + /* We can't just call memcpy for these memmove cases. On some + * chips the memcpy uses cache initializing stores and when dst + * and src are close enough, those can clobber the source data + * before we've loaded it in. + */ +2: or %o0, %o1, %g7 + or %o2, %g7, %g7 + andcc %g7, 0x7, %g0 + bne,pn %xcc, 4f + nop + +3: ldx [%o1], %g7 + add %o1, 8, %o1 + subcc %o2, 8, %o2 + add %o0, 8, %o0 + bne,pt %icc, 3b + stx %g7, [%o0 - 0x8] + ba,a,pt %xcc, 99b + +4: ldub [%o1], %g7 + add %o1, 1, %o1 + subcc %o2, 1, %o2 + add %o0, 1, %o0 + bne,pt %icc, 4b + stb %g7, [%o0 - 0x1] + ba,a,pt %xcc, 99b ENDPROC(memmove) diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S index 99c017b..f75e690 100644 --- a/arch/sparc/lib/memset.S +++ b/arch/sparc/lib/memset.S @@ -3,8 +3,9 @@ * Copyright (C) 1996,1997 Jakub Jelinek (jj@sunsite.mff.cuni.cz) * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu) * - * Returns 0, if ok, and number of bytes not yet set if exception - * occurs and we were called as clear_user. + * Calls to memset returns initial %o0. Calls to bzero returns 0, if ok, and + * number of bytes not yet set if exception occurs and we were called as + * clear_user. */ #include @@ -65,6 +66,8 @@ __bzero_begin: .globl __memset_start, __memset_end __memset_start: memset: + mov %o0, %g1 + mov 1, %g4 and %o1, 0xff, %g3 sll %g3, 8, %g2 or %g3, %g2, %g3 @@ -89,6 +92,7 @@ memset: sub %o0, %o2, %o0 __bzero: + clr %g4 mov %g0, %g3 1: cmp %o1, 7 @@ -151,8 +155,8 @@ __bzero: bne,a 8f EX(stb %g3, [%o0], and %o1, 1) 8: - retl - clr %o0 + b 0f + nop 7: be 13b orcc %o1, 0, %g0 @@ -164,6 +168,12 @@ __bzero: bne 8b EX(stb %g3, [%o0 - 1], add %o1, 1) 0: + andcc %g4, 1, %g0 + be 5f + nop + retl + mov %g1, %o0 +5: retl clr %o0 __memset_end: diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c index aa4d55b..5ce8f2f 100644 --- a/arch/sparc/math-emu/math_32.c +++ b/arch/sparc/math-emu/math_32.c @@ -499,7 +499,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs) case 0: fsr = *pfsr; if (IR == -1) IR = 2; /* fcc is always fcc0 */ - fsr &= ~0xc00; fsr |= (IR << 10); break; + fsr &= ~0xc00; fsr |= (IR << 10); *pfsr = fsr; break; case 1: rd->s = IR; break; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 59dbd46..163c787 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -252,6 +252,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 69bb818..0d6de79 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -96,38 +96,51 @@ static unsigned int get_user_insn(unsigned long tpc) pte_t *ptep, pte; unsigned long pa; u32 insn = 0; - unsigned long pstate; - if (pgd_none(*pgdp)) - goto outret; + if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp))) + goto out; pudp = pud_offset(pgdp, tpc); - if (pud_none(*pudp)) - goto outret; - pmdp = pmd_offset(pudp, tpc); - if (pmd_none(*pmdp)) - goto outret; + if (pud_none(*pudp) || unlikely(pud_bad(*pudp))) + goto out; /* This disables preemption for us as well. */ - __asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate)); - __asm__ __volatile__("wrpr %0, %1, %%pstate" - : : "r" (pstate), "i" (PSTATE_IE)); - ptep = pte_offset_map(pmdp, tpc); - pte = *ptep; - if (!pte_present(pte)) - goto out; + local_irq_disable(); + + pmdp = pmd_offset(pudp, tpc); + if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp))) + goto out_irq_enable; - pa = (pte_pfn(pte) << PAGE_SHIFT); - pa += (tpc & ~PAGE_MASK); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_trans_huge(*pmdp)) { + if (pmd_trans_splitting(*pmdp)) + goto out_irq_enable; - /* Use phys bypass so we don't pollute dtlb/dcache. */ - __asm__ __volatile__("lduwa [%1] %2, %0" - : "=r" (insn) - : "r" (pa), "i" (ASI_PHYS_USE_EC)); + pa = pmd_pfn(*pmdp) << PAGE_SHIFT; + pa += tpc & ~HPAGE_MASK; + /* Use phys bypass so we don't pollute dtlb/dcache. */ + __asm__ __volatile__("lduwa [%1] %2, %0" + : "=r" (insn) + : "r" (pa), "i" (ASI_PHYS_USE_EC)); + } else +#endif + { + ptep = pte_offset_map(pmdp, tpc); + pte = *ptep; + if (pte_present(pte)) { + pa = (pte_pfn(pte) << PAGE_SHIFT); + pa += (tpc & ~PAGE_MASK); + + /* Use phys bypass so we don't pollute dtlb/dcache. */ + __asm__ __volatile__("lduwa [%1] %2, %0" + : "=r" (insn) + : "r" (pa), "i" (ASI_PHYS_USE_EC)); + } + pte_unmap(ptep); + } +out_irq_enable: + local_irq_enable(); out: - pte_unmap(ptep); - __asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate)); -outret: return insn; } @@ -153,7 +166,8 @@ show_signal_msg(struct pt_regs *regs, int sig, int code, } static void do_fault_siginfo(int code, int sig, struct pt_regs *regs, - unsigned int insn, int fault_code) + unsigned long fault_addr, unsigned int insn, + int fault_code) { unsigned long addr; siginfo_t info; @@ -161,10 +175,18 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs, info.si_code = code; info.si_signo = sig; info.si_errno = 0; - if (fault_code & FAULT_CODE_ITLB) + if (fault_code & FAULT_CODE_ITLB) { addr = regs->tpc; - else - addr = compute_effective_address(regs, insn, 0); + } else { + /* If we were able to probe the faulting instruction, use it + * to compute a precise fault address. Otherwise use the fault + * time provided address which may only have page granularity. + */ + if (insn) + addr = compute_effective_address(regs, insn, 0); + else + addr = fault_addr; + } info.si_addr = (void __user *) addr; info.si_trapno = 0; @@ -239,7 +261,7 @@ static void __kprobes do_kernel_fault(struct pt_regs *regs, int si_code, /* The si_code was set to make clear whether * this was a SEGV_MAPERR or SEGV_ACCERR fault. */ - do_fault_siginfo(si_code, SIGSEGV, regs, insn, fault_code); + do_fault_siginfo(si_code, SIGSEGV, regs, address, insn, fault_code); return; } @@ -259,18 +281,6 @@ static void noinline __kprobes bogus_32bit_fault_tpc(struct pt_regs *regs) show_regs(regs); } -static void noinline __kprobes bogus_32bit_fault_address(struct pt_regs *regs, - unsigned long addr) -{ - static int times; - - if (times++ < 10) - printk(KERN_ERR "FAULT[%s:%d]: 32-bit process " - "reports 64-bit fault address [%lx]\n", - current->comm, current->pid, addr); - show_regs(regs); -} - asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) { enum ctx_state prev_state = exception_enter(); @@ -300,10 +310,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) goto intr_or_no_mm; } } - if (unlikely((address >> 32) != 0)) { - bogus_32bit_fault_address(regs, address); + if (unlikely((address >> 32) != 0)) goto intr_or_no_mm; - } } if (regs->tstate & TSTATE_PRIV) { @@ -340,6 +348,9 @@ retry: down_read(&mm->mmap_sem); } + if (fault_code & FAULT_CODE_BAD_RA) + goto do_sigbus; + vma = find_vma(mm, address); if (!vma) goto bad_area; @@ -437,6 +448,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); @@ -525,7 +538,7 @@ do_sigbus: * Send a sigbus, regardless of whether we were in kernel * or user mode. */ - do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, insn, fault_code); + do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, address, insn, fault_code); /* Kernel mode? Handle exceptions or die */ if (regs->tstate & TSTATE_PRIV) diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c index c4d3da6..ae6ce38 100644 --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -73,7 +73,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, struct page *head, *page, *tail; int refs; - if (!pmd_large(pmd)) + if (!(pmd_val(pmd) & _PAGE_VALID)) return 0; if (write && !pmd_write(pmd)) @@ -160,6 +160,36 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +int __get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + unsigned long addr, len, end; + unsigned long next, flags; + pgd_t *pgdp; + int nr = 0; + + start &= PAGE_MASK; + addr = start; + len = (unsigned long) nr_pages << PAGE_SHIFT; + end = start + len; + + local_irq_save(flags); + pgdp = pgd_offset(mm, addr); + do { + pgd_t pgd = *pgdp; + + next = pgd_addr_end(addr, end); + if (pgd_none(pgd)) + break; + if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + break; + } while (pgdp++, addr = next, addr != end); + local_irq_restore(flags); + + return nr; +} + int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index eafbc65..34506f2 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -73,7 +73,6 @@ unsigned long kern_linear_pte_xor[4] __read_mostly; * 'cpu' properties, but we need to have this table setup before the * MDESC is initialized. */ -unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)]; #ifndef CONFIG_DEBUG_PAGEALLOC /* A special kernel TSB for 4MB, 256MB, 2GB and 16GB linear mappings. @@ -82,10 +81,11 @@ unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)]; */ extern struct tsb swapper_4m_tsb[KERNEL_TSB4M_NENTRIES]; #endif +extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; static unsigned long cpu_pgsz_mask; -#define MAX_BANKS 32 +#define MAX_BANKS 1024 static struct linux_prom64_registers pavail[MAX_BANKS]; static int pavail_ents; @@ -163,10 +163,6 @@ static void __init read_obp_memory(const char *property, cmp_p64, NULL); } -unsigned long sparc64_valid_addr_bitmap[VALID_ADDR_BITMAP_BYTES / - sizeof(unsigned long)]; -EXPORT_SYMBOL(sparc64_valid_addr_bitmap); - /* Kernel physical address base and size in bytes. */ unsigned long kern_base __read_mostly; unsigned long kern_size __read_mostly; @@ -350,6 +346,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t * mm = vma->vm_mm; + /* Don't insert a non-valid PTE into the TSB, we'll deadlock. */ + if (!pte_accessible(mm, pte)) + return; + spin_lock_irqsave(&mm->context.lock, flags); #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) @@ -588,7 +588,7 @@ static void __init remap_kernel(void) int i, tlb_ent = sparc64_highest_locked_tlbent(); tte_vaddr = (unsigned long) KERNBASE; - phys_page = (prom_boot_mapping_phys_low >> 22UL) << 22UL; + phys_page = (prom_boot_mapping_phys_low >> ILOG2_4MB) << ILOG2_4MB; tte_data = kern_large_tte(phys_page); kern_locked_tte_data = tte_data; @@ -834,7 +834,10 @@ static int find_node(unsigned long addr) if ((addr & p->mask) == p->val) return i; } - return -1; + /* The following condition has been observed on LDOM guests.*/ + WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node" + " rule. Some physical memory will be owned by node 0."); + return 0; } static u64 memblock_nid_range(u64 start, u64 end, int *nid) @@ -1356,9 +1359,144 @@ static unsigned long __init bootmem_init(unsigned long phys_base) static struct linux_prom64_registers pall[MAX_BANKS] __initdata; static int pall_ents __initdata; -#ifdef CONFIG_DEBUG_PAGEALLOC +static unsigned long max_phys_bits = 40; + +bool kern_addr_valid(unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + if ((long)addr < 0L) { + unsigned long pa = __pa(addr); + + if ((addr >> max_phys_bits) != 0UL) + return false; + + return pfn_valid(pa >> PAGE_SHIFT); + } + + if (addr >= (unsigned long) KERNBASE && + addr < (unsigned long)&_end) + return true; + + pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) + return 0; + + pud = pud_offset(pgd, addr); + if (pud_none(*pud)) + return 0; + + if (pud_large(*pud)) + return pfn_valid(pud_pfn(*pud)); + + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return 0; + + if (pmd_large(*pmd)) + return pfn_valid(pmd_pfn(*pmd)); + + pte = pte_offset_kernel(pmd, addr); + if (pte_none(*pte)) + return 0; + + return pfn_valid(pte_pfn(*pte)); +} +EXPORT_SYMBOL(kern_addr_valid); + +static unsigned long __ref kernel_map_hugepud(unsigned long vstart, + unsigned long vend, + pud_t *pud) +{ + const unsigned long mask16gb = (1UL << 34) - 1UL; + u64 pte_val = vstart; + + /* Each PUD is 8GB */ + if ((vstart & mask16gb) || + (vend - vstart <= mask16gb)) { + pte_val ^= kern_linear_pte_xor[2]; + pud_val(*pud) = pte_val | _PAGE_PUD_HUGE; + + return vstart + PUD_SIZE; + } + + pte_val ^= kern_linear_pte_xor[3]; + pte_val |= _PAGE_PUD_HUGE; + + vend = vstart + mask16gb + 1UL; + while (vstart < vend) { + pud_val(*pud) = pte_val; + + pte_val += PUD_SIZE; + vstart += PUD_SIZE; + pud++; + } + return vstart; +} + +static bool kernel_can_map_hugepud(unsigned long vstart, unsigned long vend, + bool guard) +{ + if (guard && !(vstart & ~PUD_MASK) && (vend - vstart) >= PUD_SIZE) + return true; + + return false; +} + +static unsigned long __ref kernel_map_hugepmd(unsigned long vstart, + unsigned long vend, + pmd_t *pmd) +{ + const unsigned long mask256mb = (1UL << 28) - 1UL; + const unsigned long mask2gb = (1UL << 31) - 1UL; + u64 pte_val = vstart; + + /* Each PMD is 8MB */ + if ((vstart & mask256mb) || + (vend - vstart <= mask256mb)) { + pte_val ^= kern_linear_pte_xor[0]; + pmd_val(*pmd) = pte_val | _PAGE_PMD_HUGE; + + return vstart + PMD_SIZE; + } + + if ((vstart & mask2gb) || + (vend - vstart <= mask2gb)) { + pte_val ^= kern_linear_pte_xor[1]; + pte_val |= _PAGE_PMD_HUGE; + vend = vstart + mask256mb + 1UL; + } else { + pte_val ^= kern_linear_pte_xor[2]; + pte_val |= _PAGE_PMD_HUGE; + vend = vstart + mask2gb + 1UL; + } + + while (vstart < vend) { + pmd_val(*pmd) = pte_val; + + pte_val += PMD_SIZE; + vstart += PMD_SIZE; + pmd++; + } + + return vstart; +} + +static bool kernel_can_map_hugepmd(unsigned long vstart, unsigned long vend, + bool guard) +{ + if (guard && !(vstart & ~PMD_MASK) && (vend - vstart) >= PMD_SIZE) + return true; + + return false; +} + static unsigned long __ref kernel_map_range(unsigned long pstart, - unsigned long pend, pgprot_t prot) + unsigned long pend, pgprot_t prot, + bool use_huge) { unsigned long vstart = PAGE_OFFSET + pstart; unsigned long vend = PAGE_OFFSET + pend; @@ -1377,19 +1515,34 @@ static unsigned long __ref kernel_map_range(unsigned long pstart, pmd_t *pmd; pte_t *pte; + if (pgd_none(*pgd)) { + pud_t *new; + + new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + alloc_bytes += PAGE_SIZE; + pgd_populate(&init_mm, pgd, new); + } pud = pud_offset(pgd, vstart); if (pud_none(*pud)) { pmd_t *new; + if (kernel_can_map_hugepud(vstart, vend, use_huge)) { + vstart = kernel_map_hugepud(vstart, vend, pud); + continue; + } new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); alloc_bytes += PAGE_SIZE; pud_populate(&init_mm, pud, new); } pmd = pmd_offset(pud, vstart); - if (!pmd_present(*pmd)) { + if (pmd_none(*pmd)) { pte_t *new; + if (kernel_can_map_hugepmd(vstart, vend, use_huge)) { + vstart = kernel_map_hugepmd(vstart, vend, pmd); + continue; + } new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); alloc_bytes += PAGE_SIZE; pmd_populate_kernel(&init_mm, pmd, new); @@ -1412,100 +1565,34 @@ static unsigned long __ref kernel_map_range(unsigned long pstart, return alloc_bytes; } -extern unsigned int kvmap_linear_patch[1]; -#endif /* CONFIG_DEBUG_PAGEALLOC */ - -static void __init kpte_set_val(unsigned long index, unsigned long val) -{ - unsigned long *ptr = kpte_linear_bitmap; - - val <<= ((index % (BITS_PER_LONG / 2)) * 2); - ptr += (index / (BITS_PER_LONG / 2)); - - *ptr |= val; -} - -static const unsigned long kpte_shift_min = 28; /* 256MB */ -static const unsigned long kpte_shift_max = 34; /* 16GB */ -static const unsigned long kpte_shift_incr = 3; - -static unsigned long kpte_mark_using_shift(unsigned long start, unsigned long end, - unsigned long shift) +static void __init flush_all_kernel_tsbs(void) { - unsigned long size = (1UL << shift); - unsigned long mask = (size - 1UL); - unsigned long remains = end - start; - unsigned long val; - - if (remains < size || (start & mask)) - return start; - - /* VAL maps: - * - * shift 28 --> kern_linear_pte_xor index 1 - * shift 31 --> kern_linear_pte_xor index 2 - * shift 34 --> kern_linear_pte_xor index 3 - */ - val = ((shift - kpte_shift_min) / kpte_shift_incr) + 1; - - remains &= ~mask; - if (shift != kpte_shift_max) - remains = size; - - while (remains) { - unsigned long index = start >> kpte_shift_min; + int i; - kpte_set_val(index, val); + for (i = 0; i < KERNEL_TSB_NENTRIES; i++) { + struct tsb *ent = &swapper_tsb[i]; - start += 1UL << kpte_shift_min; - remains -= 1UL << kpte_shift_min; + ent->tag = (1UL << TSB_TAG_INVALID_BIT); } +#ifndef CONFIG_DEBUG_PAGEALLOC + for (i = 0; i < KERNEL_TSB4M_NENTRIES; i++) { + struct tsb *ent = &swapper_4m_tsb[i]; - return start; -} - -static void __init mark_kpte_bitmap(unsigned long start, unsigned long end) -{ - unsigned long smallest_size, smallest_mask; - unsigned long s; - - smallest_size = (1UL << kpte_shift_min); - smallest_mask = (smallest_size - 1UL); - - while (start < end) { - unsigned long orig_start = start; - - for (s = kpte_shift_max; s >= kpte_shift_min; s -= kpte_shift_incr) { - start = kpte_mark_using_shift(start, end, s); - - if (start != orig_start) - break; - } - - if (start == orig_start) - start = (start + smallest_size) & ~smallest_mask; + ent->tag = (1UL << TSB_TAG_INVALID_BIT); } +#endif } -static void __init init_kpte_bitmap(void) -{ - unsigned long i; - - for (i = 0; i < pall_ents; i++) { - unsigned long phys_start, phys_end; - - phys_start = pall[i].phys_addr; - phys_end = phys_start + pall[i].reg_size; - - mark_kpte_bitmap(phys_start, phys_end); - } -} +extern unsigned int kvmap_linear_patch[1]; static void __init kernel_physical_mapping_init(void) { -#ifdef CONFIG_DEBUG_PAGEALLOC unsigned long i, mem_alloced = 0UL; + bool use_huge = true; +#ifdef CONFIG_DEBUG_PAGEALLOC + use_huge = false; +#endif for (i = 0; i < pall_ents; i++) { unsigned long phys_start, phys_end; @@ -1513,7 +1600,7 @@ static void __init kernel_physical_mapping_init(void) phys_end = phys_start + pall[i].reg_size; mem_alloced += kernel_map_range(phys_start, phys_end, - PAGE_KERNEL); + PAGE_KERNEL, use_huge); } printk("Allocated %ld bytes for kernel page tables.\n", @@ -1522,8 +1609,9 @@ static void __init kernel_physical_mapping_init(void) kvmap_linear_patch[0] = 0x01000000; /* nop */ flushi(&kvmap_linear_patch[0]); + flush_all_kernel_tsbs(); + __flush_tlb_all(); -#endif } #ifdef CONFIG_DEBUG_PAGEALLOC @@ -1533,7 +1621,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable) unsigned long phys_end = phys_start + (numpages * PAGE_SIZE); kernel_map_range(phys_start, phys_end, - (enable ? PAGE_KERNEL : __pgprot(0))); + (enable ? PAGE_KERNEL : __pgprot(0)), false); flush_tsb_kernel_range(PAGE_OFFSET + phys_start, PAGE_OFFSET + phys_end); @@ -1561,76 +1649,56 @@ unsigned long __init find_ecache_flush_span(unsigned long size) unsigned long PAGE_OFFSET; EXPORT_SYMBOL(PAGE_OFFSET); -static void __init page_offset_shift_patch_one(unsigned int *insn, unsigned long phys_bits) -{ - unsigned long final_shift; - unsigned int val = *insn; - unsigned int cnt; - - /* We are patching in ilog2(max_supported_phys_address), and - * we are doing so in a manner similar to a relocation addend. - * That is, we are adding the shift value to whatever value - * is in the shift instruction count field already. - */ - cnt = (val & 0x3f); - val &= ~0x3f; - - /* If we are trying to shift >= 64 bits, clear the destination - * register. This can happen when phys_bits ends up being equal - * to MAX_PHYS_ADDRESS_BITS. - */ - final_shift = (cnt + (64 - phys_bits)); - if (final_shift >= 64) { - unsigned int rd = (val >> 25) & 0x1f; - - val = 0x80100000 | (rd << 25); - } else { - val |= final_shift; - } - *insn = val; - - __asm__ __volatile__("flush %0" - : /* no outputs */ - : "r" (insn)); -} - -static void __init page_offset_shift_patch(unsigned long phys_bits) -{ - extern unsigned int __page_offset_shift_patch; - extern unsigned int __page_offset_shift_patch_end; - unsigned int *p; - - p = &__page_offset_shift_patch; - while (p < &__page_offset_shift_patch_end) { - unsigned int *insn = (unsigned int *)(unsigned long)*p; +unsigned long VMALLOC_END = 0x0000010000000000UL; +EXPORT_SYMBOL(VMALLOC_END); - page_offset_shift_patch_one(insn, phys_bits); - - p++; - } -} +unsigned long sparc64_va_hole_top = 0xfffff80000000000UL; +unsigned long sparc64_va_hole_bottom = 0x0000080000000000UL; static void __init setup_page_offset(void) { - unsigned long max_phys_bits = 40; - if (tlb_type == cheetah || tlb_type == cheetah_plus) { + /* Cheetah/Panther support a full 64-bit virtual + * address, so we can use all that our page tables + * support. + */ + sparc64_va_hole_top = 0xfff0000000000000UL; + sparc64_va_hole_bottom = 0x0010000000000000UL; + max_phys_bits = 42; } else if (tlb_type == hypervisor) { switch (sun4v_chip_type) { case SUN4V_CHIP_NIAGARA1: case SUN4V_CHIP_NIAGARA2: + /* T1 and T2 support 48-bit virtual addresses. */ + sparc64_va_hole_top = 0xffff800000000000UL; + sparc64_va_hole_bottom = 0x0000800000000000UL; + max_phys_bits = 39; break; case SUN4V_CHIP_NIAGARA3: + /* T3 supports 48-bit virtual addresses. */ + sparc64_va_hole_top = 0xffff800000000000UL; + sparc64_va_hole_bottom = 0x0000800000000000UL; + max_phys_bits = 43; break; case SUN4V_CHIP_NIAGARA4: case SUN4V_CHIP_NIAGARA5: case SUN4V_CHIP_SPARC64X: - default: + case SUN4V_CHIP_SPARC_M6: + /* T4 and later support 52-bit virtual addresses. */ + sparc64_va_hole_top = 0xfff8000000000000UL; + sparc64_va_hole_bottom = 0x0008000000000000UL; max_phys_bits = 47; break; + case SUN4V_CHIP_SPARC_M7: + default: + /* M7 and later support 52-bit virtual addresses. */ + sparc64_va_hole_top = 0xfff8000000000000UL; + sparc64_va_hole_bottom = 0x0008000000000000UL; + max_phys_bits = 49; + break; } } @@ -1640,12 +1708,16 @@ static void __init setup_page_offset(void) prom_halt(); } - PAGE_OFFSET = PAGE_OFFSET_BY_BITS(max_phys_bits); + PAGE_OFFSET = sparc64_va_hole_top; + VMALLOC_END = ((sparc64_va_hole_bottom >> 1) + + (sparc64_va_hole_bottom >> 2)); - pr_info("PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n", + pr_info("MM: PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n", PAGE_OFFSET, max_phys_bits); - - page_offset_shift_patch(max_phys_bits); + pr_info("MM: VMALLOC [0x%016lx --> 0x%016lx]\n", + VMALLOC_START, VMALLOC_END); + pr_info("MM: VMEMMAP [0x%016lx --> 0x%016lx]\n", + VMEMMAP_BASE, VMEMMAP_BASE << 1); } static void __init tsb_phys_patch(void) @@ -1690,21 +1762,42 @@ static void __init tsb_phys_patch(void) #define NUM_KTSB_DESCR 1 #endif static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR]; -extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; + +/* The swapper TSBs are loaded with a base sequence of: + * + * sethi %uhi(SYMBOL), REG1 + * sethi %hi(SYMBOL), REG2 + * or REG1, %ulo(SYMBOL), REG1 + * or REG2, %lo(SYMBOL), REG2 + * sllx REG1, 32, REG1 + * or REG1, REG2, REG1 + * + * When we use physical addressing for the TSB accesses, we patch the + * first four instructions in the above sequence. + */ static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa) { - pa >>= KTSB_PHYS_SHIFT; + unsigned long high_bits, low_bits; + + high_bits = (pa >> 32) & 0xffffffff; + low_bits = (pa >> 0) & 0xffffffff; while (start < end) { unsigned int *ia = (unsigned int *)(unsigned long)*start; - ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10); + ia[0] = (ia[0] & ~0x3fffff) | (high_bits >> 10); __asm__ __volatile__("flush %0" : : "r" (ia)); - ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff); + ia[1] = (ia[1] & ~0x3fffff) | (low_bits >> 10); __asm__ __volatile__("flush %0" : : "r" (ia + 1)); + ia[2] = (ia[2] & ~0x1fff) | (high_bits & 0x3ff); + __asm__ __volatile__("flush %0" : : "r" (ia + 2)); + + ia[3] = (ia[3] & ~0x1fff) | (low_bits & 0x3ff); + __asm__ __volatile__("flush %0" : : "r" (ia + 3)); + start++; } } @@ -1843,7 +1936,6 @@ static void __init sun4v_linear_pte_xor_finalize(void) /* paging_init() sets up the page tables */ static unsigned long last_valid_pfn; -pgd_t swapper_pg_dir[PTRS_PER_PGD]; static void sun4u_pgprot_init(void); static void sun4v_pgprot_init(void); @@ -1881,7 +1973,7 @@ void __init paging_init(void) BUILD_BUG_ON(NR_CPUS > 4096); - kern_base = (prom_boot_mapping_phys_low >> 22UL) << 22UL; + kern_base = (prom_boot_mapping_phys_low >> ILOG2_4MB) << ILOG2_4MB; kern_size = (unsigned long)&_end - (unsigned long)KERNBASE; /* Invalidate both kernel TSBs. */ @@ -1937,7 +2029,7 @@ void __init paging_init(void) shift = kern_base + PAGE_OFFSET - ((unsigned long)KERNBASE); real_end = (unsigned long)_end; - num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << 22); + num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << ILOG2_4MB); printk("Kernel: Using %d locked TLB entries for main kernel image.\n", num_kernel_image_mappings); @@ -1946,16 +2038,10 @@ void __init paging_init(void) */ init_mm.pgd += ((shift) / (sizeof(pgd_t))); - memset(swapper_low_pmd_dir, 0, sizeof(swapper_low_pmd_dir)); + memset(swapper_pg_dir, 0, sizeof(swapper_pg_dir)); - /* Now can init the kernel/bad page tables. */ - pud_set(pud_offset(&swapper_pg_dir[0], 0), - swapper_low_pmd_dir + (shift / sizeof(pgd_t))); - inherit_prom_mappings(); - init_kpte_bitmap(); - /* Ok, we can use our TLB miss and window trap handlers safely. */ setup_tba(); @@ -2062,70 +2148,6 @@ int page_in_phys_avail(unsigned long paddr) return 0; } -static struct linux_prom64_registers pavail_rescan[MAX_BANKS] __initdata; -static int pavail_rescan_ents __initdata; - -/* Certain OBP calls, such as fetching "available" properties, can - * claim physical memory. So, along with initializing the valid - * address bitmap, what we do here is refetch the physical available - * memory list again, and make sure it provides at least as much - * memory as 'pavail' does. - */ -static void __init setup_valid_addr_bitmap_from_pavail(unsigned long *bitmap) -{ - int i; - - read_obp_memory("available", &pavail_rescan[0], &pavail_rescan_ents); - - for (i = 0; i < pavail_ents; i++) { - unsigned long old_start, old_end; - - old_start = pavail[i].phys_addr; - old_end = old_start + pavail[i].reg_size; - while (old_start < old_end) { - int n; - - for (n = 0; n < pavail_rescan_ents; n++) { - unsigned long new_start, new_end; - - new_start = pavail_rescan[n].phys_addr; - new_end = new_start + - pavail_rescan[n].reg_size; - - if (new_start <= old_start && - new_end >= (old_start + PAGE_SIZE)) { - set_bit(old_start >> 22, bitmap); - goto do_next_page; - } - } - - prom_printf("mem_init: Lost memory in pavail\n"); - prom_printf("mem_init: OLD start[%lx] size[%lx]\n", - pavail[i].phys_addr, - pavail[i].reg_size); - prom_printf("mem_init: NEW start[%lx] size[%lx]\n", - pavail_rescan[i].phys_addr, - pavail_rescan[i].reg_size); - prom_printf("mem_init: Cannot continue, aborting.\n"); - prom_halt(); - - do_next_page: - old_start += PAGE_SIZE; - } - } -} - -static void __init patch_tlb_miss_handler_bitmap(void) -{ - extern unsigned int valid_addr_bitmap_insn[]; - extern unsigned int valid_addr_bitmap_patch[]; - - valid_addr_bitmap_insn[1] = valid_addr_bitmap_patch[1]; - mb(); - valid_addr_bitmap_insn[0] = valid_addr_bitmap_patch[0]; - flushi(&valid_addr_bitmap_insn[0]); -} - static void __init register_page_bootmem_info(void) { #ifdef CONFIG_NEED_MULTIPLE_NODES @@ -2138,18 +2160,6 @@ static void __init register_page_bootmem_info(void) } void __init mem_init(void) { - unsigned long addr, last; - - addr = PAGE_OFFSET + kern_base; - last = PAGE_ALIGN(kern_size) + addr; - while (addr < last) { - set_bit(__pa(addr) >> 22, sparc64_valid_addr_bitmap); - addr += PAGE_SIZE; - } - - setup_valid_addr_bitmap_from_pavail(sparc64_valid_addr_bitmap); - patch_tlb_miss_handler_bitmap(); - high_memory = __va(last_valid_pfn << PAGE_SHIFT); register_page_bootmem_info(); @@ -2239,18 +2249,9 @@ unsigned long _PAGE_CACHE __read_mostly; EXPORT_SYMBOL(_PAGE_CACHE); #ifdef CONFIG_SPARSEMEM_VMEMMAP -unsigned long vmemmap_table[VMEMMAP_SIZE]; - -static long __meminitdata addr_start, addr_end; -static int __meminitdata node_start; - int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, int node) { - unsigned long phys_start = (vstart - VMEMMAP_BASE); - unsigned long phys_end = (vend - VMEMMAP_BASE); - unsigned long addr = phys_start & VMEMMAP_CHUNK_MASK; - unsigned long end = VMEMMAP_ALIGN(phys_end); unsigned long pte_base; pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4U | @@ -2261,47 +2262,52 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V | _PAGE_W_4V); - for (; addr < end; addr += VMEMMAP_CHUNK) { - unsigned long *vmem_pp = - vmemmap_table + (addr >> VMEMMAP_CHUNK_SHIFT); - void *block; + pte_base |= _PAGE_PMD_HUGE; - if (!(*vmem_pp & _PAGE_VALID)) { - block = vmemmap_alloc_block(1UL << 22, node); - if (!block) + vstart = vstart & PMD_MASK; + vend = ALIGN(vend, PMD_SIZE); + for (; vstart < vend; vstart += PMD_SIZE) { + pgd_t *pgd = pgd_offset_k(vstart); + unsigned long pte; + pud_t *pud; + pmd_t *pmd; + + if (pgd_none(*pgd)) { + pud_t *new = vmemmap_alloc_block(PAGE_SIZE, node); + + if (!new) return -ENOMEM; + pgd_populate(&init_mm, pgd, new); + } - *vmem_pp = pte_base | __pa(block); + pud = pud_offset(pgd, vstart); + if (pud_none(*pud)) { + pmd_t *new = vmemmap_alloc_block(PAGE_SIZE, node); - /* check to see if we have contiguous blocks */ - if (addr_end != addr || node_start != node) { - if (addr_start) - printk(KERN_DEBUG " [%lx-%lx] on node %d\n", - addr_start, addr_end-1, node_start); - addr_start = addr; - node_start = node; - } - addr_end = addr + VMEMMAP_CHUNK; + if (!new) + return -ENOMEM; + pud_populate(&init_mm, pud, new); } - } - return 0; -} -void __meminit vmemmap_populate_print_last(void) -{ - if (addr_start) { - printk(KERN_DEBUG " [%lx-%lx] on node %d\n", - addr_start, addr_end-1, node_start); - addr_start = 0; - addr_end = 0; - node_start = 0; + pmd = pmd_offset(pud, vstart); + + pte = pmd_val(*pmd); + if (!(pte & _PAGE_VALID)) { + void *block = vmemmap_alloc_block(PMD_SIZE, node); + + if (!block) + return -ENOMEM; + + pmd_val(*pmd) = pte_base | __pa(block); + } } + + return 0; } void vmemmap_free(unsigned long start, unsigned long end) { } - #endif /* CONFIG_SPARSEMEM_VMEMMAP */ static void prot_init_common(unsigned long page_none, @@ -2614,6 +2620,10 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pte = pmd_val(entry); + /* Don't insert a non-valid PMD into the TSB, we'll deadlock. */ + if (!(pte & _PAGE_VALID)) + return; + /* We are fabricating 8MB pages using 4MB real hw pages. */ pte |= (addr & (1UL << REAL_HPAGE_SHIFT)); @@ -2694,3 +2704,26 @@ void hugetlb_setup(struct pt_regs *regs) } } #endif + +#ifdef CONFIG_SMP +#define do_flush_tlb_kernel_range smp_flush_tlb_kernel_range +#else +#define do_flush_tlb_kernel_range __flush_tlb_kernel_range +#endif + +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + if (start < HI_OBP_ADDRESS && end > LOW_OBP_ADDRESS) { + if (start < LOW_OBP_ADDRESS) { + flush_tsb_kernel_range(start, LOW_OBP_ADDRESS); + do_flush_tlb_kernel_range(start, LOW_OBP_ADDRESS); + } + if (end > HI_OBP_ADDRESS) { + flush_tsb_kernel_range(HI_OBP_ADDRESS, end); + do_flush_tlb_kernel_range(HI_OBP_ADDRESS, end); + } + } else { + flush_tsb_kernel_range(start, end); + do_flush_tlb_kernel_range(start, end); + } +} diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h index 5d3782de..ac49119 100644 --- a/arch/sparc/mm/init_64.h +++ b/arch/sparc/mm/init_64.h @@ -8,15 +8,8 @@ */ #define MAX_PHYS_ADDRESS (1UL << MAX_PHYS_ADDRESS_BITS) -#define KPTE_BITMAP_CHUNK_SZ (256UL * 1024UL * 1024UL) -#define KPTE_BITMAP_BYTES \ - ((MAX_PHYS_ADDRESS / KPTE_BITMAP_CHUNK_SZ) / 4) -#define VALID_ADDR_BITMAP_CHUNK_SZ (4UL * 1024UL * 1024UL) -#define VALID_ADDR_BITMAP_BYTES \ - ((MAX_PHYS_ADDRESS / VALID_ADDR_BITMAP_CHUNK_SZ) / 8) extern unsigned long kern_linear_pte_xor[4]; -extern unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)]; extern unsigned int sparc64_highest_unlocked_tlb_ent; extern unsigned long sparc64_kern_pri_context; extern unsigned long sparc64_kern_pri_nuc_bits; @@ -38,15 +31,4 @@ extern unsigned long kern_locked_tte_data; extern void prom_world(int enter); -#ifdef CONFIG_SPARSEMEM_VMEMMAP -#define VMEMMAP_CHUNK_SHIFT 22 -#define VMEMMAP_CHUNK (1UL << VMEMMAP_CHUNK_SHIFT) -#define VMEMMAP_CHUNK_MASK ~(VMEMMAP_CHUNK - 1UL) -#define VMEMMAP_ALIGN(x) (((x)+VMEMMAP_CHUNK-1UL)&VMEMMAP_CHUNK_MASK) - -#define VMEMMAP_SIZE ((((1UL << MAX_PHYSADDR_BITS) >> PAGE_SHIFT) * \ - sizeof(struct page)) >> VMEMMAP_CHUNK_SHIFT) -extern unsigned long vmemmap_table[VMEMMAP_SIZE]; -#endif - #endif /* _SPARC64_MM_INIT_H */ diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index cfbe53c..09daebd 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -460,10 +460,12 @@ static void __init sparc_context_init(int numctx) void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk) { + unsigned long flags; + if (mm->context == NO_CONTEXT) { - spin_lock(&srmmu_context_spinlock); + spin_lock_irqsave(&srmmu_context_spinlock, flags); alloc_context(old_mm, mm); - spin_unlock(&srmmu_context_spinlock); + spin_unlock_irqrestore(&srmmu_context_spinlock, flags); srmmu_ctxd_set(&srmmu_context_table[mm->context], mm->pgd); } @@ -988,14 +990,15 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) void destroy_context(struct mm_struct *mm) { + unsigned long flags; if (mm->context != NO_CONTEXT) { flush_cache_mm(mm); srmmu_ctxd_set(&srmmu_context_table[mm->context], srmmu_swapper_pg_dir); flush_tlb_mm(mm); - spin_lock(&srmmu_context_spinlock); + spin_lock_irqsave(&srmmu_context_spinlock, flags); free_context(mm->context); - spin_unlock(&srmmu_context_spinlock); + spin_unlock_irqrestore(&srmmu_context_spinlock, flags); mm->context = NO_CONTEXT; } } diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index b12cb5e..b89aba2 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -134,7 +134,7 @@ no_cache_flush: #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr, - pmd_t pmd, bool exec) + pmd_t pmd) { unsigned long end; pte_t *pte; @@ -142,8 +142,11 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr, pte = pte_offset_map(&pmd, vaddr); end = vaddr + HPAGE_SIZE; while (vaddr < end) { - if (pte_val(*pte) & _PAGE_VALID) + if (pte_val(*pte) & _PAGE_VALID) { + bool exec = pte_exec(*pte); + tlb_batch_add_one(mm, vaddr, exec); + } pte++; vaddr += PAGE_SIZE; } @@ -177,19 +180,30 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, } if (!pmd_none(orig)) { - pte_t orig_pte = __pte(pmd_val(orig)); - bool exec = pte_exec(orig_pte); - addr &= HPAGE_MASK; if (pmd_trans_huge(orig)) { + pte_t orig_pte = __pte(pmd_val(orig)); + bool exec = pte_exec(orig_pte); + tlb_batch_add_one(mm, addr, exec); tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec); } else { - tlb_batch_pmd_scan(mm, addr, orig, exec); + tlb_batch_pmd_scan(mm, addr, orig); } } } +void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + pmd_t entry = *pmdp; + + pmd_val(entry) &= ~_PAGE_VALID; + + set_pmd_at(vma->vm_mm, address, pmdp, entry); + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); +} + void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) { diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index f5d506f..fe19b81 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -133,7 +133,19 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign mm->context.tsb_block[tsb_idx].tsb_nentries = tsb_bytes / sizeof(struct tsb); - base = TSBMAP_BASE; + switch (tsb_idx) { + case MM_TSB_BASE: + base = TSBMAP_8K_BASE; + break; +#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) + case MM_TSB_HUGE: + base = TSBMAP_4M_BASE; + break; +#endif + default: + BUG(); + } + tte = pgprot_val(PAGE_KERNEL_LOCKED); tsb_paddr = __pa(mm->context.tsb_block[tsb_idx].tsb); BUG_ON(tsb_paddr & (tsb_bytes - 1UL)); diff --git a/arch/sparc/power/hibernate.c b/arch/sparc/power/hibernate.c index 42b0b8c..17bd2e1 100644 --- a/arch/sparc/power/hibernate.c +++ b/arch/sparc/power/hibernate.c @@ -9,11 +9,9 @@ #include #include #include +#include #include -/* References to section boundaries */ -extern const void __nosave_begin, __nosave_end; - struct saved_context saved_context; /* diff --git a/arch/sparc/power/hibernate_asm.S b/arch/sparc/power/hibernate_asm.S index 7994216..d7d9017 100644 --- a/arch/sparc/power/hibernate_asm.S +++ b/arch/sparc/power/hibernate_asm.S @@ -54,8 +54,8 @@ ENTRY(swsusp_arch_resume) nop /* Write PAGE_OFFSET to %g7 */ - sethi %uhi(PAGE_OFFSET), %g7 - sllx %g7, 32, %g7 + sethi %hi(PAGE_OFFSET), %g7 + ldx [%g7 + %lo(PAGE_OFFSET)], %g7 setuw (PAGE_SIZE-8), %g3 diff --git a/arch/sparc/prom/bootstr_64.c b/arch/sparc/prom/bootstr_64.c index ab9ccc6..7149e77 100644 --- a/arch/sparc/prom/bootstr_64.c +++ b/arch/sparc/prom/bootstr_64.c @@ -14,7 +14,10 @@ * the .bss section or it will break things. */ -#define BARG_LEN 256 +/* We limit BARG_LEN to 1024 because this is the size of the + * 'barg_out' command line buffer in the SILO bootloader. + */ +#define BARG_LEN 1024 struct { int bootstr_len; int bootstr_valid; diff --git a/arch/sparc/prom/cif.S b/arch/sparc/prom/cif.S index 9c86b4b..8050f38 100644 --- a/arch/sparc/prom/cif.S +++ b/arch/sparc/prom/cif.S @@ -11,11 +11,10 @@ .text .globl prom_cif_direct prom_cif_direct: + save %sp, -192, %sp sethi %hi(p1275buf), %o1 or %o1, %lo(p1275buf), %o1 - ldx [%o1 + 0x0010], %o2 ! prom_cif_stack - save %o2, -192, %sp - ldx [%i1 + 0x0008], %l2 ! prom_cif_handler + ldx [%o1 + 0x0008], %l2 ! prom_cif_handler mov %g4, %l0 mov %g5, %l1 mov %g6, %l3 diff --git a/arch/sparc/prom/init_64.c b/arch/sparc/prom/init_64.c index d95db75..110b0d7 100644 --- a/arch/sparc/prom/init_64.c +++ b/arch/sparc/prom/init_64.c @@ -26,13 +26,13 @@ phandle prom_chosen_node; * It gets passed the pointer to the PROM vector. */ -extern void prom_cif_init(void *, void *); +extern void prom_cif_init(void *); -void __init prom_init(void *cif_handler, void *cif_stack) +void __init prom_init(void *cif_handler) { phandle node; - prom_cif_init(cif_handler, cif_stack); + prom_cif_init(cif_handler); prom_chosen_node = prom_finddevice(prom_chosen_path); if (!prom_chosen_node || (s32)prom_chosen_node == -1) diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c index e58b817..545d8bb 100644 --- a/arch/sparc/prom/p1275.c +++ b/arch/sparc/prom/p1275.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -19,7 +20,6 @@ struct { long prom_callback; /* 0x00 */ void (*prom_cif_handler)(long *); /* 0x08 */ - unsigned long prom_cif_stack; /* 0x10 */ } p1275buf; extern void prom_world(int); @@ -36,8 +36,8 @@ void p1275_cmd_direct(unsigned long *args) { unsigned long flags; - raw_local_save_flags(flags); - raw_local_irq_restore((unsigned long)PIL_NMI); + local_save_flags(flags); + local_irq_restore((unsigned long)PIL_NMI); raw_spin_lock(&prom_entry_lock); prom_world(1); @@ -45,11 +45,10 @@ void p1275_cmd_direct(unsigned long *args) prom_world(0); raw_spin_unlock(&prom_entry_lock); - raw_local_irq_restore(flags); + local_irq_restore(flags); } void prom_cif_init(void *cif_handler, void *cif_stack) { p1275buf.prom_cif_handler = (void (*)(long *))cif_handler; - p1275buf.prom_cif_stack = (unsigned long)cif_stack; } diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index 74c9172..bdb3ecf 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -1146,7 +1146,7 @@ static void __init load_hv_initrd(void) void __init free_initrd_mem(unsigned long begin, unsigned long end) { - free_bootmem(__pa(begin), end - begin); + free_bootmem_late(__pa(begin), end - begin); } static int __init setup_initrd(char *str) diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index 6c05712..c6d2a76 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -444,6 +444,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c index 004ba56..33294fd 100644 --- a/arch/tile/mm/homecache.c +++ b/arch/tile/mm/homecache.c @@ -417,7 +417,7 @@ void __homecache_free_pages(struct page *page, unsigned int order) if (put_page_testzero(page)) { homecache_change_page_home(page, order, PAGE_HOME_HASH); if (order == 0) { - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); } else { init_page_count(page); __free_pages(page, order); diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common index 21ca44c..1f0ea55 100644 --- a/arch/um/Kconfig.common +++ b/arch/um/Kconfig.common @@ -2,6 +2,7 @@ config UML bool default y select HAVE_UID16 + select HAVE_FUTEX_CMPXCHG if FUTEX select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select GENERIC_IO diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 3716e69..e8ab93c 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1277,7 +1277,7 @@ static void do_ubd_request(struct request_queue *q) while(1){ struct ubd *dev = q->queuedata; - if(dev->end_sg == 0){ + if(dev->request == NULL){ struct request *req = blk_fetch_request(q); if(req == NULL) return; @@ -1299,7 +1299,8 @@ static void do_ubd_request(struct request_queue *q) return; } prepare_flush_request(req, io_req); - submit_request(io_req, dev); + if (submit_request(io_req, dev) == false) + return; } while(dev->start_sg < dev->end_sg){ diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 974b874..53b8320 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -80,6 +80,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; + } else if (fault & VM_FAULT_SIGSEGV) { + goto out; } else if (fault & VM_FAULT_SIGBUS) { err = -EACCES; goto out; diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h index fb5e4c6..ef470a7 100644 --- a/arch/unicore32/include/asm/mmu_context.h +++ b/arch/unicore32/include/asm/mmu_context.h @@ -14,6 +14,8 @@ #include #include +#include +#include #include #include @@ -73,7 +75,7 @@ do { \ else \ mm->mmap = NULL; \ rb_erase(&high_vma->vm_rb, &mm->mm_rb); \ - mm->mmap_cache = NULL; \ + vmacache_invalidate(mm); \ mm->map_count--; \ remove_vma(high_vma); \ } \ diff --git a/arch/unicore32/include/mach/pm.h b/arch/unicore32/include/mach/pm.h index 4dcd34a..77b5226 100644 --- a/arch/unicore32/include/mach/pm.h +++ b/arch/unicore32/include/mach/pm.h @@ -36,8 +36,5 @@ extern int puv3_pm_enter(suspend_state_t state); /* Defined in hibernate_asm.S */ extern int restore_image(pgd_t *resume_pg_dir, struct pbe *restore_pblist); -/* References to section boundaries */ -extern const void __nosave_begin, __nosave_end; - extern struct pbe *restore_pblist; #endif diff --git a/arch/unicore32/kernel/hibernate.c b/arch/unicore32/kernel/hibernate.c index d75ef8b..9969ec3 100644 --- a/arch/unicore32/kernel/hibernate.c +++ b/arch/unicore32/kernel/hibernate.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include "mach/pm.h" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7324107..96e743a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -160,7 +160,7 @@ config SBUS config NEED_DMA_MAP_STATE def_bool y - depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG + depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG || SWIOTLB config NEED_SG_DMA_LENGTH def_bool y @@ -854,7 +854,7 @@ source "kernel/Kconfig.preempt" config X86_UP_APIC bool "Local APIC support on uniprocessors" - depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI + depends on X86_32 && !SMP && !X86_32_NON_STANDARD ---help--- A local APIC (Advanced Programmable Interrupt Controller) is an integrated interrupt controller in the CPU. If you have a single-CPU @@ -865,6 +865,10 @@ config X86_UP_APIC performance counters), and the NMI watchdog which detects hard lockups. +config X86_UP_APIC_MSI + def_bool y + select X86_UP_APIC if X86_32 && !SMP && !X86_32_NON_STANDARD && PCI_MSI + config X86_UP_IOAPIC bool "IO-APIC support on uniprocessors" depends on X86_UP_APIC @@ -966,10 +970,27 @@ config VM86 default y depends on X86_32 ---help--- - This option is required by programs like DOSEMU to run 16-bit legacy - code on X86 processors. It also may be needed by software like - XFree86 to initialize some video cards via BIOS. Disabling this - option saves about 6k. + This option is required by programs like DOSEMU to run + 16-bit real mode legacy code on x86 processors. It also may + be needed by software like XFree86 to initialize some video + cards via BIOS. Disabling this option saves about 6K. + +config X86_16BIT + bool "Enable support for 16-bit segments" if EXPERT + default y + ---help--- + This option is required by programs like Wine to run 16-bit + protected mode legacy code on x86 processors. Disabling + this option saves about 300 bytes on i386, or around 6K text + plus 16K runtime memory on x86-64, + +config X86_ESPFIX32 + def_bool y + depends on X86_16BIT && X86_32 + +config X86_ESPFIX64 + def_bool y + depends on X86_16BIT && X86_64 config TOSHIBA tristate "Toshiba Laptop support" @@ -1580,6 +1601,7 @@ config EFI config EFI_STUB bool "EFI stub support" depends on EFI + select RELOCATABLE ---help--- This kernel feature allows a bzImage to be loaded directly by EFI firmware without the use of a bootloader. @@ -2418,12 +2440,19 @@ config X86_DMA_REMAP depends on STA2X11 config IOSF_MBI - bool + tristate "Intel System On Chip IOSF Sideband support" depends on PCI ---help--- - To be selected by modules requiring access to the Intel OnChip System - Fabric (IOSF) Sideband MailBox Interface (MBI). For MBI platforms - enumerable by PCI. + Enables sideband access to mailbox registers on SoC's. The sideband is + available on the following platforms. This list is not meant to be + exclusive. + - BayTrail + - Cherryview + - Braswell + - Quark + + You should say Y if you are running a kernel on one of these + platforms. source "net/Kconfig" diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 0fcd913..67e9f5c 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -75,8 +75,10 @@ suffix-$(CONFIG_KERNEL_XZ) := xz suffix-$(CONFIG_KERNEL_LZO) := lzo suffix-$(CONFIG_KERNEL_LZ4) := lz4 +RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \ + $(CONFIG_SHELL) $(srctree)/arch/x86/tools/calc_run_size.sh) quiet_cmd_mkpiggy = MKPIGGY $@ - cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false ) + cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false ) targets += piggy.S $(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c index 4dbf967..6cfcf2a 100644 --- a/arch/x86/boot/compressed/aslr.c +++ b/arch/x86/boot/compressed/aslr.c @@ -183,12 +183,27 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, static bool mem_avoid_overlap(struct mem_vector *img) { int i; + struct setup_data *ptr; for (i = 0; i < MEM_AVOID_MAX; i++) { if (mem_overlaps(img, &mem_avoid[i])) return true; } + /* Avoid all entries in the setup_data linked list. */ + ptr = (struct setup_data *)(unsigned long)real_mode->hdr.setup_data; + while (ptr) { + struct mem_vector avoid; + + avoid.start = (u64)ptr; + avoid.size = sizeof(*ptr) + ptr->len; + + if (mem_overlaps(img, &avoid)) + return true; + + ptr = (struct setup_data *)(unsigned long)ptr->next; + } + return false; } diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 78cbb2d..ec5a3c7 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -560,6 +560,10 @@ static efi_status_t setup_e820(struct boot_params *params, unsigned int e820_type = 0; unsigned long m = efi->efi_memmap; +#ifdef CONFIG_X86_64 + m |= (u64)efi->efi_memmap_hi << 32; +#endif + d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size)); switch (d->type) { case EFI_RESERVED_TYPE: diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index f45ab7a..a814c80 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -54,7 +54,7 @@ ENTRY(efi_pe_entry) call reloc reloc: popl %ecx - subl reloc, %ecx + subl $reloc, %ecx movl %ecx, BP_code32_start(%eax) sub $0x4, %esp @@ -186,7 +186,8 @@ relocated: * Do the decompression, and jump to the new kernel.. */ /* push arguments for decompress_kernel: */ - pushl $z_output_len /* decompressed length */ + pushl $z_run_size /* size of kernel with .bss and .brk */ + pushl $z_output_len /* decompressed length, end of relocs */ leal z_extract_offset_negative(%ebx), %ebp pushl %ebp /* output address */ pushl $z_input_len /* input_len */ @@ -196,7 +197,7 @@ relocated: pushl %eax /* heap area */ pushl %esi /* real mode pointer */ call decompress_kernel /* returns kernel location in %eax */ - addl $24, %esp + addl $28, %esp /* * Jump to the decompressed kernel. diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index b10fa66..34bbc09 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -334,13 +334,16 @@ relocated: * Do the decompression, and jump to the new kernel.. */ pushq %rsi /* Save the real mode argument */ + movq $z_run_size, %r9 /* size of kernel with .bss and .brk */ + pushq %r9 movq %rsi, %rdi /* real mode address */ leaq boot_heap(%rip), %rsi /* malloc area for uncompression */ leaq input_data(%rip), %rdx /* input_data */ movl $z_input_len, %ecx /* input_len */ movq %rbp, %r8 /* output target address */ - movq $z_output_len, %r9 /* decompressed length */ + movq $z_output_len, %r9 /* decompressed length, end of relocs */ call decompress_kernel /* returns kernel location in %rax */ + popq %r9 popq %rsi /* diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 196eaf3..8f45c85 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -393,8 +393,11 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap, unsigned char *input_data, unsigned long input_len, unsigned char *output, - unsigned long output_len) + unsigned long output_len, + unsigned long run_size) { + unsigned char *output_orig = output; + real_mode = rmode; sanitize_boot_params(real_mode); @@ -416,8 +419,14 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap, free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; - output = choose_kernel_location(input_data, input_len, - output, output_len); + /* + * The memory hole needed for the kernel is the larger of either + * the entire decompressed kernel plus relocation table, or the + * entire decompressed kernel plus .bss and .brk sections. + */ + output = choose_kernel_location(input_data, input_len, output, + output_len > run_size ? output_len + : run_size); /* Validate memory location choices. */ if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1)) @@ -437,7 +446,12 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap, debug_putstr("\nDecompressing Linux... "); decompress(input_data, input_len, NULL, NULL, output, NULL, error); parse_elf(output); - handle_relocations(output, output_len); + /* + * 32-bit always performs relocations. 64-bit relocations are only + * needed if kASLR has chosen a different load address. + */ + if (!IS_ENABLED(CONFIG_X86_64) || output != output_orig) + handle_relocations(output, output_len); debug_putstr("done.\nBooting the kernel.\n"); return output; } diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index b669ab6..d8222f2 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -36,11 +36,13 @@ int main(int argc, char *argv[]) uint32_t olen; long ilen; unsigned long offs; + unsigned long run_size; FILE *f = NULL; int retval = 1; - if (argc < 2) { - fprintf(stderr, "Usage: %s compressed_file\n", argv[0]); + if (argc < 3) { + fprintf(stderr, "Usage: %s compressed_file run_size\n", + argv[0]); goto bail; } @@ -74,6 +76,7 @@ int main(int argc, char *argv[]) offs += olen >> 12; /* Add 8 bytes for each 32K block */ offs += 64*1024 + 128; /* Add 64K + 128 bytes slack */ offs = (offs+4095) & ~4095; /* Round to a 4K boundary */ + run_size = atoi(argv[2]); printf(".section \".rodata..compressed\",\"a\",@progbits\n"); printf(".globl z_input_len\n"); @@ -85,6 +88,8 @@ int main(int argc, char *argv[]) /* z_extract_offset_negative allows simplification of head_32.S */ printf(".globl z_extract_offset_negative\n"); printf("z_extract_offset_negative = -0x%lx\n", offs); + printf(".globl z_run_size\n"); + printf("z_run_size = %lu\n", run_size); printf(".globl input_data, input_data_end\n"); printf("input_data:\n"); diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index ec3b8ba..04da6c2 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -91,10 +91,9 @@ bs_die: .section ".bsdata", "a" bugger_off_msg: - .ascii "Direct floppy boot is not supported. " - .ascii "Use a boot loader program instead.\r\n" + .ascii "Use a boot loader.\r\n" .ascii "\n" - .ascii "Remove disk and press any key to reboot ...\r\n" + .ascii "Remove disk and press any key to reboot...\r\n" .byte 0 #ifdef CONFIG_EFI_STUB @@ -108,7 +107,7 @@ coff_header: #else .word 0x8664 # x86-64 #endif - .word 3 # nr_sections + .word 4 # nr_sections .long 0 # TimeDateStamp .long 0 # PointerToSymbolTable .long 1 # NumberOfSymbols @@ -250,6 +249,25 @@ section_table: .word 0 # NumberOfLineNumbers .long 0x60500020 # Characteristics (section flags) + # + # The offset & size fields are filled in by build.c. + # + .ascii ".bss" + .byte 0 + .byte 0 + .byte 0 + .byte 0 + .long 0 + .long 0x0 + .long 0 # Size of initialized data + # on disk + .long 0x0 + .long 0 # PointerToRelocations + .long 0 # PointerToLineNumbers + .word 0 # NumberOfRelocations + .word 0 # NumberOfLineNumbers + .long 0xc8000080 # Characteristics (section flags) + #endif /* CONFIG_EFI_STUB */ # Kernel attributes; used by setup. This is part 1 of the diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 8e15b22..3dafaeb 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -142,7 +142,7 @@ static void usage(void) #ifdef CONFIG_EFI_STUB -static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) +static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset) { unsigned int pe_header; unsigned short num_sections; @@ -163,10 +163,10 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz put_unaligned_le32(size, section + 0x8); /* section header vma field */ - put_unaligned_le32(offset, section + 0xc); + put_unaligned_le32(vma, section + 0xc); /* section header 'size of initialised data' field */ - put_unaligned_le32(size, section + 0x10); + put_unaligned_le32(datasz, section + 0x10); /* section header 'file offset' field */ put_unaligned_le32(offset, section + 0x14); @@ -178,6 +178,11 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz } } +static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) +{ + update_pecoff_section_header_fields(section_name, offset, size, size, offset); +} + static void update_pecoff_setup_and_reloc(unsigned int size) { u32 setup_offset = 0x200; @@ -202,9 +207,6 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) pe_header = get_unaligned_le32(&buf[0x3c]); - /* Size of image */ - put_unaligned_le32(file_sz, &buf[pe_header + 0x50]); - /* * Size of code: Subtract the size of the first sector (512 bytes) * which includes the header. @@ -219,6 +221,22 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) update_pecoff_section_header(".text", text_start, text_sz); } +static void update_pecoff_bss(unsigned int file_sz, unsigned int init_sz) +{ + unsigned int pe_header; + unsigned int bss_sz = init_sz - file_sz; + + pe_header = get_unaligned_le32(&buf[0x3c]); + + /* Size of uninitialized data */ + put_unaligned_le32(bss_sz, &buf[pe_header + 0x24]); + + /* Size of image */ + put_unaligned_le32(init_sz, &buf[pe_header + 0x50]); + + update_pecoff_section_header_fields(".bss", file_sz, bss_sz, 0, 0); +} + #endif /* CONFIG_EFI_STUB */ @@ -270,6 +288,9 @@ int main(int argc, char ** argv) int fd; void *kernel; u32 crc = 0xffffffffUL; +#ifdef CONFIG_EFI_STUB + unsigned int init_sz; +#endif /* Defaults for old kernel */ #ifdef CONFIG_X86_32 @@ -343,7 +364,9 @@ int main(int argc, char ** argv) put_unaligned_le32(sys_size, &buf[0x1f4]); #ifdef CONFIG_EFI_STUB - update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz)); + update_pecoff_text(setup_sectors * 512, i + (sys_size * 16)); + init_sz = get_unaligned_le32(&buf[0x260]); + update_pecoff_bss(i + (sys_size * 16), init_sz); #ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */ efi_stub_entry -= 0x200; diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c index aafe8ce..e26984f 100644 --- a/arch/x86/crypto/aes_glue.c +++ b/arch/x86/crypto/aes_glue.c @@ -66,5 +66,5 @@ module_exit(aes_fini); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, asm optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("aes"); -MODULE_ALIAS("aes-asm"); +MODULE_ALIAS_CRYPTO("aes"); +MODULE_ALIAS_CRYPTO("aes-asm"); diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 948ad0e..6d4faba 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1109,7 +1109,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC); if (!src) return -ENOMEM; - assoc = (src + req->cryptlen + auth_tag_len); + assoc = (src + req->cryptlen); scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0); scatterwalk_map_and_copy(assoc, req->assoc, 0, req->assoclen, 0); @@ -1134,7 +1134,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) scatterwalk_done(&src_sg_walk, 0, 0); scatterwalk_done(&assoc_sg_walk, 0, 0); } else { - scatterwalk_map_and_copy(dst, req->dst, 0, req->cryptlen, 1); + scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1); kfree(src); } return retval; @@ -1514,4 +1514,4 @@ module_exit(aesni_exit); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("aes"); +MODULE_ALIAS_CRYPTO("aes"); diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c index 50ec333..1477cfc 100644 --- a/arch/x86/crypto/blowfish_glue.c +++ b/arch/x86/crypto/blowfish_glue.c @@ -481,5 +481,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Blowfish Cipher Algorithm, asm optimized"); -MODULE_ALIAS("blowfish"); -MODULE_ALIAS("blowfish-asm"); +MODULE_ALIAS_CRYPTO("blowfish"); +MODULE_ALIAS_CRYPTO("blowfish-asm"); diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c index 4209a76..9a07faf 100644 --- a/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -582,5 +582,5 @@ module_exit(camellia_aesni_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX2 optimized"); -MODULE_ALIAS("camellia"); -MODULE_ALIAS("camellia-asm"); +MODULE_ALIAS_CRYPTO("camellia"); +MODULE_ALIAS_CRYPTO("camellia-asm"); diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index 87a041a..ed38d95 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -574,5 +574,5 @@ module_exit(camellia_aesni_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX optimized"); -MODULE_ALIAS("camellia"); -MODULE_ALIAS("camellia-asm"); +MODULE_ALIAS_CRYPTO("camellia"); +MODULE_ALIAS_CRYPTO("camellia-asm"); diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c index c171dcb..5c8b626 100644 --- a/arch/x86/crypto/camellia_glue.c +++ b/arch/x86/crypto/camellia_glue.c @@ -1725,5 +1725,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, asm optimized"); -MODULE_ALIAS("camellia"); -MODULE_ALIAS("camellia-asm"); +MODULE_ALIAS_CRYPTO("camellia"); +MODULE_ALIAS_CRYPTO("camellia-asm"); diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c index e6a3700..f62e9db 100644 --- a/arch/x86/crypto/cast5_avx_glue.c +++ b/arch/x86/crypto/cast5_avx_glue.c @@ -494,4 +494,4 @@ module_exit(cast5_exit); MODULE_DESCRIPTION("Cast5 Cipher Algorithm, AVX optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("cast5"); +MODULE_ALIAS_CRYPTO("cast5"); diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c index 09f3677..0160f68 100644 --- a/arch/x86/crypto/cast6_avx_glue.c +++ b/arch/x86/crypto/cast6_avx_glue.c @@ -611,4 +611,4 @@ module_exit(cast6_exit); MODULE_DESCRIPTION("Cast6 Cipher Algorithm, AVX optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("cast6"); +MODULE_ALIAS_CRYPTO("cast6"); diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c index 9d014a7..1937fc1 100644 --- a/arch/x86/crypto/crc32-pclmul_glue.c +++ b/arch/x86/crypto/crc32-pclmul_glue.c @@ -197,5 +197,5 @@ module_exit(crc32_pclmul_mod_fini); MODULE_AUTHOR("Alexander Boyko "); MODULE_LICENSE("GPL"); -MODULE_ALIAS("crc32"); -MODULE_ALIAS("crc32-pclmul"); +MODULE_ALIAS_CRYPTO("crc32"); +MODULE_ALIAS_CRYPTO("crc32-pclmul"); diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 6812ad9..28640c3 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -280,5 +280,5 @@ MODULE_AUTHOR("Austin Zhang , Kent Liu "); MODULE_DESCRIPTION("T10 DIF CRC calculation accelerated with PCLMULQDQ."); MODULE_LICENSE("GPL"); -MODULE_ALIAS("crct10dif"); -MODULE_ALIAS("crct10dif-pclmul"); +MODULE_ALIAS_CRYPTO("crct10dif"); +MODULE_ALIAS_CRYPTO("crct10dif-pclmul"); diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c index 98d7a18..f368ba2 100644 --- a/arch/x86/crypto/fpu.c +++ b/arch/x86/crypto/fpu.c @@ -17,6 +17,7 @@ #include #include #include +#include #include struct crypto_fpu_ctx { @@ -159,3 +160,5 @@ void __exit crypto_fpu_exit(void) { crypto_unregister_template(&crypto_fpu_tmpl); } + +MODULE_ALIAS_CRYPTO("fpu"); diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index d785cf2..4bcf841 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -291,6 +291,7 @@ static struct ahash_alg ghash_async_alg = { .cra_name = "ghash", .cra_driver_name = "ghash-clmulni", .cra_priority = 400, + .cra_ctxsize = sizeof(struct ghash_async_ctx), .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC, .cra_blocksize = GHASH_BLOCK_SIZE, .cra_type = &crypto_ahash_type, @@ -341,4 +342,4 @@ module_exit(ghash_pclmulqdqni_mod_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("GHASH Message Digest Algorithm, " "acclerated by PCLMULQDQ-NI"); -MODULE_ALIAS("ghash"); +MODULE_ALIAS_CRYPTO("ghash"); diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c index 5e8e677..399a29d 100644 --- a/arch/x86/crypto/salsa20_glue.c +++ b/arch/x86/crypto/salsa20_glue.c @@ -119,5 +119,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm (optimized assembly version)"); -MODULE_ALIAS("salsa20"); -MODULE_ALIAS("salsa20-asm"); +MODULE_ALIAS_CRYPTO("salsa20"); +MODULE_ALIAS_CRYPTO("salsa20-asm"); diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c index 2fae489..437e47a 100644 --- a/arch/x86/crypto/serpent_avx2_glue.c +++ b/arch/x86/crypto/serpent_avx2_glue.c @@ -558,5 +558,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX2 optimized"); -MODULE_ALIAS("serpent"); -MODULE_ALIAS("serpent-asm"); +MODULE_ALIAS_CRYPTO("serpent"); +MODULE_ALIAS_CRYPTO("serpent-asm"); diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c index ff48708..7e21739 100644 --- a/arch/x86/crypto/serpent_avx_glue.c +++ b/arch/x86/crypto/serpent_avx_glue.c @@ -617,4 +617,4 @@ module_exit(serpent_exit); MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("serpent"); +MODULE_ALIAS_CRYPTO("serpent"); diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c index 8c95f86..bf025ad 100644 --- a/arch/x86/crypto/serpent_sse2_glue.c +++ b/arch/x86/crypto/serpent_sse2_glue.c @@ -618,4 +618,4 @@ module_exit(serpent_sse2_exit); MODULE_DESCRIPTION("Serpent Cipher Algorithm, SSE2 optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("serpent"); +MODULE_ALIAS_CRYPTO("serpent"); diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 4a11a9d..29e1060 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -237,4 +237,4 @@ module_exit(sha1_ssse3_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated"); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index f248546..4dc100d 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -318,5 +318,5 @@ module_exit(sha256_ssse3_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated"); -MODULE_ALIAS("sha256"); -MODULE_ALIAS("sha224"); +MODULE_ALIAS_CRYPTO("sha256"); +MODULE_ALIAS_CRYPTO("sha224"); diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 8626b03..26a5898 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -326,5 +326,5 @@ module_exit(sha512_ssse3_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, Supplemental SSE3 accelerated"); -MODULE_ALIAS("sha512"); -MODULE_ALIAS("sha384"); +MODULE_ALIAS_CRYPTO("sha512"); +MODULE_ALIAS_CRYPTO("sha384"); diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c index 4e3c665..1ac531e 100644 --- a/arch/x86/crypto/twofish_avx_glue.c +++ b/arch/x86/crypto/twofish_avx_glue.c @@ -579,4 +579,4 @@ module_exit(twofish_exit); MODULE_DESCRIPTION("Twofish Cipher Algorithm, AVX optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("twofish"); +MODULE_ALIAS_CRYPTO("twofish"); diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c index 0a52023..77e06c2 100644 --- a/arch/x86/crypto/twofish_glue.c +++ b/arch/x86/crypto/twofish_glue.c @@ -96,5 +96,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION ("Twofish Cipher Algorithm, asm optimized"); -MODULE_ALIAS("twofish"); -MODULE_ALIAS("twofish-asm"); +MODULE_ALIAS_CRYPTO("twofish"); +MODULE_ALIAS_CRYPTO("twofish-asm"); diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c index 13e63b3..56d8a08 100644 --- a/arch/x86/crypto/twofish_glue_3way.c +++ b/arch/x86/crypto/twofish_glue_3way.c @@ -495,5 +495,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Twofish Cipher Algorithm, 3-way parallel asm optimized"); -MODULE_ALIAS("twofish"); -MODULE_ALIAS("twofish-asm"); +MODULE_ALIAS_CRYPTO("twofish"); +MODULE_ALIAS_CRYPTO("twofish-asm"); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 4299eb0..92a2e93 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -151,6 +151,16 @@ ENTRY(ia32_sysenter_target) 1: movl (%rbp),%ebp _ASM_EXTABLE(1b,ia32_badarg) ASM_CLAC + + /* + * Sysenter doesn't filter flags, so we need to clear NT + * ourselves. To save a few cycles, we can check whether + * NT was set instead of doing an unconditional popfq. + */ + testl $X86_EFLAGS_NT,EFLAGS-ARGOFFSET(%rsp) + jnz sysenter_fix_flags +sysenter_flags_fixed: + orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) CFI_REMEMBER_STATE @@ -184,6 +194,8 @@ sysexit_from_sys_call: TRACE_IRQS_ON ENABLE_INTERRUPTS_SYSEXIT32 + CFI_RESTORE_STATE + #ifdef CONFIG_AUDITSYSCALL .macro auditsys_entry_common movl %esi,%r9d /* 6th arg: 4th syscall arg */ @@ -226,7 +238,6 @@ sysexit_from_sys_call: .endm sysenter_auditsys: - CFI_RESTORE_STATE auditsys_entry_common movl %ebp,%r9d /* reload 6th syscall arg */ jmp sysenter_dispatch @@ -235,6 +246,11 @@ sysexit_audit: auditsys_exit sysexit_from_sys_call #endif +sysenter_fix_flags: + pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) + popfq_cfi + jmp sysenter_flags_fixed + sysenter_tracesys: #ifdef CONFIG_AUDITSYSCALL testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 5f12968..1717156 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -203,6 +203,7 @@ #define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */ #define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */ #define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */ +#define X86_FEATURE_VMMCALL (8*32+15) /* Prefer vmmcall to vmcall */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 50d033a..a94b82e 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -251,7 +251,8 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; } -#define _LDT_empty(info) \ +/* This intentionally ignores lm, since 32-bit apps don't have that field. */ +#define LDT_empty(info) \ ((info)->base_addr == 0 && \ (info)->limit == 0 && \ (info)->contents == 0 && \ @@ -261,11 +262,18 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) (info)->seg_not_present == 1 && \ (info)->useable == 0) -#ifdef CONFIG_X86_64 -#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0)) -#else -#define LDT_empty(info) (_LDT_empty(info)) -#endif +/* Lots of programs expect an all-zero user_desc to mean "no segment at all". */ +static inline bool LDT_zero(const struct user_desc *info) +{ + return (info->base_addr == 0 && + info->limit == 0 && + info->contents == 0 && + info->read_exec_only == 0 && + info->seg_32bit == 0 && + info->limit_in_pages == 0 && + info->seg_not_present == 0 && + info->useable == 0); +} static inline void clear_LDT(void) { diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 9c999c1..01f15b2 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -155,8 +155,9 @@ do { \ #define elf_check_arch(x) \ ((x)->e_machine == EM_X86_64) -#define compat_elf_check_arch(x) \ - (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64) +#define compat_elf_check_arch(x) \ + (elf_check_arch_ia32(x) || \ + (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) #if __USER32_DS != __USER_DS # error "The following code assumes __USER32_DS == __USER_DS" diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 7252cd3..6762a55 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -123,14 +123,14 @@ enum fixed_addresses { __end_of_permanent_fixed_addresses, /* - * 256 temporary boot-time mappings, used by early_ioremap(), + * 512 temporary boot-time mappings, used by early_ioremap(), * before ioremap() is functional. * - * If necessary we round it up to the next 256 pages boundary so + * If necessary we round it up to the next 512 pages boundary so * that we can have a single pgd entry and a single pte table: */ #define NR_FIX_BTMAPS 64 -#define FIX_BTMAPS_SLOTS 4 +#define FIX_BTMAPS_SLOTS 8 #define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS) FIX_BTMAP_END = (__end_of_permanent_fixed_addresses ^ diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index cea1c76..1ac1c00 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -368,7 +368,7 @@ static inline void drop_fpu(struct task_struct *tsk) preempt_disable(); tsk->thread.fpu_counter = 0; __drop_fpu(tsk); - clear_used_math(); + clear_stopped_child_used_math(tsk); preempt_enable(); } diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index 8e71c79..57995f0 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -50,6 +50,32 @@ #define BT_MBI_PCIE_READ 0x00 #define BT_MBI_PCIE_WRITE 0x01 +/* Quark available units */ +#define QRK_MBI_UNIT_HBA 0x00 +#define QRK_MBI_UNIT_HB 0x03 +#define QRK_MBI_UNIT_RMU 0x04 +#define QRK_MBI_UNIT_MM 0x05 +#define QRK_MBI_UNIT_MMESRAM 0x05 +#define QRK_MBI_UNIT_SOC 0x31 + +/* Quark read/write opcodes */ +#define QRK_MBI_HBA_READ 0x10 +#define QRK_MBI_HBA_WRITE 0x11 +#define QRK_MBI_HB_READ 0x10 +#define QRK_MBI_HB_WRITE 0x11 +#define QRK_MBI_RMU_READ 0x10 +#define QRK_MBI_RMU_WRITE 0x11 +#define QRK_MBI_MM_READ 0x10 +#define QRK_MBI_MM_WRITE 0x11 +#define QRK_MBI_MMESRAM_READ 0x12 +#define QRK_MBI_MMESRAM_WRITE 0x13 +#define QRK_MBI_SOC_READ 0x06 +#define QRK_MBI_SOC_WRITE 0x07 + +#if IS_ENABLED(CONFIG_IOSF_MBI) + +bool iosf_mbi_available(void); + /** * iosf_mbi_read() - MailBox Interface read command * @port: port indicating subunit being accessed @@ -87,4 +113,33 @@ int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr); */ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask); +#else /* CONFIG_IOSF_MBI is not enabled */ +static inline +bool iosf_mbi_available(void) +{ + return false; +} + +static inline +int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} +#endif /* CONFIG_IOSF_MBI */ + #endif /* IOSF_MBI_SYMS_H */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index bba3cf8..0a8b519 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void) #define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */ -#define INTERRUPT_RETURN iretq +#define INTERRUPT_RETURN jmp native_iret #define USERGS_SYSRET64 \ swapgs; \ sysretq; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3092300..ac03bd7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -99,7 +99,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) #define KVM_REFILL_PAGES 25 #define KVM_MAX_CPUID_ENTRIES 80 #define KVM_NR_FIXED_MTRR_REGION 88 -#define KVM_NR_VAR_MTRR 10 +#define KVM_NR_VAR_MTRR 8 #define ASYNC_PF_PER_VCPU 64 @@ -480,6 +480,7 @@ struct kvm_vcpu_arch { u64 mmio_gva; unsigned access; gfn_t mmio_gfn; + u64 mmio_gen; struct kvm_pmu pmu; @@ -570,7 +571,7 @@ struct kvm_arch { struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; - int vapics_in_nmi_mode; + atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; struct kvm_apic_map *apic_map; @@ -983,6 +984,20 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); } +static inline u64 get_canonical(u64 la) +{ + return ((int64_t)la << 16) >> 16; +} + +static inline bool is_noncanonical_address(u64 la) +{ +#ifdef CONFIG_X86_64 + return get_canonical(la) != la; +#else + return false; +#endif +} + #define TSS_IOPB_BASE_OFFSET 0x66 #define TSS_BASE_SIZE 0x68 #define TSS_IOPB_SIZE (65536 / 8) @@ -1041,7 +1056,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_define_shared_msr(unsigned index, u32 msr); -void kvm_set_shared_msr(unsigned index, u64 val, u64 mask); +int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index c7678e4..e62cf89 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -2,6 +2,7 @@ #define _ASM_X86_KVM_PARA_H #include +#include #include extern void kvmclock_init(void); @@ -16,10 +17,15 @@ static inline bool kvm_check_and_clear_guest_paused(void) } #endif /* CONFIG_KVM_GUEST */ -/* This instruction is vmcall. On non-VT architectures, it will generate a - * trap that we will then rewrite to the appropriate instruction. +#ifdef CONFIG_DEBUG_RODATA +#define KVM_HYPERCALL \ + ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL) +#else +/* On AMD processors, vmcall will generate a trap that we will + * then rewrite to the appropriate instruction. */ #define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1" +#endif /* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall * instruction. The hypervisor may replace it with something else but only the diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 1da25a5..3ba047c 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -30,6 +30,14 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) :: "a" (eax), "c" (ecx)); } +static inline void __sti_mwait(unsigned long eax, unsigned long ecx) +{ + trace_hardirqs_on(); + /* "mwait %eax, %ecx;" */ + asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" + :: "a" (eax), "c" (ecx)); +} + /* * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, * which can obviate IPI to trigger checking of need_resched. diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h index f48b17d..3a52ee0 100644 --- a/arch/x86/include/asm/page_32_types.h +++ b/arch/x86/include/asm/page_32_types.h @@ -20,7 +20,6 @@ #define THREAD_SIZE_ORDER 1 #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) -#define STACKFAULT_STACK 0 #define DOUBLEFAULT_STACK 1 #define NMI_STACK 0 #define DEBUG_STACK 0 diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 8de6d9c..d54d1ee 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -14,12 +14,11 @@ #define IRQ_STACK_ORDER 2 #define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER) -#define STACKFAULT_STACK 1 -#define DOUBLEFAULT_STACK 2 -#define NMI_STACK 3 -#define DEBUG_STACK 4 -#define MCE_STACK 5 -#define N_EXCEPTION_STACKS 5 /* hw limit: 7 */ +#define DOUBLEFAULT_STACK 1 +#define NMI_STACK 2 +#define DEBUG_STACK 3 +#define MCE_STACK 4 +#define N_EXCEPTION_STACKS 4 /* hw limit: 7 */ #define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) #define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index e22c1db..d869931 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -19,6 +19,7 @@ extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; +extern pte_t level1_fixmap_pgt[512]; extern pgd_t init_level4_pgt[]; #define swapper_pg_dir init_level4_pgt diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index c883bf7..7166e25 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -61,6 +61,8 @@ typedef struct { pteval_t pte; } pte_t; #define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) #define MODULES_END _AC(0xffffffffff000000, UL) #define MODULES_LEN (MODULES_END - MODULES_VADDR) +#define ESPFIX_PGD_ENTRY _AC(-2, UL) +#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT) #define EARLY_DYNAMIC_PAGE_TABLES 64 diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 6f1c3a8..bcc9a2f 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -212,10 +212,21 @@ #define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8) #ifdef __KERNEL__ + +/* + * early_idt_handler_array is an array of entry points referenced in the + * early IDT. For simplicity, it's a real array with one entry point + * every nine bytes. That leaves room for an optional 'push $0' if the + * vector has no error code (two bytes), a 'push $vector_number' (two + * bytes), and a jump to the common entry code (up to five bytes). + */ +#define EARLY_IDT_HANDLER_SIZE 9 + #ifndef __ASSEMBLY__ -extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5]; + +extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE]; #ifdef CONFIG_TRACING -#define trace_early_idt_handlers early_idt_handlers +# define trace_early_idt_handler_array early_idt_handler_array #endif /* diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index d62c9f8..75b14ca 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -65,6 +65,8 @@ static inline void x86_ce4100_early_setup(void) { } #ifndef _SETUP +#include + /* * This is set up by the setup-routine at boot-time */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index e1940c0..e870ea9 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -144,7 +144,7 @@ struct thread_info { /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ (_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME | \ - _TIF_USER_RETURN_NOTIFY) + _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE) /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 58d66fe..b409b17 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -39,6 +39,7 @@ asmlinkage void simd_coprocessor_error(void); #ifdef CONFIG_TRACING asmlinkage void trace_page_fault(void); +#define trace_stack_segment stack_segment #define trace_divide_error divide_error #define trace_bounds bounds #define trace_invalid_op invalid_op diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index 2a46ca7..2874be9 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -34,7 +34,7 @@ static inline unsigned int __getcpu(void) native_read_tscp(&p); } else { /* Load per CPU data from GDT */ - asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); + asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); } return p; diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h index 46727eb..6e1aaf7 100644 --- a/arch/x86/include/uapi/asm/ldt.h +++ b/arch/x86/include/uapi/asm/ldt.h @@ -28,6 +28,13 @@ struct user_desc { unsigned int seg_not_present:1; unsigned int useable:1; #ifdef __x86_64__ + /* + * Because this bit is not present in 32-bit user code, user + * programs can pass uninitialized values here. Therefore, in + * any context in which a user_desc comes from a 32-bit program, + * the kernel must act as though lm == 0, regardless of the + * actual value. + */ unsigned int lm:1; #endif }; diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 0e79420..990a2fe 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -67,6 +67,7 @@ #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_INVEPT 50 #define EXIT_REASON_PREEMPTION_TIMER 52 +#define EXIT_REASON_INVVPID 53 #define EXIT_REASON_WBINVD 54 #define EXIT_REASON_XSETBV 55 #define EXIT_REASON_APIC_WRITE 56 @@ -114,6 +115,7 @@ { EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \ { EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \ { EXIT_REASON_INVD, "INVD" }, \ + { EXIT_REASON_INVVPID, "INVVPID" }, \ { EXIT_REASON_INVPCID, "INVPCID" } #endif /* _UAPIVMX_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index cb648c8..56bac86 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-y += syscall_$(BITS).o obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 7f26c9a..523f147 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1290,7 +1290,7 @@ void setup_local_APIC(void) unsigned int value, queued; int i, j, acked = 0; unsigned long long tsc = 0, ntsc; - long long max_loops = cpu_khz; + long long max_loops = cpu_khz ? cpu_khz : 1000000; if (cpu_has_tsc) rdtscll(tsc); @@ -1387,7 +1387,7 @@ void setup_local_APIC(void) break; } if (queued) { - if (cpu_has_tsc) { + if (cpu_has_tsc && cpu_khz) { rdtscll(ntsc); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index c67ffa6..c005fdd 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -508,6 +508,13 @@ static void early_init_amd(struct cpuinfo_x86 *c) } #endif + /* + * This is only needed to tell the kernel whether to use VMCALL + * and VMMCALL. VMMCALL is never executed except under virt, so + * we can set it unconditionally. + */ + set_cpu_cap(c, X86_FEATURE_VMMCALL); + /* F16h erratum 793, CVE-2013-6885 */ if (c->x86 == 0x16 && c->x86_model <= 0xf) { u64 val; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8e28bf2..e6bddd5 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -144,6 +144,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); static int __init x86_xsave_setup(char *s) { + if (strlen(s)) + return 0; setup_clear_cpu_cap(X86_FEATURE_XSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); setup_clear_cpu_cap(X86_FEATURE_AVX); @@ -1141,7 +1143,7 @@ void syscall_init(void) /* Flags to clear on syscall */ wrmsrl(MSR_SYSCALL_MASK, X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF| - X86_EFLAGS_IOPL|X86_EFLAGS_AC); + X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } /* diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 5cd9bfa..66746a8 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -153,6 +153,21 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_ERMS); } } + + /* + * Intel Quark Core DevMan_001.pdf section 6.4.11 + * "The operating system also is required to invalidate (i.e., flush) + * the TLB when any changes are made to any of the page table entries. + * The operating system must reload CR3 to cause the TLB to be flushed" + * + * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should + * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE + * to be modified + */ + if (c->x86 == 5 && c->x86_model == 9) { + pr_info("Disabling PGE capability bit\n"); + setup_clear_cpu_cap(X86_FEATURE_PGE); + } } #ifdef CONFIG_X86_32 @@ -368,6 +383,13 @@ static void init_intel(struct cpuinfo_x86 *c) detect_extended_topology(c); l2 = init_intel_cacheinfo(c); + + /* Detect legacy cache sizes if init_intel_cacheinfo did not */ + if (l2 == 0) { + cpu_detect_cache_sizes(c); + l2 = c->x86_cache_size; + } + if (c->cpuid_level > 9) { unsigned eax = cpuid_eax(10); /* Check for version and the number of counters */ @@ -482,6 +504,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) */ if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0)) size = 256; + + /* + * Intel Quark SoC X1000 contains a 4-way set associative + * 16K cache with a 16 byte cache line and 256 lines per tag + */ + if ((c->x86 == 5) && (c->x86_model == 9)) + size = 16; return size; } #endif @@ -709,7 +738,8 @@ static const struct cpu_dev intel_cpu_dev = { [3] = "OverDrive PODP5V83", [4] = "Pentium MMX", [7] = "Mobile Pentium 75 - 200", - [8] = "Mobile Pentium MMX" + [8] = "Mobile Pentium MMX", + [9] = "Quark SoC X1000", } }, { .family = 6, .model_names = diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 617a9e2..b63773b 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -108,12 +108,13 @@ static size_t compute_container_size(u8 *data, u32 total_size) * load_microcode_amd() to save equivalent cpu table and microcode patches in * kernel heap memory. */ -static void apply_ucode_in_initrd(void *ucode, size_t size) +static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) { struct equiv_cpu_entry *eq; size_t *cont_sz; u32 *header; u8 *data, **cont; + u8 (*patch)[PATCH_MAX_SIZE]; u16 eq_id = 0; int offset, left; u32 rev, eax, ebx, ecx, edx; @@ -123,10 +124,12 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); cont_sz = (size_t *)__pa_nodebug(&container_size); cont = (u8 **)__pa_nodebug(&container); + patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); #else new_rev = &ucode_new_rev; cont_sz = &container_size; cont = &container; + patch = &amd_ucode_patch; #endif data = ucode; @@ -213,9 +216,9 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) rev = mc->hdr.patch_id; *new_rev = rev; - /* save ucode patch */ - memcpy(amd_ucode_patch, mc, - min_t(u32, header[1], PATCH_MAX_SIZE)); + if (save_patch) + memcpy(patch, mc, + min_t(u32, header[1], PATCH_MAX_SIZE)); } } @@ -246,7 +249,7 @@ void __init load_ucode_amd_bsp(void) *data = cp.data; *size = cp.size; - apply_ucode_in_initrd(cp.data, cp.size); + apply_ucode_in_initrd(cp.data, cp.size, true); } #ifdef CONFIG_X86_32 @@ -263,7 +266,7 @@ void load_ucode_amd_ap(void) size_t *usize; void **ucode; - mc = (struct microcode_amd *)__pa(amd_ucode_patch); + mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { __apply_microcode_amd(mc); return; @@ -275,7 +278,7 @@ void load_ucode_amd_ap(void) if (!*ucode || !*usize) return; - apply_ucode_in_initrd(*ucode, *usize); + apply_ucode_in_initrd(*ucode, *usize, false); } static void __init collect_cpu_sig_on_bsp(void *arg) @@ -339,7 +342,7 @@ void load_ucode_amd_ap(void) * AP has a different equivalence ID than BSP, looks like * mixed-steppings silicon so go through the ucode blob anew. */ - apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size); + apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false); } } #endif @@ -347,7 +350,9 @@ void load_ucode_amd_ap(void) int __init save_microcode_in_initrd_amd(void) { unsigned long cont; + int retval = 0; enum ucode_state ret; + u8 *cont_va; u32 eax; if (!container) @@ -355,13 +360,15 @@ int __init save_microcode_in_initrd_amd(void) #ifdef CONFIG_X86_32 get_bsp_sig(); - cont = (unsigned long)container; + cont = (unsigned long)container; + cont_va = __va(container); #else /* * We need the physical address of the container for both bitness since * boot_params.hdr.ramdisk_image is a physical address. */ - cont = __pa(container); + cont = __pa(container); + cont_va = container; #endif /* @@ -372,6 +379,8 @@ int __init save_microcode_in_initrd_amd(void) if (relocated_ramdisk) container = (u8 *)(__va(relocated_ramdisk) + (cont - boot_params.hdr.ramdisk_image)); + else + container = cont_va; if (ucode_new_rev) pr_info("microcode: updated early to new patch_level=0x%08x\n", @@ -382,7 +391,7 @@ int __init save_microcode_in_initrd_amd(void) ret = load_microcode_amd(eax, container, container_size); if (ret != UCODE_OK) - return -EINVAL; + retval = -EINVAL; /* * This will be freed any msec now, stash patches for the current @@ -391,5 +400,5 @@ int __init save_microcode_in_initrd_amd(void) container = NULL; container_size = 0; - return 0; + return retval; } diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c index 18f7391..43a07bf 100644 --- a/arch/x86/kernel/cpu/microcode/intel_early.c +++ b/arch/x86/kernel/cpu/microcode/intel_early.c @@ -321,7 +321,7 @@ get_matching_model_microcode(int cpu, unsigned long start, unsigned int mc_saved_count = mc_saved_data->mc_saved_count; int i; - while (leftover) { + while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) { mc_header = (struct microcode_header_intel *)ucode_ptr; mc_size = get_totalsize(mc_header); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 832d05a..317c811 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -67,6 +67,7 @@ static struct clocksource hyperv_cs = { .rating = 400, /* use this when running on Hyperv*/ .read = read_hv_clock, .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; static void __init ms_hyperv_init_platform(void) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 79f9f84..fb345c4 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -118,6 +118,9 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) continue; if (event->attr.config1 & ~er->valid_mask) return -EINVAL; + /* Check if the extra msrs can be safely accessed*/ + if (!er->extra_msr_access) + return -ENXIO; reg->idx = er->idx; reg->config = event->attr.config1; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 4972c24..7876c34 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -293,14 +293,16 @@ struct extra_reg { u64 config_mask; u64 valid_mask; int idx; /* per_xxx->regs[] reg index */ + bool extra_msr_access; }; #define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ - .event = (e), \ - .msr = (ms), \ - .config_mask = (m), \ - .valid_mask = (vm), \ - .idx = EXTRA_REG_##i, \ + .event = (e), \ + .msr = (ms), \ + .config_mask = (m), \ + .valid_mask = (vm), \ + .idx = EXTRA_REG_##i, \ + .extra_msr_access = true, \ } #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 1340ebf..d4c0a0e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2183,6 +2183,41 @@ static void intel_snb_check_microcode(void) } } +/* + * Under certain circumstances, access certain MSR may cause #GP. + * The function tests if the input MSR can be safely accessed. + */ +static bool check_msr(unsigned long msr, u64 mask) +{ + u64 val_old, val_new, val_tmp; + + /* + * Read the current value, change it and read it back to see if it + * matches, this is needed to detect certain hardware emulators + * (qemu/kvm) that don't trap on the MSR access and always return 0s. + */ + if (rdmsrl_safe(msr, &val_old)) + return false; + + /* + * Only change the bits which can be updated by wrmsrl. + */ + val_tmp = val_old ^ mask; + if (wrmsrl_safe(msr, val_tmp) || + rdmsrl_safe(msr, &val_new)) + return false; + + if (val_new != val_tmp) + return false; + + /* Here it's sure that the MSR can be safely accessed. + * Restore the old value and return. + */ + wrmsrl(msr, val_old); + + return true; +} + static __init void intel_sandybridge_quirk(void) { x86_pmu.check_microcode = intel_snb_check_microcode; @@ -2272,7 +2307,8 @@ __init int intel_pmu_init(void) union cpuid10_ebx ebx; struct event_constraint *c; unsigned int unused; - int version; + struct extra_reg *er; + int version, i; if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { switch (boot_cpu_data.x86) { @@ -2475,6 +2511,9 @@ __init int intel_pmu_init(void) case 62: /* IvyBridge EP */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + /* dTLB-load-misses on IVB is different than SNB */ + hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */ + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); @@ -2575,6 +2614,34 @@ __init int intel_pmu_init(void) } } + /* + * Access LBR MSR may cause #GP under certain circumstances. + * E.g. KVM doesn't support LBR MSR + * Check all LBT MSR here. + * Disable LBR access if any LBR MSRs can not be accessed. + */ + if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL)) + x86_pmu.lbr_nr = 0; + for (i = 0; i < x86_pmu.lbr_nr; i++) { + if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) && + check_msr(x86_pmu.lbr_to + i, 0xffffUL))) + x86_pmu.lbr_nr = 0; + } + + /* + * Access extra MSR may cause #GP under certain circumstances. + * E.g. KVM doesn't support offcore event + * Check all extra_regs here. + */ + if (x86_pmu.extra_regs) { + for (er = x86_pmu.extra_regs; er->msr; er++) { + er->extra_msr_access = check_msr(er->msr, 0x1ffUL); + /* Disable LBR select mapping */ + if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access) + x86_pmu.lbr_sel_map = NULL; + } + } + /* Support full width counters using alternative MSR range */ if (x86_pmu.intel_cap.full_width_write) { x86_pmu.max_period = x86_pmu.cntval_mask; diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 5ad35ad..95700e5 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -511,6 +511,7 @@ static int rapl_cpu_prepare(int cpu) struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); int phys_id = topology_physical_package_id(cpu); u64 ms; + u64 msr_rapl_power_unit_bits; if (pmu) return 0; @@ -518,6 +519,9 @@ static int rapl_cpu_prepare(int cpu) if (phys_id < 0) return -1; + if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits)) + return -1; + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); if (!pmu) return -1; @@ -531,8 +535,7 @@ static int rapl_cpu_prepare(int cpu) * * we cache in local PMU instance */ - rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit); - pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL; + pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; pmu->pmu = &rapl_pmu_class; /* @@ -649,7 +652,9 @@ static int __init rapl_pmu_init(void) get_online_cpus(); for_each_online_cpu(cpu) { - rapl_cpu_prepare(cpu); + ret = rapl_cpu_prepare(cpu); + if (ret) + goto out; rapl_cpu_init(cpu); } @@ -672,6 +677,7 @@ static int __init rapl_pmu_init(void) hweight32(rapl_cntr_mask), ktime_to_ms(pmu->timer_interval)); +out: put_online_cpus(); return 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 047f540..2f98588 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2886,6 +2886,17 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); } +/* + * Using uncore_pmu_event_init pmu event_init callback + * as a detection point for uncore events. + */ +static int uncore_pmu_event_init(struct perf_event *event); + +static bool is_uncore_event(struct perf_event *event) +{ + return event->pmu->event_init == uncore_pmu_event_init; +} + static int uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp) { @@ -2900,13 +2911,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b return -EINVAL; n = box->n_events; - box->event_list[n] = leader; - n++; + + if (is_uncore_event(leader)) { + box->event_list[n] = leader; + n++; + } + if (!dogrp) return n; list_for_each_entry(event, &leader->sibling_list, group_entry) { - if (event->state <= PERF_EVENT_STATE_OFF) + if (!is_uncore_event(event) || + event->state <= PERF_EVENT_STATE_OFF) continue; if (n >= max_count) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index addb207..66e274a 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -24,7 +24,6 @@ static char x86_stack_ids[][8] = { [ DEBUG_STACK-1 ] = "#DB", [ NMI_STACK-1 ] = "NMI", [ DOUBLEFAULT_STACK-1 ] = "#DF", - [ STACKFAULT_STACK-1 ] = "#SS", [ MCE_STACK-1 ] = "#MC", #if DEBUG_STKSZ > EXCEPTION_STKSZ [ N_EXCEPTION_STACKS ... diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 6491353..c5a9cb9 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -433,8 +433,8 @@ sysenter_do_call: cmpl $(NR_syscalls), %eax jae sysenter_badsys call *sys_call_table(,%eax,4) - movl %eax,PT_EAX(%esp) sysenter_after_call: + movl %eax,PT_EAX(%esp) LOCKDEP_SYS_EXIT DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF @@ -514,6 +514,7 @@ ENTRY(system_call) jae syscall_badsys syscall_call: call *sys_call_table(,%eax,4) +syscall_after_call: movl %eax,PT_EAX(%esp) # store the return value syscall_exit: LOCKDEP_SYS_EXIT @@ -528,6 +529,7 @@ syscall_exit: restore_all: TRACE_IRQS_IRET restore_all_notrace: +#ifdef CONFIG_X86_ESPFIX32 movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS # Warning: PT_OLDSS(%esp) contains the wrong/random values if we # are returning to the kernel. @@ -538,6 +540,7 @@ restore_all_notrace: cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax CFI_REMEMBER_STATE je ldt_ss # returning to user-space with LDT SS +#endif restore_nocheck: RESTORE_REGS 4 # skip orig_eax/error_code irq_return: @@ -550,6 +553,7 @@ ENTRY(iret_exc) .previous _ASM_EXTABLE(irq_return,iret_exc) +#ifdef CONFIG_X86_ESPFIX32 CFI_RESTORE_STATE ldt_ss: #ifdef CONFIG_PARAVIRT @@ -593,6 +597,7 @@ ldt_ss: lss (%esp), %esp /* switch to espfix segment */ CFI_ADJUST_CFA_OFFSET -8 jmp restore_nocheck +#endif CFI_ENDPROC ENDPROC(system_call) @@ -683,12 +688,12 @@ syscall_fault: END(syscall_fault) syscall_badsys: - movl $-ENOSYS,PT_EAX(%esp) - jmp syscall_exit + movl $-ENOSYS,%eax + jmp syscall_after_call END(syscall_badsys) sysenter_badsys: - movl $-ENOSYS,PT_EAX(%esp) + movl $-ENOSYS,%eax jmp sysenter_after_call END(syscall_badsys) CFI_ENDPROC @@ -705,6 +710,7 @@ END(syscall_badsys) * the high word of the segment base from the GDT and swiches to the * normal stack and adjusts ESP with the matching offset. */ +#ifdef CONFIG_X86_ESPFIX32 /* fixup the stack */ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ @@ -714,8 +720,10 @@ END(syscall_badsys) pushl_cfi %eax lss (%esp), %esp /* switch to the normal stack segment */ CFI_ADJUST_CFA_OFFSET -8 +#endif .endm .macro UNWIND_ESPFIX_STACK +#ifdef CONFIG_X86_ESPFIX32 movl %ss, %eax /* see if on espfix stack */ cmpw $__ESPFIX_SS, %ax @@ -726,6 +734,7 @@ END(syscall_badsys) /* switch to normal stack */ FIXUP_ESPFIX_STACK 27: +#endif .endm /* @@ -1356,11 +1365,13 @@ END(debug) ENTRY(nmi) RING0_INT_FRAME ASM_CLAC +#ifdef CONFIG_X86_ESPFIX32 pushl_cfi %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax popl_cfi %eax je nmi_espfix_stack +#endif cmpl $ia32_sysenter_target,(%esp) je nmi_stack_fixup pushl_cfi %eax @@ -1400,6 +1411,7 @@ nmi_debug_stack_check: FIX_STACK 24, nmi_stack_correct, 1 jmp nmi_stack_correct +#ifdef CONFIG_X86_ESPFIX32 nmi_espfix_stack: /* We have a RING0_INT_FRAME here. * @@ -1421,6 +1433,7 @@ nmi_espfix_stack: lss 12+4(%esp), %esp # back to espfix stack CFI_ADJUST_CFA_OFFSET -24 jmp irq_return +#endif CFI_ENDPROC END(nmi) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 1e96c36..06469ee 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -58,6 +58,7 @@ #include #include #include +#include #include /* Avoid __ASSEMBLER__'ifying just for this. */ @@ -541,11 +542,14 @@ ENTRY(ret_from_fork) testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread? jz 1f - testl $_TIF_IA32, TI_flags(%rcx) # 32-bit compat task needs IRET - jnz int_ret_from_sys_call - - RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET - jmp ret_from_sys_call # go to the SYSRET fastpath + /* + * By the time we get here, we have no idea whether our pt_regs, + * ti flags, and ti status came from the 64-bit SYSCALL fast path, + * the slow path, or one of the ia32entry paths. + * Use int_ret_from_sys_call to return, since it can safely handle + * all of the above. + */ + jmp int_ret_from_sys_call 1: subq $REST_SKIP, %rsp # leave space for volatiles @@ -1041,32 +1045,52 @@ restore_args: irq_return: INTERRUPT_RETURN - _ASM_EXTABLE(irq_return, bad_iret) -#ifdef CONFIG_PARAVIRT ENTRY(native_iret) - iretq - _ASM_EXTABLE(native_iret, bad_iret) + /* + * Are we returning to a stack segment from the LDT? Note: in + * 64-bit mode SS:RSP on the exception stack is always valid. + */ +#ifdef CONFIG_X86_ESPFIX64 + testb $4,(SS-RIP)(%rsp) + jnz native_irq_return_ldt #endif - .section .fixup,"ax" -bad_iret: +.global native_irq_return_iret +native_irq_return_iret: /* - * The iret traps when the %cs or %ss being restored is bogus. - * We've lost the original trap vector and error code. - * #GPF is the most likely one to get for an invalid selector. - * So pretend we completed the iret and took the #GPF in user mode. - * - * We are now running with the kernel GS after exception recovery. - * But error_entry expects us to have user GS to match the user %cs, - * so swap back. + * This may fault. Non-paranoid faults on return to userspace are + * handled by fixup_bad_iret. These include #SS, #GP, and #NP. + * Double-faults due to espfix64 are handled in do_double_fault. + * Other faults here are fatal. */ - pushq $0 + iretq +#ifdef CONFIG_X86_ESPFIX64 +native_irq_return_ldt: + pushq_cfi %rax + pushq_cfi %rdi SWAPGS - jmp general_protection - - .previous + movq PER_CPU_VAR(espfix_waddr),%rdi + movq %rax,(0*8)(%rdi) /* RAX */ + movq (2*8)(%rsp),%rax /* RIP */ + movq %rax,(1*8)(%rdi) + movq (3*8)(%rsp),%rax /* CS */ + movq %rax,(2*8)(%rdi) + movq (4*8)(%rsp),%rax /* RFLAGS */ + movq %rax,(3*8)(%rdi) + movq (6*8)(%rsp),%rax /* SS */ + movq %rax,(5*8)(%rdi) + movq (5*8)(%rsp),%rax /* RSP */ + movq %rax,(4*8)(%rdi) + andl $0xffff0000,%eax + popq_cfi %rdi + orq PER_CPU_VAR(espfix_stack),%rax + SWAPGS + movq %rax,%rsp + popq_cfi %rax + jmp native_irq_return_iret +#endif /* edi: workmask, edx: work */ retint_careful: @@ -1110,9 +1134,9 @@ ENTRY(retint_kernel) call preempt_schedule_irq jmp exit_intr #endif - CFI_ENDPROC END(common_interrupt) + /* * End of kprobes section */ @@ -1484,7 +1508,7 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ paranoidzeroentry_ist debug do_debug DEBUG_STACK paranoidzeroentry_ist int3 do_int3 DEBUG_STACK -paranoiderrorentry stack_segment do_stack_segment +errorentry stack_segment do_stack_segment #ifdef CONFIG_XEN zeroentry xen_debug do_debug zeroentry xen_int3 do_int3 @@ -1594,16 +1618,15 @@ error_sti: /* * There are two places in the kernel that can potentially fault with - * usergs. Handle them here. The exception handlers after iret run with - * kernel gs again, so don't set the user space flag. B stepping K8s - * sometimes report an truncated RIP for IRET exceptions returning to - * compat mode. Check for these here too. + * usergs. Handle them here. B stepping K8s sometimes report a + * truncated RIP for IRET exceptions returning to compat mode. Check + * for these here too. */ error_kernelspace: incl %ebx - leaq irq_return(%rip),%rcx + leaq native_irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) - je error_swapgs + je error_bad_iret movl %ecx,%eax /* zero extend */ cmpq %rax,RIP+8(%rsp) je bstep_iret @@ -1614,7 +1637,15 @@ error_kernelspace: bstep_iret: /* Fix truncated RIP */ movq %rcx,RIP+8(%rsp) - jmp error_swapgs + /* fall through */ + +error_bad_iret: + SWAPGS + mov %rsp,%rdi + call fixup_bad_iret + mov %rax,%rsp + decl %ebx /* Return to usergs */ + jmp error_sti CFI_ENDPROC END(error_entry) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 85126cc..5fc4ac7 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -162,7 +162,7 @@ asmlinkage void __init x86_64_start_kernel(char * real_mode_data) clear_bss(); for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) - set_intr_gate(i, early_idt_handlers[i]); + set_intr_gate(i, early_idt_handler_array[i]); load_idt((const struct desc_ptr *)&idt_descr); copy_bootdata(__va(real_mode_data)); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index f36bd42..30a2aa3 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -477,21 +477,22 @@ is486: __INIT setup_once: /* - * Set up a idt with 256 entries pointing to ignore_int, - * interrupt gates. It doesn't actually load idt - that needs - * to be done on each CPU. Interrupts are enabled elsewhere, - * when we can be relatively sure everything is ok. + * Set up a idt with 256 interrupt gates that push zero if there + * is no error code and then jump to early_idt_handler_common. + * It doesn't actually load the idt - that needs to be done on + * each CPU. Interrupts are enabled elsewhere, when we can be + * relatively sure everything is ok. */ movl $idt_table,%edi - movl $early_idt_handlers,%eax + movl $early_idt_handler_array,%eax movl $NUM_EXCEPTION_VECTORS,%ecx 1: movl %eax,(%edi) movl %eax,4(%edi) /* interrupt gate, dpl=0, present */ movl $(0x8E000000 + __KERNEL_CS),2(%edi) - addl $9,%eax + addl $EARLY_IDT_HANDLER_SIZE,%eax addl $8,%edi loop 1b @@ -523,26 +524,28 @@ setup_once: andl $0,setup_once_ref /* Once is enough, thanks */ ret -ENTRY(early_idt_handlers) +ENTRY(early_idt_handler_array) # 36(%esp) %eflags # 32(%esp) %cs # 28(%esp) %eip # 24(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .if (EXCEPTION_ERRCODE_MASK >> i) & 1 - ASM_NOP2 - .else + .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 pushl $0 # Dummy error code, to make stack frame uniform .endif pushl $i # 20(%esp) Vector number - jmp early_idt_handler + jmp early_idt_handler_common i = i + 1 + .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr -ENDPROC(early_idt_handlers) +ENDPROC(early_idt_handler_array) - /* This is global to keep gas from relaxing the jumps */ -ENTRY(early_idt_handler) +early_idt_handler_common: + /* + * The stack is the hardware frame, an error code or zero, and the + * vector number. + */ cld cmpl $2,(%esp) # X86_TRAP_NMI @@ -602,7 +605,7 @@ ex_entry: is_nmi: addl $8,%esp /* drop vector number and error code */ iret -ENDPROC(early_idt_handler) +ENDPROC(early_idt_handler_common) /* This is the default interrupt "handler" :-) */ ALIGN diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index a468c0a..a2dc0ad 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -321,26 +321,28 @@ bad_address: jmp bad_address __INIT - .globl early_idt_handlers -early_idt_handlers: +ENTRY(early_idt_handler_array) # 104(%rsp) %rflags # 96(%rsp) %cs # 88(%rsp) %rip # 80(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .if (EXCEPTION_ERRCODE_MASK >> i) & 1 - ASM_NOP2 - .else + .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 pushq $0 # Dummy error code, to make stack frame uniform .endif pushq $i # 72(%rsp) Vector number - jmp early_idt_handler + jmp early_idt_handler_common i = i + 1 + .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr +ENDPROC(early_idt_handler_array) -/* This is global to keep gas from relaxing the jumps */ -ENTRY(early_idt_handler) +early_idt_handler_common: + /* + * The stack is the hardware frame, an error code or zero, and the + * vector number. + */ cld cmpl $2,(%rsp) # X86_TRAP_NMI @@ -412,7 +414,7 @@ ENTRY(early_idt_handler) is_nmi: addq $16,%rsp # drop vector number and error code INTERRUPT_RETURN -ENDPROC(early_idt_handler) +ENDPROC(early_idt_handler_common) __INITDATA diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c index c3aae66..2e97b3c 100644 --- a/arch/x86/kernel/iosf_mbi.c +++ b/arch/x86/kernel/iosf_mbi.c @@ -25,6 +25,10 @@ #include +#define PCI_DEVICE_ID_BAYTRAIL 0x0F00 +#define PCI_DEVICE_ID_BRASWELL 0x2280 +#define PCI_DEVICE_ID_QUARK_X1000 0x0958 + static DEFINE_SPINLOCK(iosf_mbi_lock); static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset) @@ -177,6 +181,13 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) } EXPORT_SYMBOL(iosf_mbi_modify); +bool iosf_mbi_available(void) +{ + /* Mbi isn't hot-pluggable. No remove routine is provided */ + return mbi_pdev; +} +EXPORT_SYMBOL(iosf_mbi_available); + static int iosf_mbi_probe(struct pci_dev *pdev, const struct pci_device_id *unused) { @@ -193,7 +204,9 @@ static int iosf_mbi_probe(struct pci_dev *pdev, } static DEFINE_PCI_DEVICE_TABLE(iosf_mbi_pci_ids) = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0F00) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) }, { 0, }, }; MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 79a3f96..490fee1 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -326,13 +326,16 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src) { struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; + int length; kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src)); insn_get_length(&insn); + length = insn.length; + /* Another subsystem puts a breakpoint, failed to recover */ if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) return 0; - memcpy(dest, insn.kaddr, insn.length); + memcpy(dest, insn.kaddr, length); #ifdef CONFIG_X86_64 if (insn_rip_relative(&insn)) { @@ -362,7 +365,7 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src) *(s32 *) disp = (s32) newdisp; } #endif - return insn.length; + return length; } static int __kprobes arch_copy_kprobe(struct kprobe *p) @@ -1017,6 +1020,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) regs->flags &= ~X86_EFLAGS_IF; trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); + + /* + * jprobes use jprobe_return() which skips the normal return + * path of the function, and this messes up the accounting of the + * function graph tracer to get messed up. + * + * Pause function graph tracing while performing the jprobe function. + */ + pause_graph_tracing(); return 1; } @@ -1042,24 +1054,25 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); u8 *addr = (u8 *) (regs->ip - 1); struct jprobe *jp = container_of(p, struct jprobe, kp); + void *saved_sp = kcb->jprobe_saved_sp; if ((addr > (u8 *) jprobe_return) && (addr < (u8 *) jprobe_return_end)) { - if (stack_addr(regs) != kcb->jprobe_saved_sp) { + if (stack_addr(regs) != saved_sp) { struct pt_regs *saved_regs = &kcb->jprobe_saved_regs; printk(KERN_ERR "current sp %p does not match saved sp %p\n", - stack_addr(regs), kcb->jprobe_saved_sp); + stack_addr(regs), saved_sp); printk(KERN_ERR "Saved registers for jprobe %p\n", jp); show_regs(saved_regs); printk(KERN_ERR "Current registers\n"); show_regs(regs); BUG(); } + /* It's OK to start function graph tracing again */ + unpause_graph_tracing(); *regs = kcb->jprobe_saved_regs; - memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp), - kcb->jprobes_stack, - MIN_STACK_SIZE(kcb->jprobe_saved_sp)); + memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp)); preempt_enable_no_resched(); return 1; } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 713f1b3..0b1e1d5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -280,7 +280,14 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) static void __init paravirt_ops_setup(void) { pv_info.name = "KVM"; - pv_info.paravirt_enabled = 1; + + /* + * KVM isn't paravirt in the sense of paravirt_enabled. A KVM + * guest kernel works like a bare metal kernel with additional + * features, and paravirt_enabled is about features that are + * missing. + */ + pv_info.paravirt_enabled = 0; if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY)) pv_cpu_ops.io_delay = kvm_io_delay; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index e604109..c8e98cd 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -263,7 +263,6 @@ void __init kvmclock_init(void) #endif kvm_get_preset_lpj(); clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); - pv_info.paravirt_enabled = 1; pv_info.name = "KVM"; if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index dcbbaa1..c37886d 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -20,8 +20,6 @@ #include #include -int sysctl_ldt16 = 0; - #ifdef CONFIG_SMP static void flush_ldt(void *current_mm) { @@ -231,16 +229,10 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } } - /* - * On x86-64 we do not support 16-bit segments due to - * IRET leaking the high bits of the kernel stack address. - */ -#ifdef CONFIG_X86_64 - if (!ldt_info.seg_32bit && !sysctl_ldt16) { + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { error = -EINVAL; goto out_unlock; } -#endif fill_ldt(&ldt, &ldt_info); if (oldmode) diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 3f08f34..a1da673 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli"); DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq"); DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); -DEF_NATIVE(pv_cpu_ops, iret, "iretq"); DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); @@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, iret); PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 3fb8d95..1a1ff42 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -28,6 +28,7 @@ #include #include #include +#include /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -398,6 +399,52 @@ static void amd_e400_idle(void) default_idle(); } +/* + * Intel Core2 and older machines prefer MWAIT over HALT for C1. + * We can't rely on cpuidle installing MWAIT, because it will not load + * on systems that support only C1 -- so the boot default must be MWAIT. + * + * Some AMD machines are the opposite, they depend on using HALT. + * + * So for default C1, which is used during boot until cpuidle loads, + * use MWAIT-C1 on Intel HW that has it, else use HALT. + */ +static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) +{ + if (c->x86_vendor != X86_VENDOR_INTEL) + return 0; + + if (!cpu_has(c, X86_FEATURE_MWAIT)) + return 0; + + return 1; +} + +/* + * MONITOR/MWAIT with no hints, used for default default C1 state. + * This invokes MWAIT with interrutps enabled and no flags, + * which is backwards compatible with the original MWAIT implementation. + */ + +static void mwait_idle(void) +{ + if (!current_set_polling_and_test()) { + if (static_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) { + mb(); + clflush((void *)¤t_thread_info()->flags); + mb(); + } + + __monitor((void *)¤t_thread_info()->flags, 0, 0); + if (!need_resched()) + __sti_mwait(0, 0); + else + local_irq_enable(); + } else + local_irq_enable(); + current_clr_polling(); +} + void select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP @@ -411,6 +458,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c) /* E400: APIC timer interrupt does not wake up CPU from C1e */ pr_info("using AMD E400 aware idle routine\n"); x86_idle = amd_e400_idle; + } else if (prefer_mwait_c1_over_halt(c)) { + pr_info("using mwait in idle threads\n"); + x86_idle = mwait_idle; } else x86_idle = default_idle; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 9c0280f..e2d26ce 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -286,24 +286,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) fpu = switch_fpu_prepare(prev_p, next_p, cpu); - /* - * Reload esp0, LDT and the page table pointer: - */ + /* Reload esp0 and ss1. */ load_sp0(tss, next); - /* - * Switch DS and ES. - * This won't pick up thread selector changes, but I guess that is ok. - */ - savesegment(es, prev->es); - if (unlikely(next->es | prev->es)) - loadsegment(es, next->es); - - savesegment(ds, prev->ds); - if (unlikely(next->ds | prev->ds)) - loadsegment(ds, next->ds); - - /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). * @@ -312,41 +297,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) savesegment(fs, fsindex); savesegment(gs, gsindex); + /* + * Load TLS before restoring any segments so that segment loads + * reference the correct GDT entries. + */ load_TLS(next, cpu); /* - * Leave lazy mode, flushing any hypercalls made here. - * This must be done before restoring TLS segments so - * the GDT and LDT are properly updated, and must be - * done before math_state_restore, so the TS bit is up - * to date. + * Leave lazy mode, flushing any hypercalls made here. This + * must be done after loading TLS entries in the GDT but before + * loading segments that might reference them, and and it must + * be done before math_state_restore, so the TS bit is up to + * date. */ arch_end_context_switch(next_p); + /* Switch DS and ES. + * + * Reading them only returns the selectors, but writing them (if + * nonzero) loads the full descriptor from the GDT or LDT. The + * LDT for next is loaded in switch_mm, and the GDT is loaded + * above. + * + * We therefore need to write new values to the segment + * registers on every context switch unless both the new and old + * values are zero. + * + * Note that we don't need to do anything for CS and SS, as + * those are saved and restored as part of pt_regs. + */ + savesegment(es, prev->es); + if (unlikely(next->es | prev->es)) + loadsegment(es, next->es); + + savesegment(ds, prev->ds); + if (unlikely(next->ds | prev->ds)) + loadsegment(ds, next->ds); + /* * Switch FS and GS. * - * Segment register != 0 always requires a reload. Also - * reload when it has changed. When prev process used 64bit - * base always reload to avoid an information leak. + * These are even more complicated than FS and GS: they have + * 64-bit bases are that controlled by arch_prctl. Those bases + * only differ from the values in the GDT or LDT if the selector + * is 0. + * + * Loading the segment register resets the hidden base part of + * the register to 0 or the value from the GDT / LDT. If the + * next base address zero, writing 0 to the segment register is + * much faster than using wrmsr to explicitly zero the base. + * + * The thread_struct.fs and thread_struct.gs values are 0 + * if the fs and gs bases respectively are not overridden + * from the values implied by fsindex and gsindex. They + * are nonzero, and store the nonzero base addresses, if + * the bases are overridden. + * + * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should + * be impossible. + * + * Therefore we need to reload the segment registers if either + * the old or new selector is nonzero, and we need to override + * the base address if next thread expects it to be overridden. + * + * This code is unnecessarily slow in the case where the old and + * new indexes are zero and the new base is nonzero -- it will + * unnecessarily write 0 to the selector before writing the new + * base address. + * + * Note: This all depends on arch_prctl being the only way that + * user code can override the segment base. Once wrfsbase and + * wrgsbase are enabled, most of this code will need to change. */ if (unlikely(fsindex | next->fsindex | prev->fs)) { loadsegment(fs, next->fsindex); + /* - * Check if the user used a selector != 0; if yes - * clear 64bit base, since overloaded base is always - * mapped to the Null selector + * If user code wrote a nonzero value to FS, then it also + * cleared the overridden base address. + * + * XXX: if user code wrote 0 to FS and cleared the base + * address itself, we won't notice and we'll incorrectly + * restore the prior base address next time we reschdule + * the process. */ if (fsindex) prev->fs = 0; } - /* when next process has a 64bit base use it */ if (next->fs) wrmsrl(MSR_FS_BASE, next->fs); prev->fsindex = fsindex; if (unlikely(gsindex | next->gsindex | prev->gs)) { load_gs_index(next->gsindex); + + /* This works (and fails) the same way as fsindex above. */ if (gsindex) prev->gs = 0; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 7461f50..0686fe3 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1441,15 +1441,6 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, force_sig_info(SIGTRAP, &info, tsk); } - -#ifdef CONFIG_X86_32 -# define IS_IA32 1 -#elif defined CONFIG_IA32_EMULATION -# define IS_IA32 is_compat_task() -#else -# define IS_IA32 0 -#endif - /* * We must return the syscall number to actually look up in the table. * This can be -1L to skip running any syscall at all. @@ -1487,7 +1478,7 @@ long syscall_trace_enter(struct pt_regs *regs) if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); - if (IS_IA32) + if (is_ia32_task()) audit_syscall_entry(AUDIT_ARCH_I386, regs->orig_ax, regs->bx, regs->cx, diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index c752cb4..a6aa91f 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -181,6 +181,16 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { }, }, + /* ASRock */ + { /* Handle problems with rebooting on ASRock Q1900DC-ITX */ + .callback = set_pci_reboot, + .ident = "ASRock Q1900DC-ITX", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASRock"), + DMI_MATCH(DMI_BOARD_NAME, "Q1900DC-ITX"), + }, + }, + /* ASUS */ { /* Handle problems with rebooting on ASUS P4S800 */ .callback = set_bios_reboot, diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index 2a26819..80eab01 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail) void arch_remove_reservations(struct resource *avail) { - /* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */ + /* + * Trim out BIOS area (high 2MB) and E820 regions. We do not remove + * the low 1MB unconditionally, as this area is needed for some ISA + * cards requiring a memory range, e.g. the i82365 PCMCIA controller. + */ if (avail->flags & IORESOURCE_MEM) { - if (avail->start < BIOS_END) - avail->start = BIOS_END; resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END); remove_e820_regions(avail); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 9e5de68..b88fc86 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -673,6 +673,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * handler too. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); + /* + * Ensure the signal handler starts with the new fpu state. + */ + if (used_math()) + drop_init_fpu(current); } signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index a32da80..6828765 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -243,6 +243,13 @@ static void notrace start_secondary(void *unused) check_tsc_sync_target(); /* + * Enable the espfix hack for this CPU + */ +#ifdef CONFIG_X86_ESPFIX64 + init_espfix_ap(); +#endif + + /* * We need to hold vector_lock so there the set of online cpus * does not change while we are assigning vectors to cpus. Holding * this lock ensures we don't half assign or remove an irq from a cpu. @@ -1280,6 +1287,9 @@ static void remove_siblinginfo(int cpu) for_each_cpu(sibling, cpu_sibling_mask(cpu)) cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) + cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); + cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(cpu_sibling_mask(cpu)); cpumask_clear(cpu_core_mask(cpu)); c->phys_proc_id = 0; diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index f7fec09..7fc5e84 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -27,6 +27,58 @@ static int get_free_idx(void) return -ESRCH; } +static bool tls_desc_okay(const struct user_desc *info) +{ + /* + * For historical reasons (i.e. no one ever documented how any + * of the segmentation APIs work), user programs can and do + * assume that a struct user_desc that's all zeros except for + * entry_number means "no segment at all". This never actually + * worked. In fact, up to Linux 3.19, a struct user_desc like + * this would create a 16-bit read-write segment with base and + * limit both equal to zero. + * + * That was close enough to "no segment at all" until we + * hardened this function to disallow 16-bit TLS segments. Fix + * it up by interpreting these zeroed segments the way that they + * were almost certainly intended to be interpreted. + * + * The correct way to ask for "no segment at all" is to specify + * a user_desc that satisfies LDT_empty. To keep everything + * working, we accept both. + * + * Note that there's a similar kludge in modify_ldt -- look at + * the distinction between modes 1 and 0x11. + */ + if (LDT_empty(info) || LDT_zero(info)) + return true; + + /* + * espfix is required for 16-bit data segments, but espfix + * only works for LDT segments. + */ + if (!info->seg_32bit) + return false; + + /* Only allow data segments in the TLS array. */ + if (info->contents > 1) + return false; + + /* + * Non-present segments with DPL 3 present an interesting attack + * surface. The kernel should handle such segments correctly, + * but TLS is very difficult to protect in a sandbox, so prevent + * such segments from being created. + * + * If userspace needs to remove a TLS entry, it can still delete + * it outright. + */ + if (info->seg_not_present) + return false; + + return true; +} + static void set_tls_desc(struct task_struct *p, int idx, const struct user_desc *info, int n) { @@ -40,7 +92,7 @@ static void set_tls_desc(struct task_struct *p, int idx, cpu = get_cpu(); while (n-- > 0) { - if (LDT_empty(info)) + if (LDT_empty(info) || LDT_zero(info)) desc->a = desc->b = 0; else fill_ldt(desc, info); @@ -66,6 +118,9 @@ int do_set_thread_area(struct task_struct *p, int idx, if (copy_from_user(&info, u_info, sizeof(info))) return -EFAULT; + if (!tls_desc_okay(&info)) + return -EINVAL; + if (idx == -1) idx = info.entry_number; @@ -192,6 +247,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, { struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES]; const struct user_desc *info; + int i; if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || @@ -205,6 +261,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, else info = infobuf; + for (i = 0; i < count / sizeof(struct user_desc); i++) + if (!tls_desc_okay(info + i)) + return -EINVAL; + set_tls_desc(target, GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)), info, count / sizeof(struct user_desc)); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 57409f6..b1d9002 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -218,32 +218,40 @@ DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL DO_ERROR (X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun ) DO_ERROR (X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS ) DO_ERROR (X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present ) -#ifdef CONFIG_X86_32 DO_ERROR (X86_TRAP_SS, SIGBUS, "stack segment", stack_segment ) -#endif DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0 ) #ifdef CONFIG_X86_64 /* Runs on IST stack */ -dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) -{ - enum ctx_state prev_state; - - prev_state = exception_enter(); - if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { - preempt_conditional_sti(regs); - do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); - preempt_conditional_cli(regs); - } - exception_exit(prev_state); -} - dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) { static const char str[] = "double fault"; struct task_struct *tsk = current; +#ifdef CONFIG_X86_ESPFIX64 + extern unsigned char native_irq_return_iret[]; + + /* + * If IRET takes a non-IST fault on the espfix64 stack, then we + * end up promoting it to a doublefault. In that case, modify + * the stack to make it look like we just entered the #GP + * handler from user space, similar to bad_iret. + */ + if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY && + regs->cs == __KERNEL_CS && + regs->ip == (unsigned long)native_irq_return_iret) + { + struct pt_regs *normal_regs = task_pt_regs(current); + + /* Fake a #GP(0) from userspace. */ + memmove(&normal_regs->ip, (void *)regs->sp, 5*8); + normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */ + regs->ip = (unsigned long)general_protection; + regs->sp = (unsigned long)&normal_regs->orig_ax; + return; + } +#endif + exception_enter(); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -357,7 +365,7 @@ exit: * for scheduling or signal handling. The actual stack switch is done in * entry.S */ -asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) +asmlinkage notrace __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) { struct pt_regs *regs = eregs; /* Did already sync */ @@ -376,6 +384,35 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) *regs = *eregs; return regs; } + +struct bad_iret_stack { + void *error_entry_ret; + struct pt_regs regs; +}; + +asmlinkage __visible notrace __kprobes +struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) +{ + /* + * This is called from entry_64.S early in handling a fault + * caused by a bad iret to user mode. To handle the fault + * correctly, we want move our stack frame to task_pt_regs + * and we want to pretend that the exception came from the + * iret target. + */ + struct bad_iret_stack *new_stack = + container_of(task_pt_regs(current), + struct bad_iret_stack, regs); + + /* Copy the IRET target to the new stack. */ + memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); + + /* Copy the remainder of the stack from the current stack. */ + memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip)); + + BUG_ON(!user_mode_vm(&new_stack->regs)); + return new_stack; +} #endif /* @@ -748,7 +785,7 @@ void __init trap_init(void) set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun); set_intr_gate(X86_TRAP_TS, invalid_TSS); set_intr_gate(X86_TRAP_NP, segment_not_present); - set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK); + set_intr_gate(X86_TRAP_SS, stack_segment); set_intr_gate(X86_TRAP_GP, general_protection); set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug); set_intr_gate(X86_TRAP_MF, coprocessor_error); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index e0d1d7a..b20bced 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -618,7 +618,7 @@ static unsigned long quick_pit_calibrate(void) goto success; } } - pr_err("Fast TSC calibration failed\n"); + pr_info("Fast TSC calibration failed\n"); return 0; success: @@ -1173,14 +1173,17 @@ void __init tsc_init(void) x86_init.timers.tsc_pre_init(); - if (!cpu_has_tsc) + if (!cpu_has_tsc) { + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; + } tsc_khz = x86_platform.calibrate_tsc(); cpu_khz = tsc_khz; if (!tsc_khz) { mark_tsc_unstable("could not calculate TSC khz"); + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 1f96f93..09ce23a 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -125,10 +125,10 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, if (!show_unhandled_signals) return; - pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", - level, current->comm, task_pid_nr(current), - message, regs->ip, regs->cs, - regs->sp, regs->ax, regs->si, regs->di); + printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", + level, current->comm, task_pid_nr(current), + message, regs->ip, regs->cs, + regs->sp, regs->ax, regs->si, regs->di); } static int addr_to_vsyscall_nr(unsigned long addr) diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index a4b451c..7a09aca 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -268,8 +268,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) return -1; - drop_init_fpu(tsk); /* trigger finit */ - return 0; } @@ -377,7 +375,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) * thread's fpu state, reconstruct fxstate from the fsave * header. Sanitize the copied state etc. */ - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; int err = 0; @@ -391,16 +389,20 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) */ drop_fpu(tsk); - if (__copy_from_user(xsave, buf_fx, state_size) || + if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) || __copy_from_user(&env, buf, sizeof(env))) { + fpu_finit(fpu); err = -1; } else { sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only); - set_used_math(); } - if (use_eager_fpu()) + set_used_math(); + if (use_eager_fpu()) { + preempt_disable(); math_state_restore(); + preempt_enable(); + } return err; } else { diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 07ffca0..cf1eeea 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -498,11 +498,6 @@ static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) masked_increment(reg_rmw(ctxt, VCPU_REGS_RSP), stack_mask(ctxt), inc); } -static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) -{ - register_address_increment(ctxt, &ctxt->_eip, rel); -} - static u32 desc_limit_scaled(struct desc_struct *desc) { u32 limit = get_desc_limit(desc); @@ -576,6 +571,38 @@ static int emulate_nm(struct x86_emulate_ctxt *ctxt) return emulate_exception(ctxt, NM_VECTOR, 0, false); } +static inline int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst, + int cs_l) +{ + switch (ctxt->op_bytes) { + case 2: + ctxt->_eip = (u16)dst; + break; + case 4: + ctxt->_eip = (u32)dst; + break; + case 8: + if ((cs_l && is_noncanonical_address(dst)) || + (!cs_l && (dst & ~(u32)-1))) + return emulate_gp(ctxt, 0); + ctxt->_eip = dst; + break; + default: + WARN(1, "unsupported eip assignment size\n"); + } + return X86EMUL_CONTINUE; +} + +static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) +{ + return assign_eip_far(ctxt, dst, ctxt->mode == X86EMUL_MODE_PROT64); +} + +static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) +{ + return assign_eip_near(ctxt, ctxt->_eip + rel); +} + static u16 get_segment_selector(struct x86_emulate_ctxt *ctxt, unsigned seg) { u16 selector; @@ -1958,13 +1985,15 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt) case 2: /* call near abs */ { long int old_eip; old_eip = ctxt->_eip; - ctxt->_eip = ctxt->src.val; + rc = assign_eip_near(ctxt, ctxt->src.val); + if (rc != X86EMUL_CONTINUE) + break; ctxt->src.val = old_eip; rc = em_push(ctxt); break; } case 4: /* jmp abs */ - ctxt->_eip = ctxt->src.val; + rc = assign_eip_near(ctxt, ctxt->src.val); break; case 5: /* jmp far */ rc = em_jmp_far(ctxt); @@ -1996,16 +2025,21 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) static int em_ret(struct x86_emulate_ctxt *ctxt) { - ctxt->dst.type = OP_REG; - ctxt->dst.addr.reg = &ctxt->_eip; - ctxt->dst.bytes = ctxt->op_bytes; - return em_pop(ctxt); + int rc; + unsigned long eip; + + rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); + if (rc != X86EMUL_CONTINUE) + return rc; + + return assign_eip_near(ctxt, eip); } static int em_ret_far(struct x86_emulate_ctxt *ctxt) { int rc; unsigned long cs; + int cpl = ctxt->ops->cpl(ctxt); rc = emulate_pop(ctxt, &ctxt->_eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) @@ -2015,6 +2049,9 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) rc = emulate_pop(ctxt, &cs, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; + /* Outer-privilege level return is not implemented */ + if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl) + return X86EMUL_UNHANDLEABLE; rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS); return rc; } @@ -2221,7 +2258,7 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) * Not recognized on AMD in compat mode (but is recognized in legacy * mode). */ - if ((ctxt->mode == X86EMUL_MODE_PROT32) && (efer & EFER_LMA) + if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA) && !vendor_intel(ctxt)) return emulate_ud(ctxt); @@ -2234,25 +2271,13 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) setup_syscalls_segments(ctxt, &cs, &ss); ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); - switch (ctxt->mode) { - case X86EMUL_MODE_PROT32: - if ((msr_data & 0xfffc) == 0x0) - return emulate_gp(ctxt, 0); - break; - case X86EMUL_MODE_PROT64: - if (msr_data == 0x0) - return emulate_gp(ctxt, 0); - break; - default: - break; - } + if ((msr_data & 0xfffc) == 0x0) + return emulate_gp(ctxt, 0); ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF); - cs_sel = (u16)msr_data; - cs_sel &= ~SELECTOR_RPL_MASK; + cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK; ss_sel = cs_sel + 8; - ss_sel &= ~SELECTOR_RPL_MASK; - if (ctxt->mode == X86EMUL_MODE_PROT64 || (efer & EFER_LMA)) { + if (efer & EFER_LMA) { cs.d = 0; cs.l = 1; } @@ -2261,10 +2286,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ops->get_msr(ctxt, MSR_IA32_SYSENTER_EIP, &msr_data); - ctxt->_eip = msr_data; + ctxt->_eip = (efer & EFER_LMA) ? msr_data : (u32)msr_data; ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data); - *reg_write(ctxt, VCPU_REGS_RSP) = msr_data; + *reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data : + (u32)msr_data; return X86EMUL_CONTINUE; } @@ -2273,7 +2299,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) { const struct x86_emulate_ops *ops = ctxt->ops; struct desc_struct cs, ss; - u64 msr_data; + u64 msr_data, rcx, rdx; int usermode; u16 cs_sel = 0, ss_sel = 0; @@ -2289,6 +2315,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) else usermode = X86EMUL_MODE_PROT32; + rcx = reg_read(ctxt, VCPU_REGS_RCX); + rdx = reg_read(ctxt, VCPU_REGS_RDX); + cs.dpl = 3; ss.dpl = 3; ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); @@ -2306,6 +2335,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ss_sel = cs_sel + 8; cs.d = 0; cs.l = 1; + if (is_noncanonical_address(rcx) || + is_noncanonical_address(rdx)) + return emulate_gp(ctxt, 0); break; } cs_sel |= SELECTOR_RPL_MASK; @@ -2314,8 +2346,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); - ctxt->_eip = reg_read(ctxt, VCPU_REGS_RDX); - *reg_write(ctxt, VCPU_REGS_RSP) = reg_read(ctxt, VCPU_REGS_RCX); + ctxt->_eip = rdx; + *reg_write(ctxt, VCPU_REGS_RSP) = rcx; return X86EMUL_CONTINUE; } @@ -2854,10 +2886,13 @@ static int em_aad(struct x86_emulate_ctxt *ctxt) static int em_call(struct x86_emulate_ctxt *ctxt) { + int rc; long rel = ctxt->src.val; ctxt->src.val = (unsigned long)ctxt->_eip; - jmp_rel(ctxt, rel); + rc = jmp_rel(ctxt, rel); + if (rc != X86EMUL_CONTINUE) + return rc; return em_push(ctxt); } @@ -2889,11 +2924,12 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) { int rc; + unsigned long eip; - ctxt->dst.type = OP_REG; - ctxt->dst.addr.reg = &ctxt->_eip; - ctxt->dst.bytes = ctxt->op_bytes; - rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes); + rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); + if (rc != X86EMUL_CONTINUE) + return rc; + rc = assign_eip_near(ctxt, eip); if (rc != X86EMUL_CONTINUE) return rc; rsp_increment(ctxt, ctxt->src.val); @@ -3223,20 +3259,24 @@ static int em_lmsw(struct x86_emulate_ctxt *ctxt) static int em_loop(struct x86_emulate_ctxt *ctxt) { + int rc = X86EMUL_CONTINUE; + register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX), -1); if ((address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) != 0) && (ctxt->b == 0xe2 || test_cc(ctxt->b ^ 0x5, ctxt->eflags))) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); - return X86EMUL_CONTINUE; + return rc; } static int em_jcxz(struct x86_emulate_ctxt *ctxt) { + int rc = X86EMUL_CONTINUE; + if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); - return X86EMUL_CONTINUE; + return rc; } static int em_in(struct x86_emulate_ctxt *ctxt) @@ -4595,7 +4635,8 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) goto done; } - ctxt->dst.orig_val = ctxt->dst.val; + /* Copy full 64-bit value for CMPXCHG8B. */ + ctxt->dst.orig_val64 = ctxt->dst.val64; special_insn: @@ -4633,7 +4674,7 @@ special_insn: break; case 0x70 ... 0x7f: /* jcc (short) */ if (test_cc(ctxt->b, ctxt->eflags)) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); break; case 0x8d: /* lea r16/r32, m */ ctxt->dst.val = ctxt->src.addr.mem.ea; @@ -4662,7 +4703,7 @@ special_insn: break; case 0xe9: /* jmp rel */ case 0xeb: /* jmp rel short */ - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); ctxt->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xf4: /* hlt */ @@ -4782,7 +4823,7 @@ twobyte_insn: break; case 0x80 ... 0x8f: /* jnz rel, etc*/ if (test_cc(ctxt->b, ctxt->eflags)) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); break; case 0x90 ... 0x9f: /* setcc r/m8 */ ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 518d864..1406ffd 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -262,8 +262,10 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) return; timer = &pit->pit_state.timer; + mutex_lock(&pit->pit_state.lock); if (hrtimer_cancel(timer)) hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + mutex_unlock(&pit->pit_state.lock); } static void destroy_pit_timer(struct kvm_pit *pit) @@ -303,7 +305,7 @@ static void pit_do_work(struct kthread_work *work) * LVT0 to NMI delivery. Other PIC interrupts are just sent to * VCPU0, and only if its LVT0 is in EXTINT mode. */ - if (kvm->arch.vapics_in_nmi_mode > 0) + if (atomic_read(&kvm->arch.vapics_in_nmi_mode) > 0) kvm_for_each_vcpu(i, vcpu, kvm) kvm_apic_nmi_wd_deliver(vcpu); } diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 484bc87..3ec38cb 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -108,7 +108,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) vector = kvm_cpu_get_extint(v); - if (kvm_apic_vid_enabled(v->kvm) || vector != -1) + if (vector != -1) return vector; /* PIC */ return kvm_get_apic_interrupt(v); /* APIC */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 0069118..6456734 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -352,25 +352,46 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) { - apic->irr_pending = false; + struct kvm_vcpu *vcpu; + + vcpu = apic->vcpu; + apic_clear_vector(vec, apic->regs + APIC_IRR); - if (apic_search_irr(apic) != -1) - apic->irr_pending = true; + if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + /* try to update RVI */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + else { + vec = apic_search_irr(apic); + apic->irr_pending = (vec != -1); + } } static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { - /* Note that we never get here with APIC virtualization enabled. */ + struct kvm_vcpu *vcpu; + + if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) + return; + + vcpu = apic->vcpu; - if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) - ++apic->isr_count; - BUG_ON(apic->isr_count > MAX_APIC_VECTOR); /* - * ISR (in service register) bit is set when injecting an interrupt. - * The highest vector is injected. Thus the latest bit set matches - * the highest bit in ISR. + * With APIC virtualization enabled, all caching is disabled + * because the processor can modify ISR under the hood. Instead + * just set SVI. */ - apic->highest_isr_cache = vec; + if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec); + else { + ++apic->isr_count; + BUG_ON(apic->isr_count > MAX_APIC_VECTOR); + /* + * ISR (in service register) bit is set when injecting an interrupt. + * The highest vector is injected. Thus the latest bit set matches + * the highest bit in ISR. + */ + apic->highest_isr_cache = vec; + } } static inline int apic_find_highest_isr(struct kvm_lapic *apic) @@ -1088,10 +1109,10 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) if (!nmi_wd_enabled) { apic_debug("Receive NMI setting on APIC_LVT0 " "for cpu %d\n", apic->vcpu->vcpu_id); - apic->vcpu->kvm->arch.vapics_in_nmi_mode++; + atomic_inc(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); } } else if (nmi_wd_enabled) - apic->vcpu->kvm->arch.vapics_in_nmi_mode--; + atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); } static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) @@ -1627,11 +1648,16 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) int vector = kvm_apic_has_interrupt(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; - /* Note that we never get here with APIC virtualization enabled. */ - if (vector == -1) return -1; + /* + * We get here even with APIC virtualization enabled, if doing + * nested virtualization and L1 runs with the "acknowledge interrupt + * on exit" mode. Then we cannot inject the interrupt via RVI, + * because the process would deliver it through the IDT. + */ + apic_set_isr(vector, apic); apic_update_ppr(apic); apic_clear_irr(vector, apic); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 6a11845..7205173 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -165,7 +165,7 @@ static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr) static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) { - return vcpu->arch.apic->pending_events; + return kvm_vcpu_has_lapic(vcpu) && vcpu->arch.apic->pending_events; } bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 9b53135..dba56fb 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -198,16 +198,20 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask) EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); /* - * spte bits of bit 3 ~ bit 11 are used as low 9 bits of generation number, - * the bits of bits 52 ~ bit 61 are used as high 10 bits of generation - * number. + * the low bit of the generation number is always presumed to be zero. + * This disables mmio caching during memslot updates. The concept is + * similar to a seqcount but instead of retrying the access we just punt + * and ignore the cache. + * + * spte bits 3-11 are used as bits 1-9 of the generation number, + * the bits 52-61 are used as bits 10-19 of the generation number. */ -#define MMIO_SPTE_GEN_LOW_SHIFT 3 +#define MMIO_SPTE_GEN_LOW_SHIFT 2 #define MMIO_SPTE_GEN_HIGH_SHIFT 52 -#define MMIO_GEN_SHIFT 19 -#define MMIO_GEN_LOW_SHIFT 9 -#define MMIO_GEN_LOW_MASK ((1 << MMIO_GEN_LOW_SHIFT) - 1) +#define MMIO_GEN_SHIFT 20 +#define MMIO_GEN_LOW_SHIFT 10 +#define MMIO_GEN_LOW_MASK ((1 << MMIO_GEN_LOW_SHIFT) - 2) #define MMIO_GEN_MASK ((1 << MMIO_GEN_SHIFT) - 1) #define MMIO_MAX_GEN ((1 << MMIO_GEN_SHIFT) - 1) @@ -377,12 +381,6 @@ static u64 __get_spte_lockless(u64 *sptep) { return ACCESS_ONCE(*sptep); } - -static bool __check_direct_spte_mmio_pf(u64 spte) -{ - /* It is valid if the spte is zapped. */ - return spte == 0ull; -} #else union split_spte { struct { @@ -498,23 +496,6 @@ retry: return spte.spte; } - -static bool __check_direct_spte_mmio_pf(u64 spte) -{ - union split_spte sspte = (union split_spte)spte; - u32 high_mmio_mask = shadow_mmio_mask >> 32; - - /* It is valid if the spte is zapped. */ - if (spte == 0ull) - return true; - - /* It is valid if the spte is being zapped. */ - if (sspte.spte_low == 0ull && - (sspte.spte_high & high_mmio_mask) == high_mmio_mask) - return true; - - return false; -} #endif static bool spte_is_locklessly_modifiable(u64 spte) @@ -3157,7 +3138,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; - vcpu_clear_mmio_info(vcpu, ~0ul); + vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) { hpa_t root = vcpu->arch.mmu.root_hpa; @@ -3211,21 +3192,6 @@ static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct) return vcpu_match_mmio_gva(vcpu, addr); } - -/* - * On direct hosts, the last spte is only allows two states - * for mmio page fault: - * - It is the mmio spte - * - It is zapped or it is being zapped. - * - * This function completely checks the spte when the last spte - * is not the mmio spte. - */ -static bool check_direct_spte_mmio_pf(u64 spte) -{ - return __check_direct_spte_mmio_pf(spte); -} - static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr) { struct kvm_shadow_walk_iterator iterator; @@ -3268,13 +3234,6 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) } /* - * It's ok if the gva is remapped by other cpus on shadow guest, - * it's a BUG if the gfn is not a mmio page. - */ - if (direct && !check_direct_spte_mmio_pf(spte)) - return RET_MMIO_PF_BUG; - - /* * If the page table is zapped by other cpus, let CPU fault again on * the address. */ @@ -4074,7 +4033,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, ++vcpu->kvm->stat.mmu_pte_write; kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); - mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; + mask.cr0_wp = mask.cr4_pae = mask.nxe = mask.smep_andnot_wp = 1; for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { if (detect_write_misaligned(sp, gpa, bytes) || detect_write_flooding(sp)) { @@ -4379,8 +4338,8 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) * The very rare case: if the generation-number is round, * zap all shadow pages. */ - if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) { - printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n"); + if (unlikely(kvm_current_mmio_generation(kvm) == 0)) { + printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_invalidate_zap_all_pages(kvm); } } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 2de1bc0..0746334 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -495,8 +495,10 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if (svm->vmcb->control.next_rip != 0) + if (svm->vmcb->control.next_rip != 0) { + WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS)); svm->next_rip = svm->vmcb->control.next_rip; + } if (!svm->next_rip) { if (emulate_instruction(vcpu, EMULTYPE_SKIP) != @@ -3213,7 +3215,7 @@ static int wrmsr_interception(struct vcpu_svm *svm) msr.host_initiated = false; svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - if (svm_set_msr(&svm->vcpu, &msr)) { + if (kvm_set_msr(&svm->vcpu, &msr)) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(&svm->vcpu, 0); } else { @@ -3495,9 +3497,9 @@ static int handle_exit(struct kvm_vcpu *vcpu) if (exit_code >= ARRAY_SIZE(svm_exit_handlers) || !svm_exit_handlers[exit_code]) { - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = exit_code; - return 0; + WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code); + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; } return svm_exit_handlers[exit_code](svm); @@ -4246,7 +4248,9 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, break; } - vmcb->control.next_rip = info->next_rip; + /* TODO: Advertise NRIPS to guest hypervisor unconditionally */ + if (static_cpu_has(X86_FEATURE_NRIPS)) + vmcb->control.next_rip = info->next_rip; vmcb->control.exit_code = icpt_info.exit_code; vmexit = nested_svm_exit_handled(svm); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 3927528..80c22a3 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -441,6 +441,7 @@ struct vcpu_vmx { #endif int gs_ldt_reload_needed; int fs_reload_needed; + unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { int vm86_active; @@ -2320,12 +2321,12 @@ static __init void nested_vmx_setup_ctls_msrs(void) nested_vmx_secondary_ctls_low = 0; nested_vmx_secondary_ctls_high &= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_UNRESTRICTED_GUEST | SECONDARY_EXEC_WBINVD_EXITING; if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ - nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT; + nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT | + SECONDARY_EXEC_UNRESTRICTED_GUEST; nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT | VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT | VMX_EPT_INVEPT_BIT; @@ -2582,12 +2583,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: msr = find_msr_entry(vmx, msr_index); if (msr) { + u64 old_msr_data = msr->data; msr->data = data; if (msr - vmx->guest_msrs < vmx->save_nmsrs) { preempt_disable(); - kvm_set_shared_msr(msr->index, msr->data, - msr->mask); + ret = kvm_set_shared_msr(msr->index, msr->data, + msr->mask); preempt_enable(); + if (ret) + msr->data = old_msr_data; } break; } @@ -4162,11 +4166,16 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) u32 low32, high32; unsigned long tmpl; struct desc_ptr dt; + unsigned long cr4; vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS); /* 22.2.3 */ - vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */ vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ + /* Save the most likely value for this task's CR4 in the VMCS. */ + cr4 = read_cr4(); + vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ + vmx->host_state.vmcs_host_cr4 = cr4; + vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ #ifdef CONFIG_X86_64 /* @@ -5169,7 +5178,7 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu) msr.data = data; msr.index = ecx; msr.host_initiated = false; - if (vmx_set_msr(vcpu, &msr) != 0) { + if (kvm_set_msr(vcpu, &msr) != 0) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(vcpu, 0); return 1; @@ -6441,6 +6450,12 @@ static int handle_invept(struct kvm_vcpu *vcpu) return 1; } +static int handle_invvpid(struct kvm_vcpu *vcpu) +{ + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -6486,6 +6501,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op, [EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op, [EXIT_REASON_INVEPT] = handle_invept, + [EXIT_REASON_INVVPID] = handle_invvpid, }; static const int kvm_vmx_max_exit_handlers = @@ -6719,7 +6735,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD: case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE: case EXIT_REASON_VMOFF: case EXIT_REASON_VMON: - case EXIT_REASON_INVEPT: + case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID: /* * VMX instructions trap unconditionally. This allows L1 to * emulate them for its L2 guest, i.e., allows 3-level nesting! @@ -6884,10 +6900,10 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) && kvm_vmx_exit_handlers[exit_reason]) return kvm_vmx_exit_handlers[exit_reason](vcpu); else { - vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; - vcpu->run->hw.hardware_exit_reason = exit_reason; + WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason); + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; } - return 0; } static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) @@ -7186,7 +7202,7 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long debugctlmsr; + unsigned long debugctlmsr, cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) @@ -7207,6 +7223,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); + cr4 = read_cr4(); + if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { + vmcs_writel(HOST_CR4, cr4); + vmx->host_state.vmcs_host_cr4 = cr4; + } + /* When single-stepping over STI and MOV SS, we must clear the * corresponding interruptibility bits in the guest state. Otherwise * vmentry fails as it then expects bit 14 (BS) in pending debug diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8fbd1a7..1777f89 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -225,20 +225,25 @@ static void kvm_shared_msr_cpu_online(void) shared_msr_update(i, shared_msrs_global.msrs[i]); } -void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) +int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) { unsigned int cpu = smp_processor_id(); struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + int err; if (((value ^ smsr->values[slot].curr) & mask) == 0) - return; + return 0; smsr->values[slot].curr = value; - wrmsrl(shared_msrs_global.msrs[slot], value); + err = wrmsrl_safe(shared_msrs_global.msrs[slot], value); + if (err) + return 1; + if (!smsr->registered) { smsr->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&smsr->urn); smsr->registered = true; } + return 0; } EXPORT_SYMBOL_GPL(kvm_set_shared_msr); @@ -946,7 +951,6 @@ void kvm_enable_efer_bits(u64 mask) } EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); - /* * Writes msr value into into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -954,8 +958,34 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); */ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { + switch (msr->index) { + case MSR_FS_BASE: + case MSR_GS_BASE: + case MSR_KERNEL_GS_BASE: + case MSR_CSTAR: + case MSR_LSTAR: + if (is_noncanonical_address(msr->data)) + return 1; + break; + case MSR_IA32_SYSENTER_EIP: + case MSR_IA32_SYSENTER_ESP: + /* + * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if + * non-canonical address is written on Intel but not on + * AMD (which ignores the top 32-bits, because it does + * not implement 64-bit SYSENTER). + * + * 64-bit code should hence be able to write a non-canonical + * value on AMD. Making the address canonical ensures that + * vmentry does not fail on Intel after writing a non-canonical + * value, and that something deterministic happens if the guest + * invokes 64-bit SYSENTER. + */ + msr->data = get_canonical(msr->data); + } return kvm_x86_ops->set_msr(vcpu, msr); } +EXPORT_SYMBOL_GPL(kvm_set_msr); /* * Adapt set_msr() to msr_io()'s calling convention @@ -1177,21 +1207,22 @@ void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) { #ifdef CONFIG_X86_64 bool vcpus_matched; - bool do_request = false; struct kvm_arch *ka = &vcpu->kvm->arch; struct pvclock_gtod_data *gtod = &pvclock_gtod_data; vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == atomic_read(&vcpu->kvm->online_vcpus)); - if (vcpus_matched && gtod->clock.vclock_mode == VCLOCK_TSC) - if (!ka->use_master_clock) - do_request = 1; - - if (!vcpus_matched && ka->use_master_clock) - do_request = 1; - - if (do_request) + /* + * Once the masterclock is enabled, always perform request in + * order to update it. + * + * In order to enable masterclock, the host clocksource must be TSC + * and the vcpus need to have matched TSCs. When that happens, + * perform request to enable masterclock. + */ + if (ka->use_master_clock || + (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched)) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, @@ -4881,7 +4912,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu) ++vcpu->stat.insn_emulation_fail; trace_kvm_emulate_insn_failed(vcpu); - if (!is_guest_mode(vcpu)) { + if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 8da5823..21ea4fc 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -78,15 +78,23 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, vcpu->arch.mmio_gva = gva & PAGE_MASK; vcpu->arch.access = access; vcpu->arch.mmio_gfn = gfn; + vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation; +} + +static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation; } /* - * Clear the mmio cache info for the given gva, - * specially, if gva is ~0ul, we clear all mmio cache info. + * Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we + * clear all mmio cache info. */ +#define MMIO_GVA_ANY (~(gva_t)0) + static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva) { - if (gva != (~0ul) && vcpu->arch.mmio_gva != (gva & PAGE_MASK)) + if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK)) return; vcpu->arch.mmio_gva = 0; @@ -94,7 +102,8 @@ static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva) static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva) { - if (vcpu->arch.mmio_gva && vcpu->arch.mmio_gva == (gva & PAGE_MASK)) + if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva && + vcpu->arch.mmio_gva == (gva & PAGE_MASK)) return true; return false; @@ -102,7 +111,8 @@ static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva) static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) { - if (vcpu->arch.mmio_gfn && vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT) + if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn && + vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT) return true; return false; diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 0002a3a..3620928 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -30,11 +30,13 @@ struct pg_state { unsigned long start_address; unsigned long current_address; const struct addr_marker *marker; + unsigned long lines; }; struct addr_marker { unsigned long start_address; const char *name; + unsigned long max_lines; }; /* indices for address_markers; keep sync'd w/ address_markers below */ @@ -45,6 +47,7 @@ enum address_markers_idx { LOW_KERNEL_NR, VMALLOC_START_NR, VMEMMAP_START_NR, + ESPFIX_START_NR, HIGH_KERNEL_NR, MODULES_VADDR_NR, MODULES_END_NR, @@ -67,6 +70,7 @@ static struct addr_marker address_markers[] = { { PAGE_OFFSET, "Low Kernel Mapping" }, { VMALLOC_START, "vmalloc() Area" }, { VMEMMAP_START, "Vmemmap" }, + { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, { __START_KERNEL_map, "High Kernel Mapping" }, { MODULES_VADDR, "Modules" }, { MODULES_END, "End Modules" }, @@ -163,7 +167,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, pgprot_t new_prot, int level) { pgprotval_t prot, cur; - static const char units[] = "KMGTPE"; + static const char units[] = "BKMGTPE"; /* * If we have a "break" in the series, we need to flush the state that @@ -178,6 +182,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->current_prot = new_prot; st->level = level; st->marker = address_markers; + st->lines = 0; seq_printf(m, "---[ %s ]---\n", st->marker->name); } else if (prot != cur || level != st->level || st->current_address >= st->marker[1].start_address) { @@ -188,17 +193,21 @@ static void note_page(struct seq_file *m, struct pg_state *st, /* * Now print the actual finished series */ - seq_printf(m, "0x%0*lx-0x%0*lx ", - width, st->start_address, - width, st->current_address); - - delta = (st->current_address - st->start_address) >> 10; - while (!(delta & 1023) && unit[1]) { - delta >>= 10; - unit++; + if (!st->marker->max_lines || + st->lines < st->marker->max_lines) { + seq_printf(m, "0x%0*lx-0x%0*lx ", + width, st->start_address, + width, st->current_address); + + delta = (st->current_address - st->start_address) >> 10; + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; + } + seq_printf(m, "%9lu%c ", delta, *unit); + printk_prot(m, st->current_prot, st->level); } - seq_printf(m, "%9lu%c ", delta, *unit); - printk_prot(m, st->current_prot, st->level); + st->lines++; /* * We print markers for special areas of address space, diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index a10c8c7..ebc551c 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -833,11 +833,8 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) { struct task_struct *tsk = current; - struct mm_struct *mm = tsk->mm; int code = BUS_ADRERR; - up_read(&mm->mmap_sem); - /* Kernel mode? Handle exceptions or die: */ if (!(error_code & PF_USER)) { no_context(regs, error_code, address, SIGBUS, BUS_ADRERR); @@ -868,7 +865,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) { if (fatal_signal_pending(current) && !(error_code & PF_USER)) { - up_read(¤t->mm->mmap_sem); no_context(regs, error_code, address, 0, 0); return; } @@ -876,14 +872,11 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ if (!(error_code & PF_USER)) { - up_read(¤t->mm->mmap_sem); no_context(regs, error_code, address, SIGSEGV, SEGV_MAPERR); return; } - up_read(¤t->mm->mmap_sem); - /* * We ran out of memory, call the OOM killer, and return the * userspace (which will retry the fault, or kill us if we got @@ -894,6 +887,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) do_sigbus(regs, error_code, address, fault); + else if (fault & VM_FAULT_SIGSEGV) + bad_area_nosemaphore(regs, error_code, address); else BUG(); } @@ -1216,6 +1211,7 @@ good_area: return; if (unlikely(fault & VM_FAULT_ERROR)) { + up_read(&mm->mmap_sem); mm_fault_error(regs, error_code, address, fault); return; } diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 207d9aef..448ee89 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -172,7 +172,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, */ if (pmd_none(pmd) || pmd_trans_splitting(pmd)) return 0; - if (unlikely(pmd_large(pmd))) { + if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) { /* * NUMA hinting faults need to be handled in the GUP * slowpath for accounting purposes and so that they diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 8b977eb..006cc91 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -66,9 +66,15 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) return ERR_PTR(-EINVAL); } +/* + * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal + * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. + * Otherwise, returns 0. + */ int pmd_huge(pmd_t pmd) { - return !!(pmd_val(pmd) & _PAGE_PSE); + return !pmd_none(pmd) && + (pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; } int pud_huge(pud_t pud) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index f35c66c..2308a40 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1110,7 +1110,7 @@ void mark_rodata_ro(void) unsigned long end = (unsigned long) &__end_rodata_hpage_align; unsigned long text_end = PFN_ALIGN(&__stop___ex_table); unsigned long rodata_end = PFN_ALIGN(&__end_rodata); - unsigned long all_end = PFN_ALIGN(&_end); + unsigned long all_end; printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); @@ -1121,7 +1121,16 @@ void mark_rodata_ro(void) /* * The rodata/data/bss/brk section (but not the kernel text!) * should also be not-executable. + * + * We align all_end to PMD_SIZE because the existing mapping + * is a full PMD. If we would align _brk_end to PAGE_SIZE we + * split the PMD and the reminder between _brk_end and the end + * of the PMD will remain mapped executable. + * + * Any PMD which was setup after the one which covers _brk_end + * has been zapped already via cleanup_highmem(). */ + all_end = roundup((unsigned long)_brk_end, PMD_SIZE); set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT); rodata_test(); diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 25e7e13..3601ff2 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -35,12 +35,12 @@ struct __read_mostly va_alignment va_align = { .flags = -1, }; -static unsigned int stack_maxrandom_size(void) +static unsigned long stack_maxrandom_size(void) { - unsigned int max = 0; + unsigned long max = 0; if ((current->flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - max = ((-1U) & STACK_RND_MASK) << PAGE_SHIFT; + max = ((-1UL) & STACK_RND_MASK) << PAGE_SHIFT; } return max; diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a348868..fed892d 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -405,7 +405,7 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr) psize = page_level_size(level); pmask = page_level_mask(level); offset = virt_addr & ~pmask; - phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; return (phys_addr | offset); } EXPORT_SYMBOL_GPL(slow_virt_to_phys); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index c96314a..0004ac7 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -399,13 +399,20 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - int young; - - young = ptep_test_and_clear_young(vma, address, ptep); - if (young) - flush_tlb_page(vma, address); - - return young; + /* + * On x86 CPUs, clearing the accessed bit without a TLB flush + * doesn't cause data corruption. [ It could cause incorrect + * page aging and the (mistaken) reclaim of hot pages, but the + * chance of that should be relatively low. ] + * + * So as a performance optimization don't flush the TLB when + * clearing the accessed bit, it will eventually be flushed by + * a context switch or a VM operation anyway. [ In the rare + * event of it not getting flushed for a long time the delay + * shouldn't really matter because there's no real memory + * pressure for swapout to react to. ] + */ + return ptep_test_and_clear_young(vma, address, ptep); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index af2d431..1fed139 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -211,7 +211,12 @@ void bpf_jit_compile(struct sk_filter *fp) } cleanup_addr = proglen; /* epilogue address */ - for (pass = 0; pass < 10; pass++) { + /* JITed image shrinks with every pass and the loop iterates + * until the image stops shrinking. Very large bpf programs + * may converge on the last pass. In such case do one more + * pass to emit the final image + */ + for (pass = 0; pass < 10 || image; pass++) { u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen; /* no prologue/epilogue for trivial filters (RET something) */ proglen = 0; diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 4f25ec0..bf00138 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -84,6 +84,17 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"), }, }, + /* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/931368 */ + /* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/1033299 */ + { + .callback = set_use_crs, + .ident = "Foxconn K8M890-8237A", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Foxconn"), + DMI_MATCH(DMI_BOARD_NAME, "K8M890-8237A"), + DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"), + }, + }, /* Now for the blacklist.. */ @@ -124,8 +135,10 @@ void __init pci_acpi_crs_quirks(void) { int year; - if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008) - pci_use_crs = false; + if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008) { + if (iomem_resource.end <= 0xffffffff) + pci_use_crs = false; + } dmi_check_system(pci_crs_quirks); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 981c2db..88f143d 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -448,6 +448,22 @@ static const struct dmi_system_id pciprobe_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "ftServer"), }, }, + { + .callback = set_scan_all, + .ident = "Stratus/NEC ftServer", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NEC"), + DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R32"), + }, + }, + { + .callback = set_scan_all, + .ident = "Stratus/NEC ftServer", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NEC"), + DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R31"), + }, + }, {} }; diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index db6b1ab..96a159a 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -162,6 +162,10 @@ pcibios_align_resource(void *data, const struct resource *res, return start; if (start & 0x300) start = (start + 0x3ff) & ~0x3ff; + } else if (res->flags & IORESOURCE_MEM) { + /* The low 1MB range is reserved for ISA cards */ + if (start < BIOS_END) + start = BIOS_END; } return start; } diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 7d28c88..291226b 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -13,13 +13,11 @@ #include #include #include +#include /* Defined in hibernate_asm_32.S */ extern int restore_image(void); -/* References to section boundaries */ -extern const void __nosave_begin, __nosave_end; - /* Pointer to the temporary resume page tables */ pgd_t *resume_pg_dir; diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 304fca2..2276238 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -17,11 +17,9 @@ #include #include #include +#include #include -/* References to section boundaries */ -extern __visible const void __nosave_begin, __nosave_end; - /* Defined in hibernate_asm_64.S */ extern asmlinkage int restore_image(void); diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 531d426..bd16d6c 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -34,7 +34,7 @@ typedef asmlinkage void (*sys_call_ptr_t)(void); extern asmlinkage void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { +const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index f2f0723..9578308 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -46,7 +46,7 @@ typedef void (*sys_call_ptr_t)(void); extern void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { +const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index f1d633a..d6bfb87 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -41,7 +41,6 @@ enum { #ifdef CONFIG_X86_64 #define vdso_enabled sysctl_vsyscall32 #define arch_setup_additional_pages syscall32_setup_pages -extern int sysctl_ldt16; #endif /* @@ -381,13 +380,6 @@ static struct ctl_table abi_table2[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "ldt16", - .data = &sysctl_ldt16, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, {} }; diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/vdso/vdso32/sigreturn.S index 31776d0..d7ec4e2 100644 --- a/arch/x86/vdso/vdso32/sigreturn.S +++ b/arch/x86/vdso/vdso32/sigreturn.S @@ -17,6 +17,7 @@ .text .globl __kernel_sigreturn .type __kernel_sigreturn,@function + nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */ ALIGN __kernel_sigreturn: .LSTART_sigreturn: diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 431e875..ab6ba35 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -117,30 +117,45 @@ subsys_initcall(init_vdso); struct linux_binprm; -/* Put the vdso above the (randomized) stack with another randomized offset. - This way there is no hole in the middle of address space. - To save memory make sure it is still in the same PTE as the stack top. - This doesn't give that many random bits */ +/* + * Put the vdso above the (randomized) stack with another randomized + * offset. This way there is no hole in the middle of address space. + * To save memory make sure it is still in the same PTE as the stack + * top. This doesn't give that many random bits. + * + * Note that this algorithm is imperfect: the distribution of the vdso + * start address within a PMD is biased toward the end. + * + * Only used for the 64-bit and x32 vdsos. + */ static unsigned long vdso_addr(unsigned long start, unsigned len) { unsigned long addr, end; unsigned offset; - end = (start + PMD_SIZE - 1) & PMD_MASK; + + /* + * Round up the start address. It can start out unaligned as a result + * of stack start randomization. + */ + start = PAGE_ALIGN(start); + + /* Round the lowest possible end address up to a PMD boundary. */ + end = (start + len + PMD_SIZE - 1) & PMD_MASK; if (end >= TASK_SIZE_MAX) end = TASK_SIZE_MAX; end -= len; - /* This loses some more bits than a modulo, but is cheaper */ - offset = get_random_int() & (PTRS_PER_PTE - 1); - addr = start + (offset << PAGE_SHIFT); - if (addr >= end) - addr = end; + + if (end > start) { + offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); + addr = start + (offset << PAGE_SHIFT); + } else { + addr = start; + } /* - * page-align it here so that get_unmapped_area doesn't - * align it wrongfully again to the next page. addr can come in 4K - * unaligned here as a result of stack start randomization. + * Forcibly align the final address in case we have a hardware + * issue that requires alignment for performance reasons. */ - addr = PAGE_ALIGN(addr); addr = align_vdso_addr(addr); return addr; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 201d09a..2302f10 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -481,6 +481,7 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte_t pte; unsigned long pfn; struct page *page; + unsigned char dummy; ptep = lookup_address((unsigned long)v, &level); BUG_ON(ptep == NULL); @@ -490,6 +491,32 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte = pfn_pte(pfn, prot); + /* + * Careful: update_va_mapping() will fail if the virtual address + * we're poking isn't populated in the page tables. We don't + * need to worry about the direct map (that's always in the page + * tables), but we need to be careful about vmap space. In + * particular, the top level page table can lazily propagate + * entries between processes, so if we've switched mms since we + * vmapped the target in the first place, we might not have the + * top-level page table entry populated. + * + * We disable preemption because we want the same mm active when + * we probe the target and when we issue the hypercall. We'll + * have the same nominal mm, but if we're a kernel thread, lazy + * mm dropping could change our pgd. + * + * Out of an abundance of caution, this uses __get_user() to fault + * in the target address just in case there's some obscure case + * in which the target address isn't readable. + */ + + preempt_disable(); + + pagefault_disable(); /* Avoid warnings due to being atomic. */ + __get_user(dummy, (unsigned char __user __force *)v); + pagefault_enable(); + if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0)) BUG(); @@ -501,6 +528,8 @@ static void set_aliased_prot(void *v, pgprot_t prot) BUG(); } else kmap_flush_unused(); + + preempt_enable(); } static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) @@ -508,6 +537,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE; int i; + /* + * We need to mark the all aliases of the LDT pages RO. We + * don't need to call vm_flush_aliases(), though, since that's + * only responsible for flushing aliases out the TLBs, not the + * page tables, and Xen will flush the TLB for us if needed. + * + * To avoid confusing future readers: none of this is necessary + * to load the LDT. The hypervisor only checks this when the + * LDT is faulted in due to subsequent descriptor access. + */ + for(i = 0; i < entries; i += entries_per_page) set_aliased_prot(ldt + i, PAGE_KERNEL_RO); } diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c index c985835..5b406fc 100644 --- a/arch/x86/xen/grant-table.c +++ b/arch/x86/xen/grant-table.c @@ -134,6 +134,7 @@ static int __init xlated_setup_gnttab_pages(void) { struct page **pages; xen_pfn_t *pfns; + void *vaddr; int rc; unsigned int i; unsigned long nr_grant_frames = gnttab_max_grant_frames(); @@ -159,21 +160,20 @@ static int __init xlated_setup_gnttab_pages(void) for (i = 0; i < nr_grant_frames; i++) pfns[i] = page_to_pfn(pages[i]); - rc = arch_gnttab_map_shared(pfns, nr_grant_frames, nr_grant_frames, - &xen_auto_xlat_grant_frames.vaddr); - - if (rc) { + vaddr = vmap(pages, nr_grant_frames, 0, PAGE_KERNEL); + if (!vaddr) { pr_warn("%s Couldn't map %ld pfns rc:%d\n", __func__, nr_grant_frames, rc); free_xenballooned_pages(nr_grant_frames, pages); kfree(pages); kfree(pfns); - return rc; + return -ENOMEM; } kfree(pages); xen_auto_xlat_grant_frames.pfn = pfns; xen_auto_xlat_grant_frames.count = nr_grant_frames; + xen_auto_xlat_grant_frames.vaddr = vaddr; return 0; } diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 2423ef0..c83da6f 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1866,12 +1866,11 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end, * * We can construct this by grafting the Xen provided pagetable into * head_64.S's preconstructed pagetables. We copy the Xen L2's into - * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt. This - * means that only the kernel has a physical mapping to start with - - * but that's enough to get __va working. We need to fill in the rest - * of the physical mapping once some sort of allocator has been set - * up. - * NOTE: for PVH, the page tables are native. + * level2_ident_pgt, and level2_kernel_pgt. This means that only the + * kernel has a physical mapping to start with - but that's enough to + * get __va working. We need to fill in the rest of the physical + * mapping once some sort of allocator has been set up. NOTE: for + * PVH, the page tables are native. */ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) { @@ -1902,8 +1901,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* L3_i[0] -> level2_ident_pgt */ convert_pfn_mfn(level3_ident_pgt); /* L3_k[510] -> level2_kernel_pgt - * L3_i[511] -> level2_fixmap_pgt */ + * L3_k[511] -> level2_fixmap_pgt */ convert_pfn_mfn(level3_kernel_pgt); + + /* L3_k[511][506] -> level1_fixmap_pgt */ + convert_pfn_mfn(level2_fixmap_pgt); } /* We get [511][511] and have Xen's version of level2_kernel_pgt */ l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd); @@ -1913,21 +1915,15 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) addr[1] = (unsigned long)l3; addr[2] = (unsigned long)l2; /* Graft it onto L4[272][0]. Note that we creating an aliasing problem: - * Both L4[272][0] and L4[511][511] have entries that point to the same + * Both L4[272][0] and L4[511][510] have entries that point to the same * L2 (PMD) tables. Meaning that if you modify it in __va space * it will be also modified in the __ka space! (But if you just * modify the PMD table to point to other PTE's or none, then you * are OK - which is what cleanup_highmap does) */ copy_page(level2_ident_pgt, l2); - /* Graft it onto L4[511][511] */ + /* Graft it onto L4[511][510] */ copy_page(level2_kernel_pgt, l2); - /* Get [511][510] and graft that in level2_fixmap_pgt */ - l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd); - l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud); - copy_page(level2_fixmap_pgt, l2); - /* Note that we don't do anything with level1_fixmap_pgt which - * we don't need. */ if (!xen_feature(XENFEAT_auto_translated_physmap)) { /* Make pagetable pieces RO */ set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); @@ -1937,6 +1933,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); + set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO); /* Pin down new L4 */ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 0982233..a6a72ce 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -574,13 +574,7 @@ void xen_enable_syscall(void) } #endif /* CONFIG_X86_64 */ } -void xen_enable_nmi(void) -{ -#ifdef CONFIG_X86_64 - if (register_callback(CALLBACKTYPE_nmi, (char *)nmi)) - BUG(); -#endif -} + void __init xen_pvmmu_arch_setup(void) { HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments); @@ -595,7 +589,6 @@ void __init xen_pvmmu_arch_setup(void) xen_enable_sysenter(); xen_enable_syscall(); - xen_enable_nmi(); } /* This function is not called for HVM domains */ diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 7b78f88..5718b0b 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -444,7 +444,7 @@ void xen_setup_timer(int cpu) irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt, IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER| - IRQF_FORCE_RESUME, + IRQF_FORCE_RESUME|IRQF_EARLY_RESUME, name, NULL); (void)xen_set_irq_priority(irq, XEN_IRQ_PRIORITY_MAX); diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index c87ae7c..8879361 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -336,6 +336,36 @@ menu "Executable file formats" source "fs/Kconfig.binfmt" +config XTFPGA_LCD + bool "Enable XTFPGA LCD driver" + depends on XTENSA_PLATFORM_XTFPGA + default n + help + There's a 2x16 LCD on most of XTFPGA boards, kernel may output + progress messages there during bootup/shutdown. It may be useful + during board bringup. + + If unsure, say N. + +config XTFPGA_LCD_BASE_ADDR + hex "XTFPGA LCD base address" + depends on XTFPGA_LCD + default "0x0d0c0000" + help + Base address of the LCD controller inside KIO region. + Different boards from XTFPGA family have LCD controller at different + addresses. Please consult prototyping user guide for your board for + the correct address. Wrong address here may lead to hardware lockup. + +config XTFPGA_LCD_8BIT_ACCESS + bool "Use 8-bit access to XTFPGA LCD" + depends on XTFPGA_LCD + default n + help + LCD may be connected with 4- or 8-bit interface, 8-bit access may + only be used with 8-bit interface. Please consult prototyping user + guide for your board for the correct interface width. + endmenu source "net/Kconfig" diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 2164462..51230ba 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -67,7 +67,12 @@ #define VMALLOC_START 0xC0000000 #define VMALLOC_END 0xC7FEFFFF #define TLBTEMP_BASE_1 0xC7FF0000 -#define TLBTEMP_BASE_2 0xC7FF8000 +#define TLBTEMP_BASE_2 (TLBTEMP_BASE_1 + DCACHE_WAY_SIZE) +#if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE +#define TLBTEMP_SIZE (2 * DCACHE_WAY_SIZE) +#else +#define TLBTEMP_SIZE ICACHE_WAY_SIZE +#endif /* * For the Xtensa architecture, the PTE layout is as follows: diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h index 677bfcf..28f33a8 100644 --- a/arch/xtensa/include/asm/traps.h +++ b/arch/xtensa/include/asm/traps.h @@ -25,30 +25,39 @@ static inline void spill_registers(void) { #if XCHAL_NUM_AREGS > 16 __asm__ __volatile__ ( - " call12 1f\n" + " call8 1f\n" " _j 2f\n" " retw\n" " .align 4\n" "1:\n" +#if XCHAL_NUM_AREGS == 32 + " _entry a1, 32\n" + " addi a8, a0, 3\n" + " _entry a1, 16\n" + " mov a12, a12\n" + " retw\n" +#else " _entry a1, 48\n" - " addi a12, a0, 3\n" -#if XCHAL_NUM_AREGS > 32 - " .rept (" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n" + " call12 1f\n" + " retw\n" + " .align 4\n" + "1:\n" + " .rept (" __stringify(XCHAL_NUM_AREGS) " - 16) / 12\n" " _entry a1, 48\n" " mov a12, a0\n" " .endr\n" -#endif - " _entry a1, 48\n" + " _entry a1, 16\n" #if XCHAL_NUM_AREGS % 12 == 0 - " mov a8, a8\n" -#elif XCHAL_NUM_AREGS % 12 == 4 " mov a12, a12\n" -#elif XCHAL_NUM_AREGS % 12 == 8 +#elif XCHAL_NUM_AREGS % 12 == 4 " mov a4, a4\n" +#elif XCHAL_NUM_AREGS % 12 == 8 + " mov a8, a8\n" #endif " retw\n" +#endif "2:\n" - : : : "a12", "a13", "memory"); + : : : "a8", "a9", "memory"); #else __asm__ __volatile__ ( " mov a12, a12\n" diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h index fd686dc..c7211e7 100644 --- a/arch/xtensa/include/asm/uaccess.h +++ b/arch/xtensa/include/asm/uaccess.h @@ -52,7 +52,12 @@ */ .macro get_fs ad, sp GET_CURRENT(\ad,\sp) +#if THREAD_CURRENT_DS > 1020 + addi \ad, \ad, TASK_THREAD + l32i \ad, \ad, THREAD_CURRENT_DS - TASK_THREAD +#else l32i \ad, \ad, THREAD_CURRENT_DS +#endif .endm /* diff --git a/arch/xtensa/include/uapi/asm/ioctls.h b/arch/xtensa/include/uapi/asm/ioctls.h index b4cb110..a47909f 100644 --- a/arch/xtensa/include/uapi/asm/ioctls.h +++ b/arch/xtensa/include/uapi/asm/ioctls.h @@ -28,17 +28,17 @@ #define TCSETSW 0x5403 #define TCSETSF 0x5404 -#define TCGETA _IOR('t', 23, struct termio) -#define TCSETA _IOW('t', 24, struct termio) -#define TCSETAW _IOW('t', 25, struct termio) -#define TCSETAF _IOW('t', 28, struct termio) +#define TCGETA 0x80127417 /* _IOR('t', 23, struct termio) */ +#define TCSETA 0x40127418 /* _IOW('t', 24, struct termio) */ +#define TCSETAW 0x40127419 /* _IOW('t', 25, struct termio) */ +#define TCSETAF 0x4012741C /* _IOW('t', 28, struct termio) */ #define TCSBRK _IO('t', 29) #define TCXONC _IO('t', 30) #define TCFLSH _IO('t', 31) -#define TIOCSWINSZ _IOW('t', 103, struct winsize) -#define TIOCGWINSZ _IOR('t', 104, struct winsize) +#define TIOCSWINSZ 0x40087467 /* _IOW('t', 103, struct winsize) */ +#define TIOCGWINSZ 0x80087468 /* _IOR('t', 104, struct winsize) */ #define TIOCSTART _IO('t', 110) /* start output, like ^Q */ #define TIOCSTOP _IO('t', 111) /* stop output, like ^S */ #define TIOCOUTQ _IOR('t', 115, int) /* output queue size */ @@ -88,7 +88,6 @@ #define TIOCSETD _IOW('T', 35, int) #define TIOCGETD _IOR('T', 36, int) #define TCSBRKP _IOW('T', 37, int) /* Needed for POSIX tcsendbreak()*/ -#define TIOCTTYGSTRUCT _IOR('T', 38, struct tty_struct) /* For debugging only*/ #define TIOCSBRK _IO('T', 39) /* BSD compatibility */ #define TIOCCBRK _IO('T', 40) /* BSD compatibility */ #define TIOCGSID _IOR('T', 41, pid_t) /* Return the session ID of FD*/ @@ -114,8 +113,10 @@ #define TIOCSERGETLSR _IOR('T', 89, unsigned int) /* Get line status reg. */ /* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */ # define TIOCSER_TEMT 0x01 /* Transmitter physically empty */ -#define TIOCSERGETMULTI _IOR('T', 90, struct serial_multiport_struct) /* Get multiport config */ -#define TIOCSERSETMULTI _IOW('T', 91, struct serial_multiport_struct) /* Set multiport config */ +#define TIOCSERGETMULTI 0x80a8545a /* Get multiport config */ + /* _IOR('T', 90, struct serial_multiport_struct) */ +#define TIOCSERSETMULTI 0x40a8545b /* Set multiport config */ + /* _IOW('T', 91, struct serial_multiport_struct) */ #define TIOCMIWAIT _IO('T', 92) /* wait for a change on serial input line(s) */ #define TIOCGICOUNT 0x545D /* read serial port inline interrupt counts */ diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h index b939552..b54fa1b 100644 --- a/arch/xtensa/include/uapi/asm/unistd.h +++ b/arch/xtensa/include/uapi/asm/unistd.h @@ -384,7 +384,8 @@ __SYSCALL(174, sys_chroot, 1) #define __NR_pivot_root 175 __SYSCALL(175, sys_pivot_root, 2) #define __NR_umount 176 -__SYSCALL(176, sys_umount, 2) +__SYSCALL(176, sys_oldumount, 1) +#define __ARCH_WANT_SYS_OLDUMOUNT #define __NR_swapoff 177 __SYSCALL(177, sys_swapoff, 1) #define __NR_sync 178 @@ -714,7 +715,7 @@ __SYSCALL(323, sys_process_vm_writev, 6) __SYSCALL(324, sys_name_to_handle_at, 5) #define __NR_open_by_handle_at 325 __SYSCALL(325, sys_open_by_handle_at, 3) -#define __NR_sync_file_range 326 +#define __NR_sync_file_range2 326 __SYSCALL(326, sys_sync_file_range2, 6) #define __NR_perf_event_open 327 __SYSCALL(327, sys_perf_event_open, 5) diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index ef7f499..cf8a354 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -568,12 +568,13 @@ user_exception_exit: * (if we have restored WSBITS-1 frames). */ +2: #if XCHAL_HAVE_THREADPTR l32i a3, a1, PT_THREADPTR wur a3, threadptr #endif -2: j common_exception_exit + j common_exception_exit /* This is the kernel exception exit. * We avoided to do a MOVSP when we entered the exception, but we @@ -1001,9 +1002,8 @@ ENTRY(fast_syscall_xtensa) movi a7, 4 # sizeof(unsigned int) access_ok a3, a7, a0, a2, .Leac # a0: scratch reg, a2: sp - addi a6, a6, -1 # assuming SYS_XTENSA_ATOMIC_SET = 1 - _bgeui a6, SYS_XTENSA_COUNT - 1, .Lill - _bnei a6, SYS_XTENSA_ATOMIC_CMP_SWP - 1, .Lnswp + _bgeui a6, SYS_XTENSA_COUNT, .Lill + _bnei a6, SYS_XTENSA_ATOMIC_CMP_SWP, .Lnswp /* Fall through for ATOMIC_CMP_SWP. */ @@ -1015,27 +1015,26 @@ TRY s32i a5, a3, 0 # different, modify value l32i a7, a2, PT_AREG7 # restore a7 l32i a0, a2, PT_AREG0 # restore a0 movi a2, 1 # and return 1 - addi a6, a6, 1 # restore a6 (really necessary?) rfe 1: l32i a7, a2, PT_AREG7 # restore a7 l32i a0, a2, PT_AREG0 # restore a0 movi a2, 0 # return 0 (note that we cannot set - addi a6, a6, 1 # restore a6 (really necessary?) rfe .Lnswp: /* Atomic set, add, and exg_add. */ TRY l32i a7, a3, 0 # orig + addi a6, a6, -SYS_XTENSA_ATOMIC_SET add a0, a4, a7 # + arg moveqz a0, a4, a6 # set + addi a6, a6, SYS_XTENSA_ATOMIC_SET TRY s32i a0, a3, 0 # write new value mov a0, a2 mov a2, a7 l32i a7, a0, PT_AREG7 # restore a7 l32i a0, a0, PT_AREG0 # restore a0 - addi a6, a6, 1 # restore a6 (really necessary?) rfe CATCH @@ -1044,7 +1043,7 @@ CATCH movi a2, -EFAULT rfe -.Lill: l32i a7, a2, PT_AREG0 # restore a7 +.Lill: l32i a7, a2, PT_AREG7 # restore a7 l32i a0, a2, PT_AREG0 # restore a0 movi a2, -EINVAL rfe @@ -1565,7 +1564,7 @@ ENTRY(fast_second_level_miss) rsr a0, excvaddr bltu a0, a3, 2f - addi a1, a0, -(2 << (DCACHE_ALIAS_ORDER + PAGE_SHIFT)) + addi a1, a0, -TLBTEMP_SIZE bgeu a1, a3, 2f /* Check if we have to restore an ITLB mapping. */ @@ -1794,7 +1793,7 @@ ENDPROC(system_call) mov a12, a0 .endr #endif - _entry a1, 48 + _entry a1, 16 #if XCHAL_NUM_AREGS % 12 == 0 mov a8, a8 #elif XCHAL_NUM_AREGS % 12 == 4 @@ -1818,9 +1817,8 @@ ENDPROC(system_call) ENTRY(_switch_to) - entry a1, 16 + entry a1, 48 - mov a10, a2 # preserve 'prev' (a2) mov a11, a3 # and 'next' (a3) l32i a4, a2, TASK_THREAD_INFO @@ -1828,8 +1826,14 @@ ENTRY(_switch_to) save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER - s32i a0, a10, THREAD_RA # save return address - s32i a1, a10, THREAD_SP # save stack pointer +#if THREAD_RA > 1020 || THREAD_SP > 1020 + addi a10, a2, TASK_THREAD + s32i a0, a10, THREAD_RA - TASK_THREAD # save return address + s32i a1, a10, THREAD_SP - TASK_THREAD # save stack pointer +#else + s32i a0, a2, THREAD_RA # save return address + s32i a1, a2, THREAD_SP # save stack pointer +#endif /* Disable ints while we manipulate the stack pointer. */ @@ -1870,7 +1874,6 @@ ENTRY(_switch_to) load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER wsr a14, ps - mov a2, a10 # return 'prev' rsync retw diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c index 2d9cc6d..e8b76b8 100644 --- a/arch/xtensa/kernel/pci-dma.c +++ b/arch/xtensa/kernel/pci-dma.c @@ -49,9 +49,8 @@ dma_alloc_coherent(struct device *dev,size_t size,dma_addr_t *handle,gfp_t flag) /* We currently don't support coherent memory outside KSEG */ - if (ret < XCHAL_KSEG_CACHED_VADDR - || ret >= XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE) - BUG(); + BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR || + ret > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1); if (ret != 0) { @@ -68,10 +67,11 @@ EXPORT_SYMBOL(dma_alloc_coherent); void dma_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle) { - long addr=(long)vaddr+XCHAL_KSEG_CACHED_VADDR-XCHAL_KSEG_BYPASS_VADDR; + unsigned long addr = (unsigned long)vaddr + + XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR; - if (addr < 0 || addr >= XCHAL_KSEG_SIZE) - BUG(); + BUG_ON(addr < XCHAL_KSEG_CACHED_VADDR || + addr > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1); free_pages(addr, get_order(size)); } diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S index f9e1ec3..8453e6e 100644 --- a/arch/xtensa/kernel/vectors.S +++ b/arch/xtensa/kernel/vectors.S @@ -376,38 +376,42 @@ _DoubleExceptionVector_WindowOverflow: beqz a2, 1f # if at start of vector, don't restore addi a0, a0, -128 - bbsi a0, 8, 1f # don't restore except for overflow 8 and 12 - bbsi a0, 7, 2f + bbsi.l a0, 8, 1f # don't restore except for overflow 8 and 12 + + /* + * This fixup handler is for the extremely unlikely case where the + * overflow handler's reference thru a0 gets a hardware TLB refill + * that bumps out the (distinct, aliasing) TLB entry that mapped its + * prior references thru a9/a13, and where our reference now thru + * a9/a13 gets a 2nd-level miss exception (not hardware TLB refill). + */ + movi a2, window_overflow_restore_a0_fixup + s32i a2, a3, EXC_TABLE_FIXUP + l32i a2, a3, EXC_TABLE_DOUBLE_SAVE + xsr a3, excsave1 + + bbsi.l a0, 7, 2f /* * Restore a0 as saved by _WindowOverflow8(). - * - * FIXME: we really need a fixup handler for this L32E, - * for the extremely unlikely case where the overflow handler's - * reference thru a0 gets a hardware TLB refill that bumps out - * the (distinct, aliasing) TLB entry that mapped its prior - * references thru a9, and where our reference now thru a9 - * gets a 2nd-level miss exception (not hardware TLB refill). */ - l32e a2, a9, -16 - wsr a2, depc # replace the saved a0 - j 1f + l32e a0, a9, -16 + wsr a0, depc # replace the saved a0 + j 3f 2: /* * Restore a0 as saved by _WindowOverflow12(). - * - * FIXME: we really need a fixup handler for this L32E, - * for the extremely unlikely case where the overflow handler's - * reference thru a0 gets a hardware TLB refill that bumps out - * the (distinct, aliasing) TLB entry that mapped its prior - * references thru a13, and where our reference now thru a13 - * gets a 2nd-level miss exception (not hardware TLB refill). */ - l32e a2, a13, -16 - wsr a2, depc # replace the saved a0 + l32e a0, a13, -16 + wsr a0, depc # replace the saved a0 +3: + xsr a3, excsave1 + movi a0, 0 + s32i a0, a3, EXC_TABLE_FIXUP + s32i a2, a3, EXC_TABLE_DOUBLE_SAVE 1: /* * Restore WindowBase while leaving all address registers restored. @@ -449,6 +453,7 @@ _DoubleExceptionVector_WindowOverflow: s32i a0, a2, PT_DEPC +_DoubleExceptionVector_handle_exception: addx4 a0, a0, a3 l32i a0, a0, EXC_TABLE_FAST_USER xsr a3, excsave1 @@ -464,11 +469,120 @@ _DoubleExceptionVector_WindowOverflow: rotw -3 j 1b - .end literal_prefix ENDPROC(_DoubleExceptionVector) /* + * Fixup handler for TLB miss in double exception handler for window owerflow. + * We get here with windowbase set to the window that was being spilled and + * a0 trashed. a0 bit 7 determines if this is a call8 (bit clear) or call12 + * (bit set) window. + * + * We do the following here: + * - go to the original window retaining a0 value; + * - set up exception stack to return back to appropriate a0 restore code + * (we'll need to rotate window back and there's no place to save this + * information, use different return address for that); + * - handle the exception; + * - go to the window that was being spilled; + * - set up window_overflow_restore_a0_fixup as a fixup routine; + * - reload a0; + * - restore the original window; + * - reset the default fixup routine; + * - return to user. By the time we get to this fixup handler all information + * about the conditions of the original double exception that happened in + * the window overflow handler is lost, so we just return to userspace to + * retry overflow from start. + * + * a0: value of depc, original value in depc + * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE + * a3: exctable, original value in excsave1 + */ + +ENTRY(window_overflow_restore_a0_fixup) + + rsr a0, ps + extui a0, a0, PS_OWB_SHIFT, PS_OWB_WIDTH + rsr a2, windowbase + sub a0, a2, a0 + extui a0, a0, 0, 3 + l32i a2, a3, EXC_TABLE_DOUBLE_SAVE + xsr a3, excsave1 + + _beqi a0, 1, .Lhandle_1 + _beqi a0, 3, .Lhandle_3 + + .macro overflow_fixup_handle_exception_pane n + + rsr a0, depc + rotw -\n + + xsr a3, excsave1 + wsr a2, depc + l32i a2, a3, EXC_TABLE_KSTK + s32i a0, a2, PT_AREG0 + + movi a0, .Lrestore_\n + s32i a0, a2, PT_DEPC + rsr a0, exccause + j _DoubleExceptionVector_handle_exception + + .endm + + overflow_fixup_handle_exception_pane 2 +.Lhandle_1: + overflow_fixup_handle_exception_pane 1 +.Lhandle_3: + overflow_fixup_handle_exception_pane 3 + + .macro overflow_fixup_restore_a0_pane n + + rotw \n + /* Need to preserve a0 value here to be able to handle exception + * that may occur on a0 reload from stack. It may occur because + * TLB miss handler may not be atomic and pointer to page table + * may be lost before we get here. There are no free registers, + * so we need to use EXC_TABLE_DOUBLE_SAVE area. + */ + xsr a3, excsave1 + s32i a2, a3, EXC_TABLE_DOUBLE_SAVE + movi a2, window_overflow_restore_a0_fixup + s32i a2, a3, EXC_TABLE_FIXUP + l32i a2, a3, EXC_TABLE_DOUBLE_SAVE + xsr a3, excsave1 + bbsi.l a0, 7, 1f + l32e a0, a9, -16 + j 2f +1: + l32e a0, a13, -16 +2: + rotw -\n + + .endm + +.Lrestore_2: + overflow_fixup_restore_a0_pane 2 + +.Lset_default_fixup: + xsr a3, excsave1 + s32i a2, a3, EXC_TABLE_DOUBLE_SAVE + movi a2, 0 + s32i a2, a3, EXC_TABLE_FIXUP + l32i a2, a3, EXC_TABLE_DOUBLE_SAVE + xsr a3, excsave1 + rfe + +.Lrestore_1: + overflow_fixup_restore_a0_pane 1 + j .Lset_default_fixup +.Lrestore_3: + overflow_fixup_restore_a0_pane 3 + j .Lset_default_fixup + +ENDPROC(window_overflow_restore_a0_fixup) + + .end literal_prefix +/* * Debug interrupt vector * * There is not much space here, so simply jump to another handler. diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S index ee32c00..d16db6d 100644 --- a/arch/xtensa/kernel/vmlinux.lds.S +++ b/arch/xtensa/kernel/vmlinux.lds.S @@ -269,13 +269,13 @@ SECTIONS .UserExceptionVector.literal) SECTION_VECTOR (_DoubleExceptionVector_literal, .DoubleExceptionVector.literal, - DOUBLEEXC_VECTOR_VADDR - 16, + DOUBLEEXC_VECTOR_VADDR - 40, SIZEOF(.UserExceptionVector.text), .UserExceptionVector.text) SECTION_VECTOR (_DoubleExceptionVector_text, .DoubleExceptionVector.text, DOUBLEEXC_VECTOR_VADDR, - 32, + 40, .DoubleExceptionVector.literal) . = (LOADADDR( .DoubleExceptionVector.text ) + SIZEOF( .DoubleExceptionVector.text ) + 3) & ~ 3; diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index b57c4f9..9e3571a 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -117,6 +117,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index d05f8fe..17b1ef3 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -349,8 +349,8 @@ static void iss_net_timer(unsigned long priv) { struct iss_net_private *lp = (struct iss_net_private *)priv; - spin_lock(&lp->lock); iss_net_poll(); + spin_lock(&lp->lock); mod_timer(&lp->timer, jiffies + lp->timer_val); spin_unlock(&lp->lock); } @@ -361,7 +361,7 @@ static int iss_net_open(struct net_device *dev) struct iss_net_private *lp = netdev_priv(dev); int err; - spin_lock(&lp->lock); + spin_lock_bh(&lp->lock); err = lp->tp.open(lp); if (err < 0) @@ -376,9 +376,11 @@ static int iss_net_open(struct net_device *dev) while ((err = iss_net_rx(dev)) > 0) ; - spin_lock(&opened_lock); + spin_unlock_bh(&lp->lock); + spin_lock_bh(&opened_lock); list_add(&lp->opened_list, &opened); - spin_unlock(&opened_lock); + spin_unlock_bh(&opened_lock); + spin_lock_bh(&lp->lock); init_timer(&lp->timer); lp->timer_val = ISS_NET_TIMER_VALUE; @@ -387,7 +389,7 @@ static int iss_net_open(struct net_device *dev) mod_timer(&lp->timer, jiffies + lp->timer_val); out: - spin_unlock(&lp->lock); + spin_unlock_bh(&lp->lock); return err; } @@ -395,7 +397,7 @@ static int iss_net_close(struct net_device *dev) { struct iss_net_private *lp = netdev_priv(dev); netif_stop_queue(dev); - spin_lock(&lp->lock); + spin_lock_bh(&lp->lock); spin_lock(&opened_lock); list_del(&opened); @@ -405,18 +407,17 @@ static int iss_net_close(struct net_device *dev) lp->tp.close(lp); - spin_unlock(&lp->lock); + spin_unlock_bh(&lp->lock); return 0; } static int iss_net_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct iss_net_private *lp = netdev_priv(dev); - unsigned long flags; int len; netif_stop_queue(dev); - spin_lock_irqsave(&lp->lock, flags); + spin_lock_bh(&lp->lock); len = lp->tp.write(lp, &skb); @@ -438,7 +439,7 @@ static int iss_net_start_xmit(struct sk_buff *skb, struct net_device *dev) pr_err("%s: %s failed(%d)\n", dev->name, __func__, len); } - spin_unlock_irqrestore(&lp->lock, flags); + spin_unlock_bh(&lp->lock); dev_kfree_skb(skb); return NETDEV_TX_OK; @@ -466,9 +467,9 @@ static int iss_net_set_mac(struct net_device *dev, void *addr) if (!is_valid_ether_addr(hwaddr->sa_data)) return -EADDRNOTAVAIL; - spin_lock(&lp->lock); + spin_lock_bh(&lp->lock); memcpy(dev->dev_addr, hwaddr->sa_data, ETH_ALEN); - spin_unlock(&lp->lock); + spin_unlock_bh(&lp->lock); return 0; } @@ -520,11 +521,11 @@ static int iss_net_configure(int index, char *init) *lp = (struct iss_net_private) { .device_list = LIST_HEAD_INIT(lp->device_list), .opened_list = LIST_HEAD_INIT(lp->opened_list), - .lock = __SPIN_LOCK_UNLOCKED(lp.lock), .dev = dev, .index = index, - }; + }; + spin_lock_init(&lp->lock); /* * If this name ends up conflicting with an existing registered * netdevice, that is OK, register_netdev{,ice}() will notice this diff --git a/arch/xtensa/platforms/xtfpga/Makefile b/arch/xtensa/platforms/xtfpga/Makefile index b9ae206..7839d38 100644 --- a/arch/xtensa/platforms/xtfpga/Makefile +++ b/arch/xtensa/platforms/xtfpga/Makefile @@ -6,4 +6,5 @@ # # Note 2! The CFLAGS definitions are in the main makefile... -obj-y = setup.o lcd.o +obj-y += setup.o +obj-$(CONFIG_XTFPGA_LCD) += lcd.o diff --git a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h index aeb316b..e8cc86f 100644 --- a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h +++ b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h @@ -40,9 +40,6 @@ /* UART */ #define DUART16552_PADDR (XCHAL_KIO_PADDR + 0x0D050020) -/* LCD instruction and data addresses. */ -#define LCD_INSTR_ADDR ((char *)IOADDR(0x0D040000)) -#define LCD_DATA_ADDR ((char *)IOADDR(0x0D040004)) /* Misc. */ #define XTFPGA_FPGAREGS_VADDR IOADDR(0x0D020000) diff --git a/arch/xtensa/platforms/xtfpga/include/platform/lcd.h b/arch/xtensa/platforms/xtfpga/include/platform/lcd.h index 0e43564..4c8541e 100644 --- a/arch/xtensa/platforms/xtfpga/include/platform/lcd.h +++ b/arch/xtensa/platforms/xtfpga/include/platform/lcd.h @@ -11,10 +11,25 @@ #ifndef __XTENSA_XTAVNET_LCD_H #define __XTENSA_XTAVNET_LCD_H +#ifdef CONFIG_XTFPGA_LCD /* Display string STR at position POS on the LCD. */ void lcd_disp_at_pos(char *str, unsigned char pos); /* Shift the contents of the LCD display left or right. */ void lcd_shiftleft(void); void lcd_shiftright(void); +#else +static inline void lcd_disp_at_pos(char *str, unsigned char pos) +{ +} + +static inline void lcd_shiftleft(void) +{ +} + +static inline void lcd_shiftright(void) +{ +} +#endif + #endif diff --git a/arch/xtensa/platforms/xtfpga/lcd.c b/arch/xtensa/platforms/xtfpga/lcd.c index 2872301..4dc0c1b 100644 --- a/arch/xtensa/platforms/xtfpga/lcd.c +++ b/arch/xtensa/platforms/xtfpga/lcd.c @@ -1,50 +1,63 @@ /* - * Driver for the LCD display on the Tensilica LX60 Board. + * Driver for the LCD display on the Tensilica XTFPGA board family. + * http://www.mytechcorp.com/cfdata/productFile/File1/MOC-16216B-B-A0A04.pdf * * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive * for more details. * * Copyright (C) 2001, 2006 Tensilica Inc. + * Copyright (C) 2015 Cadence Design Systems Inc. */ -/* - * - * FIXME: this code is from the examples from the LX60 user guide. - * - * The lcd_pause function does busy waiting, which is probably not - * great. Maybe the code could be changed to use kernel timers, or - * change the hardware to not need to wait. - */ - +#include #include #include #include #include -#include -#define LCD_PAUSE_ITERATIONS 4000 +/* LCD instruction and data addresses. */ +#define LCD_INSTR_ADDR ((char *)IOADDR(CONFIG_XTFPGA_LCD_BASE_ADDR)) +#define LCD_DATA_ADDR (LCD_INSTR_ADDR + 4) + #define LCD_CLEAR 0x1 #define LCD_DISPLAY_ON 0xc /* 8bit and 2 lines display */ #define LCD_DISPLAY_MODE8BIT 0x38 +#define LCD_DISPLAY_MODE4BIT 0x28 #define LCD_DISPLAY_POS 0x80 #define LCD_SHIFT_LEFT 0x18 #define LCD_SHIFT_RIGHT 0x1c +static void lcd_put_byte(u8 *addr, u8 data) +{ +#ifdef CONFIG_XTFPGA_LCD_8BIT_ACCESS + ACCESS_ONCE(*addr) = data; +#else + ACCESS_ONCE(*addr) = data & 0xf0; + ACCESS_ONCE(*addr) = (data << 4) & 0xf0; +#endif +} + static int __init lcd_init(void) { - *LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT; + ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; mdelay(5); - *LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT; + ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; udelay(200); - *LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT; + ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; + udelay(50); +#ifndef CONFIG_XTFPGA_LCD_8BIT_ACCESS + ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE4BIT; + udelay(50); + lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_MODE4BIT); udelay(50); - *LCD_INSTR_ADDR = LCD_DISPLAY_ON; +#endif + lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_ON); udelay(50); - *LCD_INSTR_ADDR = LCD_CLEAR; + lcd_put_byte(LCD_INSTR_ADDR, LCD_CLEAR); mdelay(10); lcd_disp_at_pos("XTENSA LINUX", 0); return 0; @@ -52,10 +65,10 @@ static int __init lcd_init(void) void lcd_disp_at_pos(char *str, unsigned char pos) { - *LCD_INSTR_ADDR = LCD_DISPLAY_POS | pos; + lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_POS | pos); udelay(100); while (*str != 0) { - *LCD_DATA_ADDR = *str; + lcd_put_byte(LCD_DATA_ADDR, *str); udelay(200); str++; } @@ -63,13 +76,13 @@ void lcd_disp_at_pos(char *str, unsigned char pos) void lcd_shiftleft(void) { - *LCD_INSTR_ADDR = LCD_SHIFT_LEFT; + lcd_put_byte(LCD_INSTR_ADDR, LCD_SHIFT_LEFT); udelay(50); } void lcd_shiftright(void) { - *LCD_INSTR_ADDR = LCD_SHIFT_RIGHT; + lcd_put_byte(LCD_INSTR_ADDR, LCD_SHIFT_RIGHT); udelay(50); } diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index dd0dd2d..a717585 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -703,8 +703,12 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, return -EINVAL; disk = get_gendisk(MKDEV(major, minor), &part); - if (!disk || part) + if (!disk) return -EINVAL; + if (part) { + put_disk(disk); + return -EINVAL; + } rcu_read_lock(); spin_lock_irq(disk->queue->queue_lock); @@ -859,6 +863,13 @@ void blkcg_drain_queue(struct request_queue *q) { lockdep_assert_held(q->queue_lock); + /* + * @q could be exiting and already have destroyed all blkgs as + * indicated by NULL root_blkg. If so, don't confuse policies. + */ + if (!q->root_blkg) + return; + blk_throtl_drain(q); } diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c index f872127..78d3835 100644 --- a/block/blk-mq-cpumap.c +++ b/block/blk-mq-cpumap.c @@ -95,7 +95,7 @@ unsigned int *blk_mq_make_queue_map(struct blk_mq_reg *reg) unsigned int *map; /* If cpus are offline, map them to first hctx */ - map = kzalloc_node(sizeof(*map) * num_possible_cpus(), GFP_KERNEL, + map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL, reg->numa_node); if (!map) return NULL; diff --git a/block/blk-settings.c b/block/blk-settings.c index 5d21239..95138e9 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -553,7 +553,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, bottom = max(b->physical_block_size, b->io_min) + alignment; /* Verify that top and bottom intervals line up */ - if (max(top, bottom) & (min(top, bottom) - 1)) { + if (max(top, bottom) % min(top, bottom)) { t->misaligned = 1; ret = -1; } @@ -598,7 +598,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, /* Find lowest common alignment_offset */ t->alignment_offset = lcm(t->alignment_offset, alignment) - & (max(t->physical_block_size, t->io_min) - 1); + % max(t->physical_block_size, t->io_min); /* Verify that new alignment_offset is on a logical block boundary */ if (t->alignment_offset & (t->logical_block_size - 1)) { diff --git a/block/blk-tag.c b/block/blk-tag.c index 3f33d86..a185b86 100644 --- a/block/blk-tag.c +++ b/block/blk-tag.c @@ -27,18 +27,15 @@ struct request *blk_queue_find_tag(struct request_queue *q, int tag) EXPORT_SYMBOL(blk_queue_find_tag); /** - * __blk_free_tags - release a given set of tag maintenance info + * blk_free_tags - release a given set of tag maintenance info * @bqt: the tag map to free * - * Tries to free the specified @bqt. Returns true if it was - * actually freed and false if there are still references using it + * Drop the reference count on @bqt and frees it when the last reference + * is dropped. */ -static int __blk_free_tags(struct blk_queue_tag *bqt) +void blk_free_tags(struct blk_queue_tag *bqt) { - int retval; - - retval = atomic_dec_and_test(&bqt->refcnt); - if (retval) { + if (atomic_dec_and_test(&bqt->refcnt)) { BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) < bqt->max_depth); @@ -50,9 +47,8 @@ static int __blk_free_tags(struct blk_queue_tag *bqt) kfree(bqt); } - - return retval; } +EXPORT_SYMBOL(blk_free_tags); /** * __blk_queue_free_tags - release tag maintenance info @@ -69,28 +65,13 @@ void __blk_queue_free_tags(struct request_queue *q) if (!bqt) return; - __blk_free_tags(bqt); + blk_free_tags(bqt); q->queue_tags = NULL; queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q); } /** - * blk_free_tags - release a given set of tag maintenance info - * @bqt: the tag map to free - * - * For externally managed @bqt frees the map. Callers of this - * function must guarantee to have released all the queues that - * might have been using this tag map. - */ -void blk_free_tags(struct blk_queue_tag *bqt) -{ - if (unlikely(!__blk_free_tags(bqt))) - BUG(); -} -EXPORT_SYMBOL(blk_free_tags); - -/** * blk_queue_free_tags - release tag maintenance info * @q: the request queue for the device * diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 1474c3a..1599878 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1292,6 +1292,9 @@ static u64 tg_prfill_cpu_rwstat(struct seq_file *sf, struct blkg_rwstat rwstat = { }, tmp; int i, cpu; + if (tg->stats_cpu == NULL) + return 0; + for_each_possible_cpu(cpu) { struct tg_stats_cpu *sc = per_cpu_ptr(tg->stats_cpu, cpu); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 744833b..d9bba99 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -1275,12 +1275,16 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) static void cfq_update_group_weight(struct cfq_group *cfqg) { - BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node)); - if (cfqg->new_weight) { cfqg->weight = cfqg->new_weight; cfqg->new_weight = 0; } +} + +static void +cfq_update_group_leaf_weight(struct cfq_group *cfqg) +{ + BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node)); if (cfqg->new_leaf_weight) { cfqg->leaf_weight = cfqg->new_leaf_weight; @@ -1299,7 +1303,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) /* add to the service tree */ BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node)); - cfq_update_group_weight(cfqg); + cfq_update_group_leaf_weight(cfqg); __cfq_group_service_tree_add(st, cfqg); /* @@ -1323,6 +1327,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) */ while ((parent = cfqg_parent(pos))) { if (propagate) { + cfq_update_group_weight(pos); propagate = !parent->nr_active++; parent->children_weight += pos->weight; } @@ -3580,6 +3585,11 @@ retry: blkcg = bio_blkcg(bio); cfqg = cfq_lookup_create_cfqg(cfqd, blkcg); + if (!cfqg) { + cfqq = &cfqd->oom_cfqq; + goto out; + } + cfqq = cic_to_cfqq(cic, is_sync); /* @@ -3616,7 +3626,7 @@ retry: } else cfqq = &cfqd->oom_cfqq; } - +out: if (new_cfqq) kmem_cache_free(cfq_pool, new_cfqq); @@ -3646,12 +3656,17 @@ static struct cfq_queue * cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic, struct bio *bio, gfp_t gfp_mask) { - const int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio); - const int ioprio = IOPRIO_PRIO_DATA(cic->ioprio); + int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio); + int ioprio = IOPRIO_PRIO_DATA(cic->ioprio); struct cfq_queue **async_cfqq = NULL; struct cfq_queue *cfqq = NULL; if (!is_sync) { + if (!ioprio_valid(cic->ioprio)) { + struct task_struct *tsk = current; + ioprio = task_nice_ioprio(tsk); + ioprio_class = task_nice_ioclass(tsk); + } async_cfqq = cfq_async_queue_prio(cfqd, ioprio_class, ioprio); cfqq = *async_cfqq; } diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index fbd5a67..a0926a6 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -690,6 +690,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) case BLKROSET: case BLKDISCARD: case BLKSECDISCARD: + case BLKZEROOUT: /* * the ones below are implemented in blkdev_locked_ioctl, * but we call blkdev_ioctl, which gets the lock for us diff --git a/block/genhd.c b/block/genhd.c index 791f419..9316f5f 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -28,10 +28,10 @@ struct kobject *block_depr; /* for extended dynamic devt allocation, currently only one major is used */ #define NR_EXT_DEVT (1 << MINORBITS) -/* For extended devt allocation. ext_devt_mutex prevents look up +/* For extended devt allocation. ext_devt_lock prevents look up * results from going away underneath its user. */ -static DEFINE_MUTEX(ext_devt_mutex); +static DEFINE_SPINLOCK(ext_devt_lock); static DEFINE_IDR(ext_devt_idr); static struct device_type disk_type; @@ -420,9 +420,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt) } /* allocate ext devt */ - mutex_lock(&ext_devt_mutex); - idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_KERNEL); - mutex_unlock(&ext_devt_mutex); + idr_preload(GFP_KERNEL); + + spin_lock_bh(&ext_devt_lock); + idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT); + spin_unlock_bh(&ext_devt_lock); + + idr_preload_end(); if (idx < 0) return idx == -ENOSPC ? -EBUSY : idx; @@ -441,15 +445,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt) */ void blk_free_devt(dev_t devt) { - might_sleep(); - if (devt == MKDEV(0, 0)) return; if (MAJOR(devt) == BLOCK_EXT_MAJOR) { - mutex_lock(&ext_devt_mutex); + spin_lock_bh(&ext_devt_lock); idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); - mutex_unlock(&ext_devt_mutex); + spin_unlock_bh(&ext_devt_lock); } } @@ -665,7 +667,6 @@ void del_gendisk(struct gendisk *disk) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); device_del(disk_to_dev(disk)); - blk_free_devt(disk_to_dev(disk)->devt); } EXPORT_SYMBOL(del_gendisk); @@ -690,13 +691,13 @@ struct gendisk *get_gendisk(dev_t devt, int *partno) } else { struct hd_struct *part; - mutex_lock(&ext_devt_mutex); + spin_lock_bh(&ext_devt_lock); part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); if (part && get_disk(part_to_disk(part))) { *partno = part->partno; disk = part_to_disk(part); } - mutex_unlock(&ext_devt_mutex); + spin_unlock_bh(&ext_devt_lock); } return disk; @@ -1069,9 +1070,16 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno) struct disk_part_tbl *old_ptbl = disk->part_tbl; struct disk_part_tbl *new_ptbl; int len = old_ptbl ? old_ptbl->len : 0; - int target = partno + 1; + int i, target; size_t size; - int i; + + /* + * check for int overflow, since we can get here from blkpg_ioctl() + * with a user passed 'partno'. + */ + target = partno + 1; + if (target < 0) + return -EINVAL; /* disk_max_parts() is zero during initialization, ignore if so */ if (disk_max_parts(disk) && target > disk_max_parts(disk)) @@ -1098,6 +1106,7 @@ static void disk_release(struct device *dev) { struct gendisk *disk = dev_to_disk(dev); + blk_free_devt(dev->devt); disk_release_events(disk); kfree(disk->random); disk_replace_part_tbl(disk, NULL); diff --git a/block/partition-generic.c b/block/partition-generic.c index 789cdea..0d9e5f9 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -211,6 +211,7 @@ static const struct attribute_group *part_attr_groups[] = { static void part_release(struct device *dev) { struct hd_struct *p = dev_to_part(dev); + blk_free_devt(dev->devt); free_part_stats(p); free_part_info(p); kfree(p); @@ -253,7 +254,6 @@ void delete_partition(struct gendisk *disk, int partno) rcu_assign_pointer(ptbl->last_lookup, NULL); kobject_put(part->holder_dir); device_del(part_to_dev(part)); - blk_free_devt(part_devt(part)); hd_struct_put(part); } diff --git a/block/partitions/aix.c b/block/partitions/aix.c index 43be471..0931f51 100644 --- a/block/partitions/aix.c +++ b/block/partitions/aix.c @@ -253,7 +253,7 @@ int aix_partition(struct parsed_partitions *state) continue; } lv_ix = be16_to_cpu(p->lv_ix) - 1; - if (lv_ix > state->limit) { + if (lv_ix >= state->limit) { cur_lv_ix = -1; continue; } diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 2648797..4044cf7 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -489,7 +489,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) { err = DRIVER_ERROR << 24; - goto out; + goto error; } memset(sense, 0, sizeof(sense)); @@ -499,7 +499,6 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, blk_execute_rq(q, disk, rq, 0); -out: err = rq->errors & 0xff; /* only 8 bit SCSI status */ if (err) { if (rq->sense_len && rq->sense) { diff --git a/crypto/842.c b/crypto/842.c index 65c7a89c..b48f4f1 100644 --- a/crypto/842.c +++ b/crypto/842.c @@ -180,3 +180,4 @@ module_exit(nx842_mod_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("842 Compression Algorithm"); +MODULE_ALIAS_CRYPTO("842"); diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c index fd0d6b4..3dd1011 100644 --- a/crypto/aes_generic.c +++ b/crypto/aes_generic.c @@ -1474,4 +1474,5 @@ module_exit(aes_fini); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_ALIAS("aes"); +MODULE_ALIAS_CRYPTO("aes"); +MODULE_ALIAS_CRYPTO("aes-generic"); diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 966f893..1de4bee 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -21,6 +21,7 @@ #include #include #include +#include struct alg_type_list { const struct af_alg_type *type; @@ -243,6 +244,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) sock_init_data(newsock, sk2); sock_graft(sk2, newsock); + security_sk_clone(sk, sk2); err = type->accept(ask->private, sk2); if (err) { @@ -447,6 +449,9 @@ void af_alg_complete(struct crypto_async_request *req, int err) { struct af_alg_completion *completion = req->data; + if (err == -EINPROGRESS) + return; + completion->err = err; complete(&completion->completion); } diff --git a/crypto/algapi.c b/crypto/algapi.c index 7a1ae87..00d8d93 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -495,8 +495,8 @@ static struct crypto_template *__crypto_lookup_template(const char *name) struct crypto_template *crypto_lookup_template(const char *name) { - return try_then_request_module(__crypto_lookup_template(name), "%s", - name); + return try_then_request_module(__crypto_lookup_template(name), + "crypto-%s", name); } EXPORT_SYMBOL_GPL(crypto_lookup_template); diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index a19c027..83187f4 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -49,7 +49,7 @@ struct skcipher_ctx { struct ablkcipher_request req; }; -#define MAX_SGL_ENTS ((PAGE_SIZE - sizeof(struct skcipher_sg_list)) / \ +#define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \ sizeof(struct scatterlist) - 1) static inline int skcipher_sndbuf(struct sock *sk) diff --git a/crypto/ansi_cprng.c b/crypto/ansi_cprng.c index 666f196..6f5bebc 100644 --- a/crypto/ansi_cprng.c +++ b/crypto/ansi_cprng.c @@ -476,4 +476,5 @@ module_param(dbg, int, 0); MODULE_PARM_DESC(dbg, "Boolean to enable debugging (0/1 == off/on)"); module_init(prng_mod_init); module_exit(prng_mod_fini); -MODULE_ALIAS("stdrng"); +MODULE_ALIAS_CRYPTO("stdrng"); +MODULE_ALIAS_CRYPTO("ansi_cprng"); diff --git a/crypto/anubis.c b/crypto/anubis.c index 008c8a4..4bb187c 100644 --- a/crypto/anubis.c +++ b/crypto/anubis.c @@ -704,3 +704,4 @@ module_exit(anubis_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Anubis Cryptographic Algorithm"); +MODULE_ALIAS_CRYPTO("anubis"); diff --git a/crypto/api.c b/crypto/api.c index a2b39c5..2a81e98 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -216,11 +216,11 @@ struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, u32 mask) alg = crypto_alg_lookup(name, type, mask); if (!alg) { - request_module("%s", name); + request_module("crypto-%s", name); if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask & CRYPTO_ALG_NEED_FALLBACK)) - request_module("%s-all", name); + request_module("crypto-%s-all", name); alg = crypto_alg_lookup(name, type, mask); } diff --git a/crypto/arc4.c b/crypto/arc4.c index 5a772c3..f1a8192 100644 --- a/crypto/arc4.c +++ b/crypto/arc4.c @@ -166,3 +166,4 @@ module_exit(arc4_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ARC4 Cipher Algorithm"); MODULE_AUTHOR("Jon Oberheide "); +MODULE_ALIAS_CRYPTO("arc4"); diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 3c562f5..e1bce26 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -78,8 +78,6 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap, tx = dma->device_prep_dma_xor(chan, dma_dest, src_list, xor_src_cnt, unmap->len, dma_flags); - src_list[0] = tmp; - if (unlikely(!tx)) async_tx_quiesce(&submit->depend_tx); @@ -92,6 +90,7 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap, xor_src_cnt, unmap->len, dma_flags); } + src_list[0] = tmp; dma_set_unmap(tx, unmap); async_tx_submit(chan, tx, submit); diff --git a/crypto/authenc.c b/crypto/authenc.c index e122355..78fb16c 100644 --- a/crypto/authenc.c +++ b/crypto/authenc.c @@ -721,3 +721,4 @@ module_exit(crypto_authenc_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Simple AEAD wrapper for IPsec"); +MODULE_ALIAS_CRYPTO("authenc"); diff --git a/crypto/authencesn.c b/crypto/authencesn.c index 4be0dd4..024bff2 100644 --- a/crypto/authencesn.c +++ b/crypto/authencesn.c @@ -814,3 +814,4 @@ module_exit(crypto_authenc_esn_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steffen Klassert "); MODULE_DESCRIPTION("AEAD wrapper for IPsec with extended sequence numbers"); +MODULE_ALIAS_CRYPTO("authencesn"); diff --git a/crypto/blowfish_generic.c b/crypto/blowfish_generic.c index 8baf544..87b392a 100644 --- a/crypto/blowfish_generic.c +++ b/crypto/blowfish_generic.c @@ -138,4 +138,5 @@ module_exit(blowfish_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Blowfish Cipher Algorithm"); -MODULE_ALIAS("blowfish"); +MODULE_ALIAS_CRYPTO("blowfish"); +MODULE_ALIAS_CRYPTO("blowfish-generic"); diff --git a/crypto/camellia_generic.c b/crypto/camellia_generic.c index 26bcd7a..a02286b 100644 --- a/crypto/camellia_generic.c +++ b/crypto/camellia_generic.c @@ -1098,4 +1098,5 @@ module_exit(camellia_fini); MODULE_DESCRIPTION("Camellia Cipher Algorithm"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("camellia"); +MODULE_ALIAS_CRYPTO("camellia"); +MODULE_ALIAS_CRYPTO("camellia-generic"); diff --git a/crypto/cast5_generic.c b/crypto/cast5_generic.c index 5558f63..df5c726 100644 --- a/crypto/cast5_generic.c +++ b/crypto/cast5_generic.c @@ -549,4 +549,5 @@ module_exit(cast5_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Cast5 Cipher Algorithm"); -MODULE_ALIAS("cast5"); +MODULE_ALIAS_CRYPTO("cast5"); +MODULE_ALIAS_CRYPTO("cast5-generic"); diff --git a/crypto/cast6_generic.c b/crypto/cast6_generic.c index de73252..058c8d7 100644 --- a/crypto/cast6_generic.c +++ b/crypto/cast6_generic.c @@ -291,4 +291,5 @@ module_exit(cast6_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Cast6 Cipher Algorithm"); -MODULE_ALIAS("cast6"); +MODULE_ALIAS_CRYPTO("cast6"); +MODULE_ALIAS_CRYPTO("cast6-generic"); diff --git a/crypto/cbc.c b/crypto/cbc.c index 61ac42e..780ee27 100644 --- a/crypto/cbc.c +++ b/crypto/cbc.c @@ -289,3 +289,4 @@ module_exit(crypto_cbc_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CBC block cipher algorithm"); +MODULE_ALIAS_CRYPTO("cbc"); diff --git a/crypto/ccm.c b/crypto/ccm.c index 1df8421..003bbbd 100644 --- a/crypto/ccm.c +++ b/crypto/ccm.c @@ -879,5 +879,6 @@ module_exit(crypto_ccm_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Counter with CBC MAC"); -MODULE_ALIAS("ccm_base"); -MODULE_ALIAS("rfc4309"); +MODULE_ALIAS_CRYPTO("ccm_base"); +MODULE_ALIAS_CRYPTO("rfc4309"); +MODULE_ALIAS_CRYPTO("ccm"); diff --git a/crypto/chainiv.c b/crypto/chainiv.c index 834d8dd..22b7e55 100644 --- a/crypto/chainiv.c +++ b/crypto/chainiv.c @@ -359,3 +359,4 @@ module_exit(chainiv_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Chain IV Generator"); +MODULE_ALIAS_CRYPTO("chainiv"); diff --git a/crypto/cmac.c b/crypto/cmac.c index 50880cf..7a8bfbd 100644 --- a/crypto/cmac.c +++ b/crypto/cmac.c @@ -313,3 +313,4 @@ module_exit(crypto_cmac_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CMAC keyed hash algorithm"); +MODULE_ALIAS_CRYPTO("cmac"); diff --git a/crypto/crc32.c b/crypto/crc32.c index 9d1c415..187ded2 100644 --- a/crypto/crc32.c +++ b/crypto/crc32.c @@ -156,3 +156,4 @@ module_exit(crc32_mod_fini); MODULE_AUTHOR("Alexander Boyko "); MODULE_DESCRIPTION("CRC32 calculations wrapper for lib/crc32"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_CRYPTO("crc32"); diff --git a/crypto/crc32c.c b/crypto/crc32c.c index 06f7018..238f0e6 100644 --- a/crypto/crc32c.c +++ b/crypto/crc32c.c @@ -170,3 +170,4 @@ module_exit(crc32c_mod_fini); MODULE_AUTHOR("Clay Haapala "); MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_CRYPTO("crc32c"); diff --git a/crypto/crct10dif_generic.c b/crypto/crct10dif_generic.c index 877e711..c1229614 100644 --- a/crypto/crct10dif_generic.c +++ b/crypto/crct10dif_generic.c @@ -124,4 +124,5 @@ module_exit(crct10dif_mod_fini); MODULE_AUTHOR("Tim Chen "); MODULE_DESCRIPTION("T10 DIF CRC calculation."); MODULE_LICENSE("GPL"); -MODULE_ALIAS("crct10dif"); +MODULE_ALIAS_CRYPTO("crct10dif"); +MODULE_ALIAS_CRYPTO("crct10dif-generic"); diff --git a/crypto/cryptd.c b/crypto/cryptd.c index 7bdd61b..75c415d 100644 --- a/crypto/cryptd.c +++ b/crypto/cryptd.c @@ -955,3 +955,4 @@ module_exit(cryptd_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Software async crypto daemon"); +MODULE_ALIAS_CRYPTO("cryptd"); diff --git a/crypto/crypto_null.c b/crypto/crypto_null.c index fee7265..7b39fa3 100644 --- a/crypto/crypto_null.c +++ b/crypto/crypto_null.c @@ -149,9 +149,9 @@ static struct crypto_alg null_algs[3] = { { .coa_decompress = null_compress } } } }; -MODULE_ALIAS("compress_null"); -MODULE_ALIAS("digest_null"); -MODULE_ALIAS("cipher_null"); +MODULE_ALIAS_CRYPTO("compress_null"); +MODULE_ALIAS_CRYPTO("digest_null"); +MODULE_ALIAS_CRYPTO("cipher_null"); static int __init crypto_null_mod_init(void) { diff --git a/crypto/ctr.c b/crypto/ctr.c index f2b94f2..2386f73 100644 --- a/crypto/ctr.c +++ b/crypto/ctr.c @@ -466,4 +466,5 @@ module_exit(crypto_ctr_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CTR Counter block mode"); -MODULE_ALIAS("rfc3686"); +MODULE_ALIAS_CRYPTO("rfc3686"); +MODULE_ALIAS_CRYPTO("ctr"); diff --git a/crypto/cts.c b/crypto/cts.c index 042223f..60b9da3 100644 --- a/crypto/cts.c +++ b/crypto/cts.c @@ -350,3 +350,4 @@ module_exit(crypto_cts_module_exit); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("CTS-CBC CipherText Stealing for CBC"); +MODULE_ALIAS_CRYPTO("cts"); diff --git a/crypto/deflate.c b/crypto/deflate.c index b57d70e..95d8d37 100644 --- a/crypto/deflate.c +++ b/crypto/deflate.c @@ -222,4 +222,4 @@ module_exit(deflate_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Deflate Compression Algorithm for IPCOMP"); MODULE_AUTHOR("James Morris "); - +MODULE_ALIAS_CRYPTO("deflate"); diff --git a/crypto/des_generic.c b/crypto/des_generic.c index f6cf63f..3ec6071 100644 --- a/crypto/des_generic.c +++ b/crypto/des_generic.c @@ -971,8 +971,6 @@ static struct crypto_alg des_algs[2] = { { .cia_decrypt = des3_ede_decrypt } } } }; -MODULE_ALIAS("des3_ede"); - static int __init des_generic_mod_init(void) { return crypto_register_algs(des_algs, ARRAY_SIZE(des_algs)); @@ -989,4 +987,7 @@ module_exit(des_generic_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms"); MODULE_AUTHOR("Dag Arne Osvik "); -MODULE_ALIAS("des"); +MODULE_ALIAS_CRYPTO("des"); +MODULE_ALIAS_CRYPTO("des-generic"); +MODULE_ALIAS_CRYPTO("des3_ede"); +MODULE_ALIAS_CRYPTO("des3_ede-generic"); diff --git a/crypto/ecb.c b/crypto/ecb.c index 935cfef..12011af 100644 --- a/crypto/ecb.c +++ b/crypto/ecb.c @@ -185,3 +185,4 @@ module_exit(crypto_ecb_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ECB block cipher algorithm"); +MODULE_ALIAS_CRYPTO("ecb"); diff --git a/crypto/eseqiv.c b/crypto/eseqiv.c index 42ce9f5..388f582 100644 --- a/crypto/eseqiv.c +++ b/crypto/eseqiv.c @@ -267,3 +267,4 @@ module_exit(eseqiv_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Encrypted Sequence Number IV Generator"); +MODULE_ALIAS_CRYPTO("eseqiv"); diff --git a/crypto/fcrypt.c b/crypto/fcrypt.c index 021d7fe..77286ea 100644 --- a/crypto/fcrypt.c +++ b/crypto/fcrypt.c @@ -420,3 +420,4 @@ module_exit(fcrypt_mod_fini); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("FCrypt Cipher Algorithm"); MODULE_AUTHOR("David Howells "); +MODULE_ALIAS_CRYPTO("fcrypt"); diff --git a/crypto/gcm.c b/crypto/gcm.c index b4f0179..9cea4d0 100644 --- a/crypto/gcm.c +++ b/crypto/gcm.c @@ -1441,6 +1441,7 @@ module_exit(crypto_gcm_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Galois/Counter Mode"); MODULE_AUTHOR("Mikko Herranen "); -MODULE_ALIAS("gcm_base"); -MODULE_ALIAS("rfc4106"); -MODULE_ALIAS("rfc4543"); +MODULE_ALIAS_CRYPTO("gcm_base"); +MODULE_ALIAS_CRYPTO("rfc4106"); +MODULE_ALIAS_CRYPTO("rfc4543"); +MODULE_ALIAS_CRYPTO("gcm"); diff --git a/crypto/ghash-generic.c b/crypto/ghash-generic.c index 9d3f0c6..bac7099 100644 --- a/crypto/ghash-generic.c +++ b/crypto/ghash-generic.c @@ -172,4 +172,5 @@ module_exit(ghash_mod_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("GHASH Message Digest Algorithm"); -MODULE_ALIAS("ghash"); +MODULE_ALIAS_CRYPTO("ghash"); +MODULE_ALIAS_CRYPTO("ghash-generic"); diff --git a/crypto/hmac.c b/crypto/hmac.c index 8d9544c..ade790b 100644 --- a/crypto/hmac.c +++ b/crypto/hmac.c @@ -271,3 +271,4 @@ module_exit(hmac_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("HMAC hash algorithm"); +MODULE_ALIAS_CRYPTO("hmac"); diff --git a/crypto/khazad.c b/crypto/khazad.c index 60e7cd6..873eb5d 100644 --- a/crypto/khazad.c +++ b/crypto/khazad.c @@ -880,3 +880,4 @@ module_exit(khazad_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Khazad Cryptographic Algorithm"); +MODULE_ALIAS_CRYPTO("khazad"); diff --git a/crypto/krng.c b/crypto/krng.c index a2d2b72..0224841 100644 --- a/crypto/krng.c +++ b/crypto/krng.c @@ -62,4 +62,5 @@ module_exit(krng_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Kernel Random Number Generator"); -MODULE_ALIAS("stdrng"); +MODULE_ALIAS_CRYPTO("stdrng"); +MODULE_ALIAS_CRYPTO("krng"); diff --git a/crypto/lrw.c b/crypto/lrw.c index ba42acc..6f9908a 100644 --- a/crypto/lrw.c +++ b/crypto/lrw.c @@ -400,3 +400,4 @@ module_exit(crypto_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("LRW block cipher mode"); +MODULE_ALIAS_CRYPTO("lrw"); diff --git a/crypto/lz4.c b/crypto/lz4.c index 4586dd1..53279ab 100644 --- a/crypto/lz4.c +++ b/crypto/lz4.c @@ -104,3 +104,4 @@ module_exit(lz4_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("LZ4 Compression Algorithm"); +MODULE_ALIAS_CRYPTO("lz4"); diff --git a/crypto/lz4hc.c b/crypto/lz4hc.c index 151ba31..eaec5fa 100644 --- a/crypto/lz4hc.c +++ b/crypto/lz4hc.c @@ -104,3 +104,4 @@ module_exit(lz4hc_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("LZ4HC Compression Algorithm"); +MODULE_ALIAS_CRYPTO("lz4hc"); diff --git a/crypto/lzo.c b/crypto/lzo.c index 1c2aa69..d1ff694 100644 --- a/crypto/lzo.c +++ b/crypto/lzo.c @@ -103,3 +103,4 @@ module_exit(lzo_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("LZO Compression Algorithm"); +MODULE_ALIAS_CRYPTO("lzo"); diff --git a/crypto/md4.c b/crypto/md4.c index 0477a6a..3515af4 100644 --- a/crypto/md4.c +++ b/crypto/md4.c @@ -255,4 +255,4 @@ module_exit(md4_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MD4 Message Digest Algorithm"); - +MODULE_ALIAS_CRYPTO("md4"); diff --git a/crypto/md5.c b/crypto/md5.c index 7febeaa..36f5e5b 100644 --- a/crypto/md5.c +++ b/crypto/md5.c @@ -168,3 +168,4 @@ module_exit(md5_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MD5 Message Digest Algorithm"); +MODULE_ALIAS_CRYPTO("md5"); diff --git a/crypto/michael_mic.c b/crypto/michael_mic.c index 079b761..46195e0 100644 --- a/crypto/michael_mic.c +++ b/crypto/michael_mic.c @@ -184,3 +184,4 @@ module_exit(michael_mic_exit); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Michael MIC"); MODULE_AUTHOR("Jouni Malinen "); +MODULE_ALIAS_CRYPTO("michael_mic"); diff --git a/crypto/pcbc.c b/crypto/pcbc.c index d1b8bdf..f654965 100644 --- a/crypto/pcbc.c +++ b/crypto/pcbc.c @@ -295,3 +295,4 @@ module_exit(crypto_pcbc_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("PCBC block cipher algorithm"); +MODULE_ALIAS_CRYPTO("pcbc"); diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c index 309d345..c305d41 100644 --- a/crypto/pcrypt.c +++ b/crypto/pcrypt.c @@ -565,3 +565,4 @@ module_exit(pcrypt_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steffen Klassert "); MODULE_DESCRIPTION("Parallel crypto wrapper"); +MODULE_ALIAS_CRYPTO("pcrypt"); diff --git a/crypto/rmd128.c b/crypto/rmd128.c index 8a0f68b..049486e 100644 --- a/crypto/rmd128.c +++ b/crypto/rmd128.c @@ -327,3 +327,4 @@ module_exit(rmd128_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adrian-Ken Rueegsegger "); MODULE_DESCRIPTION("RIPEMD-128 Message Digest"); +MODULE_ALIAS_CRYPTO("rmd128"); diff --git a/crypto/rmd160.c b/crypto/rmd160.c index 525d7bb..de585e5 100644 --- a/crypto/rmd160.c +++ b/crypto/rmd160.c @@ -371,3 +371,4 @@ module_exit(rmd160_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adrian-Ken Rueegsegger "); MODULE_DESCRIPTION("RIPEMD-160 Message Digest"); +MODULE_ALIAS_CRYPTO("rmd160"); diff --git a/crypto/rmd256.c b/crypto/rmd256.c index 69293d9..4ec02a7 100644 --- a/crypto/rmd256.c +++ b/crypto/rmd256.c @@ -346,3 +346,4 @@ module_exit(rmd256_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adrian-Ken Rueegsegger "); MODULE_DESCRIPTION("RIPEMD-256 Message Digest"); +MODULE_ALIAS_CRYPTO("rmd256"); diff --git a/crypto/rmd320.c b/crypto/rmd320.c index 09f97df..770f2cb 100644 --- a/crypto/rmd320.c +++ b/crypto/rmd320.c @@ -395,3 +395,4 @@ module_exit(rmd320_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adrian-Ken Rueegsegger "); MODULE_DESCRIPTION("RIPEMD-320 Message Digest"); +MODULE_ALIAS_CRYPTO("rmd320"); diff --git a/crypto/salsa20_generic.c b/crypto/salsa20_generic.c index 9a4770c..f550b5d 100644 --- a/crypto/salsa20_generic.c +++ b/crypto/salsa20_generic.c @@ -248,4 +248,5 @@ module_exit(salsa20_generic_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm"); -MODULE_ALIAS("salsa20"); +MODULE_ALIAS_CRYPTO("salsa20"); +MODULE_ALIAS_CRYPTO("salsa20-generic"); diff --git a/crypto/seed.c b/crypto/seed.c index 9c904d6..c6ba843 100644 --- a/crypto/seed.c +++ b/crypto/seed.c @@ -476,3 +476,4 @@ module_exit(seed_fini); MODULE_DESCRIPTION("SEED Cipher Algorithm"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Hye-Shik Chang , Kim Hyun "); +MODULE_ALIAS_CRYPTO("seed"); diff --git a/crypto/seqiv.c b/crypto/seqiv.c index f2cba4ed..49a4069 100644 --- a/crypto/seqiv.c +++ b/crypto/seqiv.c @@ -362,3 +362,4 @@ module_exit(seqiv_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Sequence Number IV Generator"); +MODULE_ALIAS_CRYPTO("seqiv"); diff --git a/crypto/serpent_generic.c b/crypto/serpent_generic.c index 7ddbd7e..94970a7 100644 --- a/crypto/serpent_generic.c +++ b/crypto/serpent_generic.c @@ -665,5 +665,6 @@ module_exit(serpent_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Serpent and tnepres (kerneli compatible serpent reversed) Cipher Algorithm"); MODULE_AUTHOR("Dag Arne Osvik "); -MODULE_ALIAS("tnepres"); -MODULE_ALIAS("serpent"); +MODULE_ALIAS_CRYPTO("tnepres"); +MODULE_ALIAS_CRYPTO("serpent"); +MODULE_ALIAS_CRYPTO("serpent-generic"); diff --git a/crypto/sha1_generic.c b/crypto/sha1_generic.c index 4279480..fdf7c00 100644 --- a/crypto/sha1_generic.c +++ b/crypto/sha1_generic.c @@ -153,4 +153,5 @@ module_exit(sha1_generic_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm"); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); +MODULE_ALIAS_CRYPTO("sha1-generic"); diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c index 5433667..136381b 100644 --- a/crypto/sha256_generic.c +++ b/crypto/sha256_generic.c @@ -384,5 +384,7 @@ module_exit(sha256_generic_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm"); -MODULE_ALIAS("sha224"); -MODULE_ALIAS("sha256"); +MODULE_ALIAS_CRYPTO("sha224"); +MODULE_ALIAS_CRYPTO("sha224-generic"); +MODULE_ALIAS_CRYPTO("sha256"); +MODULE_ALIAS_CRYPTO("sha256-generic"); diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c index 6ed124f..6c6d901 100644 --- a/crypto/sha512_generic.c +++ b/crypto/sha512_generic.c @@ -287,5 +287,7 @@ module_exit(sha512_generic_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA-512 and SHA-384 Secure Hash Algorithms"); -MODULE_ALIAS("sha384"); -MODULE_ALIAS("sha512"); +MODULE_ALIAS_CRYPTO("sha384"); +MODULE_ALIAS_CRYPTO("sha384-generic"); +MODULE_ALIAS_CRYPTO("sha512"); +MODULE_ALIAS_CRYPTO("sha512-generic"); diff --git a/crypto/tea.c b/crypto/tea.c index 0a57232..b70b441 100644 --- a/crypto/tea.c +++ b/crypto/tea.c @@ -270,8 +270,9 @@ static void __exit tea_mod_fini(void) crypto_unregister_algs(tea_algs, ARRAY_SIZE(tea_algs)); } -MODULE_ALIAS("xtea"); -MODULE_ALIAS("xeta"); +MODULE_ALIAS_CRYPTO("tea"); +MODULE_ALIAS_CRYPTO("xtea"); +MODULE_ALIAS_CRYPTO("xeta"); module_init(tea_mod_init); module_exit(tea_mod_fini); diff --git a/crypto/tgr192.c b/crypto/tgr192.c index 8740355..f7ed2fb 100644 --- a/crypto/tgr192.c +++ b/crypto/tgr192.c @@ -676,8 +676,9 @@ static void __exit tgr192_mod_fini(void) crypto_unregister_shashes(tgr_algs, ARRAY_SIZE(tgr_algs)); } -MODULE_ALIAS("tgr160"); -MODULE_ALIAS("tgr128"); +MODULE_ALIAS_CRYPTO("tgr192"); +MODULE_ALIAS_CRYPTO("tgr160"); +MODULE_ALIAS_CRYPTO("tgr128"); module_init(tgr192_mod_init); module_exit(tgr192_mod_fini); diff --git a/crypto/twofish_generic.c b/crypto/twofish_generic.c index 2d50005..ebf7a3e 100644 --- a/crypto/twofish_generic.c +++ b/crypto/twofish_generic.c @@ -211,4 +211,5 @@ module_exit(twofish_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION ("Twofish Cipher Algorithm"); -MODULE_ALIAS("twofish"); +MODULE_ALIAS_CRYPTO("twofish"); +MODULE_ALIAS_CRYPTO("twofish-generic"); diff --git a/crypto/vmac.c b/crypto/vmac.c index 2eb11a3..bf2d3a8 100644 --- a/crypto/vmac.c +++ b/crypto/vmac.c @@ -713,3 +713,4 @@ module_exit(vmac_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("VMAC hash algorithm"); +MODULE_ALIAS_CRYPTO("vmac"); diff --git a/crypto/wp512.c b/crypto/wp512.c index 180f1d6..253db94 100644 --- a/crypto/wp512.c +++ b/crypto/wp512.c @@ -1167,8 +1167,9 @@ static void __exit wp512_mod_fini(void) crypto_unregister_shashes(wp_algs, ARRAY_SIZE(wp_algs)); } -MODULE_ALIAS("wp384"); -MODULE_ALIAS("wp256"); +MODULE_ALIAS_CRYPTO("wp512"); +MODULE_ALIAS_CRYPTO("wp384"); +MODULE_ALIAS_CRYPTO("wp256"); module_init(wp512_mod_init); module_exit(wp512_mod_fini); diff --git a/crypto/xcbc.c b/crypto/xcbc.c index a5fbdf3..df90b33 100644 --- a/crypto/xcbc.c +++ b/crypto/xcbc.c @@ -286,3 +286,4 @@ module_exit(crypto_xcbc_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("XCBC keyed hash algorithm"); +MODULE_ALIAS_CRYPTO("xcbc"); diff --git a/crypto/xts.c b/crypto/xts.c index ca1608f..f6fd43f 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -362,3 +362,4 @@ module_exit(crypto_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("XTS block cipher mode"); +MODULE_ALIAS_CRYPTO("xts"); diff --git a/crypto/zlib.c b/crypto/zlib.c index 06b62e5..d980788 100644 --- a/crypto/zlib.c +++ b/crypto/zlib.c @@ -378,3 +378,4 @@ module_exit(zlib_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Zlib Compression Algorithm"); MODULE_AUTHOR("Sony Corporation"); +MODULE_ALIAS_CRYPTO("zlib"); diff --git a/drivers/acpi/acpi_cmos_rtc.c b/drivers/acpi/acpi_cmos_rtc.c index 84190ed..aff69d9 100644 --- a/drivers/acpi/acpi_cmos_rtc.c +++ b/drivers/acpi/acpi_cmos_rtc.c @@ -35,7 +35,7 @@ acpi_cmos_rtc_space_handler(u32 function, acpi_physical_address address, void *handler_context, void *region_context) { int i; - u8 *value = (u8 *)&value64; + u8 *value = (u8 *)value64; if (address > 0xff || !value64) return AE_BAD_PARAMETER; diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h index d95ca54..e6ab104 100644 --- a/drivers/acpi/acpica/aclocal.h +++ b/drivers/acpi/acpica/aclocal.h @@ -254,6 +254,7 @@ struct acpi_create_field_info { u32 field_bit_position; u32 field_bit_length; u16 resource_length; + u16 pin_number_index; u8 field_flags; u8 attribute; u8 field_type; diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h index 2a86c65..97c7a52 100644 --- a/drivers/acpi/acpica/acmacros.h +++ b/drivers/acpi/acpica/acmacros.h @@ -63,19 +63,15 @@ #define ACPI_SET64(ptr, val) (*ACPI_CAST64 (ptr) = (u64) (val)) /* - * printf() format helpers + * printf() format helper. This macros is a workaround for the difficulties + * with emitting 64-bit integers and 64-bit pointers with the same code + * for both 32-bit and 64-bit hosts. */ /* Split 64-bit integer into two 32-bit values. Use with %8.8X%8.8X */ #define ACPI_FORMAT_UINT64(i) ACPI_HIDWORD(i), ACPI_LODWORD(i) -#if ACPI_MACHINE_WIDTH == 64 -#define ACPI_FORMAT_NATIVE_UINT(i) ACPI_FORMAT_UINT64(i) -#else -#define ACPI_FORMAT_NATIVE_UINT(i) 0, (i) -#endif - /* * Macros for moving data around to/from buffers that are possibly unaligned. * If the hardware supports the transfer of unaligned data, just do the store. diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h index cc7ab6d..a47cc78f 100644 --- a/drivers/acpi/acpica/acobject.h +++ b/drivers/acpi/acpica/acobject.h @@ -263,6 +263,7 @@ struct acpi_object_region_field { ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_FIELD_INFO u16 resource_length; union acpi_operand_object *region_obj; /* Containing op_region object */ u8 *resource_buffer; /* resource_template for serial regions/fields */ + u16 pin_number_index; /* Index relative to previous Connection/Template */ }; struct acpi_object_bank_field { diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c index e7a57c5..9af55bd 100644 --- a/drivers/acpi/acpica/dsfield.c +++ b/drivers/acpi/acpica/dsfield.c @@ -360,6 +360,7 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info, */ info->resource_buffer = NULL; info->connection_node = NULL; + info->pin_number_index = 0; /* * A Connection() is either an actual resource descriptor (buffer) @@ -437,6 +438,7 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info, } info->field_bit_position += info->field_bit_length; + info->pin_number_index++; /* Index relative to previous Connection() */ break; default: diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c index 5205edc..fe79296 100644 --- a/drivers/acpi/acpica/dsopcode.c +++ b/drivers/acpi/acpica/dsopcode.c @@ -446,7 +446,7 @@ acpi_ds_eval_region_operands(struct acpi_walk_state *walk_state, ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "RgnObj %p Addr %8.8X%8.8X Len %X\n", obj_desc, - ACPI_FORMAT_NATIVE_UINT(obj_desc->region.address), + ACPI_FORMAT_UINT64(obj_desc->region.address), obj_desc->region.length)); /* Now the address and length are valid for this opregion */ @@ -539,13 +539,12 @@ acpi_ds_eval_table_region_operands(struct acpi_walk_state *walk_state, return_ACPI_STATUS(AE_NOT_EXIST); } - obj_desc->region.address = - (acpi_physical_address) ACPI_TO_INTEGER(table); + obj_desc->region.address = ACPI_PTR_TO_PHYSADDR(table); obj_desc->region.length = table->length; ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "RgnObj %p Addr %8.8X%8.8X Len %X\n", obj_desc, - ACPI_FORMAT_NATIVE_UINT(obj_desc->region.address), + ACPI_FORMAT_UINT64(obj_desc->region.address), obj_desc->region.length)); /* Now the address and length are valid for this opregion */ diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index 144cbb9..ee8ec4b 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -142,6 +142,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, union acpi_operand_object *region_obj2; void *region_context = NULL; struct acpi_connection_info *context; + acpi_physical_address address; ACPI_FUNCTION_TRACE(ev_address_space_dispatch); @@ -231,25 +232,23 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, /* We have everything we need, we can invoke the address space handler */ handler = handler_desc->address_space.handler; - - ACPI_DEBUG_PRINT((ACPI_DB_OPREGION, - "Handler %p (@%p) Address %8.8X%8.8X [%s]\n", - ®ion_obj->region.handler->address_space, handler, - ACPI_FORMAT_NATIVE_UINT(region_obj->region.address + - region_offset), - acpi_ut_get_region_name(region_obj->region. - space_id))); + address = (region_obj->region.address + region_offset); /* * Special handling for generic_serial_bus and general_purpose_io: * There are three extra parameters that must be passed to the * handler via the context: - * 1) Connection buffer, a resource template from Connection() op. - * 2) Length of the above buffer. - * 3) Actual access length from the access_as() op. + * 1) Connection buffer, a resource template from Connection() op + * 2) Length of the above buffer + * 3) Actual access length from the access_as() op + * + * In addition, for general_purpose_io, the Address and bit_width fields + * are defined as follows: + * 1) Address is the pin number index of the field (bit offset from + * the previous Connection) + * 2) bit_width is the actual bit length of the field (number of pins) */ - if (((region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS) || - (region_obj->region.space_id == ACPI_ADR_SPACE_GPIO)) && + if ((region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS) && context && field_obj) { /* Get the Connection (resource_template) buffer */ @@ -258,6 +257,24 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, context->length = field_obj->field.resource_length; context->access_length = field_obj->field.access_length; } + if ((region_obj->region.space_id == ACPI_ADR_SPACE_GPIO) && + context && field_obj) { + + /* Get the Connection (resource_template) buffer */ + + context->connection = field_obj->field.resource_buffer; + context->length = field_obj->field.resource_length; + context->access_length = field_obj->field.access_length; + address = field_obj->field.pin_number_index; + bit_width = field_obj->field.bit_length; + } + + ACPI_DEBUG_PRINT((ACPI_DB_OPREGION, + "Handler %p (@%p) Address %8.8X%8.8X [%s]\n", + ®ion_obj->region.handler->address_space, handler, + ACPI_FORMAT_UINT64(address), + acpi_ut_get_region_name(region_obj->region. + space_id))); if (!(handler_desc->address_space.handler_flags & ACPI_ADDR_HANDLER_DEFAULT_INSTALLED)) { @@ -271,9 +288,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, /* Call the handler */ - status = handler(function, - (region_obj->region.address + region_offset), - bit_width, value, context, + status = handler(function, address, bit_width, value, context, region_obj2->extra.region_context); if (ACPI_FAILURE(status)) { diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c index 4d046fa..b64fb68 100644 --- a/drivers/acpi/acpica/exdump.c +++ b/drivers/acpi/acpica/exdump.c @@ -622,8 +622,8 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth) acpi_os_printf("\n"); } else { acpi_os_printf(" base %8.8X%8.8X Length %X\n", - ACPI_FORMAT_NATIVE_UINT(obj_desc->region. - address), + ACPI_FORMAT_UINT64(obj_desc->region. + address), obj_desc->region.length); } break; diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c index cfd8752..d36894a 100644 --- a/drivers/acpi/acpica/exfield.c +++ b/drivers/acpi/acpica/exfield.c @@ -178,6 +178,37 @@ acpi_ex_read_data_from_field(struct acpi_walk_state *walk_state, buffer = &buffer_desc->integer.value; } + if ((obj_desc->common.type == ACPI_TYPE_LOCAL_REGION_FIELD) && + (obj_desc->field.region_obj->region.space_id == + ACPI_ADR_SPACE_GPIO)) { + /* + * For GPIO (general_purpose_io), the Address will be the bit offset + * from the previous Connection() operator, making it effectively a + * pin number index. The bit_length is the length of the field, which + * is thus the number of pins. + */ + ACPI_DEBUG_PRINT((ACPI_DB_BFIELD, + "GPIO FieldRead [FROM]: Pin %u Bits %u\n", + obj_desc->field.pin_number_index, + obj_desc->field.bit_length)); + + /* Lock entire transaction if requested */ + + acpi_ex_acquire_global_lock(obj_desc->common_field.field_flags); + + /* Perform the write */ + + status = acpi_ex_access_region(obj_desc, 0, + (u64 *)buffer, ACPI_READ); + acpi_ex_release_global_lock(obj_desc->common_field.field_flags); + if (ACPI_FAILURE(status)) { + acpi_ut_remove_reference(buffer_desc); + } else { + *ret_buffer_desc = buffer_desc; + } + return_ACPI_STATUS(status); + } + ACPI_DEBUG_PRINT((ACPI_DB_BFIELD, "FieldRead [TO]: Obj %p, Type %X, Buf %p, ByteLen %X\n", obj_desc, obj_desc->common.type, buffer, @@ -325,6 +356,42 @@ acpi_ex_write_data_to_field(union acpi_operand_object *source_desc, *result_desc = buffer_desc; return_ACPI_STATUS(status); + } else if ((obj_desc->common.type == ACPI_TYPE_LOCAL_REGION_FIELD) && + (obj_desc->field.region_obj->region.space_id == + ACPI_ADR_SPACE_GPIO)) { + /* + * For GPIO (general_purpose_io), we will bypass the entire field + * mechanism and handoff the bit address and bit width directly to + * the handler. The Address will be the bit offset + * from the previous Connection() operator, making it effectively a + * pin number index. The bit_length is the length of the field, which + * is thus the number of pins. + */ + if (source_desc->common.type != ACPI_TYPE_INTEGER) { + return_ACPI_STATUS(AE_AML_OPERAND_TYPE); + } + + ACPI_DEBUG_PRINT((ACPI_DB_BFIELD, + "GPIO FieldWrite [FROM]: (%s:%X), Val %.8X [TO]: Pin %u Bits %u\n", + acpi_ut_get_type_name(source_desc->common. + type), + source_desc->common.type, + (u32)source_desc->integer.value, + obj_desc->field.pin_number_index, + obj_desc->field.bit_length)); + + buffer = &source_desc->integer.value; + + /* Lock entire transaction if requested */ + + acpi_ex_acquire_global_lock(obj_desc->common_field.field_flags); + + /* Perform the write */ + + status = acpi_ex_access_region(obj_desc, 0, + (u64 *)buffer, ACPI_WRITE); + acpi_ex_release_global_lock(obj_desc->common_field.field_flags); + return_ACPI_STATUS(status); } /* Get a pointer to the data to be written */ diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c index 49fb742..98af39f 100644 --- a/drivers/acpi/acpica/exfldio.c +++ b/drivers/acpi/acpica/exfldio.c @@ -263,17 +263,15 @@ acpi_ex_access_region(union acpi_operand_object *obj_desc, } ACPI_DEBUG_PRINT_RAW((ACPI_DB_BFIELD, - " Region [%s:%X], Width %X, ByteBase %X, Offset %X at %p\n", + " Region [%s:%X], Width %X, ByteBase %X, Offset %X at %8.8X%8.8X\n", acpi_ut_get_region_name(rgn_desc->region. space_id), rgn_desc->region.space_id, obj_desc->common_field.access_byte_width, obj_desc->common_field.base_byte_offset, - field_datum_byte_offset, ACPI_CAST_PTR(void, - (rgn_desc-> - region. - address + - region_offset)))); + field_datum_byte_offset, + ACPI_FORMAT_UINT64(rgn_desc->region.address + + region_offset))); /* Invoke the appropriate address_space/op_region handler */ diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c index 5a58861..8c88cfd 100644 --- a/drivers/acpi/acpica/exprep.c +++ b/drivers/acpi/acpica/exprep.c @@ -484,6 +484,8 @@ acpi_status acpi_ex_prep_field_value(struct acpi_create_field_info *info) obj_desc->field.resource_length = info->resource_length; } + obj_desc->field.pin_number_index = info->pin_number_index; + /* Allow full data read from EC address space */ if ((obj_desc->field.region_obj->region.space_id == diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c index 9d28867e..cf40223 100644 --- a/drivers/acpi/acpica/exregion.c +++ b/drivers/acpi/acpica/exregion.c @@ -181,7 +181,7 @@ acpi_ex_system_memory_space_handler(u32 function, if (!mem_info->mapped_logical_address) { ACPI_ERROR((AE_INFO, "Could not map memory at 0x%8.8X%8.8X, size %u", - ACPI_FORMAT_NATIVE_UINT(address), + ACPI_FORMAT_UINT64(address), (u32) map_length)); mem_info->mapped_length = 0; return_ACPI_STATUS(AE_NO_MEMORY); @@ -202,8 +202,7 @@ acpi_ex_system_memory_space_handler(u32 function, ACPI_DEBUG_PRINT((ACPI_DB_INFO, "System-Memory (width %u) R/W %u Address=%8.8X%8.8X\n", - bit_width, function, - ACPI_FORMAT_NATIVE_UINT(address))); + bit_width, function, ACPI_FORMAT_UINT64(address))); /* * Perform the memory read or write @@ -318,8 +317,7 @@ acpi_ex_system_io_space_handler(u32 function, ACPI_DEBUG_PRINT((ACPI_DB_INFO, "System-IO (width %u) R/W %u Address=%8.8X%8.8X\n", - bit_width, function, - ACPI_FORMAT_NATIVE_UINT(address))); + bit_width, function, ACPI_FORMAT_UINT64(address))); /* Decode the function parameter */ diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c index eab70d5..fae5758 100644 --- a/drivers/acpi/acpica/hwvalid.c +++ b/drivers/acpi/acpica/hwvalid.c @@ -142,17 +142,17 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width) byte_width = ACPI_DIV_8(bit_width); last_address = address + byte_width - 1; - ACPI_DEBUG_PRINT((ACPI_DB_IO, "Address %p LastAddress %p Length %X", - ACPI_CAST_PTR(void, address), ACPI_CAST_PTR(void, - last_address), - byte_width)); + ACPI_DEBUG_PRINT((ACPI_DB_IO, + "Address %8.8X%8.8X LastAddress %8.8X%8.8X Length %X", + ACPI_FORMAT_UINT64(address), + ACPI_FORMAT_UINT64(last_address), byte_width)); /* Maximum 16-bit address in I/O space */ if (last_address > ACPI_UINT16_MAX) { ACPI_ERROR((AE_INFO, - "Illegal I/O port address/length above 64K: %p/0x%X", - ACPI_CAST_PTR(void, address), byte_width)); + "Illegal I/O port address/length above 64K: %8.8X%8.8X/0x%X", + ACPI_FORMAT_UINT64(address), byte_width)); return_ACPI_STATUS(AE_LIMIT); } @@ -181,8 +181,8 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width) if (acpi_gbl_osi_data >= port_info->osi_dependency) { ACPI_DEBUG_PRINT((ACPI_DB_IO, - "Denied AML access to port 0x%p/%X (%s 0x%.4X-0x%.4X)", - ACPI_CAST_PTR(void, address), + "Denied AML access to port 0x%8.8X%8.8X/%X (%s 0x%.4X-0x%.4X)", + ACPI_FORMAT_UINT64(address), byte_width, port_info->name, port_info->start, port_info->end)); diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c index 48b9c6f..fc82c53 100644 --- a/drivers/acpi/acpica/nsdump.c +++ b/drivers/acpi/acpica/nsdump.c @@ -271,12 +271,11 @@ acpi_ns_dump_one_object(acpi_handle obj_handle, switch (type) { case ACPI_TYPE_PROCESSOR: - acpi_os_printf("ID %02X Len %02X Addr %p\n", + acpi_os_printf("ID %02X Len %02X Addr %8.8X%8.8X\n", obj_desc->processor.proc_id, obj_desc->processor.length, - ACPI_CAST_PTR(void, - obj_desc->processor. - address)); + ACPI_FORMAT_UINT64(obj_desc->processor. + address)); break; case ACPI_TYPE_DEVICE: @@ -347,8 +346,9 @@ acpi_ns_dump_one_object(acpi_handle obj_handle, space_id)); if (obj_desc->region.flags & AOPOBJ_DATA_VALID) { acpi_os_printf(" Addr %8.8X%8.8X Len %.4X\n", - ACPI_FORMAT_NATIVE_UINT - (obj_desc->region.address), + ACPI_FORMAT_UINT64(obj_desc-> + region. + address), obj_desc->region.length); } else { acpi_os_printf diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c index 634357d..c4d0977 100644 --- a/drivers/acpi/acpica/tbinstal.c +++ b/drivers/acpi/acpica/tbinstal.c @@ -294,8 +294,7 @@ struct acpi_table_header *acpi_tb_table_override(struct acpi_table_header ACPI_EXCEPTION((AE_INFO, AE_NO_MEMORY, "%4.4s %p Attempted physical table override failed", table_header->signature, - ACPI_CAST_PTR(void, - table_desc->address))); + ACPI_PHYSADDR_TO_PTR(table_desc->address))); return (NULL); } @@ -311,7 +310,7 @@ finish_override: ACPI_INFO((AE_INFO, "%4.4s %p %s table override, new table: %p", table_header->signature, - ACPI_CAST_PTR(void, table_desc->address), + ACPI_PHYSADDR_TO_PTR(table_desc->address), override_type, new_table)); /* We can now unmap/delete the original table (if fully mapped) */ diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c index 6866e76..2957ed5 100644 --- a/drivers/acpi/acpica/tbprint.c +++ b/drivers/acpi/acpica/tbprint.c @@ -127,16 +127,12 @@ acpi_tb_print_table_header(acpi_physical_address address, { struct acpi_table_header local_header; - /* - * The reason that the Address is cast to a void pointer is so that we - * can use %p which will work properly on both 32-bit and 64-bit hosts. - */ if (ACPI_COMPARE_NAME(header->signature, ACPI_SIG_FACS)) { /* FACS only has signature and length fields */ - ACPI_INFO((AE_INFO, "%4.4s %p %06X", - header->signature, ACPI_CAST_PTR(void, address), + ACPI_INFO((AE_INFO, "%-4.4s 0x%8.8X%8.8X %06X", + header->signature, ACPI_FORMAT_UINT64(address), header->length)); } else if (ACPI_VALIDATE_RSDP_SIG(header->signature)) { @@ -147,8 +143,8 @@ acpi_tb_print_table_header(acpi_physical_address address, header)->oem_id, ACPI_OEM_ID_SIZE); acpi_tb_fix_string(local_header.oem_id, ACPI_OEM_ID_SIZE); - ACPI_INFO((AE_INFO, "RSDP %p %06X (v%.2d %6.6s)", - ACPI_CAST_PTR(void, address), + ACPI_INFO((AE_INFO, "RSDP 0x%8.8X%8.8X %06X (v%.2d %-6.6s)", + ACPI_FORMAT_UINT64(address), (ACPI_CAST_PTR(struct acpi_table_rsdp, header)-> revision > 0) ? ACPI_CAST_PTR(struct acpi_table_rsdp, @@ -162,8 +158,9 @@ acpi_tb_print_table_header(acpi_physical_address address, acpi_tb_cleanup_table_header(&local_header, header); ACPI_INFO((AE_INFO, - "%4.4s %p %06X (v%.2d %6.6s %8.8s %08X %4.4s %08X)", - local_header.signature, ACPI_CAST_PTR(void, address), + "%-4.4s 0x%8.8X%8.8X" + " %06X (v%.2d %-6.6s %-8.8s %08X %-4.4s %08X)", + local_header.signature, ACPI_FORMAT_UINT64(address), local_header.length, local_header.revision, local_header.oem_id, local_header.oem_table_id, local_header.oem_revision, diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c index 1bc879e..4cca6b7 100644 --- a/drivers/acpi/acpica/tbutils.c +++ b/drivers/acpi/acpica/tbutils.c @@ -227,8 +227,8 @@ acpi_tb_install_table(acpi_physical_address address, table = acpi_os_map_memory(address, sizeof(struct acpi_table_header)); if (!table) { ACPI_ERROR((AE_INFO, - "Could not map memory for table [%s] at %p", - signature, ACPI_CAST_PTR(void, address))); + "Could not map memory for table [%s] at %8.8X%8.8X", + signature, ACPI_FORMAT_UINT64(address))); return; } diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c index 60b5a87..daad59d 100644 --- a/drivers/acpi/acpica/tbxfload.c +++ b/drivers/acpi/acpica/tbxfload.c @@ -184,11 +184,10 @@ static acpi_status acpi_tb_load_namespace(void) * be useful for debugging ACPI problems on some machines. */ if (acpi_gbl_disable_ssdt_table_load) { - ACPI_INFO((AE_INFO, "Ignoring %4.4s at %p", + ACPI_INFO((AE_INFO, "Ignoring %4.4s at %8.8X%8.8X", acpi_gbl_root_table_list.tables[i].signature. - ascii, ACPI_CAST_PTR(void, - acpi_gbl_root_table_list. - tables[i].address))); + ascii, ACPI_FORMAT_UINT64(acpi_gbl_root_table_list. + tables[i].address))); continue; } diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c index e4e1468..01bf7eb 100644 --- a/drivers/acpi/acpica/tbxfroot.c +++ b/drivers/acpi/acpica/tbxfroot.c @@ -111,7 +111,7 @@ acpi_status acpi_tb_validate_rsdp(struct acpi_table_rsdp *rsdp) * ******************************************************************************/ -acpi_status __init acpi_find_root_pointer(acpi_size *table_address) +acpi_status __init acpi_find_root_pointer(acpi_physical_address * table_address) { u8 *table_ptr; u8 *mem_rover; @@ -169,7 +169,8 @@ acpi_status __init acpi_find_root_pointer(acpi_size *table_address) physical_address += (u32) ACPI_PTR_DIFF(mem_rover, table_ptr); - *table_address = physical_address; + *table_address = + (acpi_physical_address) physical_address; return_ACPI_STATUS(AE_OK); } } @@ -202,7 +203,7 @@ acpi_status __init acpi_find_root_pointer(acpi_size *table_address) (ACPI_HI_RSDP_WINDOW_BASE + ACPI_PTR_DIFF(mem_rover, table_ptr)); - *table_address = physical_address; + *table_address = (acpi_physical_address) physical_address; return_ACPI_STATUS(AE_OK); } diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c index 2c2b6ae..3a02b65 100644 --- a/drivers/acpi/acpica/utaddress.c +++ b/drivers/acpi/acpica/utaddress.c @@ -107,10 +107,10 @@ acpi_ut_add_address_range(acpi_adr_space_type space_id, acpi_gbl_address_range_list[space_id] = range_info; ACPI_DEBUG_PRINT((ACPI_DB_NAMES, - "\nAdded [%4.4s] address range: 0x%p-0x%p\n", + "\nAdded [%4.4s] address range: 0x%8.8X%8.8X-0x%8.8X%8.8X\n", acpi_ut_get_node_name(range_info->region_node), - ACPI_CAST_PTR(void, address), - ACPI_CAST_PTR(void, range_info->end_address))); + ACPI_FORMAT_UINT64(address), + ACPI_FORMAT_UINT64(range_info->end_address))); (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); return_ACPI_STATUS(AE_OK); @@ -160,15 +160,13 @@ acpi_ut_remove_address_range(acpi_adr_space_type space_id, } ACPI_DEBUG_PRINT((ACPI_DB_NAMES, - "\nRemoved [%4.4s] address range: 0x%p-0x%p\n", + "\nRemoved [%4.4s] address range: 0x%8.8X%8.8X-0x%8.8X%8.8X\n", acpi_ut_get_node_name(range_info-> region_node), - ACPI_CAST_PTR(void, - range_info-> - start_address), - ACPI_CAST_PTR(void, - range_info-> - end_address))); + ACPI_FORMAT_UINT64(range_info-> + start_address), + ACPI_FORMAT_UINT64(range_info-> + end_address))); ACPI_FREE(range_info); return_VOID; @@ -245,16 +243,14 @@ acpi_ut_check_address_range(acpi_adr_space_type space_id, region_node); ACPI_WARNING((AE_INFO, - "%s range 0x%p-0x%p conflicts with OpRegion 0x%p-0x%p (%s)", + "%s range 0x%8.8X%8.8X-0x%8.8X%8.8X conflicts with OpRegion 0x%8.8X%8.8X-0x%8.8X%8.8X (%s)", acpi_ut_get_region_name(space_id), - ACPI_CAST_PTR(void, address), - ACPI_CAST_PTR(void, end_address), - ACPI_CAST_PTR(void, - range_info-> - start_address), - ACPI_CAST_PTR(void, - range_info-> - end_address), + ACPI_FORMAT_UINT64(address), + ACPI_FORMAT_UINT64(end_address), + ACPI_FORMAT_UINT64(range_info-> + start_address), + ACPI_FORMAT_UINT64(range_info-> + end_address), pathname)); ACPI_FREE(pathname); } diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c index edff4e6..c66bca1 100644 --- a/drivers/acpi/acpica/utcopy.c +++ b/drivers/acpi/acpica/utcopy.c @@ -1001,5 +1001,11 @@ acpi_ut_copy_iobject_to_iobject(union acpi_operand_object *source_desc, status = acpi_ut_copy_simple_object(source_desc, *dest_desc); } + /* Delete the allocated object if copy failed */ + + if (ACPI_FAILURE(status)) { + acpi_ut_remove_reference(*dest_desc); + } + return_ACPI_STATUS(status); } diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c index 246ef68..2c3c578 100644 --- a/drivers/acpi/acpica/utxfinit.c +++ b/drivers/acpi/acpica/utxfinit.c @@ -175,10 +175,12 @@ acpi_status __init acpi_enable_subsystem(u32 flags) * Obtain a permanent mapping for the FACS. This is required for the * Global Lock and the Firmware Waking Vector */ - status = acpi_tb_initialize_facs(); - if (ACPI_FAILURE(status)) { - ACPI_WARNING((AE_INFO, "Could not map the FACS table")); - return_ACPI_STATUS(status); + if (!(flags & ACPI_NO_FACS_INIT)) { + status = acpi_tb_initialize_facs(); + if (ACPI_FAILURE(status)) { + ACPI_WARNING((AE_INFO, "Could not map the FACS table")); + return_ACPI_STATUS(status); + } } #endif /* !ACPI_REDUCED_HARDWARE */ diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index b48aefa..60be8d0 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -450,6 +450,16 @@ static int __init acpi_bus_init_irq(void) u8 acpi_gbl_permanent_mmap; +/** + * acpi_early_init - Initialize ACPICA and populate the ACPI namespace. + * + * The ACPI tables are accessible after this, but the handling of events has not + * been initialized and the global lock is not available yet, so AML should not + * be executed at this point. + * + * Doing this before switching the EFI runtime services to virtual mode allows + * the EfiBootServices memory to be freed slightly earlier on boot. + */ void __init acpi_early_init(void) { acpi_status status; @@ -510,26 +520,42 @@ void __init acpi_early_init(void) acpi_gbl_FADT.sci_interrupt = acpi_sci_override_gsi; } #endif + return; + + error0: + disable_acpi(); +} + +/** + * acpi_subsystem_init - Finalize the early initialization of ACPI. + * + * Switch over the platform to the ACPI mode (if possible), initialize the + * handling of ACPI events, install the interrupt and global lock handlers. + * + * Doing this too early is generally unsafe, but at the same time it needs to be + * done before all things that really depend on ACPI. The right spot appears to + * be before finalizing the EFI initialization. + */ +void __init acpi_subsystem_init(void) +{ + acpi_status status; + + if (acpi_disabled) + return; status = acpi_enable_subsystem(~ACPI_NO_ACPI_ENABLE); if (ACPI_FAILURE(status)) { printk(KERN_ERR PREFIX "Unable to enable ACPI\n"); - goto error0; + disable_acpi(); + } else { + /* + * If the system is using ACPI then we can be reasonably + * confident that any regulators are managed by the firmware + * so tell the regulator core it has everything it needs to + * know. + */ + regulator_has_full_constraints(); } - - /* - * If the system is using ACPI then we can be reasonably - * confident that any regulators are managed by the firmware - * so tell the regulator core it has everything it needs to - * know. - */ - regulator_has_full_constraints(); - - return; - - error0: - disable_acpi(); - return; } static int __init acpi_bus_init(void) diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c index 368f9dd..e4a6f78 100644 --- a/drivers/acpi/container.c +++ b/drivers/acpi/container.c @@ -96,6 +96,13 @@ static void container_device_detach(struct acpi_device *adev) device_unregister(dev); } +static void container_device_online(struct acpi_device *adev) +{ + struct device *dev = acpi_driver_data(adev); + + kobject_uevent(&dev->kobj, KOBJ_ONLINE); +} + static struct acpi_scan_handler container_handler = { .ids = container_device_ids, .attach = container_device_attach, @@ -103,6 +110,7 @@ static struct acpi_scan_handler container_handler = { .hotplug = { .enabled = true, .demand_offline = true, + .notify_online = container_device_online, }, }; diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index c14a00d..19f6505 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -257,7 +257,7 @@ int acpi_bus_init_power(struct acpi_device *device) device->power.state = ACPI_STATE_UNKNOWN; if (!acpi_device_is_present(device)) - return 0; + return -ENXIO; result = acpi_device_get_power(device, &state); if (result) diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index fc1aa79..726c969 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -172,7 +172,7 @@ static void __init acpi_request_region (struct acpi_generic_address *gas, request_mem_region(addr, length, desc); } -static int __init acpi_reserve_resources(void) +static void __init acpi_reserve_resources(void) { acpi_request_region(&acpi_gbl_FADT.xpm1a_event_block, acpi_gbl_FADT.pm1_event_length, "ACPI PM1a_EVT_BLK"); @@ -201,10 +201,7 @@ static int __init acpi_reserve_resources(void) if (!(acpi_gbl_FADT.gpe1_block_length & 0x1)) acpi_request_region(&acpi_gbl_FADT.xgpe1_block, acpi_gbl_FADT.gpe1_block_length, "ACPI GPE1_BLK"); - - return 0; } -device_initcall(acpi_reserve_resources); void acpi_os_printf(const char *fmt, ...) { @@ -1792,6 +1789,7 @@ acpi_status __init acpi_os_initialize(void) acpi_status __init acpi_os_initialize1(void) { + acpi_reserve_resources(); kacpid_wq = alloc_workqueue("kacpid", 0, 1); kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 1); kacpi_hotplug_wq = alloc_ordered_workqueue("kacpi_hotplug", 0); diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 3dca36d..fd8496a 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -962,7 +962,7 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr) return -EINVAL; drv->safe_state_index = -1; - for (i = 0; i < CPUIDLE_STATE_MAX; i++) { + for (i = CPUIDLE_DRIVER_STATE_START; i < CPUIDLE_STATE_MAX; i++) { drv->states[i].name[0] = '\0'; drv->states[i].desc[0] = '\0'; } @@ -1071,9 +1071,9 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) if (pr->id == 0 && cpuidle_get_driver() == &acpi_idle_driver) { - cpuidle_pause_and_lock(); /* Protect against cpu-hotplug */ get_online_cpus(); + cpuidle_pause_and_lock(); /* Disable all cpuidle devices */ for_each_online_cpu(cpu) { @@ -1100,8 +1100,8 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) cpuidle_enable_device(dev); } } - put_online_cpus(); cpuidle_resume_and_unlock(); + put_online_cpus(); } return 0; diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 57b053f..9498c3d 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -106,7 +106,7 @@ static int create_modalias(struct acpi_device *acpi_dev, char *modalias, list_for_each_entry(id, &acpi_dev->pnp.ids, list) { count = snprintf(&modalias[len], size, "%s:", id->id); if (count < 0) - return EINVAL; + return -EINVAL; if (count >= size) return -ENOMEM; len += count; @@ -192,7 +192,11 @@ bool acpi_scan_is_offline(struct acpi_device *adev, bool uevent) struct acpi_device_physical_node *pn; bool offline = true; - mutex_lock(&adev->physical_node_lock); + /* + * acpi_container_offline() calls this for all of the container's + * children under the container's physical_node_lock lock. + */ + mutex_lock_nested(&adev->physical_node_lock, SINGLE_DEPTH_NESTING); list_for_each_entry(pn, &adev->physical_node_list, node) if (device_supports_offline(pn->dev) && !pn->dev->offline) { @@ -329,7 +333,8 @@ static int acpi_scan_hot_remove(struct acpi_device *device) unsigned long long sta; acpi_status status; - if (device->handler->hotplug.demand_offline && !acpi_force_hot_remove) { + if (device->handler && device->handler->hotplug.demand_offline + && !acpi_force_hot_remove) { if (!acpi_scan_is_offline(device, true)) return -EBUSY; } else { @@ -660,8 +665,14 @@ static ssize_t acpi_device_sun_show(struct device *dev, struct device_attribute *attr, char *buf) { struct acpi_device *acpi_dev = to_acpi_device(dev); + acpi_status status; + unsigned long long sun; - return sprintf(buf, "%lu\n", acpi_dev->pnp.sun); + status = acpi_evaluate_integer(acpi_dev->handle, "_SUN", NULL, &sun); + if (ACPI_FAILURE(status)) + return -ENODEV; + + return sprintf(buf, "%llu\n", sun); } static DEVICE_ATTR(sun, 0444, acpi_device_sun_show, NULL); @@ -683,7 +694,6 @@ static int acpi_device_setup_files(struct acpi_device *dev) { struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL}; acpi_status status; - unsigned long long sun; int result = 0; /* @@ -724,14 +734,10 @@ static int acpi_device_setup_files(struct acpi_device *dev) if (dev->pnp.unique_id) result = device_create_file(&dev->dev, &dev_attr_uid); - status = acpi_evaluate_integer(dev->handle, "_SUN", NULL, &sun); - if (ACPI_SUCCESS(status)) { - dev->pnp.sun = (unsigned long)sun; + if (acpi_has_method(dev->handle, "_SUN")) { result = device_create_file(&dev->dev, &dev_attr_sun); if (result) goto end; - } else { - dev->pnp.sun = (unsigned long)-1; } if (acpi_has_method(dev->handle, "_STA")) { @@ -863,7 +869,7 @@ static void acpi_free_power_resources_lists(struct acpi_device *device) if (device->wakeup.flags.valid) acpi_power_resources_list_free(&device->wakeup.resources); - if (!device->flags.power_manageable) + if (!device->power.flags.power_resources) return; for (i = ACPI_STATE_D0; i <= ACPI_STATE_D3_HOT; i++) { @@ -915,12 +921,17 @@ static void acpi_device_notify(acpi_handle handle, u32 event, void *data) device->driver->ops.notify(device, event); } -static acpi_status acpi_device_notify_fixed(void *data) +static void acpi_device_notify_fixed(void *data) { struct acpi_device *device = data; /* Fixed hardware devices have no handles */ acpi_device_notify(NULL, ACPI_FIXED_HARDWARE_EVENT, device); +} + +static acpi_status acpi_device_fixed_event(void *data) +{ + acpi_os_execute(OSL_NOTIFY_HANDLER, acpi_device_notify_fixed, data); return AE_OK; } @@ -931,12 +942,12 @@ static int acpi_device_install_notify_handler(struct acpi_device *device) if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON) status = acpi_install_fixed_event_handler(ACPI_EVENT_POWER_BUTTON, - acpi_device_notify_fixed, + acpi_device_fixed_event, device); else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON) status = acpi_install_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON, - acpi_device_notify_fixed, + acpi_device_fixed_event, device); else status = acpi_install_notify_handler(device->handle, @@ -953,10 +964,10 @@ static void acpi_device_remove_notify_handler(struct acpi_device *device) { if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON) acpi_remove_fixed_event_handler(ACPI_EVENT_POWER_BUTTON, - acpi_device_notify_fixed); + acpi_device_fixed_event); else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON) acpi_remove_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON, - acpi_device_notify_fixed); + acpi_device_fixed_event); else acpi_remove_notify_handler(device->handle, ACPI_DEVICE_NOTIFY, acpi_device_notify); @@ -1547,10 +1558,8 @@ static void acpi_bus_get_power_flags(struct acpi_device *device) device->power.flags.power_resources) device->power.states[ACPI_STATE_D3_COLD].flags.os_accessible = 1; - if (acpi_bus_init_power(device)) { - acpi_free_power_resources_lists(device); + if (acpi_bus_init_power(device)) device->flags.power_manageable = 0; - } } static void acpi_bus_get_flags(struct acpi_device *device) @@ -2036,13 +2045,18 @@ static void acpi_bus_attach(struct acpi_device *device) /* Skip devices that are not present. */ if (!acpi_device_is_present(device)) { device->flags.visited = false; + device->flags.power_manageable = 0; return; } if (device->handler) goto ok; if (!device->flags.initialized) { - acpi_bus_update_power(device, NULL); + device->flags.power_manageable = + device->power.states[ACPI_STATE_D0].flags.valid; + if (acpi_bus_init_power(device)) + device->flags.power_manageable = 0; + device->flags.initialized = true; } device->flags.visited = false; @@ -2061,6 +2075,9 @@ static void acpi_bus_attach(struct acpi_device *device) ok: list_for_each_entry(child, &device->children, node) acpi_bus_attach(child); + + if (device->handler && device->handler->hotplug.notify_online) + device->handler->hotplug.notify_online(device); } /** diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index bb0b904..997540d 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -2064,6 +2064,17 @@ EXPORT_SYMBOL(acpi_video_unregister); static int __init acpi_video_init(void) { + /* + * Let the module load even if ACPI is disabled (e.g. due to + * a broken BIOS) so that i915.ko can still be loaded on such + * old systems without an AcpiOpRegion. + * + * acpi_video_register() will report -ENODEV later as well due + * to acpi_disabled when i915.ko tries to register itself afterwards. + */ + if (acpi_disabled) + return 0; + dmi_check_system(video_dmi_table); if (intel_opregion_present()) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 3e23046..47d28b9 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -60,6 +60,7 @@ enum board_ids { /* board IDs by feature in alphabetical order */ board_ahci, board_ahci_ign_iferr, + board_ahci_nomsi, board_ahci_noncq, board_ahci_nosntf, board_ahci_yes_fbs, @@ -121,6 +122,13 @@ static const struct ata_port_info ahci_port_info[] = { .udma_mask = ATA_UDMA6, .port_ops = &ahci_ops, }, + [board_ahci_nomsi] = { + AHCI_HFLAGS (AHCI_HFLAG_NO_MSI), + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_ops, + }, [board_ahci_noncq] = { AHCI_HFLAGS (AHCI_HFLAG_NO_NCQ), .flags = AHCI_FLAG_COMMON, @@ -305,6 +313,22 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x9c85), board_ahci }, /* Wildcat Point-LP RAID */ { PCI_VDEVICE(INTEL, 0x9c87), board_ahci }, /* Wildcat Point-LP RAID */ { PCI_VDEVICE(INTEL, 0x9c8f), board_ahci }, /* Wildcat Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0x8c82), board_ahci }, /* 9 Series AHCI */ + { PCI_VDEVICE(INTEL, 0x8c83), board_ahci }, /* 9 Series AHCI */ + { PCI_VDEVICE(INTEL, 0x8c84), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c85), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c86), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c87), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c8e), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c8f), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */ + { PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */ + { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, @@ -442,6 +466,8 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x917a), .driver_data = board_ahci_yes_fbs }, /* 88se9172 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9172), + .driver_data = board_ahci_yes_fbs }, /* 88se9182 */ + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9182), .driver_data = board_ahci_yes_fbs }, /* 88se9172 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9192), .driver_data = board_ahci_yes_fbs }, /* 88se9172 on some Gigabyte */ @@ -456,6 +482,7 @@ static const struct pci_device_id ahci_pci_tbl[] = { /* Promise */ { PCI_VDEVICE(PROMISE, 0x3f20), board_ahci }, /* PDC42819 */ + { PCI_VDEVICE(PROMISE, 0x3781), board_ahci }, /* FastTrak TX8660 ahci-mode */ /* Asmedia */ { PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci }, /* ASM1060 */ @@ -464,10 +491,11 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci }, /* ASM1062 */ /* - * Samsung SSDs found on some macbooks. NCQ times out. - * https://bugzilla.kernel.org/show_bug.cgi?id=60731 + * Samsung SSDs found on some macbooks. NCQ times out if MSI is + * enabled. https://bugzilla.kernel.org/show_bug.cgi?id=60731 */ - { PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_noncq }, + { PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_nomsi }, + { PCI_VDEVICE(SAMSUNG, 0xa800), board_ahci_nomsi }, /* Enmotus */ { PCI_DEVICE(0x1c44, 0x8000), board_ahci }, diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 6334c8d..39f76b9 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -340,6 +340,14 @@ static const struct pci_device_id piix_pci_tbl[] = { { 0x8086, 0x0F21, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_byt }, /* SATA Controller IDE (Coleto Creek) */ { 0x8086, 0x23a6, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata }, + /* SATA Controller IDE (9 Series) */ + { 0x8086, 0x8c88, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb }, + /* SATA Controller IDE (9 Series) */ + { 0x8086, 0x8c89, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb }, + /* SATA Controller IDE (9 Series) */ + { 0x8086, 0x8c80, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb }, + /* SATA Controller IDE (9 Series) */ + { 0x8086, 0x8c81, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb }, { } /* terminate list */ }; diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 5509e8e..0b6cb25 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -1711,8 +1711,7 @@ static void ahci_handle_port_interrupt(struct ata_port *ap, if (unlikely(resetting)) status &= ~PORT_IRQ_BAD_PMP; - /* if LPM is enabled, PHYRDY doesn't mean anything */ - if (ap->link.lpm_policy > ATA_LPM_MAX_POWER) { + if (sata_lpm_ignore_phy_events(&ap->link)) { status &= ~PORT_IRQ_PHYRDY; ahci_scr_write(&ap->link, SCR_ERROR, SERR_PHYRDY_CHG); } diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index d09fca7..01354dd 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4173,9 +4173,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "ST3320[68]13AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, - /* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */ + /* drives which fail FPDMA_AA activation (some may freeze afterwards) */ { "ST1000LM024 HN-M101MBB", "2AR10001", ATA_HORKAGE_BROKEN_FPDMA_AA }, { "ST1000LM024 HN-M101MBB", "2BA30001", ATA_HORKAGE_BROKEN_FPDMA_AA }, + { "VB0250EAVER", "HPG7", ATA_HORKAGE_BROKEN_FPDMA_AA }, /* Blacklist entries taken from Silicon Image 3124/3132 Windows driver .inf file - also several Linux problem reports */ @@ -4227,7 +4228,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "Micron_M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, { "Crucial_CT???M500SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, { "Micron_M550*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, - { "Crucial_CT???M550SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, + { "Crucial_CT*M550SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, + + /* devices that don't properly handle TRIM commands */ + { "SuperSSpeed S238*", NULL, ATA_HORKAGE_NOTRIM, }, /* * Some WD SATA-I drives spin up and down erratically when the link @@ -4533,7 +4537,8 @@ static unsigned int ata_dev_set_xfermode(struct ata_device *dev) else /* In the ancient relic department - skip all of this */ return 0; - err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); + /* On some disks, this command causes spin-up, so we need longer timeout */ + err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 15000); DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; @@ -4787,6 +4792,10 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words) * ata_qc_new - Request an available ATA command, for queueing * @ap: target port * + * Some ATA host controllers may implement a queue depth which is less + * than ATA_MAX_QUEUE. So we shouldn't allocate a tag which is beyond + * the hardware limitation. + * * LOCKING: * None. */ @@ -4794,14 +4803,15 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words) static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap) { struct ata_queued_cmd *qc = NULL; + unsigned int max_queue = ap->host->n_tags; unsigned int i, tag; /* no command while frozen */ if (unlikely(ap->pflags & ATA_PFLAG_FROZEN)) return NULL; - for (i = 0; i < ATA_MAX_QUEUE; i++) { - tag = (i + ap->last_tag + 1) % ATA_MAX_QUEUE; + for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) { + tag = tag < max_queue ? tag : 0; /* the last tag is reserved for internal command. */ if (tag == ATA_TAG_INTERNAL) @@ -6103,6 +6113,7 @@ void ata_host_init(struct ata_host *host, struct device *dev, { spin_lock_init(&host->lock); mutex_init(&host->eh_mutex); + host->n_tags = ATA_MAX_QUEUE - 1; host->dev = dev; host->ops = ops; } @@ -6184,6 +6195,8 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht) { int i, rc; + host->n_tags = clamp(sht->can_queue, 1, ATA_MAX_QUEUE - 1); + /* host must have been started */ if (!(host->flags & ATA_HOST_STARTED)) { dev_err(host->dev, "BUG: trying to register unstarted host\n"); @@ -6817,6 +6830,38 @@ u32 ata_wait_register(struct ata_port *ap, void __iomem *reg, u32 mask, u32 val, return tmp; } +/** + * sata_lpm_ignore_phy_events - test if PHY event should be ignored + * @link: Link receiving the event + * + * Test whether the received PHY event has to be ignored or not. + * + * LOCKING: + * None: + * + * RETURNS: + * True if the event has to be ignored. + */ +bool sata_lpm_ignore_phy_events(struct ata_link *link) +{ + unsigned long lpm_timeout = link->last_lpm_change + + msecs_to_jiffies(ATA_TMOUT_SPURIOUS_PHY); + + /* if LPM is enabled, PHYRDY doesn't mean anything */ + if (link->lpm_policy > ATA_LPM_MAX_POWER) + return true; + + /* ignore the first PHY event after the LPM policy changed + * as it is might be spurious + */ + if ((link->flags & ATA_LFLAG_CHANGED) && + time_before(jiffies, lpm_timeout)) + return true; + + return false; +} +EXPORT_SYMBOL_GPL(sata_lpm_ignore_phy_events); + /* * Dummy port_ops */ diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 6d87570..c6c77b7 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -3488,6 +3488,9 @@ static int ata_eh_set_lpm(struct ata_link *link, enum ata_lpm_policy policy, } } + link->last_lpm_change = jiffies; + link->flags |= ATA_LFLAG_CHANGED; + return 0; fail: diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c index 7ccc084..85aa761 100644 --- a/drivers/ata/libata-pmp.c +++ b/drivers/ata/libata-pmp.c @@ -460,6 +460,13 @@ static void sata_pmp_quirks(struct ata_port *ap) ATA_LFLAG_NO_SRST | ATA_LFLAG_ASSUME_ATA; } + } else if (vendor == 0x11ab && devid == 0x4140) { + /* Marvell 4140 quirks */ + ata_for_each_link(link, ap, EDGE) { + /* port 4 is for SEMB device and it doesn't like SRST */ + if (link->pmp == 4) + link->flags |= ATA_LFLAG_DISABLED; + } } } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index ef8567d..6fecf0b 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2510,7 +2510,8 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf) rbuf[14] = (lowest_aligned >> 8) & 0x3f; rbuf[15] = lowest_aligned; - if (ata_id_has_trim(args->id)) { + if (ata_id_has_trim(args->id) && + !(dev->horkage & ATA_HORKAGE_NOTRIM)) { rbuf[14] |= 0x80; /* TPE */ if (ata_id_has_zero_after_trim(args->id)) diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index b603720..136803c 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1333,7 +1333,19 @@ void ata_sff_flush_pio_task(struct ata_port *ap) DPRINTK("ENTER\n"); cancel_delayed_work_sync(&ap->sff_pio_task); + + /* + * We wanna reset the HSM state to IDLE. If we do so without + * grabbing the port lock, critical sections protected by it which + * expect the HSM state to stay stable may get surprised. For + * example, we may set IDLE in between the time + * __ata_sff_port_intr() checks for HSM_ST_IDLE and before it calls + * ata_sff_hsm_move() causing ata_sff_hsm_move() to BUG(). + */ + spin_lock_irq(ap->lock); ap->hsm_task_state = HSM_ST_IDLE; + spin_unlock_irq(ap->lock); + ap->sff_pio_task_link = NULL; if (ata_msg_ctl(ap)) @@ -2008,13 +2020,15 @@ static int ata_bus_softreset(struct ata_port *ap, unsigned int devmask, DPRINTK("ata%u: bus reset via SRST\n", ap->print_id); - /* software reset. causes dev0 to be selected */ - iowrite8(ap->ctl, ioaddr->ctl_addr); - udelay(20); /* FIXME: flush */ - iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr); - udelay(20); /* FIXME: flush */ - iowrite8(ap->ctl, ioaddr->ctl_addr); - ap->last_ctl = ap->ctl; + if (ap->ioaddr.ctl_addr) { + /* software reset. causes dev0 to be selected */ + iowrite8(ap->ctl, ioaddr->ctl_addr); + udelay(20); /* FIXME: flush */ + iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr); + udelay(20); /* FIXME: flush */ + iowrite8(ap->ctl, ioaddr->ctl_addr); + ap->last_ctl = ap->ctl; + } /* wait the port to become ready */ return ata_sff_wait_after_reset(&ap->link, devmask, deadline); @@ -2215,10 +2229,6 @@ void ata_sff_error_handler(struct ata_port *ap) spin_unlock_irqrestore(ap->lock, flags); - /* ignore ata_sff_softreset if ctl isn't accessible */ - if (softreset == ata_sff_softreset && !ap->ioaddr.ctl_addr) - softreset = NULL; - /* ignore built-in hardresets if SCR access is not available */ if ((hardreset == sata_std_hardreset || hardreset == sata_sff_hardreset) && !sata_scr_valid(&ap->link)) diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c index 83c4ddb..08223cc 100644 --- a/drivers/ata/pata_octeon_cf.c +++ b/drivers/ata/pata_octeon_cf.c @@ -1069,7 +1069,7 @@ static struct of_device_id octeon_cf_match[] = { }, {}, }; -MODULE_DEVICE_TABLE(of, octeon_i2c_match); +MODULE_DEVICE_TABLE(of, octeon_cf_match); static struct platform_driver octeon_cf_driver = { .probe = octeon_cf_probe, diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c index f1f5b5a..f5640ec 100644 --- a/drivers/ata/pata_scc.c +++ b/drivers/ata/pata_scc.c @@ -585,7 +585,7 @@ static int scc_wait_after_reset(struct ata_link *link, unsigned int devmask, * Note: Original code is ata_bus_softreset(). */ -static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask, +static int scc_bus_softreset(struct ata_port *ap, unsigned int devmask, unsigned long deadline) { struct ata_ioports *ioaddr = &ap->ioaddr; @@ -599,9 +599,7 @@ static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask, udelay(20); out_be32(ioaddr->ctl_addr, ap->ctl); - scc_wait_after_reset(&ap->link, devmask, deadline); - - return 0; + return scc_wait_after_reset(&ap->link, devmask, deadline); } /** @@ -618,7 +616,8 @@ static int scc_softreset(struct ata_link *link, unsigned int *classes, { struct ata_port *ap = link->ap; unsigned int slave_possible = ap->flags & ATA_FLAG_SLAVE_POSS; - unsigned int devmask = 0, err_mask; + unsigned int devmask = 0; + int rc; u8 err; DPRINTK("ENTER\n"); @@ -634,9 +633,9 @@ static int scc_softreset(struct ata_link *link, unsigned int *classes, /* issue bus reset */ DPRINTK("about to softreset, devmask=%x\n", devmask); - err_mask = scc_bus_softreset(ap, devmask, deadline); - if (err_mask) { - ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", err_mask); + rc = scc_bus_softreset(ap, devmask, deadline); + if (rc) { + ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", rc); return -EIO; } diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c index e27f31f..9e79f55 100644 --- a/drivers/ata/pata_serverworks.c +++ b/drivers/ata/pata_serverworks.c @@ -251,12 +251,18 @@ static void serverworks_set_dmamode(struct ata_port *ap, struct ata_device *adev pci_write_config_byte(pdev, 0x54, ultra_cfg); } -static struct scsi_host_template serverworks_sht = { +static struct scsi_host_template serverworks_osb4_sht = { + ATA_BMDMA_SHT(DRV_NAME), + .sg_tablesize = LIBATA_DUMB_MAX_PRD, +}; + +static struct scsi_host_template serverworks_csb_sht = { ATA_BMDMA_SHT(DRV_NAME), }; static struct ata_port_operations serverworks_osb4_port_ops = { .inherits = &ata_bmdma_port_ops, + .qc_prep = ata_bmdma_dumb_qc_prep, .cable_detect = serverworks_cable_detect, .mode_filter = serverworks_osb4_filter, .set_piomode = serverworks_set_piomode, @@ -265,6 +271,7 @@ static struct ata_port_operations serverworks_osb4_port_ops = { static struct ata_port_operations serverworks_csb_port_ops = { .inherits = &serverworks_osb4_port_ops, + .qc_prep = ata_bmdma_qc_prep, .mode_filter = serverworks_csb_filter, }; @@ -404,6 +411,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id } }; const struct ata_port_info *ppi[] = { &info[id->driver_data], NULL }; + struct scsi_host_template *sht = &serverworks_csb_sht; int rc; rc = pcim_enable_device(pdev); @@ -417,6 +425,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id /* Select non UDMA capable OSB4 if we can't do fixups */ if (rc < 0) ppi[0] = &info[1]; + sht = &serverworks_osb4_sht; } /* setup CSB5/CSB6 : South Bridge and IDE option RAID */ else if ((pdev->device == PCI_DEVICE_ID_SERVERWORKS_CSB5IDE) || @@ -433,7 +442,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id ppi[1] = &ata_dummy_port_info; } - return ata_pci_bmdma_init_one(pdev, ppi, &serverworks_sht, NULL, 0); + return ata_pci_bmdma_init_one(pdev, ppi, sht, NULL, 0); } #ifdef CONFIG_PM diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index 73510d0..113d722 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -798,7 +798,7 @@ static int dma_dwc_init(struct sata_dwc_device *hsdev, int irq) if (err) { dev_err(host_pvt.dwc_dev, "%s: dma_request_interrupts returns" " %d\n", __func__, err); - goto error_out; + return err; } /* Enabe DMA */ @@ -809,11 +809,6 @@ static int dma_dwc_init(struct sata_dwc_device *hsdev, int irq) sata_dma_regs); return 0; - -error_out: - dma_dwc_exit(hsdev); - - return err; } static int sata_dwc_scr_read(struct ata_link *link, unsigned int scr, u32 *val) @@ -1663,7 +1658,7 @@ static int sata_dwc_probe(struct platform_device *ofdev) char *ver = (char *)&versionr; u8 *base = NULL; int err = 0; - int irq, rc; + int irq; struct ata_host *host; struct ata_port_info pi = sata_dwc_port_info[0]; const struct ata_port_info *ppi[] = { &pi, NULL }; @@ -1726,7 +1721,7 @@ static int sata_dwc_probe(struct platform_device *ofdev) if (irq == NO_IRQ) { dev_err(&ofdev->dev, "no SATA DMA irq\n"); err = -ENODEV; - goto error_out; + goto error_iomap; } /* Get physical SATA DMA register base address */ @@ -1735,14 +1730,16 @@ static int sata_dwc_probe(struct platform_device *ofdev) dev_err(&ofdev->dev, "ioremap failed for AHBDMA register" " address\n"); err = -ENODEV; - goto error_out; + goto error_iomap; } /* Save dev for later use in dev_xxx() routines */ host_pvt.dwc_dev = &ofdev->dev; /* Initialize AHB DMAC */ - dma_dwc_init(hsdev, irq); + err = dma_dwc_init(hsdev, irq); + if (err) + goto error_dma_iomap; /* Enable SATA Interrupts */ sata_dwc_enable_interrupts(hsdev); @@ -1760,9 +1757,8 @@ static int sata_dwc_probe(struct platform_device *ofdev) * device discovery process, invoking our port_start() handler & * error_handler() to execute a dummy Softreset EH session */ - rc = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht); - - if (rc != 0) + err = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht); + if (err) dev_err(&ofdev->dev, "failed to activate host"); dev_set_drvdata(&ofdev->dev, host); @@ -1771,7 +1767,8 @@ static int sata_dwc_probe(struct platform_device *ofdev) error_out: /* Free SATA DMA resources */ dma_dwc_exit(hsdev); - +error_dma_iomap: + iounmap((void __iomem *)host_pvt.sata_dma_regs); error_iomap: iounmap(base); error_kmalloc: @@ -1792,6 +1789,7 @@ static int sata_dwc_remove(struct platform_device *ofdev) /* Free SATA DMA resources */ dma_dwc_exit(hsdev); + iounmap((void __iomem *)host_pvt.sata_dma_regs); iounmap(hsdev->reg_base); kfree(hsdev); kfree(host); diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index fb0b40a..ee2780d 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1503,7 +1503,7 @@ static int sata_fsl_probe(struct platform_device *ofdev) host_priv->csr_base = csr_base; irq = irq_of_parse_and_map(ofdev->dev.of_node, 0); - if (irq < 0) { + if (!irq) { dev_err(&ofdev->dev, "invalid irq from platform\n"); goto error_exit_with_cleanup; } diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 2b25bd8..c1ea780 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -146,6 +146,7 @@ enum sata_rcar_type { RCAR_GEN1_SATA, RCAR_GEN2_SATA, + RCAR_R8A7790_ES1_SATA, }; struct sata_rcar_priv { @@ -763,6 +764,9 @@ static void sata_rcar_setup_port(struct ata_host *host) ap->udma_mask = ATA_UDMA6; ap->flags |= ATA_FLAG_SATA; + if (priv->type == RCAR_R8A7790_ES1_SATA) + ap->flags |= ATA_FLAG_NO_DIPM; + ioaddr->cmd_addr = base + SDATA_REG; ioaddr->ctl_addr = base + SSDEVCON_REG; ioaddr->scr_addr = base + SCRSSTS_REG; @@ -792,6 +796,7 @@ static void sata_rcar_init_controller(struct ata_host *host) sata_rcar_gen1_phy_init(priv); break; case RCAR_GEN2_SATA: + case RCAR_R8A7790_ES1_SATA: sata_rcar_gen2_phy_init(priv); break; default: @@ -838,6 +843,10 @@ static struct of_device_id sata_rcar_match[] = { .data = (void *)RCAR_GEN2_SATA }, { + .compatible = "renesas,sata-r8a7790-es1", + .data = (void *)RCAR_R8A7790_ES1_SATA + }, + { .compatible = "renesas,sata-r8a7791", .data = (void *)RCAR_GEN2_SATA }, @@ -849,6 +858,7 @@ static const struct platform_device_id sata_rcar_id_table[] = { { "sata_rcar", RCAR_GEN1_SATA }, /* Deprecated by "sata-r8a7779" */ { "sata-r8a7779", RCAR_GEN1_SATA }, { "sata-r8a7790", RCAR_GEN2_SATA }, + { "sata-r8a7790-es1", RCAR_R8A7790_ES1_SATA }, { "sata-r8a7791", RCAR_GEN2_SATA }, { }, }; diff --git a/drivers/auxdisplay/ks0108.c b/drivers/auxdisplay/ks0108.c index 5b93852..0d75285 100644 --- a/drivers/auxdisplay/ks0108.c +++ b/drivers/auxdisplay/ks0108.c @@ -139,6 +139,7 @@ static int __init ks0108_init(void) ks0108_pardevice = parport_register_device(ks0108_parport, KS0108_NAME, NULL, NULL, NULL, PARPORT_DEV_EXCL, NULL); + parport_put_port(ks0108_parport); if (ks0108_pardevice == NULL) { printk(KERN_ERR KS0108_NAME ": ERROR: " "parport didn't register new device\n"); diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 83e910a..79bc203 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -254,13 +254,15 @@ static ssize_t store_drivers_probe(struct bus_type *bus, const char *buf, size_t count) { struct device *dev; + int err = -EINVAL; dev = bus_find_device_by_name(bus, NULL, buf); if (!dev) return -ENODEV; - if (bus_rescan_devices_helper(dev, NULL) != 0) - return -EINVAL; - return count; + if (bus_rescan_devices_helper(dev, NULL) == 0) + err = count; + put_device(dev); + return err; } static struct device *next_device(struct klist_iter *i) @@ -513,11 +515,11 @@ int bus_add_device(struct device *dev) goto out_put; error = device_add_groups(dev, bus->dev_groups); if (error) - goto out_groups; + goto out_id; error = sysfs_create_link(&bus->p->devices_kset->kobj, &dev->kobj, dev_name(dev)); if (error) - goto out_id; + goto out_groups; error = sysfs_create_link(&dev->kobj, &dev->bus->p->subsys.kobj, "subsystem"); if (error) diff --git a/drivers/base/core.c b/drivers/base/core.c index 2b56717..6a8955e 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -741,12 +741,12 @@ class_dir_create_and_add(struct class *class, struct kobject *parent_kobj) return &dir->kobj; } +static DEFINE_MUTEX(gdp_mutex); static struct kobject *get_device_parent(struct device *dev, struct device *parent) { if (dev->class) { - static DEFINE_MUTEX(gdp_mutex); struct kobject *kobj = NULL; struct kobject *parent_kobj; struct kobject *k; @@ -810,7 +810,9 @@ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir) glue_dir->kset != &dev->class->p->glue_dirs) return; + mutex_lock(&gdp_mutex); kobject_put(glue_dir); + mutex_unlock(&gdp_mutex); } static void cleanup_device_parent(struct device *dev) diff --git a/drivers/base/devres.c b/drivers/base/devres.c index 545c4de..cbe0b58 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -297,10 +297,10 @@ void * devres_get(struct device *dev, void *new_res, if (!dr) { add_dr(dev, &new_dr->node); dr = new_dr; - new_dr = NULL; + new_res = NULL; } spin_unlock_irqrestore(&dev->devres_lock, flags); - devres_free(new_dr); + devres_free(new_res); return dr->data; } diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index c30df50e..f0c15f9 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -544,10 +544,8 @@ static void fw_dev_release(struct device *dev) kfree(fw_priv); } -static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env) +static int do_firmware_uevent(struct firmware_priv *fw_priv, struct kobj_uevent_env *env) { - struct firmware_priv *fw_priv = to_firmware_priv(dev); - if (add_uevent_var(env, "FIRMWARE=%s", fw_priv->buf->fw_id)) return -ENOMEM; if (add_uevent_var(env, "TIMEOUT=%i", loading_timeout)) @@ -558,6 +556,18 @@ static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env) return 0; } +static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + struct firmware_priv *fw_priv = to_firmware_priv(dev); + int err = 0; + + mutex_lock(&fw_lock); + if (fw_priv->buf) + err = do_firmware_uevent(fw_priv, env); + mutex_unlock(&fw_lock); + return err; +} + static struct class firmware_class = { .name = "firmware", .class_attrs = firmware_class_attrs, @@ -1081,6 +1091,9 @@ _request_firmware(const struct firmware **firmware_p, const char *name, if (!firmware_p) return -EINVAL; + if (!name || name[0] == '\0') + return -EINVAL; + ret = _request_firmware_prepare(&fw, name, device); if (ret <= 0) /* error or already assigned */ goto out; diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 3c51eb0..57d8f67 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -89,8 +89,13 @@ int platform_get_irq(struct platform_device *dev, unsigned int num) return dev->archdata.irqs[num]; #else struct resource *r; - if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) - return of_irq_get(dev->dev.of_node, num); + if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) { + int ret; + + ret = of_irq_get(dev->dev.of_node, num); + if (ret >= 0 || ret == -EPROBE_DEFER) + return ret; + } r = platform_get_resource(dev, IORESOURCE_IRQ, num); @@ -349,9 +354,7 @@ int platform_device_add(struct platform_device *pdev) while (--i >= 0) { struct resource *r = &pdev->resource[i]; - unsigned long type = resource_type(r); - - if (type == IORESOURCE_MEM || type == IORESOURCE_IO) + if (r->parent) release_resource(r); } @@ -382,9 +385,7 @@ void platform_device_del(struct platform_device *pdev) for (i = 0; i < pdev->num_resources; i++) { struct resource *r = &pdev->resource[i]; - unsigned long type = resource_type(r); - - if (type == IORESOURCE_MEM || type == IORESOURCE_IO) + if (r->parent) release_resource(r); } } diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c index 930cad4..f3f7136 100644 --- a/drivers/base/regmap/regcache-rbtree.c +++ b/drivers/base/regmap/regcache-rbtree.c @@ -302,18 +302,27 @@ static int regcache_rbtree_insert_to_block(struct regmap *map, if (!blk) return -ENOMEM; - present = krealloc(rbnode->cache_present, - BITS_TO_LONGS(blklen) * sizeof(*present), GFP_KERNEL); - if (!present) { - kfree(blk); - return -ENOMEM; + if (BITS_TO_LONGS(blklen) > BITS_TO_LONGS(rbnode->blklen)) { + present = krealloc(rbnode->cache_present, + BITS_TO_LONGS(blklen) * sizeof(*present), + GFP_KERNEL); + if (!present) { + kfree(blk); + return -ENOMEM; + } + + memset(present + BITS_TO_LONGS(rbnode->blklen), 0, + (BITS_TO_LONGS(blklen) - BITS_TO_LONGS(rbnode->blklen)) + * sizeof(*present)); + } else { + present = rbnode->cache_present; } /* insert the register value in the correct place in the rbnode block */ if (pos == 0) { memmove(blk + offset * map->cache_word_size, blk, rbnode->blklen * map->cache_word_size); - bitmap_shift_right(present, present, offset, blklen); + bitmap_shift_left(present, present, offset, blklen); } /* update the rbnode block, its size and the base register */ diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index d4dd771..154e7a8 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -701,7 +701,7 @@ int regcache_sync_block(struct regmap *map, void *block, unsigned int block_base, unsigned int start, unsigned int end) { - if (regmap_can_raw_write(map)) + if (regmap_can_raw_write(map) && !map->use_single_rw) return regcache_sync_block_raw(map, block, cache_present, block_base, start, end); else diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index c5471cd..d39fd61 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -473,6 +473,7 @@ void regmap_debugfs_init(struct regmap *map, const char *name) { struct rb_node *next; struct regmap_range_node *range_node; + const char *devname = "dummy"; /* If we don't have the debugfs root yet, postpone init */ if (!regmap_debugfs_root) { @@ -491,12 +492,15 @@ void regmap_debugfs_init(struct regmap *map, const char *name) INIT_LIST_HEAD(&map->debugfs_off_cache); mutex_init(&map->cache_lock); + if (map->dev) + devname = dev_name(map->dev); + if (name) { map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s", - dev_name(map->dev), name); + devname, name); name = map->debugfs_name; } else { - name = dev_name(map->dev); + name = devname; } map->debugfs = debugfs_create_dir(name, regmap_debugfs_root); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 6a19515..58559d7 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -105,7 +105,7 @@ bool regmap_readable(struct regmap *map, unsigned int reg) bool regmap_volatile(struct regmap *map, unsigned int reg) { - if (!regmap_readable(map, reg)) + if (!map->format.format_write && !regmap_readable(map, reg)) return false; if (map->volatile_reg) @@ -808,11 +808,10 @@ EXPORT_SYMBOL_GPL(devm_regmap_init); static void regmap_field_init(struct regmap_field *rm_field, struct regmap *regmap, struct reg_field reg_field) { - int field_bits = reg_field.msb - reg_field.lsb + 1; rm_field->regmap = regmap; rm_field->reg = reg_field.reg; rm_field->shift = reg_field.lsb; - rm_field->mask = ((BIT(field_bits) - 1) << reg_field.lsb); + rm_field->mask = GENMASK(reg_field.msb, reg_field.lsb); rm_field->id_size = reg_field.id_size; rm_field->id_offset = reg_field.id_offset; } @@ -1308,7 +1307,7 @@ int _regmap_write(struct regmap *map, unsigned int reg, } #ifdef LOG_DEVICE - if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0) + if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0) dev_info(map->dev, "%x <= %x\n", reg, val); #endif @@ -1557,6 +1556,11 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, } else { void *wval; + if (!val_count) { + ret = -EINVAL; + goto out; + } + wval = kmemdup(val, val_count * val_bytes, GFP_KERNEL); if (!wval) { ret = -ENOMEM; @@ -1739,7 +1743,7 @@ static int _regmap_read(struct regmap *map, unsigned int reg, ret = map->reg_read(context, reg, val); if (ret == 0) { #ifdef LOG_DEVICE - if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0) + if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0) dev_info(map->dev, "%x => %x\n", reg, *val); #endif @@ -1942,7 +1946,7 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, &ival); if (ret != 0) return ret; - memcpy(val + (i * val_bytes), &ival, val_bytes); + map->format.format_val(val + (i * val_bytes), ival, 0); } } diff --git a/drivers/block/drbd/drbd_interval.c b/drivers/block/drbd/drbd_interval.c index 89c497c..04a14e0 100644 --- a/drivers/block/drbd/drbd_interval.c +++ b/drivers/block/drbd/drbd_interval.c @@ -79,6 +79,7 @@ bool drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) { struct rb_node **new = &root->rb_node, *parent = NULL; + sector_t this_end = this->sector + (this->size >> 9); BUG_ON(!IS_ALIGNED(this->size, 512)); @@ -87,6 +88,8 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) rb_entry(*new, struct drbd_interval, rb); parent = *new; + if (here->end < this_end) + here->end = this_end; if (this->sector < here->sector) new = &(*new)->rb_left; else if (this->sector > here->sector) @@ -99,6 +102,7 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) return false; } + this->end = this_end; rb_link_node(&this->rb, parent, new); rb_insert_augmented(&this->rb, root, &augment_callbacks); return true; diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index c706d50..8c16c2f 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -525,6 +525,12 @@ void conn_try_outdate_peer_async(struct drbd_tconn *tconn) struct task_struct *opa; kref_get(&tconn->kref); + /* We may just have force_sig()'ed this thread + * to get it out of some blocking network function. + * Clear signals; otherwise kthread_run(), which internally uses + * wait_on_completion_killable(), will mistake our pending signal + * for a new fatal signal and fail. */ + flush_signals(current); opa = kthread_run(_try_outdate_peer_async, tconn, "drbd_async_h"); if (IS_ERR(opa)) { conn_err(tconn, "out of mem, failed to invoke fence-peer helper\n"); diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 104a040..6efdbea 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -1310,6 +1310,7 @@ int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct struct request_queue * const b = mdev->ldev->backing_bdev->bd_disk->queue; if (b->merge_bvec_fn) { + bvm->bi_bdev = mdev->ldev->backing_bdev; backing_limit = b->merge_bvec_fn(b, bvm, bvec); limit = min(limit, backing_limit); } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 55298db..d180936 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -814,10 +814,6 @@ static int __init nbd_init(void) return -EINVAL; } - nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL); - if (!nbd_dev) - return -ENOMEM; - part_shift = 0; if (max_part > 0) { part_shift = fls(max_part); @@ -839,6 +835,10 @@ static int __init nbd_init(void) if (nbds_max > 1UL << (MINORBITS - part_shift)) return -EINVAL; + nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL); + if (!nbd_dev) + return -ENOMEM; + for (i = 0; i < nbds_max; i++) { struct gendisk *disk = alloc_disk(1 << part_shift); if (!disk) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 7296c7f..b583773 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -508,6 +508,7 @@ void rbd_warn(struct rbd_device *rbd_dev, const char *fmt, ...) # define rbd_assert(expr) ((void) 0) #endif /* !RBD_DEBUG */ +static void rbd_osd_copyup_callback(struct rbd_obj_request *obj_request); static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request); static void rbd_img_parent_read(struct rbd_obj_request *obj_request); static void rbd_dev_remove_parent(struct rbd_device *rbd_dev); @@ -1651,6 +1652,16 @@ static void rbd_osd_stat_callback(struct rbd_obj_request *obj_request) obj_request_done_set(obj_request); } +static void rbd_osd_call_callback(struct rbd_obj_request *obj_request) +{ + dout("%s: obj %p\n", __func__, obj_request); + + if (obj_request_img_data_test(obj_request)) + rbd_osd_copyup_callback(obj_request); + else + obj_request_done_set(obj_request); +} + static void rbd_osd_req_callback(struct ceph_osd_request *osd_req, struct ceph_msg *msg) { @@ -1689,6 +1700,8 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req, rbd_osd_stat_callback(obj_request); break; case CEPH_OSD_OP_CALL: + rbd_osd_call_callback(obj_request); + break; case CEPH_OSD_OP_NOTIFY_ACK: case CEPH_OSD_OP_WATCH: rbd_osd_trivial_callback(obj_request); @@ -1826,11 +1839,11 @@ static struct rbd_obj_request *rbd_obj_request_create(const char *object_name, rbd_assert(obj_request_type_valid(type)); size = strlen(object_name) + 1; - name = kmalloc(size, GFP_KERNEL); + name = kmalloc(size, GFP_NOIO); if (!name) return NULL; - obj_request = kmem_cache_zalloc(rbd_obj_request_cache, GFP_KERNEL); + obj_request = kmem_cache_zalloc(rbd_obj_request_cache, GFP_NOIO); if (!obj_request) { kfree(name); return NULL; @@ -1926,32 +1939,26 @@ static void rbd_dev_parent_put(struct rbd_device *rbd_dev) * If an image has a non-zero parent overlap, get a reference to its * parent. * - * We must get the reference before checking for the overlap to - * coordinate properly with zeroing the parent overlap in - * rbd_dev_v2_parent_info() when an image gets flattened. We - * drop it again if there is no overlap. - * * Returns true if the rbd device has a parent with a non-zero * overlap and a reference for it was successfully taken, or * false otherwise. */ static bool rbd_dev_parent_get(struct rbd_device *rbd_dev) { - int counter; + int counter = 0; if (!rbd_dev->parent_spec) return false; - counter = atomic_inc_return_safe(&rbd_dev->parent_ref); - if (counter > 0 && rbd_dev->parent_overlap) - return true; - - /* Image was flattened, but parent is not yet torn down */ + down_read(&rbd_dev->header_rwsem); + if (rbd_dev->parent_overlap) + counter = atomic_inc_return_safe(&rbd_dev->parent_ref); + up_read(&rbd_dev->header_rwsem); if (counter < 0) rbd_warn(rbd_dev, "parent reference overflow\n"); - return false; + return counter > 0; } /* @@ -2090,6 +2097,11 @@ static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request) result, xferred); if (!img_request->result) img_request->result = result; + /* + * Need to end I/O on the entire obj_request worth of + * bytes in case of error. + */ + xferred = obj_request->length; } /* Image object requests don't own their page array */ @@ -2276,13 +2288,15 @@ out_unwind: } static void -rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request) +rbd_osd_copyup_callback(struct rbd_obj_request *obj_request) { struct rbd_img_request *img_request; struct rbd_device *rbd_dev; struct page **pages; u32 page_count; + dout("%s: obj %p\n", __func__, obj_request); + rbd_assert(obj_request->type == OBJ_REQUEST_BIO); rbd_assert(obj_request_img_data_test(obj_request)); img_request = obj_request->img_request; @@ -2308,9 +2322,7 @@ rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request) if (!obj_request->result) obj_request->xferred = obj_request->length; - /* Finish up with the normal image object callback */ - - rbd_img_obj_callback(obj_request); + obj_request_done_set(obj_request); } static void @@ -2407,7 +2419,6 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request) /* All set, send it off. */ - orig_request->callback = rbd_img_obj_copyup_callback; osdc = &rbd_dev->rbd_client->client->osdc; img_result = rbd_obj_request_submit(osdc, orig_request); if (!img_result) @@ -3217,7 +3228,7 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev, page_count = (u32) calc_pages_for(offset, length); pages = ceph_alloc_page_vector(page_count, GFP_KERNEL); if (IS_ERR(pages)) - ret = PTR_ERR(pages); + return PTR_ERR(pages); ret = -ENOMEM; obj_request = rbd_obj_request_create(object_name, offset, length, @@ -3904,7 +3915,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) */ if (rbd_dev->parent_overlap) { rbd_dev->parent_overlap = 0; - smp_mb(); rbd_dev_parent_put(rbd_dev); pr_info("%s: clone image has been flattened\n", rbd_dev->disk->disk_name); @@ -3948,7 +3958,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) * treat it specially. */ rbd_dev->parent_overlap = overlap; - smp_mb(); if (!overlap) { /* A null parent_spec indicates it's the initial probe */ @@ -4764,10 +4773,7 @@ static void rbd_dev_unprobe(struct rbd_device *rbd_dev) { struct rbd_image_header *header; - /* Drop parent reference unless it's already been done (or none) */ - - if (rbd_dev->parent_overlap) - rbd_dev_parent_put(rbd_dev); + rbd_dev_parent_put(rbd_dev); /* Free dynamic fields from the header, then zero it out */ diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 5814deb..0ebadf9 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -22,8 +23,8 @@ #define DRV_MODULE_NAME "sunvdc" #define PFX DRV_MODULE_NAME ": " -#define DRV_MODULE_VERSION "1.0" -#define DRV_MODULE_RELDATE "June 25, 2007" +#define DRV_MODULE_VERSION "1.1" +#define DRV_MODULE_RELDATE "February 13, 2013" static char version[] = DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n"; @@ -32,7 +33,7 @@ MODULE_DESCRIPTION("Sun LDOM virtual disk client driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_MODULE_VERSION); -#define VDC_TX_RING_SIZE 256 +#define VDC_TX_RING_SIZE 512 #define WAITING_FOR_LINK_UP 0x01 #define WAITING_FOR_TX_SPACE 0x02 @@ -65,11 +66,9 @@ struct vdc_port { u64 operations; u32 vdisk_size; u8 vdisk_type; + u8 vdisk_mtype; char disk_name[32]; - - struct vio_disk_geom geom; - struct vio_disk_vtoc label; }; static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio) @@ -79,9 +78,16 @@ static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio) /* Ordered from largest major to lowest */ static struct vio_version vdc_versions[] = { + { .major = 1, .minor = 1 }, { .major = 1, .minor = 0 }, }; +static inline int vdc_version_supported(struct vdc_port *port, + u16 major, u16 minor) +{ + return port->vio.ver.major == major && port->vio.ver.minor >= minor; +} + #define VDCBLK_NAME "vdisk" static int vdc_major; #define PARTITION_SHIFT 3 @@ -94,18 +100,54 @@ static inline u32 vdc_tx_dring_avail(struct vio_dring_state *dr) static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo) { struct gendisk *disk = bdev->bd_disk; - struct vdc_port *port = disk->private_data; + sector_t nsect = get_capacity(disk); + sector_t cylinders = nsect; - geo->heads = (u8) port->geom.num_hd; - geo->sectors = (u8) port->geom.num_sec; - geo->cylinders = port->geom.num_cyl; + geo->heads = 0xff; + geo->sectors = 0x3f; + sector_div(cylinders, geo->heads * geo->sectors); + geo->cylinders = cylinders; + if ((sector_t)(geo->cylinders + 1) * geo->heads * geo->sectors < nsect) + geo->cylinders = 0xffff; return 0; } +/* Add ioctl/CDROM_GET_CAPABILITY to support cdrom_id in udev + * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD. + * Needed to be able to install inside an ldom from an iso image. + */ +static int vdc_ioctl(struct block_device *bdev, fmode_t mode, + unsigned command, unsigned long argument) +{ + int i; + struct gendisk *disk; + + switch (command) { + case CDROMMULTISESSION: + pr_debug(PFX "Multisession CDs not supported\n"); + for (i = 0; i < sizeof(struct cdrom_multisession); i++) + if (put_user(0, (char __user *)(argument + i))) + return -EFAULT; + return 0; + + case CDROM_GET_CAPABILITY: + disk = bdev->bd_disk; + + if (bdev->bd_disk && (disk->flags & GENHD_FL_CD)) + return 0; + return -EINVAL; + + default: + pr_debug(PFX "ioctl %08x not supported\n", command); + return -EINVAL; + } +} + static const struct block_device_operations vdc_fops = { .owner = THIS_MODULE, .getgeo = vdc_getgeo, + .ioctl = vdc_ioctl, }; static void vdc_finish(struct vio_driver_state *vio, int err, int waiting_for) @@ -165,9 +207,9 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg) struct vio_disk_attr_info *pkt = arg; viodbg(HS, "GOT ATTR stype[0x%x] ops[%llx] disk_size[%llu] disk_type[%x] " - "xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n", + "mtype[0x%x] xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n", pkt->tag.stype, pkt->operations, - pkt->vdisk_size, pkt->vdisk_type, + pkt->vdisk_size, pkt->vdisk_type, pkt->vdisk_mtype, pkt->xfer_mode, pkt->vdisk_block_size, pkt->max_xfer_size); @@ -192,8 +234,11 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg) } port->operations = pkt->operations; - port->vdisk_size = pkt->vdisk_size; port->vdisk_type = pkt->vdisk_type; + if (vdc_version_supported(port, 1, 1)) { + port->vdisk_size = pkt->vdisk_size; + port->vdisk_mtype = pkt->vdisk_mtype; + } if (pkt->max_xfer_size < port->max_xfer_size) port->max_xfer_size = pkt->max_xfer_size; port->vdisk_block_size = pkt->vdisk_block_size; @@ -236,7 +281,9 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr, __blk_end_request(req, (desc->status ? -EIO : 0), desc->size); - if (blk_queue_stopped(port->disk->queue)) + /* restart blk queue when ring is half emptied */ + if (blk_queue_stopped(port->disk->queue) && + vdc_tx_dring_avail(dr) * 100 / VDC_TX_RING_SIZE >= 50) blk_start_queue(port->disk->queue); } @@ -388,12 +435,6 @@ static int __send_request(struct request *req) for (i = 0; i < nsg; i++) len += sg[i].length; - if (unlikely(vdc_tx_dring_avail(dr) < 1)) { - blk_stop_queue(port->disk->queue); - err = -ENOMEM; - goto out; - } - desc = vio_dring_cur(dr); err = ldc_map_sg(port->vio.lp, sg, nsg, @@ -433,21 +474,32 @@ static int __send_request(struct request *req) port->req_id++; dr->prod = (dr->prod + 1) & (VDC_TX_RING_SIZE - 1); } -out: return err; } -static void do_vdc_request(struct request_queue *q) +static void do_vdc_request(struct request_queue *rq) { - while (1) { - struct request *req = blk_fetch_request(q); + struct request *req; - if (!req) - break; + while ((req = blk_peek_request(rq)) != NULL) { + struct vdc_port *port; + struct vio_dring_state *dr; - if (__send_request(req) < 0) - __blk_end_request_all(req, -EIO); + port = req->rq_disk->private_data; + dr = &port->vio.drings[VIO_DRIVER_TX_RING]; + if (unlikely(vdc_tx_dring_avail(dr) < 1)) + goto wait; + + blk_start_request(req); + + if (__send_request(req) < 0) { + blk_requeue_request(rq, req); +wait: + /* Avoid pointless unplugs. */ + blk_stop_queue(rq); + break; + } } } @@ -656,25 +708,27 @@ static int probe_disk(struct vdc_port *port) if (comp.err) return comp.err; - err = generic_request(port, VD_OP_GET_VTOC, - &port->label, sizeof(port->label)); - if (err < 0) { - printk(KERN_ERR PFX "VD_OP_GET_VTOC returns error %d\n", err); - return err; - } - - err = generic_request(port, VD_OP_GET_DISKGEOM, - &port->geom, sizeof(port->geom)); - if (err < 0) { - printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns " - "error %d\n", err); - return err; + if (vdc_version_supported(port, 1, 1)) { + /* vdisk_size should be set during the handshake, if it wasn't + * then the underlying disk is reserved by another system + */ + if (port->vdisk_size == -1) + return -ENODEV; + } else { + struct vio_disk_geom geom; + + err = generic_request(port, VD_OP_GET_DISKGEOM, + &geom, sizeof(geom)); + if (err < 0) { + printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns " + "error %d\n", err); + return err; + } + port->vdisk_size = ((u64)geom.num_cyl * + (u64)geom.num_hd * + (u64)geom.num_sec); } - port->vdisk_size = ((u64)port->geom.num_cyl * - (u64)port->geom.num_hd * - (u64)port->geom.num_sec); - q = blk_init_queue(do_vdc_request, &port->vio.lock); if (!q) { printk(KERN_ERR PFX "%s: Could not allocate queue.\n", @@ -691,6 +745,10 @@ static int probe_disk(struct vdc_port *port) port->disk = g; + /* Each segment in a request is up to an aligned page in size. */ + blk_queue_segment_boundary(q, PAGE_SIZE - 1); + blk_queue_max_segment_size(q, PAGE_SIZE); + blk_queue_max_segments(q, port->ring_cookies); blk_queue_max_hw_sectors(q, port->max_xfer_size); g->major = vdc_major; @@ -704,9 +762,32 @@ static int probe_disk(struct vdc_port *port) set_capacity(g, port->vdisk_size); - printk(KERN_INFO PFX "%s: %u sectors (%u MB)\n", + if (vdc_version_supported(port, 1, 1)) { + switch (port->vdisk_mtype) { + case VD_MEDIA_TYPE_CD: + pr_info(PFX "Virtual CDROM %s\n", port->disk_name); + g->flags |= GENHD_FL_CD; + g->flags |= GENHD_FL_REMOVABLE; + set_disk_ro(g, 1); + break; + + case VD_MEDIA_TYPE_DVD: + pr_info(PFX "Virtual DVD %s\n", port->disk_name); + g->flags |= GENHD_FL_CD; + g->flags |= GENHD_FL_REMOVABLE; + set_disk_ro(g, 1); + break; + + case VD_MEDIA_TYPE_FIXED: + pr_info(PFX "Virtual Hard disk %s\n", port->disk_name); + break; + } + } + + pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n", g->disk_name, - port->vdisk_size, (port->vdisk_size >> (20 - 9))); + port->vdisk_size, (port->vdisk_size >> (20 - 9)), + port->vio.ver.major, port->vio.ver.minor); add_disk(g); @@ -765,6 +846,7 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) else snprintf(port->disk_name, sizeof(port->disk_name), VDCBLK_NAME "%c", 'a' + ((int)vdev->dev_no % 26)); + port->vdisk_size = -1; err = vio_driver_init(&port->vio, vdev, VDEV_DISK, vdc_versions, ARRAY_SIZE(vdc_versions), diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 64c60ed..63fc7f0 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -763,6 +763,7 @@ again: BUG_ON(new_map_idx >= segs_to_map); if (unlikely(map[new_map_idx].status != 0)) { pr_debug(DRV_PFX "invalid buffer -- could not remap it\n"); + put_free_pages(blkif, &pages[seg_idx]->page, 1); pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE; ret |= 1; goto next; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index efe1b47..e88556a 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1093,8 +1093,10 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info, * Add the used indirect page back to the list of * available pages for indirect grefs. */ - indirect_page = pfn_to_page(s->indirect_grants[i]->pfn); - list_add(&indirect_page->lru, &info->indirect_pages); + if (!info->feature_persistent) { + indirect_page = pfn_to_page(s->indirect_grants[i]->pfn); + list_add(&indirect_page->lru, &info->indirect_pages); + } s->indirect_grants[i]->gref = GRANT_INVALID_REF; list_add_tail(&s->indirect_grants[i]->node, &info->grants); } diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 51c557c..d8ddb8e 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -447,7 +447,8 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, } if (page_zero_filled(uncmem)) { - kunmap_atomic(user_mem); + if (user_mem) + kunmap_atomic(user_mem); /* Free memory associated with this sector now. */ write_lock(&zram->meta->tb_lock); zram_free_page(zram, index); diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index b11949c..8ff2b3c 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -62,51 +62,62 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x0CF3, 0x3000) }, /* Atheros AR3011 with sflash firmware*/ + { USB_DEVICE(0x0489, 0xE027) }, + { USB_DEVICE(0x0489, 0xE03D) }, + { USB_DEVICE(0x04F2, 0xAFF1) }, + { USB_DEVICE(0x0930, 0x0215) }, { USB_DEVICE(0x0CF3, 0x3002) }, { USB_DEVICE(0x0CF3, 0xE019) }, { USB_DEVICE(0x13d3, 0x3304) }, - { USB_DEVICE(0x0930, 0x0215) }, - { USB_DEVICE(0x0489, 0xE03D) }, - { USB_DEVICE(0x0489, 0xE027) }, /* Atheros AR9285 Malbec with sflash firmware */ { USB_DEVICE(0x03F0, 0x311D) }, /* Atheros AR3012 with sflash firmware*/ - { USB_DEVICE(0x0CF3, 0x0036) }, - { USB_DEVICE(0x0CF3, 0x3004) }, - { USB_DEVICE(0x0CF3, 0x3008) }, - { USB_DEVICE(0x0CF3, 0x311D) }, - { USB_DEVICE(0x0CF3, 0x817a) }, - { USB_DEVICE(0x13d3, 0x3375) }, + { USB_DEVICE(0x0489, 0xe04d) }, + { USB_DEVICE(0x0489, 0xe04e) }, + { USB_DEVICE(0x0489, 0xe057) }, + { USB_DEVICE(0x0489, 0xe056) }, + { USB_DEVICE(0x0489, 0xe05f) }, + { USB_DEVICE(0x0489, 0xe076) }, + { USB_DEVICE(0x0489, 0xe078) }, + { USB_DEVICE(0x04c5, 0x1330) }, { USB_DEVICE(0x04CA, 0x3004) }, { USB_DEVICE(0x04CA, 0x3005) }, { USB_DEVICE(0x04CA, 0x3006) }, { USB_DEVICE(0x04CA, 0x3007) }, { USB_DEVICE(0x04CA, 0x3008) }, { USB_DEVICE(0x04CA, 0x300b) }, - { USB_DEVICE(0x13d3, 0x3362) }, - { USB_DEVICE(0x0CF3, 0xE004) }, - { USB_DEVICE(0x0CF3, 0xE005) }, + { USB_DEVICE(0x04CA, 0x3010) }, { USB_DEVICE(0x0930, 0x0219) }, { USB_DEVICE(0x0930, 0x0220) }, - { USB_DEVICE(0x0489, 0xe057) }, - { USB_DEVICE(0x13d3, 0x3393) }, - { USB_DEVICE(0x0489, 0xe04e) }, - { USB_DEVICE(0x0489, 0xe056) }, - { USB_DEVICE(0x0489, 0xe04d) }, - { USB_DEVICE(0x04c5, 0x1330) }, - { USB_DEVICE(0x13d3, 0x3402) }, + { USB_DEVICE(0x0930, 0x0227) }, + { USB_DEVICE(0x0b05, 0x17d0) }, + { USB_DEVICE(0x0CF3, 0x0036) }, + { USB_DEVICE(0x0CF3, 0x3004) }, + { USB_DEVICE(0x0CF3, 0x3008) }, + { USB_DEVICE(0x0CF3, 0x311D) }, + { USB_DEVICE(0x0CF3, 0x311E) }, + { USB_DEVICE(0x0CF3, 0x311F) }, { USB_DEVICE(0x0cf3, 0x3121) }, + { USB_DEVICE(0x0CF3, 0x817a) }, { USB_DEVICE(0x0cf3, 0xe003) }, - { USB_DEVICE(0x0489, 0xe05f) }, + { USB_DEVICE(0x0CF3, 0xE004) }, + { USB_DEVICE(0x0CF3, 0xE005) }, + { USB_DEVICE(0x13d3, 0x3362) }, + { USB_DEVICE(0x13d3, 0x3375) }, + { USB_DEVICE(0x13d3, 0x3393) }, + { USB_DEVICE(0x13d3, 0x3402) }, + { USB_DEVICE(0x13d3, 0x3408) }, + { USB_DEVICE(0x13d3, 0x3432) }, + { USB_DEVICE(0x13d3, 0x3474) }, /* Atheros AR5BBU12 with sflash firmware */ { USB_DEVICE(0x0489, 0xE02C) }, /* Atheros AR5BBU22 with sflash firmware */ - { USB_DEVICE(0x0489, 0xE03C) }, { USB_DEVICE(0x0489, 0xE036) }, + { USB_DEVICE(0x0489, 0xE03C) }, { } /* Terminating entry */ }; @@ -119,37 +130,47 @@ MODULE_DEVICE_TABLE(usb, ath3k_table); static const struct usb_device_id ath3k_blist_tbl[] = { /* Atheros AR3012 with sflash firmware*/ - { USB_DEVICE(0x0CF3, 0x0036), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0x311D), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0CF3, 0x817a), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe04d), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe076), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0489, 0xe04d), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0930, 0x0227), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0b05, 0x17d0), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0CF3, 0x0036), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x311D), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x311E), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x311F), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x3121), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0CF3, 0x817a), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0xe003), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3474), .driver_info = BTUSB_ATH3012 }, /* Atheros AR5BBU22 with sflash firmware */ - { USB_DEVICE(0x0489, 0xE03C), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xE036), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xE03C), .driver_info = BTUSB_ATH3012 }, { } /* Terminating entry */ }; @@ -157,6 +178,8 @@ static const struct usb_device_id ath3k_blist_tbl[] = { #define USB_REQ_DFU_DNLOAD 1 #define BULK_SIZE 4096 #define FW_HDR_SIZE 20 +#define TIMEGAP_USEC_MIN 50 +#define TIMEGAP_USEC_MAX 100 static int ath3k_load_firmware(struct usb_device *udev, const struct firmware *firmware) @@ -187,6 +210,9 @@ static int ath3k_load_firmware(struct usb_device *udev, count -= 20; while (count) { + /* workaround the compatibility issue with xHCI controller*/ + usleep_range(TIMEGAP_USEC_MIN, TIMEGAP_USEC_MAX); + size = min_t(uint, count, BULK_SIZE); pipe = usb_sndbulkpipe(udev, 0x02); memcpy(send_buf, firmware->data + sent, size); @@ -283,6 +309,9 @@ static int ath3k_load_fwfile(struct usb_device *udev, count -= size; while (count) { + /* workaround the compatibility issue with xHCI controller*/ + usleep_range(TIMEGAP_USEC_MIN, TIMEGAP_USEC_MAX); + size = min_t(uint, count, BULK_SIZE); pipe = usb_sndbulkpipe(udev, 0x02); diff --git a/drivers/bluetooth/btmrvl_drv.h b/drivers/bluetooth/btmrvl_drv.h index 7399303..9e81a3d0 100644 --- a/drivers/bluetooth/btmrvl_drv.h +++ b/drivers/bluetooth/btmrvl_drv.h @@ -66,6 +66,7 @@ struct btmrvl_adapter { u8 hs_state; u8 wakeup_tries; wait_queue_head_t cmd_wait_q; + wait_queue_head_t event_hs_wait_q; u8 cmd_complete; bool is_suspended; }; diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index 1e0320a..49d2098 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -112,6 +112,7 @@ int btmrvl_process_event(struct btmrvl_private *priv, struct sk_buff *skb) adapter->hs_state = HS_ACTIVATED; if (adapter->psmode) adapter->ps_state = PS_SLEEP; + wake_up_interruptible(&adapter->event_hs_wait_q); BT_DBG("HS ACTIVATED!"); } else { BT_DBG("HS Enable failed"); @@ -251,11 +252,31 @@ EXPORT_SYMBOL_GPL(btmrvl_enable_ps); int btmrvl_enable_hs(struct btmrvl_private *priv) { + struct btmrvl_adapter *adapter = priv->adapter; int ret; ret = btmrvl_send_sync_cmd(priv, BT_CMD_HOST_SLEEP_ENABLE, NULL, 0); - if (ret) + if (ret) { BT_ERR("Host sleep enable command failed\n"); + return ret; + } + + ret = wait_event_interruptible_timeout(adapter->event_hs_wait_q, + adapter->hs_state, + msecs_to_jiffies(WAIT_UNTIL_HS_STATE_CHANGED)); + if (ret < 0) { + BT_ERR("event_hs_wait_q terminated (%d): %d,%d,%d", + ret, adapter->hs_state, adapter->ps_state, + adapter->wakeup_tries); + } else if (!ret) { + BT_ERR("hs_enable timeout: %d,%d,%d", adapter->hs_state, + adapter->ps_state, adapter->wakeup_tries); + ret = -ETIMEDOUT; + } else { + BT_DBG("host sleep enabled: %d,%d,%d", adapter->hs_state, + adapter->ps_state, adapter->wakeup_tries); + ret = 0; + } return ret; } @@ -341,6 +362,7 @@ static void btmrvl_init_adapter(struct btmrvl_private *priv) priv->adapter->ps_state = PS_AWAKE; init_waitqueue_head(&priv->adapter->cmd_wait_q); + init_waitqueue_head(&priv->adapter->event_hs_wait_q); } static void btmrvl_free_adapter(struct btmrvl_private *priv) @@ -648,6 +670,7 @@ int btmrvl_remove_card(struct btmrvl_private *priv) hdev = priv->btmrvl_dev.hcidev; wake_up_interruptible(&priv->adapter->cmd_wait_q); + wake_up_interruptible(&priv->adapter->event_hs_wait_q); kthread_stop(priv->main_thread.task); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 1c7b504..c23658e 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -49,6 +49,7 @@ static struct usb_driver btusb_driver; #define BTUSB_WRONG_SCO_MTU 0x40 #define BTUSB_ATH3012 0x80 #define BTUSB_INTEL 0x100 +#define BTUSB_INTEL_BOOT 0x200 static const struct usb_device_id btusb_table[] = { /* Generic Bluetooth USB device */ @@ -101,21 +102,31 @@ static const struct usb_device_id btusb_table[] = { { USB_DEVICE(0x0c10, 0x0000) }, /* Broadcom BCM20702A0 */ + { USB_DEVICE(0x0489, 0xe042) }, + { USB_DEVICE(0x04ca, 0x2003) }, { USB_DEVICE(0x0b05, 0x17b5) }, { USB_DEVICE(0x0b05, 0x17cb) }, - { USB_DEVICE(0x04ca, 0x2003) }, - { USB_DEVICE(0x0489, 0xe042) }, { USB_DEVICE(0x413c, 0x8197) }, /* Foxconn - Hon Hai */ { USB_VENDOR_AND_INTERFACE_INFO(0x0489, 0xff, 0x01, 0x01) }, - /*Broadcom devices with vendor specific id */ + /* Broadcom devices with vendor specific id */ { USB_VENDOR_AND_INTERFACE_INFO(0x0a5c, 0xff, 0x01, 0x01) }, + /* ASUSTek Computer - Broadcom based */ + { USB_VENDOR_AND_INTERFACE_INFO(0x0b05, 0xff, 0x01, 0x01) }, + /* Belkin F8065bf - Broadcom based */ { USB_VENDOR_AND_INTERFACE_INFO(0x050d, 0xff, 0x01, 0x01) }, + /* IMC Networks - Broadcom based */ + { USB_VENDOR_AND_INTERFACE_INFO(0x13d3, 0xff, 0x01, 0x01) }, + + /* Intel Bluetooth USB Bootloader (RAM module) */ + { USB_DEVICE(0x8087, 0x0a5a), + .driver_info = BTUSB_INTEL_BOOT | BTUSB_BROKEN_ISOC }, + { } /* Terminating entry */ }; @@ -129,56 +140,67 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0a5c, 0x2033), .driver_info = BTUSB_IGNORE }, /* Atheros 3011 with sflash firmware */ + { USB_DEVICE(0x0489, 0xe027), .driver_info = BTUSB_IGNORE }, + { USB_DEVICE(0x0489, 0xe03d), .driver_info = BTUSB_IGNORE }, + { USB_DEVICE(0x04f2, 0xaff1), .driver_info = BTUSB_IGNORE }, + { USB_DEVICE(0x0930, 0x0215), .driver_info = BTUSB_IGNORE }, { USB_DEVICE(0x0cf3, 0x3002), .driver_info = BTUSB_IGNORE }, { USB_DEVICE(0x0cf3, 0xe019), .driver_info = BTUSB_IGNORE }, { USB_DEVICE(0x13d3, 0x3304), .driver_info = BTUSB_IGNORE }, - { USB_DEVICE(0x0930, 0x0215), .driver_info = BTUSB_IGNORE }, - { USB_DEVICE(0x0489, 0xe03d), .driver_info = BTUSB_IGNORE }, - { USB_DEVICE(0x0489, 0xe027), .driver_info = BTUSB_IGNORE }, /* Atheros AR9285 Malbec with sflash firmware */ { USB_DEVICE(0x03f0, 0x311d), .driver_info = BTUSB_IGNORE }, /* Atheros 3012 with sflash firmware */ - { USB_DEVICE(0x0cf3, 0x0036), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0x817a), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe04d), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe076), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0489, 0xe04d), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0930, 0x0227), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0b05, 0x17d0), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x0036), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x311e), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x311f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x3121), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x817a), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0xe003), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3474), .driver_info = BTUSB_ATH3012 }, /* Atheros AR5BBU12 with sflash firmware */ { USB_DEVICE(0x0489, 0xe02c), .driver_info = BTUSB_IGNORE }, /* Atheros AR5BBU12 with sflash firmware */ - { USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe036), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 }, /* Broadcom BCM2035 */ - { USB_DEVICE(0x0a5c, 0x2035), .driver_info = BTUSB_WRONG_SCO_MTU }, - { USB_DEVICE(0x0a5c, 0x200a), .driver_info = BTUSB_WRONG_SCO_MTU }, { USB_DEVICE(0x0a5c, 0x2009), .driver_info = BTUSB_BCM92035 }, + { USB_DEVICE(0x0a5c, 0x200a), .driver_info = BTUSB_WRONG_SCO_MTU }, + { USB_DEVICE(0x0a5c, 0x2035), .driver_info = BTUSB_WRONG_SCO_MTU }, /* Broadcom BCM2045 */ { USB_DEVICE(0x0a5c, 0x2039), .driver_info = BTUSB_WRONG_SCO_MTU }, @@ -309,6 +331,9 @@ static void btusb_intr_complete(struct urb *urb) BT_ERR("%s corrupted event packet", hdev->name); hdev->stat.err_rx++; } + } else if (urb->status == -ENOENT) { + /* Avoid suspend failed when usb_kill_urb */ + return; } if (!test_bit(BTUSB_INTR_RUNNING, &data->flags)) @@ -397,6 +422,9 @@ static void btusb_bulk_complete(struct urb *urb) BT_ERR("%s corrupted ACL packet", hdev->name); hdev->stat.err_rx++; } + } else if (urb->status == -ENOENT) { + /* Avoid suspend failed when usb_kill_urb */ + return; } if (!test_bit(BTUSB_BULK_RUNNING, &data->flags)) @@ -491,6 +519,9 @@ static void btusb_isoc_complete(struct urb *urb) hdev->stat.err_rx++; } } + } else if (urb->status == -ENOENT) { + /* Avoid suspend failed when usb_kill_urb */ + return; } if (!test_bit(BTUSB_ISOC_RUNNING, &data->flags)) @@ -1262,6 +1293,8 @@ static int btusb_setup_intel(struct hci_dev *hdev) } fw_ptr = fw->data; + kfree_skb(skb); + /* This Intel specific command enables the manufacturer mode of the * controller. * @@ -1482,6 +1515,9 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_INTEL) hdev->setup = btusb_setup_intel; + if (id->driver_info & BTUSB_INTEL_BOOT) + set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); + /* Interface numbers are hardcoded in the specification */ data->isoc = usb_ifnum_to_if(data->udev, 1); diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index e36a024..5651992 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -237,7 +237,7 @@ static void h5_pkt_cull(struct h5 *h5) break; to_remove--; - seq = (seq - 1) % 8; + seq = (seq - 1) & 0x07; } if (seq != h5->rx_ack) diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c index 372ae72..1aa0130 100644 --- a/drivers/bus/mvebu-mbus.c +++ b/drivers/bus/mvebu-mbus.c @@ -181,12 +181,25 @@ static void mvebu_mbus_disable_window(struct mvebu_mbus_state *mbus, } /* Checks whether the given window number is available */ + +/* On Armada XP, 375 and 38x the MBus window 13 has the remap + * capability, like windows 0 to 7. However, the mvebu-mbus driver + * isn't currently taking into account this special case, which means + * that when window 13 is actually used, the remap registers are left + * to 0, making the device using this MBus window unavailable. The + * quick fix for stable is to not use window 13. A follow up patch + * will correctly handle this window. +*/ static int mvebu_mbus_window_is_free(struct mvebu_mbus_state *mbus, const int win) { void __iomem *addr = mbus->mbuswins_base + mbus->soc->win_cfg_offset(win); u32 ctrl = readl(addr + WIN_CTRL_OFF); + + if (win == 13) + return false; + return !(ctrl & WIN_CTRL_ENABLE); } @@ -688,7 +701,6 @@ static int __init mvebu_mbus_common_init(struct mvebu_mbus_state *mbus, phys_addr_t sdramwins_phys_base, size_t sdramwins_size) { - struct device_node *np; int win; mbus->mbuswins_base = ioremap(mbuswins_phys_base, mbuswins_size); @@ -701,12 +713,6 @@ static int __init mvebu_mbus_common_init(struct mvebu_mbus_state *mbus, return -ENOMEM; } - np = of_find_compatible_node(NULL, NULL, "marvell,coherency-fabric"); - if (np) { - mbus->hw_io_coherency = 1; - of_node_put(np); - } - for (win = 0; win < mbus->soc->num_wins; win++) mvebu_mbus_disable_window(mbus, win); @@ -876,7 +882,7 @@ static void __init mvebu_mbus_get_pcie_resources(struct device_node *np, } } -int __init mvebu_mbus_dt_init(void) +int __init mvebu_mbus_dt_init(bool is_coherent) { struct resource mbuswins_res, sdramwins_res; struct device_node *np, *controller; @@ -915,6 +921,8 @@ int __init mvebu_mbus_dt_init(void) return -EINVAL; } + mbus_state.hw_io_coherency = is_coherent; + /* Get optional pcie-{mem,io}-aperture properties */ mvebu_mbus_get_pcie_resources(np, &mbus_state.pcie_mem_aperture, &mbus_state.pcie_io_aperture); diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c index 5c85350..19e301f 100644 --- a/drivers/char/agp/intel-gtt.c +++ b/drivers/char/agp/intel-gtt.c @@ -586,7 +586,7 @@ static inline int needs_ilk_vtd_wa(void) /* Query intel_iommu to see if we need the workaround. Presumably that * was loaded first. */ - if ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB || + if ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_D_IG || gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG) && intel_iommu_gfx_mapped) return 1; diff --git a/drivers/char/hw_random/pseries-rng.c b/drivers/char/hw_random/pseries-rng.c index ab7ffde..f38f2c1 100644 --- a/drivers/char/hw_random/pseries-rng.c +++ b/drivers/char/hw_random/pseries-rng.c @@ -25,18 +25,21 @@ #include -static int pseries_rng_data_read(struct hwrng *rng, u32 *data) +static int pseries_rng_read(struct hwrng *rng, void *data, size_t max, bool wait) { + u64 buffer[PLPAR_HCALL_BUFSIZE]; + size_t size = max < 8 ? max : 8; int rc; - rc = plpar_hcall(H_RANDOM, (unsigned long *)data); + rc = plpar_hcall(H_RANDOM, (unsigned long *)buffer); if (rc != H_SUCCESS) { pr_err_ratelimited("H_RANDOM call failed %d\n", rc); return -EIO; } + memcpy(data, buffer, size); /* The hypervisor interface returns 64 bits */ - return 8; + return size; } /** @@ -55,7 +58,7 @@ static unsigned long pseries_rng_get_desired_dma(struct vio_dev *vdev) static struct hwrng pseries_rng = { .name = KBUILD_MODNAME, - .data_read = pseries_rng_data_read, + .read = pseries_rng_read, }; static int __init pseries_rng_probe(struct vio_dev *dev, diff --git a/drivers/char/random.c b/drivers/char/random.c index 429b75b..8a64dbe 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1063,8 +1063,8 @@ static void extract_buf(struct entropy_store *r, __u8 *out) * pool while mixing, and hash one final time. */ sha_transform(hash.w, extract, workspace); - memset(extract, 0, sizeof(extract)); - memset(workspace, 0, sizeof(workspace)); + memzero_explicit(extract, sizeof(extract)); + memzero_explicit(workspace, sizeof(workspace)); /* * In case the hash function has some recognizable output @@ -1076,7 +1076,7 @@ static void extract_buf(struct entropy_store *r, __u8 *out) hash.w[2] ^= rol32(hash.w[2], 16); memcpy(out, &hash, EXTRACT_SIZE); - memset(&hash, 0, sizeof(hash)); + memzero_explicit(&hash, sizeof(hash)); } static ssize_t extract_entropy(struct entropy_store *r, void *buf, @@ -1124,7 +1124,7 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf, } /* Wipe data just returned from memory */ - memset(tmp, 0, sizeof(tmp)); + memzero_explicit(tmp, sizeof(tmp)); return ret; } @@ -1162,7 +1162,7 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf, } /* Wipe data just returned from memory */ - memset(tmp, 0, sizeof(tmp)); + memzero_explicit(tmp, sizeof(tmp)); return ret; } diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 62e10fd..cfb9089 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -491,11 +491,10 @@ static int tpm_startup(struct tpm_chip *chip, __be16 startup_type) int tpm_get_timeouts(struct tpm_chip *chip) { struct tpm_cmd_t tpm_cmd; - struct timeout_t *timeout_cap; + unsigned long new_timeout[4]; + unsigned long old_timeout[4]; struct duration_t *duration_cap; ssize_t rc; - u32 timeout; - unsigned int scale = 1; tpm_cmd.header.in = tpm_getcap_header; tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP; @@ -529,25 +528,46 @@ int tpm_get_timeouts(struct tpm_chip *chip) != sizeof(tpm_cmd.header.out) + sizeof(u32) + 4 * sizeof(u32)) return -EINVAL; - timeout_cap = &tpm_cmd.params.getcap_out.cap.timeout; - /* Don't overwrite default if value is 0 */ - timeout = be32_to_cpu(timeout_cap->a); - if (timeout && timeout < 1000) { - /* timeouts in msec rather usec */ - scale = 1000; - chip->vendor.timeout_adjusted = true; + old_timeout[0] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.a); + old_timeout[1] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.b); + old_timeout[2] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.c); + old_timeout[3] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.d); + memcpy(new_timeout, old_timeout, sizeof(new_timeout)); + + /* + * Provide ability for vendor overrides of timeout values in case + * of misreporting. + */ + if (chip->ops->update_timeouts != NULL) + chip->vendor.timeout_adjusted = + chip->ops->update_timeouts(chip, new_timeout); + + if (!chip->vendor.timeout_adjusted) { + /* Don't overwrite default if value is 0 */ + if (new_timeout[0] != 0 && new_timeout[0] < 1000) { + int i; + + /* timeouts in msec rather usec */ + for (i = 0; i != ARRAY_SIZE(new_timeout); i++) + new_timeout[i] *= 1000; + chip->vendor.timeout_adjusted = true; + } + } + + /* Report adjusted timeouts */ + if (chip->vendor.timeout_adjusted) { + dev_info(chip->dev, + HW_ERR "Adjusting reported timeouts: A %lu->%luus B %lu->%luus C %lu->%luus D %lu->%luus\n", + old_timeout[0], new_timeout[0], + old_timeout[1], new_timeout[1], + old_timeout[2], new_timeout[2], + old_timeout[3], new_timeout[3]); } - if (timeout) - chip->vendor.timeout_a = usecs_to_jiffies(timeout * scale); - timeout = be32_to_cpu(timeout_cap->b); - if (timeout) - chip->vendor.timeout_b = usecs_to_jiffies(timeout * scale); - timeout = be32_to_cpu(timeout_cap->c); - if (timeout) - chip->vendor.timeout_c = usecs_to_jiffies(timeout * scale); - timeout = be32_to_cpu(timeout_cap->d); - if (timeout) - chip->vendor.timeout_d = usecs_to_jiffies(timeout * scale); + + chip->vendor.timeout_a = usecs_to_jiffies(new_timeout[0]); + chip->vendor.timeout_b = usecs_to_jiffies(new_timeout[1]); + chip->vendor.timeout_c = usecs_to_jiffies(new_timeout[2]); + chip->vendor.timeout_d = usecs_to_jiffies(new_timeout[3]); duration: tpm_cmd.header.in = tpm_getcap_header; @@ -991,13 +1011,13 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max) int err, total = 0, retries = 5; u8 *dest = out; + if (!out || !num_bytes || max > TPM_MAX_RNG_DATA) + return -EINVAL; + chip = tpm_chip_find_get(chip_num); if (chip == NULL) return -ENODEV; - if (!out || !num_bytes || max > TPM_MAX_RNG_DATA) - return -EINVAL; - do { tpm_cmd.header.in = tpm_getrandom_header; tpm_cmd.params.getrandom_in.num_bytes = cpu_to_be32(num_bytes); @@ -1016,6 +1036,7 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max) num_bytes -= recd; } while (retries-- && total < max); + tpm_chip_put(chip); return total ? total : -EIO; } EXPORT_SYMBOL_GPL(tpm_get_random); @@ -1095,17 +1116,19 @@ struct tpm_chip *tpm_register_hardware(struct device *dev, goto del_misc; if (tpm_add_ppi(&dev->kobj)) - goto del_misc; + goto del_sysfs; chip->bios_dir = tpm_bios_log_setup(chip->devname); /* Make chip available */ spin_lock(&driver_lock); - list_add_rcu(&chip->list, &tpm_chip_list); + list_add_tail_rcu(&chip->list, &tpm_chip_list); spin_unlock(&driver_lock); return chip; +del_sysfs: + tpm_sysfs_del_device(chip); del_misc: tpm_dev_del_device(chip); put_device: diff --git a/drivers/char/tpm/tpm_i2c_atmel.c b/drivers/char/tpm/tpm_i2c_atmel.c index 7727292..503a85a 100644 --- a/drivers/char/tpm/tpm_i2c_atmel.c +++ b/drivers/char/tpm/tpm_i2c_atmel.c @@ -168,6 +168,10 @@ static int i2c_atmel_probe(struct i2c_client *client, chip->vendor.priv = devm_kzalloc(dev, sizeof(struct priv_data), GFP_KERNEL); + if (!chip->vendor.priv) { + rc = -ENOMEM; + goto out_err; + } /* Default timeouts */ chip->vendor.timeout_a = msecs_to_jiffies(TPM_I2C_SHORT_TIMEOUT); diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c index 7b158ef..23c7b13 100644 --- a/drivers/char/tpm/tpm_i2c_nuvoton.c +++ b/drivers/char/tpm/tpm_i2c_nuvoton.c @@ -538,6 +538,11 @@ static int i2c_nuvoton_probe(struct i2c_client *client, chip->vendor.priv = devm_kzalloc(dev, sizeof(struct priv_data), GFP_KERNEL); + if (!chip->vendor.priv) { + rc = -ENOMEM; + goto out_err; + } + init_waitqueue_head(&chip->vendor.read_queue); init_waitqueue_head(&chip->vendor.int_queue); diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.c b/drivers/char/tpm/tpm_i2c_stm_st33.c index 5b0dd8e..576d111 100644 --- a/drivers/char/tpm/tpm_i2c_stm_st33.c +++ b/drivers/char/tpm/tpm_i2c_stm_st33.c @@ -488,7 +488,7 @@ static int tpm_stm_i2c_send(struct tpm_chip *chip, unsigned char *buf, if (burstcnt < 0) return burstcnt; size = min_t(int, len - i - 1, burstcnt); - ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf, size); + ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf + i, size); if (ret < 0) goto out_err; @@ -715,6 +715,7 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id) } tpm_get_timeouts(chip); + tpm_do_selftest(chip); dev_info(chip->dev, "TPM I2C Initialized\n"); return 0; diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c index af74c57..643bba7 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.c +++ b/drivers/char/tpm/tpm_ibmvtpm.c @@ -124,7 +124,7 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) { struct ibmvtpm_dev *ibmvtpm; struct ibmvtpm_crq crq; - u64 *word = (u64 *) &crq; + __be64 *word = (__be64 *)&crq; int rc; ibmvtpm = (struct ibmvtpm_dev *)TPM_VPRIV(chip); @@ -145,10 +145,11 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) memcpy((void *)ibmvtpm->rtce_buf, (void *)buf, count); crq.valid = (u8)IBMVTPM_VALID_CMD; crq.msg = (u8)VTPM_TPM_COMMAND; - crq.len = (u16)count; - crq.data = ibmvtpm->rtce_dma_handle; + crq.len = cpu_to_be16(count); + crq.data = cpu_to_be32(ibmvtpm->rtce_dma_handle); - rc = ibmvtpm_send_crq(ibmvtpm->vdev, word[0], word[1]); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, be64_to_cpu(word[0]), + be64_to_cpu(word[1])); if (rc != H_SUCCESS) { dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc); rc = 0; @@ -186,7 +187,8 @@ static int ibmvtpm_crq_get_rtce_size(struct ibmvtpm_dev *ibmvtpm) crq.valid = (u8)IBMVTPM_VALID_CMD; crq.msg = (u8)VTPM_GET_RTCE_BUFFER_SIZE; - rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]), + cpu_to_be64(buf[1])); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "ibmvtpm_crq_get_rtce_size failed rc=%d\n", rc); @@ -212,7 +214,8 @@ static int ibmvtpm_crq_get_version(struct ibmvtpm_dev *ibmvtpm) crq.valid = (u8)IBMVTPM_VALID_CMD; crq.msg = (u8)VTPM_GET_VERSION; - rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]), + cpu_to_be64(buf[1])); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "ibmvtpm_crq_get_version failed rc=%d\n", rc); @@ -307,6 +310,14 @@ static int tpm_ibmvtpm_remove(struct vio_dev *vdev) static unsigned long tpm_ibmvtpm_get_desired_dma(struct vio_dev *vdev) { struct ibmvtpm_dev *ibmvtpm = ibmvtpm_get_data(&vdev->dev); + + /* ibmvtpm initializes at probe time, so the data we are + * asking for may not be set yet. Estimate that 4K required + * for TCE-mapped buffer in addition to CRQ. + */ + if (!ibmvtpm) + return CRQ_RES_BUF_SIZE + PAGE_SIZE; + return CRQ_RES_BUF_SIZE + ibmvtpm->rtce_size; } @@ -327,7 +338,8 @@ static int tpm_ibmvtpm_suspend(struct device *dev) crq.valid = (u8)IBMVTPM_VALID_CMD; crq.msg = (u8)VTPM_PREPARE_TO_SUSPEND; - rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]), + cpu_to_be64(buf[1])); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "tpm_ibmvtpm_suspend failed rc=%d\n", rc); @@ -472,11 +484,11 @@ static void ibmvtpm_crq_process(struct ibmvtpm_crq *crq, case IBMVTPM_VALID_CMD: switch (crq->msg) { case VTPM_GET_RTCE_BUFFER_SIZE_RES: - if (crq->len <= 0) { + if (be16_to_cpu(crq->len) <= 0) { dev_err(ibmvtpm->dev, "Invalid rtce size\n"); return; } - ibmvtpm->rtce_size = crq->len; + ibmvtpm->rtce_size = be16_to_cpu(crq->len); ibmvtpm->rtce_buf = kmalloc(ibmvtpm->rtce_size, GFP_KERNEL); if (!ibmvtpm->rtce_buf) { @@ -497,11 +509,11 @@ static void ibmvtpm_crq_process(struct ibmvtpm_crq *crq, return; case VTPM_GET_VERSION_RES: - ibmvtpm->vtpm_version = crq->data; + ibmvtpm->vtpm_version = be32_to_cpu(crq->data); return; case VTPM_TPM_COMMAND_RES: /* len of the data in rtce buffer */ - ibmvtpm->res_len = crq->len; + ibmvtpm->res_len = be16_to_cpu(crq->len); wake_up_interruptible(&ibmvtpm->wq); return; default: @@ -567,6 +579,9 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev, goto cleanup; } + ibmvtpm->dev = dev; + ibmvtpm->vdev = vio_dev; + crq_q = &ibmvtpm->crq_queue; crq_q->crq_addr = (struct ibmvtpm_crq *)get_zeroed_page(GFP_KERNEL); if (!crq_q->crq_addr) { @@ -611,8 +626,6 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev, crq_q->index = 0; - ibmvtpm->dev = dev; - ibmvtpm->vdev = vio_dev; TPM_VPRIV(chip) = (void *)ibmvtpm; spin_lock_init(&ibmvtpm->rtce_lock); diff --git a/drivers/char/tpm/tpm_ibmvtpm.h b/drivers/char/tpm/tpm_ibmvtpm.h index bd82a79..b2c231b 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.h +++ b/drivers/char/tpm/tpm_ibmvtpm.h @@ -22,9 +22,9 @@ struct ibmvtpm_crq { u8 valid; u8 msg; - u16 len; - u32 data; - u64 reserved; + __be16 len; + __be32 data; + __be64 reserved; } __attribute__((packed, aligned(8))); struct ibmvtpm_crq_queue { diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index a9ed227..51350cd 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -75,6 +75,10 @@ enum tis_defaults { #define TPM_DID_VID(l) (0x0F00 | ((l) << 12)) #define TPM_RID(l) (0x0F04 | ((l) << 12)) +struct priv_data { + bool irq_tested; +}; + static LIST_HEAD(tis_chips); static DEFINE_MUTEX(tis_lock); @@ -338,12 +342,27 @@ out_err: return rc; } +static void disable_interrupts(struct tpm_chip *chip) +{ + u32 intmask; + + intmask = + ioread32(chip->vendor.iobase + + TPM_INT_ENABLE(chip->vendor.locality)); + intmask &= ~TPM_GLOBAL_INT_ENABLE; + iowrite32(intmask, + chip->vendor.iobase + + TPM_INT_ENABLE(chip->vendor.locality)); + free_irq(chip->vendor.irq, chip); + chip->vendor.irq = 0; +} + /* * If interrupts are used (signaled by an irq set in the vendor structure) * tpm.c can skip polling for the data to be available as the interrupt is * waited for here */ -static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len) +static int tpm_tis_send_main(struct tpm_chip *chip, u8 *buf, size_t len) { int rc; u32 ordinal; @@ -373,6 +392,60 @@ out_err: return rc; } +static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len) +{ + int rc, irq; + struct priv_data *priv = chip->vendor.priv; + + if (!chip->vendor.irq || priv->irq_tested) + return tpm_tis_send_main(chip, buf, len); + + /* Verify receipt of the expected IRQ */ + irq = chip->vendor.irq; + chip->vendor.irq = 0; + rc = tpm_tis_send_main(chip, buf, len); + chip->vendor.irq = irq; + if (!priv->irq_tested) + msleep(1); + if (!priv->irq_tested) { + disable_interrupts(chip); + dev_err(chip->dev, + FW_BUG "TPM interrupt not working, polling instead\n"); + } + priv->irq_tested = true; + return rc; +} + +struct tis_vendor_timeout_override { + u32 did_vid; + unsigned long timeout_us[4]; +}; + +static const struct tis_vendor_timeout_override vendor_timeout_overrides[] = { + /* Atmel 3204 */ + { 0x32041114, { (TIS_SHORT_TIMEOUT*1000), (TIS_LONG_TIMEOUT*1000), + (TIS_SHORT_TIMEOUT*1000), (TIS_SHORT_TIMEOUT*1000) } }, +}; + +static bool tpm_tis_update_timeouts(struct tpm_chip *chip, + unsigned long *timeout_cap) +{ + int i; + u32 did_vid; + + did_vid = ioread32(chip->vendor.iobase + TPM_DID_VID(0)); + + for (i = 0; i != ARRAY_SIZE(vendor_timeout_overrides); i++) { + if (vendor_timeout_overrides[i].did_vid != did_vid) + continue; + memcpy(timeout_cap, vendor_timeout_overrides[i].timeout_us, + sizeof(vendor_timeout_overrides[i].timeout_us)); + return true; + } + + return false; +} + /* * Early probing for iTPM with STS_DATA_EXPECT flaw. * Try sending command without itpm flag set and if that @@ -437,6 +510,7 @@ static const struct tpm_class_ops tpm_tis = { .recv = tpm_tis_recv, .send = tpm_tis_send, .cancel = tpm_tis_ready, + .update_timeouts = tpm_tis_update_timeouts, .req_complete_mask = TPM_STS_DATA_AVAIL | TPM_STS_VALID, .req_complete_val = TPM_STS_DATA_AVAIL | TPM_STS_VALID, .req_canceled = tpm_tis_req_canceled, @@ -474,6 +548,7 @@ static irqreturn_t tis_int_handler(int dummy, void *dev_id) if (interrupt == 0) return IRQ_NONE; + ((struct priv_data *)chip->vendor.priv)->irq_tested = true; if (interrupt & TPM_INTF_DATA_AVAIL_INT) wake_up_interruptible(&chip->vendor.read_queue); if (interrupt & TPM_INTF_LOCALITY_CHANGE_INT) @@ -503,9 +578,14 @@ static int tpm_tis_init(struct device *dev, resource_size_t start, u32 vendor, intfcaps, intmask; int rc, i, irq_s, irq_e, probe; struct tpm_chip *chip; + struct priv_data *priv; + priv = devm_kzalloc(dev, sizeof(struct priv_data), GFP_KERNEL); + if (priv == NULL) + return -ENOMEM; if (!(chip = tpm_register_hardware(dev, &tpm_tis))) return -ENODEV; + chip->vendor.priv = priv; chip->vendor.iobase = ioremap(start, len); if (!chip->vendor.iobase) { @@ -574,19 +654,6 @@ static int tpm_tis_init(struct device *dev, resource_size_t start, if (intfcaps & TPM_INTF_DATA_AVAIL_INT) dev_dbg(dev, "\tData Avail Int Support\n"); - /* get the timeouts before testing for irqs */ - if (tpm_get_timeouts(chip)) { - dev_err(dev, "Could not get TPM timeouts and durations\n"); - rc = -ENODEV; - goto out_err; - } - - if (tpm_do_selftest(chip)) { - dev_err(dev, "TPM self test failed\n"); - rc = -ENODEV; - goto out_err; - } - /* INTERRUPT Setup */ init_waitqueue_head(&chip->vendor.read_queue); init_waitqueue_head(&chip->vendor.int_queue); @@ -688,6 +755,18 @@ static int tpm_tis_init(struct device *dev, resource_size_t start, } } + if (tpm_get_timeouts(chip)) { + dev_err(dev, "Could not get TPM timeouts and durations\n"); + rc = -ENODEV; + goto out_err; + } + + if (tpm_do_selftest(chip)) { + dev_err(dev, "TPM self test failed\n"); + rc = -ENODEV; + goto out_err; + } + INIT_LIST_HEAD(&chip->vendor.list); mutex_lock(&tis_lock); list_add(&chip->vendor.list, &tis_chips); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 6928d09..b08eadb 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -142,6 +142,7 @@ struct ports_device { * notification */ struct work_struct control_work; + struct work_struct config_work; struct list_head ports; @@ -1832,10 +1833,21 @@ static void config_intr(struct virtio_device *vdev) portdev = vdev->priv; + if (!use_multiport(portdev)) + schedule_work(&portdev->config_work); +} + +static void config_work_handler(struct work_struct *work) +{ + struct ports_device *portdev; + + portdev = container_of(work, struct ports_device, control_work); if (!use_multiport(portdev)) { + struct virtio_device *vdev; struct port *port; u16 rows, cols; + vdev = portdev->vdev; virtio_cread(vdev, struct virtio_console_config, cols, &cols); virtio_cread(vdev, struct virtio_console_config, rows, &rows); @@ -2024,12 +2036,14 @@ static int virtcons_probe(struct virtio_device *vdev) spin_lock_init(&portdev->ports_lock); INIT_LIST_HEAD(&portdev->ports); + INIT_WORK(&portdev->config_work, &config_work_handler); + INIT_WORK(&portdev->control_work, &control_work_handler); + if (multiport) { unsigned int nr_added_bufs; spin_lock_init(&portdev->c_ivq_lock); spin_lock_init(&portdev->c_ovq_lock); - INIT_WORK(&portdev->control_work, &control_work_handler); nr_added_bufs = fill_queue(portdev->c_ivq, &portdev->c_ivq_lock); @@ -2097,6 +2111,8 @@ static void virtcons_remove(struct virtio_device *vdev) /* Finish up work that's lined up */ if (use_multiport(portdev)) cancel_work_sync(&portdev->control_work); + else + cancel_work_sync(&portdev->config_work); list_for_each_entry_safe(port, port2, &portdev->ports, list) unplug_port(port); @@ -2148,6 +2164,7 @@ static int virtcons_freeze(struct virtio_device *vdev) virtqueue_disable_cb(portdev->c_ivq); cancel_work_sync(&portdev->control_work); + cancel_work_sync(&portdev->config_work); /* * Once more: if control_work_handler() was running, it would * enable the cb as the last step. diff --git a/drivers/clk/clk-gate.c b/drivers/clk/clk-gate.c index 4a58c55..797bab9 100644 --- a/drivers/clk/clk-gate.c +++ b/drivers/clk/clk-gate.c @@ -128,7 +128,7 @@ struct clk *clk_register_gate(struct device *dev, const char *name, struct clk_init_data init; if (clk_gate_flags & CLK_GATE_HIWORD_MASK) { - if (bit_idx > 16) { + if (bit_idx > 15) { pr_err("gate bit exceeds LOWORD field\n"); return ERR_PTR(-EINVAL); } diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 020400d..8b1e2ef 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1487,6 +1487,7 @@ static struct clk *clk_propagate_rate_change(struct clk *clk, unsigned long even static void clk_change_rate(struct clk *clk) { struct clk *child; + struct hlist_node *tmp; unsigned long old_rate; unsigned long best_parent_rate = 0; bool skip_set_rate = false; @@ -1525,7 +1526,11 @@ static void clk_change_rate(struct clk *clk) if (clk->notifier_count && old_rate != clk->rate) __clk_notify(clk, POST_RATE_CHANGE, old_rate, clk->rate); - hlist_for_each_entry(child, &clk->children, child_node) { + /* + * Use safe iteration, as change_rate can actually swap parents + * for certain clock types. + */ + hlist_for_each_entry_safe(child, tmp, &clk->children, child_node) { /* Skip children who will be reparented to another clock */ if (child->new_parent && child->new_parent != clk) continue; @@ -2240,14 +2245,17 @@ int __clk_get(struct clk *clk) void __clk_put(struct clk *clk) { + struct module *owner; + if (!clk || WARN_ON_ONCE(IS_ERR(clk))) return; clk_prepare_lock(); + owner = clk->owner; kref_put(&clk->ref, __clk_release); clk_prepare_unlock(); - module_put(clk->owner); + module_put(owner); } /*** clk rate change notifiers ***/ diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index 0996a3a..a9dd21a 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -257,7 +257,7 @@ static int __clk_rcg2_set_rate(struct clk_hw *hw, unsigned long rate) mask |= CFG_SRC_SEL_MASK | CFG_MODE_MASK; cfg = f->pre_div << CFG_SRC_DIV_SHIFT; cfg |= rcg->parent_map[f->src] << CFG_SRC_SEL_SHIFT; - if (rcg->mnd_width && f->n) + if (rcg->mnd_width && f->n && (f->m != f->n)) cfg |= CFG_MODE_DUAL_EDGE; ret = regmap_update_bits(rcg->clkr.regmap, rcg->cmd_rcgr + CFG_REG, mask, cfg); diff --git a/drivers/clk/qcom/mmcc-msm8960.c b/drivers/clk/qcom/mmcc-msm8960.c index 9be47a8..f3c95d6 100644 --- a/drivers/clk/qcom/mmcc-msm8960.c +++ b/drivers/clk/qcom/mmcc-msm8960.c @@ -37,6 +37,8 @@ #define P_PLL2 2 #define P_PLL3 3 +#define F_MN(f, s, _m, _n) { .freq = f, .src = s, .m = _m, .n = _n } + static u8 mmcc_pxo_pll8_pll2_map[] = { [P_PXO] = 0, [P_PLL8] = 2, @@ -58,8 +60,8 @@ static u8 mmcc_pxo_pll8_pll2_pll3_map[] = { static const char *mmcc_pxo_pll8_pll2_pll3[] = { "pxo", - "pll2", "pll8_vote", + "pll2", "pll3", }; @@ -709,18 +711,18 @@ static struct clk_branch csiphy2_timer_clk = { }; static struct freq_tbl clk_tbl_gfx2d[] = { - { 27000000, P_PXO, 1, 0 }, - { 48000000, P_PLL8, 1, 8 }, - { 54857000, P_PLL8, 1, 7 }, - { 64000000, P_PLL8, 1, 6 }, - { 76800000, P_PLL8, 1, 5 }, - { 96000000, P_PLL8, 1, 4 }, - { 128000000, P_PLL8, 1, 3 }, - { 145455000, P_PLL2, 2, 11 }, - { 160000000, P_PLL2, 1, 5 }, - { 177778000, P_PLL2, 2, 9 }, - { 200000000, P_PLL2, 1, 4 }, - { 228571000, P_PLL2, 2, 7 }, + F_MN( 27000000, P_PXO, 1, 0), + F_MN( 48000000, P_PLL8, 1, 8), + F_MN( 54857000, P_PLL8, 1, 7), + F_MN( 64000000, P_PLL8, 1, 6), + F_MN( 76800000, P_PLL8, 1, 5), + F_MN( 96000000, P_PLL8, 1, 4), + F_MN(128000000, P_PLL8, 1, 3), + F_MN(145455000, P_PLL2, 2, 11), + F_MN(160000000, P_PLL2, 1, 5), + F_MN(177778000, P_PLL2, 2, 9), + F_MN(200000000, P_PLL2, 1, 4), + F_MN(228571000, P_PLL2, 2, 7), { } }; @@ -841,22 +843,22 @@ static struct clk_branch gfx2d1_clk = { }; static struct freq_tbl clk_tbl_gfx3d[] = { - { 27000000, P_PXO, 1, 0 }, - { 48000000, P_PLL8, 1, 8 }, - { 54857000, P_PLL8, 1, 7 }, - { 64000000, P_PLL8, 1, 6 }, - { 76800000, P_PLL8, 1, 5 }, - { 96000000, P_PLL8, 1, 4 }, - { 128000000, P_PLL8, 1, 3 }, - { 145455000, P_PLL2, 2, 11 }, - { 160000000, P_PLL2, 1, 5 }, - { 177778000, P_PLL2, 2, 9 }, - { 200000000, P_PLL2, 1, 4 }, - { 228571000, P_PLL2, 2, 7 }, - { 266667000, P_PLL2, 1, 3 }, - { 300000000, P_PLL3, 1, 4 }, - { 320000000, P_PLL2, 2, 5 }, - { 400000000, P_PLL2, 1, 2 }, + F_MN( 27000000, P_PXO, 1, 0), + F_MN( 48000000, P_PLL8, 1, 8), + F_MN( 54857000, P_PLL8, 1, 7), + F_MN( 64000000, P_PLL8, 1, 6), + F_MN( 76800000, P_PLL8, 1, 5), + F_MN( 96000000, P_PLL8, 1, 4), + F_MN(128000000, P_PLL8, 1, 3), + F_MN(145455000, P_PLL2, 2, 11), + F_MN(160000000, P_PLL2, 1, 5), + F_MN(177778000, P_PLL2, 2, 9), + F_MN(200000000, P_PLL2, 1, 4), + F_MN(228571000, P_PLL2, 2, 7), + F_MN(266667000, P_PLL2, 1, 3), + F_MN(300000000, P_PLL3, 1, 4), + F_MN(320000000, P_PLL2, 2, 5), + F_MN(400000000, P_PLL2, 1, 2), { } }; @@ -896,7 +898,7 @@ static struct clk_dyn_rcg gfx3d_src = { .hw.init = &(struct clk_init_data){ .name = "gfx3d_src", .parent_names = mmcc_pxo_pll8_pll2_pll3, - .num_parents = 3, + .num_parents = 4, .ops = &clk_dyn_rcg_ops, }, }, @@ -994,7 +996,7 @@ static struct clk_rcg jpegd_src = { .ns_reg = 0x00ac, .p = { .pre_div_shift = 12, - .pre_div_width = 2, + .pre_div_width = 4, }, .s = { .src_sel_shift = 0, @@ -1114,7 +1116,7 @@ static struct clk_branch mdp_lut_clk = { .enable_reg = 0x016c, .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .parent_names = (const char *[]){ "mdp_clk" }, + .parent_names = (const char *[]){ "mdp_src" }, .num_parents = 1, .name = "mdp_lut_clk", .ops = &clk_branch_ops, @@ -1341,15 +1343,15 @@ static struct clk_branch hdmi_app_clk = { }; static struct freq_tbl clk_tbl_vcodec[] = { - { 27000000, P_PXO, 1, 0 }, - { 32000000, P_PLL8, 1, 12 }, - { 48000000, P_PLL8, 1, 8 }, - { 54860000, P_PLL8, 1, 7 }, - { 96000000, P_PLL8, 1, 4 }, - { 133330000, P_PLL2, 1, 6 }, - { 200000000, P_PLL2, 1, 4 }, - { 228570000, P_PLL2, 2, 7 }, - { 266670000, P_PLL2, 1, 3 }, + F_MN( 27000000, P_PXO, 1, 0), + F_MN( 32000000, P_PLL8, 1, 12), + F_MN( 48000000, P_PLL8, 1, 8), + F_MN( 54860000, P_PLL8, 1, 7), + F_MN( 96000000, P_PLL8, 1, 4), + F_MN(133330000, P_PLL2, 1, 6), + F_MN(200000000, P_PLL2, 1, 4), + F_MN(228570000, P_PLL2, 2, 7), + F_MN(266670000, P_PLL2, 1, 3), { } }; diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c index 884187f..7f30b94 100644 --- a/drivers/clk/samsung/clk-exynos-audss.c +++ b/drivers/clk/samsung/clk-exynos-audss.c @@ -210,6 +210,10 @@ static int exynos_audss_clk_remove(struct platform_device *pdev) { int i; +#ifdef CONFIG_PM_SLEEP + unregister_syscore_ops(&exynos_audss_clk_syscore_ops); +#endif + of_clk_del_provider(pdev->dev.of_node); for (i = 0; i < clk_data.clk_num; i++) { diff --git a/drivers/clk/sunxi/clk-factors.c b/drivers/clk/sunxi/clk-factors.c index 9e23264..ea4db84 100644 --- a/drivers/clk/sunxi/clk-factors.c +++ b/drivers/clk/sunxi/clk-factors.c @@ -62,7 +62,7 @@ static unsigned long clk_factors_recalc_rate(struct clk_hw *hw, p = FACTOR_GET(config->pshift, config->pwidth, reg); /* Calculate the rate */ - rate = (parent_rate * n * (k + 1) >> p) / (m + 1); + rate = (parent_rate * (n + config->n_start) * (k + 1) >> p) / (m + 1); return rate; } diff --git a/drivers/clk/sunxi/clk-factors.h b/drivers/clk/sunxi/clk-factors.h index 02e1a43..d2d0efa 100644 --- a/drivers/clk/sunxi/clk-factors.h +++ b/drivers/clk/sunxi/clk-factors.h @@ -15,6 +15,7 @@ struct clk_factors_config { u8 mwidth; u8 pshift; u8 pwidth; + u8 n_start; }; struct clk_factors { diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c index abb6c5a..06a14b8 100644 --- a/drivers/clk/sunxi/clk-sunxi.c +++ b/drivers/clk/sunxi/clk-sunxi.c @@ -407,6 +407,7 @@ static struct clk_factors_config sun6i_a31_pll1_config = { .kwidth = 2, .mshift = 0, .mwidth = 2, + .n_start = 1, }; static struct clk_factors_config sun4i_pll5_config = { diff --git a/drivers/clk/tegra/clk.c b/drivers/clk/tegra/clk.c index c0a7d77..a90af17 100644 --- a/drivers/clk/tegra/clk.c +++ b/drivers/clk/tegra/clk.c @@ -266,7 +266,7 @@ void __init tegra_add_of_provider(struct device_node *np) of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data); rst_ctlr.of_node = np; - rst_ctlr.nr_resets = clk_num * 32; + rst_ctlr.nr_resets = periph_banks * 32; reset_controller_register(&rst_ctlr); } diff --git a/drivers/clk/versatile/clk-sp810.c b/drivers/clk/versatile/clk-sp810.c index c6e86a9..5122ef2 100644 --- a/drivers/clk/versatile/clk-sp810.c +++ b/drivers/clk/versatile/clk-sp810.c @@ -128,8 +128,8 @@ static struct clk *clk_sp810_timerclken_of_get(struct of_phandle_args *clkspec, { struct clk_sp810 *sp810 = data; - if (WARN_ON(clkspec->args_count != 1 || clkspec->args[0] > - ARRAY_SIZE(sp810->timerclken))) + if (WARN_ON(clkspec->args_count != 1 || + clkspec->args[0] >= ARRAY_SIZE(sp810->timerclken))) return NULL; return sp810->timerclken[clkspec->args[0]].clk; diff --git a/drivers/clk/zynq/clkc.c b/drivers/clk/zynq/clkc.c index 09dd017..5f52f3f 100644 --- a/drivers/clk/zynq/clkc.c +++ b/drivers/clk/zynq/clkc.c @@ -300,6 +300,7 @@ static void __init zynq_clk_setup(struct device_node *np) clks[cpu_2x] = clk_register_gate(NULL, clk_output_name[cpu_2x], "cpu_2x_div", CLK_IGNORE_UNUSED, SLCR_ARM_CLK_CTRL, 26, 0, &armclk_lock); + clk_prepare_enable(clks[cpu_2x]); clk = clk_register_fixed_factor(NULL, "cpu_1x_div", "cpu_div", 0, 1, 4 + 2 * tmp); diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c index e252939..ddd03f8 100644 --- a/drivers/clocksource/exynos_mct.c +++ b/drivers/clocksource/exynos_mct.c @@ -98,8 +98,8 @@ static void exynos4_mct_write(unsigned int value, unsigned long offset) __raw_writel(value, reg_base + offset); if (likely(offset >= EXYNOS4_MCT_L_BASE(0))) { - stat_addr = (offset & ~EXYNOS4_MCT_L_MASK) + MCT_L_WSTAT_OFFSET; - switch (offset & EXYNOS4_MCT_L_MASK) { + stat_addr = (offset & EXYNOS4_MCT_L_MASK) + MCT_L_WSTAT_OFFSET; + switch (offset & ~EXYNOS4_MCT_L_MASK) { case MCT_L_TCON_OFFSET: mask = 1 << 3; /* L_TCON write status */ break; @@ -422,15 +422,12 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt) exynos4_mct_write(TICK_BASE_CNT, mevt->base + MCT_L_TCNTB_OFFSET); if (mct_int_type == MCT_INT_SPI) { - evt->irq = mct_irqs[MCT_L0_IRQ + cpu]; - if (request_irq(evt->irq, exynos4_mct_tick_isr, - IRQF_TIMER | IRQF_NOBALANCING, - evt->name, mevt)) { - pr_err("exynos-mct: cannot register IRQ %d\n", - evt->irq); + + if (evt->irq == -1) return -EIO; - } - irq_force_affinity(mct_irqs[MCT_L0_IRQ + cpu], cpumask_of(cpu)); + + irq_force_affinity(evt->irq, cpumask_of(cpu)); + enable_irq(evt->irq); } else { enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0); } @@ -443,10 +440,12 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt) static void exynos4_local_timer_stop(struct clock_event_device *evt) { evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt); - if (mct_int_type == MCT_INT_SPI) - free_irq(evt->irq, this_cpu_ptr(&percpu_mct_tick)); - else + if (mct_int_type == MCT_INT_SPI) { + if (evt->irq != -1) + disable_irq_nosync(evt->irq); + } else { disable_percpu_irq(mct_irqs[MCT_L0_IRQ]); + } } static int exynos4_mct_cpu_notify(struct notifier_block *self, @@ -478,7 +477,7 @@ static struct notifier_block exynos4_mct_cpu_nb = { static void __init exynos4_timer_resources(struct device_node *np, void __iomem *base) { - int err; + int err, cpu; struct mct_clock_event_device *mevt = this_cpu_ptr(&percpu_mct_tick); struct clk *mct_clk, *tick_clk; @@ -505,7 +504,25 @@ static void __init exynos4_timer_resources(struct device_node *np, void __iomem WARN(err, "MCT: can't request IRQ %d (%d)\n", mct_irqs[MCT_L0_IRQ], err); } else { - irq_set_affinity(mct_irqs[MCT_L0_IRQ], cpumask_of(0)); + for_each_possible_cpu(cpu) { + int mct_irq = mct_irqs[MCT_L0_IRQ + cpu]; + struct mct_clock_event_device *pcpu_mevt = + per_cpu_ptr(&percpu_mct_tick, cpu); + + pcpu_mevt->evt.irq = -1; + + irq_set_status_flags(mct_irq, IRQ_NOAUTOEN); + if (request_irq(mct_irq, + exynos4_mct_tick_isr, + IRQF_TIMER | IRQF_NOBALANCING, + pcpu_mevt->name, pcpu_mevt)) { + pr_err("exynos-mct: cannot register IRQ (cpu%d)\n", + cpu); + + continue; + } + pcpu_mevt->evt.irq = mct_irq; + } } err = register_cpu_notifier(&exynos4_mct_cpu_nb); diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c index bf497af..7d19f86 100644 --- a/drivers/clocksource/sun4i_timer.c +++ b/drivers/clocksource/sun4i_timer.c @@ -182,6 +182,12 @@ static void __init sun4i_timer_init(struct device_node *node) /* Make sure timer is stopped before playing with interrupts */ sun4i_clkevt_time_stop(0); + sun4i_clockevent.cpumask = cpu_possible_mask; + sun4i_clockevent.irq = irq; + + clockevents_config_and_register(&sun4i_clockevent, rate, + TIMER_SYNC_TICKS, 0xffffffff); + ret = setup_irq(irq, &sun4i_timer_irq); if (ret) pr_warn("failed to setup irq %d\n", irq); @@ -189,12 +195,6 @@ static void __init sun4i_timer_init(struct device_node *node) /* Enable timer0 interrupt */ val = readl(timer_base + TIMER_IRQ_EN_REG); writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG); - - sun4i_clockevent.cpumask = cpu_possible_mask; - sun4i_clockevent.irq = irq; - - clockevents_config_and_register(&sun4i_clockevent, rate, - TIMER_SYNC_TICKS, 0xffffffff); } CLOCKSOURCE_OF_DECLARE(sun4i, "allwinner,sun4i-timer", sun4i_timer_init); diff --git a/drivers/clocksource/time-efm32.c b/drivers/clocksource/time-efm32.c index 1a6205b..35b0161 100644 --- a/drivers/clocksource/time-efm32.c +++ b/drivers/clocksource/time-efm32.c @@ -225,12 +225,12 @@ static int __init efm32_clockevent_init(struct device_node *np) clock_event_ddata.base = base; clock_event_ddata.periodic_top = DIV_ROUND_CLOSEST(rate, 1024 * HZ); - setup_irq(irq, &efm32_clock_event_irq); - clockevents_config_and_register(&clock_event_ddata.evtdev, DIV_ROUND_CLOSEST(rate, 1024), 0xf, 0xffff); + setup_irq(irq, &efm32_clock_event_irq); + return 0; err_get_irq: diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c index deebcd6..4f0f361 100644 --- a/drivers/clocksource/timer-sun5i.c +++ b/drivers/clocksource/timer-sun5i.c @@ -172,10 +172,6 @@ static void __init sun5i_timer_init(struct device_node *node) ticks_per_jiffy = DIV_ROUND_UP(rate, HZ); - ret = setup_irq(irq, &sun5i_timer_irq); - if (ret) - pr_warn("failed to setup irq %d\n", irq); - /* Enable timer0 interrupt */ val = readl(timer_base + TIMER_IRQ_EN_REG); writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG); @@ -185,6 +181,10 @@ static void __init sun5i_timer_init(struct device_node *node) clockevents_config_and_register(&sun5i_clockevent, rate, TIMER_SYNC_TICKS, 0xffffffff); + + ret = setup_irq(irq, &sun5i_timer_irq); + if (ret) + pr_warn("failed to setup irq %d\n", irq); } CLOCKSOURCE_OF_DECLARE(sun5i_a13, "allwinner,sun5i-a13-hstimer", sun5i_timer_init); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 199b52b..ef3b8ad 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -460,7 +460,18 @@ show_one(cpuinfo_max_freq, cpuinfo.max_freq); show_one(cpuinfo_transition_latency, cpuinfo.transition_latency); show_one(scaling_min_freq, min); show_one(scaling_max_freq, max); -show_one(scaling_cur_freq, cur); + +static ssize_t show_scaling_cur_freq( + struct cpufreq_policy *policy, char *buf) +{ + ssize_t ret; + + if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get) + ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu)); + else + ret = sprintf(buf, "%u\n", policy->cur); + return ret; +} static int cpufreq_set_policy(struct cpufreq_policy *policy, struct cpufreq_policy *new_policy); @@ -854,11 +865,11 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy, if (ret) goto err_out_kobj_put; } - if (has_target()) { - ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr); - if (ret) - goto err_out_kobj_put; - } + + ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr); + if (ret) + goto err_out_kobj_put; + if (cpufreq_driver->bios_limit) { ret = sysfs_create_file(&policy->kobj, &bios_limit.attr); if (ret) @@ -1089,10 +1100,12 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif, * the creation of a brand new one. So we need to perform this update * by invoking update_policy_cpu(). */ - if (frozen && cpu != policy->cpu) + if (frozen && cpu != policy->cpu) { update_policy_cpu(policy, cpu); - else + WARN_ON(kobject_move(&policy->kobj, &dev->kobj)); + } else { policy->cpu = cpu; + } policy->governor = CPUFREQ_DEFAULT_GOVERNOR; cpumask_copy(policy->cpus, cpumask_of(cpu)); @@ -1223,6 +1236,8 @@ err_get_freq: per_cpu(cpufreq_cpu_data, j) = NULL; write_unlock_irqrestore(&cpufreq_driver_lock, flags); + up_write(&policy->rwsem); + if (cpufreq_driver->exit) cpufreq_driver->exit(policy); err_set_policy_cpu: @@ -1350,9 +1365,10 @@ static int __cpufreq_remove_dev_finish(struct device *dev, unsigned long flags; struct cpufreq_policy *policy; - read_lock_irqsave(&cpufreq_driver_lock, flags); + write_lock_irqsave(&cpufreq_driver_lock, flags); policy = per_cpu(cpufreq_cpu_data, cpu); - read_unlock_irqrestore(&cpufreq_driver_lock, flags); + per_cpu(cpufreq_cpu_data, cpu) = NULL; + write_unlock_irqrestore(&cpufreq_driver_lock, flags); if (!policy) { pr_debug("%s: No cpu_data found\n", __func__); @@ -1407,7 +1423,6 @@ static int __cpufreq_remove_dev_finish(struct device *dev, } } - per_cpu(cpufreq_cpu_data, cpu) = NULL; return 0; } diff --git a/drivers/cpufreq/integrator-cpufreq.c b/drivers/cpufreq/integrator-cpufreq.c index 0e27844..8089dd2 100644 --- a/drivers/cpufreq/integrator-cpufreq.c +++ b/drivers/cpufreq/integrator-cpufreq.c @@ -213,9 +213,9 @@ static int __init integrator_cpufreq_probe(struct platform_device *pdev) return cpufreq_register_driver(&integrator_driver); } -static void __exit integrator_cpufreq_remove(struct platform_device *pdev) +static int __exit integrator_cpufreq_remove(struct platform_device *pdev) { - cpufreq_unregister_driver(&integrator_driver); + return cpufreq_unregister_driver(&integrator_driver); } static const struct of_device_id integrator_cpufreq_match[] = { diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index ae52c77..fbc693b 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -55,6 +55,17 @@ static inline int32_t div_fp(int32_t x, int32_t y) return div_s64((int64_t)x << FRAC_BITS, (int64_t)y); } +static inline int ceiling_fp(int32_t x) +{ + int mask, ret; + + ret = fp_toint(x); + mask = (1 << FRAC_BITS) - 1; + if (x & mask) + ret += 1; + return ret; +} + struct sample { int32_t core_pct_busy; u64 aperf; @@ -67,6 +78,7 @@ struct pstate_data { int current_pstate; int min_pstate; int max_pstate; + int scaling; int turbo_pstate; }; @@ -118,6 +130,7 @@ struct pstate_funcs { int (*get_max)(void); int (*get_min)(void); int (*get_turbo)(void); + int (*get_scaling)(void); void (*set)(struct cpudata*, int pstate); void (*get_vid)(struct cpudata *); }; @@ -397,14 +410,30 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate) cpudata->vid.ratio); vid_fp = clamp_t(int32_t, vid_fp, cpudata->vid.min, cpudata->vid.max); - vid = fp_toint(vid_fp); + vid = ceiling_fp(vid_fp); if (pstate > cpudata->pstate.max_pstate) vid = cpudata->vid.turbo; val |= vid; - wrmsrl(MSR_IA32_PERF_CTL, val); + wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val); +} + +#define BYT_BCLK_FREQS 5 +static int byt_freq_table[BYT_BCLK_FREQS] = { 833, 1000, 1333, 1167, 800}; + +static int byt_get_scaling(void) +{ + u64 value; + int i; + + rdmsrl(MSR_FSB_FREQ, value); + i = value & 0x3; + + BUG_ON(i > BYT_BCLK_FREQS); + + return byt_freq_table[i] * 100; } static void byt_get_vid(struct cpudata *cpudata) @@ -451,6 +480,11 @@ static int core_get_turbo_pstate(void) return ret; } +static inline int core_get_scaling(void) +{ + return 100000; +} + static void core_set_pstate(struct cpudata *cpudata, int pstate) { u64 val; @@ -475,6 +509,7 @@ static struct cpu_defaults core_params = { .get_max = core_get_max_pstate, .get_min = core_get_min_pstate, .get_turbo = core_get_turbo_pstate, + .get_scaling = core_get_scaling, .set = core_set_pstate, }, }; @@ -493,6 +528,7 @@ static struct cpu_defaults byt_params = { .get_min = byt_get_min_pstate, .get_turbo = byt_get_turbo_pstate, .set = byt_set_pstate, + .get_scaling = byt_get_scaling, .get_vid = byt_get_vid, }, }; @@ -526,7 +562,7 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate) if (pstate == cpu->pstate.current_pstate) return; - trace_cpu_frequency(pstate * 100000, cpu->cpu); + trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu); cpu->pstate.current_pstate = pstate; @@ -555,6 +591,7 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) cpu->pstate.min_pstate = pstate_funcs.get_min(); cpu->pstate.max_pstate = pstate_funcs.get_max(); cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(); + cpu->pstate.scaling = pstate_funcs.get_scaling(); if (pstate_funcs.get_vid) pstate_funcs.get_vid(cpu); @@ -574,7 +611,9 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu, core_pct += 1; sample->freq = fp_toint( - mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct)); + mul_fp(int_tofp( + cpu->pstate.max_pstate * cpu->pstate.scaling / 100), + core_pct)); sample->core_pct_busy = (int32_t)core_pct; } @@ -685,10 +724,14 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = { ICPU(0x37, byt_params), ICPU(0x3a, core_params), ICPU(0x3c, core_params), + ICPU(0x3d, core_params), ICPU(0x3e, core_params), ICPU(0x3f, core_params), ICPU(0x45, core_params), ICPU(0x46, core_params), + ICPU(0x4c, byt_params), + ICPU(0x4f, core_params), + ICPU(0x56, core_params), {} }; MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids); @@ -751,6 +794,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) { limits.min_perf_pct = 100; limits.min_perf = int_tofp(1); + limits.max_policy_pct = 100; limits.max_perf_pct = 100; limits.max_perf = int_tofp(1); limits.no_turbo = limits.turbo_disabled; @@ -812,12 +856,13 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) else policy->policy = CPUFREQ_POLICY_POWERSAVE; - policy->min = cpu->pstate.min_pstate * 100000; - policy->max = cpu->pstate.turbo_pstate * 100000; + policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling; + policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling; /* cpuinfo and default policy values */ - policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000; - policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate * 100000; + policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling; + policy->cpuinfo.max_freq = + cpu->pstate.turbo_pstate * cpu->pstate.scaling; policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; cpumask_set_cpu(policy->cpu, policy->cpus); @@ -875,6 +920,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs) pstate_funcs.get_max = funcs->get_max; pstate_funcs.get_min = funcs->get_min; pstate_funcs.get_turbo = funcs->get_turbo; + pstate_funcs.get_scaling = funcs->get_scaling; pstate_funcs.set = funcs->set; pstate_funcs.get_vid = funcs->get_vid; } diff --git a/drivers/cpufreq/s3c2416-cpufreq.c b/drivers/cpufreq/s3c2416-cpufreq.c index 826b8be..82cef00 100644 --- a/drivers/cpufreq/s3c2416-cpufreq.c +++ b/drivers/cpufreq/s3c2416-cpufreq.c @@ -263,7 +263,7 @@ out: } #ifdef CONFIG_ARM_S3C2416_CPUFREQ_VCORESCALE -static void __init s3c2416_cpufreq_cfg_regulator(struct s3c2416_data *s3c_freq) +static void s3c2416_cpufreq_cfg_regulator(struct s3c2416_data *s3c_freq) { int count, v, i, found; struct cpufreq_frequency_table *freq; @@ -335,7 +335,7 @@ static struct notifier_block s3c2416_cpufreq_reboot_notifier = { .notifier_call = s3c2416_cpufreq_reboot_notifier_evt, }; -static int __init s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy) +static int s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy) { struct s3c2416_data *s3c_freq = &s3c2416_cpufreq; struct cpufreq_frequency_table *freq; diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c index 2506974..0eb5b40 100644 --- a/drivers/cpufreq/s3c24xx-cpufreq.c +++ b/drivers/cpufreq/s3c24xx-cpufreq.c @@ -454,7 +454,7 @@ static struct cpufreq_driver s3c24xx_driver = { }; -int __init s3c_cpufreq_register(struct s3c_cpufreq_info *info) +int s3c_cpufreq_register(struct s3c_cpufreq_info *info) { if (!info || !info->name) { printk(KERN_ERR "%s: failed to pass valid information\n", diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c index 7047821..4ab7a21 100644 --- a/drivers/cpufreq/speedstep-lib.c +++ b/drivers/cpufreq/speedstep-lib.c @@ -400,6 +400,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor, pr_debug("previous speed is %u\n", prev_speed); + preempt_disable(); local_irq_save(flags); /* switch to low state */ @@ -464,6 +465,8 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor, out: local_irq_restore(flags); + preempt_enable(); + return ret; } EXPORT_SYMBOL_GPL(speedstep_get_freqs); diff --git a/drivers/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c index 998c17b..b52d8af 100644 --- a/drivers/cpufreq/speedstep-smi.c +++ b/drivers/cpufreq/speedstep-smi.c @@ -156,6 +156,7 @@ static void speedstep_set_state(unsigned int state) return; /* Disable IRQs */ + preempt_disable(); local_irq_save(flags); command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); @@ -166,9 +167,19 @@ static void speedstep_set_state(unsigned int state) do { if (retry) { + /* + * We need to enable interrupts, otherwise the blockage + * won't resolve. + * + * We disable preemption so that other processes don't + * run. If other processes were running, they could + * submit more DMA requests, making the blockage worse. + */ pr_debug("retry %u, previous result %u, waiting...\n", retry, result); + local_irq_enable(); mdelay(retry * 50); + local_irq_disable(); } retry++; __asm__ __volatile__( @@ -185,6 +196,7 @@ static void speedstep_set_state(unsigned int state) /* enable IRQs */ local_irq_restore(flags); + preempt_enable(); if (new_state == state) pr_debug("change to %u MHz succeeded after %u tries " diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index a55e68f..1adc039 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -131,6 +131,9 @@ int cpuidle_idle_call(void) /* ask the governor for the next state */ next_state = cpuidle_curr_governor->select(drv, dev); + if (next_state < 0) + return -EBUSY; + if (need_resched()) { dev->last_residency = 0; /* give the governor an opportunity to reflect on the outcome */ @@ -252,9 +255,6 @@ int cpuidle_enable_device(struct cpuidle_device *dev) if (!dev->registered) return -EINVAL; - if (!dev->state_count) - dev->state_count = drv->state_count; - ret = cpuidle_add_device_sysfs(dev); if (ret) return ret; diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index cf7f2f0..027c484 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -297,7 +297,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) data->needs_update = 0; } - data->last_state_idx = 0; + data->last_state_idx = CPUIDLE_DRIVER_STATE_START - 1; data->exit_us = 0; /* Special case when user has set very strict latency requirement */ diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index e918b6d..dcaae4c 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -398,7 +398,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device) struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device); /* state statistics */ - for (i = 0; i < device->state_count; i++) { + for (i = 0; i < drv->state_count; i++) { kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL); if (!kobj) goto error_state; @@ -430,9 +430,10 @@ error_state: */ static void cpuidle_remove_state_sysfs(struct cpuidle_device *device) { + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device); int i; - for (i = 0; i < device->state_count; i++) + for (i = 0; i < drv->state_count; i++) cpuidle_free_state_kobj(device, i); } diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index 0378328..1489927 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -835,8 +835,9 @@ static int ahash_update_ctx(struct ahash_request *req) edesc->sec4_sg + sec4_sg_src_index, chained); if (*next_buflen) { - sg_copy_part(next_buf, req->src, to_hash - - *buflen, req->nbytes); + scatterwalk_map_and_copy(next_buf, req->src, + to_hash - *buflen, + *next_buflen, 0); state->current_buf = !state->current_buf; } } else { @@ -869,7 +870,8 @@ static int ahash_update_ctx(struct ahash_request *req) kfree(edesc); } } else if (*next_buflen) { - sg_copy(buf + *buflen, req->src, req->nbytes); + scatterwalk_map_and_copy(buf + *buflen, req->src, 0, + req->nbytes, 0); *buflen = *next_buflen; *next_buflen = last_buflen; } @@ -898,13 +900,14 @@ static int ahash_final_ctx(struct ahash_request *req) state->buflen_1; u32 *sh_desc = ctx->sh_desc_fin, *desc; dma_addr_t ptr = ctx->sh_desc_fin_dma; - int sec4_sg_bytes; + int sec4_sg_bytes, sec4_sg_src_index; int digestsize = crypto_ahash_digestsize(ahash); struct ahash_edesc *edesc; int ret = 0; int sh_len; - sec4_sg_bytes = (1 + (buflen ? 1 : 0)) * sizeof(struct sec4_sg_entry); + sec4_sg_src_index = 1 + (buflen ? 1 : 0); + sec4_sg_bytes = sec4_sg_src_index * sizeof(struct sec4_sg_entry); /* allocate space for base edesc and hw desc commands, link tables */ edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN + @@ -931,7 +934,7 @@ static int ahash_final_ctx(struct ahash_request *req) state->buf_dma = try_buf_map_to_sec4_sg(jrdev, edesc->sec4_sg + 1, buf, state->buf_dma, buflen, last_buflen); - (edesc->sec4_sg + sec4_sg_bytes - 1)->len |= SEC4_SG_LEN_FIN; + (edesc->sec4_sg + sec4_sg_src_index - 1)->len |= SEC4_SG_LEN_FIN; append_seq_in_ptr(desc, edesc->sec4_sg_dma, ctx->ctx_len + buflen, LDST_SGF); @@ -1216,8 +1219,9 @@ static int ahash_update_no_ctx(struct ahash_request *req) src_map_to_sec4_sg(jrdev, req->src, src_nents, edesc->sec4_sg + 1, chained); if (*next_buflen) { - sg_copy_part(next_buf, req->src, to_hash - *buflen, - req->nbytes); + scatterwalk_map_and_copy(next_buf, req->src, + to_hash - *buflen, + *next_buflen, 0); state->current_buf = !state->current_buf; } @@ -1248,7 +1252,8 @@ static int ahash_update_no_ctx(struct ahash_request *req) kfree(edesc); } } else if (*next_buflen) { - sg_copy(buf + *buflen, req->src, req->nbytes); + scatterwalk_map_and_copy(buf + *buflen, req->src, 0, + req->nbytes, 0); *buflen = *next_buflen; *next_buflen = 0; } @@ -1348,9 +1353,9 @@ static int ahash_update_first(struct ahash_request *req) struct device *jrdev = ctx->jrdev; gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC; - u8 *next_buf = state->buf_0 + state->current_buf * - CAAM_MAX_HASH_BLOCK_SIZE; - int *next_buflen = &state->buflen_0 + state->current_buf; + u8 *next_buf = state->current_buf ? state->buf_1 : state->buf_0; + int *next_buflen = state->current_buf ? + &state->buflen_1 : &state->buflen_0; int to_hash; u32 *sh_desc = ctx->sh_desc_update_first, *desc; dma_addr_t ptr = ctx->sh_desc_update_first_dma; @@ -1405,7 +1410,8 @@ static int ahash_update_first(struct ahash_request *req) } if (*next_buflen) - sg_copy_part(next_buf, req->src, to_hash, req->nbytes); + scatterwalk_map_and_copy(next_buf, req->src, to_hash, + *next_buflen, 0); sh_len = desc_len(sh_desc); desc = edesc->hw_desc; @@ -1438,7 +1444,8 @@ static int ahash_update_first(struct ahash_request *req) state->update = ahash_update_no_ctx; state->finup = ahash_finup_no_ctx; state->final = ahash_final_no_ctx; - sg_copy(next_buf, req->src, req->nbytes); + scatterwalk_map_and_copy(next_buf, req->src, 0, + req->nbytes, 0); } #ifdef DEBUG print_hex_dump(KERN_ERR, "next buf@"__stringify(__LINE__)": ", diff --git a/drivers/crypto/caam/caamrng.c b/drivers/crypto/caam/caamrng.c index 28486b1..ae6dae8 100644 --- a/drivers/crypto/caam/caamrng.c +++ b/drivers/crypto/caam/caamrng.c @@ -56,7 +56,7 @@ /* Buffer, its dma address and lock */ struct buf_data { - u8 buf[RN_BUF_SIZE]; + u8 buf[RN_BUF_SIZE] ____cacheline_aligned; dma_addr_t addr; struct completion filled; u32 hw_desc[DESC_JOB_O_LEN]; diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c index ea2e406..b872eed 100644 --- a/drivers/crypto/caam/key_gen.c +++ b/drivers/crypto/caam/key_gen.c @@ -51,23 +51,29 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, u32 *desc; struct split_key_result result; dma_addr_t dma_addr_in, dma_addr_out; - int ret = 0; + int ret = -ENOMEM; desc = kmalloc(CAAM_CMD_SZ * 6 + CAAM_PTR_SZ * 2, GFP_KERNEL | GFP_DMA); if (!desc) { dev_err(jrdev, "unable to allocate key input memory\n"); - return -ENOMEM; + return ret; } - init_job_desc(desc, 0); - dma_addr_in = dma_map_single(jrdev, (void *)key_in, keylen, DMA_TO_DEVICE); if (dma_mapping_error(jrdev, dma_addr_in)) { dev_err(jrdev, "unable to map key input memory\n"); - kfree(desc); - return -ENOMEM; + goto out_free; } + + dma_addr_out = dma_map_single(jrdev, key_out, split_key_pad_len, + DMA_FROM_DEVICE); + if (dma_mapping_error(jrdev, dma_addr_out)) { + dev_err(jrdev, "unable to map key output memory\n"); + goto out_unmap_in; + } + + init_job_desc(desc, 0); append_key(desc, dma_addr_in, keylen, CLASS_2 | KEY_DEST_CLASS_REG); /* Sets MDHA up into an HMAC-INIT */ @@ -84,13 +90,6 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, * FIFO_STORE with the explicit split-key content store * (0x26 output type) */ - dma_addr_out = dma_map_single(jrdev, key_out, split_key_pad_len, - DMA_FROM_DEVICE); - if (dma_mapping_error(jrdev, dma_addr_out)) { - dev_err(jrdev, "unable to map key output memory\n"); - kfree(desc); - return -ENOMEM; - } append_fifo_store(desc, dma_addr_out, split_key_len, LDST_CLASS_2_CCB | FIFOST_TYPE_SPLIT_KEK); @@ -118,10 +117,10 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, dma_unmap_single(jrdev, dma_addr_out, split_key_pad_len, DMA_FROM_DEVICE); +out_unmap_in: dma_unmap_single(jrdev, dma_addr_in, keylen, DMA_TO_DEVICE); - +out_free: kfree(desc); - return ret; } EXPORT_SYMBOL(gen_split_key); diff --git a/drivers/crypto/caam/sg_sw_sec4.h b/drivers/crypto/caam/sg_sw_sec4.h index b12ff85..ce28a56 100644 --- a/drivers/crypto/caam/sg_sw_sec4.h +++ b/drivers/crypto/caam/sg_sw_sec4.h @@ -116,57 +116,3 @@ static int dma_unmap_sg_chained(struct device *dev, struct scatterlist *sg, } return nents; } - -/* Map SG page in kernel virtual address space and copy */ -static inline void sg_map_copy(u8 *dest, struct scatterlist *sg, - int len, int offset) -{ - u8 *mapped_addr; - - /* - * Page here can be user-space pinned using get_user_pages - * Same must be kmapped before use and kunmapped subsequently - */ - mapped_addr = kmap_atomic(sg_page(sg)); - memcpy(dest, mapped_addr + offset, len); - kunmap_atomic(mapped_addr); -} - -/* Copy from len bytes of sg to dest, starting from beginning */ -static inline void sg_copy(u8 *dest, struct scatterlist *sg, unsigned int len) -{ - struct scatterlist *current_sg = sg; - int cpy_index = 0, next_cpy_index = current_sg->length; - - while (next_cpy_index < len) { - sg_map_copy(dest + cpy_index, current_sg, current_sg->length, - current_sg->offset); - current_sg = scatterwalk_sg_next(current_sg); - cpy_index = next_cpy_index; - next_cpy_index += current_sg->length; - } - if (cpy_index < len) - sg_map_copy(dest + cpy_index, current_sg, len-cpy_index, - current_sg->offset); -} - -/* Copy sg data, from to_skip to end, to dest */ -static inline void sg_copy_part(u8 *dest, struct scatterlist *sg, - int to_skip, unsigned int end) -{ - struct scatterlist *current_sg = sg; - int sg_index, cpy_index, offset; - - sg_index = current_sg->length; - while (sg_index <= to_skip) { - current_sg = scatterwalk_sg_next(current_sg); - sg_index += current_sg->length; - } - cpy_index = sg_index - to_skip; - offset = current_sg->offset + current_sg->length - cpy_index; - sg_map_copy(dest, current_sg, cpy_index, offset); - if (end - sg_index) { - current_sg = scatterwalk_sg_next(current_sg); - sg_copy(dest + cpy_index, current_sg, end - sg_index); - } -} diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c index f757a0f..3beed38 100644 --- a/drivers/crypto/ixp4xx_crypto.c +++ b/drivers/crypto/ixp4xx_crypto.c @@ -904,7 +904,6 @@ static int ablk_perform(struct ablkcipher_request *req, int encrypt) crypt->mode |= NPE_OP_NOT_IN_PLACE; /* This was never tested by Intel * for more than one dst buffer, I think. */ - BUG_ON(req->dst->length < nbytes); req_ctx->dst = NULL; if (!chainup_buffers(dev, req->dst, nbytes, &dst_hook, flags, DMA_FROM_DEVICE)) diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c index dde41f1d..d522396 100644 --- a/drivers/crypto/omap-aes.c +++ b/drivers/crypto/omap-aes.c @@ -554,15 +554,23 @@ static int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd) return err; } -static int omap_aes_check_aligned(struct scatterlist *sg) +static int omap_aes_check_aligned(struct scatterlist *sg, int total) { + int len = 0; + while (sg) { if (!IS_ALIGNED(sg->offset, 4)) return -1; if (!IS_ALIGNED(sg->length, AES_BLOCK_SIZE)) return -1; + + len += sg->length; sg = sg_next(sg); } + + if (len != total) + return -1; + return 0; } @@ -633,8 +641,8 @@ static int omap_aes_handle_queue(struct omap_aes_dev *dd, dd->in_sg = req->src; dd->out_sg = req->dst; - if (omap_aes_check_aligned(dd->in_sg) || - omap_aes_check_aligned(dd->out_sg)) { + if (omap_aes_check_aligned(dd->in_sg, dd->total) || + omap_aes_check_aligned(dd->out_sg, dd->total)) { if (omap_aes_copy_sgs(dd)) pr_err("Failed to copy SGs for unaligned cases\n"); dd->sgs_copied = 1; diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index 633ba94..c178ed8 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -563,4 +563,4 @@ MODULE_DESCRIPTION("VIA PadLock AES algorithm support"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michal Ludvig"); -MODULE_ALIAS("aes"); +MODULE_ALIAS_CRYPTO("aes"); diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c index 9266c0e..93d7753 100644 --- a/drivers/crypto/padlock-sha.c +++ b/drivers/crypto/padlock-sha.c @@ -593,7 +593,7 @@ MODULE_DESCRIPTION("VIA PadLock SHA1/SHA256 algorithms support."); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michal Ludvig"); -MODULE_ALIAS("sha1-all"); -MODULE_ALIAS("sha256-all"); -MODULE_ALIAS("sha1-padlock"); -MODULE_ALIAS("sha256-padlock"); +MODULE_ALIAS_CRYPTO("sha1-all"); +MODULE_ALIAS_CRYPTO("sha256-all"); +MODULE_ALIAS_CRYPTO("sha1-padlock"); +MODULE_ALIAS_CRYPTO("sha256-padlock"); diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index 5967667..1f35487 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -927,7 +927,8 @@ static int sg_to_link_tbl(struct scatterlist *sg, int sg_count, sg_count--; link_tbl_ptr--; } - be16_add_cpu(&link_tbl_ptr->len, cryptlen); + link_tbl_ptr->len = cpu_to_be16(be16_to_cpu(link_tbl_ptr->len) + + cryptlen); /* tag end of link table */ link_tbl_ptr->j_extent = DESC_PTR_LNKTBL_RETURN; @@ -2563,6 +2564,7 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev, break; default: dev_err(dev, "unknown algorithm type %d\n", t_alg->algt.type); + kfree(t_alg); return ERR_PTR(-EINVAL); } diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c index a999f53..e4cea7c 100644 --- a/drivers/crypto/ux500/cryp/cryp_core.c +++ b/drivers/crypto/ux500/cryp/cryp_core.c @@ -190,7 +190,7 @@ static void add_session_id(struct cryp_ctx *ctx) static irqreturn_t cryp_interrupt_handler(int irq, void *param) { struct cryp_ctx *ctx; - int i; + int count; struct cryp_device_data *device_data; if (param == NULL) { @@ -215,12 +215,11 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param) if (cryp_pending_irq_src(device_data, CRYP_IRQ_SRC_OUTPUT_FIFO)) { if (ctx->outlen / ctx->blocksize > 0) { - for (i = 0; i < ctx->blocksize / 4; i++) { - *(ctx->outdata) = readl_relaxed( - &device_data->base->dout); - ctx->outdata += 4; - ctx->outlen -= 4; - } + count = ctx->blocksize / 4; + + readsl(&device_data->base->dout, ctx->outdata, count); + ctx->outdata += count; + ctx->outlen -= count; if (ctx->outlen == 0) { cryp_disable_irq_src(device_data, @@ -230,12 +229,12 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param) } else if (cryp_pending_irq_src(device_data, CRYP_IRQ_SRC_INPUT_FIFO)) { if (ctx->datalen / ctx->blocksize > 0) { - for (i = 0 ; i < ctx->blocksize / 4; i++) { - writel_relaxed(ctx->indata, - &device_data->base->din); - ctx->indata += 4; - ctx->datalen -= 4; - } + count = ctx->blocksize / 4; + + writesl(&device_data->base->din, ctx->indata, count); + + ctx->indata += count; + ctx->datalen -= count; if (ctx->datalen == 0) cryp_disable_irq_src(device_data, @@ -1811,7 +1810,7 @@ module_exit(ux500_cryp_mod_fini); module_param(cryp_mode, int, 0); MODULE_DESCRIPTION("Driver for ST-Ericsson UX500 CRYP crypto engine."); -MODULE_ALIAS("aes-all"); -MODULE_ALIAS("des-all"); +MODULE_ALIAS_CRYPTO("aes-all"); +MODULE_ALIAS_CRYPTO("des-all"); MODULE_LICENSE("GPL"); diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c index 1c73f4f..8e5e018 100644 --- a/drivers/crypto/ux500/hash/hash_core.c +++ b/drivers/crypto/ux500/hash/hash_core.c @@ -1995,7 +1995,7 @@ module_exit(ux500_hash_mod_fini); MODULE_DESCRIPTION("Driver for ST-Ericsson UX500 HASH engine."); MODULE_LICENSE("GPL"); -MODULE_ALIAS("sha1-all"); -MODULE_ALIAS("sha256-all"); -MODULE_ALIAS("hmac-sha1-all"); -MODULE_ALIAS("hmac-sha256-all"); +MODULE_ALIAS_CRYPTO("sha1-all"); +MODULE_ALIAS_CRYPTO("sha256-all"); +MODULE_ALIAS_CRYPTO("hmac-sha1-all"); +MODULE_ALIAS_CRYPTO("hmac-sha256-all"); diff --git a/drivers/dma/TODO b/drivers/dma/TODO index 734ed02..b8045cd 100644 --- a/drivers/dma/TODO +++ b/drivers/dma/TODO @@ -7,7 +7,6 @@ TODO for slave dma - imx-dma - imx-sdma - mxs-dma.c - - dw_dmac - intel_mid_dma 4. Check other subsystems for dma drivers and merge/move to dmaengine 5. Remove dma_slave_config's dma direction. diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 01a200c..b0972b3 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -279,6 +279,15 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first) channel_set_bit(dw, CH_EN, dwc->mask); } +static void dwc_dostart_first_queued(struct dw_dma_chan *dwc) +{ + if (list_empty(&dwc->queue)) + return; + + list_move(dwc->queue.next, &dwc->active_list); + dwc_dostart(dwc, dwc_first_active(dwc)); +} + /*----------------------------------------------------------------------*/ static void @@ -335,10 +344,7 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc) * the completed ones. */ list_splice_init(&dwc->active_list, &list); - if (!list_empty(&dwc->queue)) { - list_move(dwc->queue.next, &dwc->active_list); - dwc_dostart(dwc, dwc_first_active(dwc)); - } + dwc_dostart_first_queued(dwc); spin_unlock_irqrestore(&dwc->lock, flags); @@ -467,10 +473,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc) /* Try to continue after resetting the channel... */ dwc_chan_disable(dw, dwc); - if (!list_empty(&dwc->queue)) { - list_move(dwc->queue.next, &dwc->active_list); - dwc_dostart(dwc, dwc_first_active(dwc)); - } + dwc_dostart_first_queued(dwc); spin_unlock_irqrestore(&dwc->lock, flags); } @@ -677,17 +680,9 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx) * possible, perhaps even appending to those already submitted * for DMA. But this is hard to do in a race-free manner. */ - if (list_empty(&dwc->active_list)) { - dev_vdbg(chan2dev(tx->chan), "%s: started %u\n", __func__, - desc->txd.cookie); - list_add_tail(&desc->desc_node, &dwc->active_list); - dwc_dostart(dwc, dwc_first_active(dwc)); - } else { - dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__, - desc->txd.cookie); - list_add_tail(&desc->desc_node, &dwc->queue); - } + dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__, desc->txd.cookie); + list_add_tail(&desc->desc_node, &dwc->queue); spin_unlock_irqrestore(&dwc->lock, flags); @@ -1092,9 +1087,12 @@ dwc_tx_status(struct dma_chan *chan, static void dwc_issue_pending(struct dma_chan *chan) { struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + unsigned long flags; - if (!list_empty(&dwc->queue)) - dwc_scan_descriptors(to_dw_dma(chan->device), dwc); + spin_lock_irqsave(&dwc->lock, flags); + if (list_empty(&dwc->active_list)) + dwc_dostart_first_queued(dwc); + spin_unlock_irqrestore(&dwc->lock, flags); } static int dwc_alloc_chan_resources(struct dma_chan *chan) diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index 453822c..fe8b0c9 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -48,6 +48,8 @@ static bool dw_dma_of_filter(struct dma_chan *chan, void *param) return true; } +#define DRV_NAME "dw_dmac" + static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma) { @@ -293,7 +295,7 @@ static struct platform_driver dw_driver = { .remove = dw_remove, .shutdown = dw_shutdown, .driver = { - .name = "dw_dmac", + .name = DRV_NAME, .pm = &dw_dev_pm_ops, .of_match_table = of_match_ptr(dw_dma_of_id_table), .acpi_match_table = ACPI_PTR(dw_dma_acpi_id_table), @@ -314,3 +316,4 @@ module_exit(dw_exit); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller platform driver"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 394cbc5..6b2f01d 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -316,7 +316,8 @@ static void __mv_xor_slot_cleanup(struct mv_xor_chan *mv_chan) dma_cookie_t cookie = 0; int busy = mv_chan_is_busy(mv_chan); u32 current_desc = mv_chan_get_current_desc(mv_chan); - int seen_current = 0; + int current_cleaned = 0; + struct mv_xor_desc *hw_desc; dev_dbg(mv_chan_to_devp(mv_chan), "%s %d\n", __func__, __LINE__); dev_dbg(mv_chan_to_devp(mv_chan), "current_desc %x\n", current_desc); @@ -328,38 +329,57 @@ static void __mv_xor_slot_cleanup(struct mv_xor_chan *mv_chan) list_for_each_entry_safe(iter, _iter, &mv_chan->chain, chain_node) { - prefetch(_iter); - prefetch(&_iter->async_tx); - /* do not advance past the current descriptor loaded into the - * hardware channel, subsequent descriptors are either in - * process or have not been submitted - */ - if (seen_current) - break; + /* clean finished descriptors */ + hw_desc = iter->hw_desc; + if (hw_desc->status & XOR_DESC_SUCCESS) { + cookie = mv_xor_run_tx_complete_actions(iter, mv_chan, + cookie); - /* stop the search if we reach the current descriptor and the - * channel is busy - */ - if (iter->async_tx.phys == current_desc) { - seen_current = 1; - if (busy) + /* done processing desc, clean slot */ + mv_xor_clean_slot(iter, mv_chan); + + /* break if we did cleaned the current */ + if (iter->async_tx.phys == current_desc) { + current_cleaned = 1; + break; + } + } else { + if (iter->async_tx.phys == current_desc) { + current_cleaned = 0; break; + } } - - cookie = mv_xor_run_tx_complete_actions(iter, mv_chan, cookie); - - if (mv_xor_clean_slot(iter, mv_chan)) - break; } if ((busy == 0) && !list_empty(&mv_chan->chain)) { - struct mv_xor_desc_slot *chain_head; - chain_head = list_entry(mv_chan->chain.next, - struct mv_xor_desc_slot, - chain_node); - - mv_xor_start_new_chain(mv_chan, chain_head); + if (current_cleaned) { + /* + * current descriptor cleaned and removed, run + * from list head + */ + iter = list_entry(mv_chan->chain.next, + struct mv_xor_desc_slot, + chain_node); + mv_xor_start_new_chain(mv_chan, iter); + } else { + if (!list_is_last(&iter->chain_node, &mv_chan->chain)) { + /* + * descriptors are still waiting after + * current, trigger them + */ + iter = list_entry(iter->chain_node.next, + struct mv_xor_desc_slot, + chain_node); + mv_xor_start_new_chain(mv_chan, iter); + } else { + /* + * some descriptors are still waiting + * to be cleaned + */ + tasklet_schedule(&mv_chan->irq_tasklet); + } + } } if (cookie > 0) diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h index d074922..5d14e4b 100644 --- a/drivers/dma/mv_xor.h +++ b/drivers/dma/mv_xor.h @@ -33,6 +33,7 @@ #define XOR_OPERATION_MODE_XOR 0 #define XOR_OPERATION_MODE_MEMCPY 2 #define XOR_DESCRIPTOR_SWAP BIT(14) +#define XOR_DESC_SUCCESS 0x40000000 #define XOR_CURR_DESC(chan) (chan->mmr_high_base + 0x10 + (chan->idx * 4)) #define XOR_NEXT_DESC(chan) (chan->mmr_high_base + 0x00 + (chan->idx * 4)) diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c index 362e7c4..12f8294 100644 --- a/drivers/dma/omap-dma.c +++ b/drivers/dma/omap-dma.c @@ -487,6 +487,7 @@ static int omap_dma_terminate_all(struct omap_chan *c) * c->desc is NULL and exit.) */ if (c->desc) { + omap_dma_desc_free(&c->desc->vd); c->desc = NULL; /* Avoid stopping the dma twice */ if (!c->paused) diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 98e14ee..278603c 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -2006,14 +2006,20 @@ static void __log_bus_error(struct mem_ctl_info *mci, struct err_info *err, static inline void decode_bus_error(int node_id, struct mce *m) { - struct mem_ctl_info *mci = mcis[node_id]; - struct amd64_pvt *pvt = mci->pvt_info; + struct mem_ctl_info *mci; + struct amd64_pvt *pvt; u8 ecc_type = (m->status >> 45) & 0x3; u8 xec = XEC(m->status, 0x1f); u16 ec = EC(m->status); u64 sys_addr; struct err_info err; + mci = edac_mc_find(node_id); + if (!mci) + return; + + pvt = mci->pvt_info; + /* Bail out early if this was an 'observed' error */ if (PP(ec) == NBSL_PP_OBS) return; diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c index df6575f..682288c 100644 --- a/drivers/edac/cpc925_edac.c +++ b/drivers/edac/cpc925_edac.c @@ -562,7 +562,7 @@ static void cpc925_mc_check(struct mem_ctl_info *mci) if (apiexcp & UECC_EXCP_DETECTED) { cpc925_mc_printk(mci, KERN_INFO, "DRAM UECC Fault\n"); - edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, + edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, pfn, offset, 0, csrow, -1, -1, mci->ctl_name, ""); diff --git a/drivers/edac/e7xxx_edac.c b/drivers/edac/e7xxx_edac.c index 3cda79b..ece3aef 100644 --- a/drivers/edac/e7xxx_edac.c +++ b/drivers/edac/e7xxx_edac.c @@ -226,7 +226,7 @@ static void process_ce(struct mem_ctl_info *mci, struct e7xxx_error_info *info) static void process_ce_no_info(struct mem_ctl_info *mci) { edac_dbg(3, "\n"); - edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0, -1, -1, -1, + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, 0, 0, 0, -1, -1, -1, "e7xxx CE log register overflow", ""); } diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c index fa1326e..ad76f10 100644 --- a/drivers/edac/i3200_edac.c +++ b/drivers/edac/i3200_edac.c @@ -242,11 +242,11 @@ static void i3200_process_error_info(struct mem_ctl_info *mci, -1, -1, "i3000 UE", ""); } else if (log & I3200_ECCERRLOG_CE) { - edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, 0, 0, eccerrlog_syndrome(log), eccerrlog_row(channel, log), -1, -1, - "i3000 UE", ""); + "i3000 CE", ""); } } } diff --git a/drivers/edac/i82860_edac.c b/drivers/edac/i82860_edac.c index 3382f63..4382343 100644 --- a/drivers/edac/i82860_edac.c +++ b/drivers/edac/i82860_edac.c @@ -124,7 +124,7 @@ static int i82860_process_error_info(struct mem_ctl_info *mci, dimm->location[0], dimm->location[1], -1, "i82860 UE", ""); else - edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, info->eap, 0, info->derrsyn, dimm->location[0], dimm->location[1], -1, "i82860 CE", ""); diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c index ef6b7e0..5c361f3 100644 --- a/drivers/edac/ppc4xx_edac.c +++ b/drivers/edac/ppc4xx_edac.c @@ -921,7 +921,7 @@ static int ppc4xx_edac_init_csrows(struct mem_ctl_info *mci, u32 mcopt1) */ for (row = 0; row < mci->nr_csrows; row++) { - struct csrow_info *csi = &mci->csrows[row]; + struct csrow_info *csi = mci->csrows[row]; /* * Get the configuration settings for this diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 54e2abe..3e623ab 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -285,8 +285,9 @@ static const u32 correrrthrsld[] = { * sbridge structs */ -#define NUM_CHANNELS 4 -#define MAX_DIMMS 3 /* Max DIMMS per channel */ +#define NUM_CHANNELS 4 +#define MAX_DIMMS 3 /* Max DIMMS per channel */ +#define CHANNEL_UNSPECIFIED 0xf /* Intel IA32 SDM 15-14 */ enum type { SANDY_BRIDGE, @@ -764,7 +765,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci) u32 reg; u64 limit, prv = 0; u64 tmp_mb; - u32 mb, kb; + u32 gb, mb; u32 rir_way; /* @@ -774,15 +775,17 @@ static void get_memory_layout(const struct mem_ctl_info *mci) pvt->tolm = pvt->info.get_tolm(pvt); tmp_mb = (1 + pvt->tolm) >> 20; - mb = div_u64_rem(tmp_mb, 1000, &kb); - edac_dbg(0, "TOLM: %u.%03u GB (0x%016Lx)\n", mb, kb, (u64)pvt->tolm); + gb = div_u64_rem(tmp_mb, 1024, &mb); + edac_dbg(0, "TOLM: %u.%03u GB (0x%016Lx)\n", + gb, (mb*1000)/1024, (u64)pvt->tolm); /* Address range is already 45:25 */ pvt->tohm = pvt->info.get_tohm(pvt); tmp_mb = (1 + pvt->tohm) >> 20; - mb = div_u64_rem(tmp_mb, 1000, &kb); - edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)\n", mb, kb, (u64)pvt->tohm); + gb = div_u64_rem(tmp_mb, 1024, &mb); + edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)\n", + gb, (mb*1000)/1024, (u64)pvt->tohm); /* * Step 2) Get SAD range and SAD Interleave list @@ -804,11 +807,11 @@ static void get_memory_layout(const struct mem_ctl_info *mci) break; tmp_mb = (limit + 1) >> 20; - mb = div_u64_rem(tmp_mb, 1000, &kb); + gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "SAD#%d %s up to %u.%03u GB (0x%016Lx) Interleave: %s reg=0x%08x\n", n_sads, get_dram_attr(reg), - mb, kb, + gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, INTERLEAVE_MODE(reg) ? "8:6" : "[8:6]XOR[18:16]", reg); @@ -839,9 +842,9 @@ static void get_memory_layout(const struct mem_ctl_info *mci) break; tmp_mb = (limit + 1) >> 20; - mb = div_u64_rem(tmp_mb, 1000, &kb); + gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "TAD#%d: up to %u.%03u GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n", - n_tads, mb, kb, + n_tads, gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, (u32)TAD_SOCK(reg), (u32)TAD_CH(reg), @@ -864,10 +867,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci) tad_ch_nilv_offset[j], ®); tmp_mb = TAD_OFFSET(reg) >> 20; - mb = div_u64_rem(tmp_mb, 1000, &kb); + gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "TAD CH#%d, offset #%d: %u.%03u GB (0x%016Lx), reg=0x%08x\n", i, j, - mb, kb, + gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, reg); } @@ -889,10 +892,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci) tmp_mb = RIR_LIMIT(reg) >> 20; rir_way = 1 << RIR_WAY(reg); - mb = div_u64_rem(tmp_mb, 1000, &kb); + gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "CH#%d RIR#%d, limit: %u.%03u GB (0x%016Lx), way: %d, reg=0x%08x\n", i, j, - mb, kb, + gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, rir_way, reg); @@ -903,10 +906,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci) ®); tmp_mb = RIR_OFFSET(reg) << 6; - mb = div_u64_rem(tmp_mb, 1000, &kb); + gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n", i, j, k, - mb, kb, + gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, (u32)RIR_RNK_TGT(reg), reg); @@ -944,7 +947,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, u8 ch_way, sck_way, pkg, sad_ha = 0; u32 tad_offset; u32 rir_way; - u32 mb, kb; + u32 mb, gb; u64 ch_addr, offset, limit = 0, prv = 0; @@ -1182,10 +1185,10 @@ static int get_memory_error_data(struct mem_ctl_info *mci, continue; limit = RIR_LIMIT(reg); - mb = div_u64_rem(limit >> 20, 1000, &kb); + gb = div_u64_rem(limit >> 20, 1024, &mb); edac_dbg(0, "RIR#%d, limit: %u.%03u GB (0x%016Lx), way: %d\n", n_rir, - mb, kb, + gb, (mb*1000)/1024, limit, 1 << RIR_WAY(reg)); if (ch_addr <= limit) @@ -1750,6 +1753,9 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, /* FIXME: need support for channel mask */ + if (channel == CHANNEL_UNSPECIFIED) + channel = -1; + /* Call the helper to output message */ edac_mc_handle_error(tp_event, mci, core_err_cnt, m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0, diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index d7d5c8a..6d44568 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1637,8 +1637,7 @@ static int dispatch_ioctl(struct client *client, _IOC_SIZE(cmd) > sizeof(buffer)) return -ENOTTY; - if (_IOC_DIR(cmd) == _IOC_READ) - memset(&buffer, 0, _IOC_SIZE(cmd)); + memset(&buffer, 0, sizeof(buffer)); if (_IOC_DIR(cmd) & _IOC_WRITE) if (copy_from_user(&buffer, arg, _IOC_SIZE(cmd))) diff --git a/drivers/firmware/efi/runtime-map.c b/drivers/firmware/efi/runtime-map.c index 97cdd16..c98b101 100644 --- a/drivers/firmware/efi/runtime-map.c +++ b/drivers/firmware/efi/runtime-map.c @@ -170,7 +170,7 @@ int __init efi_runtime_map_init(struct kobject *efi_kobj) return 0; out_add_entry: - for (j = i - 1; j > 0; j--) { + for (j = i - 1; j >= 0; j--) { entry = *(map_entries + j); kobject_put(&entry->kobj); } diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index b22659c..e612552 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -481,7 +481,7 @@ EXPORT_SYMBOL_GPL(efivar_entry_remove); */ static void efivar_entry_list_del_unlock(struct efivar_entry *entry) { - WARN_ON(!spin_is_locked(&__efivars->lock)); + lockdep_assert_held(&__efivars->lock); list_del(&entry->list); spin_unlock_irq(&__efivars->lock); @@ -507,7 +507,7 @@ int __efivar_entry_delete(struct efivar_entry *entry) const struct efivar_operations *ops = __efivars->ops; efi_status_t status; - WARN_ON(!spin_is_locked(&__efivars->lock)); + lockdep_assert_held(&__efivars->lock); status = ops->set_variable(entry->var.VariableName, &entry->var.VendorGuid, @@ -667,7 +667,7 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, int strsize1, strsize2; bool found = false; - WARN_ON(!spin_is_locked(&__efivars->lock)); + lockdep_assert_held(&__efivars->lock); list_for_each_entry_safe(entry, n, head, list) { strsize1 = ucs2_strsize(name, 1024); @@ -739,7 +739,7 @@ int __efivar_entry_get(struct efivar_entry *entry, u32 *attributes, const struct efivar_operations *ops = __efivars->ops; efi_status_t status; - WARN_ON(!spin_is_locked(&__efivars->lock)); + lockdep_assert_held(&__efivars->lock); status = ops->get_variable(entry->var.VariableName, &entry->var.VendorGuid, diff --git a/drivers/gpio/gpio-kempld.c b/drivers/gpio/gpio-kempld.c index c6d8817..fe6d4a1 100644 --- a/drivers/gpio/gpio-kempld.c +++ b/drivers/gpio/gpio-kempld.c @@ -117,7 +117,7 @@ static int kempld_gpio_get_direction(struct gpio_chip *chip, unsigned offset) = container_of(chip, struct kempld_gpio_data, chip); struct kempld_device_data *pld = gpio->pld; - return kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset); + return !kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset); } static int kempld_gpio_pincount(struct kempld_device_data *pld) diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index 3b1fd1c..e9d8cf6 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -304,11 +304,13 @@ static void mvebu_gpio_edge_irq_mask(struct irq_data *d) { struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct mvebu_gpio_chip *mvchip = gc->private; + struct irq_chip_type *ct = irq_data_get_chip_type(d); u32 mask = 1 << (d->irq - gc->irq_base); irq_gc_lock(gc); - gc->mask_cache &= ~mask; - writel_relaxed(gc->mask_cache, mvebu_gpioreg_edge_mask(mvchip)); + ct->mask_cache_priv &= ~mask; + + writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_edge_mask(mvchip)); irq_gc_unlock(gc); } @@ -316,11 +318,13 @@ static void mvebu_gpio_edge_irq_unmask(struct irq_data *d) { struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct mvebu_gpio_chip *mvchip = gc->private; + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = 1 << (d->irq - gc->irq_base); irq_gc_lock(gc); - gc->mask_cache |= mask; - writel_relaxed(gc->mask_cache, mvebu_gpioreg_edge_mask(mvchip)); + ct->mask_cache_priv |= mask; + writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_edge_mask(mvchip)); irq_gc_unlock(gc); } @@ -328,11 +332,13 @@ static void mvebu_gpio_level_irq_mask(struct irq_data *d) { struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct mvebu_gpio_chip *mvchip = gc->private; + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = 1 << (d->irq - gc->irq_base); irq_gc_lock(gc); - gc->mask_cache &= ~mask; - writel_relaxed(gc->mask_cache, mvebu_gpioreg_level_mask(mvchip)); + ct->mask_cache_priv &= ~mask; + writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_level_mask(mvchip)); irq_gc_unlock(gc); } @@ -340,11 +346,13 @@ static void mvebu_gpio_level_irq_unmask(struct irq_data *d) { struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct mvebu_gpio_chip *mvchip = gc->private; + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = 1 << (d->irq - gc->irq_base); irq_gc_lock(gc); - gc->mask_cache |= mask; - writel_relaxed(gc->mask_cache, mvebu_gpioreg_level_mask(mvchip)); + ct->mask_cache_priv |= mask; + writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_level_mask(mvchip)); irq_gc_unlock(gc); } diff --git a/drivers/gpio/gpio-tps65912.c b/drivers/gpio/gpio-tps65912.c index 59ee486..6005d26 100644 --- a/drivers/gpio/gpio-tps65912.c +++ b/drivers/gpio/gpio-tps65912.c @@ -26,9 +26,12 @@ struct tps65912_gpio_data { struct gpio_chip gpio_chip; }; +#define to_tgd(gc) container_of(gc, struct tps65912_gpio_data, gpio_chip) + static int tps65912_gpio_get(struct gpio_chip *gc, unsigned offset) { - struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc); + struct tps65912 *tps65912 = tps65912_gpio->tps65912; int val; val = tps65912_reg_read(tps65912, TPS65912_GPIO1 + offset); @@ -42,7 +45,8 @@ static int tps65912_gpio_get(struct gpio_chip *gc, unsigned offset) static void tps65912_gpio_set(struct gpio_chip *gc, unsigned offset, int value) { - struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc); + struct tps65912 *tps65912 = tps65912_gpio->tps65912; if (value) tps65912_set_bits(tps65912, TPS65912_GPIO1 + offset, @@ -55,7 +59,8 @@ static void tps65912_gpio_set(struct gpio_chip *gc, unsigned offset, static int tps65912_gpio_output(struct gpio_chip *gc, unsigned offset, int value) { - struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc); + struct tps65912 *tps65912 = tps65912_gpio->tps65912; /* Set the initial value */ tps65912_gpio_set(gc, offset, value); @@ -66,7 +71,8 @@ static int tps65912_gpio_output(struct gpio_chip *gc, unsigned offset, static int tps65912_gpio_input(struct gpio_chip *gc, unsigned offset) { - struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc); + struct tps65912 *tps65912 = tps65912_gpio->tps65912; return tps65912_clear_bits(tps65912, TPS65912_GPIO1 + offset, GPIO_CFG_MASK); diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index e0a98f5..d26028c 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -44,8 +44,15 @@ static int of_gpiochip_find_and_xlate(struct gpio_chip *gc, void *data) return false; ret = gc->of_xlate(gc, &gg_data->gpiospec, gg_data->flags); - if (ret < 0) + if (ret < 0) { + /* We've found a gpio chip, but the translation failed. + * Store translation error in out_gpio. + * Return false to keep looking, as more than one gpio chip + * could be registered per of-node. + */ + gg_data->out_gpio = ERR_PTR(ret); return false; + } gg_data->out_gpio = gpio_to_desc(ret + gc->base); return true; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 50c4922..a03e18f 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -408,7 +408,7 @@ static ssize_t gpio_value_store(struct device *dev, return status; } -static const DEVICE_ATTR(value, 0644, +static DEVICE_ATTR(value, 0644, gpio_value_show, gpio_value_store); static irqreturn_t gpio_sysfs_irq(int irq, void *priv) @@ -633,18 +633,16 @@ static ssize_t gpio_active_low_store(struct device *dev, return status ? : size; } -static const DEVICE_ATTR(active_low, 0644, +static DEVICE_ATTR(active_low, 0644, gpio_active_low_show, gpio_active_low_store); -static const struct attribute *gpio_attrs[] = { +static struct attribute *gpio_attrs[] = { &dev_attr_value.attr, &dev_attr_active_low.attr, NULL, }; -static const struct attribute_group gpio_attr_group = { - .attrs = (struct attribute **) gpio_attrs, -}; +ATTRIBUTE_GROUPS(gpio); /* * /sys/class/gpio/gpiochipN/ @@ -680,16 +678,13 @@ static ssize_t chip_ngpio_show(struct device *dev, } static DEVICE_ATTR(ngpio, 0444, chip_ngpio_show, NULL); -static const struct attribute *gpiochip_attrs[] = { +static struct attribute *gpiochip_attrs[] = { &dev_attr_base.attr, &dev_attr_label.attr, &dev_attr_ngpio.attr, NULL, }; - -static const struct attribute_group gpiochip_attr_group = { - .attrs = (struct attribute **) gpiochip_attrs, -}; +ATTRIBUTE_GROUPS(gpiochip); /* * /sys/class/gpio/export ... write-only @@ -805,6 +800,7 @@ static struct class gpio_class = { */ int gpiod_export(struct gpio_desc *desc, bool direction_may_change) { + struct gpio_chip *chip; unsigned long flags; int status; const char *ioname = NULL; @@ -822,8 +818,16 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change) return -EINVAL; } + chip = desc->chip; + mutex_lock(&sysfs_lock); + /* check if chip is being removed */ + if (!chip || !chip->exported) { + status = -ENODEV; + goto fail_unlock; + } + spin_lock_irqsave(&gpio_lock, flags); if (!test_bit(FLAG_REQUESTED, &desc->flags) || test_bit(FLAG_EXPORT, &desc->flags)) { @@ -844,18 +848,15 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change) if (desc->chip->names && desc->chip->names[offset]) ioname = desc->chip->names[offset]; - dev = device_create(&gpio_class, desc->chip->dev, MKDEV(0, 0), - desc, ioname ? ioname : "gpio%u", - desc_to_gpio(desc)); + dev = device_create_with_groups(&gpio_class, desc->chip->dev, + MKDEV(0, 0), desc, gpio_groups, + ioname ? ioname : "gpio%u", + desc_to_gpio(desc)); if (IS_ERR(dev)) { status = PTR_ERR(dev); goto fail_unlock; } - status = sysfs_create_group(&dev->kobj, &gpio_attr_group); - if (status) - goto fail_unregister_device; - if (direction_may_change) { status = device_create_file(dev, &dev_attr_direction); if (status) @@ -866,13 +867,15 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change) !test_bit(FLAG_IS_OUT, &desc->flags))) { status = device_create_file(dev, &dev_attr_edge); if (status) - goto fail_unregister_device; + goto fail_remove_attr_direction; } set_bit(FLAG_EXPORT, &desc->flags); mutex_unlock(&sysfs_lock); return 0; +fail_remove_attr_direction: + device_remove_file(dev, &dev_attr_direction); fail_unregister_device: device_unregister(dev); fail_unlock: @@ -917,6 +920,7 @@ int gpiod_export_link(struct device *dev, const char *name, if (tdev != NULL) { status = sysfs_create_link(&dev->kobj, &tdev->kobj, name); + put_device(tdev); } else { status = -ENODEV; } @@ -964,7 +968,7 @@ int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value) } status = sysfs_set_active_low(desc, dev, value); - + put_device(dev); unlock: mutex_unlock(&sysfs_lock); @@ -1006,6 +1010,8 @@ void gpiod_unexport(struct gpio_desc *desc) mutex_unlock(&sysfs_lock); if (dev) { + device_remove_file(dev, &dev_attr_edge); + device_remove_file(dev, &dev_attr_direction); device_unregister(dev); put_device(dev); } @@ -1030,13 +1036,13 @@ static int gpiochip_export(struct gpio_chip *chip) /* use chip->base for the ID; it's already known to be unique */ mutex_lock(&sysfs_lock); - dev = device_create(&gpio_class, chip->dev, MKDEV(0, 0), chip, - "gpiochip%d", chip->base); - if (!IS_ERR(dev)) { - status = sysfs_create_group(&dev->kobj, - &gpiochip_attr_group); - } else + dev = device_create_with_groups(&gpio_class, chip->dev, MKDEV(0, 0), + chip, gpiochip_groups, + "gpiochip%d", chip->base); + if (IS_ERR(dev)) status = PTR_ERR(dev); + else + status = 0; chip->exported = (status == 0); mutex_unlock(&sysfs_lock); @@ -1060,12 +1066,15 @@ static void gpiochip_unexport(struct gpio_chip *chip) { int status; struct device *dev; + struct gpio_desc *desc; + unsigned int i; mutex_lock(&sysfs_lock); dev = class_find_device(&gpio_class, NULL, chip, match_export); if (dev) { put_device(dev); device_unregister(dev); + /* prevent further gpiod exports */ chip->exported = false; status = 0; } else @@ -1074,6 +1083,13 @@ static void gpiochip_unexport(struct gpio_chip *chip) if (status) chip_dbg(chip, "%s: status %d\n", __func__, status); + + /* unregister gpiod class devices owned by sysfs */ + for (i = 0; i < chip->ngpio; i++) { + desc = &chip->desc[i]; + if (test_and_clear_bit(FLAG_SYSFS, &desc->flags)) + gpiod_free(desc); + } } static int __init gpiolib_sysfs_init(void) @@ -1222,6 +1238,9 @@ int gpiochip_add(struct gpio_chip *chip) spin_unlock_irqrestore(&gpio_lock, flags); + if (status) + goto fail; + #ifdef CONFIG_PINCTRL INIT_LIST_HEAD(&chip->pin_ranges); #endif @@ -1229,12 +1248,12 @@ int gpiochip_add(struct gpio_chip *chip) of_gpiochip_add(chip); acpi_gpiochip_add(chip); - if (status) - goto fail; - status = gpiochip_export(chip); - if (status) + if (status) { + acpi_gpiochip_remove(chip); + of_gpiochip_remove(chip); goto fail; + } pr_debug("%s: registered GPIOs %d to %d on device: %s\n", __func__, chip->base, chip->base + chip->ngpio - 1, @@ -1265,6 +1284,8 @@ int gpiochip_remove(struct gpio_chip *chip) int status = 0; unsigned id; + gpiochip_unexport(chip); + spin_lock_irqsave(&gpio_lock, flags); gpiochip_remove_pin_ranges(chip); @@ -1286,9 +1307,6 @@ int gpiochip_remove(struct gpio_chip *chip) spin_unlock_irqrestore(&gpio_lock, flags); - if (status == 0) - gpiochip_unexport(chip); - return status; } EXPORT_SYMBOL_GPL(gpiochip_remove); @@ -1928,15 +1946,15 @@ EXPORT_SYMBOL_GPL(gpiod_is_active_low); * that the GPIO was actually requested. */ -static int _gpiod_get_raw_value(const struct gpio_desc *desc) +static bool _gpiod_get_raw_value(const struct gpio_desc *desc) { struct gpio_chip *chip; - int value; + bool value; int offset; chip = desc->chip; offset = gpio_chip_hwgpio(desc); - value = chip->get ? chip->get(chip, offset) : 0; + value = chip->get ? chip->get(chip, offset) : false; trace_gpio_value(desc_to_gpio(desc), 1, value); return value; } @@ -1992,7 +2010,7 @@ EXPORT_SYMBOL_GPL(gpiod_get_value); * @desc: gpio descriptor whose state need to be set. * @value: Non-zero for setting it HIGH otherise it will set to LOW. */ -static void _gpio_set_open_drain_value(struct gpio_desc *desc, int value) +static void _gpio_set_open_drain_value(struct gpio_desc *desc, bool value) { int err = 0; struct gpio_chip *chip = desc->chip; @@ -2019,7 +2037,7 @@ static void _gpio_set_open_drain_value(struct gpio_desc *desc, int value) * @desc: gpio descriptor whose state need to be set. * @value: Non-zero for setting it HIGH otherise it will set to LOW. */ -static void _gpio_set_open_source_value(struct gpio_desc *desc, int value) +static void _gpio_set_open_source_value(struct gpio_desc *desc, bool value) { int err = 0; struct gpio_chip *chip = desc->chip; @@ -2041,7 +2059,7 @@ static void _gpio_set_open_source_value(struct gpio_desc *desc, int value) __func__, err); } -static void _gpiod_set_raw_value(struct gpio_desc *desc, int value) +static void _gpiod_set_raw_value(struct gpio_desc *desc, bool value) { struct gpio_chip *chip; diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 50535fd..d830b38 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -100,7 +100,7 @@ static int ast_detect_chip(struct drm_device *dev) } ast->vga2_clone = false; } else { - ast->chip = 2000; + ast->chip = AST2000; DRM_INFO("AST 2000 detected\n"); } } diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index cca063b..d2e56e9 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -1012,8 +1012,8 @@ static u32 copy_cursor_image(u8 *src, u8 *dst, int width, int height) srcdata32[1].ul = *((u32 *)(srcxor + 4)) & 0xf0f0f0f0; data32.b[0] = srcdata32[0].b[1] | (srcdata32[0].b[0] >> 4); data32.b[1] = srcdata32[0].b[3] | (srcdata32[0].b[2] >> 4); - data32.b[2] = srcdata32[0].b[1] | (srcdata32[1].b[0] >> 4); - data32.b[3] = srcdata32[0].b[3] | (srcdata32[1].b[2] >> 4); + data32.b[2] = srcdata32[1].b[1] | (srcdata32[1].b[0] >> 4); + data32.b[3] = srcdata32[1].b[3] | (srcdata32[1].b[2] >> 4); writel(data32.ul, dstxor); csum += data32.ul; diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c index 08ce520..faa1f42 100644 --- a/drivers/gpu/drm/cirrus/cirrus_drv.c +++ b/drivers/gpu/drm/cirrus/cirrus_drv.c @@ -32,6 +32,8 @@ static struct drm_driver driver; static DEFINE_PCI_DEVICE_TABLE(pciidlist) = { { PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_5446, 0x1af4, 0x1100, 0, 0, 0 }, + { PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_5446, PCI_VENDOR_ID_XEN, + 0x0001, 0, 0, 0 }, {0,} }; diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 3b7d32d..903db3c 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -2155,8 +2155,11 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EINVAL; - /* For some reason crtc x/y offsets are signed internally. */ - if (crtc_req->x > INT_MAX || crtc_req->y > INT_MAX) + /* + * Universal plane src offsets are only 16.16, prevent havoc for + * drivers using universal plane code internally. + */ + if (crtc_req->x & 0xffff0000 || crtc_req->y & 0xffff0000) return -ERANGE; drm_modeset_lock_all(dev); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 3ecb332..de5ab48 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1426,10 +1426,13 @@ unlock: out: switch (ret) { case -EIO: - /* If this -EIO is due to a gpu hang, give the reset code a - * chance to clean up the mess. Otherwise return the proper - * SIGBUS. */ - if (i915_terminally_wedged(&dev_priv->gpu_error)) { + /* + * We eat errors when the gpu is terminally wedged to avoid + * userspace unduly crashing (gl has no provisions for mmaps to + * fail). But any other -EIO isn't ours (e.g. swap in failure) + * and so needs to be reported. + */ + if (!i915_terminally_wedged(&dev_priv->gpu_error)) { ret = VM_FAULT_SIGBUS; break; } @@ -2890,6 +2893,13 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, u32 size = i915_gem_obj_ggtt_size(obj); uint64_t val; + /* Adjust fence size to match tiled area */ + if (obj->tiling_mode != I915_TILING_NONE) { + uint32_t row_size = obj->stride * + (obj->tiling_mode == I915_TILING_Y ? 32 : 8); + size = (size / row_size) * row_size; + } + val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) & 0xfffff000) << 32; val |= i915_gem_obj_ggtt_offset(obj) & 0xfffff000; @@ -4975,7 +4985,7 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task) if (!mutex_is_locked(mutex)) return false; -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES) +#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES) return mutex->owner == task; #else /* Since UP may be pre-empted, we cannot assume that we own the lock */ diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index d278be1..1855cdc 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -827,6 +827,16 @@ void i915_check_and_clear_faults(struct drm_device *dev) POSTING_READ(RING_FAULT_REG(&dev_priv->ring[RCS])); } +static void i915_ggtt_flush(struct drm_i915_private *dev_priv) +{ + if (INTEL_INFO(dev_priv->dev)->gen < 6) { + intel_gtt_chipset_flush(); + } else { + I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN); + POSTING_READ(GFX_FLSH_CNTL_GEN6); + } +} + void i915_gem_suspend_gtt_mappings(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -843,6 +853,8 @@ void i915_gem_suspend_gtt_mappings(struct drm_device *dev) dev_priv->gtt.base.start / PAGE_SIZE, dev_priv->gtt.base.total / PAGE_SIZE, true); + + i915_ggtt_flush(dev_priv); } void i915_gem_restore_gtt_mappings(struct drm_device *dev) @@ -863,7 +875,7 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev) i915_gem_gtt_bind_object(obj, obj->cache_level); } - i915_gem_chipset_flush(dev); + i915_ggtt_flush(dev_priv); } int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj) diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index 3c78b22..800e06c 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -137,7 +137,11 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev) r = devm_request_mem_region(dev->dev, base + 1, dev_priv->gtt.stolen_size - 1, "Graphics Stolen Memory"); - if (r == NULL) { + /* + * GEN3 firmware likes to smash pci bridges into the stolen + * range. Apparently this works. + */ + if (r == NULL && !IS_GEN3(dev)) { DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n", base, base + (uint32_t)dev_priv->gtt.stolen_size); base = 0; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 0a3b938..5b38bf8 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -320,6 +320,7 @@ #define PIPE_CONTROL_GLOBAL_GTT_IVB (1<<24) /* gen7+ */ #define PIPE_CONTROL_CS_STALL (1<<20) #define PIPE_CONTROL_TLB_INVALIDATE (1<<18) +#define PIPE_CONTROL_MEDIA_STATE_CLEAR (1<<16) #define PIPE_CONTROL_QW_WRITE (1<<14) #define PIPE_CONTROL_DEPTH_STALL (1<<13) #define PIPE_CONTROL_WRITE_FLUSH (1<<12) @@ -1180,6 +1181,7 @@ #define GMBUS_CYCLE_INDEX (2<<25) #define GMBUS_CYCLE_STOP (4<<25) #define GMBUS_BYTE_COUNT_SHIFT 16 +#define GMBUS_BYTE_COUNT_MAX 256U #define GMBUS_SLAVE_INDEX_SHIFT 8 #define GMBUS_SLAVE_ADDR_SHIFT 1 #define GMBUS_SLAVE_READ (1<<0) diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index f220419..08105fd 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -839,7 +839,7 @@ init_vbt_defaults(struct drm_i915_private *dev_priv) } } -static int __init intel_no_opregion_vbt_callback(const struct dmi_system_id *id) +static int intel_no_opregion_vbt_callback(const struct dmi_system_id *id) { DRM_DEBUG_KMS("Falling back to manually reading VBT from " "VBIOS ROM for %s\n", diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index b19ddac..8348475 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -750,7 +750,7 @@ static const struct drm_encoder_funcs intel_crt_enc_funcs = { .destroy = intel_encoder_destroy, }; -static int __init intel_no_crt_dmi_callback(const struct dmi_system_id *id) +static int intel_no_crt_dmi_callback(const struct dmi_system_id *id) { DRM_INFO("Skipping CRT initialization for %s\n", id->ident); return 1; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index b6fb3eb..c514690 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -3817,7 +3817,6 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc) ironlake_fdi_disable(crtc); ironlake_disable_pch_transcoder(dev_priv, pipe); - intel_set_pch_fifo_underrun_reporting(dev, pipe, true); if (HAS_PCH_CPT(dev)) { /* disable TRANS_DP_CTL */ @@ -3883,7 +3882,6 @@ static void haswell_crtc_disable(struct drm_crtc *crtc) if (intel_crtc->config.has_pch_encoder) { lpt_disable_pch_transcoder(dev_priv); - intel_set_pch_fifo_underrun_reporting(dev, TRANSCODER_A, true); intel_ddi_fdi_disable(crtc); } diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index b2d0887..462307c 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -481,10 +481,8 @@ intel_dp_aux_ch(struct intel_dp *intel_dp, DP_AUX_CH_CTL_RECEIVE_ERROR)) continue; if (status & DP_AUX_CH_CTL_DONE) - break; + goto done; } - if (status & DP_AUX_CH_CTL_DONE) - break; } if ((status & DP_AUX_CH_CTL_DONE) == 0) { @@ -493,6 +491,7 @@ intel_dp_aux_ch(struct intel_dp *intel_dp, goto out; } +done: /* Check for timeout or receive error. * Timeouts occur when the sink is not connected */ diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index d33b61d..81f8ec8 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -324,18 +324,17 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv) } static int -gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, - u32 gmbus1_index) +gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv, + unsigned short addr, u8 *buf, unsigned int len, + u32 gmbus1_index) { int reg_offset = dev_priv->gpio_mmio_base; - u16 len = msg->len; - u8 *buf = msg->buf; I915_WRITE(GMBUS1 + reg_offset, gmbus1_index | GMBUS_CYCLE_WAIT | (len << GMBUS_BYTE_COUNT_SHIFT) | - (msg->addr << GMBUS_SLAVE_ADDR_SHIFT) | + (addr << GMBUS_SLAVE_ADDR_SHIFT) | GMBUS_SLAVE_READ | GMBUS_SW_RDY); while (len) { int ret; @@ -357,11 +356,35 @@ gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, } static int -gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg) +gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, + u32 gmbus1_index) { - int reg_offset = dev_priv->gpio_mmio_base; - u16 len = msg->len; u8 *buf = msg->buf; + unsigned int rx_size = msg->len; + unsigned int len; + int ret; + + do { + len = min(rx_size, GMBUS_BYTE_COUNT_MAX); + + ret = gmbus_xfer_read_chunk(dev_priv, msg->addr, + buf, len, gmbus1_index); + if (ret) + return ret; + + rx_size -= len; + buf += len; + } while (rx_size != 0); + + return 0; +} + +static int +gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv, + unsigned short addr, u8 *buf, unsigned int len) +{ + int reg_offset = dev_priv->gpio_mmio_base; + unsigned int chunk_size = len; u32 val, loop; val = loop = 0; @@ -373,8 +396,8 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg) I915_WRITE(GMBUS3 + reg_offset, val); I915_WRITE(GMBUS1 + reg_offset, GMBUS_CYCLE_WAIT | - (msg->len << GMBUS_BYTE_COUNT_SHIFT) | - (msg->addr << GMBUS_SLAVE_ADDR_SHIFT) | + (chunk_size << GMBUS_BYTE_COUNT_SHIFT) | + (addr << GMBUS_SLAVE_ADDR_SHIFT) | GMBUS_SLAVE_WRITE | GMBUS_SW_RDY); while (len) { int ret; @@ -391,6 +414,29 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg) if (ret) return ret; } + + return 0; +} + +static int +gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg) +{ + u8 *buf = msg->buf; + unsigned int tx_size = msg->len; + unsigned int len; + int ret; + + do { + len = min(tx_size, GMBUS_BYTE_COUNT_MAX); + + ret = gmbus_xfer_write_chunk(dev_priv, msg->addr, buf, len); + if (ret) + return ret; + + buf += len; + tx_size -= len; + } while (tx_size != 0); + return 0; } @@ -443,7 +489,7 @@ gmbus_xfer(struct i2c_adapter *adapter, struct intel_gmbus, adapter); struct drm_i915_private *dev_priv = bus->dev_priv; - int i, reg_offset; + int i = 0, inc, try = 0, reg_offset; int ret = 0; intel_aux_display_runtime_get(dev_priv); @@ -456,12 +502,14 @@ gmbus_xfer(struct i2c_adapter *adapter, reg_offset = dev_priv->gpio_mmio_base; +retry: I915_WRITE(GMBUS0 + reg_offset, bus->reg0); - for (i = 0; i < num; i++) { + for (; i < num; i += inc) { + inc = 1; if (gmbus_is_index_read(msgs, i, num)) { ret = gmbus_xfer_index_read(dev_priv, &msgs[i]); - i += 1; /* set i to the index of the read xfer */ + inc = 2; /* an index read is two msgs */ } else if (msgs[i].flags & I2C_M_RD) { ret = gmbus_xfer_read(dev_priv, &msgs[i], 0); } else { @@ -533,6 +581,18 @@ clear_err: adapter->name, msgs[i].addr, (msgs[i].flags & I2C_M_RD) ? 'r' : 'w', msgs[i].len); + /* + * Passive adapters sometimes NAK the first probe. Retry the first + * message once on -ENXIO for GMBUS transfers; the bit banging algorithm + * has retries internally. See also the retry loop in + * drm_do_probe_ddc_edid, which bails out on the first -ENXIO. + */ + if (ret == -ENXIO && i == 0 && try++ == 0) { + DRM_DEBUG_KMS("GMBUS [%s] NAK on first message, retry\n", + adapter->name); + goto retry; + } + goto out; timeout: diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index eb8f64b..1eb4994 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -544,7 +544,7 @@ static const struct drm_encoder_funcs intel_lvds_enc_funcs = { .destroy = intel_encoder_destroy, }; -static int __init intel_no_lvds_dmi_callback(const struct dmi_system_id *id) +static int intel_no_lvds_dmi_callback(const struct dmi_system_id *id) { DRM_INFO("Skipping LVDS initialization for %s\n", id->ident); return 1; @@ -815,12 +815,28 @@ static int intel_dual_link_lvds_callback(const struct dmi_system_id *id) static const struct dmi_system_id intel_dual_link_lvds[] = { { .callback = intel_dual_link_lvds_callback, - .ident = "Apple MacBook Pro (Core i5/i7 Series)", + .ident = "Apple MacBook Pro 15\" (2010)", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro6,2"), + }, + }, + { + .callback = intel_dual_link_lvds_callback, + .ident = "Apple MacBook Pro 15\" (2011)", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro8,2"), }, }, + { + .callback = intel_dual_link_lvds_callback, + .ident = "Apple MacBook Pro 15\" (2012)", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro9,1"), + }, + }, { } /* terminating entry */ }; @@ -905,6 +921,17 @@ void intel_lvds_init(struct drm_device *dev) int pipe; u8 pin; + /* + * Unlock registers and just leave them unlocked. Do this before + * checking quirk lists to avoid bogus WARNINGs. + */ + if (HAS_PCH_SPLIT(dev)) { + I915_WRITE(PCH_PP_CONTROL, + I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS); + } else { + I915_WRITE(PP_CONTROL, + I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS); + } if (!intel_lvds_supported(dev)) return; @@ -1099,17 +1126,6 @@ out: DRM_DEBUG_KMS("detected %s-link lvds configuration\n", lvds_encoder->is_dual_link ? "dual" : "single"); - /* - * Unlock registers and just - * leave them unlocked - */ - if (HAS_PCH_SPLIT(dev)) { - I915_WRITE(PCH_PP_CONTROL, - I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS); - } else { - I915_WRITE(PP_CONTROL, - I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS); - } lvds_connector->lid_notifier.notifier_call = intel_lid_notify; if (acpi_lid_notifier_register(&lvds_connector->lid_notifier)) { DRM_DEBUG_KMS("lid notifier registration failed\n"); diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index fd98bec..c6d9777 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -645,7 +645,7 @@ static void pch_enable_backlight(struct intel_connector *connector) cpu_ctl2 = I915_READ(BLC_PWM_CPU_CTL2); if (cpu_ctl2 & BLM_PWM_ENABLE) { - WARN(1, "cpu backlight already enabled\n"); + DRM_DEBUG_KMS("cpu backlight already enabled\n"); cpu_ctl2 &= ~BLM_PWM_ENABLE; I915_WRITE(BLC_PWM_CPU_CTL2, cpu_ctl2); } @@ -693,7 +693,7 @@ static void i9xx_enable_backlight(struct intel_connector *connector) ctl = I915_READ(BLC_PWM_CTL); if (ctl & BACKLIGHT_DUTY_CYCLE_MASK_PNV) { - WARN(1, "backlight already enabled\n"); + DRM_DEBUG_KMS("backlight already enabled\n"); I915_WRITE(BLC_PWM_CTL, 0); } @@ -724,7 +724,7 @@ static void i965_enable_backlight(struct intel_connector *connector) ctl2 = I915_READ(BLC_PWM_CTL2); if (ctl2 & BLM_PWM_ENABLE) { - WARN(1, "backlight already enabled\n"); + DRM_DEBUG_KMS("backlight already enabled\n"); ctl2 &= ~BLM_PWM_ENABLE; I915_WRITE(BLC_PWM_CTL2, ctl2); } @@ -758,7 +758,7 @@ static void vlv_enable_backlight(struct intel_connector *connector) ctl2 = I915_READ(VLV_BLC_PWM_CTL2(pipe)); if (ctl2 & BLM_PWM_ENABLE) { - WARN(1, "backlight already enabled\n"); + DRM_DEBUG_KMS("backlight already enabled\n"); ctl2 &= ~BLM_PWM_ENABLE; I915_WRITE(VLV_BLC_PWM_CTL2(pipe), ctl2); } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 31b36c5..d2af1e1 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -334,12 +334,15 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring, flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE; flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE; flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE; + flags |= PIPE_CONTROL_MEDIA_STATE_CLEAR; /* * TLB invalidate requires a post-sync write. */ flags |= PIPE_CONTROL_QW_WRITE; flags |= PIPE_CONTROL_GLOBAL_GTT_IVB; + flags |= PIPE_CONTROL_STALL_AT_SCOREBOARD; + /* Workaround: we must issue a pipe_control with CS-stall bit * set before a pipe_control command that has the state cache * invalidate bit set. */ @@ -475,6 +478,9 @@ static int init_ring_common(struct intel_ring_buffer *ring) } } + /* Enforce ordering by reading HEAD register back */ + I915_READ_HEAD(ring); + /* Initialize the ring. This must happen _after_ we've cleared the ring * registers with the above sequence (the readback of the HEAD registers * also enforces ordering), otherwise the hw might lose the new ring diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index 365c7c4..9c9606c 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -854,6 +854,10 @@ intel_enable_tv(struct intel_encoder *encoder) struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + /* Prevents vblank waits from timing out in intel_tv_detect_type() */ + intel_wait_for_vblank(encoder->base.dev, + to_intel_crtc(encoder->base.crtc)->pipe); + I915_WRITE(TV_CTL, I915_READ(TV_CTL) | TV_ENC_ENABLE); } diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index c879631..b6c063c 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -451,8 +451,8 @@ hsw_unclaimed_reg_check(struct drm_i915_private *dev_priv, u32 reg) static void assert_device_not_suspended(struct drm_i915_private *dev_priv) { - WARN(HAS_RUNTIME_PM(dev_priv->dev) && dev_priv->pm.suspended, - "Device suspended\n"); + WARN_ONCE(HAS_RUNTIME_PM(dev_priv->dev) && dev_priv->pm.suspended, + "Device suspended\n"); } #define REG_READ_HEADER(x) \ diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index 9683747..f2511a0 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -1529,6 +1529,11 @@ static int mga_vga_mode_valid(struct drm_connector *connector, return MODE_BANDWIDTH; } + if ((mode->hdisplay % 8) != 0 || (mode->hsync_start % 8) != 0 || + (mode->hsync_end % 8) != 0 || (mode->htotal % 8) != 0) { + return MODE_H_ILLEGAL; + } + if (mode->crtc_hdisplay > 2048 || mode->crtc_hsync_start > 4096 || mode->crtc_hsync_end > 4096 || mode->crtc_htotal > 4096 || mode->crtc_vdisplay > 2048 || mode->crtc_vsync_start > 4096 || diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index 461df93..4f32b34 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -35,8 +35,6 @@ A3XX_INT0_CP_AHB_ERROR_HALT | \ A3XX_INT0_UCHE_OOB_ACCESS) -static struct platform_device *a3xx_pdev; - static void a3xx_me_init(struct msm_gpu *gpu) { struct msm_ringbuffer *ring = gpu->rb; @@ -311,7 +309,6 @@ static void a3xx_destroy(struct msm_gpu *gpu) ocmem_free(OCMEM_GRAPHICS, a3xx_gpu->ocmem_hdl); #endif - put_device(&a3xx_gpu->pdev->dev); kfree(a3xx_gpu); } @@ -439,7 +436,8 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) struct a3xx_gpu *a3xx_gpu = NULL; struct adreno_gpu *adreno_gpu; struct msm_gpu *gpu; - struct platform_device *pdev = a3xx_pdev; + struct msm_drm_private *priv = dev->dev_private; + struct platform_device *pdev = priv->gpu_pdev; struct adreno_platform_config *config; int ret; @@ -460,7 +458,6 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) adreno_gpu = &a3xx_gpu->base; gpu = &adreno_gpu->base; - get_device(&pdev->dev); a3xx_gpu->pdev = pdev; gpu->fast_rate = config->fast_rate; @@ -522,17 +519,24 @@ fail: # include #endif -static int a3xx_probe(struct platform_device *pdev) +static void set_gpu_pdev(struct drm_device *dev, + struct platform_device *pdev) +{ + struct msm_drm_private *priv = dev->dev_private; + priv->gpu_pdev = pdev; +} + +static int a3xx_bind(struct device *dev, struct device *master, void *data) { static struct adreno_platform_config config = {}; #ifdef CONFIG_OF - struct device_node *child, *node = pdev->dev.of_node; + struct device_node *child, *node = dev->of_node; u32 val; int ret; ret = of_property_read_u32(node, "qcom,chipid", &val); if (ret) { - dev_err(&pdev->dev, "could not find chipid: %d\n", ret); + dev_err(dev, "could not find chipid: %d\n", ret); return ret; } @@ -548,7 +552,7 @@ static int a3xx_probe(struct platform_device *pdev) for_each_child_of_node(child, pwrlvl) { ret = of_property_read_u32(pwrlvl, "qcom,gpu-freq", &val); if (ret) { - dev_err(&pdev->dev, "could not find gpu-freq: %d\n", ret); + dev_err(dev, "could not find gpu-freq: %d\n", ret); return ret; } config.fast_rate = max(config.fast_rate, val); @@ -558,12 +562,12 @@ static int a3xx_probe(struct platform_device *pdev) } if (!config.fast_rate) { - dev_err(&pdev->dev, "could not find clk rates\n"); + dev_err(dev, "could not find clk rates\n"); return -ENXIO; } #else - struct kgsl_device_platform_data *pdata = pdev->dev.platform_data; + struct kgsl_device_platform_data *pdata = dev->platform_data; uint32_t version = socinfo_get_version(); if (cpu_is_apq8064ab()) { config.fast_rate = 450000000; @@ -609,14 +613,30 @@ static int a3xx_probe(struct platform_device *pdev) config.bus_scale_table = pdata->bus_scale_table; # endif #endif - pdev->dev.platform_data = &config; - a3xx_pdev = pdev; + dev->platform_data = &config; + set_gpu_pdev(dev_get_drvdata(master), to_platform_device(dev)); return 0; } +static void a3xx_unbind(struct device *dev, struct device *master, + void *data) +{ + set_gpu_pdev(dev_get_drvdata(master), NULL); +} + +static const struct component_ops a3xx_ops = { + .bind = a3xx_bind, + .unbind = a3xx_unbind, +}; + +static int a3xx_probe(struct platform_device *pdev) +{ + return component_add(&pdev->dev, &a3xx_ops); +} + static int a3xx_remove(struct platform_device *pdev) { - a3xx_pdev = NULL; + component_del(&pdev->dev, &a3xx_ops); return 0; } @@ -624,7 +644,6 @@ static const struct of_device_id dt_match[] = { { .compatible = "qcom,kgsl-3d0" }, {} }; -MODULE_DEVICE_TABLE(of, dt_match); static struct platform_driver a3xx_driver = { .probe = a3xx_probe, diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 6f1588a..8a04a1d 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -17,8 +17,6 @@ #include "hdmi.h" -static struct platform_device *hdmi_pdev; - void hdmi_set_mode(struct hdmi *hdmi, bool power_on) { uint32_t ctrl = 0; @@ -75,7 +73,7 @@ struct hdmi *hdmi_init(struct drm_device *dev, struct drm_encoder *encoder) { struct hdmi *hdmi = NULL; struct msm_drm_private *priv = dev->dev_private; - struct platform_device *pdev = hdmi_pdev; + struct platform_device *pdev = priv->hdmi_pdev; struct hdmi_platform_config *config; int i, ret; @@ -95,8 +93,6 @@ struct hdmi *hdmi_init(struct drm_device *dev, struct drm_encoder *encoder) kref_init(&hdmi->refcount); - get_device(&pdev->dev); - hdmi->dev = dev; hdmi->pdev = pdev; hdmi->config = config; @@ -249,17 +245,24 @@ fail: #include -static int hdmi_dev_probe(struct platform_device *pdev) +static void set_hdmi_pdev(struct drm_device *dev, + struct platform_device *pdev) +{ + struct msm_drm_private *priv = dev->dev_private; + priv->hdmi_pdev = pdev; +} + +static int hdmi_bind(struct device *dev, struct device *master, void *data) { static struct hdmi_platform_config config = {}; #ifdef CONFIG_OF - struct device_node *of_node = pdev->dev.of_node; + struct device_node *of_node = dev->of_node; int get_gpio(const char *name) { int gpio = of_get_named_gpio(of_node, name, 0); if (gpio < 0) { - dev_err(&pdev->dev, "failed to get gpio: %s (%d)\n", + dev_err(dev, "failed to get gpio: %s (%d)\n", name, gpio); gpio = -1; } @@ -336,14 +339,30 @@ static int hdmi_dev_probe(struct platform_device *pdev) config.mux_sel_gpio = -1; } #endif - pdev->dev.platform_data = &config; - hdmi_pdev = pdev; + dev->platform_data = &config; + set_hdmi_pdev(dev_get_drvdata(master), to_platform_device(dev)); return 0; } +static void hdmi_unbind(struct device *dev, struct device *master, + void *data) +{ + set_hdmi_pdev(dev_get_drvdata(master), NULL); +} + +static const struct component_ops hdmi_ops = { + .bind = hdmi_bind, + .unbind = hdmi_unbind, +}; + +static int hdmi_dev_probe(struct platform_device *pdev) +{ + return component_add(&pdev->dev, &hdmi_ops); +} + static int hdmi_dev_remove(struct platform_device *pdev) { - hdmi_pdev = NULL; + component_del(&pdev->dev, &hdmi_ops); return 0; } @@ -351,7 +370,6 @@ static const struct of_device_id dt_match[] = { { .compatible = "qcom,hdmi-tx" }, {} }; -MODULE_DEVICE_TABLE(of, dt_match); static struct platform_driver hdmi_driver = { .probe = hdmi_dev_probe, diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index e6adafc..e79cfd0 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -56,6 +56,10 @@ static char *vram; MODULE_PARM_DESC(vram, "Configure VRAM size (for devices without IOMMU/GPUMMU"); module_param(vram, charp, 0); +/* + * Util/helpers: + */ + void __iomem *msm_ioremap(struct platform_device *pdev, const char *name, const char *dbgname) { @@ -143,6 +147,8 @@ static int msm_unload(struct drm_device *dev) priv->vram.paddr, &attrs); } + component_unbind_all(dev->dev, dev); + dev->dev_private = NULL; kfree(priv); @@ -175,6 +181,7 @@ static int msm_load(struct drm_device *dev, unsigned long flags) struct msm_kms *kms; int ret; + priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) { dev_err(dev->dev, "failed to allocate private data\n"); @@ -226,6 +233,13 @@ static int msm_load(struct drm_device *dev, unsigned long flags) (uint32_t)(priv->vram.paddr + size)); } + platform_set_drvdata(pdev, dev); + + /* Bind all our sub-components: */ + ret = component_bind_all(dev->dev, dev); + if (ret) + return ret; + switch (get_mdp_ver(pdev)) { case 4: kms = mdp4_kms_init(dev); @@ -281,8 +295,6 @@ static int msm_load(struct drm_device *dev, unsigned long flags) goto fail; } - platform_set_drvdata(pdev, dev); - #ifdef CONFIG_DRM_MSM_FBDEV priv->fbdev = msm_fbdev_init(dev); #endif @@ -819,18 +831,110 @@ static const struct dev_pm_ops msm_pm_ops = { }; /* + * Componentized driver support: + */ + +#ifdef CONFIG_OF +/* NOTE: the CONFIG_OF case duplicates the same code as exynos or imx + * (or probably any other).. so probably some room for some helpers + */ +static int compare_of(struct device *dev, void *data) +{ + return dev->of_node == data; +} + +static int msm_drm_add_components(struct device *master, struct master *m) +{ + struct device_node *np = master->of_node; + unsigned i; + int ret; + + for (i = 0; ; i++) { + struct device_node *node; + + node = of_parse_phandle(np, "connectors", i); + if (!node) + break; + + ret = component_master_add_child(m, compare_of, node); + of_node_put(node); + + if (ret) + return ret; + } + return 0; +} +#else +static int compare_dev(struct device *dev, void *data) +{ + return dev == data; +} + +static int msm_drm_add_components(struct device *master, struct master *m) +{ + /* For non-DT case, it kinda sucks. We don't actually have a way + * to know whether or not we are waiting for certain devices (or if + * they are simply not present). But for non-DT we only need to + * care about apq8064/apq8060/etc (all mdp4/a3xx): + */ + static const char *devnames[] = { + "hdmi_msm.0", "kgsl-3d0.0", + }; + int i; + + DBG("Adding components.."); + + for (i = 0; i < ARRAY_SIZE(devnames); i++) { + struct device *dev; + int ret; + + dev = bus_find_device_by_name(&platform_bus_type, + NULL, devnames[i]); + if (!dev) { + dev_info(master, "still waiting for %s\n", devnames[i]); + return -EPROBE_DEFER; + } + + ret = component_master_add_child(m, compare_dev, dev); + if (ret) { + DBG("could not add child: %d", ret); + return ret; + } + } + + return 0; +} +#endif + +static int msm_drm_bind(struct device *dev) +{ + return drm_platform_init(&msm_driver, to_platform_device(dev)); +} + +static void msm_drm_unbind(struct device *dev) +{ + drm_put_dev(platform_get_drvdata(to_platform_device(dev))); +} + +static const struct component_master_ops msm_drm_ops = { + .add_components = msm_drm_add_components, + .bind = msm_drm_bind, + .unbind = msm_drm_unbind, +}; + +/* * Platform driver: */ static int msm_pdev_probe(struct platform_device *pdev) { pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); - return drm_platform_init(&msm_driver, pdev); + return component_master_add(&pdev->dev, &msm_drm_ops); } static int msm_pdev_remove(struct platform_device *pdev) { - drm_put_dev(platform_get_drvdata(pdev)); + component_master_del(&pdev->dev, &msm_drm_ops); return 0; } diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 3d63269..9d10ee0 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -69,6 +70,9 @@ struct msm_drm_private { struct msm_kms *kms; + /* subordinate devices, if present: */ + struct platform_device *hdmi_pdev, *gpu_pdev; + /* when we have more than one 'msm_gpu' these need to be an array: */ struct msm_gpu *gpu; struct msm_file_private *lastctx; diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c index 2d9b9d7..f3edd28 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c +++ b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c @@ -124,6 +124,7 @@ dcb_outp_parse(struct nouveau_bios *bios, u8 idx, u8 *ver, u8 *len, struct dcb_output *outp) { u16 dcb = dcb_outp(bios, idx, ver, len); + memset(outp, 0x00, sizeof(*outp)); if (dcb) { if (*ver >= 0x20) { u32 conn = nv_ro32(bios, dcb + 0x00); diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c index a75c35c..165401c 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c @@ -24,13 +24,6 @@ #include "nv04.h" -static void -nv4c_mc_msi_rearm(struct nouveau_mc *pmc) -{ - struct nv04_mc_priv *priv = (void *)pmc; - nv_wr08(priv, 0x088050, 0xff); -} - struct nouveau_oclass * nv4c_mc_oclass = &(struct nouveau_mc_oclass) { .base.handle = NV_SUBDEV(MC, 0x4c), @@ -41,5 +34,4 @@ nv4c_mc_oclass = &(struct nouveau_mc_oclass) { .fini = _nouveau_mc_fini, }, .intr = nv04_mc_intr, - .msi_rearm = nv4c_mc_msi_rearm, }.base; diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.h b/drivers/gpu/drm/nouveau/nouveau_drm.h index 23ca7a5..74ed08a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.h +++ b/drivers/gpu/drm/nouveau/nouveau_drm.h @@ -10,7 +10,7 @@ #define DRIVER_MAJOR 1 #define DRIVER_MINOR 1 -#define DRIVER_PATCHLEVEL 1 +#define DRIVER_PATCHLEVEL 2 /* * 1.1.1: @@ -21,6 +21,8 @@ * to control registers on the MPs to enable performance counters, * and to control the warp error enable mask (OpenGL requires out of * bounds access to local memory to be silently ignored / return 0). + * 1.1.2: + * - fixes multiple bugs in flip completion events and timestamping */ #include diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c index 471347e..a92fb01 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vga.c +++ b/drivers/gpu/drm/nouveau/nouveau_vga.c @@ -100,7 +100,16 @@ void nouveau_vga_fini(struct nouveau_drm *drm) { struct drm_device *dev = drm->dev; + bool runtime = false; + + if (nouveau_runtime_pm == 1) + runtime = true; + if ((nouveau_runtime_pm == -1) && (nouveau_is_optimus() || nouveau_is_v1_dsm())) + runtime = true; + vga_switcheroo_unregister_client(dev->pdev); + if (runtime && nouveau_is_v1_dsm() && !nouveau_is_optimus()) + vga_switcheroo_fini_domain_pm_ops(drm->dev->dev); vga_client_register(dev->pdev, NULL, NULL, NULL); } diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c index f926b4c..56c6055 100644 --- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c +++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c @@ -199,7 +199,7 @@ static struct dmm_txn *dmm_txn_init(struct dmm *dmm, struct tcm *tcm) static void dmm_txn_append(struct dmm_txn *txn, struct pat_area *area, struct page **pages, uint32_t npages, uint32_t roll) { - dma_addr_t pat_pa = 0; + dma_addr_t pat_pa = 0, data_pa = 0; uint32_t *data; struct pat *pat; struct refill_engine *engine = txn->engine_handle; @@ -223,7 +223,9 @@ static void dmm_txn_append(struct dmm_txn *txn, struct pat_area *area, .lut_id = engine->tcm->lut_id, }; - data = alloc_dma(txn, 4*i, &pat->data_pa); + data = alloc_dma(txn, 4*i, &data_pa); + /* FIXME: what if data_pa is more than 32-bit ? */ + pat->data_pa = data_pa; while (i--) { int n = i + roll; diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index 5aec3e8..5fd3bab 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -791,7 +791,7 @@ int omap_gem_get_paddr(struct drm_gem_object *obj, omap_obj->paddr = tiler_ssptr(block); omap_obj->block = block; - DBG("got paddr: %08x", omap_obj->paddr); + DBG("got paddr: %pad", &omap_obj->paddr); } omap_obj->paddr_cnt++; @@ -988,9 +988,9 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m) off = drm_vma_node_start(&obj->vma_node); - seq_printf(m, "%08x: %2d (%2d) %08llx %08Zx (%2d) %p %4d", + seq_printf(m, "%08x: %2d (%2d) %08llx %pad (%2d) %p %4d", omap_obj->flags, obj->name, obj->refcount.refcount.counter, - off, omap_obj->paddr, omap_obj->paddr_cnt, + off, &omap_obj->paddr, omap_obj->paddr_cnt, omap_obj->vaddr, omap_obj->roll); if (omap_obj->flags & OMAP_BO_TILED) { @@ -1468,8 +1468,8 @@ void omap_gem_init(struct drm_device *dev) entry->paddr = tiler_ssptr(block); entry->block = block; - DBG("%d:%d: %dx%d: paddr=%08x stride=%d", i, j, w, h, - entry->paddr, + DBG("%d:%d: %dx%d: paddr=%pad stride=%d", i, j, w, h, + &entry->paddr, usergart[i].stride_pfn << PAGE_SHIFT); } } diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c index 046d5e6..5b62e21 100644 --- a/drivers/gpu/drm/omapdrm/omap_plane.c +++ b/drivers/gpu/drm/omapdrm/omap_plane.c @@ -142,8 +142,8 @@ static void omap_plane_pre_apply(struct omap_drm_apply *apply) DBG("%dx%d -> %dx%d (%d)", info->width, info->height, info->out_width, info->out_height, info->screen_width); - DBG("%d,%d %08x %08x", info->pos_x, info->pos_y, - info->paddr, info->p_uv_addr); + DBG("%d,%d %pad %pad", info->pos_x, info->pos_y, + &info->paddr, &info->p_uv_addr); /* TODO: */ ilace = false; diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c index eb89653..c5e96a3 100644 --- a/drivers/gpu/drm/qxl/qxl_cmd.c +++ b/drivers/gpu/drm/qxl/qxl_cmd.c @@ -505,6 +505,7 @@ int qxl_hw_surface_alloc(struct qxl_device *qdev, cmd = (struct qxl_surface_cmd *)qxl_release_map(qdev, release); cmd->type = QXL_SURFACE_CMD_CREATE; + cmd->flags = QXL_SURF_FLAG_KEEP_DATA; cmd->u.surface_create.format = surf->surf.format; cmd->u.surface_create.width = surf->surf.width; cmd->u.surface_create.height = surf->surf.height; diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 798bde2..8e3267a 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -136,9 +136,35 @@ static int qxl_add_monitors_config_modes(struct drm_connector *connector, *pwidth = head->width; *pheight = head->height; drm_mode_probed_add(connector, mode); + /* remember the last custom size for mode validation */ + qdev->monitors_config_width = mode->hdisplay; + qdev->monitors_config_height = mode->vdisplay; return 1; } +static struct mode_size { + int w; + int h; +} common_modes[] = { + { 640, 480}, + { 720, 480}, + { 800, 600}, + { 848, 480}, + {1024, 768}, + {1152, 768}, + {1280, 720}, + {1280, 800}, + {1280, 854}, + {1280, 960}, + {1280, 1024}, + {1440, 900}, + {1400, 1050}, + {1680, 1050}, + {1600, 1200}, + {1920, 1080}, + {1920, 1200} +}; + static int qxl_add_common_modes(struct drm_connector *connector, unsigned pwidth, unsigned pheight) @@ -146,29 +172,6 @@ static int qxl_add_common_modes(struct drm_connector *connector, struct drm_device *dev = connector->dev; struct drm_display_mode *mode = NULL; int i; - struct mode_size { - int w; - int h; - } common_modes[] = { - { 640, 480}, - { 720, 480}, - { 800, 600}, - { 848, 480}, - {1024, 768}, - {1152, 768}, - {1280, 720}, - {1280, 800}, - {1280, 854}, - {1280, 960}, - {1280, 1024}, - {1440, 900}, - {1400, 1050}, - {1680, 1050}, - {1600, 1200}, - {1920, 1080}, - {1920, 1200} - }; - for (i = 0; i < ARRAY_SIZE(common_modes); i++) { mode = drm_cvt_mode(dev, common_modes[i].w, common_modes[i].h, 60, false, false, false); @@ -523,7 +526,6 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc, struct qxl_framebuffer *qfb; struct qxl_bo *bo, *old_bo = NULL; struct qxl_crtc *qcrtc = to_qxl_crtc(crtc); - uint32_t width, height, base_offset; bool recreate_primary = false; int ret; int surf_id; @@ -553,9 +555,10 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc, if (qcrtc->index == 0) recreate_primary = true; - width = mode->hdisplay; - height = mode->vdisplay; - base_offset = 0; + if (bo->surf.stride * bo->surf.height > qdev->vram_size) { + DRM_ERROR("Mode doesn't fit in vram size (vgamem)"); + return -EINVAL; + } ret = qxl_bo_reserve(bo, false); if (ret != 0) @@ -569,10 +572,10 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc, if (recreate_primary) { qxl_io_destroy_primary(qdev); qxl_io_log(qdev, - "recreate primary: %dx%d (was %dx%d,%d,%d)\n", - width, height, bo->surf.width, - bo->surf.height, bo->surf.stride, bo->surf.format); - qxl_io_create_primary(qdev, base_offset, bo); + "recreate primary: %dx%d,%d,%d\n", + bo->surf.width, bo->surf.height, + bo->surf.stride, bo->surf.format); + qxl_io_create_primary(qdev, 0, bo); bo->is_primary = true; surf_id = 0; } else { @@ -753,11 +756,22 @@ static int qxl_conn_get_modes(struct drm_connector *connector) static int qxl_conn_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct drm_device *ddev = connector->dev; + struct qxl_device *qdev = ddev->dev_private; + int i; + /* TODO: is this called for user defined modes? (xrandr --add-mode) * TODO: check that the mode fits in the framebuffer */ - DRM_DEBUG("%s: %dx%d status=%d\n", mode->name, mode->hdisplay, - mode->vdisplay, mode->status); - return MODE_OK; + + if(qdev->monitors_config_width == mode->hdisplay && + qdev->monitors_config_height == mode->vdisplay) + return MODE_OK; + + for (i = 0; i < ARRAY_SIZE(common_modes); i++) { + if (common_modes[i].w == mode->hdisplay && common_modes[i].h == mode->vdisplay) + return MODE_OK; + } + return MODE_BAD; } static struct drm_encoder *qxl_best_encoder(struct drm_connector *connector) diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 36ed40b..8aa077c 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -325,6 +325,8 @@ struct qxl_device { struct work_struct fb_work; struct drm_property *hotplug_mode_update_property; + int monitors_config_width; + int monitors_config_height; }; /* forward declaration for QXL_INFO_IO */ diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c index 0bb86e6..56a13a9 100644 --- a/drivers/gpu/drm/qxl/qxl_ioctl.c +++ b/drivers/gpu/drm/qxl/qxl_ioctl.c @@ -122,8 +122,10 @@ static struct qxl_bo *qxlhw_handle_to_bo(struct qxl_device *qdev, qobj = gem_to_qxl_bo(gobj); ret = qxl_release_list_add(release, qobj); - if (ret) + if (ret) { + drm_gem_object_unreference_unlocked(gobj); return NULL; + } return qobj; } diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index 0cca5f2..0db3e20 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -330,8 +330,10 @@ atombios_set_crtc_dtd_timing(struct drm_crtc *crtc, misc |= ATOM_COMPOSITESYNC; if (mode->flags & DRM_MODE_FLAG_INTERLACE) misc |= ATOM_INTERLACE; - if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + if (mode->flags & DRM_MODE_FLAG_DBLCLK) misc |= ATOM_DOUBLE_CLOCK_MODE; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + misc |= ATOM_H_REPLICATIONBY2 | ATOM_V_REPLICATIONBY2; args.susModeMiscInfo.usAccess = cpu_to_le16(misc); args.ucCRTC = radeon_crtc->crtc_id; @@ -374,8 +376,10 @@ static void atombios_crtc_set_timing(struct drm_crtc *crtc, misc |= ATOM_COMPOSITESYNC; if (mode->flags & DRM_MODE_FLAG_INTERLACE) misc |= ATOM_INTERLACE; - if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + if (mode->flags & DRM_MODE_FLAG_DBLCLK) misc |= ATOM_DOUBLE_CLOCK_MODE; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) + misc |= ATOM_H_REPLICATIONBY2 | ATOM_V_REPLICATIONBY2; args.susModeMiscInfo.usAccess = cpu_to_le16(misc); args.ucCRTC = radeon_crtc->crtc_id; @@ -1306,6 +1310,9 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc, (x << 16) | y); viewport_w = crtc->mode.hdisplay; viewport_h = (crtc->mode.vdisplay + 1) & ~1; + if ((rdev->family >= CHIP_BONAIRE) && + (crtc->mode.flags & DRM_MODE_FLAG_INTERLACE)) + viewport_h *= 2; WREG32(EVERGREEN_VIEWPORT_SIZE + radeon_crtc->crtc_offset, (viewport_w << 16) | viewport_h); diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c index 5727dbd..b4dbaded 100644 --- a/drivers/gpu/drm/radeon/atombios_dp.c +++ b/drivers/gpu/drm/radeon/atombios_dp.c @@ -576,6 +576,10 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector, struct radeon_connector_atom_dig *dig_connector; int dp_clock; + if ((mode->clock > 340000) && + (!radeon_connector_is_dp12_capable(connector))) + return MODE_CLOCK_HIGH; + if (!radeon_connector->con_priv) return MODE_CLOCK_HIGH; dig_connector = radeon_connector->con_priv; diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index 5fa854c..c7c2856 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -851,6 +851,9 @@ static int ci_set_thermal_temperature_range(struct radeon_device *rdev, WREG32_SMC(CG_THERMAL_CTRL, tmp); #endif + rdev->pm.dpm.thermal.min_temp = low_temp; + rdev->pm.dpm.thermal.max_temp = high_temp; + return 0; } @@ -922,7 +925,18 @@ static void ci_get_leakage_voltages(struct radeon_device *rdev) pi->vddc_leakage.count = 0; pi->vddci_leakage.count = 0; - if (radeon_atom_get_leakage_id_from_vbios(rdev, &leakage_id) == 0) { + if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_EVV) { + for (i = 0; i < CISLANDS_MAX_LEAKAGE_COUNT; i++) { + virtual_voltage_id = ATOM_VIRTUAL_VOLTAGE_ID0 + i; + if (radeon_atom_get_voltage_evv(rdev, virtual_voltage_id, &vddc) != 0) + continue; + if (vddc != 0 && vddc != virtual_voltage_id) { + pi->vddc_leakage.actual_voltage[pi->vddc_leakage.count] = vddc; + pi->vddc_leakage.leakage_id[pi->vddc_leakage.count] = virtual_voltage_id; + pi->vddc_leakage.count++; + } + } + } else if (radeon_atom_get_leakage_id_from_vbios(rdev, &leakage_id) == 0) { for (i = 0; i < CISLANDS_MAX_LEAKAGE_COUNT; i++) { virtual_voltage_id = ATOM_VIRTUAL_VOLTAGE_ID0 + i; if (radeon_atom_get_leakage_vddc_based_on_leakage_params(rdev, &vddc, &vddci, @@ -4719,7 +4733,7 @@ void ci_dpm_disable(struct radeon_device *rdev) ci_enable_spread_spectrum(rdev, false); ci_enable_auto_throttle_source(rdev, RADEON_DPM_AUTO_THROTTLE_SRC_THERMAL, false); ci_stop_dpm(rdev); - ci_enable_ds_master_switch(rdev, true); + ci_enable_ds_master_switch(rdev, false); ci_enable_ulv(rdev, false); ci_clear_vc(rdev); ci_reset_to_default(rdev); diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index 270f68a..2fd2fb3 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -2219,6 +2219,7 @@ static void cik_tiling_mode_table_init(struct radeon_device *rdev) gb_tile_moden = 0; break; } + rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden; WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden); } } else if (num_pipe_configs == 8) { @@ -3230,6 +3231,7 @@ static void cik_gpu_init(struct radeon_device *rdev) (rdev->pdev->device == 0x130B) || (rdev->pdev->device == 0x130E) || (rdev->pdev->device == 0x1315) || + (rdev->pdev->device == 0x1318) || (rdev->pdev->device == 0x131B)) { rdev->config.cik.max_cu_per_sh = 4; rdev->config.cik.max_backends_per_se = 1; @@ -3556,7 +3558,21 @@ void cik_fence_gfx_ring_emit(struct radeon_device *rdev, struct radeon_ring *ring = &rdev->ring[fence->ring]; u64 addr = rdev->fence_drv[fence->ring].gpu_addr; - /* EVENT_WRITE_EOP - flush caches, send int */ + /* Workaround for cache flush problems. First send a dummy EOP + * event down the pipe with seq one below. + */ + radeon_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4)); + radeon_ring_write(ring, (EOP_TCL1_ACTION_EN | + EOP_TC_ACTION_EN | + EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) | + EVENT_INDEX(5))); + radeon_ring_write(ring, addr & 0xfffffffc); + radeon_ring_write(ring, (upper_32_bits(addr) & 0xffff) | + DATA_SEL(1) | INT_SEL(0)); + radeon_ring_write(ring, fence->seq - 1); + radeon_ring_write(ring, 0); + + /* Then send the real EOP event down the pipe. */ radeon_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4)); radeon_ring_write(ring, (EOP_TCL1_ACTION_EN | EOP_TC_ACTION_EN | @@ -3934,8 +3950,8 @@ static int cik_cp_gfx_start(struct radeon_device *rdev) /* init the CE partitions. CE only used for gfx on CIK */ radeon_ring_write(ring, PACKET3(PACKET3_SET_BASE, 2)); radeon_ring_write(ring, PACKET3_BASE_INDEX(CE_PARTITION_BASE)); - radeon_ring_write(ring, 0xc000); - radeon_ring_write(ring, 0xc000); + radeon_ring_write(ring, 0x8000); + radeon_ring_write(ring, 0x8000); /* setup clear context state */ radeon_ring_write(ring, PACKET3(PACKET3_PREAMBLE_CNTL, 0)); @@ -4132,6 +4148,31 @@ void cik_compute_set_wptr(struct radeon_device *rdev, WDOORBELL32(ring->doorbell_index, ring->wptr); } +static void cik_compute_stop(struct radeon_device *rdev, + struct radeon_ring *ring) +{ + u32 j, tmp; + + cik_srbm_select(rdev, ring->me, ring->pipe, ring->queue, 0); + /* Disable wptr polling. */ + tmp = RREG32(CP_PQ_WPTR_POLL_CNTL); + tmp &= ~WPTR_POLL_EN; + WREG32(CP_PQ_WPTR_POLL_CNTL, tmp); + /* Disable HQD. */ + if (RREG32(CP_HQD_ACTIVE) & 1) { + WREG32(CP_HQD_DEQUEUE_REQUEST, 1); + for (j = 0; j < rdev->usec_timeout; j++) { + if (!(RREG32(CP_HQD_ACTIVE) & 1)) + break; + udelay(1); + } + WREG32(CP_HQD_DEQUEUE_REQUEST, 0); + WREG32(CP_HQD_PQ_RPTR, 0); + WREG32(CP_HQD_PQ_WPTR, 0); + } + cik_srbm_select(rdev, 0, 0, 0, 0); +} + /** * cik_cp_compute_enable - enable/disable the compute CP MEs * @@ -4145,6 +4186,15 @@ static void cik_cp_compute_enable(struct radeon_device *rdev, bool enable) if (enable) WREG32(CP_MEC_CNTL, 0); else { + /* + * To make hibernation reliable we need to clear compute ring + * configuration before halting the compute ring. + */ + mutex_lock(&rdev->srbm_mutex); + cik_compute_stop(rdev,&rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX]); + cik_compute_stop(rdev,&rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX]); + mutex_unlock(&rdev->srbm_mutex); + WREG32(CP_MEC_CNTL, (MEC_ME1_HALT | MEC_ME2_HALT)); rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX].ready = false; rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX].ready = false; @@ -4390,7 +4440,7 @@ struct bonaire_mqd */ static int cik_cp_compute_resume(struct radeon_device *rdev) { - int r, i, idx; + int r, i, j, idx; u32 tmp; bool use_doorbell = true; u64 hqd_gpu_addr; @@ -4509,7 +4559,7 @@ static int cik_cp_compute_resume(struct radeon_device *rdev) mqd->queue_state.cp_hqd_pq_wptr= 0; if (RREG32(CP_HQD_ACTIVE) & 1) { WREG32(CP_HQD_DEQUEUE_REQUEST, 1); - for (i = 0; i < rdev->usec_timeout; i++) { + for (j = 0; j < rdev->usec_timeout; j++) { if (!(RREG32(CP_HQD_ACTIVE) & 1)) break; udelay(1); @@ -5344,7 +5394,7 @@ static int cik_pcie_gart_enable(struct radeon_device *rdev) */ /* set vm size, must be a multiple of 4 */ WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0); - WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn); + WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn - 1); for (i = 1; i < 16; i++) { if (i < 8) WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2), @@ -5543,12 +5593,13 @@ static void cik_vm_decode_fault(struct radeon_device *rdev, void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm) { struct radeon_ring *ring = &rdev->ring[ridx]; + int usepfp = (ridx == RADEON_RING_TYPE_GFX_INDEX); if (vm == NULL) return; radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); - radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) | + radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) | WRITE_DATA_DST_SEL(0))); if (vm->id < 8) { radeon_ring_write(ring, @@ -5598,7 +5649,7 @@ void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm) radeon_ring_write(ring, 1 << vm->id); /* compute doesn't have PFP */ - if (ridx == RADEON_RING_TYPE_GFX_INDEX) { + if (usepfp) { /* sync PFP to ME, otherwise we might get invalid PFP reads */ radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0)); radeon_ring_write(ring, 0x0); @@ -5876,6 +5927,7 @@ static void cik_enable_mgcg(struct radeon_device *rdev, bool enable) } orig = data = RREG32(RLC_CGTT_MGCG_OVERRIDE); + data |= 0x00000001; data &= 0xfffffffd; if (orig != data) WREG32(RLC_CGTT_MGCG_OVERRIDE, data); @@ -5907,7 +5959,7 @@ static void cik_enable_mgcg(struct radeon_device *rdev, bool enable) } } else { orig = data = RREG32(RLC_CGTT_MGCG_OVERRIDE); - data |= 0x00000002; + data |= 0x00000003; if (orig != data) WREG32(RLC_CGTT_MGCG_OVERRIDE, data); @@ -6805,7 +6857,6 @@ int cik_irq_set(struct radeon_device *rdev) u32 hpd1, hpd2, hpd3, hpd4, hpd5, hpd6; u32 grbm_int_cntl = 0; u32 dma_cntl, dma_cntl1; - u32 thermal_int; if (!rdev->irq.installed) { WARN(1, "Can't enable IRQ/MSI because no handler is installed\n"); @@ -6842,13 +6893,6 @@ int cik_irq_set(struct radeon_device *rdev) cp_m2p2 = RREG32(CP_ME2_PIPE2_INT_CNTL) & ~TIME_STAMP_INT_ENABLE; cp_m2p3 = RREG32(CP_ME2_PIPE3_INT_CNTL) & ~TIME_STAMP_INT_ENABLE; - if (rdev->flags & RADEON_IS_IGP) - thermal_int = RREG32_SMC(CG_THERMAL_INT_CTRL) & - ~(THERM_INTH_MASK | THERM_INTL_MASK); - else - thermal_int = RREG32_SMC(CG_THERMAL_INT) & - ~(THERM_INT_MASK_HIGH | THERM_INT_MASK_LOW); - /* enable CP interrupts on all rings */ if (atomic_read(&rdev->irq.ring_int[RADEON_RING_TYPE_GFX_INDEX])) { DRM_DEBUG("cik_irq_set: sw int gfx\n"); @@ -7006,14 +7050,6 @@ int cik_irq_set(struct radeon_device *rdev) hpd6 |= DC_HPDx_INT_EN; } - if (rdev->irq.dpm_thermal) { - DRM_DEBUG("dpm thermal\n"); - if (rdev->flags & RADEON_IS_IGP) - thermal_int |= THERM_INTH_MASK | THERM_INTL_MASK; - else - thermal_int |= THERM_INT_MASK_HIGH | THERM_INT_MASK_LOW; - } - WREG32(CP_INT_CNTL_RING0, cp_int_cntl); WREG32(SDMA0_CNTL + SDMA0_REGISTER_OFFSET, dma_cntl); @@ -7067,10 +7103,8 @@ int cik_irq_set(struct radeon_device *rdev) WREG32(DC_HPD5_INT_CONTROL, hpd5); WREG32(DC_HPD6_INT_CONTROL, hpd6); - if (rdev->flags & RADEON_IS_IGP) - WREG32_SMC(CG_THERMAL_INT_CTRL, thermal_int); - else - WREG32_SMC(CG_THERMAL_INT, thermal_int); + /* posting read */ + RREG32(SRBM_STATUS); return 0; } @@ -7270,6 +7304,7 @@ static inline u32 cik_get_ih_wptr(struct radeon_device *rdev) tmp = RREG32(IH_RB_CNTL); tmp |= IH_WPTR_OVERFLOW_CLEAR; WREG32(IH_RB_CNTL, tmp); + wptr &= ~RB_OVERFLOW; } return (wptr & rdev->ih.ptr_mask); } @@ -7776,6 +7811,7 @@ restart_ih: static int cik_startup(struct radeon_device *rdev) { struct radeon_ring *ring; + u32 nop; int r; /* enable pcie gen2/3 link */ @@ -7893,9 +7929,15 @@ static int cik_startup(struct radeon_device *rdev) } cik_irq_set(rdev); + if (rdev->family == CHIP_HAWAII) { + nop = RADEON_CP_PACKET2; + } else { + nop = PACKET3(PACKET3_NOP, 0x3FFF); + } + ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]; r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET, - PACKET3(PACKET3_NOP, 0x3FFF)); + nop); if (r) return r; @@ -7903,7 +7945,7 @@ static int cik_startup(struct radeon_device *rdev) /* type-2 packets are deprecated on MEC, use type-3 instead */ ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX]; r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP1_RPTR_OFFSET, - PACKET3(PACKET3_NOP, 0x3FFF)); + nop); if (r) return r; ring->me = 1; /* first MEC */ @@ -7914,7 +7956,7 @@ static int cik_startup(struct radeon_device *rdev) /* type-2 packets are deprecated on MEC, use type-3 instead */ ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX]; r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP2_RPTR_OFFSET, - PACKET3(PACKET3_NOP, 0x3FFF)); + nop); if (r) return r; /* dGPU only have 1 MEC */ @@ -8882,6 +8924,9 @@ void dce8_bandwidth_update(struct radeon_device *rdev) u32 num_heads = 0, lb_size; int i; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); for (i = 0; i < rdev->num_crtc; i++) { diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c index aac8f48..e590aec 100644 --- a/drivers/gpu/drm/radeon/cik_sdma.c +++ b/drivers/gpu/drm/radeon/cik_sdma.c @@ -266,6 +266,17 @@ static void cik_sdma_gfx_stop(struct radeon_device *rdev) } rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false; rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX].ready = false; + + /* FIXME use something else than big hammer but after few days can not + * seem to find good combination so reset SDMA blocks as it seems we + * do not shut them down properly. This fix hibernation and does not + * affect suspend to ram. + */ + WREG32(SRBM_SOFT_RESET, SOFT_RESET_SDMA | SOFT_RESET_SDMA1); + (void)RREG32(SRBM_SOFT_RESET); + udelay(50); + WREG32(SRBM_SOFT_RESET, 0); + (void)RREG32(SRBM_SOFT_RESET); } /** @@ -461,13 +472,6 @@ int cik_sdma_resume(struct radeon_device *rdev) { int r; - /* Reset dma */ - WREG32(SRBM_SOFT_RESET, SOFT_RESET_SDMA | SOFT_RESET_SDMA1); - RREG32(SRBM_SOFT_RESET); - udelay(50); - WREG32(SRBM_SOFT_RESET, 0); - RREG32(SRBM_SOFT_RESET); - r = cik_sdma_load_microcode(rdev); if (r) return r; diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 64108db..ee9f0b4 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -2362,6 +2362,9 @@ void evergreen_bandwidth_update(struct radeon_device *rdev) u32 num_heads = 0, lb_size; int i; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); for (i = 0; i < rdev->num_crtc; i++) { @@ -2570,6 +2573,7 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1); tmp |= EVERGREEN_CRTC_BLANK_DATA_EN; WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp); + WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0); } } else { tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]); @@ -4592,6 +4596,9 @@ int evergreen_irq_set(struct radeon_device *rdev) WREG32(AFMT_AUDIO_PACKET_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, afmt5); WREG32(AFMT_AUDIO_PACKET_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, afmt6); + /* posting read */ + RREG32(SRBM_STATUS); + return 0; } @@ -4763,6 +4770,7 @@ static u32 evergreen_get_ih_wptr(struct radeon_device *rdev) tmp = RREG32(IH_RB_CNTL); tmp |= IH_WPTR_OVERFLOW_CLEAR; WREG32(IH_RB_CNTL, tmp); + wptr &= ~RB_OVERFLOW; } return (wptr & rdev->ih.ptr_mask); } diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c index 351db36..c7c7bc5 100644 --- a/drivers/gpu/drm/radeon/kv_dpm.c +++ b/drivers/gpu/drm/radeon/kv_dpm.c @@ -1121,6 +1121,19 @@ void kv_dpm_enable_bapm(struct radeon_device *rdev, bool enable) } } +static void kv_enable_thermal_int(struct radeon_device *rdev, bool enable) +{ + u32 thermal_int; + + thermal_int = RREG32_SMC(CG_THERMAL_INT_CTRL); + if (enable) + thermal_int |= THERM_INTH_MASK | THERM_INTL_MASK; + else + thermal_int &= ~(THERM_INTH_MASK | THERM_INTL_MASK); + WREG32_SMC(CG_THERMAL_INT_CTRL, thermal_int); + +} + int kv_dpm_enable(struct radeon_device *rdev) { struct kv_power_info *pi = kv_get_pi(rdev); @@ -1232,8 +1245,7 @@ int kv_dpm_late_enable(struct radeon_device *rdev) DRM_ERROR("kv_set_thermal_temperature_range failed\n"); return ret; } - rdev->irq.dpm_thermal = true; - radeon_irq_set(rdev); + kv_enable_thermal_int(rdev, true); } /* powerdown unused blocks for now */ @@ -1261,6 +1273,7 @@ void kv_dpm_disable(struct radeon_device *rdev) kv_stop_dpm(rdev); kv_enable_ulv(rdev, false); kv_reset_am(rdev); + kv_enable_thermal_int(rdev, false); kv_update_current_ps(rdev, rdev->pm.dpm.boot_ps); } diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index bf6300c..392d94b 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -1073,12 +1073,12 @@ static void cayman_gpu_init(struct radeon_device *rdev) if ((rdev->config.cayman.max_backends_per_se == 1) && (rdev->flags & RADEON_IS_IGP)) { - if ((disabled_rb_mask & 3) == 1) { - /* RB0 disabled, RB1 enabled */ - tmp = 0x11111111; - } else { + if ((disabled_rb_mask & 3) == 2) { /* RB1 disabled, RB0 enabled */ tmp = 0x00000000; + } else { + /* RB0 disabled, RB1 enabled */ + tmp = 0x11111111; } } else { tmp = gb_addr_config & NUM_PIPES_MASK; @@ -1256,7 +1256,8 @@ static int cayman_pcie_gart_enable(struct radeon_device *rdev) */ for (i = 1; i < 8; i++) { WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR + (i << 2), 0); - WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2), rdev->vm_manager.max_pfn); + WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2), + rdev->vm_manager.max_pfn - 1); WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2), rdev->gart.table_addr >> 12); } diff --git a/drivers/gpu/drm/radeon/ni_dma.c b/drivers/gpu/drm/radeon/ni_dma.c index 7cf96b1..94fa49e 100644 --- a/drivers/gpu/drm/radeon/ni_dma.c +++ b/drivers/gpu/drm/radeon/ni_dma.c @@ -191,12 +191,6 @@ int cayman_dma_resume(struct radeon_device *rdev) u32 reg_offset, wb_offset; int i, r; - /* Reset dma */ - WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA | SOFT_RESET_DMA1); - RREG32(SRBM_SOFT_RESET); - udelay(50); - WREG32(SRBM_SOFT_RESET, 0); - for (i = 0; i < 2; i++) { if (i == 0) { ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX]; diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 3cc78bb..e28de20 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -742,6 +742,10 @@ int r100_irq_set(struct radeon_device *rdev) tmp |= RADEON_FP2_DETECT_MASK; } WREG32(RADEON_GEN_INT_CNTL, tmp); + + /* read back to post the write */ + RREG32(RADEON_GEN_INT_CNTL); + return 0; } @@ -3219,6 +3223,9 @@ void r100_bandwidth_update(struct radeon_device *rdev) uint32_t pixel_bytes1 = 0; uint32_t pixel_bytes2 = 0; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); if (rdev->mode_info.crtcs[0]->base.enabled) { diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index f28ab84..74a8a38 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -3647,6 +3647,9 @@ int r600_irq_set(struct radeon_device *rdev) WREG32(RV770_CG_THERMAL_INT, thermal_int); } + /* posting read */ + RREG32(R_000E50_SRBM_STATUS); + return 0; } @@ -3795,6 +3798,7 @@ static u32 r600_get_ih_wptr(struct radeon_device *rdev) tmp = RREG32(IH_RB_CNTL); tmp |= IH_WPTR_OVERFLOW_CLEAR; WREG32(IH_RB_CNTL, tmp); + wptr &= ~RB_OVERFLOW; } return (wptr & rdev->ih.ptr_mask); } diff --git a/drivers/gpu/drm/radeon/r600_dma.c b/drivers/gpu/drm/radeon/r600_dma.c index b2d4c91..9949551 100644 --- a/drivers/gpu/drm/radeon/r600_dma.c +++ b/drivers/gpu/drm/radeon/r600_dma.c @@ -124,15 +124,6 @@ int r600_dma_resume(struct radeon_device *rdev) u32 rb_bufsz; int r; - /* Reset dma */ - if (rdev->family >= CHIP_RV770) - WREG32(SRBM_SOFT_RESET, RV770_SOFT_RESET_DMA); - else - WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA); - RREG32(SRBM_SOFT_RESET); - udelay(50); - WREG32(SRBM_SOFT_RESET, 0); - WREG32(DMA_SEM_INCOMPLETE_TIMER_CNTL, 0); WREG32(DMA_SEM_WAIT_FAIL_TIMER_CNTL, 0); diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c index 813db8d..e981082 100644 --- a/drivers/gpu/drm/radeon/r600_dpm.c +++ b/drivers/gpu/drm/radeon/r600_dpm.c @@ -187,7 +187,7 @@ u32 r600_dpm_get_vrefresh(struct radeon_device *rdev) list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { radeon_crtc = to_radeon_crtc(crtc); if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) { - vrefresh = radeon_crtc->hw_mode.vrefresh; + vrefresh = drm_mode_vrefresh(&radeon_crtc->hw_mode); break; } } @@ -1209,7 +1209,7 @@ int r600_parse_extended_power_table(struct radeon_device *rdev) (mode_info->atom_context->bios + data_offset + le16_to_cpu(ext_hdr->usPowerTuneTableOffset)); rdev->pm.dpm.dyn_state.cac_tdp_table->maximum_power_delivery_limit = - ppt->usMaximumPowerDeliveryLimit; + le16_to_cpu(ppt->usMaximumPowerDeliveryLimit); pt = &ppt->power_tune_table; } else { ATOM_PPLIB_POWERTUNE_Table *ppt = (ATOM_PPLIB_POWERTUNE_Table *) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 08e86f9..b837e9f 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -294,6 +294,9 @@ int radeon_atom_get_leakage_vddc_based_on_leakage_params(struct radeon_device *r u16 *vddc, u16 *vddci, u16 virtual_voltage_id, u16 vbios_voltage_id); +int radeon_atom_get_voltage_evv(struct radeon_device *rdev, + u16 virtual_voltage_id, + u16 *voltage); int radeon_atom_round_to_true_voltage(struct radeon_device *rdev, u8 voltage_type, u16 nominal_voltage, diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index 5600d4c..d625a14 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -335,6 +335,20 @@ static struct radeon_asic_ring r300_gfx_ring = { .set_wptr = &r100_gfx_set_wptr, }; +static struct radeon_asic_ring rv515_gfx_ring = { + .ib_execute = &r100_ring_ib_execute, + .emit_fence = &r300_fence_ring_emit, + .emit_semaphore = &r100_semaphore_ring_emit, + .cs_parse = &r300_cs_parse, + .ring_start = &rv515_ring_start, + .ring_test = &r100_ring_test, + .ib_test = &r100_ib_test, + .is_lockup = &r100_gpu_is_lockup, + .get_rptr = &r100_gfx_get_rptr, + .get_wptr = &r100_gfx_get_wptr, + .set_wptr = &r100_gfx_set_wptr, +}; + static struct radeon_asic r300_asic = { .init = &r300_init, .fini = &r300_fini, @@ -756,7 +770,7 @@ static struct radeon_asic rv515_asic = { .set_page = &rv370_pcie_gart_set_page, }, .ring = { - [RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring + [RADEON_RING_TYPE_GFX_INDEX] = &rv515_gfx_ring }, .irq = { .set = &rs600_irq_set, @@ -823,7 +837,7 @@ static struct radeon_asic r520_asic = { .set_page = &rv370_pcie_gart_set_page, }, .ring = { - [RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring + [RADEON_RING_TYPE_GFX_INDEX] = &rv515_gfx_ring }, .irq = { .set = &rs600_irq_set, @@ -1159,7 +1173,7 @@ static struct radeon_asic rs780_asic = { static struct radeon_asic_ring rv770_uvd_ring = { .ib_execute = &uvd_v1_0_ib_execute, .emit_fence = &uvd_v2_2_fence_emit, - .emit_semaphore = &uvd_v1_0_semaphore_emit, + .emit_semaphore = &uvd_v2_2_semaphore_emit, .cs_parse = &radeon_uvd_cs_parse, .ring_test = &uvd_v1_0_ring_test, .ib_test = &uvd_v1_0_ib_test, diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index ae637cf..f6e19ed 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -853,6 +853,10 @@ void uvd_v1_0_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib); int uvd_v2_2_resume(struct radeon_device *rdev); void uvd_v2_2_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence); +bool uvd_v2_2_semaphore_emit(struct radeon_device *rdev, + struct radeon_ring *ring, + struct radeon_semaphore *semaphore, + bool emit_wait); /* uvd v3.1 */ bool uvd_v3_1_semaphore_emit(struct radeon_device *rdev, diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 3084481..2fa3cf6 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -447,6 +447,13 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev, } } + /* Fujitsu D3003-S2 board lists DVI-I as DVI-I and VGA */ + if ((dev->pdev->device == 0x9805) && + (dev->pdev->subsystem_vendor == 0x1734) && + (dev->pdev->subsystem_device == 0x11bd)) { + if (*connector_type == DRM_MODE_CONNECTOR_VGA) + return false; + } return true; } @@ -1955,7 +1962,7 @@ static const char *thermal_controller_names[] = { "adm1032", "adm1030", "max6649", - "lm64", + "lm63", /* lm64 */ "f75375", "asc7xxx", }; @@ -1966,7 +1973,7 @@ static const char *pp_lib_thermal_controller_names[] = { "adm1032", "adm1030", "max6649", - "lm64", + "lm63", /* lm64 */ "f75375", "RV6xx", "RV770", @@ -2273,19 +2280,31 @@ static void radeon_atombios_add_pplib_thermal_controller(struct radeon_device *r (controller->ucFanParameters & ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); rdev->pm.int_thermal_type = THERMAL_TYPE_KV; - } else if ((controller->ucType == - ATOM_PP_THERMALCONTROLLER_EXTERNAL_GPIO) || - (controller->ucType == - ATOM_PP_THERMALCONTROLLER_ADT7473_WITH_INTERNAL) || - (controller->ucType == - ATOM_PP_THERMALCONTROLLER_EMC2103_WITH_INTERNAL)) { - DRM_INFO("Special thermal controller config\n"); + } else if (controller->ucType == + ATOM_PP_THERMALCONTROLLER_EXTERNAL_GPIO) { + DRM_INFO("External GPIO thermal controller %s fan control\n", + (controller->ucFanParameters & + ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_EXTERNAL_GPIO; + } else if (controller->ucType == + ATOM_PP_THERMALCONTROLLER_ADT7473_WITH_INTERNAL) { + DRM_INFO("ADT7473 with internal thermal controller %s fan control\n", + (controller->ucFanParameters & + ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_ADT7473_WITH_INTERNAL; + } else if (controller->ucType == + ATOM_PP_THERMALCONTROLLER_EMC2103_WITH_INTERNAL) { + DRM_INFO("EMC2103 with internal thermal controller %s fan control\n", + (controller->ucFanParameters & + ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_EMC2103_WITH_INTERNAL; } else if (controller->ucType < ARRAY_SIZE(pp_lib_thermal_controller_names)) { DRM_INFO("Possible %s thermal controller at 0x%02x %s fan control\n", pp_lib_thermal_controller_names[controller->ucType], controller->ucI2cAddress >> 1, (controller->ucFanParameters & ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_EXTERNAL; i2c_bus = radeon_lookup_i2c_gpio(rdev, controller->ucI2cLine); rdev->pm.i2c_bus = radeon_i2c_lookup(rdev, &i2c_bus); if (rdev->pm.i2c_bus) { @@ -3228,6 +3247,42 @@ int radeon_atom_get_leakage_vddc_based_on_leakage_params(struct radeon_device *r return 0; } +union get_voltage_info { + struct _GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2 in; + struct _GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 evv_out; +}; + +int radeon_atom_get_voltage_evv(struct radeon_device *rdev, + u16 virtual_voltage_id, + u16 *voltage) +{ + int index = GetIndexIntoMasterTable(COMMAND, GetVoltageInfo); + u32 entry_id; + u32 count = rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.count; + union get_voltage_info args; + + for (entry_id = 0; entry_id < count; entry_id++) { + if (rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].v == + virtual_voltage_id) + break; + } + + if (entry_id >= count) + return -EINVAL; + + args.in.ucVoltageType = VOLTAGE_TYPE_VDDC; + args.in.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE; + args.in.usVoltageLevel = cpu_to_le16(virtual_voltage_id); + args.in.ulSCLKFreq = + cpu_to_le32(rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].clk); + + atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); + + *voltage = le16_to_cpu(args.evv_out.usVoltageLevel); + + return 0; +} + int radeon_atom_get_voltage_gpio_settings(struct radeon_device *rdev, u16 voltage_level, u8 voltage_type, u32 *gpio_value, u32 *gpio_mask) diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index 9ab3097..c43335c 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -76,7 +76,7 @@ static bool igp_read_bios_from_vram(struct radeon_device *rdev) static bool radeon_read_bios(struct radeon_device *rdev) { - uint8_t __iomem *bios; + uint8_t __iomem *bios, val1, val2; size_t size; rdev->bios = NULL; @@ -86,15 +86,19 @@ static bool radeon_read_bios(struct radeon_device *rdev) return false; } - if (size == 0 || bios[0] != 0x55 || bios[1] != 0xaa) { + val1 = readb(&bios[0]); + val2 = readb(&bios[1]); + + if (size == 0 || val1 != 0x55 || val2 != 0xaa) { pci_unmap_rom(rdev->pdev, bios); return false; } - rdev->bios = kmemdup(bios, size, GFP_KERNEL); + rdev->bios = kzalloc(size, GFP_KERNEL); if (rdev->bios == NULL) { pci_unmap_rom(rdev->pdev, bios); return false; } + memcpy_fromio(rdev->bios, bios, size); pci_unmap_rom(rdev->pdev, bios); return true; } diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c index 6651177..79a2669 100644 --- a/drivers/gpu/drm/radeon/radeon_combios.c +++ b/drivers/gpu/drm/radeon/radeon_combios.c @@ -1255,10 +1255,15 @@ struct radeon_encoder_lvds *radeon_combios_get_lvds_info(struct radeon_encoder if ((RBIOS16(tmp) == lvds->native_mode.hdisplay) && (RBIOS16(tmp + 2) == lvds->native_mode.vdisplay)) { + u32 hss = (RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8; + + if (hss > lvds->native_mode.hdisplay) + hss = (10 - 1) * 8; + lvds->native_mode.htotal = lvds->native_mode.hdisplay + (RBIOS16(tmp + 17) - RBIOS16(tmp + 19)) * 8; lvds->native_mode.hsync_start = lvds->native_mode.hdisplay + - (RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8; + hss; lvds->native_mode.hsync_end = lvds->native_mode.hsync_start + (RBIOS8(tmp + 23) * 8); diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index 4d36b9e..17ae621 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -71,6 +71,11 @@ void radeon_connector_hotplug(struct drm_connector *connector) if (!radeon_hpd_sense(rdev, radeon_connector->hpd.hpd)) { drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF); } else if (radeon_dp_needs_link_train(radeon_connector)) { + /* Don't try to start link training before we + * have the dpcd */ + if (!radeon_dp_getdpcd(radeon_connector)) + return; + /* set it to OFF so that drm_helper_connector_dpms() * won't return immediately since the current state * is ON at this point. diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 7f2d6c0..2f2d2ce 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -179,11 +179,13 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) u32 ring = RADEON_CS_RING_GFX; s32 priority = 0; + INIT_LIST_HEAD(&p->validated); + if (!cs->num_chunks) { return 0; } + /* get chunks */ - INIT_LIST_HEAD(&p->validated); p->idx = 0; p->ib.sa_bo = NULL; p->ib.semaphore = NULL; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 0bf6f4a..129915e 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1314,7 +1314,7 @@ int radeon_device_init(struct radeon_device *rdev, r = radeon_init(rdev); if (r) - return r; + goto failed; r = radeon_ib_ring_tests(rdev); if (r) @@ -1334,7 +1334,22 @@ int radeon_device_init(struct radeon_device *rdev, radeon_agp_disable(rdev); r = radeon_init(rdev); if (r) - return r; + goto failed; + } + + /* + * Turks/Thames GPU will freeze whole laptop if DPM is not restarted + * after the CP ring have chew one packet at least. Hence here we stop + * and restart DPM after the radeon_ib_ring_tests(). + */ + if (rdev->pm.dpm_enabled && + (rdev->pm.pm_method == PM_METHOD_DPM) && + (rdev->family == CHIP_TURKS) && + (rdev->flags & RADEON_IS_MOBILITY)) { + mutex_lock(&rdev->pm.mutex); + radeon_dpm_disable(rdev); + radeon_dpm_enable(rdev); + mutex_unlock(&rdev->pm.mutex); } if ((radeon_testing & 1)) { @@ -1356,6 +1371,11 @@ int radeon_device_init(struct radeon_device *rdev, DRM_INFO("radeon: acceleration disabled, skipping benchmarks\n"); } return 0; + +failed: + if (runtime) + vga_switcheroo_fini_domain_pm_ops(rdev->dev); + return r; } static void radeon_debugfs_remove_files(struct radeon_device *rdev); @@ -1376,6 +1396,8 @@ void radeon_device_fini(struct radeon_device *rdev) radeon_bo_evict_vram(rdev); radeon_fini(rdev); vga_switcheroo_unregister_client(rdev->pdev); + if (rdev->flags & RADEON_IS_PX) + vga_switcheroo_fini_domain_pm_ops(rdev->dev); vga_client_register(rdev->pdev, NULL, NULL, NULL); if (rdev->rio_mem) pci_iounmap(rdev->pdev, rdev->rio_mem); @@ -1600,7 +1622,6 @@ int radeon_gpu_reset(struct radeon_device *rdev) radeon_save_bios_scratch_regs(rdev); /* block TTM */ resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev); - radeon_pm_suspend(rdev); radeon_suspend(rdev); for (i = 0; i < RADEON_NUM_RINGS; ++i) { @@ -1646,9 +1667,24 @@ retry: } } - radeon_pm_resume(rdev); + if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) { + /* do dpm late init */ + r = radeon_pm_late_init(rdev); + if (r) { + rdev->pm.dpm_enabled = false; + DRM_ERROR("radeon_pm_late_init failed, disabling dpm\n"); + } + } else { + /* resume old pm late */ + radeon_pm_resume(rdev); + } + drm_helper_resume_force_mode(rdev->ddev); + /* set the power state here in case we are a PX system or headless */ + if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) + radeon_pm_compute_clocks(rdev); + ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched); if (r) { /* bad news, how to tell it to userspace ? */ diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c index a8f9b46..e609722 100644 --- a/drivers/gpu/drm/radeon/radeon_gart.c +++ b/drivers/gpu/drm/radeon/radeon_gart.c @@ -251,8 +251,10 @@ void radeon_gart_unbind(struct radeon_device *rdev, unsigned offset, } } } - mb(); - radeon_gart_tlb_flush(rdev); + if (rdev->gart.ptr) { + mb(); + radeon_gart_tlb_flush(rdev); + } } /** @@ -294,8 +296,10 @@ int radeon_gart_bind(struct radeon_device *rdev, unsigned offset, } } } - mb(); - radeon_gart_tlb_flush(rdev); + if (rdev->gart.ptr) { + mb(); + radeon_gart_tlb_flush(rdev); + } return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c index 089c9ff..f8b20e1 100644 --- a/drivers/gpu/drm/radeon/radeon_irq_kms.c +++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c @@ -79,10 +79,12 @@ static void radeon_hotplug_work_func(struct work_struct *work) struct drm_mode_config *mode_config = &dev->mode_config; struct drm_connector *connector; + mutex_lock(&mode_config->mutex); if (mode_config->num_connector) { list_for_each_entry(connector, &mode_config->connector_list, head) radeon_connector_hotplug(connector); } + mutex_unlock(&mode_config->mutex); /* Just fire off a uevent and let userspace tell us what to do */ drm_helper_hpd_irq_event(dev); } @@ -202,6 +204,16 @@ static bool radeon_msi_ok(struct radeon_device *rdev) if (rdev->flags & RADEON_IS_AGP) return false; + /* + * Older chips have a HW limitation, they can only generate 40 bits + * of address for "64-bit" MSIs which breaks on some platforms, notably + * IBM POWER servers, so we limit them + */ + if (rdev->family < CHIP_BONAIRE) { + dev_info(rdev->dev, "radeon: MSI limited to 32-bit\n"); + rdev->pdev->no_64bit_msi = 1; + } + /* force MSI on */ if (radeon_msi == 1) return true; diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index ea34a31..6bffe82 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -254,7 +254,14 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file } break; case RADEON_INFO_ACCEL_WORKING2: - *value = rdev->accel_working; + if (rdev->family == CHIP_HAWAII) { + if (rdev->accel_working) + *value = 2; + else + *value = 0; + } else { + *value = rdev->accel_working; + } break; case RADEON_INFO_TILING_CONFIG: if (rdev->family >= CHIP_BONAIRE) @@ -733,6 +740,8 @@ int radeon_get_vblank_timestamp_kms(struct drm_device *dev, int crtc, /* Get associated drm_crtc: */ drmcrtc = &rdev->mode_info.crtcs[crtc]->base; + if (!drmcrtc) + return -EINVAL; /* Helper routine in DRM core does all the work: */ return drm_calc_vbltimestamp_from_scanoutpos(dev, crtc, max_error, diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index f77d9d0..0095ee7 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -458,10 +458,6 @@ static ssize_t radeon_get_dpm_state(struct device *dev, struct radeon_device *rdev = ddev->dev_private; enum radeon_pm_state_type pm = rdev->pm.dpm.user_state; - if ((rdev->flags & RADEON_IS_PX) && - (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) - return snprintf(buf, PAGE_SIZE, "off\n"); - return snprintf(buf, PAGE_SIZE, "%s\n", (pm == POWER_STATE_TYPE_BATTERY) ? "battery" : (pm == POWER_STATE_TYPE_BALANCED) ? "balanced" : "performance"); @@ -475,11 +471,6 @@ static ssize_t radeon_set_dpm_state(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct radeon_device *rdev = ddev->dev_private; - /* Can't set dpm state when the card is off */ - if ((rdev->flags & RADEON_IS_PX) && - (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) - return -EINVAL; - mutex_lock(&rdev->pm.mutex); if (strncmp("battery", buf, strlen("battery")) == 0) rdev->pm.dpm.user_state = POWER_STATE_TYPE_BATTERY; @@ -493,7 +484,12 @@ static ssize_t radeon_set_dpm_state(struct device *dev, goto fail; } mutex_unlock(&rdev->pm.mutex); - radeon_pm_compute_clocks(rdev); + + /* Can't set dpm state when the card is off */ + if (!(rdev->flags & RADEON_IS_PX) || + (ddev->switch_power_state == DRM_SWITCH_POWER_ON)) + radeon_pm_compute_clocks(rdev); + fail: return count; } @@ -1264,8 +1260,39 @@ dpm_failed: return ret; } +struct radeon_dpm_quirk { + u32 chip_vendor; + u32 chip_device; + u32 subsys_vendor; + u32 subsys_device; +}; + +/* cards with dpm stability problems */ +static struct radeon_dpm_quirk radeon_dpm_quirk_list[] = { + /* TURKS - https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1386534 */ + { PCI_VENDOR_ID_ATI, 0x6759, 0x1682, 0x3195 }, + /* TURKS - https://bugzilla.kernel.org/show_bug.cgi?id=83731 */ + { PCI_VENDOR_ID_ATI, 0x6840, 0x1179, 0xfb81 }, + { 0, 0, 0, 0 }, +}; + int radeon_pm_init(struct radeon_device *rdev) { + struct radeon_dpm_quirk *p = radeon_dpm_quirk_list; + bool disable_dpm = false; + + /* Apply dpm quirks */ + while (p && p->chip_device != 0) { + if (rdev->pdev->vendor == p->chip_vendor && + rdev->pdev->device == p->chip_device && + rdev->pdev->subsystem_vendor == p->subsys_vendor && + rdev->pdev->subsystem_device == p->subsys_device) { + disable_dpm = true; + break; + } + ++p; + } + /* enable dpm on rv6xx+ */ switch (rdev->family) { case CHIP_RV610: @@ -1276,10 +1303,6 @@ int radeon_pm_init(struct radeon_device *rdev) case CHIP_RS780: case CHIP_RS880: case CHIP_RV770: - case CHIP_BARTS: - case CHIP_TURKS: - case CHIP_CAICOS: - case CHIP_CAYMAN: /* DPM requires the RLC, RV770+ dGPU requires SMC */ if (!rdev->rlc_fw) rdev->pm.pm_method = PM_METHOD_PROFILE; @@ -1303,6 +1326,10 @@ int radeon_pm_init(struct radeon_device *rdev) case CHIP_PALM: case CHIP_SUMO: case CHIP_SUMO2: + case CHIP_BARTS: + case CHIP_TURKS: + case CHIP_CAICOS: + case CHIP_CAYMAN: case CHIP_ARUBA: case CHIP_TAHITI: case CHIP_PITCAIRN: @@ -1320,6 +1347,8 @@ int radeon_pm_init(struct radeon_device *rdev) (!(rdev->flags & RADEON_IS_IGP)) && (!rdev->smc_fw)) rdev->pm.pm_method = PM_METHOD_PROFILE; + else if (disable_dpm && (radeon_dpm == -1)) + rdev->pm.pm_method = PM_METHOD_PROFILE; else if (radeon_dpm == 0) rdev->pm.pm_method = PM_METHOD_PROFILE; else diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c index 9006b32..eb7b600 100644 --- a/drivers/gpu/drm/radeon/radeon_semaphore.c +++ b/drivers/gpu/drm/radeon/radeon_semaphore.c @@ -34,7 +34,7 @@ int radeon_semaphore_create(struct radeon_device *rdev, struct radeon_semaphore **semaphore) { - uint32_t *cpu_addr; + uint64_t *cpu_addr; int i, r; *semaphore = kmalloc(sizeof(struct radeon_semaphore), GFP_KERNEL); diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 040a2a1..45a9a03 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -191,7 +191,7 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo, rbo = container_of(bo, struct radeon_bo, tbo); switch (bo->mem.mem_type) { case TTM_PL_VRAM: - if (rbo->rdev->ring[RADEON_RING_TYPE_GFX_INDEX].ready == false) + if (rbo->rdev->ring[radeon_copy_ring_index(rbo->rdev)].ready == false) radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_CPU); else radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT); diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 414e079..bcfac76 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -350,6 +350,29 @@ static int radeon_uvd_cs_msg_decode(uint32_t *msg, unsigned buf_sizes[]) return 0; } +static int radeon_uvd_validate_codec(struct radeon_cs_parser *p, + unsigned stream_type) +{ + switch (stream_type) { + case 0: /* H264 */ + case 1: /* VC1 */ + /* always supported */ + return 0; + + case 3: /* MPEG2 */ + case 4: /* MPEG4 */ + /* only since UVD 3 */ + if (p->rdev->family >= CHIP_PALM) + return 0; + + /* fall through */ + default: + DRM_ERROR("UVD codec not supported by hardware %d!\n", + stream_type); + return -EINVAL; + } +} + static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, unsigned offset, unsigned buf_sizes[]) { @@ -388,50 +411,70 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, return -EINVAL; } - if (msg_type == 1) { - /* it's a decode msg, calc buffer sizes */ - r = radeon_uvd_cs_msg_decode(msg, buf_sizes); - /* calc image size (width * height) */ - img_size = msg[6] * msg[7]; + switch (msg_type) { + case 0: + /* it's a create msg, calc image size (width * height) */ + img_size = msg[7] * msg[8]; + + r = radeon_uvd_validate_codec(p, msg[4]); + radeon_bo_kunmap(bo); + if (r) + return r; + + /* try to alloc a new handle */ + for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) { + if (atomic_read(&p->rdev->uvd.handles[i]) == handle) { + DRM_ERROR("Handle 0x%x already in use!\n", handle); + return -EINVAL; + } + + if (!atomic_cmpxchg(&p->rdev->uvd.handles[i], 0, handle)) { + p->rdev->uvd.filp[i] = p->filp; + p->rdev->uvd.img_size[i] = img_size; + return 0; + } + } + + DRM_ERROR("No more free UVD handles!\n"); + return -EINVAL; + + case 1: + /* it's a decode msg, validate codec and calc buffer sizes */ + r = radeon_uvd_validate_codec(p, msg[4]); + if (!r) + r = radeon_uvd_cs_msg_decode(msg, buf_sizes); radeon_bo_kunmap(bo); if (r) return r; - } else if (msg_type == 2) { + /* validate the handle */ + for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) { + if (atomic_read(&p->rdev->uvd.handles[i]) == handle) { + if (p->rdev->uvd.filp[i] != p->filp) { + DRM_ERROR("UVD handle collision detected!\n"); + return -EINVAL; + } + return 0; + } + } + + DRM_ERROR("Invalid UVD handle 0x%x!\n", handle); + return -ENOENT; + + case 2: /* it's a destroy msg, free the handle */ for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) atomic_cmpxchg(&p->rdev->uvd.handles[i], handle, 0); radeon_bo_kunmap(bo); return 0; - } else { - /* it's a create msg, calc image size (width * height) */ - img_size = msg[7] * msg[8]; - radeon_bo_kunmap(bo); - if (msg_type != 0) { - DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type); - return -EINVAL; - } - - /* it's a create msg, no special handling needed */ - } - - /* create or decode, validate the handle */ - for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) { - if (atomic_read(&p->rdev->uvd.handles[i]) == handle) - return 0; - } + default: - /* handle not found try to alloc a new one */ - for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) { - if (!atomic_cmpxchg(&p->rdev->uvd.handles[i], 0, handle)) { - p->rdev->uvd.filp[i] = p->filp; - p->rdev->uvd.img_size[i] = img_size; - return 0; - } + DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type); + return -EINVAL; } - DRM_ERROR("No more free UVD handles!\n"); + BUG(); return -EINVAL; } diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c index 95b693c..4261b38 100644 --- a/drivers/gpu/drm/radeon/rs600.c +++ b/drivers/gpu/drm/radeon/rs600.c @@ -700,6 +700,10 @@ int rs600_irq_set(struct radeon_device *rdev) WREG32(R_007D18_DC_HOT_PLUG_DETECT2_INT_CONTROL, hpd2); if (ASIC_IS_DCE2(rdev)) WREG32(R_007408_HDMI0_AUDIO_PACKET_CONTROL, hdmi0); + + /* posting read */ + RREG32(R_000040_GEN_INT_CNTL); + return 0; } @@ -890,6 +894,9 @@ void rs600_bandwidth_update(struct radeon_device *rdev) u32 d1mode_priority_a_cnt, d2mode_priority_a_cnt; /* FIXME: implement full support */ + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); if (rdev->mode_info.crtcs[0]->base.enabled) diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c index 3462b64..0a2d36e 100644 --- a/drivers/gpu/drm/radeon/rs690.c +++ b/drivers/gpu/drm/radeon/rs690.c @@ -579,6 +579,9 @@ void rs690_bandwidth_update(struct radeon_device *rdev) u32 d1mode_priority_a_cnt, d1mode_priority_b_cnt; u32 d2mode_priority_a_cnt, d2mode_priority_b_cnt; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); if (rdev->mode_info.crtcs[0]->base.enabled) diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 237dd29..b49965a 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -1276,6 +1276,9 @@ void rv515_bandwidth_update(struct radeon_device *rdev) struct drm_display_mode *mode0 = NULL; struct drm_display_mode *mode1 = NULL; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); if (rdev->mode_info.crtcs[0]->base.enabled) diff --git a/drivers/gpu/drm/radeon/rv770d.h b/drivers/gpu/drm/radeon/rv770d.h index 3cf1e29..9ef2064 100644 --- a/drivers/gpu/drm/radeon/rv770d.h +++ b/drivers/gpu/drm/radeon/rv770d.h @@ -989,6 +989,9 @@ ((n) & 0x3FFF) << 16) /* UVD */ +#define UVD_SEMA_ADDR_LOW 0xef00 +#define UVD_SEMA_ADDR_HIGH 0xef04 +#define UVD_SEMA_CMD 0xef08 #define UVD_GPCOM_VCPU_CMD 0xef0c #define UVD_GPCOM_VCPU_DATA0 0xef10 #define UVD_GPCOM_VCPU_DATA1 0xef14 diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index cb7508d..49da9fc 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -2227,6 +2227,9 @@ void dce6_bandwidth_update(struct radeon_device *rdev) u32 num_heads = 0, lb_size; int i; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); for (i = 0; i < rdev->num_crtc; i++) { @@ -4081,7 +4084,7 @@ static int si_pcie_gart_enable(struct radeon_device *rdev) /* empty context1-15 */ /* set vm size, must be a multiple of 4 */ WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0); - WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn); + WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn - 1); /* Assign the pt base to something valid for now; the pts used for * the VMs are determined by the application and setup and assigned * on the fly in the vm part of radeon_gart.c @@ -4810,7 +4813,7 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm) /* write new base address */ radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); - radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) | + radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) | WRITE_DATA_DST_SEL(0))); if (vm->id < 8) { @@ -5955,6 +5958,9 @@ int si_irq_set(struct radeon_device *rdev) WREG32(CG_THERMAL_INT, thermal_int); + /* posting read */ + RREG32(SRBM_STATUS); + return 0; } @@ -6098,6 +6104,7 @@ static inline u32 si_get_ih_wptr(struct radeon_device *rdev) tmp = RREG32(IH_RB_CNTL); tmp |= IH_WPTR_OVERFLOW_CLEAR; WREG32(IH_RB_CNTL, tmp); + wptr &= ~RB_OVERFLOW; } return (wptr & rdev->ih.ptr_mask); } @@ -6871,8 +6878,7 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk) WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_BYPASS_EN_MASK, ~UPLL_BYPASS_EN_MASK); if (!vclk || !dclk) { - /* keep the Bypass mode, put PLL to sleep */ - WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK); + /* keep the Bypass mode */ return 0; } @@ -6888,8 +6894,7 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk) /* set VCO_MODE to 1 */ WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_VCO_MODE_MASK, ~UPLL_VCO_MODE_MASK); - /* toggle UPLL_SLEEP to 1 then back to 0 */ - WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK); + /* disable sleep mode */ WREG32_P(CG_UPLL_FUNC_CNTL, 0, ~UPLL_SLEEP_MASK); /* deassert UPLL_RESET */ diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 0a2f5b4..c9053f7 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2900,6 +2900,24 @@ static int si_init_smc_spll_table(struct radeon_device *rdev) return ret; } +struct si_dpm_quirk { + u32 chip_vendor; + u32 chip_device; + u32 subsys_vendor; + u32 subsys_device; + u32 max_sclk; + u32 max_mclk; +}; + +/* cards with dpm stability problems */ +static struct si_dpm_quirk si_dpm_quirk_list[] = { + /* PITCAIRN - https://bugs.freedesktop.org/show_bug.cgi?id=76490 */ + { PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 }, + { 0, 0, 0, 0 }, +}; + static void si_apply_state_adjust_rules(struct radeon_device *rdev, struct radeon_ps *rps) { @@ -2910,7 +2928,22 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, u32 mclk, sclk; u16 vddc, vddci; u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc; + u32 max_sclk = 0, max_mclk = 0; int i; + struct si_dpm_quirk *p = si_dpm_quirk_list; + + /* Apply dpm quirks */ + while (p && p->chip_device != 0) { + if (rdev->pdev->vendor == p->chip_vendor && + rdev->pdev->device == p->chip_device && + rdev->pdev->subsystem_vendor == p->subsys_vendor && + rdev->pdev->subsystem_device == p->subsys_device) { + max_sclk = p->max_sclk; + max_mclk = p->max_mclk; + break; + } + ++p; + } if ((rdev->pm.dpm.new_active_crtc_count > 1) || ni_dpm_vblank_too_short(rdev)) @@ -2964,6 +2997,14 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, if (ps->performance_levels[i].mclk > max_mclk_vddc) ps->performance_levels[i].mclk = max_mclk_vddc; } + if (max_mclk) { + if (ps->performance_levels[i].mclk > max_mclk) + ps->performance_levels[i].mclk = max_mclk; + } + if (max_sclk) { + if (ps->performance_levels[i].sclk > max_sclk) + ps->performance_levels[i].sclk = max_sclk; + } } /* XXX validate the min clocks required for display */ @@ -6200,7 +6241,7 @@ static void si_parse_pplib_clock_info(struct radeon_device *rdev, if ((rps->class2 & ATOM_PPLIB_CLASSIFICATION2_ULV) && index == 0) { /* XXX disable for A0 tahiti */ - si_pi->ulv.supported = true; + si_pi->ulv.supported = false; si_pi->ulv.pl = *pl; si_pi->ulv.one_pcie_lane_in_ulv = false; si_pi->ulv.volt_change_delay = SISLANDS_ULVVOLTAGECHANGEDELAY_DFLT; diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c index 2da0e17..d9cfa09b 100644 --- a/drivers/gpu/drm/radeon/trinity_dpm.c +++ b/drivers/gpu/drm/radeon/trinity_dpm.c @@ -1877,7 +1877,16 @@ int trinity_dpm_init(struct radeon_device *rdev) for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++) pi->at[i] = TRINITY_AT_DFLT; - pi->enable_bapm = false; + /* There are stability issues reported on with + * bapm enabled when switching between AC and battery + * power. At the same time, some MSI boards hang + * if it's not enabled and dpm is enabled. Just enable + * it for MSI boards right now. + */ + if (rdev->pdev->subsystem_vendor == 0x1462) + pi->enable_bapm = true; + else + pi->enable_bapm = false; pi->enable_nbps_policy = true; pi->enable_sclk_ds = true; pi->enable_gfx_power_gating = true; diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c index c310a0a..0fa9009 100644 --- a/drivers/gpu/drm/radeon/uvd_v1_0.c +++ b/drivers/gpu/drm/radeon/uvd_v1_0.c @@ -365,18 +365,8 @@ bool uvd_v1_0_semaphore_emit(struct radeon_device *rdev, struct radeon_semaphore *semaphore, bool emit_wait) { - uint64_t addr = semaphore->gpu_addr; - - radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0)); - radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF); - - radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0)); - radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF); - - radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0)); - radeon_ring_write(ring, emit_wait ? 1 : 0); - - return true; + /* disable semaphores for UVD V1 hardware */ + return false; } /** diff --git a/drivers/gpu/drm/radeon/uvd_v2_2.c b/drivers/gpu/drm/radeon/uvd_v2_2.c index d177100..19ccb2a 100644 --- a/drivers/gpu/drm/radeon/uvd_v2_2.c +++ b/drivers/gpu/drm/radeon/uvd_v2_2.c @@ -60,6 +60,35 @@ void uvd_v2_2_fence_emit(struct radeon_device *rdev, } /** + * uvd_v2_2_semaphore_emit - emit semaphore command + * + * @rdev: radeon_device pointer + * @ring: radeon_ring pointer + * @semaphore: semaphore to emit commands for + * @emit_wait: true if we should emit a wait command + * + * Emit a semaphore command (either wait or signal) to the UVD ring. + */ +bool uvd_v2_2_semaphore_emit(struct radeon_device *rdev, + struct radeon_ring *ring, + struct radeon_semaphore *semaphore, + bool emit_wait) +{ + uint64_t addr = semaphore->gpu_addr; + + radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0)); + radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF); + + radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0)); + radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF); + + radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0)); + radeon_ring_write(ring, emit_wait ? 1 : 0); + + return true; +} + +/** * uvd_v2_2_resume - memory controller programming * * @rdev: radeon_device pointer diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c index 171a820..52b4711 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c @@ -84,6 +84,7 @@ static int modeset_init(struct drm_device *dev) if ((priv->num_encoders == 0) || (priv->num_connectors == 0)) { /* oh nos! */ dev_err(dev->dev, "no encoders/connectors found\n"); + drm_mode_config_cleanup(dev); return -ENXIO; } @@ -122,6 +123,7 @@ static int tilcdc_unload(struct drm_device *dev) struct tilcdc_drm_private *priv = dev->dev_private; struct tilcdc_module *mod, *cur; + drm_fbdev_cma_fini(priv->fbdev); drm_kms_helper_poll_fini(dev); drm_mode_config_cleanup(dev); drm_vblank_cleanup(dev); @@ -177,33 +179,37 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) dev->dev_private = priv; priv->wq = alloc_ordered_workqueue("tilcdc", 0); + if (!priv->wq) { + ret = -ENOMEM; + goto fail_free_priv; + } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) { dev_err(dev->dev, "failed to get memory resource\n"); ret = -EINVAL; - goto fail; + goto fail_free_wq; } priv->mmio = ioremap_nocache(res->start, resource_size(res)); if (!priv->mmio) { dev_err(dev->dev, "failed to ioremap\n"); ret = -ENOMEM; - goto fail; + goto fail_free_wq; } priv->clk = clk_get(dev->dev, "fck"); if (IS_ERR(priv->clk)) { dev_err(dev->dev, "failed to get functional clock\n"); ret = -ENODEV; - goto fail; + goto fail_iounmap; } priv->disp_clk = clk_get(dev->dev, "dpll_disp_ck"); if (IS_ERR(priv->clk)) { dev_err(dev->dev, "failed to get display clock\n"); ret = -ENODEV; - goto fail; + goto fail_put_clk; } #ifdef CONFIG_CPU_FREQ @@ -213,7 +219,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) CPUFREQ_TRANSITION_NOTIFIER); if (ret) { dev_err(dev->dev, "failed to register cpufreq notifier\n"); - goto fail; + goto fail_put_disp_clk; } #endif @@ -258,13 +264,13 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) ret = modeset_init(dev); if (ret < 0) { dev_err(dev->dev, "failed to initialize mode setting\n"); - goto fail; + goto fail_cpufreq_unregister; } ret = drm_vblank_init(dev, 1); if (ret < 0) { dev_err(dev->dev, "failed to initialize vblank\n"); - goto fail; + goto fail_mode_config_cleanup; } pm_runtime_get_sync(dev->dev); @@ -272,7 +278,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) pm_runtime_put_sync(dev->dev); if (ret < 0) { dev_err(dev->dev, "failed to install IRQ handler\n"); - goto fail; + goto fail_vblank_cleanup; } platform_set_drvdata(pdev, dev); @@ -288,13 +294,48 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) priv->fbdev = drm_fbdev_cma_init(dev, bpp, dev->mode_config.num_crtc, dev->mode_config.num_connector); + if (IS_ERR(priv->fbdev)) { + ret = PTR_ERR(priv->fbdev); + goto fail_irq_uninstall; + } drm_kms_helper_poll_init(dev); return 0; -fail: - tilcdc_unload(dev); +fail_irq_uninstall: + pm_runtime_get_sync(dev->dev); + drm_irq_uninstall(dev); + pm_runtime_put_sync(dev->dev); + +fail_vblank_cleanup: + drm_vblank_cleanup(dev); + +fail_mode_config_cleanup: + drm_mode_config_cleanup(dev); + +fail_cpufreq_unregister: + pm_runtime_disable(dev->dev); +#ifdef CONFIG_CPU_FREQ + cpufreq_unregister_notifier(&priv->freq_transition, + CPUFREQ_TRANSITION_NOTIFIER); +fail_put_disp_clk: + clk_put(priv->disp_clk); +#endif + +fail_put_clk: + clk_put(priv->clk); + +fail_iounmap: + iounmap(priv->mmio); + +fail_free_wq: + flush_workqueue(priv->wq); + destroy_workqueue(priv->wq); + +fail_free_priv: + dev->dev_private = NULL; + kfree(priv); return ret; } @@ -628,10 +669,10 @@ static int __init tilcdc_drm_init(void) static void __exit tilcdc_drm_fini(void) { DBG("fini"); - tilcdc_tfp410_fini(); - tilcdc_slave_fini(); - tilcdc_panel_fini(); platform_driver_unregister(&tilcdc_platform_driver); + tilcdc_panel_fini(); + tilcdc_slave_fini(); + tilcdc_tfp410_fini(); } late_initcall(tilcdc_drm_init); diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c index 86c6732..b085dcc 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c @@ -151,6 +151,7 @@ struct panel_connector { static void panel_connector_destroy(struct drm_connector *connector) { struct panel_connector *panel_connector = to_panel_connector(connector); + drm_sysfs_connector_remove(connector); drm_connector_cleanup(connector); kfree(panel_connector); } @@ -285,10 +286,8 @@ static void panel_destroy(struct tilcdc_module *mod) { struct panel_module *panel_mod = to_panel_module(mod); - if (panel_mod->timings) { + if (panel_mod->timings) display_timings_release(panel_mod->timings); - kfree(panel_mod->timings); - } tilcdc_module_cleanup(mod); kfree(panel_mod->info); diff --git a/drivers/gpu/drm/tilcdc/tilcdc_slave.c b/drivers/gpu/drm/tilcdc/tilcdc_slave.c index 595068b..2f83ffb 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_slave.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_slave.c @@ -166,6 +166,7 @@ struct slave_connector { static void slave_connector_destroy(struct drm_connector *connector) { struct slave_connector *slave_connector = to_slave_connector(connector); + drm_sysfs_connector_remove(connector); drm_connector_cleanup(connector); kfree(slave_connector); } diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c index c38b56b..ce75ac8 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c @@ -167,6 +167,7 @@ struct tfp410_connector { static void tfp410_connector_destroy(struct drm_connector *connector) { struct tfp410_connector *tfp410_connector = to_tfp410_connector(connector); + drm_sysfs_connector_remove(connector); drm_connector_cleanup(connector); kfree(tfp410_connector); } diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c index 863bef9..76329d2 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c @@ -297,9 +297,12 @@ static void ttm_pool_update_free_locked(struct ttm_page_pool *pool, * * @pool: to free the pages from * @free_all: If set to true will free all pages in pool + * @use_static: Safe to use static buffer **/ -static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free) +static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free, + bool use_static) { + static struct page *static_buf[NUM_PAGES_TO_ALLOC]; unsigned long irq_flags; struct page *p; struct page **pages_to_free; @@ -309,8 +312,11 @@ static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free) if (NUM_PAGES_TO_ALLOC < nr_free) npages_to_free = NUM_PAGES_TO_ALLOC; - pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), - GFP_KERNEL); + if (use_static) + pages_to_free = static_buf; + else + pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), + GFP_KERNEL); if (!pages_to_free) { pr_err("Failed to allocate memory for pool free operation\n"); return 0; @@ -373,7 +379,8 @@ restart: if (freed_pages) ttm_pages_put(pages_to_free, freed_pages); out: - kfree(pages_to_free); + if (pages_to_free != static_buf) + kfree(pages_to_free); return nr_free; } @@ -382,32 +389,33 @@ out: * * XXX: (dchinner) Deadlock warning! * - * ttm_page_pool_free() does memory allocation using GFP_KERNEL. that means - * this can deadlock when called a sc->gfp_mask that is not equal to - * GFP_KERNEL. - * * This code is crying out for a shrinker per pool.... */ static unsigned long ttm_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { - static atomic_t start_pool = ATOMIC_INIT(0); + static DEFINE_MUTEX(lock); + static unsigned start_pool; unsigned i; - unsigned pool_offset = atomic_add_return(1, &start_pool); + unsigned pool_offset; struct ttm_page_pool *pool; int shrink_pages = sc->nr_to_scan; unsigned long freed = 0; - pool_offset = pool_offset % NUM_POOLS; + if (!mutex_trylock(&lock)) + return SHRINK_STOP; + pool_offset = ++start_pool % NUM_POOLS; /* select start pool in round robin fashion */ for (i = 0; i < NUM_POOLS; ++i) { unsigned nr_free = shrink_pages; if (shrink_pages == 0) break; pool = &_manager->pools[(i + pool_offset)%NUM_POOLS]; - shrink_pages = ttm_page_pool_free(pool, nr_free); + /* OK to use static buffer since global mutex is held. */ + shrink_pages = ttm_page_pool_free(pool, nr_free, true); freed += nr_free - shrink_pages; } + mutex_unlock(&lock); return freed; } @@ -706,7 +714,7 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags, } spin_unlock_irqrestore(&pool->lock, irq_flags); if (npages) - ttm_page_pool_free(pool, npages); + ttm_page_pool_free(pool, npages, false); } /* @@ -845,8 +853,9 @@ void ttm_page_alloc_fini(void) pr_info("Finalizing pool allocator\n"); ttm_pool_mm_shrink_fini(_manager); + /* OK to use static buffer since global mutex is no longer used. */ for (i = 0; i < NUM_POOLS; ++i) - ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES); + ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES, true); kobject_put(&_manager->kobj); _manager = NULL; diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c index fb8259f..3dfa97d 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c @@ -411,9 +411,12 @@ static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page) * * @pool: to free the pages from * @nr_free: If set to true will free all pages in pool + * @use_static: Safe to use static buffer **/ -static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free) +static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free, + bool use_static) { + static struct page *static_buf[NUM_PAGES_TO_ALLOC]; unsigned long irq_flags; struct dma_page *dma_p, *tmp; struct page **pages_to_free; @@ -430,8 +433,11 @@ static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free) npages_to_free, nr_free); } #endif - pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), - GFP_KERNEL); + if (use_static) + pages_to_free = static_buf; + else + pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), + GFP_KERNEL); if (!pages_to_free) { pr_err("%s: Failed to allocate memory for pool free operation\n", @@ -501,7 +507,8 @@ restart: if (freed_pages) ttm_dma_pages_put(pool, &d_pages, pages_to_free, freed_pages); out: - kfree(pages_to_free); + if (pages_to_free != static_buf) + kfree(pages_to_free); return nr_free; } @@ -530,7 +537,8 @@ static void ttm_dma_free_pool(struct device *dev, enum pool_type type) if (pool->type != type) continue; /* Takes a spinlock.. */ - ttm_dma_page_pool_free(pool, FREE_ALL_PAGES); + /* OK to use static buffer since global mutex is held. */ + ttm_dma_page_pool_free(pool, FREE_ALL_PAGES, true); WARN_ON(((pool->npages_in_use + pool->npages_free) != 0)); /* This code path is called after _all_ references to the * struct device has been dropped - so nobody should be @@ -983,7 +991,7 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev) /* shrink pool if necessary (only on !is_cached pools)*/ if (npages) - ttm_dma_page_pool_free(pool, npages); + ttm_dma_page_pool_free(pool, npages, false); ttm->state = tt_unpopulated; } EXPORT_SYMBOL_GPL(ttm_dma_unpopulate); @@ -993,20 +1001,15 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate); * * XXX: (dchinner) Deadlock warning! * - * ttm_dma_page_pool_free() does GFP_KERNEL memory allocation, and so attention - * needs to be paid to sc->gfp_mask to determine if this can be done or not. - * GFP_KERNEL memory allocation in a GFP_ATOMIC reclaim context woul dbe really - * bad. - * * I'm getting sadder as I hear more pathetical whimpers about needing per-pool * shrinkers */ static unsigned long ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { - static atomic_t start_pool = ATOMIC_INIT(0); + static unsigned start_pool; unsigned idx = 0; - unsigned pool_offset = atomic_add_return(1, &start_pool); + unsigned pool_offset; unsigned shrink_pages = sc->nr_to_scan; struct device_pools *p; unsigned long freed = 0; @@ -1014,8 +1017,11 @@ ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) if (list_empty(&_manager->pools)) return SHRINK_STOP; - mutex_lock(&_manager->lock); - pool_offset = pool_offset % _manager->npools; + if (!mutex_trylock(&_manager->lock)) + return SHRINK_STOP; + if (!_manager->npools) + goto out; + pool_offset = ++start_pool % _manager->npools; list_for_each_entry(p, &_manager->pools, pools) { unsigned nr_free; @@ -1027,13 +1033,15 @@ ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) if (++idx < pool_offset) continue; nr_free = shrink_pages; - shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free); + /* OK to use static buffer since global mutex is held. */ + shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free, true); freed += nr_free - shrink_pages; pr_debug("%s: (%s:%d) Asked to shrink %d, have %d more to go\n", p->pool->dev_name, p->pool->name, current->pid, nr_free, shrink_pages); } +out: mutex_unlock(&_manager->lock); return freed; } @@ -1044,7 +1052,8 @@ ttm_dma_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc) struct device_pools *p; unsigned long count = 0; - mutex_lock(&_manager->lock); + if (!mutex_trylock(&_manager->lock)) + return 0; list_for_each_entry(p, &_manager->pools, pools) count += p->pool->npages_free; mutex_unlock(&_manager->lock); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 0083cbf..0771dcb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -688,7 +688,11 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) goto out_err0; } - if (unlikely(dev_priv->prim_bb_mem < dev_priv->vram_size)) + /* + * Limit back buffer size to VRAM size. Remove this once + * screen targets are implemented. + */ + if (dev_priv->prim_bb_mem > dev_priv->vram_size) dev_priv->prim_bb_mem = dev_priv->vram_size; mutex_unlock(&dev_priv->hw_mutex); @@ -729,32 +733,6 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) goto out_err1; } - ret = ttm_bo_init_mm(&dev_priv->bdev, TTM_PL_VRAM, - (dev_priv->vram_size >> PAGE_SHIFT)); - if (unlikely(ret != 0)) { - DRM_ERROR("Failed initializing memory manager for VRAM.\n"); - goto out_err2; - } - - dev_priv->has_gmr = true; - if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) || - refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR, - VMW_PL_GMR) != 0) { - DRM_INFO("No GMR memory available. " - "Graphics memory resources are very limited.\n"); - dev_priv->has_gmr = false; - } - - if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) { - dev_priv->has_mob = true; - if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_MOB, - VMW_PL_MOB) != 0) { - DRM_INFO("No MOB memory available. " - "3D will be disabled.\n"); - dev_priv->has_mob = false; - } - } - dev_priv->mmio_mtrr = arch_phys_wc_add(dev_priv->mmio_start, dev_priv->mmio_size); @@ -817,6 +795,33 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) goto out_no_fman; } + + ret = ttm_bo_init_mm(&dev_priv->bdev, TTM_PL_VRAM, + (dev_priv->vram_size >> PAGE_SHIFT)); + if (unlikely(ret != 0)) { + DRM_ERROR("Failed initializing memory manager for VRAM.\n"); + goto out_no_vram; + } + + dev_priv->has_gmr = true; + if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) || + refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR, + VMW_PL_GMR) != 0) { + DRM_INFO("No GMR memory available. " + "Graphics memory resources are very limited.\n"); + dev_priv->has_gmr = false; + } + + if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) { + dev_priv->has_mob = true; + if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_MOB, + VMW_PL_MOB) != 0) { + DRM_INFO("No MOB memory available. " + "3D will be disabled.\n"); + dev_priv->has_mob = false; + } + } + vmw_kms_save_vga(dev_priv); /* Start kms and overlay systems, needs fifo. */ @@ -842,6 +847,12 @@ out_no_fifo: vmw_kms_close(dev_priv); out_no_kms: vmw_kms_restore_vga(dev_priv); + if (dev_priv->has_mob) + (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); + if (dev_priv->has_gmr) + (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); + (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); +out_no_vram: vmw_fence_manager_takedown(dev_priv->fman); out_no_fman: if (dev_priv->capabilities & SVGA_CAP_IRQMASK) @@ -857,12 +868,6 @@ out_err4: iounmap(dev_priv->mmio_virt); out_err3: arch_phys_wc_del(dev_priv->mmio_mtrr); - if (dev_priv->has_mob) - (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); - if (dev_priv->has_gmr) - (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); - (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); -out_err2: (void)ttm_bo_device_release(&dev_priv->bdev); out_err1: vmw_ttm_global_release(dev_priv); @@ -892,6 +897,13 @@ static int vmw_driver_unload(struct drm_device *dev) } vmw_kms_close(dev_priv); vmw_overlay_close(dev_priv); + + if (dev_priv->has_mob) + (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); + if (dev_priv->has_gmr) + (void)ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); + (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); + vmw_fence_manager_takedown(dev_priv->fman); if (dev_priv->capabilities & SVGA_CAP_IRQMASK) drm_irq_uninstall(dev_priv->dev); @@ -903,11 +915,6 @@ static int vmw_driver_unload(struct drm_device *dev) ttm_object_device_release(&dev_priv->tdev); iounmap(dev_priv->mmio_virt); arch_phys_wc_del(dev_priv->mmio_mtrr); - if (dev_priv->has_mob) - (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); - if (dev_priv->has_gmr) - (void)ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); - (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); (void)ttm_bo_device_release(&dev_priv->bdev); vmw_ttm_global_release(dev_priv); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index a3480c1..9fe10d1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -2475,7 +2475,7 @@ int vmw_execbuf_process(struct drm_file *file_priv, ret = vmw_resources_validate(sw_context); if (unlikely(ret != 0)) - goto out_err; + goto out_err_nores; if (throttle_us) { ret = vmw_wait_lag(dev_priv, &dev_priv->fifo.marker_queue, @@ -2511,6 +2511,7 @@ int vmw_execbuf_process(struct drm_file *file_priv, vmw_resource_relocations_free(&sw_context->res_relocations); vmw_fifo_commit(dev_priv, command_size); + mutex_unlock(&dev_priv->binding_mutex); vmw_query_bo_switch_commit(dev_priv, sw_context); ret = vmw_execbuf_fence_commands(file_priv, dev_priv, @@ -2526,7 +2527,6 @@ int vmw_execbuf_process(struct drm_file *file_priv, DRM_ERROR("Fence submission error. Syncing.\n"); vmw_resource_list_unreserve(&sw_context->resource_list, false); - mutex_unlock(&dev_priv->binding_mutex); ttm_eu_fence_buffer_objects(&ticket, &sw_context->validate_nodes, (void *) fence); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 436b013..b65272d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -1049,6 +1049,8 @@ static int vmw_event_fence_action_create(struct drm_file *file_priv, if (ret != 0) goto out_no_queue; + return 0; + out_no_queue: event->base.destroy(&event->base); out_no_event: @@ -1124,17 +1126,10 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data, BUG_ON(fence == NULL); - if (arg->flags & DRM_VMW_FE_FLAG_REQ_TIME) - ret = vmw_event_fence_action_create(file_priv, fence, - arg->flags, - arg->user_data, - true); - else - ret = vmw_event_fence_action_create(file_priv, fence, - arg->flags, - arg->user_data, - true); - + ret = vmw_event_fence_action_create(file_priv, fence, + arg->flags, + arg->user_data, + true); if (unlikely(ret != 0)) { if (ret != -ERESTARTSYS) DRM_ERROR("Failed to attach event to fence.\n"); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c index 6ccd993..6eae14d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c @@ -180,8 +180,9 @@ void vmw_fifo_release(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo) mutex_lock(&dev_priv->hw_mutex); + vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC); while (vmw_read(dev_priv, SVGA_REG_BUSY) != 0) - vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC); + ; dev_priv->last_read_seqno = ioread32(fifo_mem + SVGA_FIFO_FENCE); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 8a65041..c8f8ecf 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1954,6 +1954,14 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }; int i; + u32 assumed_bpp = 2; + + /* + * If using screen objects, then assume 32-bpp because that's what the + * SVGA device is assuming + */ + if (dev_priv->sou_priv) + assumed_bpp = 4; /* Add preferred mode */ { @@ -1964,8 +1972,9 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, mode->vdisplay = du->pref_height; vmw_guess_mode_timing(mode); - if (vmw_kms_validate_mode_vram(dev_priv, mode->hdisplay * 2, - mode->vdisplay)) { + if (vmw_kms_validate_mode_vram(dev_priv, + mode->hdisplay * assumed_bpp, + mode->vdisplay)) { drm_mode_probed_add(connector, mode); } else { drm_mode_destroy(dev, mode); @@ -1987,7 +1996,8 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, bmode->vdisplay > max_height) continue; - if (!vmw_kms_validate_mode_vram(dev_priv, bmode->hdisplay * 2, + if (!vmw_kms_validate_mode_vram(dev_priv, + bmode->hdisplay * assumed_bpp, bmode->vdisplay)) continue; diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c index 6866448..37ac7b5 100644 --- a/drivers/gpu/vga/vga_switcheroo.c +++ b/drivers/gpu/vga/vga_switcheroo.c @@ -660,6 +660,12 @@ int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain * } EXPORT_SYMBOL(vga_switcheroo_init_domain_pm_ops); +void vga_switcheroo_fini_domain_pm_ops(struct device *dev) +{ + dev->pm_domain = NULL; +} +EXPORT_SYMBOL(vga_switcheroo_fini_domain_pm_ops); + static int vga_switcheroo_runtime_resume_hdmi_audio(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); diff --git a/drivers/hid/hid-cherry.c b/drivers/hid/hid-cherry.c index 1bdcccc..f745d2c 100644 --- a/drivers/hid/hid-cherry.c +++ b/drivers/hid/hid-cherry.c @@ -28,7 +28,7 @@ static __u8 *ch_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { - if (*rsize >= 17 && rdesc[11] == 0x3c && rdesc[12] == 0x02) { + if (*rsize >= 18 && rdesc[11] == 0x3c && rdesc[12] == 0x02) { hid_info(hdev, "fixing up Cherry Cymotion report descriptor\n"); rdesc[11] = rdesc[16] = 0xff; rdesc[12] = rdesc[17] = 0x03; diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 7cd42ea..d92c7d9 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1743,6 +1743,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_I405X) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X) }, + { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X) }, { HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD) }, { HID_USB_DEVICE(USB_VENDOR_ID_LCPOWER, USB_DEVICE_ID_LCPOWER_LC1000 ) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 6e12cd0..4850da3 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -292,6 +292,11 @@ #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_73F7 0x73f7 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001 0xa001 +#define USB_VENDOR_ID_ELAN 0x04f3 +#define USB_DEVICE_ID_ELAN_TOUCHSCREEN 0x0089 +#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B 0x009b +#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F 0x016f + #define USB_VENDOR_ID_ELECOM 0x056e #define USB_DEVICE_ID_ELECOM_BM084 0x0061 @@ -506,6 +511,7 @@ #define USB_DEVICE_ID_KYE_GPEN_560 0x5003 #define USB_DEVICE_ID_KYE_EASYPEN_I405X 0x5010 #define USB_DEVICE_ID_KYE_MOUSEPEN_I608X 0x5011 +#define USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2 0x501a #define USB_DEVICE_ID_KYE_EASYPEN_M610X 0x5013 #define USB_VENDOR_ID_LABTEC 0x1020 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index a713e62..a413f76 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -312,6 +312,9 @@ static const struct hid_device_id hid_battery_quirks[] = { USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, + USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO), + HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, {} @@ -1063,6 +1066,23 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct return; } + /* + * Ignore reports for absolute data if the data didn't change. This is + * not only an optimization but also fixes 'dead' key reports. Some + * RollOver implementations for localized keys (like BACKSLASH/PIPE; HID + * 0x31 and 0x32) report multiple keys, even though a localized keyboard + * can only have one of them physically available. The 'dead' keys + * report constant 0. As all map to the same keycode, they'd confuse + * the input layer. If we filter the 'dead' keys on the HID level, we + * skip the keycode translation and only forward real events. + */ + if (!(field->flags & (HID_MAIN_ITEM_RELATIVE | + HID_MAIN_ITEM_BUFFERED_BYTE)) && + (field->flags & HID_MAIN_ITEM_VARIABLE) && + usage->usage_index < field->maxusage && + value == field->value[usage->usage_index]) + return; + /* report the usage code as scancode if the key status has changed */ if (usage->type == EV_KEY && !!test_bit(usage->code, input->key) != value) input_event(input, EV_MSC, MSC_SCAN, usage->hid); diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c index e776963..158fcf5 100644 --- a/drivers/hid/hid-kye.c +++ b/drivers/hid/hid-kye.c @@ -300,7 +300,7 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc, * - change the button usage range to 4-7 for the extra * buttons */ - if (*rsize >= 74 && + if (*rsize >= 75 && rdesc[61] == 0x05 && rdesc[62] == 0x08 && rdesc[63] == 0x19 && rdesc[64] == 0x08 && rdesc[65] == 0x29 && rdesc[66] == 0x0f && @@ -323,6 +323,7 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc, } break; case USB_DEVICE_ID_KYE_MOUSEPEN_I608X: + case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2: if (*rsize == MOUSEPEN_I608X_RDESC_ORIG_SIZE) { rdesc = mousepen_i608x_rdesc_fixed; *rsize = sizeof(mousepen_i608x_rdesc_fixed); @@ -415,6 +416,7 @@ static int kye_probe(struct hid_device *hdev, const struct hid_device_id *id) switch (id->product) { case USB_DEVICE_ID_KYE_EASYPEN_I405X: case USB_DEVICE_ID_KYE_MOUSEPEN_I608X: + case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2: case USB_DEVICE_ID_KYE_EASYPEN_M610X: ret = kye_tablet_enable(hdev); if (ret) { @@ -446,6 +448,8 @@ static const struct hid_device_id kye_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, + USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) }, + { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE) }, diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c index 9fe9d4a..b8207e0 100644 --- a/drivers/hid/hid-lg.c +++ b/drivers/hid/hid-lg.c @@ -345,14 +345,14 @@ static __u8 *lg_report_fixup(struct hid_device *hdev, __u8 *rdesc, struct usb_device_descriptor *udesc; __u16 bcdDevice, rev_maj, rev_min; - if ((drv_data->quirks & LG_RDESC) && *rsize >= 90 && rdesc[83] == 0x26 && + if ((drv_data->quirks & LG_RDESC) && *rsize >= 91 && rdesc[83] == 0x26 && rdesc[84] == 0x8c && rdesc[85] == 0x02) { hid_info(hdev, "fixing up Logitech keyboard report descriptor\n"); rdesc[84] = rdesc[89] = 0x4d; rdesc[85] = rdesc[90] = 0x10; } - if ((drv_data->quirks & LG_RDESC_REL_ABS) && *rsize >= 50 && + if ((drv_data->quirks & LG_RDESC_REL_ABS) && *rsize >= 51 && rdesc[32] == 0x81 && rdesc[33] == 0x06 && rdesc[49] == 0x81 && rdesc[50] == 0x06) { hid_info(hdev, diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index f45279c..5da115a 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -237,13 +237,6 @@ static void logi_dj_recv_add_djhid_device(struct dj_receiver_dev *djrcv_dev, return; } - if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) || - (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) { - dev_err(&djrcv_hdev->dev, "%s: invalid device index:%d\n", - __func__, dj_report->device_index); - return; - } - if (djrcv_dev->paired_dj_devices[dj_report->device_index]) { /* The device is already known. No need to reallocate it. */ dbg_hid("%s: device is already known\n", __func__); @@ -694,7 +687,6 @@ static int logi_dj_raw_event(struct hid_device *hdev, struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev); struct dj_report *dj_report = (struct dj_report *) data; unsigned long flags; - bool report_processed = false; dbg_hid("%s, size:%d\n", __func__, size); @@ -722,27 +714,41 @@ static int logi_dj_raw_event(struct hid_device *hdev, * anything else with it. */ + /* case 1) */ + if (data[0] != REPORT_ID_DJ_SHORT) + return false; + + if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) || + (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) { + /* + * Device index is wrong, bail out. + * This driver can ignore safely the receiver notifications, + * so ignore those reports too. + */ + if (dj_report->device_index != DJ_RECEIVER_INDEX) + dev_err(&hdev->dev, "%s: invalid device index:%d\n", + __func__, dj_report->device_index); + return false; + } + spin_lock_irqsave(&djrcv_dev->lock, flags); - if (dj_report->report_id == REPORT_ID_DJ_SHORT) { - switch (dj_report->report_type) { - case REPORT_TYPE_NOTIF_DEVICE_PAIRED: - case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED: - logi_dj_recv_queue_notification(djrcv_dev, dj_report); - break; - case REPORT_TYPE_NOTIF_CONNECTION_STATUS: - if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] == - STATUS_LINKLOSS) { - logi_dj_recv_forward_null_report(djrcv_dev, dj_report); - } - break; - default: - logi_dj_recv_forward_report(djrcv_dev, dj_report); + switch (dj_report->report_type) { + case REPORT_TYPE_NOTIF_DEVICE_PAIRED: + case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED: + logi_dj_recv_queue_notification(djrcv_dev, dj_report); + break; + case REPORT_TYPE_NOTIF_CONNECTION_STATUS: + if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] == + STATUS_LINKLOSS) { + logi_dj_recv_forward_null_report(djrcv_dev, dj_report); } - report_processed = true; + break; + default: + logi_dj_recv_forward_report(djrcv_dev, dj_report); } spin_unlock_irqrestore(&djrcv_dev->lock, flags); - return report_processed; + return true; } static int logi_dj_probe(struct hid_device *hdev, diff --git a/drivers/hid/hid-logitech-dj.h b/drivers/hid/hid-logitech-dj.h index 4a40003..daeb0aa 100644 --- a/drivers/hid/hid-logitech-dj.h +++ b/drivers/hid/hid-logitech-dj.h @@ -27,6 +27,7 @@ #define DJ_MAX_PAIRED_DEVICES 6 #define DJ_MAX_NUMBER_NOTIFICATIONS 8 +#define DJ_RECEIVER_INDEX 0 #define DJ_DEVICE_INDEX_MIN 1 #define DJ_DEVICE_INDEX_MAX 6 diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index 3b43d1c..991ba79 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -290,6 +290,11 @@ static int magicmouse_raw_event(struct hid_device *hdev, if (size < 4 || ((size - 4) % 9) != 0) return 0; npoints = (size - 4) / 9; + if (npoints > 15) { + hid_warn(hdev, "invalid size value (%d) for TRACKPAD_REPORT_ID\n", + size); + return 0; + } msc->ntouches = 0; for (ii = 0; ii < npoints; ii++) magicmouse_emit_touch(msc, ii, data + ii * 9 + 4); @@ -307,6 +312,11 @@ static int magicmouse_raw_event(struct hid_device *hdev, if (size < 6 || ((size - 6) % 8) != 0) return 0; npoints = (size - 6) / 8; + if (npoints > 15) { + hid_warn(hdev, "invalid size value (%d) for MOUSE_REPORT_ID\n", + size); + return 0; + } msc->ntouches = 0; for (ii = 0; ii < npoints; ii++) magicmouse_emit_touch(msc, ii, data + ii * 8 + 6); diff --git a/drivers/hid/hid-monterey.c b/drivers/hid/hid-monterey.c index 9e14c00..25daf28 100644 --- a/drivers/hid/hid-monterey.c +++ b/drivers/hid/hid-monterey.c @@ -24,7 +24,7 @@ static __u8 *mr_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { - if (*rsize >= 30 && rdesc[29] == 0x05 && rdesc[30] == 0x09) { + if (*rsize >= 31 && rdesc[29] == 0x05 && rdesc[30] == 0x09) { hid_info(hdev, "fixing up button/consumer in HID report descriptor\n"); rdesc[30] = 0x0c; } diff --git a/drivers/hid/hid-petalynx.c b/drivers/hid/hid-petalynx.c index 736b250..6aca4f2 100644 --- a/drivers/hid/hid-petalynx.c +++ b/drivers/hid/hid-petalynx.c @@ -25,7 +25,7 @@ static __u8 *pl_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { - if (*rsize >= 60 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 && + if (*rsize >= 62 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 && rdesc[41] == 0x00 && rdesc[59] == 0x26 && rdesc[60] == 0xf9 && rdesc[61] == 0x00) { hid_info(hdev, "fixing up Petalynx Maxter Remote report descriptor\n"); diff --git a/drivers/hid/hid-picolcd_core.c b/drivers/hid/hid-picolcd_core.c index acbb0210..020df3c 100644 --- a/drivers/hid/hid-picolcd_core.c +++ b/drivers/hid/hid-picolcd_core.c @@ -350,6 +350,12 @@ static int picolcd_raw_event(struct hid_device *hdev, if (!data) return 1; + if (size > 64) { + hid_warn(hdev, "invalid size value (%d) for picolcd raw event\n", + size); + return 0; + } + if (report->id == REPORT_KEY_STATE) { if (data->input_keys) ret = picolcd_raw_keypad(data, report, raw_data+1, size-1); diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c index 1a07e07..47d7e74 100644 --- a/drivers/hid/hid-roccat-pyra.c +++ b/drivers/hid/hid-roccat-pyra.c @@ -35,6 +35,8 @@ static struct class *pyra_class; static void profile_activated(struct pyra_device *pyra, unsigned int new_profile) { + if (new_profile >= ARRAY_SIZE(pyra->profile_settings)) + return; pyra->actual_profile = new_profile; pyra->actual_cpi = pyra->profile_settings[pyra->actual_profile].y_cpi; } @@ -257,9 +259,11 @@ static ssize_t pyra_sysfs_write_settings(struct file *fp, if (off != 0 || count != PYRA_SIZE_SETTINGS) return -EINVAL; - mutex_lock(&pyra->pyra_lock); - settings = (struct pyra_settings const *)buf; + if (settings->startup_profile >= ARRAY_SIZE(pyra->profile_settings)) + return -EINVAL; + + mutex_lock(&pyra->pyra_lock); retval = pyra_set_settings(usb_dev, settings); if (retval) { diff --git a/drivers/hid/hid-sunplus.c b/drivers/hid/hid-sunplus.c index 87fc91e..91072fa 100644 --- a/drivers/hid/hid-sunplus.c +++ b/drivers/hid/hid-sunplus.c @@ -24,7 +24,7 @@ static __u8 *sp_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { - if (*rsize >= 107 && rdesc[104] == 0x26 && rdesc[105] == 0x80 && + if (*rsize >= 112 && rdesc[104] == 0x26 && rdesc[105] == 0x80 && rdesc[106] == 0x03) { hid_info(hdev, "fixing up Sunplus Wireless Desktop report descriptor\n"); rdesc[105] = rdesc[110] = 0x03; diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 42eebd1..17be889 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -136,6 +136,7 @@ struct i2c_hid { * descriptor. */ unsigned int bufsize; /* i2c buffer size */ char *inbuf; /* Input buffer */ + char *rawbuf; /* Raw Input buffer */ char *cmdbuf; /* Command buffer */ char *argsbuf; /* Command arguments buffer */ @@ -357,6 +358,9 @@ static void i2c_hid_get_input(struct i2c_hid *ihid) int ret, ret_size; int size = le16_to_cpu(ihid->hdesc.wMaxInputLength); + if (size > ihid->bufsize) + size = ihid->bufsize; + ret = i2c_master_recv(ihid->client, ihid->inbuf, size); if (ret != size) { if (ret < 0) @@ -482,9 +486,11 @@ static void i2c_hid_find_max_report(struct hid_device *hid, unsigned int type, static void i2c_hid_free_buffers(struct i2c_hid *ihid) { kfree(ihid->inbuf); + kfree(ihid->rawbuf); kfree(ihid->argsbuf); kfree(ihid->cmdbuf); ihid->inbuf = NULL; + ihid->rawbuf = NULL; ihid->cmdbuf = NULL; ihid->argsbuf = NULL; ihid->bufsize = 0; @@ -500,10 +506,11 @@ static int i2c_hid_alloc_buffers(struct i2c_hid *ihid, size_t report_size) report_size; /* report */ ihid->inbuf = kzalloc(report_size, GFP_KERNEL); + ihid->rawbuf = kzalloc(report_size, GFP_KERNEL); ihid->argsbuf = kzalloc(args_len, GFP_KERNEL); ihid->cmdbuf = kzalloc(sizeof(union command) + args_len, GFP_KERNEL); - if (!ihid->inbuf || !ihid->argsbuf || !ihid->cmdbuf) { + if (!ihid->inbuf || !ihid->rawbuf || !ihid->argsbuf || !ihid->cmdbuf) { i2c_hid_free_buffers(ihid); return -ENOMEM; } @@ -530,12 +537,12 @@ static int i2c_hid_get_raw_report(struct hid_device *hid, ret = i2c_hid_get_report(client, report_type == HID_FEATURE_REPORT ? 0x03 : 0x01, - report_number, ihid->inbuf, ask_count); + report_number, ihid->rawbuf, ask_count); if (ret < 0) return ret; - ret_count = ihid->inbuf[0] | (ihid->inbuf[1] << 8); + ret_count = ihid->rawbuf[0] | (ihid->rawbuf[1] << 8); if (ret_count <= 2) return 0; @@ -544,7 +551,7 @@ static int i2c_hid_get_raw_report(struct hid_device *hid, /* The query buffer contains the size, dropping it in the reply */ count = min(count, ret_count - 2); - memcpy(buf, ihid->inbuf + 2, count); + memcpy(buf, ihid->rawbuf + 2, count); return count; } diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 44df131..deabd2c 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -82,7 +82,7 @@ static int hid_start_in(struct hid_device *hid) struct usbhid_device *usbhid = hid->driver_data; spin_lock_irqsave(&usbhid->lock, flags); - if (hid->open > 0 && + if ((hid->open > 0 || hid->quirks & HID_QUIRK_ALWAYS_POLL) && !test_bit(HID_DISCONNECTED, &usbhid->iofl) && !test_bit(HID_SUSPENDED, &usbhid->iofl) && !test_and_set_bit(HID_IN_RUNNING, &usbhid->iofl)) { @@ -180,7 +180,7 @@ static void hid_io_error(struct hid_device *hid) if (time_after(jiffies, usbhid->stop_retry)) { /* Retries failed, so do a port reset unless we lack bandwidth*/ - if (test_bit(HID_NO_BANDWIDTH, &usbhid->iofl) + if (!test_bit(HID_NO_BANDWIDTH, &usbhid->iofl) && !test_and_set_bit(HID_RESET_PENDING, &usbhid->iofl)) { schedule_work(&usbhid->reset_work); @@ -292,6 +292,8 @@ static void hid_irq_in(struct urb *urb) case 0: /* success */ usbhid_mark_busy(usbhid); usbhid->retry_delay = 0; + if ((hid->quirks & HID_QUIRK_ALWAYS_POLL) && !hid->open) + break; hid_input_report(urb->context, HID_INPUT_REPORT, urb->transfer_buffer, urb->actual_length, 1); @@ -734,8 +736,10 @@ void usbhid_close(struct hid_device *hid) if (!--hid->open) { spin_unlock_irq(&usbhid->lock); hid_cancel_delayed_stuff(usbhid); - usb_kill_urb(usbhid->urbin); - usbhid->intf->needs_remote_wakeup = 0; + if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) { + usb_kill_urb(usbhid->urbin); + usbhid->intf->needs_remote_wakeup = 0; + } } else { spin_unlock_irq(&usbhid->lock); } @@ -1119,6 +1123,19 @@ static int usbhid_start(struct hid_device *hid) set_bit(HID_STARTED, &usbhid->iofl); + if (hid->quirks & HID_QUIRK_ALWAYS_POLL) { + ret = usb_autopm_get_interface(usbhid->intf); + if (ret) + goto fail; + usbhid->intf->needs_remote_wakeup = 1; + ret = hid_start_in(hid); + if (ret) { + dev_err(&hid->dev, + "failed to start in urb: %d\n", ret); + } + usb_autopm_put_interface(usbhid->intf); + } + /* Some keyboards don't work until their LEDs have been set. * Since BIOSes do set the LEDs, it must be safe for any device * that supports the keyboard boot protocol. @@ -1151,6 +1168,9 @@ static void usbhid_stop(struct hid_device *hid) if (WARN_ON(!usbhid)) return; + if (hid->quirks & HID_QUIRK_ALWAYS_POLL) + usbhid->intf->needs_remote_wakeup = 0; + clear_bit(HID_STARTED, &usbhid->iofl); spin_lock_irq(&usbhid->lock); /* Sync with error and led handlers */ set_bit(HID_DISCONNECTED, &usbhid->iofl); diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index 8e4ddb3..473c0c4 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -69,6 +69,9 @@ static const struct hid_blacklist { { USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_3AXIS_5BUTTON_STICK, HID_QUIRK_NOGET }, { USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET }, { USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET }, + { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN, HID_QUIRK_ALWAYS_POLL }, + { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B, HID_QUIRK_ALWAYS_POLL }, + { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET }, { USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET }, @@ -113,6 +116,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_WIRELESS, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_SIGMA_MICRO, USB_DEVICE_ID_SIGMA_MICRO_KEYBOARD, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X, HID_QUIRK_MULTI_INPUT }, + { USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_DUOSENSE, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS1, HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 69ea36f..356f22f 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -134,7 +134,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, GFP_KERNEL); if (!open_info) { err = -ENOMEM; - goto error0; + goto error_gpadl; } init_completion(&open_info->waitevent); @@ -150,7 +150,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, if (userdatalen > MAX_USER_DEFINED_BYTES) { err = -EINVAL; - goto error0; + goto error_gpadl; } if (userdatalen) @@ -164,8 +164,10 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, ret = vmbus_post_msg(open_msg, sizeof(struct vmbus_channel_open_channel)); - if (ret != 0) + if (ret != 0) { + err = ret; goto error1; + } t = wait_for_completion_timeout(&open_info->waitevent, 5*HZ); if (t == 0) { @@ -192,6 +194,9 @@ error1: list_del(&open_info->msglistentry); spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); +error_gpadl: + vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle); + error0: free_pages((unsigned long)out, get_order(send_ringbuffer_size + recv_ringbuffer_size)); @@ -362,7 +367,6 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, u32 next_gpadl_handle; unsigned long flags; int ret = 0; - int t; next_gpadl_handle = atomic_read(&vmbus_connection.next_gpadl_handle); atomic_inc(&vmbus_connection.next_gpadl_handle); @@ -409,9 +413,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, } } - t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ); - BUG_ON(t == 0); - + wait_for_completion(&msginfo->waitevent); /* At this point, we received the gpadl created msg */ *gpadl_handle = gpadlmsg->gpadl; @@ -434,7 +436,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) struct vmbus_channel_gpadl_teardown *msg; struct vmbus_channel_msginfo *info; unsigned long flags; - int ret, t; + int ret; info = kmalloc(sizeof(*info) + sizeof(struct vmbus_channel_gpadl_teardown), GFP_KERNEL); @@ -456,11 +458,12 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_gpadl_teardown)); - BUG_ON(ret != 0); - t = wait_for_completion_timeout(&info->waitevent, 5*HZ); - BUG_ON(t == 0); + if (ret) + goto post_msg_err; + + wait_for_completion(&info->waitevent); - /* Received a torndown response */ +post_msg_err: spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); list_del(&info->msglistentry); spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); @@ -470,7 +473,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) } EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl); -static void vmbus_close_internal(struct vmbus_channel *channel) +static int vmbus_close_internal(struct vmbus_channel *channel) { struct vmbus_channel_close_channel *msg; int ret; @@ -492,11 +495,28 @@ static void vmbus_close_internal(struct vmbus_channel *channel) ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel)); - BUG_ON(ret != 0); + if (ret) { + pr_err("Close failed: close post msg return is %d\n", ret); + /* + * If we failed to post the close msg, + * it is perhaps better to leak memory. + */ + return ret; + } + /* Tear down the gpadl for the channel's ring buffer */ - if (channel->ringbuffer_gpadlhandle) - vmbus_teardown_gpadl(channel, - channel->ringbuffer_gpadlhandle); + if (channel->ringbuffer_gpadlhandle) { + ret = vmbus_teardown_gpadl(channel, + channel->ringbuffer_gpadlhandle); + if (ret) { + pr_err("Close failed: teardown gpadl return %d\n", ret); + /* + * If we failed to teardown gpadl, + * it is perhaps better to leak memory. + */ + return ret; + } + } /* Cleanup the ring buffers for this channel */ hv_ringbuffer_cleanup(&channel->outbound); @@ -505,7 +525,7 @@ static void vmbus_close_internal(struct vmbus_channel *channel) free_pages((unsigned long)channel->ringbuffer_pages, get_order(channel->ringbuffer_pagecount * PAGE_SIZE)); - + return ret; } /* diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index fa92046..8c24881 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -202,9 +202,16 @@ static void vmbus_process_rescind_offer(struct work_struct *work) unsigned long flags; struct vmbus_channel *primary_channel; struct vmbus_channel_relid_released msg; + struct device *dev; + + if (channel->device_obj) { + dev = get_device(&channel->device_obj->device); + if (dev) { + vmbus_device_unregister(channel->device_obj); + put_device(dev); + } + } - if (channel->device_obj) - vmbus_device_unregister(channel->device_obj); memset(&msg, 0, sizeof(struct vmbus_channel_relid_released)); msg.child_relid = channel->offermsg.child_relid; msg.header.msgtype = CHANNELMSG_RELID_RELEASED; @@ -709,7 +716,7 @@ int vmbus_request_offers(void) { struct vmbus_channel_message_header *msg; struct vmbus_channel_msginfo *msginfo; - int ret, t; + int ret; msginfo = kmalloc(sizeof(*msginfo) + sizeof(struct vmbus_channel_message_header), @@ -717,8 +724,6 @@ int vmbus_request_offers(void) if (!msginfo) return -ENOMEM; - init_completion(&msginfo->waitevent); - msg = (struct vmbus_channel_message_header *)msginfo->msg; msg->msgtype = CHANNELMSG_REQUESTOFFERS; @@ -732,14 +737,6 @@ int vmbus_request_offers(void) goto cleanup; } - t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ); - if (t == 0) { - ret = -ETIMEDOUT; - goto cleanup; - } - - - cleanup: kfree(msginfo); diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index ce5a9f2..d8fd95c 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -408,10 +408,21 @@ int vmbus_post_msg(void *buffer, size_t buflen) * insufficient resources. Retry the operation a couple of * times before giving up. */ - while (retries < 3) { - ret = hv_post_message(conn_id, 1, buffer, buflen); - if (ret != HV_STATUS_INSUFFICIENT_BUFFERS) + while (retries < 10) { + ret = hv_post_message(conn_id, 1, buffer, buflen); + + switch (ret) { + case HV_STATUS_INSUFFICIENT_BUFFERS: + ret = -ENOMEM; + case -ENOMEM: + break; + case HV_STATUS_SUCCESS: return ret; + default: + pr_err("hv_post_msg() failed; error code:%d\n", ret); + return -EINVAL; + } + retries++; msleep(100); } diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c index 7f9dc2f..1265164 100644 --- a/drivers/hwmon/ads1015.c +++ b/drivers/hwmon/ads1015.c @@ -198,7 +198,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client) } channel = be32_to_cpup(property); - if (channel > ADS1015_CHANNELS) { + if (channel >= ADS1015_CHANNELS) { dev_err(&client->dev, "invalid channel index %d on %s\n", channel, node->full_name); @@ -212,6 +212,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client) dev_err(&client->dev, "invalid gain on %s\n", node->full_name); + return -EINVAL; } } @@ -222,6 +223,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client) dev_err(&client->dev, "invalid data_rate on %s\n", node->full_name); + return -EINVAL; } } diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c index 9f2be3d..8a67ec6 100644 --- a/drivers/hwmon/amc6821.c +++ b/drivers/hwmon/amc6821.c @@ -360,11 +360,13 @@ static ssize_t set_pwm1_enable( if (config) return config; + mutex_lock(&data->update_lock); config = i2c_smbus_read_byte_data(client, AMC6821_REG_CONF1); if (config < 0) { dev_err(&client->dev, "Error reading configuration register, aborting.\n"); - return config; + count = config; + goto unlock; } switch (val) { @@ -381,14 +383,15 @@ static ssize_t set_pwm1_enable( config |= AMC6821_CONF1_FDRC1; break; default: - return -EINVAL; + count = -EINVAL; + goto unlock; } - mutex_lock(&data->update_lock); if (i2c_smbus_write_byte_data(client, AMC6821_REG_CONF1, config)) { dev_err(&client->dev, "Configuration register write error, aborting.\n"); count = -EIO; } +unlock: mutex_unlock(&data->update_lock); return count; } @@ -493,8 +496,9 @@ static ssize_t set_temp_auto_point_temp( return -EINVAL; } - data->valid = 0; mutex_lock(&data->update_lock); + data->valid = 0; + switch (ix) { case 0: ptemp[0] = clamp_val(val / 1000, 0, @@ -658,13 +662,14 @@ static ssize_t set_fan1_div( if (config) return config; + mutex_lock(&data->update_lock); config = i2c_smbus_read_byte_data(client, AMC6821_REG_CONF4); if (config < 0) { dev_err(&client->dev, "Error reading configuration register, aborting.\n"); - return config; + count = config; + goto EXIT; } - mutex_lock(&data->update_lock); switch (val) { case 2: config &= ~AMC6821_CONF4_PSPR; diff --git a/drivers/hwmon/dme1737.c b/drivers/hwmon/dme1737.c index 4ae3fff..bea0a34 100644 --- a/drivers/hwmon/dme1737.c +++ b/drivers/hwmon/dme1737.c @@ -247,8 +247,8 @@ struct dme1737_data { u8 pwm_acz[3]; u8 pwm_freq[6]; u8 pwm_rr[2]; - u8 zone_low[3]; - u8 zone_abs[3]; + s8 zone_low[3]; + s8 zone_abs[3]; u8 zone_hyst[2]; u32 alarms; }; @@ -277,7 +277,7 @@ static inline int IN_FROM_REG(int reg, int nominal, int res) return (reg * nominal + (3 << (res - 3))) / (3 << (res - 2)); } -static inline int IN_TO_REG(int val, int nominal) +static inline int IN_TO_REG(long val, int nominal) { return clamp_val((val * 192 + nominal / 2) / nominal, 0, 255); } @@ -293,7 +293,7 @@ static inline int TEMP_FROM_REG(int reg, int res) return (reg * 1000) >> (res - 8); } -static inline int TEMP_TO_REG(int val) +static inline int TEMP_TO_REG(long val) { return clamp_val((val < 0 ? val - 500 : val + 500) / 1000, -128, 127); } @@ -308,7 +308,7 @@ static inline int TEMP_RANGE_FROM_REG(int reg) return TEMP_RANGE[(reg >> 4) & 0x0f]; } -static int TEMP_RANGE_TO_REG(int val, int reg) +static int TEMP_RANGE_TO_REG(long val, int reg) { int i; @@ -331,7 +331,7 @@ static inline int TEMP_HYST_FROM_REG(int reg, int ix) return (((ix == 1) ? reg : reg >> 4) & 0x0f) * 1000; } -static inline int TEMP_HYST_TO_REG(int val, int ix, int reg) +static inline int TEMP_HYST_TO_REG(long val, int ix, int reg) { int hyst = clamp_val((val + 500) / 1000, 0, 15); @@ -347,7 +347,7 @@ static inline int FAN_FROM_REG(int reg, int tpc) return (reg == 0 || reg == 0xffff) ? 0 : 90000 * 60 / reg; } -static inline int FAN_TO_REG(int val, int tpc) +static inline int FAN_TO_REG(long val, int tpc) { if (tpc) { return clamp_val(val / tpc, 0, 0xffff); @@ -379,7 +379,7 @@ static inline int FAN_TYPE_FROM_REG(int reg) return (edge > 0) ? 1 << (edge - 1) : 0; } -static inline int FAN_TYPE_TO_REG(int val, int reg) +static inline int FAN_TYPE_TO_REG(long val, int reg) { int edge = (val == 4) ? 3 : val; @@ -402,7 +402,7 @@ static int FAN_MAX_FROM_REG(int reg) return 1000 + i * 500; } -static int FAN_MAX_TO_REG(int val) +static int FAN_MAX_TO_REG(long val) { int i; @@ -460,7 +460,7 @@ static inline int PWM_ACZ_FROM_REG(int reg) return acz[(reg >> 5) & 0x07]; } -static inline int PWM_ACZ_TO_REG(int val, int reg) +static inline int PWM_ACZ_TO_REG(long val, int reg) { int acz = (val == 4) ? 2 : val - 1; @@ -476,7 +476,7 @@ static inline int PWM_FREQ_FROM_REG(int reg) return PWM_FREQ[reg & 0x0f]; } -static int PWM_FREQ_TO_REG(int val, int reg) +static int PWM_FREQ_TO_REG(long val, int reg) { int i; @@ -510,7 +510,7 @@ static inline int PWM_RR_FROM_REG(int reg, int ix) return (rr & 0x08) ? PWM_RR[rr & 0x07] : 0; } -static int PWM_RR_TO_REG(int val, int ix, int reg) +static int PWM_RR_TO_REG(long val, int ix, int reg) { int i; @@ -528,7 +528,7 @@ static inline int PWM_RR_EN_FROM_REG(int reg, int ix) return PWM_RR_FROM_REG(reg, ix) ? 1 : 0; } -static inline int PWM_RR_EN_TO_REG(int val, int ix, int reg) +static inline int PWM_RR_EN_TO_REG(long val, int ix, int reg) { int en = (ix == 1) ? 0x80 : 0x08; @@ -1481,13 +1481,16 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct dme1737_data *data = dev_get_drvdata(dev); - long val; + unsigned long val; int err; - err = kstrtol(buf, 10, &val); + err = kstrtoul(buf, 10, &val); if (err) return err; + if (val > 255) + return -EINVAL; + data->vrm = val; return count; } diff --git a/drivers/hwmon/ds1621.c b/drivers/hwmon/ds1621.c index fc6f5d5..8890870 100644 --- a/drivers/hwmon/ds1621.c +++ b/drivers/hwmon/ds1621.c @@ -309,6 +309,7 @@ static ssize_t set_convrate(struct device *dev, struct device_attribute *da, data->conf |= (resol << DS1621_REG_CONFIG_RESOL_SHIFT); i2c_smbus_write_byte_data(client, DS1621_REG_CONF, data->conf); data->update_interval = ds1721_convrates[resol]; + data->zbits = 7 - resol; mutex_unlock(&data->update_lock); return count; diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c index 73181be..814f7ee 100644 --- a/drivers/hwmon/gpio-fan.c +++ b/drivers/hwmon/gpio-fan.c @@ -173,7 +173,7 @@ static int get_fan_speed_index(struct gpio_fan_data *fan_data) return -ENODEV; } -static int rpm_to_speed_index(struct gpio_fan_data *fan_data, int rpm) +static int rpm_to_speed_index(struct gpio_fan_data *fan_data, unsigned long rpm) { struct gpio_fan_speed *speed = fan_data->speed; int i; diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c index 9efadfc..c1eb464 100644 --- a/drivers/hwmon/lm78.c +++ b/drivers/hwmon/lm78.c @@ -108,7 +108,7 @@ static inline int FAN_FROM_REG(u8 val, int div) * TEMP: mC (-128C to +127C) * REG: 1C/bit, two's complement */ -static inline s8 TEMP_TO_REG(int val) +static inline s8 TEMP_TO_REG(long val) { int nval = clamp_val(val, -128000, 127000) ; return nval < 0 ? (nval - 500) / 1000 : (nval + 500) / 1000; diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c index bed4af35..21d6cc8 100644 --- a/drivers/hwmon/lm85.c +++ b/drivers/hwmon/lm85.c @@ -158,7 +158,7 @@ static inline u16 FAN_TO_REG(unsigned long val) /* Temperature is reported in .001 degC increments */ #define TEMP_TO_REG(val) \ - clamp_val(SCALE(val, 1000, 1), -127, 127) + DIV_ROUND_CLOSEST(clamp_val((val), -127000, 127000), 1000) #define TEMPEXT_FROM_REG(val, ext) \ SCALE(((val) << 4) + (ext), 16, 1000) #define TEMP_FROM_REG(val) ((val) * 1000) @@ -192,7 +192,7 @@ static const int lm85_range_map[] = { 13300, 16000, 20000, 26600, 32000, 40000, 53300, 80000 }; -static int RANGE_TO_REG(int range) +static int RANGE_TO_REG(long range) { int i; @@ -214,7 +214,7 @@ static const int adm1027_freq_map[8] = { /* 1 Hz */ 11, 15, 22, 29, 35, 44, 59, 88 }; -static int FREQ_TO_REG(const int *map, int freq) +static int FREQ_TO_REG(const int *map, unsigned long freq) { int i; @@ -463,6 +463,9 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr, if (err) return err; + if (val > 255) + return -EINVAL; + data->vrm = val; return count; } diff --git a/drivers/hwmon/mcp3021.c b/drivers/hwmon/mcp3021.c index d219c06..972444a 100644 --- a/drivers/hwmon/mcp3021.c +++ b/drivers/hwmon/mcp3021.c @@ -31,14 +31,11 @@ /* output format */ #define MCP3021_SAR_SHIFT 2 #define MCP3021_SAR_MASK 0x3ff - #define MCP3021_OUTPUT_RES 10 /* 10-bit resolution */ -#define MCP3021_OUTPUT_SCALE 4 #define MCP3221_SAR_SHIFT 0 #define MCP3221_SAR_MASK 0xfff #define MCP3221_OUTPUT_RES 12 /* 12-bit resolution */ -#define MCP3221_OUTPUT_SCALE 1 enum chips { mcp3021, @@ -54,7 +51,6 @@ struct mcp3021_data { u16 sar_shift; u16 sar_mask; u8 output_res; - u8 output_scale; }; static int mcp3021_read16(struct i2c_client *client) @@ -84,13 +80,7 @@ static int mcp3021_read16(struct i2c_client *client) static inline u16 volts_from_reg(struct mcp3021_data *data, u16 val) { - if (val == 0) - return 0; - - val = val * data->output_scale - data->output_scale / 2; - - return val * DIV_ROUND_CLOSEST(data->vdd, - (1 << data->output_res) * data->output_scale); + return DIV_ROUND_CLOSEST(data->vdd * val, 1 << data->output_res); } static ssize_t show_in_input(struct device *dev, struct device_attribute *attr, @@ -132,14 +122,12 @@ static int mcp3021_probe(struct i2c_client *client, data->sar_shift = MCP3021_SAR_SHIFT; data->sar_mask = MCP3021_SAR_MASK; data->output_res = MCP3021_OUTPUT_RES; - data->output_scale = MCP3021_OUTPUT_SCALE; break; case mcp3221: data->sar_shift = MCP3221_SAR_SHIFT; data->sar_mask = MCP3221_SAR_MASK; data->output_res = MCP3221_OUTPUT_RES; - data->output_scale = MCP3221_OUTPUT_SCALE; break; } diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index 38d5a63..20b69bf 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -986,6 +986,7 @@ nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg, (*t)->dev_attr.attr.name, tg->base + i); if ((*t)->s2) { a2 = &su->u.a2; + sysfs_attr_init(&a2->dev_attr.attr); a2->dev_attr.attr.name = su->name; a2->nr = (*t)->u.s.nr + i; a2->index = (*t)->u.s.index; @@ -996,6 +997,7 @@ nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg, *attrs = &a2->dev_attr.attr; } else { a = &su->u.a1; + sysfs_attr_init(&a->dev_attr.attr); a->dev_attr.attr.name = su->name; a->index = (*t)->u.index + i; a->dev_attr.attr.mode = diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c index e76feb86..3660cb6 100644 --- a/drivers/hwmon/ntc_thermistor.c +++ b/drivers/hwmon/ntc_thermistor.c @@ -181,8 +181,10 @@ static struct ntc_thermistor_platform_data * ntc_thermistor_parse_dt(struct platform_device *pdev) { struct iio_channel *chan; + enum iio_chan_type type; struct device_node *np = pdev->dev.of_node; struct ntc_thermistor_platform_data *pdata; + int ret; if (!np) return NULL; @@ -195,6 +197,13 @@ ntc_thermistor_parse_dt(struct platform_device *pdev) if (IS_ERR(chan)) return ERR_CAST(chan); + ret = iio_get_channel_type(chan, &type); + if (ret < 0) + return ERR_PTR(ret); + + if (type != IIO_VOLTAGE) + return ERR_PTR(-EINVAL); + if (of_property_read_u32(np, "pullup-uv", &pdata->pullup_uv)) return ERR_PTR(-ENODEV); if (of_property_read_u32(np, "pullup-ohm", &pdata->pullup_ohm)) diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c index 3532026..bf1d789 100644 --- a/drivers/hwmon/sis5595.c +++ b/drivers/hwmon/sis5595.c @@ -159,7 +159,7 @@ static inline int TEMP_FROM_REG(s8 val) { return val * 830 + 52120; } -static inline s8 TEMP_TO_REG(int val) +static inline s8 TEMP_TO_REG(long val) { int nval = clamp_val(val, -54120, 157530) ; return nval < 0 ? (nval - 5212 - 415) / 830 : (nval - 5212 + 415) / 830; diff --git a/drivers/hwmon/smsc47m192.c b/drivers/hwmon/smsc47m192.c index efee4c5..34b9a60 100644 --- a/drivers/hwmon/smsc47m192.c +++ b/drivers/hwmon/smsc47m192.c @@ -86,7 +86,7 @@ static inline u8 IN_TO_REG(unsigned long val, int n) */ static inline s8 TEMP_TO_REG(int val) { - return clamp_val(SCALE(val, 1, 1000), -128000, 127000); + return SCALE(clamp_val(val, -128000, 127000), 1, 1000); } static inline int TEMP_FROM_REG(s8 val) @@ -384,6 +384,8 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, err = kstrtoul(buf, 10, &val); if (err) return err; + if (val > 255) + return -EINVAL; data->vrm = val; return count; diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c index 843d012..50862c9 100644 --- a/drivers/i2c/busses/i2c-at91.c +++ b/drivers/i2c/busses/i2c-at91.c @@ -62,6 +62,9 @@ #define AT91_TWI_UNRE 0x0080 /* Underrun Error */ #define AT91_TWI_NACK 0x0100 /* Not Acknowledged */ +#define AT91_TWI_INT_MASK \ + (AT91_TWI_TXCOMP | AT91_TWI_RXRDY | AT91_TWI_TXRDY | AT91_TWI_NACK) + #define AT91_TWI_IER 0x0024 /* Interrupt Enable Register */ #define AT91_TWI_IDR 0x0028 /* Interrupt Disable Register */ #define AT91_TWI_IMR 0x002c /* Interrupt Mask Register */ @@ -101,6 +104,7 @@ struct at91_twi_dev { unsigned twi_cwgr_reg; struct at91_twi_pdata *pdata; bool use_dma; + bool recv_len_abort; struct at91_twi_dma dma; }; @@ -116,13 +120,12 @@ static void at91_twi_write(struct at91_twi_dev *dev, unsigned reg, unsigned val) static void at91_disable_twi_interrupts(struct at91_twi_dev *dev) { - at91_twi_write(dev, AT91_TWI_IDR, - AT91_TWI_TXCOMP | AT91_TWI_RXRDY | AT91_TWI_TXRDY); + at91_twi_write(dev, AT91_TWI_IDR, AT91_TWI_INT_MASK); } static void at91_twi_irq_save(struct at91_twi_dev *dev) { - dev->imr = at91_twi_read(dev, AT91_TWI_IMR) & 0x7; + dev->imr = at91_twi_read(dev, AT91_TWI_IMR) & AT91_TWI_INT_MASK; at91_disable_twi_interrupts(dev); } @@ -210,8 +213,16 @@ static void at91_twi_write_data_dma_callback(void *data) struct at91_twi_dev *dev = (struct at91_twi_dev *)data; dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg), - dev->buf_len, DMA_MEM_TO_DEV); + dev->buf_len, DMA_TO_DEVICE); + /* + * When this callback is called, THR/TX FIFO is likely not to be empty + * yet. So we have to wait for TXCOMP or NACK bits to be set into the + * Status Register to be sure that the STOP bit has been sent and the + * transfer is completed. The NACK interrupt has already been enabled, + * we just have to enable TXCOMP one. + */ + at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_TXCOMP); at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP); } @@ -267,12 +278,24 @@ static void at91_twi_read_next_byte(struct at91_twi_dev *dev) *dev->buf = at91_twi_read(dev, AT91_TWI_RHR) & 0xff; --dev->buf_len; + /* return if aborting, we only needed to read RHR to clear RXRDY*/ + if (dev->recv_len_abort) + return; + /* handle I2C_SMBUS_BLOCK_DATA */ if (unlikely(dev->msg->flags & I2C_M_RECV_LEN)) { - dev->msg->flags &= ~I2C_M_RECV_LEN; - dev->buf_len += *dev->buf; - dev->msg->len = dev->buf_len + 1; - dev_dbg(dev->dev, "received block length %d\n", dev->buf_len); + /* ensure length byte is a valid value */ + if (*dev->buf <= I2C_SMBUS_BLOCK_MAX && *dev->buf > 0) { + dev->msg->flags &= ~I2C_M_RECV_LEN; + dev->buf_len += *dev->buf; + dev->msg->len = dev->buf_len + 1; + dev_dbg(dev->dev, "received block length %d\n", + dev->buf_len); + } else { + /* abort and send the stop by reading one more byte */ + dev->recv_len_abort = true; + dev->buf_len = 1; + } } /* send stop if second but last byte has been read */ @@ -289,12 +312,12 @@ static void at91_twi_read_data_dma_callback(void *data) struct at91_twi_dev *dev = (struct at91_twi_dev *)data; dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg), - dev->buf_len, DMA_DEV_TO_MEM); + dev->buf_len, DMA_FROM_DEVICE); /* The last two bytes have to be read without using dma */ dev->buf += dev->buf_len - 2; dev->buf_len = 2; - at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_RXRDY); + at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_RXRDY | AT91_TWI_TXCOMP); } static void at91_twi_read_data_dma(struct at91_twi_dev *dev) @@ -355,7 +378,7 @@ static irqreturn_t atmel_twi_interrupt(int irq, void *dev_id) /* catch error flags */ dev->transfer_status |= status; - if (irqstatus & AT91_TWI_TXCOMP) { + if (irqstatus & (AT91_TWI_TXCOMP | AT91_TWI_NACK)) { at91_disable_twi_interrupts(dev); complete(&dev->cmd_complete); } @@ -368,6 +391,34 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev) int ret; bool has_unre_flag = dev->pdata->has_unre_flag; + /* + * WARNING: the TXCOMP bit in the Status Register is NOT a clear on + * read flag but shows the state of the transmission at the time the + * Status Register is read. According to the programmer datasheet, + * TXCOMP is set when both holding register and internal shifter are + * empty and STOP condition has been sent. + * Consequently, we should enable NACK interrupt rather than TXCOMP to + * detect transmission failure. + * + * Besides, the TXCOMP bit is already set before the i2c transaction + * has been started. For read transactions, this bit is cleared when + * writing the START bit into the Control Register. So the + * corresponding interrupt can safely be enabled just after. + * However for write transactions managed by the CPU, we first write + * into THR, so TXCOMP is cleared. Then we can safely enable TXCOMP + * interrupt. If TXCOMP interrupt were enabled before writing into THR, + * the interrupt handler would be called immediately and the i2c command + * would be reported as completed. + * Also when a write transaction is managed by the DMA controller, + * enabling the TXCOMP interrupt in this function may lead to a race + * condition since we don't know whether the TXCOMP interrupt is enabled + * before or after the DMA has started to write into THR. So the TXCOMP + * interrupt is enabled later by at91_twi_write_data_dma_callback(). + * Immediately after in that DMA callback, we still need to send the + * STOP condition manually writing the corresponding bit into the + * Control Register. + */ + dev_dbg(dev->dev, "transfer: %s %d bytes.\n", (dev->msg->flags & I2C_M_RD) ? "read" : "write", dev->buf_len); @@ -398,31 +449,29 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev) * seems to be the best solution. */ if (dev->use_dma && (dev->buf_len > AT91_I2C_DMA_THRESHOLD)) { + at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_NACK); at91_twi_read_data_dma(dev); - /* - * It is important to enable TXCOMP irq here because - * doing it only when transferring the last two bytes - * will mask NACK errors since TXCOMP is set when a - * NACK occurs. - */ - at91_twi_write(dev, AT91_TWI_IER, - AT91_TWI_TXCOMP); - } else + } else { at91_twi_write(dev, AT91_TWI_IER, - AT91_TWI_TXCOMP | AT91_TWI_RXRDY); + AT91_TWI_TXCOMP | + AT91_TWI_NACK | + AT91_TWI_RXRDY); + } } else { if (dev->use_dma && (dev->buf_len > AT91_I2C_DMA_THRESHOLD)) { + at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_NACK); at91_twi_write_data_dma(dev); - at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_TXCOMP); } else { at91_twi_write_next_byte(dev); at91_twi_write(dev, AT91_TWI_IER, - AT91_TWI_TXCOMP | AT91_TWI_TXRDY); + AT91_TWI_TXCOMP | + AT91_TWI_NACK | + AT91_TWI_TXRDY); } } - ret = wait_for_completion_interruptible_timeout(&dev->cmd_complete, - dev->adapter.timeout); + ret = wait_for_completion_timeout(&dev->cmd_complete, + dev->adapter.timeout); if (ret == 0) { dev_err(dev->dev, "controller timed out\n"); at91_init_twi_bus(dev); @@ -444,6 +493,12 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev) ret = -EIO; goto error; } + if (dev->recv_len_abort) { + dev_err(dev->dev, "invalid smbus block length recvd\n"); + ret = -EPROTO; + goto error; + } + dev_dbg(dev->dev, "transfer complete\n"); return 0; @@ -500,6 +555,7 @@ static int at91_twi_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, int num) dev->buf_len = m_start->len; dev->buf = m_start->buf; dev->msg = m_start; + dev->recv_len_abort = false; ret = at91_do_twi_transfer(dev); diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c index af0b583..e3c6a96 100644 --- a/drivers/i2c/busses/i2c-davinci.c +++ b/drivers/i2c/busses/i2c-davinci.c @@ -411,11 +411,9 @@ i2c_davinci_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg, int stop) if (dev->cmd_err & DAVINCI_I2C_STR_NACK) { if (msg->flags & I2C_M_IGNORE_NAK) return msg->len; - if (stop) { - w = davinci_i2c_read_reg(dev, DAVINCI_I2C_MDR_REG); - w |= DAVINCI_I2C_MDR_STP; - davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, w); - } + w = davinci_i2c_read_reg(dev, DAVINCI_I2C_MDR_REG); + w |= DAVINCI_I2C_MDR_STP; + davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, w); return -EREMOTEIO; } return -EIO; diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index 8ce4f51..6e932d1 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -497,7 +497,7 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr, desc->wr_len_cmd = dma_size; desc->control |= ISMT_DESC_BLK; priv->dma_buffer[0] = command; - memcpy(&priv->dma_buffer[1], &data->block[1], dma_size); + memcpy(&priv->dma_buffer[1], &data->block[1], dma_size - 1); } else { /* Block Read */ dev_dbg(dev, "I2C_SMBUS_BLOCK_DATA: READ\n"); @@ -525,7 +525,7 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr, desc->wr_len_cmd = dma_size; desc->control |= ISMT_DESC_I2C; priv->dma_buffer[0] = command; - memcpy(&priv->dma_buffer[1], &data->block[1], dma_size); + memcpy(&priv->dma_buffer[1], &data->block[1], dma_size - 1); } else { /* i2c Block Read */ dev_dbg(dev, "I2C_SMBUS_I2C_BLOCK_DATA: READ\n"); diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index d52d849..cf89175 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -748,8 +748,7 @@ mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data, } tclk = clk_get_rate(drv_data->clk); - rc = of_property_read_u32(np, "clock-frequency", &bus_freq); - if (rc) + if (of_property_read_u32(np, "clock-frequency", &bus_freq)) bus_freq = 100000; /* 100kHz by default */ if (!mv64xxx_find_baud_factors(bus_freq, tclk, diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 90dcc2e..a686057 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -926,14 +926,12 @@ omap_i2c_isr_thread(int this_irq, void *dev_id) if (stat & OMAP_I2C_STAT_NACK) { err |= OMAP_I2C_STAT_NACK; omap_i2c_ack_stat(dev, OMAP_I2C_STAT_NACK); - break; } if (stat & OMAP_I2C_STAT_AL) { dev_err(dev->dev, "Arbitration lost\n"); err |= OMAP_I2C_STAT_AL; omap_i2c_ack_stat(dev, OMAP_I2C_STAT_AL); - break; } /* @@ -958,11 +956,13 @@ omap_i2c_isr_thread(int this_irq, void *dev_id) if (dev->fifo_size) num_bytes = dev->buf_len; - omap_i2c_receive_data(dev, num_bytes, true); - - if (dev->errata & I2C_OMAP_ERRATA_I207) + if (dev->errata & I2C_OMAP_ERRATA_I207) { i2c_omap_errata_i207(dev, stat); + num_bytes = (omap_i2c_read_reg(dev, + OMAP_I2C_BUFSTAT_REG) >> 8) & 0x3F; + } + omap_i2c_receive_data(dev, num_bytes, true); omap_i2c_ack_stat(dev, OMAP_I2C_STAT_RDR); continue; } diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index 93ec376..79a2117 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -753,14 +753,16 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap, int ret; pm_runtime_get_sync(&adap->dev); - clk_prepare_enable(i2c->clk); + ret = clk_enable(i2c->clk); + if (ret) + return ret; for (retry = 0; retry < adap->retries; retry++) { ret = s3c24xx_i2c_doxfer(i2c, msgs, num); if (ret != -EAGAIN) { - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); pm_runtime_put(&adap->dev); return ret; } @@ -770,7 +772,7 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap, udelay(100); } - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); pm_runtime_put(&adap->dev); return -EREMOTEIO; } @@ -1153,7 +1155,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) clk_prepare_enable(i2c->clk); ret = s3c24xx_i2c_init(i2c); - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); if (ret != 0) { dev_err(&pdev->dev, "I2C controller init failed\n"); return ret; @@ -1166,6 +1168,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) i2c->irq = ret = platform_get_irq(pdev, 0); if (ret <= 0) { dev_err(&pdev->dev, "cannot find IRQ\n"); + clk_unprepare(i2c->clk); return ret; } @@ -1174,6 +1177,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) if (ret != 0) { dev_err(&pdev->dev, "cannot claim IRQ %d\n", i2c->irq); + clk_unprepare(i2c->clk); return ret; } } @@ -1181,6 +1185,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) ret = s3c24xx_i2c_register_cpufreq(i2c); if (ret < 0) { dev_err(&pdev->dev, "failed to register cpufreq notifier\n"); + clk_unprepare(i2c->clk); return ret; } @@ -1197,6 +1202,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) if (ret < 0) { dev_err(&pdev->dev, "failed to add bus to i2c core\n"); s3c24xx_i2c_deregister_cpufreq(i2c); + clk_unprepare(i2c->clk); return ret; } @@ -1218,6 +1224,8 @@ static int s3c24xx_i2c_remove(struct platform_device *pdev) { struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev); + clk_unprepare(i2c->clk); + pm_runtime_disable(&i2c->adap.dev); pm_runtime_disable(&pdev->dev); @@ -1246,10 +1254,13 @@ static int s3c24xx_i2c_resume(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev); + int ret; - clk_prepare_enable(i2c->clk); + ret = clk_enable(i2c->clk); + if (ret) + return ret; s3c24xx_i2c_init(i2c); - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); i2c->suspended = 0; return 0; diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 5fb80b8..43fe15a 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -217,6 +217,7 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap) adap->bus_recovery_info->set_scl(adap, 1); return i2c_generic_recovery(adap); } +EXPORT_SYMBOL_GPL(i2c_generic_scl_recovery); int i2c_generic_gpio_recovery(struct i2c_adapter *adap) { @@ -231,6 +232,7 @@ int i2c_generic_gpio_recovery(struct i2c_adapter *adap) return ret; } +EXPORT_SYMBOL_GPL(i2c_generic_gpio_recovery); int i2c_recover_bus(struct i2c_adapter *adap) { @@ -240,6 +242,7 @@ int i2c_recover_bus(struct i2c_adapter *adap) dev_dbg(&adap->dev, "Trying i2c bus recovery\n"); return adap->bus_recovery_info->recover_bus(adap); } +EXPORT_SYMBOL_GPL(i2c_recover_bus); static int i2c_device_probe(struct device *dev) { diff --git a/drivers/iio/accel/bma180.c b/drivers/iio/accel/bma180.c index bfec313..6f039c3 100644 --- a/drivers/iio/accel/bma180.c +++ b/drivers/iio/accel/bma180.c @@ -68,13 +68,13 @@ /* Defaults values */ #define BMA180_DEF_PMODE 0 #define BMA180_DEF_BW 20 -#define BMA180_DEF_SCALE 250 +#define BMA180_DEF_SCALE 2452 /* Available values for sysfs */ #define BMA180_FLP_FREQ_AVAILABLE \ "10 20 40 75 150 300" #define BMA180_SCALE_AVAILABLE \ - "0.000130 0.000190 0.000250 0.000380 0.000500 0.000990 0.001980" + "0.001275 0.001863 0.002452 0.003727 0.004903 0.009709 0.019417" struct bma180_data { struct i2c_client *client; @@ -94,7 +94,7 @@ enum bma180_axis { }; static int bw_table[] = { 10, 20, 40, 75, 150, 300 }; /* Hz */ -static int scale_table[] = { 130, 190, 250, 380, 500, 990, 1980 }; +static int scale_table[] = { 1275, 1863, 2452, 3727, 4903, 9709, 19417 }; static int bma180_get_acc_reg(struct bma180_data *data, enum bma180_axis axis) { @@ -376,6 +376,8 @@ static int bma180_write_raw(struct iio_dev *indio_dev, mutex_unlock(&data->mutex); return ret; case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY: + if (val2) + return -EINVAL; mutex_lock(&data->mutex); ret = bma180_set_bw(data, val); mutex_unlock(&data->mutex); @@ -569,7 +571,7 @@ static int bma180_probe(struct i2c_client *client, trig->ops = &bma180_trigger_ops; iio_trigger_set_drvdata(trig, indio_dev); data->trig = trig; - indio_dev->trig = trig; + indio_dev->trig = iio_trigger_get(trig); ret = iio_trigger_register(trig); if (ret) diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index 9a4e0e3..eb799a4 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -472,7 +472,7 @@ static int ad_sd_probe_trigger(struct iio_dev *indio_dev) goto error_free_irq; /* select default trigger */ - indio_dev->trig = sigma_delta->trig; + indio_dev->trig = iio_trigger_get(sigma_delta->trig); return 0; diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index e6bf77d..ed4e45f 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -58,7 +58,7 @@ struct at91_adc_caps { u8 ts_pen_detect_sensitivity; /* startup time calculate function */ - u32 (*calc_startup_ticks)(u8 startup_time, u32 adc_clk_khz); + u32 (*calc_startup_ticks)(u32 startup_time, u32 adc_clk_khz); u8 num_channels; struct at91_adc_reg_desc registers; @@ -82,7 +82,7 @@ struct at91_adc_state { u8 num_channels; void __iomem *reg_base; struct at91_adc_reg_desc *registers; - u8 startup_time; + u32 startup_time; u8 sample_hold_time; bool sleep_mode; struct iio_trigger **trig; @@ -590,7 +590,7 @@ ret: return ret; } -static u32 calc_startup_ticks_9260(u8 startup_time, u32 adc_clk_khz) +static u32 calc_startup_ticks_9260(u32 startup_time, u32 adc_clk_khz) { /* * Number of ticks needed to cover the startup time of the ADC @@ -601,7 +601,7 @@ static u32 calc_startup_ticks_9260(u8 startup_time, u32 adc_clk_khz) return round_up((startup_time * adc_clk_khz / 1000) - 1, 8) / 8; } -static u32 calc_startup_ticks_9x5(u8 startup_time, u32 adc_clk_khz) +static u32 calc_startup_ticks_9x5(u32 startup_time, u32 adc_clk_khz) { /* * For sama5d3x and at91sam9x5, the formula changes to: diff --git a/drivers/iio/adc/mcp3422.c b/drivers/iio/adc/mcp3422.c index 47dcb34..3a615f3 100644 --- a/drivers/iio/adc/mcp3422.c +++ b/drivers/iio/adc/mcp3422.c @@ -57,20 +57,11 @@ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SAMP_FREQ), \ } -/* LSB is in nV to eliminate floating point */ -static const u32 rates_to_lsb[] = {1000000, 250000, 62500, 15625}; - -/* - * scales calculated as: - * rates_to_lsb[sample_rate] / (1 << pga); - * pga is 1 for 0, 2 - */ - static const int mcp3422_scales[4][4] = { - { 1000000, 250000, 62500, 15625 }, - { 500000 , 125000, 31250, 7812 }, - { 250000 , 62500 , 15625, 3906 }, - { 125000 , 31250 , 7812 , 1953 } }; + { 1000000, 500000, 250000, 125000 }, + { 250000 , 125000, 62500 , 31250 }, + { 62500 , 31250 , 15625 , 7812 }, + { 15625 , 7812 , 3906 , 1953 } }; /* Constant msleep times for data acquisitions */ static const int mcp3422_read_times[4] = { diff --git a/drivers/iio/adc/twl6030-gpadc.c b/drivers/iio/adc/twl6030-gpadc.c index 53a24eb..779dac5 100644 --- a/drivers/iio/adc/twl6030-gpadc.c +++ b/drivers/iio/adc/twl6030-gpadc.c @@ -1003,7 +1003,7 @@ static struct platform_driver twl6030_gpadc_driver = { module_platform_driver(twl6030_gpadc_driver); -MODULE_ALIAS("platform: " DRIVER_NAME); +MODULE_ALIAS("platform:" DRIVER_NAME); MODULE_AUTHOR("Balaji T K "); MODULE_AUTHOR("Graeme Gregory "); MODULE_AUTHOR("Oleksandr Kozaruk dev, "Trigger Register Failed\n"); goto error_free_trig; } - indio_dev->trig = attrb->trigger = trig; + attrb->trigger = trig; + indio_dev->trig = iio_trigger_get(trig); return ret; diff --git a/drivers/iio/common/st_sensors/st_sensors_buffer.c b/drivers/iio/common/st_sensors/st_sensors_buffer.c index 1665c8e..e18bc67 100644 --- a/drivers/iio/common/st_sensors/st_sensors_buffer.c +++ b/drivers/iio/common/st_sensors/st_sensors_buffer.c @@ -71,7 +71,7 @@ int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf) goto st_sensors_free_memory; } - for (i = 0; i < n * num_data_channels; i++) { + for (i = 0; i < n * byte_for_channel; i++) { if (i < n) buf[i] = rx_array[i]; else diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index 8fc3a97..8d8ca6f 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -49,7 +49,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, dev_err(&indio_dev->dev, "failed to register iio trigger.\n"); goto iio_trigger_register_error; } - indio_dev->trig = sdata->trig; + indio_dev->trig = iio_trigger_get(sdata->trig); return 0; diff --git a/drivers/iio/dac/ad5624r_spi.c b/drivers/iio/dac/ad5624r_spi.c index e8199cc..1e66651 100644 --- a/drivers/iio/dac/ad5624r_spi.c +++ b/drivers/iio/dac/ad5624r_spi.c @@ -22,7 +22,7 @@ #include "ad5624r.h" static int ad5624r_spi_write(struct spi_device *spi, - u8 cmd, u8 addr, u16 val, u8 len) + u8 cmd, u8 addr, u16 val, u8 shift) { u32 data; u8 msg[3]; @@ -35,7 +35,7 @@ static int ad5624r_spi_write(struct spi_device *spi, * 14-, 12-bit input code followed by 0, 2, or 4 don't care bits, * for the AD5664R, AD5644R, and AD5624R, respectively. */ - data = (0 << 22) | (cmd << 19) | (addr << 16) | (val << (16 - len)); + data = (0 << 22) | (cmd << 19) | (addr << 16) | (val << shift); msg[0] = data >> 16; msg[1] = data >> 8; msg[2] = data; diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c index 17aca4d..861ba3d 100644 --- a/drivers/iio/dac/ad5686.c +++ b/drivers/iio/dac/ad5686.c @@ -322,7 +322,7 @@ static int ad5686_probe(struct spi_device *spi) st = iio_priv(indio_dev); spi_set_drvdata(spi, indio_dev); - st->reg = devm_regulator_get(&spi->dev, "vcc"); + st->reg = devm_regulator_get_optional(&spi->dev, "vcc"); if (!IS_ERR(st->reg)) { ret = regulator_enable(st->reg); if (ret) diff --git a/drivers/iio/gyro/Kconfig b/drivers/iio/gyro/Kconfig index ac2d69e..6f64c5c 100644 --- a/drivers/iio/gyro/Kconfig +++ b/drivers/iio/gyro/Kconfig @@ -93,7 +93,8 @@ config IIO_ST_GYRO_SPI_3AXIS config ITG3200 tristate "InvenSense ITG3200 Digital 3-Axis Gyroscope I2C driver" depends on I2C - select IIO_TRIGGERED_BUFFER if IIO_BUFFER + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER help Say yes here to add support for the InvenSense ITG3200 digital 3-axis gyroscope sensor. diff --git a/drivers/iio/gyro/itg3200_buffer.c b/drivers/iio/gyro/itg3200_buffer.c index e3b3c50..eef50e9 100644 --- a/drivers/iio/gyro/itg3200_buffer.c +++ b/drivers/iio/gyro/itg3200_buffer.c @@ -132,7 +132,7 @@ int itg3200_probe_trigger(struct iio_dev *indio_dev) goto error_free_irq; /* select default trigger */ - indio_dev->trig = st->trig; + indio_dev->trig = iio_trigger_get(st->trig); return 0; diff --git a/drivers/iio/imu/adis16400.h b/drivers/iio/imu/adis16400.h index 0916bf6..1e8fd2e 100644 --- a/drivers/iio/imu/adis16400.h +++ b/drivers/iio/imu/adis16400.h @@ -165,6 +165,7 @@ struct adis16400_state { int filt_int; struct adis adis; + unsigned long avail_scan_mask[2]; }; /* At the moment triggers are only used for ring buffer diff --git a/drivers/iio/imu/adis16400_core.c b/drivers/iio/imu/adis16400_core.c index 7c582f7..ccfaf3a 100644 --- a/drivers/iio/imu/adis16400_core.c +++ b/drivers/iio/imu/adis16400_core.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -437,6 +438,11 @@ static int adis16400_read_raw(struct iio_dev *indio_dev, *val = st->variant->temp_scale_nano / 1000000; *val2 = (st->variant->temp_scale_nano % 1000000); return IIO_VAL_INT_PLUS_MICRO; + case IIO_PRESSURE: + /* 20 uBar = 0.002kPascal */ + *val = 0; + *val2 = 2000; + return IIO_VAL_INT_PLUS_MICRO; default: return -EINVAL; } @@ -447,7 +453,7 @@ static int adis16400_read_raw(struct iio_dev *indio_dev, mutex_unlock(&indio_dev->mlock); if (ret) return ret; - val16 = ((val16 & 0xFFF) << 4) >> 4; + val16 = sign_extend32(val16, 11); *val = val16; return IIO_VAL_INT; case IIO_CHAN_INFO_OFFSET: @@ -479,10 +485,10 @@ static int adis16400_read_raw(struct iio_dev *indio_dev, } } -#define ADIS16400_VOLTAGE_CHAN(addr, bits, name, si) { \ +#define ADIS16400_VOLTAGE_CHAN(addr, bits, name, si, chn) { \ .type = IIO_VOLTAGE, \ .indexed = 1, \ - .channel = 0, \ + .channel = chn, \ .extend_name = name, \ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ BIT(IIO_CHAN_INFO_SCALE), \ @@ -498,10 +504,10 @@ static int adis16400_read_raw(struct iio_dev *indio_dev, } #define ADIS16400_SUPPLY_CHAN(addr, bits) \ - ADIS16400_VOLTAGE_CHAN(addr, bits, "supply", ADIS16400_SCAN_SUPPLY) + ADIS16400_VOLTAGE_CHAN(addr, bits, "supply", ADIS16400_SCAN_SUPPLY, 0) #define ADIS16400_AUX_ADC_CHAN(addr, bits) \ - ADIS16400_VOLTAGE_CHAN(addr, bits, NULL, ADIS16400_SCAN_ADC) + ADIS16400_VOLTAGE_CHAN(addr, bits, NULL, ADIS16400_SCAN_ADC, 1) #define ADIS16400_GYRO_CHAN(mod, addr, bits) { \ .type = IIO_ANGL_VEL, \ @@ -818,11 +824,6 @@ static const struct iio_info adis16400_info = { .debugfs_reg_access = adis_debugfs_reg_access, }; -static const unsigned long adis16400_burst_scan_mask[] = { - ~0UL, - 0, -}; - static const char * const adis16400_status_error_msgs[] = { [ADIS16400_DIAG_STAT_ZACCL_FAIL] = "Z-axis accelerometer self-test failure", [ADIS16400_DIAG_STAT_YACCL_FAIL] = "Y-axis accelerometer self-test failure", @@ -870,6 +871,20 @@ static const struct adis_data adis16400_data = { BIT(ADIS16400_DIAG_STAT_POWER_LOW), }; +static void adis16400_setup_chan_mask(struct adis16400_state *st) +{ + const struct adis16400_chip_info *chip_info = st->variant; + unsigned i; + + for (i = 0; i < chip_info->num_channels; i++) { + const struct iio_chan_spec *ch = &chip_info->channels[i]; + + if (ch->scan_index >= 0 && + ch->scan_index != ADIS16400_SCAN_TIMESTAMP) + st->avail_scan_mask[0] |= BIT(ch->scan_index); + } +} + static int adis16400_probe(struct spi_device *spi) { struct adis16400_state *st; @@ -893,8 +908,10 @@ static int adis16400_probe(struct spi_device *spi) indio_dev->info = &adis16400_info; indio_dev->modes = INDIO_DIRECT_MODE; - if (!(st->variant->flags & ADIS16400_NO_BURST)) - indio_dev->available_scan_masks = adis16400_burst_scan_mask; + if (!(st->variant->flags & ADIS16400_NO_BURST)) { + adis16400_setup_chan_mask(st); + indio_dev->available_scan_masks = st->avail_scan_mask; + } ret = adis_init(&st->adis, indio_dev, spi, &adis16400_data); if (ret) diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c index dd4206c..5e1b117 100644 --- a/drivers/iio/imu/adis16480.c +++ b/drivers/iio/imu/adis16480.c @@ -110,6 +110,10 @@ struct adis16480_chip_info { unsigned int num_channels; const struct iio_chan_spec *channels; + unsigned int gyro_max_val; + unsigned int gyro_max_scale; + unsigned int accel_max_val; + unsigned int accel_max_scale; }; struct adis16480 { @@ -533,19 +537,21 @@ static int adis16480_set_filter_freq(struct iio_dev *indio_dev, static int adis16480_read_raw(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, int *val, int *val2, long info) { + struct adis16480 *st = iio_priv(indio_dev); + switch (info) { case IIO_CHAN_INFO_RAW: return adis_single_conversion(indio_dev, chan, 0, val); case IIO_CHAN_INFO_SCALE: switch (chan->type) { case IIO_ANGL_VEL: - *val = 0; - *val2 = IIO_DEGREE_TO_RAD(20000); /* 0.02 degree/sec */ - return IIO_VAL_INT_PLUS_MICRO; + *val = st->chip_info->gyro_max_scale; + *val2 = st->chip_info->gyro_max_val; + return IIO_VAL_FRACTIONAL; case IIO_ACCEL: - *val = 0; - *val2 = IIO_G_TO_M_S_2(800); /* 0.8 mg */ - return IIO_VAL_INT_PLUS_MICRO; + *val = st->chip_info->accel_max_scale; + *val2 = st->chip_info->accel_max_val; + return IIO_VAL_FRACTIONAL; case IIO_MAGN: *val = 0; *val2 = 100; /* 0.0001 gauss */ @@ -702,18 +708,39 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { [ADIS16375] = { .channels = adis16485_channels, .num_channels = ARRAY_SIZE(adis16485_channels), + /* + * storing the value in rad/degree and the scale in degree + * gives us the result in rad and better precession than + * storing the scale directly in rad. + */ + .gyro_max_val = IIO_RAD_TO_DEGREE(22887), + .gyro_max_scale = 300, + .accel_max_val = IIO_M_S_2_TO_G(21973), + .accel_max_scale = 18, }, [ADIS16480] = { .channels = adis16480_channels, .num_channels = ARRAY_SIZE(adis16480_channels), + .gyro_max_val = IIO_RAD_TO_DEGREE(22500), + .gyro_max_scale = 450, + .accel_max_val = IIO_M_S_2_TO_G(12500), + .accel_max_scale = 5, }, [ADIS16485] = { .channels = adis16485_channels, .num_channels = ARRAY_SIZE(adis16485_channels), + .gyro_max_val = IIO_RAD_TO_DEGREE(22500), + .gyro_max_scale = 450, + .accel_max_val = IIO_M_S_2_TO_G(20000), + .accel_max_scale = 5, }, [ADIS16488] = { .channels = adis16480_channels, .num_channels = ARRAY_SIZE(adis16480_channels), + .gyro_max_val = IIO_RAD_TO_DEGREE(22500), + .gyro_max_scale = 450, + .accel_max_val = IIO_M_S_2_TO_G(22500), + .accel_max_scale = 18, }, }; diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c index e0017c2..f53e9a8 100644 --- a/drivers/iio/imu/adis_trigger.c +++ b/drivers/iio/imu/adis_trigger.c @@ -60,7 +60,7 @@ int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev) iio_trigger_set_drvdata(adis->trig, adis); ret = iio_trigger_register(adis->trig); - indio_dev->trig = adis->trig; + indio_dev->trig = iio_trigger_get(adis->trig); if (ret) goto error_free_irq; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c index 4295171..30fce67 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c @@ -25,6 +25,16 @@ #include #include "inv_mpu_iio.h" +static void inv_clear_kfifo(struct inv_mpu6050_state *st) +{ + unsigned long flags; + + /* take the spin lock sem to avoid interrupt kick in */ + spin_lock_irqsave(&st->time_stamp_lock, flags); + kfifo_reset(&st->timestamps); + spin_unlock_irqrestore(&st->time_stamp_lock, flags); +} + int inv_reset_fifo(struct iio_dev *indio_dev) { int result; @@ -51,6 +61,10 @@ int inv_reset_fifo(struct iio_dev *indio_dev) INV_MPU6050_BIT_FIFO_RST); if (result) goto reset_fifo_fail; + + /* clear timestamps fifo */ + inv_clear_kfifo(st); + /* enable interrupt */ if (st->chip_config.accl_fifo_enable || st->chip_config.gyro_fifo_enable) { @@ -84,16 +98,6 @@ reset_fifo_fail: return result; } -static void inv_clear_kfifo(struct inv_mpu6050_state *st) -{ - unsigned long flags; - - /* take the spin lock sem to avoid interrupt kick in */ - spin_lock_irqsave(&st->time_stamp_lock, flags); - kfifo_reset(&st->timestamps); - spin_unlock_irqrestore(&st->time_stamp_lock, flags); -} - /** * inv_mpu6050_irq_handler() - Cache a timestamp at each data ready interrupt. */ @@ -185,7 +189,6 @@ end_session: flush_fifo: /* Flush HW and SW FIFOs. */ inv_reset_fifo(indio_dev); - inv_clear_kfifo(st); mutex_unlock(&indio_dev->mlock); iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c index 03b9372..926fcce 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c @@ -135,7 +135,7 @@ int inv_mpu6050_probe_trigger(struct iio_dev *indio_dev) ret = iio_trigger_register(st->trig); if (ret) goto error_free_irq; - indio_dev->trig = st->trig; + indio_dev->trig = iio_trigger_get(st->trig); return 0; diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index fe25042..37b52bd 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -96,7 +96,7 @@ unsigned int iio_buffer_poll(struct file *filp, struct iio_buffer *rb = indio_dev->buffer; if (!indio_dev->info) - return -ENODEV; + return 0; poll_wait(filp, &rb->pollq, wait); if (iio_buffer_data_available(rb)) @@ -953,7 +953,7 @@ static int iio_buffer_update_demux(struct iio_dev *indio_dev, /* Now we have the two masks, work from least sig and build up sizes */ for_each_set_bit(out_ind, - indio_dev->active_scan_mask, + buffer->scan_mask, indio_dev->masklength) { in_ind = find_next_bit(indio_dev->active_scan_mask, indio_dev->masklength, diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c index f9360f4..05b5994 100644 --- a/drivers/iio/industrialio-event.c +++ b/drivers/iio/industrialio-event.c @@ -83,7 +83,7 @@ static unsigned int iio_event_poll(struct file *filep, unsigned int events = 0; if (!indio_dev->info) - return -ENODEV; + return events; poll_wait(filep, &ev_int->wait, wait); diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index 1e8e94d..4fc88e6 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -178,7 +178,7 @@ static struct iio_channel *of_iio_channel_get_by_name(struct device_node *np, index = of_property_match_string(np, "io-channel-names", name); chan = of_iio_channel_get(np, index); - if (!IS_ERR(chan)) + if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER) break; else if (name && index >= 0) { pr_err("ERROR: could not get IIO channel %s:%s(%i)\n", diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index 52bbcfa..476aa13 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -42,7 +42,8 @@ #define ST_MAGN_FS_AVL_5600MG 5600 #define ST_MAGN_FS_AVL_8000MG 8000 #define ST_MAGN_FS_AVL_8100MG 8100 -#define ST_MAGN_FS_AVL_10000MG 10000 +#define ST_MAGN_FS_AVL_12000MG 12000 +#define ST_MAGN_FS_AVL_16000MG 16000 /* CUSTOM VALUES FOR SENSOR 1 */ #define ST_MAGN_1_WAI_EXP 0x3c @@ -69,20 +70,20 @@ #define ST_MAGN_1_FS_AVL_4700_VAL 0x05 #define ST_MAGN_1_FS_AVL_5600_VAL 0x06 #define ST_MAGN_1_FS_AVL_8100_VAL 0x07 -#define ST_MAGN_1_FS_AVL_1300_GAIN_XY 1100 -#define ST_MAGN_1_FS_AVL_1900_GAIN_XY 855 -#define ST_MAGN_1_FS_AVL_2500_GAIN_XY 670 -#define ST_MAGN_1_FS_AVL_4000_GAIN_XY 450 -#define ST_MAGN_1_FS_AVL_4700_GAIN_XY 400 -#define ST_MAGN_1_FS_AVL_5600_GAIN_XY 330 -#define ST_MAGN_1_FS_AVL_8100_GAIN_XY 230 -#define ST_MAGN_1_FS_AVL_1300_GAIN_Z 980 -#define ST_MAGN_1_FS_AVL_1900_GAIN_Z 760 -#define ST_MAGN_1_FS_AVL_2500_GAIN_Z 600 -#define ST_MAGN_1_FS_AVL_4000_GAIN_Z 400 -#define ST_MAGN_1_FS_AVL_4700_GAIN_Z 355 -#define ST_MAGN_1_FS_AVL_5600_GAIN_Z 295 -#define ST_MAGN_1_FS_AVL_8100_GAIN_Z 205 +#define ST_MAGN_1_FS_AVL_1300_GAIN_XY 909 +#define ST_MAGN_1_FS_AVL_1900_GAIN_XY 1169 +#define ST_MAGN_1_FS_AVL_2500_GAIN_XY 1492 +#define ST_MAGN_1_FS_AVL_4000_GAIN_XY 2222 +#define ST_MAGN_1_FS_AVL_4700_GAIN_XY 2500 +#define ST_MAGN_1_FS_AVL_5600_GAIN_XY 3030 +#define ST_MAGN_1_FS_AVL_8100_GAIN_XY 4347 +#define ST_MAGN_1_FS_AVL_1300_GAIN_Z 1020 +#define ST_MAGN_1_FS_AVL_1900_GAIN_Z 1315 +#define ST_MAGN_1_FS_AVL_2500_GAIN_Z 1666 +#define ST_MAGN_1_FS_AVL_4000_GAIN_Z 2500 +#define ST_MAGN_1_FS_AVL_4700_GAIN_Z 2816 +#define ST_MAGN_1_FS_AVL_5600_GAIN_Z 3389 +#define ST_MAGN_1_FS_AVL_8100_GAIN_Z 4878 #define ST_MAGN_1_MULTIREAD_BIT false /* CUSTOM VALUES FOR SENSOR 2 */ @@ -105,10 +106,12 @@ #define ST_MAGN_2_FS_MASK 0x60 #define ST_MAGN_2_FS_AVL_4000_VAL 0x00 #define ST_MAGN_2_FS_AVL_8000_VAL 0x01 -#define ST_MAGN_2_FS_AVL_10000_VAL 0x02 -#define ST_MAGN_2_FS_AVL_4000_GAIN 430 -#define ST_MAGN_2_FS_AVL_8000_GAIN 230 -#define ST_MAGN_2_FS_AVL_10000_GAIN 230 +#define ST_MAGN_2_FS_AVL_12000_VAL 0x02 +#define ST_MAGN_2_FS_AVL_16000_VAL 0x03 +#define ST_MAGN_2_FS_AVL_4000_GAIN 146 +#define ST_MAGN_2_FS_AVL_8000_GAIN 292 +#define ST_MAGN_2_FS_AVL_12000_GAIN 438 +#define ST_MAGN_2_FS_AVL_16000_GAIN 584 #define ST_MAGN_2_MULTIREAD_BIT false #define ST_MAGN_2_OUT_X_L_ADDR 0x28 #define ST_MAGN_2_OUT_Y_L_ADDR 0x2a @@ -266,9 +269,14 @@ static const struct st_sensors st_magn_sensors[] = { .gain = ST_MAGN_2_FS_AVL_8000_GAIN, }, [2] = { - .num = ST_MAGN_FS_AVL_10000MG, - .value = ST_MAGN_2_FS_AVL_10000_VAL, - .gain = ST_MAGN_2_FS_AVL_10000_GAIN, + .num = ST_MAGN_FS_AVL_12000MG, + .value = ST_MAGN_2_FS_AVL_12000_VAL, + .gain = ST_MAGN_2_FS_AVL_12000_GAIN, + }, + [3] = { + .num = ST_MAGN_FS_AVL_16000MG, + .value = ST_MAGN_2_FS_AVL_16000_VAL, + .gain = ST_MAGN_2_FS_AVL_16000_GAIN, }, }, }, diff --git a/drivers/iio/temperature/tmp006.c b/drivers/iio/temperature/tmp006.c index 84a0789..7a80509 100644 --- a/drivers/iio/temperature/tmp006.c +++ b/drivers/iio/temperature/tmp006.c @@ -132,6 +132,9 @@ static int tmp006_write_raw(struct iio_dev *indio_dev, struct tmp006_data *data = iio_priv(indio_dev); int i; + if (mask != IIO_CHAN_INFO_SAMP_FREQ) + return -EINVAL; + for (i = 0; i < ARRAY_SIZE(tmp006_freqs); i++) if ((val == tmp006_freqs[i][0]) && (val2 == tmp006_freqs[i][1])) { diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 42c3058..dbd7d66 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -859,19 +859,27 @@ static void cma_save_ib_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id memcpy(&ib->sib_addr, &path->dgid, 16); } +static __be16 ss_get_port(const struct sockaddr_storage *ss) +{ + if (ss->ss_family == AF_INET) + return ((struct sockaddr_in *)ss)->sin_port; + else if (ss->ss_family == AF_INET6) + return ((struct sockaddr_in6 *)ss)->sin6_port; + BUG(); +} + static void cma_save_ip4_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id, struct cma_hdr *hdr) { - struct sockaddr_in *listen4, *ip4; + struct sockaddr_in *ip4; - listen4 = (struct sockaddr_in *) &listen_id->route.addr.src_addr; ip4 = (struct sockaddr_in *) &id->route.addr.src_addr; - ip4->sin_family = listen4->sin_family; + ip4->sin_family = AF_INET; ip4->sin_addr.s_addr = hdr->dst_addr.ip4.addr; - ip4->sin_port = listen4->sin_port; + ip4->sin_port = ss_get_port(&listen_id->route.addr.src_addr); ip4 = (struct sockaddr_in *) &id->route.addr.dst_addr; - ip4->sin_family = listen4->sin_family; + ip4->sin_family = AF_INET; ip4->sin_addr.s_addr = hdr->src_addr.ip4.addr; ip4->sin_port = hdr->port; } @@ -879,16 +887,15 @@ static void cma_save_ip4_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_i static void cma_save_ip6_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id, struct cma_hdr *hdr) { - struct sockaddr_in6 *listen6, *ip6; + struct sockaddr_in6 *ip6; - listen6 = (struct sockaddr_in6 *) &listen_id->route.addr.src_addr; ip6 = (struct sockaddr_in6 *) &id->route.addr.src_addr; - ip6->sin6_family = listen6->sin6_family; + ip6->sin6_family = AF_INET6; ip6->sin6_addr = hdr->dst_addr.ip6; - ip6->sin6_port = listen6->sin6_port; + ip6->sin6_port = ss_get_port(&listen_id->route.addr.src_addr); ip6 = (struct sockaddr_in6 *) &id->route.addr.dst_addr; - ip6->sin6_family = listen6->sin6_family; + ip6->sin6_family = AF_INET6; ip6->sin6_addr = hdr->src_addr.ip6; ip6->sin6_port = hdr->port; } diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index 3d2e489..ff9163d 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include @@ -65,6 +66,20 @@ struct iwcm_work { struct list_head free_list; }; +static unsigned int default_backlog = 256; + +static struct ctl_table_header *iwcm_ctl_table_hdr; +static struct ctl_table iwcm_ctl_table[] = { + { + .procname = "default_backlog", + .data = &default_backlog, + .maxlen = sizeof(default_backlog), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + /* * The following services provide a mechanism for pre-allocating iwcm_work * elements. The design pre-allocates them based on the cm_id type: @@ -425,6 +440,9 @@ int iw_cm_listen(struct iw_cm_id *cm_id, int backlog) cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); + if (!backlog) + backlog = default_backlog; + ret = alloc_work_entries(cm_id_priv, backlog); if (ret) return ret; @@ -1030,11 +1048,20 @@ static int __init iw_cm_init(void) if (!iwcm_wq) return -ENOMEM; + iwcm_ctl_table_hdr = register_net_sysctl(&init_net, "net/iw_cm", + iwcm_ctl_table); + if (!iwcm_ctl_table_hdr) { + pr_err("iw_cm: couldn't register sysctl paths\n"); + destroy_workqueue(iwcm_wq); + return -ENOMEM; + } + return 0; } static void __exit iw_cm_cleanup(void) { + unregister_net_sysctl_table(iwcm_ctl_table_hdr); destroy_workqueue(iwcm_wq); } diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 56a4b7c..45d67e9 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1124,6 +1124,9 @@ static int ucma_set_ib_path(struct ucma_context *ctx, if (!optlen) return -EINVAL; + memset(&sa_path, 0, sizeof(sa_path)); + sa_path.vlan_id = 0xffff; + ib_sa_unpack_path(path_data->path_rec, &sa_path); ret = rdma_set_ib_paths(ctx->cm_id, &sa_path, 1); if (ret) diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index a841123..c1fef27 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -94,6 +94,17 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, if (dmasync) dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs); + if (!size) + return ERR_PTR(-EINVAL); + + /* + * If the combination of the addr and size requested for this memory + * region causes an integer overflow, return error. + */ + if (((addr + size) < addr) || + PAGE_ALIGN(addr + size) < (addr + size)) + return ERR_PTR(-EINVAL); + if (!can_do_mlock()) return ERR_PTR(-EPERM); diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index ea6203e..2adc143 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1964,20 +1964,21 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file, if (qp->real_qp == qp) { ret = ib_resolve_eth_l2_attrs(qp, attr, &cmd.attr_mask); if (ret) - goto out; + goto release_qp; ret = qp->device->modify_qp(qp, attr, modify_qp_mask(qp->qp_type, cmd.attr_mask), &udata); } else { ret = ib_modify_qp(qp, attr, modify_qp_mask(qp->qp_type, cmd.attr_mask)); } - put_qp_read(qp); - if (ret) - goto out; + goto release_qp; ret = in_len; +release_qp: + put_qp_read(qp); + out: kfree(attr); @@ -2425,6 +2426,8 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file, attr.grh.sgid_index = cmd.attr.grh.sgid_index; attr.grh.hop_limit = cmd.attr.grh.hop_limit; attr.grh.traffic_class = cmd.attr.grh.traffic_class; + attr.vlan_id = 0; + memset(&attr.dmac, 0, sizeof(attr.dmac)); memcpy(attr.grh.dgid.raw, cmd.attr.grh.dgid, 16); ah = ib_create_ah(pd, &attr); diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 08219fb..7a515c8 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -476,6 +476,7 @@ static void ib_uverbs_async_handler(struct ib_uverbs_file *file, entry->desc.async.element = element; entry->desc.async.event_type = event; + entry->desc.async.reserved = 0; entry->counter = counter; list_add_tail(&entry->list, &file->async_file->event_list); diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c index e7bee46..abd9724 100644 --- a/drivers/infiniband/core/uverbs_marshall.c +++ b/drivers/infiniband/core/uverbs_marshall.c @@ -140,5 +140,9 @@ void ib_copy_path_rec_from_user(struct ib_sa_path_rec *dst, dst->packet_life_time = src->packet_life_time; dst->preference = src->preference; dst->packet_life_time_selector = src->packet_life_time_selector; + + memset(dst->smac, 0, sizeof(dst->smac)); + memset(dst->dmac, 0, sizeof(dst->dmac)); + dst->vlan_id = 0xffff; } EXPORT_SYMBOL(ib_copy_path_rec_from_user); diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index f2a3f48..2592ab5 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -64,6 +64,14 @@ enum { #define GUID_TBL_BLK_NUM_ENTRIES 8 #define GUID_TBL_BLK_SIZE (GUID_TBL_ENTRY_SIZE * GUID_TBL_BLK_NUM_ENTRIES) +/* Counters should be saturate once they reach their maximum value */ +#define ASSIGN_32BIT_COUNTER(counter, value) do {\ + if ((value) > U32_MAX) \ + counter = cpu_to_be32(U32_MAX); \ + else \ + counter = cpu_to_be32(value); \ +} while (0) + struct mlx4_mad_rcv_buf { struct ib_grh grh; u8 payload[256]; @@ -730,10 +738,14 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, static void edit_counter(struct mlx4_counter *cnt, struct ib_pma_portcounters *pma_cnt) { - pma_cnt->port_xmit_data = cpu_to_be32((be64_to_cpu(cnt->tx_bytes)>>2)); - pma_cnt->port_rcv_data = cpu_to_be32((be64_to_cpu(cnt->rx_bytes)>>2)); - pma_cnt->port_xmit_packets = cpu_to_be32(be64_to_cpu(cnt->tx_frames)); - pma_cnt->port_rcv_packets = cpu_to_be32(be64_to_cpu(cnt->rx_frames)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data, + (be64_to_cpu(cnt->tx_bytes) >> 2)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data, + (be64_to_cpu(cnt->rx_bytes) >> 2)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets, + be64_to_cpu(cnt->tx_frames)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets, + be64_to_cpu(cnt->rx_frames)); } static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index f9c12e9..1a3d924 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1161,8 +1161,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) struct mlx4_ib_qp *mqp = to_mqp(ibqp); u64 reg_id; struct mlx4_ib_steering *ib_steering = NULL; - enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ? - MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6; + enum mlx4_protocol prot = MLX4_PROT_IB_IPV6; if (mdev->dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) { @@ -1175,8 +1174,10 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) !!(mqp->flags & MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK), prot, ®_id); - if (err) + if (err) { + pr_err("multicast attach op failed, err %d\n", err); goto err_malloc; + } err = add_gid_entry(ibqp, gid); if (err) @@ -1224,8 +1225,7 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) struct net_device *ndev; struct mlx4_ib_gid_entry *ge; u64 reg_id = 0; - enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ? - MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6; + enum mlx4_protocol prot = MLX4_PROT_IB_IPV6; if (mdev->dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) { @@ -1622,6 +1622,7 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev, struct inet6_dev *in6_dev; union ib_gid *pgid; struct inet6_ifaddr *ifp; + union ib_gid default_gid; #endif union ib_gid gid; @@ -1642,12 +1643,15 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev, in_dev_put(in_dev); } #if IS_ENABLED(CONFIG_IPV6) + mlx4_make_default_gid(dev, &default_gid); /* IPv6 gids */ in6_dev = in6_dev_get(dev); if (in6_dev) { read_lock_bh(&in6_dev->lock); list_for_each_entry(ifp, &in6_dev->addr_list, if_list) { pgid = (union ib_gid *)&ifp->addr; + if (!memcmp(pgid, &default_gid, sizeof(*pgid))) + continue; update_gid_table(ibdev, port, pgid, 0, 0); } read_unlock_bh(&in6_dev->lock); @@ -1723,31 +1727,34 @@ static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev) port_state = (netif_running(curr_netdev) && netif_carrier_ok(curr_netdev)) ? IB_PORT_ACTIVE : IB_PORT_DOWN; mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - } else { - reset_gid_table(ibdev, port); - } - /* if using bonding/team and a slave port is down, we don't the bond IP - * based gids in the table since flows that select port by gid may get - * the down port. - */ - if (curr_master && (port_state == IB_PORT_DOWN)) { - reset_gid_table(ibdev, port); - mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - } - /* if bonding is used it is possible that we add it to masters - * only after IP address is assigned to the net bonding - * interface. - */ - if (curr_master && (old_master != curr_master)) { - reset_gid_table(ibdev, port); - mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - mlx4_ib_get_dev_addr(curr_master, ibdev, port); - } + /* if using bonding/team and a slave port is down, we + * don't the bond IP based gids in the table since + * flows that select port by gid may get the down port. + */ + if (curr_master && (port_state == IB_PORT_DOWN)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, + curr_netdev, port); + } + /* if bonding is used it is possible that we add it to + * masters only after IP address is assigned to the + * net bonding interface. + */ + if (curr_master && (old_master != curr_master)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, + curr_netdev, port); + mlx4_ib_get_dev_addr(curr_master, ibdev, port); + } - if (!curr_master && (old_master != curr_master)) { + if (!curr_master && (old_master != curr_master)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, + curr_netdev, port); + mlx4_ib_get_dev_addr(curr_netdev, ibdev, port); + } + } else { reset_gid_table(ibdev, port); - mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - mlx4_ib_get_dev_addr(curr_netdev, ibdev, port); } } diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index d8f4d1f..8d7cd98 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -2274,8 +2274,7 @@ static int build_lso_seg(struct mlx4_wqe_lso_seg *wqe, struct ib_send_wr *wr, memcpy(wqe->header, wr->wr.ud.header, wr->wr.ud.hlen); - *lso_hdr_sz = cpu_to_be32((wr->wr.ud.mss - wr->wr.ud.hlen) << 16 | - wr->wr.ud.hlen); + *lso_hdr_sz = cpu_to_be32(wr->wr.ud.mss << 16 | wr->wr.ud.hlen); *lso_seg_len = halign; return 0; } diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h index 1946101..675d3c7 100644 --- a/drivers/infiniband/hw/qib/qib.h +++ b/drivers/infiniband/hw/qib/qib.h @@ -1080,12 +1080,6 @@ struct qib_devdata { /* control high-level access to EEPROM */ struct mutex eep_lock; uint64_t traffic_wds; - /* active time is kept in seconds, but logged in hours */ - atomic_t active_time; - /* Below are nominal shadow of EEPROM, new since last EEPROM update */ - uint8_t eep_st_errs[QIB_EEP_LOG_CNT]; - uint8_t eep_st_new_errs[QIB_EEP_LOG_CNT]; - uint16_t eep_hrs; /* * masks for which bits of errs, hwerrs that cause * each of the counters to increment. @@ -1307,8 +1301,7 @@ int qib_twsi_blk_rd(struct qib_devdata *dd, int dev, int addr, void *buffer, int qib_twsi_blk_wr(struct qib_devdata *dd, int dev, int addr, const void *buffer, int len); void qib_get_eeprom_info(struct qib_devdata *); -int qib_update_eeprom_log(struct qib_devdata *dd); -void qib_inc_eeprom_err(struct qib_devdata *dd, u32 eidx, u32 incr); +#define qib_inc_eeprom_err(dd, eidx, incr) void qib_dump_lookup_output_queue(struct qib_devdata *); void qib_force_pio_avail_update(struct qib_devdata *); void qib_clear_symerror_on_linkup(unsigned long opaque); diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c index 799a0c3..6abd3ed 100644 --- a/drivers/infiniband/hw/qib/qib_debugfs.c +++ b/drivers/infiniband/hw/qib/qib_debugfs.c @@ -193,6 +193,7 @@ static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) struct qib_qp_iter *iter; loff_t n = *pos; + rcu_read_lock(); iter = qib_qp_iter_init(s->private); if (!iter) return NULL; @@ -224,7 +225,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) { - /* nothing for now */ + rcu_read_unlock(); } static int _qp_stats_seq_show(struct seq_file *s, void *iter_ptr) diff --git a/drivers/infiniband/hw/qib/qib_eeprom.c b/drivers/infiniband/hw/qib/qib_eeprom.c index 4d5d71a..e2280b0 100644 --- a/drivers/infiniband/hw/qib/qib_eeprom.c +++ b/drivers/infiniband/hw/qib/qib_eeprom.c @@ -267,190 +267,9 @@ void qib_get_eeprom_info(struct qib_devdata *dd) "Board SN %s did not pass functional test: %s\n", dd->serial, ifp->if_comment); - memcpy(&dd->eep_st_errs, &ifp->if_errcntp, QIB_EEP_LOG_CNT); - /* - * Power-on (actually "active") hours are kept as little-endian value - * in EEPROM, but as seconds in a (possibly as small as 24-bit) - * atomic_t while running. - */ - atomic_set(&dd->active_time, 0); - dd->eep_hrs = ifp->if_powerhour[0] | (ifp->if_powerhour[1] << 8); - done: vfree(buf); bail:; } -/** - * qib_update_eeprom_log - copy active-time and error counters to eeprom - * @dd: the qlogic_ib device - * - * Although the time is kept as seconds in the qib_devdata struct, it is - * rounded to hours for re-write, as we have only 16 bits in EEPROM. - * First-cut code reads whole (expected) struct qib_flash, modifies, - * re-writes. Future direction: read/write only what we need, assuming - * that the EEPROM had to have been "good enough" for driver init, and - * if not, we aren't making it worse. - * - */ -int qib_update_eeprom_log(struct qib_devdata *dd) -{ - void *buf; - struct qib_flash *ifp; - int len, hi_water; - uint32_t new_time, new_hrs; - u8 csum; - int ret, idx; - unsigned long flags; - - /* first, check if we actually need to do anything. */ - ret = 0; - for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) { - if (dd->eep_st_new_errs[idx]) { - ret = 1; - break; - } - } - new_time = atomic_read(&dd->active_time); - - if (ret == 0 && new_time < 3600) - goto bail; - - /* - * The quick-check above determined that there is something worthy - * of logging, so get current contents and do a more detailed idea. - * read full flash, not just currently used part, since it may have - * been written with a newer definition - */ - len = sizeof(struct qib_flash); - buf = vmalloc(len); - ret = 1; - if (!buf) { - qib_dev_err(dd, - "Couldn't allocate memory to read %u bytes from eeprom for logging\n", - len); - goto bail; - } - - /* Grab semaphore and read current EEPROM. If we get an - * error, let go, but if not, keep it until we finish write. - */ - ret = mutex_lock_interruptible(&dd->eep_lock); - if (ret) { - qib_dev_err(dd, "Unable to acquire EEPROM for logging\n"); - goto free_bail; - } - ret = qib_twsi_blk_rd(dd, dd->twsi_eeprom_dev, 0, buf, len); - if (ret) { - mutex_unlock(&dd->eep_lock); - qib_dev_err(dd, "Unable read EEPROM for logging\n"); - goto free_bail; - } - ifp = (struct qib_flash *)buf; - - csum = flash_csum(ifp, 0); - if (csum != ifp->if_csum) { - mutex_unlock(&dd->eep_lock); - qib_dev_err(dd, "EEPROM cks err (0x%02X, S/B 0x%02X)\n", - csum, ifp->if_csum); - ret = 1; - goto free_bail; - } - hi_water = 0; - spin_lock_irqsave(&dd->eep_st_lock, flags); - for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) { - int new_val = dd->eep_st_new_errs[idx]; - if (new_val) { - /* - * If we have seen any errors, add to EEPROM values - * We need to saturate at 0xFF (255) and we also - * would need to adjust the checksum if we were - * trying to minimize EEPROM traffic - * Note that we add to actual current count in EEPROM, - * in case it was altered while we were running. - */ - new_val += ifp->if_errcntp[idx]; - if (new_val > 0xFF) - new_val = 0xFF; - if (ifp->if_errcntp[idx] != new_val) { - ifp->if_errcntp[idx] = new_val; - hi_water = offsetof(struct qib_flash, - if_errcntp) + idx; - } - /* - * update our shadow (used to minimize EEPROM - * traffic), to match what we are about to write. - */ - dd->eep_st_errs[idx] = new_val; - dd->eep_st_new_errs[idx] = 0; - } - } - /* - * Now update active-time. We would like to round to the nearest hour - * but unless atomic_t are sure to be proper signed ints we cannot, - * because we need to account for what we "transfer" to EEPROM and - * if we log an hour at 31 minutes, then we would need to set - * active_time to -29 to accurately count the _next_ hour. - */ - if (new_time >= 3600) { - new_hrs = new_time / 3600; - atomic_sub((new_hrs * 3600), &dd->active_time); - new_hrs += dd->eep_hrs; - if (new_hrs > 0xFFFF) - new_hrs = 0xFFFF; - dd->eep_hrs = new_hrs; - if ((new_hrs & 0xFF) != ifp->if_powerhour[0]) { - ifp->if_powerhour[0] = new_hrs & 0xFF; - hi_water = offsetof(struct qib_flash, if_powerhour); - } - if ((new_hrs >> 8) != ifp->if_powerhour[1]) { - ifp->if_powerhour[1] = new_hrs >> 8; - hi_water = offsetof(struct qib_flash, if_powerhour) + 1; - } - } - /* - * There is a tiny possibility that we could somehow fail to write - * the EEPROM after updating our shadows, but problems from holding - * the spinlock too long are a much bigger issue. - */ - spin_unlock_irqrestore(&dd->eep_st_lock, flags); - if (hi_water) { - /* we made some change to the data, uopdate cksum and write */ - csum = flash_csum(ifp, 1); - ret = eeprom_write_with_enable(dd, 0, buf, hi_water + 1); - } - mutex_unlock(&dd->eep_lock); - if (ret) - qib_dev_err(dd, "Failed updating EEPROM\n"); - -free_bail: - vfree(buf); -bail: - return ret; -} - -/** - * qib_inc_eeprom_err - increment one of the four error counters - * that are logged to EEPROM. - * @dd: the qlogic_ib device - * @eidx: 0..3, the counter to increment - * @incr: how much to add - * - * Each counter is 8-bits, and saturates at 255 (0xFF). They - * are copied to the EEPROM (aka flash) whenever qib_update_eeprom_log() - * is called, but it can only be called in a context that allows sleep. - * This function can be called even at interrupt level. - */ -void qib_inc_eeprom_err(struct qib_devdata *dd, u32 eidx, u32 incr) -{ - uint new_val; - unsigned long flags; - - spin_lock_irqsave(&dd->eep_st_lock, flags); - new_val = dd->eep_st_new_errs[eidx] + incr; - if (new_val > 255) - new_val = 255; - dd->eep_st_new_errs[eidx] = new_val; - spin_unlock_irqrestore(&dd->eep_st_lock, flags); -} diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c index 84e593d..295f631 100644 --- a/drivers/infiniband/hw/qib/qib_iba6120.c +++ b/drivers/infiniband/hw/qib/qib_iba6120.c @@ -2682,8 +2682,6 @@ static void qib_get_6120_faststats(unsigned long opaque) spin_lock_irqsave(&dd->eep_st_lock, flags); traffic_wds -= dd->traffic_wds; dd->traffic_wds += traffic_wds; - if (traffic_wds >= QIB_TRAFFIC_ACTIVE_THRESHOLD) - atomic_add(5, &dd->active_time); /* S/B #define */ spin_unlock_irqrestore(&dd->eep_st_lock, flags); qib_chk_6120_errormask(dd); diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c index 454c2e7..c86e71b 100644 --- a/drivers/infiniband/hw/qib/qib_iba7220.c +++ b/drivers/infiniband/hw/qib/qib_iba7220.c @@ -3299,8 +3299,6 @@ static void qib_get_7220_faststats(unsigned long opaque) spin_lock_irqsave(&dd->eep_st_lock, flags); traffic_wds -= dd->traffic_wds; dd->traffic_wds += traffic_wds; - if (traffic_wds >= QIB_TRAFFIC_ACTIVE_THRESHOLD) - atomic_add(5, &dd->active_time); /* S/B #define */ spin_unlock_irqrestore(&dd->eep_st_lock, flags); done: mod_timer(&dd->stats_timer, jiffies + HZ * ACTIVITY_TIMER); diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c index d1bd213..0f8d1f0 100644 --- a/drivers/infiniband/hw/qib/qib_iba7322.c +++ b/drivers/infiniband/hw/qib/qib_iba7322.c @@ -5191,8 +5191,6 @@ static void qib_get_7322_faststats(unsigned long opaque) spin_lock_irqsave(&ppd->dd->eep_st_lock, flags); traffic_wds -= ppd->dd->traffic_wds; ppd->dd->traffic_wds += traffic_wds; - if (traffic_wds >= QIB_TRAFFIC_ACTIVE_THRESHOLD) - atomic_add(ACTIVITY_TIMER, &ppd->dd->active_time); spin_unlock_irqrestore(&ppd->dd->eep_st_lock, flags); if (ppd->cpspec->qdr_dfe_on && (ppd->link_speed_active & QIB_IB_QDR) && diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c index 76c3e17..8c9bb6c 100644 --- a/drivers/infiniband/hw/qib/qib_init.c +++ b/drivers/infiniband/hw/qib/qib_init.c @@ -922,7 +922,6 @@ static void qib_shutdown_device(struct qib_devdata *dd) } } - qib_update_eeprom_log(dd); } /** diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 0cad0c4..6a71b2b 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -1324,7 +1324,6 @@ int qib_qp_iter_next(struct qib_qp_iter *iter) struct qib_qp *pqp = iter->qp; struct qib_qp *qp; - rcu_read_lock(); for (; n < dev->qp_table_size; n++) { if (pqp) qp = rcu_dereference(pqp->next); @@ -1332,18 +1331,11 @@ int qib_qp_iter_next(struct qib_qp_iter *iter) qp = rcu_dereference(dev->qp_table[n]); pqp = qp; if (qp) { - if (iter->qp) - atomic_dec(&iter->qp->refcount); - atomic_inc(&qp->refcount); - rcu_read_unlock(); iter->qp = qp; iter->n = n; return 0; } } - rcu_read_unlock(); - if (iter->qp) - atomic_dec(&iter->qp->refcount); return ret; } diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c index 3c8e4e3..b9ccbda 100644 --- a/drivers/infiniband/hw/qib/qib_sysfs.c +++ b/drivers/infiniband/hw/qib/qib_sysfs.c @@ -611,28 +611,6 @@ bail: return ret < 0 ? ret : count; } -static ssize_t show_logged_errs(struct device *device, - struct device_attribute *attr, char *buf) -{ - struct qib_ibdev *dev = - container_of(device, struct qib_ibdev, ibdev.dev); - struct qib_devdata *dd = dd_from_dev(dev); - int idx, count; - - /* force consistency with actual EEPROM */ - if (qib_update_eeprom_log(dd) != 0) - return -ENXIO; - - count = 0; - for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) { - count += scnprintf(buf + count, PAGE_SIZE - count, "%d%c", - dd->eep_st_errs[idx], - idx == (QIB_EEP_LOG_CNT - 1) ? '\n' : ' '); - } - - return count; -} - /* * Dump tempsense regs. in decimal, to ease shell-scripts. */ @@ -679,7 +657,6 @@ static DEVICE_ATTR(nctxts, S_IRUGO, show_nctxts, NULL); static DEVICE_ATTR(nfreectxts, S_IRUGO, show_nfreectxts, NULL); static DEVICE_ATTR(serial, S_IRUGO, show_serial, NULL); static DEVICE_ATTR(boardversion, S_IRUGO, show_boardversion, NULL); -static DEVICE_ATTR(logged_errors, S_IRUGO, show_logged_errs, NULL); static DEVICE_ATTR(tempsense, S_IRUGO, show_tempsense, NULL); static DEVICE_ATTR(localbus_info, S_IRUGO, show_localbus_info, NULL); static DEVICE_ATTR(chip_reset, S_IWUSR, NULL, store_chip_reset); @@ -693,7 +670,6 @@ static struct device_attribute *qib_attributes[] = { &dev_attr_nfreectxts, &dev_attr_serial, &dev_attr_boardversion, - &dev_attr_logged_errors, &dev_attr_tempsense, &dev_attr_localbus_info, &dev_attr_chip_reset, diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 156205a..dd2b610 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -41,6 +41,7 @@ static DEFINE_MUTEX(device_list_mutex); static LIST_HEAD(device_list); static struct workqueue_struct *isert_rx_wq; static struct workqueue_struct *isert_comp_wq; +static struct workqueue_struct *isert_release_wq; static void isert_unmap_cmd(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn); @@ -52,6 +53,13 @@ isert_unreg_rdma(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn); static int isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd, struct isert_rdma_wr *wr); +static int +isert_rdma_post_recvl(struct isert_conn *isert_conn); +static int +isert_rdma_accept(struct isert_conn *isert_conn); +struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np); + +static void isert_release_work(struct work_struct *work); static void isert_qp_event_callback(struct ib_event *e, void *context) @@ -112,9 +120,12 @@ isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id) attr.cap.max_recv_wr = ISERT_QP_MAX_RECV_DTOS; /* * FIXME: Use devattr.max_sge - 2 for max_send_sge as - * work-around for RDMA_READ.. + * work-around for RDMA_READs with ConnectX-2. + * + * Also, still make sure to have at least two SGEs for + * outgoing control PDU responses. */ - attr.cap.max_send_sge = device->dev_attr.max_sge - 2; + attr.cap.max_send_sge = max(2, device->dev_attr.max_sge - 2); isert_conn->max_sge = attr.cap.max_send_sge; attr.cap.max_recv_sge = 1; @@ -129,12 +140,18 @@ isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id) ret = rdma_create_qp(cma_id, isert_conn->conn_pd, &attr); if (ret) { pr_err("rdma_create_qp failed for cma_id %d\n", ret); - return ret; + goto err; } isert_conn->conn_qp = cma_id->qp; pr_debug("rdma_create_qp() returned success >>>>>>>>>>>>>>>>>>>>>>>>>.\n"); return 0; +err: + mutex_lock(&device_list_mutex); + device->cq_active_qps[min_index]--; + mutex_unlock(&device_list_mutex); + + return ret; } static void @@ -191,7 +208,7 @@ fail: static void isert_free_rx_descriptors(struct isert_conn *isert_conn) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct ib_device *ib_dev = isert_conn->conn_device->ib_device; struct iser_rx_desc *rx_desc; int i; @@ -220,12 +237,16 @@ isert_create_device_ib_res(struct isert_device *device) struct isert_cq_desc *cq_desc; struct ib_device_attr *dev_attr; int ret = 0, i, j; + int max_rx_cqe, max_tx_cqe; dev_attr = &device->dev_attr; ret = isert_query_device(ib_dev, dev_attr); if (ret) return ret; + max_rx_cqe = min(ISER_MAX_RX_CQ_LEN, dev_attr->max_cqe); + max_tx_cqe = min(ISER_MAX_TX_CQ_LEN, dev_attr->max_cqe); + /* asign function handlers */ if (dev_attr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) { device->use_fastreg = 1; @@ -261,7 +282,7 @@ isert_create_device_ib_res(struct isert_device *device) isert_cq_rx_callback, isert_cq_event_callback, (void *)&cq_desc[i], - ISER_MAX_RX_CQ_LEN, i); + max_rx_cqe, i); if (IS_ERR(device->dev_rx_cq[i])) { ret = PTR_ERR(device->dev_rx_cq[i]); device->dev_rx_cq[i] = NULL; @@ -273,7 +294,7 @@ isert_create_device_ib_res(struct isert_device *device) isert_cq_tx_callback, isert_cq_event_callback, (void *)&cq_desc[i], - ISER_MAX_TX_CQ_LEN, i); + max_tx_cqe, i); if (IS_ERR(device->dev_tx_cq[i])) { ret = PTR_ERR(device->dev_tx_cq[i]); device->dev_tx_cq[i] = NULL; @@ -482,8 +503,8 @@ err: static int isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { - struct iscsi_np *np = cma_id->context; - struct isert_np *isert_np = np->np_context; + struct isert_np *isert_np = cma_id->context; + struct iscsi_np *np = isert_np->np; struct isert_conn *isert_conn; struct isert_device *device; struct ib_device *ib_dev = cma_id->device; @@ -508,15 +529,15 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) isert_conn->state = ISER_CONN_INIT; INIT_LIST_HEAD(&isert_conn->conn_accept_node); init_completion(&isert_conn->conn_login_comp); + init_completion(&isert_conn->login_req_comp); init_completion(&isert_conn->conn_wait); init_completion(&isert_conn->conn_wait_comp_err); kref_init(&isert_conn->conn_kref); - kref_get(&isert_conn->conn_kref); mutex_init(&isert_conn->conn_mutex); spin_lock_init(&isert_conn->conn_lock); INIT_LIST_HEAD(&isert_conn->conn_fr_pool); + INIT_WORK(&isert_conn->release_work, isert_release_work); - cma_id->context = isert_conn; isert_conn->conn_cm_id = cma_id; isert_conn->responder_resources = event->param.conn.responder_resources; isert_conn->initiator_depth = event->param.conn.initiator_depth; @@ -590,6 +611,14 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) if (ret) goto out_conn_dev; + ret = isert_rdma_post_recvl(isert_conn); + if (ret) + goto out_conn_dev; + + ret = isert_rdma_accept(isert_conn); + if (ret) + goto out_conn_dev; + mutex_lock(&isert_np->np_accept_mutex); list_add_tail(&isert_conn->conn_accept_node, &isert_np->np_accept_list); mutex_unlock(&isert_np->np_accept_mutex); @@ -614,33 +643,37 @@ out_login_buf: kfree(isert_conn->login_buf); out: kfree(isert_conn); + rdma_reject(cma_id, NULL, 0); return ret; } static void isert_connect_release(struct isert_conn *isert_conn) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; struct isert_device *device = isert_conn->conn_device; int cq_index; + struct ib_device *ib_dev = device->ib_device; pr_debug("Entering isert_connect_release(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n"); if (device && device->use_fastreg) isert_conn_free_fastreg_pool(isert_conn); + isert_free_rx_descriptors(isert_conn); + if (isert_conn->conn_cm_id) + rdma_destroy_id(isert_conn->conn_cm_id); + if (isert_conn->conn_qp) { cq_index = ((struct isert_cq_desc *) isert_conn->conn_qp->recv_cq->cq_context)->cq_index; pr_debug("isert_connect_release: cq_index: %d\n", cq_index); + mutex_lock(&device_list_mutex); isert_conn->conn_device->cq_active_qps[cq_index]--; + mutex_unlock(&device_list_mutex); - rdma_destroy_qp(isert_conn->conn_cm_id); + ib_destroy_qp(isert_conn->conn_qp); } - isert_free_rx_descriptors(isert_conn); - rdma_destroy_id(isert_conn->conn_cm_id); - ib_dereg_mr(isert_conn->conn_mr); ib_dealloc_pd(isert_conn->conn_pd); @@ -663,7 +696,19 @@ isert_connect_release(struct isert_conn *isert_conn) static void isert_connected_handler(struct rdma_cm_id *cma_id) { - return; + struct isert_conn *isert_conn = cma_id->qp->qp_context; + + pr_info("conn %p\n", isert_conn); + + if (!kref_get_unless_zero(&isert_conn->conn_kref)) { + pr_warn("conn %p connect_release is running\n", isert_conn); + return; + } + + mutex_lock(&isert_conn->conn_mutex); + if (isert_conn->state != ISER_CONN_FULL_FEATURE) + isert_conn->state = ISER_CONN_UP; + mutex_unlock(&isert_conn->conn_mutex); } static void @@ -684,55 +729,125 @@ isert_put_conn(struct isert_conn *isert_conn) kref_put(&isert_conn->conn_kref, isert_release_conn_kref); } +/** + * isert_conn_terminate() - Initiate connection termination + * @isert_conn: isert connection struct + * + * Notes: + * In case the connection state is FULL_FEATURE, move state + * to TEMINATING and start teardown sequence (rdma_disconnect). + * In case the connection state is UP, complete flush as well. + * + * This routine must be called with conn_mutex held. Thus it is + * safe to call multiple times. + */ static void -isert_disconnect_work(struct work_struct *work) +isert_conn_terminate(struct isert_conn *isert_conn) { - struct isert_conn *isert_conn = container_of(work, - struct isert_conn, conn_logout_work); + int err; - pr_debug("isert_disconnect_work(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n"); - mutex_lock(&isert_conn->conn_mutex); - if (isert_conn->state == ISER_CONN_UP) + switch (isert_conn->state) { + case ISER_CONN_TERMINATING: + break; + case ISER_CONN_UP: + /* + * No flush completions will occur as we didn't + * get to ISER_CONN_FULL_FEATURE yet, complete + * to allow teardown progress. + */ + complete(&isert_conn->conn_wait_comp_err); + case ISER_CONN_FULL_FEATURE: /* FALLTHRU */ + pr_info("Terminating conn %p state %d\n", + isert_conn, isert_conn->state); isert_conn->state = ISER_CONN_TERMINATING; - - if (isert_conn->post_recv_buf_count == 0 && - atomic_read(&isert_conn->post_send_buf_count) == 0) { - mutex_unlock(&isert_conn->conn_mutex); - goto wake_up; - } - if (!isert_conn->conn_cm_id) { - mutex_unlock(&isert_conn->conn_mutex); - isert_put_conn(isert_conn); - return; + err = rdma_disconnect(isert_conn->conn_cm_id); + if (err) + pr_warn("Failed rdma_disconnect isert_conn %p\n", + isert_conn); + break; + default: + pr_warn("conn %p teminating in state %d\n", + isert_conn, isert_conn->state); } +} + +static int +isert_np_cma_handler(struct isert_np *isert_np, + enum rdma_cm_event_type event) +{ + pr_debug("isert np %p, handling event %d\n", isert_np, event); - if (isert_conn->disconnect) { - /* Send DREQ/DREP towards our initiator */ - rdma_disconnect(isert_conn->conn_cm_id); + switch (event) { + case RDMA_CM_EVENT_DEVICE_REMOVAL: + isert_np->np_cm_id = NULL; + break; + case RDMA_CM_EVENT_ADDR_CHANGE: + isert_np->np_cm_id = isert_setup_id(isert_np); + if (IS_ERR(isert_np->np_cm_id)) { + pr_err("isert np %p setup id failed: %ld\n", + isert_np, PTR_ERR(isert_np->np_cm_id)); + isert_np->np_cm_id = NULL; + } + break; + default: + pr_err("isert np %p Unexpected event %d\n", + isert_np, event); } + return -1; +} + +static int +isert_disconnected_handler(struct rdma_cm_id *cma_id, + enum rdma_cm_event_type event) +{ + struct isert_np *isert_np = cma_id->context; + struct isert_conn *isert_conn; + bool terminating = false; + + if (isert_np->np_cm_id == cma_id) + return isert_np_cma_handler(cma_id->context, event); + + isert_conn = cma_id->qp->qp_context; + + mutex_lock(&isert_conn->conn_mutex); + terminating = (isert_conn->state == ISER_CONN_TERMINATING); + isert_conn_terminate(isert_conn); mutex_unlock(&isert_conn->conn_mutex); -wake_up: + pr_info("conn %p completing conn_wait\n", isert_conn); complete(&isert_conn->conn_wait); - isert_put_conn(isert_conn); + + if (terminating) + goto out; + + mutex_lock(&isert_np->np_accept_mutex); + if (!list_empty(&isert_conn->conn_accept_node)) { + list_del_init(&isert_conn->conn_accept_node); + isert_put_conn(isert_conn); + queue_work(isert_release_wq, &isert_conn->release_work); + } + mutex_unlock(&isert_np->np_accept_mutex); + +out: + return 0; } -static void -isert_disconnected_handler(struct rdma_cm_id *cma_id, bool disconnect) +static int +isert_connect_error(struct rdma_cm_id *cma_id) { - struct isert_conn *isert_conn = (struct isert_conn *)cma_id->context; + struct isert_conn *isert_conn = cma_id->qp->qp_context; + + isert_conn->conn_cm_id = NULL; + isert_put_conn(isert_conn); - isert_conn->disconnect = disconnect; - INIT_WORK(&isert_conn->conn_logout_work, isert_disconnect_work); - schedule_work(&isert_conn->conn_logout_work); + return -1; } static int isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { int ret = 0; - bool disconnect = false; pr_debug("isert_cma_handler: event %d status %d conn %p id %p\n", event->event, event->status, cma_id->context, cma_id); @@ -740,6 +855,9 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) switch (event->event) { case RDMA_CM_EVENT_CONNECT_REQUEST: ret = isert_connect_request(cma_id, event); + if (ret) + pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n", + event->event, ret); break; case RDMA_CM_EVENT_ESTABLISHED: isert_connected_handler(cma_id); @@ -747,22 +865,19 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) case RDMA_CM_EVENT_ADDR_CHANGE: /* FALLTHRU */ case RDMA_CM_EVENT_DISCONNECTED: /* FALLTHRU */ case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */ - disconnect = true; case RDMA_CM_EVENT_TIMEWAIT_EXIT: /* FALLTHRU */ - isert_disconnected_handler(cma_id, disconnect); + ret = isert_disconnected_handler(cma_id, event->event); break; + case RDMA_CM_EVENT_REJECTED: /* FALLTHRU */ + case RDMA_CM_EVENT_UNREACHABLE: /* FALLTHRU */ case RDMA_CM_EVENT_CONNECT_ERROR: + ret = isert_connect_error(cma_id); + break; default: pr_err("Unhandled RDMA CMA event: %d\n", event->event); break; } - if (ret != 0) { - pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n", - event->event, ret); - dump_stack(); - } - return ret; } @@ -891,7 +1006,7 @@ isert_init_send_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd, * bit for every ISERT_COMP_BATCH_COUNT number of ib_post_send() calls. */ mutex_lock(&isert_conn->conn_mutex); - if (coalesce && isert_conn->state == ISER_CONN_UP && + if (coalesce && isert_conn->state == ISER_CONN_FULL_FEATURE && ++isert_conn->conn_comp_batch < ISERT_COMP_BATCH_COUNT) { tx_desc->llnode_active = true; llist_add(&tx_desc->comp_llnode, &isert_conn->conn_comp_llist); @@ -970,7 +1085,8 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login, } if (!login->login_failed) { if (login->login_complete) { - if (isert_conn->conn_device->use_fastreg) { + if (!conn->sess->sess_ops->SessionType && + isert_conn->conn_device->use_fastreg) { ret = isert_conn_create_fastreg_pool(isert_conn); if (ret) { pr_err("Conn: %p failed to create" @@ -987,7 +1103,10 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login, if (ret) return ret; - isert_conn->state = ISER_CONN_UP; + /* Now we are in FULL_FEATURE phase */ + mutex_lock(&isert_conn->conn_mutex); + isert_conn->state = ISER_CONN_FULL_FEATURE; + mutex_unlock(&isert_conn->conn_mutex); goto post_send; } @@ -1004,18 +1123,17 @@ post_send: } static void -isert_rx_login_req(struct iser_rx_desc *rx_desc, int rx_buflen, - struct isert_conn *isert_conn) +isert_rx_login_req(struct isert_conn *isert_conn) { + struct iser_rx_desc *rx_desc = (void *)isert_conn->login_req_buf; + int rx_buflen = isert_conn->login_req_len; struct iscsi_conn *conn = isert_conn->conn; struct iscsi_login *login = conn->conn_login; int size; - if (!login) { - pr_err("conn->conn_login is NULL\n"); - dump_stack(); - return; - } + pr_info("conn %p\n", isert_conn); + + WARN_ON_ONCE(!login); if (login->first_request) { struct iscsi_login_req *login_req = @@ -1378,11 +1496,20 @@ isert_rx_completion(struct iser_rx_desc *desc, struct isert_conn *isert_conn, hdr->opcode, hdr->itt, hdr->flags, (int)(xfer_len - ISER_HEADERS_LEN)); - if ((char *)desc == isert_conn->login_req_buf) - isert_rx_login_req(desc, xfer_len - ISER_HEADERS_LEN, - isert_conn); - else + if ((char *)desc == isert_conn->login_req_buf) { + isert_conn->login_req_len = xfer_len - ISER_HEADERS_LEN; + if (isert_conn->conn) { + struct iscsi_login *login = isert_conn->conn->conn_login; + + if (login && !login->first_request) + isert_rx_login_req(isert_conn); + } + mutex_lock(&isert_conn->conn_mutex); + complete(&isert_conn->login_req_comp); + mutex_unlock(&isert_conn->conn_mutex); + } else { isert_rx_do_work(desc, isert_conn); + } ib_dma_sync_single_for_device(ib_dev, rx_dma, rx_buflen, DMA_FROM_DEVICE); @@ -1783,7 +1910,7 @@ isert_cq_rx_comp_err(struct isert_conn *isert_conn) msleep(3000); mutex_lock(&isert_conn->conn_mutex); - isert_conn->state = ISER_CONN_DOWN; + isert_conn_terminate(isert_conn); mutex_unlock(&isert_conn->conn_mutex); iscsit_cause_connection_reinstatement(isert_conn->conn, 0); @@ -1937,7 +2064,7 @@ isert_put_response(struct iscsi_conn *conn, struct iscsi_cmd *cmd) isert_cmd->tx_desc.num_sge = 2; } - isert_init_send_wr(isert_conn, isert_cmd, send_wr, true); + isert_init_send_wr(isert_conn, isert_cmd, send_wr, false); pr_debug("Posting SCSI Response IB_WR_SEND >>>>>>>>>>>>>>>>>>>>>>\n"); @@ -2456,7 +2583,7 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd) &isert_cmd->tx_desc.iscsi_header); isert_init_tx_hdrs(isert_conn, &isert_cmd->tx_desc); isert_init_send_wr(isert_conn, isert_cmd, - &isert_cmd->tx_desc.send_wr, true); + &isert_cmd->tx_desc.send_wr, false); atomic_add(wr->send_wr_num + 1, &isert_conn->post_send_buf_count); @@ -2563,13 +2690,51 @@ isert_response_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state) return ret; } +struct rdma_cm_id * +isert_setup_id(struct isert_np *isert_np) +{ + struct iscsi_np *np = isert_np->np; + struct rdma_cm_id *id; + struct sockaddr *sa; + int ret; + + sa = (struct sockaddr *)&np->np_sockaddr; + pr_debug("ksockaddr: %p, sa: %p\n", &np->np_sockaddr, sa); + + id = rdma_create_id(isert_cma_handler, isert_np, + RDMA_PS_TCP, IB_QPT_RC); + if (IS_ERR(id)) { + pr_err("rdma_create_id() failed: %ld\n", PTR_ERR(id)); + ret = PTR_ERR(id); + goto out; + } + pr_debug("id %p context %p\n", id, id->context); + + ret = rdma_bind_addr(id, sa); + if (ret) { + pr_err("rdma_bind_addr() failed: %d\n", ret); + goto out_id; + } + + ret = rdma_listen(id, ISERT_RDMA_LISTEN_BACKLOG); + if (ret) { + pr_err("rdma_listen() failed: %d\n", ret); + goto out_id; + } + + return id; +out_id: + rdma_destroy_id(id); +out: + return ERR_PTR(ret); +} + static int isert_setup_np(struct iscsi_np *np, struct __kernel_sockaddr_storage *ksockaddr) { struct isert_np *isert_np; struct rdma_cm_id *isert_lid; - struct sockaddr *sa; int ret; isert_np = kzalloc(sizeof(struct isert_np), GFP_KERNEL); @@ -2581,9 +2746,8 @@ isert_setup_np(struct iscsi_np *np, mutex_init(&isert_np->np_accept_mutex); INIT_LIST_HEAD(&isert_np->np_accept_list); init_completion(&isert_np->np_login_comp); + isert_np->np = np; - sa = (struct sockaddr *)ksockaddr; - pr_debug("ksockaddr: %p, sa: %p\n", ksockaddr, sa); /* * Setup the np->np_sockaddr from the passed sockaddr setup * in iscsi_target_configfs.c code.. @@ -2591,37 +2755,20 @@ isert_setup_np(struct iscsi_np *np, memcpy(&np->np_sockaddr, ksockaddr, sizeof(struct __kernel_sockaddr_storage)); - isert_lid = rdma_create_id(isert_cma_handler, np, RDMA_PS_TCP, - IB_QPT_RC); + isert_lid = isert_setup_id(isert_np); if (IS_ERR(isert_lid)) { - pr_err("rdma_create_id() for isert_listen_handler failed: %ld\n", - PTR_ERR(isert_lid)); ret = PTR_ERR(isert_lid); goto out; } - ret = rdma_bind_addr(isert_lid, sa); - if (ret) { - pr_err("rdma_bind_addr() for isert_lid failed: %d\n", ret); - goto out_lid; - } - - ret = rdma_listen(isert_lid, ISERT_RDMA_LISTEN_BACKLOG); - if (ret) { - pr_err("rdma_listen() for isert_lid failed: %d\n", ret); - goto out_lid; - } - isert_np->np_cm_id = isert_lid; np->np_context = isert_np; - pr_debug("Setup isert_lid->context: %p\n", isert_lid->context); return 0; -out_lid: - rdma_destroy_id(isert_lid); out: kfree(isert_np); + return ret; } @@ -2657,7 +2804,15 @@ isert_get_login_rx(struct iscsi_conn *conn, struct iscsi_login *login) struct isert_conn *isert_conn = (struct isert_conn *)conn->context; int ret; - pr_debug("isert_get_login_rx before conn_login_comp conn: %p\n", conn); + pr_info("before login_req comp conn: %p\n", isert_conn); + ret = wait_for_completion_interruptible(&isert_conn->login_req_comp); + if (ret) { + pr_err("isert_conn %p interrupted before got login req\n", + isert_conn); + return ret; + } + reinit_completion(&isert_conn->login_req_comp); + /* * For login requests after the first PDU, isert_rx_login_req() will * kick schedule_delayed_work(&conn->login_work) as the packet is @@ -2667,11 +2822,15 @@ isert_get_login_rx(struct iscsi_conn *conn, struct iscsi_login *login) if (!login->first_request) return 0; + isert_rx_login_req(isert_conn); + + pr_info("before conn_login_comp conn: %p\n", conn); ret = wait_for_completion_interruptible(&isert_conn->conn_login_comp); if (ret) return ret; - pr_debug("isert_get_login_rx processing login->req: %p\n", login->req); + pr_info("processing login->req: %p\n", login->req); + return 0; } @@ -2749,17 +2908,10 @@ accept_wait: isert_conn->conn = conn; max_accept = 0; - ret = isert_rdma_post_recvl(isert_conn); - if (ret) - return ret; - - ret = isert_rdma_accept(isert_conn); - if (ret) - return ret; - isert_set_conn_info(np, conn, isert_conn); - pr_debug("Processing isert_accept_np: isert_conn: %p\n", isert_conn); + pr_debug("Processing isert_conn: %p\n", isert_conn); + return 0; } @@ -2768,12 +2920,31 @@ isert_free_np(struct iscsi_np *np) { struct isert_np *isert_np = (struct isert_np *)np->np_context; - rdma_destroy_id(isert_np->np_cm_id); + if (isert_np->np_cm_id) + rdma_destroy_id(isert_np->np_cm_id); np->np_context = NULL; kfree(isert_np); } +static void isert_release_work(struct work_struct *work) +{ + struct isert_conn *isert_conn = container_of(work, + struct isert_conn, + release_work); + + pr_info("Starting release conn %p\n", isert_conn); + + wait_for_completion(&isert_conn->conn_wait); + + mutex_lock(&isert_conn->conn_mutex); + isert_conn->state = ISER_CONN_DOWN; + mutex_unlock(&isert_conn->conn_mutex); + + pr_info("Destroying conn %p\n", isert_conn); + isert_put_conn(isert_conn); +} + static void isert_wait_conn(struct iscsi_conn *conn) { struct isert_conn *isert_conn = conn->context; @@ -2781,10 +2952,6 @@ static void isert_wait_conn(struct iscsi_conn *conn) pr_debug("isert_wait_conn: Starting \n"); mutex_lock(&isert_conn->conn_mutex); - if (isert_conn->conn_cm_id) { - pr_debug("Calling rdma_disconnect from isert_wait_conn\n"); - rdma_disconnect(isert_conn->conn_cm_id); - } /* * Only wait for conn_wait_comp_err if the isert_conn made it * into full feature phase.. @@ -2793,13 +2960,12 @@ static void isert_wait_conn(struct iscsi_conn *conn) mutex_unlock(&isert_conn->conn_mutex); return; } - if (isert_conn->state == ISER_CONN_UP) - isert_conn->state = ISER_CONN_TERMINATING; + isert_conn_terminate(isert_conn); mutex_unlock(&isert_conn->conn_mutex); wait_for_completion(&isert_conn->conn_wait_comp_err); - wait_for_completion(&isert_conn->conn_wait); + queue_work(isert_release_wq, &isert_conn->release_work); } static void isert_free_conn(struct iscsi_conn *conn) @@ -2845,10 +3011,21 @@ static int __init isert_init(void) goto destroy_rx_wq; } + isert_release_wq = alloc_workqueue("isert_release_wq", WQ_UNBOUND, + WQ_UNBOUND_MAX_ACTIVE); + if (!isert_release_wq) { + pr_err("Unable to allocate isert_release_wq\n"); + ret = -ENOMEM; + goto destroy_comp_wq; + } + iscsit_register_transport(&iser_target_transport); - pr_debug("iSER_TARGET[0] - Loaded iser_target_transport\n"); + pr_info("iSER_TARGET[0] - Loaded iser_target_transport\n"); + return 0; +destroy_comp_wq: + destroy_workqueue(isert_comp_wq); destroy_rx_wq: destroy_workqueue(isert_rx_wq); return ret; @@ -2857,6 +3034,7 @@ destroy_rx_wq: static void __exit isert_exit(void) { flush_scheduled_work(); + destroy_workqueue(isert_release_wq); destroy_workqueue(isert_comp_wq); destroy_workqueue(isert_rx_wq); iscsit_unregister_transport(&iser_target_transport); diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index cbecaab..1178c5b 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -23,6 +23,7 @@ enum iser_ib_op_code { enum iser_conn_state { ISER_CONN_INIT, ISER_CONN_UP, + ISER_CONN_FULL_FEATURE, ISER_CONN_TERMINATING, ISER_CONN_DOWN, }; @@ -102,6 +103,7 @@ struct isert_conn { char *login_req_buf; char *login_rsp_buf; u64 login_req_dma; + int login_req_len; u64 login_rsp_dma; unsigned int conn_rx_desc_head; struct iser_rx_desc *conn_rx_descs; @@ -109,13 +111,13 @@ struct isert_conn { struct iscsi_conn *conn; struct list_head conn_accept_node; struct completion conn_login_comp; + struct completion login_req_comp; struct iser_tx_desc conn_login_tx_desc; struct rdma_cm_id *conn_cm_id; struct ib_pd *conn_pd; struct ib_mr *conn_mr; struct ib_qp *conn_qp; struct isert_device *conn_device; - struct work_struct conn_logout_work; struct mutex conn_mutex; struct completion conn_wait; struct completion conn_wait_comp_err; @@ -124,10 +126,10 @@ struct isert_conn { int conn_fr_pool_size; /* lock to protect fastreg pool */ spinlock_t conn_lock; + struct work_struct release_work; #define ISERT_COMP_BATCH_COUNT 8 int conn_comp_batch; struct llist_head conn_comp_llist; - bool disconnect; }; #define ISERT_MAX_CQ 64 @@ -158,6 +160,7 @@ struct isert_device { }; struct isert_np { + struct iscsi_np *np; struct semaphore np_sem; struct rdma_cm_id *np_cm_id; struct mutex np_accept_mutex; diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index e96c07e..ca0bc6c 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -120,6 +120,7 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr); static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event); static struct scsi_transport_template *ib_srp_transport_template; +static struct workqueue_struct *srp_remove_wq; static struct ib_client srp_client = { .name = "srp", @@ -539,7 +540,7 @@ static bool srp_queue_remove_work(struct srp_target_port *target) spin_unlock_irq(&target->lock); if (changed) - queue_work(system_long_wq, &target->remove_work); + queue_work(srp_remove_wq, &target->remove_work); return changed; } @@ -2886,9 +2887,10 @@ static void srp_remove_one(struct ib_device *device) spin_unlock(&host->target_lock); /* - * Wait for target port removal tasks. + * Wait for tl_err and target port removal tasks. */ flush_workqueue(system_long_wq); + flush_workqueue(srp_remove_wq); kfree(host); } @@ -2940,16 +2942,22 @@ static int __init srp_init_module(void) indirect_sg_entries = cmd_sg_entries; } + srp_remove_wq = create_workqueue("srp_remove"); + if (IS_ERR(srp_remove_wq)) { + ret = PTR_ERR(srp_remove_wq); + goto out; + } + + ret = -ENOMEM; ib_srp_transport_template = srp_attach_transport(&ib_srp_transport_functions); if (!ib_srp_transport_template) - return -ENOMEM; + goto destroy_wq; ret = class_register(&srp_class); if (ret) { pr_err("couldn't register class infiniband_srp\n"); - srp_release_transport(ib_srp_transport_template); - return ret; + goto release_tr; } ib_sa_register_client(&srp_sa_client); @@ -2957,13 +2965,22 @@ static int __init srp_init_module(void) ret = ib_register_client(&srp_client); if (ret) { pr_err("couldn't register IB client\n"); - srp_release_transport(ib_srp_transport_template); - ib_sa_unregister_client(&srp_sa_client); - class_unregister(&srp_class); - return ret; + goto unreg_sa; } - return 0; +out: + return ret; + +unreg_sa: + ib_sa_unregister_client(&srp_sa_client); + class_unregister(&srp_class); + +release_tr: + srp_release_transport(ib_srp_transport_template); + +destroy_wq: + destroy_workqueue(srp_remove_wq); + goto out; } static void __exit srp_cleanup_module(void) @@ -2972,6 +2989,7 @@ static void __exit srp_cleanup_module(void) ib_sa_unregister_client(&srp_sa_client); class_unregister(&srp_class); srp_release_transport(ib_srp_transport_template); + destroy_workqueue(srp_remove_wq); } module_init(srp_init_module); diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index d1078ce..0097b8d 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -2091,6 +2091,7 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch) if (!qp_init) goto out; +retry: ch->cq = ib_create_cq(sdev->device, srpt_completion, NULL, ch, ch->rq_size + srp_sq_size, 0); if (IS_ERR(ch->cq)) { @@ -2114,6 +2115,13 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch) ch->qp = ib_create_qp(sdev->pd, qp_init); if (IS_ERR(ch->qp)) { ret = PTR_ERR(ch->qp); + if (ret == -ENOMEM) { + srp_sq_size /= 2; + if (srp_sq_size >= MIN_SRPT_SQ_SIZE) { + ib_destroy_cq(ch->cq); + goto retry; + } + } printk(KERN_ERR "failed to create_qp ret= %d\n", ret); goto err_destroy_cq; } diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index ce953d8..fb787c3 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -757,20 +757,23 @@ static int evdev_handle_set_keycode_v2(struct input_dev *dev, void __user *p) */ static int evdev_handle_get_val(struct evdev_client *client, struct input_dev *dev, unsigned int type, - unsigned long *bits, unsigned int max, - unsigned int size, void __user *p, int compat) + unsigned long *bits, unsigned int maxbit, + unsigned int maxlen, void __user *p, + int compat) { int ret; unsigned long *mem; + size_t len; - mem = kmalloc(sizeof(unsigned long) * max, GFP_KERNEL); + len = BITS_TO_LONGS(maxbit) * sizeof(unsigned long); + mem = kmalloc(len, GFP_KERNEL); if (!mem) return -ENOMEM; spin_lock_irq(&dev->event_lock); spin_lock(&client->buffer_lock); - memcpy(mem, bits, sizeof(unsigned long) * max); + memcpy(mem, bits, len); spin_unlock(&dev->event_lock); @@ -778,7 +781,7 @@ static int evdev_handle_get_val(struct evdev_client *client, spin_unlock_irq(&client->buffer_lock); - ret = bits_to_user(mem, max, size, p, compat); + ret = bits_to_user(mem, maxbit, maxlen, p, compat); if (ret < 0) evdev_queue_syn_dropped(client); diff --git a/drivers/input/input.c b/drivers/input/input.c index 1c4c0db..29ca0bb 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -257,9 +257,10 @@ static int input_handle_abs_event(struct input_dev *dev, } static int input_get_disposition(struct input_dev *dev, - unsigned int type, unsigned int code, int value) + unsigned int type, unsigned int code, int *pval) { int disposition = INPUT_IGNORE_EVENT; + int value = *pval; switch (type) { @@ -357,6 +358,7 @@ static int input_get_disposition(struct input_dev *dev, break; } + *pval = value; return disposition; } @@ -365,7 +367,7 @@ static void input_handle_event(struct input_dev *dev, { int disposition; - disposition = input_get_disposition(dev, type, code, value); + disposition = input_get_disposition(dev, type, code, &value); if ((disposition & INPUT_PASS_TO_DEVICE) && dev->event) dev->event(dev, type, code, value); diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 603fe0d..517829f 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -1003,9 +1003,19 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id } ep_irq_in = &intf->cur_altsetting->endpoint[1].desc; - usb_fill_bulk_urb(xpad->bulk_out, udev, - usb_sndbulkpipe(udev, ep_irq_in->bEndpointAddress), - xpad->bdata, XPAD_PKT_LEN, xpad_bulk_out, xpad); + if (usb_endpoint_is_bulk_out(ep_irq_in)) { + usb_fill_bulk_urb(xpad->bulk_out, udev, + usb_sndbulkpipe(udev, + ep_irq_in->bEndpointAddress), + xpad->bdata, XPAD_PKT_LEN, + xpad_bulk_out, xpad); + } else { + usb_fill_int_urb(xpad->bulk_out, udev, + usb_sndintpipe(udev, + ep_irq_in->bEndpointAddress), + xpad->bdata, XPAD_PKT_LEN, + xpad_bulk_out, xpad, 0); + } /* * Submit the int URB immediately rather than waiting for open diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index 2dd1d0d..6f5d795 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -1791,14 +1791,6 @@ static const struct dmi_system_id atkbd_dmi_quirk_table[] __initconst = { { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), - DMI_MATCH(DMI_PRODUCT_NAME, "LW25-B7HV"), - }, - .callback = atkbd_deactivate_fixup, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), - DMI_MATCH(DMI_PRODUCT_NAME, "P1-J273B"), }, .callback = atkbd_deactivate_fixup, }, diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index fb15c64..4979b00 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -1047,7 +1047,13 @@ static psmouse_ret_t alps_process_byte(struct psmouse *psmouse) { struct alps_data *priv = psmouse->private; - if ((psmouse->packet[0] & 0xc8) == 0x08) { /* PS/2 packet */ + /* + * Check if we are dealing with a bare PS/2 packet, presumably from + * a device connected to the external PS/2 port. Because bare PS/2 + * protocol does not have enough constant bits to self-synchronize + * properly we only do this if the device is fully synchronized. + */ + if (!psmouse->out_of_sync_cnt && (psmouse->packet[0] & 0xc8) == 0x08) { if (psmouse->pktcnt == 3) { alps_report_bare_ps2_packet(psmouse, psmouse->packet, true); @@ -1071,12 +1077,27 @@ static psmouse_ret_t alps_process_byte(struct psmouse *psmouse) } /* Bytes 2 - pktsize should have 0 in the highest bit */ - if ((priv->proto_version < ALPS_PROTO_V5) && + if (priv->proto_version < ALPS_PROTO_V5 && psmouse->pktcnt >= 2 && psmouse->pktcnt <= psmouse->pktsize && (psmouse->packet[psmouse->pktcnt - 1] & 0x80)) { psmouse_dbg(psmouse, "refusing packet[%i] = %x\n", psmouse->pktcnt - 1, psmouse->packet[psmouse->pktcnt - 1]); + + if (priv->proto_version == ALPS_PROTO_V3 && + psmouse->pktcnt == psmouse->pktsize) { + /* + * Some Dell boxes, such as Latitude E6440 or E7440 + * with closed lid, quite often smash last byte of + * otherwise valid packet with 0xff. Given that the + * next packet is very likely to be valid let's + * report PSMOUSE_FULL_PACKET but not process data, + * rather than reporting PSMOUSE_BAD_DATA and + * filling the logs. + */ + return PSMOUSE_FULL_PACKET; + } + return PSMOUSE_BAD_DATA; } @@ -2148,6 +2169,9 @@ int alps_init(struct psmouse *psmouse) /* We are having trouble resyncing ALPS touchpads so disable it for now */ psmouse->resync_time = 0; + /* Allow 2 invalid packets without resetting device */ + psmouse->resetafter = psmouse->pktsize * 2; + return 0; init_fail: diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 233516a..94eaaf0 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -314,7 +314,7 @@ static void elantech_report_semi_mt_data(struct input_dev *dev, unsigned int x2, unsigned int y2) { elantech_set_slot(dev, 0, num_fingers != 0, x1, y1); - elantech_set_slot(dev, 1, num_fingers == 2, x2, y2); + elantech_set_slot(dev, 1, num_fingers >= 2, x2, y2); } /* @@ -814,6 +814,21 @@ static psmouse_ret_t elantech_process_byte(struct psmouse *psmouse) } /* + * This writes the reg_07 value again to the hardware at the end of every + * set_rate call because the register loses its value. reg_07 allows setting + * absolute mode on v4 hardware + */ +static void elantech_set_rate_restore_reg_07(struct psmouse *psmouse, + unsigned int rate) +{ + struct elantech_data *etd = psmouse->private; + + etd->original_set_rate(psmouse, rate); + if (elantech_write_reg(psmouse, 0x07, etd->reg_07)) + psmouse_err(psmouse, "restoring reg_07 failed\n"); +} + +/* * Put the touchpad into absolute mode */ static int elantech_set_absolute_mode(struct psmouse *psmouse) @@ -1015,6 +1030,8 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse, * Asus K53SV 0x450f01 78, 15, 0c 2 hw buttons * Asus G46VW 0x460f02 00, 18, 0c 2 hw buttons * Asus G750JX 0x360f00 00, 16, 0c 2 hw buttons + * Asus TP500LN 0x381f17 10, 14, 0e clickpad + * Asus X750JN 0x381f17 10, 14, 0e clickpad * Asus UX31 0x361f00 20, 15, 0e clickpad * Asus UX32VD 0x361f02 00, 15, 0e clickpad * Avatar AVIU-145A2 0x361f00 ? clickpad @@ -1253,6 +1270,14 @@ static bool elantech_is_signature_valid(const unsigned char *param) if (param[1] == 0) return true; + /* + * Some hw_version >= 4 models have a revision higher then 20. Meaning + * that param[2] may be 10 or 20, skip the rates check for these. + */ + if ((param[0] & 0x0f) >= 0x06 && (param[1] & 0xaf) == 0x0f && + param[2] < 40) + return true; + for (i = 0; i < ARRAY_SIZE(rates); i++) if (param[2] == rates[i]) return false; @@ -1483,6 +1508,11 @@ int elantech_init(struct psmouse *psmouse) goto init_fail; } + if (etd->fw_version == 0x381f17) { + etd->original_set_rate = psmouse->set_rate; + psmouse->set_rate = elantech_set_rate_restore_reg_07; + } + if (elantech_set_input_params(psmouse)) { psmouse_err(psmouse, "failed to query touchpad range.\n"); goto init_fail; diff --git a/drivers/input/mouse/elantech.h b/drivers/input/mouse/elantech.h index 9e0e2a1..59263a3 100644 --- a/drivers/input/mouse/elantech.h +++ b/drivers/input/mouse/elantech.h @@ -139,6 +139,7 @@ struct elantech_data { struct finger_pos mt[ETP_MAX_FINGERS]; unsigned char parity[256]; int (*send_cmd)(struct psmouse *psmouse, unsigned char c, unsigned char *param); + void (*original_set_rate)(struct psmouse *psmouse, unsigned int rate); }; #ifdef CONFIG_MOUSE_PS2_ELANTECH diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index ec772d9..53f09a8 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -132,13 +132,23 @@ static const struct min_max_quirk min_max_pnpid_table[] = { 1232, 5710, 1156, 4696 }, { - (const char * const []){"LEN0034", "LEN0036", "LEN2004", NULL}, + (const char * const []){"LEN0034", "LEN0036", "LEN0037", + "LEN0039", "LEN2002", "LEN2004", + NULL}, 1024, 5112, 2024, 4832 }, { + (const char * const []){"LEN2000", NULL}, + 1024, 5113, 2021, 4832 + }, + { (const char * const []){"LEN2001", NULL}, 1024, 5022, 2508, 4832 }, + { + (const char * const []){"LEN2006", NULL}, + 1264, 5675, 1171, 4688 + }, { } }; @@ -157,8 +167,9 @@ static const char * const topbuttonpad_pnp_ids[] = { "LEN0034", /* T431s, L440, L540, T540, W540, X1 Carbon 2nd */ "LEN0035", /* X240 */ "LEN0036", /* T440 */ - "LEN0037", + "LEN0037", /* X1 Carbon 2nd */ "LEN0038", + "LEN0039", /* T440s */ "LEN0041", "LEN0042", /* Yoga */ "LEN0045", @@ -166,9 +177,9 @@ static const char * const topbuttonpad_pnp_ids[] = { "LEN0047", "LEN0048", "LEN0049", - "LEN2000", + "LEN2000", /* S540 */ "LEN2001", /* Edge E431 */ - "LEN2002", + "LEN2002", /* Edge E531 */ "LEN2003", "LEN2004", /* L440 */ "LEN2005", @@ -625,10 +636,61 @@ static int synaptics_parse_hw_state(const unsigned char buf[], ((buf[0] & 0x04) >> 1) | ((buf[3] & 0x04) >> 2)); + if ((SYN_CAP_ADV_GESTURE(priv->ext_cap_0c) || + SYN_CAP_IMAGE_SENSOR(priv->ext_cap_0c)) && + hw->w == 2) { + synaptics_parse_agm(buf, priv, hw); + return 1; + } + + hw->x = (((buf[3] & 0x10) << 8) | + ((buf[1] & 0x0f) << 8) | + buf[4]); + hw->y = (((buf[3] & 0x20) << 7) | + ((buf[1] & 0xf0) << 4) | + buf[5]); + hw->z = buf[2]; + hw->left = (buf[0] & 0x01) ? 1 : 0; hw->right = (buf[0] & 0x02) ? 1 : 0; - if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) { + if (SYN_CAP_FORCEPAD(priv->ext_cap_0c)) { + /* + * ForcePads, like Clickpads, use middle button + * bits to report primary button clicks. + * Unfortunately they report primary button not + * only when user presses on the pad above certain + * threshold, but also when there are more than one + * finger on the touchpad, which interferes with + * out multi-finger gestures. + */ + if (hw->z == 0) { + /* No contacts */ + priv->press = priv->report_press = false; + } else if (hw->w >= 4 && ((buf[0] ^ buf[3]) & 0x01)) { + /* + * Single-finger touch with pressure above + * the threshold. If pressure stays long + * enough, we'll start reporting primary + * button. We rely on the device continuing + * sending data even if finger does not + * move. + */ + if (!priv->press) { + priv->press_start = jiffies; + priv->press = true; + } else if (time_after(jiffies, + priv->press_start + + msecs_to_jiffies(50))) { + priv->report_press = true; + } + } else { + priv->press = false; + } + + hw->left = priv->report_press; + + } else if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) { /* * Clickpad's button is transmitted as middle button, * however, since it is primary button, we will report @@ -647,21 +709,6 @@ static int synaptics_parse_hw_state(const unsigned char buf[], hw->down = ((buf[0] ^ buf[3]) & 0x02) ? 1 : 0; } - if ((SYN_CAP_ADV_GESTURE(priv->ext_cap_0c) || - SYN_CAP_IMAGE_SENSOR(priv->ext_cap_0c)) && - hw->w == 2) { - synaptics_parse_agm(buf, priv, hw); - return 1; - } - - hw->x = (((buf[3] & 0x10) << 8) | - ((buf[1] & 0x0f) << 8) | - buf[4]); - hw->y = (((buf[3] & 0x20) << 7) | - ((buf[1] & 0xf0) << 4) | - buf[5]); - hw->z = buf[2]; - if (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) && ((buf[0] ^ buf[3]) & 0x02)) { switch (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) & ~0x01) { diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h index e594af0..fb2e076 100644 --- a/drivers/input/mouse/synaptics.h +++ b/drivers/input/mouse/synaptics.h @@ -78,6 +78,11 @@ * 2 0x08 image sensor image sensor tracks 5 fingers, but only * reports 2. * 2 0x20 report min query 0x0f gives min coord reported + * 2 0x80 forcepad forcepad is a variant of clickpad that + * does not have physical buttons but rather + * uses pressure above certain threshold to + * report primary clicks. Forcepads also have + * clickpad bit set. */ #define SYN_CAP_CLICKPAD(ex0c) ((ex0c) & 0x100000) /* 1-button ClickPad */ #define SYN_CAP_CLICKPAD2BTN(ex0c) ((ex0c) & 0x000100) /* 2-button ClickPad */ @@ -86,6 +91,7 @@ #define SYN_CAP_ADV_GESTURE(ex0c) ((ex0c) & 0x080000) #define SYN_CAP_REDUCED_FILTERING(ex0c) ((ex0c) & 0x000400) #define SYN_CAP_IMAGE_SENSOR(ex0c) ((ex0c) & 0x000800) +#define SYN_CAP_FORCEPAD(ex0c) ((ex0c) & 0x008000) /* synaptics modes query bits */ #define SYN_MODE_ABSOLUTE(m) ((m) & (1 << 7)) @@ -177,6 +183,11 @@ struct synaptics_data { */ struct synaptics_hw_state agm; bool agm_pending; /* new AGM packet received */ + + /* ForcePad handling */ + unsigned long press_start; + bool press; + bool report_press; }; void synaptics_module_init(void); diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 381b20d..dd6d14d 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -101,6 +101,12 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { }, { .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X750LN"), + }, + }, + { + .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), DMI_MATCH(DMI_PRODUCT_NAME , "ProLiant"), DMI_MATCH(DMI_PRODUCT_VERSION, "8500"), @@ -146,6 +152,14 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { }, }, { + /* Medion Akoya E7225 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Medion"), + DMI_MATCH(DMI_PRODUCT_NAME, "Akoya E7225"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), + }, + }, + { /* Blue FB5601 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "blue"), @@ -402,6 +416,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { }, }, { + /* Acer Aspire 7738 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7738"), + }, + }, + { /* Gericom Bellagio */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Gericom"), @@ -458,6 +479,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"), }, }, + { + /* Avatar AVIU-145A6 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel"), + DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"), + }, + }, { } }; @@ -601,6 +629,30 @@ static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"), }, }, + { + /* Fujitsu A544 laptop */ + /* https://bugzilla.redhat.com/show_bug.cgi?id=1111138 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK A544"), + }, + }, + { + /* Fujitsu AH544 laptop */ + /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK AH544"), + }, + }, + { + /* Fujitsu U574 laptop */ + /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"), + }, + }, { } }; @@ -684,6 +736,35 @@ static const struct dmi_system_id __initconst i8042_dmi_dritek_table[] = { { } }; +/* + * Some laptops need keyboard reset before probing for the trackpad to get + * it detected, initialised & finally work. + */ +static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = { + { + /* Gigabyte P35 v2 - Elantech touchpad */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "P35V2"), + }, + }, + { + /* Aorus branded Gigabyte X3 Plus - Elantech touchpad */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "X3"), + }, + }, + { + /* Gigabyte P34 - Elantech touchpad */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "P34"), + }, + }, + { } +}; + #endif /* CONFIG_X86 */ #ifdef CONFIG_PNP @@ -979,6 +1060,9 @@ static int __init i8042_platform_init(void) if (dmi_check_system(i8042_dmi_dritek_table)) i8042_dritek = true; + if (dmi_check_system(i8042_dmi_kbdreset_table)) + i8042_kbdreset = true; + /* * A20 was already enabled during early kernel init. But some buggy * BIOSes (in MSI Laptops) require A20 to be enabled using 8042 to diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index 3807c3e..eb796ff 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -67,6 +67,10 @@ static bool i8042_notimeout; module_param_named(notimeout, i8042_notimeout, bool, 0); MODULE_PARM_DESC(notimeout, "Ignore timeouts signalled by i8042"); +static bool i8042_kbdreset; +module_param_named(kbdreset, i8042_kbdreset, bool, 0); +MODULE_PARM_DESC(kbdreset, "Reset device connected to KBD port"); + #ifdef CONFIG_X86 static bool i8042_dritek; module_param_named(dritek, i8042_dritek, bool, 0); @@ -790,6 +794,16 @@ static int __init i8042_check_aux(void) return -1; /* + * Reset keyboard (needed on some laptops to successfully detect + * touchpad, e.g., some Gigabyte laptop models with Elantech + * touchpads). + */ + if (i8042_kbdreset) { + pr_warn("Attempting to reset device connected to KBD port\n"); + i8042_kbd_write(NULL, (unsigned char) 0xff); + } + +/* * Test AUX IRQ delivery to make sure BIOS did not grab the IRQ and * used it for a PCI card or somethig else. */ diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c index 0cb7ef5..69175b8 100644 --- a/drivers/input/serio/serport.c +++ b/drivers/input/serio/serport.c @@ -21,6 +21,7 @@ #include #include #include +#include MODULE_AUTHOR("Vojtech Pavlik "); MODULE_DESCRIPTION("Input device TTY line discipline"); @@ -198,28 +199,55 @@ static ssize_t serport_ldisc_read(struct tty_struct * tty, struct file * file, u return 0; } +static void serport_set_type(struct tty_struct *tty, unsigned long type) +{ + struct serport *serport = tty->disc_data; + + serport->id.proto = type & 0x000000ff; + serport->id.id = (type & 0x0000ff00) >> 8; + serport->id.extra = (type & 0x00ff0000) >> 16; +} + /* * serport_ldisc_ioctl() allows to set the port protocol, and device ID */ -static int serport_ldisc_ioctl(struct tty_struct * tty, struct file * file, unsigned int cmd, unsigned long arg) +static int serport_ldisc_ioctl(struct tty_struct *tty, struct file *file, + unsigned int cmd, unsigned long arg) { - struct serport *serport = (struct serport*) tty->disc_data; - unsigned long type; - if (cmd == SPIOCSTYPE) { + unsigned long type; + if (get_user(type, (unsigned long __user *) arg)) return -EFAULT; - serport->id.proto = type & 0x000000ff; - serport->id.id = (type & 0x0000ff00) >> 8; - serport->id.extra = (type & 0x00ff0000) >> 16; + serport_set_type(tty, type); + return 0; + } + + return -EINVAL; +} + +#ifdef CONFIG_COMPAT +#define COMPAT_SPIOCSTYPE _IOW('q', 0x01, compat_ulong_t) +static long serport_ldisc_compat_ioctl(struct tty_struct *tty, + struct file *file, + unsigned int cmd, unsigned long arg) +{ + if (cmd == COMPAT_SPIOCSTYPE) { + void __user *uarg = compat_ptr(arg); + compat_ulong_t compat_type; + + if (get_user(compat_type, (compat_ulong_t __user *)uarg)) + return -EFAULT; + serport_set_type(tty, compat_type); return 0; } return -EINVAL; } +#endif static void serport_ldisc_write_wakeup(struct tty_struct * tty) { @@ -243,6 +271,9 @@ static struct tty_ldisc_ops serport_ldisc = { .close = serport_ldisc_close, .read = serport_ldisc_read, .ioctl = serport_ldisc_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = serport_ldisc_compat_ioctl, +#endif .receive_buf = serport_ldisc_receive, .write_wakeup = serport_ldisc_write_wakeup }; diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c index 05f371d..d4b0a31 100644 --- a/drivers/input/tablet/wacom_wac.c +++ b/drivers/input/tablet/wacom_wac.c @@ -700,6 +700,12 @@ static int wacom_intuos_irq(struct wacom_wac *wacom) input_report_key(input, BTN_7, (data[4] & 0x40)); /* Left */ input_report_key(input, BTN_8, (data[4] & 0x80)); /* Down */ input_report_key(input, BTN_0, (data[3] & 0x01)); /* Center */ + + if (data[4] | (data[3] & 0x01)) { + input_report_abs(input, ABS_MISC, PAD_DEVICE_ID); + } else { + input_report_abs(input, ABS_MISC, 0); + } } else if (features->type >= INTUOS5S && features->type <= INTUOSPL) { int i; diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c index a096633..c6f7e91 100644 --- a/drivers/input/touchscreen/usbtouchscreen.c +++ b/drivers/input/touchscreen/usbtouchscreen.c @@ -625,6 +625,9 @@ static int dmc_tsc10_init(struct usbtouch_usb *usbtouch) goto err_out; } + /* TSC-25 data sheet specifies a delay after the RESET command */ + msleep(150); + /* set coordinate output rate */ buf[0] = buf[1] = 0xFF; ret = usb_control_msg(dev, usb_rcvctrlpipe (dev, 0), diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 71776ff..9359740 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1922,9 +1922,15 @@ static void free_pt_##LVL (unsigned long __pt) \ pt = (u64 *)__pt; \ \ for (i = 0; i < 512; ++i) { \ + /* PTE present? */ \ if (!IOMMU_PTE_PRESENT(pt[i])) \ continue; \ \ + /* Large PTE? */ \ + if (PM_PTE_LEVEL(pt[i]) == 0 || \ + PM_PTE_LEVEL(pt[i]) == 7) \ + continue; \ + \ p = (unsigned long)IOMMU_PTE_PAGE(pt[i]); \ FN(p); \ } \ @@ -3227,14 +3233,16 @@ free_domains: static void cleanup_domain(struct protection_domain *domain) { - struct iommu_dev_data *dev_data, *next; + struct iommu_dev_data *entry; unsigned long flags; write_lock_irqsave(&amd_iommu_devtable_lock, flags); - list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) { - __detach_device(dev_data); - atomic_set(&dev_data->bind, 0); + while (!list_empty(&domain->dev_list)) { + entry = list_first_entry(&domain->dev_list, + struct iommu_dev_data, list); + __detach_device(entry); + atomic_set(&entry->bind, 0); } write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 1d9ab39..2ecac46 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -794,8 +794,11 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain) reg |= TTBCR_EAE | (TTBCR_SH_IS << TTBCR_SH0_SHIFT) | (TTBCR_RGN_WBWA << TTBCR_ORGN0_SHIFT) | - (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT) | - (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT); + (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT); + + if (!stage1) + reg |= (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT); + writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR); /* MAIR0 (stage-1 only) */ diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 40f6b47..8855ecb 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1768,7 +1768,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, struct dma_pte *first_pte = NULL, *pte = NULL; phys_addr_t uninitialized_var(pteval); int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; - unsigned long sg_res; + unsigned long sg_res = 0; unsigned int largepage_lvl = 0; unsigned long lvl_pages = 0; @@ -1779,10 +1779,8 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP; - if (sg) - sg_res = 0; - else { - sg_res = nr_pages + 1; + if (!sg) { + sg_res = nr_pages; pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot; } diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index f37d63c..825545c 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -178,6 +178,7 @@ void led_classdev_resume(struct led_classdev *led_cdev) } EXPORT_SYMBOL_GPL(led_classdev_resume); +#ifdef CONFIG_PM_SLEEP static int led_suspend(struct device *dev) { struct led_classdev *led_cdev = dev_get_drvdata(dev); @@ -197,11 +198,9 @@ static int led_resume(struct device *dev) return 0; } +#endif -static const struct dev_pm_ops leds_class_dev_pm_ops = { - .suspend = led_suspend, - .resume = led_resume, -}; +static SIMPLE_DEV_PM_OPS(leds_class_dev_pm_ops, led_suspend, led_resume); /** * led_classdev_register - register a new object of led_classdev class. diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c index 0bf1e4e..19da222 100644 --- a/drivers/lguest/core.c +++ b/drivers/lguest/core.c @@ -176,7 +176,7 @@ static void unmap_switcher(void) bool lguest_address_ok(const struct lguest *lg, unsigned long addr, unsigned long len) { - return (addr+len) / PAGE_SIZE < lg->pfn_limit && (addr+len >= addr); + return addr+len <= lg->pfn_limit * PAGE_SIZE && (addr+len >= addr); } /* diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 5f9c2a6..fbcb622 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -199,7 +199,7 @@ void bch_btree_node_read_done(struct btree *b) struct bset *i = btree_bset_first(b); struct btree_iter *iter; - iter = mempool_alloc(b->c->fill_iter, GFP_NOWAIT); + iter = mempool_alloc(b->c->fill_iter, GFP_NOIO); iter->size = b->c->sb.bucket_size / b->c->sb.block_size; iter->used = 0; diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 4195a01..cc3dc0c 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -564,6 +564,8 @@ static int bitmap_read_sb(struct bitmap *bitmap) if (err) return err; + err = -EINVAL; + sb = kmap_atomic(sb_page); chunksize = le32_to_cpu(sb->chunksize); @@ -883,7 +885,6 @@ void bitmap_unplug(struct bitmap *bitmap) { unsigned long i; int dirty, need_write; - int wait = 0; if (!bitmap || !bitmap->storage.filemap || test_bit(BITMAP_STALE, &bitmap->flags)) @@ -901,16 +902,13 @@ void bitmap_unplug(struct bitmap *bitmap) clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING); write_page(bitmap, bitmap->storage.filemap[i], 0); } - if (dirty) - wait = 1; - } - if (wait) { /* if any writes were performed, we need to wait on them */ - if (bitmap->storage.file) - wait_event(bitmap->write_wait, - atomic_read(&bitmap->pending_writes)==0); - else - md_super_wait(bitmap->mddev); } + if (bitmap->storage.file) + wait_event(bitmap->write_wait, + atomic_read(&bitmap->pending_writes)==0); + else + md_super_wait(bitmap->mddev); + if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags)) bitmap_file_kick(bitmap); } diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 66c5d13..03c872f 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -465,6 +465,7 @@ static void __relink_lru(struct dm_buffer *b, int dirty) c->n_buffers[dirty]++; b->list_mode = dirty; list_move(&b->lru_list, &c->lru[dirty]); + b->last_accessed = jiffies; } /*---------------------------------------------------------------- @@ -531,6 +532,19 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t block, end_io(&b->bio, r); } +static void inline_endio(struct bio *bio, int error) +{ + bio_end_io_t *end_fn = bio->bi_private; + + /* + * Reset the bio to free any attached resources + * (e.g. bio integrity profiles). + */ + bio_reset(bio); + + end_fn(bio, error); +} + static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block, bio_end_io_t *end_io) { @@ -542,7 +556,12 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block, b->bio.bi_max_vecs = DM_BUFIO_INLINE_VECS; b->bio.bi_iter.bi_sector = block << b->c->sectors_per_block_bits; b->bio.bi_bdev = b->c->bdev; - b->bio.bi_end_io = end_io; + b->bio.bi_end_io = inline_endio; + /* + * Use of .bi_private isn't a problem here because + * the dm_buffer's inline bio is local to bufio. + */ + b->bio.bi_private = end_io; /* * We assume that if len >= PAGE_SIZE ptr is page-aligned. @@ -1447,9 +1466,9 @@ static void drop_buffers(struct dm_bufio_client *c) /* * Test if the buffer is unused and too old, and commit it. - * At if noio is set, we must not do any I/O because we hold - * dm_bufio_clients_lock and we would risk deadlock if the I/O gets rerouted to - * different bufio client. + * And if GFP_NOFS is used, we must not do any I/O because we hold + * dm_bufio_clients_lock and we would risk deadlock if the I/O gets + * rerouted to different bufio client. */ static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp, unsigned long max_jiffies) @@ -1457,7 +1476,7 @@ static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp, if (jiffies - b->last_accessed < max_jiffies) return 0; - if (!(gfp & __GFP_IO)) { + if (!(gfp & __GFP_FS)) { if (test_bit(B_READING, &b->state) || test_bit(B_WRITING, &b->state) || test_bit(B_DIRTY, &b->state)) @@ -1485,9 +1504,9 @@ static long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) { freed += __cleanup_old_buffer(b, gfp_mask, 0); if (!--nr_to_scan) - break; + return freed; + dm_bufio_cond_resched(); } - dm_bufio_cond_resched(); } return freed; } @@ -1499,7 +1518,7 @@ dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) unsigned long freed; c = container_of(shrink, struct dm_bufio_client, shrinker); - if (sc->gfp_mask & __GFP_IO) + if (sc->gfp_mask & __GFP_FS) dm_bufio_lock(c); else if (!dm_bufio_trylock(c)) return SHRINK_STOP; @@ -1516,7 +1535,7 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc) unsigned long count; c = container_of(shrink, struct dm_bufio_client, shrinker); - if (sc->gfp_mask & __GFP_IO) + if (sc->gfp_mask & __GFP_FS) dm_bufio_lock(c); else if (!dm_bufio_trylock(c)) return 0; @@ -1541,7 +1560,7 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign BUG_ON(block_size < 1 << SECTOR_SHIFT || (block_size & (block_size - 1))); - c = kmalloc(sizeof(*c), GFP_KERNEL); + c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) { r = -ENOMEM; goto bad_client; diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index a87d3fa..b950a80 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -94,6 +94,9 @@ struct cache_disk_superblock { } __packed; struct dm_cache_metadata { + atomic_t ref_count; + struct list_head list; + struct block_device *bdev; struct dm_block_manager *bm; struct dm_space_map *metadata_sm; @@ -669,10 +672,10 @@ static void unpack_value(__le64 value_le, dm_oblock_t *block, unsigned *flags) /*----------------------------------------------------------------*/ -struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, - sector_t data_block_size, - bool may_format_device, - size_t policy_hint_size) +static struct dm_cache_metadata *metadata_open(struct block_device *bdev, + sector_t data_block_size, + bool may_format_device, + size_t policy_hint_size) { int r; struct dm_cache_metadata *cmd; @@ -680,9 +683,10 @@ struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) { DMERR("could not allocate metadata struct"); - return NULL; + return ERR_PTR(-ENOMEM); } + atomic_set(&cmd->ref_count, 1); init_rwsem(&cmd->root_lock); cmd->bdev = bdev; cmd->data_block_size = data_block_size; @@ -705,10 +709,96 @@ struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, return cmd; } +/* + * We keep a little list of ref counted metadata objects to prevent two + * different target instances creating separate bufio instances. This is + * an issue if a table is reloaded before the suspend. + */ +static DEFINE_MUTEX(table_lock); +static LIST_HEAD(table); + +static struct dm_cache_metadata *lookup(struct block_device *bdev) +{ + struct dm_cache_metadata *cmd; + + list_for_each_entry(cmd, &table, list) + if (cmd->bdev == bdev) { + atomic_inc(&cmd->ref_count); + return cmd; + } + + return NULL; +} + +static struct dm_cache_metadata *lookup_or_open(struct block_device *bdev, + sector_t data_block_size, + bool may_format_device, + size_t policy_hint_size) +{ + struct dm_cache_metadata *cmd, *cmd2; + + mutex_lock(&table_lock); + cmd = lookup(bdev); + mutex_unlock(&table_lock); + + if (cmd) + return cmd; + + cmd = metadata_open(bdev, data_block_size, may_format_device, policy_hint_size); + if (!IS_ERR(cmd)) { + mutex_lock(&table_lock); + cmd2 = lookup(bdev); + if (cmd2) { + mutex_unlock(&table_lock); + __destroy_persistent_data_objects(cmd); + kfree(cmd); + return cmd2; + } + list_add(&cmd->list, &table); + mutex_unlock(&table_lock); + } + + return cmd; +} + +static bool same_params(struct dm_cache_metadata *cmd, sector_t data_block_size) +{ + if (cmd->data_block_size != data_block_size) { + DMERR("data_block_size (%llu) different from that in metadata (%llu)\n", + (unsigned long long) data_block_size, + (unsigned long long) cmd->data_block_size); + return false; + } + + return true; +} + +struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, + sector_t data_block_size, + bool may_format_device, + size_t policy_hint_size) +{ + struct dm_cache_metadata *cmd = lookup_or_open(bdev, data_block_size, + may_format_device, policy_hint_size); + + if (!IS_ERR(cmd) && !same_params(cmd, data_block_size)) { + dm_cache_metadata_close(cmd); + return ERR_PTR(-EINVAL); + } + + return cmd; +} + void dm_cache_metadata_close(struct dm_cache_metadata *cmd) { - __destroy_persistent_data_objects(cmd); - kfree(cmd); + if (atomic_dec_and_test(&cmd->ref_count)) { + mutex_lock(&table_lock); + list_del(&cmd->list); + mutex_unlock(&table_lock); + + __destroy_persistent_data_objects(cmd); + kfree(cmd); + } } /* diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index c0ad90d..c10dec0 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -222,7 +222,13 @@ struct cache { struct list_head need_commit_migrations; sector_t migration_threshold; wait_queue_head_t migration_wait; - atomic_t nr_migrations; + atomic_t nr_allocated_migrations; + + /* + * The number of in flight migrations that are performing + * background io. eg, promotion, writeback. + */ + atomic_t nr_io_migrations; wait_queue_head_t quiescing_wait; atomic_t quiescing; @@ -231,7 +237,7 @@ struct cache { /* * cache_size entries, dirty if set */ - dm_cblock_t nr_dirty; + atomic_t nr_dirty; unsigned long *dirty_bitset; /* @@ -259,7 +265,6 @@ struct cache { struct dm_deferred_set *all_io_ds; mempool_t *migration_pool; - struct dm_cache_migration *next_migration; struct dm_cache_policy *policy; unsigned policy_nr_args; @@ -350,10 +355,31 @@ static void free_prison_cell(struct cache *cache, struct dm_bio_prison_cell *cel dm_bio_prison_free_cell(cache->prison, cell); } +static struct dm_cache_migration *alloc_migration(struct cache *cache) +{ + struct dm_cache_migration *mg; + + mg = mempool_alloc(cache->migration_pool, GFP_NOWAIT); + if (mg) { + mg->cache = cache; + atomic_inc(&mg->cache->nr_allocated_migrations); + } + + return mg; +} + +static void free_migration(struct dm_cache_migration *mg) +{ + if (atomic_dec_and_test(&mg->cache->nr_allocated_migrations)) + wake_up(&mg->cache->migration_wait); + + mempool_free(mg, mg->cache->migration_pool); +} + static int prealloc_data_structs(struct cache *cache, struct prealloc *p) { if (!p->mg) { - p->mg = mempool_alloc(cache->migration_pool, GFP_NOWAIT); + p->mg = alloc_migration(cache); if (!p->mg) return -ENOMEM; } @@ -382,7 +408,7 @@ static void prealloc_free_structs(struct cache *cache, struct prealloc *p) free_prison_cell(cache, p->cell1); if (p->mg) - mempool_free(p->mg, cache->migration_pool); + free_migration(p->mg); } static struct dm_cache_migration *prealloc_get_migration(struct prealloc *p) @@ -493,7 +519,7 @@ static bool is_dirty(struct cache *cache, dm_cblock_t b) static void set_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cblock) { if (!test_and_set_bit(from_cblock(cblock), cache->dirty_bitset)) { - cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) + 1); + atomic_inc(&cache->nr_dirty); policy_set_dirty(cache->policy, oblock); } } @@ -502,8 +528,7 @@ static void clear_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cbl { if (test_and_clear_bit(from_cblock(cblock), cache->dirty_bitset)) { policy_clear_dirty(cache->policy, oblock); - cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) - 1); - if (!from_cblock(cache->nr_dirty)) + if (atomic_dec_return(&cache->nr_dirty) == 0) dm_table_event(cache->ti->table); } } @@ -813,24 +838,14 @@ static void remap_to_origin_then_cache(struct cache *cache, struct bio *bio, * Migration covers moving data from the origin device to the cache, or * vice versa. *--------------------------------------------------------------*/ -static void free_migration(struct dm_cache_migration *mg) +static void inc_io_migrations(struct cache *cache) { - mempool_free(mg, mg->cache->migration_pool); + atomic_inc(&cache->nr_io_migrations); } -static void inc_nr_migrations(struct cache *cache) +static void dec_io_migrations(struct cache *cache) { - atomic_inc(&cache->nr_migrations); -} - -static void dec_nr_migrations(struct cache *cache) -{ - atomic_dec(&cache->nr_migrations); - - /* - * Wake the worker in case we're suspending the target. - */ - wake_up(&cache->migration_wait); + atomic_dec(&cache->nr_io_migrations); } static void __cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell, @@ -853,11 +868,10 @@ static void cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell, wake_worker(cache); } -static void cleanup_migration(struct dm_cache_migration *mg) +static void free_io_migration(struct dm_cache_migration *mg) { - struct cache *cache = mg->cache; + dec_io_migrations(mg->cache); free_migration(mg); - dec_nr_migrations(cache); } static void migration_failure(struct dm_cache_migration *mg) @@ -882,7 +896,7 @@ static void migration_failure(struct dm_cache_migration *mg) cell_defer(cache, mg->new_ocell, true); } - cleanup_migration(mg); + free_io_migration(mg); } static void migration_success_pre_commit(struct dm_cache_migration *mg) @@ -891,9 +905,9 @@ static void migration_success_pre_commit(struct dm_cache_migration *mg) struct cache *cache = mg->cache; if (mg->writeback) { - cell_defer(cache, mg->old_ocell, false); clear_dirty(cache, mg->old_oblock, mg->cblock); - cleanup_migration(mg); + cell_defer(cache, mg->old_ocell, false); + free_io_migration(mg); return; } else if (mg->demote) { @@ -903,14 +917,14 @@ static void migration_success_pre_commit(struct dm_cache_migration *mg) mg->old_oblock); if (mg->promote) cell_defer(cache, mg->new_ocell, true); - cleanup_migration(mg); + free_io_migration(mg); return; } } else { if (dm_cache_insert_mapping(cache->cmd, mg->cblock, mg->new_oblock)) { DMWARN_LIMIT("promotion failed; couldn't update on disk metadata"); policy_remove_mapping(cache->policy, mg->new_oblock); - cleanup_migration(mg); + free_io_migration(mg); return; } } @@ -943,18 +957,22 @@ static void migration_success_post_commit(struct dm_cache_migration *mg) } else { if (mg->invalidate) policy_remove_mapping(cache->policy, mg->old_oblock); - cleanup_migration(mg); + free_io_migration(mg); } } else { - if (mg->requeue_holder) + if (mg->requeue_holder) { + clear_dirty(cache, mg->new_oblock, mg->cblock); cell_defer(cache, mg->new_ocell, true); - else { + } else { + /* + * The block was promoted via an overwrite, so it's dirty. + */ + set_dirty(cache, mg->new_oblock, mg->cblock); bio_endio(mg->new_ocell->holder, 0); cell_defer(cache, mg->new_ocell, false); } - clear_dirty(cache, mg->new_oblock, mg->cblock); - cleanup_migration(mg); + free_io_migration(mg); } } @@ -1061,7 +1079,8 @@ static void issue_copy(struct dm_cache_migration *mg) avoid = is_discarded_oblock(cache, mg->new_oblock); - if (!avoid && bio_writes_complete_block(cache, bio)) { + if (writeback_mode(&cache->features) && + !avoid && bio_writes_complete_block(cache, bio)) { issue_overwrite(mg, bio); return; } @@ -1165,7 +1184,7 @@ static void promote(struct cache *cache, struct prealloc *structs, mg->new_ocell = cell; mg->start_jiffies = jiffies; - inc_nr_migrations(cache); + inc_io_migrations(cache); quiesce_migration(mg); } @@ -1188,7 +1207,7 @@ static void writeback(struct cache *cache, struct prealloc *structs, mg->new_ocell = NULL; mg->start_jiffies = jiffies; - inc_nr_migrations(cache); + inc_io_migrations(cache); quiesce_migration(mg); } @@ -1214,7 +1233,7 @@ static void demote_then_promote(struct cache *cache, struct prealloc *structs, mg->new_ocell = new_ocell; mg->start_jiffies = jiffies; - inc_nr_migrations(cache); + inc_io_migrations(cache); quiesce_migration(mg); } @@ -1241,7 +1260,7 @@ static void invalidate(struct cache *cache, struct prealloc *structs, mg->new_ocell = NULL; mg->start_jiffies = jiffies; - inc_nr_migrations(cache); + inc_io_migrations(cache); quiesce_migration(mg); } @@ -1302,7 +1321,7 @@ static void process_discard_bio(struct cache *cache, struct bio *bio) static bool spare_migration_bandwidth(struct cache *cache) { - sector_t current_volume = (atomic_read(&cache->nr_migrations) + 1) * + sector_t current_volume = (atomic_read(&cache->nr_io_migrations) + 1) * cache->sectors_per_block; return current_volume < cache->migration_threshold; } @@ -1657,7 +1676,7 @@ static void stop_quiescing(struct cache *cache) static void wait_for_migrations(struct cache *cache) { - wait_event(cache->migration_wait, !atomic_read(&cache->nr_migrations)); + wait_event(cache->migration_wait, !atomic_read(&cache->nr_allocated_migrations)); } static void stop_worker(struct cache *cache) @@ -1768,9 +1787,6 @@ static void destroy(struct cache *cache) { unsigned i; - if (cache->next_migration) - mempool_free(cache->next_migration, cache->migration_pool); - if (cache->migration_pool) mempool_destroy(cache->migration_pool); @@ -2278,7 +2294,8 @@ static int cache_create(struct cache_args *ca, struct cache **result) INIT_LIST_HEAD(&cache->quiesced_migrations); INIT_LIST_HEAD(&cache->completed_migrations); INIT_LIST_HEAD(&cache->need_commit_migrations); - atomic_set(&cache->nr_migrations, 0); + atomic_set(&cache->nr_allocated_migrations, 0); + atomic_set(&cache->nr_io_migrations, 0); init_waitqueue_head(&cache->migration_wait); init_waitqueue_head(&cache->quiescing_wait); @@ -2286,7 +2303,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) atomic_set(&cache->quiescing_ack, 0); r = -ENOMEM; - cache->nr_dirty = 0; + atomic_set(&cache->nr_dirty, 0); cache->dirty_bitset = alloc_bitset(from_cblock(cache->cache_size)); if (!cache->dirty_bitset) { *error = "could not allocate dirty bitset"; @@ -2338,8 +2355,6 @@ static int cache_create(struct cache_args *ca, struct cache **result) goto bad; } - cache->next_migration = NULL; - cache->need_tick_bio = true; cache->sized = false; cache->invalidate = false; @@ -2828,7 +2843,7 @@ static void cache_status(struct dm_target *ti, status_type_t type, residency = policy_residency(cache->policy); - DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %llu ", + DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %lu ", (unsigned)(DM_CACHE_METADATA_BLOCK_SIZE >> SECTOR_SHIFT), (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata), (unsigned long long)nr_blocks_metadata, @@ -2841,7 +2856,7 @@ static void cache_status(struct dm_target *ti, status_type_t type, (unsigned) atomic_read(&cache->stats.write_miss), (unsigned) atomic_read(&cache->stats.demotion), (unsigned) atomic_read(&cache->stats.promotion), - (unsigned long long) from_cblock(cache->nr_dirty)); + (unsigned long) atomic_read(&cache->nr_dirty)); if (writethrough_mode(&cache->features)) DMEMIT("1 writethrough "); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 53b2132..4a8d19d 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -709,7 +709,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc, for (i = 0; i < ((1 << SECTOR_SHIFT) / 8); i++) crypto_xor(data + i * 8, buf, 8); out: - memset(buf, 0, sizeof(buf)); + memzero_explicit(buf, sizeof(buf)); return r; } @@ -1681,6 +1681,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) unsigned int key_size, opt_params; unsigned long long tmpll; int ret; + size_t iv_size_padding; struct dm_arg_set as; const char *opt_string; char dummy; @@ -1717,12 +1718,23 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) cc->dmreq_start = sizeof(struct ablkcipher_request); cc->dmreq_start += crypto_ablkcipher_reqsize(any_tfm(cc)); - cc->dmreq_start = ALIGN(cc->dmreq_start, crypto_tfm_ctx_alignment()); - cc->dmreq_start += crypto_ablkcipher_alignmask(any_tfm(cc)) & - ~(crypto_tfm_ctx_alignment() - 1); + cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request)); + + if (crypto_ablkcipher_alignmask(any_tfm(cc)) < CRYPTO_MINALIGN) { + /* Allocate the padding exactly */ + iv_size_padding = -(cc->dmreq_start + sizeof(struct dm_crypt_request)) + & crypto_ablkcipher_alignmask(any_tfm(cc)); + } else { + /* + * If the cipher requires greater alignment than kmalloc + * alignment, we don't know the exact position of the + * initialization vector. We must assume worst case. + */ + iv_size_padding = crypto_ablkcipher_alignmask(any_tfm(cc)); + } cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start + - sizeof(struct dm_crypt_request) + cc->iv_size); + sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size); if (!cc->req_pool) { ti->error = "Cannot allocate crypt request mempool"; goto bad; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index db404a0..080e767 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -291,6 +291,19 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, struct request_queue *q = bdev_get_queue(where->bdev); unsigned short logical_block_size = queue_logical_block_size(q); sector_t num_sectors; + unsigned int uninitialized_var(special_cmd_max_sectors); + + /* + * Reject unsupported discard and write same requests. + */ + if (rw & REQ_DISCARD) + special_cmd_max_sectors = q->limits.max_discard_sectors; + else if (rw & REQ_WRITE_SAME) + special_cmd_max_sectors = q->limits.max_write_same_sectors; + if ((rw & (REQ_DISCARD | REQ_WRITE_SAME)) && special_cmd_max_sectors == 0) { + dec_count(io, region, -EOPNOTSUPP); + return; + } /* * where->count may be zero if rw holds a flush and we need to @@ -313,7 +326,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, store_io_and_region_in_bio(bio, io, region); if (rw & REQ_DISCARD) { - num_sectors = min_t(sector_t, q->limits.max_discard_sectors, remaining); + num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining); bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT; remaining -= num_sectors; } else if (rw & REQ_WRITE_SAME) { @@ -322,7 +335,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, */ dp->get_page(dp, &page, &len, &offset); bio_add_page(bio, page, logical_block_size, offset); - num_sectors = min_t(sector_t, q->limits.max_write_same_sectors, remaining); + num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining); bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT; offset = 0; diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c index 08d9a20..c69d0b7 100644 --- a/drivers/md/dm-log-userspace-transfer.c +++ b/drivers/md/dm-log-userspace-transfer.c @@ -272,7 +272,7 @@ int dm_ulog_tfr_init(void) r = cn_add_callback(&ulog_cn_id, "dmlogusr", cn_ulog_callback); if (r) { - cn_del_callback(&ulog_cn_id); + kfree(prealloced_cn_msg); return r; } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 4880b69..5971538 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -785,8 +785,7 @@ struct dm_raid_superblock { __le32 layout; __le32 stripe_sectors; - __u8 pad[452]; /* Round struct to 512 bytes. */ - /* Always set to 0 when writing. */ + /* Remainder of a logical block is zero-filled when writing (see super_sync()). */ } __packed; static int read_disk_sb(struct md_rdev *rdev, int size) @@ -823,7 +822,7 @@ static void super_sync(struct mddev *mddev, struct md_rdev *rdev) test_bit(Faulty, &(rs->dev[i].rdev.flags))) failed_devices |= (1ULL << i); - memset(sb, 0, sizeof(*sb)); + memset(sb + 1, 0, rdev->sb_size - sizeof(*sb)); sb->magic = cpu_to_le32(DM_RAID_MAGIC); sb->features = cpu_to_le32(0); /* No features yet */ @@ -858,7 +857,11 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev) uint64_t events_sb, events_refsb; rdev->sb_start = 0; - rdev->sb_size = sizeof(*sb); + rdev->sb_size = bdev_logical_block_size(rdev->meta_bdev); + if (rdev->sb_size < sizeof(*sb) || rdev->sb_size > PAGE_SIZE) { + DMERR("superblock size of a logical block is no longer valid"); + return -EINVAL; + } ret = read_disk_sb(rdev, rdev->sb_size); if (ret) diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 7dfdb5c..089d627 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -604,6 +604,15 @@ static void write_callback(unsigned long error, void *context) return; } + /* + * If the bio is discard, return an error, but do not + * degrade the array. + */ + if (bio->bi_rw & REQ_DISCARD) { + bio_endio(bio, -EOPNOTSUPP); + return; + } + for (i = 0; i < ms->nr_mirrors; i++) if (test_bit(i, &error)) fail_mirror(ms->mirror + i, DM_RAID1_WRITE_ERROR); diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index ebddef5..c356a10 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1440,8 +1440,6 @@ out: full_bio->bi_private = pe->full_bio_private; atomic_inc(&full_bio->bi_remaining); } - free_pending_exception(pe); - increment_pending_exceptions_done_count(); up_write(&s->lock); @@ -1458,6 +1456,8 @@ out: } retry_origin_bios(s, origin_bios); + + free_pending_exception(pe); } static void commit_callback(void *context, int success) diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 28a9012..b3b0697 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -795,6 +795,8 @@ static int message_stats_create(struct mapped_device *md, return -EINVAL; if (sscanf(argv[2], "/%u%c", &divisor, &dummy) == 1) { + if (!divisor) + return -EINVAL; step = end - start; if (do_div(step, divisor)) step++; diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index e9d33ad..3412b86 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -1295,8 +1295,8 @@ static int __release_metadata_snap(struct dm_pool_metadata *pmd) return r; disk_super = dm_block_data(copy); - dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->data_mapping_root)); - dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->device_details_root)); + dm_btree_del(&pmd->info, le64_to_cpu(disk_super->data_mapping_root)); + dm_btree_del(&pmd->details_info, le64_to_cpu(disk_super->device_details_root)); dm_sm_dec_block(pmd->metadata_sm, held_root); return dm_tm_unlock(pmd->tm, copy); diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 359af3a..c1120eb 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -916,6 +916,24 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block, } } +static void set_pool_mode(struct pool *pool, enum pool_mode new_mode); + +static void check_for_space(struct pool *pool) +{ + int r; + dm_block_t nr_free; + + if (get_pool_mode(pool) != PM_OUT_OF_DATA_SPACE) + return; + + r = dm_pool_get_free_block_count(pool->pmd, &nr_free); + if (r) + return; + + if (nr_free) + set_pool_mode(pool, PM_WRITE); +} + /* * A non-zero return indicates read_only or fail_io mode. * Many callers don't care about the return value. @@ -930,6 +948,8 @@ static int commit(struct pool *pool) r = dm_pool_commit_metadata(pool->pmd); if (r) metadata_operation_failed(pool, "dm_pool_commit_metadata", r); + else + check_for_space(pool); return r; } @@ -948,8 +968,6 @@ static void check_low_water_mark(struct pool *pool, dm_block_t free_blocks) } } -static void set_pool_mode(struct pool *pool, enum pool_mode new_mode); - static int alloc_data_block(struct thin_c *tc, dm_block_t *result) { int r; @@ -1592,7 +1610,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) pool->process_bio = process_bio_read_only; pool->process_discard = process_discard; pool->process_prepared_mapping = process_prepared_mapping; - pool->process_prepared_discard = process_prepared_discard_passdown; + pool->process_prepared_discard = process_prepared_discard; if (!pool->pf.error_if_no_space && no_space_timeout) queue_delayed_work(pool->wq, &pool->no_space_timeout, no_space_timeout); @@ -1704,6 +1722,14 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } + /* + * We must hold the virtual cell before doing the lookup, otherwise + * there's a race with discard. + */ + build_virtual_key(tc->td, block, &key); + if (dm_bio_detain(tc->pool->prison, &key, bio, &cell1, &cell_result)) + return DM_MAPIO_SUBMITTED; + r = dm_thin_find_block(td, block, 0, &result); /* @@ -1727,13 +1753,10 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) * shared flag will be set in their case. */ thin_defer_bio(tc, bio); + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; } - build_virtual_key(tc->td, block, &key); - if (dm_bio_detain(tc->pool->prison, &key, bio, &cell1, &cell_result)) - return DM_MAPIO_SUBMITTED; - build_data_key(tc->td, result.block, &key); if (dm_bio_detain(tc->pool->prison, &key, bio, &cell2, &cell_result)) { cell_defer_no_holder_no_free(tc, &cell1); @@ -1754,6 +1777,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) * of doing so. */ handle_unserviceable_bio(tc->pool, bio); + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; } /* fall through */ @@ -1764,6 +1788,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) * provide the hint to load the metadata into cache. */ thin_defer_bio(tc, bio); + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; default: @@ -1773,6 +1798,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) * pool is switched to fail-io mode. */ bio_io_error(bio); + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; } } @@ -2718,6 +2744,12 @@ static int pool_message(struct dm_target *ti, unsigned argc, char **argv) struct pool_c *pt = ti->private; struct pool *pool = pt->pool; + if (get_pool_mode(pool) >= PM_READ_ONLY) { + DMERR("%s: unable to service pool target messages in READ_ONLY or FAIL mode", + dm_device_name(pool->pool_md)); + return -EINVAL; + } + if (!strcasecmp(argv[0], "create_thin")) r = process_create_thin_mesg(argc, argv, pool); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 65ee3a0..e400591 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2288,7 +2288,7 @@ int dm_setup_md_queue(struct mapped_device *md) return 0; } -static struct mapped_device *dm_find_md(dev_t dev) +struct mapped_device *dm_get_md(dev_t dev) { struct mapped_device *md; unsigned minor = MINOR(dev); @@ -2299,12 +2299,15 @@ static struct mapped_device *dm_find_md(dev_t dev) spin_lock(&_minor_lock); md = idr_find(&_minor_idr, minor); - if (md && (md == MINOR_ALLOCED || - (MINOR(disk_devt(dm_disk(md))) != minor) || - dm_deleting_md(md) || - test_bit(DMF_FREEING, &md->flags))) { - md = NULL; - goto out; + if (md) { + if ((md == MINOR_ALLOCED || + (MINOR(disk_devt(dm_disk(md))) != minor) || + dm_deleting_md(md) || + test_bit(DMF_FREEING, &md->flags))) { + md = NULL; + goto out; + } + dm_get(md); } out: @@ -2312,16 +2315,6 @@ out: return md; } - -struct mapped_device *dm_get_md(dev_t dev) -{ - struct mapped_device *md = dm_find_md(dev); - - if (md) - dm_get(md); - - return md; -} EXPORT_SYMBOL_GPL(dm_get_md); void *dm_get_mdptr(struct mapped_device *md) @@ -2359,10 +2352,16 @@ static void __dm_destroy(struct mapped_device *md, bool wait) set_bit(DMF_FREEING, &md->flags); spin_unlock(&_minor_lock); + /* + * Take suspend_lock so that presuspend and postsuspend methods + * do not race with internal suspend. + */ + mutex_lock(&md->suspend_lock); if (!dm_suspended_md(md)) { dm_table_presuspend_targets(map); dm_table_postsuspend_targets(map); } + mutex_unlock(&md->suspend_lock); /* dm_put_live_table must be before msleep, otherwise deadlock is possible */ dm_put_live_table(md, srcu_idx); diff --git a/drivers/md/md.c b/drivers/md/md.c index 73aedcb..2ffd277 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5333,6 +5333,7 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) printk("md: %s still in use.\n",mdname(mddev)); if (did_freeze) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); } err = -EBUSY; @@ -5347,6 +5348,8 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) mddev->ro = 1; set_disk_ro(mddev->gendisk, 1); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_wakeup_thread(mddev->thread); sysfs_notify_dirent_safe(mddev->sysfs_state); err = 0; } @@ -5390,6 +5393,7 @@ static int do_md_stop(struct mddev * mddev, int mode, mutex_unlock(&mddev->open_mutex); if (did_freeze) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); } return -EBUSY; @@ -5641,8 +5645,7 @@ static int get_bitmap_file(struct mddev * mddev, void __user * arg) char *ptr, *buf = NULL; int err = -ENOMEM; - file = kmalloc(sizeof(*file), GFP_NOIO); - + file = kzalloc(sizeof(*file), GFP_NOIO); if (!file) goto out; @@ -6228,7 +6231,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) mddev->ctime != info->ctime || mddev->level != info->level || /* mddev->layout != info->layout || */ - !mddev->persistent != info->not_persistent|| + mddev->persistent != !info->not_persistent || mddev->chunk_sectors != info->chunk_size >> 9 || /* ignore bottom 8 bits of state, and allow SB_BITMAP_PRESENT to change */ ((state^info->state) & 0xfffffe00) diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h index 37d367b..bf2b80d 100644 --- a/drivers/md/persistent-data/dm-btree-internal.h +++ b/drivers/md/persistent-data/dm-btree-internal.h @@ -42,6 +42,12 @@ struct btree_node { } __packed; +/* + * Locks a block using the btree node validator. + */ +int bn_read_lock(struct dm_btree_info *info, dm_block_t b, + struct dm_block **result); + void inc_children(struct dm_transaction_manager *tm, struct btree_node *n, struct dm_btree_value_type *vt); diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index b88757c..a03178e 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -309,8 +309,8 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent, if (s < 0 && nr_center < -s) { /* not enough in central node */ - shift(left, center, nr_center); - s = nr_center - target; + shift(left, center, -nr_center); + s += nr_center; shift(left, right, s); nr_right += s; } else @@ -323,7 +323,7 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent, if (s > 0 && nr_center < s) { /* not enough in central node */ shift(center, right, nr_center); - s = target - nr_center; + s -= nr_center; shift(left, right, s); nr_left -= s; } else diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index cf9fd67..1b5e13e 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -92,7 +92,7 @@ struct dm_block_validator btree_node_validator = { /*----------------------------------------------------------------*/ -static int bn_read_lock(struct dm_btree_info *info, dm_block_t b, +int bn_read_lock(struct dm_btree_info *info, dm_block_t b, struct dm_block **result) { return dm_tm_read_lock(info->tm, b, &btree_node_validator, result); diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index 416060c..fdd3793 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -255,7 +255,7 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root) int r; struct del_stack *s; - s = kmalloc(sizeof(*s), GFP_KERNEL); + s = kmalloc(sizeof(*s), GFP_NOIO); if (!s) return -ENOMEM; s->info = info; @@ -847,22 +847,26 @@ EXPORT_SYMBOL_GPL(dm_btree_find_lowest_key); * FIXME: We shouldn't use a recursive algorithm when we have limited stack * space. Also this only works for single level trees. */ -static int walk_node(struct ro_spine *s, dm_block_t block, +static int walk_node(struct dm_btree_info *info, dm_block_t block, int (*fn)(void *context, uint64_t *keys, void *leaf), void *context) { int r; unsigned i, nr; + struct dm_block *node; struct btree_node *n; uint64_t keys; - r = ro_step(s, block); - n = ro_node(s); + r = bn_read_lock(info, block, &node); + if (r) + return r; + + n = dm_block_data(node); nr = le32_to_cpu(n->header.nr_entries); for (i = 0; i < nr; i++) { if (le32_to_cpu(n->header.flags) & INTERNAL_NODE) { - r = walk_node(s, value64(n, i), fn, context); + r = walk_node(info, value64(n, i), fn, context); if (r) goto out; } else { @@ -874,7 +878,7 @@ static int walk_node(struct ro_spine *s, dm_block_t block, } out: - ro_pop(s); + dm_tm_unlock(info->tm, node); return r; } @@ -882,15 +886,7 @@ int dm_btree_walk(struct dm_btree_info *info, dm_block_t root, int (*fn)(void *context, uint64_t *keys, void *leaf), void *context) { - int r; - struct ro_spine spine; - BUG_ON(info->levels > 1); - - init_ro_spine(&spine, info); - r = walk_node(&spine, root, fn, context); - exit_ro_spine(&spine); - - return r; + return walk_node(info, root, fn, context); } EXPORT_SYMBOL_GPL(dm_btree_walk); diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index 786b689..199c9cc 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -204,6 +204,27 @@ static void in(struct sm_metadata *smm) smm->recursion_count++; } +static int apply_bops(struct sm_metadata *smm) +{ + int r = 0; + + while (!brb_empty(&smm->uncommitted)) { + struct block_op bop; + + r = brb_pop(&smm->uncommitted, &bop); + if (r) { + DMERR("bug in bop ring buffer"); + break; + } + + r = commit_bop(smm, &bop); + if (r) + break; + } + + return r; +} + static int out(struct sm_metadata *smm) { int r = 0; @@ -216,21 +237,8 @@ static int out(struct sm_metadata *smm) return -ENOMEM; } - if (smm->recursion_count == 1) { - while (!brb_empty(&smm->uncommitted)) { - struct block_op bop; - - r = brb_pop(&smm->uncommitted, &bop); - if (r) { - DMERR("bug in bop ring buffer"); - break; - } - - r = commit_bop(smm, &bop); - if (r) - break; - } - } + if (smm->recursion_count == 1) + apply_bops(smm); smm->recursion_count--; @@ -564,7 +572,9 @@ static int sm_bootstrap_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count { struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); - return smm->ll.nr_blocks; + *count = smm->ll.nr_blocks; + + return 0; } static int sm_bootstrap_get_nr_free(struct dm_space_map *sm, dm_block_t *count) @@ -700,6 +710,12 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks) } old_len = smm->begin; + r = apply_bops(smm); + if (r) { + DMERR("%s: apply_bops failed", __func__); + goto out; + } + r = sm_ll_commit(&smm->ll); if (r) goto out; @@ -769,6 +785,12 @@ int dm_sm_metadata_create(struct dm_space_map *sm, if (r) return r; + r = apply_bops(smm); + if (r) { + DMERR("%s: apply_bops failed", __func__); + return r; + } + return sm_metadata_commit(sm); } diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 407a99e..9afd00b 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -320,7 +320,7 @@ static struct strip_zone *find_zone(struct r0conf *conf, /* * remaps the bio to the target device. we separate two flows. - * power 2 flow and a general flow for the sake of perfromance + * power 2 flow and a general flow for the sake of performance */ static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone, sector_t sector, sector_t *sector_offset) @@ -531,6 +531,9 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio) ? (sector & (chunk_sects-1)) : sector_div(sector, chunk_sects)); + /* Restore due to sector_div */ + sector = bio->bi_iter.bi_sector; + if (sectors < bio_sectors(bio)) { split = bio_split(bio, sectors, GFP_NOIO, fs_bio_set); bio_chain(split, bio); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 56e24c0..47b7c31 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -336,7 +336,7 @@ static void raid1_end_read_request(struct bio *bio, int error) spin_lock_irqsave(&conf->device_lock, flags); if (r1_bio->mddev->degraded == conf->raid_disks || (r1_bio->mddev->degraded == conf->raid_disks-1 && - !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags))) + test_bit(In_sync, &conf->mirrors[mirror].rdev->flags))) uptodate = 1; spin_unlock_irqrestore(&conf->device_lock, flags); } @@ -540,11 +540,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect has_nonrot_disk = 0; choose_next_idle = 0; - if (conf->mddev->recovery_cp < MaxSector && - (this_sector + sectors >= conf->next_resync)) - choose_first = 1; - else - choose_first = 0; + choose_first = (conf->mddev->recovery_cp < this_sector + sectors); for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { sector_t dist; @@ -565,7 +561,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect if (test_bit(WriteMostly, &rdev->flags)) { /* Don't balance among write-mostly, just * use the first as a last resort */ - if (best_disk < 0) { + if (best_dist_disk < 0) { if (is_badblock(rdev, this_sector, sectors, &first_bad, &bad_sectors)) { if (first_bad < this_sector) @@ -574,7 +570,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect best_good_sectors = first_bad - this_sector; } else best_good_sectors = sectors; - best_disk = disk; + best_dist_disk = disk; + best_pending_disk = disk; } continue; } @@ -831,7 +828,7 @@ static void flush_pending_writes(struct r1conf *conf) * there is no normal IO happeing. It must arrange to call * lower_barrier when the particular background IO completes. */ -static void raise_barrier(struct r1conf *conf) +static void raise_barrier(struct r1conf *conf, sector_t sector_nr) { spin_lock_irq(&conf->resync_lock); @@ -841,6 +838,7 @@ static void raise_barrier(struct r1conf *conf) /* block any new IO from starting */ conf->barrier++; + conf->next_resync = sector_nr; /* For these conditions we must wait: * A: while the array is in frozen state @@ -849,14 +847,17 @@ static void raise_barrier(struct r1conf *conf) * C: next_resync + RESYNC_SECTORS > start_next_window, meaning * next resync will reach to the window which normal bios are * handling. + * D: while there are any active requests in the current window. */ wait_event_lock_irq(conf->wait_barrier, !conf->array_frozen && conf->barrier < RESYNC_DEPTH && + conf->current_window_requests == 0 && (conf->start_next_window >= conf->next_resync + RESYNC_SECTORS), conf->resync_lock); + conf->nr_pending++; spin_unlock_irq(&conf->resync_lock); } @@ -866,6 +867,7 @@ static void lower_barrier(struct r1conf *conf) BUG_ON(conf->barrier <= 0); spin_lock_irqsave(&conf->resync_lock, flags); conf->barrier--; + conf->nr_pending--; spin_unlock_irqrestore(&conf->resync_lock, flags); wake_up(&conf->wait_barrier); } @@ -877,12 +879,10 @@ static bool need_to_wait_for_sync(struct r1conf *conf, struct bio *bio) if (conf->array_frozen || !bio) wait = true; else if (conf->barrier && bio_data_dir(bio) == WRITE) { - if (conf->next_resync < RESYNC_WINDOW_SECTORS) - wait = true; - else if ((conf->next_resync - RESYNC_WINDOW_SECTORS - >= bio_end_sector(bio)) || - (conf->next_resync + NEXT_NORMALIO_DISTANCE - <= bio->bi_iter.bi_sector)) + if ((conf->mddev->curr_resync_completed + >= bio_end_sector(bio)) || + (conf->next_resync + NEXT_NORMALIO_DISTANCE + <= bio->bi_iter.bi_sector)) wait = false; else wait = true; @@ -919,8 +919,8 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio) } if (bio && bio_data_dir(bio) == WRITE) { - if (conf->next_resync + NEXT_NORMALIO_DISTANCE - <= bio->bi_iter.bi_sector) { + if (bio->bi_iter.bi_sector >= + conf->mddev->curr_resync_completed) { if (conf->start_next_window == MaxSector) conf->start_next_window = conf->next_resync + @@ -1186,6 +1186,7 @@ read_again: atomic_read(&bitmap->behind_writes) == 0); } r1_bio->read_disk = rdisk; + r1_bio->start_next_window = 0; read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev); bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector, @@ -1476,6 +1477,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) { char b[BDEVNAME_SIZE]; struct r1conf *conf = mddev->private; + unsigned long flags; /* * If it is not operational, then we have already marked it as dead @@ -1495,18 +1497,17 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) return; } set_bit(Blocked, &rdev->flags); + spin_lock_irqsave(&conf->device_lock, flags); if (test_and_clear_bit(In_sync, &rdev->flags)) { - unsigned long flags; - spin_lock_irqsave(&conf->device_lock, flags); mddev->degraded++; set_bit(Faulty, &rdev->flags); - spin_unlock_irqrestore(&conf->device_lock, flags); - /* - * if recovery is running, make sure it aborts. - */ - set_bit(MD_RECOVERY_INTR, &mddev->recovery); } else set_bit(Faulty, &rdev->flags); + spin_unlock_irqrestore(&conf->device_lock, flags); + /* + * if recovery is running, make sure it aborts. + */ + set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(MD_CHANGE_DEVS, &mddev->flags); printk(KERN_ALERT "md/raid1:%s: Disk failure on %s, disabling device.\n" @@ -1548,8 +1549,13 @@ static void close_sync(struct r1conf *conf) mempool_destroy(conf->r1buf_pool); conf->r1buf_pool = NULL; + spin_lock_irq(&conf->resync_lock); conf->next_resync = 0; conf->start_next_window = MaxSector; + conf->current_window_requests += + conf->next_window_requests; + conf->next_window_requests = 0; + spin_unlock_irq(&conf->resync_lock); } static int raid1_spare_active(struct mddev *mddev) @@ -1563,7 +1569,10 @@ static int raid1_spare_active(struct mddev *mddev) * Find all failed disks within the RAID1 configuration * and mark them readable. * Called under mddev lock, so rcu protection not needed. + * device_lock used to avoid races with raid1_end_read_request + * which expects 'In_sync' flags and ->degraded to be consistent. */ + spin_lock_irqsave(&conf->device_lock, flags); for (i = 0; i < conf->raid_disks; i++) { struct md_rdev *rdev = conf->mirrors[i].rdev; struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev; @@ -1593,7 +1602,6 @@ static int raid1_spare_active(struct mddev *mddev) sysfs_notify_dirent_safe(rdev->sysfs_state); } } - spin_lock_irqsave(&conf->device_lock, flags); mddev->degraded -= count; spin_unlock_irqrestore(&conf->device_lock, flags); @@ -2150,7 +2158,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk, d--; rdev = conf->mirrors[d].rdev; if (rdev && - test_bit(In_sync, &rdev->flags)) + !test_bit(Faulty, &rdev->flags)) r1_sync_page_io(rdev, sect, s, conf->tmppage, WRITE); } @@ -2162,7 +2170,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk, d--; rdev = conf->mirrors[d].rdev; if (rdev && - test_bit(In_sync, &rdev->flags)) { + !test_bit(Faulty, &rdev->flags)) { if (r1_sync_page_io(rdev, sect, s, conf->tmppage, READ)) { atomic_add(s, &rdev->corrected_errors); @@ -2541,9 +2549,8 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp bitmap_cond_end_sync(mddev->bitmap, sector_nr); r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO); - raise_barrier(conf); - conf->next_resync = sector_nr; + raise_barrier(conf, sector_nr); rcu_read_lock(); /* diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index cb882aa..a46124e 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1684,13 +1684,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) spin_unlock_irqrestore(&conf->device_lock, flags); return; } - if (test_and_clear_bit(In_sync, &rdev->flags)) { + if (test_and_clear_bit(In_sync, &rdev->flags)) mddev->degraded++; - /* - * if recovery is running, make sure it aborts. - */ - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - } + /* + * If recovery is running, make sure it aborts. + */ + set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(Blocked, &rdev->flags); set_bit(Faulty, &rdev->flags); set_bit(MD_CHANGE_DEVS, &mddev->flags); @@ -2954,6 +2953,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, */ if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) { end_reshape(conf); + close_sync(conf); return 0; } @@ -4411,7 +4411,7 @@ read_more: read_bio->bi_private = r10_bio; read_bio->bi_end_io = end_sync_read; read_bio->bi_rw = READ; - read_bio->bi_flags &= ~(BIO_POOL_MASK - 1); + read_bio->bi_flags &= (~0UL << BIO_RESET_BITS); read_bio->bi_flags |= 1 << BIO_UPTODATE; read_bio->bi_vcnt = 0; read_bio->bi_iter.bi_size = 0; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 16f5c21..b98c70e 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -64,6 +64,10 @@ #define cpu_to_group(cpu) cpu_to_node(cpu) #define ANY_GROUP NUMA_NO_NODE +static bool devices_handle_discard_safely = false; +module_param(devices_handle_discard_safely, bool, 0644); +MODULE_PARM_DESC(devices_handle_discard_safely, + "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions"); static struct workqueue_struct *raid5_wq; /* * Stripe cache @@ -1910,7 +1914,8 @@ static int resize_stripes(struct r5conf *conf, int newsize) conf->slab_cache = sc; conf->active_name = 1-conf->active_name; - conf->pool_size = newsize; + if (!err) + conf->pool_size = newsize; return err; } @@ -2892,7 +2897,8 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s, (s->failed >= 2 && fdev[1]->toread) || (sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite && !test_bit(R5_OVERWRITE, &fdev[0]->flags)) || - (sh->raid_conf->level == 6 && s->failed && s->to_write))) { + ((sh->raid_conf->level == 6 || sh->sector >= sh->raid_conf->mddev->recovery_cp) + && s->failed && s->to_write))) { /* we would like to get this block, possibly by computing it, * otherwise read it if the backing disk is insync */ @@ -3066,7 +3072,8 @@ static void handle_stripe_dirtying(struct r5conf *conf, * generate correct data from the parity. */ if (conf->max_degraded == 2 || - (recovery_cp < MaxSector && sh->sector >= recovery_cp)) { + (recovery_cp < MaxSector && sh->sector >= recovery_cp && + s->failed == 0)) { /* Calculate the real rcw later - for now make it * look like rcw is cheaper */ @@ -3779,6 +3786,8 @@ static void handle_stripe(struct stripe_head *sh) set_bit(R5_Wantwrite, &dev->flags); if (prexor) continue; + if (s.failed > 1) + continue; if (!test_bit(R5_Insync, &dev->flags) || ((i == sh->pd_idx || i == sh->qd_idx) && s.failed == 0)) @@ -6115,7 +6124,7 @@ static int run(struct mddev *mddev) mddev->queue->limits.discard_granularity = stripe; /* * unaligned part of discard request will be ignored, so can't - * guarantee discard_zerors_data + * guarantee discard_zeroes_data */ mddev->queue->limits.discard_zeroes_data = 0; @@ -6140,6 +6149,18 @@ static int run(struct mddev *mddev) !bdev_get_queue(rdev->bdev)-> limits.discard_zeroes_data) discard_supported = false; + /* Unfortunately, discard_zeroes_data is not currently + * a guarantee - just a hint. So we only allow DISCARD + * if the sysadmin has confirmed that only safe devices + * are in use by setting a module parameter. + */ + if (!devices_handle_discard_safely) { + if (discard_supported) { + pr_info("md/raid456: discard support disabled due to uncertainty.\n"); + pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n"); + } + discard_supported = false; + } } if (discard_supported && diff --git a/drivers/media/common/siano/Kconfig b/drivers/media/common/siano/Kconfig index f953d33..4bfbd5f 100644 --- a/drivers/media/common/siano/Kconfig +++ b/drivers/media/common/siano/Kconfig @@ -22,8 +22,7 @@ config SMS_SIANO_DEBUGFS bool "Enable debugfs for smsdvb" depends on SMS_SIANO_MDTV depends on DEBUG_FS - depends on SMS_USB_DRV - depends on CONFIG_SMS_USB_DRV = CONFIG_SMS_SDIO_DRV + depends on SMS_USB_DRV = SMS_SDIO_DRV ---help--- Choose Y to enable visualizing a dump of the frontend diff --git a/drivers/media/dvb-core/dvb-usb-ids.h b/drivers/media/dvb-core/dvb-usb-ids.h index 80643ef..fabe2fc 100644 --- a/drivers/media/dvb-core/dvb-usb-ids.h +++ b/drivers/media/dvb-core/dvb-usb-ids.h @@ -279,6 +279,8 @@ #define USB_PID_PCTV_400E 0x020f #define USB_PID_PCTV_450E 0x0222 #define USB_PID_PCTV_452E 0x021f +#define USB_PID_PCTV_78E 0x025a +#define USB_PID_PCTV_79E 0x0262 #define USB_PID_REALTEK_RTL2831U 0x2831 #define USB_PID_REALTEK_RTL2832U 0x2832 #define USB_PID_TECHNOTREND_CONNECT_S2_3600 0x3007 diff --git a/drivers/media/dvb-frontends/af9013.c b/drivers/media/dvb-frontends/af9013.c index fb504f1..5930aee 100644 --- a/drivers/media/dvb-frontends/af9013.c +++ b/drivers/media/dvb-frontends/af9013.c @@ -606,6 +606,10 @@ static int af9013_set_frontend(struct dvb_frontend *fe) } } + /* Return an error if can't find bandwidth or the right clock */ + if (i == ARRAY_SIZE(coeff_lut)) + return -EINVAL; + ret = af9013_wr_regs(state, 0xae00, coeff_lut[i].val, sizeof(coeff_lut[i].val)); } diff --git a/drivers/media/dvb-frontends/cx24116.c b/drivers/media/dvb-frontends/cx24116.c index 2916d7c..7bc68b3 100644 --- a/drivers/media/dvb-frontends/cx24116.c +++ b/drivers/media/dvb-frontends/cx24116.c @@ -963,6 +963,10 @@ static int cx24116_send_diseqc_msg(struct dvb_frontend *fe, struct cx24116_state *state = fe->demodulator_priv; int i, ret; + /* Validate length */ + if (d->msg_len > sizeof(d->msg)) + return -EINVAL; + /* Dump DiSEqC message */ if (debug) { printk(KERN_INFO "cx24116: %s(", __func__); @@ -974,10 +978,6 @@ static int cx24116_send_diseqc_msg(struct dvb_frontend *fe, printk(") toneburst=%d\n", toneburst); } - /* Validate length */ - if (d->msg_len > (CX24116_ARGLEN - CX24116_DISEQC_MSGOFS)) - return -EINVAL; - /* DiSEqC message */ for (i = 0; i < d->msg_len; i++) state->dsec_cmd.args[CX24116_DISEQC_MSGOFS + i] = d->msg[i]; diff --git a/drivers/media/dvb-frontends/cx24117.c b/drivers/media/dvb-frontends/cx24117.c index a6c3c9e..d2eab06 100644 --- a/drivers/media/dvb-frontends/cx24117.c +++ b/drivers/media/dvb-frontends/cx24117.c @@ -1043,7 +1043,7 @@ static int cx24117_send_diseqc_msg(struct dvb_frontend *fe, dev_dbg(&state->priv->i2c->dev, ")\n"); /* Validate length */ - if (d->msg_len > 15) + if (d->msg_len > sizeof(d->msg)) return -EINVAL; /* DiSEqC message */ diff --git a/drivers/media/dvb-frontends/ds3000.c b/drivers/media/dvb-frontends/ds3000.c index 1e344b0..22e8c20 100644 --- a/drivers/media/dvb-frontends/ds3000.c +++ b/drivers/media/dvb-frontends/ds3000.c @@ -864,6 +864,13 @@ struct dvb_frontend *ds3000_attach(const struct ds3000_config *config, memcpy(&state->frontend.ops, &ds3000_ops, sizeof(struct dvb_frontend_ops)); state->frontend.demodulator_priv = state; + + /* + * Some devices like T480 starts with voltage on. Be sure + * to turn voltage off during init, as this can otherwise + * interfere with Unicable SCR systems. + */ + ds3000_set_voltage(&state->frontend, SEC_VOLTAGE_OFF); return &state->frontend; error3: diff --git a/drivers/media/dvb-frontends/s5h1420.c b/drivers/media/dvb-frontends/s5h1420.c index 93eeaf7..0b4f8fe 100644 --- a/drivers/media/dvb-frontends/s5h1420.c +++ b/drivers/media/dvb-frontends/s5h1420.c @@ -180,7 +180,7 @@ static int s5h1420_send_master_cmd (struct dvb_frontend* fe, int result = 0; dprintk("enter %s\n", __func__); - if (cmd->msg_len > 8) + if (cmd->msg_len > sizeof(cmd->msg)) return -EINVAL; /* setup for DISEQC */ diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c index 8ad3a57..287b977 100644 --- a/drivers/media/dvb-frontends/tda10071.c +++ b/drivers/media/dvb-frontends/tda10071.c @@ -667,6 +667,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe) struct dtv_frontend_properties *c = &fe->dtv_property_cache; int ret, i; u8 mode, rolloff, pilot, inversion, div; + fe_modulation_t modulation; dev_dbg(&priv->i2c->dev, "%s: delivery_system=%d modulation=%d " \ "frequency=%d symbol_rate=%d inversion=%d pilot=%d " \ @@ -701,10 +702,13 @@ static int tda10071_set_frontend(struct dvb_frontend *fe) switch (c->delivery_system) { case SYS_DVBS: + modulation = QPSK; rolloff = 0; pilot = 2; break; case SYS_DVBS2: + modulation = c->modulation; + switch (c->rolloff) { case ROLLOFF_20: rolloff = 2; @@ -749,7 +753,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe) for (i = 0, mode = 0xff; i < ARRAY_SIZE(TDA10071_MODCOD); i++) { if (c->delivery_system == TDA10071_MODCOD[i].delivery_system && - c->modulation == TDA10071_MODCOD[i].modulation && + modulation == TDA10071_MODCOD[i].modulation && c->fec_inner == TDA10071_MODCOD[i].fec) { mode = TDA10071_MODCOD[i].val; dev_dbg(&priv->i2c->dev, "%s: mode found=%02x\n", diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c index 71c8570..112394d 100644 --- a/drivers/media/i2c/adv7604.c +++ b/drivers/media/i2c/adv7604.c @@ -1984,7 +1984,7 @@ static int adv7604_log_status(struct v4l2_subdev *sd) v4l2_info(sd, "HDCP keys read: %s%s\n", (hdmi_read(sd, 0x04) & 0x20) ? "yes" : "no", (hdmi_read(sd, 0x04) & 0x10) ? "ERROR" : ""); - if (!is_hdmi(sd)) { + if (is_hdmi(sd)) { bool audio_pll_locked = hdmi_read(sd, 0x04) & 0x01; bool audio_sample_packet_detect = hdmi_read(sd, 0x18) & 0x01; bool audio_mute = io_read(sd, 0x65) & 0x40; diff --git a/drivers/media/i2c/mt9v032.c b/drivers/media/i2c/mt9v032.c index 36c504b..008ac87 100644 --- a/drivers/media/i2c/mt9v032.c +++ b/drivers/media/i2c/mt9v032.c @@ -305,8 +305,8 @@ mt9v032_update_hblank(struct mt9v032 *mt9v032) if (mt9v032->version->version == MT9V034_CHIP_ID_REV1) min_hblank += (mt9v032->hratio - 1) * 10; - min_hblank = max_t(unsigned int, (int)mt9v032->model->data->min_row_time - crop->width, - (int)min_hblank); + min_hblank = max_t(int, mt9v032->model->data->min_row_time - crop->width, + min_hblank); hblank = max_t(unsigned int, mt9v032->hblank, min_hblank); return mt9v032_write(client, MT9V032_HORIZONTAL_BLANKING, hblank); diff --git a/drivers/media/i2c/smiapp-pll.c b/drivers/media/i2c/smiapp-pll.c index 2335529..ab5d9a3 100644 --- a/drivers/media/i2c/smiapp-pll.c +++ b/drivers/media/i2c/smiapp-pll.c @@ -67,7 +67,7 @@ static void print_pll(struct device *dev, struct smiapp_pll *pll) { dev_dbg(dev, "pre_pll_clk_div\t%d\n", pll->pre_pll_clk_div); dev_dbg(dev, "pll_multiplier \t%d\n", pll->pll_multiplier); - if (pll->flags != SMIAPP_PLL_FLAG_NO_OP_CLOCKS) { + if (!(pll->flags & SMIAPP_PLL_FLAG_NO_OP_CLOCKS)) { dev_dbg(dev, "op_sys_clk_div \t%d\n", pll->op_sys_clk_div); dev_dbg(dev, "op_pix_clk_div \t%d\n", pll->op_pix_clk_div); } @@ -77,7 +77,7 @@ static void print_pll(struct device *dev, struct smiapp_pll *pll) dev_dbg(dev, "ext_clk_freq_hz \t%d\n", pll->ext_clk_freq_hz); dev_dbg(dev, "pll_ip_clk_freq_hz \t%d\n", pll->pll_ip_clk_freq_hz); dev_dbg(dev, "pll_op_clk_freq_hz \t%d\n", pll->pll_op_clk_freq_hz); - if (pll->flags & SMIAPP_PLL_FLAG_NO_OP_CLOCKS) { + if (!(pll->flags & SMIAPP_PLL_FLAG_NO_OP_CLOCKS)) { dev_dbg(dev, "op_sys_clk_freq_hz \t%d\n", pll->op_sys_clk_freq_hz); dev_dbg(dev, "op_pix_clk_freq_hz \t%d\n", diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c index 8741cae..873d062 100644 --- a/drivers/media/i2c/smiapp/smiapp-core.c +++ b/drivers/media/i2c/smiapp/smiapp-core.c @@ -2138,7 +2138,7 @@ static int smiapp_set_selection(struct v4l2_subdev *subdev, ret = smiapp_set_compose(subdev, fh, sel); break; default: - BUG(); + ret = -EINVAL; } mutex_unlock(&sensor->mutex); @@ -2624,7 +2624,9 @@ static int smiapp_registered(struct v4l2_subdev *subdev) pll->flags |= SMIAPP_PLL_FLAG_OP_PIX_CLOCK_PER_LANE; pll->scale_n = sensor->limits[SMIAPP_LIMIT_SCALER_N_MIN]; + mutex_lock(&sensor->mutex); rval = smiapp_update_mode(sensor); + mutex_unlock(&sensor->mutex); if (rval) { dev_err(&client->dev, "update mode failed\n"); goto out_nvm_release; diff --git a/drivers/media/i2c/tda7432.c b/drivers/media/i2c/tda7432.c index 72af644..cf93021 100644 --- a/drivers/media/i2c/tda7432.c +++ b/drivers/media/i2c/tda7432.c @@ -293,7 +293,7 @@ static int tda7432_s_ctrl(struct v4l2_ctrl *ctrl) if (t->mute->val) { lf |= TDA7432_MUTE; lr |= TDA7432_MUTE; - lf |= TDA7432_MUTE; + rf |= TDA7432_MUTE; rr |= TDA7432_MUTE; } /* Mute & update balance*/ diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index 703560f..88c1606 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -106,8 +106,6 @@ static long media_device_enum_entities(struct media_device *mdev, if (ent->name) { strncpy(u_ent.name, ent->name, sizeof(u_ent.name)); u_ent.name[sizeof(u_ent.name) - 1] = '\0'; - } else { - memset(u_ent.name, 0, sizeof(u_ent.name)); } u_ent.type = ent->type; u_ent.revision = ent->revision; diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c index 716bdc5..83f5074 100644 --- a/drivers/media/pci/cx18/cx18-driver.c +++ b/drivers/media/pci/cx18/cx18-driver.c @@ -1091,6 +1091,7 @@ static int cx18_probe(struct pci_dev *pci_dev, setup.addr = ADDR_UNSET; setup.type = cx->options.tuner; setup.mode_mask = T_ANALOG_TV; /* matches TV tuners */ + setup.config = NULL; if (cx->options.radio > 0) setup.mode_mask |= T_RADIO; setup.tuner_callback = (setup.type == TUNER_XC2028) ? diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h index f723f1f..ab85127 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h +++ b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h @@ -30,7 +30,7 @@ /* Offset base used to differentiate between CAPTURE and OUTPUT * while mmaping */ -#define DST_QUEUE_OFF_BASE (TASK_SIZE / 2) +#define DST_QUEUE_OFF_BASE (1 << 30) #define MFC_BANK1_ALLOC_CTX 0 #define MFC_BANK2_ALLOC_CTX 1 diff --git a/drivers/media/platform/sh_veu.c b/drivers/media/platform/sh_veu.c index 744e43b..f698e32 100644 --- a/drivers/media/platform/sh_veu.c +++ b/drivers/media/platform/sh_veu.c @@ -1183,6 +1183,7 @@ static int sh_veu_probe(struct platform_device *pdev) } *vdev = sh_veu_videodev; + vdev->v4l2_dev = &veu->v4l2_dev; spin_lock_init(&veu->lock); mutex_init(&veu->fop_lock); vdev->lock = &veu->fop_lock; diff --git a/drivers/media/platform/vsp1/vsp1_video.c b/drivers/media/platform/vsp1/vsp1_video.c index b4687a8..7245cca 100644 --- a/drivers/media/platform/vsp1/vsp1_video.c +++ b/drivers/media/platform/vsp1/vsp1_video.c @@ -635,8 +635,6 @@ static int vsp1_video_buffer_prepare(struct vb2_buffer *vb) if (vb->num_planes < format->num_planes) return -EINVAL; - buf->video = video; - for (i = 0; i < vb->num_planes; ++i) { buf->addr[i] = vb2_dma_contig_plane_dma_addr(vb, i); buf->length[i] = vb2_plane_size(vb, i); diff --git a/drivers/media/platform/vsp1/vsp1_video.h b/drivers/media/platform/vsp1/vsp1_video.h index d8612a3..47b7a8a 100644 --- a/drivers/media/platform/vsp1/vsp1_video.h +++ b/drivers/media/platform/vsp1/vsp1_video.h @@ -89,7 +89,6 @@ static inline struct vsp1_pipeline *to_vsp1_pipeline(struct media_entity *e) } struct vsp1_video_buffer { - struct vsp1_video *video; struct vb2_buffer buf; struct list_head queue; diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c index ed2c8a1..98893a8 100644 --- a/drivers/media/rc/ir-lirc-codec.c +++ b/drivers/media/rc/ir-lirc-codec.c @@ -42,11 +42,17 @@ static int ir_lirc_decode(struct rc_dev *dev, struct ir_raw_event ev) return -EINVAL; /* Packet start */ - if (ev.reset) - return 0; + if (ev.reset) { + /* Userspace expects a long space event before the start of + * the signal to use as a sync. This may be done with repeat + * packets and normal samples. But if a reset has been sent + * then we assume that a long time has passed, so we send a + * space with the maximum time value. */ + sample = LIRC_SPACE(LIRC_VALUE_MASK); + IR_dprintk(2, "delivering reset sync space to lirc_dev\n"); /* Carrier reports */ - if (ev.carrier_report) { + } else if (ev.carrier_report) { sample = LIRC_FREQUENCY(ev.carrier); IR_dprintk(2, "carrier report (freq: %d)\n", sample); diff --git a/drivers/media/tuners/m88ts2022.c b/drivers/media/tuners/m88ts2022.c index 40c42de..7a62097 100644 --- a/drivers/media/tuners/m88ts2022.c +++ b/drivers/media/tuners/m88ts2022.c @@ -314,7 +314,7 @@ static int m88ts2022_set_params(struct dvb_frontend *fe) div_min = gdiv28 * 78 / 100; div_max = clamp_val(div_max, 0U, 63U); - f_3db_hz = c->symbol_rate * 135UL / 200UL; + f_3db_hz = mult_frac(c->symbol_rate, 135, 200); f_3db_hz += 2000000U + (frequency_offset_khz * 1000U); f_3db_hz = clamp(f_3db_hz, 7000000U, 40000000U); diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c index 2018bef..e71decb 100644 --- a/drivers/media/tuners/xc4000.c +++ b/drivers/media/tuners/xc4000.c @@ -93,7 +93,7 @@ struct xc4000_priv { struct firmware_description *firm; int firm_size; u32 if_khz; - u32 freq_hz; + u32 freq_hz, freq_offset; u32 bandwidth; u8 video_standard; u8 rf_mode; @@ -1157,14 +1157,14 @@ static int xc4000_set_params(struct dvb_frontend *fe) case SYS_ATSC: dprintk(1, "%s() VSB modulation\n", __func__); priv->rf_mode = XC_RF_MODE_AIR; - priv->freq_hz = c->frequency - 1750000; + priv->freq_offset = 1750000; priv->video_standard = XC4000_DTV6; type = DTV6; break; case SYS_DVBC_ANNEX_B: dprintk(1, "%s() QAM modulation\n", __func__); priv->rf_mode = XC_RF_MODE_CABLE; - priv->freq_hz = c->frequency - 1750000; + priv->freq_offset = 1750000; priv->video_standard = XC4000_DTV6; type = DTV6; break; @@ -1173,23 +1173,23 @@ static int xc4000_set_params(struct dvb_frontend *fe) dprintk(1, "%s() OFDM\n", __func__); if (bw == 0) { if (c->frequency < 400000000) { - priv->freq_hz = c->frequency - 2250000; + priv->freq_offset = 2250000; } else { - priv->freq_hz = c->frequency - 2750000; + priv->freq_offset = 2750000; } priv->video_standard = XC4000_DTV7_8; type = DTV78; } else if (bw <= 6000000) { priv->video_standard = XC4000_DTV6; - priv->freq_hz = c->frequency - 1750000; + priv->freq_offset = 1750000; type = DTV6; } else if (bw <= 7000000) { priv->video_standard = XC4000_DTV7; - priv->freq_hz = c->frequency - 2250000; + priv->freq_offset = 2250000; type = DTV7; } else { priv->video_standard = XC4000_DTV8; - priv->freq_hz = c->frequency - 2750000; + priv->freq_offset = 2750000; type = DTV8; } priv->rf_mode = XC_RF_MODE_AIR; @@ -1200,6 +1200,8 @@ static int xc4000_set_params(struct dvb_frontend *fe) goto fail; } + priv->freq_hz = c->frequency - priv->freq_offset; + dprintk(1, "%s() frequency=%d (compensated)\n", __func__, priv->freq_hz); @@ -1520,7 +1522,7 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq) { struct xc4000_priv *priv = fe->tuner_priv; - *freq = priv->freq_hz; + *freq = priv->freq_hz + priv->freq_offset; if (debug) { mutex_lock(&priv->lock); diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c index 5cd09a6..b2d9e9c 100644 --- a/drivers/media/tuners/xc5000.c +++ b/drivers/media/tuners/xc5000.c @@ -55,7 +55,7 @@ struct xc5000_priv { u32 if_khz; u16 xtal_khz; - u32 freq_hz; + u32 freq_hz, freq_offset; u32 bandwidth; u8 video_standard; u8 rf_mode; @@ -755,13 +755,13 @@ static int xc5000_set_params(struct dvb_frontend *fe) case SYS_ATSC: dprintk(1, "%s() VSB modulation\n", __func__); priv->rf_mode = XC_RF_MODE_AIR; - priv->freq_hz = freq - 1750000; + priv->freq_offset = 1750000; priv->video_standard = DTV6; break; case SYS_DVBC_ANNEX_B: dprintk(1, "%s() QAM modulation\n", __func__); priv->rf_mode = XC_RF_MODE_CABLE; - priv->freq_hz = freq - 1750000; + priv->freq_offset = 1750000; priv->video_standard = DTV6; break; case SYS_ISDBT: @@ -776,15 +776,15 @@ static int xc5000_set_params(struct dvb_frontend *fe) switch (bw) { case 6000000: priv->video_standard = DTV6; - priv->freq_hz = freq - 1750000; + priv->freq_offset = 1750000; break; case 7000000: priv->video_standard = DTV7; - priv->freq_hz = freq - 2250000; + priv->freq_offset = 2250000; break; case 8000000: priv->video_standard = DTV8; - priv->freq_hz = freq - 2750000; + priv->freq_offset = 2750000; break; default: printk(KERN_ERR "xc5000 bandwidth not set!\n"); @@ -798,15 +798,15 @@ static int xc5000_set_params(struct dvb_frontend *fe) priv->rf_mode = XC_RF_MODE_CABLE; if (bw <= 6000000) { priv->video_standard = DTV6; - priv->freq_hz = freq - 1750000; + priv->freq_offset = 1750000; b = 6; } else if (bw <= 7000000) { priv->video_standard = DTV7; - priv->freq_hz = freq - 2250000; + priv->freq_offset = 2250000; b = 7; } else { priv->video_standard = DTV7_8; - priv->freq_hz = freq - 2750000; + priv->freq_offset = 2750000; b = 8; } dprintk(1, "%s() Bandwidth %dMHz (%d)\n", __func__, @@ -817,6 +817,8 @@ static int xc5000_set_params(struct dvb_frontend *fe) return -EINVAL; } + priv->freq_hz = freq - priv->freq_offset; + dprintk(1, "%s() frequency=%d (compensated to %d)\n", __func__, freq, priv->freq_hz); @@ -1067,7 +1069,7 @@ static int xc5000_get_frequency(struct dvb_frontend *fe, u32 *freq) { struct xc5000_priv *priv = fe->tuner_priv; dprintk(1, "%s()\n", __func__); - *freq = priv->freq_hz; + *freq = priv->freq_hz + priv->freq_offset; return 0; } diff --git a/drivers/media/usb/au0828/au0828-cards.c b/drivers/media/usb/au0828/au0828-cards.c index dd32dec..1d4b110 100644 --- a/drivers/media/usb/au0828/au0828-cards.c +++ b/drivers/media/usb/au0828/au0828-cards.c @@ -36,6 +36,11 @@ static void hvr950q_cs5340_audio(void *priv, int enable) au0828_clear(dev, REG_000, 0x10); } +/* + * WARNING: There's a quirks table at sound/usb/quirks-table.h + * that should also be updated every time a new device with V4L2 support + * is added here. + */ struct au0828_board au0828_boards[] = { [AU0828_BOARD_UNKNOWN] = { .name = "Unknown board", diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c index f615454..7ed75ef 100644 --- a/drivers/media/usb/au0828/au0828-video.c +++ b/drivers/media/usb/au0828/au0828-video.c @@ -787,11 +787,27 @@ static int au0828_i2s_init(struct au0828_dev *dev) /* * Auvitek au0828 analog stream enable - * Please set interface0 to AS5 before enable the stream */ static int au0828_analog_stream_enable(struct au0828_dev *d) { + struct usb_interface *iface; + int ret; + dprintk(1, "au0828_analog_stream_enable called\n"); + + iface = usb_ifnum_to_if(d->usbdev, 0); + if (iface && iface->cur_altsetting->desc.bAlternateSetting != 5) { + dprintk(1, "Changing intf#0 to alt 5\n"); + /* set au0828 interface0 to AS5 here again */ + ret = usb_set_interface(d->usbdev, 0, 5); + if (ret < 0) { + printk(KERN_INFO "Au0828 can't set alt setting to 5!\n"); + return -EBUSY; + } + } + + /* FIXME: size should be calculated using d->width, d->height */ + au0828_writereg(d, AU0828_SENSORCTRL_VBI_103, 0x00); au0828_writereg(d, 0x106, 0x00); /* set x position */ @@ -1002,15 +1018,6 @@ static int au0828_v4l2_open(struct file *filp) return -ERESTARTSYS; } if (dev->users == 0) { - /* set au0828 interface0 to AS5 here again */ - ret = usb_set_interface(dev->usbdev, 0, 5); - if (ret < 0) { - mutex_unlock(&dev->lock); - printk(KERN_INFO "Au0828 can't set alternate to 5!\n"); - kfree(fh); - return -EBUSY; - } - au0828_analog_stream_enable(dev); au0828_analog_stream_reset(dev); @@ -1252,13 +1259,6 @@ static int au0828_set_format(struct au0828_dev *dev, unsigned int cmd, } } - /* set au0828 interface0 to AS5 here again */ - ret = usb_set_interface(dev->usbdev, 0, 5); - if (ret < 0) { - printk(KERN_INFO "Au0828 can't set alt setting to 5!\n"); - return -EBUSY; - } - au0828_analog_stream_enable(dev); return 0; diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c index 8ede8ea..88228f7 100644 --- a/drivers/media/usb/dvb-usb-v2/af9035.c +++ b/drivers/media/usb/dvb-usb-v2/af9035.c @@ -1541,6 +1541,10 @@ static const struct usb_device_id af9035_id_table[] = { &af9035_props, "Leadtek WinFast DTV Dongle Dual", NULL) }, { DVB_USB_DEVICE(USB_VID_HAUPPAUGE, 0xf900, &af9035_props, "Hauppauge WinTV-MiniStick 2", NULL) }, + { DVB_USB_DEVICE(USB_VID_PCTV, USB_PID_PCTV_78E, + &af9035_props, "PCTV 78e", RC_MAP_IT913X_V1) }, + { DVB_USB_DEVICE(USB_VID_PCTV, USB_PID_PCTV_79E, + &af9035_props, "PCTV 79e", RC_MAP_IT913X_V2) }, { } }; MODULE_DEVICE_TABLE(usb, af9035_id_table); diff --git a/drivers/media/usb/dvb-usb-v2/lmedm04.c b/drivers/media/usb/dvb-usb-v2/lmedm04.c index f674dc0..d2a4e6d 100644 --- a/drivers/media/usb/dvb-usb-v2/lmedm04.c +++ b/drivers/media/usb/dvb-usb-v2/lmedm04.c @@ -350,6 +350,7 @@ static int lme2510_int_read(struct dvb_usb_adapter *adap) { struct dvb_usb_device *d = adap_to_d(adap); struct lme2510_state *lme_int = adap_to_priv(adap); + struct usb_host_endpoint *ep; lme_int->lme_urb = usb_alloc_urb(0, GFP_ATOMIC); @@ -371,6 +372,12 @@ static int lme2510_int_read(struct dvb_usb_adapter *adap) adap, 8); + /* Quirk of pipe reporting PIPE_BULK but behaves as interrupt */ + ep = usb_pipe_endpoint(d->udev, lme_int->lme_urb->pipe); + + if (usb_endpoint_type(&ep->desc) == USB_ENDPOINT_XFER_BULK) + lme_int->lme_urb->pipe = usb_rcvbulkpipe(d->udev, 0xa), + lme_int->lme_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; usb_submit_urb(lme_int->lme_urb, GFP_ATOMIC); diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c index af176b6..e6d3561 100644 --- a/drivers/media/usb/dvb-usb/af9005.c +++ b/drivers/media/usb/dvb-usb/af9005.c @@ -1081,9 +1081,12 @@ static int __init af9005_usb_module_init(void) err("usb_register failed. (%d)", result); return result; } +#if IS_MODULE(CONFIG_DVB_USB_AF9005) || defined(CONFIG_DVB_USB_AF9005_REMOTE) + /* FIXME: convert to todays kernel IR infrastructure */ rc_decode = symbol_request(af9005_rc_decode); rc_keys = symbol_request(rc_map_af9005_table); rc_keys_size = symbol_request(rc_map_af9005_table_size); +#endif if (rc_decode == NULL || rc_keys == NULL || rc_keys_size == NULL) { err("af9005_rc_decode function not found, disabling remote"); af9005_properties.rc.legacy.rc_query = NULL; diff --git a/drivers/media/usb/em28xx/em28xx-audio.c b/drivers/media/usb/em28xx/em28xx-audio.c index dfdfa77..c39f7d3 100644 --- a/drivers/media/usb/em28xx/em28xx-audio.c +++ b/drivers/media/usb/em28xx/em28xx-audio.c @@ -814,7 +814,7 @@ static int em28xx_audio_urb_init(struct em28xx *dev) if (urb_size > ep_size * npackets) npackets = DIV_ROUND_UP(urb_size, ep_size); - em28xx_info("Number of URBs: %d, with %d packets and %d size", + em28xx_info("Number of URBs: %d, with %d packets and %d size\n", num_urb, npackets, urb_size); /* Estimate the bytes per period */ @@ -974,7 +974,7 @@ static int em28xx_audio_fini(struct em28xx *dev) return 0; } - em28xx_info("Closing audio extension"); + em28xx_info("Closing audio extension\n"); if (dev->adev.sndcard) { snd_card_disconnect(dev->adev.sndcard); diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c index 4d97a76..c1a3f8f 100644 --- a/drivers/media/usb/em28xx/em28xx-cards.c +++ b/drivers/media/usb/em28xx/em28xx-cards.c @@ -2993,16 +2993,6 @@ static int em28xx_init_dev(struct em28xx *dev, struct usb_device *udev, } } - if (dev->chip_id == CHIP_ID_EM2870 || - dev->chip_id == CHIP_ID_EM2874 || - dev->chip_id == CHIP_ID_EM28174 || - dev->chip_id == CHIP_ID_EM28178) { - /* Digital only device - don't load any alsa module */ - dev->audio_mode.has_audio = false; - dev->has_audio_class = false; - dev->has_alsa_audio = false; - } - if (chip_name != default_chip_name) printk(KERN_INFO DRIVER_NAME ": chip ID is %s\n", chip_name); @@ -3272,7 +3262,6 @@ static int em28xx_usb_probe(struct usb_interface *interface, dev->alt = -1; dev->is_audio_only = has_audio && !(has_video || has_dvb); dev->has_alsa_audio = has_audio; - dev->audio_mode.has_audio = has_audio; dev->has_video = has_video; dev->ifnum = ifnum; diff --git a/drivers/media/usb/em28xx/em28xx-core.c b/drivers/media/usb/em28xx/em28xx-core.c index 898fb9b..97fd881 100644 --- a/drivers/media/usb/em28xx/em28xx-core.c +++ b/drivers/media/usb/em28xx/em28xx-core.c @@ -506,8 +506,18 @@ int em28xx_audio_setup(struct em28xx *dev) int vid1, vid2, feat, cfg; u32 vid; - if (!dev->audio_mode.has_audio) + if (dev->chip_id == CHIP_ID_EM2870 || + dev->chip_id == CHIP_ID_EM2874 || + dev->chip_id == CHIP_ID_EM28174 || + dev->chip_id == CHIP_ID_EM28178) { + /* Digital only device - don't load any alsa module */ + dev->audio_mode.has_audio = false; + dev->has_audio_class = false; + dev->has_alsa_audio = false; return 0; + } + + dev->audio_mode.has_audio = true; /* See how this device is configured */ cfg = em28xx_read_reg(dev, EM28XX_R00_CHIPCFG); diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c index 1373cfa..ec2ebe9 100644 --- a/drivers/media/usb/em28xx/em28xx-dvb.c +++ b/drivers/media/usb/em28xx/em28xx-dvb.c @@ -1468,7 +1468,7 @@ static int em28xx_dvb_fini(struct em28xx *dev) return 0; } - em28xx_info("Closing DVB extension"); + em28xx_info("Closing DVB extension\n"); if (dev->dvb) { struct em28xx_dvb *dvb = dev->dvb; diff --git a/drivers/media/usb/em28xx/em28xx-input.c b/drivers/media/usb/em28xx/em28xx-input.c index 18f65d8..dd59c00 100644 --- a/drivers/media/usb/em28xx/em28xx-input.c +++ b/drivers/media/usb/em28xx/em28xx-input.c @@ -810,7 +810,7 @@ static int em28xx_ir_fini(struct em28xx *dev) return 0; } - em28xx_info("Closing input extension"); + em28xx_info("Closing input extension\n"); em28xx_shutdown_buttons(dev); diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c index c3c9289..0e8d085 100644 --- a/drivers/media/usb/em28xx/em28xx-video.c +++ b/drivers/media/usb/em28xx/em28xx-video.c @@ -953,13 +953,16 @@ static int em28xx_stop_streaming(struct vb2_queue *vq) } spin_lock_irqsave(&dev->slock, flags); + if (dev->usb_ctl.vid_buf != NULL) { + vb2_buffer_done(&dev->usb_ctl.vid_buf->vb, VB2_BUF_STATE_ERROR); + dev->usb_ctl.vid_buf = NULL; + } while (!list_empty(&vidq->active)) { struct em28xx_buffer *buf; buf = list_entry(vidq->active.next, struct em28xx_buffer, list); list_del(&buf->list); vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR); } - dev->usb_ctl.vid_buf = NULL; spin_unlock_irqrestore(&dev->slock, flags); return 0; @@ -981,13 +984,16 @@ int em28xx_stop_vbi_streaming(struct vb2_queue *vq) } spin_lock_irqsave(&dev->slock, flags); + if (dev->usb_ctl.vbi_buf != NULL) { + vb2_buffer_done(&dev->usb_ctl.vbi_buf->vb, VB2_BUF_STATE_ERROR); + dev->usb_ctl.vbi_buf = NULL; + } while (!list_empty(&vbiq->active)) { struct em28xx_buffer *buf; buf = list_entry(vbiq->active.next, struct em28xx_buffer, list); list_del(&buf->list); vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR); } - dev->usb_ctl.vbi_buf = NULL; spin_unlock_irqrestore(&dev->slock, flags); return 0; @@ -1894,7 +1900,7 @@ static int em28xx_v4l2_fini(struct em28xx *dev) return 0; } - em28xx_info("Closing video extension"); + em28xx_info("Closing video extension\n"); mutex_lock(&dev->lock); diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c index 0500c417..6bce01a 100644 --- a/drivers/media/usb/hdpvr/hdpvr-video.c +++ b/drivers/media/usb/hdpvr/hdpvr-video.c @@ -82,7 +82,7 @@ static void hdpvr_read_bulk_callback(struct urb *urb) } /*=========================================================================*/ -/* bufffer bits */ +/* buffer bits */ /* function expects dev->io_mutex to be hold by caller */ int hdpvr_cancel_queue(struct hdpvr_device *dev) @@ -926,7 +926,7 @@ static int hdpvr_s_ctrl(struct v4l2_ctrl *ctrl) case V4L2_CID_MPEG_AUDIO_ENCODING: if (dev->flags & HDPVR_FLAG_AC3_CAP) { opt->audio_codec = ctrl->val; - return hdpvr_set_audio(dev, opt->audio_input, + return hdpvr_set_audio(dev, opt->audio_input + 1, opt->audio_codec); } return 0; @@ -1198,7 +1198,7 @@ int hdpvr_register_videodev(struct hdpvr_device *dev, struct device *parent, v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops, V4L2_CID_MPEG_AUDIO_ENCODING, ac3 ? V4L2_MPEG_AUDIO_ENCODING_AC3 : V4L2_MPEG_AUDIO_ENCODING_AAC, - 0x7, V4L2_MPEG_AUDIO_ENCODING_AAC); + 0x7, ac3 ? dev->options.audio_codec : V4L2_MPEG_AUDIO_ENCODING_AAC); v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops, V4L2_CID_MPEG_VIDEO_ENCODING, V4L2_MPEG_VIDEO_ENCODING_MPEG_4_AVC, 0x3, diff --git a/drivers/media/usb/stk1160/stk1160-v4l.c b/drivers/media/usb/stk1160/stk1160-v4l.c index c45c988..4572530 100644 --- a/drivers/media/usb/stk1160/stk1160-v4l.c +++ b/drivers/media/usb/stk1160/stk1160-v4l.c @@ -244,6 +244,11 @@ static int stk1160_stop_streaming(struct stk1160 *dev) if (mutex_lock_interruptible(&dev->v4l_lock)) return -ERESTARTSYS; + /* + * Once URBs are cancelled, the URB complete handler + * won't be running. This is required to safely release the + * current buffer (dev->isoc_ctl.buf). + */ stk1160_cancel_isoc(dev); /* @@ -624,8 +629,16 @@ void stk1160_clear_queue(struct stk1160 *dev) stk1160_info("buffer [%p/%d] aborted\n", buf, buf->vb.v4l2_buf.index); } - /* It's important to clear current buffer */ - dev->isoc_ctl.buf = NULL; + + /* It's important to release the current buffer */ + if (dev->isoc_ctl.buf) { + buf = dev->isoc_ctl.buf; + dev->isoc_ctl.buf = NULL; + + vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR); + stk1160_info("buffer [%p/%d] aborted\n", + buf, buf->vb.v4l2_buf.index); + } spin_unlock_irqrestore(&dev->buf_lock, flags); } diff --git a/drivers/media/usb/ttusb-dec/ttusbdecfe.c b/drivers/media/usb/ttusb-dec/ttusbdecfe.c index 5c45c9d..9c29552 100644 --- a/drivers/media/usb/ttusb-dec/ttusbdecfe.c +++ b/drivers/media/usb/ttusb-dec/ttusbdecfe.c @@ -156,6 +156,9 @@ static int ttusbdecfe_dvbs_diseqc_send_master_cmd(struct dvb_frontend* fe, struc 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; + if (cmd->msg_len > sizeof(b) - 4) + return -EINVAL; + memcpy(&b[4], cmd->msg, cmd->msg_len); state->config->send_command(fe, 0x72, diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index c3bb250..4531441 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -1603,12 +1603,12 @@ static void uvc_delete(struct uvc_device *dev) { struct list_head *p, *n; - usb_put_intf(dev->intf); - usb_put_dev(dev->udev); - uvc_status_cleanup(dev); uvc_ctrl_cleanup_device(dev); + usb_put_intf(dev->intf); + usb_put_dev(dev->udev); + if (dev->vdev.dev) v4l2_device_unregister(&dev->vdev); #ifdef CONFIG_MEDIA_CONTROLLER @@ -2210,6 +2210,15 @@ static struct usb_device_id uvc_ids[] = { .bInterfaceSubClass = 1, .bInterfaceProtocol = 0, .driver_info = UVC_QUIRK_PROBE_DEF }, + /* Dell XPS M1330 (OmniVision OV7670 webcam) */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x05a9, + .idProduct = 0x7670, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_QUIRK_PROBE_DEF }, /* Apple Built-In iSight */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c index 433d6d7..c5521ce 100644 --- a/drivers/media/v4l2-core/v4l2-common.c +++ b/drivers/media/v4l2-core/v4l2-common.c @@ -431,16 +431,13 @@ static unsigned int clamp_align(unsigned int x, unsigned int min, /* Bits that must be zero to be aligned */ unsigned int mask = ~((1 << align) - 1); + /* Clamp to aligned min and max */ + x = clamp(x, (min + ~mask) & mask, max & mask); + /* Round to nearest aligned value */ if (align) x = (x + (1 << (align - 1))) & mask; - /* Clamp to aligned value of min and max */ - if (x < min) - x = (min + ~mask) & mask; - else if (x > max) - x = max & mask; - return x; } diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c index a2e2579..78d99b1 100644 --- a/drivers/media/v4l2-core/v4l2-dv-timings.c +++ b/drivers/media/v4l2-core/v4l2-dv-timings.c @@ -595,10 +595,10 @@ struct v4l2_fract v4l2_calc_aspect_ratio(u8 hor_landscape, u8 vert_portrait) aspect.denominator = 9; } else if (ratio == 34) { aspect.numerator = 4; - aspect.numerator = 3; + aspect.denominator = 3; } else if (ratio == 68) { aspect.numerator = 15; - aspect.numerator = 9; + aspect.denominator = 9; } else { aspect.numerator = hor_landscape + 99; aspect.denominator = 100; diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c index a127925..06faea4 100644 --- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -745,6 +745,7 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) * to the userspace. */ req->count = allocated_buffers; + q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type); return 0; } @@ -793,6 +794,7 @@ static int __create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create memset(q->plane_sizes, 0, sizeof(q->plane_sizes)); memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx)); q->memory = create->memory; + q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type); } num_buffers = min(create->count, VIDEO_MAX_FRAME - q->num_buffers); @@ -1447,6 +1449,7 @@ static int vb2_internal_qbuf(struct vb2_queue *q, struct v4l2_buffer *b) * dequeued in dqbuf. */ list_add_tail(&vb->queued_entry, &q->queued_list); + q->waiting_for_buffers = false; vb->state = VB2_BUF_STATE_QUEUED; /* @@ -1841,6 +1844,7 @@ static int vb2_internal_streamoff(struct vb2_queue *q, enum v4l2_buf_type type) * and videobuf, effectively returning control over them to userspace. */ __vb2_queue_cancel(q); + q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type); dprintk(3, "Streamoff successful\n"); return 0; @@ -2150,9 +2154,16 @@ unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait) } /* - * There is nothing to wait for if no buffers have already been queued. + * There is nothing to wait for if the queue isn't streaming. */ - if (list_empty(&q->queued_list)) + if (!vb2_is_streaming(q)) + return res | POLLERR; + /* + * For compatibility with vb1: if QBUF hasn't been called yet, then + * return POLLERR as well. This only affects capture queues, output + * queues will always initialize waiting_for_buffers to false. + */ + if (q->waiting_for_buffers) return res | POLLERR; if (list_empty(&q->done_list)) diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index fc145d2..922a750 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -758,7 +758,7 @@ static int mspro_block_complete_req(struct memstick_dev *card, int error) if (error || (card->current_mrq.tpc == MSPRO_CMD_STOP)) { if (msb->data_dir == READ) { - for (cnt = 0; cnt < msb->current_seg; cnt++) + for (cnt = 0; cnt < msb->current_seg; cnt++) { t_len += msb->req_sg[cnt].length / msb->page_size; @@ -766,6 +766,7 @@ static int mspro_block_complete_req(struct memstick_dev *card, int error) t_len += msb->current_page - 1; t_len *= msb->page_size; + } } } else t_len = blk_rq_bytes(msb->block_req); diff --git a/drivers/message/fusion/mptspi.c b/drivers/message/fusion/mptspi.c index 5653e50..424f51d 100644 --- a/drivers/message/fusion/mptspi.c +++ b/drivers/message/fusion/mptspi.c @@ -1422,6 +1422,11 @@ mptspi_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto out_mptspi_probe; } + /* VMWare emulation doesn't properly implement WRITE_SAME + */ + if (pdev->subsystem_vendor == 0x15AD) + sh->no_write_same = 1; + spin_lock_irqsave(&ioc->FreeQlock, flags); /* Attach the SCSI Host to the IOC structure diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c index 38917a8..2df3cbc 100644 --- a/drivers/mfd/kempld-core.c +++ b/drivers/mfd/kempld-core.c @@ -629,7 +629,7 @@ static int __init kempld_init(void) if (force_device_id[0]) { for (id = kempld_dmi_table; id->matches[0].slot != DMI_NONE; id++) if (strstr(id->ident, force_device_id)) - if (id->callback && id->callback(id)) + if (id->callback && !id->callback(id)) break; if (id->matches[0].slot == DMI_NONE) return -ENODEV; diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c index 90b630c..0aefe50 100644 --- a/drivers/mfd/omap-usb-host.c +++ b/drivers/mfd/omap-usb-host.c @@ -445,7 +445,7 @@ static unsigned omap_usbhs_rev1_hostconfig(struct usbhs_hcd_omap *omap, for (i = 0; i < omap->nports; i++) { if (is_ehci_phy_mode(pdata->port_mode[i])) { - reg &= OMAP_UHH_HOSTCONFIG_ULPI_BYPASS; + reg &= ~OMAP_UHH_HOSTCONFIG_ULPI_BYPASS; break; } } diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c index 1d15735..89b4c42 100644 --- a/drivers/mfd/rtsx_pcr.c +++ b/drivers/mfd/rtsx_pcr.c @@ -1177,7 +1177,7 @@ static int rtsx_pci_probe(struct pci_dev *pcidev, pcr->msi_en = msi_en; if (pcr->msi_en) { ret = pci_enable_msi(pcidev); - if (ret < 0) + if (ret) pcr->msi_en = false; } diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c index 11c19e5..48579e5 100644 --- a/drivers/mfd/tc6393xb.c +++ b/drivers/mfd/tc6393xb.c @@ -263,6 +263,17 @@ static int tc6393xb_ohci_disable(struct platform_device *dev) return 0; } +static int tc6393xb_ohci_suspend(struct platform_device *dev) +{ + struct tc6393xb_platform_data *tcpd = dev_get_platdata(dev->dev.parent); + + /* We can't properly store/restore OHCI state, so fail here */ + if (tcpd->resume_restore) + return -EBUSY; + + return tc6393xb_ohci_disable(dev); +} + static int tc6393xb_fb_enable(struct platform_device *dev) { struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent); @@ -403,7 +414,7 @@ static struct mfd_cell tc6393xb_cells[] = { .num_resources = ARRAY_SIZE(tc6393xb_ohci_resources), .resources = tc6393xb_ohci_resources, .enable = tc6393xb_ohci_enable, - .suspend = tc6393xb_ohci_disable, + .suspend = tc6393xb_ohci_suspend, .resume = tc6393xb_ohci_enable, .disable = tc6393xb_ohci_disable, }, diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c index d4e8604..e87a248 100644 --- a/drivers/mfd/ti_am335x_tscadc.c +++ b/drivers/mfd/ti_am335x_tscadc.c @@ -54,11 +54,11 @@ void am335x_tsc_se_set_cache(struct ti_tscadc_dev *tsadc, u32 val) unsigned long flags; spin_lock_irqsave(&tsadc->reg_lock, flags); - tsadc->reg_se_cache = val; + tsadc->reg_se_cache |= val; if (tsadc->adc_waiting) wake_up(&tsadc->reg_se_wait); else if (!tsadc->adc_in_use) - tscadc_writel(tsadc, REG_SE, val); + tscadc_writel(tsadc, REG_SE, tsadc->reg_se_cache); spin_unlock_irqrestore(&tsadc->reg_lock, flags); } @@ -97,6 +97,7 @@ static void am335x_tscadc_need_adc(struct ti_tscadc_dev *tsadc) void am335x_tsc_se_set_once(struct ti_tscadc_dev *tsadc, u32 val) { spin_lock_irq(&tsadc->reg_lock); + tsadc->reg_se_cache |= val; am335x_tscadc_need_adc(tsadc); tscadc_writel(tsadc, REG_SE, val); diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c index 6b1a6ef..0c3a647 100644 --- a/drivers/misc/genwqe/card_utils.c +++ b/drivers/misc/genwqe/card_utils.c @@ -490,6 +490,8 @@ int genwqe_user_vmap(struct genwqe_dev *cd, struct dma_mapping *m, void *uaddr, m->nr_pages, 1, /* write by caller */ m->page_list); /* ptrs to pages */ + if (rc < 0) + goto fail_get_user_pages; /* assumption: get_user_pages can be killed by signals. */ if (rc < m->nr_pages) { diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 4bc7d62..9a07bba 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -71,7 +71,7 @@ static int mei_cl_device_probe(struct device *dev) dev_dbg(dev, "Device probe\n"); - strncpy(id.name, dev_name(dev), sizeof(id.name)); + strlcpy(id.name, dev_name(dev), sizeof(id.name)); return driver->probe(device, &id); } diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 5a9bfa7..540fe11 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -459,6 +459,7 @@ int mei_cl_disconnect(struct mei_cl *cl) cl_err(dev, cl, "failed to disconnect.\n"); goto free; } + cl->timer_count = MEI_CONNECT_TIMEOUT; mdelay(10); /* Wait for hardware disconnection ready */ list_add_tail(&cb->list, &dev->ctrl_rd_list.list); } else { @@ -563,6 +564,7 @@ int mei_cl_connect(struct mei_cl *cl, struct file *file) cl->timer_count = MEI_CONNECT_TIMEOUT; list_add_tail(&cb->list, &dev->ctrl_rd_list.list); } else { + cl->state = MEI_FILE_INITIALIZING; list_add_tail(&cb->list, &dev->ctrl_wr_list.list); } diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c index cdd31c2..b296538 100644 --- a/drivers/misc/mei/init.c +++ b/drivers/misc/mei/init.c @@ -275,6 +275,8 @@ void mei_stop(struct mei_device *dev) dev->dev_state = MEI_DEV_POWER_DOWN; mei_reset(dev); + /* move device to disabled state unconditionally */ + dev->dev_state = MEI_DEV_DISABLED; mutex_unlock(&dev->device_lock); diff --git a/drivers/misc/mei/nfc.c b/drivers/misc/mei/nfc.c index a58320c..3114901 100644 --- a/drivers/misc/mei/nfc.c +++ b/drivers/misc/mei/nfc.c @@ -342,9 +342,10 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length) ndev = (struct mei_nfc_dev *) cldev->priv_data; dev = ndev->cl->dev; + err = -ENOMEM; mei_buf = kzalloc(length + MEI_NFC_HEADER_SIZE, GFP_KERNEL); if (!mei_buf) - return -ENOMEM; + goto out; hdr = (struct mei_nfc_hci_hdr *) mei_buf; hdr->cmd = MEI_NFC_CMD_HCI_SEND; @@ -354,12 +355,9 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length) hdr->data_size = length; memcpy(mei_buf + MEI_NFC_HEADER_SIZE, buf, length); - err = __mei_cl_send(ndev->cl, mei_buf, length + MEI_NFC_HEADER_SIZE); if (err < 0) - return err; - - kfree(mei_buf); + goto out; if (!wait_event_interruptible_timeout(ndev->send_wq, ndev->recv_req_id == ndev->req_id, HZ)) { @@ -368,7 +366,8 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length) } else { ndev->req_id++; } - +out: + kfree(mei_buf); return err; } diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 7b5424f..d71f5ef 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -205,6 +205,8 @@ static ssize_t power_ro_lock_show(struct device *dev, ret = snprintf(buf, PAGE_SIZE, "%d\n", locked); + mmc_blk_put(md); + return ret; } @@ -260,7 +262,7 @@ static ssize_t force_ro_show(struct device *dev, struct device_attribute *attr, int ret; struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); - ret = snprintf(buf, PAGE_SIZE, "%d", + ret = snprintf(buf, PAGE_SIZE, "%d\n", get_disk_ro(dev_to_disk(dev)) ^ md->read_only); mmc_blk_put(md); @@ -951,6 +953,18 @@ static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type) md->reset_done &= ~type; } +int mmc_access_rpmb(struct mmc_queue *mq) +{ + struct mmc_blk_data *md = mq->data; + /* + * If this is a RPMB partition access, return ture + */ + if (md && md->part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) + return true; + + return false; +} + static int mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) { struct mmc_blk_data *md = mq->data; @@ -1849,9 +1863,11 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) break; case MMC_BLK_CMD_ERR: ret = mmc_blk_cmd_err(md, card, brq, req, ret); - if (!mmc_blk_reset(md, card->host, type)) - break; - goto cmd_abort; + if (mmc_blk_reset(md, card->host, type)) + goto cmd_abort; + if (!ret) + goto start_new_req; + break; case MMC_BLK_RETRY: if (retry++ < 5) break; diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index 3e049c1..6ceede0 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -38,7 +38,7 @@ static int mmc_prep_request(struct request_queue *q, struct request *req) return BLKPREP_KILL; } - if (mq && mmc_card_removed(mq->card)) + if (mq && (mmc_card_removed(mq->card) || mmc_access_rpmb(mq))) return BLKPREP_KILL; req->cmd_flags |= REQ_DONTPREP; diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index 5752d50..99e6521 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -73,4 +73,6 @@ extern void mmc_queue_bounce_post(struct mmc_queue_req *); extern int mmc_packed_init(struct mmc_queue *, struct mmc_card *); extern void mmc_packed_clean(struct mmc_queue *); +extern int mmc_access_rpmb(struct mmc_queue *); + #endif diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index c43e6c8..daca58b 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -2699,6 +2699,7 @@ int mmc_pm_notify(struct notifier_block *notify_block, switch (mode) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: + case PM_RESTORE_PREPARE: spin_lock_irqsave(&host->lock, flags); host->rescan_disable = 1; spin_unlock_irqrestore(&host->lock, flags); diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c index 42706ea..201ce37 100644 --- a/drivers/mmc/host/atmel-mci.c +++ b/drivers/mmc/host/atmel-mci.c @@ -1300,7 +1300,7 @@ static void atmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) if (ios->clock) { unsigned int clock_min = ~0U; - u32 clkdiv; + int clkdiv; clk_prepare(host->mck); unprepare_clk = true; @@ -1329,7 +1329,12 @@ static void atmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) /* Calculate clock divider */ if (host->caps.has_odd_clk_div) { clkdiv = DIV_ROUND_UP(host->bus_hz, clock_min) - 2; - if (clkdiv > 511) { + if (clkdiv < 0) { + dev_warn(&mmc->class_dev, + "clock %u too fast; using %lu\n", + clock_min, host->bus_hz / 2); + clkdiv = 0; + } else if (clkdiv > 511) { dev_warn(&mmc->class_dev, "clock %u too slow; using %lu\n", clock_min, host->bus_hz / (511 + 2)); diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 054e03d..5d59c92 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -632,6 +632,13 @@ static void dw_mci_ctrl_rd_thld(struct dw_mci *host, struct mmc_data *data) WARN_ON(!(data->flags & MMC_DATA_READ)); + /* + * CDTHRCTL doesn't exist prior to 240A (in fact that register offset is + * in the FIFO region, so we really shouldn't access it). + */ + if (host->verid < DW_MMC_240A) + return; + if (host->timing != MMC_TIMING_MMC_HS200 && host->timing != MMC_TIMING_UHS_SDR104) goto disable; diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c index 7e18661..ca297d7 100644 --- a/drivers/mmc/host/rtsx_pci_sdmmc.c +++ b/drivers/mmc/host/rtsx_pci_sdmmc.c @@ -342,6 +342,13 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host, } if (rsp_type == SD_RSP_TYPE_R2) { + /* + * The controller offloads the last byte {CRC-7, end bit 1'b1} + * of response type R2. Assign dummy CRC, 0, and end bit to the + * byte(ptr[16], goes into the LSB of resp[3] later). + */ + ptr[16] = 1; + for (i = 0; i < 4; i++) { cmd->resp[i] = get_unaligned_be32(ptr + 1 + i * 4); dev_dbg(sdmmc_dev(host), "cmd->resp[%d] = 0x%08x\n", diff --git a/drivers/mmc/host/sdhci-esdhc.h b/drivers/mmc/host/sdhci-esdhc.h index 5c0f27f..28f61b7 100644 --- a/drivers/mmc/host/sdhci-esdhc.h +++ b/drivers/mmc/host/sdhci-esdhc.h @@ -46,6 +46,6 @@ #define ESDHC_DMA_SYSCTL 0x40c #define ESDHC_DMA_SNOOP 0x00000040 -#define ESDHC_HOST_CONTROL_RES 0x05 +#define ESDHC_HOST_CONTROL_RES 0x01 #endif /* _DRIVERS_MMC_SDHCI_ESDHC_H */ diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c index f49666b..257e9ca 100644 --- a/drivers/mmc/host/sdhci-pci-o2micro.c +++ b/drivers/mmc/host/sdhci-pci-o2micro.c @@ -88,8 +88,6 @@ void sdhci_pci_o2_fujin2_pci_init(struct sdhci_pci_chip *chip) return; scratch_32 &= ~((1 << 21) | (1 << 30)); - /* Set RTD3 function disabled */ - scratch_32 |= ((1 << 29) | (1 << 28)); pci_write_config_dword(chip->pdev, O2_SD_FUNC_REG3, scratch_32); /* Set L1 Entrance Timer */ diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c index ba4eaf0..19de28b 100644 --- a/drivers/mmc/host/sdhci-pci.c +++ b/drivers/mmc/host/sdhci-pci.c @@ -103,6 +103,10 @@ static const struct sdhci_pci_fixes sdhci_cafe = { SDHCI_QUIRK_BROKEN_TIMEOUT_VAL, }; +static const struct sdhci_pci_fixes sdhci_intel_qrk = { + .quirks = SDHCI_QUIRK_NO_HISPD_BIT, +}; + static int mrst_hc_probe_slot(struct sdhci_pci_slot *slot) { slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA; @@ -733,6 +737,14 @@ static const struct pci_device_id pci_ids[] = { { .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_QRK_SD, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .driver_data = (kernel_ulong_t)&sdhci_intel_qrk, + }, + + { + .vendor = PCI_VENDOR_ID_INTEL, .device = PCI_DEVICE_ID_INTEL_MRST_SD0, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h index 6d71871..c101477 100644 --- a/drivers/mmc/host/sdhci-pci.h +++ b/drivers/mmc/host/sdhci-pci.h @@ -17,6 +17,7 @@ #define PCI_DEVICE_ID_INTEL_CLV_SDIO2 0x08fb #define PCI_DEVICE_ID_INTEL_CLV_EMMC0 0x08e5 #define PCI_DEVICE_ID_INTEL_CLV_EMMC1 0x08e6 +#define PCI_DEVICE_ID_INTEL_QRK_SD 0x08A7 /* * PCI registers diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c index 4c5e52f..d70b8aa3 100644 --- a/drivers/mmc/host/sdhci-pxav3.c +++ b/drivers/mmc/host/sdhci-pxav3.c @@ -204,8 +204,8 @@ static struct sdhci_pxa_platdata *pxav3_get_mmc_pdata(struct device *dev) if (!pdata) return NULL; - of_property_read_u32(np, "mrvl,clk-delay-cycles", &clk_delay_cycles); - if (clk_delay_cycles > 0) + if (!of_property_read_u32(np, "mrvl,clk-delay-cycles", + &clk_delay_cycles)) pdata->clk_delay_cycles = clk_delay_cycles; return pdata; @@ -260,6 +260,7 @@ static int sdhci_pxav3_probe(struct platform_device *pdev) goto err_of_parse; sdhci_get_of_property(pdev); pdata = pxav3_get_mmc_pdata(dev); + pdev->dev.platform_data = pdata; } else if (pdata) { /* on-chip device */ if (pdata->flags & PXA_FLAG_CARD_PERMANENT) diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 38e1cd4..af7507b 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -1310,6 +1310,8 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq) sdhci_runtime_pm_get(host); + present = mmc_gpio_get_cd(host->mmc); + spin_lock_irqsave(&host->lock, flags); WARN_ON(host->mrq != NULL); @@ -1338,7 +1340,6 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq) * zero: cd-gpio is used, and card is removed * one: cd-gpio is used, and card is present */ - present = mmc_gpio_get_cd(host->mmc); if (present < 0) { /* If polling, assume that the card is always present. */ if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) @@ -2049,15 +2050,18 @@ static void sdhci_card_event(struct mmc_host *mmc) { struct sdhci_host *host = mmc_priv(mmc); unsigned long flags; + int present; /* First check if client has provided their own card event */ if (host->ops->card_event) host->ops->card_event(host); + present = sdhci_do_get_cd(host); + spin_lock_irqsave(&host->lock, flags); /* Check host->mrq first in case we are runtime suspended */ - if (host->mrq && !sdhci_do_get_cd(host)) { + if (host->mrq && !present) { pr_err("%s: Card removed during transfer!\n", mmc_hostname(host->mmc)); pr_err("%s: Resetting controller.\n", diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c index 54730f4..9c208fd 100644 --- a/drivers/mmc/host/sh_mmcif.c +++ b/drivers/mmc/host/sh_mmcif.c @@ -1401,7 +1401,7 @@ static int sh_mmcif_probe(struct platform_device *pdev) host = mmc_priv(mmc); host->mmc = mmc; host->addr = reg; - host->timeout = msecs_to_jiffies(1000); + host->timeout = msecs_to_jiffies(10000); host->ccs_enable = !pd || !pd->ccs_unsupported; host->clk_ctrl2_enable = pd && pd->clk_ctrl2_present; diff --git a/drivers/mtd/ftl.c b/drivers/mtd/ftl.c index 19d6372..71e4f6c 100644 --- a/drivers/mtd/ftl.c +++ b/drivers/mtd/ftl.c @@ -1075,7 +1075,6 @@ static void ftl_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd) return; } - ftl_freepart(partition); kfree(partition); } diff --git a/drivers/mtd/maps/dc21285.c b/drivers/mtd/maps/dc21285.c index f8a7dd1..70a3db3 100644 --- a/drivers/mtd/maps/dc21285.c +++ b/drivers/mtd/maps/dc21285.c @@ -38,9 +38,9 @@ static void nw_en_write(void) * we want to write a bit pattern XXX1 to Xilinx to enable * the write gate, which will be open for about the next 2ms. */ - spin_lock_irqsave(&nw_gpio_lock, flags); + raw_spin_lock_irqsave(&nw_gpio_lock, flags); nw_cpld_modify(CPLD_FLASH_WR_ENABLE, CPLD_FLASH_WR_ENABLE); - spin_unlock_irqrestore(&nw_gpio_lock, flags); + raw_spin_unlock_irqrestore(&nw_gpio_lock, flags); /* * let the ISA bus to catch on... diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 5073cbc..32d5e40 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -199,6 +199,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode) return -ERESTARTSYS; /* FIXME: busy loop! -arnd*/ mutex_lock(&dev->lock); + mutex_lock(&mtd_table_mutex); if (dev->open) goto unlock; @@ -222,6 +223,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode) unlock: dev->open++; + mutex_unlock(&mtd_table_mutex); mutex_unlock(&dev->lock); blktrans_dev_put(dev); return ret; @@ -232,6 +234,7 @@ error_release: error_put: module_put(dev->tr->owner); kref_put(&dev->ref, blktrans_dev_release); + mutex_unlock(&mtd_table_mutex); mutex_unlock(&dev->lock); blktrans_dev_put(dev); return ret; @@ -245,6 +248,7 @@ static void blktrans_release(struct gendisk *disk, fmode_t mode) return; mutex_lock(&dev->lock); + mutex_lock(&mtd_table_mutex); if (--dev->open) goto unlock; @@ -258,6 +262,7 @@ static void blktrans_release(struct gendisk *disk, fmode_t mode) __put_mtd_device(dev->mtd); } unlock: + mutex_unlock(&mtd_table_mutex); mutex_unlock(&dev->lock); blktrans_dev_put(dev); } diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 9715a7b..efc542d 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -2000,7 +2000,7 @@ static int nand_write_page_raw_syndrome(struct mtd_info *mtd, oob += chip->ecc.prepad; } - chip->read_buf(mtd, oob, eccbytes); + chip->write_buf(mtd, oob, eccbytes); oob += eccbytes; if (chip->ecc.postpad) { @@ -3063,7 +3063,7 @@ static int nand_flash_detect_onfi(struct mtd_info *mtd, struct nand_chip *chip, int *busw) { struct nand_onfi_params *p = &chip->onfi_params; - int i; + int i, j; int val; /* Try ONFI for unknown chip or LP */ @@ -3072,18 +3072,10 @@ static int nand_flash_detect_onfi(struct mtd_info *mtd, struct nand_chip *chip, chip->read_byte(mtd) != 'F' || chip->read_byte(mtd) != 'I') return 0; - /* - * ONFI must be probed in 8-bit mode or with NAND_BUSWIDTH_AUTO, not - * with NAND_BUSWIDTH_16 - */ - if (chip->options & NAND_BUSWIDTH_16) { - pr_err("ONFI cannot be probed in 16-bit mode; aborting\n"); - return 0; - } - chip->cmdfunc(mtd, NAND_CMD_PARAM, 0, -1); for (i = 0; i < 3; i++) { - chip->read_buf(mtd, (uint8_t *)p, sizeof(*p)); + for (j = 0; j < sizeof(*p); j++) + ((uint8_t *)p)[j] = chip->read_byte(mtd); if (onfi_crc16(ONFI_CRC_BASE, (uint8_t *)p, 254) == le16_to_cpu(p->crc)) { break; diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c index 6f55d92..64d8e32 100644 --- a/drivers/mtd/nand/omap2.c +++ b/drivers/mtd/nand/omap2.c @@ -933,7 +933,7 @@ static int omap_calculate_ecc(struct mtd_info *mtd, const u_char *dat, u32 val; val = readl(info->reg.gpmc_ecc_config); - if (((val >> ECC_CONFIG_CS_SHIFT) & ~CS_MASK) != info->gpmc_cs) + if (((val >> ECC_CONFIG_CS_SHIFT) & CS_MASK) != info->gpmc_cs) return -EINVAL; /* read ecc result */ diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index 51e15fd..d058b00 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -481,6 +481,42 @@ static void disable_int(struct pxa3xx_nand_info *info, uint32_t int_mask) nand_writel(info, NDCR, ndcr | int_mask); } +static void drain_fifo(struct pxa3xx_nand_info *info, void *data, int len) +{ + if (info->ecc_bch) { + int timeout; + + /* + * According to the datasheet, when reading from NDDB + * with BCH enabled, after each 32 bytes reads, we + * have to make sure that the NDSR.RDDREQ bit is set. + * + * Drain the FIFO 8 32 bits reads at a time, and skip + * the polling on the last read. + */ + while (len > 8) { + __raw_readsl(info->mmio_base + NDDB, data, 8); + + for (timeout = 0; + !(nand_readl(info, NDSR) & NDSR_RDDREQ); + timeout++) { + if (timeout >= 5) { + dev_err(&info->pdev->dev, + "Timeout on RDDREQ while draining the FIFO\n"); + return; + } + + mdelay(1); + } + + data += 32; + len -= 8; + } + } + + __raw_readsl(info->mmio_base + NDDB, data, len); +} + static void handle_data_pio(struct pxa3xx_nand_info *info) { unsigned int do_bytes = min(info->data_size, info->chunk_size); @@ -497,14 +533,14 @@ static void handle_data_pio(struct pxa3xx_nand_info *info) DIV_ROUND_UP(info->oob_size, 4)); break; case STATE_PIO_READING: - __raw_readsl(info->mmio_base + NDDB, - info->data_buff + info->data_buff_pos, - DIV_ROUND_UP(do_bytes, 4)); + drain_fifo(info, + info->data_buff + info->data_buff_pos, + DIV_ROUND_UP(do_bytes, 4)); if (info->oob_size > 0) - __raw_readsl(info->mmio_base + NDDB, - info->oob_buff + info->oob_buff_pos, - DIV_ROUND_UP(info->oob_size, 4)); + drain_fifo(info, + info->oob_buff + info->oob_buff_pos, + DIV_ROUND_UP(info->oob_size, 4)); break; default: dev_err(&info->pdev->dev, "%s: invalid state %d\n", __func__, diff --git a/drivers/mtd/tests/torturetest.c b/drivers/mtd/tests/torturetest.c index eeab969..b55bc52 100644 --- a/drivers/mtd/tests/torturetest.c +++ b/drivers/mtd/tests/torturetest.c @@ -264,7 +264,9 @@ static int __init tort_init(void) int i; void *patt; - mtdtest_erase_good_eraseblocks(mtd, bad_ebs, eb, ebcnt); + err = mtdtest_erase_good_eraseblocks(mtd, bad_ebs, eb, ebcnt); + if (err) + goto out; /* Check if the eraseblocks contain only 0xFF bytes */ if (check) { diff --git a/drivers/mtd/ubi/attach.c b/drivers/mtd/ubi/attach.c index 6f27d9a..21841fe 100644 --- a/drivers/mtd/ubi/attach.c +++ b/drivers/mtd/ubi/attach.c @@ -408,7 +408,7 @@ int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb, second_is_newer = !second_is_newer; } else { dbg_bld("PEB %d CRC is OK", pnum); - bitflips = !!err; + bitflips |= !!err; } mutex_unlock(&ubi->buf_mutex); diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c index 8ca49f2..4cbbd55 100644 --- a/drivers/mtd/ubi/cdev.c +++ b/drivers/mtd/ubi/cdev.c @@ -451,7 +451,7 @@ static long vol_cdev_ioctl(struct file *file, unsigned int cmd, /* Validate the request */ err = -EINVAL; if (req.lnum < 0 || req.lnum >= vol->reserved_pebs || - req.bytes < 0 || req.lnum >= vol->usable_leb_size) + req.bytes < 0 || req.bytes > vol->usable_leb_size) break; err = get_exclusive(desc); diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index 0e11671d..930cf2c 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -1362,7 +1362,8 @@ int ubi_eba_init(struct ubi_device *ubi, struct ubi_attach_info *ai) * during re-size. */ ubi_move_aeb_to_list(av, aeb, &ai->erase); - vol->eba_tbl[aeb->lnum] = aeb->pnum; + else + vol->eba_tbl[aeb->lnum] = aeb->pnum; } } diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index c5dad65..904b451 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -330,6 +330,7 @@ static int process_pool_aeb(struct ubi_device *ubi, struct ubi_attach_info *ai, av = tmp_av; else { ubi_err("orphaned volume in fastmap pool!"); + kmem_cache_free(ai->aeb_slab_cache, new_aeb); return UBI_BAD_FASTMAP; } diff --git a/drivers/mtd/ubi/misc.c b/drivers/mtd/ubi/misc.c index f913d70..c4b1af0 100644 --- a/drivers/mtd/ubi/misc.c +++ b/drivers/mtd/ubi/misc.c @@ -74,6 +74,8 @@ int ubi_check_volume(struct ubi_device *ubi, int vol_id) for (i = 0; i < vol->used_ebs; i++) { int size; + cond_resched(); + if (i == vol->used_ebs - 1) size = vol->last_eb_bytes; else diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c index ec2c2dc..2a1b6e0 100644 --- a/drivers/mtd/ubi/upd.c +++ b/drivers/mtd/ubi/upd.c @@ -133,6 +133,10 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol, ubi_assert(!vol->updating && !vol->changing_leb); vol->updating = 1; + vol->upd_buf = vmalloc(ubi->leb_size); + if (!vol->upd_buf) + return -ENOMEM; + err = set_update_marker(ubi, vol); if (err) return err; @@ -152,14 +156,12 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol, err = clear_update_marker(ubi, vol, 0); if (err) return err; + + vfree(vol->upd_buf); vol->updating = 0; return 0; } - vol->upd_buf = vmalloc(ubi->leb_size); - if (!vol->upd_buf) - return -ENOMEM; - vol->upd_ebs = div_u64(bytes + vol->usable_leb_size - 1, vol->usable_leb_size); vol->upd_bytes = bytes; diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 02317c1..c6b0b07 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -995,7 +995,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, int cancel) { int err, scrubbing = 0, torture = 0, protect = 0, erroneous = 0; - int vol_id = -1, uninitialized_var(lnum); + int vol_id = -1, lnum = -1; #ifdef CONFIG_MTD_UBI_FASTMAP int anchor = wrk->anchor; #endif @@ -1205,7 +1205,6 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, err = do_sync_erase(ubi, e1, vol_id, lnum, 0); if (err) { - kmem_cache_free(ubi_wl_entry_slab, e1); if (e2) kmem_cache_free(ubi_wl_entry_slab, e2); goto out_ro; @@ -1219,10 +1218,8 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, dbg_wl("PEB %d (LEB %d:%d) was put meanwhile, erase", e2->pnum, vol_id, lnum); err = do_sync_erase(ubi, e2, vol_id, lnum, 0); - if (err) { - kmem_cache_free(ubi_wl_entry_slab, e2); + if (err) goto out_ro; - } } dbg_wl("done"); @@ -1258,10 +1255,9 @@ out_not_moved: ubi_free_vid_hdr(ubi, vid_hdr); err = do_sync_erase(ubi, e2, vol_id, lnum, torture); - if (err) { - kmem_cache_free(ubi_wl_entry_slab, e2); + if (err) goto out_ro; - } + mutex_unlock(&ubi->move_mutex); return 0; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 494b888..7e5c6a8 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -135,6 +135,7 @@ config MACVLAN config MACVTAP tristate "MAC-VLAN based tap driver" depends on MACVLAN + depends on INET help This adds a specialized tap character device driver that is based on the MAC-VLAN network interface, called macvtap. A macvtap device @@ -205,6 +206,7 @@ config RIONET_RX_SIZE config TUN tristate "Universal TUN/TAP device driver support" + depends on INET select CRC32 ---help--- TUN/TAP provides packet reception and transmission for user space diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index dcde560..3177498 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -2479,7 +2479,7 @@ out: return NETDEV_TX_OK; err_free: /* no suitable interface, frame not sent */ - kfree_skb(skb); + dev_kfree_skb_any(skb); goto out; } diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index e8f133e..c67bbc9 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1479,7 +1479,7 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) } /* no suitable interface, frame not sent */ - kfree_skb(skb); + dev_kfree_skb_any(skb); out: return NETDEV_TX_OK; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1c5caf5..6f56d07 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2454,9 +2454,9 @@ static void bond_loadbalance_arp_mon(struct work_struct *work) if (!rtnl_trylock()) goto re_arm; - if (slave_state_changed) { + if (slave_state_changed) bond_slave_state_change(bond); - } else if (do_failover) { + if (do_failover) { /* the bond_select_active_slave must hold RTNL * and curr_slave_lock for write. */ @@ -3572,7 +3572,7 @@ static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int sl } } /* no slave that can tx has been found */ - kfree_skb(skb); + dev_kfree_skb_any(skb); } /** @@ -3628,8 +3628,14 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev else bond_xmit_slave_id(bond, skb, 0); } else { - slave_id = bond_rr_gen_slave_id(bond); - bond_xmit_slave_id(bond, skb, slave_id % bond->slave_cnt); + int slave_cnt = ACCESS_ONCE(bond->slave_cnt); + + if (likely(slave_cnt)) { + slave_id = bond_rr_gen_slave_id(bond); + bond_xmit_slave_id(bond, skb, slave_id % slave_cnt); + } else { + dev_kfree_skb_any(skb); + } } return NETDEV_TX_OK; @@ -3648,7 +3654,7 @@ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_d if (slave) bond_dev_queue_xmit(bond, skb, slave->dev); else - kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -3660,8 +3666,13 @@ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_d static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + int slave_cnt = ACCESS_ONCE(bond->slave_cnt); - bond_xmit_slave_id(bond, skb, bond_xmit_hash(bond, skb, bond->slave_cnt)); + if (likely(slave_cnt)) + bond_xmit_slave_id(bond, skb, + bond_xmit_hash(bond, skb, bond->slave_cnt)); + else + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -3691,7 +3702,7 @@ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) if (slave && IS_UP(slave->dev) && slave->link == BOND_LINK_UP) bond_dev_queue_xmit(bond, skb, slave->dev); else - kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -3778,7 +3789,7 @@ static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev pr_err("%s: Error: Unknown bonding mode %d\n", dev->name, bond->params.mode); WARN_ON_ONCE(1); - kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } } @@ -3799,7 +3810,7 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) if (bond_has_slaves(bond)) ret = __bond_start_xmit(skb, dev); else - kfree_skb(skb); + dev_kfree_skb_any(skb); rcu_read_unlock(); return ret; diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index fc59bc6..84ad2b4 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -384,7 +384,7 @@ void can_free_echo_skb(struct net_device *dev, unsigned int idx) BUG_ON(idx >= priv->echo_skb_max); if (priv->echo_skb[idx]) { - kfree_skb(priv->echo_skb[idx]); + dev_kfree_skb_any(priv->echo_skb[idx]); priv->echo_skb[idx] = NULL; } } @@ -502,6 +502,14 @@ struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf) skb->pkt_type = PACKET_BROADCAST; skb->ip_summed = CHECKSUM_UNNECESSARY; + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; @@ -664,10 +672,14 @@ static int can_changelink(struct net_device *dev, if (dev->flags & IFF_UP) return -EBUSY; cm = nla_data(data[IFLA_CAN_CTRLMODE]); - if (cm->flags & ~priv->ctrlmode_supported) + + /* check whether changed bits are allowed to be modified */ + if (cm->mask & ~priv->ctrlmode_supported) return -EOPNOTSUPP; + + /* clear bits to be modified and copy the flag values */ priv->ctrlmode &= ~cm->mask; - priv->ctrlmode |= cm->flags; + priv->ctrlmode |= (cm->flags & cm->mask); } if (data[IFLA_CAN_RESTART_MS]) { diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 9250e28..534c0b8 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -1102,12 +1102,19 @@ static int flexcan_probe(struct platform_device *pdev) const struct flexcan_devtype_data *devtype_data; struct net_device *dev; struct flexcan_priv *priv; + struct regulator *reg_xceiver; struct resource *mem; struct clk *clk_ipg = NULL, *clk_per = NULL; void __iomem *base; int err, irq; u32 clock_freq = 0; + reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver"); + if (PTR_ERR(reg_xceiver) == -EPROBE_DEFER) + return -EPROBE_DEFER; + else if (IS_ERR(reg_xceiver)) + reg_xceiver = NULL; + if (pdev->dev.of_node) of_property_read_u32(pdev->dev.of_node, "clock-frequency", &clock_freq); @@ -1169,9 +1176,7 @@ static int flexcan_probe(struct platform_device *pdev) priv->pdata = dev_get_platdata(&pdev->dev); priv->devtype_data = devtype_data; - priv->reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver"); - if (IS_ERR(priv->reg_xceiver)) - priv->reg_xceiver = NULL; + priv->reg_xceiver = reg_xceiver; netif_napi_add(dev, &priv->napi, flexcan_poll, FLEXCAN_NAPI_WEIGHT); diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c index 7fbe859..f34f7fa 100644 --- a/drivers/net/can/usb/esd_usb2.c +++ b/drivers/net/can/usb/esd_usb2.c @@ -1141,6 +1141,7 @@ static void esd_usb2_disconnect(struct usb_interface *intf) } } unlink_all_urbs(dev); + kfree(dev); } } diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index e77d110..3d19867 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -578,7 +578,7 @@ static int kvaser_usb_simple_msg_async(struct kvaser_usb_net_priv *priv, usb_sndbulkpipe(dev->udev, dev->bulk_out->bEndpointAddress), buf, msg->len, - kvaser_usb_simple_msg_callback, priv); + kvaser_usb_simple_msg_callback, netdev); usb_anchor_urb(urb, &priv->tx_submitted); err = usb_submit_urb(urb, GFP_ATOMIC); @@ -653,11 +653,6 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev, priv = dev->nets[channel]; stats = &priv->netdev->stats; - if (status & M16C_STATE_BUS_RESET) { - kvaser_usb_unlink_tx_urbs(priv); - return; - } - skb = alloc_can_err_skb(priv->netdev, &cf); if (!skb) { stats->rx_dropped++; @@ -668,7 +663,7 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev, netdev_dbg(priv->netdev, "Error status: 0x%02x\n", status); - if (status & M16C_STATE_BUS_OFF) { + if (status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) { cf->can_id |= CAN_ERR_BUSOFF; priv->can.can_stats.bus_off++; @@ -694,9 +689,7 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev, } new_state = CAN_STATE_ERROR_PASSIVE; - } - - if (status == M16C_STATE_BUS_ERROR) { + } else if (status & M16C_STATE_BUS_ERROR) { if ((priv->can.state < CAN_STATE_ERROR_WARNING) && ((txerr >= 96) || (rxerr >= 96))) { cf->can_id |= CAN_ERR_CRTL; @@ -706,7 +699,8 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev, priv->can.can_stats.error_warning++; new_state = CAN_STATE_ERROR_WARNING; - } else if (priv->can.state > CAN_STATE_ERROR_ACTIVE) { + } else if ((priv->can.state > CAN_STATE_ERROR_ACTIVE) && + ((txerr < 96) && (rxerr < 96))) { cf->can_id |= CAN_ERR_PROT; cf->data[2] = CAN_ERR_PROT_ACTIVE; @@ -1237,6 +1231,9 @@ static int kvaser_usb_close(struct net_device *netdev) if (err) netdev_warn(netdev, "Cannot stop device, error %d\n", err); + /* reset tx contexts */ + kvaser_usb_unlink_tx_urbs(priv); + priv->can.state = CAN_STATE_STOPPED; close_candev(priv->netdev); @@ -1285,12 +1282,14 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, if (!urb) { netdev_err(netdev, "No memory left for URBs\n"); stats->tx_dropped++; - goto nourbmem; + dev_kfree_skb(skb); + return NETDEV_TX_OK; } buf = kmalloc(sizeof(struct kvaser_msg), GFP_ATOMIC); if (!buf) { stats->tx_dropped++; + dev_kfree_skb(skb); goto nobufmem; } @@ -1325,6 +1324,7 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, } } + /* This should never happen; it implies a flow control bug */ if (!context) { netdev_warn(netdev, "cannot find free context\n"); ret = NETDEV_TX_BUSY; @@ -1355,9 +1355,6 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, if (unlikely(err)) { can_free_echo_skb(netdev, context->echo_index); - skb = NULL; /* set to NULL to avoid double free in - * dev_kfree_skb(skb) */ - atomic_dec(&priv->active_tx_urbs); usb_unanchor_urb(urb); @@ -1379,8 +1376,6 @@ releasebuf: kfree(buf); nobufmem: usb_free_urb(urb); -nourbmem: - dev_kfree_skb(skb); return ret; } @@ -1492,6 +1487,10 @@ static int kvaser_usb_init_one(struct usb_interface *intf, struct kvaser_usb_net_priv *priv; int i, err; + err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, channel); + if (err) + return err; + netdev = alloc_candev(sizeof(*priv), MAX_TX_URBS); if (!netdev) { dev_err(&intf->dev, "Cannot alloc candev\n"); @@ -1577,7 +1576,7 @@ static int kvaser_usb_probe(struct usb_interface *intf, { struct kvaser_usb *dev; int err = -ENOMEM; - int i; + int i, retry = 3; dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL); if (!dev) @@ -1595,10 +1594,15 @@ static int kvaser_usb_probe(struct usb_interface *intf, usb_set_intfdata(intf, dev); - for (i = 0; i < MAX_NET_DEVICES; i++) - kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, i); + /* On some x86 laptops, plugging a Kvaser device again after + * an unplug makes the firmware always ignore the very first + * command. For such a case, provide some room for retries + * instead of completely exiting the driver. + */ + do { + err = kvaser_usb_get_software_info(dev); + } while (--retry && err == -ETIMEDOUT); - err = kvaser_usb_get_software_info(dev); if (err) { dev_err(&intf->dev, "Cannot get software infos, error %d\n", err); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 0b7a4c3..03e7f0c 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -734,7 +734,7 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter, dev->cmd_buf = kmalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL); if (!dev->cmd_buf) { err = -ENOMEM; - goto lbl_set_intf_data; + goto lbl_free_candev; } dev->udev = usb_dev; @@ -773,7 +773,7 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter, err = register_candev(netdev); if (err) { dev_err(&intf->dev, "couldn't register CAN device: %d\n", err); - goto lbl_free_cmd_buf; + goto lbl_restore_intf_data; } if (dev->prev_siblings) @@ -786,14 +786,14 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter, if (dev->adapter->dev_init) { err = dev->adapter->dev_init(dev); if (err) - goto lbl_free_cmd_buf; + goto lbl_unregister_candev; } /* set bus off */ if (dev->adapter->dev_set_bus) { err = dev->adapter->dev_set_bus(dev, 0); if (err) - goto lbl_free_cmd_buf; + goto lbl_unregister_candev; } /* get device number early */ @@ -805,11 +805,14 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter, return 0; -lbl_free_cmd_buf: - kfree(dev->cmd_buf); +lbl_unregister_candev: + unregister_candev(netdev); -lbl_set_intf_data: +lbl_restore_intf_data: usb_set_intfdata(intf, dev->prev_siblings); + kfree(dev->cmd_buf); + +lbl_free_candev: free_candev(netdev); return err; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 263dd92..f7f796a 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -333,8 +333,6 @@ static int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id, if (!(dev->state & PCAN_USB_STATE_CONNECTED)) return 0; - memset(req_addr, '\0', req_size); - req_type = USB_TYPE_VENDOR | USB_RECIP_OTHER; switch (req_id) { @@ -345,6 +343,7 @@ static int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id, default: p = usb_rcvctrlpipe(dev->udev, 0); req_type |= USB_DIR_IN; + memset(req_addr, '\0', req_size); break; } diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index 9339ccc..ad0e71c 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1516,7 +1516,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) { struct pcnet32_private *lp; int i, media; - int fdx, mii, fset, dxsuflo; + int fdx, mii, fset, dxsuflo, sram; int chip_version; char *chipname; struct net_device *dev; @@ -1553,7 +1553,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) } /* initialize variables */ - fdx = mii = fset = dxsuflo = 0; + fdx = mii = fset = dxsuflo = sram = 0; chip_version = (chip_version >> 12) & 0xffff; switch (chip_version) { @@ -1586,6 +1586,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) chipname = "PCnet/FAST III 79C973"; /* PCI */ fdx = 1; mii = 1; + sram = 1; break; case 0x2626: chipname = "PCnet/Home 79C978"; /* PCI */ @@ -1609,6 +1610,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) chipname = "PCnet/FAST III 79C975"; /* PCI */ fdx = 1; mii = 1; + sram = 1; break; case 0x2628: chipname = "PCnet/PRO 79C976"; @@ -1637,6 +1639,31 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) dxsuflo = 1; } + /* + * The Am79C973/Am79C975 controllers come with 12K of SRAM + * which we can use for the Tx/Rx buffers but most importantly, + * the use of SRAM allow us to use the BCR18:NOUFLO bit to avoid + * Tx fifo underflows. + */ + if (sram) { + /* + * The SRAM is being configured in two steps. First we + * set the SRAM size in the BCR25:SRAM_SIZE bits. According + * to the datasheet, each bit corresponds to a 512-byte + * page so we can have at most 24 pages. The SRAM_SIZE + * holds the value of the upper 8 bits of the 16-bit SRAM size. + * The low 8-bits start at 0x00 and end at 0xff. So the + * address range is from 0x0000 up to 0x17ff. Therefore, + * the SRAM_SIZE is set to 0x17. The next step is to set + * the BCR26:SRAM_BND midway through so the Tx and Rx + * buffers can share the SRAM equally. + */ + a->write_bcr(ioaddr, 25, 0x17); + a->write_bcr(ioaddr, 26, 0xc); + /* And finally enable the NOUFLO bit */ + a->write_bcr(ioaddr, 18, a->read_bcr(ioaddr, 18) | (1 << 11)); + } + dev = alloc_etherdev(sizeof(*lp)); if (!dev) { ret = -ENOMEM; diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 380d249..3e1d7d2 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -184,15 +184,16 @@ static void alx_schedule_reset(struct alx_priv *alx) schedule_work(&alx->reset_wk); } -static bool alx_clean_rx_irq(struct alx_priv *alx, int budget) +static int alx_clean_rx_irq(struct alx_priv *alx, int budget) { struct alx_rx_queue *rxq = &alx->rxq; struct alx_rrd *rrd; struct alx_buffer *rxb; struct sk_buff *skb; u16 length, rfd_cleaned = 0; + int work = 0; - while (budget > 0) { + while (work < budget) { rrd = &rxq->rrd[rxq->rrd_read_idx]; if (!(rrd->word3 & cpu_to_le32(1 << RRD_UPDATED_SHIFT))) break; @@ -203,7 +204,7 @@ static bool alx_clean_rx_irq(struct alx_priv *alx, int budget) ALX_GET_FIELD(le32_to_cpu(rrd->word0), RRD_NOR) != 1) { alx_schedule_reset(alx); - return 0; + return work; } rxb = &rxq->bufs[rxq->read_idx]; @@ -243,7 +244,7 @@ static bool alx_clean_rx_irq(struct alx_priv *alx, int budget) } napi_gro_receive(&alx->napi, skb); - budget--; + work++; next_pkt: if (++rxq->read_idx == alx->rx_ringsz) @@ -258,21 +259,22 @@ next_pkt: if (rfd_cleaned) alx_refill_rx_ring(alx, GFP_ATOMIC); - return budget > 0; + return work; } static int alx_poll(struct napi_struct *napi, int budget) { struct alx_priv *alx = container_of(napi, struct alx_priv, napi); struct alx_hw *hw = &alx->hw; - bool complete = true; unsigned long flags; + bool tx_complete; + int work; - complete = alx_clean_tx_irq(alx) && - alx_clean_rx_irq(alx, budget); + tx_complete = alx_clean_tx_irq(alx); + work = alx_clean_rx_irq(alx, budget); - if (!complete) - return 1; + if (!tx_complete || work == budget) + return budget; napi_complete(&alx->napi); @@ -284,7 +286,7 @@ static int alx_poll(struct napi_struct *napi, int budget) alx_post_write(hw); - return 0; + return work; } static irqreturn_t alx_intr_handle(struct alx_priv *alx, u32 intr) diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index 6c9e1c9..0c8a168 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -2886,7 +2886,7 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget) sw_cons = BNX2_NEXT_TX_BD(sw_cons); tx_bytes += skb->len; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); tx_pkt++; if (tx_pkt == budget) break; @@ -6640,7 +6640,7 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) mapping = dma_map_single(&bp->pdev->dev, skb->data, len, PCI_DMA_TODEVICE); if (dma_mapping_error(&bp->pdev->dev, mapping)) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -6733,7 +6733,7 @@ dma_error: PCI_DMA_TODEVICE); } - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index 391f29e..1fbeaa9 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -337,6 +337,7 @@ struct sw_tx_bd { u8 flags; /* Set on the first BD descriptor when there is a split BD */ #define BNX2X_TSO_SPLIT_BD (1<<0) +#define BNX2X_HAS_SECOND_PBD (1<<1) }; struct sw_rx_page { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 5ed5124..a830d42 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -223,6 +223,12 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata, --nbd; bd_idx = TX_BD(NEXT_TX_IDX(bd_idx)); + if (tx_buf->flags & BNX2X_HAS_SECOND_PBD) { + /* Skip second parse bd... */ + --nbd; + bd_idx = TX_BD(NEXT_TX_IDX(bd_idx)); + } + /* TSO headers+data bds share a common mapping. See bnx2x_tx_split() */ if (tx_buf->flags & BNX2X_TSO_SPLIT_BD) { tx_data_bd = &txdata->tx_desc_ring[bd_idx].reg_bd; @@ -3125,7 +3131,7 @@ static int bnx2x_poll(struct napi_struct *napi, int budget) } #endif if (!bnx2x_fp_lock_napi(fp)) - return work_done; + return budget; for_each_cos_in_tx_queue(fp, cos) if (bnx2x_tx_queue_has_work(fp->txdata_ptr[cos])) @@ -3868,6 +3874,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) /* set encapsulation flag in start BD */ SET_FLAG(tx_start_bd->general_data, ETH_TX_START_BD_TUNNEL_EXIST, 1); + + tx_buf->flags |= BNX2X_HAS_SECOND_PBD; + nbd++; } else if (xmit_type & XMIT_CSUM) { /* Set PBD in checksum offload case w/o encapsulation */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 7d43822..2428740 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -12395,6 +12395,9 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev, pci_write_config_dword(bp->pdev, PCICFG_GRC_ADDRESS, PCICFG_VENDOR_ID_OFFSET); + /* Set PCIe reset type to fundamental for EEH recovery */ + pdev->needs_freset = 1; + /* AER (Advanced Error reporting) configuration */ rc = pci_enable_pcie_error_reporting(pdev); if (!rc) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 9ab6cc3..1ff5698 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6594,7 +6594,7 @@ static void tg3_tx(struct tg3_napi *tnapi) pkts_compl++; bytes_compl += skb->len; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); if (unlikely(tx_bug)) { tg3_tx_recover(tp); @@ -6924,8 +6924,9 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget) skb->protocol = eth_type_trans(skb, tp->dev); if (len > (tp->dev->mtu + ETH_HLEN) && - skb->protocol != htons(ETH_P_8021Q)) { - dev_kfree_skb(skb); + skb->protocol != htons(ETH_P_8021Q) && + skb->protocol != htons(ETH_P_8021AD)) { + dev_kfree_skb_any(skb); goto drop_it_no_recycle; } @@ -7808,7 +7809,7 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi, PCI_DMA_TODEVICE); /* Make sure the mapping succeeded */ if (pci_dma_mapping_error(tp->pdev, new_addr)) { - dev_kfree_skb(new_skb); + dev_kfree_skb_any(new_skb); ret = -1; } else { u32 save_entry = *entry; @@ -7823,13 +7824,13 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi, new_skb->len, base_flags, mss, vlan)) { tg3_tx_skb_unmap(tnapi, save_entry, -1); - dev_kfree_skb(new_skb); + dev_kfree_skb_any(new_skb); ret = -1; } } } - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); *pskb = new_skb; return ret; } @@ -7872,7 +7873,7 @@ static int tg3_tso_bug(struct tg3 *tp, struct sk_buff *skb) } while (segs); tg3_tso_bug_end: - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -7916,8 +7917,6 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) entry = tnapi->tx_prod; base_flags = 0; - if (skb->ip_summed == CHECKSUM_PARTIAL) - base_flags |= TXD_FLAG_TCPUDP_CSUM; mss = skb_shinfo(skb)->gso_size; if (mss) { @@ -7933,6 +7932,13 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb) - ETH_HLEN; + /* HW/FW can not correctly segment packets that have been + * vlan encapsulated. + */ + if (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)) + return tg3_tso_bug(tp, skb); + if (!skb_is_gso_v6(skb)) { iph->check = 0; iph->tot_len = htons(mss + hdr_len); @@ -7979,6 +7985,17 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) base_flags |= tsflags << 12; } } + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + /* HW/FW can not correctly checksum packets that have been + * vlan encapsulated. + */ + if (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)) { + if (skb_checksum_help(skb)) + goto drop; + } else { + base_flags |= TXD_FLAG_TCPUDP_CSUM; + } } if (tg3_flag(tp, USE_JUMBO_BDFLAG) && @@ -8094,7 +8111,7 @@ dma_error: tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, --i); tnapi->tx_buffers[tnapi->tx_prod].skb = NULL; drop: - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); drop_nofree: tp->tx_dropped++; return NETDEV_TX_OK; @@ -8532,7 +8549,8 @@ static int tg3_init_rings(struct tg3 *tp) if (tnapi->rx_rcb) memset(tnapi->rx_rcb, 0, TG3_RX_RCB_RING_BYTES(tp)); - if (tg3_rx_prodring_alloc(tp, &tnapi->prodring)) { + if (tnapi->prodring.rx_std && + tg3_rx_prodring_alloc(tp, &tnapi->prodring)) { tg3_free_rings(tp); return -ENOMEM; } @@ -17714,23 +17732,6 @@ static int tg3_init_one(struct pci_dev *pdev, goto err_out_apeunmap; } - /* - * Reset chip in case UNDI or EFI driver did not shutdown - * DMA self test will enable WDMAC and we'll see (spurious) - * pending DMA on the PCI bus at that point. - */ - if ((tr32(HOSTCC_MODE) & HOSTCC_MODE_ENABLE) || - (tr32(WDMAC_MODE) & WDMAC_MODE_ENABLE)) { - tw32(MEMARB_MODE, MEMARB_MODE_ENABLE); - tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); - } - - err = tg3_test_dma(tp); - if (err) { - dev_err(&pdev->dev, "DMA engine test failed, aborting\n"); - goto err_out_apeunmap; - } - intmbx = MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW; rcvmbx = MAILBOX_RCVRET_CON_IDX_0 + TG3_64BIT_REG_LOW; sndmbx = MAILBOX_SNDHOST_PROD_IDX_0 + TG3_64BIT_REG_LOW; @@ -17775,6 +17776,23 @@ static int tg3_init_one(struct pci_dev *pdev, sndmbx += 0xc; } + /* + * Reset chip in case UNDI or EFI driver did not shutdown + * DMA self test will enable WDMAC and we'll see (spurious) + * pending DMA on the PCI bus at that point. + */ + if ((tr32(HOSTCC_MODE) & HOSTCC_MODE_ENABLE) || + (tr32(WDMAC_MODE) & WDMAC_MODE_ENABLE)) { + tw32(MEMARB_MODE, MEMARB_MODE_ENABLE); + tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); + } + + err = tg3_test_dma(tp); + if (err) { + dev_err(&pdev->dev, "DMA engine test failed, aborting\n"); + goto err_out_apeunmap; + } + tg3_init_coal(tp); pci_set_drvdata(pdev, dev); diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 4ad1187..669eeb4 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -600,9 +600,9 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget) prefetch(bnad->netdev); cq = ccb->sw_q; - cmpl = &cq[ccb->producer_index]; while (packets < budget) { + cmpl = &cq[ccb->producer_index]; if (!cmpl->valid) break; /* The 'valid' field is set by the adapter, only after writing diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 6c78848..9e8f4be 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -30,7 +30,6 @@ #include #include #include -#include #include "macb.h" @@ -1800,7 +1799,6 @@ static int __init macb_probe(struct platform_device *pdev) struct phy_device *phydev; u32 config; int err = -ENXIO; - struct pinctrl *pinctrl; const char *mac; regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -1809,15 +1807,6 @@ static int __init macb_probe(struct platform_device *pdev) goto err_out; } - pinctrl = devm_pinctrl_get_select_default(&pdev->dev); - if (IS_ERR(pinctrl)) { - err = PTR_ERR(pinctrl); - if (err == -EPROBE_DEFER) - goto err_out; - - dev_warn(&pdev->dev, "No pinctrl provided\n"); - } - err = -ENOMEM; dev = alloc_etherdev(sizeof(*bp)); if (!dev) diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index b740bfc..ff9b423 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1044,10 +1044,14 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq, PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3); } - if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc) { - skb->csum = htons(checksum); - skb->ip_summed = CHECKSUM_COMPLETE; - } + /* Hardware does not provide whole packet checksum. It only + * provides pseudo checksum. Since hw validates the packet + * checksum but not provide us the checksum value. use + * CHECSUM_UNNECESSARY. + */ + if ((netdev->features & NETIF_F_RXCSUM) && tcp_udp_csum_ok && + ipv4_csum_ok) + skb->ip_summed = CHECKSUM_UNNECESSARY; if (vlan_stripped) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 80bfa03..075e7e7 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1883,7 +1883,7 @@ static u16 be_tx_compl_process(struct be_adapter *adapter, queue_tail_inc(txq); } while (cur_index != last_index); - kfree_skb(sent_skb); + dev_kfree_skb_any(sent_skb); return num_wrbs; } diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 1fc8334..55e3075 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -292,6 +292,18 @@ failure: atomic_add(buffers_added, &(pool->available)); } +/* + * The final 8 bytes of the buffer list is a counter of frames dropped + * because there was not a buffer in the buffer list capable of holding + * the frame. + */ +static void ibmveth_update_rx_no_buffer(struct ibmveth_adapter *adapter) +{ + __be64 *p = adapter->buffer_list_addr + 4096 - 8; + + adapter->rx_no_buffer = be64_to_cpup(p); +} + /* replenish routine */ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter) { @@ -307,8 +319,7 @@ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter) ibmveth_replenish_buffer_pool(adapter, pool); } - adapter->rx_no_buffer = *(u64 *)(((char*)adapter->buffer_list_addr) + - 4096 - 8); + ibmveth_update_rx_no_buffer(adapter); } /* empty and free ana buffer pool - also used to do cleanup in error paths */ @@ -698,8 +709,7 @@ static int ibmveth_close(struct net_device *netdev) free_irq(netdev->irq, netdev); - adapter->rx_no_buffer = *(u64 *)(((char *)adapter->buffer_list_addr) + - 4096 - 8); + ibmveth_update_rx_no_buffer(adapter); ibmveth_cleanup(adapter); diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 46e6544..b655fe4 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -144,6 +144,11 @@ static bool e1000_clean_rx_irq(struct e1000_adapter *adapter, static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter, struct e1000_rx_ring *rx_ring, int *work_done, int work_to_do); +static void e1000_alloc_dummy_rx_buffers(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring, + int cleaned_count) +{ +} static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter, struct e1000_rx_ring *rx_ring, int cleaned_count); @@ -3531,8 +3536,11 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) msleep(1); /* e1000_down has a dependency on max_frame_size */ hw->max_frame_size = max_frame; - if (netif_running(netdev)) + if (netif_running(netdev)) { + /* prevent buffers from being reallocated */ + adapter->alloc_rx_buf = e1000_alloc_dummy_rx_buffers; e1000_down(adapter); + } /* NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN * means we reserve 2 more, this pushes us to allocate from the next diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b901371..5d3206d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4024,6 +4024,9 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) DCB_CAP_DCBX_VER_IEEE; pf->flags |= I40E_FLAG_DCB_ENABLED; } + } else { + dev_info(&pf->pdev->dev, "AQ Querying DCB configuration failed: %d\n", + pf->hw.aq.asq_last_status); } out: @@ -8003,7 +8006,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) { dev_info(&pdev->dev, "init_pf_dcb failed: %d\n", err); pf->flags &= ~I40E_FLAG_DCB_ENABLED; - goto err_init_dcb; + /* Continue without DCB enabled */ } #endif /* CONFIG_I40E_DCB */ @@ -8119,9 +8122,6 @@ err_vsis: err_switch_setup: i40e_reset_interrupt_capability(pf); del_timer_sync(&pf->service_timer); -#ifdef CONFIG_I40E_DCB -err_init_dcb: -#endif /* CONFIG_I40E_DCB */ err_mac_addr: err_configure_lan_hmc: (void)i40e_shutdown_lan_hmc(hw); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 5ca8c47..206e79d 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1613,6 +1613,8 @@ void igb_power_up_link(struct igb_adapter *adapter) igb_power_up_phy_copper(&adapter->hw); else igb_power_up_serdes_link_82575(&adapter->hw); + + igb_setup_link(&adapter->hw); } /** diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 57e390c..f42c201 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -1521,12 +1521,12 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev) int tso; if (test_bit(__IXGB_DOWN, &adapter->flags)) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } if (skb->len <= 0) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -1543,7 +1543,7 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev) tso = ixgb_tso(adapter, skb); if (tso < 0) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index c4c00d9f..96fc7fe 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -213,7 +213,7 @@ /* Various constants */ /* Coalescing */ -#define MVNETA_TXDONE_COAL_PKTS 16 +#define MVNETA_TXDONE_COAL_PKTS 1 #define MVNETA_RX_COAL_PKTS 32 #define MVNETA_RX_COAL_USEC 100 @@ -1612,6 +1612,7 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev) u16 txq_id = skb_get_queue_mapping(skb); struct mvneta_tx_queue *txq = &pp->txqs[txq_id]; struct mvneta_tx_desc *tx_desc; + int len = skb->len; struct netdev_queue *nq; int frags = 0; u32 tx_cmd; @@ -1675,7 +1676,7 @@ out: u64_stats_update_begin(&stats->syncp); stats->tx_packets++; - stats->tx_bytes += skb->len; + stats->tx_bytes += len; u64_stats_update_end(&stats->syncp); } else { dev->stats.tx_dropped++; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 2f83f34..8be0f3e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2497,13 +2497,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, netif_carrier_off(dev); mlx4_en_set_default_moderation(priv); - err = register_netdev(dev); - if (err) { - en_err(priv, "Netdev registration failed for port %d\n", port); - goto out; - } - priv->registered = 1; - en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num); en_warn(priv, "Using %d RX rings\n", prof->rx_ring_num); @@ -2543,6 +2536,14 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, queue_delayed_work(mdev->workqueue, &priv->service_task, SERVICE_TASK_DELAY); + err = register_netdev(dev); + if (err) { + en_err(priv, "Netdev registration failed for port %d\n", port); + goto out; + } + + priv->registered = 1; + return 0; out: diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 1345703..a467261 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -325,7 +325,7 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, } } } - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return tx_info->nr_txbb; } @@ -810,8 +810,11 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) tx_desc->ctrl.fence_size = (real_size / 16) & 0x3f; tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { - tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM | - MLX4_WQE_CTRL_TCP_UDP_CSUM); + if (!skb->encapsulation) + tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM | + MLX4_WQE_CTRL_TCP_UDP_CSUM); + else + tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM); ring->tx_csum++; } diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 57428a0..1e8a4b4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -1456,7 +1456,7 @@ static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, switch (op) { case RES_OP_RESERVE: - count = get_param_l(&in_param); + count = get_param_l(&in_param) & 0xffffff; align = get_param_h(&in_param); err = mlx4_grant_resource(dev, slave, RES_QP, count, 0); if (err) diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 68026f7..4a474dd 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -872,6 +872,10 @@ static int myri10ge_dma_test(struct myri10ge_priv *mgp, int test_type) return -ENOMEM; dmatest_bus = pci_map_page(mgp->pdev, dmatest_page, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); + if (unlikely(pci_dma_mapping_error(mgp->pdev, dmatest_bus))) { + __free_page(dmatest_page); + return -ENOMEM; + } /* Run a small DMA test. * The magic multipliers to the length tell the firmware @@ -1293,6 +1297,7 @@ myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx, int bytes, int watchdog) { struct page *page; + dma_addr_t bus; int idx; #if MYRI10GE_ALLOC_SIZE > 4096 int end_offset; @@ -1317,11 +1322,21 @@ myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx, rx->watchdog_needed = 1; return; } + + bus = pci_map_page(mgp->pdev, page, 0, + MYRI10GE_ALLOC_SIZE, + PCI_DMA_FROMDEVICE); + if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) { + __free_pages(page, MYRI10GE_ALLOC_ORDER); + if (rx->fill_cnt - rx->cnt < 16) + rx->watchdog_needed = 1; + return; + } + rx->page = page; rx->page_offset = 0; - rx->bus = pci_map_page(mgp->pdev, page, 0, - MYRI10GE_ALLOC_SIZE, - PCI_DMA_FROMDEVICE); + rx->bus = bus; + } rx->info[idx].page = rx->page; rx->info[idx].page_offset = rx->page_offset; @@ -2765,6 +2780,35 @@ myri10ge_submit_req(struct myri10ge_tx_buf *tx, struct mcp_kreq_ether_send *src, mb(); } +static void myri10ge_unmap_tx_dma(struct myri10ge_priv *mgp, + struct myri10ge_tx_buf *tx, int idx) +{ + unsigned int len; + int last_idx; + + /* Free any DMA resources we've alloced and clear out the skb slot */ + last_idx = (idx + 1) & tx->mask; + idx = tx->req & tx->mask; + do { + len = dma_unmap_len(&tx->info[idx], len); + if (len) { + if (tx->info[idx].skb != NULL) + pci_unmap_single(mgp->pdev, + dma_unmap_addr(&tx->info[idx], + bus), len, + PCI_DMA_TODEVICE); + else + pci_unmap_page(mgp->pdev, + dma_unmap_addr(&tx->info[idx], + bus), len, + PCI_DMA_TODEVICE); + dma_unmap_len_set(&tx->info[idx], len, 0); + tx->info[idx].skb = NULL; + } + idx = (idx + 1) & tx->mask; + } while (idx != last_idx); +} + /* * Transmit a packet. We need to split the packet so that a single * segment does not cross myri10ge->tx_boundary, so this makes segment @@ -2788,7 +2832,7 @@ static netdev_tx_t myri10ge_xmit(struct sk_buff *skb, u32 low; __be32 high_swapped; unsigned int len; - int idx, last_idx, avail, frag_cnt, frag_idx, count, mss, max_segments; + int idx, avail, frag_cnt, frag_idx, count, mss, max_segments; u16 pseudo_hdr_offset, cksum_offset, queue; int cum_len, seglen, boundary, rdma_count; u8 flags, odd_flag; @@ -2885,9 +2929,12 @@ again: /* map the skb for DMA */ len = skb_headlen(skb); + bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE); + if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) + goto drop; + idx = tx->req & tx->mask; tx->info[idx].skb = skb; - bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE); dma_unmap_addr_set(&tx->info[idx], bus, bus); dma_unmap_len_set(&tx->info[idx], len, len); @@ -2986,12 +3033,16 @@ again: break; /* map next fragment for DMA */ - idx = (count + tx->req) & tx->mask; frag = &skb_shinfo(skb)->frags[frag_idx]; frag_idx++; len = skb_frag_size(frag); bus = skb_frag_dma_map(&mgp->pdev->dev, frag, 0, len, DMA_TO_DEVICE); + if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) { + myri10ge_unmap_tx_dma(mgp, tx, idx); + goto drop; + } + idx = (count + tx->req) & tx->mask; dma_unmap_addr_set(&tx->info[idx], bus, bus); dma_unmap_len_set(&tx->info[idx], len, len); } @@ -3022,31 +3073,8 @@ again: return NETDEV_TX_OK; abort_linearize: - /* Free any DMA resources we've alloced and clear out the skb - * slot so as to not trip up assertions, and to avoid a - * double-free if linearizing fails */ + myri10ge_unmap_tx_dma(mgp, tx, idx); - last_idx = (idx + 1) & tx->mask; - idx = tx->req & tx->mask; - tx->info[idx].skb = NULL; - do { - len = dma_unmap_len(&tx->info[idx], len); - if (len) { - if (tx->info[idx].skb != NULL) - pci_unmap_single(mgp->pdev, - dma_unmap_addr(&tx->info[idx], - bus), len, - PCI_DMA_TODEVICE); - else - pci_unmap_page(mgp->pdev, - dma_unmap_addr(&tx->info[idx], - bus), len, - PCI_DMA_TODEVICE); - dma_unmap_len_set(&tx->info[idx], len, 0); - tx->info[idx].skb = NULL; - } - idx = (idx + 1) & tx->mask; - } while (idx != last_idx); if (skb_is_gso(skb)) { netdev_err(mgp->dev, "TSO but wanted to linearize?!?!?\n"); goto drop; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 70849de..5fa076f 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -2390,7 +2390,10 @@ static int netxen_nic_poll(struct napi_struct *napi, int budget) work_done = netxen_process_rcv_ring(sds_ring, budget); - if ((work_done < budget) && tx_complete) { + if (!tx_complete) + work_done = budget; + + if (work_done < budget) { napi_complete(&sds_ring->napi); if (test_bit(__NX_DEV_UP, &adapter->state)) netxen_nic_enable_int(sds_ring); diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 737c1a8..a3c1daa 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -899,7 +899,7 @@ out_unlock: return NETDEV_TX_OK; out_dma_error: - kfree_skb(skb); + dev_kfree_skb_any(skb); cp->dev->stats.tx_dropped++; goto out_unlock; } diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index da5972e..8cb2f35 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -1717,9 +1717,9 @@ static netdev_tx_t rtl8139_start_xmit (struct sk_buff *skb, if (len < ETH_ZLEN) memset(tp->tx_buf[entry], 0, ETH_ZLEN); skb_copy_and_csum_dev(skb, tp->tx_buf[entry]); - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); } else { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 3ff7bc3..90c14d1 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -5834,7 +5834,7 @@ static void rtl8169_tx_clear_range(struct rtl8169_private *tp, u32 start, tp->TxDescArray + entry); if (skb) { tp->dev->stats.tx_dropped++; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); tx_skb->skb = NULL; } } @@ -6059,7 +6059,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, err_dma_1: rtl8169_unmap_tx_skb(d, tp->tx_skb + entry, txd); err_dma_0: - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); err_update_stats: dev->stats.tx_dropped++; return NETDEV_TX_OK; @@ -6142,7 +6142,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp) tp->tx_stats.packets++; tp->tx_stats.bytes += tx_skb->skb->len; u64_stats_update_end(&tp->tx_stats.syncp); - dev_kfree_skb(tx_skb->skb); + dev_kfree_skb_any(tx_skb->skb); tx_skb->skb = NULL; } dirty_tx++; diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index 6382b7c..e10f5ed 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -1341,6 +1341,42 @@ static void smsc911x_rx_multicast_update_workaround(struct smsc911x_data *pdata) spin_unlock(&pdata->mac_lock); } +static int smsc911x_phy_general_power_up(struct smsc911x_data *pdata) +{ + int rc = 0; + + if (!pdata->phy_dev) + return rc; + + /* If the internal PHY is in General Power-Down mode, all, except the + * management interface, is powered-down and stays in that condition as + * long as Phy register bit 0.11 is HIGH. + * + * In that case, clear the bit 0.11, so the PHY powers up and we can + * access to the phy registers. + */ + rc = phy_read(pdata->phy_dev, MII_BMCR); + if (rc < 0) { + SMSC_WARN(pdata, drv, "Failed reading PHY control reg"); + return rc; + } + + /* If the PHY general power-down bit is not set is not necessary to + * disable the general power down-mode. + */ + if (rc & BMCR_PDOWN) { + rc = phy_write(pdata->phy_dev, MII_BMCR, rc & ~BMCR_PDOWN); + if (rc < 0) { + SMSC_WARN(pdata, drv, "Failed writing PHY control reg"); + return rc; + } + + usleep_range(1000, 1500); + } + + return 0; +} + static int smsc911x_phy_disable_energy_detect(struct smsc911x_data *pdata) { int rc = 0; @@ -1414,6 +1450,16 @@ static int smsc911x_soft_reset(struct smsc911x_data *pdata) int ret; /* + * Make sure to power-up the PHY chip before doing a reset, otherwise + * the reset fails. + */ + ret = smsc911x_phy_general_power_up(pdata); + if (ret) { + SMSC_WARN(pdata, drv, "Failed to power-up the PHY chip"); + return ret; + } + + /* * LAN9210/LAN9211/LAN9220/LAN9221 chips have an internal PHY that * are initialized in a Energy Detect Power-Down mode that prevents * the MAC chip to be software reseted. So we have to wakeup the PHY diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index fd411d6..03ae9de 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -656,7 +656,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) spin_lock_irqsave(&port->vio.lock, flags); dr = &port->vio.drings[VIO_DRIVER_TX_RING]; - if (unlikely(vnet_tx_dring_avail(dr) < 2)) { + if (unlikely(vnet_tx_dring_avail(dr) < 1)) { if (!netif_queue_stopped(dev)) { netif_stop_queue(dev); @@ -704,7 +704,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_bytes += skb->len; dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1); - if (unlikely(vnet_tx_dring_avail(dr) < 2)) { + if (unlikely(vnet_tx_dring_avail(dr) < 1)) { netif_stop_queue(dev); if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr)) netif_wake_queue(dev); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 921b9df..4eb091d 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -596,7 +596,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) /* Clear all mcast from ALE */ cpsw_ale_flush_multicast(ale, ALE_ALL_PORTS << - priv->host_port); + priv->host_port, -1); /* Flood All Unicast Packets to Host port */ cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 1); @@ -620,6 +620,12 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) static void cpsw_ndo_set_rx_mode(struct net_device *ndev) { struct cpsw_priv *priv = netdev_priv(ndev); + int vid; + + if (priv->data.dual_emac) + vid = priv->slaves[priv->emac_port].port_vlan; + else + vid = priv->data.default_vlan; if (ndev->flags & IFF_PROMISC) { /* Enable promiscuous mode */ @@ -631,7 +637,8 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) } /* Clear all mcast from ALE */ - cpsw_ale_flush_multicast(priv->ale, ALE_ALL_PORTS << priv->host_port); + cpsw_ale_flush_multicast(priv->ale, ALE_ALL_PORTS << priv->host_port, + vid); if (!netdev_mc_empty(ndev)) { struct netdev_hw_addr *ha; @@ -716,6 +723,14 @@ static void cpsw_rx_handler(void *token, int len, int status) static irqreturn_t cpsw_interrupt(int irq, void *dev_id) { struct cpsw_priv *priv = dev_id; + int value = irq - priv->irqs_table[0]; + + /* NOTICE: Ending IRQ here. The trick with the 'value' variable above + * is to make sure we will always write the correct value to the EOI + * register. Namely 0 for RX_THRESH Interrupt, 1 for RX Interrupt, 2 + * for TX Interrupt and 3 for MISC Interrupt. + */ + cpdma_ctlr_eoi(priv->dma, value); cpsw_intr_disable(priv); if (priv->irq_enabled == true) { @@ -745,8 +760,6 @@ static int cpsw_poll(struct napi_struct *napi, int budget) int num_tx, num_rx; num_tx = cpdma_chan_process(priv->txch, 128); - if (num_tx) - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX); num_rx = cpdma_chan_process(priv->rxch, budget); if (num_rx < budget) { @@ -754,7 +767,6 @@ static int cpsw_poll(struct napi_struct *napi, int budget) napi_complete(napi); cpsw_intr_enable(priv); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX); prim_cpsw = cpsw_get_slave_priv(priv, 0); if (prim_cpsw->irq_enabled == false) { prim_cpsw->irq_enabled = true; @@ -1265,8 +1277,6 @@ static int cpsw_ndo_open(struct net_device *ndev) napi_enable(&priv->napi); cpdma_ctlr_start(priv->dma); cpsw_intr_enable(priv); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX); if (priv->data.dual_emac) priv->slaves[priv->emac_port].open_stat = true; @@ -1512,9 +1522,6 @@ static void cpsw_ndo_tx_timeout(struct net_device *ndev) cpdma_chan_start(priv->txch); cpdma_ctlr_int_ctrl(priv->dma, true); cpsw_intr_enable(priv); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX); - } static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p) @@ -1560,9 +1567,6 @@ static void cpsw_ndo_poll_controller(struct net_device *ndev) cpsw_interrupt(ndev->irq, priv); cpdma_ctlr_int_ctrl(priv->dma, true); cpsw_intr_enable(priv); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX); - } #endif @@ -1606,6 +1610,19 @@ static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev, if (vid == priv->data.default_vlan) return 0; + if (priv->data.dual_emac) { + /* In dual EMAC, reserved VLAN id should not be used for + * creating VLAN interfaces as this can break the dual + * EMAC port separation + */ + int i; + + for (i = 0; i < priv->data.slaves; i++) { + if (vid == priv->slaves[i].port_vlan) + return -EINVAL; + } + } + dev_info(priv->dev, "Adding vlanid %d to vlan filter\n", vid); return cpsw_add_vlan_ale_entry(priv, vid); } @@ -1619,6 +1636,15 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev, if (vid == priv->data.default_vlan) return 0; + if (priv->data.dual_emac) { + int i; + + for (i = 0; i < priv->data.slaves; i++) { + if (vid == priv->slaves[i].port_vlan) + return -EINVAL; + } + } + dev_info(priv->dev, "removing vlanid %d from vlan filter\n", vid); ret = cpsw_ale_del_vlan(priv->ale, vid, 0); if (ret != 0) diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 7f89306..4eceb7e 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -236,7 +236,7 @@ static void cpsw_ale_flush_mcast(struct cpsw_ale *ale, u32 *ale_entry, cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE); } -int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask) +int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid) { u32 ale_entry[ALE_ENTRY_WORDS]; int ret, idx; @@ -247,6 +247,14 @@ int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask) if (ret != ALE_TYPE_ADDR && ret != ALE_TYPE_VLAN_ADDR) continue; + /* if vid passed is -1 then remove all multicast entry from + * the table irrespective of vlan id, if a valid vlan id is + * passed then remove only multicast added to that vlan id. + * if vlan id doesn't match then move on to next entry. + */ + if (vid != -1 && cpsw_ale_get_vlan_id(ale_entry) != vid) + continue; + if (cpsw_ale_get_mcast(ale_entry)) { u8 addr[6]; diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h index de409c3..e701358 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.h +++ b/drivers/net/ethernet/ti/cpsw_ale.h @@ -88,7 +88,7 @@ void cpsw_ale_stop(struct cpsw_ale *ale); int cpsw_ale_set_ageout(struct cpsw_ale *ale, int ageout); int cpsw_ale_flush(struct cpsw_ale *ale, int port_mask); -int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask); +int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid); int cpsw_ale_add_ucast(struct cpsw_ale *ale, u8 *addr, int port, int flags, u16 vid); int cpsw_ale_del_ucast(struct cpsw_ale *ale, u8 *addr, int port, diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index d6fce97..3c1c33c 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -146,6 +146,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) struct hv_netvsc_packet *packet; int ret; unsigned int i, num_pages, npg_data; + u32 skb_length = skb->len; /* Add multipages for skb->data and additional 2 for RNDIS */ npg_data = (((unsigned long)skb->data + skb_headlen(skb) - 1) @@ -216,7 +217,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) ret = rndis_filter_send(net_device_ctx->device_ctx, packet); if (ret == 0) { - net->stats.tx_bytes += skb->len; + net->stats.tx_bytes += skb_length; net->stats.tx_packets++; } else { kfree(packet); diff --git a/drivers/net/ieee802154/fakehard.c b/drivers/net/ieee802154/fakehard.c index bf0d55e..6adbef8 100644 --- a/drivers/net/ieee802154/fakehard.c +++ b/drivers/net/ieee802154/fakehard.c @@ -376,17 +376,20 @@ static int ieee802154fake_probe(struct platform_device *pdev) err = wpan_phy_register(phy); if (err) - goto out; + goto err_phy_reg; err = register_netdev(dev); - if (err < 0) - goto out; + if (err) + goto err_netdev_reg; dev_info(&pdev->dev, "Added ieee802154 HardMAC hardware\n"); return 0; -out: - unregister_netdev(dev); +err_netdev_reg: + wpan_phy_unregister(phy); +err_phy_reg: + free_netdev(dev); + wpan_phy_free(phy); return err; } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 5adecc5..fbf7dcd 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -548,6 +548,7 @@ static int macvlan_init(struct net_device *dev) (lowerdev->state & MACVLAN_STATE_MASK); dev->features = lowerdev->features & MACVLAN_FEATURES; dev->features |= ALWAYS_ON_FEATURES; + dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; dev->gso_max_size = lowerdev->gso_max_size; dev->iflink = lowerdev->ifindex; dev->hard_header_len = lowerdev->hard_header_len; @@ -708,6 +709,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev, features, mask); features |= ALWAYS_ON_FEATURES; + features &= ~NETIF_F_NETNS_LOCAL; return features; } diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 3381c4f..e8c21f9 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -16,6 +16,7 @@ #include #include +#include #include #include #include @@ -112,17 +113,15 @@ out: return err; } +/* Requires RTNL */ static int macvtap_set_queue(struct net_device *dev, struct file *file, struct macvtap_queue *q) { struct macvlan_dev *vlan = netdev_priv(dev); - int err = -EBUSY; - rtnl_lock(); if (vlan->numqueues == MAX_MACVTAP_QUEUES) - goto out; + return -EBUSY; - err = 0; rcu_assign_pointer(q->vlan, vlan); rcu_assign_pointer(vlan->taps[vlan->numvtaps], q); sock_hold(&q->sk); @@ -136,9 +135,7 @@ static int macvtap_set_queue(struct net_device *dev, struct file *file, vlan->numvtaps++; vlan->numqueues++; -out: - rtnl_unlock(); - return err; + return 0; } static int macvtap_disable_queue(struct macvtap_queue *q) @@ -454,11 +451,12 @@ static void macvtap_sock_destruct(struct sock *sk) static int macvtap_open(struct inode *inode, struct file *file) { struct net *net = current->nsproxy->net_ns; - struct net_device *dev = dev_get_by_macvtap_minor(iminor(inode)); + struct net_device *dev; struct macvtap_queue *q; - int err; + int err = -ENODEV; - err = -ENODEV; + rtnl_lock(); + dev = dev_get_by_macvtap_minor(iminor(inode)); if (!dev) goto out; @@ -498,6 +496,7 @@ out: if (dev) dev_put(dev); + rtnl_unlock(); return err; } @@ -572,6 +571,8 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb, break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; + if (skb->protocol == htons(ETH_P_IPV6)) + ipv6_proxy_select_ident(skb); break; default: return -EINVAL; @@ -628,18 +629,23 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_PARTIAL) { vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; vnet_hdr->csum_start = skb_checksum_start_offset(skb); + if (vlan_tx_tag_present(skb)) + vnet_hdr->csum_start += VLAN_HLEN; vnet_hdr->csum_offset = skb->csum_offset; } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ } +/* Neighbour code has some assumptions on HH_DATA_MOD alignment */ +#define MACVTAP_RESERVE HH_DATA_OFF(ETH_HLEN) + /* Get packet from user space buffer */ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, const struct iovec *iv, unsigned long total_len, size_t count, int noblock) { - int good_linear = SKB_MAX_HEAD(NET_IP_ALIGN); + int good_linear = SKB_MAX_HEAD(MACVTAP_RESERVE); struct sk_buff *skb; struct macvlan_dev *vlan; unsigned long len = total_len; @@ -698,7 +704,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, linear = vnet_hdr.hdr_len; } - skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen, + skb = macvtap_alloc_skb(&q->sk, MACVTAP_RESERVE, copylen, linear, noblock, &err); if (!skb) goto err; diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 98e7cbf..0be3f9d 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -45,7 +45,7 @@ #define PSF_TX 0x1000 #define EXT_EVENT 1 #define CAL_EVENT 7 -#define CAL_TRIGGER 7 +#define CAL_TRIGGER 1 #define PER_TRIGGER 6 #define MII_DP83640_MICR 0x11 @@ -442,7 +442,9 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp, else evnt |= EVNT_RISE; } + mutex_lock(&clock->extreg_lock); ext_write(0, phydev, PAGE5, PTP_EVNT, evnt); + mutex_unlock(&clock->extreg_lock); return 0; case PTP_CLK_REQ_PEROUT: @@ -463,6 +465,8 @@ static u8 status_frame_src[6] = { 0x08, 0x00, 0x17, 0x0B, 0x6B, 0x0F }; static void enable_status_frames(struct phy_device *phydev, bool on) { + struct dp83640_private *dp83640 = phydev->priv; + struct dp83640_clock *clock = dp83640->clock; u16 cfg0 = 0, ver; if (on) @@ -470,9 +474,13 @@ static void enable_status_frames(struct phy_device *phydev, bool on) ver = (PSF_PTPVER & VERSIONPTP_MASK) << VERSIONPTP_SHIFT; + mutex_lock(&clock->extreg_lock); + ext_write(0, phydev, PAGE5, PSF_CFG0, cfg0); ext_write(0, phydev, PAGE6, PSF_CFG1, ver); + mutex_unlock(&clock->extreg_lock); + if (!phydev->attached_dev) { pr_warn("expected to find an attached netdevice\n"); return; @@ -1063,11 +1071,18 @@ static int dp83640_config_init(struct phy_device *phydev) if (clock->chosen && !list_empty(&clock->phylist)) recalibrate(clock); - else + else { + mutex_lock(&clock->extreg_lock); enable_broadcast(phydev, clock->page, 1); + mutex_unlock(&clock->extreg_lock); + } enable_status_frames(phydev, true); + + mutex_lock(&clock->extreg_lock); ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE); + mutex_unlock(&clock->extreg_lock); + return 0; } diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 76d96b9..65cfc5a 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -194,6 +194,25 @@ static inline unsigned int phy_find_valid(unsigned int idx, u32 features) } /** + * phy_check_valid - check if there is a valid PHY setting which matches + * speed, duplex, and feature mask + * @speed: speed to match + * @duplex: duplex to match + * @features: A mask of the valid settings + * + * Description: Returns true if there is a valid setting, false otherwise. + */ +static inline bool phy_check_valid(int speed, int duplex, u32 features) +{ + unsigned int idx; + + idx = phy_find_valid(phy_find_setting(speed, duplex), features); + + return settings[idx].speed == speed && settings[idx].duplex == duplex && + (settings[idx].setting & features); +} + +/** * phy_sanitize_settings - make sure the PHY is set to supported speed and duplex * @phydev: the target phy_device struct * @@ -946,16 +965,17 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) { /* According to 802.3az,the EEE is supported only in full duplex-mode. * Also EEE feature is active when core is operating with MII, GMII - * or RGMII. + * or RGMII (all kinds). Internal PHYs are also allowed to proceed and + * should return an error if they do not support EEE. */ if ((phydev->duplex == DUPLEX_FULL) && ((phydev->interface == PHY_INTERFACE_MODE_MII) || (phydev->interface == PHY_INTERFACE_MODE_GMII) || - (phydev->interface == PHY_INTERFACE_MODE_RGMII))) { + (phydev->interface >= PHY_INTERFACE_MODE_RGMII && + phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID))) { int eee_lp, eee_cap, eee_adv; u32 lp, cap, adv; int status; - unsigned int idx; /* Read phy status to properly get the right settings */ status = phy_read_status(phydev); @@ -987,8 +1007,7 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) adv = mmd_eee_adv_to_ethtool_adv_t(eee_adv); lp = mmd_eee_adv_to_ethtool_adv_t(eee_lp); - idx = phy_find_setting(phydev->speed, phydev->duplex); - if (!(lp & adv & settings[idx].setting)) + if (!phy_check_valid(phydev->speed, phydev->duplex, lp & adv)) return -EPROTONOSUPPORT; if (clk_stop_enable) { diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 701cc2e..db7017c 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -353,7 +353,7 @@ int phy_device_register(struct phy_device *phydev) phydev->bus->phy_map[phydev->addr] = phydev; /* Run all of the fixups for this PHY */ - err = phy_init_hw(phydev); + err = phy_scan_fixups(phydev); if (err) { pr_err("PHY %d failed to initialize\n", phydev->addr); goto out; @@ -765,10 +765,11 @@ static int genphy_config_advert(struct phy_device *phydev) if (phydev->supported & (SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full)) { adv |= ethtool_adv_to_mii_ctrl1000_t(advertise); - if (adv != oldadv) - changed = 1; } + if (adv != oldadv) + changed = 1; + err = phy_write(phydev, MII_CTRL1000, adv); if (err < 0) return err; diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c index 602c625..b5edc7f 100644 --- a/drivers/net/ppp/ppp_deflate.c +++ b/drivers/net/ppp/ppp_deflate.c @@ -246,7 +246,7 @@ static int z_compress(void *arg, unsigned char *rptr, unsigned char *obuf, /* * See if we managed to reduce the size of the packet. */ - if (olen < isize) { + if (olen < isize && olen <= osize) { state->stats.comp_bytes += olen; state->stats.comp_packets++; } else { diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 72ff14b..5a1897d 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -601,7 +601,7 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (file == ppp->owner) ppp_shutdown_interface(ppp); } - if (atomic_long_read(&file->f_count) <= 2) { + if (atomic_long_read(&file->f_count) < 2) { ppp_release(NULL, file); err = 0; } else diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 0180531..1dc628f 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -281,7 +281,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) nf_reset(skb); skb->ip_summed = CHECKSUM_NONE; - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); ip_send_check(iph); ip_local_out(skb); @@ -506,7 +506,9 @@ static int pptp_getname(struct socket *sock, struct sockaddr *uaddr, int len = sizeof(struct sockaddr_pppox); struct sockaddr_pppox sp; - sp.sa_family = AF_PPPOX; + memset(&sp.sa_addr, 0, sizeof(sp.sa_addr)); + + sp.sa_family = AF_PPPOX; sp.sa_protocol = PX_PROTO_PPTP; sp.sa_addr.pptp = pppox_sk(sock->sk)->proto.pptp.src_addr; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 26d8c29..c28e2da 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -42,9 +42,7 @@ static struct team_port *team_port_get_rcu(const struct net_device *dev) { - struct team_port *port = rcu_dereference(dev->rx_handler_data); - - return team_port_exists(dev) ? port : NULL; + return rcu_dereference(dev->rx_handler_data); } static struct team_port *team_port_get_rtnl(const struct net_device *dev) @@ -629,6 +627,7 @@ static int team_change_mode(struct team *team, const char *kind) static void team_notify_peers_work(struct work_struct *work) { struct team *team; + int val; team = container_of(work, struct team, notify_peers.dw.work); @@ -636,9 +635,14 @@ static void team_notify_peers_work(struct work_struct *work) schedule_delayed_work(&team->notify_peers.dw, 0); return; } + val = atomic_dec_if_positive(&team->notify_peers.count_pending); + if (val < 0) { + rtnl_unlock(); + return; + } call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, team->dev); rtnl_unlock(); - if (!atomic_dec_and_test(&team->notify_peers.count_pending)) + if (val) schedule_delayed_work(&team->notify_peers.dw, msecs_to_jiffies(team->notify_peers.interval)); } @@ -647,7 +651,7 @@ static void team_notify_peers(struct team *team) { if (!team->notify_peers.count || !netif_running(team->dev)) return; - atomic_set(&team->notify_peers.count_pending, team->notify_peers.count); + atomic_add(team->notify_peers.count, &team->notify_peers.count_pending); schedule_delayed_work(&team->notify_peers.dw, 0); } @@ -669,6 +673,7 @@ static void team_notify_peers_fini(struct team *team) static void team_mcast_rejoin_work(struct work_struct *work) { struct team *team; + int val; team = container_of(work, struct team, mcast_rejoin.dw.work); @@ -676,9 +681,14 @@ static void team_mcast_rejoin_work(struct work_struct *work) schedule_delayed_work(&team->mcast_rejoin.dw, 0); return; } + val = atomic_dec_if_positive(&team->mcast_rejoin.count_pending); + if (val < 0) { + rtnl_unlock(); + return; + } call_netdevice_notifiers(NETDEV_RESEND_IGMP, team->dev); rtnl_unlock(); - if (!atomic_dec_and_test(&team->mcast_rejoin.count_pending)) + if (val) schedule_delayed_work(&team->mcast_rejoin.dw, msecs_to_jiffies(team->mcast_rejoin.interval)); } @@ -687,7 +697,7 @@ static void team_mcast_rejoin(struct team *team) { if (!team->mcast_rejoin.count || !netif_running(team->dev)) return; - atomic_set(&team->mcast_rejoin.count_pending, team->mcast_rejoin.count); + atomic_add(team->mcast_rejoin.count, &team->mcast_rejoin.count_pending); schedule_delayed_work(&team->mcast_rejoin.dw, 0); } @@ -1713,11 +1723,11 @@ static int team_set_mac_address(struct net_device *dev, void *p) if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); - rcu_read_lock(); - list_for_each_entry_rcu(port, &team->port_list, list) + mutex_lock(&team->lock); + list_for_each_entry(port, &team->port_list, list) if (team->ops.port_change_dev_addr) team->ops.port_change_dev_addr(team, port); - rcu_read_unlock(); + mutex_unlock(&team->lock); return 0; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 26f8635..ec63314 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -65,6 +65,7 @@ #include #include #include +#include #include #include #include @@ -1140,6 +1141,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, break; } + skb_reset_network_header(skb); + if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) { pr_debug("GSO!\n"); switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { @@ -1151,6 +1154,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, break; case VIRTIO_NET_HDR_GSO_UDP: skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + if (skb->protocol == htons(ETH_P_IPV6)) + ipv6_proxy_select_ident(skb); break; default: tun->dev->stats.rx_frame_errors++; @@ -1180,7 +1185,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; } - skb_reset_network_header(skb); skb_probe_transport_header(skb, 0); rxhash = skb_get_hash(skb); @@ -1222,6 +1226,10 @@ static ssize_t tun_put_user(struct tun_struct *tun, struct tun_pi pi = { 0, skb->protocol }; ssize_t total = 0; int vlan_offset = 0, copied; + int vlan_hlen = 0; + + if (vlan_tx_tag_present(skb)) + vlan_hlen = VLAN_HLEN; if (!(tun->flags & TUN_NO_PI)) { if ((len -= sizeof(pi)) < 0) @@ -1273,7 +1281,8 @@ static ssize_t tun_put_user(struct tun_struct *tun, if (skb->ip_summed == CHECKSUM_PARTIAL) { gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; - gso.csum_start = skb_checksum_start_offset(skb); + gso.csum_start = skb_checksum_start_offset(skb) + + vlan_hlen; gso.csum_offset = skb->csum_offset; } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { gso.flags = VIRTIO_NET_HDR_F_DATA_VALID; @@ -1286,10 +1295,9 @@ static ssize_t tun_put_user(struct tun_struct *tun, } copied = total; - total += skb->len; - if (!vlan_tx_tag_present(skb)) { - len = min_t(int, skb->len, len); - } else { + len = min_t(int, skb->len + vlan_hlen, len); + total += skb->len + vlan_hlen; + if (vlan_hlen) { int copy, ret; struct { __be16 h_vlan_proto; @@ -1300,8 +1308,6 @@ static ssize_t tun_put_user(struct tun_struct *tun, veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb)); vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto); - len = min_t(int, skb->len + VLAN_HLEN, len); - total += VLAN_HLEN; copy = min_t(int, vlan_offset, len); ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy); diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 054e59c..8cee173 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -696,6 +696,7 @@ static int ax88179_set_mac_addr(struct net_device *net, void *p) { struct usbnet *dev = netdev_priv(net); struct sockaddr *addr = p; + int ret; if (netif_running(net)) return -EBUSY; @@ -705,8 +706,12 @@ static int ax88179_set_mac_addr(struct net_device *net, void *p) memcpy(net->dev_addr, addr->sa_data, ETH_ALEN); /* Set the MAC address */ - return ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN, + ret = ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN, ETH_ALEN, net->dev_addr); + if (ret < 0) + return ret; + + return 0; } static const struct net_device_ops ax88179_netdev_ops = { diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c index 3eed708..fe48f4c 100644 --- a/drivers/net/usb/cx82310_eth.c +++ b/drivers/net/usb/cx82310_eth.c @@ -300,9 +300,18 @@ static const struct driver_info cx82310_info = { .tx_fixup = cx82310_tx_fixup, }; +#define USB_DEVICE_CLASS(vend, prod, cl, sc, pr) \ + .match_flags = USB_DEVICE_ID_MATCH_DEVICE | \ + USB_DEVICE_ID_MATCH_DEV_INFO, \ + .idVendor = (vend), \ + .idProduct = (prod), \ + .bDeviceClass = (cl), \ + .bDeviceSubClass = (sc), \ + .bDeviceProtocol = (pr) + static const struct usb_device_id products[] = { { - USB_DEVICE_AND_INTERFACE_INFO(0x0572, 0xcb01, 0xff, 0, 0), + USB_DEVICE_CLASS(0x0572, 0xcb01, 0xff, 0, 0), .driver_info = (unsigned long) &cx82310_info }, { }, diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c index 3d18bb0..1bfe0fc 100644 --- a/drivers/net/usb/plusb.c +++ b/drivers/net/usb/plusb.c @@ -134,6 +134,11 @@ static const struct usb_device_id products [] = { }, { USB_DEVICE(0x050d, 0x258a), /* Belkin F5U258/F5U279 (PL-25A1) */ .driver_info = (unsigned long) &prolific_info, +}, { + USB_DEVICE(0x3923, 0x7825), /* National Instruments USB + * Host-to-Host Cable + */ + .driver_info = (unsigned long) &prolific_info, }, { }, // END diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index d510f1d..db21af8 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -769,6 +769,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81a4, 8)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a8, 8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ + {QMI_FIXED_INTF(0x03f0, 0x581d, 4)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 40ad25d..5988910 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -279,13 +279,15 @@ static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb) return list_first_entry(&fdb->remotes, struct vxlan_rdst, list); } -/* Find VXLAN socket based on network namespace and UDP port */ -static struct vxlan_sock *vxlan_find_sock(struct net *net, __be16 port) +/* Find VXLAN socket based on network namespace, address family and UDP port */ +static struct vxlan_sock *vxlan_find_sock(struct net *net, + sa_family_t family, __be16 port) { struct vxlan_sock *vs; hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) { - if (inet_sk(vs->sock->sk)->inet_sport == port) + if (inet_sk(vs->sock->sk)->inet_sport == port && + inet_sk(vs->sock->sk)->sk.sk_family == family) return vs; } return NULL; @@ -304,11 +306,12 @@ static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, u32 id) } /* Look up VNI in a per net namespace table */ -static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, __be16 port) +static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, + sa_family_t family, __be16 port) { struct vxlan_sock *vs; - vs = vxlan_find_sock(net, port); + vs = vxlan_find_sock(net, family, port); if (!vs) return NULL; @@ -1334,7 +1337,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) } else if (vxlan->flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = tip, - .sa.sa_family = AF_INET, + .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); @@ -1447,9 +1450,6 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) if (!in6_dev) goto out; - if (!pskb_may_pull(skb, skb->len)) - goto out; - iphdr = ipv6_hdr(skb); saddr = &iphdr->saddr; daddr = &iphdr->daddr; @@ -1495,7 +1495,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) } else if (vxlan->flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin6.sin6_addr = msg->target, - .sa.sa_family = AF_INET6, + .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); @@ -1528,7 +1528,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) if (!n && (vxlan->flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = pip->daddr, - .sa.sa_family = AF_INET, + .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); @@ -1549,7 +1549,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) if (!n && (vxlan->flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin6.sin6_addr = pip6->daddr, - .sa.sa_family = AF_INET6, + .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); @@ -1770,6 +1770,8 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct pcpu_sw_netstats *tx_stats, *rx_stats; union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; + struct net_device *dev = skb->dev; + int len = skb->len; tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats); @@ -1793,16 +1795,16 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, u64_stats_update_begin(&tx_stats->syncp); tx_stats->tx_packets++; - tx_stats->tx_bytes += skb->len; + tx_stats->tx_bytes += len; u64_stats_update_end(&tx_stats->syncp); if (netif_rx(skb) == NET_RX_SUCCESS) { u64_stats_update_begin(&rx_stats->syncp); rx_stats->rx_packets++; - rx_stats->rx_bytes += skb->len; + rx_stats->rx_bytes += len; u64_stats_update_end(&rx_stats->syncp); } else { - skb->dev->stats.rx_dropped++; + dev->stats.rx_dropped++; } } @@ -1873,7 +1875,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *dst_vxlan; ip_rt_put(rt); - dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port); + dst_vxlan = vxlan_find_vni(dev_net(dev), vni, + dst->sa.sa_family, dst_port); if (!dst_vxlan) goto tx_error; vxlan_encap_bypass(skb, vxlan, dst_vxlan); @@ -1926,7 +1929,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *dst_vxlan; dst_release(ndst); - dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port); + dst_vxlan = vxlan_find_vni(dev_net(dev), vni, + dst->sa.sa_family, dst_port); if (!dst_vxlan) goto tx_error; vxlan_encap_bypass(skb, vxlan, dst_vxlan); @@ -1977,7 +1981,8 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) return arp_reduce(dev, skb); #if IS_ENABLED(CONFIG_IPV6) else if (ntohs(eth->h_proto) == ETH_P_IPV6 && - skb->len >= sizeof(struct ipv6hdr) + sizeof(struct nd_msg) && + pskb_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { struct nd_msg *msg; @@ -1986,6 +1991,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) return neigh_reduce(dev, skb); } + eth = eth_hdr(skb); #endif } @@ -2082,6 +2088,7 @@ static int vxlan_init(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); + bool ipv6 = vxlan->flags & VXLAN_F_IPV6; struct vxlan_sock *vs; int i; @@ -2097,10 +2104,10 @@ static int vxlan_init(struct net_device *dev) spin_lock(&vn->sock_lock); - vs = vxlan_find_sock(dev_net(dev), vxlan->dst_port); - if (vs) { + vs = vxlan_find_sock(dev_net(dev), ipv6 ? AF_INET6 : AF_INET, + vxlan->dst_port); + if (vs && atomic_add_unless(&vs->refcnt, 1, 0)) { /* If we have a socket with same port already, reuse it */ - atomic_inc(&vs->refcnt); vxlan_vs_add_dev(vs, vxlan); } else { /* otherwise make new socket outside of RTNL */ @@ -2565,13 +2572,10 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, return vs; spin_lock(&vn->sock_lock); - vs = vxlan_find_sock(net, port); - if (vs) { - if (vs->rcv == rcv) - atomic_inc(&vs->refcnt); - else + vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port); + if (vs && ((vs->rcv != rcv) || + !atomic_add_unless(&vs->refcnt, 1, 0))) vs = ERR_PTR(-EBUSY); - } spin_unlock(&vn->sock_lock); if (!vs) @@ -2711,7 +2715,8 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, if (data[IFLA_VXLAN_PORT]) vxlan->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); - if (vxlan_find_vni(net, vni, vxlan->dst_port)) { + if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET, + vxlan->dst_port)) { pr_info("duplicate VNI %u\n", vni); return -EEXIST; } diff --git a/drivers/net/wireless/ath/ath5k/qcu.c b/drivers/net/wireless/ath/ath5k/qcu.c index 0583c69..ddaad71 100644 --- a/drivers/net/wireless/ath/ath5k/qcu.c +++ b/drivers/net/wireless/ath/ath5k/qcu.c @@ -225,13 +225,7 @@ ath5k_hw_setup_tx_queue(struct ath5k_hw *ah, enum ath5k_tx_queue queue_type, } else { switch (queue_type) { case AR5K_TX_QUEUE_DATA: - for (queue = AR5K_TX_QUEUE_ID_DATA_MIN; - ah->ah_txq[queue].tqi_type != - AR5K_TX_QUEUE_INACTIVE; queue++) { - - if (queue > AR5K_TX_QUEUE_ID_DATA_MAX) - return -EINVAL; - } + queue = queue_info->tqi_subtype; break; case AR5K_TX_QUEUE_UAPSD: queue = AR5K_TX_QUEUE_ID_UAPSD; diff --git a/drivers/net/wireless/ath/ath5k/reset.c b/drivers/net/wireless/ath/ath5k/reset.c index a3399c4..b9b651e 100644 --- a/drivers/net/wireless/ath/ath5k/reset.c +++ b/drivers/net/wireless/ath/ath5k/reset.c @@ -478,7 +478,7 @@ ath5k_hw_wisoc_reset(struct ath5k_hw *ah, u32 flags) regval = ioread32(reg); iowrite32(regval | val, reg); regval = ioread32(reg); - usleep_range(100, 150); + udelay(100); /* NB: should be atomic */ /* Bring BB/MAC out of reset */ iowrite32(regval & ~val, reg); diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c index 09facba..390c2de 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c @@ -647,6 +647,19 @@ static void ar9003_hw_override_ini(struct ath_hw *ah) ah->enabled_cals |= TX_CL_CAL; else ah->enabled_cals &= ~TX_CL_CAL; + + if (AR_SREV_9340(ah) || AR_SREV_9531(ah) || AR_SREV_9550(ah)) { + if (ah->is_clk_25mhz) { + REG_WRITE(ah, AR_RTC_DERIVED_CLK, 0x17c << 1); + REG_WRITE(ah, AR_SLP32_MODE, 0x0010f3d7); + REG_WRITE(ah, AR_SLP32_INC, 0x0001e7ae); + } else { + REG_WRITE(ah, AR_RTC_DERIVED_CLK, 0x261 << 1); + REG_WRITE(ah, AR_SLP32_MODE, 0x0010f400); + REG_WRITE(ah, AR_SLP32_INC, 0x0001e800); + } + udelay(100); + } } static void ar9003_hw_prog_ini(struct ath_hw *ah, diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 9078a6c..dcc1494 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -858,19 +858,6 @@ static void ath9k_hw_init_pll(struct ath_hw *ah, udelay(RTC_PLL_SETTLE_DELAY); REG_WRITE(ah, AR_RTC_SLEEP_CLK, AR_RTC_FORCE_DERIVED_CLK); - - if (AR_SREV_9340(ah) || AR_SREV_9550(ah)) { - if (ah->is_clk_25mhz) { - REG_WRITE(ah, AR_RTC_DERIVED_CLK, 0x17c << 1); - REG_WRITE(ah, AR_SLP32_MODE, 0x0010f3d7); - REG_WRITE(ah, AR_SLP32_INC, 0x0001e7ae); - } else { - REG_WRITE(ah, AR_RTC_DERIVED_CLK, 0x261 << 1); - REG_WRITE(ah, AR_SLP32_MODE, 0x0010f400); - REG_WRITE(ah, AR_SLP32_INC, 0x0001e800); - } - udelay(100); - } } static void ath9k_hw_init_interrupt_masks(struct ath_hw *ah, diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h index 0acd4b5..32ae0a4 100644 --- a/drivers/net/wireless/ath/ath9k/hw.h +++ b/drivers/net/wireless/ath/ath9k/hw.h @@ -216,8 +216,8 @@ #define AH_WOW_BEACON_MISS BIT(3) enum ath_hw_txq_subtype { - ATH_TXQ_AC_BE = 0, - ATH_TXQ_AC_BK = 1, + ATH_TXQ_AC_BK = 0, + ATH_TXQ_AC_BE = 1, ATH_TXQ_AC_VI = 2, ATH_TXQ_AC_VO = 3, }; diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c index 5f72758..8f93ed3 100644 --- a/drivers/net/wireless/ath/ath9k/mac.c +++ b/drivers/net/wireless/ath/ath9k/mac.c @@ -311,14 +311,7 @@ int ath9k_hw_setuptxqueue(struct ath_hw *ah, enum ath9k_tx_queue type, q = ATH9K_NUM_TX_QUEUES - 3; break; case ATH9K_TX_QUEUE_DATA: - for (q = 0; q < ATH9K_NUM_TX_QUEUES; q++) - if (ah->txq[q].tqi_type == - ATH9K_TX_QUEUE_INACTIVE) - break; - if (q == ATH9K_NUM_TX_QUEUES) { - ath_err(common, "No available TX queue\n"); - return -1; - } + q = qinfo->tqi_subtype; break; default: ath_err(common, "Invalid TX queue type: %u\n", type); diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index a8e6d41..5d75b569 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -205,11 +205,13 @@ static bool ath_prepare_reset(struct ath_softc *sc) ath_stop_ani(sc); ath9k_hw_disable_interrupts(ah); - if (!ath_drain_all_txq(sc)) - ret = false; - - if (!ath_stoprecv(sc)) - ret = false; + if (AR_SREV_9300_20_OR_LATER(ah)) { + ret &= ath_stoprecv(sc); + ret &= ath_drain_all_txq(sc); + } else { + ret &= ath_drain_all_txq(sc); + ret &= ath_stoprecv(sc); + } return ret; } diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index 0526ddf..0fe7674 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -890,6 +890,15 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq, tx_info = IEEE80211_SKB_CB(skb); tx_info->flags &= ~IEEE80211_TX_CTL_CLEAR_PS_FILT; + + /* + * No aggregation session is running, but there may be frames + * from a previous session or a failed attempt in the queue. + * Send them out as normal data frames + */ + if (!tid->active) + tx_info->flags &= ~IEEE80211_TX_CTL_AMPDU; + if (!(tx_info->flags & IEEE80211_TX_CTL_AMPDU)) { bf->bf_state.bf_type = 0; return bf; diff --git a/drivers/net/wireless/ath/carl9170/carl9170.h b/drivers/net/wireless/ath/carl9170/carl9170.h index 8596aba..237d0cd 100644 --- a/drivers/net/wireless/ath/carl9170/carl9170.h +++ b/drivers/net/wireless/ath/carl9170/carl9170.h @@ -256,6 +256,7 @@ struct ar9170 { atomic_t rx_work_urbs; atomic_t rx_pool_urbs; kernel_ulong_t features; + bool usb_ep_cmd_is_bulk; /* firmware settings */ struct completion fw_load_wait; diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c index ca115f3..bc931f6 100644 --- a/drivers/net/wireless/ath/carl9170/usb.c +++ b/drivers/net/wireless/ath/carl9170/usb.c @@ -621,9 +621,16 @@ int __carl9170_exec_cmd(struct ar9170 *ar, struct carl9170_cmd *cmd, goto err_free; } - usb_fill_int_urb(urb, ar->udev, usb_sndintpipe(ar->udev, - AR9170_USB_EP_CMD), cmd, cmd->hdr.len + 4, - carl9170_usb_cmd_complete, ar, 1); + if (ar->usb_ep_cmd_is_bulk) + usb_fill_bulk_urb(urb, ar->udev, + usb_sndbulkpipe(ar->udev, AR9170_USB_EP_CMD), + cmd, cmd->hdr.len + 4, + carl9170_usb_cmd_complete, ar); + else + usb_fill_int_urb(urb, ar->udev, + usb_sndintpipe(ar->udev, AR9170_USB_EP_CMD), + cmd, cmd->hdr.len + 4, + carl9170_usb_cmd_complete, ar, 1); if (free_buf) urb->transfer_flags |= URB_FREE_BUFFER; @@ -1032,9 +1039,10 @@ static void carl9170_usb_firmware_step2(const struct firmware *fw, static int carl9170_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) { + struct usb_endpoint_descriptor *ep; struct ar9170 *ar; struct usb_device *udev; - int err; + int i, err; err = usb_reset_device(interface_to_usbdev(intf)); if (err) @@ -1050,6 +1058,21 @@ static int carl9170_usb_probe(struct usb_interface *intf, ar->intf = intf; ar->features = id->driver_info; + /* We need to remember the type of endpoint 4 because it differs + * between high- and full-speed configuration. The high-speed + * configuration specifies it as interrupt and the full-speed + * configuration as bulk endpoint. This information is required + * later when sending urbs to that endpoint. + */ + for (i = 0; i < intf->cur_altsetting->desc.bNumEndpoints; ++i) { + ep = &intf->cur_altsetting->endpoint[i].desc; + + if (usb_endpoint_num(ep) == AR9170_USB_EP_CMD && + usb_endpoint_dir_out(ep) && + usb_endpoint_type(ep) == USB_ENDPOINT_XFER_BULK) + ar->usb_ep_cmd_is_bulk = true; + } + usb_set_intfdata(intf, ar); SET_IEEE80211_DEV(ar->hw, &intf->dev); diff --git a/drivers/net/wireless/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/brcm80211/brcmfmac/fweh.c index fad77dd..3f9cb89 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/fweh.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/fweh.c @@ -185,7 +185,13 @@ static void brcmf_fweh_handle_if_event(struct brcmf_pub *drvr, ifevent->action, ifevent->ifidx, ifevent->bssidx, ifevent->flags, ifevent->role); - if (ifevent->flags & BRCMF_E_IF_FLAG_NOIF) { + /* The P2P Device interface event must not be ignored + * contrary to what firmware tells us. The only way to + * distinguish the P2P Device is by looking at the ifidx + * and bssidx received. + */ + if (!(ifevent->ifidx == 0 && ifevent->bssidx == 1) && + (ifevent->flags & BRCMF_E_IF_FLAG_NOIF)) { brcmf_dbg(EVENT, "event can be ignored\n"); return; } @@ -210,12 +216,12 @@ static void brcmf_fweh_handle_if_event(struct brcmf_pub *drvr, return; } - if (ifevent->action == BRCMF_E_IF_CHANGE) + if (ifp && ifevent->action == BRCMF_E_IF_CHANGE) brcmf_fws_reset_interface(ifp); err = brcmf_fweh_call_event_handler(ifp, emsg->event_code, emsg, data); - if (ifevent->action == BRCMF_E_IF_DEL) { + if (ifp && ifevent->action == BRCMF_E_IF_DEL) { brcmf_fws_del_interface(ifp); brcmf_del_if(drvr, ifevent->bssidx); } diff --git a/drivers/net/wireless/brcm80211/brcmfmac/fweh.h b/drivers/net/wireless/brcm80211/brcmfmac/fweh.h index 51b53a7..d26b476 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/fweh.h +++ b/drivers/net/wireless/brcm80211/brcmfmac/fweh.h @@ -167,6 +167,8 @@ enum brcmf_fweh_event_code { #define BRCMF_E_IF_ROLE_STA 0 #define BRCMF_E_IF_ROLE_AP 1 #define BRCMF_E_IF_ROLE_WDS 2 +#define BRCMF_E_IF_ROLE_P2P_GO 3 +#define BRCMF_E_IF_ROLE_P2P_CLIENT 4 /** * definitions for event packet validation. diff --git a/drivers/net/wireless/iwlwifi/dvm/dev.h b/drivers/net/wireless/iwlwifi/dvm/dev.h index 3441f70..6e8cdb8 100644 --- a/drivers/net/wireless/iwlwifi/dvm/dev.h +++ b/drivers/net/wireless/iwlwifi/dvm/dev.h @@ -708,7 +708,6 @@ struct iwl_priv { unsigned long reload_jiffies; int reload_count; bool ucode_loaded; - bool init_ucode_run; /* Don't run init uCode again */ u8 plcp_delta_threshold; diff --git a/drivers/net/wireless/iwlwifi/dvm/rxon.c b/drivers/net/wireless/iwlwifi/dvm/rxon.c index c1e3113..503a81e 100644 --- a/drivers/net/wireless/iwlwifi/dvm/rxon.c +++ b/drivers/net/wireless/iwlwifi/dvm/rxon.c @@ -1068,6 +1068,13 @@ int iwlagn_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx) /* recalculate basic rates */ iwl_calc_basic_rates(priv, ctx); + /* + * force CTS-to-self frames protection if RTS-CTS is not preferred + * one aggregation protection method + */ + if (!priv->hw_params.use_rts_for_aggregation) + ctx->staging.flags |= RXON_FLG_SELF_CTS_EN; + if ((ctx->vif && ctx->vif->bss_conf.use_short_slot) || !(ctx->staging.flags & RXON_FLG_BAND_24G_MSK)) ctx->staging.flags |= RXON_FLG_SHORT_SLOT_MSK; @@ -1473,6 +1480,11 @@ void iwlagn_bss_info_changed(struct ieee80211_hw *hw, else ctx->staging.flags &= ~RXON_FLG_TGG_PROTECT_MSK; + if (bss_conf->use_cts_prot) + ctx->staging.flags |= RXON_FLG_SELF_CTS_EN; + else + ctx->staging.flags &= ~RXON_FLG_SELF_CTS_EN; + memcpy(ctx->staging.bssid_addr, bss_conf->bssid, ETH_ALEN); if (vif->type == NL80211_IFTYPE_AP || diff --git a/drivers/net/wireless/iwlwifi/dvm/ucode.c b/drivers/net/wireless/iwlwifi/dvm/ucode.c index cf03ef5..8b2dedc 100644 --- a/drivers/net/wireless/iwlwifi/dvm/ucode.c +++ b/drivers/net/wireless/iwlwifi/dvm/ucode.c @@ -418,9 +418,6 @@ int iwl_run_init_ucode(struct iwl_priv *priv) if (!priv->fw->img[IWL_UCODE_INIT].sec[0].len) return 0; - if (priv->init_ucode_run) - return 0; - iwl_init_notification_wait(&priv->notif_wait, &calib_wait, calib_complete, ARRAY_SIZE(calib_complete), iwlagn_wait_calib, priv); @@ -440,8 +437,6 @@ int iwl_run_init_ucode(struct iwl_priv *priv) */ ret = iwl_wait_notification(&priv->notif_wait, &calib_wait, UCODE_CALIB_TIMEOUT); - if (!ret) - priv->init_ucode_run = true; goto out; diff --git a/drivers/net/wireless/iwlwifi/iwl-config.h b/drivers/net/wireless/iwlwifi/iwl-config.h index 1ced525..b45d78f 100644 --- a/drivers/net/wireless/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/iwlwifi/iwl-config.h @@ -119,6 +119,8 @@ enum iwl_led_mode { #define IWL_LONG_WD_TIMEOUT 10000 #define IWL_MAX_WD_TIMEOUT 120000 +#define IWL_DEFAULT_MAX_TX_POWER 22 + /* Antenna presence definitions */ #define ANT_NONE 0x0 #define ANT_A BIT(0) diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c index 725e954..3c3eb78 100644 --- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c @@ -118,8 +118,6 @@ static const u8 iwl_nvm_channels[] = { #define LAST_2GHZ_HT_PLUS 9 #define LAST_5GHZ_HT 161 -#define DEFAULT_MAX_TX_POWER 16 - /* rate data (static) */ static struct ieee80211_rate iwl_cfg80211_rates[] = { { .bitrate = 1 * 10, .hw_value = 0, .hw_value_short = 0, }, @@ -242,7 +240,7 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg, * Default value - highest tx power value. max_power * is not used in mvm, and is used for backwards compatibility */ - channel->max_power = DEFAULT_MAX_TX_POWER; + channel->max_power = IWL_DEFAULT_MAX_TX_POWER; is_5ghz = channel->band == IEEE80211_BAND_5GHZ; IWL_DEBUG_EEPROM(dev, "Ch. %d [%sGHz] %s%s%s%s%s%s(0x%02x %ddBm): Ad-Hoc %ssupported\n", diff --git a/drivers/net/wireless/iwlwifi/iwl-trans.h b/drivers/net/wireless/iwlwifi/iwl-trans.h index 1f065cf..d090ed7 100644 --- a/drivers/net/wireless/iwlwifi/iwl-trans.h +++ b/drivers/net/wireless/iwlwifi/iwl-trans.h @@ -514,6 +514,7 @@ enum iwl_trans_state { * Set during transport allocation. * @hw_id_str: a string with info about HW ID. Set during transport allocation. * @pm_support: set to true in start_hw if link pm is supported + * @ltr_enabled: set to true if the LTR is enabled * @dev_cmd_pool: pool for Tx cmd allocation - for internal use only. * The user should use iwl_trans_{alloc,free}_tx_cmd. * @dev_cmd_headroom: room needed for the transport's private use before the @@ -539,6 +540,7 @@ struct iwl_trans { u8 rx_mpdu_cmd, rx_mpdu_cmd_hdr_size; bool pm_support; + bool ltr_enabled; /* The following fields are internal only */ struct kmem_cache *dev_cmd_pool; diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h index 884c087..fa66471 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h +++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h @@ -66,13 +66,46 @@ /* Power Management Commands, Responses, Notifications */ +/** + * enum iwl_ltr_config_flags - masks for LTR config command flags + * @LTR_CFG_FLAG_FEATURE_ENABLE: Feature operational status + * @LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS: allow LTR change on shadow + * memory access + * @LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH: allow LTR msg send on ANY LTR + * reg change + * @LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3: allow LTR msg send on transition from + * D0 to D3 + * @LTR_CFG_FLAG_SW_SET_SHORT: fixed static short LTR register + * @LTR_CFG_FLAG_SW_SET_LONG: fixed static short LONG register + * @LTR_CFG_FLAG_DENIE_C10_ON_PD: allow going into C10 on PD + */ +enum iwl_ltr_config_flags { + LTR_CFG_FLAG_FEATURE_ENABLE = BIT(0), + LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS = BIT(1), + LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH = BIT(2), + LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3 = BIT(3), + LTR_CFG_FLAG_SW_SET_SHORT = BIT(4), + LTR_CFG_FLAG_SW_SET_LONG = BIT(5), + LTR_CFG_FLAG_DENIE_C10_ON_PD = BIT(6), +}; + +/** + * struct iwl_ltr_config_cmd - configures the LTR + * @flags: See %enum iwl_ltr_config_flags + */ +struct iwl_ltr_config_cmd { + __le32 flags; + __le32 static_long; + __le32 static_short; +} __packed; + /* Radio LP RX Energy Threshold measured in dBm */ #define POWER_LPRX_RSSI_THRESHOLD 75 #define POWER_LPRX_RSSI_THRESHOLD_MAX 94 #define POWER_LPRX_RSSI_THRESHOLD_MIN 30 /** - * enum iwl_scan_flags - masks for power table command flags + * enum iwl_power_flags - masks for power table command flags * @POWER_FLAGS_POWER_SAVE_ENA_MSK: '1' Allow to save power by turning off * receiver and transmitter. '0' - does not allow. * @POWER_FLAGS_POWER_MANAGEMENT_ENA_MSK: '0' Driver disables power management, diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/iwlwifi/mvm/fw-api.h index 989d7db..60dc387 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw-api.h +++ b/drivers/net/wireless/iwlwifi/mvm/fw-api.h @@ -142,6 +142,7 @@ enum { /* Power - legacy power table command */ POWER_TABLE_CMD = 0x77, PSM_UAPSD_AP_MISBEHAVING_NOTIFICATION = 0x78, + LTR_CONFIG = 0xee, /* Thermal Throttling*/ REPLY_THERMAL_MNG_BACKOFF = 0x7e, @@ -1393,7 +1394,7 @@ enum iwl_sf_scenario { #define SF_NUM_TIMEOUT_TYPES 2 /* Aging timer and Idle timer */ /* smart FIFO default values */ -#define SF_W_MARK_SISO 4096 +#define SF_W_MARK_SISO 6144 #define SF_W_MARK_MIMO2 8192 #define SF_W_MARK_MIMO3 6144 #define SF_W_MARK_LEGACY 4096 @@ -1415,14 +1416,14 @@ enum iwl_sf_scenario { /** * Smart Fifo configuration command. - * @state: smart fifo state, types listed in iwl_sf_sate. + * @state: smart fifo state, types listed in enum %iwl_sf_sate. * @watermark: Minimum allowed availabe free space in RXF for transient state. * @long_delay_timeouts: aging and idle timer values for each scenario * in long delay state. * @full_on_timeouts: timer values for each scenario in full on state. */ struct iwl_sf_cfg_cmd { - enum iwl_sf_state state; + __le32 state; __le32 watermark[SF_TRANSIENT_STATES_NUMBER]; __le32 long_delay_timeouts[SF_NUM_SCENARIO][SF_NUM_TIMEOUT_TYPES]; __le32 full_on_timeouts[SF_NUM_SCENARIO][SF_NUM_TIMEOUT_TYPES]; diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c index c03d395..2ef344f 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/iwlwifi/mvm/fw.c @@ -439,6 +439,15 @@ int iwl_mvm_up(struct iwl_mvm *mvm) goto error; } + if (mvm->trans->ltr_enabled) { + struct iwl_ltr_config_cmd cmd = { + .flags = cpu_to_le32(LTR_CFG_FLAG_FEATURE_ENABLE), + }; + + WARN_ON(iwl_mvm_send_cmd_pdu(mvm, LTR_CONFIG, 0, + sizeof(cmd), &cmd)); + } + ret = iwl_mvm_power_update_device_mode(mvm); if (ret) goto error; diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c index d06414e..4a3b8b7 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c @@ -410,9 +410,6 @@ static void iwl_mvm_cleanup_iterator(void *data, u8 *mac, mvmvif->uploaded = false; mvmvif->ap_sta_id = IWL_MVM_STATION_COUNT; - /* does this make sense at all? */ - mvmvif->color++; - spin_lock_bh(&mvm->time_event_lock); iwl_mvm_te_clear_data(mvm, &mvmvif->time_event_data); spin_unlock_bh(&mvm->time_event_lock); diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c index a3d43de..dbff7f0 100644 --- a/drivers/net/wireless/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/iwlwifi/mvm/ops.c @@ -313,6 +313,7 @@ static const char *iwl_mvm_cmd_strings[REPLY_MAX] = { CMD(REPLY_BEACON_FILTERING_CMD), CMD(REPLY_THERMAL_MNG_BACKOFF), CMD(MAC_PM_POWER_TABLE), + CMD(LTR_CONFIG), CMD(BT_COEX_CI), CMD(PSM_UAPSD_AP_MISBEHAVING_NOTIFICATION), }; diff --git a/drivers/net/wireless/iwlwifi/mvm/sf.c b/drivers/net/wireless/iwlwifi/mvm/sf.c index 88809b2..dab8fd1 100644 --- a/drivers/net/wireless/iwlwifi/mvm/sf.c +++ b/drivers/net/wireless/iwlwifi/mvm/sf.c @@ -172,7 +172,7 @@ static int iwl_mvm_sf_config(struct iwl_mvm *mvm, u8 sta_id, enum iwl_sf_state new_state) { struct iwl_sf_cfg_cmd sf_cmd = { - .state = new_state, + .state = cpu_to_le32(new_state), }; struct ieee80211_sta *sta; int ret = 0; diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c index 76ee486..4efcb28 100644 --- a/drivers/net/wireless/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/iwlwifi/mvm/tx.c @@ -835,6 +835,11 @@ int iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb, sta_id = ba_notif->sta_id; tid = ba_notif->tid; + if (WARN_ONCE(sta_id >= IWL_MVM_STATION_COUNT || + tid >= IWL_MAX_TID_COUNT, + "sta_id %d tid %d", sta_id, tid)) + return 0; + rcu_read_lock(); sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]); diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c index df1f5e7..1ac33d9 100644 --- a/drivers/net/wireless/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/iwlwifi/pcie/drv.c @@ -272,6 +272,8 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { {IWL_PCI_DEVICE(0x08B1, 0x4070, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4072, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4170, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x4C60, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x4C70, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4060, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x406A, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4160, iwl7260_2n_cfg)}, @@ -315,6 +317,8 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { {IWL_PCI_DEVICE(0x08B1, 0xC770, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC760, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC270, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xCC70, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xCC60, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC272, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC260, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC26A, iwl7260_n_cfg)}, diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c index 16be0c0..fb62927 100644 --- a/drivers/net/wireless/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/iwlwifi/pcie/trans.c @@ -94,6 +94,7 @@ static void iwl_pcie_apm_config(struct iwl_trans *trans) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); u16 lctl; + u16 cap; /* * HW bug W/A for instability in PCIe bus L0S->L1 transition. @@ -104,16 +105,17 @@ static void iwl_pcie_apm_config(struct iwl_trans *trans) * power savings, even without L1. */ pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_LNKCTL, &lctl); - if (lctl & PCI_EXP_LNKCTL_ASPM_L1) { - /* L1-ASPM enabled; disable(!) L0S */ + if (lctl & PCI_EXP_LNKCTL_ASPM_L1) iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED); - dev_info(trans->dev, "L1 Enabled; Disabling L0S\n"); - } else { - /* L1-ASPM disabled; enable(!) L0S */ + else iwl_clear_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED); - dev_info(trans->dev, "L1 Disabled; Enabling L0S\n"); - } trans->pm_support = !(lctl & PCI_EXP_LNKCTL_ASPM_L0S); + + pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_DEVCTL2, &cap); + trans->ltr_enabled = cap & PCI_EXP_DEVCTL2_LTR_EN; + dev_info(trans->dev, "L1 %sabled - LTR %sabled\n", + (lctl & PCI_EXP_LNKCTL_ASPM_L1) ? "En" : "Dis", + trans->ltr_enabled ? "En" : "Dis"); } /* diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c index 3d54900..52427fb 100644 --- a/drivers/net/wireless/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/iwlwifi/pcie/tx.c @@ -729,7 +729,12 @@ void iwl_trans_pcie_tx_reset(struct iwl_trans *trans) iwl_write_direct32(trans, FH_KW_MEM_ADDR_REG, trans_pcie->kw.dma >> 4); - iwl_pcie_tx_start(trans, trans_pcie->scd_base_addr); + /* + * Send 0 as the scd_base_addr since the device may have be reset + * while we were in WoWLAN in which case SCD_SRAM_BASE_ADDR will + * contain garbage. + */ + iwl_pcie_tx_start(trans, 0); } /* diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 98718e4..5e836b1 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1976,7 +1976,7 @@ static int mac80211_hwsim_create_radio(int channels, const char *reg_alpha2, if (err != 0) { printk(KERN_DEBUG "mac80211_hwsim: device_bind_driver failed (%d)\n", err); - goto failed_hw; + goto failed_bind; } skb_queue_head_init(&data->pending); @@ -2159,6 +2159,8 @@ static int mac80211_hwsim_create_radio(int channels, const char *reg_alpha2, return idx; failed_hw: + device_release_driver(data->dev); +failed_bind: device_unregister(data->dev); failed_drvdata: ieee80211_free_hw(hw); diff --git a/drivers/net/wireless/rt2x00/rt2800.h b/drivers/net/wireless/rt2x00/rt2800.h index a394a9a..ebd5625 100644 --- a/drivers/net/wireless/rt2x00/rt2800.h +++ b/drivers/net/wireless/rt2x00/rt2800.h @@ -52,6 +52,7 @@ * RF5592 2.4G/5G 2T2R * RF3070 2.4G 1T1R * RF5360 2.4G 1T1R + * RF5362 2.4G 1T1R * RF5370 2.4G 1T1R * RF5390 2.4G 1T1R */ @@ -72,6 +73,7 @@ #define RF3070 0x3070 #define RF3290 0x3290 #define RF5360 0x5360 +#define RF5362 0x5362 #define RF5370 0x5370 #define RF5372 0x5372 #define RF5390 0x5390 @@ -2039,7 +2041,7 @@ struct mac_iveiv_entry { * 2 - drop tx power by 12dBm, * 3 - increase tx power by 6dBm */ -#define BBP1_TX_POWER_CTRL FIELD8(0x07) +#define BBP1_TX_POWER_CTRL FIELD8(0x03) #define BBP1_TX_ANTENNA FIELD8(0x18) /* @@ -2145,7 +2147,7 @@ struct mac_iveiv_entry { /* Bits [7-4] for RF3320 (RT3370/RT3390), on other chipsets reserved */ #define RFCSR3_PA1_BIAS_CCK FIELD8(0x70) #define RFCSR3_PA2_CASCODE_BIAS_CCKK FIELD8(0x80) -/* Bits for RF3290/RF5360/RF5370/RF5372/RF5390/RF5392 */ +/* Bits for RF3290/RF5360/RF5362/RF5370/RF5372/RF5390/RF5392 */ #define RFCSR3_VCOCAL_EN FIELD8(0x80) /* Bits for RF3050 */ #define RFCSR3_BIT1 FIELD8(0x02) diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c index 41d4a81..4e16d4d 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/rt2x00/rt2800lib.c @@ -3142,6 +3142,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev, break; case RF3070: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: @@ -3159,6 +3160,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev, rt2x00_rf(rt2x00dev, RF3290) || rt2x00_rf(rt2x00dev, RF3322) || rt2x00_rf(rt2x00dev, RF5360) || + rt2x00_rf(rt2x00dev, RF5362) || rt2x00_rf(rt2x00dev, RF5370) || rt2x00_rf(rt2x00dev, RF5372) || rt2x00_rf(rt2x00dev, RF5390) || @@ -4273,6 +4275,7 @@ void rt2800_vco_calibration(struct rt2x00_dev *rt2x00dev) case RF3070: case RF3290: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: @@ -7073,6 +7076,7 @@ static int rt2800_init_eeprom(struct rt2x00_dev *rt2x00dev) case RF3320: case RF3322: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: @@ -7529,6 +7533,7 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev) case RF3320: case RF3322: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: @@ -7658,6 +7663,7 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev) case RF3070: case RF3290: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c index caddc1b..e8abd0f 100644 --- a/drivers/net/wireless/rt2x00/rt2800usb.c +++ b/drivers/net/wireless/rt2x00/rt2800usb.c @@ -991,6 +991,7 @@ static struct usb_device_id rt2800usb_device_table[] = { { USB_DEVICE(0x07d1, 0x3c17) }, { USB_DEVICE(0x2001, 0x3317) }, { USB_DEVICE(0x2001, 0x3c1b) }, + { USB_DEVICE(0x2001, 0x3c25) }, /* Draytek */ { USB_DEVICE(0x07fa, 0x7712) }, /* DVICO */ @@ -1062,6 +1063,7 @@ static struct usb_device_id rt2800usb_device_table[] = { /* Ovislink */ { USB_DEVICE(0x1b75, 0x3071) }, { USB_DEVICE(0x1b75, 0x3072) }, + { USB_DEVICE(0x1b75, 0xa200) }, /* Para */ { USB_DEVICE(0x20b8, 0x8888) }, /* Pegatron */ @@ -1235,6 +1237,8 @@ static struct usb_device_id rt2800usb_device_table[] = { /* Arcadyan */ { USB_DEVICE(0x043e, 0x7a12) }, { USB_DEVICE(0x043e, 0x7a32) }, + /* ASUS */ + { USB_DEVICE(0x0b05, 0x17e8) }, /* Azurewave */ { USB_DEVICE(0x13d3, 0x3329) }, { USB_DEVICE(0x13d3, 0x3365) }, @@ -1271,6 +1275,7 @@ static struct usb_device_id rt2800usb_device_table[] = { { USB_DEVICE(0x057c, 0x8501) }, /* Buffalo */ { USB_DEVICE(0x0411, 0x0241) }, + { USB_DEVICE(0x0411, 0x0253) }, /* D-Link */ { USB_DEVICE(0x2001, 0x3c1a) }, { USB_DEVICE(0x2001, 0x3c21) }, @@ -1361,6 +1366,7 @@ static struct usb_device_id rt2800usb_device_table[] = { { USB_DEVICE(0x0df6, 0x0053) }, { USB_DEVICE(0x0df6, 0x0069) }, { USB_DEVICE(0x0df6, 0x006f) }, + { USB_DEVICE(0x0df6, 0x0078) }, /* SMC */ { USB_DEVICE(0x083a, 0xa512) }, { USB_DEVICE(0x083a, 0xc522) }, diff --git a/drivers/net/wireless/rt2x00/rt2x00queue.c b/drivers/net/wireless/rt2x00/rt2x00queue.c index 5642ccc..22d49d5 100644 --- a/drivers/net/wireless/rt2x00/rt2x00queue.c +++ b/drivers/net/wireless/rt2x00/rt2x00queue.c @@ -158,55 +158,29 @@ void rt2x00queue_align_frame(struct sk_buff *skb) skb_trim(skb, frame_length); } -void rt2x00queue_insert_l2pad(struct sk_buff *skb, unsigned int header_length) +/* + * H/W needs L2 padding between the header and the paylod if header size + * is not 4 bytes aligned. + */ +void rt2x00queue_insert_l2pad(struct sk_buff *skb, unsigned int hdr_len) { - unsigned int payload_length = skb->len - header_length; - unsigned int header_align = ALIGN_SIZE(skb, 0); - unsigned int payload_align = ALIGN_SIZE(skb, header_length); - unsigned int l2pad = payload_length ? L2PAD_SIZE(header_length) : 0; + unsigned int l2pad = (skb->len > hdr_len) ? L2PAD_SIZE(hdr_len) : 0; - /* - * Adjust the header alignment if the payload needs to be moved more - * than the header. - */ - if (payload_align > header_align) - header_align += 4; - - /* There is nothing to do if no alignment is needed */ - if (!header_align) + if (!l2pad) return; - /* Reserve the amount of space needed in front of the frame */ - skb_push(skb, header_align); - - /* - * Move the header. - */ - memmove(skb->data, skb->data + header_align, header_length); - - /* Move the payload, if present and if required */ - if (payload_length && payload_align) - memmove(skb->data + header_length + l2pad, - skb->data + header_length + l2pad + payload_align, - payload_length); - - /* Trim the skb to the correct size */ - skb_trim(skb, header_length + l2pad + payload_length); + skb_push(skb, l2pad); + memmove(skb->data, skb->data + l2pad, hdr_len); } -void rt2x00queue_remove_l2pad(struct sk_buff *skb, unsigned int header_length) +void rt2x00queue_remove_l2pad(struct sk_buff *skb, unsigned int hdr_len) { - /* - * L2 padding is only present if the skb contains more than just the - * IEEE 802.11 header. - */ - unsigned int l2pad = (skb->len > header_length) ? - L2PAD_SIZE(header_length) : 0; + unsigned int l2pad = (skb->len > hdr_len) ? L2PAD_SIZE(hdr_len) : 0; if (!l2pad) return; - memmove(skb->data + l2pad, skb->data, header_length); + memmove(skb->data + l2pad, skb->data, hdr_len); skb_pull(skb, l2pad); } diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c index c613110..66c92a1 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c +++ b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c @@ -314,9 +314,11 @@ static struct usb_device_id rtl8192c_usb_ids[] = { {RTL_USB_DEVICE(0x07b8, 0x8188, rtl92cu_hal_cfg)}, /*Abocom - Abocom*/ {RTL_USB_DEVICE(0x07b8, 0x8189, rtl92cu_hal_cfg)}, /*Funai - Abocom*/ {RTL_USB_DEVICE(0x0846, 0x9041, rtl92cu_hal_cfg)}, /*NetGear WNA1000M*/ + {RTL_USB_DEVICE(0x0b05, 0x17ba, rtl92cu_hal_cfg)}, /*ASUS-Edimax*/ {RTL_USB_DEVICE(0x0bda, 0x5088, rtl92cu_hal_cfg)}, /*Thinkware-CC&C*/ {RTL_USB_DEVICE(0x0df6, 0x0052, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ {RTL_USB_DEVICE(0x0df6, 0x005c, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ + {RTL_USB_DEVICE(0x0df6, 0x0070, rtl92cu_hal_cfg)}, /*Sitecom - 150N */ {RTL_USB_DEVICE(0x0df6, 0x0077, rtl92cu_hal_cfg)}, /*Sitecom-WLA2100V2*/ {RTL_USB_DEVICE(0x0eb0, 0x9071, rtl92cu_hal_cfg)}, /*NO Brand - Etop*/ {RTL_USB_DEVICE(0x4856, 0x0091, rtl92cu_hal_cfg)}, /*NetweeN - Feixun*/ @@ -369,6 +371,7 @@ static struct usb_device_id rtl8192c_usb_ids[] = { {RTL_USB_DEVICE(0x2001, 0x3307, rtl92cu_hal_cfg)}, /*D-Link-Cameo*/ {RTL_USB_DEVICE(0x2001, 0x3309, rtl92cu_hal_cfg)}, /*D-Link-Alpha*/ {RTL_USB_DEVICE(0x2001, 0x330a, rtl92cu_hal_cfg)}, /*D-Link-Alpha*/ + {RTL_USB_DEVICE(0x2001, 0x330d, rtl92cu_hal_cfg)}, /*D-Link DWA-131 */ {RTL_USB_DEVICE(0x2019, 0xab2b, rtl92cu_hal_cfg)}, /*Planex -Abocom*/ {RTL_USB_DEVICE(0x20f4, 0x624d, rtl92cu_hal_cfg)}, /*TRENDNet*/ {RTL_USB_DEVICE(0x2357, 0x0100, rtl92cu_hal_cfg)}, /*TP-Link WN8200ND*/ diff --git a/drivers/net/wireless/rtlwifi/usb.c b/drivers/net/wireless/rtlwifi/usb.c index 4933f02..bc409ec 100644 --- a/drivers/net/wireless/rtlwifi/usb.c +++ b/drivers/net/wireless/rtlwifi/usb.c @@ -126,7 +126,7 @@ static int _usbctrl_vendorreq_sync_read(struct usb_device *udev, u8 request, do { status = usb_control_msg(udev, pipe, request, reqtype, value, - index, pdata, len, 0); /*max. timeout*/ + index, pdata, len, 1000); if (status < 0) { /* firmware download is checksumed, don't retry */ if ((value >= FW_8192C_START_ADDRESS && diff --git a/drivers/net/wireless/ti/wl18xx/debugfs.c b/drivers/net/wireless/ti/wl18xx/debugfs.c index 7f1669c..779dc2b 100644 --- a/drivers/net/wireless/ti/wl18xx/debugfs.c +++ b/drivers/net/wireless/ti/wl18xx/debugfs.c @@ -136,7 +136,7 @@ WL18XX_DEBUGFS_FWSTATS_FILE(rx_filter, protection_filter, "%u"); WL18XX_DEBUGFS_FWSTATS_FILE(rx_filter, accum_arp_pend_requests, "%u"); WL18XX_DEBUGFS_FWSTATS_FILE(rx_filter, max_arp_queue_dep, "%u"); -WL18XX_DEBUGFS_FWSTATS_FILE(rx_rate, rx_frames_per_rates, "%u"); +WL18XX_DEBUGFS_FWSTATS_FILE_ARRAY(rx_rate, rx_frames_per_rates, 50); WL18XX_DEBUGFS_FWSTATS_FILE_ARRAY(aggr_size, tx_agg_vs_rate, AGGR_STATS_TX_AGG*AGGR_STATS_TX_RATE); diff --git a/drivers/net/wireless/ti/wlcore/debugfs.h b/drivers/net/wireless/ti/wlcore/debugfs.h index f7381dd..1bce432 100644 --- a/drivers/net/wireless/ti/wlcore/debugfs.h +++ b/drivers/net/wireless/ti/wlcore/debugfs.h @@ -26,8 +26,8 @@ #include "wlcore.h" -int wl1271_format_buffer(char __user *userbuf, size_t count, - loff_t *ppos, char *fmt, ...); +__printf(4, 5) int wl1271_format_buffer(char __user *userbuf, size_t count, + loff_t *ppos, char *fmt, ...); int wl1271_debugfs_init(struct wl1271 *wl); void wl1271_debugfs_exit(struct wl1271 *wl); diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 7a206cf..d18e653 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -32,6 +32,8 @@ struct backend_info { enum xenbus_state frontend_state; struct xenbus_watch hotplug_status_watch; u8 have_hotplug_status_watch:1; + + const char *hotplug_script; }; static int connect_rings(struct backend_info *); @@ -54,6 +56,7 @@ static int netback_remove(struct xenbus_device *dev) xenvif_free(be->vif); be->vif = NULL; } + kfree(be->hotplug_script); kfree(be); dev_set_drvdata(&dev->dev, NULL); return 0; @@ -71,6 +74,7 @@ static int netback_probe(struct xenbus_device *dev, struct xenbus_transaction xbt; int err; int sg; + const char *script; struct backend_info *be = kzalloc(sizeof(struct backend_info), GFP_KERNEL); if (!be) { @@ -157,6 +161,15 @@ static int netback_probe(struct xenbus_device *dev, if (err) pr_debug("Error writing feature-split-event-channels\n"); + script = xenbus_read(XBT_NIL, dev->nodename, "script", NULL); + if (IS_ERR(script)) { + err = PTR_ERR(script); + xenbus_dev_fatal(dev, err, "reading script"); + goto fail; + } + + be->hotplug_script = script; + err = xenbus_switch_state(dev, XenbusStateInitWait); if (err) goto fail; @@ -187,22 +200,14 @@ static int netback_uevent(struct xenbus_device *xdev, struct kobj_uevent_env *env) { struct backend_info *be = dev_get_drvdata(&xdev->dev); - char *val; - val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL); - if (IS_ERR(val)) { - int err = PTR_ERR(val); - xenbus_dev_fatal(xdev, err, "reading script"); - return err; - } else { - if (add_uevent_var(env, "script=%s", val)) { - kfree(val); - return -ENOMEM; - } - kfree(val); - } + if (!be) + return 0; + + if (add_uevent_var(env, "script=%s", be->hotplug_script)) + return -ENOMEM; - if (!be || !be->vif) + if (!be->vif) return 0; return add_uevent_var(env, "vif=%s", be->vif->dev->name); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index e30d800..19db057 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -469,9 +469,6 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev, len = skb_frag_size(frag); offset = frag->page_offset; - /* Data must not cross a page boundary. */ - BUG_ON(len + offset > PAGE_SIZE<> PAGE_SHIFT; offset &= ~PAGE_MASK; @@ -479,8 +476,6 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev, while (len > 0) { unsigned long bytes; - BUG_ON(offset >= PAGE_SIZE); - bytes = PAGE_SIZE - offset; if (bytes > len) bytes = len; diff --git a/drivers/nfc/microread/microread.c b/drivers/nfc/microread/microread.c index f868333..963a4a5 100644 --- a/drivers/nfc/microread/microread.c +++ b/drivers/nfc/microread/microread.c @@ -501,9 +501,13 @@ static void microread_target_discovered(struct nfc_hci_dev *hdev, u8 gate, targets->sens_res = be16_to_cpu(*(u16 *)&skb->data[MICROREAD_EMCF_A_ATQA]); targets->sel_res = skb->data[MICROREAD_EMCF_A_SAK]; - memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A_UID], - skb->data[MICROREAD_EMCF_A_LEN]); targets->nfcid1_len = skb->data[MICROREAD_EMCF_A_LEN]; + if (targets->nfcid1_len > sizeof(targets->nfcid1)) { + r = -EINVAL; + goto exit_free; + } + memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A_UID], + targets->nfcid1_len); break; case MICROREAD_GATE_ID_MREAD_ISO_A_3: targets->supported_protocols = @@ -511,9 +515,13 @@ static void microread_target_discovered(struct nfc_hci_dev *hdev, u8 gate, targets->sens_res = be16_to_cpu(*(u16 *)&skb->data[MICROREAD_EMCF_A3_ATQA]); targets->sel_res = skb->data[MICROREAD_EMCF_A3_SAK]; - memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A3_UID], - skb->data[MICROREAD_EMCF_A3_LEN]); targets->nfcid1_len = skb->data[MICROREAD_EMCF_A3_LEN]; + if (targets->nfcid1_len > sizeof(targets->nfcid1)) { + r = -EINVAL; + goto exit_free; + } + memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A3_UID], + targets->nfcid1_len); break; case MICROREAD_GATE_ID_MREAD_ISO_B: targets->supported_protocols = NFC_PROTO_ISO14443_B_MASK; diff --git a/drivers/of/address.c b/drivers/of/address.c index 1a54f1f..9eae613 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -401,6 +401,21 @@ static struct of_bus *of_match_bus(struct device_node *np) return NULL; } +static int of_empty_ranges_quirk(void) +{ + if (IS_ENABLED(CONFIG_PPC)) { + /* To save cycles, we cache the result */ + static int quirk_state = -1; + + if (quirk_state < 0) + quirk_state = + of_machine_is_compatible("Power Macintosh") || + of_machine_is_compatible("MacRISC"); + return quirk_state; + } + return false; +} + static int of_translate_one(struct device_node *parent, struct of_bus *bus, struct of_bus *pbus, __be32 *addr, int na, int ns, int pna, const char *rprop) @@ -426,12 +441,10 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus, * This code is only enabled on powerpc. --gcl */ ranges = of_get_property(parent, rprop, &rlen); -#if !defined(CONFIG_PPC) - if (ranges == NULL) { + if (ranges == NULL && !of_empty_ranges_quirk()) { pr_err("OF: no ranges; cannot translate\n"); return 1; } -#endif /* !defined(CONFIG_PPC) */ if (ranges == NULL || rlen == 0) { offset = of_read_number(addr, na); memset(addr, 0, pna * 4); @@ -691,10 +704,10 @@ struct device_node *of_find_matching_node_by_address(struct device_node *from, struct resource res; while (dn) { - if (of_address_to_resource(dn, 0, &res)) - continue; - if (res.start == base_address) + if (!of_address_to_resource(dn, 0, &res) && + res.start == base_address) return dn; + dn = of_find_matching_node(dn, matches); } diff --git a/drivers/of/base.c b/drivers/of/base.c index 89e888a..e99f329 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -77,7 +77,7 @@ EXPORT_SYMBOL(of_n_size_cells); #ifdef CONFIG_NUMA int __weak of_node_to_nid(struct device_node *np) { - return numa_node_id(); + return NUMA_NO_NODE; } #endif @@ -1117,52 +1117,6 @@ int of_property_read_string(struct device_node *np, const char *propname, EXPORT_SYMBOL_GPL(of_property_read_string); /** - * of_property_read_string_index - Find and read a string from a multiple - * strings property. - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @index: index of the string in the list of strings - * @out_string: pointer to null terminated return string, modified only if - * return value is 0. - * - * Search for a property in a device tree node and retrieve a null - * terminated string value (pointer to data, not a copy) in the list of strings - * contained in that property. - * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if - * property does not have a value, and -EILSEQ if the string is not - * null-terminated within the length of the property data. - * - * The out_string pointer is modified only if a valid string can be decoded. - */ -int of_property_read_string_index(struct device_node *np, const char *propname, - int index, const char **output) -{ - struct property *prop = of_find_property(np, propname, NULL); - int i = 0; - size_t l = 0, total = 0; - const char *p; - - if (!prop) - return -EINVAL; - if (!prop->value) - return -ENODATA; - if (strnlen(prop->value, prop->length) >= prop->length) - return -EILSEQ; - - p = prop->value; - - for (i = 0; total < prop->length; total += l, p += l) { - l = strlen(p) + 1; - if (i++ == index) { - *output = p; - return 0; - } - } - return -ENODATA; -} -EXPORT_SYMBOL_GPL(of_property_read_string_index); - -/** * of_property_match_string() - Find string in a list and return index * @np: pointer to node containing string list property * @propname: string list property name @@ -1188,7 +1142,7 @@ int of_property_match_string(struct device_node *np, const char *propname, end = p + prop->length; for (i = 0; p < end; i++, p += l) { - l = strlen(p) + 1; + l = strnlen(p, end - p) + 1; if (p + l > end) return -EILSEQ; pr_debug("comparing %s with %s\n", string, p); @@ -1200,39 +1154,41 @@ int of_property_match_string(struct device_node *np, const char *propname, EXPORT_SYMBOL_GPL(of_property_match_string); /** - * of_property_count_strings - Find and return the number of strings from a - * multiple strings property. + * of_property_read_string_util() - Utility helper for parsing string properties * @np: device node from which the property value is to be read. * @propname: name of the property to be searched. + * @out_strs: output array of string pointers. + * @sz: number of array elements to read. + * @skip: Number of strings to skip over at beginning of list. * - * Search for a property in a device tree node and retrieve the number of null - * terminated string contain in it. Returns the number of strings on - * success, -EINVAL if the property does not exist, -ENODATA if property - * does not have a value, and -EILSEQ if the string is not null-terminated - * within the length of the property data. + * Don't call this function directly. It is a utility helper for the + * of_property_read_string*() family of functions. */ -int of_property_count_strings(struct device_node *np, const char *propname) +int of_property_read_string_helper(struct device_node *np, const char *propname, + const char **out_strs, size_t sz, int skip) { struct property *prop = of_find_property(np, propname, NULL); - int i = 0; - size_t l = 0, total = 0; - const char *p; + int l = 0, i = 0; + const char *p, *end; if (!prop) return -EINVAL; if (!prop->value) return -ENODATA; - if (strnlen(prop->value, prop->length) >= prop->length) - return -EILSEQ; - p = prop->value; + end = p + prop->length; - for (i = 0; total < prop->length; total += l, p += l, i++) - l = strlen(p) + 1; - - return i; + for (i = 0; p < end && (!out_strs || i < skip + sz); i++, p += l) { + l = strnlen(p, end - p) + 1; + if (p + l > end) + return -EILSEQ; + if (out_strs && i >= skip) + *out_strs++ = p; + } + i -= skip; + return i <= 0 ? -ENODATA : i; } -EXPORT_SYMBOL_GPL(of_property_count_strings); +EXPORT_SYMBOL_GPL(of_property_read_string_helper); void of_print_phandle_args(const char *msg, const struct of_phandle_args *args) { diff --git a/drivers/of/irq.c b/drivers/of/irq.c index ca01893..bbff99d 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -290,7 +290,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar struct device_node *p; const __be32 *intspec, *tmp, *addr; u32 intsize, intlen; - int i, res = -EINVAL; + int i, res; pr_debug("of_irq_parse_one: dev=%s, index=%d\n", of_node_full_name(device), index); @@ -301,16 +301,17 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar /* Get the reg property (if any) */ addr = of_get_property(device, "reg", NULL); + /* Try the new-style interrupts-extended first */ + res = of_parse_phandle_with_args(device, "interrupts-extended", + "#interrupt-cells", index, out_irq); + if (!res) + return of_irq_parse_raw(addr, out_irq); + /* Get the interrupts property */ intspec = of_get_property(device, "interrupts", &intlen); - if (intspec == NULL) { - /* Try the new-style interrupts-extended */ - res = of_parse_phandle_with_args(device, "interrupts-extended", - "#interrupt-cells", index, out_irq); - if (res) - return -EINVAL; - return of_irq_parse_raw(addr, out_irq); - } + if (intspec == NULL) + return -EINVAL; + intlen /= sizeof(*intspec); pr_debug(" intspec=%d intlen=%d\n", be32_to_cpup(intspec), intlen); @@ -322,15 +323,19 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar /* Get size of interrupt specifier */ tmp = of_get_property(p, "#interrupt-cells", NULL); - if (tmp == NULL) + if (tmp == NULL) { + res = -EINVAL; goto out; + } intsize = be32_to_cpu(*tmp); pr_debug(" intsize=%d intlen=%d\n", intsize, intlen); /* Check index */ - if ((index + 1) * intsize > intlen) + if ((index + 1) * intsize > intlen) { + res = -EINVAL; goto out; + } /* Copy intspec into irq structure */ intspec += index * intsize; diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c index 6643d19..70c61d7 100644 --- a/drivers/of/selftest.c +++ b/drivers/of/selftest.c @@ -132,8 +132,9 @@ static void __init of_selftest_parse_phandle_with_args(void) selftest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); } -static void __init of_selftest_property_match_string(void) +static void __init of_selftest_property_string(void) { + const char *strings[4]; struct device_node *np; int rc; @@ -150,13 +151,66 @@ static void __init of_selftest_property_match_string(void) rc = of_property_match_string(np, "phandle-list-names", "third"); selftest(rc == 2, "third expected:0 got:%i\n", rc); rc = of_property_match_string(np, "phandle-list-names", "fourth"); - selftest(rc == -ENODATA, "unmatched string; rc=%i", rc); + selftest(rc == -ENODATA, "unmatched string; rc=%i\n", rc); rc = of_property_match_string(np, "missing-property", "blah"); - selftest(rc == -EINVAL, "missing property; rc=%i", rc); + selftest(rc == -EINVAL, "missing property; rc=%i\n", rc); rc = of_property_match_string(np, "empty-property", "blah"); - selftest(rc == -ENODATA, "empty property; rc=%i", rc); + selftest(rc == -ENODATA, "empty property; rc=%i\n", rc); rc = of_property_match_string(np, "unterminated-string", "blah"); - selftest(rc == -EILSEQ, "unterminated string; rc=%i", rc); + selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc); + + /* of_property_count_strings() tests */ + rc = of_property_count_strings(np, "string-property"); + selftest(rc == 1, "Incorrect string count; rc=%i\n", rc); + rc = of_property_count_strings(np, "phandle-list-names"); + selftest(rc == 3, "Incorrect string count; rc=%i\n", rc); + rc = of_property_count_strings(np, "unterminated-string"); + selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc); + rc = of_property_count_strings(np, "unterminated-string-list"); + selftest(rc == -EILSEQ, "unterminated string array; rc=%i\n", rc); + + /* of_property_read_string_index() tests */ + rc = of_property_read_string_index(np, "string-property", 0, strings); + selftest(rc == 0 && !strcmp(strings[0], "foobar"), "of_property_read_string_index() failure; rc=%i\n", rc); + strings[0] = NULL; + rc = of_property_read_string_index(np, "string-property", 1, strings); + selftest(rc == -ENODATA && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc); + rc = of_property_read_string_index(np, "phandle-list-names", 0, strings); + selftest(rc == 0 && !strcmp(strings[0], "first"), "of_property_read_string_index() failure; rc=%i\n", rc); + rc = of_property_read_string_index(np, "phandle-list-names", 1, strings); + selftest(rc == 0 && !strcmp(strings[0], "second"), "of_property_read_string_index() failure; rc=%i\n", rc); + rc = of_property_read_string_index(np, "phandle-list-names", 2, strings); + selftest(rc == 0 && !strcmp(strings[0], "third"), "of_property_read_string_index() failure; rc=%i\n", rc); + strings[0] = NULL; + rc = of_property_read_string_index(np, "phandle-list-names", 3, strings); + selftest(rc == -ENODATA && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc); + strings[0] = NULL; + rc = of_property_read_string_index(np, "unterminated-string", 0, strings); + selftest(rc == -EILSEQ && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc); + rc = of_property_read_string_index(np, "unterminated-string-list", 0, strings); + selftest(rc == 0 && !strcmp(strings[0], "first"), "of_property_read_string_index() failure; rc=%i\n", rc); + strings[0] = NULL; + rc = of_property_read_string_index(np, "unterminated-string-list", 2, strings); /* should fail */ + selftest(rc == -EILSEQ && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc); + strings[1] = NULL; + + /* of_property_read_string_array() tests */ + rc = of_property_read_string_array(np, "string-property", strings, 4); + selftest(rc == 1, "Incorrect string count; rc=%i\n", rc); + rc = of_property_read_string_array(np, "phandle-list-names", strings, 4); + selftest(rc == 3, "Incorrect string count; rc=%i\n", rc); + rc = of_property_read_string_array(np, "unterminated-string", strings, 4); + selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc); + /* -- An incorrectly formed string should cause a failure */ + rc = of_property_read_string_array(np, "unterminated-string-list", strings, 4); + selftest(rc == -EILSEQ, "unterminated string array; rc=%i\n", rc); + /* -- parsing the correctly formed strings should still work: */ + strings[2] = NULL; + rc = of_property_read_string_array(np, "unterminated-string-list", strings, 2); + selftest(rc == 2 && strings[2] == NULL, "of_property_read_string_array() failure; rc=%i\n", rc); + strings[1] = NULL; + rc = of_property_read_string_array(np, "phandle-list-names", strings, 1); + selftest(rc == 1 && strings[1] == NULL, "Overwrote end of string array; rc=%i, str='%s'\n", rc, strings[1]); } static void __init of_selftest_parse_interrupts(void) @@ -379,7 +433,7 @@ static int __init of_selftest(void) pr_info("start of selftest - you will see error messages\n"); of_selftest_parse_phandle_with_args(); - of_selftest_property_match_string(); + of_selftest_property_string(); of_selftest_parse_interrupts(); of_selftest_parse_interrupts_extended(); of_selftest_match_node(); diff --git a/drivers/of/testcase-data/tests-phandle.dtsi b/drivers/of/testcase-data/tests-phandle.dtsi index 0007d3c..eedee37 100644 --- a/drivers/of/testcase-data/tests-phandle.dtsi +++ b/drivers/of/testcase-data/tests-phandle.dtsi @@ -32,7 +32,9 @@ phandle-list-bad-args = <&provider2 1 0>, <&provider3 0>; empty-property; + string-property = "foobar"; unterminated-string = [40 41 42 43]; + unterminated-string-list = "first", "second", [40 41 42 43]; }; }; }; diff --git a/drivers/parport/Kconfig b/drivers/parport/Kconfig index 2872ece..44333bd 100644 --- a/drivers/parport/Kconfig +++ b/drivers/parport/Kconfig @@ -5,6 +5,12 @@ # Parport configuration. # +config ARCH_MIGHT_HAVE_PC_PARPORT + bool + help + Select this config option from the architecture Kconfig if + the architecture might have PC parallel port hardware. + menuconfig PARPORT tristate "Parallel port support" depends on HAS_IOMEM @@ -31,12 +37,6 @@ menuconfig PARPORT If unsure, say Y. -config ARCH_MIGHT_HAVE_PC_PARPORT - bool - help - Select this config option from the architecture Kconfig if - the architecture might have PC parallel port hardware. - if PARPORT config PARPORT_PC diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c index 483d9ad..9773667 100644 --- a/drivers/pci/host/pci-mvebu.c +++ b/drivers/pci/host/pci-mvebu.c @@ -855,7 +855,7 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn, rangesz = pna + na + ns; nranges = rlen / sizeof(__be32) / rangesz; - for (i = 0; i < nranges; i++) { + for (i = 0; i < nranges; i++, range += rangesz) { u32 flags = of_read_number(range, 1); u32 slot = of_read_number(range + 1, 1); u64 cpuaddr = of_read_number(range + na, pna); @@ -865,14 +865,14 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn, rtype = IORESOURCE_IO; else if (DT_FLAGS_TO_TYPE(flags) == DT_TYPE_MEM32) rtype = IORESOURCE_MEM; + else + continue; if (slot == PCI_SLOT(devfn) && type == rtype) { *tgt = DT_CPUADDR_TO_TARGET(cpuaddr); *attr = DT_CPUADDR_TO_ATTR(cpuaddr); return 0; } - - range += rangesz; } return -ENOENT; diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index fb02fc2..ced17f2 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -599,6 +599,20 @@ error_attrs: return ret; } +static int msi_verify_entries(struct pci_dev *dev) +{ + struct msi_desc *entry; + + list_for_each_entry(entry, &dev->msi_list, list) { + if (!dev->no_64bit_msi || !entry->msg.address_hi) + continue; + dev_err(&dev->dev, "Device has broken 64-bit MSI but arch" + " tried to assign one above 4G\n"); + return -EIO; + } + return 0; +} + /** * msi_capability_init - configure device's MSI capability structure * @dev: pointer to the pci_dev data structure of MSI device function @@ -652,6 +666,13 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) return ret; } + ret = msi_verify_entries(dev); + if (ret) { + msi_mask_irq(entry, mask, ~mask); + free_msi_irqs(dev); + return ret; + } + ret = populate_msi_sysfs(dev); if (ret) { msi_mask_irq(entry, mask, ~mask); @@ -767,6 +788,11 @@ static int msix_capability_init(struct pci_dev *dev, if (ret) goto out_avail; + /* Check if all MSI entries honor device restrictions */ + ret = msi_verify_entries(dev); + if (ret) + goto out_free; + /* * Some devices require MSI-X to be enabled before we can touch the * MSI-X registers. We need to mask all the vectors to prevent diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 25f0bc6..7f41551 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -1324,7 +1324,7 @@ static int pci_uevent(struct device *dev, struct kobj_uevent_env *env) if (add_uevent_var(env, "PCI_SLOT_NAME=%s", pci_name(pdev))) return -ENOMEM; - if (add_uevent_var(env, "MODALIAS=pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x", + if (add_uevent_var(env, "MODALIAS=pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X", pdev->vendor, pdev->device, pdev->subsystem_vendor, pdev->subsystem_device, (u8)(pdev->class >> 16), (u8)(pdev->class >> 8), diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c index 45113da..e27a3dc 100644 --- a/drivers/pci/pci-label.c +++ b/drivers/pci/pci-label.c @@ -168,8 +168,8 @@ enum acpi_attr_enum { static void dsm_label_utf16s_to_utf8s(union acpi_object *obj, char *buf) { int len; - len = utf16s_to_utf8s((const wchar_t *)obj->string.pointer, - obj->string.length, + len = utf16s_to_utf8s((const wchar_t *)obj->buffer.pointer, + obj->buffer.length, UTF16_LITTLE_ENDIAN, buf, PAGE_SIZE); buf[len] = '\n'; @@ -194,16 +194,22 @@ dsm_get_label(struct device *dev, char *buf, enum acpi_attr_enum attr) tmp = obj->package.elements; if (obj->type == ACPI_TYPE_PACKAGE && obj->package.count == 2 && tmp[0].type == ACPI_TYPE_INTEGER && - tmp[1].type == ACPI_TYPE_STRING) { + (tmp[1].type == ACPI_TYPE_STRING || + tmp[1].type == ACPI_TYPE_BUFFER)) { /* * The second string element is optional even when * this _DSM is implemented; when not implemented, * this entry must return a null string. */ - if (attr == ACPI_ATTR_INDEX_SHOW) + if (attr == ACPI_ATTR_INDEX_SHOW) { scnprintf(buf, PAGE_SIZE, "%llu\n", tmp->integer.value); - else if (attr == ACPI_ATTR_LABEL_SHOW) - dsm_label_utf16s_to_utf8s(tmp + 1, buf); + } else if (attr == ACPI_ATTR_LABEL_SHOW) { + if (tmp[1].type == ACPI_TYPE_STRING) + scnprintf(buf, PAGE_SIZE, "%s\n", + tmp[1].string.pointer); + else if (tmp[1].type == ACPI_TYPE_BUFFER) + dsm_label_utf16s_to_utf8s(tmp + 1, buf); + } len = strlen(buf) > 0 ? strlen(buf) : -1; } diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 276ef9c..a943c6c 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -178,7 +178,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, { struct pci_dev *pci_dev = to_pci_dev(dev); - return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x\n", + return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X\n", pci_dev->vendor, pci_dev->device, pci_dev->subsystem_vendor, pci_dev->subsystem_device, (u8)(pci_dev->class >> 16), (u8)(pci_dev->class >> 8), @@ -186,9 +186,9 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(modalias); -static ssize_t enabled_store(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) +static ssize_t enable_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct pci_dev *pdev = to_pci_dev(dev); unsigned long val; @@ -212,15 +212,15 @@ static ssize_t enabled_store(struct device *dev, return result < 0 ? result : count; } -static ssize_t enabled_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t enable_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct pci_dev *pdev; pdev = to_pci_dev (dev); return sprintf (buf, "%u\n", atomic_read(&pdev->enable_cnt)); } -static DEVICE_ATTR_RW(enabled); +static DEVICE_ATTR_RW(enable); #ifdef CONFIG_NUMA static ssize_t @@ -526,7 +526,7 @@ static struct attribute *pci_dev_attrs[] = { #endif &dev_attr_dma_mask_bits.attr, &dev_attr_consistent_dma_mask_bits.attr, - &dev_attr_enabled.attr, + &dev_attr_enable.attr, &dev_attr_broken_parity_status.attr, &dev_attr_msi_bus.attr, #if defined(CONFIG_PM_RUNTIME) && defined(CONFIG_ACPI) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index be36adf..78c65d3 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -830,12 +830,6 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) if (!__pci_complete_power_transition(dev, state)) error = 0; - /* - * When aspm_policy is "powersave" this call ensures - * that ASPM is configured. - */ - if (!error && dev->bus->self) - pcie_aspm_powersave_config_link(dev->bus->self); return error; } @@ -1181,12 +1175,18 @@ EXPORT_SYMBOL_GPL(pci_load_and_free_saved_state); static int do_pci_enable_device(struct pci_dev *dev, int bars) { int err; + struct pci_dev *bridge; u16 cmd; u8 pin; err = pci_set_power_state(dev, PCI_D0); if (err < 0 && err != -EIO) return err; + + bridge = pci_upstream_bridge(dev); + if (bridge) + pcie_aspm_powersave_config_link(bridge); + err = pcibios_enable_device(dev, bars); if (err < 0) return err; @@ -3187,7 +3187,8 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe) { struct pci_dev *pdev; - if (pci_is_root_bus(dev->bus) || dev->subordinate || !dev->bus->self) + if (pci_is_root_bus(dev->bus) || dev->subordinate || + !dev->bus->self || dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET) return -ENOTTY; list_for_each_entry(pdev, &dev->bus->devices, bus_list) @@ -3221,7 +3222,8 @@ static int pci_dev_reset_slot_function(struct pci_dev *dev, int probe) { struct pci_dev *pdev; - if (dev->subordinate || !dev->slot) + if (dev->subordinate || !dev->slot || + dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET) return -ENOTTY; list_for_each_entry(pdev, &dev->bus->devices, bus_list) @@ -3452,6 +3454,20 @@ int pci_try_reset_function(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_try_reset_function); +/* Do any devices on or below this bus prevent a bus reset? */ +static bool pci_bus_resetable(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || + (dev->subordinate && !pci_bus_resetable(dev->subordinate))) + return false; + } + + return true; +} + /* Lock devices from the top of the tree down */ static void pci_bus_lock(struct pci_bus *bus) { @@ -3502,6 +3518,22 @@ unlock: return 0; } +/* Do any devices on or below this slot prevent a bus reset? */ +static bool pci_slot_resetable(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || + (dev->subordinate && !pci_bus_resetable(dev->subordinate))) + return false; + } + + return true; +} + /* Lock devices from the top of the tree down */ static void pci_slot_lock(struct pci_slot *slot) { @@ -3623,7 +3655,7 @@ static int pci_slot_reset(struct pci_slot *slot, int probe) { int rc; - if (!slot) + if (!slot || !pci_slot_resetable(slot)) return -ENOTTY; if (!probe) @@ -3715,7 +3747,7 @@ EXPORT_SYMBOL_GPL(pci_try_reset_slot); static int pci_bus_reset(struct pci_bus *bus, int probe) { - if (!bus->self) + if (!bus->self || !pci_bus_resetable(bus)) return -ENOTTY; if (probe) diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c index 34ff702..5d3b456 100644 --- a/drivers/pci/pcie/aer/aerdrv_errprint.c +++ b/drivers/pci/pcie/aer/aerdrv_errprint.c @@ -127,16 +127,8 @@ static const char *aer_agent_string[] = { static void __print_tlp_header(struct pci_dev *dev, struct aer_header_log_regs *t) { - unsigned char *tlp = (unsigned char *)&t; - - dev_err(&dev->dev, " TLP Header:" - " %02x%02x%02x%02x %02x%02x%02x%02x" - " %02x%02x%02x%02x %02x%02x%02x%02x\n", - *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp, - *(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4), - *(tlp + 11), *(tlp + 10), *(tlp + 9), - *(tlp + 8), *(tlp + 15), *(tlp + 14), - *(tlp + 13), *(tlp + 12)); + dev_err(&dev->dev, " TLP Header: %08x %08x %08x %08x\n", + t->dw0, t->dw1, t->dw2, t->dw3); } static void __aer_print_error(struct pci_dev *dev, diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 6e34498..5b428db 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -214,14 +214,17 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, res->flags |= IORESOURCE_SIZEALIGN; if (res->flags & IORESOURCE_IO) { l &= PCI_BASE_ADDRESS_IO_MASK; + sz &= PCI_BASE_ADDRESS_IO_MASK; mask = PCI_BASE_ADDRESS_IO_MASK & (u32) IO_SPACE_LIMIT; } else { l &= PCI_BASE_ADDRESS_MEM_MASK; + sz &= PCI_BASE_ADDRESS_MEM_MASK; mask = (u32)PCI_BASE_ADDRESS_MEM_MASK; } } else { res->flags |= (l & IORESOURCE_ROM_ENABLE); l &= PCI_ROM_ADDRESS_MASK; + sz &= PCI_ROM_ADDRESS_MASK; mask = (u32)PCI_ROM_ADDRESS_MASK; } @@ -395,15 +398,16 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child) { struct pci_dev *dev = child->self; u16 mem_base_lo, mem_limit_lo; - unsigned long base, limit; + u64 base64, limit64; + dma_addr_t base, limit; struct pci_bus_region region; struct resource *res; res = child->resource[2]; pci_read_config_word(dev, PCI_PREF_MEMORY_BASE, &mem_base_lo); pci_read_config_word(dev, PCI_PREF_MEMORY_LIMIT, &mem_limit_lo); - base = ((unsigned long) mem_base_lo & PCI_PREF_RANGE_MASK) << 16; - limit = ((unsigned long) mem_limit_lo & PCI_PREF_RANGE_MASK) << 16; + base64 = (mem_base_lo & PCI_PREF_RANGE_MASK) << 16; + limit64 = (mem_limit_lo & PCI_PREF_RANGE_MASK) << 16; if ((mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64) { u32 mem_base_hi, mem_limit_hi; @@ -417,18 +421,20 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child) * this, just assume they are not being used. */ if (mem_base_hi <= mem_limit_hi) { -#if BITS_PER_LONG == 64 - base |= ((unsigned long) mem_base_hi) << 32; - limit |= ((unsigned long) mem_limit_hi) << 32; -#else - if (mem_base_hi || mem_limit_hi) { - dev_err(&dev->dev, "can't handle 64-bit " - "address space for bridge\n"); - return; - } -#endif + base64 |= (u64) mem_base_hi << 32; + limit64 |= (u64) mem_limit_hi << 32; } } + + base = (dma_addr_t) base64; + limit = (dma_addr_t) limit64; + + if (base != base64) { + dev_err(&dev->dev, "can't handle bridge window above 4GB (bus address %#010llx)\n", + (unsigned long long) base64); + return; + } + if (base <= limit) { res->flags = (mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) | IORESOURCE_MEM | IORESOURCE_PREFETCH; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 813f437..2afa480 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -24,6 +24,7 @@ #include #include #include +#include #include /* isa_dma_bridge_buggy */ #include "pci.h" @@ -287,6 +288,25 @@ static void quirk_citrine(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CITRINE, quirk_citrine); +/* On IBM Crocodile ipr SAS adapters, expand BAR to system page size */ +static void quirk_extend_bar_to_page(struct pci_dev *dev) +{ + int i; + + for (i = 0; i < PCI_STD_RESOURCE_END; i++) { + struct resource *r = &dev->resource[i]; + + if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) { + r->end = PAGE_SIZE - 1; + r->start = 0; + r->flags |= IORESOURCE_UNSET; + dev_info(&dev->dev, "expanded BAR %d to page size: %pR\n", + i, r); + } + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, 0x034a, quirk_extend_bar_to_page); + /* * S3 868 and 968 chips report region size equal to 32M, but they decode 64M. * If it's needed, re-allocate the region. @@ -2770,12 +2790,15 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x3c28, vtd_mask_spec_errors); static void fixup_ti816x_class(struct pci_dev *dev) { + u32 class = dev->class; + /* TI 816x devices do not have class code set when in PCIe boot mode */ - dev_info(&dev->dev, "Setting PCI class for 816x PCIe device\n"); - dev->class = PCI_CLASS_MULTIMEDIA_VIDEO; + dev->class = PCI_CLASS_MULTIMEDIA_VIDEO << 8; + dev_info(&dev->dev, "PCI class overridden (%#08x -> %#08x)\n", + class, dev->class); } DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_TI, 0xb800, - PCI_CLASS_NOT_DEFINED, 0, fixup_ti816x_class); + PCI_CLASS_NOT_DEFINED, 0, fixup_ti816x_class); /* Some PCIe devices do not work reliably with the claimed maximum * payload size supported. @@ -2988,6 +3011,20 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CHELSIO, 0x0030, DECLARE_PCI_FIXUP_HEADER(0x1814, 0x0601, /* Ralink RT2800 802.11n PCI */ quirk_broken_intx_masking); +static void quirk_no_bus_reset(struct pci_dev *dev) +{ + dev->dev_flags |= PCI_DEV_FLAGS_NO_BUS_RESET; +} + +/* + * Atheros AR93xx chips do not behave after a bus reset. The device will + * throw a Link Down error on AER-capable systems and regardless of AER, + * config space of the device is never accessible again and typically + * causes the system to hang or reset when access is attempted. + * http://www.spinics.net/lists/linux-pci/msg34797.html + */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0030, quirk_no_bus_reset); + static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f, struct pci_fixup *end) { diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c index 5d59572..5510c88 100644 --- a/drivers/pci/rom.c +++ b/drivers/pci/rom.c @@ -69,6 +69,7 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size) { void __iomem *image; int last_image; + unsigned length; image = rom; do { @@ -91,9 +92,9 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size) if (readb(pds + 3) != 'R') break; last_image = readb(pds + 21) & 0x80; - /* this length is reliable */ - image += readw(pds + 16) * 512; - } while (!last_image); + length = readw(pds + 16); + image += length * 512; + } while (length && !last_image); /* never return a size larger than the PCI resource window */ /* there are known ROMs that get the size wrong */ diff --git a/drivers/pcmcia/topic.h b/drivers/pcmcia/topic.h index 615a45a..582688f 100644 --- a/drivers/pcmcia/topic.h +++ b/drivers/pcmcia/topic.h @@ -104,6 +104,9 @@ #define TOPIC_EXCA_IF_CONTROL 0x3e /* 8 bit */ #define TOPIC_EXCA_IFC_33V_ENA 0x01 +#define TOPIC_PCI_CFG_PPBCN 0x3e /* 16-bit */ +#define TOPIC_PCI_CFG_PPBCN_WBEN 0x0400 + static void topic97_zoom_video(struct pcmcia_socket *sock, int onoff) { struct yenta_socket *socket = container_of(sock, struct yenta_socket, socket); @@ -138,6 +141,7 @@ static int topic97_override(struct yenta_socket *socket) static int topic95_override(struct yenta_socket *socket) { u8 fctrl; + u16 ppbcn; /* enable 3.3V support for 16bit cards */ fctrl = exca_readb(socket, TOPIC_EXCA_IF_CONTROL); @@ -146,6 +150,18 @@ static int topic95_override(struct yenta_socket *socket) /* tell yenta to use exca registers to power 16bit cards */ socket->flags |= YENTA_16BIT_POWER_EXCA | YENTA_16BIT_POWER_DF; + /* Disable write buffers to prevent lockups under load with numerous + Cardbus cards, observed on Tecra 500CDT and reported elsewhere on the + net. This is not a power-on default according to the datasheet + but some BIOSes seem to set it. */ + if (pci_read_config_word(socket->dev, TOPIC_PCI_CFG_PPBCN, &ppbcn) == 0 + && socket->dev->revision <= 7 + && (ppbcn & TOPIC_PCI_CFG_PPBCN_WBEN)) { + ppbcn &= ~TOPIC_PCI_CFG_PPBCN_WBEN; + pci_write_config_word(socket->dev, TOPIC_PCI_CFG_PPBCN, ppbcn); + dev_info(&socket->dev->dev, "Disabled ToPIC95 Cardbus write buffers.\n"); + } + return 0; } diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 34d56f7..86592dd 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -50,7 +50,9 @@ static void devm_phy_consume(struct device *dev, void *res) static int devm_phy_match(struct device *dev, void *res, void *match_data) { - return res == match_data; + struct phy **phy = res; + + return *phy == match_data; } static struct phy *phy_lookup(struct device *device, const char *port) diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index c3ace1d..aaac359 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -422,37 +423,55 @@ static void twl4030_phy_power(struct twl4030_usb *twl, int on) } } -static int twl4030_phy_power_off(struct phy *phy) +static int twl4030_usb_runtime_suspend(struct device *dev) { - struct twl4030_usb *twl = phy_get_drvdata(phy); + struct twl4030_usb *twl = dev_get_drvdata(dev); + dev_dbg(twl->dev, "%s\n", __func__); if (twl->asleep) return 0; twl4030_phy_power(twl, 0); twl->asleep = 1; - dev_dbg(twl->dev, "%s\n", __func__); + return 0; } -static void __twl4030_phy_power_on(struct twl4030_usb *twl) +static int twl4030_usb_runtime_resume(struct device *dev) { + struct twl4030_usb *twl = dev_get_drvdata(dev); + + dev_dbg(twl->dev, "%s\n", __func__); + if (!twl->asleep) + return 0; + twl4030_phy_power(twl, 1); - twl4030_i2c_access(twl, 1); - twl4030_usb_set_mode(twl, twl->usb_mode); - if (twl->usb_mode == T2_USB_MODE_ULPI) - twl4030_i2c_access(twl, 0); + twl->asleep = 0; + + return 0; +} + +static int twl4030_phy_power_off(struct phy *phy) +{ + struct twl4030_usb *twl = phy_get_drvdata(phy); + + dev_dbg(twl->dev, "%s\n", __func__); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_autosuspend(twl->dev); + + return 0; } static int twl4030_phy_power_on(struct phy *phy) { struct twl4030_usb *twl = phy_get_drvdata(phy); - if (!twl->asleep) - return 0; - __twl4030_phy_power_on(twl); - twl->asleep = 0; dev_dbg(twl->dev, "%s\n", __func__); + pm_runtime_get_sync(twl->dev); + twl4030_i2c_access(twl, 1); + twl4030_usb_set_mode(twl, twl->usb_mode); + if (twl->usb_mode == T2_USB_MODE_ULPI) + twl4030_i2c_access(twl, 0); /* * XXX When VBUS gets driven after musb goes to A mode, @@ -558,9 +577,27 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl) * USB_LINK_VBUS state. musb_hdrc won't care until it * starts to handle softconnect right. */ + if ((status == OMAP_MUSB_VBUS_VALID) || + (status == OMAP_MUSB_ID_GROUND)) { + if (twl->asleep) + pm_runtime_get_sync(twl->dev); + } else { + if (!twl->asleep) { + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_autosuspend(twl->dev); + } + } omap_musb_mailbox(status); } - sysfs_notify(&twl->dev->kobj, NULL, "vbus"); + + /* don't schedule during sleep - irq works right then */ + if (status == OMAP_MUSB_ID_GROUND && !twl->asleep) { + cancel_delayed_work(&twl->id_workaround_work); + schedule_delayed_work(&twl->id_workaround_work, HZ); + } + + if (irq) + sysfs_notify(&twl->dev->kobj, NULL, "vbus"); return IRQ_HANDLED; } @@ -569,29 +606,8 @@ static void twl4030_id_workaround_work(struct work_struct *work) { struct twl4030_usb *twl = container_of(work, struct twl4030_usb, id_workaround_work.work); - enum omap_musb_vbus_id_status status; - bool status_changed = false; - - status = twl4030_usb_linkstat(twl); - - spin_lock_irq(&twl->lock); - if (status >= 0 && status != twl->linkstat) { - twl->linkstat = status; - status_changed = true; - } - spin_unlock_irq(&twl->lock); - - if (status_changed) { - dev_dbg(twl->dev, "handle missing status change to %d\n", - status); - omap_musb_mailbox(status); - } - /* don't schedule during sleep - irq works right then */ - if (status == OMAP_MUSB_ID_GROUND && !twl->asleep) { - cancel_delayed_work(&twl->id_workaround_work); - schedule_delayed_work(&twl->id_workaround_work, HZ); - } + twl4030_usb_irq(0, twl); } static int twl4030_phy_init(struct phy *phy) @@ -599,22 +615,17 @@ static int twl4030_phy_init(struct phy *phy) struct twl4030_usb *twl = phy_get_drvdata(phy); enum omap_musb_vbus_id_status status; - /* - * Start in sleep state, we'll get called through set_suspend() - * callback when musb is runtime resumed and it's time to start. - */ - __twl4030_phy_power(twl, 0); - twl->asleep = 1; - + pm_runtime_get_sync(twl->dev); status = twl4030_usb_linkstat(twl); twl->linkstat = status; - if (status == OMAP_MUSB_ID_GROUND || status == OMAP_MUSB_VBUS_VALID) { + if (status == OMAP_MUSB_ID_GROUND || status == OMAP_MUSB_VBUS_VALID) omap_musb_mailbox(twl->linkstat); - twl4030_phy_power_on(phy); - } sysfs_notify(&twl->dev->kobj, NULL, "vbus"); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_autosuspend(twl->dev); + return 0; } @@ -650,6 +661,11 @@ static const struct phy_ops ops = { .owner = THIS_MODULE, }; +static const struct dev_pm_ops twl4030_usb_pm_ops = { + SET_RUNTIME_PM_OPS(twl4030_usb_runtime_suspend, + twl4030_usb_runtime_resume, NULL) +}; + static int twl4030_usb_probe(struct platform_device *pdev) { struct twl4030_usb_data *pdata = dev_get_platdata(&pdev->dev); @@ -726,6 +742,11 @@ static int twl4030_usb_probe(struct platform_device *pdev) ATOMIC_INIT_NOTIFIER_HEAD(&twl->phy.notifier); + pm_runtime_use_autosuspend(&pdev->dev); + pm_runtime_set_autosuspend_delay(&pdev->dev, 2000); + pm_runtime_enable(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); + /* Our job is to use irqs and status from the power module * to keep the transceiver disabled when nothing's connected. * @@ -744,6 +765,9 @@ static int twl4030_usb_probe(struct platform_device *pdev) return status; } + pm_runtime_mark_last_busy(&pdev->dev); + pm_runtime_put_autosuspend(twl->dev); + dev_info(&pdev->dev, "Initialized TWL4030 USB module\n"); return 0; } @@ -753,6 +777,7 @@ static int twl4030_usb_remove(struct platform_device *pdev) struct twl4030_usb *twl = platform_get_drvdata(pdev); int val; + pm_runtime_get_sync(twl->dev); cancel_delayed_work(&twl->id_workaround_work); device_remove_file(twl->dev, &dev_attr_vbus); @@ -772,9 +797,8 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* disable complete OTG block */ twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB); - - if (!twl->asleep) - twl4030_phy_power(twl, 0); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put(twl->dev); return 0; } @@ -792,6 +816,7 @@ static struct platform_driver twl4030_usb_driver = { .remove = twl4030_usb_remove, .driver = { .name = "twl4030_usb", + .pm = &twl4030_usb_pm_ops, .owner = THIS_MODULE, .of_match_table = of_match_ptr(twl4030_usb_id_table), }, diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index c0fe609..a2a79c7 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -1121,7 +1121,7 @@ void devm_pinctrl_put(struct pinctrl *p) EXPORT_SYMBOL_GPL(devm_pinctrl_put); int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps, - bool dup, bool locked) + bool dup) { int i, ret; struct pinctrl_maps *maps_node; @@ -1189,11 +1189,9 @@ int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps, maps_node->maps = maps; } - if (!locked) - mutex_lock(&pinctrl_maps_mutex); + mutex_lock(&pinctrl_maps_mutex); list_add_tail(&maps_node->node, &pinctrl_maps); - if (!locked) - mutex_unlock(&pinctrl_maps_mutex); + mutex_unlock(&pinctrl_maps_mutex); return 0; } @@ -1208,7 +1206,7 @@ int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps, int pinctrl_register_mappings(struct pinctrl_map const *maps, unsigned num_maps) { - return pinctrl_register_map(maps, num_maps, true, false); + return pinctrl_register_map(maps, num_maps, true); } void pinctrl_unregister_map(struct pinctrl_map const *map) @@ -1812,14 +1810,15 @@ void pinctrl_unregister(struct pinctrl_dev *pctldev) if (pctldev == NULL) return; - mutex_lock(&pinctrldev_list_mutex); mutex_lock(&pctldev->mutex); - pinctrl_remove_device_debugfs(pctldev); + mutex_unlock(&pctldev->mutex); if (!IS_ERR(pctldev->p)) pinctrl_put(pctldev->p); + mutex_lock(&pinctrldev_list_mutex); + mutex_lock(&pctldev->mutex); /* TODO: check that no pinmuxes are still active? */ list_del(&pctldev->node); /* Destroy descriptor tree */ diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h index 75476b3..b24ea84 100644 --- a/drivers/pinctrl/core.h +++ b/drivers/pinctrl/core.h @@ -183,7 +183,7 @@ static inline struct pin_desc *pin_desc_get(struct pinctrl_dev *pctldev, } int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps, - bool dup, bool locked); + bool dup); void pinctrl_unregister_map(struct pinctrl_map const *map); extern int pinctrl_force_sleep(struct pinctrl_dev *pctldev); diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c index a53d15c..243e533 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -93,7 +93,7 @@ static int dt_remember_or_free_map(struct pinctrl *p, const char *statename, dt_map->num_maps = num_maps; list_add_tail(&dt_map->node, &p->dt_maps); - return pinctrl_register_map(map, num_maps, false, true); + return pinctrl_register_map(map, num_maps, false); } struct pinctrl_dev *of_pinctrl_get(struct device_node *np) diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-370.c b/drivers/pinctrl/mvebu/pinctrl-armada-370.c index ae1f760..bb525b1 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-370.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-370.c @@ -358,11 +358,11 @@ static struct mvebu_mpp_mode mv88f6710_mpp_modes[] = { MPP_MODE(64, MPP_FUNCTION(0x0, "gpio", NULL), MPP_FUNCTION(0x1, "spi0", "miso"), - MPP_FUNCTION(0x2, "spi0-1", "cs1")), + MPP_FUNCTION(0x2, "spi0", "cs1")), MPP_MODE(65, MPP_FUNCTION(0x0, "gpio", NULL), MPP_FUNCTION(0x1, "spi0", "mosi"), - MPP_FUNCTION(0x2, "spi0-1", "cs2")), + MPP_FUNCTION(0x2, "spi0", "cs2")), }; static struct mvebu_pinctrl_soc_info armada_370_pinctrl_info; diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-xp.c b/drivers/pinctrl/mvebu/pinctrl-armada-xp.c index 843a51f..d918c51 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-xp.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-xp.c @@ -14,10 +14,7 @@ * available: mv78230, mv78260 and mv78460. From a pin muxing * perspective, the mv78230 has 49 MPP pins. The mv78260 and mv78460 * both have 67 MPP pins (more GPIOs and address lines for the memory - * bus mainly). The only difference between the mv78260 and the - * mv78460 in terms of pin muxing is the addition of two functions on - * pins 43 and 56 to access the VDD of the CPU2 and 3 (mv78260 has two - * cores, mv78460 has four cores). + * bus mainly). */ #include @@ -159,20 +156,17 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = { MPP_MODE(24, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), MPP_VAR_FUNCTION(0x1, "sata1", "prsnt", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x2, "nf", "bootcs-re", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x3, "tdm", "rst", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x4, "lcd", "hsync", V_MV78230_PLUS)), MPP_MODE(25, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), MPP_VAR_FUNCTION(0x1, "sata0", "prsnt", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x2, "nf", "bootcs-we", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x3, "tdm", "pclk", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x4, "lcd", "vsync", V_MV78230_PLUS)), MPP_MODE(26, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), MPP_VAR_FUNCTION(0x3, "tdm", "fsync", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x4, "lcd", "clk", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x5, "vdd", "cpu1-pd", V_MV78230_PLUS)), + MPP_VAR_FUNCTION(0x4, "lcd", "clk", V_MV78230_PLUS)), MPP_MODE(27, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), MPP_VAR_FUNCTION(0x1, "ptp", "trig", V_MV78230_PLUS), @@ -187,8 +181,7 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = { MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), MPP_VAR_FUNCTION(0x1, "ptp", "clk", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x3, "tdm", "int0", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x4, "lcd", "ref-clk", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x5, "vdd", "cpu0-pd", V_MV78230_PLUS)), + MPP_VAR_FUNCTION(0x4, "lcd", "ref-clk", V_MV78230_PLUS)), MPP_MODE(30, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), MPP_VAR_FUNCTION(0x1, "sd0", "clk", V_MV78230_PLUS), @@ -196,13 +189,11 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = { MPP_MODE(31, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), MPP_VAR_FUNCTION(0x1, "sd0", "cmd", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x3, "tdm", "int2", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x5, "vdd", "cpu0-pd", V_MV78230_PLUS)), + MPP_VAR_FUNCTION(0x3, "tdm", "int2", V_MV78230_PLUS)), MPP_MODE(32, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), MPP_VAR_FUNCTION(0x1, "sd0", "d0", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x3, "tdm", "int3", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x5, "vdd", "cpu1-pd", V_MV78230_PLUS)), + MPP_VAR_FUNCTION(0x3, "tdm", "int3", V_MV78230_PLUS)), MPP_MODE(33, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), MPP_VAR_FUNCTION(0x1, "sd0", "d1", V_MV78230_PLUS), @@ -234,7 +225,6 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = { MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), MPP_VAR_FUNCTION(0x1, "spi", "cs1", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x2, "uart2", "cts", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x3, "vdd", "cpu1-pd", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x4, "lcd", "vga-hsync", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x5, "pcie", "clkreq0", V_MV78230_PLUS)), MPP_MODE(41, @@ -249,15 +239,13 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = { MPP_VAR_FUNCTION(0x1, "uart2", "rxd", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x2, "uart0", "cts", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x3, "tdm", "int7", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x4, "tdm-1", "timer", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x5, "vdd", "cpu0-pd", V_MV78230_PLUS)), + MPP_VAR_FUNCTION(0x4, "tdm-1", "timer", V_MV78230_PLUS)), MPP_MODE(43, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), MPP_VAR_FUNCTION(0x1, "uart2", "txd", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x2, "uart0", "rts", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x3, "spi", "cs3", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x4, "pcie", "rstout", V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x5, "vdd", "cpu2-3-pd", V_MV78460)), + MPP_VAR_FUNCTION(0x4, "pcie", "rstout", V_MV78230_PLUS)), MPP_MODE(44, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), MPP_VAR_FUNCTION(0x1, "uart2", "cts", V_MV78230_PLUS), @@ -286,7 +274,7 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = { MPP_VAR_FUNCTION(0x5, "pcie", "clkreq3", V_MV78230_PLUS)), MPP_MODE(48, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78230_PLUS), - MPP_VAR_FUNCTION(0x1, "tclk", NULL, V_MV78230_PLUS), + MPP_VAR_FUNCTION(0x1, "dev", "clkout", V_MV78230_PLUS), MPP_VAR_FUNCTION(0x2, "dev", "burst/last", V_MV78230_PLUS)), MPP_MODE(49, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78260_PLUS), @@ -308,16 +296,13 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = { MPP_VAR_FUNCTION(0x1, "dev", "ad19", V_MV78260_PLUS)), MPP_MODE(55, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78260_PLUS), - MPP_VAR_FUNCTION(0x1, "dev", "ad20", V_MV78260_PLUS), - MPP_VAR_FUNCTION(0x2, "vdd", "cpu0-pd", V_MV78260_PLUS)), + MPP_VAR_FUNCTION(0x1, "dev", "ad20", V_MV78260_PLUS)), MPP_MODE(56, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78260_PLUS), - MPP_VAR_FUNCTION(0x1, "dev", "ad21", V_MV78260_PLUS), - MPP_VAR_FUNCTION(0x2, "vdd", "cpu1-pd", V_MV78260_PLUS)), + MPP_VAR_FUNCTION(0x1, "dev", "ad21", V_MV78260_PLUS)), MPP_MODE(57, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78260_PLUS), - MPP_VAR_FUNCTION(0x1, "dev", "ad22", V_MV78260_PLUS), - MPP_VAR_FUNCTION(0x2, "vdd", "cpu2-3-pd", V_MV78460)), + MPP_VAR_FUNCTION(0x1, "dev", "ad22", V_MV78260_PLUS)), MPP_MODE(58, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_MV78260_PLUS), MPP_VAR_FUNCTION(0x1, "dev", "ad23", V_MV78260_PLUS)), diff --git a/drivers/pinctrl/pinctrl-baytrail.c b/drivers/pinctrl/pinctrl-baytrail.c index 665b96b..eb9f190 100644 --- a/drivers/pinctrl/pinctrl-baytrail.c +++ b/drivers/pinctrl/pinctrl-baytrail.c @@ -263,7 +263,7 @@ static int byt_gpio_direction_output(struct gpio_chip *chip, spin_lock_irqsave(&vg->lock, flags); reg_val = readl(reg) | BYT_DIR_MASK; - reg_val &= ~BYT_OUTPUT_EN; + reg_val &= ~(BYT_OUTPUT_EN | BYT_INPUT_EN); if (value) writel(reg_val | BYT_LEVEL, reg); diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index c91f69b3..dcfcaea 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -570,6 +570,17 @@ static const struct dmi_system_id video_vendor_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5750"), }, }, + { + /* + * Note no video_set_backlight_video_vendor, we must use the + * acer interface, as there is no native backlight interface. + */ + .ident = "Acer KAV80", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "KAV80"), + }, + }, {} }; diff --git a/drivers/platform/x86/compal-laptop.c b/drivers/platform/x86/compal-laptop.c index 7297df2..54407a8 100644 --- a/drivers/platform/x86/compal-laptop.c +++ b/drivers/platform/x86/compal-laptop.c @@ -1027,9 +1027,9 @@ static int compal_probe(struct platform_device *pdev) if (err) return err; - hwmon_dev = hwmon_device_register_with_groups(&pdev->dev, - DRIVER_NAME, data, - compal_hwmon_groups); + hwmon_dev = devm_hwmon_device_register_with_groups(&pdev->dev, + DRIVER_NAME, data, + compal_hwmon_groups); if (IS_ERR(hwmon_dev)) { err = PTR_ERR(hwmon_dev); goto remove; @@ -1037,7 +1037,9 @@ static int compal_probe(struct platform_device *pdev) /* Power supply */ initialize_power_supply_data(data); - power_supply_register(&compal_device->dev, &data->psy); + err = power_supply_register(&compal_device->dev, &data->psy); + if (err < 0) + goto remove; platform_set_drvdata(pdev, data); diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index fed4111..1beb232 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -272,7 +272,6 @@ static struct dmi_system_id dell_quirks[] = { }; static struct calling_interface_buffer *buffer; -static struct page *bufferpage; static DEFINE_MUTEX(buffer_mutex); static int hwswitch_state; @@ -825,12 +824,11 @@ static int __init dell_init(void) * Allocate buffer below 4GB for SMI data--only 32-bit physical addr * is passed to SMI handler. */ - bufferpage = alloc_page(GFP_KERNEL | GFP_DMA32); - if (!bufferpage) { + buffer = (void *)__get_free_page(GFP_KERNEL | GFP_DMA32); + if (!buffer) { ret = -ENOMEM; goto fail_buffer; } - buffer = page_address(bufferpage); ret = dell_setup_rfkill(); @@ -892,7 +890,7 @@ fail_backlight: cancel_delayed_work_sync(&dell_rfkill_work); dell_cleanup_rfkill(); fail_rfkill: - free_page((unsigned long)bufferpage); + free_page((unsigned long)buffer); fail_buffer: platform_device_del(platform_device); fail_platform_device2: diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index 390e8e3..25721bf 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -163,18 +163,24 @@ static void dell_wmi_notify(u32 value, void *context) const struct key_entry *key; int reported_key; u16 *buffer_entry = (u16 *)obj->buffer.pointer; + int buffer_size = obj->buffer.length/2; - if (dell_new_hk_type && (buffer_entry[1] != 0x10)) { + if (buffer_size >= 2 && dell_new_hk_type && buffer_entry[1] != 0x10) { pr_info("Received unknown WMI event (0x%x)\n", buffer_entry[1]); kfree(obj); return; } - if (dell_new_hk_type || buffer_entry[1] == 0x0) + if (buffer_size >= 3 && (dell_new_hk_type || buffer_entry[1] == 0x0)) reported_key = (int)buffer_entry[2]; - else + else if (buffer_size >= 2) reported_key = (int)buffer_entry[1] & 0xffff; + else { + pr_info("Received unknown WMI event\n"); + kfree(obj); + return; + } key = sparse_keymap_entry_from_scancode(dell_wmi_input_dev, reported_key); diff --git a/drivers/platform/x86/hp_accel.c b/drivers/platform/x86/hp_accel.c index 3dc9344..07fbcb0 100644 --- a/drivers/platform/x86/hp_accel.c +++ b/drivers/platform/x86/hp_accel.c @@ -237,6 +237,7 @@ static struct dmi_system_id lis3lv02d_dmi_ids[] = { AXIS_DMI_MATCH("HPB64xx", "HP ProBook 64", xy_swap), AXIS_DMI_MATCH("HPB64xx", "HP EliteBook 84", xy_swap), AXIS_DMI_MATCH("HPB65xx", "HP ProBook 65", x_inverted), + AXIS_DMI_MATCH("HPZBook15", "HP ZBook 15", x_inverted), { NULL, } /* Laptop models without axis info (yet): * "NC6910" "HP Compaq 6910" diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 6dd060a..0d1a5d4 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -461,8 +461,9 @@ const struct ideapad_rfk_data ideapad_rfk_data[] = { static int ideapad_rfk_set(void *data, bool blocked) { struct ideapad_rfk_priv *priv = data; + int opcode = ideapad_rfk_data[priv->dev].opcode; - return write_ec_cmd(priv->priv->adev->handle, priv->dev, !blocked); + return write_ec_cmd(priv->priv->adev->handle, opcode, !blocked); } static struct rfkill_ops ideapad_rfk_ops = { diff --git a/drivers/pnp/pnpacpi/core.c b/drivers/pnp/pnpacpi/core.c index c31aa07..da1c6cb 100644 --- a/drivers/pnp/pnpacpi/core.c +++ b/drivers/pnp/pnpacpi/core.c @@ -339,8 +339,7 @@ static int __init acpi_pnp_match(struct device *dev, void *_pnp) struct pnp_dev *pnp = _pnp; /* true means it matched */ - return !acpi->physical_node_count - && compare_pnp_id(pnp->id, acpi_device_hid(acpi)); + return pnp->data == acpi; } static struct acpi_device * __init acpi_pnp_find_companion(struct device *dev) diff --git a/drivers/power/88pm860x_charger.c b/drivers/power/88pm860x_charger.c index de029bb..5ccca87 100644 --- a/drivers/power/88pm860x_charger.c +++ b/drivers/power/88pm860x_charger.c @@ -711,6 +711,7 @@ static int pm860x_charger_probe(struct platform_device *pdev) return 0; out_irq: + power_supply_unregister(&info->usb); while (--i >= 0) free_irq(info->irq[i], info); out: diff --git a/drivers/power/bq2415x_charger.c b/drivers/power/bq2415x_charger.c index 79a37f6..1f49986 100644 --- a/drivers/power/bq2415x_charger.c +++ b/drivers/power/bq2415x_charger.c @@ -840,8 +840,7 @@ static int bq2415x_notifier_call(struct notifier_block *nb, if (bq->automode < 1) return NOTIFY_OK; - sysfs_notify(&bq->charger.dev->kobj, NULL, "reported_mode"); - bq2415x_set_mode(bq, bq->reported_mode); + schedule_delayed_work(&bq->work, 0); return NOTIFY_OK; } @@ -892,6 +891,11 @@ static void bq2415x_timer_work(struct work_struct *work) int error; int boost; + if (bq->automode > 0 && (bq->reported_mode != bq->mode)) { + sysfs_notify(&bq->charger.dev->kobj, NULL, "reported_mode"); + bq2415x_set_mode(bq, bq->reported_mode); + } + if (!bq->autotimer) return; @@ -1575,8 +1579,15 @@ static int bq2415x_probe(struct i2c_client *client, if (np) { bq->notify_psy = power_supply_get_by_phandle(np, "ti,usb-charger-detection"); - if (!bq->notify_psy) - return -EPROBE_DEFER; + if (IS_ERR(bq->notify_psy)) { + dev_info(&client->dev, + "no 'ti,usb-charger-detection' property (err=%ld)\n", + PTR_ERR(bq->notify_psy)); + bq->notify_psy = NULL; + } else if (!bq->notify_psy) { + ret = -EPROBE_DEFER; + goto error_2; + } } else if (pdata->notify_device) bq->notify_psy = power_supply_get_by_name(pdata->notify_device); @@ -1598,27 +1609,27 @@ static int bq2415x_probe(struct i2c_client *client, ret = of_property_read_u32(np, "ti,current-limit", &bq->init_data.current_limit); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,weak-battery-voltage", &bq->init_data.weak_battery_voltage); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,battery-regulation-voltage", &bq->init_data.battery_regulation_voltage); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,charge-current", &bq->init_data.charge_current); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,termination-current", &bq->init_data.termination_current); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,resistor-sense", &bq->init_data.resistor_sense); if (ret) - return ret; + goto error_2; } else { memcpy(&bq->init_data, pdata, sizeof(bq->init_data)); } diff --git a/drivers/power/bq24190_charger.c b/drivers/power/bq24190_charger.c index ad3ff8f..e4c95e1 100644 --- a/drivers/power/bq24190_charger.c +++ b/drivers/power/bq24190_charger.c @@ -929,7 +929,7 @@ static void bq24190_charger_init(struct power_supply *charger) charger->properties = bq24190_charger_properties; charger->num_properties = ARRAY_SIZE(bq24190_charger_properties); charger->supplied_to = bq24190_charger_supplied_to; - charger->num_supplies = ARRAY_SIZE(bq24190_charger_supplied_to); + charger->num_supplicants = ARRAY_SIZE(bq24190_charger_supplied_to); charger->get_property = bq24190_charger_get_property; charger->set_property = bq24190_charger_set_property; charger->property_is_writeable = bq24190_charger_property_is_writeable; diff --git a/drivers/power/charger-manager.c b/drivers/power/charger-manager.c index 9e4dab4..03bfac3 100644 --- a/drivers/power/charger-manager.c +++ b/drivers/power/charger-manager.c @@ -97,6 +97,7 @@ static struct charger_global_desc *g_desc; /* init with setup_charger_manager */ static bool is_batt_present(struct charger_manager *cm) { union power_supply_propval val; + struct power_supply *psy; bool present = false; int i, ret; @@ -107,16 +108,27 @@ static bool is_batt_present(struct charger_manager *cm) case CM_NO_BATTERY: break; case CM_FUEL_GAUGE: - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + psy = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!psy) + break; + + ret = psy->get_property(psy, POWER_SUPPLY_PROP_PRESENT, &val); if (ret == 0 && val.intval) present = true; break; case CM_CHARGER_STAT: - for (i = 0; cm->charger_stat[i]; i++) { - ret = cm->charger_stat[i]->get_property( - cm->charger_stat[i], - POWER_SUPPLY_PROP_PRESENT, &val); + for (i = 0; cm->desc->psy_charger_stat[i]; i++) { + psy = power_supply_get_by_name( + cm->desc->psy_charger_stat[i]); + if (!psy) { + dev_err(cm->dev, "Cannot find power supply \"%s\"\n", + cm->desc->psy_charger_stat[i]); + continue; + } + + ret = psy->get_property(psy, POWER_SUPPLY_PROP_PRESENT, + &val); if (ret == 0 && val.intval) { present = true; break; @@ -139,14 +151,20 @@ static bool is_batt_present(struct charger_manager *cm) static bool is_ext_pwr_online(struct charger_manager *cm) { union power_supply_propval val; + struct power_supply *psy; bool online = false; int i, ret; /* If at least one of them has one, it's yes. */ - for (i = 0; cm->charger_stat[i]; i++) { - ret = cm->charger_stat[i]->get_property( - cm->charger_stat[i], - POWER_SUPPLY_PROP_ONLINE, &val); + for (i = 0; cm->desc->psy_charger_stat[i]; i++) { + psy = power_supply_get_by_name(cm->desc->psy_charger_stat[i]); + if (!psy) { + dev_err(cm->dev, "Cannot find power supply \"%s\"\n", + cm->desc->psy_charger_stat[i]); + continue; + } + + ret = psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &val); if (ret == 0 && val.intval) { online = true; break; @@ -167,12 +185,14 @@ static bool is_ext_pwr_online(struct charger_manager *cm) static int get_batt_uV(struct charger_manager *cm, int *uV) { union power_supply_propval val; + struct power_supply *fuel_gauge; int ret; - if (!cm->fuel_gauge) + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) return -ENODEV; - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_VOLTAGE_NOW, &val); if (ret) return ret; @@ -189,6 +209,7 @@ static bool is_charging(struct charger_manager *cm) { int i, ret; bool charging = false; + struct power_supply *psy; union power_supply_propval val; /* If there is no battery, it cannot be charged */ @@ -196,17 +217,22 @@ static bool is_charging(struct charger_manager *cm) return false; /* If at least one of the charger is charging, return yes */ - for (i = 0; cm->charger_stat[i]; i++) { + for (i = 0; cm->desc->psy_charger_stat[i]; i++) { /* 1. The charger sholuld not be DISABLED */ if (cm->emergency_stop) continue; if (!cm->charger_enabled) continue; + psy = power_supply_get_by_name(cm->desc->psy_charger_stat[i]); + if (!psy) { + dev_err(cm->dev, "Cannot find power supply \"%s\"\n", + cm->desc->psy_charger_stat[i]); + continue; + } + /* 2. The charger should be online (ext-power) */ - ret = cm->charger_stat[i]->get_property( - cm->charger_stat[i], - POWER_SUPPLY_PROP_ONLINE, &val); + ret = psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &val); if (ret) { dev_warn(cm->dev, "Cannot read ONLINE value from %s\n", cm->desc->psy_charger_stat[i]); @@ -219,9 +245,7 @@ static bool is_charging(struct charger_manager *cm) * 3. The charger should not be FULL, DISCHARGING, * or NOT_CHARGING. */ - ret = cm->charger_stat[i]->get_property( - cm->charger_stat[i], - POWER_SUPPLY_PROP_STATUS, &val); + ret = psy->get_property(psy, POWER_SUPPLY_PROP_STATUS, &val); if (ret) { dev_warn(cm->dev, "Cannot read STATUS value from %s\n", cm->desc->psy_charger_stat[i]); @@ -248,6 +272,7 @@ static bool is_full_charged(struct charger_manager *cm) { struct charger_desc *desc = cm->desc; union power_supply_propval val; + struct power_supply *fuel_gauge; int ret = 0; int uV; @@ -255,11 +280,15 @@ static bool is_full_charged(struct charger_manager *cm) if (!is_batt_present(cm)) return false; - if (cm->fuel_gauge && desc->fullbatt_full_capacity > 0) { + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) + return false; + + if (desc->fullbatt_full_capacity > 0) { val.intval = 0; /* Not full if capacity of fuel gauge isn't full */ - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CHARGE_FULL, &val); if (!ret && val.intval > desc->fullbatt_full_capacity) return true; @@ -273,10 +302,10 @@ static bool is_full_charged(struct charger_manager *cm) } /* Full, if the capacity is more than fullbatt_soc */ - if (cm->fuel_gauge && desc->fullbatt_soc > 0) { + if (desc->fullbatt_soc > 0) { val.intval = 0; - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CAPACITY, &val); if (!ret && val.intval >= desc->fullbatt_soc) return true; @@ -551,6 +580,20 @@ static int check_charging_duration(struct charger_manager *cm) return ret; } +static int cm_get_battery_temperature_by_psy(struct charger_manager *cm, + int *temp) +{ + struct power_supply *fuel_gauge; + + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) + return -ENODEV; + + return fuel_gauge->get_property(fuel_gauge, + POWER_SUPPLY_PROP_TEMP, + (union power_supply_propval *)temp); +} + static int cm_get_battery_temperature(struct charger_manager *cm, int *temp) { @@ -560,15 +603,18 @@ static int cm_get_battery_temperature(struct charger_manager *cm, return -ENODEV; #ifdef CONFIG_THERMAL - ret = thermal_zone_get_temp(cm->tzd_batt, (unsigned long *)temp); - if (!ret) - /* Calibrate temperature unit */ - *temp /= 100; -#else - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, - POWER_SUPPLY_PROP_TEMP, - (union power_supply_propval *)temp); + if (cm->tzd_batt) { + ret = thermal_zone_get_temp(cm->tzd_batt, (unsigned long *)temp); + if (!ret) + /* Calibrate temperature unit */ + *temp /= 100; + } else #endif + { + /* if-else continued from CONFIG_THERMAL */ + ret = cm_get_battery_temperature_by_psy(cm, temp); + } + return ret; } @@ -827,6 +873,7 @@ static int charger_get_property(struct power_supply *psy, struct charger_manager *cm = container_of(psy, struct charger_manager, charger_psy); struct charger_desc *desc = cm->desc; + struct power_supply *fuel_gauge; int ret = 0; int uV; @@ -857,14 +904,20 @@ static int charger_get_property(struct power_supply *psy, ret = get_batt_uV(cm, &val->intval); break; case POWER_SUPPLY_PROP_CURRENT_NOW: - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) { + ret = -ENODEV; + break; + } + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CURRENT_NOW, val); break; case POWER_SUPPLY_PROP_TEMP: case POWER_SUPPLY_PROP_TEMP_AMBIENT: return cm_get_battery_temperature(cm, &val->intval); case POWER_SUPPLY_PROP_CAPACITY: - if (!cm->fuel_gauge) { + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) { ret = -ENODEV; break; } @@ -875,7 +928,7 @@ static int charger_get_property(struct power_supply *psy, break; } - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CAPACITY, val); if (ret) break; @@ -924,7 +977,14 @@ static int charger_get_property(struct power_supply *psy, break; case POWER_SUPPLY_PROP_CHARGE_NOW: if (is_charging(cm)) { - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + fuel_gauge = power_supply_get_by_name( + cm->desc->psy_fuel_gauge); + if (!fuel_gauge) { + ret = -ENODEV; + break; + } + + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CHARGE_NOW, val); if (ret) { @@ -1485,14 +1545,15 @@ err: return ret; } -static int cm_init_thermal_data(struct charger_manager *cm) +static int cm_init_thermal_data(struct charger_manager *cm, + struct power_supply *fuel_gauge) { struct charger_desc *desc = cm->desc; union power_supply_propval val; int ret; /* Verify whether fuel gauge provides battery temperature */ - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_TEMP, &val); if (!ret) { @@ -1502,8 +1563,6 @@ static int cm_init_thermal_data(struct charger_manager *cm) cm->desc->measure_battery_temp = true; } #ifdef CONFIG_THERMAL - cm->tzd_batt = cm->fuel_gauge->tzd; - if (ret && desc->thermal_zone) { cm->tzd_batt = thermal_zone_get_zone_by_name(desc->thermal_zone); @@ -1666,6 +1725,7 @@ static int charger_manager_probe(struct platform_device *pdev) int ret = 0, i = 0; int j = 0; union power_supply_propval val; + struct power_supply *fuel_gauge; if (g_desc && !rtc_dev && g_desc->rtc_name) { rtc_dev = rtc_class_open(g_desc->rtc_name); @@ -1720,27 +1780,29 @@ static int charger_manager_probe(struct platform_device *pdev) return -EINVAL; } + if (!desc->psy_fuel_gauge) { + dev_err(&pdev->dev, "No fuel gauge power supply defined\n"); + return -EINVAL; + } + /* Counting index only */ while (desc->psy_charger_stat[i]) i++; - cm->charger_stat = devm_kzalloc(&pdev->dev, - sizeof(struct power_supply *) * i, GFP_KERNEL); - if (!cm->charger_stat) - return -ENOMEM; - + /* Check if charger's supplies are present at probe */ for (i = 0; desc->psy_charger_stat[i]; i++) { - cm->charger_stat[i] = power_supply_get_by_name( - desc->psy_charger_stat[i]); - if (!cm->charger_stat[i]) { + struct power_supply *psy; + + psy = power_supply_get_by_name(desc->psy_charger_stat[i]); + if (!psy) { dev_err(&pdev->dev, "Cannot find power supply \"%s\"\n", desc->psy_charger_stat[i]); return -ENODEV; } } - cm->fuel_gauge = power_supply_get_by_name(desc->psy_fuel_gauge); - if (!cm->fuel_gauge) { + fuel_gauge = power_supply_get_by_name(desc->psy_fuel_gauge); + if (!fuel_gauge) { dev_err(&pdev->dev, "Cannot find power supply \"%s\"\n", desc->psy_fuel_gauge); return -ENODEV; @@ -1783,13 +1845,13 @@ static int charger_manager_probe(struct platform_device *pdev) cm->charger_psy.num_properties = psy_default.num_properties; /* Find which optional psy-properties are available */ - if (!cm->fuel_gauge->get_property(cm->fuel_gauge, + if (!fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CHARGE_NOW, &val)) { cm->charger_psy.properties[cm->charger_psy.num_properties] = POWER_SUPPLY_PROP_CHARGE_NOW; cm->charger_psy.num_properties++; } - if (!cm->fuel_gauge->get_property(cm->fuel_gauge, + if (!fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CURRENT_NOW, &val)) { cm->charger_psy.properties[cm->charger_psy.num_properties] = @@ -1797,7 +1859,7 @@ static int charger_manager_probe(struct platform_device *pdev) cm->charger_psy.num_properties++; } - ret = cm_init_thermal_data(cm); + ret = cm_init_thermal_data(cm, fuel_gauge); if (ret) { dev_err(&pdev->dev, "Failed to initialize thermal data\n"); cm->desc->measure_battery_temp = false; @@ -2054,8 +2116,8 @@ static bool find_power_supply(struct charger_manager *cm, int i; bool found = false; - for (i = 0; cm->charger_stat[i]; i++) { - if (psy == cm->charger_stat[i]) { + for (i = 0; cm->desc->psy_charger_stat[i]; i++) { + if (!strcmp(psy->name, cm->desc->psy_charger_stat[i])) { found = true; break; } diff --git a/drivers/power/gpio-charger.c b/drivers/power/gpio-charger.c index a0024b2..86e03c6 100644 --- a/drivers/power/gpio-charger.c +++ b/drivers/power/gpio-charger.c @@ -168,7 +168,7 @@ static int gpio_charger_suspend(struct device *dev) if (device_may_wakeup(dev)) gpio_charger->wakeup_enabled = - enable_irq_wake(gpio_charger->irq); + !enable_irq_wake(gpio_charger->irq); return 0; } @@ -178,7 +178,7 @@ static int gpio_charger_resume(struct device *dev) struct platform_device *pdev = to_platform_device(dev); struct gpio_charger *gpio_charger = platform_get_drvdata(pdev); - if (gpio_charger->wakeup_enabled) + if (device_may_wakeup(dev) && gpio_charger->wakeup_enabled) disable_irq_wake(gpio_charger->irq); power_supply_changed(&gpio_charger->charger); diff --git a/drivers/power/lp8788-charger.c b/drivers/power/lp8788-charger.c index ed49b50..72da2a6 100644 --- a/drivers/power/lp8788-charger.c +++ b/drivers/power/lp8788-charger.c @@ -417,8 +417,10 @@ static int lp8788_psy_register(struct platform_device *pdev, pchg->battery.num_properties = ARRAY_SIZE(lp8788_battery_prop); pchg->battery.get_property = lp8788_battery_get_property; - if (power_supply_register(&pdev->dev, &pchg->battery)) + if (power_supply_register(&pdev->dev, &pchg->battery)) { + power_supply_unregister(&pchg->charger); return -EPERM; + } return 0; } diff --git a/drivers/power/twl4030_madc_battery.c b/drivers/power/twl4030_madc_battery.c index 7ef445a..cf90760 100644 --- a/drivers/power/twl4030_madc_battery.c +++ b/drivers/power/twl4030_madc_battery.c @@ -192,6 +192,7 @@ static int twl4030_madc_battery_probe(struct platform_device *pdev) { struct twl4030_madc_battery *twl4030_madc_bat; struct twl4030_madc_bat_platform_data *pdata = pdev->dev.platform_data; + int ret = 0; twl4030_madc_bat = kzalloc(sizeof(*twl4030_madc_bat), GFP_KERNEL); if (!twl4030_madc_bat) @@ -216,9 +217,11 @@ static int twl4030_madc_battery_probe(struct platform_device *pdev) twl4030_madc_bat->pdata = pdata; platform_set_drvdata(pdev, twl4030_madc_bat); - power_supply_register(&pdev->dev, &twl4030_madc_bat->psy); + ret = power_supply_register(&pdev->dev, &twl4030_madc_bat->psy); + if (ret < 0) + kfree(twl4030_madc_bat); - return 0; + return ret; } static int twl4030_madc_battery_remove(struct platform_device *pdev) diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c index 91245f5..47257b6 100644 --- a/drivers/rapidio/devices/tsi721_dma.c +++ b/drivers/rapidio/devices/tsi721_dma.c @@ -287,6 +287,12 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan) "desc %p not ACKed\n", tx_desc); } + if (ret == NULL) { + dev_dbg(bdma_chan->dchan.device->dev, + "%s: unable to obtain tx descriptor\n", __func__); + goto err_out; + } + i = bdma_chan->wr_count_next % bdma_chan->bd_num; if (i == bdma_chan->bd_num - 1) { i = 0; @@ -297,7 +303,7 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan) tx_desc->txd.phys = bdma_chan->bd_phys + i * sizeof(struct tsi721_dma_desc); tx_desc->hw_desc = &((struct tsi721_dma_desc *)bdma_chan->bd_base)[i]; - +err_out: spin_unlock_bh(&bdma_chan->lock); return ret; diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c index f0ea4fd..8b963a7 100644 --- a/drivers/regulator/arizona-ldo1.c +++ b/drivers/regulator/arizona-ldo1.c @@ -141,8 +141,6 @@ static struct regulator_ops arizona_ldo1_ops = { .map_voltage = regulator_map_voltage_linear, .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = regulator_set_voltage_sel_regmap, - .get_bypass = regulator_get_bypass_regmap, - .set_bypass = regulator_set_bypass_regmap, }; static const struct regulator_desc arizona_ldo1 = { diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 8a9f2b0..e4491c5 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -775,7 +775,7 @@ static int suspend_prepare(struct regulator_dev *rdev, suspend_state_t state) static void print_constraints(struct regulator_dev *rdev) { struct regulation_constraints *constraints = rdev->constraints; - char buf[80] = ""; + char buf[160] = ""; int count = 0; int ret; @@ -1481,7 +1481,7 @@ struct regulator *regulator_get_optional(struct device *dev, const char *id) } EXPORT_SYMBOL_GPL(regulator_get_optional); -/* Locks held by regulator_put() */ +/* regulator_list_mutex lock held by regulator_put() */ static void _regulator_put(struct regulator *regulator) { struct regulator_dev *rdev; @@ -1496,12 +1496,14 @@ static void _regulator_put(struct regulator *regulator) /* remove any sysfs entries */ if (regulator->dev) sysfs_remove_link(&rdev->dev.kobj, regulator->supply_name); + mutex_lock(&rdev->mutex); kfree(regulator->supply_name); list_del(®ulator->list); kfree(regulator); rdev->open_count--; rdev->exclusive = 0; + mutex_unlock(&rdev->mutex); module_put(rdev->owner); } @@ -1767,10 +1769,12 @@ static int _regulator_do_enable(struct regulator_dev *rdev) trace_regulator_enable(rdev_get_name(rdev)); if (rdev->ena_pin) { - ret = regulator_ena_gpio_ctrl(rdev, true); - if (ret < 0) - return ret; - rdev->ena_gpio_state = 1; + if (!rdev->ena_gpio_state) { + ret = regulator_ena_gpio_ctrl(rdev, true); + if (ret < 0) + return ret; + rdev->ena_gpio_state = 1; + } } else if (rdev->desc->ops->enable) { ret = rdev->desc->ops->enable(rdev); if (ret < 0) @@ -1902,10 +1906,12 @@ static int _regulator_do_disable(struct regulator_dev *rdev) trace_regulator_disable(rdev_get_name(rdev)); if (rdev->ena_pin) { - ret = regulator_ena_gpio_ctrl(rdev, false); - if (ret < 0) - return ret; - rdev->ena_gpio_state = 0; + if (rdev->ena_gpio_state) { + ret = regulator_ena_gpio_ctrl(rdev, false); + if (ret < 0) + return ret; + rdev->ena_gpio_state = 0; + } } else if (rdev->desc->ops->disable) { ret = rdev->desc->ops->disable(rdev); @@ -3459,12 +3465,6 @@ regulator_register(const struct regulator_desc *regulator_desc, config->ena_gpio, ret); goto wash; } - - if (config->ena_gpio_flags & GPIOF_OUT_INIT_HIGH) - rdev->ena_gpio_state = 1; - - if (config->ena_gpio_invert) - rdev->ena_gpio_state = !rdev->ena_gpio_state; } /* set regulator constraints */ @@ -3636,9 +3636,11 @@ int regulator_suspend_finish(void) list_for_each_entry(rdev, ®ulator_list, list) { mutex_lock(&rdev->mutex); if (rdev->use_count > 0 || rdev->constraints->always_on) { - error = _regulator_do_enable(rdev); - if (error) - ret = error; + if (!_regulator_is_enabled(rdev)) { + error = _regulator_do_enable(rdev); + if (error) + ret = error; + } } else { if (!have_full_constraints()) goto unlock; diff --git a/drivers/regulator/max77693.c b/drivers/regulator/max77693.c index 5fb899f..24c926b 100644 --- a/drivers/regulator/max77693.c +++ b/drivers/regulator/max77693.c @@ -232,7 +232,7 @@ static int max77693_pmic_probe(struct platform_device *pdev) struct max77693_pmic_dev *max77693_pmic; struct max77693_regulator_data *rdata = NULL; int num_rdata, i; - struct regulator_config config; + struct regulator_config config = { }; num_rdata = max77693_pmic_init_rdata(&pdev->dev, &rdata); if (!rdata || num_rdata <= 0) { diff --git a/drivers/rtc/rtc-isl12057.c b/drivers/rtc/rtc-isl12057.c index 7854a65..110eab8 100644 --- a/drivers/rtc/rtc-isl12057.c +++ b/drivers/rtc/rtc-isl12057.c @@ -89,7 +89,7 @@ static void isl12057_rtc_regs_to_tm(struct rtc_time *tm, u8 *regs) tm->tm_min = bcd2bin(regs[ISL12057_REG_RTC_MN]); if (regs[ISL12057_REG_RTC_HR] & ISL12057_REG_RTC_HR_MIL) { /* AM/PM */ - tm->tm_hour = bcd2bin(regs[ISL12057_REG_RTC_HR] & 0x0f); + tm->tm_hour = bcd2bin(regs[ISL12057_REG_RTC_HR] & 0x1f); if (regs[ISL12057_REG_RTC_HR] & ISL12057_REG_RTC_HR_PM) tm->tm_hour += 12; } else { /* 24 hour mode */ @@ -98,7 +98,7 @@ static void isl12057_rtc_regs_to_tm(struct rtc_time *tm, u8 *regs) tm->tm_mday = bcd2bin(regs[ISL12057_REG_RTC_DT]); tm->tm_wday = bcd2bin(regs[ISL12057_REG_RTC_DW]) - 1; /* starts at 1 */ - tm->tm_mon = bcd2bin(regs[ISL12057_REG_RTC_MO]) - 1; /* starts at 1 */ + tm->tm_mon = bcd2bin(regs[ISL12057_REG_RTC_MO] & 0x1f) - 1; /* ditto */ tm->tm_year = bcd2bin(regs[ISL12057_REG_RTC_YR]) + 100; } diff --git a/drivers/rtc/rtc-sirfsoc.c b/drivers/rtc/rtc-sirfsoc.c index 3eb3642..d2b1ab3 100644 --- a/drivers/rtc/rtc-sirfsoc.c +++ b/drivers/rtc/rtc-sirfsoc.c @@ -290,14 +290,6 @@ static int sirfsoc_rtc_probe(struct platform_device *pdev) rtc_div = ((32768 / RTC_HZ) / 2) - 1; sirfsoc_rtc_iobrg_writel(rtc_div, rtcdrv->rtc_base + RTC_DIV); - rtcdrv->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, - &sirfsoc_rtc_ops, THIS_MODULE); - if (IS_ERR(rtcdrv->rtc)) { - err = PTR_ERR(rtcdrv->rtc); - dev_err(&pdev->dev, "can't register RTC device\n"); - return err; - } - /* 0x3 -> RTC_CLK */ sirfsoc_rtc_iobrg_writel(SIRFSOC_RTC_CLK, rtcdrv->rtc_base + RTC_CLOCK_SWITCH); @@ -312,6 +304,14 @@ static int sirfsoc_rtc_probe(struct platform_device *pdev) rtcdrv->overflow_rtc = sirfsoc_rtc_iobrg_readl(rtcdrv->rtc_base + RTC_SW_VALUE); + rtcdrv->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, + &sirfsoc_rtc_ops, THIS_MODULE); + if (IS_ERR(rtcdrv->rtc)) { + err = PTR_ERR(rtcdrv->rtc); + dev_err(&pdev->dev, "can't register RTC device\n"); + return err; + } + rtcdrv->irq = platform_get_irq(pdev, 0); err = devm_request_irq( &pdev->dev, diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index bb86494..19915c5 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -288,12 +288,16 @@ static void raw3215_timeout(unsigned long __data) unsigned long flags; spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags); - if (raw->flags & RAW3215_TIMER_RUNS) { - del_timer(&raw->timer); - raw->flags &= ~RAW3215_TIMER_RUNS; - if (!(raw->port.flags & ASYNC_SUSPENDED)) { - raw3215_mk_write_req(raw); - raw3215_start_io(raw); + raw->flags &= ~RAW3215_TIMER_RUNS; + if (!(raw->port.flags & ASYNC_SUSPENDED)) { + raw3215_mk_write_req(raw); + raw3215_start_io(raw); + if ((raw->queued_read || raw->queued_write) && + !(raw->flags & RAW3215_WORKING) && + !(raw->flags & RAW3215_TIMER_RUNS)) { + raw->timer.expires = RAW3215_TIMEOUT + jiffies; + add_timer(&raw->timer); + raw->flags |= RAW3215_TIMER_RUNS; } } spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags); @@ -317,17 +321,15 @@ static inline void raw3215_try_io(struct raw3215_info *raw) (raw->flags & RAW3215_FLUSHING)) { /* execute write requests bigger than minimum size */ raw3215_start_io(raw); - if (raw->flags & RAW3215_TIMER_RUNS) { - del_timer(&raw->timer); - raw->flags &= ~RAW3215_TIMER_RUNS; - } - } else if (!(raw->flags & RAW3215_TIMER_RUNS)) { - /* delay small writes */ - raw->timer.expires = RAW3215_TIMEOUT + jiffies; - add_timer(&raw->timer); - raw->flags |= RAW3215_TIMER_RUNS; } } + if ((raw->queued_read || raw->queued_write) && + !(raw->flags & RAW3215_WORKING) && + !(raw->flags & RAW3215_TIMER_RUNS)) { + raw->timer.expires = RAW3215_TIMEOUT + jiffies; + add_timer(&raw->timer); + raw->flags |= RAW3215_TIMER_RUNS; + } } /* @@ -1027,12 +1029,26 @@ static int tty3215_write(struct tty_struct * tty, const unsigned char *buf, int count) { struct raw3215_info *raw; + int i, written; if (!tty) return 0; raw = (struct raw3215_info *) tty->driver_data; - raw3215_write(raw, buf, count); - return count; + written = count; + while (count > 0) { + for (i = 0; i < count; i++) + if (buf[i] == '\t' || buf[i] == '\n') + break; + raw3215_write(raw, buf, i); + count -= i; + buf += i; + if (count > 0) { + raw3215_putchar(raw, *buf); + count--; + buf++; + } + } + return written; } /* @@ -1180,7 +1196,7 @@ static int __init tty3215_init(void) driver->subtype = SYSTEM_TYPE_TTY; driver->init_termios = tty_std_termios; driver->init_termios.c_iflag = IGNBRK | IGNPAR; - driver->init_termios.c_oflag = ONLCR | XTABS; + driver->init_termios.c_oflag = ONLCR; driver->init_termios.c_lflag = ISIG; driver->flags = TTY_DRIVER_REAL_RAW; tty_set_operations(driver, &tty3215_ops); diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index 82f2c38..b334f68 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -7,6 +7,7 @@ #define KMSG_COMPONENT "sclp_early" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#include #include #include #include diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index ab3baa7..86ade85 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -44,6 +44,7 @@ #include #include #include +#include #include "ap_bus.h" @@ -71,7 +72,7 @@ MODULE_AUTHOR("IBM Corporation"); MODULE_DESCRIPTION("Adjunct Processor Bus driver, " \ "Copyright IBM Corp. 2006, 2012"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("z90crypt"); +MODULE_ALIAS_CRYPTO("z90crypt"); /* * Module parameter diff --git a/drivers/sbus/char/bbc_envctrl.c b/drivers/sbus/char/bbc_envctrl.c index 160e751..0787b97 100644 --- a/drivers/sbus/char/bbc_envctrl.c +++ b/drivers/sbus/char/bbc_envctrl.c @@ -452,6 +452,9 @@ static void attach_one_temp(struct bbc_i2c_bus *bp, struct platform_device *op, if (!tp) return; + INIT_LIST_HEAD(&tp->bp_list); + INIT_LIST_HEAD(&tp->glob_list); + tp->client = bbc_i2c_attach(bp, op); if (!tp->client) { kfree(tp); @@ -497,6 +500,9 @@ static void attach_one_fan(struct bbc_i2c_bus *bp, struct platform_device *op, if (!fp) return; + INIT_LIST_HEAD(&fp->bp_list); + INIT_LIST_HEAD(&fp->glob_list); + fp->client = bbc_i2c_attach(bp, op); if (!fp->client) { kfree(fp); diff --git a/drivers/sbus/char/bbc_i2c.c b/drivers/sbus/char/bbc_i2c.c index c7763e4..812b5f0 100644 --- a/drivers/sbus/char/bbc_i2c.c +++ b/drivers/sbus/char/bbc_i2c.c @@ -300,13 +300,18 @@ static struct bbc_i2c_bus * attach_one_i2c(struct platform_device *op, int index if (!bp) return NULL; + INIT_LIST_HEAD(&bp->temps); + INIT_LIST_HEAD(&bp->fans); + bp->i2c_control_regs = of_ioremap(&op->resource[0], 0, 0x2, "bbc_i2c_regs"); if (!bp->i2c_control_regs) goto fail; - bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel"); - if (!bp->i2c_bussel_reg) - goto fail; + if (op->num_resources == 2) { + bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel"); + if (!bp->i2c_bussel_reg) + goto fail; + } bp->waiting = 0; init_waitqueue_head(&bp->wq); diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c index 0a73253..5f57e3d 100644 --- a/drivers/scsi/3w-9xxx.c +++ b/drivers/scsi/3w-9xxx.c @@ -149,7 +149,6 @@ static int twa_reset_sequence(TW_Device_Extension *tw_dev, int soft_reset); static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, char *cdb, int use_sg, TW_SG_Entry *sglistarg); static void twa_scsiop_execute_scsi_complete(TW_Device_Extension *tw_dev, int request_id); static char *twa_string_lookup(twa_message_type *table, unsigned int aen_code); -static void twa_unmap_scsi_data(TW_Device_Extension *tw_dev, int request_id); /* Functions */ @@ -1352,11 +1351,11 @@ static irqreturn_t twa_interrupt(int irq, void *dev_instance) } /* Now complete the io */ + scsi_dma_unmap(cmd); + cmd->scsi_done(cmd); tw_dev->state[request_id] = TW_S_COMPLETED; twa_free_request_id(tw_dev, request_id); tw_dev->posted_request_count--; - tw_dev->srb[request_id]->scsi_done(tw_dev->srb[request_id]); - twa_unmap_scsi_data(tw_dev, request_id); } /* Check for valid status after each drain */ @@ -1414,26 +1413,6 @@ static void twa_load_sgl(TW_Device_Extension *tw_dev, TW_Command_Full *full_comm } } /* End twa_load_sgl() */ -/* This function will perform a pci-dma mapping for a scatter gather list */ -static int twa_map_scsi_sg_data(TW_Device_Extension *tw_dev, int request_id) -{ - int use_sg; - struct scsi_cmnd *cmd = tw_dev->srb[request_id]; - - use_sg = scsi_dma_map(cmd); - if (!use_sg) - return 0; - else if (use_sg < 0) { - TW_PRINTK(tw_dev->host, TW_DRIVER, 0x1c, "Failed to map scatter gather list"); - return 0; - } - - cmd->SCp.phase = TW_PHASE_SGLIST; - cmd->SCp.have_data_in = use_sg; - - return use_sg; -} /* End twa_map_scsi_sg_data() */ - /* This function will poll for a response interrupt of a request */ static int twa_poll_response(TW_Device_Extension *tw_dev, int request_id, int seconds) { @@ -1612,9 +1591,11 @@ static int twa_reset_device_extension(TW_Device_Extension *tw_dev) (tw_dev->state[i] != TW_S_INITIAL) && (tw_dev->state[i] != TW_S_COMPLETED)) { if (tw_dev->srb[i]) { - tw_dev->srb[i]->result = (DID_RESET << 16); - tw_dev->srb[i]->scsi_done(tw_dev->srb[i]); - twa_unmap_scsi_data(tw_dev, i); + struct scsi_cmnd *cmd = tw_dev->srb[i]; + + cmd->result = (DID_RESET << 16); + scsi_dma_unmap(cmd); + cmd->scsi_done(cmd); } } } @@ -1793,21 +1774,18 @@ static int twa_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_ /* Save the scsi command for use by the ISR */ tw_dev->srb[request_id] = SCpnt; - /* Initialize phase to zero */ - SCpnt->SCp.phase = TW_PHASE_INITIAL; - retval = twa_scsiop_execute_scsi(tw_dev, request_id, NULL, 0, NULL); switch (retval) { case SCSI_MLQUEUE_HOST_BUSY: + scsi_dma_unmap(SCpnt); twa_free_request_id(tw_dev, request_id); - twa_unmap_scsi_data(tw_dev, request_id); break; case 1: - tw_dev->state[request_id] = TW_S_COMPLETED; - twa_free_request_id(tw_dev, request_id); - twa_unmap_scsi_data(tw_dev, request_id); SCpnt->result = (DID_ERROR << 16); + scsi_dma_unmap(SCpnt); done(SCpnt); + tw_dev->state[request_id] = TW_S_COMPLETED; + twa_free_request_id(tw_dev, request_id); retval = 0; } out: @@ -1875,8 +1853,8 @@ static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, command_packet->sg_list[0].address = TW_CPU_TO_SGL(tw_dev->generic_buffer_phys[request_id]); command_packet->sg_list[0].length = cpu_to_le32(TW_MIN_SGL_LENGTH); } else { - sg_count = twa_map_scsi_sg_data(tw_dev, request_id); - if (sg_count == 0) + sg_count = scsi_dma_map(srb); + if (sg_count < 0) goto out; scsi_for_each_sg(srb, sg, sg_count, i) { @@ -1991,15 +1969,6 @@ static char *twa_string_lookup(twa_message_type *table, unsigned int code) return(table[index].text); } /* End twa_string_lookup() */ -/* This function will perform a pci-dma unmap */ -static void twa_unmap_scsi_data(TW_Device_Extension *tw_dev, int request_id) -{ - struct scsi_cmnd *cmd = tw_dev->srb[request_id]; - - if (cmd->SCp.phase == TW_PHASE_SGLIST) - scsi_dma_unmap(cmd); -} /* End twa_unmap_scsi_data() */ - /* This function gets called when a disk is coming on-line */ static int twa_slave_configure(struct scsi_device *sdev) { diff --git a/drivers/scsi/3w-9xxx.h b/drivers/scsi/3w-9xxx.h index 040f721..0fdc83c 100644 --- a/drivers/scsi/3w-9xxx.h +++ b/drivers/scsi/3w-9xxx.h @@ -324,11 +324,6 @@ static twa_message_type twa_error_table[] = { #define TW_CURRENT_DRIVER_BUILD 0 #define TW_CURRENT_DRIVER_BRANCH 0 -/* Phase defines */ -#define TW_PHASE_INITIAL 0 -#define TW_PHASE_SINGLE 1 -#define TW_PHASE_SGLIST 2 - /* Misc defines */ #define TW_9550SX_DRAIN_COMPLETED 0xFFFF #define TW_SECTOR_SIZE 512 diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c index 4de3460..61702ac 100644 --- a/drivers/scsi/3w-sas.c +++ b/drivers/scsi/3w-sas.c @@ -303,26 +303,6 @@ static int twl_post_command_packet(TW_Device_Extension *tw_dev, int request_id) return 0; } /* End twl_post_command_packet() */ -/* This function will perform a pci-dma mapping for a scatter gather list */ -static int twl_map_scsi_sg_data(TW_Device_Extension *tw_dev, int request_id) -{ - int use_sg; - struct scsi_cmnd *cmd = tw_dev->srb[request_id]; - - use_sg = scsi_dma_map(cmd); - if (!use_sg) - return 0; - else if (use_sg < 0) { - TW_PRINTK(tw_dev->host, TW_DRIVER, 0x1, "Failed to map scatter gather list"); - return 0; - } - - cmd->SCp.phase = TW_PHASE_SGLIST; - cmd->SCp.have_data_in = use_sg; - - return use_sg; -} /* End twl_map_scsi_sg_data() */ - /* This function hands scsi cdb's to the firmware */ static int twl_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, char *cdb, int use_sg, TW_SG_Entry_ISO *sglistarg) { @@ -370,8 +350,8 @@ static int twl_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, if (!sglistarg) { /* Map sglist from scsi layer to cmd packet */ if (scsi_sg_count(srb)) { - sg_count = twl_map_scsi_sg_data(tw_dev, request_id); - if (sg_count == 0) + sg_count = scsi_dma_map(srb); + if (sg_count <= 0) goto out; scsi_for_each_sg(srb, sg, sg_count, i) { @@ -1116,15 +1096,6 @@ out: return retval; } /* End twl_initialize_device_extension() */ -/* This function will perform a pci-dma unmap */ -static void twl_unmap_scsi_data(TW_Device_Extension *tw_dev, int request_id) -{ - struct scsi_cmnd *cmd = tw_dev->srb[request_id]; - - if (cmd->SCp.phase == TW_PHASE_SGLIST) - scsi_dma_unmap(cmd); -} /* End twl_unmap_scsi_data() */ - /* This function will handle attention interrupts */ static int twl_handle_attention_interrupt(TW_Device_Extension *tw_dev) { @@ -1265,11 +1236,11 @@ static irqreturn_t twl_interrupt(int irq, void *dev_instance) } /* Now complete the io */ + scsi_dma_unmap(cmd); + cmd->scsi_done(cmd); tw_dev->state[request_id] = TW_S_COMPLETED; twl_free_request_id(tw_dev, request_id); tw_dev->posted_request_count--; - tw_dev->srb[request_id]->scsi_done(tw_dev->srb[request_id]); - twl_unmap_scsi_data(tw_dev, request_id); } /* Check for another response interrupt */ @@ -1414,10 +1385,12 @@ static int twl_reset_device_extension(TW_Device_Extension *tw_dev, int ioctl_res if ((tw_dev->state[i] != TW_S_FINISHED) && (tw_dev->state[i] != TW_S_INITIAL) && (tw_dev->state[i] != TW_S_COMPLETED)) { - if (tw_dev->srb[i]) { - tw_dev->srb[i]->result = (DID_RESET << 16); - tw_dev->srb[i]->scsi_done(tw_dev->srb[i]); - twl_unmap_scsi_data(tw_dev, i); + struct scsi_cmnd *cmd = tw_dev->srb[i]; + + if (cmd) { + cmd->result = (DID_RESET << 16); + scsi_dma_unmap(cmd); + cmd->scsi_done(cmd); } } } @@ -1521,9 +1494,6 @@ static int twl_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_ /* Save the scsi command for use by the ISR */ tw_dev->srb[request_id] = SCpnt; - /* Initialize phase to zero */ - SCpnt->SCp.phase = TW_PHASE_INITIAL; - retval = twl_scsiop_execute_scsi(tw_dev, request_id, NULL, 0, NULL); if (retval) { tw_dev->state[request_id] = TW_S_COMPLETED; diff --git a/drivers/scsi/3w-sas.h b/drivers/scsi/3w-sas.h index d474892..fec6449 100644 --- a/drivers/scsi/3w-sas.h +++ b/drivers/scsi/3w-sas.h @@ -103,10 +103,6 @@ static char *twl_aen_severity_table[] = #define TW_CURRENT_DRIVER_BUILD 0 #define TW_CURRENT_DRIVER_BRANCH 0 -/* Phase defines */ -#define TW_PHASE_INITIAL 0 -#define TW_PHASE_SGLIST 2 - /* Misc defines */ #define TW_SECTOR_SIZE 512 #define TW_MAX_UNITS 32 diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c index 752624e..b327742 100644 --- a/drivers/scsi/3w-xxxx.c +++ b/drivers/scsi/3w-xxxx.c @@ -1284,32 +1284,6 @@ static int tw_initialize_device_extension(TW_Device_Extension *tw_dev) return 0; } /* End tw_initialize_device_extension() */ -static int tw_map_scsi_sg_data(struct pci_dev *pdev, struct scsi_cmnd *cmd) -{ - int use_sg; - - dprintk(KERN_WARNING "3w-xxxx: tw_map_scsi_sg_data()\n"); - - use_sg = scsi_dma_map(cmd); - if (use_sg < 0) { - printk(KERN_WARNING "3w-xxxx: tw_map_scsi_sg_data(): pci_map_sg() failed.\n"); - return 0; - } - - cmd->SCp.phase = TW_PHASE_SGLIST; - cmd->SCp.have_data_in = use_sg; - - return use_sg; -} /* End tw_map_scsi_sg_data() */ - -static void tw_unmap_scsi_data(struct pci_dev *pdev, struct scsi_cmnd *cmd) -{ - dprintk(KERN_WARNING "3w-xxxx: tw_unmap_scsi_data()\n"); - - if (cmd->SCp.phase == TW_PHASE_SGLIST) - scsi_dma_unmap(cmd); -} /* End tw_unmap_scsi_data() */ - /* This function will reset a device extension */ static int tw_reset_device_extension(TW_Device_Extension *tw_dev) { @@ -1332,8 +1306,8 @@ static int tw_reset_device_extension(TW_Device_Extension *tw_dev) srb = tw_dev->srb[i]; if (srb != NULL) { srb->result = (DID_RESET << 16); - tw_dev->srb[i]->scsi_done(tw_dev->srb[i]); - tw_unmap_scsi_data(tw_dev->tw_pci_dev, tw_dev->srb[i]); + scsi_dma_unmap(srb); + srb->scsi_done(srb); } } } @@ -1780,8 +1754,8 @@ static int tw_scsiop_read_write(TW_Device_Extension *tw_dev, int request_id) command_packet->byte8.io.lba = lba; command_packet->byte6.block_count = num_sectors; - use_sg = tw_map_scsi_sg_data(tw_dev->tw_pci_dev, tw_dev->srb[request_id]); - if (!use_sg) + use_sg = scsi_dma_map(srb); + if (use_sg <= 0) return 1; scsi_for_each_sg(tw_dev->srb[request_id], sg, use_sg, i) { @@ -1968,9 +1942,6 @@ static int tw_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_c /* Save the scsi command for use by the ISR */ tw_dev->srb[request_id] = SCpnt; - /* Initialize phase to zero */ - SCpnt->SCp.phase = TW_PHASE_INITIAL; - switch (*command) { case READ_10: case READ_6: @@ -2198,12 +2169,11 @@ static irqreturn_t tw_interrupt(int irq, void *dev_instance) /* Now complete the io */ if ((error != TW_ISR_DONT_COMPLETE)) { + scsi_dma_unmap(tw_dev->srb[request_id]); + tw_dev->srb[request_id]->scsi_done(tw_dev->srb[request_id]); tw_dev->state[request_id] = TW_S_COMPLETED; tw_state_request_finish(tw_dev, request_id); tw_dev->posted_request_count--; - tw_dev->srb[request_id]->scsi_done(tw_dev->srb[request_id]); - - tw_unmap_scsi_data(tw_dev->tw_pci_dev, tw_dev->srb[request_id]); } } diff --git a/drivers/scsi/3w-xxxx.h b/drivers/scsi/3w-xxxx.h index 49dcf03..1d31858 100644 --- a/drivers/scsi/3w-xxxx.h +++ b/drivers/scsi/3w-xxxx.h @@ -195,11 +195,6 @@ static unsigned char tw_sense_table[][4] = #define TW_AEN_SMART_FAIL 0x000F #define TW_AEN_SBUF_FAIL 0x0024 -/* Phase defines */ -#define TW_PHASE_INITIAL 0 -#define TW_PHASE_SINGLE 1 -#define TW_PHASE_SGLIST 2 - /* Misc defines */ #define TW_ALIGNMENT_6000 64 /* 64 bytes */ #define TW_ALIGNMENT_7000 4 /* 4 bytes */ diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c index 1e9d6ad..7563b3d 100644 --- a/drivers/scsi/NCR5380.c +++ b/drivers/scsi/NCR5380.c @@ -2655,14 +2655,14 @@ static void NCR5380_dma_complete(NCR5380_instance * instance) { * * Purpose : abort a command * - * Inputs : cmd - the Scsi_Cmnd to abort, code - code to set the - * host byte of the result field to, if zero DID_ABORTED is + * Inputs : cmd - the Scsi_Cmnd to abort, code - code to set the + * host byte of the result field to, if zero DID_ABORTED is * used. * - * Returns : 0 - success, -1 on failure. + * Returns : SUCCESS - success, FAILED on failure. * - * XXX - there is no way to abort the command that is currently - * connected, you have to wait for it to complete. If this is + * XXX - there is no way to abort the command that is currently + * connected, you have to wait for it to complete. If this is * a problem, we could implement longjmp() / setjmp(), setjmp() * called where the loop started in NCR5380_main(). * @@ -2712,7 +2712,7 @@ static int NCR5380_abort(Scsi_Cmnd * cmd) { * aborted flag and get back into our main loop. */ - return 0; + return SUCCESS; } #endif diff --git a/drivers/scsi/aha1740.c b/drivers/scsi/aha1740.c index 5f31017..31ace4b 100644 --- a/drivers/scsi/aha1740.c +++ b/drivers/scsi/aha1740.c @@ -531,7 +531,7 @@ static int aha1740_eh_abort_handler (Scsi_Cmnd *dummy) * quiet as possible... */ - return 0; + return SUCCESS; } static struct scsi_host_template aha1740_template = { diff --git a/drivers/scsi/atari_NCR5380.c b/drivers/scsi/atari_NCR5380.c index 0f3cdbc..30073d4 100644 --- a/drivers/scsi/atari_NCR5380.c +++ b/drivers/scsi/atari_NCR5380.c @@ -2613,7 +2613,7 @@ static void NCR5380_reselect(struct Scsi_Host *instance) * host byte of the result field to, if zero DID_ABORTED is * used. * - * Returns : 0 - success, -1 on failure. + * Returns : SUCCESS - success, FAILED on failure. * * XXX - there is no way to abort the command that is currently * connected, you have to wait for it to complete. If this is diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index 5642a9b..19ddd43 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -581,7 +581,6 @@ static struct beiscsi_hba *beiscsi_hba_alloc(struct pci_dev *pcidev) "beiscsi_hba_alloc - iscsi_host_alloc failed\n"); return NULL; } - shost->dma_boundary = pcidev->dma_mask; shost->max_id = BE2_MAX_SESSIONS; shost->max_channel = 0; shost->max_cmd_len = BEISCSI_MAX_CMD_LEN; @@ -5685,9 +5684,9 @@ free_port: hba_free: if (phba->msix_enabled) pci_disable_msix(phba->pcidev); - iscsi_host_remove(phba->shost); pci_dev_put(phba->pcidev); iscsi_host_free(phba->shost); + pci_set_drvdata(pcidev, NULL); disable_pci: pci_disable_device(pcidev); return ret; diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c index b2fcac7..5bb9406 100644 --- a/drivers/scsi/be2iscsi/be_mgmt.c +++ b/drivers/scsi/be2iscsi/be_mgmt.c @@ -897,17 +897,20 @@ mgmt_static_ip_modify(struct beiscsi_hba *phba, if (ip_action == IP_ACTION_ADD) { memcpy(req->ip_params.ip_record.ip_addr.addr, ip_param->value, - ip_param->len); + sizeof(req->ip_params.ip_record.ip_addr.addr)); if (subnet_param) memcpy(req->ip_params.ip_record.ip_addr.subnet_mask, - subnet_param->value, subnet_param->len); + subnet_param->value, + sizeof(req->ip_params.ip_record.ip_addr.subnet_mask)); } else { memcpy(req->ip_params.ip_record.ip_addr.addr, - if_info->ip_addr.addr, ip_param->len); + if_info->ip_addr.addr, + sizeof(req->ip_params.ip_record.ip_addr.addr)); memcpy(req->ip_params.ip_record.ip_addr.subnet_mask, - if_info->ip_addr.subnet_mask, ip_param->len); + if_info->ip_addr.subnet_mask, + sizeof(req->ip_params.ip_record.ip_addr.subnet_mask)); } rc = mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0); @@ -935,7 +938,7 @@ static int mgmt_modify_gateway(struct beiscsi_hba *phba, uint8_t *gt_addr, req->action = gtway_action; req->ip_addr.ip_type = BE2_IPV4; - memcpy(req->ip_addr.addr, gt_addr, param_len); + memcpy(req->ip_addr.addr, gt_addr, sizeof(req->ip_addr.addr)); return mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0); } diff --git a/drivers/scsi/bfa/bfa_ioc.c b/drivers/scsi/bfa/bfa_ioc.c index 65180e1..50c75e1 100644 --- a/drivers/scsi/bfa/bfa_ioc.c +++ b/drivers/scsi/bfa/bfa_ioc.c @@ -7006,7 +7006,7 @@ bfa_flash_sem_get(void __iomem *bar) while (!bfa_raw_sem_get(bar)) { if (--n <= 0) return BFA_STATUS_BADFLASH; - udelay(10000); + mdelay(10); } return BFA_STATUS_OK; } diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h index 2e28392..a38aafa0 100644 --- a/drivers/scsi/bfa/bfa_ioc.h +++ b/drivers/scsi/bfa/bfa_ioc.h @@ -72,7 +72,7 @@ struct bfa_sge_s { } while (0) #define bfa_swap_words(_x) ( \ - ((_x) << 32) | ((_x) >> 32)) + ((u64)(_x) << 32) | ((u64)(_x) >> 32)) #ifdef __BIG_ENDIAN #define bfa_sge_to_be(_x) diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index 9b94850..cc6b13b 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -411,6 +411,7 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev, struct fc_frame_header *fh; struct fcoe_rcv_info *fr; struct fcoe_percpu_s *bg; + struct sk_buff *tmp_skb; unsigned short oxid; interface = container_of(ptype, struct bnx2fc_interface, @@ -423,6 +424,12 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev, goto err; } + tmp_skb = skb_share_check(skb, GFP_ATOMIC); + if (!tmp_skb) + goto err; + + skb = tmp_skb; + if (unlikely(eth_hdr(skb)->h_proto != htons(ETH_P_FCOE))) { printk(KERN_ERR PFX "bnx2fc_rcv: Wrong FC type frame\n"); goto err; diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c index f37f3e3..28fe6fe 100644 --- a/drivers/scsi/esas2r/esas2r_main.c +++ b/drivers/scsi/esas2r/esas2r_main.c @@ -1057,7 +1057,7 @@ int esas2r_eh_abort(struct scsi_cmnd *cmd) cmd->scsi_done(cmd); - return 0; + return SUCCESS; } spin_lock_irqsave(&a->queue_lock, flags); diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 868318a..85d370e 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -3131,7 +3131,7 @@ static int hpsa_big_passthru_ioctl(struct ctlr_info *h, void __user *argp) } if (ioc->Request.Type.Direction == XFER_WRITE) { if (copy_from_user(buff[sg_used], data_ptr, sz)) { - status = -ENOMEM; + status = -EFAULT; goto cleanup1; } } else @@ -3984,10 +3984,6 @@ static int hpsa_kdump_hard_reset_controller(struct pci_dev *pdev) /* Save the PCI command register */ pci_read_config_word(pdev, 4, &command_register); - /* Turn the board off. This is so that later pci_restore_state() - * won't turn the board on before the rest of config space is ready. - */ - pci_disable_device(pdev); pci_save_state(pdev); /* find the first memory BAR, so we can find the cfg table */ @@ -4035,11 +4031,6 @@ static int hpsa_kdump_hard_reset_controller(struct pci_dev *pdev) goto unmap_cfgtable; pci_restore_state(pdev); - rc = pci_enable_device(pdev); - if (rc) { - dev_warn(&pdev->dev, "failed to enable device.\n"); - goto unmap_cfgtable; - } pci_write_config_word(pdev, 4, command_register); /* Some devices (notably the HP Smart Array 5i Controller) @@ -4367,9 +4358,9 @@ static inline void hpsa_set_driver_support_bits(struct ctlr_info *h) { u32 driver_support; -#ifdef CONFIG_X86 - /* Need to enable prefetch in the SCSI core for 6400 in x86 */ driver_support = readl(&(h->cfgtable->driver_support)); + /* Need to enable prefetch in the SCSI core for 6400 in x86 */ +#ifdef CONFIG_X86 driver_support |= ENABLE_SCSI_PREFETCH; #endif driver_support |= ENABLE_UNIT_ATTN; @@ -4525,6 +4516,23 @@ static int hpsa_init_reset_devices(struct pci_dev *pdev) if (!reset_devices) return 0; + /* kdump kernel is loading, we don't know in which state is + * the pci interface. The dev->enable_cnt is equal zero + * so we call enable+disable, wait a while and switch it on. + */ + rc = pci_enable_device(pdev); + if (rc) { + dev_warn(&pdev->dev, "Failed to enable PCI device\n"); + return -ENODEV; + } + pci_disable_device(pdev); + msleep(260); /* a randomly chosen number */ + rc = pci_enable_device(pdev); + if (rc) { + dev_warn(&pdev->dev, "failed to enable device.\n"); + return -ENODEV; + } + pci_set_master(pdev); /* Reset the controller with a PCI power-cycle or via doorbell */ rc = hpsa_kdump_hard_reset_controller(pdev); @@ -4533,10 +4541,11 @@ static int hpsa_init_reset_devices(struct pci_dev *pdev) * "performant mode". Or, it might be 640x, which can't reset * due to concerns about shared bbwc between 6402/6404 pair. */ - if (rc == -ENOTSUPP) - return rc; /* just try to do the kdump anyhow. */ - if (rc) - return -ENODEV; + if (rc) { + if (rc != -ENOTSUPP) /* just try to do the kdump anyhow. */ + rc = -ENODEV; + goto out_disable; + } /* Now try to get the controller to respond to a no-op */ dev_warn(&pdev->dev, "Waiting for controller to respond to no-op\n"); @@ -4547,7 +4556,11 @@ static int hpsa_init_reset_devices(struct pci_dev *pdev) dev_warn(&pdev->dev, "no-op failed%s\n", (i < 11 ? "; re-trying" : "")); } - return 0; + +out_disable: + + pci_disable_device(pdev); + return rc; } static int hpsa_allocate_cmd_pool(struct ctlr_info *h) @@ -4690,6 +4703,7 @@ static void hpsa_undo_allocations_after_kdump_soft_reset(struct ctlr_info *h) iounmap(h->transtable); if (h->cfgtable) iounmap(h->cfgtable); + pci_disable_device(h->pdev); pci_release_regions(h->pdev); kfree(h); } diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 3f5b56a..128dc2f 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -592,9 +592,10 @@ static void ipr_trc_hook(struct ipr_cmnd *ipr_cmd, { struct ipr_trace_entry *trace_entry; struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg; + unsigned int trace_index; - trace_entry = &ioa_cfg->trace[atomic_add_return - (1, &ioa_cfg->trace_index)%IPR_NUM_TRACE_ENTRIES]; + trace_index = atomic_add_return(1, &ioa_cfg->trace_index) & IPR_TRACE_INDEX_MASK; + trace_entry = &ioa_cfg->trace[trace_index]; trace_entry->time = jiffies; trace_entry->op_code = ipr_cmd->ioarcb.cmd_pkt.cdb[0]; trace_entry->type = type; @@ -683,6 +684,7 @@ static void ipr_init_ipr_cmnd(struct ipr_cmnd *ipr_cmd, ipr_reinit_ipr_cmnd(ipr_cmd); ipr_cmd->u.scratch = 0; ipr_cmd->sibling = NULL; + ipr_cmd->eh_comp = NULL; ipr_cmd->fast_done = fast_done; init_timer(&ipr_cmd->timer); } @@ -848,6 +850,8 @@ static void ipr_scsi_eh_done(struct ipr_cmnd *ipr_cmd) scsi_dma_unmap(ipr_cmd->scsi_cmd); scsi_cmd->scsi_done(scsi_cmd); + if (ipr_cmd->eh_comp) + complete(ipr_cmd->eh_comp); list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q); } @@ -1041,10 +1045,15 @@ static void ipr_send_blocking_cmd(struct ipr_cmnd *ipr_cmd, static int ipr_get_hrrq_index(struct ipr_ioa_cfg *ioa_cfg) { + unsigned int hrrq; + if (ioa_cfg->hrrq_num == 1) - return 0; - else - return (atomic_add_return(1, &ioa_cfg->hrrq_index) % (ioa_cfg->hrrq_num - 1)) + 1; + hrrq = 0; + else { + hrrq = atomic_add_return(1, &ioa_cfg->hrrq_index); + hrrq = (hrrq % (ioa_cfg->hrrq_num - 1)) + 1; + } + return hrrq; } /** @@ -4805,6 +4814,84 @@ static int ipr_slave_alloc(struct scsi_device *sdev) return rc; } +/** + * ipr_match_lun - Match function for specified LUN + * @ipr_cmd: ipr command struct + * @device: device to match (sdev) + * + * Returns: + * 1 if command matches sdev / 0 if command does not match sdev + **/ +static int ipr_match_lun(struct ipr_cmnd *ipr_cmd, void *device) +{ + if (ipr_cmd->scsi_cmd && ipr_cmd->scsi_cmd->device == device) + return 1; + return 0; +} + +/** + * ipr_wait_for_ops - Wait for matching commands to complete + * @ipr_cmd: ipr command struct + * @device: device to match (sdev) + * @match: match function to use + * + * Returns: + * SUCCESS / FAILED + **/ +static int ipr_wait_for_ops(struct ipr_ioa_cfg *ioa_cfg, void *device, + int (*match)(struct ipr_cmnd *, void *)) +{ + struct ipr_cmnd *ipr_cmd; + int wait; + unsigned long flags; + struct ipr_hrr_queue *hrrq; + signed long timeout = IPR_ABORT_TASK_TIMEOUT; + DECLARE_COMPLETION_ONSTACK(comp); + + ENTER; + do { + wait = 0; + + for_each_hrrq(hrrq, ioa_cfg) { + spin_lock_irqsave(hrrq->lock, flags); + list_for_each_entry(ipr_cmd, &hrrq->hrrq_pending_q, queue) { + if (match(ipr_cmd, device)) { + ipr_cmd->eh_comp = ∁ + wait++; + } + } + spin_unlock_irqrestore(hrrq->lock, flags); + } + + if (wait) { + timeout = wait_for_completion_timeout(&comp, timeout); + + if (!timeout) { + wait = 0; + + for_each_hrrq(hrrq, ioa_cfg) { + spin_lock_irqsave(hrrq->lock, flags); + list_for_each_entry(ipr_cmd, &hrrq->hrrq_pending_q, queue) { + if (match(ipr_cmd, device)) { + ipr_cmd->eh_comp = NULL; + wait++; + } + } + spin_unlock_irqrestore(hrrq->lock, flags); + } + + if (wait) + dev_err(&ioa_cfg->pdev->dev, "Timed out waiting for aborted commands\n"); + LEAVE; + return wait ? FAILED : SUCCESS; + } + } + } while (wait); + + LEAVE; + return SUCCESS; +} + static int ipr_eh_host_reset(struct scsi_cmnd *cmd) { struct ipr_ioa_cfg *ioa_cfg; @@ -5023,11 +5110,17 @@ static int __ipr_eh_dev_reset(struct scsi_cmnd *scsi_cmd) static int ipr_eh_dev_reset(struct scsi_cmnd *cmd) { int rc; + struct ipr_ioa_cfg *ioa_cfg; + + ioa_cfg = (struct ipr_ioa_cfg *) cmd->device->host->hostdata; spin_lock_irq(cmd->device->host->host_lock); rc = __ipr_eh_dev_reset(cmd); spin_unlock_irq(cmd->device->host->host_lock); + if (rc == SUCCESS) + rc = ipr_wait_for_ops(ioa_cfg, cmd->device, ipr_match_lun); + return rc; } @@ -5205,13 +5298,18 @@ static int ipr_eh_abort(struct scsi_cmnd *scsi_cmd) { unsigned long flags; int rc; + struct ipr_ioa_cfg *ioa_cfg; ENTER; + ioa_cfg = (struct ipr_ioa_cfg *) scsi_cmd->device->host->hostdata; + spin_lock_irqsave(scsi_cmd->device->host->host_lock, flags); rc = ipr_cancel_op(scsi_cmd); spin_unlock_irqrestore(scsi_cmd->device->host->host_lock, flags); + if (rc == SUCCESS) + rc = ipr_wait_for_ops(ioa_cfg, scsi_cmd->device, ipr_match_lun); LEAVE; return rc; } @@ -6087,21 +6185,23 @@ static void ipr_scsi_done(struct ipr_cmnd *ipr_cmd) struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg; struct scsi_cmnd *scsi_cmd = ipr_cmd->scsi_cmd; u32 ioasc = be32_to_cpu(ipr_cmd->s.ioasa.hdr.ioasc); - unsigned long hrrq_flags; + unsigned long lock_flags; scsi_set_resid(scsi_cmd, be32_to_cpu(ipr_cmd->s.ioasa.hdr.residual_data_len)); if (likely(IPR_IOASC_SENSE_KEY(ioasc) == 0)) { scsi_dma_unmap(scsi_cmd); - spin_lock_irqsave(ipr_cmd->hrrq->lock, hrrq_flags); + spin_lock_irqsave(ipr_cmd->hrrq->lock, lock_flags); list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q); scsi_cmd->scsi_done(scsi_cmd); - spin_unlock_irqrestore(ipr_cmd->hrrq->lock, hrrq_flags); + spin_unlock_irqrestore(ipr_cmd->hrrq->lock, lock_flags); } else { - spin_lock_irqsave(ipr_cmd->hrrq->lock, hrrq_flags); + spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); + spin_lock(&ipr_cmd->hrrq->_lock); ipr_erp_start(ioa_cfg, ipr_cmd); - spin_unlock_irqrestore(ipr_cmd->hrrq->lock, hrrq_flags); + spin_unlock(&ipr_cmd->hrrq->_lock); + spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); } } diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h index 9ce38a2..694ec20 100644 --- a/drivers/scsi/ipr.h +++ b/drivers/scsi/ipr.h @@ -264,7 +264,7 @@ #define IPR_RUNTIME_RESET 0x40000000 #define IPR_IPL_INIT_MIN_STAGE_TIME 5 -#define IPR_IPL_INIT_DEFAULT_STAGE_TIME 15 +#define IPR_IPL_INIT_DEFAULT_STAGE_TIME 30 #define IPR_IPL_INIT_STAGE_UNKNOWN 0x0 #define IPR_IPL_INIT_STAGE_TRANSOP 0xB0000000 #define IPR_IPL_INIT_STAGE_MASK 0xff000000 @@ -1459,6 +1459,7 @@ struct ipr_ioa_cfg { #define IPR_NUM_TRACE_INDEX_BITS 8 #define IPR_NUM_TRACE_ENTRIES (1 << IPR_NUM_TRACE_INDEX_BITS) +#define IPR_TRACE_INDEX_MASK (IPR_NUM_TRACE_ENTRIES - 1) #define IPR_TRACE_SIZE (sizeof(struct ipr_trace_entry) * IPR_NUM_TRACE_ENTRIES) char trace_start[8]; #define IPR_TRACE_START_LABEL "trace" @@ -1585,6 +1586,7 @@ struct ipr_cmnd { struct scsi_device *sdev; } u; + struct completion *eh_comp; struct ipr_hrr_queue *hrrq; struct ipr_ioa_cfg *ioa_cfg; }; diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c index 1b3a094..30f9ef0 100644 --- a/drivers/scsi/libfc/fc_exch.c +++ b/drivers/scsi/libfc/fc_exch.c @@ -733,8 +733,6 @@ static bool fc_invoke_resp(struct fc_exch *ep, struct fc_seq *sp, if (resp) { resp(sp, fp, arg); res = true; - } else if (!IS_ERR(fp)) { - fc_frame_free(fp); } spin_lock_bh(&ep->ex_lock); @@ -1596,7 +1594,8 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp) * If new exch resp handler is valid then call that * first. */ - fc_invoke_resp(ep, sp, fp); + if (!fc_invoke_resp(ep, sp, fp)) + fc_frame_free(fp); fc_exch_release(ep); return; @@ -1695,7 +1694,8 @@ static void fc_exch_abts_resp(struct fc_exch *ep, struct fc_frame *fp) fc_exch_hold(ep); if (!rc) fc_exch_delete(ep); - fc_invoke_resp(ep, sp, fp); + if (!fc_invoke_resp(ep, sp, fp)) + fc_frame_free(fp); if (has_rec) fc_exch_timer_set(ep, ep->r_a_tov); fc_exch_release(ep); diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c index 1d7e76e..ae6fc1a 100644 --- a/drivers/scsi/libfc/fc_fcp.c +++ b/drivers/scsi/libfc/fc_fcp.c @@ -1039,11 +1039,26 @@ restart: fc_fcp_pkt_hold(fsp); spin_unlock_irqrestore(&si->scsi_queue_lock, flags); - if (!fc_fcp_lock_pkt(fsp)) { + spin_lock_bh(&fsp->scsi_pkt_lock); + if (!(fsp->state & FC_SRB_COMPL)) { + fsp->state |= FC_SRB_COMPL; + /* + * TODO: dropping scsi_pkt_lock and then reacquiring + * again around fc_fcp_cleanup_cmd() is required, + * since fc_fcp_cleanup_cmd() calls into + * fc_seq_set_resp() and that func preempts cpu using + * schedule. May be schedule and related code should be + * removed instead of unlocking here to avoid scheduling + * while atomic bug. + */ + spin_unlock_bh(&fsp->scsi_pkt_lock); + fc_fcp_cleanup_cmd(fsp, error); + + spin_lock_bh(&fsp->scsi_pkt_lock); fc_io_compl(fsp); - fc_fcp_unlock_pkt(fsp); } + spin_unlock_bh(&fsp->scsi_pkt_lock); fc_fcp_pkt_release(fsp); spin_lock_irqsave(&si->scsi_queue_lock, flags); diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 4046241..4549986 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -717,11 +717,21 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, return NULL; } + if (data_size > ISCSI_DEF_MAX_RECV_SEG_LEN) { + iscsi_conn_printk(KERN_ERR, conn, "Invalid buffer len of %u for login task. Max len is %u\n", data_size, ISCSI_DEF_MAX_RECV_SEG_LEN); + return NULL; + } + task = conn->login_task; } else { if (session->state != ISCSI_STATE_LOGGED_IN) return NULL; + if (data_size != 0) { + iscsi_conn_printk(KERN_ERR, conn, "Can not send data buffer of len %u for op 0x%x\n", data_size, opcode); + return NULL; + } + BUG_ON(conn->c_stage == ISCSI_CONN_INITIAL_STAGE); BUG_ON(conn->c_stage == ISCSI_CONN_STOPPED); diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c index 62b58d3..60de662 100644 --- a/drivers/scsi/libsas/sas_discover.c +++ b/drivers/scsi/libsas/sas_discover.c @@ -500,6 +500,7 @@ static void sas_revalidate_domain(struct work_struct *work) struct sas_discovery_event *ev = to_sas_discovery_event(work); struct asd_sas_port *port = ev->port; struct sas_ha_struct *ha = port->ha; + struct domain_device *ddev = port->port_dev; /* prevent revalidation from finding sata links in recovery */ mutex_lock(&ha->disco_mutex); @@ -514,8 +515,9 @@ static void sas_revalidate_domain(struct work_struct *work) SAS_DPRINTK("REVALIDATING DOMAIN on port %d, pid:%d\n", port->id, task_pid_nr(current)); - if (port->port_dev) - res = sas_ex_revalidate_domain(port->port_dev); + if (ddev && (ddev->dev_type == SAS_FANOUT_EXPANDER_DEVICE || + ddev->dev_type == SAS_EDGE_EXPANDER_DEVICE)) + res = sas_ex_revalidate_domain(ddev); SAS_DPRINTK("done REVALIDATING DOMAIN on port %d, pid:%d, res 0x%x\n", port->id, task_pid_nr(current), res); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 8f580fd..ce21132 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -265,6 +265,16 @@ lpfc_sli4_eq_get(struct lpfc_queue *q) return NULL; q->hba_index = idx; + + /* + * insert barrier for instruction interlock : data from the hardware + * must have the valid bit checked before it can be copied and acted + * upon. Given what was seen in lpfc_sli4_cq_get() of speculative + * instructions allowing action on content before valid bit checked, + * add barrier here as well. May not be needed as "content" is a + * single 32-bit entity here (vs multi word structure for cq's). + */ + mb(); return eqe; } @@ -370,6 +380,17 @@ lpfc_sli4_cq_get(struct lpfc_queue *q) cqe = q->qe[q->hba_index].cqe; q->hba_index = idx; + + /* + * insert barrier for instruction interlock : data from the hardware + * must have the valid bit checked before it can be copied and acted + * upon. Speculative instructions were allowing a bcopy at the start + * of lpfc_sli4_fp_handle_wcqe(), which is called immediately + * after our return, to copy data before the valid bit check above + * was done. As such, some of the copied data was stale. The barrier + * ensures the check is before any data is copied. + */ + mb(); return cqe; } diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c index 816db12..52587ce 100644 --- a/drivers/scsi/megaraid.c +++ b/drivers/scsi/megaraid.c @@ -1967,7 +1967,7 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor) cmd->device->id, cmd->device->lun); if(list_empty(&adapter->pending_list)) - return FALSE; + return FAILED; list_for_each_safe(pos, next, &adapter->pending_list) { @@ -1990,7 +1990,7 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor) (aor==SCB_ABORT) ? "ABORTING":"RESET", scb->idx); - return FALSE; + return FAILED; } else { @@ -2015,12 +2015,12 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor) list_add_tail(SCSI_LIST(cmd), &adapter->completed_list); - return TRUE; + return SUCCESS; } } } - return FALSE; + return FAILED; } static inline int diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 3b7ad10..c80afde 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -953,7 +953,7 @@ megasas_issue_blocked_abort_cmd(struct megasas_instance *instance, cpu_to_le32(upper_32_bits(cmd_to_abort->frame_phys_addr)); cmd->sync_cmd = 1; - cmd->cmd_status = 0xFF; + cmd->cmd_status = ENODATA; instance->instancet->issue_dcmd(instance, cmd); diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index f655592..a1f04e3 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -92,6 +92,8 @@ megasas_enable_intr_fusion(struct megasas_instance *instance) { struct megasas_register_set __iomem *regs; regs = instance->reg_set; + + instance->mask_interrupts = 0; /* For Thunderbolt/Invader also clear intr on enable */ writel(~0, ®s->outbound_intr_status); readl(®s->outbound_intr_status); @@ -100,7 +102,6 @@ megasas_enable_intr_fusion(struct megasas_instance *instance) /* Dummy readl to force pci flush */ readl(®s->outbound_intr_mask); - instance->mask_interrupts = 0; } /** diff --git a/drivers/scsi/mpt2sas/mpt2sas_transport.c b/drivers/scsi/mpt2sas/mpt2sas_transport.c index 410f4a3..72f9c55 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_transport.c +++ b/drivers/scsi/mpt2sas/mpt2sas_transport.c @@ -1006,12 +1006,9 @@ mpt2sas_transport_update_links(struct MPT2SAS_ADAPTER *ioc, &mpt2sas_phy->remote_identify); _transport_add_phy_to_an_existing_port(ioc, sas_node, mpt2sas_phy, mpt2sas_phy->remote_identify.sas_address); - } else { + } else memset(&mpt2sas_phy->remote_identify, 0 , sizeof(struct sas_identify)); - _transport_del_phy_from_an_existing_port(ioc, sas_node, - mpt2sas_phy); - } if (mpt2sas_phy->phy) mpt2sas_phy->phy->negotiated_linkrate = diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c index 65170cb..55aa597 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_transport.c +++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c @@ -1003,12 +1003,9 @@ mpt3sas_transport_update_links(struct MPT3SAS_ADAPTER *ioc, &mpt3sas_phy->remote_identify); _transport_add_phy_to_an_existing_port(ioc, sas_node, mpt3sas_phy, mpt3sas_phy->remote_identify.sas_address); - } else { + } else memset(&mpt3sas_phy->remote_identify, 0 , sizeof(struct sas_identify)); - _transport_del_phy_from_an_existing_port(ioc, sas_node, - mpt3sas_phy); - } if (mpt3sas_phy->phy) mpt3sas_phy->phy->negotiated_linkrate = diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c index 6c1f223..4c0b8b4 100644 --- a/drivers/scsi/mvsas/mv_sas.c +++ b/drivers/scsi/mvsas/mv_sas.c @@ -441,14 +441,11 @@ static u32 mvs_get_ncq_tag(struct sas_task *task, u32 *tag) static int mvs_task_prep_ata(struct mvs_info *mvi, struct mvs_task_exec_info *tei) { - struct sas_ha_struct *sha = mvi->sas; struct sas_task *task = tei->task; struct domain_device *dev = task->dev; struct mvs_device *mvi_dev = dev->lldd_dev; struct mvs_cmd_hdr *hdr = tei->hdr; struct asd_sas_port *sas_port = dev->port; - struct sas_phy *sphy = dev->phy; - struct asd_sas_phy *sas_phy = sha->sas_phy[sphy->number]; struct mvs_slot_info *slot; void *buf_prd; u32 tag = tei->tag, hdr_tag; @@ -468,7 +465,7 @@ static int mvs_task_prep_ata(struct mvs_info *mvi, slot->tx = mvi->tx_prod; del_q = TXQ_MODE_I | tag | (TXQ_CMD_STP << TXQ_CMD_SHIFT) | - (MVS_PHY_ID << TXQ_PHY_SHIFT) | + ((sas_port->phy_mask & TXQ_PHY_MASK) << TXQ_PHY_SHIFT) | (mvi_dev->taskfileset << TXQ_SRS_SHIFT); mvi->tx[mvi->tx_prod] = cpu_to_le32(del_q); diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index 1f42662..b5f22a9 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -728,8 +728,6 @@ extern void qla8044_set_idc_dontreset(struct scsi_qla_host *ha); extern int qla8044_rd_direct(struct scsi_qla_host *vha, const uint32_t crb_reg); extern void qla8044_wr_direct(struct scsi_qla_host *vha, const uint32_t crb_reg, const uint32_t value); -extern inline void qla8044_set_qsnt_ready(struct scsi_qla_host *vha); -extern inline void qla8044_need_reset_handler(struct scsi_qla_host *vha); extern int qla8044_device_state_handler(struct scsi_qla_host *vha); extern void qla8044_clear_qsnt_ready(struct scsi_qla_host *vha); extern void qla8044_clear_drv_active(struct qla_hw_data *); diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 0a1dcb4..13f4bef 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -572,8 +572,9 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb) struct device_reg_2xxx __iomem *reg = &ha->iobase->isp; struct device_reg_24xx __iomem *reg24 = &ha->iobase->isp24; struct device_reg_82xx __iomem *reg82 = &ha->iobase->isp82; - uint32_t rscn_entry, host_pid; + uint32_t rscn_entry, host_pid, tmp_pid; unsigned long flags; + fc_port_t *fcport = NULL; /* Setup to process RIO completion. */ handle_cnt = 0; @@ -968,6 +969,20 @@ skip_rio: if (qla2x00_is_a_vp_did(vha, rscn_entry)) break; + /* + * Search for the rport related to this RSCN entry and mark it + * as lost. + */ + list_for_each_entry(fcport, &vha->vp_fcports, list) { + if (atomic_read(&fcport->state) != FCS_ONLINE) + continue; + tmp_pid = fcport->d_id.b24; + if (fcport->d_id.b24 == rscn_entry) { + qla2x00_mark_device_lost(vha, fcport, 0, 0); + break; + } + } + atomic_set(&vha->loop_down_timer, 0); vha->flags.management_server_logged_in = 0; diff --git a/drivers/scsi/qla2xxx/qla_nx2.c b/drivers/scsi/qla2xxx/qla_nx2.c index f60989d..24f69ac 100644 --- a/drivers/scsi/qla2xxx/qla_nx2.c +++ b/drivers/scsi/qla2xxx/qla_nx2.c @@ -146,7 +146,7 @@ qla8044_rmw_crb_reg(struct scsi_qla_host *vha, return; } -inline void +static inline void qla8044_set_qsnt_ready(struct scsi_qla_host *vha) { uint32_t qsnt_state; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 83cb612..23c1b0c 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3039,10 +3039,8 @@ qla2x00_unmap_iobases(struct qla_hw_data *ha) } static void -qla2x00_clear_drv_active(scsi_qla_host_t *vha) +qla2x00_clear_drv_active(struct qla_hw_data *ha) { - struct qla_hw_data *ha = vha->hw; - if (IS_QLA8044(ha)) { qla8044_idc_lock(ha); qla8044_clear_drv_active(ha); @@ -3111,7 +3109,7 @@ qla2x00_remove_one(struct pci_dev *pdev) scsi_host_put(base_vha->host); - qla2x00_clear_drv_active(base_vha); + qla2x00_clear_drv_active(ha); qla2x00_unmap_iobases(ha); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 0cb7307..2f264ac 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1382,12 +1382,10 @@ static inline void qlt_unmap_sg(struct scsi_qla_host *vha, static int qlt_check_reserve_free_req(struct scsi_qla_host *vha, uint32_t req_cnt) { - struct qla_hw_data *ha = vha->hw; - device_reg_t __iomem *reg = ha->iobase; uint32_t cnt; if (vha->req->cnt < (req_cnt + 2)) { - cnt = (uint16_t)RD_REG_DWORD(®->isp24.req_q_out); + cnt = (uint16_t)RD_REG_DWORD(vha->req->req_q_out); ql_dbg(ql_dbg_tgt, vha, 0xe00a, "Request ring circled: cnt=%d, vha->->ring_index=%d, " diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 788c4fe..1817f3f 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -707,7 +707,16 @@ static void tcm_qla2xxx_clear_nacl_from_fcport_map(struct qla_tgt_sess *sess) pr_debug("fc_rport domain: port_id 0x%06x\n", nacl->nport_id); node = btree_remove32(&lport->lport_fcport_map, nacl->nport_id); - WARN_ON(node && (node != se_nacl)); + if (WARN_ON(node && (node != se_nacl))) { + /* + * The nacl no longer matches what we think it should be. + * Most likely a new dynamic acl has been added while + * someone dropped the hardware lock. It clearly is a + * bug elsewhere, but this bit can't make things worse. + */ + btree_insert32(&lport->lport_fcport_map, nacl->nport_id, + node, GFP_ATOMIC); + } pr_debug("Removed from fcport_map: %p for WWNN: 0x%016LX, port_id: 0x%06x\n", se_nacl, nacl->nport_wwnn, nacl->nport_id); @@ -1506,7 +1515,7 @@ static int tcm_qla2xxx_check_initiator_node_acl( /* * Finally register the new FC Nexus with TCM */ - __transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess); + transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess); return 0; } diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index f969aca..262ab83 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -202,6 +202,7 @@ static struct { {"IOMEGA", "Io20S *F", NULL, BLIST_KEY}, {"INSITE", "Floptical F*8I", NULL, BLIST_KEY}, {"INSITE", "I325VM", NULL, BLIST_KEY}, + {"Intel", "Multi-Flex", NULL, BLIST_NO_RSOC}, {"iRiver", "iFP Mass Driver", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, {"LASOUND", "CDX7405", "3.10", BLIST_MAX5LUN | BLIST_SINGLELUN}, {"MATSHITA", "PD-1", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, @@ -210,6 +211,7 @@ static struct { {"Medion", "Flash XL MMC/SD", "2.6D", BLIST_FORCELUN}, {"MegaRAID", "LD", NULL, BLIST_FORCELUN}, {"MICROP", "4110", NULL, BLIST_NOTQ}, + {"MSFT", "Virtual HD", NULL, BLIST_NO_RSOC}, {"MYLEX", "DACARMRB", "*", BLIST_REPORTLUN2}, {"nCipher", "Fastness Crypto", NULL, BLIST_FORCELUN}, {"NAKAMICH", "MJ-4.8S", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, @@ -222,6 +224,7 @@ static struct { {"PIONEER", "CD-ROM DRM-602X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, {"PIONEER", "CD-ROM DRM-604X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, {"PIONEER", "CD-ROM DRM-624X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, + {"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC}, {"Promise", "", NULL, BLIST_SPARSELUN}, {"QUANTUM", "XP34301", "1071", BLIST_NOTQ}, {"REGAL", "CDC-4X", NULL, BLIST_MAX5LUN | BLIST_SINGLELUN}, diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index edb4d46..96b6664 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1984,8 +1984,10 @@ static void scsi_restart_operations(struct Scsi_Host *shost) * is no point trying to lock the door of an off-line device. */ shost_for_each_device(sdev, shost) { - if (scsi_device_online(sdev) && sdev->locked) + if (scsi_device_online(sdev) && sdev->was_reset && sdev->locked) { scsi_eh_lock_door(sdev); + sdev->was_reset = 0; + } } /* diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 62ec84b..719bd82 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -831,6 +831,14 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) scsi_next_command(cmd); return; } + } else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) { + /* + * Certain non BLOCK_PC requests are commands that don't + * actually transfer anything (FLUSH), so cannot use + * good_bytes != blk_rq_bytes(req) as the signal for an error. + * This sets the error explicitly for the problem case. + */ + error = __scsi_error_from_host_byte(cmd, result); } /* no bidi support for !REQ_TYPE_BLOCK_PC yet */ @@ -1250,9 +1258,11 @@ int scsi_prep_state_check(struct scsi_device *sdev, struct request *req) "rejecting I/O to dead device\n"); ret = BLKPREP_KILL; break; - case SDEV_QUIESCE: case SDEV_BLOCK: case SDEV_CREATED_BLOCK: + ret = BLKPREP_DEFER; + break; + case SDEV_QUIESCE: /* * If the devices is blocked we defer normal commands. */ diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c index 001e9ce..a59be67 100644 --- a/drivers/scsi/scsi_pm.c +++ b/drivers/scsi/scsi_pm.c @@ -149,15 +149,15 @@ static int sdev_runtime_suspend(struct device *dev) { const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; struct scsi_device *sdev = to_scsi_device(dev); - int err; + int err = 0; - err = blk_pre_runtime_suspend(sdev->request_queue); - if (err) - return err; - if (pm && pm->runtime_suspend) + if (pm && pm->runtime_suspend) { + err = blk_pre_runtime_suspend(sdev->request_queue); + if (err) + return err; err = pm->runtime_suspend(dev); - blk_post_runtime_suspend(sdev->request_queue, err); - + blk_post_runtime_suspend(sdev->request_queue, err); + } return err; } @@ -180,11 +180,11 @@ static int sdev_runtime_resume(struct device *dev) const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; int err = 0; - blk_pre_runtime_resume(sdev->request_queue); - if (pm && pm->runtime_resume) + if (pm && pm->runtime_resume) { + blk_pre_runtime_resume(sdev->request_queue); err = pm->runtime_resume(dev); - blk_post_runtime_resume(sdev->request_queue, err); - + blk_post_runtime_resume(sdev->request_queue, err); + } return err; } diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 4109530..054ec2c 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -922,6 +922,12 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, if (*bflags & BLIST_USE_10_BYTE_MS) sdev->use_10_for_ms = 1; + /* some devices don't like REPORT SUPPORTED OPERATION CODES + * and will simply timeout causing sd_mod init to take a very + * very long time */ + if (*bflags & BLIST_NO_RSOC) + sdev->no_report_opcodes = 1; + /* set the device running here so that slave configure * may do I/O */ ret = scsi_device_set_state(sdev, SDEV_RUNNING); @@ -950,7 +956,9 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, sdev->eh_timeout = SCSI_DEFAULT_EH_TIMEOUT; - if (*bflags & BLIST_SKIP_VPD_PAGES) + if (*bflags & BLIST_TRY_VPD_PAGES) + sdev->try_vpd_pages = 1; + else if (*bflags & BLIST_SKIP_VPD_PAGES) sdev->skip_vpd_pages = 1; transport_configure_device(&sdev->sdev_gendev); @@ -1236,6 +1244,12 @@ static void scsi_sequential_lun_scan(struct scsi_target *starget, max_dev_lun = min(8U, max_dev_lun); /* + * Stop scanning at 255 unless BLIST_SCSI3LUN + */ + if (!(bflags & BLIST_SCSI3LUN)) + max_dev_lun = min(256U, max_dev_lun); + + /* * We have already scanned LUN 0, so start at LUN 1. Keep scanning * until we reach the max, or no LUN is found and we are not * sparse_lun. diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c index d47ffc8..b85eaa0 100644 --- a/drivers/scsi/scsi_transport_srp.c +++ b/drivers/scsi/scsi_transport_srp.c @@ -397,6 +397,36 @@ static void srp_reconnect_work(struct work_struct *work) } } +/** + * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn() + * @shost: SCSI host for which to count the number of scsi_request_fn() callers. + * + * To do: add support for scsi-mq in this function. + */ +static int scsi_request_fn_active(struct Scsi_Host *shost) +{ + struct scsi_device *sdev; + struct request_queue *q; + int request_fn_active = 0; + + shost_for_each_device(sdev, shost) { + q = sdev->request_queue; + + spin_lock_irq(q->queue_lock); + request_fn_active += q->request_fn_active; + spin_unlock_irq(q->queue_lock); + } + + return request_fn_active; +} + +/* Wait until ongoing shost->hostt->queuecommand() calls have finished. */ +static void srp_wait_for_queuecommand(struct Scsi_Host *shost) +{ + while (scsi_request_fn_active(shost)) + msleep(20); +} + static void __rport_fail_io_fast(struct srp_rport *rport) { struct Scsi_Host *shost = rport_to_shost(rport); @@ -410,8 +440,10 @@ static void __rport_fail_io_fast(struct srp_rport *rport) /* Involve the LLD if possible to terminate all I/O on the rport. */ i = to_srp_internal(shost->transportt); - if (i->f->terminate_rport_io) + if (i->f->terminate_rport_io) { + srp_wait_for_queuecommand(shost); i->f->terminate_rport_io(rport); + } } /** @@ -473,7 +505,8 @@ static void __srp_start_tl_fail_timers(struct srp_rport *rport) if (delay > 0) queue_delayed_work(system_long_wq, &rport->reconnect_work, 1UL * delay * HZ); - if (srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) { + if ((fast_io_fail_tmo >= 0 || dev_loss_tmo >= 0) && + srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) { pr_debug("%s new state: %d\n", dev_name(&shost->shost_gendev), rport->state); scsi_target_block(&shost->shost_gendev); @@ -504,27 +537,6 @@ void srp_start_tl_fail_timers(struct srp_rport *rport) EXPORT_SYMBOL(srp_start_tl_fail_timers); /** - * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn() - * @shost: SCSI host for which to count the number of scsi_request_fn() callers. - */ -static int scsi_request_fn_active(struct Scsi_Host *shost) -{ - struct scsi_device *sdev; - struct request_queue *q; - int request_fn_active = 0; - - shost_for_each_device(sdev, shost) { - q = sdev->request_queue; - - spin_lock_irq(q->queue_lock); - request_fn_active += q->request_fn_active; - spin_unlock_irq(q->queue_lock); - } - - return request_fn_active; -} - -/** * srp_reconnect_rport() - reconnect to an SRP target port * @rport: SRP target port. * @@ -559,8 +571,7 @@ int srp_reconnect_rport(struct srp_rport *rport) if (res) goto out; scsi_target_block(&shost->shost_gendev); - while (scsi_request_fn_active(shost)) - msleep(20); + srp_wait_for_queuecommand(shost); res = rport->state != SRP_RPORT_LOST ? i->f->reconnect(rport) : -ENODEV; pr_debug("%s (state %d): transport.reconnect() returned %d\n", dev_name(&shost->shost_gendev), rport->state, res); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 36d1a23..a107064 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1599,6 +1599,7 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) { u64 start_lba = blk_rq_pos(scmd->request); u64 end_lba = blk_rq_pos(scmd->request) + (scsi_bufflen(scmd) / 512); + u64 factor = scmd->device->sector_size / 512; u64 bad_lba; int info_valid; /* @@ -1620,16 +1621,9 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) if (scsi_bufflen(scmd) <= scmd->device->sector_size) return 0; - if (scmd->device->sector_size < 512) { - /* only legitimate sector_size here is 256 */ - start_lba <<= 1; - end_lba <<= 1; - } else { - /* be careful ... don't want any overflows */ - unsigned int factor = scmd->device->sector_size / 512; - do_div(start_lba, factor); - do_div(end_lba, factor); - } + /* be careful ... don't want any overflows */ + do_div(start_lba, factor); + do_div(end_lba, factor); /* The bad lba was reported incorrectly, we have no idea where * the error is. @@ -2196,8 +2190,7 @@ got_data: if (sector_size != 512 && sector_size != 1024 && sector_size != 2048 && - sector_size != 4096 && - sector_size != 256) { + sector_size != 4096) { sd_printk(KERN_NOTICE, sdkp, "Unsupported sector size %d.\n", sector_size); /* @@ -2248,8 +2241,6 @@ got_data: sdkp->capacity <<= 2; else if (sector_size == 1024) sdkp->capacity <<= 1; - else if (sector_size == 256) - sdkp->capacity >>= 1; blk_queue_physical_block_size(sdp->request_queue, sdkp->physical_block_size); @@ -2686,6 +2677,11 @@ static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer) static int sd_try_extended_inquiry(struct scsi_device *sdp) { + /* Attempt VPD inquiry if the device blacklist explicitly calls + * for it. + */ + if (sdp->try_vpd_pages) + return 1; /* * Although VPD inquiries can go to SCSI-2 type devices, * some USB ones crash on receiving them, and the pages diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index df5e961..721d839 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -522,7 +522,7 @@ static ssize_t sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp) { sg_io_hdr_t *hp = &srp->header; - int err = 0; + int err = 0, err2; int len; if (count < SZ_SG_IO_HDR) { @@ -551,8 +551,8 @@ sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp) goto err_out; } err_out: - err = sg_finish_rem_req(srp); - return (0 == err) ? count : err; + err2 = sg_finish_rem_req(srp); + return err ? : err2 ? : count; } static ssize_t @@ -1694,6 +1694,9 @@ static int sg_start_req(Sg_request *srp, unsigned char *cmd) md->from_user = 0; } + if (unlikely(iov_count > UIO_MAXIOV)) + return -EINVAL; + if (iov_count) { int len, size = sizeof(struct sg_iovec) * iov_count; struct iovec *iov; diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index a1d6986..f310982 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -1262,9 +1262,9 @@ static int st_open(struct inode *inode, struct file *filp) spin_lock(&st_use_lock); STp->in_use = 0; spin_unlock(&st_use_lock); - scsi_tape_put(STp); if (resumed) scsi_autopm_put_device(STp->device); + scsi_tape_put(STp); return retval; } diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 9969fa1..3bb6646 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -330,17 +331,17 @@ static int storvsc_timeout = 180; static void storvsc_on_channel_callback(void *context); -/* - * In Hyper-V, each port/path/target maps to 1 scsi host adapter. In - * reality, the path/target is not used (ie always set to 0) so our - * scsi host adapter essentially has 1 bus with 1 target that contains - * up to 256 luns. - */ -#define STORVSC_MAX_LUNS_PER_TARGET 64 -#define STORVSC_MAX_TARGETS 1 -#define STORVSC_MAX_CHANNELS 1 +#define STORVSC_MAX_LUNS_PER_TARGET 255 +#define STORVSC_MAX_TARGETS 2 +#define STORVSC_MAX_CHANNELS 8 +#define STORVSC_FC_MAX_LUNS_PER_TARGET 255 +#define STORVSC_FC_MAX_TARGETS 128 +#define STORVSC_FC_MAX_CHANNELS 8 +#define STORVSC_IDE_MAX_LUNS_PER_TARGET 64 +#define STORVSC_IDE_MAX_TARGETS 1 +#define STORVSC_IDE_MAX_CHANNELS 1 struct storvsc_cmd_request { struct list_head entry; @@ -738,21 +739,22 @@ static unsigned int copy_to_bounce_buffer(struct scatterlist *orig_sgl, if (bounce_sgl[j].length == PAGE_SIZE) { /* full..move to next entry */ sg_kunmap_atomic(bounce_addr); + bounce_addr = 0; j++; + } - /* if we need to use another bounce buffer */ - if (srclen || i != orig_sgl_count - 1) - bounce_addr = sg_kmap_atomic(bounce_sgl,j); + /* if we need to use another bounce buffer */ + if (srclen && bounce_addr == 0) + bounce_addr = sg_kmap_atomic(bounce_sgl, j); - } else if (srclen == 0 && i == orig_sgl_count - 1) { - /* unmap the last bounce that is < PAGE_SIZE */ - sg_kunmap_atomic(bounce_addr); - } } sg_kunmap_atomic(src_addr - orig_sgl[i].offset); } + if (bounce_addr) + sg_kunmap_atomic(bounce_addr); + local_irq_restore(flags); return total_copied; @@ -1017,6 +1019,13 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, case ATA_12: set_host_byte(scmnd, DID_PASSTHROUGH); break; + /* + * On Some Windows hosts TEST_UNIT_READY command can return + * SRB_STATUS_ERROR, let the upper level code deal with it + * based on the sense information. + */ + case TEST_UNIT_READY: + break; default: set_host_byte(scmnd, DID_TARGET_FAILURE); } @@ -1518,6 +1527,16 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd) return SUCCESS; } +/* + * The host guarantees to respond to each command, although I/O latencies might + * be unbounded on Azure. Reset the timer unconditionally to give the host a + * chance to perform EH. + */ +static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd) +{ + return BLK_EH_RESET_TIMER; +} + static bool storvsc_scsi_cmd_ok(struct scsi_cmnd *scmnd) { bool allowed = true; @@ -1553,9 +1572,19 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) struct vmscsi_request *vm_srb; struct stor_mem_pools *memp = scmnd->device->hostdata; - if (!storvsc_scsi_cmd_ok(scmnd)) { - scmnd->scsi_done(scmnd); - return 0; + if (vmstor_current_major <= VMSTOR_WIN8_MAJOR) { + /* + * On legacy hosts filter unimplemented commands. + * Future hosts are expected to correctly handle + * unsupported commands. Furthermore, it is + * possible that some of the currently + * unsupported commands maybe supported in + * future versions of the host. + */ + if (!storvsc_scsi_cmd_ok(scmnd)) { + scmnd->scsi_done(scmnd); + return 0; + } } request_size = sizeof(struct storvsc_cmd_request); @@ -1580,26 +1609,23 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) vm_srb = &cmd_request->vstor_packet.vm_srb; vm_srb->win8_extension.time_out_value = 60; + vm_srb->win8_extension.srb_flags |= + (SRB_FLAGS_QUEUE_ACTION_ENABLE | + SRB_FLAGS_DISABLE_SYNCH_TRANSFER); /* Build the SRB */ switch (scmnd->sc_data_direction) { case DMA_TO_DEVICE: vm_srb->data_in = WRITE_TYPE; vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_OUT; - vm_srb->win8_extension.srb_flags |= - (SRB_FLAGS_QUEUE_ACTION_ENABLE | - SRB_FLAGS_DISABLE_SYNCH_TRANSFER); break; case DMA_FROM_DEVICE: vm_srb->data_in = READ_TYPE; vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_IN; - vm_srb->win8_extension.srb_flags |= - (SRB_FLAGS_QUEUE_ACTION_ENABLE | - SRB_FLAGS_DISABLE_SYNCH_TRANSFER); break; default: vm_srb->data_in = UNKNOWN_TYPE; - vm_srb->win8_extension.srb_flags = 0; + vm_srb->win8_extension.srb_flags |= SRB_FLAGS_NO_DATA_TRANSFER; break; } @@ -1664,13 +1690,12 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) if (ret == -EAGAIN) { /* no more space */ - if (cmd_request->bounce_sgl_count) { + if (cmd_request->bounce_sgl_count) destroy_bounce_buffer(cmd_request->bounce_sgl, cmd_request->bounce_sgl_count); - ret = SCSI_MLQUEUE_DEVICE_BUSY; - goto queue_error; - } + ret = SCSI_MLQUEUE_DEVICE_BUSY; + goto queue_error; } return 0; @@ -1687,11 +1712,11 @@ static struct scsi_host_template scsi_driver = { .bios_param = storvsc_get_chs, .queuecommand = storvsc_queuecommand, .eh_host_reset_handler = storvsc_host_reset_handler, + .eh_timed_out = storvsc_eh_timed_out, .slave_alloc = storvsc_device_alloc, .slave_destroy = storvsc_device_destroy, .slave_configure = storvsc_device_configure, - .cmd_per_lun = 1, - /* 64 max_queue * 1 target */ + .cmd_per_lun = 255, .can_queue = STORVSC_MAX_IO_REQUESTS*STORVSC_MAX_TARGETS, .this_id = -1, /* no use setting to 0 since ll_blk_rw reset it to 1 */ @@ -1743,19 +1768,25 @@ static int storvsc_probe(struct hv_device *device, * set state to properly communicate with the host. */ - if (vmbus_proto_version == VERSION_WIN8) { - sense_buffer_size = POST_WIN7_STORVSC_SENSE_BUFFER_SIZE; - vmscsi_size_delta = 0; - vmstor_current_major = VMSTOR_WIN8_MAJOR; - vmstor_current_minor = VMSTOR_WIN8_MINOR; - } else { + switch (vmbus_proto_version) { + case VERSION_WS2008: + case VERSION_WIN7: sense_buffer_size = PRE_WIN8_STORVSC_SENSE_BUFFER_SIZE; vmscsi_size_delta = sizeof(struct vmscsi_win8_extension); vmstor_current_major = VMSTOR_WIN7_MAJOR; vmstor_current_minor = VMSTOR_WIN7_MINOR; + break; + default: + sense_buffer_size = POST_WIN7_STORVSC_SENSE_BUFFER_SIZE; + vmscsi_size_delta = 0; + vmstor_current_major = VMSTOR_WIN8_MAJOR; + vmstor_current_minor = VMSTOR_WIN8_MINOR; + break; } - + if (dev_id->driver_data == SFC_GUID) + scsi_driver.can_queue = (STORVSC_MAX_IO_REQUESTS * + STORVSC_FC_MAX_TARGETS); host = scsi_host_alloc(&scsi_driver, sizeof(struct hv_host_device)); if (!host) @@ -1789,12 +1820,25 @@ static int storvsc_probe(struct hv_device *device, host_dev->path = stor_device->path_id; host_dev->target = stor_device->target_id; - /* max # of devices per target */ - host->max_lun = STORVSC_MAX_LUNS_PER_TARGET; - /* max # of targets per channel */ - host->max_id = STORVSC_MAX_TARGETS; - /* max # of channels */ - host->max_channel = STORVSC_MAX_CHANNELS - 1; + switch (dev_id->driver_data) { + case SFC_GUID: + host->max_lun = STORVSC_FC_MAX_LUNS_PER_TARGET; + host->max_id = STORVSC_FC_MAX_TARGETS; + host->max_channel = STORVSC_FC_MAX_CHANNELS - 1; + break; + + case SCSI_GUID: + host->max_lun = STORVSC_MAX_LUNS_PER_TARGET; + host->max_id = STORVSC_MAX_TARGETS; + host->max_channel = STORVSC_MAX_CHANNELS - 1; + break; + + default: + host->max_lun = STORVSC_IDE_MAX_LUNS_PER_TARGET; + host->max_id = STORVSC_IDE_MAX_TARGETS; + host->max_channel = STORVSC_IDE_MAX_CHANNELS - 1; + break; + } /* max cmd length */ host->max_cmd_len = STORVSC_MAX_CMD_LEN; diff --git a/drivers/scsi/sun3_NCR5380.c b/drivers/scsi/sun3_NCR5380.c index 636bbe0..fc57c8a 100644 --- a/drivers/scsi/sun3_NCR5380.c +++ b/drivers/scsi/sun3_NCR5380.c @@ -2597,15 +2597,15 @@ static void NCR5380_reselect (struct Scsi_Host *instance) * Purpose : abort a command * * Inputs : cmd - the struct scsi_cmnd to abort, code - code to set the - * host byte of the result field to, if zero DID_ABORTED is + * host byte of the result field to, if zero DID_ABORTED is * used. * - * Returns : 0 - success, -1 on failure. + * Returns : SUCCESS - success, FAILED on failure. * - * XXX - there is no way to abort the command that is currently - * connected, you have to wait for it to complete. If this is + * XXX - there is no way to abort the command that is currently + * connected, you have to wait for it to complete. If this is * a problem, we could implement longjmp() / setjmp(), setjmp() - * called where the loop started in NCR5380_main(). + * called where the loop started in NCR5380_main(). */ static int NCR5380_abort(struct scsi_cmnd *cmd) diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index 5d7b07f..5f8c6d2 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -781,17 +781,17 @@ static void atmel_spi_pdc_next_xfer(struct spi_master *master, (unsigned long long)xfer->rx_dma); } - /* REVISIT: We're waiting for ENDRX before we start the next + /* REVISIT: We're waiting for RXBUFF before we start the next * transfer because we need to handle some difficult timing - * issues otherwise. If we wait for ENDTX in one transfer and - * then starts waiting for ENDRX in the next, it's difficult - * to tell the difference between the ENDRX interrupt we're - * actually waiting for and the ENDRX interrupt of the + * issues otherwise. If we wait for TXBUFE in one transfer and + * then starts waiting for RXBUFF in the next, it's difficult + * to tell the difference between the RXBUFF interrupt we're + * actually waiting for and the RXBUFF interrupt of the * previous transfer. * * It should be doable, though. Just not now... */ - spi_writel(as, IER, SPI_BIT(ENDRX) | SPI_BIT(OVRES)); + spi_writel(as, IER, SPI_BIT(RXBUFF) | SPI_BIT(OVRES)); spi_writel(as, PTCR, SPI_BIT(TXTEN) | SPI_BIT(RXTEN)); } diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c index 6d207af..996e16d 100644 --- a/drivers/spi/spi-dw-mid.c +++ b/drivers/spi/spi-dw-mid.c @@ -89,7 +89,13 @@ err_exit: static void mid_spi_dma_exit(struct dw_spi *dws) { + if (!dws->dma_inited) + return; + + dmaengine_terminate_all(dws->txchan); dma_release_channel(dws->txchan); + + dmaengine_terminate_all(dws->rxchan); dma_release_channel(dws->rxchan); } @@ -136,7 +142,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change) txconf.dst_addr = dws->dma_addr; txconf.dst_maxburst = LNW_DMA_MSIZE_16; txconf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - txconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; + txconf.dst_addr_width = dws->dma_width; txconf.device_fc = false; txchan->device->device_control(txchan, DMA_SLAVE_CONFIG, @@ -159,7 +165,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change) rxconf.src_addr = dws->dma_addr; rxconf.src_maxburst = LNW_DMA_MSIZE_16; rxconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - rxconf.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; + rxconf.src_addr_width = dws->dma_width; rxconf.device_fc = false; rxchan->device->device_control(rxchan, DMA_SLAVE_CONFIG, @@ -216,7 +222,6 @@ int dw_spi_mid_init(struct dw_spi *dws) iounmap(clk_reg); dws->num_cs = 16; - dws->fifo_len = 40; /* FIFO has 40 words buffer */ #ifdef CONFIG_SPI_DW_MID_DMA dws->dma_priv = kzalloc(sizeof(struct mid_dma), GFP_KERNEL); diff --git a/drivers/spi/spi-dw-pci.c b/drivers/spi/spi-dw-pci.c index 3f3dc12..e149604 100644 --- a/drivers/spi/spi-dw-pci.c +++ b/drivers/spi/spi-dw-pci.c @@ -62,6 +62,8 @@ static int spi_pci_probe(struct pci_dev *pdev, if (ret) return ret; + dws->regs = pcim_iomap_table(pdev)[pci_bar]; + dws->bus_num = 0; dws->num_cs = 4; dws->irq = pdev->irq; diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c index e63d270..e543b80 100644 --- a/drivers/spi/spi-dw.c +++ b/drivers/spi/spi-dw.c @@ -394,9 +394,6 @@ static void pump_transfers(unsigned long data) chip = dws->cur_chip; spi = message->spi; - if (unlikely(!chip->clk_div)) - chip->clk_div = dws->max_freq / chip->speed_hz; - if (message->state == ERROR_STATE) { message->status = -EIO; goto early_exit; @@ -437,7 +434,7 @@ static void pump_transfers(unsigned long data) if (transfer->speed_hz) { speed = chip->speed_hz; - if (transfer->speed_hz != speed) { + if ((transfer->speed_hz != speed) || (!chip->clk_div)) { speed = transfer->speed_hz; if (speed > dws->max_freq) { printk(KERN_ERR "MRST SPI0: unsupported" @@ -659,7 +656,6 @@ static int dw_spi_setup(struct spi_device *spi) dev_err(&spi->dev, "No max speed HZ parameter\n"); return -EINVAL; } - chip->speed_hz = spi->max_speed_hz; chip->tmode = 0; /* Tx & Rx */ /* Default SPI mode is SCPOL = 0, SCPH = 0 */ diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index a253920..a5db6f9 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -45,7 +45,7 @@ #define SPI_TCR 0x08 -#define SPI_CTAR(x) (0x0c + (x * 4)) +#define SPI_CTAR(x) (0x0c + (((x) & 0x3) * 4)) #define SPI_CTAR_FMSZ(x) (((x) & 0x0000000f) << 27) #define SPI_CTAR_CPOL(x) ((x) << 26) #define SPI_CTAR_CPHA(x) ((x) << 25) @@ -69,7 +69,7 @@ #define SPI_PUSHR 0x34 #define SPI_PUSHR_CONT (1 << 31) -#define SPI_PUSHR_CTAS(x) (((x) & 0x00000007) << 28) +#define SPI_PUSHR_CTAS(x) (((x) & 0x00000003) << 28) #define SPI_PUSHR_EOQ (1 << 27) #define SPI_PUSHR_CTCNT (1 << 26) #define SPI_PUSHR_PCS(x) (((1 << x) & 0x0000003f) << 16) diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c index 119f7af..4dcb292 100644 --- a/drivers/spi/spi-fsl-spi.c +++ b/drivers/spi/spi-fsl-spi.c @@ -362,18 +362,28 @@ static int fsl_spi_bufs(struct spi_device *spi, struct spi_transfer *t, static void fsl_spi_do_one_msg(struct spi_message *m) { struct spi_device *spi = m->spi; - struct spi_transfer *t; + struct spi_transfer *t, *first; unsigned int cs_change; const int nsecs = 50; int status; - cs_change = 1; - status = 0; + /* Don't allow changes if CS is active */ + first = list_first_entry(&m->transfers, struct spi_transfer, + transfer_list); list_for_each_entry(t, &m->transfers, transfer_list) { - if (t->bits_per_word || t->speed_hz) { - /* Don't allow changes if CS is active */ + if ((first->bits_per_word != t->bits_per_word) || + (first->speed_hz != t->speed_hz)) { status = -EINVAL; + dev_err(&spi->dev, + "bits_per_word/speed_hz should be same for the same SPI transfer\n"); + return; + } + } + cs_change = 1; + status = -EINVAL; + list_for_each_entry(t, &m->transfers, transfer_list) { + if (t->bits_per_word || t->speed_hz) { if (cs_change) status = fsl_spi_setup_transfer(spi, t); if (status < 0) diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index a72127f..b0059e7 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -147,6 +147,7 @@ struct omap2_mcspi_cs { void __iomem *base; unsigned long phys; int word_len; + u16 mode; struct list_head node; /* Context save and restore shadow register */ u32 chconf0; @@ -320,7 +321,8 @@ static void omap2_mcspi_set_fifo(const struct spi_device *spi, disable_fifo: if (t->rx_buf != NULL) chconf &= ~OMAP2_MCSPI_CHCONF_FFER; - else + + if (t->tx_buf != NULL) chconf &= ~OMAP2_MCSPI_CHCONF_FFET; mcspi_write_chconf0(spi, chconf); @@ -899,6 +901,8 @@ static int omap2_mcspi_setup_transfer(struct spi_device *spi, mcspi_write_chconf0(spi, l); + cs->mode = spi->mode; + dev_dbg(&spi->dev, "setup: speed %d, sample %s edge, clk %s\n", OMAP2_MCSPI_MAX_FREQ >> div, (spi->mode & SPI_CPHA) ? "trailing" : "leading", @@ -971,6 +975,7 @@ static int omap2_mcspi_setup(struct spi_device *spi) return -ENOMEM; cs->base = mcspi->base + spi->chip_select * 0x14; cs->phys = mcspi->phys + spi->chip_select * 0x14; + cs->mode = 0; cs->chconf0 = 0; spi->controller_state = cs; /* Link this to context save list */ @@ -1051,6 +1056,16 @@ static void omap2_mcspi_work(struct omap2_mcspi *mcspi, struct spi_message *m) cs = spi->controller_state; cd = spi->controller_data; + /* + * The slave driver could have changed spi->mode in which case + * it will be different from cs->mode (the current hardware setup). + * If so, set par_override (even though its not a parity issue) so + * omap2_mcspi_setup_transfer will be called to configure the hardware + * with the correct mode on the first iteration of the loop below. + */ + if (spi->mode != cs->mode) + par_override = 1; + omap2_mcspi_set_enable(spi, 0); list_for_each_entry(t, &m->transfers, transfer_list) { if (t->tx_buf == NULL && t->rx_buf == NULL && t->len) { diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c index 7f2121f..977b061 100644 --- a/drivers/spi/spi-orion.c +++ b/drivers/spi/spi-orion.c @@ -404,8 +404,6 @@ static int orion_spi_probe(struct platform_device *pdev) struct resource *r; unsigned long tclk_hz; int status = 0; - const u32 *iprop; - int size; master = spi_alloc_master(&pdev->dev, sizeof(*spi)); if (master == NULL) { @@ -416,10 +414,10 @@ static int orion_spi_probe(struct platform_device *pdev) if (pdev->id != -1) master->bus_num = pdev->id; if (pdev->dev.of_node) { - iprop = of_get_property(pdev->dev.of_node, "cell-index", - &size); - if (iprop && size == sizeof(*iprop)) - master->bus_num = *iprop; + u32 cell_index; + if (!of_property_read_u32(pdev->dev.of_node, "cell-index", + &cell_index)) + master->bus_num = cell_index; } /* we support only mode 0, and no options */ diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c index 2789b45..fe091a8 100644 --- a/drivers/spi/spi-pl022.c +++ b/drivers/spi/spi-pl022.c @@ -503,12 +503,12 @@ static void giveback(struct pl022 *pl022) pl022->cur_msg = NULL; pl022->cur_transfer = NULL; pl022->cur_chip = NULL; - spi_finalize_current_message(pl022->master); /* disable the SPI/SSP operation */ writew((readw(SSP_CR1(pl022->virtbase)) & (~SSP_CR1_MASK_SSE)), SSP_CR1(pl022->virtbase)); + spi_finalize_current_message(pl022->master); } /** @@ -1075,7 +1075,7 @@ err_rxdesc: pl022->sgt_tx.nents, DMA_TO_DEVICE); err_tx_sgmap: dma_unmap_sg(rxchan->device->dev, pl022->sgt_rx.sgl, - pl022->sgt_tx.nents, DMA_FROM_DEVICE); + pl022->sgt_rx.nents, DMA_FROM_DEVICE); err_rx_sgmap: sg_free_table(&pl022->sgt_tx); err_alloc_tx_sg: diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index c702fc5..458a148 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -400,8 +400,8 @@ static void giveback(struct driver_data *drv_data) cs_deassert(drv_data); } - spi_finalize_current_message(drv_data->master); drv_data->cur_chip = NULL; + spi_finalize_current_message(drv_data->master); } static void reset_sccr1(struct driver_data *drv_data) @@ -1078,6 +1078,7 @@ static struct acpi_device_id pxa2xx_spi_acpi_match[] = { { "INT3430", 0 }, { "INT3431", 0 }, { "80860F0E", 0 }, + { "8086228E", 0 }, { }, }; MODULE_DEVICE_TABLE(acpi, pxa2xx_spi_acpi_match); @@ -1279,7 +1280,9 @@ static int pxa2xx_spi_suspend(struct device *dev) if (status != 0) return status; write_SSCR0(0, drv_data->ioaddr); - clk_disable_unprepare(ssp->clk); + + if (!pm_runtime_suspended(dev)) + clk_disable_unprepare(ssp->clk); return 0; } @@ -1293,7 +1296,8 @@ static int pxa2xx_spi_resume(struct device *dev) pxa2xx_spi_dma_resume(drv_data); /* Enable the SSP clock */ - clk_prepare_enable(ssp->clk); + if (!pm_runtime_suspended(dev)) + clk_prepare_enable(ssp->clk); /* Restore LPSS private register bits */ lpss_ssp_setup(drv_data); diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index fbf3b22..f3e3ae8 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -834,9 +834,6 @@ void spi_finalize_current_message(struct spi_master *master) spin_lock_irqsave(&master->queue_lock, flags); mesg = master->cur_msg; - master->cur_msg = NULL; - - queue_kthread_work(&master->kworker, &master->pump_messages); spin_unlock_irqrestore(&master->queue_lock, flags); if (master->cur_msg_prepared && master->unprepare_message) { @@ -846,13 +843,18 @@ void spi_finalize_current_message(struct spi_master *master) "failed to unprepare message: %d\n", ret); } } + + spin_lock_irqsave(&master->queue_lock, flags); + master->cur_msg = NULL; master->cur_msg_prepared = false; + queue_kthread_work(&master->kworker, &master->pump_messages); + spin_unlock_irqrestore(&master->queue_lock, flags); + + trace_spi_message_done(mesg); mesg->state = NULL; if (mesg->complete) mesg->complete(mesg->context); - - trace_spi_message_done(mesg); } EXPORT_SYMBOL_GPL(spi_finalize_current_message); diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index d7c6e36..2fe5b61 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -243,7 +243,10 @@ static int spidev_message(struct spidev_data *spidev, k_tmp->len = u_tmp->len; total += k_tmp->len; - if (total > bufsiz) { + /* Check total length of transfers. Also check each + * transfer length to avoid arithmetic overflow. + */ + if (total > bufsiz || k_tmp->len > bufsiz) { status = -EMSGSIZE; goto done; } diff --git a/drivers/staging/comedi/comedi_compat32.c b/drivers/staging/comedi/comedi_compat32.c index 1e9da40..5287810 100644 --- a/drivers/staging/comedi/comedi_compat32.c +++ b/drivers/staging/comedi/comedi_compat32.c @@ -262,7 +262,7 @@ static int compat_cmd(struct file *file, unsigned long arg) { struct comedi_cmd __user *cmd; struct comedi32_cmd_struct __user *cmd32; - int rc; + int rc, err; cmd32 = compat_ptr(arg); cmd = compat_alloc_user_space(sizeof(*cmd)); @@ -271,7 +271,15 @@ static int compat_cmd(struct file *file, unsigned long arg) if (rc) return rc; - return translated_ioctl(file, COMEDI_CMD, (unsigned long)cmd); + rc = translated_ioctl(file, COMEDI_CMD, (unsigned long)cmd); + if (rc == -EAGAIN) { + /* Special case: copy cmd back to user. */ + err = put_compat_cmd(cmd32, cmd); + if (err) + rc = err; + } + + return rc; } /* Handle 32-bit COMEDI_CMDTEST ioctl. */ diff --git a/drivers/staging/comedi/drivers/adl_pci7x3x.c b/drivers/staging/comedi/drivers/adl_pci7x3x.c index 6f622b4..927edd1 100644 --- a/drivers/staging/comedi/drivers/adl_pci7x3x.c +++ b/drivers/staging/comedi/drivers/adl_pci7x3x.c @@ -113,8 +113,20 @@ static int adl_pci7x3x_do_insn_bits(struct comedi_device *dev, { unsigned long reg = (unsigned long)s->private; - if (comedi_dio_update_state(s, data)) - outl(s->state, dev->iobase + reg); + if (comedi_dio_update_state(s, data)) { + unsigned int val = s->state; + + if (s->n_chan == 16) { + /* + * It seems the PCI-7230 needs the 16-bit DO state + * to be shifted left by 16 bits before being written + * to the 32-bit register. Set the value in both + * halves of the register to be sure. + */ + val |= val << 16; + } + outl(val, dev->iobase + reg); + } data[1] = s->state; diff --git a/drivers/staging/comedi/drivers/cb_pcidas64.c b/drivers/staging/comedi/drivers/cb_pcidas64.c index 4fff173..3d1cb5b 100644 --- a/drivers/staging/comedi/drivers/cb_pcidas64.c +++ b/drivers/staging/comedi/drivers/cb_pcidas64.c @@ -441,6 +441,29 @@ static const struct comedi_lrange ai_ranges_64xx = { } }; +static const uint8_t ai_range_code_64xx[8] = { + 0x0, 0x1, 0x2, 0x3, /* bipolar 10, 5, 2,5, 1.25 */ + 0x8, 0x9, 0xa, 0xb /* unipolar 10, 5, 2.5, 1.25 */ +}; + +/* analog input ranges for 64-Mx boards */ +static const struct comedi_lrange ai_ranges_64_mx = { + 7, { + BIP_RANGE(5), + BIP_RANGE(2.5), + BIP_RANGE(1.25), + BIP_RANGE(0.625), + UNI_RANGE(5), + UNI_RANGE(2.5), + UNI_RANGE(1.25) + } +}; + +static const uint8_t ai_range_code_64_mx[7] = { + 0x0, 0x1, 0x2, 0x3, /* bipolar 5, 2.5, 1.25, 0.625 */ + 0x9, 0xa, 0xb /* unipolar 5, 2.5, 1.25 */ +}; + /* analog input ranges for 60xx boards */ static const struct comedi_lrange ai_ranges_60xx = { 4, { @@ -451,6 +474,10 @@ static const struct comedi_lrange ai_ranges_60xx = { } }; +static const uint8_t ai_range_code_60xx[4] = { + 0x0, 0x1, 0x4, 0x7 /* bipolar 10, 5, 0.5, 0.05 */ +}; + /* analog input ranges for 6030, etc boards */ static const struct comedi_lrange ai_ranges_6030 = { 14, { @@ -471,6 +498,11 @@ static const struct comedi_lrange ai_ranges_6030 = { } }; +static const uint8_t ai_range_code_6030[14] = { + 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, /* bip 10, 5, 2, 1, 0.5, 0.2, 0.1 */ + 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf /* uni 10, 5, 2, 1, 0.5, 0.2, 0.1 */ +}; + /* analog input ranges for 6052, etc boards */ static const struct comedi_lrange ai_ranges_6052 = { 15, { @@ -492,6 +524,11 @@ static const struct comedi_lrange ai_ranges_6052 = { } }; +static const uint8_t ai_range_code_6052[15] = { + 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, /* bipolar 10 ... 0.05 */ + 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf /* unipolar 10 ... 0.1 */ +}; + /* analog input ranges for 4020 board */ static const struct comedi_lrange ai_ranges_4020 = { 2, { @@ -595,6 +632,7 @@ struct pcidas64_board { int ai_bits; /* analog input resolution */ int ai_speed; /* fastest conversion period in ns */ const struct comedi_lrange *ai_range_table; + const uint8_t *ai_range_code; int ao_nchan; /* number of analog out channels */ int ao_bits; /* analog output resolution */ int ao_scan_speed; /* analog output scan speed */ @@ -653,6 +691,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 10000, .layout = LAYOUT_64XX, .ai_range_table = &ai_ranges_64xx, + .ai_range_code = ai_range_code_64xx, .ao_range_table = &ao_ranges_64xx, .ao_range_code = ao_range_code_64xx, .ai_fifo = &ai_fifo_64xx, @@ -668,6 +707,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 10000, .layout = LAYOUT_64XX, .ai_range_table = &ai_ranges_64xx, + .ai_range_code = ai_range_code_64xx, .ao_range_table = &ao_ranges_64xx, .ao_range_code = ao_range_code_64xx, .ai_fifo = &ai_fifo_64xx, @@ -682,7 +722,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_bits = 16, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ao_range_table = &ao_ranges_64xx, .ao_range_code = ao_range_code_64xx, .ai_fifo = &ai_fifo_64xx, @@ -697,7 +738,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_bits = 16, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ao_range_table = &ao_ranges_64xx, .ao_range_code = ao_range_code_64xx, .ai_fifo = &ai_fifo_64xx, @@ -712,7 +754,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_bits = 16, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ao_range_table = &ao_ranges_64xx, .ao_range_code = ao_range_code_64xx, .ai_fifo = &ai_fifo_64xx, @@ -727,6 +770,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_bits = 16, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ao_range_table = &range_bipolar10, .ao_range_code = ao_range_code_60xx, .ai_fifo = &ai_fifo_60xx, @@ -742,6 +786,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 100000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ao_range_table = &range_bipolar10, .ao_range_code = ao_range_code_60xx, .ai_fifo = &ai_fifo_60xx, @@ -756,6 +801,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 100000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ao_range_table = &range_bipolar10, .ao_range_code = ao_range_code_60xx, .ai_fifo = &ai_fifo_60xx, @@ -771,6 +817,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 100000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ao_range_table = &range_bipolar10, .ao_range_code = ao_range_code_60xx, .ai_fifo = &ai_fifo_60xx, @@ -786,6 +833,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 10000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6030, + .ai_range_code = ai_range_code_6030, .ao_range_table = &ao_ranges_6030, .ao_range_code = ao_range_code_6030, .ai_fifo = &ai_fifo_60xx, @@ -801,6 +849,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 10000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6030, + .ai_range_code = ai_range_code_6030, .ao_range_table = &ao_ranges_6030, .ao_range_code = ao_range_code_6030, .ai_fifo = &ai_fifo_60xx, @@ -814,6 +863,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 0, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6030, + .ai_range_code = ai_range_code_6030, .ai_fifo = &ai_fifo_60xx, .has_8255 = 0, }, @@ -825,6 +875,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 0, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6030, + .ai_range_code = ai_range_code_6030, .ai_fifo = &ai_fifo_60xx, .has_8255 = 0, }, @@ -837,6 +888,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 0, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ai_fifo = &ai_fifo_60xx, .has_8255 = 0, }, @@ -850,6 +902,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 100000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ao_range_table = &range_bipolar10, .ao_range_code = ao_range_code_60xx, .ai_fifo = &ai_fifo_60xx, @@ -865,6 +918,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 100000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ao_range_table = &range_bipolar10, .ao_range_code = ao_range_code_60xx, .ai_fifo = &ai_fifo_60xx, @@ -880,6 +934,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 1000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6052, + .ai_range_code = ai_range_code_6052, .ao_range_table = &ao_ranges_6030, .ao_range_code = ao_range_code_6030, .ai_fifo = &ai_fifo_60xx, @@ -895,6 +950,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 3333, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6052, + .ai_range_code = ai_range_code_6052, .ao_range_table = &ao_ranges_6030, .ao_range_code = ao_range_code_6030, .ai_fifo = &ai_fifo_60xx, @@ -910,6 +966,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 1000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6052, + .ai_range_code = ai_range_code_6052, .ao_range_table = &ao_ranges_6030, .ao_range_code = ao_range_code_6030, .ai_fifo = &ai_fifo_60xx, @@ -925,6 +982,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 1000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6052, + .ai_range_code = ai_range_code_6052, .ao_range_table = &ao_ranges_6030, .ao_range_code = ao_range_code_6030, .ai_fifo = &ai_fifo_60xx, @@ -959,6 +1017,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 10000, .layout = LAYOUT_64XX, .ai_range_table = &ai_ranges_64xx, + .ai_range_code = ai_range_code_64xx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -970,7 +1029,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 0, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -982,7 +1042,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 0, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -994,7 +1055,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 0, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -1006,7 +1068,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 2, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -1018,7 +1081,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 2, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -1030,7 +1094,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 2, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -1127,45 +1192,8 @@ static unsigned int ai_range_bits_6xxx(const struct comedi_device *dev, unsigned int range_index) { const struct pcidas64_board *thisboard = comedi_board(dev); - const struct comedi_krange *range = - &thisboard->ai_range_table->range[range_index]; - unsigned int bits = 0; - switch (range->max) { - case 10000000: - bits = 0x000; - break; - case 5000000: - bits = 0x100; - break; - case 2000000: - case 2500000: - bits = 0x200; - break; - case 1000000: - case 1250000: - bits = 0x300; - break; - case 500000: - bits = 0x400; - break; - case 200000: - case 250000: - bits = 0x500; - break; - case 100000: - bits = 0x600; - break; - case 50000: - bits = 0x700; - break; - default: - comedi_error(dev, "bug! in ai_range_bits_6xxx"); - break; - } - if (range->min == 0) - bits += 0x900; - return bits; + return thisboard->ai_range_code[range_index] << 8; } static unsigned int hw_revision(const struct comedi_device *dev, diff --git a/drivers/staging/et131x/et131x.c b/drivers/staging/et131x/et131x.c index e516bb6..907aa30 100644 --- a/drivers/staging/et131x/et131x.c +++ b/drivers/staging/et131x/et131x.c @@ -1422,22 +1422,16 @@ static int et131x_mii_read(struct et131x_adapter *adapter, u8 reg, u16 *value) * @reg: the register to read * @value: 16-bit value to write */ -static int et131x_mii_write(struct et131x_adapter *adapter, u8 reg, u16 value) +static int et131x_mii_write(struct et131x_adapter *adapter, u8 addr, u8 reg, + u16 value) { struct mac_regs __iomem *mac = &adapter->regs->mac; - struct phy_device *phydev = adapter->phydev; int status = 0; - u8 addr; u32 delay = 0; u32 mii_addr; u32 mii_cmd; u32 mii_indicator; - if (!phydev) - return -EIO; - - addr = phydev->addr; - /* Save a local copy of the registers we are dealing with so we can * set them back */ @@ -1632,17 +1626,7 @@ static int et131x_mdio_write(struct mii_bus *bus, int phy_addr, struct net_device *netdev = bus->priv; struct et131x_adapter *adapter = netdev_priv(netdev); - return et131x_mii_write(adapter, reg, value); -} - -static int et131x_mdio_reset(struct mii_bus *bus) -{ - struct net_device *netdev = bus->priv; - struct et131x_adapter *adapter = netdev_priv(netdev); - - et131x_mii_write(adapter, MII_BMCR, BMCR_RESET); - - return 0; + return et131x_mii_write(adapter, phy_addr, reg, value); } /* et1310_phy_power_switch - PHY power control @@ -1657,18 +1641,20 @@ static int et131x_mdio_reset(struct mii_bus *bus) static void et1310_phy_power_switch(struct et131x_adapter *adapter, bool down) { u16 data; + struct phy_device *phydev = adapter->phydev; et131x_mii_read(adapter, MII_BMCR, &data); data &= ~BMCR_PDOWN; if (down) data |= BMCR_PDOWN; - et131x_mii_write(adapter, MII_BMCR, data); + et131x_mii_write(adapter, phydev->addr, MII_BMCR, data); } /* et131x_xcvr_init - Init the phy if we are setting it into force mode */ static void et131x_xcvr_init(struct et131x_adapter *adapter) { u16 lcr2; + struct phy_device *phydev = adapter->phydev; /* Set the LED behavior such that LED 1 indicates speed (off = * 10Mbits, blink = 100Mbits, on = 1000Mbits) and LED 2 indicates @@ -1689,7 +1675,7 @@ static void et131x_xcvr_init(struct et131x_adapter *adapter) else lcr2 |= (LED_VAL_LINKON << LED_TXRX_SHIFT); - et131x_mii_write(adapter, PHY_LED_2, lcr2); + et131x_mii_write(adapter, phydev->addr, PHY_LED_2, lcr2); } } @@ -3638,14 +3624,14 @@ static void et131x_adjust_link(struct net_device *netdev) et131x_mii_read(adapter, PHY_MPHY_CONTROL_REG, ®ister18); - et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG, - register18 | 0x4); - et131x_mii_write(adapter, PHY_INDEX_REG, + et131x_mii_write(adapter, phydev->addr, + PHY_MPHY_CONTROL_REG, register18 | 0x4); + et131x_mii_write(adapter, phydev->addr, PHY_INDEX_REG, register18 | 0x8402); - et131x_mii_write(adapter, PHY_DATA_REG, + et131x_mii_write(adapter, phydev->addr, PHY_DATA_REG, register18 | 511); - et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG, - register18); + et131x_mii_write(adapter, phydev->addr, + PHY_MPHY_CONTROL_REG, register18); } et1310_config_flow_control(adapter); @@ -3657,7 +3643,8 @@ static void et131x_adjust_link(struct net_device *netdev) et131x_mii_read(adapter, PHY_CONFIG, ®); reg &= ~ET_PHY_CONFIG_TX_FIFO_DEPTH; reg |= ET_PHY_CONFIG_FIFO_DEPTH_32; - et131x_mii_write(adapter, PHY_CONFIG, reg); + et131x_mii_write(adapter, phydev->addr, PHY_CONFIG, + reg); } et131x_set_rx_dma_timer(adapter); @@ -3670,14 +3657,14 @@ static void et131x_adjust_link(struct net_device *netdev) et131x_mii_read(adapter, PHY_MPHY_CONTROL_REG, ®ister18); - et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG, - register18 | 0x4); - et131x_mii_write(adapter, PHY_INDEX_REG, - register18 | 0x8402); - et131x_mii_write(adapter, PHY_DATA_REG, - register18 | 511); - et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG, - register18); + et131x_mii_write(adapter, phydev->addr, + PHY_MPHY_CONTROL_REG, register18 | 0x4); + et131x_mii_write(adapter, phydev->addr, + PHY_INDEX_REG, register18 | 0x8402); + et131x_mii_write(adapter, phydev->addr, + PHY_DATA_REG, register18 | 511); + et131x_mii_write(adapter, phydev->addr, + PHY_MPHY_CONTROL_REG, register18); } /* Free the packets being actively sent & stopped */ @@ -4646,10 +4633,6 @@ static int et131x_pci_setup(struct pci_dev *pdev, /* Copy address into the net_device struct */ memcpy(netdev->dev_addr, adapter->addr, ETH_ALEN); - /* Init variable for counting how long we do not have link status */ - adapter->boot_coma = 0; - et1310_disable_phy_coma(adapter); - rc = -ENOMEM; /* Setup the mii_bus struct */ @@ -4665,7 +4648,6 @@ static int et131x_pci_setup(struct pci_dev *pdev, adapter->mii_bus->priv = netdev; adapter->mii_bus->read = et131x_mdio_read; adapter->mii_bus->write = et131x_mdio_write; - adapter->mii_bus->reset = et131x_mdio_reset; adapter->mii_bus->irq = kmalloc_array(PHY_MAX_ADDR, sizeof(int), GFP_KERNEL); if (!adapter->mii_bus->irq) @@ -4689,6 +4671,10 @@ static int et131x_pci_setup(struct pci_dev *pdev, /* Setup et1310 as per the documentation */ et131x_adapter_setup(adapter); + /* Init variable for counting how long we do not have link status */ + adapter->boot_coma = 0; + et1310_disable_phy_coma(adapter); + /* We can enable interrupts now * * NOTE - Because registration of interrupt handler is done in the diff --git a/drivers/staging/gdm724x/gdm_mux.c b/drivers/staging/gdm724x/gdm_mux.c index 2fa3a5a..f2e6599 100644 --- a/drivers/staging/gdm724x/gdm_mux.c +++ b/drivers/staging/gdm724x/gdm_mux.c @@ -158,7 +158,7 @@ static int up_to_host(struct mux_rx *r) unsigned int start_flag; unsigned int payload_size; unsigned short packet_type; - int dummy_cnt; + int total_len; u32 packet_size_sum = r->offset; int index; int ret = TO_HOST_INVALID_PACKET; @@ -175,10 +175,10 @@ static int up_to_host(struct mux_rx *r) break; } - dummy_cnt = ALIGN(MUX_HEADER_SIZE + payload_size, 4); + total_len = ALIGN(MUX_HEADER_SIZE + payload_size, 4); if (len - packet_size_sum < - MUX_HEADER_SIZE + payload_size + dummy_cnt) { + total_len) { pr_err("invalid payload : %d %d %04x\n", payload_size, len, packet_type); break; @@ -201,7 +201,7 @@ static int up_to_host(struct mux_rx *r) break; } - packet_size_sum += MUX_HEADER_SIZE + payload_size + dummy_cnt; + packet_size_sum += total_len; if (len - packet_size_sum <= MUX_HEADER_SIZE + 2) { ret = r->callback(NULL, 0, @@ -359,7 +359,6 @@ static int gdm_mux_send(void *priv_dev, void *data, int len, int tty_index, struct mux_pkt_header *mux_header; struct mux_tx *t = NULL; static u32 seq_num = 1; - int dummy_cnt; int total_len; int ret; unsigned long flags; @@ -372,9 +371,7 @@ static int gdm_mux_send(void *priv_dev, void *data, int len, int tty_index, spin_lock_irqsave(&mux_dev->write_lock, flags); - dummy_cnt = ALIGN(MUX_HEADER_SIZE + len, 4); - - total_len = len + MUX_HEADER_SIZE + dummy_cnt; + total_len = ALIGN(MUX_HEADER_SIZE + len, 4); t = alloc_mux_tx(total_len); if (!t) { @@ -390,7 +387,8 @@ static int gdm_mux_send(void *priv_dev, void *data, int len, int tty_index, mux_header->packet_type = __cpu_to_le16(packet_type[tty_index]); memcpy(t->buf+MUX_HEADER_SIZE, data, len); - memset(t->buf+MUX_HEADER_SIZE+len, 0, dummy_cnt); + memset(t->buf+MUX_HEADER_SIZE+len, 0, total_len - MUX_HEADER_SIZE - + len); t->len = total_len; t->callback = cb; diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c index 9ec1df9..27e1a6e 100644 --- a/drivers/staging/iio/adc/mxs-lradc.c +++ b/drivers/staging/iio/adc/mxs-lradc.c @@ -214,11 +214,17 @@ struct mxs_lradc { unsigned long is_divided; /* - * Touchscreen LRADC channels receives a private slot in the CTRL4 - * register, the slot #7. Therefore only 7 slots instead of 8 in the - * CTRL4 register can be mapped to LRADC channels when using the - * touchscreen. - * + * When the touchscreen is enabled, we give it two private virtual + * channels: #6 and #7. This means that only 6 virtual channels (instead + * of 8) will be available for buffered capture. + */ +#define TOUCHSCREEN_VCHANNEL1 7 +#define TOUCHSCREEN_VCHANNEL2 6 +#define BUFFER_VCHANS_LIMITED 0x3f +#define BUFFER_VCHANS_ALL 0xff + u8 buffer_vchans; + + /* * Furthermore, certain LRADC channels are shared between touchscreen * and/or touch-buttons and generic LRADC block. Therefore when using * either of these, these channels are not available for the regular @@ -342,6 +348,9 @@ struct mxs_lradc { #define LRADC_CTRL4 0x140 #define LRADC_CTRL4_LRADCSELECT_MASK(n) (0xf << ((n) * 4)) #define LRADC_CTRL4_LRADCSELECT_OFFSET(n) ((n) * 4) +#define LRADC_CTRL4_LRADCSELECT(n, x) \ + (((x) << LRADC_CTRL4_LRADCSELECT_OFFSET(n)) & \ + LRADC_CTRL4_LRADCSELECT_MASK(n)) #define LRADC_RESOLUTION 12 #define LRADC_SINGLE_SAMPLE_MASK ((1 << LRADC_RESOLUTION) - 1) @@ -423,6 +432,14 @@ static bool mxs_lradc_check_touch_event(struct mxs_lradc *lradc) LRADC_STATUS_TOUCH_DETECT_RAW); } +static void mxs_lradc_map_channel(struct mxs_lradc *lradc, unsigned vch, + unsigned ch) +{ + mxs_lradc_reg_clear(lradc, LRADC_CTRL4_LRADCSELECT_MASK(vch), + LRADC_CTRL4); + mxs_lradc_reg_set(lradc, LRADC_CTRL4_LRADCSELECT(vch, ch), LRADC_CTRL4); +} + static void mxs_lradc_setup_ts_channel(struct mxs_lradc *lradc, unsigned ch) { /* @@ -450,12 +467,8 @@ static void mxs_lradc_setup_ts_channel(struct mxs_lradc *lradc, unsigned ch) LRADC_DELAY_DELAY(lradc->over_sample_delay - 1), LRADC_DELAY(3)); - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(2) | - LRADC_CTRL1_LRADC_IRQ(3) | LRADC_CTRL1_LRADC_IRQ(4) | - LRADC_CTRL1_LRADC_IRQ(5), LRADC_CTRL1); + mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(ch), LRADC_CTRL1); - /* wake us again, when the complete conversion is done */ - mxs_lradc_reg_set(lradc, LRADC_CTRL1_LRADC_IRQ_EN(ch), LRADC_CTRL1); /* * after changing the touchscreen plates setting * the signals need some initial time to settle. Start the @@ -508,12 +521,8 @@ static void mxs_lradc_setup_ts_pressure(struct mxs_lradc *lradc, unsigned ch1, LRADC_DELAY_DELAY(lradc->over_sample_delay - 1), LRADC_DELAY(3)); - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(2) | - LRADC_CTRL1_LRADC_IRQ(3) | LRADC_CTRL1_LRADC_IRQ(4) | - LRADC_CTRL1_LRADC_IRQ(5), LRADC_CTRL1); + mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(ch2), LRADC_CTRL1); - /* wake us again, when the conversions are done */ - mxs_lradc_reg_set(lradc, LRADC_CTRL1_LRADC_IRQ_EN(ch2), LRADC_CTRL1); /* * after changing the touchscreen plates setting * the signals need some initial time to settle. Start the @@ -578,36 +587,6 @@ static unsigned mxs_lradc_read_ts_pressure(struct mxs_lradc *lradc, #define TS_CH_XM 4 #define TS_CH_YM 5 -static int mxs_lradc_read_ts_channel(struct mxs_lradc *lradc) -{ - u32 reg; - int val; - - reg = readl(lradc->base + LRADC_CTRL1); - - /* only channels 3 to 5 are of interest here */ - if (reg & LRADC_CTRL1_LRADC_IRQ(TS_CH_YP)) { - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ_EN(TS_CH_YP) | - LRADC_CTRL1_LRADC_IRQ(TS_CH_YP), LRADC_CTRL1); - val = mxs_lradc_read_raw_channel(lradc, TS_CH_YP); - } else if (reg & LRADC_CTRL1_LRADC_IRQ(TS_CH_XM)) { - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ_EN(TS_CH_XM) | - LRADC_CTRL1_LRADC_IRQ(TS_CH_XM), LRADC_CTRL1); - val = mxs_lradc_read_raw_channel(lradc, TS_CH_XM); - } else if (reg & LRADC_CTRL1_LRADC_IRQ(TS_CH_YM)) { - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ_EN(TS_CH_YM) | - LRADC_CTRL1_LRADC_IRQ(TS_CH_YM), LRADC_CTRL1); - val = mxs_lradc_read_raw_channel(lradc, TS_CH_YM); - } else { - return -EIO; - } - - mxs_lradc_reg_wrt(lradc, 0, LRADC_DELAY(2)); - mxs_lradc_reg_wrt(lradc, 0, LRADC_DELAY(3)); - - return val; -} - /* * YP(open)--+-------------+ * | |--+ @@ -651,7 +630,8 @@ static void mxs_lradc_prepare_x_pos(struct mxs_lradc *lradc) mxs_lradc_reg_set(lradc, mxs_lradc_drive_x_plate(lradc), LRADC_CTRL0); lradc->cur_plate = LRADC_SAMPLE_X; - mxs_lradc_setup_ts_channel(lradc, TS_CH_YP); + mxs_lradc_map_channel(lradc, TOUCHSCREEN_VCHANNEL1, TS_CH_YP); + mxs_lradc_setup_ts_channel(lradc, TOUCHSCREEN_VCHANNEL1); } /* @@ -672,7 +652,8 @@ static void mxs_lradc_prepare_y_pos(struct mxs_lradc *lradc) mxs_lradc_reg_set(lradc, mxs_lradc_drive_y_plate(lradc), LRADC_CTRL0); lradc->cur_plate = LRADC_SAMPLE_Y; - mxs_lradc_setup_ts_channel(lradc, TS_CH_XM); + mxs_lradc_map_channel(lradc, TOUCHSCREEN_VCHANNEL1, TS_CH_XM); + mxs_lradc_setup_ts_channel(lradc, TOUCHSCREEN_VCHANNEL1); } /* @@ -693,7 +674,10 @@ static void mxs_lradc_prepare_pressure(struct mxs_lradc *lradc) mxs_lradc_reg_set(lradc, mxs_lradc_drive_pressure(lradc), LRADC_CTRL0); lradc->cur_plate = LRADC_SAMPLE_PRESSURE; - mxs_lradc_setup_ts_pressure(lradc, TS_CH_XP, TS_CH_YM); + mxs_lradc_map_channel(lradc, TOUCHSCREEN_VCHANNEL1, TS_CH_YM); + mxs_lradc_map_channel(lradc, TOUCHSCREEN_VCHANNEL2, TS_CH_XP); + mxs_lradc_setup_ts_pressure(lradc, TOUCHSCREEN_VCHANNEL2, + TOUCHSCREEN_VCHANNEL1); } static void mxs_lradc_enable_touch_detection(struct mxs_lradc *lradc) @@ -706,6 +690,19 @@ static void mxs_lradc_enable_touch_detection(struct mxs_lradc *lradc) mxs_lradc_reg_set(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, LRADC_CTRL1); } +static void mxs_lradc_start_touch_event(struct mxs_lradc *lradc) +{ + mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, + LRADC_CTRL1); + mxs_lradc_reg_set(lradc, + LRADC_CTRL1_LRADC_IRQ_EN(TOUCHSCREEN_VCHANNEL1), LRADC_CTRL1); + /* + * start with the Y-pos, because it uses nearly the same plate + * settings like the touch detection + */ + mxs_lradc_prepare_y_pos(lradc); +} + static void mxs_lradc_report_ts_event(struct mxs_lradc *lradc) { input_report_abs(lradc->ts_input, ABS_X, lradc->ts_x_pos); @@ -723,10 +720,12 @@ static void mxs_lradc_complete_touch_event(struct mxs_lradc *lradc) * start a dummy conversion to burn time to settle the signals * note: we are not interested in the conversion's value */ - mxs_lradc_reg_wrt(lradc, 0, LRADC_CH(5)); - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(5), LRADC_CTRL1); - mxs_lradc_reg_set(lradc, LRADC_CTRL1_LRADC_IRQ_EN(5), LRADC_CTRL1); - mxs_lradc_reg_wrt(lradc, LRADC_DELAY_TRIGGER(1 << 5) | + mxs_lradc_reg_wrt(lradc, 0, LRADC_CH(TOUCHSCREEN_VCHANNEL1)); + mxs_lradc_reg_clear(lradc, + LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL1) | + LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL2), LRADC_CTRL1); + mxs_lradc_reg_wrt(lradc, + LRADC_DELAY_TRIGGER(1 << TOUCHSCREEN_VCHANNEL1) | LRADC_DELAY_KICK | LRADC_DELAY_DELAY(10), /* waste 5 ms */ LRADC_DELAY(2)); } @@ -758,59 +757,45 @@ static void mxs_lradc_finish_touch_event(struct mxs_lradc *lradc, bool valid) /* if it is released, wait for the next touch via IRQ */ lradc->cur_plate = LRADC_TOUCH; - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ, LRADC_CTRL1); + mxs_lradc_reg_wrt(lradc, 0, LRADC_DELAY(2)); + mxs_lradc_reg_wrt(lradc, 0, LRADC_DELAY(3)); + mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ | + LRADC_CTRL1_LRADC_IRQ_EN(TOUCHSCREEN_VCHANNEL1) | + LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL1), LRADC_CTRL1); mxs_lradc_reg_set(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, LRADC_CTRL1); } /* touchscreen's state machine */ static void mxs_lradc_handle_touch(struct mxs_lradc *lradc) { - int val; - switch (lradc->cur_plate) { case LRADC_TOUCH: - /* - * start with the Y-pos, because it uses nearly the same plate - * settings like the touch detection - */ - if (mxs_lradc_check_touch_event(lradc)) { - mxs_lradc_reg_clear(lradc, - LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, - LRADC_CTRL1); - mxs_lradc_prepare_y_pos(lradc); - } + if (mxs_lradc_check_touch_event(lradc)) + mxs_lradc_start_touch_event(lradc); mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ, LRADC_CTRL1); return; case LRADC_SAMPLE_Y: - val = mxs_lradc_read_ts_channel(lradc); - if (val < 0) { - mxs_lradc_enable_touch_detection(lradc); /* re-start */ - return; - } - lradc->ts_y_pos = val; + lradc->ts_y_pos = mxs_lradc_read_raw_channel(lradc, + TOUCHSCREEN_VCHANNEL1); mxs_lradc_prepare_x_pos(lradc); return; case LRADC_SAMPLE_X: - val = mxs_lradc_read_ts_channel(lradc); - if (val < 0) { - mxs_lradc_enable_touch_detection(lradc); /* re-start */ - return; - } - lradc->ts_x_pos = val; + lradc->ts_x_pos = mxs_lradc_read_raw_channel(lradc, + TOUCHSCREEN_VCHANNEL1); mxs_lradc_prepare_pressure(lradc); return; case LRADC_SAMPLE_PRESSURE: - lradc->ts_pressure = - mxs_lradc_read_ts_pressure(lradc, TS_CH_XP, TS_CH_YM); + lradc->ts_pressure = mxs_lradc_read_ts_pressure(lradc, + TOUCHSCREEN_VCHANNEL2, + TOUCHSCREEN_VCHANNEL1); mxs_lradc_complete_touch_event(lradc); return; case LRADC_SAMPLE_VALID: - val = mxs_lradc_read_ts_channel(lradc); /* ignore the value */ mxs_lradc_finish_touch_event(lradc, 1); break; } @@ -842,9 +827,9 @@ static int mxs_lradc_read_single(struct iio_dev *iio_dev, int chan, int *val) * used if doing raw sampling. */ if (lradc->soc == IMX28_LRADC) - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_MX28_LRADC_IRQ_EN_MASK, + mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ_EN(0), LRADC_CTRL1); - mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0); + mxs_lradc_reg_clear(lradc, 0x1, LRADC_CTRL0); /* Enable / disable the divider per requirement */ if (test_bit(chan, &lradc->is_divided)) @@ -1091,9 +1076,8 @@ static void mxs_lradc_disable_ts(struct mxs_lradc *lradc) { /* stop all interrupts from firing */ mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN | - LRADC_CTRL1_LRADC_IRQ_EN(2) | LRADC_CTRL1_LRADC_IRQ_EN(3) | - LRADC_CTRL1_LRADC_IRQ_EN(4) | LRADC_CTRL1_LRADC_IRQ_EN(5), - LRADC_CTRL1); + LRADC_CTRL1_LRADC_IRQ_EN(TOUCHSCREEN_VCHANNEL1) | + LRADC_CTRL1_LRADC_IRQ_EN(TOUCHSCREEN_VCHANNEL2), LRADC_CTRL1); /* Power-down touchscreen touch-detect circuitry. */ mxs_lradc_reg_clear(lradc, mxs_lradc_plate_mask(lradc), LRADC_CTRL0); @@ -1159,25 +1143,30 @@ static irqreturn_t mxs_lradc_handle_irq(int irq, void *data) struct iio_dev *iio = data; struct mxs_lradc *lradc = iio_priv(iio); unsigned long reg = readl(lradc->base + LRADC_CTRL1); + uint32_t clr_irq = mxs_lradc_irq_mask(lradc); const uint32_t ts_irq_mask = LRADC_CTRL1_TOUCH_DETECT_IRQ | - LRADC_CTRL1_LRADC_IRQ(2) | - LRADC_CTRL1_LRADC_IRQ(3) | - LRADC_CTRL1_LRADC_IRQ(4) | - LRADC_CTRL1_LRADC_IRQ(5); + LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL1) | + LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL2); if (!(reg & mxs_lradc_irq_mask(lradc))) return IRQ_NONE; - if (lradc->use_touchscreen && (reg & ts_irq_mask)) + if (lradc->use_touchscreen && (reg & ts_irq_mask)) { mxs_lradc_handle_touch(lradc); + /* Make sure we don't clear the next conversion's interrupt. */ + clr_irq &= ~(LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL1) | + LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL2)); + } - if (iio_buffer_enabled(iio)) - iio_trigger_poll(iio->trig, iio_get_time_ns()); - else if (reg & LRADC_CTRL1_LRADC_IRQ(0)) + if (iio_buffer_enabled(iio)) { + if (reg & lradc->buffer_vchans) + iio_trigger_poll(iio->trig, iio_get_time_ns()); + } else if (reg & LRADC_CTRL1_LRADC_IRQ(0)) { complete(&lradc->completion); + } - mxs_lradc_reg_clear(lradc, reg & mxs_lradc_irq_mask(lradc), LRADC_CTRL1); + mxs_lradc_reg_clear(lradc, reg & clr_irq, LRADC_CTRL1); return IRQ_HANDLED; } @@ -1288,9 +1277,10 @@ static int mxs_lradc_buffer_preenable(struct iio_dev *iio) } if (lradc->soc == IMX28_LRADC) - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_MX28_LRADC_IRQ_EN_MASK, - LRADC_CTRL1); - mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0); + mxs_lradc_reg_clear(lradc, + lradc->buffer_vchans << LRADC_CTRL1_LRADC_IRQ_EN_OFFSET, + LRADC_CTRL1); + mxs_lradc_reg_clear(lradc, lradc->buffer_vchans, LRADC_CTRL0); for_each_set_bit(chan, iio->active_scan_mask, LRADC_MAX_TOTAL_CHANS) { ctrl4_set |= chan << LRADC_CTRL4_LRADCSELECT_OFFSET(ofs); @@ -1323,10 +1313,11 @@ static int mxs_lradc_buffer_postdisable(struct iio_dev *iio) mxs_lradc_reg_clear(lradc, LRADC_DELAY_TRIGGER_LRADCS_MASK | LRADC_DELAY_KICK, LRADC_DELAY(0)); - mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0); + mxs_lradc_reg_clear(lradc, lradc->buffer_vchans, LRADC_CTRL0); if (lradc->soc == IMX28_LRADC) - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_MX28_LRADC_IRQ_EN_MASK, - LRADC_CTRL1); + mxs_lradc_reg_clear(lradc, + lradc->buffer_vchans << LRADC_CTRL1_LRADC_IRQ_EN_OFFSET, + LRADC_CTRL1); kfree(lradc->buffer); mutex_unlock(&lradc->lock); @@ -1352,7 +1343,7 @@ static bool mxs_lradc_validate_scan_mask(struct iio_dev *iio, if (lradc->use_touchbutton) rsvd_chans++; if (lradc->use_touchscreen) - rsvd_chans++; + rsvd_chans += 2; /* Test for attempts to map channels with special mode of operation. */ if (bitmap_intersects(mask, &rsvd_mask, LRADC_MAX_TOTAL_CHANS)) @@ -1412,6 +1403,13 @@ static const struct iio_chan_spec mxs_lradc_chan_spec[] = { .channel = 8, .scan_type = {.sign = 'u', .realbits = 18, .storagebits = 32,}, }, + /* Hidden channel to keep indexes */ + { + .type = IIO_TEMP, + .indexed = 1, + .scan_index = -1, + .channel = 9, + }, MXS_ADC_CHAN(10, IIO_VOLTAGE), /* VDDIO */ MXS_ADC_CHAN(11, IIO_VOLTAGE), /* VTH */ MXS_ADC_CHAN(12, IIO_VOLTAGE), /* VDDA */ @@ -1563,6 +1561,11 @@ static int mxs_lradc_probe(struct platform_device *pdev) touch_ret = mxs_lradc_probe_touchscreen(lradc, node); + if (touch_ret == 0) + lradc->buffer_vchans = BUFFER_VCHANS_LIMITED; + else + lradc->buffer_vchans = BUFFER_VCHANS_ALL; + /* Grab all IRQ sources */ for (i = 0; i < of_cfg->irq_count; i++) { lradc->irq[i] = platform_get_irq(pdev, i); diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index 2b96665..97d4b3f 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -115,6 +115,7 @@ static const struct iio_chan_spec ad5933_channels[] = { .channel = 0, .info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED), .address = AD5933_REG_TEMP_DATA, + .scan_index = -1, .scan_type = { .sign = 's', .realbits = 14, @@ -124,9 +125,7 @@ static const struct iio_chan_spec ad5933_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 0, - .extend_name = "real_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "real", .address = AD5933_REG_REAL_DATA, .scan_index = 0, .scan_type = { @@ -138,9 +137,7 @@ static const struct iio_chan_spec ad5933_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 0, - .extend_name = "imag_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "imag", .address = AD5933_REG_IMAG_DATA, .scan_index = 1, .scan_type = { @@ -748,14 +745,14 @@ static int ad5933_probe(struct i2c_client *client, indio_dev->name = id->name; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = ad5933_channels; - indio_dev->num_channels = 1; /* only register temp0_input */ + indio_dev->num_channels = ARRAY_SIZE(ad5933_channels); ret = ad5933_register_ring_funcs_and_init(indio_dev); if (ret) goto error_disable_reg; - /* skip temp0_input, register in0_(real|imag)_raw */ - ret = iio_buffer_register(indio_dev, &ad5933_channels[1], 2); + ret = iio_buffer_register(indio_dev, ad5933_channels, + ARRAY_SIZE(ad5933_channels)); if (ret) goto error_unreg_ring; diff --git a/drivers/staging/iio/meter/ade7758.h b/drivers/staging/iio/meter/ade7758.h index 0731820..e8c98cf 100644 --- a/drivers/staging/iio/meter/ade7758.h +++ b/drivers/staging/iio/meter/ade7758.h @@ -119,7 +119,6 @@ struct ade7758_state { u8 *tx; u8 *rx; struct mutex buf_lock; - const struct iio_chan_spec *ade7758_ring_channels; struct spi_transfer ring_xfer[4]; struct spi_message ring_msg; /* diff --git a/drivers/staging/iio/meter/ade7758_core.c b/drivers/staging/iio/meter/ade7758_core.c index cba183e..94d9914 100644 --- a/drivers/staging/iio/meter/ade7758_core.c +++ b/drivers/staging/iio/meter/ade7758_core.c @@ -630,9 +630,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 0, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_A, AD7758_VOLTAGE), .scan_index = 0, .scan_type = { @@ -644,9 +641,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_CURRENT, .indexed = 1, .channel = 0, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_A, AD7758_CURRENT), .scan_index = 1, .scan_type = { @@ -658,9 +652,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 0, - .extend_name = "apparent_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "apparent", .address = AD7758_WT(AD7758_PHASE_A, AD7758_APP_PWR), .scan_index = 2, .scan_type = { @@ -672,9 +664,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 0, - .extend_name = "active_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "active", .address = AD7758_WT(AD7758_PHASE_A, AD7758_ACT_PWR), .scan_index = 3, .scan_type = { @@ -686,9 +676,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 0, - .extend_name = "reactive_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "reactive", .address = AD7758_WT(AD7758_PHASE_A, AD7758_REACT_PWR), .scan_index = 4, .scan_type = { @@ -700,9 +688,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 1, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_B, AD7758_VOLTAGE), .scan_index = 5, .scan_type = { @@ -714,9 +699,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_CURRENT, .indexed = 1, .channel = 1, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_B, AD7758_CURRENT), .scan_index = 6, .scan_type = { @@ -728,9 +710,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 1, - .extend_name = "apparent_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "apparent", .address = AD7758_WT(AD7758_PHASE_B, AD7758_APP_PWR), .scan_index = 7, .scan_type = { @@ -742,9 +722,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 1, - .extend_name = "active_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "active", .address = AD7758_WT(AD7758_PHASE_B, AD7758_ACT_PWR), .scan_index = 8, .scan_type = { @@ -756,9 +734,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 1, - .extend_name = "reactive_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "reactive", .address = AD7758_WT(AD7758_PHASE_B, AD7758_REACT_PWR), .scan_index = 9, .scan_type = { @@ -770,9 +746,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 2, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_C, AD7758_VOLTAGE), .scan_index = 10, .scan_type = { @@ -784,9 +757,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_CURRENT, .indexed = 1, .channel = 2, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_C, AD7758_CURRENT), .scan_index = 11, .scan_type = { @@ -798,9 +768,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 2, - .extend_name = "apparent_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "apparent", .address = AD7758_WT(AD7758_PHASE_C, AD7758_APP_PWR), .scan_index = 12, .scan_type = { @@ -812,9 +780,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 2, - .extend_name = "active_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "active", .address = AD7758_WT(AD7758_PHASE_C, AD7758_ACT_PWR), .scan_index = 13, .scan_type = { @@ -826,9 +792,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 2, - .extend_name = "reactive_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "reactive", .address = AD7758_WT(AD7758_PHASE_C, AD7758_REACT_PWR), .scan_index = 14, .scan_type = { @@ -869,13 +833,14 @@ static int ade7758_probe(struct spi_device *spi) goto error_free_rx; } st->us = spi; - st->ade7758_ring_channels = &ade7758_channels[0]; mutex_init(&st->buf_lock); indio_dev->name = spi->dev.driver->name; indio_dev->dev.parent = &spi->dev; indio_dev->info = &ade7758_info; indio_dev->modes = INDIO_DIRECT_MODE; + indio_dev->channels = ade7758_channels; + indio_dev->num_channels = ARRAY_SIZE(ade7758_channels); ret = ade7758_configure_ring(indio_dev); if (ret) diff --git a/drivers/staging/iio/meter/ade7758_ring.c b/drivers/staging/iio/meter/ade7758_ring.c index c0accf8..6e90064 100644 --- a/drivers/staging/iio/meter/ade7758_ring.c +++ b/drivers/staging/iio/meter/ade7758_ring.c @@ -85,17 +85,16 @@ static irqreturn_t ade7758_trigger_handler(int irq, void *p) **/ static int ade7758_ring_preenable(struct iio_dev *indio_dev) { - struct ade7758_state *st = iio_priv(indio_dev); unsigned channel; - if (!bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength)) + if (bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength)) return -EINVAL; channel = find_first_bit(indio_dev->active_scan_mask, indio_dev->masklength); ade7758_write_waveform_type(&indio_dev->dev, - st->ade7758_ring_channels[channel].address); + indio_dev->channels[channel].address); return 0; } diff --git a/drivers/staging/iio/meter/ade7758_trigger.c b/drivers/staging/iio/meter/ade7758_trigger.c index 7a94ddd..8c4f289 100644 --- a/drivers/staging/iio/meter/ade7758_trigger.c +++ b/drivers/staging/iio/meter/ade7758_trigger.c @@ -85,7 +85,7 @@ int ade7758_probe_trigger(struct iio_dev *indio_dev) ret = iio_trigger_register(st->trig); /* select default trigger */ - indio_dev->trig = st->trig; + indio_dev->trig = iio_trigger_get(st->trig); if (ret) goto error_free_irq; diff --git a/drivers/staging/imx-drm/ipuv3-plane.c b/drivers/staging/imx-drm/ipuv3-plane.c index 34b642a..c70f173 100644 --- a/drivers/staging/imx-drm/ipuv3-plane.c +++ b/drivers/staging/imx-drm/ipuv3-plane.c @@ -277,7 +277,8 @@ static void ipu_plane_dpms(struct ipu_plane *ipu_plane, int mode) ipu_idmac_put(ipu_plane->ipu_ch); ipu_dmfc_put(ipu_plane->dmfc); - ipu_dp_put(ipu_plane->dp); + if (ipu_plane->dp) + ipu_dp_put(ipu_plane->dp); } } diff --git a/drivers/staging/lustre/lustre/Kconfig b/drivers/staging/lustre/lustre/Kconfig index 209e4c7..4f65ba1 100644 --- a/drivers/staging/lustre/lustre/Kconfig +++ b/drivers/staging/lustre/lustre/Kconfig @@ -57,4 +57,5 @@ config LUSTRE_TRANSLATE_ERRNOS config LUSTRE_LLITE_LLOOP tristate "Lustre virtual block device" depends on LUSTRE_FS && BLOCK + depends on !PPC_64K_PAGES && !ARM64_64K_PAGES default m diff --git a/drivers/staging/lustre/lustre/llite/dcache.c b/drivers/staging/lustre/lustre/llite/dcache.c index cbd663e..19405ed 100644 --- a/drivers/staging/lustre/lustre/llite/dcache.c +++ b/drivers/staging/lustre/lustre/llite/dcache.c @@ -278,7 +278,7 @@ void ll_invalidate_aliases(struct inode *inode) inode->i_ino, inode->i_generation, inode); ll_lock_dcache(inode); - ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { + ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_u.d_alias) { CDEBUG(D_DENTRY, "dentry in drop %.*s (%p) parent %p " "inode %p flags %d\n", dentry->d_name.len, dentry->d_name.name, dentry, dentry->d_parent, diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c index 6cfdb9e..5ae562e 100644 --- a/drivers/staging/lustre/lustre/llite/llite_lib.c +++ b/drivers/staging/lustre/lustre/llite/llite_lib.c @@ -678,7 +678,7 @@ void lustre_dump_dentry(struct dentry *dentry, int recur) return; list_for_each(tmp, &dentry->d_subdirs) { - struct dentry *d = list_entry(tmp, struct dentry, d_u.d_child); + struct dentry *d = list_entry(tmp, struct dentry, d_child); lustre_dump_dentry(d, recur - 1); } } diff --git a/drivers/staging/lustre/lustre/llite/namei.c b/drivers/staging/lustre/lustre/llite/namei.c index fc8d264..8e9a9e9 100644 --- a/drivers/staging/lustre/lustre/llite/namei.c +++ b/drivers/staging/lustre/lustre/llite/namei.c @@ -175,14 +175,14 @@ static void ll_invalidate_negative_children(struct inode *dir) struct ll_d_hlist_node *p; ll_lock_dcache(dir); - ll_d_hlist_for_each_entry(dentry, p, &dir->i_dentry, d_alias) { + ll_d_hlist_for_each_entry(dentry, p, &dir->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!list_empty(&dentry->d_subdirs)) { struct dentry *child; list_for_each_entry_safe(child, tmp_subdir, &dentry->d_subdirs, - d_u.d_child) { + d_child) { if (child->d_inode == NULL) d_lustre_invalidate(child, 1); } @@ -364,7 +364,7 @@ static struct dentry *ll_find_alias(struct inode *inode, struct dentry *dentry) discon_alias = invalid_alias = NULL; ll_lock_dcache(inode); - ll_d_hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { + ll_d_hlist_for_each_entry(alias, p, &inode->i_dentry, d_u.d_alias) { LASSERT(alias != dentry); spin_lock(&alias->d_lock); @@ -953,7 +953,7 @@ static void ll_get_child_fid(struct inode * dir, struct qstr *name, { struct dentry *parent, *child; - parent = ll_d_hlist_entry(dir->i_dentry, struct dentry, d_alias); + parent = ll_d_hlist_entry(dir->i_dentry, struct dentry, d_u.d_alias); child = d_lookup(parent, name); if (child) { if (child->d_inode) diff --git a/drivers/staging/lustre/lustre/llite/vvp_io.c b/drivers/staging/lustre/lustre/llite/vvp_io.c index 93cbfbb..6096771 100644 --- a/drivers/staging/lustre/lustre/llite/vvp_io.c +++ b/drivers/staging/lustre/lustre/llite/vvp_io.c @@ -642,7 +642,7 @@ static int vvp_io_kernel_fault(struct vvp_fault_io *cfio) return 0; } - if (cfio->fault.ft_flags & VM_FAULT_SIGBUS) { + if (cfio->fault.ft_flags & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) { CDEBUG(D_PAGE, "got addr %p - SIGBUS\n", vmf->virtual_address); return -EFAULT; } diff --git a/drivers/staging/media/omap4iss/Kconfig b/drivers/staging/media/omap4iss/Kconfig index b9fe753..15940f8 100644 --- a/drivers/staging/media/omap4iss/Kconfig +++ b/drivers/staging/media/omap4iss/Kconfig @@ -1,6 +1,6 @@ config VIDEO_OMAP4 bool "OMAP 4 Camera support" - depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && I2C && ARCH_OMAP4 + depends on VIDEO_V4L2=y && VIDEO_V4L2_SUBDEV_API && I2C=y && ARCH_OMAP4 select VIDEOBUF2_DMA_CONTIG ---help--- Driver for an OMAP 4 ISS controller. diff --git a/drivers/staging/ozwpan/ozusbsvc1.c b/drivers/staging/ozwpan/ozusbsvc1.c index 617f51c..b58e87e 100644 --- a/drivers/staging/ozwpan/ozusbsvc1.c +++ b/drivers/staging/ozwpan/ozusbsvc1.c @@ -323,7 +323,11 @@ static void oz_usb_handle_ep_data(struct oz_usb_ctx *usb_ctx, struct oz_multiple_fixed *body = (struct oz_multiple_fixed *)data_hdr; u8 *data = body->data; - int n = (len - sizeof(struct oz_multiple_fixed)+1) + unsigned int n; + if (!body->unit_size || + len < sizeof(struct oz_multiple_fixed) - 1) + break; + n = (len - (sizeof(struct oz_multiple_fixed) - 1)) / body->unit_size; while (n--) { oz_hcd_data_ind(usb_ctx->hport, body->endpoint, @@ -386,10 +390,15 @@ void oz_usb_rx(struct oz_pd *pd, struct oz_elt *elt) case OZ_GET_DESC_RSP: { struct oz_get_desc_rsp *body = (struct oz_get_desc_rsp *)usb_hdr; - int data_len = elt->length - - sizeof(struct oz_get_desc_rsp) + 1; - u16 offs = le16_to_cpu(get_unaligned(&body->offset)); - u16 total_size = + u16 offs, total_size; + u8 data_len; + + if (elt->length < sizeof(struct oz_get_desc_rsp) - 1) + break; + data_len = elt->length - + (sizeof(struct oz_get_desc_rsp) - 1); + offs = le16_to_cpu(get_unaligned(&body->offset)); + total_size = le16_to_cpu(get_unaligned(&body->total_size)); oz_dbg(ON, "USB_REQ_GET_DESCRIPTOR - cnf\n"); oz_hcd_get_desc_cnf(usb_ctx->hport, body->req_id, diff --git a/drivers/staging/panel/panel.c b/drivers/staging/panel/panel.c index ec4b1fd..790e12e 100644 --- a/drivers/staging/panel/panel.c +++ b/drivers/staging/panel/panel.c @@ -275,11 +275,11 @@ static unsigned char lcd_bits[LCD_PORTS][LCD_BITS][BIT_STATES]; * LCD types */ #define LCD_TYPE_NONE 0 -#define LCD_TYPE_OLD 1 -#define LCD_TYPE_KS0074 2 -#define LCD_TYPE_HANTRONIX 3 -#define LCD_TYPE_NEXCOM 4 -#define LCD_TYPE_CUSTOM 5 +#define LCD_TYPE_CUSTOM 1 +#define LCD_TYPE_OLD 2 +#define LCD_TYPE_KS0074 3 +#define LCD_TYPE_HANTRONIX 4 +#define LCD_TYPE_NEXCOM 5 /* * keypad types @@ -457,8 +457,7 @@ MODULE_PARM_DESC(keypad_enabled, "Deprecated option, use keypad_type instead"); static int lcd_type = -1; module_param(lcd_type, int, 0000); MODULE_PARM_DESC(lcd_type, - "LCD type: 0=none, 1=old //, 2=serial ks0074, " - "3=hantronix //, 4=nexcom //, 5=compiled-in"); + "LCD type: 0=none, 1=compiled-in, 2=old, 3=serial ks0074, 4=hantronix, 5=nexcom"); static int lcd_proto = -1; module_param(lcd_proto, int, 0000); diff --git a/drivers/staging/rtl8187se/ieee80211/ieee80211.h b/drivers/staging/rtl8187se/ieee80211/ieee80211.h index 09ffd9b..6ebdd3f 100644 --- a/drivers/staging/rtl8187se/ieee80211/ieee80211.h +++ b/drivers/staging/rtl8187se/ieee80211/ieee80211.h @@ -1460,12 +1460,12 @@ extern void ieee80211_sta_ps_send_null_frame(struct ieee80211_device *ieee, extern const long ieee80211_wlan_frequencies[]; -extern inline void ieee80211_increment_scans(struct ieee80211_device *ieee) +static inline void ieee80211_increment_scans(struct ieee80211_device *ieee) { ieee->scans++; } -extern inline int ieee80211_get_scans(struct ieee80211_device *ieee) +static inline int ieee80211_get_scans(struct ieee80211_device *ieee) { return ieee->scans; } diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c index 2f40ff5..2185a71 100644 --- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c +++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c @@ -53,9 +53,12 @@ static struct usb_device_id rtw_usb_id_tbl[] = { {USB_DEVICE(USB_VENDER_ID_REALTEK, 0x0179)}, /* 8188ETV */ /*=== Customer ID ===*/ /****** 8188EUS ********/ + {USB_DEVICE(0x056e, 0x4008)}, /* Elecom WDC-150SU2M */ {USB_DEVICE(0x07b8, 0x8179)}, /* Abocom - Abocom */ {USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */ {USB_DEVICE(0x2001, 0x3310)}, /* Dlink DWA-123 REV D1 */ + {USB_DEVICE(0x2001, 0x3311)}, /* DLink GO-USB-N150 REV B1 */ + {USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */ {} /* Terminating entry */ }; diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 83f5f57..59dc078 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -2761,7 +2761,6 @@ extern void rtllib_stop_scan(struct rtllib_device *ieee); extern bool rtllib_act_scanning(struct rtllib_device *ieee, bool sync_scan); extern void rtllib_stop_scan_syncro(struct rtllib_device *ieee); extern void rtllib_start_scan_syncro(struct rtllib_device *ieee, u8 is_mesh); -extern inline struct sk_buff *rtllib_probe_req(struct rtllib_device *ieee); extern u8 MgntQuery_MgntFrameTxRate(struct rtllib_device *ieee); extern void rtllib_sta_ps_send_null_frame(struct rtllib_device *ieee, short pwr); @@ -2943,12 +2942,12 @@ void rtllib_softmac_scan_syncro(struct rtllib_device *ieee, u8 is_mesh); extern const long rtllib_wlan_frequencies[]; -extern inline void rtllib_increment_scans(struct rtllib_device *ieee) +static inline void rtllib_increment_scans(struct rtllib_device *ieee) { ieee->scans++; } -extern inline int rtllib_get_scans(struct rtllib_device *ieee) +static inline int rtllib_get_scans(struct rtllib_device *ieee) { return ieee->scans; } diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c index 4bf72bc..7b5093a 100644 --- a/drivers/staging/rtl8192e/rtllib_softmac.c +++ b/drivers/staging/rtl8192e/rtllib_softmac.c @@ -341,7 +341,7 @@ inline void softmac_ps_mgmt_xmit(struct sk_buff *skb, } } -inline struct sk_buff *rtllib_probe_req(struct rtllib_device *ieee) +static inline struct sk_buff *rtllib_probe_req(struct rtllib_device *ieee) { unsigned int len, rate_len; u8 *tag; diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211.h b/drivers/staging/rtl8192u/ieee80211/ieee80211.h index bc64f05..b1a0380 100644 --- a/drivers/staging/rtl8192u/ieee80211/ieee80211.h +++ b/drivers/staging/rtl8192u/ieee80211/ieee80211.h @@ -2250,7 +2250,7 @@ static inline void *ieee80211_priv(struct net_device *dev) return ((struct ieee80211_device *)netdev_priv(dev))->priv; } -extern inline int ieee80211_is_empty_essid(const char *essid, int essid_len) +static inline int ieee80211_is_empty_essid(const char *essid, int essid_len) { /* Single white space is for Linksys APs */ if (essid_len == 1 && essid[0] == ' ') @@ -2266,7 +2266,7 @@ extern inline int ieee80211_is_empty_essid(const char *essid, int essid_len) return 1; } -extern inline int ieee80211_is_valid_mode(struct ieee80211_device *ieee, int mode) +static inline int ieee80211_is_valid_mode(struct ieee80211_device *ieee, int mode) { /* * It is possible for both access points and our device to support @@ -2292,7 +2292,7 @@ extern inline int ieee80211_is_valid_mode(struct ieee80211_device *ieee, int mod return 0; } -extern inline int ieee80211_get_hdrlen(u16 fc) +static inline int ieee80211_get_hdrlen(u16 fc) { int hdrlen = IEEE80211_3ADDR_LEN; @@ -2578,12 +2578,12 @@ void ieee80211_softmac_scan_syncro(struct ieee80211_device *ieee); extern const long ieee80211_wlan_frequencies[]; -extern inline void ieee80211_increment_scans(struct ieee80211_device *ieee) +static inline void ieee80211_increment_scans(struct ieee80211_device *ieee) { ieee->scans++; } -extern inline int ieee80211_get_scans(struct ieee80211_device *ieee) +static inline int ieee80211_get_scans(struct ieee80211_device *ieee) { return ieee->scans; } diff --git a/drivers/staging/rtl8712/ieee80211.h b/drivers/staging/rtl8712/ieee80211.h index da4000e..8269be8 100644 --- a/drivers/staging/rtl8712/ieee80211.h +++ b/drivers/staging/rtl8712/ieee80211.h @@ -734,7 +734,7 @@ enum ieee80211_state { #define IEEE_G (1<<2) #define IEEE_MODE_MASK (IEEE_A|IEEE_B|IEEE_G) -extern inline int ieee80211_is_empty_essid(const char *essid, int essid_len) +static inline int ieee80211_is_empty_essid(const char *essid, int essid_len) { /* Single white space is for Linksys APs */ if (essid_len == 1 && essid[0] == ' ') @@ -748,7 +748,7 @@ extern inline int ieee80211_is_empty_essid(const char *essid, int essid_len) return 1; } -extern inline int ieee80211_get_hdrlen(u16 fc) +static inline int ieee80211_get_hdrlen(u16 fc) { int hdrlen = 24; diff --git a/drivers/staging/rtl8712/rtl8712_recv.c b/drivers/staging/rtl8712/rtl8712_recv.c index ea96537..d060b1f 100644 --- a/drivers/staging/rtl8712/rtl8712_recv.c +++ b/drivers/staging/rtl8712/rtl8712_recv.c @@ -1075,7 +1075,8 @@ static int recvbuf2recvframe(struct _adapter *padapter, struct sk_buff *pskb) /* for first fragment packet, driver need allocate 1536 + * drvinfo_sz + RXDESC_SIZE to defrag packet. */ if ((mf == 1) && (frag == 0)) - alloc_sz = 1658;/*1658+6=1664, 1664 is 128 alignment.*/ + /*1658+6=1664, 1664 is 128 alignment.*/ + alloc_sz = max_t(u16, tmp_len, 1658); else alloc_sz = tmp_len; /* 2 is for IP header 4 bytes alignment in QoS packet case. diff --git a/drivers/staging/vt6655/bssdb.c b/drivers/staging/vt6655/bssdb.c index d7efd017..7d75788 100644 --- a/drivers/staging/vt6655/bssdb.c +++ b/drivers/staging/vt6655/bssdb.c @@ -983,7 +983,7 @@ start: pDevice->byERPFlag &= ~(WLAN_SET_ERP_USE_PROTECTION(1)); } - { + if (pDevice->eCommandState == WLAN_ASSOCIATE_WAIT) { pDevice->byReAssocCount++; /* 10 sec timeout */ if ((pDevice->byReAssocCount > 10) && (!pDevice->bLinkPass)) { diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c index a952df1..6f13f0e 100644 --- a/drivers/staging/vt6655/device_main.c +++ b/drivers/staging/vt6655/device_main.c @@ -2430,6 +2430,7 @@ static irqreturn_t device_intr(int irq, void *dev_instance) { int handled = 0; unsigned char byData = 0; int ii = 0; + unsigned long flags; // unsigned char byRSSI; MACvReadISR(pDevice->PortOffset, &pDevice->dwIsr); @@ -2455,7 +2456,8 @@ static irqreturn_t device_intr(int irq, void *dev_instance) { handled = 1; MACvIntDisable(pDevice->PortOffset); - spin_lock_irq(&pDevice->lock); + + spin_lock_irqsave(&pDevice->lock, flags); //Make sure current page is 0 VNSvInPortB(pDevice->PortOffset + MAC_REG_PAGE1SEL, &byOrgPageSel); @@ -2696,7 +2698,8 @@ static irqreturn_t device_intr(int irq, void *dev_instance) { MACvSelectPage1(pDevice->PortOffset); } - spin_unlock_irq(&pDevice->lock); + spin_unlock_irqrestore(&pDevice->lock, flags); + MACvIntEnable(pDevice->PortOffset, IMR_MASK_VALUE); return IRQ_RETVAL(handled); diff --git a/drivers/staging/vt6655/rf.c b/drivers/staging/vt6655/rf.c index edb1b27..dbd9d44 100644 --- a/drivers/staging/vt6655/rf.c +++ b/drivers/staging/vt6655/rf.c @@ -936,6 +936,7 @@ bool RFbSetPower( break; case RATE_6M: case RATE_9M: + case RATE_12M: case RATE_18M: byPwr = pDevice->abyOFDMPwrTbl[uCH]; if (pDevice->byRFType == RF_UW2452) { diff --git a/drivers/staging/vt6656/rf.c b/drivers/staging/vt6656/rf.c index 1e8f64b..2dc48d4 100644 --- a/drivers/staging/vt6656/rf.c +++ b/drivers/staging/vt6656/rf.c @@ -752,6 +752,7 @@ int RFbSetPower(struct vnt_private *priv, u32 rate, u32 channel) break; case RATE_6M: case RATE_9M: + case RATE_12M: case RATE_18M: case RATE_24M: case RATE_36M: diff --git a/drivers/staging/wlags49_h2/wl_internal.h b/drivers/staging/wlags49_h2/wl_internal.h index 78129e9..1ecb5cb 100644 --- a/drivers/staging/wlags49_h2/wl_internal.h +++ b/drivers/staging/wlags49_h2/wl_internal.h @@ -1013,7 +1013,7 @@ static inline void wl_unlock(struct wl_private *lp, /* Interrupt enable disable functions */ /********************************************************************/ -extern inline void wl_act_int_on(struct wl_private *lp) +static inline void wl_act_int_on(struct wl_private *lp) { /* * Only do something when the driver is handling @@ -1025,7 +1025,7 @@ extern inline void wl_act_int_on(struct wl_private *lp) } } -extern inline void wl_act_int_off(struct wl_private *lp) +static inline void wl_act_int_off(struct wl_private *lp) { /* * Only do something when the driver is handling diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index f329ad2..9dbf176 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -518,7 +518,7 @@ static struct iscsit_transport iscsi_target_transport = { static int __init iscsi_target_init_module(void) { - int ret = 0; + int ret = 0, size; pr_debug("iSCSI-Target "ISCSIT_VERSION"\n"); @@ -527,6 +527,7 @@ static int __init iscsi_target_init_module(void) pr_err("Unable to allocate memory for iscsit_global\n"); return -1; } + spin_lock_init(&iscsit_global->ts_bitmap_lock); mutex_init(&auth_id_lock); spin_lock_init(&sess_idr_lock); idr_init(&tiqn_idr); @@ -536,15 +537,11 @@ static int __init iscsi_target_init_module(void) if (ret < 0) goto out; - ret = iscsi_thread_set_init(); - if (ret < 0) + size = BITS_TO_LONGS(ISCSIT_BITMAP_BITS) * sizeof(long); + iscsit_global->ts_bitmap = vzalloc(size); + if (!iscsit_global->ts_bitmap) { + pr_err("Unable to allocate iscsit_global->ts_bitmap\n"); goto configfs_out; - - if (iscsi_allocate_thread_sets(TARGET_THREAD_SET_COUNT) != - TARGET_THREAD_SET_COUNT) { - pr_err("iscsi_allocate_thread_sets() returned" - " unexpected value!\n"); - goto ts_out1; } lio_qr_cache = kmem_cache_create("lio_qr_cache", @@ -553,7 +550,7 @@ static int __init iscsi_target_init_module(void) if (!lio_qr_cache) { pr_err("nable to kmem_cache_create() for" " lio_qr_cache\n"); - goto ts_out2; + goto bitmap_out; } lio_dr_cache = kmem_cache_create("lio_dr_cache", @@ -597,10 +594,8 @@ dr_out: kmem_cache_destroy(lio_dr_cache); qr_out: kmem_cache_destroy(lio_qr_cache); -ts_out2: - iscsi_deallocate_thread_sets(); -ts_out1: - iscsi_thread_set_free(); +bitmap_out: + vfree(iscsit_global->ts_bitmap); configfs_out: iscsi_target_deregister_configfs(); out: @@ -610,8 +605,6 @@ out: static void __exit iscsi_target_cleanup_module(void) { - iscsi_deallocate_thread_sets(); - iscsi_thread_set_free(); iscsit_release_discovery_tpg(); iscsit_unregister_transport(&iscsi_target_transport); kmem_cache_destroy(lio_qr_cache); @@ -621,6 +614,7 @@ static void __exit iscsi_target_cleanup_module(void) iscsi_target_deregister_configfs(); + vfree(iscsit_global->ts_bitmap); kfree(iscsit_global); } @@ -1165,7 +1159,7 @@ iscsit_handle_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, * traditional iSCSI block I/O. */ if (iscsit_allocate_iovecs(cmd) < 0) { - return iscsit_add_reject_cmd(cmd, + return iscsit_reject_cmd(cmd, ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf); } immed_data = cmd->immediate_data; @@ -3653,17 +3647,16 @@ static int iscsit_send_reject( void iscsit_thread_get_cpumask(struct iscsi_conn *conn) { - struct iscsi_thread_set *ts = conn->thread_set; int ord, cpu; /* - * thread_id is assigned from iscsit_global->ts_bitmap from - * within iscsi_thread_set.c:iscsi_allocate_thread_sets() + * bitmap_id is assigned from iscsit_global->ts_bitmap from + * within iscsit_start_kthreads() * - * Here we use thread_id to determine which CPU that this - * iSCSI connection's iscsi_thread_set will be scheduled to + * Here we use bitmap_id to determine which CPU that this + * iSCSI connection's RX/TX threads will be scheduled to * execute upon. */ - ord = ts->thread_id % cpumask_weight(cpu_online_mask); + ord = conn->bitmap_id % cpumask_weight(cpu_online_mask); for_each_online_cpu(cpu) { if (ord-- == 0) { cpumask_set_cpu(cpu, conn->conn_cpumask); @@ -3855,7 +3848,7 @@ check_rsp_state: switch (state) { case ISTATE_SEND_LOGOUTRSP: if (!iscsit_logout_post_handler(cmd, conn)) - goto restart; + return -ECONNRESET; /* fall through */ case ISTATE_SEND_STATUS: case ISTATE_SEND_ASYNCMSG: @@ -3883,8 +3876,6 @@ check_rsp_state: err: return -1; -restart: - return -EAGAIN; } static int iscsit_handle_response_queue(struct iscsi_conn *conn) @@ -3911,21 +3902,13 @@ static int iscsit_handle_response_queue(struct iscsi_conn *conn) int iscsi_target_tx_thread(void *arg) { int ret = 0; - struct iscsi_conn *conn; - struct iscsi_thread_set *ts = arg; + struct iscsi_conn *conn = arg; /* * Allow ourselves to be interrupted by SIGINT so that a * connection recovery / failure event can be triggered externally. */ allow_signal(SIGINT); -restart: - conn = iscsi_tx_thread_pre_handler(ts); - if (!conn) - goto out; - - ret = 0; - while (!kthread_should_stop()) { /* * Ensure that both TX and RX per connection kthreads @@ -3934,11 +3917,9 @@ restart: iscsit_thread_check_cpumask(conn, current, 1); wait_event_interruptible(conn->queues_wq, - !iscsit_conn_all_queues_empty(conn) || - ts->status == ISCSI_THREAD_SET_RESET); + !iscsit_conn_all_queues_empty(conn)); - if ((ts->status == ISCSI_THREAD_SET_RESET) || - signal_pending(current)) + if (signal_pending(current)) goto transport_err; get_immediate: @@ -3949,15 +3930,20 @@ get_immediate: ret = iscsit_handle_response_queue(conn); if (ret == 1) goto get_immediate; - else if (ret == -EAGAIN) - goto restart; + else if (ret == -ECONNRESET) + goto out; else if (ret < 0) goto transport_err; } transport_err: - iscsit_take_action_for_connection_exit(conn); - goto restart; + /* + * Avoid the normal connection failure code-path if this connection + * is still within LOGIN mode, and iscsi_np process context is + * responsible for cleaning up the early connection failure. + */ + if (conn->conn_state != TARG_CONN_STATE_IN_LOGIN) + iscsit_take_action_for_connection_exit(conn); out: return 0; } @@ -4043,33 +4029,33 @@ reject: int iscsi_target_rx_thread(void *arg) { - int ret; + int ret, rc; u8 buffer[ISCSI_HDR_LEN], opcode; u32 checksum = 0, digest = 0; - struct iscsi_conn *conn = NULL; - struct iscsi_thread_set *ts = arg; + struct iscsi_conn *conn = arg; struct kvec iov; /* * Allow ourselves to be interrupted by SIGINT so that a * connection recovery / failure event can be triggered externally. */ allow_signal(SIGINT); - -restart: - conn = iscsi_rx_thread_pre_handler(ts); - if (!conn) - goto out; + /* + * Wait for iscsi_post_login_handler() to complete before allowing + * incoming iscsi/tcp socket I/O, and/or failing the connection. + */ + rc = wait_for_completion_interruptible(&conn->rx_login_comp); + if (rc < 0) + return 0; if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) { struct completion comp; - int rc; init_completion(&comp); rc = wait_for_completion_interruptible(&comp); if (rc < 0) goto transport_err; - goto out; + goto transport_err; } while (!kthread_should_stop()) { @@ -4145,8 +4131,6 @@ transport_err: if (!signal_pending(current)) atomic_set(&conn->transport_failed, 1); iscsit_take_action_for_connection_exit(conn); - goto restart; -out: return 0; } @@ -4196,13 +4180,36 @@ int iscsit_close_connection( pr_debug("Closing iSCSI connection CID %hu on SID:" " %u\n", conn->cid, sess->sid); /* - * Always up conn_logout_comp just in case the RX Thread is sleeping - * and the logout response never got sent because the connection - * failed. + * Always up conn_logout_comp for the traditional TCP case just in case + * the RX Thread in iscsi_target_rx_opcode() is sleeping and the logout + * response never got sent because the connection failed. + * + * However for iser-target, isert_wait4logout() is using conn_logout_comp + * to signal logout response TX interrupt completion. Go ahead and skip + * this for iser since isert_rx_opcode() does not wait on logout failure, + * and to avoid iscsi_conn pointer dereference in iser-target code. */ - complete(&conn->conn_logout_comp); + if (conn->conn_transport->transport_type == ISCSI_TCP) + complete(&conn->conn_logout_comp); + + if (!strcmp(current->comm, ISCSI_RX_THREAD_NAME)) { + if (conn->tx_thread && + cmpxchg(&conn->tx_thread_active, true, false)) { + send_sig(SIGINT, conn->tx_thread, 1); + kthread_stop(conn->tx_thread); + } + } else if (!strcmp(current->comm, ISCSI_TX_THREAD_NAME)) { + if (conn->rx_thread && + cmpxchg(&conn->rx_thread_active, true, false)) { + send_sig(SIGINT, conn->rx_thread, 1); + kthread_stop(conn->rx_thread); + } + } - iscsi_release_thread_set(conn); + spin_lock(&iscsit_global->ts_bitmap_lock); + bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id, + get_order(1)); + spin_unlock(&iscsit_global->ts_bitmap_lock); iscsit_stop_timers_for_cmds(conn); iscsit_stop_nopin_response_timer(conn); @@ -4481,15 +4488,24 @@ static void iscsit_logout_post_handler_closesession( struct iscsi_conn *conn) { struct iscsi_session *sess = conn->sess; - - iscsi_set_thread_clear(conn, ISCSI_CLEAR_TX_THREAD); - iscsi_set_thread_set_signal(conn, ISCSI_SIGNAL_TX_THREAD); + int sleep = 1; + /* + * Traditional iscsi/tcp will invoke this logic from TX thread + * context during session logout, so clear tx_thread_active and + * sleep if iscsit_close_connection() has not already occured. + * + * Since iser-target invokes this logic from it's own workqueue, + * always sleep waiting for RX/TX thread shutdown to complete + * within iscsit_close_connection(). + */ + if (conn->conn_transport->transport_type == ISCSI_TCP) + sleep = cmpxchg(&conn->tx_thread_active, true, false); atomic_set(&conn->conn_logout_remove, 0); complete(&conn->conn_logout_comp); iscsit_dec_conn_usage_count(conn); - iscsit_stop_session(sess, 1, 1); + iscsit_stop_session(sess, sleep, sleep); iscsit_dec_session_usage_count(sess); target_put_session(sess->se_sess); } @@ -4497,13 +4513,15 @@ static void iscsit_logout_post_handler_closesession( static void iscsit_logout_post_handler_samecid( struct iscsi_conn *conn) { - iscsi_set_thread_clear(conn, ISCSI_CLEAR_TX_THREAD); - iscsi_set_thread_set_signal(conn, ISCSI_SIGNAL_TX_THREAD); + int sleep = 1; + + if (conn->conn_transport->transport_type == ISCSI_TCP) + sleep = cmpxchg(&conn->tx_thread_active, true, false); atomic_set(&conn->conn_logout_remove, 0); complete(&conn->conn_logout_comp); - iscsit_cause_connection_reinstatement(conn, 1); + iscsit_cause_connection_reinstatement(conn, sleep); iscsit_dec_conn_usage_count(conn); } @@ -4513,6 +4531,7 @@ static void iscsit_logout_post_handler_diffcid( { struct iscsi_conn *l_conn; struct iscsi_session *sess = conn->sess; + bool conn_found = false; if (!sess) return; @@ -4521,12 +4540,13 @@ static void iscsit_logout_post_handler_diffcid( list_for_each_entry(l_conn, &sess->sess_conn_list, conn_list) { if (l_conn->cid == cid) { iscsit_inc_conn_usage_count(l_conn); + conn_found = true; break; } } spin_unlock_bh(&sess->conn_lock); - if (!l_conn) + if (!conn_found) return; if (l_conn->sock) @@ -4715,6 +4735,7 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force) struct iscsi_session *sess; struct se_portal_group *se_tpg = &tpg->tpg_se_tpg; struct se_session *se_sess, *se_sess_tmp; + LIST_HEAD(free_list); int session_count = 0; spin_lock_bh(&se_tpg->session_lock); @@ -4736,14 +4757,17 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force) } atomic_set(&sess->session_reinstatement, 1); spin_unlock(&sess->conn_lock); - spin_unlock_bh(&se_tpg->session_lock); - iscsit_free_session(sess); - spin_lock_bh(&se_tpg->session_lock); + list_move_tail(&se_sess->sess_list, &free_list); + } + spin_unlock_bh(&se_tpg->session_lock); + list_for_each_entry_safe(se_sess, se_sess_tmp, &free_list, sess_list) { + sess = (struct iscsi_session *)se_sess->fabric_sess_ptr; + + iscsit_free_session(sess); session_count++; } - spin_unlock_bh(&se_tpg->session_lock); pr_debug("Released %d iSCSI Session(s) from Target Portal" " Group: %hu\n", session_count, tpg->tpgt); diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h index 1d4a8c8..92abbe2 100644 --- a/drivers/target/iscsi/iscsi_target_core.h +++ b/drivers/target/iscsi/iscsi_target_core.h @@ -601,6 +601,12 @@ struct iscsi_conn { struct iscsi_session *sess; /* Pointer to thread_set in use for this conn's threads */ struct iscsi_thread_set *thread_set; + int bitmap_id; + int rx_thread_active; + struct task_struct *rx_thread; + struct completion rx_login_comp; + int tx_thread_active; + struct task_struct *tx_thread; /* list_head for session connection list */ struct list_head conn_list; } ____cacheline_aligned; @@ -869,10 +875,12 @@ struct iscsit_global { /* Unique identifier used for the authentication daemon */ u32 auth_id; u32 inactive_ts; +#define ISCSIT_BITMAP_BITS 262144 /* Thread Set bitmap count */ int ts_bitmap_count; /* Thread Set bitmap pointer */ unsigned long *ts_bitmap; + spinlock_t ts_bitmap_lock; /* Used for iSCSI discovery session authentication */ struct iscsi_node_acl discovery_acl; struct iscsi_portal_group *discovery_tpg; diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c index 0d1e6ee..7396d90 100644 --- a/drivers/target/iscsi/iscsi_target_erl0.c +++ b/drivers/target/iscsi/iscsi_target_erl0.c @@ -864,7 +864,10 @@ void iscsit_connection_reinstatement_rcfr(struct iscsi_conn *conn) } spin_unlock_bh(&conn->state_lock); - iscsi_thread_set_force_reinstatement(conn); + if (conn->tx_thread && conn->tx_thread_active) + send_sig(SIGINT, conn->tx_thread, 1); + if (conn->rx_thread && conn->rx_thread_active) + send_sig(SIGINT, conn->rx_thread, 1); sleep: wait_for_completion(&conn->conn_wait_rcfr_comp); @@ -889,10 +892,10 @@ void iscsit_cause_connection_reinstatement(struct iscsi_conn *conn, int sleep) return; } - if (iscsi_thread_set_force_reinstatement(conn) < 0) { - spin_unlock_bh(&conn->state_lock); - return; - } + if (conn->tx_thread && conn->tx_thread_active) + send_sig(SIGINT, conn->tx_thread, 1); + if (conn->rx_thread && conn->rx_thread_active) + send_sig(SIGINT, conn->rx_thread, 1); atomic_set(&conn->connection_reinstatement, 1); if (!sleep) { diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index d509aa7..01c27aa 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -83,6 +83,7 @@ static struct iscsi_login *iscsi_login_init_conn(struct iscsi_conn *conn) init_completion(&conn->conn_logout_comp); init_completion(&conn->rx_half_close_comp); init_completion(&conn->tx_half_close_comp); + init_completion(&conn->rx_login_comp); spin_lock_init(&conn->cmd_lock); spin_lock_init(&conn->conn_usage_lock); spin_lock_init(&conn->immed_queue_lock); @@ -681,7 +682,53 @@ static void iscsi_post_login_start_timers(struct iscsi_conn *conn) iscsit_start_nopin_timer(conn); } -int iscsi_post_login_handler( +int iscsit_start_kthreads(struct iscsi_conn *conn) +{ + int ret = 0; + + spin_lock(&iscsit_global->ts_bitmap_lock); + conn->bitmap_id = bitmap_find_free_region(iscsit_global->ts_bitmap, + ISCSIT_BITMAP_BITS, get_order(1)); + spin_unlock(&iscsit_global->ts_bitmap_lock); + + if (conn->bitmap_id < 0) { + pr_err("bitmap_find_free_region() failed for" + " iscsit_start_kthreads()\n"); + return -ENOMEM; + } + + conn->tx_thread = kthread_run(iscsi_target_tx_thread, conn, + "%s", ISCSI_TX_THREAD_NAME); + if (IS_ERR(conn->tx_thread)) { + pr_err("Unable to start iscsi_target_tx_thread\n"); + ret = PTR_ERR(conn->tx_thread); + goto out_bitmap; + } + conn->tx_thread_active = true; + + conn->rx_thread = kthread_run(iscsi_target_rx_thread, conn, + "%s", ISCSI_RX_THREAD_NAME); + if (IS_ERR(conn->rx_thread)) { + pr_err("Unable to start iscsi_target_rx_thread\n"); + ret = PTR_ERR(conn->rx_thread); + goto out_tx; + } + conn->rx_thread_active = true; + + return 0; +out_tx: + send_sig(SIGINT, conn->tx_thread, 1); + kthread_stop(conn->tx_thread); + conn->tx_thread_active = false; +out_bitmap: + spin_lock(&iscsit_global->ts_bitmap_lock); + bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id, + get_order(1)); + spin_unlock(&iscsit_global->ts_bitmap_lock); + return ret; +} + +void iscsi_post_login_handler( struct iscsi_np *np, struct iscsi_conn *conn, u8 zero_tsih) @@ -691,7 +738,6 @@ int iscsi_post_login_handler( struct se_session *se_sess = sess->se_sess; struct iscsi_portal_group *tpg = sess->tpg; struct se_portal_group *se_tpg = &tpg->tpg_se_tpg; - struct iscsi_thread_set *ts; iscsit_inc_conn_usage_count(conn); @@ -706,7 +752,6 @@ int iscsi_post_login_handler( /* * SCSI Initiator -> SCSI Target Port Mapping */ - ts = iscsi_get_thread_set(); if (!zero_tsih) { iscsi_set_session_parameters(sess->sess_ops, conn->param_list, 0); @@ -734,8 +779,6 @@ int iscsi_post_login_handler( spin_unlock_bh(&sess->conn_lock); iscsi_post_login_start_timers(conn); - - iscsi_activate_thread_set(conn, ts); /* * Determine CPU mask to ensure connection's RX and TX kthreads * are scheduled on the same CPU. @@ -743,15 +786,20 @@ int iscsi_post_login_handler( iscsit_thread_get_cpumask(conn); conn->conn_rx_reset_cpumask = 1; conn->conn_tx_reset_cpumask = 1; - + /* + * Wakeup the sleeping iscsi_target_rx_thread() now that + * iscsi_conn is in TARG_CONN_STATE_LOGGED_IN state. + */ + complete(&conn->rx_login_comp); iscsit_dec_conn_usage_count(conn); + if (stop_timer) { spin_lock_bh(&se_tpg->session_lock); iscsit_stop_time2retain_timer(sess); spin_unlock_bh(&se_tpg->session_lock); } iscsit_dec_session_usage_count(sess); - return 0; + return; } iscsi_set_session_parameters(sess->sess_ops, conn->param_list, 1); @@ -793,7 +841,6 @@ int iscsi_post_login_handler( spin_unlock_bh(&se_tpg->session_lock); iscsi_post_login_start_timers(conn); - iscsi_activate_thread_set(conn, ts); /* * Determine CPU mask to ensure connection's RX and TX kthreads * are scheduled on the same CPU. @@ -801,10 +848,12 @@ int iscsi_post_login_handler( iscsit_thread_get_cpumask(conn); conn->conn_rx_reset_cpumask = 1; conn->conn_tx_reset_cpumask = 1; - + /* + * Wakeup the sleeping iscsi_target_rx_thread() now that + * iscsi_conn is in TARG_CONN_STATE_LOGGED_IN state. + */ + complete(&conn->rx_login_comp); iscsit_dec_conn_usage_count(conn); - - return 0; } static void iscsi_handle_login_thread_timeout(unsigned long data) @@ -1186,6 +1235,9 @@ old_sess_out: conn->sock = NULL; } + if (conn->conn_transport->iscsit_wait_conn) + conn->conn_transport->iscsit_wait_conn(conn); + if (conn->conn_transport->iscsit_free_conn) conn->conn_transport->iscsit_free_conn(conn); @@ -1366,23 +1418,12 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) if (ret < 0) goto new_sess_out; - if (!conn->sess) { - pr_err("struct iscsi_conn session pointer is NULL!\n"); - goto new_sess_out; - } - iscsi_stop_login_thread_timer(np); - if (signal_pending(current)) - goto new_sess_out; - if (ret == 1) { tpg_np = conn->tpg_np; - ret = iscsi_post_login_handler(np, conn, zero_tsih); - if (ret < 0) - goto new_sess_out; - + iscsi_post_login_handler(np, conn, zero_tsih); iscsit_deaccess_np(np, tpg, tpg_np); } diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h index 29d0983..55cbf45 100644 --- a/drivers/target/iscsi/iscsi_target_login.h +++ b/drivers/target/iscsi/iscsi_target_login.h @@ -12,7 +12,8 @@ extern int iscsit_accept_np(struct iscsi_np *, struct iscsi_conn *); extern int iscsit_get_login_rx(struct iscsi_conn *, struct iscsi_login *); extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32); extern void iscsit_free_conn(struct iscsi_np *, struct iscsi_conn *); -extern int iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8); +extern int iscsit_start_kthreads(struct iscsi_conn *); +extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8); extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *, bool, bool); extern int iscsi_target_login_thread(void *); diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index 582ba84..25ad113 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -17,6 +17,7 @@ ******************************************************************************/ #include +#include #include #include #include @@ -361,10 +362,24 @@ static int iscsi_target_do_tx_login_io(struct iscsi_conn *conn, struct iscsi_log ntohl(login_rsp->statsn), login->rsp_length); padding = ((-login->rsp_length) & 3); + /* + * Before sending the last login response containing the transition + * bit for full-feature-phase, go ahead and start up TX/RX threads + * now to avoid potential resource allocation failures after the + * final login response has been sent. + */ + if (login->login_complete) { + int rc = iscsit_start_kthreads(conn); + if (rc) { + iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, + ISCSI_LOGIN_STATUS_NO_RESOURCES); + return -1; + } + } if (conn->conn_transport->iscsit_put_login_tx(conn, login, login->rsp_length + padding) < 0) - return -1; + goto err; login->rsp_length = 0; mutex_lock(&sess->cmdsn_mutex); @@ -373,6 +388,23 @@ static int iscsi_target_do_tx_login_io(struct iscsi_conn *conn, struct iscsi_log mutex_unlock(&sess->cmdsn_mutex); return 0; + +err: + if (login->login_complete) { + if (conn->rx_thread && conn->rx_thread_active) { + send_sig(SIGINT, conn->rx_thread, 1); + kthread_stop(conn->rx_thread); + } + if (conn->tx_thread && conn->tx_thread_active) { + send_sig(SIGINT, conn->tx_thread, 1); + kthread_stop(conn->tx_thread); + } + spin_lock(&iscsit_global->ts_bitmap_lock); + bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id, + get_order(1)); + spin_unlock(&iscsit_global->ts_bitmap_lock); + } + return -1; } static void iscsi_target_sk_data_ready(struct sock *sk, int count) diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c index 4d2e23f..43b7e6a 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.c +++ b/drivers/target/iscsi/iscsi_target_parameters.c @@ -601,7 +601,7 @@ int iscsi_copy_param_list( param_list = kzalloc(sizeof(struct iscsi_param_list), GFP_KERNEL); if (!param_list) { pr_err("Unable to allocate memory for struct iscsi_param_list.\n"); - goto err_out; + return -1; } INIT_LIST_HEAD(¶m_list->param_list); INIT_LIST_HEAD(¶m_list->extra_response_list); diff --git a/drivers/target/iscsi/iscsi_target_tq.c b/drivers/target/iscsi/iscsi_target_tq.c index 601e9cc..bb2890e 100644 --- a/drivers/target/iscsi/iscsi_target_tq.c +++ b/drivers/target/iscsi/iscsi_target_tq.c @@ -24,36 +24,22 @@ #include "iscsi_target_tq.h" #include "iscsi_target.h" -static LIST_HEAD(active_ts_list); static LIST_HEAD(inactive_ts_list); -static DEFINE_SPINLOCK(active_ts_lock); static DEFINE_SPINLOCK(inactive_ts_lock); static DEFINE_SPINLOCK(ts_bitmap_lock); -static void iscsi_add_ts_to_active_list(struct iscsi_thread_set *ts) -{ - spin_lock(&active_ts_lock); - list_add_tail(&ts->ts_list, &active_ts_list); - iscsit_global->active_ts++; - spin_unlock(&active_ts_lock); -} - static void iscsi_add_ts_to_inactive_list(struct iscsi_thread_set *ts) { + if (!list_empty(&ts->ts_list)) { + WARN_ON(1); + return; + } spin_lock(&inactive_ts_lock); list_add_tail(&ts->ts_list, &inactive_ts_list); iscsit_global->inactive_ts++; spin_unlock(&inactive_ts_lock); } -static void iscsi_del_ts_from_active_list(struct iscsi_thread_set *ts) -{ - spin_lock(&active_ts_lock); - list_del(&ts->ts_list); - iscsit_global->active_ts--; - spin_unlock(&active_ts_lock); -} - static struct iscsi_thread_set *iscsi_get_ts_from_inactive_list(void) { struct iscsi_thread_set *ts; @@ -66,7 +52,7 @@ static struct iscsi_thread_set *iscsi_get_ts_from_inactive_list(void) ts = list_first_entry(&inactive_ts_list, struct iscsi_thread_set, ts_list); - list_del(&ts->ts_list); + list_del_init(&ts->ts_list); iscsit_global->inactive_ts--; spin_unlock(&inactive_ts_lock); @@ -204,8 +190,6 @@ static void iscsi_deallocate_extra_thread_sets(void) void iscsi_activate_thread_set(struct iscsi_conn *conn, struct iscsi_thread_set *ts) { - iscsi_add_ts_to_active_list(ts); - spin_lock_bh(&ts->ts_state_lock); conn->thread_set = ts; ts->conn = conn; @@ -397,7 +381,6 @@ struct iscsi_conn *iscsi_rx_thread_pre_handler(struct iscsi_thread_set *ts) if (ts->delay_inactive && (--ts->thread_count == 0)) { spin_unlock_bh(&ts->ts_state_lock); - iscsi_del_ts_from_active_list(ts); if (!iscsit_global->in_shutdown) iscsi_deallocate_extra_thread_sets(); @@ -452,7 +435,6 @@ struct iscsi_conn *iscsi_tx_thread_pre_handler(struct iscsi_thread_set *ts) if (ts->delay_inactive && (--ts->thread_count == 0)) { spin_unlock_bh(&ts->ts_state_lock); - iscsi_del_ts_from_active_list(ts); if (!iscsit_global->in_shutdown) iscsi_deallocate_extra_thread_sets(); diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index ab77f80..1e406af 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -1356,15 +1356,15 @@ static int iscsit_do_tx_data( struct iscsi_conn *conn, struct iscsi_data_count *count) { - int data = count->data_length, total_tx = 0, tx_loop = 0, iov_len; + int ret, iov_len; struct kvec *iov_p; struct msghdr msg; if (!conn || !conn->sock || !conn->conn_ops) return -1; - if (data <= 0) { - pr_err("Data length is: %d\n", data); + if (count->data_length <= 0) { + pr_err("Data length is: %d\n", count->data_length); return -1; } @@ -1373,20 +1373,16 @@ static int iscsit_do_tx_data( iov_p = count->iov; iov_len = count->iov_count; - while (total_tx < data) { - tx_loop = kernel_sendmsg(conn->sock, &msg, iov_p, iov_len, - (data - total_tx)); - if (tx_loop <= 0) { - pr_debug("tx_loop: %d total_tx %d\n", - tx_loop, total_tx); - return tx_loop; - } - total_tx += tx_loop; - pr_debug("tx_loop: %d, total_tx: %d, data: %d\n", - tx_loop, total_tx, data); + ret = kernel_sendmsg(conn->sock, &msg, iov_p, iov_len, + count->data_length); + if (ret != count->data_length) { + pr_err("Unexpected ret: %d send data %d\n", + ret, count->data_length); + return -EPIPE; } + pr_debug("ret: %d, sent data: %d\n", ret, count->data_length); - return total_tx; + return ret; } int rx_data( diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index fadad7c..67c802c 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -153,18 +153,11 @@ static int tcm_loop_change_queue_type(struct scsi_device *sdev, int tag) /* * Locate the SAM Task Attr from struct scsi_cmnd * */ -static int tcm_loop_sam_attr(struct scsi_cmnd *sc) -{ - if (sc->device->tagged_supported) { - switch (sc->tag) { - case HEAD_OF_QUEUE_TAG: - return MSG_HEAD_TAG; - case ORDERED_QUEUE_TAG: - return MSG_ORDERED_TAG; - default: - break; - } - } +static int tcm_loop_sam_attr(struct scsi_cmnd *sc, int tag) +{ + if (sc->device->tagged_supported && + sc->device->ordered_tags && tag >= 0) + return MSG_ORDERED_TAG; return MSG_SIMPLE_TAG; } @@ -197,7 +190,7 @@ static void tcm_loop_submission_work(struct work_struct *work) set_host_byte(sc, DID_TRANSPORT_DISRUPTED); goto out_done; } - tl_nexus = tl_hba->tl_nexus; + tl_nexus = tl_tpg->tl_nexus; if (!tl_nexus) { scmd_printk(KERN_ERR, sc, "TCM_Loop I_T Nexus" " does not exist\n"); @@ -214,7 +207,7 @@ static void tcm_loop_submission_work(struct work_struct *work) } rc = target_submit_cmd_map_sgls(se_cmd, tl_nexus->se_sess, sc->cmnd, &tl_cmd->tl_sense_buf[0], tl_cmd->sc->device->lun, - scsi_bufflen(sc), tcm_loop_sam_attr(sc), + scsi_bufflen(sc), tcm_loop_sam_attr(sc, tl_cmd->sc_cmd_tag), sc->sc_data_direction, 0, scsi_sglist(sc), scsi_sg_count(sc), sgl_bidi, sgl_bidi_count, @@ -252,7 +245,7 @@ static int tcm_loop_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc) } tl_cmd->sc = sc; - tl_cmd->sc_cmd_tag = sc->tag; + tl_cmd->sc_cmd_tag = sc->request->tag; INIT_WORK(&tl_cmd->work, tcm_loop_submission_work); queue_work(tcm_loop_workqueue, &tl_cmd->work); return 0; @@ -263,16 +256,26 @@ static int tcm_loop_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc) * to struct scsi_device */ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, - struct tcm_loop_nexus *tl_nexus, int lun, int task, enum tcm_tmreq_table tmr) { struct se_cmd *se_cmd = NULL; struct se_session *se_sess; struct se_portal_group *se_tpg; + struct tcm_loop_nexus *tl_nexus; struct tcm_loop_cmd *tl_cmd = NULL; struct tcm_loop_tmr *tl_tmr = NULL; int ret = TMR_FUNCTION_FAILED, rc; + /* + * Locate the tl_nexus and se_sess pointers + */ + tl_nexus = tl_tpg->tl_nexus; + if (!tl_nexus) { + pr_err("Unable to perform device reset without" + " active I_T Nexus\n"); + return ret; + } + tl_cmd = kmem_cache_zalloc(tcm_loop_cmd_cache, GFP_KERNEL); if (!tl_cmd) { pr_err("Unable to allocate memory for tl_cmd\n"); @@ -288,7 +291,7 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, se_cmd = &tl_cmd->tl_se_cmd; se_tpg = &tl_tpg->tl_se_tpg; - se_sess = tl_nexus->se_sess; + se_sess = tl_tpg->tl_nexus->se_sess; /* * Initialize struct se_cmd descriptor from target_core_mod infrastructure */ @@ -333,7 +336,6 @@ release: static int tcm_loop_abort_task(struct scsi_cmnd *sc) { struct tcm_loop_hba *tl_hba; - struct tcm_loop_nexus *tl_nexus; struct tcm_loop_tpg *tl_tpg; int ret = FAILED; @@ -341,22 +343,9 @@ static int tcm_loop_abort_task(struct scsi_cmnd *sc) * Locate the tcm_loop_hba_t pointer */ tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host); - /* - * Locate the tl_nexus and se_sess pointers - */ - tl_nexus = tl_hba->tl_nexus; - if (!tl_nexus) { - pr_err("Unable to perform device reset without" - " active I_T Nexus\n"); - return FAILED; - } - - /* - * Locate the tl_tpg pointer from TargetID in sc->device->id - */ tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id]; - ret = tcm_loop_issue_tmr(tl_tpg, tl_nexus, sc->device->lun, - sc->tag, TMR_ABORT_TASK); + ret = tcm_loop_issue_tmr(tl_tpg, sc->device->lun, + sc->request->tag, TMR_ABORT_TASK); return (ret == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED; } @@ -367,7 +356,6 @@ static int tcm_loop_abort_task(struct scsi_cmnd *sc) static int tcm_loop_device_reset(struct scsi_cmnd *sc) { struct tcm_loop_hba *tl_hba; - struct tcm_loop_nexus *tl_nexus; struct tcm_loop_tpg *tl_tpg; int ret = FAILED; @@ -375,20 +363,9 @@ static int tcm_loop_device_reset(struct scsi_cmnd *sc) * Locate the tcm_loop_hba_t pointer */ tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host); - /* - * Locate the tl_nexus and se_sess pointers - */ - tl_nexus = tl_hba->tl_nexus; - if (!tl_nexus) { - pr_err("Unable to perform device reset without" - " active I_T Nexus\n"); - return FAILED; - } - /* - * Locate the tl_tpg pointer from TargetID in sc->device->id - */ tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id]; - ret = tcm_loop_issue_tmr(tl_tpg, tl_nexus, sc->device->lun, + + ret = tcm_loop_issue_tmr(tl_tpg, sc->device->lun, 0, TMR_LUN_RESET); return (ret == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED; } @@ -995,8 +972,8 @@ static int tcm_loop_make_nexus( struct tcm_loop_nexus *tl_nexus; int ret = -ENOMEM; - if (tl_tpg->tl_hba->tl_nexus) { - pr_debug("tl_tpg->tl_hba->tl_nexus already exists\n"); + if (tl_tpg->tl_nexus) { + pr_debug("tl_tpg->tl_nexus already exists\n"); return -EEXIST; } se_tpg = &tl_tpg->tl_se_tpg; @@ -1031,7 +1008,7 @@ static int tcm_loop_make_nexus( */ __transport_register_session(se_tpg, tl_nexus->se_sess->se_node_acl, tl_nexus->se_sess, tl_nexus); - tl_tpg->tl_hba->tl_nexus = tl_nexus; + tl_tpg->tl_nexus = tl_nexus; pr_debug("TCM_Loop_ConfigFS: Established I_T Nexus to emulated" " %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tl_hba), name); @@ -1047,12 +1024,8 @@ static int tcm_loop_drop_nexus( { struct se_session *se_sess; struct tcm_loop_nexus *tl_nexus; - struct tcm_loop_hba *tl_hba = tpg->tl_hba; - if (!tl_hba) - return -ENODEV; - - tl_nexus = tl_hba->tl_nexus; + tl_nexus = tpg->tl_nexus; if (!tl_nexus) return -ENODEV; @@ -1068,13 +1041,13 @@ static int tcm_loop_drop_nexus( } pr_debug("TCM_Loop_ConfigFS: Removing I_T Nexus to emulated" - " %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tl_hba), + " %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tpg->tl_hba), tl_nexus->se_sess->se_node_acl->initiatorname); /* * Release the SCSI I_T Nexus to the emulated SAS Target Port */ transport_deregister_session(tl_nexus->se_sess); - tpg->tl_hba->tl_nexus = NULL; + tpg->tl_nexus = NULL; kfree(tl_nexus); return 0; } @@ -1090,7 +1063,7 @@ static ssize_t tcm_loop_tpg_show_nexus( struct tcm_loop_nexus *tl_nexus; ssize_t ret; - tl_nexus = tl_tpg->tl_hba->tl_nexus; + tl_nexus = tl_tpg->tl_nexus; if (!tl_nexus) return -ENODEV; diff --git a/drivers/target/loopback/tcm_loop.h b/drivers/target/loopback/tcm_loop.h index 54c59d0..6ae49f2 100644 --- a/drivers/target/loopback/tcm_loop.h +++ b/drivers/target/loopback/tcm_loop.h @@ -27,11 +27,6 @@ struct tcm_loop_tmr { }; struct tcm_loop_nexus { - int it_nexus_active; - /* - * Pointer to Linux/SCSI HBA from linux/include/scsi_host.h - */ - struct scsi_host *sh; /* * Pointer to TCM session for I_T Nexus */ @@ -51,6 +46,7 @@ struct tcm_loop_tpg { atomic_t tl_tpg_port_count; struct se_portal_group tl_se_tpg; struct tcm_loop_hba *tl_hba; + struct tcm_loop_nexus *tl_nexus; }; struct tcm_loop_hba { @@ -59,7 +55,6 @@ struct tcm_loop_hba { struct se_hba_s *se_hba; struct se_lun *tl_hba_lun; struct se_port *tl_hba_lun_sep; - struct tcm_loop_nexus *tl_nexus; struct device dev; struct Scsi_Host *sh; struct tcm_loop_tpg tl_hba_tpgs[TL_TPGS_PER_HBA]; diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 483d324..f303853 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -2359,7 +2359,7 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_support_##_name(\ pr_err("Invalid value '%ld', must be '0' or '1'\n", tmp); \ return -EINVAL; \ } \ - if (!tmp) \ + if (tmp) \ t->_var |= _bit; \ else \ t->_var &= ~_bit; \ diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 6ea95d2..093b8cb 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -1153,10 +1153,10 @@ int se_dev_set_optimal_sectors(struct se_device *dev, u32 optimal_sectors) " changed for TCM/pSCSI\n", dev); return -EINVAL; } - if (optimal_sectors > dev->dev_attrib.fabric_max_sectors) { + if (optimal_sectors > dev->dev_attrib.hw_max_sectors) { pr_err("dev[%p]: Passed optimal_sectors %u cannot be" - " greater than fabric_max_sectors: %u\n", dev, - optimal_sectors, dev->dev_attrib.fabric_max_sectors); + " greater than hw_max_sectors: %u\n", dev, + optimal_sectors, dev->dev_attrib.hw_max_sectors); return -EINVAL; } @@ -1409,7 +1409,8 @@ int core_dev_add_initiator_node_lun_acl( * Check to see if there are any existing persistent reservation APTPL * pre-registrations that need to be enabled for this LUN ACL.. */ - core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, lacl); + core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, nacl, + lacl->mapped_lun); return 0; } @@ -1564,7 +1565,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) DA_UNMAP_GRANULARITY_ALIGNMENT_DEFAULT; dev->dev_attrib.max_write_same_len = DA_MAX_WRITE_SAME_LEN; dev->dev_attrib.fabric_max_sectors = DA_FABRIC_MAX_SECTORS; - dev->dev_attrib.optimal_sectors = DA_FABRIC_MAX_SECTORS; xcopy_lun = &dev->xcopy_lun; xcopy_lun->lun_se_dev = dev; @@ -1591,8 +1591,6 @@ int target_configure_device(struct se_device *dev) ret = dev->transport->configure_device(dev); if (ret) goto out; - dev->dev_flags |= DF_CONFIGURED; - /* * XXX: there is not much point to have two different values here.. */ @@ -1605,6 +1603,7 @@ int target_configure_device(struct se_device *dev) dev->dev_attrib.hw_max_sectors = se_dev_align_max_sectors(dev->dev_attrib.hw_max_sectors, dev->dev_attrib.hw_block_size); + dev->dev_attrib.optimal_sectors = dev->dev_attrib.hw_max_sectors; dev->dev_index = scsi_get_new_index(SCSI_DEVICE_INDEX); dev->creation_time = get_jiffies_64(); @@ -1653,6 +1652,8 @@ int target_configure_device(struct se_device *dev) list_add_tail(&dev->g_dev_node, &g_device_list); mutex_unlock(&g_device_mutex); + dev->dev_flags |= DF_CONFIGURED; + return 0; out_free_alua: diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index cf991a9..b199f1e 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -263,40 +263,32 @@ static int fd_do_prot_rw(struct se_cmd *cmd, struct fd_prot *fd_prot, struct se_device *se_dev = cmd->se_dev; struct fd_dev *dev = FD_DEV(se_dev); struct file *prot_fd = dev->fd_prot_file; - struct scatterlist *sg; loff_t pos = (cmd->t_task_lba * se_dev->prot_length); unsigned char *buf; - u32 prot_size, len, size; - int rc, ret = 1, i; + u32 prot_size; + int rc, ret = 1; prot_size = (cmd->data_length / se_dev->dev_attrib.block_size) * se_dev->prot_length; if (!is_write) { - fd_prot->prot_buf = vzalloc(prot_size); + fd_prot->prot_buf = kzalloc(prot_size, GFP_KERNEL); if (!fd_prot->prot_buf) { pr_err("Unable to allocate fd_prot->prot_buf\n"); return -ENOMEM; } buf = fd_prot->prot_buf; - fd_prot->prot_sg_nents = cmd->t_prot_nents; - fd_prot->prot_sg = kzalloc(sizeof(struct scatterlist) * - fd_prot->prot_sg_nents, GFP_KERNEL); + fd_prot->prot_sg_nents = 1; + fd_prot->prot_sg = kzalloc(sizeof(struct scatterlist), + GFP_KERNEL); if (!fd_prot->prot_sg) { pr_err("Unable to allocate fd_prot->prot_sg\n"); - vfree(fd_prot->prot_buf); + kfree(fd_prot->prot_buf); return -ENOMEM; } - size = prot_size; - - for_each_sg(fd_prot->prot_sg, sg, fd_prot->prot_sg_nents, i) { - - len = min_t(u32, PAGE_SIZE, size); - sg_set_buf(sg, buf, len); - size -= len; - buf += len; - } + sg_init_table(fd_prot->prot_sg, fd_prot->prot_sg_nents); + sg_set_buf(fd_prot->prot_sg, buf, prot_size); } if (is_write) { @@ -317,7 +309,7 @@ static int fd_do_prot_rw(struct se_cmd *cmd, struct fd_prot *fd_prot, if (is_write || ret < 0) { kfree(fd_prot->prot_sg); - vfree(fd_prot->prot_buf); + kfree(fd_prot->prot_buf); } return ret; @@ -620,7 +612,16 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, struct fd_prot fd_prot; sense_reason_t rc; int ret = 0; - + /* + * We are currently limited by the number of iovecs (2048) per + * single vfs_[writev,readv] call. + */ + if (cmd->data_length > FD_MAX_BYTES) { + pr_err("FILEIO: Not able to process I/O of %u bytes due to" + "FD_MAX_BYTES: %u iovec count limitiation\n", + cmd->data_length, FD_MAX_BYTES); + return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + } /* * Call vectorized fileio functions to map struct scatterlist * physical memory addresses to struct iovec virtual memory. @@ -643,11 +644,11 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, 0, fd_prot.prot_sg, 0); if (rc) { kfree(fd_prot.prot_sg); - vfree(fd_prot.prot_buf); + kfree(fd_prot.prot_buf); return rc; } kfree(fd_prot.prot_sg); - vfree(fd_prot.prot_buf); + kfree(fd_prot.prot_buf); } } else { memset(&fd_prot, 0, sizeof(struct fd_prot)); @@ -663,7 +664,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, 0, fd_prot.prot_sg, 0); if (rc) { kfree(fd_prot.prot_sg); - vfree(fd_prot.prot_buf); + kfree(fd_prot.prot_buf); return rc; } } @@ -694,7 +695,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, if (ret < 0) { kfree(fd_prot.prot_sg); - vfree(fd_prot.prot_buf); + kfree(fd_prot.prot_buf); return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 9e0232c..feefe24 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -123,7 +123,7 @@ static int iblock_configure_device(struct se_device *dev) q = bdev_get_queue(bd); dev->dev_attrib.hw_block_size = bdev_logical_block_size(bd); - dev->dev_attrib.hw_max_sectors = UINT_MAX; + dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q); dev->dev_attrib.hw_queue_depth = q->nr_requests; /* diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 3013287..70cb375 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -76,7 +76,7 @@ enum preempt_type { }; static void __core_scsi3_complete_pro_release(struct se_device *, struct se_node_acl *, - struct t10_pr_registration *, int); + struct t10_pr_registration *, int, int); static sense_reason_t target_scsi2_reservation_check(struct se_cmd *cmd) @@ -528,6 +528,18 @@ static int core_scsi3_pr_seq_non_holder( return 0; } + } else if (we && registered_nexus) { + /* + * Reads are allowed for Write Exclusive locks + * from all registrants. + */ + if (cmd->data_direction == DMA_FROM_DEVICE) { + pr_debug("Allowing READ CDB: 0x%02x for %s" + " reservation\n", cdb[0], + core_scsi3_pr_dump_type(pr_reg_type)); + + return 0; + } } pr_debug("%s Conflict for %sregistered nexus %s CDB: 0x%2x" " for %s reservation\n", transport_dump_cmd_direction(cmd), @@ -944,10 +956,10 @@ int core_scsi3_check_aptpl_registration( struct se_device *dev, struct se_portal_group *tpg, struct se_lun *lun, - struct se_lun_acl *lun_acl) + struct se_node_acl *nacl, + u32 mapped_lun) { - struct se_node_acl *nacl = lun_acl->se_lun_nacl; - struct se_dev_entry *deve = nacl->device_list[lun_acl->mapped_lun]; + struct se_dev_entry *deve = nacl->device_list[mapped_lun]; if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS) return 0; @@ -1186,7 +1198,7 @@ static int core_scsi3_check_implicit_release( * service action with the SERVICE ACTION RESERVATION KEY * field set to zero (see 5.7.11.3). */ - __core_scsi3_complete_pro_release(dev, nacl, pr_reg, 0); + __core_scsi3_complete_pro_release(dev, nacl, pr_reg, 0, 1); ret = 1; /* * For 'All Registrants' reservation types, all existing @@ -1228,7 +1240,8 @@ static void __core_scsi3_free_registration( pr_reg->pr_reg_deve->def_pr_registered = 0; pr_reg->pr_reg_deve->pr_res_key = 0; - list_del(&pr_reg->pr_reg_list); + if (!list_empty(&pr_reg->pr_reg_list)) + list_del(&pr_reg->pr_reg_list); /* * Caller accessing *pr_reg using core_scsi3_locate_pr_reg(), * so call core_scsi3_put_pr_reg() to decrement our reference. @@ -1280,6 +1293,7 @@ void core_scsi3_free_pr_reg_from_nacl( { struct t10_reservation *pr_tmpl = &dev->t10_pr; struct t10_pr_registration *pr_reg, *pr_reg_tmp, *pr_res_holder; + bool free_reg = false; /* * If the passed se_node_acl matches the reservation holder, * release the reservation. @@ -1287,13 +1301,18 @@ void core_scsi3_free_pr_reg_from_nacl( spin_lock(&dev->dev_reservation_lock); pr_res_holder = dev->dev_pr_res_holder; if ((pr_res_holder != NULL) && - (pr_res_holder->pr_reg_nacl == nacl)) - __core_scsi3_complete_pro_release(dev, nacl, pr_res_holder, 0); + (pr_res_holder->pr_reg_nacl == nacl)) { + __core_scsi3_complete_pro_release(dev, nacl, pr_res_holder, 0, 1); + free_reg = true; + } spin_unlock(&dev->dev_reservation_lock); /* * Release any registration associated with the struct se_node_acl. */ spin_lock(&pr_tmpl->registration_lock); + if (pr_res_holder && free_reg) + __core_scsi3_free_registration(dev, pr_res_holder, NULL, 0); + list_for_each_entry_safe(pr_reg, pr_reg_tmp, &pr_tmpl->registration_list, pr_reg_list) { @@ -1316,7 +1335,7 @@ void core_scsi3_free_all_registrations( if (pr_res_holder != NULL) { struct se_node_acl *pr_res_nacl = pr_res_holder->pr_reg_nacl; __core_scsi3_complete_pro_release(dev, pr_res_nacl, - pr_res_holder, 0); + pr_res_holder, 0, 0); } spin_unlock(&dev->dev_reservation_lock); @@ -1877,8 +1896,8 @@ static int core_scsi3_update_aptpl_buf( } if ((len + strlen(tmp) >= pr_aptpl_buf_len)) { - pr_err("Unable to update renaming" - " APTPL metadata\n"); + pr_err("Unable to update renaming APTPL metadata," + " reallocating larger buffer\n"); ret = -EMSGSIZE; goto out; } @@ -1895,8 +1914,8 @@ static int core_scsi3_update_aptpl_buf( lun->lun_sep->sep_rtpi, lun->unpacked_lun, reg_count); if ((len + strlen(tmp) >= pr_aptpl_buf_len)) { - pr_err("Unable to update renaming" - " APTPL metadata\n"); + pr_err("Unable to update renaming APTPL metadata," + " reallocating larger buffer\n"); ret = -EMSGSIZE; goto out; } @@ -1959,7 +1978,7 @@ static int __core_scsi3_write_aptpl_to_file( static sense_reason_t core_scsi3_update_and_write_aptpl(struct se_device *dev, bool aptpl) { unsigned char *buf; - int rc; + int rc, len = PR_APTPL_BUF_LEN; if (!aptpl) { char *null_buf = "No Registrations or Reservations\n"; @@ -1973,25 +1992,26 @@ static sense_reason_t core_scsi3_update_and_write_aptpl(struct se_device *dev, b return 0; } - - buf = kzalloc(PR_APTPL_BUF_LEN, GFP_KERNEL); +retry: + buf = vzalloc(len); if (!buf) return TCM_OUT_OF_RESOURCES; - rc = core_scsi3_update_aptpl_buf(dev, buf, PR_APTPL_BUF_LEN); + rc = core_scsi3_update_aptpl_buf(dev, buf, len); if (rc < 0) { - kfree(buf); - return TCM_OUT_OF_RESOURCES; + vfree(buf); + len *= 2; + goto retry; } rc = __core_scsi3_write_aptpl_to_file(dev, buf); if (rc != 0) { pr_err("SPC-3 PR: Could not update APTPL\n"); - kfree(buf); + vfree(buf); return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } dev->t10_pr.pr_aptpl_active = 1; - kfree(buf); + vfree(buf); pr_debug("SPC-3 PR: Set APTPL Bit Activated\n"); return 0; } @@ -2125,13 +2145,13 @@ core_scsi3_emulate_pro_register(struct se_cmd *cmd, u64 res_key, u64 sa_res_key, /* * sa_res_key=0 Unregister Reservation Key for registered I_T Nexus. */ - pr_holder = core_scsi3_check_implicit_release( - cmd->se_dev, pr_reg); + type = pr_reg->pr_res_type; + pr_holder = core_scsi3_check_implicit_release(cmd->se_dev, + pr_reg); if (pr_holder < 0) { ret = TCM_RESERVATION_CONFLICT; goto out; } - type = pr_reg->pr_res_type; spin_lock(&pr_tmpl->registration_lock); /* @@ -2289,6 +2309,7 @@ core_scsi3_pro_reserve(struct se_cmd *cmd, int type, int scope, u64 res_key) spin_lock(&dev->dev_reservation_lock); pr_res_holder = dev->dev_pr_res_holder; if (pr_res_holder) { + int pr_res_type = pr_res_holder->pr_res_type; /* * From spc4r17 Section 5.7.9: Reserving: * @@ -2299,7 +2320,9 @@ core_scsi3_pro_reserve(struct se_cmd *cmd, int type, int scope, u64 res_key) * the logical unit, then the command shall be completed with * RESERVATION CONFLICT status. */ - if (pr_res_holder != pr_reg) { + if ((pr_res_holder != pr_reg) && + (pr_res_type != PR_TYPE_WRITE_EXCLUSIVE_ALLREG) && + (pr_res_type != PR_TYPE_EXCLUSIVE_ACCESS_ALLREG)) { struct se_node_acl *pr_res_nacl = pr_res_holder->pr_reg_nacl; pr_err("SPC-3 PR: Attempted RESERVE from" " [%s]: %s while reservation already held by" @@ -2405,23 +2428,59 @@ static void __core_scsi3_complete_pro_release( struct se_device *dev, struct se_node_acl *se_nacl, struct t10_pr_registration *pr_reg, - int explicit) + int explicit, + int unreg) { struct target_core_fabric_ops *tfo = se_nacl->se_tpg->se_tpg_tfo; char i_buf[PR_REG_ISID_ID_LEN]; + int pr_res_type = 0, pr_res_scope = 0; memset(i_buf, 0, PR_REG_ISID_ID_LEN); core_pr_dump_initiator_port(pr_reg, i_buf, PR_REG_ISID_ID_LEN); /* * Go ahead and release the current PR reservation holder. + * If an All Registrants reservation is currently active and + * a unregister operation is requested, replace the current + * dev_pr_res_holder with another active registration. */ - dev->dev_pr_res_holder = NULL; + if (dev->dev_pr_res_holder) { + pr_res_type = dev->dev_pr_res_holder->pr_res_type; + pr_res_scope = dev->dev_pr_res_holder->pr_res_scope; + dev->dev_pr_res_holder->pr_res_type = 0; + dev->dev_pr_res_holder->pr_res_scope = 0; + dev->dev_pr_res_holder->pr_res_holder = 0; + dev->dev_pr_res_holder = NULL; + } + if (!unreg) + goto out; - pr_debug("SPC-3 PR [%s] Service Action: %s RELEASE cleared" - " reservation holder TYPE: %s ALL_TG_PT: %d\n", - tfo->get_fabric_name(), (explicit) ? "explicit" : "implicit", - core_scsi3_pr_dump_type(pr_reg->pr_res_type), - (pr_reg->pr_reg_all_tg_pt) ? 1 : 0); + spin_lock(&dev->t10_pr.registration_lock); + list_del_init(&pr_reg->pr_reg_list); + /* + * If the I_T nexus is a reservation holder, the persistent reservation + * is of an all registrants type, and the I_T nexus is the last remaining + * registered I_T nexus, then the device server shall also release the + * persistent reservation. + */ + if (!list_empty(&dev->t10_pr.registration_list) && + ((pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_ALLREG) || + (pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_ALLREG))) { + dev->dev_pr_res_holder = + list_entry(dev->t10_pr.registration_list.next, + struct t10_pr_registration, pr_reg_list); + dev->dev_pr_res_holder->pr_res_type = pr_res_type; + dev->dev_pr_res_holder->pr_res_scope = pr_res_scope; + dev->dev_pr_res_holder->pr_res_holder = 1; + } + spin_unlock(&dev->t10_pr.registration_lock); +out: + if (!dev->dev_pr_res_holder) { + pr_debug("SPC-3 PR [%s] Service Action: %s RELEASE cleared" + " reservation holder TYPE: %s ALL_TG_PT: %d\n", + tfo->get_fabric_name(), (explicit) ? "explicit" : + "implicit", core_scsi3_pr_dump_type(pr_res_type), + (pr_reg->pr_reg_all_tg_pt) ? 1 : 0); + } pr_debug("SPC-3 PR [%s] RELEASE Node: %s%s\n", tfo->get_fabric_name(), se_nacl->initiatorname, i_buf); @@ -2552,7 +2611,7 @@ core_scsi3_emulate_pro_release(struct se_cmd *cmd, int type, int scope, * server shall not establish a unit attention condition. */ __core_scsi3_complete_pro_release(dev, se_sess->se_node_acl, - pr_reg, 1); + pr_reg, 1, 0); spin_unlock(&dev->dev_reservation_lock); @@ -2640,7 +2699,7 @@ core_scsi3_emulate_pro_clear(struct se_cmd *cmd, u64 res_key) if (pr_res_holder) { struct se_node_acl *pr_res_nacl = pr_res_holder->pr_reg_nacl; __core_scsi3_complete_pro_release(dev, pr_res_nacl, - pr_res_holder, 0); + pr_res_holder, 0, 0); } spin_unlock(&dev->dev_reservation_lock); /* @@ -2699,7 +2758,7 @@ static void __core_scsi3_complete_pro_preempt( */ if (dev->dev_pr_res_holder) __core_scsi3_complete_pro_release(dev, nacl, - dev->dev_pr_res_holder, 0); + dev->dev_pr_res_holder, 0, 0); dev->dev_pr_res_holder = pr_reg; pr_reg->pr_res_holder = 1; @@ -2943,8 +3002,8 @@ core_scsi3_pro_preempt(struct se_cmd *cmd, int type, int scope, u64 res_key, */ if (pr_reg_n != pr_res_holder) __core_scsi3_complete_pro_release(dev, - pr_res_holder->pr_reg_nacl, - dev->dev_pr_res_holder, 0); + pr_res_holder->pr_reg_nacl, + dev->dev_pr_res_holder, 0, 0); /* * b) Remove the registrations for all I_T nexuses identified * by the SERVICE ACTION RESERVATION KEY field, except the @@ -3414,7 +3473,7 @@ after_iport_check: * holder (i.e., the I_T nexus on which the */ __core_scsi3_complete_pro_release(dev, pr_res_nacl, - dev->dev_pr_res_holder, 0); + dev->dev_pr_res_holder, 0, 0); /* * g) Move the persistent reservation to the specified I_T nexus using * the same scope and type as the persistent reservation released in @@ -3854,7 +3913,8 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd) unsigned char *buf; u32 add_desc_len = 0, add_len = 0, desc_len, exp_desc_len; u32 off = 8; /* off into first Full Status descriptor */ - int format_code = 0; + int format_code = 0, pr_res_type = 0, pr_res_scope = 0; + bool all_reg = false; if (cmd->data_length < 8) { pr_err("PRIN SA READ_FULL_STATUS SCSI Data Length: %u" @@ -3871,6 +3931,19 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd) buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff); buf[3] = (dev->t10_pr.pr_generation & 0xff); + spin_lock(&dev->dev_reservation_lock); + if (dev->dev_pr_res_holder) { + struct t10_pr_registration *pr_holder = dev->dev_pr_res_holder; + + if (pr_holder->pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_ALLREG || + pr_holder->pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_ALLREG) { + all_reg = true; + pr_res_type = pr_holder->pr_res_type; + pr_res_scope = pr_holder->pr_res_scope; + } + } + spin_unlock(&dev->dev_reservation_lock); + spin_lock(&pr_tmpl->registration_lock); list_for_each_entry_safe(pr_reg, pr_reg_tmp, &pr_tmpl->registration_list, pr_reg_list) { @@ -3920,14 +3993,20 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd) * reservation holder for PR_HOLDER bit. * * Also, if this registration is the reservation - * holder, fill in SCOPE and TYPE in the next byte. + * holder or there is an All Registrants reservation + * active, fill in SCOPE and TYPE in the next byte. */ if (pr_reg->pr_res_holder) { buf[off++] |= 0x01; buf[off++] = (pr_reg->pr_res_scope & 0xf0) | (pr_reg->pr_res_type & 0x0f); - } else + } else if (all_reg) { + buf[off++] |= 0x01; + buf[off++] = (pr_res_scope & 0xf0) | + (pr_res_type & 0x0f); + } else { off += 2; + } off += 4; /* Skip over reserved area */ /* diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h index 2ee2936..749fd7b 100644 --- a/drivers/target/target_core_pr.h +++ b/drivers/target/target_core_pr.h @@ -60,7 +60,7 @@ extern int core_scsi3_alloc_aptpl_registration( unsigned char *, u16, u32, int, int, u8); extern int core_scsi3_check_aptpl_registration(struct se_device *, struct se_portal_group *, struct se_lun *, - struct se_lun_acl *); + struct se_node_acl *, u32); extern void core_scsi3_free_pr_reg_from_nacl(struct se_device *, struct se_node_acl *); extern void core_scsi3_free_all_registrations(struct se_device *); diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 0f199f6..9b90cfa 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -520,6 +520,7 @@ static int pscsi_configure_device(struct se_device *dev) " pdv_host_id: %d\n", pdv->pdv_host_id); return -EINVAL; } + pdv->pdv_lld_host = sh; } } else { if (phv->phv_mode == PHV_VIRTUAL_HOST_ID) { @@ -602,6 +603,8 @@ static void pscsi_free_device(struct se_device *dev) if ((phv->phv_mode == PHV_LLD_SCSI_HOST_NO) && (phv->phv_lld_host != NULL)) scsi_host_put(phv->phv_lld_host); + else if (pdv->pdv_lld_host) + scsi_host_put(pdv->pdv_lld_host); if ((sd->type == TYPE_DISK) || (sd->type == TYPE_ROM)) scsi_device_put(sd); @@ -1111,7 +1114,7 @@ static u32 pscsi_get_device_type(struct se_device *dev) struct pscsi_dev_virt *pdv = PSCSI_DEV(dev); struct scsi_device *sd = pdv->pdv_sd; - return sd->type; + return (sd) ? sd->type : TYPE_NO_LUN; } static sector_t pscsi_get_blocks(struct se_device *dev) diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h index 1bd757d..820d305 100644 --- a/drivers/target/target_core_pscsi.h +++ b/drivers/target/target_core_pscsi.h @@ -45,6 +45,7 @@ struct pscsi_dev_virt { int pdv_lun_id; struct block_device *pdv_bd; struct scsi_device *pdv_sd; + struct Scsi_Host *pdv_lld_host; } ____cacheline_aligned; typedef enum phv_modes { diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 379033f..f89b24a 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -266,6 +266,8 @@ static inline unsigned long long transport_lba_64_ext(unsigned char *cdb) static sense_reason_t sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *ops) { + struct se_device *dev = cmd->se_dev; + sector_t end_lba = dev->transport->get_blocks(dev) + 1; unsigned int sectors = sbc_get_write_same_sectors(cmd); if ((flags[0] & 0x04) || (flags[0] & 0x02)) { @@ -279,6 +281,16 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o sectors, cmd->se_dev->dev_attrib.max_write_same_len); return TCM_INVALID_CDB_FIELD; } + /* + * Sanity check for LBA wrap and request past end of device. + */ + if (((cmd->t_task_lba + sectors) < cmd->t_task_lba) || + ((cmd->t_task_lba + sectors) > end_lba)) { + pr_err("WRITE_SAME exceeds last lba %llu (lba %llu, sectors %u)\n", + (unsigned long long)end_lba, cmd->t_task_lba, sectors); + return TCM_ADDRESS_OUT_OF_RANGE; + } + /* We always have ANC_SUP == 0 so setting ANCHOR is always an error */ if (flags[0] & 0x10) { pr_warn("WRITE SAME with ANCHOR not supported\n"); @@ -302,7 +314,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o return 0; } -static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd) +static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd, bool success) { unsigned char *buf, *addr; struct scatterlist *sg; @@ -366,7 +378,7 @@ sbc_execute_rw(struct se_cmd *cmd) cmd->data_direction); } -static sense_reason_t compare_and_write_post(struct se_cmd *cmd) +static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success) { struct se_device *dev = cmd->se_dev; @@ -389,7 +401,7 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd) return TCM_NO_SENSE; } -static sense_reason_t compare_and_write_callback(struct se_cmd *cmd) +static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success) { struct se_device *dev = cmd->se_dev; struct scatterlist *write_sg = NULL, *sg; @@ -404,11 +416,16 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd) /* * Handle early failure in transport_generic_request_failure(), - * which will not have taken ->caw_mutex yet.. + * which will not have taken ->caw_sem yet.. */ - if (!cmd->t_data_sg || !cmd->t_bidi_data_sg) + if (!success && (!cmd->t_data_sg || !cmd->t_bidi_data_sg)) return TCM_NO_SENSE; /* + * Handle special case for zero-length COMPARE_AND_WRITE + */ + if (!cmd->data_length) + goto out; + /* * Immediately exit + release dev->caw_sem if command has already * been failed with a non-zero SCSI status. */ @@ -910,23 +927,9 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) { unsigned long long end_lba; - if (sectors > dev->dev_attrib.fabric_max_sectors) { - printk_ratelimited(KERN_ERR "SCSI OP %02xh with too" - " big sectors %u exceeds fabric_max_sectors:" - " %u\n", cdb[0], sectors, - dev->dev_attrib.fabric_max_sectors); - return TCM_INVALID_CDB_FIELD; - } - if (sectors > dev->dev_attrib.hw_max_sectors) { - printk_ratelimited(KERN_ERR "SCSI OP %02xh with too" - " big sectors %u exceeds backend hw_max_sectors:" - " %u\n", cdb[0], sectors, - dev->dev_attrib.hw_max_sectors); - return TCM_INVALID_CDB_FIELD; - } - end_lba = dev->transport->get_blocks(dev) + 1; - if (cmd->t_task_lba + sectors > end_lba) { + if (((cmd->t_task_lba + sectors) < cmd->t_task_lba) || + ((cmd->t_task_lba + sectors) > end_lba)) { pr_err("cmd exceeds last lba %llu " "(lba %llu, sectors %u)\n", end_lba, cmd->t_task_lba, sectors); diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index fcdf98f..12a74f6 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -503,7 +503,6 @@ static sense_reason_t spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf) { struct se_device *dev = cmd->se_dev; - u32 max_sectors; int have_tp = 0; int opt, min; @@ -537,9 +536,7 @@ spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf) /* * Set MAXIMUM TRANSFER LENGTH */ - max_sectors = min(dev->dev_attrib.fabric_max_sectors, - dev->dev_attrib.hw_max_sectors); - put_unaligned_be32(max_sectors, &buf[8]); + put_unaligned_be32(dev->dev_attrib.hw_max_sectors, &buf[8]); /* * Set OPTIMAL TRANSFER LENGTH diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index c036595..fb8a1a1 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -40,6 +40,7 @@ #include #include "target_core_internal.h" +#include "target_core_pr.h" extern struct se_device *g_lun0_dev; @@ -166,6 +167,13 @@ void core_tpg_add_node_to_devs( core_enable_device_list_for_node(lun, NULL, lun->unpacked_lun, lun_access, acl, tpg); + /* + * Check to see if there are any existing persistent reservation + * APTPL pre-registrations that need to be enabled for this dynamic + * LUN ACL now.. + */ + core_scsi3_check_aptpl_registration(dev, tpg, lun, acl, + lun->unpacked_lun); spin_lock(&tpg->tpg_lun_lock); } spin_unlock(&tpg->tpg_lun_lock); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 24f5279..6fc3890 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1600,11 +1600,11 @@ void transport_generic_request_failure(struct se_cmd *cmd, transport_complete_task_attr(cmd); /* * Handle special case for COMPARE_AND_WRITE failure, where the - * callback is expected to drop the per device ->caw_mutex. + * callback is expected to drop the per device ->caw_sem. */ if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) && cmd->transport_complete_callback) - cmd->transport_complete_callback(cmd); + cmd->transport_complete_callback(cmd, false); switch (sense_reason) { case TCM_NON_EXISTENT_LUN: @@ -1855,8 +1855,7 @@ static void transport_complete_qf(struct se_cmd *cmd) if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) { trace_target_cmd_complete(cmd); ret = cmd->se_tfo->queue_status(cmd); - if (ret) - goto out; + goto out; } switch (cmd->data_direction) { @@ -1942,8 +1941,12 @@ static void target_complete_ok_work(struct work_struct *work) if (cmd->transport_complete_callback) { sense_reason_t rc; - rc = cmd->transport_complete_callback(cmd); + rc = cmd->transport_complete_callback(cmd, true); if (!rc && !(cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE_POST)) { + if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) && + !cmd->data_length) + goto queue_rsp; + return; } else if (rc) { ret = transport_send_check_condition_and_sense(cmd, @@ -1957,6 +1960,7 @@ static void target_complete_ok_work(struct work_struct *work) } } +queue_rsp: switch (cmd->data_direction) { case DMA_FROM_DEVICE: spin_lock(&cmd->se_lun->lun_sep_lock); @@ -2045,6 +2049,16 @@ static inline void transport_reset_sgl_orig(struct se_cmd *cmd) static inline void transport_free_pages(struct se_cmd *cmd) { if (cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) { + /* + * Release special case READ buffer payload required for + * SG_TO_MEM_NOALLOC to function with COMPARE_AND_WRITE + */ + if (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) { + transport_free_sgl(cmd->t_bidi_data_sg, + cmd->t_bidi_data_nents); + cmd->t_bidi_data_sg = NULL; + cmd->t_bidi_data_nents = 0; + } transport_reset_sgl_orig(cmd); return; } @@ -2193,6 +2207,7 @@ sense_reason_t transport_generic_new_cmd(struct se_cmd *cmd) { int ret = 0; + bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB); /* * Determine is the TCM fabric module has already allocated physical @@ -2201,7 +2216,6 @@ transport_generic_new_cmd(struct se_cmd *cmd) */ if (!(cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) && cmd->data_length) { - bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB); if ((cmd->se_cmd_flags & SCF_BIDI) || (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE)) { @@ -2224,6 +2238,20 @@ transport_generic_new_cmd(struct se_cmd *cmd) cmd->data_length, zero_flag); if (ret < 0) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + } else if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) && + cmd->data_length) { + /* + * Special case for COMPARE_AND_WRITE with fabrics + * using SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC. + */ + u32 caw_length = cmd->t_task_nolb * + cmd->se_dev->dev_attrib.block_size; + + ret = target_alloc_sgl(&cmd->t_bidi_data_sg, + &cmd->t_bidi_data_nents, + caw_length, zero_flag); + if (ret < 0) + return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } /* * If this command is not a write we can execute it right here, @@ -2231,7 +2259,7 @@ transport_generic_new_cmd(struct se_cmd *cmd) * and let it call back once the write buffers are ready. */ target_add_to_state_list(cmd); - if (cmd->data_direction != DMA_TO_DEVICE) { + if (cmd->data_direction != DMA_TO_DEVICE || cmd->data_length == 0) { target_execute_cmd(cmd); return 0; } @@ -2328,6 +2356,10 @@ int target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd, list_add_tail(&se_cmd->se_cmd_list, &se_sess->sess_cmd_list); out: spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + + if (ret && ack_kref) + target_put_sess_cmd(se_sess, se_cmd); + return ret; } EXPORT_SYMBOL(target_get_sess_cmd); diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c index e415af3..c67d379 100644 --- a/drivers/target/tcm_fc/tfc_io.c +++ b/drivers/target/tcm_fc/tfc_io.c @@ -346,7 +346,7 @@ void ft_invl_hw_context(struct ft_cmd *cmd) ep = fc_seq_exch(seq); if (ep) { lport = ep->lp; - if (lport && (ep->xid <= lport->lro_xid)) + if (lport && (ep->xid <= lport->lro_xid)) { /* * "ddp_done" trigger invalidation of HW * specific DDP context @@ -361,6 +361,7 @@ void ft_invl_hw_context(struct ft_cmd *cmd) * identified using ep->xid) */ cmd->was_ddp_setup = 0; + } } } } diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c index a084325..6e75177 100644 --- a/drivers/thermal/intel_powerclamp.c +++ b/drivers/thermal/intel_powerclamp.c @@ -435,7 +435,6 @@ static int clamp_thread(void *arg) * allowed. thus jiffies are updated properly. */ preempt_disable(); - tick_nohz_idle_enter(); /* mwait until target jiffies is reached */ while (time_before(jiffies, target_jiffies)) { unsigned long ecx = 1; @@ -451,7 +450,6 @@ static int clamp_thread(void *arg) start_critical_timings(); atomic_inc(&idle_wakeup_counter); } - tick_nohz_idle_exit(); preempt_enable(); } del_timer_sync(&wakeup_timer); diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c index 4db78ea..8a6f06b 100644 --- a/drivers/thermal/step_wise.c +++ b/drivers/thermal/step_wise.c @@ -79,7 +79,7 @@ static unsigned long get_target_state(struct thermal_instance *instance, dev_dbg(&cdev->device, "THERMAL_TREND_RAISE_FULL: next_target=%ld\n", next_target); break; case THERMAL_TREND_DROPPING: - if (cur_state == instance->lower) { + if (cur_state <= instance->lower) { if (!throttle) next_target = THERMAL_NO_TARGET; } else { @@ -153,9 +153,6 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) dev_dbg(&instance->cdev->device, "old_target=%ld, target=%ld\n", old_target, instance->target); - if (old_target == instance->target) - continue; - /* Activate a passive thermal instance */ if (old_target == THERMAL_NO_TARGET && instance->target != THERMAL_NO_TARGET) diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 691c756..0821074 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1830,10 +1830,10 @@ static int __init thermal_init(void) exit_netlink: genetlink_exit(); -unregister_governors: - thermal_unregister_governors(); unregister_class: class_unregister(&thermal_class); +unregister_governors: + thermal_unregister_governors(); error: idr_destroy(&thermal_tz_idr); idr_destroy(&thermal_cdev_idr); diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index 2dc2831..59a7da7 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -289,7 +289,7 @@ static int xen_initial_domain_console_init(void) return -ENOMEM; } - info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0); + info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0, false); info->vtermno = HVC_COOKIE; spin_lock(&xencons_lock); @@ -299,11 +299,27 @@ static int xen_initial_domain_console_init(void) return 0; } +static void xen_console_update_evtchn(struct xencons_info *info) +{ + if (xen_hvm_domain()) { + uint64_t v; + int err; + + err = hvm_get_parameter(HVM_PARAM_CONSOLE_EVTCHN, &v); + if (!err && v) + info->evtchn = v; + } else + info->evtchn = xen_start_info->console.domU.evtchn; +} + void xen_console_resume(void) { struct xencons_info *info = vtermno_to_xencons(HVC_COOKIE); - if (info != NULL && info->irq) + if (info != NULL && info->irq) { + if (!xen_initial_domain()) + xen_console_update_evtchn(info); rebind_evtchn_irq(info->evtchn, info->irq); + } } static void xencons_disconnect_backend(struct xencons_info *info) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 2ebe47b..5bfd807 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -3166,7 +3166,7 @@ static int gsmtty_break_ctl(struct tty_struct *tty, int state) return gsmtty_modem_update(dlci, encode); } -static void gsmtty_remove(struct tty_driver *driver, struct tty_struct *tty) +static void gsmtty_cleanup(struct tty_struct *tty) { struct gsm_dlci *dlci = tty->driver_data; struct gsm_mux *gsm = dlci->gsm; @@ -3174,7 +3174,6 @@ static void gsmtty_remove(struct tty_driver *driver, struct tty_struct *tty) dlci_put(dlci); dlci_put(gsm->dlci[0]); mux_put(gsm); - driver->ttys[tty->index] = NULL; } /* Virtual ttys for the demux */ @@ -3195,7 +3194,7 @@ static const struct tty_operations gsmtty_ops = { .tiocmget = gsmtty_tiocmget, .tiocmset = gsmtty_tiocmset, .break_ctl = gsmtty_break_ctl, - .remove = gsmtty_remove, + .cleanup = gsmtty_cleanup, }; diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 28ac3f3..8195190 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -186,6 +186,17 @@ static int receive_room(struct tty_struct *tty) return left; } +static inline int tty_copy_to_user(struct tty_struct *tty, + void __user *to, + const void *from, + unsigned long n) +{ + struct n_tty_data *ldata = tty->disc_data; + + tty_audit_add_data(tty, to, n, ldata->icanon); + return copy_to_user(to, from, n); +} + /** * n_tty_set_room - receive space * @tty: terminal @@ -247,8 +258,6 @@ static void n_tty_write_wakeup(struct tty_struct *tty) static void n_tty_check_throttle(struct tty_struct *tty) { - if (tty->driver->type == TTY_DRIVER_TYPE_PTY) - return; /* * Check the remaining room for the input canonicalization * mode. We don't want to throttle the driver if we're in @@ -321,7 +330,8 @@ static void n_tty_check_unthrottle(struct tty_struct *tty) static inline void put_tty_queue(unsigned char c, struct n_tty_data *ldata) { - *read_buf_addr(ldata, ldata->read_head++) = c; + *read_buf_addr(ldata, ldata->read_head) = c; + ldata->read_head++; } /** @@ -1511,23 +1521,6 @@ n_tty_receive_char_lnext(struct tty_struct *tty, unsigned char c, char flag) n_tty_receive_char_flagged(tty, c, flag); } -/** - * n_tty_receive_buf - data receive - * @tty: terminal device - * @cp: buffer - * @fp: flag buffer - * @count: characters - * - * Called by the terminal driver when a block of characters has - * been received. This function must be called from soft contexts - * not from interrupt context. The driver is responsible for making - * calls one at a time and in order (or using flush_to_ldisc) - * - * n_tty_receive_buf()/producer path: - * claims non-exclusive termios_rwsem - * publishes read_head and canon_head - */ - static void n_tty_receive_buf_real_raw(struct tty_struct *tty, const unsigned char *cp, char *fp, int count) @@ -1683,24 +1676,85 @@ static void __receive_buf(struct tty_struct *tty, const unsigned char *cp, } } +/** + * n_tty_receive_buf_common - process input + * @tty: device to receive input + * @cp: input chars + * @fp: flags for each char (if NULL, all chars are TTY_NORMAL) + * @count: number of input chars in @cp + * + * Called by the terminal driver when a block of characters has + * been received. This function must be called from soft contexts + * not from interrupt context. The driver is responsible for making + * calls one at a time and in order (or using flush_to_ldisc) + * + * Returns the # of input chars from @cp which were processed. + * + * In canonical mode, the maximum line length is 4096 chars (including + * the line termination char); lines longer than 4096 chars are + * truncated. After 4095 chars, input data is still processed but + * not stored. Overflow processing ensures the tty can always + * receive more input until at least one line can be read. + * + * In non-canonical mode, the read buffer will only accept 4095 chars; + * this provides the necessary space for a newline char if the input + * mode is switched to canonical. + * + * Note it is possible for the read buffer to _contain_ 4096 chars + * in non-canonical mode: the read buffer could already contain the + * maximum canon line of 4096 chars when the mode is switched to + * non-canonical. + * + * n_tty_receive_buf()/producer path: + * claims non-exclusive termios_rwsem + * publishes commit_head or canon_head + */ static int n_tty_receive_buf_common(struct tty_struct *tty, const unsigned char *cp, char *fp, int count, int flow) { struct n_tty_data *ldata = tty->disc_data; - int room, n, rcvd = 0; + int room, n, rcvd = 0, overflow; down_read(&tty->termios_rwsem); while (1) { - room = receive_room(tty); + /* + * When PARMRK is set, each input char may take up to 3 chars + * in the read buf; reduce the buffer space avail by 3x + * + * If we are doing input canonicalization, and there are no + * pending newlines, let characters through without limit, so + * that erase characters will be handled. Other excess + * characters will be beeped. + * + * paired with store in *_copy_from_read_buf() -- guarantees + * the consumer has loaded the data in read_buf up to the new + * read_tail (so this producer will not overwrite unread data) + */ + size_t tail = ldata->read_tail; + + room = N_TTY_BUF_SIZE - (ldata->read_head - tail); + if (I_PARMRK(tty)) + room = (room + 2) / 3; + room--; + if (room <= 0) { + overflow = ldata->icanon && ldata->canon_head == tail; + if (overflow && room < 0) + ldata->read_head--; + room = overflow; + ldata->no_room = flow && !room; + } else + overflow = 0; + n = min(count, room); - if (!n) { - if (flow && !room) - ldata->no_room = 1; + if (!n) break; - } - __receive_buf(tty, cp, fp, n); + + /* ignore parity errors if handling overflow */ + if (!overflow || !fp || *fp != TTY_PARITY) + __receive_buf(tty, cp, fp, n); + cp += n; if (fp) fp += n; @@ -1709,7 +1763,17 @@ n_tty_receive_buf_common(struct tty_struct *tty, const unsigned char *cp, } tty->receive_room = room; - n_tty_check_throttle(tty); + + /* Unthrottle if handling overflow on pty */ + if (tty->driver->type == TTY_DRIVER_TYPE_PTY) { + if (overflow) { + tty_set_flow_change(tty, TTY_UNTHROTTLE_SAFE); + tty_unthrottle_safe(tty); + __tty_set_flow_change(tty, 0); + } + } else + n_tty_check_throttle(tty); + up_read(&tty->termios_rwsem); return rcvd; @@ -2031,12 +2095,12 @@ static int canon_copy_from_read_buf(struct tty_struct *tty, __func__, eol, found, n, c, size, more); if (n > size) { - ret = copy_to_user(*b, read_buf_addr(ldata, tail), size); + ret = tty_copy_to_user(tty, *b, read_buf_addr(ldata, tail), size); if (ret) return -EFAULT; - ret = copy_to_user(*b + size, ldata->read_buf, n - size); + ret = tty_copy_to_user(tty, *b + size, ldata->read_buf, n - size); } else - ret = copy_to_user(*b, read_buf_addr(ldata, tail), n); + ret = tty_copy_to_user(tty, *b, read_buf_addr(ldata, tail), n); if (ret) return -EFAULT; @@ -2416,12 +2480,17 @@ static unsigned int n_tty_poll(struct tty_struct *tty, struct file *file, poll_wait(file, &tty->read_wait, wait); poll_wait(file, &tty->write_wait, wait); + if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) + mask |= POLLHUP; if (input_available_p(tty, 1)) mask |= POLLIN | POLLRDNORM; + else if (mask & POLLHUP) { + tty_flush_to_ldisc(tty); + if (input_available_p(tty, 1)) + mask |= POLLIN | POLLRDNORM; + } if (tty->packet && tty->link->ctrl_status) mask |= POLLPRI | POLLIN | POLLRDNORM; - if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) - mask |= POLLHUP; if (tty_hung_up_p(file)) mask |= POLLHUP; if (!(mask & (POLLHUP | POLLIN | POLLRDNORM))) { diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 25c9bc7..e49616e 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -209,6 +209,9 @@ static int pty_signal(struct tty_struct *tty, int sig) unsigned long flags; struct pid *pgrp; + if (sig != SIGINT && sig != SIGQUIT && sig != SIGTSTP) + return -EINVAL; + if (tty->link) { spin_lock_irqsave(&tty->link->ctrl_lock, flags); pgrp = get_pid(tty->link->pgrp); diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index ab9096d..148ffe4 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -192,21 +192,28 @@ int serial8250_request_dma(struct uart_8250_port *p) dma->rx_buf = dma_alloc_coherent(dma->rxchan->device->dev, dma->rx_size, &dma->rx_addr, GFP_KERNEL); - if (!dma->rx_buf) { - dma_release_channel(dma->rxchan); - dma_release_channel(dma->txchan); - return -ENOMEM; - } + if (!dma->rx_buf) + goto err; /* TX buffer */ dma->tx_addr = dma_map_single(dma->txchan->device->dev, p->port.state->xmit.buf, UART_XMIT_SIZE, DMA_TO_DEVICE); + if (dma_mapping_error(dma->txchan->device->dev, dma->tx_addr)) { + dma_free_coherent(dma->rxchan->device->dev, dma->rx_size, + dma->rx_buf, dma->rx_addr); + goto err; + } dev_dbg_ratelimited(p->port.dev, "got both dma channels\n"); return 0; +err: + dma_release_channel(dma->rxchan); + dma_release_channel(dma->txchan); + + return -ENOMEM; } EXPORT_SYMBOL_GPL(serial8250_request_dma); diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 0ff3e36..5892eab 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -66,7 +66,7 @@ static void moan_device(const char *str, struct pci_dev *dev) "Please send the output of lspci -vv, this\n" "message (0x%04x,0x%04x,0x%04x,0x%04x), the\n" "manufacturer and name of serial board or\n" - "modem board to rmk+serial@arm.linux.org.uk.\n", + "modem board to .\n", pci_name(dev), str, dev->vendor, dev->device, dev->subsystem_vendor, dev->subsystem_device); } @@ -1766,6 +1766,7 @@ pci_wch_ch353_setup(struct serial_private *priv, #define PCI_DEVICE_ID_COMMTECH_4222PCIE 0x0022 #define PCI_DEVICE_ID_BROADCOM_TRUMANAGE 0x160a #define PCI_DEVICE_ID_AMCC_ADDIDATA_APCI7800 0x818e +#define PCI_DEVICE_ID_INTEL_QRK_UART 0x0936 #define PCI_VENDOR_ID_SUNIX 0x1fd4 #define PCI_DEVICE_ID_SUNIX_1999 0x1999 @@ -1876,6 +1877,13 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = byt_serial_setup, }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_QRK_UART, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_default_setup, + }, /* * ITE */ @@ -2710,6 +2718,7 @@ enum pci_board_num_t { pbn_ADDIDATA_PCIe_8_3906250, pbn_ce4100_1_115200, pbn_byt, + pbn_qrk, pbn_omegapci, pbn_NETMOS9900_2s_115200, pbn_brcm_trumanage, @@ -3456,6 +3465,12 @@ static struct pciserial_board pci_boards[] = { .uart_offset = 0x80, .reg_shift = 2, }, + [pbn_qrk] = { + .flags = FL_BASE0, + .num_ports = 1, + .base_baud = 2764800, + .reg_shift = 2, + }, [pbn_omegapci] = { .flags = FL_BASE0, .num_ports = 8, @@ -5150,6 +5165,12 @@ static struct pci_device_id serial_pci_tbl[] = { pbn_byt }, /* + * Intel Quark x1000 + */ + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_QRK_UART, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_qrk }, + /* * Cronyx Omega PCI */ { PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_CRONYX_OMEGA, diff --git a/drivers/tty/serial/8250/8250_pnp.c b/drivers/tty/serial/8250/8250_pnp.c index 682a2fb..2b22cc1 100644 --- a/drivers/tty/serial/8250/8250_pnp.c +++ b/drivers/tty/serial/8250/8250_pnp.c @@ -364,6 +364,11 @@ static const struct pnp_device_id pnp_dev_table[] = { /* Winbond CIR port, should not be probed. We should keep track of it to prevent the legacy serial driver from probing it */ { "WEC1022", CIR_PORT }, + /* + * SMSC IrCC SIR/FIR port, should not be probed by serial driver + * as well so its own driver can bind to it. + */ + { "SMCF010", CIR_PORT }, { "", 0 } }; diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index ce352b8..9d162ef7 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -757,6 +757,7 @@ static int atmel_prepare_tx_dma(struct uart_port *port) config.direction = DMA_MEM_TO_DEV; config.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; config.dst_addr = port->mapbase + ATMEL_US_THR; + config.dst_maxburst = 1; ret = dmaengine_device_control(atmel_port->chan_tx, DMA_SLAVE_CONFIG, @@ -921,6 +922,7 @@ static int atmel_prepare_rx_dma(struct uart_port *port) config.direction = DMA_DEV_TO_MEM; config.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; config.src_addr = port->mapbase + ATMEL_US_RHR; + config.src_maxburst = 1; ret = dmaengine_device_control(atmel_port->chan_rx, DMA_SLAVE_CONFIG, @@ -2392,7 +2394,7 @@ static int atmel_serial_probe(struct platform_device *pdev) ret = atmel_init_port(port, pdev); if (ret) - goto err; + goto err_clear_bit; if (!atmel_use_pdc_rx(&port->uart)) { ret = -ENOMEM; @@ -2441,6 +2443,8 @@ err_alloc_ring: clk_put(port->clk); port->clk = NULL; } +err_clear_bit: + clear_bit(port->uart.line, atmel_ports_in_use); err: return ret; } diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 175f123..501c465 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -362,6 +362,9 @@ static void lpuart_setup_watermark(struct lpuart_port *sport) writeb(val | UARTPFIFO_TXFE | UARTPFIFO_RXFE, sport->port.membase + UARTPFIFO); + /* explicitly clear RDRF */ + readb(sport->port.membase + UARTSR1); + /* flush Tx and Rx FIFO */ writeb(UARTCFIFO_TXFLUSH | UARTCFIFO_RXFLUSH, sport->port.membase + UARTCFIFO); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index d799140..1fd9bc6 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -907,6 +907,14 @@ static void dma_rx_callback(void *data) status = dmaengine_tx_status(chan, (dma_cookie_t)0, &state); count = RX_BUF_SIZE - state.residue; + + if (readl(sport->port.membase + USR2) & USR2_IDLE) { + /* In condition [3] the SDMA counted up too early */ + count--; + + writel(USR2_IDLE, sport->port.membase + USR2); + } + dev_dbg(sport->port.dev, "We get %d bytes.\n", count); if (count) { diff --git a/drivers/tty/serial/of_serial.c b/drivers/tty/serial/of_serial.c index 9924660..9dd8a71 100644 --- a/drivers/tty/serial/of_serial.c +++ b/drivers/tty/serial/of_serial.c @@ -261,7 +261,6 @@ static struct of_device_id of_platform_serial_table[] = { { .compatible = "ibm,qpace-nwp-serial", .data = (void *)PORT_NWPSERIAL, }, #endif - { .type = "serial", .data = (void *)PORT_UNKNOWN, }, { /* end of list */ }, }; diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index db8434d..f4e68b3 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -260,8 +260,16 @@ serial_omap_baud_is_mode16(struct uart_port *port, unsigned int baud) { unsigned int n13 = port->uartclk / (13 * baud); unsigned int n16 = port->uartclk / (16 * baud); - int baudAbsDiff13 = baud - (port->uartclk / (13 * n13)); - int baudAbsDiff16 = baud - (port->uartclk / (16 * n16)); + int baudAbsDiff13; + int baudAbsDiff16; + + if (n13 == 0) + n13 = 1; + if (n16 == 0) + n16 = 1; + + baudAbsDiff13 = baud - (port->uartclk / (13 * n13)); + baudAbsDiff16 = baud - (port->uartclk / (16 * n16)); if (baudAbsDiff13 < 0) baudAbsDiff13 = -baudAbsDiff13; if (baudAbsDiff16 < 0) diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c index 9cd706d..7d3a3f5 100644 --- a/drivers/tty/serial/samsung.c +++ b/drivers/tty/serial/samsung.c @@ -544,11 +544,15 @@ static void s3c24xx_serial_pm(struct uart_port *port, unsigned int level, unsigned int old) { struct s3c24xx_uart_port *ourport = to_ourport(port); + int timeout = 10000; ourport->pm_level = level; switch (level) { case 3: + while (--timeout && !s3c24xx_serial_txempty_nofifo(port)) + udelay(100); + if (!IS_ERR(ourport->baudclk)) clk_disable_unprepare(ourport->baudclk); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index ece2049..27b5554 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -235,6 +235,9 @@ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state) /* * Turn off DTR and RTS early. */ + if (uart_console(uport) && tty) + uport->cons->cflag = tty->termios.c_cflag; + if (!tty || (tty->termios.c_cflag & HUPCL)) uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS); @@ -350,7 +353,7 @@ uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, * The spd_hi, spd_vhi, spd_shi, spd_warp kludge... * Die! Die! Die! */ - if (baud == 38400) + if (try == 0 && baud == 38400) baud = altbaud; /* diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c index 80a58ec..e8f7760 100644 --- a/drivers/tty/serial/sunsab.c +++ b/drivers/tty/serial/sunsab.c @@ -157,6 +157,15 @@ receive_chars(struct uart_sunsab_port *up, (up->port.line == up->port.cons->index)) saw_console_brk = 1; + if (count == 0) { + if (unlikely(stat->sreg.isr1 & SAB82532_ISR1_BRK)) { + stat->sreg.isr0 &= ~(SAB82532_ISR0_PERR | + SAB82532_ISR0_FERR); + up->port.icount.brk++; + uart_handle_break(&up->port); + } + } + for (i = 0; i < count; i++) { unsigned char ch = buf[i], flag; diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index d3448a9..39988fa 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -996,8 +996,8 @@ EXPORT_SYMBOL(start_tty); /* We limit tty time update visibility to every 8 seconds or so. */ static void tty_update_time(struct timespec *time) { - unsigned long sec = get_seconds() & ~7; - if ((long)(sec - time->tv_sec) > 0) + unsigned long sec = get_seconds(); + if (abs(sec - time->tv_sec) & ~7) time->tv_sec = sec; } @@ -1701,6 +1701,7 @@ int tty_release(struct inode *inode, struct file *filp) int pty_master, tty_closing, o_tty_closing, do_sleep; int idx; char buf[64]; + long timeout = 0; if (tty_paranoia_check(tty, inode, __func__)) return 0; @@ -1785,7 +1786,11 @@ int tty_release(struct inode *inode, struct file *filp) __func__, tty_name(tty, buf)); tty_unlock_pair(tty, o_tty); mutex_unlock(&tty_mutex); - schedule(); + schedule_timeout_killable(timeout); + if (timeout < 120 * HZ) + timeout = 2 * timeout + 1; + else + timeout = MAX_SCHEDULE_TIMEOUT; } /* diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 6fd60fe..22da05d 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -217,11 +217,17 @@ void tty_wait_until_sent(struct tty_struct *tty, long timeout) #endif if (!timeout) timeout = MAX_SCHEDULE_TIMEOUT; + if (wait_event_interruptible_timeout(tty->write_wait, - !tty_chars_in_buffer(tty), timeout) >= 0) { - if (tty->ops->wait_until_sent) - tty->ops->wait_until_sent(tty, timeout); + !tty_chars_in_buffer(tty), timeout) < 0) { + return; } + + if (timeout == MAX_SCHEDULE_TIMEOUT) + timeout = 0; + + if (tty->ops->wait_until_sent) + tty->ops->wait_until_sent(tty, timeout); } EXPORT_SYMBOL(tty_wait_until_sent); diff --git a/drivers/tty/vt/consolemap.c b/drivers/tty/vt/consolemap.c index 2978ca5..0e75d2a 100644 --- a/drivers/tty/vt/consolemap.c +++ b/drivers/tty/vt/consolemap.c @@ -540,6 +540,12 @@ int con_set_unimap(struct vc_data *vc, ushort ct, struct unipair __user *list) /* Save original vc_unipagdir_loc in case we allocate a new one */ p = (struct uni_pagedir *)*vc->vc_uni_pagedir_loc; + + if (!p) { + err = -EINVAL; + + goto out_unlock; + } if (p->readonly) { console_unlock(); return -EIO; @@ -633,6 +639,7 @@ int con_set_unimap(struct vc_data *vc, ushort ct, struct unipair __user *list) set_inverse_transl(vc, p, i); /* Update inverse translations */ set_inverse_trans_unicode(vc, p); +out_unlock: console_unlock(); return err; } diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 23b5d32..693091a 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -498,6 +498,7 @@ void invert_screen(struct vc_data *vc, int offset, int count, int viewed) #endif if (DO_UPDATE(vc)) do_update_region(vc, (unsigned long) p, count); + notify_update(vc); } /* used by selection: complement pointer position */ @@ -514,6 +515,7 @@ void complement_pos(struct vc_data *vc, int offset) scr_writew(old, screenpos(vc, old_offset, 1)); if (DO_UPDATE(vc)) vc->vc_sw->con_putc(vc, old, oldy, oldx); + notify_update(vc); } old_offset = offset; @@ -531,8 +533,8 @@ void complement_pos(struct vc_data *vc, int offset) oldy = (offset >> 1) / vc->vc_cols; vc->vc_sw->con_putc(vc, new, oldy, oldx); } + notify_update(vc); } - } static void insert_char(struct vc_data *vc, unsigned int nr) diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c index 0b24e6e..7a9c5a4 100644 --- a/drivers/usb/chipidea/ci_hdrc_msm.c +++ b/drivers/usb/chipidea/ci_hdrc_msm.c @@ -20,13 +20,13 @@ static int ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event) { struct device *dev = ci->gadget.dev.parent; - int val; switch (event) { case CI_HDRC_CONTROLLER_RESET_EVENT: dev_dbg(dev, "CI_HDRC_CONTROLLER_RESET_EVENT received\n"); writel(0, USB_AHBBURST); writel(0, USB_AHBMODE); + usb_phy_init(ci->transceiver); break; case CI_HDRC_CONTROLLER_STOPPED_EVENT: dev_dbg(dev, "CI_HDRC_CONTROLLER_STOPPED_EVENT received\n"); @@ -34,10 +34,7 @@ static int ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event) * Put the transceiver in non-driving mode. Otherwise host * may not detect soft-disconnection. */ - val = usb_phy_io_read(ci->transceiver, ULPI_FUNC_CTRL); - val &= ~ULPI_FUNC_CTRL_OPMODE_MASK; - val |= ULPI_FUNC_CTRL_OPMODE_NONDRIVING; - usb_phy_io_write(ci->transceiver, val, ULPI_FUNC_CTRL); + usb_phy_notify_disconnect(ci->transceiver, USB_SPEED_UNKNOWN); break; default: dev_dbg(dev, "unknown ci_hdrc event\n"); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index eabccd4..d7049c3 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -965,11 +965,12 @@ static void acm_tty_set_termios(struct tty_struct *tty, /* FIXME: Needs to clear unsupported bits in the termios */ acm->clocal = ((termios->c_cflag & CLOCAL) != 0); - if (!newline.dwDTERate) { + if (C_BAUD(tty) == B0) { newline.dwDTERate = acm->line.dwDTERate; newctrl &= ~ACM_CTRL_DTR; - } else + } else if (termios_old && (termios_old->c_cflag & CBAUD) == B0) { newctrl |= ACM_CTRL_DTR; + } if (newctrl != acm->ctrlout) acm_set_control(acm, acm->ctrlout = newctrl); @@ -1168,10 +1169,11 @@ next_desc: } else { control_interface = usb_ifnum_to_if(usb_dev, union_header->bMasterInterface0); data_interface = usb_ifnum_to_if(usb_dev, (data_interface_num = union_header->bSlaveInterface0)); - if (!control_interface || !data_interface) { - dev_dbg(&intf->dev, "no interfaces\n"); - return -ENODEV; - } + } + + if (!control_interface || !data_interface) { + dev_dbg(&intf->dev, "no interfaces\n"); + return -ENODEV; } if (data_interface_num != call_interface_num) @@ -1447,6 +1449,7 @@ alloc_fail8: &dev_attr_wCountryCodes); device_remove_file(&acm->control->dev, &dev_attr_iCountryCodeRelDate); + kfree(acm->country_codes); } device_remove_file(&acm->control->dev, &dev_attr_bmCapabilities); alloc_fail7: @@ -1672,6 +1675,7 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x0572, 0x1328), /* Shiro / Aztech USB MODEM UM-3100 */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, + { USB_DEVICE(0x2184, 0x001c) }, /* GW Instek AFG-2225 */ { USB_DEVICE(0x22b8, 0x6425), /* Motorola MOTOMAGX phones */ }, /* Motorola H24 HSPA module: */ diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index a051a7a..a81f9dd 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -245,7 +245,7 @@ static void wdm_int_callback(struct urb *urb) case USB_CDC_NOTIFY_RESPONSE_AVAILABLE: dev_dbg(&desc->intf->dev, "NOTIFY_RESPONSE_AVAILABLE received: index %d len %d", - dr->wIndex, dr->wLength); + le16_to_cpu(dr->wIndex), le16_to_cpu(dr->wLength)); break; case USB_CDC_NOTIFY_NETWORK_CONNECTION: @@ -262,7 +262,9 @@ static void wdm_int_callback(struct urb *urb) clear_bit(WDM_POLL_RUNNING, &desc->flags); dev_err(&desc->intf->dev, "unknown notification %d received: index %d len %d\n", - dr->bNotificationType, dr->wIndex, dr->wLength); + dr->bNotificationType, + le16_to_cpu(dr->wIndex), + le16_to_cpu(dr->wLength)); goto exit; } @@ -408,7 +410,7 @@ static ssize_t wdm_write USB_RECIP_INTERFACE); req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND; req->wValue = 0; - req->wIndex = desc->inum; + req->wIndex = desc->inum; /* already converted */ req->wLength = cpu_to_le16(count); set_bit(WDM_IN_USE, &desc->flags); desc->outbuf = buf; @@ -422,7 +424,7 @@ static ssize_t wdm_write rv = usb_translate_errors(rv); } else { dev_dbg(&desc->intf->dev, "Tx URB has been submitted index=%d", - req->wIndex); + le16_to_cpu(req->wIndex)); } out: usb_autopm_put_interface(desc->intf); @@ -820,7 +822,7 @@ static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor desc->irq->bRequestType = (USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE); desc->irq->bRequest = USB_CDC_GET_ENCAPSULATED_RESPONSE; desc->irq->wValue = 0; - desc->irq->wIndex = desc->inum; + desc->irq->wIndex = desc->inum; /* already converted */ desc->irq->wLength = cpu_to_le16(desc->wMaxCommand); usb_fill_control_urb( diff --git a/drivers/usb/core/buffer.c b/drivers/usb/core/buffer.c index 684ef70..506b969 100644 --- a/drivers/usb/core/buffer.c +++ b/drivers/usb/core/buffer.c @@ -22,17 +22,25 @@ */ /* FIXME tune these based on pool statistics ... */ -static const size_t pool_max[HCD_BUFFER_POOLS] = { - /* platforms without dma-friendly caches might need to - * prevent cacheline sharing... - */ - 32, - 128, - 512, - PAGE_SIZE / 2 - /* bigger --> allocate pages */ +static size_t pool_max[HCD_BUFFER_POOLS] = { + 32, 128, 512, 2048, }; +void __init usb_init_pool_max(void) +{ + /* + * The pool_max values must never be smaller than + * ARCH_KMALLOC_MINALIGN. + */ + if (ARCH_KMALLOC_MINALIGN <= 32) + ; /* Original value is okay */ + else if (ARCH_KMALLOC_MINALIGN <= 64) + pool_max[0] = 64; + else if (ARCH_KMALLOC_MINALIGN <= 128) + pool_max[0] = 0; /* Don't use this pool */ + else + BUILD_BUG(); /* We don't allow this */ +} /* SETUP primitives */ diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 90e18f6..8016aaa 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -501,6 +501,7 @@ static void async_completed(struct urb *urb) as->status = urb->status; signr = as->signr; if (signr) { + memset(&sinfo, 0, sizeof(sinfo)); sinfo.si_signo = as->signr; sinfo.si_errno = as->status; sinfo.si_code = SI_ASYNCIO; @@ -512,7 +513,7 @@ static void async_completed(struct urb *urb) snoop(&urb->dev->dev, "urb complete\n"); snoop_urb(urb->dev, as->userurb, urb->pipe, urb->actual_length, as->status, COMPLETE, NULL, 0); - if ((urb->transfer_flags & URB_DIR_MASK) == USB_DIR_IN) + if ((urb->transfer_flags & URB_DIR_MASK) == URB_DIR_IN) snoop_urb_data(urb, urb->actual_length); if (as->status < 0 && as->bulk_addr && as->status != -ECONNRESET && @@ -1411,7 +1412,7 @@ static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb, u = (is_in ? URB_DIR_IN : URB_DIR_OUT); if (uurb->flags & USBDEVFS_URB_ISO_ASAP) u |= URB_ISO_ASAP; - if (uurb->flags & USBDEVFS_URB_SHORT_NOT_OK) + if (uurb->flags & USBDEVFS_URB_SHORT_NOT_OK && is_in) u |= URB_SHORT_NOT_OK; if (uurb->flags & USBDEVFS_URB_NO_FSBR) u |= URB_NO_FSBR; @@ -1590,7 +1591,7 @@ static struct async *reap_as(struct dev_state *ps) for (;;) { __set_current_state(TASK_INTERRUPTIBLE); as = async_getcompleted(ps); - if (as) + if (as || !connected(ps)) break; if (signal_pending(current)) break; @@ -1613,7 +1614,7 @@ static int proc_reapurb(struct dev_state *ps, void __user *arg) } if (signal_pending(current)) return -EINTR; - return -EIO; + return -ENODEV; } static int proc_reapurbnonblock(struct dev_state *ps, void __user *arg) @@ -1622,10 +1623,11 @@ static int proc_reapurbnonblock(struct dev_state *ps, void __user *arg) struct async *as; as = async_getcompleted(ps); - retval = -EAGAIN; if (as) { retval = processcompl(as, (void __user * __user *)arg); free_async(as); + } else { + retval = (connected(ps) ? -EAGAIN : -ENODEV); } return retval; } @@ -1755,7 +1757,7 @@ static int proc_reapurb_compat(struct dev_state *ps, void __user *arg) } if (signal_pending(current)) return -EINTR; - return -EIO; + return -ENODEV; } static int proc_reapurbnonblock_compat(struct dev_state *ps, void __user *arg) @@ -1763,11 +1765,12 @@ static int proc_reapurbnonblock_compat(struct dev_state *ps, void __user *arg) int retval; struct async *as; - retval = -EAGAIN; as = async_getcompleted(ps); if (as) { retval = processcompl_compat(as, (void __user * __user *)arg); free_async(as); + } else { + retval = (connected(ps) ? -EAGAIN : -ENODEV); } return retval; } @@ -1939,7 +1942,8 @@ static int proc_get_capabilities(struct dev_state *ps, void __user *arg) { __u32 caps; - caps = USBDEVFS_CAP_ZERO_PACKET | USBDEVFS_CAP_NO_PACKET_SIZE_LIM; + caps = USBDEVFS_CAP_ZERO_PACKET | USBDEVFS_CAP_NO_PACKET_SIZE_LIM | + USBDEVFS_CAP_REAP_AFTER_DISCONNECT; if (!ps->dev->bus->no_stop_on_short) caps |= USBDEVFS_CAP_BULK_CONTINUATION; if (ps->dev->bus->sg_tablesize) @@ -2000,6 +2004,32 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd, return -EPERM; usb_lock_device(dev); + + /* Reap operations are allowed even after disconnection */ + switch (cmd) { + case USBDEVFS_REAPURB: + snoop(&dev->dev, "%s: REAPURB\n", __func__); + ret = proc_reapurb(ps, p); + goto done; + + case USBDEVFS_REAPURBNDELAY: + snoop(&dev->dev, "%s: REAPURBNDELAY\n", __func__); + ret = proc_reapurbnonblock(ps, p); + goto done; + +#ifdef CONFIG_COMPAT + case USBDEVFS_REAPURB32: + snoop(&dev->dev, "%s: REAPURB32\n", __func__); + ret = proc_reapurb_compat(ps, p); + goto done; + + case USBDEVFS_REAPURBNDELAY32: + snoop(&dev->dev, "%s: REAPURBNDELAY32\n", __func__); + ret = proc_reapurbnonblock_compat(ps, p); + goto done; +#endif + } + if (!connected(ps)) { usb_unlock_device(dev); return -ENODEV; @@ -2093,16 +2123,6 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd, inode->i_mtime = CURRENT_TIME; break; - case USBDEVFS_REAPURB32: - snoop(&dev->dev, "%s: REAPURB32\n", __func__); - ret = proc_reapurb_compat(ps, p); - break; - - case USBDEVFS_REAPURBNDELAY32: - snoop(&dev->dev, "%s: REAPURBNDELAY32\n", __func__); - ret = proc_reapurbnonblock_compat(ps, p); - break; - case USBDEVFS_IOCTL32: snoop(&dev->dev, "%s: IOCTL32\n", __func__); ret = proc_ioctl_compat(ps, ptr_to_compat(p)); @@ -2114,16 +2134,6 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd, ret = proc_unlinkurb(ps, p); break; - case USBDEVFS_REAPURB: - snoop(&dev->dev, "%s: REAPURB\n", __func__); - ret = proc_reapurb(ps, p); - break; - - case USBDEVFS_REAPURBNDELAY: - snoop(&dev->dev, "%s: REAPURBNDELAY\n", __func__); - ret = proc_reapurbnonblock(ps, p); - break; - case USBDEVFS_DISCSIGNAL: snoop(&dev->dev, "%s: DISCSIGNAL\n", __func__); ret = proc_disconnectsignal(ps, p); @@ -2160,6 +2170,8 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd, ret = proc_disconnect_claim(ps, p); break; } + + done: usb_unlock_device(dev); if (ret >= 0) inode->i_atime = CURRENT_TIME; @@ -2227,6 +2239,7 @@ static void usbdev_remove(struct usb_device *udev) wake_up_all(&ps->wait); list_del_init(&ps->list); if (ps->discsignr) { + memset(&sinfo, 0, sizeof(sinfo)); sinfo.si_signo = ps->discsignr; sinfo.si_errno = EPIPE; sinfo.si_code = SI_ASYNCIO; diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 2518c32..ee6c556 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1617,6 +1617,7 @@ static int unlink1(struct usb_hcd *hcd, struct urb *urb, int status) int usb_hcd_unlink_urb (struct urb *urb, int status) { struct usb_hcd *hcd; + struct usb_device *udev = urb->dev; int retval = -EIDRM; unsigned long flags; @@ -1628,20 +1629,19 @@ int usb_hcd_unlink_urb (struct urb *urb, int status) spin_lock_irqsave(&hcd_urb_unlink_lock, flags); if (atomic_read(&urb->use_count) > 0) { retval = 0; - usb_get_dev(urb->dev); + usb_get_dev(udev); } spin_unlock_irqrestore(&hcd_urb_unlink_lock, flags); if (retval == 0) { hcd = bus_to_hcd(urb->dev->bus); retval = unlink1(hcd, urb, status); - usb_put_dev(urb->dev); + if (retval == 0) + retval = -EINPROGRESS; + else if (retval != -EIDRM && retval != -EBUSY) + dev_dbg(&udev->dev, "hcd_unlink_urb %p fail %d\n", + urb, retval); + usb_put_dev(udev); } - - if (retval == 0) - retval = -EINPROGRESS; - else if (retval != -EIDRM && retval != -EBUSY) - dev_dbg(&urb->dev->dev, "hcd_unlink_urb %p fail %d\n", - urb, retval); return retval; } @@ -2057,6 +2057,8 @@ int usb_alloc_streams(struct usb_interface *interface, return -EINVAL; if (dev->speed != USB_SPEED_SUPER) return -EINVAL; + if (dev->state < USB_STATE_CONFIGURED) + return -ENODEV; /* Streams only apply to bulk endpoints. */ for (i = 0; i < num_eps; i++) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 5af4a66..e4e06ed 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1695,8 +1695,14 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id) * - Change autosuspend delay of hub can avoid unnecessary auto * suspend timer for hub, also may decrease power consumption * of USB bus. + * + * - If user has indicated to prevent autosuspend by passing + * usbcore.autosuspend = -1 then keep autosuspend disabled. */ - pm_runtime_set_autosuspend_delay(&hdev->dev, 0); +#ifdef CONFIG_PM_RUNTIME + if (hdev->dev.power.autosuspend_delay >= 0) + pm_runtime_set_autosuspend_delay(&hdev->dev, 0); +#endif /* * Hubs have proper suspend/resume support, except for root hubs @@ -1942,8 +1948,10 @@ void usb_set_device_state(struct usb_device *udev, || new_state == USB_STATE_SUSPENDED) ; /* No change to wakeup settings */ else if (new_state == USB_STATE_CONFIGURED) - wakeup = udev->actconfig->desc.bmAttributes - & USB_CONFIG_ATT_WAKEUP; + wakeup = (udev->quirks & + USB_QUIRK_IGNORE_REMOTE_WAKEUP) ? 0 : + udev->actconfig->desc.bmAttributes & + USB_CONFIG_ATT_WAKEUP; else wakeup = 0; } @@ -3174,6 +3182,43 @@ static int finish_port_resume(struct usb_device *udev) } /* + * There are some SS USB devices which take longer time for link training. + * XHCI specs 4.19.4 says that when Link training is successful, port + * sets CSC bit to 1. So if SW reads port status before successful link + * training, then it will not find device to be present. + * USB Analyzer log with such buggy devices show that in some cases + * device switch on the RX termination after long delay of host enabling + * the VBUS. In few other cases it has been seen that device fails to + * negotiate link training in first attempt. It has been + * reported till now that few devices take as long as 2000 ms to train + * the link after host enabling its VBUS and termination. Following + * routine implements a 2000 ms timeout for link training. If in a case + * link trains before timeout, loop will exit earlier. + * + * FIXME: If a device was connected before suspend, but was removed + * while system was asleep, then the loop in the following routine will + * only exit at timeout. + * + * This routine should only be called when persist is enabled for a SS + * device. + */ +static int wait_for_ss_port_enable(struct usb_device *udev, + struct usb_hub *hub, int *port1, + u16 *portchange, u16 *portstatus) +{ + int status = 0, delay_ms = 0; + + while (delay_ms < 2000) { + if (status || *portstatus & USB_PORT_STAT_CONNECTION) + break; + msleep(20); + delay_ms += 20; + status = hub_port_status(hub, *port1, portstatus, portchange); + } + return status; +} + +/* * usb_port_resume - re-activate a suspended usb device's upstream port * @udev: device to re-activate, not a root hub * Context: must be able to sleep; device not locked; pm locks held @@ -3244,10 +3289,10 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg) dev_dbg(hub->intfdev, "can't resume port %d, status %d\n", port1, status); } else { - /* drive resume for at least 20 msec */ + /* drive resume for USB_RESUME_TIMEOUT msec */ dev_dbg(&udev->dev, "usb %sresume\n", (PMSG_IS_AUTO(msg) ? "auto-" : "")); - msleep(25); + msleep(USB_RESUME_TIMEOUT); /* Virtual root hubs can trigger on GET_PORT_STATUS to * stop resume signaling. Then finish the resume @@ -3275,6 +3320,10 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg) clear_bit(port1, hub->busy_bits); + if (udev->persist_enabled && hub_is_superspeed(hub->hdev)) + status = wait_for_ss_port_enable(udev, hub, &port1, &portchange, + &portstatus); + status = check_port_resume_type(udev, hub, port1, status, portchange, portstatus); if (status == 0) @@ -4335,6 +4384,9 @@ check_highspeed (struct usb_hub *hub, struct usb_device *udev, int port1) struct usb_qualifier_descriptor *qual; int status; + if (udev->quirks & USB_QUIRK_DEVICE_QUALIFIER) + return; + qual = kmalloc (sizeof *qual, GFP_KERNEL); if (qual == NULL) return; @@ -4722,9 +4774,10 @@ static void hub_events(void) hub = list_entry(tmp, struct usb_hub, event_list); kref_get(&hub->kref); + hdev = hub->hdev; + usb_get_dev(hdev); spin_unlock_irq(&hub_event_lock); - hdev = hub->hdev; hub_dev = hub->intfdev; intf = to_usb_interface(hub_dev); dev_dbg(hub_dev, "state %d ports %d chg %04x evt %04x\n", @@ -4937,6 +4990,7 @@ static void hub_events(void) usb_autopm_put_interface(intf); loop_disconnected: usb_unlock_device(hdev); + usb_put_dev(hdev); kref_put(&hub->kref, hub_release); } /* end while (1) */ diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 739ee8e..b195fdb 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -44,6 +44,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Creative SB Audigy 2 NX */ { USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Microsoft Wireless Laser Mouse 6000 Receiver */ + { USB_DEVICE(0x045e, 0x00e1), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Microsoft LifeCam-VX700 v2.0 */ { USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -93,6 +96,16 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x04e8, 0x6601), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Elan Touchscreen */ + { USB_DEVICE(0x04f3, 0x0089), .driver_info = + USB_QUIRK_DEVICE_QUALIFIER }, + + { USB_DEVICE(0x04f3, 0x009b), .driver_info = + USB_QUIRK_DEVICE_QUALIFIER }, + + { USB_DEVICE(0x04f3, 0x016f), .driver_info = + USB_QUIRK_DEVICE_QUALIFIER }, + /* Roland SC-8820 */ { USB_DEVICE(0x0582, 0x0007), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -160,6 +173,10 @@ static const struct usb_device_id usb_interface_quirk_list[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x046d, USB_CLASS_VIDEO, 1, 0), .driver_info = USB_QUIRK_RESET_RESUME }, + /* ASUS Base Station(T100) */ + { USB_DEVICE(0x0b05, 0x17e0), .driver_info = + USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + { } /* terminating entry must be last */ }; diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c index 4d11449..a922730 100644 --- a/drivers/usb/core/usb.c +++ b/drivers/usb/core/usb.c @@ -1050,6 +1050,7 @@ static int __init usb_init(void) pr_info("%s: USB support disabled\n", usbcore_name); return 0; } + usb_init_pool_max(); retval = usb_debugfs_init(); if (retval) diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index 4d918ed..0f99800 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -1501,7 +1501,7 @@ static int dwc2_hcd_hub_control(struct dwc2_hsotg *hsotg, u16 typereq, dev_dbg(hsotg->dev, "ClearPortFeature USB_PORT_FEAT_SUSPEND\n"); writel(0, hsotg->regs + PCGCTL); - usleep_range(20000, 40000); + msleep(USB_RESUME_TIMEOUT); hprt0 = dwc2_read_hprt0(hsotg); hprt0 |= HPRT0_RES; diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index a49217a..f074755 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -583,12 +583,6 @@ static int dwc3_remove(struct platform_device *pdev) { struct dwc3 *dwc = platform_get_drvdata(pdev); - usb_phy_set_suspend(dwc->usb2_phy, 1); - usb_phy_set_suspend(dwc->usb3_phy, 1); - - pm_runtime_put_sync(&pdev->dev); - pm_runtime_disable(&pdev->dev); - dwc3_debugfs_exit(dwc); switch (dwc->dr_mode) { @@ -609,8 +603,15 @@ static int dwc3_remove(struct platform_device *pdev) dwc3_event_buffers_cleanup(dwc); dwc3_free_event_buffers(dwc); + + usb_phy_set_suspend(dwc->usb2_phy, 1); + usb_phy_set_suspend(dwc->usb3_phy, 1); + dwc3_core_exit(dwc); + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + return 0; } diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c index b269dbd..cfca302 100644 --- a/drivers/usb/dwc3/dwc3-omap.c +++ b/drivers/usb/dwc3/dwc3-omap.c @@ -211,6 +211,18 @@ static void dwc3_omap_write_irq0_set(struct dwc3_omap *omap, u32 value) omap->irq0_offset, value); } +static void dwc3_omap_write_irqmisc_clr(struct dwc3_omap *omap, u32 value) +{ + dwc3_omap_writel(omap->base, USBOTGSS_IRQENABLE_CLR_MISC + + omap->irqmisc_offset, value); +} + +static void dwc3_omap_write_irq0_clr(struct dwc3_omap *omap, u32 value) +{ + dwc3_omap_writel(omap->base, USBOTGSS_IRQENABLE_CLR_0 - + omap->irq0_offset, value); +} + static void dwc3_omap_set_mailbox(struct dwc3_omap *omap, enum omap_dwc3_vbus_id_status status) { @@ -351,9 +363,23 @@ static void dwc3_omap_enable_irqs(struct dwc3_omap *omap) static void dwc3_omap_disable_irqs(struct dwc3_omap *omap) { + u32 reg; + /* disable all IRQs */ - dwc3_omap_write_irqmisc_set(omap, 0x00); - dwc3_omap_write_irq0_set(omap, 0x00); + reg = USBOTGSS_IRQO_COREIRQ_ST; + dwc3_omap_write_irq0_clr(omap, reg); + + reg = (USBOTGSS_IRQMISC_OEVT | + USBOTGSS_IRQMISC_DRVVBUS_RISE | + USBOTGSS_IRQMISC_CHRGVBUS_RISE | + USBOTGSS_IRQMISC_DISCHRGVBUS_RISE | + USBOTGSS_IRQMISC_IDPULLUP_RISE | + USBOTGSS_IRQMISC_DRVVBUS_FALL | + USBOTGSS_IRQMISC_CHRGVBUS_FALL | + USBOTGSS_IRQMISC_DISCHRGVBUS_FALL | + USBOTGSS_IRQMISC_IDPULLUP_FALL); + + dwc3_omap_write_irqmisc_clr(omap, reg); } static u64 dwc3_omap_dma_mask = DMA_BIT_MASK(32); @@ -582,9 +608,9 @@ static int dwc3_omap_remove(struct platform_device *pdev) if (omap->extcon_id_dev.edev) extcon_unregister_interest(&omap->extcon_id_dev); dwc3_omap_disable_irqs(omap); + device_for_each_child(&pdev->dev, NULL, dwc3_omap_remove_core); pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); - device_for_each_child(&pdev->dev, NULL, dwc3_omap_remove_core); return 0; } diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 21a3520..965c9ac 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -251,7 +251,7 @@ static void dwc3_ep0_stall_and_restart(struct dwc3 *dwc) /* stall is always issued on EP0 */ dep = dwc->eps[0]; - __dwc3_gadget_ep_set_halt(dep, 1); + __dwc3_gadget_ep_set_halt(dep, 1, false); dep->flags = DWC3_EP_ENABLED; dwc->delayed_status = false; @@ -461,7 +461,7 @@ static int dwc3_ep0_handle_feature(struct dwc3 *dwc, return -EINVAL; if (set == 0 && (dep->flags & DWC3_EP_WEDGE)) break; - ret = __dwc3_gadget_ep_set_halt(dep, set); + ret = __dwc3_gadget_ep_set_halt(dep, set, true); if (ret) return -EINVAL; break; @@ -707,6 +707,10 @@ static int dwc3_ep0_std_request(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) dev_vdbg(dwc->dev, "USB_REQ_SET_ISOCH_DELAY\n"); ret = dwc3_ep0_set_isoch_delay(dwc, ctrl); break; + case USB_REQ_SET_INTERFACE: + dev_vdbg(dwc->dev, "USB_REQ_SET_INTERFACE\n"); + dwc->start_config_issued = false; + /* Fall through */ default: dev_vdbg(dwc->dev, "Forwarding to gadget driver\n"); ret = dwc3_ep0_delegate_req(dwc, ctrl); @@ -789,6 +793,11 @@ static void dwc3_ep0_complete_data(struct dwc3 *dwc, unsigned maxp = ep0->endpoint.maxpacket; transfer_size += (maxp - (transfer_size % maxp)); + + /* Maximum of DWC3_EP0_BOUNCE_SIZE can only be received */ + if (transfer_size > DWC3_EP0_BOUNCE_SIZE) + transfer_size = DWC3_EP0_BOUNCE_SIZE; + transferred = min_t(u32, ur->length, transfer_size - length); memcpy(ur->buf, dwc->ep0_bounce, transferred); @@ -901,11 +910,14 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, return; } - WARN_ON(req->request.length > DWC3_EP0_BOUNCE_SIZE); - maxpacket = dep->endpoint.maxpacket; transfer_size = roundup(req->request.length, maxpacket); + if (transfer_size > DWC3_EP0_BOUNCE_SIZE) { + dev_WARN(dwc->dev, "bounce buf can't handle req len\n"); + transfer_size = DWC3_EP0_BOUNCE_SIZE; + } + dwc->ep0_bounced = true; /* diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 09e9619..a57ad1f 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -299,6 +299,8 @@ int dwc3_send_gadget_generic_command(struct dwc3 *dwc, int cmd, u32 param) if (!(reg & DWC3_DGCMD_CMDACT)) { dev_vdbg(dwc->dev, "Command Complete --> %d\n", DWC3_DGCMD_STATUS(reg)); + if (DWC3_DGCMD_STATUS(reg)) + return -EINVAL; return 0; } @@ -335,6 +337,8 @@ int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep, if (!(reg & DWC3_DEPCMD_CMDACT)) { dev_vdbg(dwc->dev, "Command Complete --> %d\n", DWC3_DEPCMD_STATUS(reg)); + if (DWC3_DEPCMD_STATUS(reg)) + return -EINVAL; return 0; } @@ -532,12 +536,11 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, if (!usb_endpoint_xfer_isoc(desc)) return 0; - memset(&trb_link, 0, sizeof(trb_link)); - /* Link TRB for ISOC. The HWO bit is never reset */ trb_st_hw = &dep->trb_pool[0]; trb_link = &dep->trb_pool[DWC3_TRB_NUM - 1]; + memset(trb_link, 0, sizeof(*trb_link)); trb_link->bpl = lower_32_bits(dwc3_trb_dma_offset(dep, trb_st_hw)); trb_link->bph = upper_32_bits(dwc3_trb_dma_offset(dep, trb_st_hw)); @@ -588,7 +591,7 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) /* make sure HW endpoint isn't stalled */ if (dep->flags & DWC3_EP_STALL) - __dwc3_gadget_ep_set_halt(dep, 0); + __dwc3_gadget_ep_set_halt(dep, 0, false); reg = dwc3_readl(dwc->regs, DWC3_DALEPENA); reg &= ~DWC3_DALEPENA_EP(dep->number); @@ -888,8 +891,7 @@ static void dwc3_prepare_trbs(struct dwc3_ep *dep, bool starting) if (i == (request->num_mapped_sgs - 1) || sg_is_last(s)) { - if (list_is_last(&req->list, - &dep->request_list)) + if (list_empty(&dep->request_list)) last_one = true; chain = false; } @@ -907,6 +909,9 @@ static void dwc3_prepare_trbs(struct dwc3_ep *dep, bool starting) if (last_one) break; } + + if (last_one) + break; } else { dma = req->request.dma; length = req->request.length; @@ -1186,7 +1191,7 @@ out0: return ret; } -int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value) +int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol) { struct dwc3_gadget_ep_cmd_params params; struct dwc3 *dwc = dep->dwc; @@ -1195,6 +1200,14 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value) memset(¶ms, 0x00, sizeof(params)); if (value) { + if (!protocol && ((dep->direction && dep->flags & DWC3_EP_BUSY) || + (!list_empty(&dep->req_queued) || + !list_empty(&dep->request_list)))) { + dev_dbg(dwc->dev, "%s: pending request, cannot halt\n", + dep->name); + return -EAGAIN; + } + ret = dwc3_send_gadget_ep_cmd(dwc, dep->number, DWC3_DEPCMD_SETSTALL, ¶ms); if (ret) @@ -1234,7 +1247,7 @@ static int dwc3_gadget_ep_set_halt(struct usb_ep *ep, int value) goto out; } - ret = __dwc3_gadget_ep_set_halt(dep, value); + ret = __dwc3_gadget_ep_set_halt(dep, value, false); out: spin_unlock_irqrestore(&dwc->lock, flags); @@ -1254,7 +1267,7 @@ static int dwc3_gadget_ep_set_wedge(struct usb_ep *ep) if (dep->number == 0 || dep->number == 1) return dwc3_gadget_ep0_set_halt(ep, 1); else - return dwc3_gadget_ep_set_halt(ep, 1); + return __dwc3_gadget_ep_set_halt(dep, 1, false); } /* -------------------------------------------------------------------------- */ diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h index a0ee75b..ac625582 100644 --- a/drivers/usb/dwc3/gadget.h +++ b/drivers/usb/dwc3/gadget.h @@ -85,7 +85,7 @@ void dwc3_ep0_out_start(struct dwc3 *dwc); int dwc3_gadget_ep0_set_halt(struct usb_ep *ep, int value); int dwc3_gadget_ep0_queue(struct usb_ep *ep, struct usb_request *request, gfp_t gfp_flags); -int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value); +int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol); /** * dwc3_gadget_ep_get_transfer_index - Gets transfer index from HW diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index ebaae9a..a6101e0 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -445,7 +445,7 @@ config USB_GOKU gadget drivers to also be dynamically linked. config USB_EG20T - tristate "Intel EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC" + tristate "Intel QUARK X1000/EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC" depends on PCI help This is a USB device driver for EG20T PCH. @@ -466,6 +466,7 @@ config USB_EG20T ML7213/ML7831 is companion chip for Intel Atom E6xx series. ML7213/ML7831 is completely compatible for Intel EG20T PCH. + This driver can be used with Intel's Quark X1000 SOC platform # # LAST -- dummy/emulated controller # diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index d742bed..82df926 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -528,7 +528,7 @@ static int bos_desc(struct usb_composite_dev *cdev) usb_ext->bLength = USB_DT_USB_EXT_CAP_SIZE; usb_ext->bDescriptorType = USB_DT_DEVICE_CAPABILITY; usb_ext->bDevCapabilityType = USB_CAP_TYPE_EXT; - usb_ext->bmAttributes = cpu_to_le32(USB_LPM_SUPPORT); + usb_ext->bmAttributes = cpu_to_le32(USB_LPM_SUPPORT | USB_BESL_SUPPORT); /* * The Superspeed USB Capability descriptor shall be implemented by all diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 7d1cc01..3740a3f 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -765,6 +765,7 @@ static void purge_configs_funcs(struct gadget_info *gi) } } c->next_interface_id = 0; + memset(c->interface, 0, sizeof(c->interface)); c->superspeed = 0; c->highspeed = 0; c->fullspeed = 0; diff --git a/drivers/usb/gadget/f_acm.c b/drivers/usb/gadget/f_acm.c index ab1065a..3384486 100644 --- a/drivers/usb/gadget/f_acm.c +++ b/drivers/usb/gadget/f_acm.c @@ -430,11 +430,12 @@ static int acm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) if (acm->notify->driver_data) { VDBG(cdev, "reset acm control interface %d\n", intf); usb_ep_disable(acm->notify); - } else { - VDBG(cdev, "init acm ctrl interface %d\n", intf); + } + + if (!acm->notify->desc) if (config_ep_by_speed(cdev->gadget, f, acm->notify)) return -EINVAL; - } + usb_ep_enable(acm->notify); acm->notify->driver_data = acm; diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c index 5bcf7d0..afd0a15 100644 --- a/drivers/usb/gadget/f_fs.c +++ b/drivers/usb/gadget/f_fs.c @@ -1995,8 +1995,6 @@ static inline struct f_fs_opts *ffs_do_functionfs_bind(struct usb_function *f, func->conf = c; func->gadget = c->cdev->gadget; - ffs_data_get(func->ffs); - /* * in drivers/usb/gadget/configfs.c:configfs_composite_bind() * configurations are bound in sequence with list_for_each_entry, diff --git a/drivers/usb/gadget/pch_udc.c b/drivers/usb/gadget/pch_udc.c index eb8c3be..460d953 100644 --- a/drivers/usb/gadget/pch_udc.c +++ b/drivers/usb/gadget/pch_udc.c @@ -343,6 +343,7 @@ struct pch_vbus_gpio_data { * @setup_data: Received setup data * @phys_addr: of device memory * @base_addr: for mapped device memory + * @bar: Indicates which PCI BAR for USB regs * @irq: IRQ line for the device * @cfg_data: current cfg, intf, and alt in use * @vbus_gpio: GPIO informaton for detecting VBUS @@ -370,14 +371,17 @@ struct pch_udc_dev { struct usb_ctrlrequest setup_data; unsigned long phys_addr; void __iomem *base_addr; + unsigned bar; unsigned irq; struct pch_udc_cfg_data cfg_data; struct pch_vbus_gpio_data vbus_gpio; }; #define to_pch_udc(g) (container_of((g), struct pch_udc_dev, gadget)) +#define PCH_UDC_PCI_BAR_QUARK_X1000 0 #define PCH_UDC_PCI_BAR 1 #define PCI_DEVICE_ID_INTEL_EG20T_UDC 0x8808 +#define PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC 0x0939 #define PCI_VENDOR_ID_ROHM 0x10DB #define PCI_DEVICE_ID_ML7213_IOH_UDC 0x801D #define PCI_DEVICE_ID_ML7831_IOH_UDC 0x8808 @@ -3076,7 +3080,7 @@ static void pch_udc_remove(struct pci_dev *pdev) iounmap(dev->base_addr); if (dev->mem_region) release_mem_region(dev->phys_addr, - pci_resource_len(pdev, PCH_UDC_PCI_BAR)); + pci_resource_len(pdev, dev->bar)); if (dev->active) pci_disable_device(pdev); kfree(dev); @@ -3144,9 +3148,15 @@ static int pch_udc_probe(struct pci_dev *pdev, dev->active = 1; pci_set_drvdata(pdev, dev); + /* Determine BAR based on PCI ID */ + if (id->device == PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC) + dev->bar = PCH_UDC_PCI_BAR_QUARK_X1000; + else + dev->bar = PCH_UDC_PCI_BAR; + /* PCI resource allocation */ - resource = pci_resource_start(pdev, 1); - len = pci_resource_len(pdev, 1); + resource = pci_resource_start(pdev, dev->bar); + len = pci_resource_len(pdev, dev->bar); if (!request_mem_region(resource, len, KBUILD_MODNAME)) { dev_err(&pdev->dev, "%s: pci device used already\n", __func__); @@ -3212,6 +3222,12 @@ finished: static const struct pci_device_id pch_udc_pcidev_id[] = { { + PCI_DEVICE(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC), + .class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe, + .class_mask = 0xffffffff, + }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_EG20T_UDC), .class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe, .class_mask = 0xffffffff, diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c index 69b76ef..44e698c 100644 --- a/drivers/usb/gadget/printer.c +++ b/drivers/usb/gadget/printer.c @@ -975,6 +975,15 @@ unknown: break; } /* host either stalls (value < 0) or reports success */ + if (value >= 0) { + req->length = value; + req->zero = value < wLength; + value = usb_ep_queue(cdev->gadget->ep0, req, GFP_ATOMIC); + if (value < 0) { + ERROR(dev, "%s:%d Error!\n", __func__, __LINE__); + req->status = 0; + } + } return value; } diff --git a/drivers/usb/gadget/udc-core.c b/drivers/usb/gadget/udc-core.c index 27768a7..9ce0b13 100644 --- a/drivers/usb/gadget/udc-core.c +++ b/drivers/usb/gadget/udc-core.c @@ -456,6 +456,11 @@ static ssize_t usb_udc_softconn_store(struct device *dev, { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); + if (!udc->driver) { + dev_err(dev, "soft-connect without a gadget driver\n"); + return -EOPNOTSUPP; + } + if (sysfs_streq(buf, "connect")) { usb_gadget_udc_start(udc->gadget, udc->driver); usb_gadget_connect(udc->gadget); diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 142ebd8..1e0b9b9 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -792,12 +792,12 @@ static irqreturn_t ehci_irq (struct usb_hcd *hcd) ehci->reset_done[i] == 0)) continue; - /* start 20 msec resume signaling from this port, - * and make khubd collect PORT_STAT_C_SUSPEND to - * stop that signaling. Use 5 ms extra for safety, - * like usb_port_resume() does. + /* start USB_RESUME_TIMEOUT msec resume signaling from + * this port, and make hub_wq collect + * PORT_STAT_C_SUSPEND to stop that signaling. */ - ehci->reset_done[i] = jiffies + msecs_to_jiffies(25); + ehci->reset_done[i] = jiffies + + msecs_to_jiffies(USB_RESUME_TIMEOUT); set_bit(i, &ehci->resuming_ports); ehci_dbg (ehci, "port %d remote wakeup\n", i + 1); usb_hcd_start_port_resume(&hcd->self, i); @@ -970,8 +970,6 @@ rescan: } qh->exception = 1; - if (ehci->rh_state < EHCI_RH_RUNNING) - qh->qh_state = QH_STATE_IDLE; switch (qh->qh_state) { case QH_STATE_LINKED: WARN_ON(!list_empty(&qh->qtd_list)); diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index de63775..857953c 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -491,10 +491,13 @@ static int ehci_bus_resume (struct usb_hcd *hcd) ehci_writel(ehci, temp, &ehci->regs->port_status [i]); } - /* msleep for 20ms only if code is trying to resume port */ + /* + * msleep for USB_RESUME_TIMEOUT ms only if code is trying to resume + * port + */ if (resume_needed) { spin_unlock_irq(&ehci->lock); - msleep(20); + msleep(USB_RESUME_TIMEOUT); spin_lock_irq(&ehci->lock); if (ehci->shutdown) goto shutdown; @@ -962,7 +965,7 @@ static int ehci_hub_control ( temp &= ~PORT_WAKE_BITS; ehci_writel(ehci, temp | PORT_RESUME, status_reg); ehci->reset_done[wIndex] = jiffies - + msecs_to_jiffies(20); + + msecs_to_jiffies(USB_RESUME_TIMEOUT); set_bit(wIndex, &ehci->resuming_ports); usb_hcd_start_port_resume(&hcd->self, wIndex); break; @@ -1248,7 +1251,7 @@ static int ehci_hub_control ( if (selector == EHSET_TEST_SINGLE_STEP_SET_FEATURE) { spin_unlock_irqrestore(&ehci->lock, flags); retval = ehset_single_step_set_feature(hcd, - wIndex); + wIndex + 1); spin_lock_irqsave(&ehci->lock, flags); break; } diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index 3e86bf4..ca7b964 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -35,6 +35,21 @@ static const char hcd_name[] = "ehci-pci"; #define PCI_DEVICE_ID_INTEL_CE4100_USB 0x2e70 /*-------------------------------------------------------------------------*/ +#define PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC 0x0939 +static inline bool is_intel_quark_x1000(struct pci_dev *pdev) +{ + return pdev->vendor == PCI_VENDOR_ID_INTEL && + pdev->device == PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC; +} + +/* + * 0x84 is the offset of in/out threshold register, + * and it is the same offset as the register of 'hostpc'. + */ +#define intel_quark_x1000_insnreg01 hostpc + +/* Maximum usable threshold value is 0x7f dwords for both IN and OUT */ +#define INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD 0x007f007f /* called after powerup, by probe or system-pm "wakeup" */ static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev) @@ -50,6 +65,16 @@ static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev) if (!retval) ehci_dbg(ehci, "MWI active\n"); + /* Reset the threshold limit */ + if (is_intel_quark_x1000(pdev)) { + /* + * For the Intel QUARK X1000, raise the I/O threshold to the + * maximum usable value in order to improve performance. + */ + ehci_writel(ehci, INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD, + ehci->regs->intel_quark_x1000_insnreg01); + } + return 0; } diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c index e113fd7..c399606 100644 --- a/drivers/usb/host/ehci-sched.c +++ b/drivers/usb/host/ehci-sched.c @@ -1581,6 +1581,10 @@ iso_stream_schedule ( else next = (now + 2 + 7) & ~0x07; /* full frame cache */ + /* If needed, initialize last_iso_frame so that this URB will be seen */ + if (ehci->isoc_count == 0) + ehci->last_iso_frame = now >> 3; + /* * Use ehci->last_iso_frame as the base. There can't be any * TDs scheduled for earlier than that. @@ -1671,10 +1675,6 @@ iso_stream_schedule ( urb->start_frame = start & (mod - 1); if (!stream->highspeed) urb->start_frame >>= 3; - - /* Make sure scan_isoc() sees these */ - if (ehci->isoc_count == 0) - ehci->last_iso_frame = now >> 3; return status; fail: diff --git a/drivers/usb/host/ehci-sysfs.c b/drivers/usb/host/ehci-sysfs.c index f6459df..94054da 100644 --- a/drivers/usb/host/ehci-sysfs.c +++ b/drivers/usb/host/ehci-sysfs.c @@ -29,7 +29,7 @@ static ssize_t show_companion(struct device *dev, int count = PAGE_SIZE; char *ptr = buf; - ehci = hcd_to_ehci(bus_to_hcd(dev_get_drvdata(dev))); + ehci = hcd_to_ehci(dev_get_drvdata(dev)); nports = HCS_N_PORTS(ehci->hcs_params); for (index = 0; index < nports; ++index) { @@ -54,7 +54,7 @@ static ssize_t store_companion(struct device *dev, struct ehci_hcd *ehci; int portnum, new_owner; - ehci = hcd_to_ehci(bus_to_hcd(dev_get_drvdata(dev))); + ehci = hcd_to_ehci(dev_get_drvdata(dev)); new_owner = PORT_OWNER; /* Owned by companion */ if (sscanf(buf, "%d", &portnum) != 1) return -EINVAL; @@ -85,7 +85,7 @@ static ssize_t show_uframe_periodic_max(struct device *dev, struct ehci_hcd *ehci; int n; - ehci = hcd_to_ehci(bus_to_hcd(dev_get_drvdata(dev))); + ehci = hcd_to_ehci(dev_get_drvdata(dev)); n = scnprintf(buf, PAGE_SIZE, "%d\n", ehci->uframe_periodic_max); return n; } @@ -101,7 +101,7 @@ static ssize_t store_uframe_periodic_max(struct device *dev, unsigned long flags; ssize_t ret; - ehci = hcd_to_ehci(bus_to_hcd(dev_get_drvdata(dev))); + ehci = hcd_to_ehci(dev_get_drvdata(dev)); if (kstrtouint(buf, 0, &uframe_periodic_max) < 0) return -EINVAL; diff --git a/drivers/usb/host/fotg210-hcd.c b/drivers/usb/host/fotg210-hcd.c index 98a89d1..8aa4ba0 100644 --- a/drivers/usb/host/fotg210-hcd.c +++ b/drivers/usb/host/fotg210-hcd.c @@ -1595,7 +1595,7 @@ static int fotg210_hub_control( /* resume signaling for 20 msec */ fotg210_writel(fotg210, temp | PORT_RESUME, status_reg); fotg210->reset_done[wIndex] = jiffies - + msecs_to_jiffies(20); + + msecs_to_jiffies(USB_RESUME_TIMEOUT); break; case USB_PORT_FEAT_C_SUSPEND: clear_bit(wIndex, &fotg210->port_c_suspend); diff --git a/drivers/usb/host/fusbh200-hcd.c b/drivers/usb/host/fusbh200-hcd.c index ba94990..3e3926a 100644 --- a/drivers/usb/host/fusbh200-hcd.c +++ b/drivers/usb/host/fusbh200-hcd.c @@ -1550,10 +1550,9 @@ static int fusbh200_hub_control ( if ((temp & PORT_PE) == 0) goto error; - /* resume signaling for 20 msec */ fusbh200_writel(fusbh200, temp | PORT_RESUME, status_reg); fusbh200->reset_done[wIndex] = jiffies - + msecs_to_jiffies(20); + + msecs_to_jiffies(USB_RESUME_TIMEOUT); break; case USB_PORT_FEAT_C_SUSPEND: clear_bit(wIndex, &fusbh200->port_c_suspend); diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c index 240e792..b62298f 100644 --- a/drivers/usb/host/isp116x-hcd.c +++ b/drivers/usb/host/isp116x-hcd.c @@ -1487,7 +1487,7 @@ static int isp116x_bus_resume(struct usb_hcd *hcd) spin_unlock_irq(&isp116x->lock); hcd->state = HC_STATE_RESUMING; - msleep(20); + msleep(USB_RESUME_TIMEOUT); /* Go operational */ spin_lock_irq(&isp116x->lock); diff --git a/drivers/usb/host/ohci-dbg.c b/drivers/usb/host/ohci-dbg.c index 45032e9..04f2186 100644 --- a/drivers/usb/host/ohci-dbg.c +++ b/drivers/usb/host/ohci-dbg.c @@ -236,7 +236,7 @@ ohci_dump_roothub ( } } -static void ohci_dump (struct ohci_hcd *controller, int verbose) +static void ohci_dump(struct ohci_hcd *controller) { ohci_dbg (controller, "OHCI controller state\n"); @@ -464,15 +464,16 @@ show_list (struct ohci_hcd *ohci, char *buf, size_t count, struct ed *ed) static ssize_t fill_async_buffer(struct debug_buffer *buf) { struct ohci_hcd *ohci; - size_t temp; + size_t temp, size; unsigned long flags; ohci = buf->ohci; + size = PAGE_SIZE; /* display control and bulk lists together, for simplicity */ spin_lock_irqsave (&ohci->lock, flags); - temp = show_list(ohci, buf->page, buf->count, ohci->ed_controltail); - temp += show_list(ohci, buf->page + temp, buf->count - temp, + temp = show_list(ohci, buf->page, size, ohci->ed_controltail); + temp += show_list(ohci, buf->page + temp, size - temp, ohci->ed_bulktail); spin_unlock_irqrestore (&ohci->lock, flags); diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 3586460..34fc86c 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -76,8 +76,8 @@ static const char hcd_name [] = "ohci_hcd"; #include "ohci.h" #include "pci-quirks.h" -static void ohci_dump (struct ohci_hcd *ohci, int verbose); -static void ohci_stop (struct usb_hcd *hcd); +static void ohci_dump(struct ohci_hcd *ohci); +static void ohci_stop(struct usb_hcd *hcd); #include "ohci-hub.c" #include "ohci-dbg.c" @@ -744,7 +744,7 @@ retry: ohci->ed_to_check = NULL; } - ohci_dump (ohci, 1); + ohci_dump(ohci); return 0; } @@ -825,7 +825,7 @@ static irqreturn_t ohci_irq (struct usb_hcd *hcd) usb_hc_died(hcd); } - ohci_dump (ohci, 1); + ohci_dump(ohci); ohci_usb_reset (ohci); } @@ -925,7 +925,7 @@ static void ohci_stop (struct usb_hcd *hcd) { struct ohci_hcd *ohci = hcd_to_ohci (hcd); - ohci_dump (ohci, 1); + ohci_dump(ohci); if (quirk_nec(ohci)) flush_work(&ohci->nec_work); diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c index d4253e3..a8bde5b 100644 --- a/drivers/usb/host/ohci-q.c +++ b/drivers/usb/host/ohci-q.c @@ -311,8 +311,7 @@ static void periodic_unlink (struct ohci_hcd *ohci, struct ed *ed) * - ED_OPER: when there's any request queued, the ED gets rescheduled * immediately. HC should be working on them. * - * - ED_IDLE: when there's no TD queue. there's no reason for the HC - * to care about this ED; safe to disable the endpoint. + * - ED_IDLE: when there's no TD queue or the HC isn't running. * * When finish_unlinks() runs later, after SOF interrupt, it will often * complete one or more URB unlinks before making that state change. @@ -926,6 +925,10 @@ rescan_all: int completed, modified; __hc32 *prev; + /* Is this ED already invisible to the hardware? */ + if (ed->state == ED_IDLE) + goto ed_idle; + /* only take off EDs that the HC isn't using, accounting for * frame counter wraps and EDs with partially retired TDs */ @@ -955,12 +958,20 @@ skip_ed: } } + /* ED's now officially unlinked, hc doesn't see */ + ed->state = ED_IDLE; + if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT) + ohci->eds_scheduled--; + ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H); + ed->hwNextED = 0; + wmb(); + ed->hwINFO &= ~cpu_to_hc32(ohci, ED_SKIP | ED_DEQUEUE); +ed_idle: + /* reentrancy: if we drop the schedule lock, someone might * have modified this list. normally it's just prepending * entries (which we'd ignore), but paranoia won't hurt. */ - *last = ed->ed_next; - ed->ed_next = NULL; modified = 0; /* unlink urbs as requested, but rescan the list after @@ -1018,19 +1029,20 @@ rescan_this: if (completed && !list_empty (&ed->td_list)) goto rescan_this; - /* ED's now officially unlinked, hc doesn't see */ - ed->state = ED_IDLE; - if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT) - ohci->eds_scheduled--; - ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H); - ed->hwNextED = 0; - wmb (); - ed->hwINFO &= ~cpu_to_hc32 (ohci, ED_SKIP | ED_DEQUEUE); - - /* but if there's work queued, reschedule */ - if (!list_empty (&ed->td_list)) { - if (ohci->rh_state == OHCI_RH_RUNNING) - ed_schedule (ohci, ed); + /* + * If no TDs are queued, take ED off the ed_rm_list. + * Otherwise, if the HC is running, reschedule. + * If not, leave it on the list for further dequeues. + */ + if (list_empty(&ed->td_list)) { + *last = ed->ed_next; + ed->ed_next = NULL; + } else if (ohci->rh_state == OHCI_RH_RUNNING) { + *last = ed->ed_next; + ed->ed_next = NULL; + ed_schedule(ohci, ed); + } else { + last = &ed->ed_next; } if (modified) diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c index e07248b..1b1e6e0 100644 --- a/drivers/usb/host/oxu210hp-hcd.c +++ b/drivers/usb/host/oxu210hp-hcd.c @@ -2500,11 +2500,12 @@ static irqreturn_t oxu210_hcd_irq(struct usb_hcd *hcd) || oxu->reset_done[i] != 0) continue; - /* start 20 msec resume signaling from this port, - * and make khubd collect PORT_STAT_C_SUSPEND to + /* start USB_RESUME_TIMEOUT resume signaling from this + * port, and make hub_wq collect PORT_STAT_C_SUSPEND to * stop that signaling. */ - oxu->reset_done[i] = jiffies + msecs_to_jiffies(20); + oxu->reset_done[i] = jiffies + + msecs_to_jiffies(USB_RESUME_TIMEOUT); oxu_dbg(oxu, "port %d remote wakeup\n", i + 1); mod_timer(&hcd->rh_timer, oxu->reset_done[i]); } diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 2f3aceb..f4e6b94 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -571,7 +571,8 @@ static void quirk_usb_handoff_ohci(struct pci_dev *pdev) { void __iomem *base; u32 control; - u32 fminterval; + u32 fminterval = 0; + bool no_fminterval = false; int cnt; if (!mmio_resource_enabled(pdev, 0)) @@ -581,6 +582,13 @@ static void quirk_usb_handoff_ohci(struct pci_dev *pdev) if (base == NULL) return; + /* + * ULi M5237 OHCI controller locks the whole system when accessing + * the OHCI_FMINTERVAL offset. + */ + if (pdev->vendor == PCI_VENDOR_ID_AL && pdev->device == 0x5237) + no_fminterval = true; + control = readl(base + OHCI_CONTROL); /* On PA-RISC, PDC can leave IR set incorrectly; ignore it there. */ @@ -619,7 +627,9 @@ static void quirk_usb_handoff_ohci(struct pci_dev *pdev) } /* software reset of the controller, preserving HcFmInterval */ - fminterval = readl(base + OHCI_FMINTERVAL); + if (!no_fminterval) + fminterval = readl(base + OHCI_FMINTERVAL); + writel(OHCI_HCR, base + OHCI_CMDSTATUS); /* reset requires max 10 us delay */ @@ -628,7 +638,9 @@ static void quirk_usb_handoff_ohci(struct pci_dev *pdev) break; udelay(1); } - writel(fminterval, base + OHCI_FMINTERVAL); + + if (!no_fminterval) + writel(fminterval, base + OHCI_FMINTERVAL); /* Now the controller is safely in SUSPEND and nothing can wake it up */ iounmap(base); diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c index 110b4b9..f130bb2 100644 --- a/drivers/usb/host/r8a66597-hcd.c +++ b/drivers/usb/host/r8a66597-hcd.c @@ -2300,7 +2300,7 @@ static int r8a66597_bus_resume(struct usb_hcd *hcd) rh->port &= ~USB_PORT_STAT_SUSPEND; rh->port |= USB_PORT_STAT_C_SUSPEND << 16; r8a66597_mdfy(r8a66597, RESUME, RESUME | UACT, dvstctr_reg); - msleep(50); + msleep(USB_RESUME_TIMEOUT); r8a66597_mdfy(r8a66597, UACT, RESUME | UACT, dvstctr_reg); } diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c index a517151..0f53cc8 100644 --- a/drivers/usb/host/sl811-hcd.c +++ b/drivers/usb/host/sl811-hcd.c @@ -1259,7 +1259,7 @@ sl811h_hub_control( sl811_write(sl811, SL11H_CTLREG1, sl811->ctrl1); mod_timer(&sl811->timer, jiffies - + msecs_to_jiffies(20)); + + msecs_to_jiffies(USB_RESUME_TIMEOUT)); break; case USB_PORT_FEAT_POWER: port_power(sl811, 0); diff --git a/drivers/usb/host/uhci-hub.c b/drivers/usb/host/uhci-hub.c index 93e17b1..98c66d8 100644 --- a/drivers/usb/host/uhci-hub.c +++ b/drivers/usb/host/uhci-hub.c @@ -165,7 +165,7 @@ static void uhci_check_ports(struct uhci_hcd *uhci) /* Port received a wakeup request */ set_bit(port, &uhci->resuming_ports); uhci->ports_timeout = jiffies + - msecs_to_jiffies(25); + msecs_to_jiffies(USB_RESUME_TIMEOUT); usb_hcd_start_port_resume( &uhci_to_hcd(uhci)->self, port); @@ -337,7 +337,8 @@ static int uhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, uhci_finish_suspend(uhci, port, port_addr); /* USB v2.0 7.1.7.5 */ - uhci->ports_timeout = jiffies + msecs_to_jiffies(50); + uhci->ports_timeout = jiffies + + msecs_to_jiffies(USB_RESUME_TIMEOUT); break; case USB_PORT_FEAT_POWER: /* UHCI has no power switching */ diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 9992fbf..5c95765 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -383,6 +383,10 @@ static void xhci_clear_port_change_bit(struct xhci_hcd *xhci, u16 wValue, status = PORT_PLC; port_change_bit = "link state"; break; + case USB_PORT_FEAT_C_PORT_CONFIG_ERROR: + status = PORT_CEC; + port_change_bit = "config error"; + break; default: /* Should never happen */ return; @@ -470,15 +474,19 @@ static void xhci_hub_report_usb2_link_state(u32 *status, u32 status_reg) } /* Updates Link Status for super Speed port */ -static void xhci_hub_report_usb3_link_state(u32 *status, u32 status_reg) +static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci, + u32 *status, u32 status_reg) { u32 pls = status_reg & PORT_PLS_MASK; /* resume state is a xHCI internal state. - * Do not report it to usb core. + * Do not report it to usb core, instead, pretend to be U3, + * thus usb core knows it's not ready for transfer */ - if (pls == XDEV_RESUME) + if (pls == XDEV_RESUME) { + *status |= USB_SS_PORT_LS_U3; return; + } /* When the CAS bit is set then warm reset * should be performed on port @@ -509,7 +517,8 @@ static void xhci_hub_report_usb3_link_state(u32 *status, u32 status_reg) * in which sometimes the port enters compliance mode * caused by a delay on the host-device negotiation. */ - if (pls == USB_SS_PORT_LS_COMP_MOD) + if ((xhci->quirks & XHCI_COMP_MODE_QUIRK) && + (pls == USB_SS_PORT_LS_COMP_MOD)) pls |= USB_PORT_STAT_CONNECTION; } @@ -578,10 +587,19 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd, status |= USB_PORT_STAT_C_RESET << 16; /* USB3.0 only */ if (hcd->speed == HCD_USB3) { - if ((raw_port_status & PORT_PLC)) + /* Port link change with port in resume state should not be + * reported to usbcore, as this is an internal state to be + * handled by xhci driver. Reporting PLC to usbcore may + * cause usbcore clearing PLC first and port change event + * irq won't be generated. + */ + if ((raw_port_status & PORT_PLC) && + (raw_port_status & PORT_PLS_MASK) != XDEV_RESUME) status |= USB_PORT_STAT_C_LINK_STATE << 16; if ((raw_port_status & PORT_WRC)) status |= USB_PORT_STAT_C_BH_RESET << 16; + if ((raw_port_status & PORT_CEC)) + status |= USB_PORT_STAT_C_CONFIG_ERROR << 16; } if (hcd->speed != HCD_USB3) { @@ -668,7 +686,7 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd, } /* Update Port Link State */ if (hcd->speed == HCD_USB3) { - xhci_hub_report_usb3_link_state(&status, raw_port_status); + xhci_hub_report_usb3_link_state(xhci, &status, raw_port_status); /* * Verify if all USB3 Ports Have entered U0 already. * Delete Compliance Mode Timer if so. @@ -997,6 +1015,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, case USB_PORT_FEAT_C_OVER_CURRENT: case USB_PORT_FEAT_C_ENABLE: case USB_PORT_FEAT_C_PORT_LINK_STATE: + case USB_PORT_FEAT_C_PORT_CONFIG_ERROR: xhci_clear_port_change_bit(xhci, wValue, wIndex, port_array[wIndex], temp); break; @@ -1061,7 +1080,7 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf) */ status = bus_state->resuming_ports; - mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC; + mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC | PORT_CEC; spin_lock_irqsave(&xhci->lock, flags); /* For each port, did anything change? If so, set that bit in buf. */ @@ -1105,10 +1124,10 @@ int xhci_bus_suspend(struct usb_hcd *hcd) spin_lock_irqsave(&xhci->lock, flags); if (hcd->self.root_hub->do_remote_wakeup) { - if (bus_state->resuming_ports) { + if (bus_state->resuming_ports || /* USB2 */ + bus_state->port_remote_wakeup) { /* USB3 */ spin_unlock_irqrestore(&xhci->lock, flags); - xhci_dbg(xhci, "suspend failed because " - "a port is resuming\n"); + xhci_dbg(xhci, "suspend failed because a port is resuming\n"); return -EBUSY; } } diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 4133a00..f8893b3 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1331,10 +1331,10 @@ int xhci_endpoint_init(struct xhci_hcd *xhci, /* Attempt to use the ring cache */ if (virt_dev->num_rings_cached == 0) return -ENOMEM; + virt_dev->num_rings_cached--; virt_dev->eps[ep_index].new_ring = virt_dev->ring_cache[virt_dev->num_rings_cached]; virt_dev->ring_cache[virt_dev->num_rings_cached] = NULL; - virt_dev->num_rings_cached--; xhci_reinit_cached_ring(xhci, virt_dev->eps[ep_index].new_ring, 1, type); } @@ -1723,7 +1723,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci) } num_ports = HCS_MAX_PORTS(xhci->hcs_params1); - for (i = 0; i < num_ports; i++) { + for (i = 0; i < num_ports && xhci->rh_bw; i++) { struct xhci_interval_bw_table *bwt = &xhci->rh_bw[i].bw_table; for (j = 0; j < XHCI_MAX_INTERVAL; j++) { struct list_head *ep = &bwt->interval_bw[j].endpoints; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 08a5f92..eb3399f 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -101,9 +101,14 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) /* AMD PLL quirk */ if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info()) xhci->quirks |= XHCI_AMD_PLL_FIX; + + if (pdev->vendor == PCI_VENDOR_ID_AMD) + xhci->quirks |= XHCI_TRUST_TX_LENGTH; + if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; xhci->quirks |= XHCI_INTEL_HOST; + xhci->quirks |= XHCI_AVOID_BEI; } if (pdev->vendor == PCI_VENDOR_ID_INTEL && pdev->device == PCI_DEVICE_ID_INTEL_PANTHERPOINT_XHCI) { @@ -119,7 +124,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) * PPT chipsets. */ xhci->quirks |= XHCI_SPURIOUS_REBOOT; - xhci->quirks |= XHCI_AVOID_BEI; } if (pdev->vendor == PCI_VENDOR_ID_INTEL && (pdev->device == PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI || @@ -277,7 +281,7 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) if (xhci_compliance_mode_recovery_timer_quirk_check()) pdev->no_d3cold = true; - return xhci_suspend(xhci); + return xhci_suspend(xhci, do_wakeup); } static int xhci_pci_resume(struct usb_hcd *hcd, bool hibernated) diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 8abda5c..1d5ba3c 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -205,7 +205,15 @@ static int xhci_plat_suspend(struct device *dev) struct usb_hcd *hcd = dev_get_drvdata(dev); struct xhci_hcd *xhci = hcd_to_xhci(hcd); - return xhci_suspend(xhci); + /* + * xhci_suspend() needs `do_wakeup` to know whether host is allowed + * to do wakeup during suspend. Since xhci_plat_suspend is currently + * only designed for system suspend, device_may_wakeup() is enough + * to dertermine whether host is allowed to do wakeup. Need to + * reconsider this when xhci_plat_suspend enlarges its scope, e.g., + * also applies to runtime suspend. + */ + return xhci_suspend(xhci, device_may_wakeup(dev)); } static int xhci_plat_resume(struct device *dev) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 65091d9..a365e97 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -86,7 +86,7 @@ dma_addr_t xhci_trb_virt_to_dma(struct xhci_segment *seg, return 0; /* offset in TRBs */ segment_offset = trb - seg->trbs; - if (segment_offset > TRBS_PER_SEGMENT) + if (segment_offset >= TRBS_PER_SEGMENT) return 0; return seg->dma + (segment_offset * sizeof(*trb)); } @@ -1180,9 +1180,8 @@ static void xhci_handle_cmd_reset_ep(struct xhci_hcd *xhci, int slot_id, false); xhci_ring_cmd_db(xhci); } else { - /* Clear our internal halted state and restart the ring(s) */ + /* Clear our internal halted state */ xhci->devs[slot_id]->eps[ep_index].ep_state &= ~EP_HALTED; - ring_doorbell_for_active_rings(xhci, slot_id, ep_index); } } @@ -1741,6 +1740,9 @@ static void handle_port_status(struct xhci_hcd *xhci, usb_hcd_resume_root_hub(hcd); } + if (hcd->speed == HCD_USB3 && (temp & PORT_PLS_MASK) == XDEV_INACTIVE) + bus_state->port_remote_wakeup &= ~(1 << faked_port_index); + if ((temp & PORT_PLC) && (temp & PORT_PLS_MASK) == XDEV_RESUME) { xhci_dbg(xhci, "port resume event for port %d\n", port_id); @@ -1769,7 +1771,7 @@ static void handle_port_status(struct xhci_hcd *xhci, } else { xhci_dbg(xhci, "resume HS port %d\n", port_id); bus_state->resume_done[faked_port_index] = jiffies + - msecs_to_jiffies(20); + msecs_to_jiffies(USB_RESUME_TIMEOUT); set_bit(faked_port_index, &bus_state->resuming_ports); mod_timer(&hcd->rh_timer, bus_state->resume_done[faked_port_index]); @@ -1999,22 +2001,13 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, ep->stopped_td = td; return 0; } else { - if (trb_comp_code == COMP_STALL) { - /* The transfer is completed from the driver's - * perspective, but we need to issue a set dequeue - * command for this stalled endpoint to move the dequeue - * pointer past the TD. We can't do that here because - * the halt condition must be cleared first. Let the - * USB class driver clear the stall later. - */ - ep->stopped_td = td; - ep->stopped_stream = ep_ring->stream_id; - } else if (xhci_requires_manual_halt_cleanup(xhci, - ep_ctx, trb_comp_code)) { - /* Other types of errors halt the endpoint, but the - * class driver doesn't call usb_reset_endpoint() unless - * the error is -EPIPE. Clear the halted status in the - * xHCI hardware manually. + if (trb_comp_code == COMP_STALL || + xhci_requires_manual_halt_cleanup(xhci, ep_ctx, + trb_comp_code)) { + /* Issue a reset endpoint command to clear the host side + * halt, followed by a set dequeue command to move the + * dequeue pointer past the TD. + * The class driver clears the device side halt later. */ xhci_cleanup_halted_endpoint(xhci, slot_id, ep_index, ep_ring->stream_id, @@ -2134,9 +2127,7 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, else td->urb->actual_length = 0; - xhci_cleanup_halted_endpoint(xhci, - slot_id, ep_index, 0, td, event_trb); - return finish_td(xhci, td, event_trb, event, ep, status, true); + return finish_td(xhci, td, event_trb, event, ep, status, false); } /* * Did we transfer any data, despite the errors that might have @@ -2145,7 +2136,7 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, if (event_trb != ep_ring->dequeue) { /* The event was for the status stage */ if (event_trb == td->last_trb) { - if (td->urb->actual_length != 0) { + if (td->urb_length_set) { /* Don't overwrite a previously set error code */ if ((*status == -EINPROGRESS || *status == 0) && @@ -2159,7 +2150,13 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, td->urb->transfer_buffer_length; } } else { - /* Maybe the event was for the data stage? */ + /* + * Maybe the event was for the data stage? If so, update + * already the actual_length of the URB and flag it as + * set, so that it is not overwritten in the event for + * the last TRB. + */ + td->urb_length_set = true; td->urb->actual_length = td->urb->transfer_buffer_length - EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)); @@ -2219,8 +2216,13 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, break; case COMP_DEV_ERR: case COMP_STALL: + frame->status = -EPROTO; + skip_td = true; + break; case COMP_TX_ERR: frame->status = -EPROTO; + if (event_trb != td->last_trb) + return 0; skip_td = true; break; case COMP_STOP: @@ -2612,7 +2614,8 @@ static int handle_tx_event(struct xhci_hcd *xhci, * last TRB of the previous TD. The command completion handle * will take care the rest. */ - if (!event_seg && trb_comp_code == COMP_STOP_INVAL) { + if (!event_seg && (trb_comp_code == COMP_STOP || + trb_comp_code == COMP_STOP_INVAL)) { ret = 0; goto cleanup; } @@ -2689,17 +2692,8 @@ cleanup: if (ret) { urb = td->urb; urb_priv = urb->hcpriv; - /* Leave the TD around for the reset endpoint function - * to use(but only if it's not a control endpoint, - * since we already queued the Set TR dequeue pointer - * command for stalled control endpoints). - */ - if (usb_endpoint_xfer_control(&urb->ep->desc) || - (trb_comp_code != COMP_STALL && - trb_comp_code != COMP_BABBLE)) - xhci_urb_free_priv(xhci, urb_priv); - else - kfree(urb_priv); + + xhci_urb_free_priv(xhci, urb_priv); usb_hcd_unlink_urb_from_ep(bus_to_hcd(urb->dev->bus), urb); if ((urb->actual_length != urb->transfer_buffer_length && @@ -2836,7 +2830,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) xhci_halt(xhci); hw_died: spin_unlock(&xhci->lock); - return -ESHUTDOWN; + return IRQ_HANDLED; } /* diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index ab83104..fc61e663b 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -35,6 +35,8 @@ #define DRIVER_AUTHOR "Sarah Sharp" #define DRIVER_DESC "'eXtensible' Host Controller (xHC) Driver" +#define PORT_WAKE_BITS (PORT_WKOC_E | PORT_WKDISC_E | PORT_WKCONN_E) + /* Some 0.95 hardware can't handle the chain bit on a Link TRB being cleared */ static int link_quirk; module_param(link_quirk, int, S_IRUGO | S_IWUSR); @@ -842,13 +844,47 @@ static void xhci_clear_command_ring(struct xhci_hcd *xhci) xhci_set_cmd_ring_deq(xhci); } +static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci) +{ + int port_index; + __le32 __iomem **port_array; + unsigned long flags; + u32 t1, t2; + + spin_lock_irqsave(&xhci->lock, flags); + + /* disble usb3 ports Wake bits*/ + port_index = xhci->num_usb3_ports; + port_array = xhci->usb3_ports; + while (port_index--) { + t1 = readl(port_array[port_index]); + t1 = xhci_port_state_to_neutral(t1); + t2 = t1 & ~PORT_WAKE_BITS; + if (t1 != t2) + writel(t2, port_array[port_index]); + } + + /* disble usb2 ports Wake bits*/ + port_index = xhci->num_usb2_ports; + port_array = xhci->usb2_ports; + while (port_index--) { + t1 = readl(port_array[port_index]); + t1 = xhci_port_state_to_neutral(t1); + t2 = t1 & ~PORT_WAKE_BITS; + if (t1 != t2) + writel(t2, port_array[port_index]); + } + + spin_unlock_irqrestore(&xhci->lock, flags); +} + /* * Stop HC (not bus-specific) * * This is called when the machine transition into S3/S4 mode. * */ -int xhci_suspend(struct xhci_hcd *xhci) +int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup) { int rc = 0; unsigned int delay = XHCI_MAX_HALT_USEC; @@ -859,6 +895,10 @@ int xhci_suspend(struct xhci_hcd *xhci) xhci->shared_hcd->state != HC_STATE_SUSPENDED) return -EINVAL; + /* Clear root port wake on bits if wakeup not allowed. */ + if (!do_wakeup) + xhci_disable_port_wake_on_bits(xhci); + /* Don't poll the roothubs on bus suspend. */ xhci_dbg(xhci, "%s: stopping port polling.\n", __func__); clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); @@ -2885,63 +2925,33 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, } } -/* Deal with stalled endpoints. The core should have sent the control message - * to clear the halt condition. However, we need to make the xHCI hardware - * reset its sequence number, since a device will expect a sequence number of - * zero after the halt condition is cleared. +/* Called when clearing halted device. The core should have sent the control + * message to clear the device halt condition. The host side of the halt should + * already be cleared with a reset endpoint command issued when the STALL tx + * event was received. + * * Context: in_interrupt */ + void xhci_endpoint_reset(struct usb_hcd *hcd, struct usb_host_endpoint *ep) { struct xhci_hcd *xhci; - struct usb_device *udev; - unsigned int ep_index; - unsigned long flags; - int ret; - struct xhci_virt_ep *virt_ep; xhci = hcd_to_xhci(hcd); - udev = (struct usb_device *) ep->hcpriv; - /* Called with a root hub endpoint (or an endpoint that wasn't added - * with xhci_add_endpoint() - */ - if (!ep->hcpriv) - return; - ep_index = xhci_get_endpoint_index(&ep->desc); - virt_ep = &xhci->devs[udev->slot_id]->eps[ep_index]; - if (!virt_ep->stopped_td) { - xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep, - "Endpoint 0x%x not halted, refusing to reset.", - ep->desc.bEndpointAddress); - return; - } - if (usb_endpoint_xfer_control(&ep->desc)) { - xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep, - "Control endpoint stall already handled."); - return; - } - xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep, - "Queueing reset endpoint command"); - spin_lock_irqsave(&xhci->lock, flags); - ret = xhci_queue_reset_ep(xhci, udev->slot_id, ep_index); /* - * Can't change the ring dequeue pointer until it's transitioned to the - * stopped state, which is only upon a successful reset endpoint - * command. Better hope that last command worked! + * We might need to implement the config ep cmd in xhci 4.8.1 note: + * The Reset Endpoint Command may only be issued to endpoints in the + * Halted state. If software wishes reset the Data Toggle or Sequence + * Number of an endpoint that isn't in the Halted state, then software + * may issue a Configure Endpoint Command with the Drop and Add bits set + * for the target endpoint. that is in the Stopped state. */ - if (!ret) { - xhci_cleanup_stalled_ring(xhci, udev, ep_index); - kfree(virt_ep->stopped_td); - xhci_ring_cmd_db(xhci); - } - virt_ep->stopped_td = NULL; - virt_ep->stopped_stream = 0; - spin_unlock_irqrestore(&xhci->lock, flags); - if (ret) - xhci_warn(xhci, "FIXME allocate a new ring segment\n"); + /* For now just print debug to follow the situation */ + xhci_dbg(xhci, "Endpoint 0x%x ep reset callback called\n", + ep->desc.bEndpointAddress); } static int xhci_check_streams_endpoint(struct xhci_hcd *xhci, @@ -3414,6 +3424,9 @@ int xhci_discover_or_reset_device(struct usb_hcd *hcd, struct usb_device *udev) return -EINVAL; } + if (virt_dev->tt_info) + old_active_eps = virt_dev->tt_info->active_eps; + if (virt_dev->udev != udev) { /* If the virt_dev and the udev does not match, this virt_dev * may belong to another udev. @@ -3928,13 +3941,21 @@ static int __maybe_unused xhci_change_max_exit_latency(struct xhci_hcd *xhci, int ret; spin_lock_irqsave(&xhci->lock, flags); - if (max_exit_latency == xhci->devs[udev->slot_id]->current_mel) { + + virt_dev = xhci->devs[udev->slot_id]; + + /* + * virt_dev might not exists yet if xHC resumed from hibernate (S4) and + * xHC was re-initialized. Exit latency will be set later after + * hub_port_finish_reset() is done and xhci->devs[] are re-allocated + */ + + if (!virt_dev || max_exit_latency == virt_dev->current_mel) { spin_unlock_irqrestore(&xhci->lock, flags); return 0; } /* Attempt to issue an Evaluate Context command to change the MEL. */ - virt_dev = xhci->devs[udev->slot_id]; command = xhci->lpm_command; ctrl_ctx = xhci_get_input_control_ctx(xhci, command->in_ctx); if (!ctrl_ctx) { diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 8faef64..c167485 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1,3 +1,4 @@ + /* * xHCI host controller driver * @@ -88,9 +89,10 @@ struct xhci_cap_regs { #define HCS_IST(p) (((p) >> 0) & 0xf) /* bits 4:7, max number of Event Ring segments */ #define HCS_ERST_MAX(p) (((p) >> 4) & 0xf) +/* bits 21:25 Hi 5 bits of Scratchpad buffers SW must allocate for the HW */ /* bit 26 Scratchpad restore - for save/restore HW state - not used yet */ -/* bits 27:31 number of Scratchpad buffers SW must allocate for the HW */ -#define HCS_MAX_SCRATCHPAD(p) (((p) >> 27) & 0x1f) +/* bits 27:31 Lo 5 bits of Scratchpad buffers SW must allocate for the HW */ +#define HCS_MAX_SCRATCHPAD(p) ((((p) >> 16) & 0x3e0) | (((p) >> 27) & 0x1f)) /* HCSPARAMS3 - hcs_params3 - bitmasks */ /* bits 0:7, Max U1 to U0 latency for the roothub ports */ @@ -283,6 +285,7 @@ struct xhci_op_regs { #define XDEV_U0 (0x0 << 5) #define XDEV_U2 (0x2 << 5) #define XDEV_U3 (0x3 << 5) +#define XDEV_INACTIVE (0x6 << 5) #define XDEV_RESUME (0xf << 5) /* true: port has power (see HCC_PPC) */ #define PORT_POWER (1 << 9) @@ -1266,7 +1269,7 @@ union xhci_trb { * since the command ring is 64-byte aligned. * It must also be greater than 16. */ -#define TRBS_PER_SEGMENT 64 +#define TRBS_PER_SEGMENT 256 /* Allow two commands + a link TRB, along with any reserved command TRBs */ #define MAX_RSVD_CMD_TRBS (TRBS_PER_SEGMENT - 3) #define TRB_SEGMENT_SIZE (TRBS_PER_SEGMENT*16) @@ -1289,6 +1292,8 @@ struct xhci_td { struct xhci_segment *start_seg; union xhci_trb *first_trb; union xhci_trb *last_trb; + /* actual_length of the URB has already been set */ + bool urb_length_set; }; /* xHCI command default timeout value */ @@ -1760,7 +1765,7 @@ void xhci_shutdown(struct usb_hcd *hcd); int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks); #ifdef CONFIG_PM -int xhci_suspend(struct xhci_hcd *xhci); +int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup); int xhci_resume(struct xhci_hcd *xhci, bool hibernated); #else #define xhci_suspend NULL diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c index de98906..0aef801 100644 --- a/drivers/usb/misc/sisusbvga/sisusb.c +++ b/drivers/usb/misc/sisusbvga/sisusb.c @@ -3248,6 +3248,7 @@ static const struct usb_device_id sisusb_table[] = { { USB_DEVICE(0x0711, 0x0918) }, { USB_DEVICE(0x0711, 0x0920) }, { USB_DEVICE(0x0711, 0x0950) }, + { USB_DEVICE(0x0711, 0x5200) }, { USB_DEVICE(0x182d, 0x021c) }, { USB_DEVICE(0x182d, 0x0269) }, { } diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 0757690..ec69b90 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -99,6 +99,7 @@ #include #include #include +#include #include "musb_core.h" @@ -477,10 +478,11 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb, (USB_PORT_STAT_C_SUSPEND << 16) | MUSB_PORT_STAT_RESUME; musb->rh_timer = jiffies - + msecs_to_jiffies(20); + + msecs_to_jiffies(USB_RESUME_TIMEOUT); + schedule_delayed_work( &musb->finish_resume_work, - msecs_to_jiffies(20)); + msecs_to_jiffies(USB_RESUME_TIMEOUT)); musb->xceiv->state = OTG_STATE_A_HOST; musb->is_active = 1; diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c index c2d5afc..1d29bbf 100644 --- a/drivers/usb/musb/musb_cppi41.c +++ b/drivers/usb/musb/musb_cppi41.c @@ -190,7 +190,8 @@ static enum hrtimer_restart cppi41_recheck_tx_req(struct hrtimer *timer) } } - if (!list_empty(&controller->early_tx_list)) { + if (!list_empty(&controller->early_tx_list) && + !hrtimer_is_queued(&controller->early_tx)) { ret = HRTIMER_RESTART; hrtimer_forward_now(&controller->early_tx, ktime_set(0, 150 * NSEC_PER_USEC)); diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index 7a109ea..865243e 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -707,6 +707,7 @@ static int dsps_suspend(struct device *dev) struct musb *musb = platform_get_drvdata(glue->musb); void __iomem *mbase = musb->ctrl_base; + del_timer_sync(&glue->timer); glue->context.control = dsps_readl(mbase, wrp->control); glue->context.epintr = dsps_readl(mbase, wrp->epintr_set); glue->context.coreintr = dsps_readl(mbase, wrp->coreintr_set); @@ -732,6 +733,9 @@ static int dsps_resume(struct device *dev) dsps_writel(mbase, wrp->mode, glue->context.mode); dsps_writel(mbase, wrp->tx_mode, glue->context.tx_mode); dsps_writel(mbase, wrp->rx_mode, glue->context.rx_mode); + if (musb->xceiv->state == OTG_STATE_B_IDLE && + musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE) + mod_timer(&glue->timer, jiffies + wrp->poll_seconds * HZ); return 0; } diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index abb38c3..6b0fb6a 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -2640,7 +2640,6 @@ void musb_host_cleanup(struct musb *musb) if (musb->port_mode == MUSB_PORT_MODE_GADGET) return; usb_remove_hcd(musb->hcd); - musb->hcd = NULL; } void musb_host_free(struct musb *musb) diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c index e2d2d8c..1e9bde4 100644 --- a/drivers/usb/musb/musb_virthub.c +++ b/drivers/usb/musb/musb_virthub.c @@ -136,7 +136,7 @@ void musb_port_suspend(struct musb *musb, bool do_suspend) /* later, GetPortStatus will stop RESUME signaling */ musb->port1_status |= MUSB_PORT_STAT_RESUME; schedule_delayed_work(&musb->finish_resume_work, - msecs_to_jiffies(20)); + msecs_to_jiffies(USB_RESUME_TIMEOUT)); } } @@ -273,9 +273,7 @@ static int musb_has_gadget(struct musb *musb) #ifdef CONFIG_USB_MUSB_HOST return 1; #else - if (musb->port_mode == MUSB_PORT_MODE_HOST) - return 1; - return musb->g.dev.driver != NULL; + return musb->port_mode == MUSB_PORT_MODE_HOST; #endif } diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index bbe4f8e..8834b70 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -881,8 +881,8 @@ static int utmi_phy_probe(struct tegra_usb_phy *tegra_phy, return -ENOMEM; } - tegra_phy->config = devm_kzalloc(&pdev->dev, - sizeof(*tegra_phy->config), GFP_KERNEL); + tegra_phy->config = devm_kzalloc(&pdev->dev, sizeof(*config), + GFP_KERNEL); if (!tegra_phy->config) { dev_err(&pdev->dev, "unable to allocate memory for USB UTMIP config\n"); diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c index 8afa813..964ebaf 100644 --- a/drivers/usb/phy/phy.c +++ b/drivers/usb/phy/phy.c @@ -78,7 +78,9 @@ static void devm_usb_phy_release(struct device *dev, void *res) static int devm_usb_phy_match(struct device *dev, void *res, void *match_data) { - return res == match_data; + struct usb_phy **phy = res; + + return *phy == match_data; } /** @@ -229,6 +231,9 @@ struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index) phy = __usb_find_phy_dev(dev, &phy_bind_list, index); if (IS_ERR(phy) || !try_module_get(phy->dev->driver->owner)) { dev_dbg(dev, "unable to find transceiver\n"); + if (!IS_ERR(phy)) + phy = ERR_PTR(-ENODEV); + goto err0; } diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c index 9374bd2..6f91eb9 100644 --- a/drivers/usb/serial/bus.c +++ b/drivers/usb/serial/bus.c @@ -51,6 +51,7 @@ static int usb_serial_device_probe(struct device *dev) { struct usb_serial_driver *driver; struct usb_serial_port *port; + struct device *tty_dev; int retval = 0; int minor; @@ -75,12 +76,20 @@ static int usb_serial_device_probe(struct device *dev) retval = device_create_file(dev, &dev_attr_port_number); if (retval) { if (driver->port_remove) - retval = driver->port_remove(port); + driver->port_remove(port); goto exit_with_autopm; } minor = port->minor; - tty_register_device(usb_serial_tty_driver, minor, dev); + tty_dev = tty_register_device(usb_serial_tty_driver, minor, dev); + if (IS_ERR(tty_dev)) { + retval = PTR_ERR(tty_dev); + device_remove_file(dev, &dev_attr_port_number); + if (driver->port_remove) + driver->port_remove(port); + goto exit_with_autopm; + } + dev_info(&port->serial->dev->dev, "%s converter now attached to ttyUSB%d\n", driver->description, minor); diff --git a/drivers/usb/serial/console.c b/drivers/usb/serial/console.c index 8d7fc48..29fa1c3 100644 --- a/drivers/usb/serial/console.c +++ b/drivers/usb/serial/console.c @@ -46,6 +46,8 @@ static struct console usbcons; * ------------------------------------------------------------ */ +static const struct tty_operations usb_console_fake_tty_ops = { +}; /* * The parsing of the command line works exactly like the @@ -137,13 +139,17 @@ static int usb_console_setup(struct console *co, char *options) goto reset_open_count; } kref_init(&tty->kref); - tty_port_tty_set(&port->port, tty); tty->driver = usb_serial_tty_driver; tty->index = co->index; + init_ldsem(&tty->ldisc_sem); + INIT_LIST_HEAD(&tty->tty_files); + kref_get(&tty->driver->kref); + tty->ops = &usb_console_fake_tty_ops; if (tty_init_termios(tty)) { retval = -ENOMEM; - goto free_tty; + goto put_tty; } + tty_port_tty_set(&port->port, tty); } /* only call the device specific open if this @@ -161,7 +167,7 @@ static int usb_console_setup(struct console *co, char *options) serial->type->set_termios(tty, port, &dummy); tty_port_tty_set(&port->port, NULL); - kfree(tty); + tty_kref_put(tty); } set_bit(ASYNCB_INITIALIZED, &port->port.flags); } @@ -177,8 +183,8 @@ static int usb_console_setup(struct console *co, char *options) fail: tty_port_tty_set(&port->port, NULL); - free_tty: - kfree(tty); + put_tty: + tty_kref_put(tty); reset_open_count: port->port.count = 0; usb_autopm_put_interface(serial->interface); diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 330df5c..d11335d 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -56,6 +56,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x0846, 0x1100) }, /* NetGear Managed Switch M4100 series, M5300 series, M7100 series */ { USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */ { USB_DEVICE(0x08FD, 0x000A) }, /* Digianswer A/S , ZigBee/802.15.4 MAC Device */ + { USB_DEVICE(0x0908, 0x01FF) }, /* Siemens RUGGEDCOM USB Serial Console */ { USB_DEVICE(0x0BED, 0x1100) }, /* MEI (TM) Cashflow-SC Bill/Voucher Acceptor */ { USB_DEVICE(0x0BED, 0x1101) }, /* MEI series 2000 Combo Acceptor */ { USB_DEVICE(0x0FCF, 0x1003) }, /* Dynastream ANT development board */ @@ -120,8 +121,14 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */ { USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */ { USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */ + { USB_DEVICE(0x10C4, 0x8856) }, /* CEL EM357 ZigBee USB Stick - LR */ + { USB_DEVICE(0x10C4, 0x8857) }, /* CEL EM357 ZigBee USB Stick */ { USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */ { USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */ + { USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */ + { USB_DEVICE(0x10C4, 0x8977) }, /* CEL MeshWorks DevKit Device */ + { USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */ + { USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */ { USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */ @@ -142,6 +149,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x166A, 0x0305) }, /* Clipsal C-5000CT2 C-Bus Spectrum Colour Touchscreen */ { USB_DEVICE(0x166A, 0x0401) }, /* Clipsal L51xx C-Bus Architectural Dimmer */ { USB_DEVICE(0x166A, 0x0101) }, /* Clipsal 5560884 C-Bus Multi-room Audio Matrix Switcher */ + { USB_DEVICE(0x16C0, 0x09B0) }, /* Lunatico Seletek */ + { USB_DEVICE(0x16C0, 0x09B1) }, /* Lunatico Seletek */ { USB_DEVICE(0x16D6, 0x0001) }, /* Jablotron serial interface */ { USB_DEVICE(0x16DC, 0x0010) }, /* W-IE-NE-R Plein & Baus GmbH PL512 Power Supply */ { USB_DEVICE(0x16DC, 0x0011) }, /* W-IE-NE-R Plein & Baus GmbH RCM Remote Control for MARATON Power Supply */ @@ -154,7 +163,9 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ + { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ { USB_DEVICE(0x1BE3, 0x07A6) }, /* WAGO 750-923 USB Service Cable */ + { USB_DEVICE(0x1D6F, 0x0010) }, /* Seluxit ApS RF Dongle */ { USB_DEVICE(0x1E29, 0x0102) }, /* Festo CPX-USB */ { USB_DEVICE(0x1E29, 0x0501) }, /* Festo CMSP */ { USB_DEVICE(0x1FB9, 0x0100) }, /* Lake Shore Model 121 Current Source */ @@ -176,6 +187,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1FB9, 0x0602) }, /* Lake Shore Model 648 Magnet Power Supply */ { USB_DEVICE(0x1FB9, 0x0700) }, /* Lake Shore Model 737 VSM Controller */ { USB_DEVICE(0x1FB9, 0x0701) }, /* Lake Shore Model 776 Hall Matrix */ + { USB_DEVICE(0x2626, 0xEA60) }, /* Aruba Networks 7xxx USB Serial Console */ { USB_DEVICE(0x3195, 0xF190) }, /* Link Instruments MSO-19 */ { USB_DEVICE(0x3195, 0xF280) }, /* Link Instruments MSO-28 */ { USB_DEVICE(0x3195, 0xF281) }, /* Link Instruments MSO-28 */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 8a3813b..7fb81db 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -145,12 +145,14 @@ static struct ftdi_sio_quirk ftdi_8u2232c_quirk = { * /sys/bus/usb-serial/drivers/ftdi_sio/new_id and send a patch or report. */ static const struct usb_device_id id_table_combined[] = { + { USB_DEVICE(FTDI_VID, FTDI_BRICK_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ZEITCONTROL_TAGTRACE_MIFARE_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CTI_MINI_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CTI_NANO_PID) }, { USB_DEVICE(FTDI_VID, FTDI_AMC232_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CANUSB_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CANDAPTER_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_BM_ATOM_NANO_PID) }, { USB_DEVICE(FTDI_VID, FTDI_NXTCAM_PID) }, { USB_DEVICE(FTDI_VID, FTDI_EV3CON_PID) }, { USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_0_PID) }, @@ -481,6 +483,39 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FD_PID) }, { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FE_PID) }, { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FF_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_4701_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9300_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9301_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9302_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9303_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9304_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9305_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9306_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9307_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9308_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9309_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930A_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930B_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930C_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930D_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930E_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930F_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9310_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9311_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9312_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9313_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9314_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9315_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9316_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9317_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9318_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9319_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931A_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931B_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931C_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931D_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931E_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931F_PID) }, { USB_DEVICE(FTDI_VID, FTDI_PERLE_ULTRAPORT_PID) }, { USB_DEVICE(FTDI_VID, FTDI_PIEGROUP_PID) }, { USB_DEVICE(FTDI_VID, FTDI_TNC_X_PID) }, @@ -582,6 +617,11 @@ static const struct usb_device_id id_table_combined[] = { .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLXM_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE(FTDI_VID, FTDI_SYNAPSE_SS200_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX2_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX2WI_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX3_PID) }, /* * ELV devices: */ @@ -673,6 +713,11 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_5_PID) }, { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_6_PID) }, { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_7_PID) }, + { USB_DEVICE(XSENS_VID, XSENS_AWINDA_DONGLE_PID) }, + { USB_DEVICE(XSENS_VID, XSENS_AWINDA_STATION_PID) }, + { USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) }, + { USB_DEVICE(XSENS_VID, XSENS_MTDEVBOARD_PID) }, + { USB_DEVICE(XSENS_VID, XSENS_MTW_PID) }, { USB_DEVICE(FTDI_VID, FTDI_OMNI1509) }, { USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ACTIVE_ROBOTS_PID) }, @@ -738,6 +783,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_NDI_AURORA_SCU_PID), .driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk }, { USB_DEVICE(TELLDUS_VID, TELLDUS_TELLSTICK_PID) }, + { USB_DEVICE(NOVITUS_VID, NOVITUS_BONO_E_PID) }, { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_S03_PID) }, { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_59_PID) }, { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_57A_PID) }, @@ -772,6 +818,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_ELSTER_UNICOM_PID) }, { USB_DEVICE(FTDI_VID, FTDI_PROPOX_JTAGCABLEII_PID) }, { USB_DEVICE(FTDI_VID, FTDI_PROPOX_ISPCABLEIII_PID) }, + { USB_DEVICE(FTDI_VID, CYBER_CORTEX_AV_PID), + .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID), @@ -945,8 +993,29 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_2_PID) }, { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_3_PID) }, { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_4_PID) }, + /* ekey Devices */ + { USB_DEVICE(FTDI_VID, FTDI_EKEY_CONV_USB_PID) }, /* Infineon Devices */ { USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_PID, 1) }, + /* GE Healthcare devices */ + { USB_DEVICE(GE_HEALTHCARE_VID, GE_HEALTHCARE_NEMO_TRACKER_PID) }, + /* Active Research (Actisense) devices */ + { USB_DEVICE(FTDI_VID, ACTISENSE_NDC_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_USG_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_NGT_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_NGW_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_D9AC_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_D9AD_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_D9AE_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_D9AF_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEAGAUGE_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASWITCH_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_NMEA2000_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_ETHERNET_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_WIFI_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_DISPLAY_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_LITE_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_ANALOG_PID) }, { } /* Terminating entry */ }; @@ -1838,8 +1907,12 @@ static int ftdi_8u2232c_probe(struct usb_serial *serial) { struct usb_device *udev = serial->dev; - if ((udev->manufacturer && !strcmp(udev->manufacturer, "CALAO Systems")) || - (udev->product && !strcmp(udev->product, "BeagleBone/XDS100V2"))) + if (udev->manufacturer && !strcmp(udev->manufacturer, "CALAO Systems")) + return ftdi_jtag_probe(serial); + + if (udev->product && + (!strcmp(udev->product, "BeagleBone/XDS100V2") || + !strcmp(udev->product, "SNAP Connect E10"))) return ftdi_jtag_probe(serial); return 0; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index c4777bc..2943b97 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -30,8 +30,17 @@ /*** third-party PIDs (using FTDI_VID) ***/ +/* + * Certain versions of the official Windows FTDI driver reprogrammed + * counterfeit FTDI devices to PID 0. Support these devices anyway. + */ +#define FTDI_BRICK_PID 0x0000 + #define FTDI_LUMEL_PD12_PID 0x6002 +/* Cyber Cortex AV by Fabulous Silicon (http://fabuloussilicon.com) */ +#define CYBER_CORTEX_AV_PID 0x8698 + /* * Marvell OpenRD Base, Client * http://www.open-rd.org @@ -42,6 +51,8 @@ /* www.candapter.com Ewert Energy Systems CANdapter device */ #define FTDI_CANDAPTER_PID 0x9F80 /* Product Id */ +#define FTDI_BM_ATOM_NANO_PID 0xa559 /* Basic Micro ATOM Nano USB2Serial */ + /* * Texas Instruments XDS100v2 JTAG / BeagleBone A3 * http://processors.wiki.ti.com/index.php/XDS100 @@ -140,12 +151,20 @@ /* * Xsens Technologies BV products (http://www.xsens.com). */ -#define XSENS_CONVERTER_0_PID 0xD388 -#define XSENS_CONVERTER_1_PID 0xD389 +#define XSENS_VID 0x2639 +#define XSENS_AWINDA_STATION_PID 0x0101 +#define XSENS_AWINDA_DONGLE_PID 0x0102 +#define XSENS_MTW_PID 0x0200 /* Xsens MTw */ +#define XSENS_MTDEVBOARD_PID 0x0300 /* Motion Tracker Development Board */ +#define XSENS_CONVERTER_PID 0xD00D /* Xsens USB-serial converter */ + +/* Xsens devices using FTDI VID */ +#define XSENS_CONVERTER_0_PID 0xD388 /* Xsens USB converter */ +#define XSENS_CONVERTER_1_PID 0xD389 /* Xsens Wireless Receiver */ #define XSENS_CONVERTER_2_PID 0xD38A -#define XSENS_CONVERTER_3_PID 0xD38B -#define XSENS_CONVERTER_4_PID 0xD38C -#define XSENS_CONVERTER_5_PID 0xD38D +#define XSENS_CONVERTER_3_PID 0xD38B /* Xsens USB-serial converter */ +#define XSENS_CONVERTER_4_PID 0xD38C /* Xsens Wireless Receiver */ +#define XSENS_CONVERTER_5_PID 0xD38D /* Xsens Awinda Station */ #define XSENS_CONVERTER_6_PID 0xD38E #define XSENS_CONVERTER_7_PID 0xD38F @@ -543,6 +562,20 @@ */ #define FTDI_NT_ORIONLXM_PID 0x7c90 /* OrionLXm Substation Automation Platform */ +/* + * Synapse Wireless product ids (FTDI_VID) + * http://www.synapse-wireless.com + */ +#define FTDI_SYNAPSE_SS200_PID 0x9090 /* SS200 - SNAP Stick 200 */ + +/* + * CustomWare / ShipModul NMEA multiplexers product ids (FTDI_VID) + */ +#define FTDI_CUSTOMWARE_MINIPLEX_PID 0xfd48 /* MiniPlex first generation NMEA Multiplexer */ +#define FTDI_CUSTOMWARE_MINIPLEX2_PID 0xfd49 /* MiniPlex-USB and MiniPlex-2 series */ +#define FTDI_CUSTOMWARE_MINIPLEX2WI_PID 0xfd4a /* MiniPlex-2Wi */ +#define FTDI_CUSTOMWARE_MINIPLEX3_PID 0xfd4b /* MiniPlex-3 series */ + /********************************/ /** third-party VID/PID combos **/ @@ -832,6 +865,12 @@ #define TELLDUS_TELLSTICK_PID 0x0C30 /* RF control dongle 433 MHz using FT232RL */ /* + * NOVITUS printers + */ +#define NOVITUS_VID 0x1a28 +#define NOVITUS_BONO_E_PID 0x6010 + +/* * RT Systems programming cables for various ham radios */ #define RTSYSTEMS_VID 0x2100 /* Vendor ID */ @@ -905,8 +944,8 @@ #define BAYER_CONTOUR_CABLE_PID 0x6001 /* - * The following are the values for the Matrix Orbital FTDI Range - * Anything in this range will use an FT232RL. + * Matrix Orbital Intelligent USB displays. + * http://www.matrixorbital.com */ #define MTXORB_VID 0x1B3D #define MTXORB_FTDI_RANGE_0100_PID 0x0100 @@ -1165,8 +1204,39 @@ #define MTXORB_FTDI_RANGE_01FD_PID 0x01FD #define MTXORB_FTDI_RANGE_01FE_PID 0x01FE #define MTXORB_FTDI_RANGE_01FF_PID 0x01FF - - +#define MTXORB_FTDI_RANGE_4701_PID 0x4701 +#define MTXORB_FTDI_RANGE_9300_PID 0x9300 +#define MTXORB_FTDI_RANGE_9301_PID 0x9301 +#define MTXORB_FTDI_RANGE_9302_PID 0x9302 +#define MTXORB_FTDI_RANGE_9303_PID 0x9303 +#define MTXORB_FTDI_RANGE_9304_PID 0x9304 +#define MTXORB_FTDI_RANGE_9305_PID 0x9305 +#define MTXORB_FTDI_RANGE_9306_PID 0x9306 +#define MTXORB_FTDI_RANGE_9307_PID 0x9307 +#define MTXORB_FTDI_RANGE_9308_PID 0x9308 +#define MTXORB_FTDI_RANGE_9309_PID 0x9309 +#define MTXORB_FTDI_RANGE_930A_PID 0x930A +#define MTXORB_FTDI_RANGE_930B_PID 0x930B +#define MTXORB_FTDI_RANGE_930C_PID 0x930C +#define MTXORB_FTDI_RANGE_930D_PID 0x930D +#define MTXORB_FTDI_RANGE_930E_PID 0x930E +#define MTXORB_FTDI_RANGE_930F_PID 0x930F +#define MTXORB_FTDI_RANGE_9310_PID 0x9310 +#define MTXORB_FTDI_RANGE_9311_PID 0x9311 +#define MTXORB_FTDI_RANGE_9312_PID 0x9312 +#define MTXORB_FTDI_RANGE_9313_PID 0x9313 +#define MTXORB_FTDI_RANGE_9314_PID 0x9314 +#define MTXORB_FTDI_RANGE_9315_PID 0x9315 +#define MTXORB_FTDI_RANGE_9316_PID 0x9316 +#define MTXORB_FTDI_RANGE_9317_PID 0x9317 +#define MTXORB_FTDI_RANGE_9318_PID 0x9318 +#define MTXORB_FTDI_RANGE_9319_PID 0x9319 +#define MTXORB_FTDI_RANGE_931A_PID 0x931A +#define MTXORB_FTDI_RANGE_931B_PID 0x931B +#define MTXORB_FTDI_RANGE_931C_PID 0x931C +#define MTXORB_FTDI_RANGE_931D_PID 0x931D +#define MTXORB_FTDI_RANGE_931E_PID 0x931E +#define MTXORB_FTDI_RANGE_931F_PID 0x931F /* * The Mobility Lab (TML) @@ -1375,3 +1445,34 @@ #define BRAINBOXES_US_160_6_PID 0x9006 /* US-160 16xRS232 1Mbaud Port 11 and 12 */ #define BRAINBOXES_US_160_7_PID 0x9007 /* US-160 16xRS232 1Mbaud Port 13 and 14 */ #define BRAINBOXES_US_160_8_PID 0x9008 /* US-160 16xRS232 1Mbaud Port 15 and 16 */ + +/* + * ekey biometric systems GmbH (http://ekey.net/) + */ +#define FTDI_EKEY_CONV_USB_PID 0xCB08 /* Converter USB */ + +/* + * GE Healthcare devices + */ +#define GE_HEALTHCARE_VID 0x1901 +#define GE_HEALTHCARE_NEMO_TRACKER_PID 0x0015 + +/* + * Active Research (Actisense) devices + */ +#define ACTISENSE_NDC_PID 0xD9A8 /* NDC USB Serial Adapter */ +#define ACTISENSE_USG_PID 0xD9A9 /* USG USB Serial Adapter */ +#define ACTISENSE_NGT_PID 0xD9AA /* NGT NMEA2000 Interface */ +#define ACTISENSE_NGW_PID 0xD9AB /* NGW NMEA2000 Gateway */ +#define ACTISENSE_D9AC_PID 0xD9AC /* Actisense Reserved */ +#define ACTISENSE_D9AD_PID 0xD9AD /* Actisense Reserved */ +#define ACTISENSE_D9AE_PID 0xD9AE /* Actisense Reserved */ +#define ACTISENSE_D9AF_PID 0xD9AF /* Actisense Reserved */ +#define CHETCO_SEAGAUGE_PID 0xA548 /* SeaGauge USB Adapter */ +#define CHETCO_SEASWITCH_PID 0xA549 /* SeaSwitch USB Adapter */ +#define CHETCO_SEASMART_NMEA2000_PID 0xA54A /* SeaSmart NMEA2000 Gateway */ +#define CHETCO_SEASMART_ETHERNET_PID 0xA54B /* SeaSmart Ethernet Gateway */ +#define CHETCO_SEASMART_WIFI_PID 0xA5AC /* SeaSmart Wifi Gateway */ +#define CHETCO_SEASMART_DISPLAY_PID 0xA5AD /* SeaSmart NMEA2000 Display */ +#define CHETCO_SEASMART_LITE_PID 0xA5AE /* SeaSmart Lite USB Adapter */ +#define CHETCO_SEASMART_ANALOG_PID 0xA5AF /* SeaSmart Analog Adapter */ diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c index b63ce02..d6a1979 100644 --- a/drivers/usb/serial/generic.c +++ b/drivers/usb/serial/generic.c @@ -258,7 +258,8 @@ void usb_serial_generic_wait_until_sent(struct tty_struct *tty, long timeout) * character or at least one jiffy. */ period = max_t(unsigned long, (10 * HZ / bps), 1); - period = min_t(unsigned long, period, timeout); + if (timeout) + period = min_t(unsigned long, period, timeout); dev_dbg(&port->dev, "%s - timeout = %u ms, period = %u ms\n", __func__, jiffies_to_msecs(timeout), @@ -268,7 +269,7 @@ void usb_serial_generic_wait_until_sent(struct tty_struct *tty, long timeout) schedule_timeout_interruptible(period); if (signal_pending(current)) break; - if (time_after(jiffies, expire)) + if (timeout && time_after(jiffies, expire)) break; } } diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c index 265c677..35297a8 100644 --- a/drivers/usb/serial/keyspan.c +++ b/drivers/usb/serial/keyspan.c @@ -311,24 +311,30 @@ static void usa26_indat_callback(struct urb *urb) if ((data[0] & 0x80) == 0) { /* no errors on individual bytes, only possible overrun err */ - if (data[0] & RXERROR_OVERRUN) - err = TTY_OVERRUN; - else - err = 0; + if (data[0] & RXERROR_OVERRUN) { + tty_insert_flip_char(&port->port, 0, + TTY_OVERRUN); + } for (i = 1; i < urb->actual_length ; ++i) - tty_insert_flip_char(&port->port, data[i], err); + tty_insert_flip_char(&port->port, data[i], + TTY_NORMAL); } else { /* some bytes had errors, every byte has status */ dev_dbg(&port->dev, "%s - RX error!!!!\n", __func__); for (i = 0; i + 1 < urb->actual_length; i += 2) { - int stat = data[i], flag = 0; - if (stat & RXERROR_OVERRUN) - flag |= TTY_OVERRUN; - if (stat & RXERROR_FRAMING) - flag |= TTY_FRAME; - if (stat & RXERROR_PARITY) - flag |= TTY_PARITY; + int stat = data[i]; + int flag = TTY_NORMAL; + + if (stat & RXERROR_OVERRUN) { + tty_insert_flip_char(&port->port, 0, + TTY_OVERRUN); + } /* XXX should handle break (0x10) */ + if (stat & RXERROR_PARITY) + flag = TTY_PARITY; + else if (stat & RXERROR_FRAMING) + flag = TTY_FRAME; + tty_insert_flip_char(&port->port, data[i+1], flag); } @@ -415,6 +421,8 @@ static void usa26_instat_callback(struct urb *urb) } port = serial->port[msg->port]; p_priv = usb_get_serial_port_data(port); + if (!p_priv) + goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; @@ -425,7 +433,7 @@ static void usa26_instat_callback(struct urb *urb) if (old_dcd_state != p_priv->dcd_state) tty_port_tty_hangup(&port->port, true); - +resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) @@ -535,6 +543,8 @@ static void usa28_instat_callback(struct urb *urb) } port = serial->port[msg->port]; p_priv = usb_get_serial_port_data(port); + if (!p_priv) + goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; @@ -545,7 +555,7 @@ static void usa28_instat_callback(struct urb *urb) if (old_dcd_state != p_priv->dcd_state && old_dcd_state) tty_port_tty_hangup(&port->port, true); - +resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) @@ -618,6 +628,8 @@ static void usa49_instat_callback(struct urb *urb) } port = serial->port[msg->portNumber]; p_priv = usb_get_serial_port_data(port); + if (!p_priv) + goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; @@ -628,7 +640,7 @@ static void usa49_instat_callback(struct urb *urb) if (old_dcd_state != p_priv->dcd_state && old_dcd_state) tty_port_tty_hangup(&port->port, true); - +resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) @@ -666,14 +678,19 @@ static void usa49_indat_callback(struct urb *urb) } else { /* some bytes had errors, every byte has status */ for (i = 0; i + 1 < urb->actual_length; i += 2) { - int stat = data[i], flag = 0; - if (stat & RXERROR_OVERRUN) - flag |= TTY_OVERRUN; - if (stat & RXERROR_FRAMING) - flag |= TTY_FRAME; - if (stat & RXERROR_PARITY) - flag |= TTY_PARITY; + int stat = data[i]; + int flag = TTY_NORMAL; + + if (stat & RXERROR_OVERRUN) { + tty_insert_flip_char(&port->port, 0, + TTY_OVERRUN); + } /* XXX should handle break (0x10) */ + if (stat & RXERROR_PARITY) + flag = TTY_PARITY; + else if (stat & RXERROR_FRAMING) + flag = TTY_FRAME; + tty_insert_flip_char(&port->port, data[i+1], flag); } @@ -730,15 +747,19 @@ static void usa49wg_indat_callback(struct urb *urb) */ for (x = 0; x + 1 < len && i + 1 < urb->actual_length; x += 2) { - int stat = data[i], flag = 0; + int stat = data[i]; + int flag = TTY_NORMAL; - if (stat & RXERROR_OVERRUN) - flag |= TTY_OVERRUN; - if (stat & RXERROR_FRAMING) - flag |= TTY_FRAME; - if (stat & RXERROR_PARITY) - flag |= TTY_PARITY; + if (stat & RXERROR_OVERRUN) { + tty_insert_flip_char(&port->port, 0, + TTY_OVERRUN); + } /* XXX should handle break (0x10) */ + if (stat & RXERROR_PARITY) + flag = TTY_PARITY; + else if (stat & RXERROR_FRAMING) + flag = TTY_FRAME; + tty_insert_flip_char(&port->port, data[i+1], flag); i += 2; @@ -790,25 +811,31 @@ static void usa90_indat_callback(struct urb *urb) if ((data[0] & 0x80) == 0) { /* no errors on individual bytes, only possible overrun err*/ - if (data[0] & RXERROR_OVERRUN) - err = TTY_OVERRUN; - else - err = 0; + if (data[0] & RXERROR_OVERRUN) { + tty_insert_flip_char(&port->port, 0, + TTY_OVERRUN); + } for (i = 1; i < urb->actual_length ; ++i) tty_insert_flip_char(&port->port, - data[i], err); + data[i], TTY_NORMAL); } else { /* some bytes had errors, every byte has status */ dev_dbg(&port->dev, "%s - RX error!!!!\n", __func__); for (i = 0; i + 1 < urb->actual_length; i += 2) { - int stat = data[i], flag = 0; - if (stat & RXERROR_OVERRUN) - flag |= TTY_OVERRUN; - if (stat & RXERROR_FRAMING) - flag |= TTY_FRAME; - if (stat & RXERROR_PARITY) - flag |= TTY_PARITY; + int stat = data[i]; + int flag = TTY_NORMAL; + + if (stat & RXERROR_OVERRUN) { + tty_insert_flip_char( + &port->port, 0, + TTY_OVERRUN); + } /* XXX should handle break (0x10) */ + if (stat & RXERROR_PARITY) + flag = TTY_PARITY; + else if (stat & RXERROR_FRAMING) + flag = TTY_FRAME; + tty_insert_flip_char(&port->port, data[i+1], flag); } @@ -851,6 +878,8 @@ static void usa90_instat_callback(struct urb *urb) port = serial->port[0]; p_priv = usb_get_serial_port_data(port); + if (!p_priv) + goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; @@ -861,7 +890,7 @@ static void usa90_instat_callback(struct urb *urb) if (old_dcd_state != p_priv->dcd_state && old_dcd_state) tty_port_tty_hangup(&port->port, true); - +resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) @@ -922,6 +951,8 @@ static void usa67_instat_callback(struct urb *urb) port = serial->port[msg->port]; p_priv = usb_get_serial_port_data(port); + if (!p_priv) + goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; @@ -930,7 +961,7 @@ static void usa67_instat_callback(struct urb *urb) if (old_dcd_state != p_priv->dcd_state && old_dcd_state) tty_port_tty_hangup(&port->port, true); - +resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) diff --git a/drivers/usb/serial/kobil_sct.c b/drivers/usb/serial/kobil_sct.c index 618c1c1..5cdb32b 100644 --- a/drivers/usb/serial/kobil_sct.c +++ b/drivers/usb/serial/kobil_sct.c @@ -335,7 +335,8 @@ static int kobil_write(struct tty_struct *tty, struct usb_serial_port *port, port->interrupt_out_urb->transfer_buffer_length = length; priv->cur_pos = priv->cur_pos + length; - result = usb_submit_urb(port->interrupt_out_urb, GFP_NOIO); + result = usb_submit_urb(port->interrupt_out_urb, + GFP_ATOMIC); dev_dbg(&port->dev, "%s - Send write URB returns: %i\n", __func__, result); todo = priv->filled - priv->cur_pos; @@ -350,7 +351,7 @@ static int kobil_write(struct tty_struct *tty, struct usb_serial_port *port, if (priv->device_type == KOBIL_ADAPTER_B_PRODUCT_ID || priv->device_type == KOBIL_ADAPTER_K_PRODUCT_ID) { result = usb_submit_urb(port->interrupt_in_urb, - GFP_NOIO); + GFP_ATOMIC); dev_dbg(&port->dev, "%s - Send read URB returns: %i\n", __func__, result); } } diff --git a/drivers/usb/serial/mxuport.c b/drivers/usb/serial/mxuport.c index ab1d690..460a406 100644 --- a/drivers/usb/serial/mxuport.c +++ b/drivers/usb/serial/mxuport.c @@ -1284,7 +1284,8 @@ static int mxuport_open(struct tty_struct *tty, struct usb_serial_port *port) } /* Initial port termios */ - mxuport_set_termios(tty, port, NULL); + if (tty) + mxuport_set_termios(tty, port, NULL); /* * TODO: use RQ_VENDOR_GET_MSR, once we know what it diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c index 4856fb7..4b7bfb3 100644 --- a/drivers/usb/serial/opticon.c +++ b/drivers/usb/serial/opticon.c @@ -215,7 +215,7 @@ static int opticon_write(struct tty_struct *tty, struct usb_serial_port *port, /* The connected devices do not have a bulk write endpoint, * to transmit data to de barcode device the control endpoint is used */ - dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_NOIO); + dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_ATOMIC); if (!dr) { count = -ENOMEM; goto error_no_dr; diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 240c073..096438e 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -269,14 +269,19 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_DE910_DUAL 0x1010 #define TELIT_PRODUCT_UE910_V2 0x1012 #define TELIT_PRODUCT_LE920 0x1200 +#define TELIT_PRODUCT_LE910 0x1201 /* ZTE PRODUCTS */ #define ZTE_VENDOR_ID 0x19d2 #define ZTE_PRODUCT_MF622 0x0001 #define ZTE_PRODUCT_MF628 0x0015 #define ZTE_PRODUCT_MF626 0x0031 -#define ZTE_PRODUCT_MC2718 0xffe8 #define ZTE_PRODUCT_AC2726 0xfff1 +#define ZTE_PRODUCT_CDMA_TECH 0xfffe +#define ZTE_PRODUCT_AC8710T 0xffff +#define ZTE_PRODUCT_MC2718 0xffe8 +#define ZTE_PRODUCT_AD3812 0xffeb +#define ZTE_PRODUCT_MC2716 0xffed #define BENQ_VENDOR_ID 0x04a5 #define BENQ_PRODUCT_H10 0x4068 @@ -357,6 +362,7 @@ static void option_instat_callback(struct urb *urb); /* Haier products */ #define HAIER_VENDOR_ID 0x201e +#define HAIER_PRODUCT_CE81B 0x10f8 #define HAIER_PRODUCT_CE100 0x2009 /* Cinterion (formerly Siemens) products */ @@ -494,6 +500,10 @@ static void option_instat_callback(struct urb *urb); #define INOVIA_VENDOR_ID 0x20a6 #define INOVIA_SEW858 0x1105 +/* VIA Telecom */ +#define VIATELECOM_VENDOR_ID 0x15eb +#define VIATELECOM_PRODUCT_CDS7 0x0001 + /* some devices interfaces need special handling due to a number of reasons */ enum option_blacklist_reason { OPTION_BLACKLIST_NONE = 0, @@ -527,10 +537,18 @@ static const struct option_blacklist_info zte_k3765_z_blacklist = { .reserved = BIT(4), }; +static const struct option_blacklist_info zte_ad3812_z_blacklist = { + .sendsetup = BIT(0) | BIT(1) | BIT(2), +}; + static const struct option_blacklist_info zte_mc2718_z_blacklist = { .sendsetup = BIT(1) | BIT(2) | BIT(3) | BIT(4), }; +static const struct option_blacklist_info zte_mc2716_z_blacklist = { + .sendsetup = BIT(1) | BIT(2) | BIT(3), +}; + static const struct option_blacklist_info huawei_cdc12_blacklist = { .reserved = BIT(1) | BIT(2), }; @@ -572,6 +590,11 @@ static const struct option_blacklist_info zte_1255_blacklist = { .reserved = BIT(3) | BIT(4), }; +static const struct option_blacklist_info telit_le910_blacklist = { + .sendsetup = BIT(0), + .reserved = BIT(1) | BIT(2), +}; + static const struct option_blacklist_info telit_le920_blacklist = { .sendsetup = BIT(0), .reserved = BIT(1) | BIT(5), @@ -1070,6 +1093,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(BANDRICH_VENDOR_ID, BANDRICH_PRODUCT_1012, 0xff) }, { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) }, { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) }, + { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */ @@ -1120,6 +1144,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), + .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), .driver_info = (kernel_ulong_t)&telit_le920_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ @@ -1544,13 +1570,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff93, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff94, 0xff, 0xff, 0xff) }, - /* NOTE: most ZTE CDMA devices should be driven by zte_ev, not option */ + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_CDMA_TECH, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710T, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2718, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&zte_mc2718_z_blacklist }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AD3812, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist }, { USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x01) }, { USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x05) }, { USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x86, 0x10) }, - { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) }, { USB_DEVICE(BENQ_VENDOR_ID, BENQ_PRODUCT_H10) }, { USB_DEVICE(DLINK_VENDOR_ID, DLINK_PRODUCT_DWM_652) }, @@ -1590,6 +1621,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) }, { USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) }, + { USB_DEVICE_AND_INTERFACE_INFO(HAIER_VENDOR_ID, HAIER_PRODUCT_CE81B, 0xff, 0xff, 0xff) }, /* Pirelli */ { USB_DEVICE_INTERFACE_CLASS(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_1, 0xff) }, { USB_DEVICE_INTERFACE_CLASS(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_2, 0xff) }, @@ -1723,7 +1755,9 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) }, { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ + { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */ { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, + { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index b3d5a35..5219593 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -45,6 +45,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_GPRS) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_HCR331) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MOTOROLA) }, + { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_ZTEK) }, { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) }, { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) }, { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) }, @@ -60,7 +61,6 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(DCU10_VENDOR_ID, DCU10_PRODUCT_ID) }, { USB_DEVICE(SITECOM_VENDOR_ID, SITECOM_PRODUCT_ID) }, { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_ID) }, - { USB_DEVICE(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_ID) }, { USB_DEVICE(SIEMENS_VENDOR_ID, SIEMENS_PRODUCT_ID_SX1), .driver_info = PL2303_QUIRK_UART_STATE_IDX0 }, { USB_DEVICE(SIEMENS_VENDOR_ID, SIEMENS_PRODUCT_ID_X65), diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index 42bc082..e3b7af8 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -22,6 +22,7 @@ #define PL2303_PRODUCT_ID_GPRS 0x0609 #define PL2303_PRODUCT_ID_HCR331 0x331a #define PL2303_PRODUCT_ID_MOTOROLA 0x0307 +#define PL2303_PRODUCT_ID_ZTEK 0xe1f1 #define ATEN_VENDOR_ID 0x0557 #define ATEN_VENDOR_ID2 0x0547 @@ -61,10 +62,6 @@ #define ALCATEL_VENDOR_ID 0x11f7 #define ALCATEL_PRODUCT_ID 0x02df -/* Samsung I330 phone cradle */ -#define SAMSUNG_VENDOR_ID 0x04e8 -#define SAMSUNG_PRODUCT_ID 0x8001 - #define SIEMENS_VENDOR_ID 0x11f5 #define SIEMENS_PRODUCT_ID_SX1 0x0001 #define SIEMENS_PRODUCT_ID_X65 0x0003 diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c index 3748034..89c55d4 100644 --- a/drivers/usb/serial/sierra.c +++ b/drivers/usb/serial/sierra.c @@ -282,14 +282,20 @@ static const struct usb_device_id id_table[] = { /* Sierra Wireless HSPA Non-Composite Device */ { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x6892, 0xFF, 0xFF, 0xFF)}, { USB_DEVICE(0x1199, 0x6893) }, /* Sierra Wireless Device */ - { USB_DEVICE(0x1199, 0x68A3), /* Sierra Wireless Direct IP modems */ + /* Sierra Wireless Direct IP modems */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68A3, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, + { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68AA, 0xFF, 0xFF, 0xFF), + .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist + }, + { USB_DEVICE(0x1199, 0x68AB) }, /* Sierra Wireless AR8550 */ /* AT&T Direct IP LTE modems */ { USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68AA, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, - { USB_DEVICE(0x0f3d, 0x68A3), /* Airprime/Sierra Wireless Direct IP modems */ + /* Airprime/Sierra Wireless Direct IP modems */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68A3, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, diff --git a/drivers/usb/serial/ssu100.c b/drivers/usb/serial/ssu100.c index a7fe664..70a098d 100644 --- a/drivers/usb/serial/ssu100.c +++ b/drivers/usb/serial/ssu100.c @@ -490,10 +490,9 @@ static void ssu100_update_lsr(struct usb_serial_port *port, u8 lsr, if (*tty_flag == TTY_NORMAL) *tty_flag = TTY_FRAME; } - if (lsr & UART_LSR_OE){ + if (lsr & UART_LSR_OE) { port->icount.overrun++; - if (*tty_flag == TTY_NORMAL) - *tty_flag = TTY_OVERRUN; + tty_insert_flip_char(&port->port, 0, TTY_OVERRUN); } } @@ -511,12 +510,8 @@ static void ssu100_process_read_urb(struct urb *urb) if ((len >= 4) && (packet[0] == 0x1b) && (packet[1] == 0x1b) && ((packet[2] == 0x00) || (packet[2] == 0x01))) { - if (packet[2] == 0x00) { + if (packet[2] == 0x00) ssu100_update_lsr(port, packet[3], &flag); - if (flag == TTY_OVERRUN) - tty_insert_flip_char(&port->port, 0, - TTY_OVERRUN); - } if (packet[2] == 0x01) ssu100_update_msr(port, packet[3]); diff --git a/drivers/usb/serial/symbolserial.c b/drivers/usb/serial/symbolserial.c index 9fa7dd4..5e5e882 100644 --- a/drivers/usb/serial/symbolserial.c +++ b/drivers/usb/serial/symbolserial.c @@ -96,7 +96,7 @@ exit: static int symbol_open(struct tty_struct *tty, struct usb_serial_port *port) { - struct symbol_private *priv = usb_get_serial_data(port->serial); + struct symbol_private *priv = usb_get_serial_port_data(port); unsigned long flags; int result = 0; @@ -122,7 +122,7 @@ static void symbol_close(struct usb_serial_port *port) static void symbol_throttle(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; - struct symbol_private *priv = usb_get_serial_data(port->serial); + struct symbol_private *priv = usb_get_serial_port_data(port); spin_lock_irq(&priv->lock); priv->throttled = true; @@ -132,7 +132,7 @@ static void symbol_throttle(struct tty_struct *tty) static void symbol_unthrottle(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; - struct symbol_private *priv = usb_get_serial_data(port->serial); + struct symbol_private *priv = usb_get_serial_port_data(port); int result; bool was_throttled; diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index b169b0f..3d66e9c 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -764,29 +764,39 @@ static int usb_serial_probe(struct usb_interface *interface, if (usb_endpoint_is_bulk_in(endpoint)) { /* we found a bulk in endpoint */ dev_dbg(ddev, "found bulk in on endpoint %d\n", i); - bulk_in_endpoint[num_bulk_in] = endpoint; - ++num_bulk_in; + if (num_bulk_in < MAX_NUM_PORTS) { + bulk_in_endpoint[num_bulk_in] = endpoint; + ++num_bulk_in; + } } if (usb_endpoint_is_bulk_out(endpoint)) { /* we found a bulk out endpoint */ dev_dbg(ddev, "found bulk out on endpoint %d\n", i); - bulk_out_endpoint[num_bulk_out] = endpoint; - ++num_bulk_out; + if (num_bulk_out < MAX_NUM_PORTS) { + bulk_out_endpoint[num_bulk_out] = endpoint; + ++num_bulk_out; + } } if (usb_endpoint_is_int_in(endpoint)) { /* we found a interrupt in endpoint */ dev_dbg(ddev, "found interrupt in on endpoint %d\n", i); - interrupt_in_endpoint[num_interrupt_in] = endpoint; - ++num_interrupt_in; + if (num_interrupt_in < MAX_NUM_PORTS) { + interrupt_in_endpoint[num_interrupt_in] = + endpoint; + ++num_interrupt_in; + } } if (usb_endpoint_is_int_out(endpoint)) { /* we found an interrupt out endpoint */ dev_dbg(ddev, "found interrupt out on endpoint %d\n", i); - interrupt_out_endpoint[num_interrupt_out] = endpoint; - ++num_interrupt_out; + if (num_interrupt_out < MAX_NUM_PORTS) { + interrupt_out_endpoint[num_interrupt_out] = + endpoint; + ++num_interrupt_out; + } } } @@ -809,8 +819,10 @@ static int usb_serial_probe(struct usb_interface *interface, if (usb_endpoint_is_int_in(endpoint)) { /* we found a interrupt in endpoint */ dev_dbg(ddev, "found interrupt in for Prolific device on separate interface\n"); - interrupt_in_endpoint[num_interrupt_in] = endpoint; - ++num_interrupt_in; + if (num_interrupt_in < MAX_NUM_PORTS) { + interrupt_in_endpoint[num_interrupt_in] = endpoint; + ++num_interrupt_in; + } } } } @@ -850,6 +862,11 @@ static int usb_serial_probe(struct usb_interface *interface, num_ports = type->num_ports; } + if (num_ports > MAX_NUM_PORTS) { + dev_warn(ddev, "too many ports requested: %d\n", num_ports); + num_ports = MAX_NUM_PORTS; + } + serial->num_ports = num_ports; serial->num_bulk_in = num_bulk_in; serial->num_bulk_out = num_bulk_out; @@ -1283,6 +1300,7 @@ static void __exit usb_serial_exit(void) tty_unregister_driver(usb_serial_tty_driver); put_tty_driver(usb_serial_tty_driver); bus_unregister(&usb_serial_bus_type); + idr_destroy(&serial_minors); } diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c index bf2bd40..60afb39 100644 --- a/drivers/usb/serial/visor.c +++ b/drivers/usb/serial/visor.c @@ -95,7 +95,7 @@ static const struct usb_device_id id_table[] = { .driver_info = (kernel_ulong_t)&palm_os_4_probe }, { USB_DEVICE(ACER_VENDOR_ID, ACER_S10_ID), .driver_info = (kernel_ulong_t)&palm_os_4_probe }, - { USB_DEVICE(SAMSUNG_VENDOR_ID, SAMSUNG_SCH_I330_ID), + { USB_DEVICE_INTERFACE_CLASS(SAMSUNG_VENDOR_ID, SAMSUNG_SCH_I330_ID, 0xff), .driver_info = (kernel_ulong_t)&palm_os_4_probe }, { USB_DEVICE(SAMSUNG_VENDOR_ID, SAMSUNG_SPH_I500_ID), .driver_info = (kernel_ulong_t)&palm_os_4_probe }, diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c index e62f2df..6c3734d 100644 --- a/drivers/usb/serial/whiteheat.c +++ b/drivers/usb/serial/whiteheat.c @@ -514,6 +514,10 @@ static void command_port_read_callback(struct urb *urb) dev_dbg(&urb->dev->dev, "%s - command_info is NULL, exiting.\n", __func__); return; } + if (!urb->actual_length) { + dev_dbg(&urb->dev->dev, "%s - empty response, exiting.\n", __func__); + return; + } if (status) { dev_dbg(&urb->dev->dev, "%s - nonzero urb status: %d\n", __func__, status); if (status != -ENOENT) @@ -534,7 +538,8 @@ static void command_port_read_callback(struct urb *urb) /* These are unsolicited reports from the firmware, hence no waiting command to wakeup */ dev_dbg(&urb->dev->dev, "%s - event received\n", __func__); - } else if (data[0] == WHITEHEAT_GET_DTR_RTS) { + } else if ((data[0] == WHITEHEAT_GET_DTR_RTS) && + (urb->actual_length - 1 <= sizeof(command_info->result_buffer))) { memcpy(command_info->result_buffer, &data[1], urb->actual_length - 1); command_info->command_finished = WHITEHEAT_CMD_COMPLETE; diff --git a/drivers/usb/serial/zte_ev.c b/drivers/usb/serial/zte_ev.c index e40ab73..c9bb107 100644 --- a/drivers/usb/serial/zte_ev.c +++ b/drivers/usb/serial/zte_ev.c @@ -272,28 +272,16 @@ static void zte_ev_usb_serial_close(struct usb_serial_port *port) } static const struct usb_device_id id_table[] = { - /* AC8710, AC8710T */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffff, 0xff, 0xff, 0xff) }, - /* AC8700 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xfffe, 0xff, 0xff, 0xff) }, - /* MG880 */ - { USB_DEVICE(0x19d2, 0xfffd) }, - { USB_DEVICE(0x19d2, 0xfffc) }, - { USB_DEVICE(0x19d2, 0xfffb) }, - /* AC8710_V3 */ + { USB_DEVICE(0x19d2, 0xffec) }, + { USB_DEVICE(0x19d2, 0xffee) }, { USB_DEVICE(0x19d2, 0xfff6) }, { USB_DEVICE(0x19d2, 0xfff7) }, { USB_DEVICE(0x19d2, 0xfff8) }, { USB_DEVICE(0x19d2, 0xfff9) }, - { USB_DEVICE(0x19d2, 0xffee) }, - /* AC2716, MC2716 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffed, 0xff, 0xff, 0xff) }, - /* AD3812 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffeb, 0xff, 0xff, 0xff) }, - { USB_DEVICE(0x19d2, 0xffec) }, - { USB_DEVICE(0x05C6, 0x3197) }, - { USB_DEVICE(0x05C6, 0x6000) }, - { USB_DEVICE(0x05C6, 0x9008) }, + { USB_DEVICE(0x19d2, 0xfffb) }, + { USB_DEVICE(0x19d2, 0xfffc) }, + /* MG880 */ + { USB_DEVICE(0x19d2, 0xfffd) }, { }, }; MODULE_DEVICE_TABLE(usb, id_table); diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index 22c7d43..b1d815e 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -1118,6 +1118,31 @@ int usb_stor_Bulk_transport(struct scsi_cmnd *srb, struct us_data *us) */ if (result == USB_STOR_XFER_LONG) fake_sense = 1; + + /* + * Sometimes a device will mistakenly skip the data phase + * and go directly to the status phase without sending a + * zero-length packet. If we get a 13-byte response here, + * check whether it really is a CSW. + */ + if (result == USB_STOR_XFER_SHORT && + srb->sc_data_direction == DMA_FROM_DEVICE && + transfer_length - scsi_get_resid(srb) == + US_BULK_CS_WRAP_LEN) { + struct scatterlist *sg = NULL; + unsigned int offset = 0; + + if (usb_stor_access_xfer_buf((unsigned char *) bcs, + US_BULK_CS_WRAP_LEN, srb, &sg, + &offset, FROM_XFER_BUF) == + US_BULK_CS_WRAP_LEN && + bcs->Signature == + cpu_to_le32(US_BULK_CS_SIGN)) { + usb_stor_dbg(us, "Device skipped data phase\n"); + scsi_set_resid(srb, transfer_length); + goto skipped_data_phase; + } + } } /* See flow chart on pg 15 of the Bulk Only Transport spec for @@ -1153,6 +1178,7 @@ int usb_stor_Bulk_transport(struct scsi_cmnd *srb, struct us_data *us) if (result != USB_STOR_XFER_GOOD) return USB_STOR_TRANSPORT_ERROR; + skipped_data_phase: /* check bulk status */ residue = le32_to_cpu(bcs->Residue); usb_stor_dbg(us, "Bulk Status S 0x%x T 0x%x R %u Stat 0x%x\n", diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 042c83b0..da380a9 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -101,6 +101,12 @@ UNUSUAL_DEV( 0x03f0, 0x4002, 0x0001, 0x0001, "PhotoSmart R707", USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_FIX_CAPACITY), +UNUSUAL_DEV( 0x03f3, 0x0001, 0x0000, 0x9999, + "Adaptec", + "USBConnect 2000", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + /* Reported by Sebastian Kapfer * and Olaf Hering (different bcd's, same vendor/product) * for USB floppies that need the SINGLE_LUN enforcement. @@ -741,6 +747,12 @@ UNUSUAL_DEV( 0x059b, 0x0001, 0x0100, 0x0100, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_SINGLE_LUN ), +UNUSUAL_DEV( 0x059b, 0x0040, 0x0100, 0x0100, + "Iomega", + "Jaz USB Adapter", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_SINGLE_LUN ), + /* Reported by */ UNUSUAL_DEV( 0x059f, 0x0643, 0x0000, 0x0000, "LaCie", @@ -748,6 +760,13 @@ UNUSUAL_DEV( 0x059f, 0x0643, 0x0000, 0x0000, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_GO_SLOW ), +/* Reported by Christian Schaller */ +UNUSUAL_DEV( 0x059f, 0x0651, 0x0000, 0x0000, + "LaCie", + "External HDD", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_WP_DETECT ), + /* Submitted by Joel Bourquard * Some versions of this device need the SubClass and Protocol overrides * while others don't. @@ -1113,6 +1132,18 @@ UNUSUAL_DEV( 0x0851, 0x1543, 0x0200, 0x0200, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NOT_LOCKABLE), +UNUSUAL_DEV( 0x085a, 0x0026, 0x0100, 0x0133, + "Xircom", + "PortGear USB-SCSI (Mac USB Dock)", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + +UNUSUAL_DEV( 0x085a, 0x0028, 0x0100, 0x0133, + "Xircom", + "PortGear USB to SCSI Converter", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + /* Submitted by Jan De Luyck */ UNUSUAL_DEV( 0x08bd, 0x1100, 0x0000, 0x0000, "CITIZEN", @@ -1945,6 +1976,14 @@ UNUSUAL_DEV( 0x152d, 0x2329, 0x0100, 0x0100, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ), +/* Entrega Technologies U1-SC25 (later Xircom PortGear PGSCSI) + * and Mac USB Dock USB-SCSI */ +UNUSUAL_DEV( 0x1645, 0x0007, 0x0100, 0x0133, + "Entrega Technologies", + "USB to SCSI Converter", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + /* Reported by Robert Schedel * Note: this is a 'super top' device like the above 14cd/6600 device */ UNUSUAL_DEV( 0x1652, 0x6600, 0x0201, 0x0201, @@ -1967,6 +2006,12 @@ UNUSUAL_DEV( 0x177f, 0x0400, 0x0000, 0x0000, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_BULK_IGNORE_TAG | US_FL_MAX_SECTORS_64 ), +UNUSUAL_DEV( 0x1822, 0x0001, 0x0000, 0x9999, + "Ariston Technologies", + "iConnect USB to SCSI adapter", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + /* Reported by Hans de Goede * These Appotech controllers are found in Picture Frames, they provide a * (buggy) emulation of a cdrom drive which contains the windows software @@ -1987,6 +2032,18 @@ UNUSUAL_DEV( 0x1908, 0x3335, 0x0200, 0x0200, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_READ_DISC_INFO ), +/* Reported by Oliver Neukum + * This device morphes spontaneously into another device if the access + * pattern of Windows isn't followed. Thus writable media would be dirty + * if the initial instance is used. So the device is limited to its + * virtual CD. + * And yes, the concept that BCD goes up to 9 is not heeded */ +UNUSUAL_DEV( 0x19d2, 0x1225, 0x0000, 0xffff, + "ZTE,Incorporated", + "ZTE WCDMA Technologies MSM", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_SINGLE_LUN ), + /* Reported by Sven Geggus * This encrypted pen drive returns bogus data for the initial READ(10). */ diff --git a/drivers/uwb/lc-dev.c b/drivers/uwb/lc-dev.c index 80079b8..d0303f0 100644 --- a/drivers/uwb/lc-dev.c +++ b/drivers/uwb/lc-dev.c @@ -431,16 +431,19 @@ void uwbd_dev_onair(struct uwb_rc *rc, struct uwb_beca_e *bce) uwb_dev->mac_addr = *bce->mac_addr; uwb_dev->dev_addr = bce->dev_addr; dev_set_name(&uwb_dev->dev, "%s", macbuf); + + /* plug the beacon cache */ + bce->uwb_dev = uwb_dev; + uwb_dev->bce = bce; + uwb_bce_get(bce); /* released in uwb_dev_sys_release() */ + result = uwb_dev_add(uwb_dev, &rc->uwb_dev.dev, rc); if (result < 0) { dev_err(dev, "new device %s: cannot instantiate device\n", macbuf); goto error_dev_add; } - /* plug the beacon cache */ - bce->uwb_dev = uwb_dev; - uwb_dev->bce = bce; - uwb_bce_get(bce); /* released in uwb_dev_sys_release() */ + dev_info(dev, "uwb device (mac %s dev %s) connected to %s %s\n", macbuf, devbuf, rc->uwb_dev.dev.parent->bus->name, dev_name(rc->uwb_dev.dev.parent)); @@ -448,6 +451,8 @@ void uwbd_dev_onair(struct uwb_rc *rc, struct uwb_beca_e *bce) return; error_dev_add: + bce->uwb_dev = NULL; + uwb_bce_put(bce); kfree(uwb_dev); return; } diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 7ba0424..75e1d03 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -810,13 +810,11 @@ static const struct vfio_device_ops vfio_pci_ops = { static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - u8 type; struct vfio_pci_device *vdev; struct iommu_group *group; int ret; - pci_read_config_byte(pdev, PCI_HEADER_TYPE, &type); - if ((type & PCI_HEADER_TYPE) != PCI_HEADER_TYPE_NORMAL) + if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL) return -EINVAL; group = iommu_group_get(&pdev->dev); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index e48d4a6..486d710 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -861,6 +861,23 @@ vhost_scsi_map_iov_to_sgl(struct tcm_vhost_cmd *cmd, return 0; } +static int vhost_scsi_to_tcm_attr(int attr) +{ + switch (attr) { + case VIRTIO_SCSI_S_SIMPLE: + return MSG_SIMPLE_TAG; + case VIRTIO_SCSI_S_ORDERED: + return MSG_ORDERED_TAG; + case VIRTIO_SCSI_S_HEAD: + return MSG_HEAD_TAG; + case VIRTIO_SCSI_S_ACA: + return MSG_ACA_TAG; + default: + break; + } + return MSG_SIMPLE_TAG; +} + static void tcm_vhost_submission_work(struct work_struct *work) { struct tcm_vhost_cmd *cmd = @@ -887,9 +904,10 @@ static void tcm_vhost_submission_work(struct work_struct *work) rc = target_submit_cmd_map_sgls(se_cmd, tv_nexus->tvn_se_sess, cmd->tvc_cdb, &cmd->tvc_sense_buf[0], cmd->tvc_lun, cmd->tvc_exp_data_len, - cmd->tvc_task_attr, cmd->tvc_data_direction, - TARGET_SCF_ACK_KREF, sg_ptr, cmd->tvc_sgl_count, - sg_bidi_ptr, sg_no_bidi, NULL, 0); + vhost_scsi_to_tcm_attr(cmd->tvc_task_attr), + cmd->tvc_data_direction, TARGET_SCF_ACK_KREF, + sg_ptr, cmd->tvc_sgl_count, sg_bidi_ptr, sg_no_bidi, + NULL, 0); if (rc < 0) { transport_send_check_condition_and_sense(se_cmd, TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE, 0); @@ -1200,6 +1218,7 @@ static int vhost_scsi_set_endpoint(struct vhost_scsi *vs, struct vhost_scsi_target *t) { + struct se_portal_group *se_tpg; struct tcm_vhost_tport *tv_tport; struct tcm_vhost_tpg *tpg; struct tcm_vhost_tpg **vs_tpg; @@ -1247,6 +1266,21 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, ret = -EEXIST; goto out; } + /* + * In order to ensure individual vhost-scsi configfs + * groups cannot be removed while in use by vhost ioctl, + * go ahead and take an explicit se_tpg->tpg_group.cg_item + * dependency now. + */ + se_tpg = &tpg->se_tpg; + ret = configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys, + &se_tpg->tpg_group.cg_item); + if (ret) { + pr_warn("configfs_depend_item() failed: %d\n", ret); + kfree(vs_tpg); + mutex_unlock(&tpg->tv_tpg_mutex); + goto out; + } tpg->tv_tpg_vhost_count++; tpg->vhost_scsi = vs; vs_tpg[tpg->tport_tpgt] = tpg; @@ -1289,6 +1323,7 @@ static int vhost_scsi_clear_endpoint(struct vhost_scsi *vs, struct vhost_scsi_target *t) { + struct se_portal_group *se_tpg; struct tcm_vhost_tport *tv_tport; struct tcm_vhost_tpg *tpg; struct vhost_virtqueue *vq; @@ -1337,6 +1372,13 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, vs->vs_tpg[target] = NULL; match = true; mutex_unlock(&tpg->tv_tpg_mutex); + /* + * Release se_tpg->tpg_group.cg_item configfs dependency now + * to allow vhost-scsi WWPN se_tpg->tpg_group shutdown to occur. + */ + se_tpg = &tpg->se_tpg; + configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys, + &se_tpg->tpg_group.cg_item); } if (match) { for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) { diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 78987e4..85095d7 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -876,6 +876,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp) } if (eventfp != d->log_file) { filep = d->log_file; + d->log_file = eventfp; ctx = d->log_ctx; d->log_ctx = eventfp ? eventfd_ctx_fileget(eventfp) : NULL; diff --git a/drivers/video/console/bitblit.c b/drivers/video/console/bitblit.c index 61b182b..dbfe4ee 100644 --- a/drivers/video/console/bitblit.c +++ b/drivers/video/console/bitblit.c @@ -205,7 +205,6 @@ static void bit_putcs(struct vc_data *vc, struct fb_info *info, static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, int bottom_only) { - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; unsigned int cw = vc->vc_font.width; unsigned int ch = vc->vc_font.height; unsigned int rw = info->var.xres - (vc->vc_cols*cw); @@ -214,7 +213,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, unsigned int bs = info->var.yres - bh; struct fb_fillrect region; - region.color = attr_bgcol_ec(bgshift, vc, info); + region.color = 0; region.rop = ROP_COPY; if (rw && !bottom_only) { diff --git a/drivers/video/console/fbcon_ccw.c b/drivers/video/console/fbcon_ccw.c index 41b32ae..5a3cbf6 100644 --- a/drivers/video/console/fbcon_ccw.c +++ b/drivers/video/console/fbcon_ccw.c @@ -197,9 +197,8 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info, unsigned int bh = info->var.xres - (vc->vc_rows*ch); unsigned int bs = vc->vc_rows*ch; struct fb_fillrect region; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - region.color = attr_bgcol_ec(bgshift,vc,info); + region.color = 0; region.rop = ROP_COPY; if (rw && !bottom_only) { diff --git a/drivers/video/console/fbcon_cw.c b/drivers/video/console/fbcon_cw.c index a93670e..e7ee44d 100644 --- a/drivers/video/console/fbcon_cw.c +++ b/drivers/video/console/fbcon_cw.c @@ -180,9 +180,8 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info, unsigned int bh = info->var.xres - (vc->vc_rows*ch); unsigned int rs = info->var.yres - rw; struct fb_fillrect region; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - region.color = attr_bgcol_ec(bgshift,vc,info); + region.color = 0; region.rop = ROP_COPY; if (rw && !bottom_only) { diff --git a/drivers/video/console/fbcon_ud.c b/drivers/video/console/fbcon_ud.c index ff0872c..19e3714 100644 --- a/drivers/video/console/fbcon_ud.c +++ b/drivers/video/console/fbcon_ud.c @@ -227,9 +227,8 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info, unsigned int rw = info->var.xres - (vc->vc_cols*cw); unsigned int bh = info->var.yres - (vc->vc_rows*ch); struct fb_fillrect region; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - region.color = attr_bgcol_ec(bgshift,vc,info); + region.color = 0; region.rop = ROP_COPY; if (rw && !bottom_only) { diff --git a/drivers/video/logo/logo.c b/drivers/video/logo/logo.c index b670cbd..ffe024b 100644 --- a/drivers/video/logo/logo.c +++ b/drivers/video/logo/logo.c @@ -21,6 +21,21 @@ static bool nologo; module_param(nologo, bool, 0); MODULE_PARM_DESC(nologo, "Disables startup logo"); +/* + * Logos are located in the initdata, and will be freed in kernel_init. + * Use late_init to mark the logos as freed to prevent any further use. + */ + +static bool logos_freed; + +static int __init fb_logo_late_init(void) +{ + logos_freed = true; + return 0; +} + +late_initcall(fb_logo_late_init); + /* logo's are marked __initdata. Use __init_refok to tell * modpost that it is intended that this function uses data * marked __initdata. @@ -29,7 +44,7 @@ const struct linux_logo * __init_refok fb_find_logo(int depth) { const struct linux_logo *logo = NULL; - if (nologo) + if (nologo || logos_freed) return NULL; if (depth >= 1) { diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c index a416f9b..827b5f8 100644 --- a/drivers/virtio/virtio_pci.c +++ b/drivers/virtio/virtio_pci.c @@ -791,6 +791,7 @@ static int virtio_pci_restore(struct device *dev) struct pci_dev *pci_dev = to_pci_dev(dev); struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); struct virtio_driver *drv; + unsigned status = 0; int ret; drv = container_of(vp_dev->vdev.dev.driver, @@ -801,14 +802,40 @@ static int virtio_pci_restore(struct device *dev) return ret; pci_set_master(pci_dev); + /* We always start by resetting the device, in case a previous + * driver messed it up. */ + vp_reset(&vp_dev->vdev); + + /* Acknowledge that we've seen the device. */ + status |= VIRTIO_CONFIG_S_ACKNOWLEDGE; + vp_set_status(&vp_dev->vdev, status); + + /* Maybe driver failed before freeze. + * Restore the failed status, for debugging. */ + status |= vp_dev->saved_status & VIRTIO_CONFIG_S_FAILED; + vp_set_status(&vp_dev->vdev, status); + + if (!drv) + return 0; + + /* We have a driver! */ + status |= VIRTIO_CONFIG_S_DRIVER; + vp_set_status(&vp_dev->vdev, status); + vp_finalize_features(&vp_dev->vdev); - if (drv && drv->restore) + if (drv->restore) { ret = drv->restore(&vp_dev->vdev); + if (ret) { + status |= VIRTIO_CONFIG_S_FAILED; + vp_set_status(&vp_dev->vdev, status); + return ret; + } + } /* Finally, tell the device we're all set */ - if (!ret) - vp_set_status(&vp_dev->vdev, vp_dev->saved_status); + status |= VIRTIO_CONFIG_S_DRIVER_OK; + vp_set_status(&vp_dev->vdev, status); return ret; } diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c index 09cf013..90a6406 100644 --- a/drivers/watchdog/omap_wdt.c +++ b/drivers/watchdog/omap_wdt.c @@ -134,6 +134,13 @@ static int omap_wdt_start(struct watchdog_device *wdog) pm_runtime_get_sync(wdev->dev); + /* + * Make sure the watchdog is disabled. This is unfortunately required + * because writing to various registers with the watchdog running has no + * effect. + */ + omap_wdt_disable(wdev); + /* initialize prescaler */ while (readl_relaxed(base + OMAP_WATCHDOG_WPS) & 0x01) cpu_relax(); diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c index d7ff917..843e5d8 100644 --- a/drivers/xen/events/events_2l.c +++ b/drivers/xen/events/events_2l.c @@ -352,6 +352,15 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } +static void evtchn_2l_resume(void) +{ + int i; + + for_each_online_cpu(i) + memset(per_cpu(cpu_evtchn_mask, i), 0, sizeof(xen_ulong_t) * + EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD); +} + static const struct evtchn_ops evtchn_ops_2l = { .max_channels = evtchn_2l_max_channels, .nr_channels = evtchn_2l_max_channels, @@ -363,6 +372,7 @@ static const struct evtchn_ops evtchn_ops_2l = { .mask = evtchn_2l_mask, .unmask = evtchn_2l_unmask, .handle_events = evtchn_2l_handle_events, + .resume = evtchn_2l_resume, }; void __init xen_evtchn_2l_init(void) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index f4a9e33..5af64e9 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -547,20 +547,26 @@ static unsigned int __startup_pirq(unsigned int irq) pirq_query_unmask(irq); rc = set_evtchn_to_irq(evtchn, irq); - if (rc != 0) { - pr_err("irq%d: Failed to set port to irq mapping (%d)\n", - irq, rc); - xen_evtchn_close(evtchn); - return 0; - } - bind_evtchn_to_cpu(evtchn, 0); + if (rc) + goto err; + info->evtchn = evtchn; + bind_evtchn_to_cpu(evtchn, 0); + + rc = xen_evtchn_port_setup(info); + if (rc) + goto err; out: unmask_evtchn(evtchn); eoi_pirq(irq_get_irq_data(irq)); return 0; + +err: + pr_err("irq%d: Failed to set port to irq mapping (%d)\n", irq, rc); + xen_evtchn_close(evtchn); + return 0; } static unsigned int startup_pirq(struct irq_data *data) @@ -967,7 +973,7 @@ unsigned xen_evtchn_nr_channels(void) } EXPORT_SYMBOL_GPL(xen_evtchn_nr_channels); -int bind_virq_to_irq(unsigned int virq, unsigned int cpu) +int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu) { struct evtchn_bind_virq bind_virq; int evtchn, irq, ret; @@ -981,8 +987,12 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu) if (irq < 0) goto out; - irq_set_chip_and_handler_name(irq, &xen_percpu_chip, - handle_percpu_irq, "virq"); + if (percpu) + irq_set_chip_and_handler_name(irq, &xen_percpu_chip, + handle_percpu_irq, "virq"); + else + irq_set_chip_and_handler_name(irq, &xen_dynamic_chip, + handle_edge_irq, "virq"); bind_virq.virq = virq; bind_virq.vcpu = cpu; @@ -1072,7 +1082,7 @@ int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, { int irq, retval; - irq = bind_virq_to_irq(virq, cpu); + irq = bind_virq_to_irq(virq, cpu, irqflags & IRQF_PERCPU); if (irq < 0) return irq; retval = request_irq(irq, handler, irqflags, devname, dev_id); @@ -1288,8 +1298,9 @@ void rebind_evtchn_irq(int evtchn, int irq) mutex_unlock(&irq_mapping_update_lock); - /* new event channels are always bound to cpu 0 */ - irq_set_affinity(irq, cpumask_of(0)); + bind_evtchn_to_cpu(evtchn, info->cpu); + /* This will be deferred until interrupt is processed */ + irq_set_affinity(irq, cpumask_of(info->cpu)); /* Unmask the event channel. */ enable_irq(irq); diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index 640b3cf..ef7d446 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -67,10 +67,9 @@ static event_word_t *event_array[MAX_EVENT_ARRAY_PAGES] __read_mostly; static unsigned event_array_pages __read_mostly; /* - * sync_set_bit() and friends must be unsigned long aligned on non-x86 - * platforms. + * sync_set_bit() and friends must be unsigned long aligned. */ -#if !defined(CONFIG_X86) && BITS_PER_LONG > 32 +#if BITS_PER_LONG > 32 #define BM(w) (unsigned long *)((unsigned long)w & ~0x7UL) #define EVTCHN_FIFO_BIT(b, w) \ @@ -100,6 +99,25 @@ static unsigned evtchn_fifo_nr_channels(void) return event_array_pages * EVENT_WORDS_PER_PAGE; } +static int init_control_block(int cpu, + struct evtchn_fifo_control_block *control_block) +{ + struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu); + struct evtchn_init_control init_control; + unsigned int i; + + /* Reset the control block and the local HEADs. */ + clear_page(control_block); + for (i = 0; i < EVTCHN_FIFO_MAX_QUEUES; i++) + q->head[i] = 0; + + init_control.control_gfn = virt_to_mfn(control_block); + init_control.offset = 0; + init_control.vcpu = cpu; + + return HYPERVISOR_event_channel_op(EVTCHNOP_init_control, &init_control); +} + static void free_unused_array_pages(void) { unsigned i; @@ -328,7 +346,6 @@ static void evtchn_fifo_resume(void) for_each_possible_cpu(cpu) { void *control_block = per_cpu(cpu_control_block, cpu); - struct evtchn_init_control init_control; int ret; if (!control_block) @@ -345,12 +362,7 @@ static void evtchn_fifo_resume(void) continue; } - init_control.control_gfn = virt_to_mfn(control_block); - init_control.offset = 0; - init_control.vcpu = cpu; - - ret = HYPERVISOR_event_channel_op(EVTCHNOP_init_control, - &init_control); + ret = init_control_block(cpu, control_block); if (ret < 0) BUG(); } @@ -378,30 +390,25 @@ static const struct evtchn_ops evtchn_ops_fifo = { .resume = evtchn_fifo_resume, }; -static int evtchn_fifo_init_control_block(unsigned cpu) +static int evtchn_fifo_alloc_control_block(unsigned cpu) { - struct page *control_block = NULL; - struct evtchn_init_control init_control; + void *control_block = NULL; int ret = -ENOMEM; - control_block = alloc_page(GFP_KERNEL|__GFP_ZERO); + control_block = (void *)__get_free_page(GFP_KERNEL); if (control_block == NULL) goto error; - init_control.control_gfn = virt_to_mfn(page_address(control_block)); - init_control.offset = 0; - init_control.vcpu = cpu; - - ret = HYPERVISOR_event_channel_op(EVTCHNOP_init_control, &init_control); + ret = init_control_block(cpu, control_block); if (ret < 0) goto error; - per_cpu(cpu_control_block, cpu) = page_address(control_block); + per_cpu(cpu_control_block, cpu) = control_block; return 0; error: - __free_page(control_block); + free_page((unsigned long)control_block); return ret; } @@ -415,7 +422,7 @@ static int evtchn_fifo_cpu_notification(struct notifier_block *self, switch (action) { case CPU_UP_PREPARE: if (!per_cpu(cpu_control_block, cpu)) - ret = evtchn_fifo_init_control_block(cpu); + ret = evtchn_fifo_alloc_control_block(cpu); break; default: break; @@ -432,7 +439,7 @@ int __init xen_evtchn_fifo_init(void) int cpu = get_cpu(); int ret; - ret = evtchn_fifo_init_control_block(cpu); + ret = evtchn_fifo_alloc_control_block(cpu); if (ret < 0) goto out; diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 073b4a1..ff3c98f 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -529,12 +529,14 @@ static int gntdev_release(struct inode *inode, struct file *flip) pr_debug("priv %p\n", priv); + mutex_lock(&priv->lock); while (!list_empty(&priv->maps)) { map = list_entry(priv->maps.next, struct grant_map, next); list_del(&map->next); gntdev_put_map(NULL /* already removed */, map); } WARN_ON(!list_empty(&priv->freeable_maps)); + mutex_unlock(&priv->lock); if (use_ptemod) mmu_notifier_unregister(&priv->mn, priv->mm); diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 624e8dc..edfd797 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -111,16 +111,17 @@ static void do_suspend(void) shutting_down = SHUTDOWN_SUSPEND; -#ifdef CONFIG_PREEMPT - /* If the kernel is preemptible, we need to freeze all the processes - to prevent them from being in the middle of a pagetable update - during suspend. */ err = freeze_processes(); if (err) { - pr_err("%s: freeze failed %d\n", __func__, err); + pr_err("%s: freeze processes failed %d\n", __func__, err); goto out; } -#endif + + err = freeze_kernel_threads(); + if (err) { + pr_err("%s: freeze kernel threads failed %d\n", __func__, err); + goto out_thaw; + } err = dpm_suspend_start(PMSG_FREEZE); if (err) { @@ -169,10 +170,8 @@ out_resume: dpm_resume_end(si.cancelled ? PMSG_THAW : PMSG_RESTORE); out_thaw: -#ifdef CONFIG_PREEMPT thaw_processes(); out: -#endif shutting_down = SHUTDOWN_INVALID; } #endif /* CONFIG_HIBERNATE_CALLBACKS */ diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index ebd8f21..f3a9d83 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -96,8 +96,6 @@ static inline phys_addr_t xen_bus_to_phys(dma_addr_t baddr) dma_addr_t dma = (dma_addr_t)pfn << PAGE_SHIFT; phys_addr_t paddr = dma; - BUG_ON(paddr != dma); /* truncation has occurred, should never happen */ - paddr |= baddr & ~PAGE_MASK; return paddr; @@ -447,7 +445,7 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr, BUG_ON(dir == DMA_NONE); - xen_dma_unmap_page(hwdev, paddr, size, dir, attrs); + xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs); /* NOTE: We use dev_addr here, not paddr! */ if (is_xen_swiotlb_buffer(dev_addr)) { @@ -495,14 +493,14 @@ xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, BUG_ON(dir == DMA_NONE); if (target == SYNC_FOR_CPU) - xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir); + xen_dma_sync_single_for_cpu(hwdev, dev_addr, size, dir); /* NOTE: We use dev_addr here, not paddr! */ if (is_xen_swiotlb_buffer(dev_addr)) swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target); if (target == SYNC_FOR_DEVICE) - xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir); + xen_dma_sync_single_for_device(hwdev, dev_addr, size, dir); if (dir != DMA_FROM_DEVICE) return; diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c index 46ae0f9..75fe3d4 100644 --- a/drivers/xen/xen-pciback/conf_space.c +++ b/drivers/xen/xen-pciback/conf_space.c @@ -16,7 +16,7 @@ #include "conf_space.h" #include "conf_space_quirks.h" -static bool permissive; +bool permissive; module_param(permissive, bool, 0644); /* This is where xen_pcibk_read_config_byte, xen_pcibk_read_config_word, diff --git a/drivers/xen/xen-pciback/conf_space.h b/drivers/xen/xen-pciback/conf_space.h index e56c934..2e1d73d 100644 --- a/drivers/xen/xen-pciback/conf_space.h +++ b/drivers/xen/xen-pciback/conf_space.h @@ -64,6 +64,8 @@ struct config_field_entry { void *data; }; +extern bool permissive; + #define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset) /* Add fields to a device - the add_fields macro expects to get a pointer to diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index c5ee825..2d73693 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -11,6 +11,10 @@ #include "pciback.h" #include "conf_space.h" +struct pci_cmd_info { + u16 val; +}; + struct pci_bar_info { u32 val; u32 len_val; @@ -20,22 +24,36 @@ struct pci_bar_info { #define is_enable_cmd(value) ((value)&(PCI_COMMAND_MEMORY|PCI_COMMAND_IO)) #define is_master_cmd(value) ((value)&PCI_COMMAND_MASTER) -static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data) +/* Bits guests are allowed to control in permissive mode. */ +#define PCI_COMMAND_GUEST (PCI_COMMAND_MASTER|PCI_COMMAND_SPECIAL| \ + PCI_COMMAND_INVALIDATE|PCI_COMMAND_VGA_PALETTE| \ + PCI_COMMAND_WAIT|PCI_COMMAND_FAST_BACK) + +static void *command_init(struct pci_dev *dev, int offset) { - int i; - int ret; - - ret = xen_pcibk_read_config_word(dev, offset, value, data); - if (!pci_is_enabled(dev)) - return ret; - - for (i = 0; i < PCI_ROM_RESOURCE; i++) { - if (dev->resource[i].flags & IORESOURCE_IO) - *value |= PCI_COMMAND_IO; - if (dev->resource[i].flags & IORESOURCE_MEM) - *value |= PCI_COMMAND_MEMORY; + struct pci_cmd_info *cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + int err; + + if (!cmd) + return ERR_PTR(-ENOMEM); + + err = pci_read_config_word(dev, PCI_COMMAND, &cmd->val); + if (err) { + kfree(cmd); + return ERR_PTR(err); } + return cmd; +} + +static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data) +{ + int ret = pci_read_config_word(dev, offset, value); + const struct pci_cmd_info *cmd = data; + + *value &= PCI_COMMAND_GUEST; + *value |= cmd->val & ~PCI_COMMAND_GUEST; + return ret; } @@ -43,6 +61,8 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data) { struct xen_pcibk_dev_data *dev_data; int err; + u16 val; + struct pci_cmd_info *cmd = data; dev_data = pci_get_drvdata(dev); if (!pci_is_enabled(dev) && is_enable_cmd(value)) { @@ -83,6 +103,19 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data) } } + cmd->val = value; + + if (!permissive && (!dev_data || !dev_data->permissive)) + return 0; + + /* Only allow the guest to control certain bits. */ + err = pci_read_config_word(dev, offset, &val); + if (err || val == value) + return err; + + value &= PCI_COMMAND_GUEST; + value |= val & ~PCI_COMMAND_GUEST; + return pci_write_config_word(dev, offset, value); } @@ -282,6 +315,8 @@ static const struct config_field header_common[] = { { .offset = PCI_COMMAND, .size = 2, + .init = command_init, + .release = bar_release, .u.w.read = command_read, .u.w.write = command_write, }, diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index bb7991c..bfdeadb 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -540,8 +540,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb, unlock_new_inode(inode); return inode; error: - unlock_new_inode(inode); - iput(inode); + iget_failed(inode); return ERR_PTR(retval); } diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 59dc8e8..de8606c 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -149,8 +149,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb, unlock_new_inode(inode); return inode; error: - unlock_new_inode(inode); - iput(inode); + iget_failed(inode); return ERR_PTR(retval); } diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index d9a4367..9cca0ea 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -126,7 +126,7 @@ affs_fix_dcache(struct inode *inode, u32 entry_ino) { struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { if (entry_ino == (u32)(long)dentry->d_fsdata) { dentry->d_fsdata = (void *)inode->i_ino; break; diff --git a/fs/aio.c b/fs/aio.c index 6d68e01..3241659 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -141,6 +141,7 @@ struct kioctx { struct { unsigned tail; + unsigned completed_events; spinlock_t completion_lock; } ____cacheline_aligned_in_smp; @@ -164,6 +165,15 @@ static struct vfsmount *aio_mnt; static const struct file_operations aio_ring_fops; static const struct address_space_operations aio_ctx_aops; +/* Backing dev info for aio fs. + * -no dirty page accounting or writeback happens + */ +static struct backing_dev_info aio_fs_backing_dev_info = { + .name = "aiofs", + .state = 0, + .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_MAP_COPY, +}; + static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) { struct qstr this = QSTR_INIT("[aio]", 5); @@ -175,6 +185,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) inode->i_mapping->a_ops = &aio_ctx_aops; inode->i_mapping->private_data = ctx; + inode->i_mapping->backing_dev_info = &aio_fs_backing_dev_info; inode->i_size = PAGE_SIZE * nr_pages; path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this); @@ -220,6 +231,9 @@ static int __init aio_setup(void) if (IS_ERR(aio_mnt)) panic("Failed to create aio fs mount."); + if (bdi_init(&aio_fs_backing_dev_info)) + panic("Failed to init aio fs backing dev info."); + kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); @@ -281,11 +295,6 @@ static const struct file_operations aio_ring_fops = { .mmap = aio_ring_mmap, }; -static int aio_set_page_dirty(struct page *page) -{ - return 0; -} - #if IS_ENABLED(CONFIG_MIGRATION) static int aio_migratepage(struct address_space *mapping, struct page *new, struct page *old, enum migrate_mode mode) @@ -357,7 +366,7 @@ out: #endif static const struct address_space_operations aio_ctx_aops = { - .set_page_dirty = aio_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, #if IS_ENABLED(CONFIG_MIGRATION) .migratepage = aio_migratepage, #endif @@ -412,7 +421,6 @@ static int aio_setup_ring(struct kioctx *ctx) pr_debug("pid(%d) page[%d]->count=%d\n", current->pid, i, page_count(page)); SetPageUptodate(page); - SetPageDirty(page); unlock_page(page); ctx->ring_pages[i] = page; @@ -711,6 +719,9 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) err_cleanup: aio_nr_sub(ctx->max_reqs); err_ctx: + atomic_set(&ctx->dead, 1); + if (ctx->mmap_size) + vm_munmap(ctx->mmap_base, ctx->mmap_size); aio_free_ring(ctx); err: mutex_unlock(&ctx->ring_lock); @@ -796,6 +807,9 @@ void exit_aio(struct mm_struct *mm) unsigned i = 0; while (1) { + struct completion requests_done = + COMPLETION_INITIALIZER_ONSTACK(requests_done); + rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); @@ -823,7 +837,10 @@ void exit_aio(struct mm_struct *mm) */ ctx->mmap_size = 0; - kill_ioctx(mm, ctx, NULL); + kill_ioctx(mm, ctx, &requests_done); + + /* Wait until all IO for the context are done. */ + wait_for_completion(&requests_done); } } @@ -880,6 +897,68 @@ out: return ret; } +/* refill_reqs_available + * Updates the reqs_available reference counts used for tracking the + * number of free slots in the completion ring. This can be called + * from aio_complete() (to optimistically update reqs_available) or + * from aio_get_req() (the we're out of events case). It must be + * called holding ctx->completion_lock. + */ +static void refill_reqs_available(struct kioctx *ctx, unsigned head, + unsigned tail) +{ + unsigned events_in_ring, completed; + + /* Clamp head since userland can write to it. */ + head %= ctx->nr_events; + if (head <= tail) + events_in_ring = tail - head; + else + events_in_ring = ctx->nr_events - (head - tail); + + completed = ctx->completed_events; + if (events_in_ring < completed) + completed -= events_in_ring; + else + completed = 0; + + if (!completed) + return; + + ctx->completed_events -= completed; + put_reqs_available(ctx, completed); +} + +/* user_refill_reqs_available + * Called to refill reqs_available when aio_get_req() encounters an + * out of space in the completion ring. + */ +static void user_refill_reqs_available(struct kioctx *ctx) +{ + spin_lock_irq(&ctx->completion_lock); + if (ctx->completed_events) { + struct aio_ring *ring; + unsigned head; + + /* Access of ring->head may race with aio_read_events_ring() + * here, but that's okay since whether we read the old version + * or the new version, and either will be valid. The important + * part is that head cannot pass tail since we prevent + * aio_complete() from updating tail by holding + * ctx->completion_lock. Even if head is invalid, the check + * against ctx->completed_events below will make sure we do the + * safe/right thing. + */ + ring = kmap_atomic(ctx->ring_pages[0]); + head = ring->head; + kunmap_atomic(ring); + + refill_reqs_available(ctx, head, ctx->tail); + } + + spin_unlock_irq(&ctx->completion_lock); +} + /* aio_get_req * Allocate a slot for an aio request. * Returns NULL if no requests are free. @@ -888,8 +967,11 @@ static inline struct kiocb *aio_get_req(struct kioctx *ctx) { struct kiocb *req; - if (!get_reqs_available(ctx)) - return NULL; + if (!get_reqs_available(ctx)) { + user_refill_reqs_available(ctx); + if (!get_reqs_available(ctx)) + return NULL; + } req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO); if (unlikely(!req)) @@ -948,8 +1030,8 @@ void aio_complete(struct kiocb *iocb, long res, long res2) struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; struct io_event *ev_page, *event; + unsigned tail, pos, head; unsigned long flags; - unsigned tail, pos; /* * Special case handling for sync iocbs: @@ -1010,10 +1092,14 @@ void aio_complete(struct kiocb *iocb, long res, long res2) ctx->tail = tail; ring = kmap_atomic(ctx->ring_pages[0]); + head = ring->head; ring->tail = tail; kunmap_atomic(ring); flush_dcache_page(ctx->ring_pages[0]); + ctx->completed_events++; + if (ctx->completed_events > 1) + refill_reqs_available(ctx, head, tail); spin_unlock_irqrestore(&ctx->completion_lock, flags); pr_debug("added to ring %p at [%u]\n", iocb, tail); @@ -1028,7 +1114,6 @@ void aio_complete(struct kiocb *iocb, long res, long res2) /* everything turned out well, dispose of the aiocb. */ kiocb_free(iocb); - put_reqs_available(ctx, 1); /* * We have to order our ring_info tail store above and test @@ -1065,6 +1150,12 @@ static long aio_read_events_ring(struct kioctx *ctx, tail = ring->tail; kunmap_atomic(ring); + /* + * Ensure that once we've read the current tail pointer, that + * we also see the events that were stored up to the tail. + */ + smp_rmb(); + pr_debug("h%u t%u m%u\n", head, tail, ctx->nr_events); if (head == tail) diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index 3182c0e..e3399dc 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -95,7 +95,7 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param) */ static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *in) { - struct autofs_dev_ioctl tmp; + struct autofs_dev_ioctl tmp, *res; if (copy_from_user(&tmp, in, sizeof(tmp))) return ERR_PTR(-EFAULT); @@ -103,7 +103,11 @@ static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *i if (tmp.size < sizeof(tmp)) return ERR_PTR(-EINVAL); - return memdup_user(in, tmp.size); + res = memdup_user(in, tmp.size); + if (!IS_ERR(res)) + res->size = tmp.size; + + return res; } static inline void free_dev_ioctl(struct autofs_dev_ioctl *param) diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 394e90b..edb46e6 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -91,7 +91,7 @@ static struct dentry *get_next_positive_subdir(struct dentry *prev, spin_lock(&root->d_lock); if (prev) - next = prev->d_u.d_child.next; + next = prev->d_child.next; else { prev = dget_dlock(root); next = prev->d_subdirs.next; @@ -105,13 +105,13 @@ cont: return NULL; } - q = list_entry(next, struct dentry, d_u.d_child); + q = list_entry(next, struct dentry, d_child); spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED); /* Already gone or negative dentry (under construction) - try next */ if (!d_count(q) || !simple_positive(q)) { spin_unlock(&q->d_lock); - next = q->d_u.d_child.next; + next = q->d_child.next; goto cont; } dget_dlock(q); @@ -161,13 +161,13 @@ again: goto relock; } spin_unlock(&p->d_lock); - next = p->d_u.d_child.next; + next = p->d_child.next; p = parent; if (next != &parent->d_subdirs) break; } } - ret = list_entry(next, struct dentry, d_u.d_child); + ret = list_entry(next, struct dentry, d_child); spin_lock_nested(&ret->d_lock, DENTRY_D_LOCK_NESTED); /* Negative dentry - try next */ @@ -461,7 +461,7 @@ found: spin_lock(&sbi->lookup_lock); spin_lock(&expired->d_parent->d_lock); spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child); + list_move(&expired->d_parent->d_subdirs, &expired->d_child); spin_unlock(&expired->d_lock); spin_unlock(&expired->d_parent->d_lock); spin_unlock(&sbi->lookup_lock); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index cc87c1a..9e016e6 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -655,7 +655,7 @@ static void autofs_clear_leaf_automount_flags(struct dentry *dentry) /* only consider parents below dentrys in the root */ if (IS_ROOT(parent->d_parent)) return; - d_child = &dentry->d_u.d_child; + d_child = &dentry->d_child; /* Set parent managed if it's becoming empty */ if (d_child->next == &parent->d_subdirs && d_child->prev == &parent->d_subdirs) diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 67be295..35240a7 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -549,11 +549,12 @@ out: static unsigned long randomize_stack_top(unsigned long stack_top) { - unsigned int random_variable = 0; + unsigned long random_variable = 0; if ((current->flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - random_variable = get_random_int() & STACK_RND_MASK; + random_variable = (unsigned long) get_random_int(); + random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } #ifdef CONFIG_STACK_GROWSUP @@ -750,6 +751,7 @@ static int load_elf_binary(struct linux_binprm *bprm) i < loc->elf_ex.e_phnum; i++, elf_ppnt++) { int elf_prot = 0, elf_flags; unsigned long k, vaddr; + unsigned long total_size = 0; if (elf_ppnt->p_type != PT_LOAD) continue; @@ -814,10 +816,16 @@ static int load_elf_binary(struct linux_binprm *bprm) #else load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr); #endif + total_size = total_mapping_size(elf_phdata, + loc->elf_ex.e_phnum); + if (!total_size) { + retval = -EINVAL; + goto out_free_dentry; + } } error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt, - elf_prot, elf_flags, 0); + elf_prot, elf_flags, total_size); if (BAD_ADDR(error)) { send_sig(SIGKILL, current, 0); retval = IS_ERR((void *)error) ? diff --git a/fs/bio.c b/fs/bio.c index 8754e7b..b2b1451 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -1806,8 +1806,9 @@ EXPORT_SYMBOL(bio_endio_nodec); * Allocates and returns a new bio which represents @sectors from the start of * @bio, and updates @bio to represent the remaining sectors. * - * The newly allocated bio will point to @bio's bi_io_vec; it is the caller's - * responsibility to ensure that @bio is not freed before the split. + * Unless this is a discard request the newly allocated bio will point + * to @bio's bi_io_vec; it is the caller's responsibility to ensure that + * @bio is not freed before the split. */ struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs) @@ -1817,7 +1818,15 @@ struct bio *bio_split(struct bio *bio, int sectors, BUG_ON(sectors <= 0); BUG_ON(sectors >= bio_sectors(bio)); - split = bio_clone_fast(bio, gfp, bs); + /* + * Discards need a mutable bio_vec to accommodate the payload + * required by the DSM TRIM and UNMAP commands. + */ + if (bio->bi_rw & REQ_DISCARD) + split = bio_clone_bioset(bio, gfp, bs); + else + split = bio_clone_fast(bio, gfp, bs); + if (!split) return NULL; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 14d29d0..6244f9c 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -275,9 +275,8 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, } if (ret > 0) goto next; - ret = ulist_add_merge(parents, eb->start, - (uintptr_t)eie, - (u64 *)&old, GFP_NOFS); + ret = ulist_add_merge_ptr(parents, eb->start, + eie, (void **)&old, GFP_NOFS); if (ret < 0) break; if (!ret && extent_item_pos) { @@ -985,16 +984,19 @@ again: ret = -EIO; goto out; } + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); ret = find_extent_in_eb(eb, bytenr, *extent_item_pos, &eie); + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); if (ret < 0) goto out; ref->inode_list = eie; } - ret = ulist_add_merge(refs, ref->parent, - (uintptr_t)ref->inode_list, - (u64 *)&eie, GFP_NOFS); + ret = ulist_add_merge_ptr(refs, ref->parent, + ref->inode_list, + (void **)&eie, GFP_NOFS); if (ret < 0) goto out; if (!ret && extent_item_pos) { diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b01fb6c..d43c544 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -472,7 +472,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, pg_index); rcu_read_unlock(); - if (page) { + if (page && !radix_tree_exceptional_entry(page)) { misses++; if (misses > 4) break; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index cbd3a7d..f8ffee4 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2655,32 +2655,23 @@ static int key_search(struct extent_buffer *b, struct btrfs_key *key, return 0; } -int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *found_path, +int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path, u64 iobjectid, u64 ioff, u8 key_type, struct btrfs_key *found_key) { int ret; struct btrfs_key key; struct extent_buffer *eb; - struct btrfs_path *path; + + ASSERT(path); key.type = key_type; key.objectid = iobjectid; key.offset = ioff; - if (found_path == NULL) { - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - } else - path = found_path; - ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0); - if ((ret < 0) || (found_key == NULL)) { - if (path != found_path) - btrfs_free_path(path); + if ((ret < 0) || (found_key == NULL)) return ret; - } eb = path->nodes[0]; if (ret && path->slots[0] >= btrfs_header_nritems(eb)) { @@ -2972,7 +2963,7 @@ done: */ if (!p->leave_spinning) btrfs_set_path_blocking(p); - if (ret < 0) + if (ret < 0 && !p->skip_release_on_error) btrfs_release_path(p); return ret; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index d3511cc..3b39eb4 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -608,6 +608,7 @@ struct btrfs_path { unsigned int skip_locking:1; unsigned int leave_spinning:1; unsigned int search_commit_root:1; + unsigned int skip_release_on_error:1; }; /* @@ -3609,6 +3610,10 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, int verify_dir_item(struct btrfs_root *root, struct extent_buffer *leaf, struct btrfs_dir_item *dir_item); +struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, + struct btrfs_path *path, + const char *name, + int name_len); /* orphan.c */ int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 451b00c..12e3556 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1854,6 +1854,14 @@ int btrfs_delayed_delete_inode_ref(struct inode *inode) { struct btrfs_delayed_node *delayed_node; + /* + * we don't do delayed inode updates during log recovery because it + * leads to enospc problems. This means we also can't do + * delayed inode refs + */ + if (BTRFS_I(inode)->root->fs_info->log_root_recovering) + return -EAGAIN; + delayed_node = btrfs_get_or_create_delayed_node(inode); if (IS_ERR(delayed_node)) return PTR_ERR(delayed_node); diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index a0691df..9521a93 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -21,10 +21,6 @@ #include "hash.h" #include "transaction.h" -static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, - struct btrfs_path *path, - const char *name, int name_len); - /* * insert a name into a directory, doing overflow properly if there is a hash * collision. data_size indicates how big the item inserted should be. On @@ -383,9 +379,9 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, * this walks through all the entries in a dir item and finds one * for a specific name. */ -static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, - struct btrfs_path *path, - const char *name, int name_len) +struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, + struct btrfs_path *path, + const char *name, int name_len) { struct btrfs_dir_item *dir_item; unsigned long name_ptr; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 370ef74..f48d5fc 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1560,6 +1560,7 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, bool check_ref) { struct btrfs_root *root; + struct btrfs_path *path; int ret; if (location->objectid == BTRFS_ROOT_TREE_OBJECTID) @@ -1599,8 +1600,14 @@ again: if (ret) goto fail; - ret = btrfs_find_item(fs_info->tree_root, NULL, BTRFS_ORPHAN_OBJECTID, + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto fail; + } + ret = btrfs_find_item(fs_info->tree_root, path, BTRFS_ORPHAN_OBJECTID, location->objectid, BTRFS_ORPHAN_ITEM_KEY, NULL); + btrfs_free_path(path); if (ret < 0) goto fail; if (ret == 0) @@ -2411,7 +2418,7 @@ int open_ctree(struct super_block *sb, features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA) - printk(KERN_ERR "BTRFS: has skinny extents\n"); + printk(KERN_INFO "BTRFS: has skinny extents\n"); /* * flag our filesystem as having big metadata blocks if @@ -3978,12 +3985,6 @@ again: if (ret) break; - /* opt_discard */ - if (btrfs_test_opt(root, DISCARD)) - ret = btrfs_error_discard_extent(root, start, - end + 1 - start, - NULL); - clear_extent_dirty(unpin, start, end, GFP_NOFS); btrfs_error_unpin_extent_range(root, start, end); cond_resched(); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 3ff98e2..794d7c6 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5503,7 +5503,8 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, update_global_block_rsv(fs_info); } -static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) +static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end, + const bool return_free_space) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_group_cache *cache = NULL; @@ -5527,7 +5528,8 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) if (start < cache->last_byte_to_unpin) { len = min(len, cache->last_byte_to_unpin - start); - btrfs_add_free_space(cache, start, len); + if (return_free_space) + btrfs_add_free_space(cache, start, len); } start += len; @@ -5590,7 +5592,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, end + 1 - start, NULL); clear_extent_dirty(unpin, start, end, GFP_NOFS); - unpin_extent_range(root, start, end); + unpin_extent_range(root, start, end, true); cond_resched(); } @@ -6643,12 +6645,11 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root, return -ENOSPC; } - if (btrfs_test_opt(root, DISCARD)) - ret = btrfs_discard_extent(root, start, len, NULL); - if (pin) pin_down_extent(root, cache, start, len, 1); else { + if (btrfs_test_opt(root, DISCARD)) + ret = btrfs_discard_extent(root, start, len, NULL); btrfs_add_free_space(cache, start, len); btrfs_update_reserved_bytes(cache, len, RESERVE_FREE); } @@ -8886,7 +8887,7 @@ out: int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) { - return unpin_extent_range(root, start, end); + return unpin_extent_range(root, start, end, false); } int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 2eea43f..8adfc65 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2525,6 +2525,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err) test_bit(BIO_UPTODATE, &bio->bi_flags); if (err) uptodate = 0; + offset += len; continue; } } @@ -4288,8 +4289,11 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } ret = fiemap_fill_next_extent(fieinfo, em_start, disko, em_len, flags); - if (ret) + if (ret) { + if (ret == 1) + ret = 0; goto out_free; + } } out_free: free_extent_map(em); @@ -4506,7 +4510,8 @@ static void check_buffer_tree_ref(struct extent_buffer *eb) spin_unlock(&eb->refs_lock); } -static void mark_extent_buffer_accessed(struct extent_buffer *eb) +static void mark_extent_buffer_accessed(struct extent_buffer *eb, + struct page *accessed) { unsigned long num_pages, i; @@ -4515,7 +4520,8 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb) num_pages = num_extent_pages(eb->start, eb->len); for (i = 0; i < num_pages; i++) { struct page *p = extent_buffer_page(eb, i); - mark_page_accessed(p); + if (p != accessed) + mark_page_accessed(p); } } @@ -4529,7 +4535,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, start >> PAGE_CACHE_SHIFT); if (eb && atomic_inc_not_zero(&eb->refs)) { rcu_read_unlock(); - mark_extent_buffer_accessed(eb); + mark_extent_buffer_accessed(eb, NULL); return eb; } rcu_read_unlock(); @@ -4577,7 +4583,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, spin_unlock(&mapping->private_lock); unlock_page(p); page_cache_release(p); - mark_extent_buffer_accessed(exists); + mark_extent_buffer_accessed(exists, p); goto free_eb; } @@ -4592,7 +4598,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, attach_extent_buffer_page(eb, p); spin_unlock(&mapping->private_lock); WARN_ON(PageDirty(p)); - mark_page_accessed(p); eb->pages[i] = p; if (!PageUptodate(p)) uptodate = 0; diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 996ad56b..82845a6 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -290,8 +290,6 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len, if (!em) goto out; - if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags)) - list_move(&em->list, &tree->modified_extents); em->generation = gen; clear_bit(EXTENT_FLAG_PINNED, &em->flags); em->mod_start = em->start; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 127555b..196b089 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -423,7 +423,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, ret = 0; fail: while (ret < 0 && !list_empty(&tmplist)) { - sums = list_entry(&tmplist, struct btrfs_ordered_sum, list); + sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list); list_del(&sums->list); kfree(sums); } @@ -756,7 +756,7 @@ again: found_next = 1; if (ret != 0) goto insert; - slot = 0; + slot = path->slots[0]; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot); if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID || diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0165b86..0a841dd 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -425,13 +425,8 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages, struct page *page = prepared_pages[pg]; /* * Copy data from userspace to the current page - * - * Disable pagefault to avoid recursive lock since - * the pages are already locked */ - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, count); - pagefault_enable(); /* Flush processor's dcache for this page */ flush_dcache_page(page); @@ -475,11 +470,12 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) for (i = 0; i < num_pages; i++) { /* page checked is some magic around finding pages that * have been modified without going through btrfs_set_page_dirty - * clear it here + * clear it here. There should be no need to mark the pages + * accessed as prepare_pages should have marked them accessed + * in prepare_pages via find_or_create_page() */ ClearPageChecked(pages[i]); unlock_page(pages[i]); - mark_page_accessed(pages[i]); page_cache_release(pages[i]); } } @@ -1778,22 +1774,10 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, mutex_unlock(&inode->i_mutex); /* - * we want to make sure fsync finds this change - * but we haven't joined a transaction running right now. - * - * Later on, someone is sure to update the inode and get the - * real transid recorded. - * - * We set last_trans now to the fs_info generation + 1, - * this will either be one more than the running transaction - * or the generation used for the next transaction if there isn't - * one running right now. - * * We also have to set last_sub_trans to the current log transid, * otherwise subsequent syncs to a file that's been synced in this * transaction will appear to have already occured. */ - BTRFS_I(inode)->last_trans = root->fs_info->generation + 1; BTRFS_I(inode)->last_sub_trans = root->log_transid; if (num_written > 0) { err = generic_write_sync(file, pos, num_written); @@ -1896,25 +1880,37 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) atomic_inc(&root->log_batch); /* - * check the transaction that last modified this inode - * and see if its already been committed - */ - if (!BTRFS_I(inode)->last_trans) { - mutex_unlock(&inode->i_mutex); - goto out; - } - - /* - * if the last transaction that changed this file was before - * the current transaction, we can bail out now without any - * syncing + * If the last transaction that changed this file was before the current + * transaction and we have the full sync flag set in our inode, we can + * bail out now without any syncing. + * + * Note that we can't bail out if the full sync flag isn't set. This is + * because when the full sync flag is set we start all ordered extents + * and wait for them to fully complete - when they complete they update + * the inode's last_trans field through: + * + * btrfs_finish_ordered_io() -> + * btrfs_update_inode_fallback() -> + * btrfs_update_inode() -> + * btrfs_set_inode_last_trans() + * + * So we are sure that last_trans is up to date and can do this check to + * bail out safely. For the fast path, when the full sync flag is not + * set in our inode, we can not do it because we start only our ordered + * extents and don't wait for them to complete (that is when + * btrfs_finish_ordered_io runs), so here at this point their last_trans + * value might be less than or equals to fs_info->last_trans_committed, + * and setting a speculative last_trans for an inode when a buffered + * write is made (such as fs_info->generation + 1 for example) would not + * be reliable since after setting the value and before fsync is called + * any number of transactions can start and commit (transaction kthread + * commits the current transaction periodically), and a transaction + * commit does not start nor waits for ordered extents to complete. */ smp_mb(); if (btrfs_inode_in_log(inode, root->fs_info->generation) || - BTRFS_I(inode)->last_trans <= - root->fs_info->last_trans_committed) { - BTRFS_I(inode)->last_trans = 0; - + (full_sync && BTRFS_I(inode)->last_trans <= + root->fs_info->last_trans_committed)) { /* * We'v had everything committed since the last time we were * modified so clear this flag in case it was set for whatever @@ -2510,23 +2506,28 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence) struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_map *em = NULL; struct extent_state *cached_state = NULL; - u64 lockstart = *offset; - u64 lockend = i_size_read(inode); - u64 start = *offset; - u64 len = i_size_read(inode); + u64 lockstart; + u64 lockend; + u64 start; + u64 len; int ret = 0; - lockend = max_t(u64, root->sectorsize, lockend); + if (inode->i_size == 0) + return -ENXIO; + + /* + * *offset can be negative, in this case we start finding DATA/HOLE from + * the very start of the file. + */ + start = max_t(loff_t, 0, *offset); + + lockstart = round_down(start, root->sectorsize); + lockend = round_up(i_size_read(inode), root->sectorsize); if (lockend <= lockstart) lockend = lockstart + root->sectorsize; - lockend--; len = lockend - lockstart + 1; - len = max_t(u64, len, root->sectorsize); - if (inode->i_size == 0) - return -ENXIO; - lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, 0, &cached_state); diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index ab485e5..644942a 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -281,7 +281,7 @@ void btrfs_unpin_free_ino(struct btrfs_root *root) __btrfs_add_free_space(ctl, info->offset, count); free: rb_erase(&info->offset_index, rbroot); - kfree(info); + kmem_cache_free(btrfs_free_space_cachep, info); } } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d3d4448..653cdd8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -701,6 +701,18 @@ retry: unlock_extent(io_tree, async_extent->start, async_extent->start + async_extent->ram_size - 1); + + /* + * we need to redirty the pages if we decide to + * fallback to uncompressed IO, otherwise we + * will not submit these pages down to lower + * layers. + */ + extent_range_redirty_for_io(inode, + async_extent->start, + async_extent->start + + async_extent->ram_size - 1); + goto retry; } goto out_free; @@ -3584,7 +3596,8 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, * without delay */ if (!btrfs_is_free_space_inode(inode) - && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) { + && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID + && !root->fs_info->log_root_recovering) { btrfs_update_root_times(trans, root); ret = btrfs_delayed_update_inode(trans, root, inode); @@ -6857,7 +6870,6 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) && em->block_start != EXTENT_MAP_HOLE)) { int type; - int ret; u64 block_start, orig_start, orig_block_len, ram_bytes; if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a6d8efa..d40ae42 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -302,6 +302,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) goto out_drop; } else { + ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0); + if (ret && ret != -ENODATA) + goto out_drop; ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS); } @@ -2705,6 +2708,9 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 len, if (src == dst) return -EINVAL; + if (len == 0) + return 0; + btrfs_double_lock(src, loff, dst, dst_loff, len); ret = extent_same_check_offsets(src, loff, len); @@ -2737,7 +2743,7 @@ out_unlock: static long btrfs_ioctl_file_extent_same(struct file *file, struct btrfs_ioctl_same_args __user *argp) { - struct btrfs_ioctl_same_args *same; + struct btrfs_ioctl_same_args *same = NULL; struct btrfs_ioctl_same_extent_info *info; struct inode *src = file_inode(file); u64 off; @@ -2767,6 +2773,7 @@ static long btrfs_ioctl_file_extent_same(struct file *file, if (IS_ERR(same)) { ret = PTR_ERR(same); + same = NULL; goto out; } @@ -2837,6 +2844,7 @@ static long btrfs_ioctl_file_extent_same(struct file *file, out: mnt_drop_write_file(file); + kfree(same); return ret; } @@ -3223,6 +3231,11 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, if (off + len == src->i_size) len = ALIGN(src->i_size, bs) - off; + if (len == 0) { + ret = 0; + goto out_unlock; + } + /* verify the end result is block aligned */ if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) || !IS_ALIGNED(destoff, bs)) @@ -4750,6 +4763,12 @@ long btrfs_ioctl(struct file *file, unsigned int if (ret) return ret; ret = btrfs_sync_fs(file->f_dentry->d_sb, 1); + /* + * The transaction thread may want to do more work, + * namely it pokes the cleaner ktread that will start + * processing uncleaned subvols. + */ + wake_up_process(root->fs_info->transaction_kthread); return ret; } case BTRFS_IOC_START_SYNC: diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 07b3b36..01f977e 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -736,7 +736,8 @@ again: err = ret; goto out; } - BUG_ON(!ret || !path1->slots[0]); + ASSERT(ret); + ASSERT(path1->slots[0]); path1->slots[0]--; @@ -746,10 +747,10 @@ again: * the backref was added previously when processing * backref of type BTRFS_TREE_BLOCK_REF_KEY */ - BUG_ON(!list_is_singular(&cur->upper)); + ASSERT(list_is_singular(&cur->upper)); edge = list_entry(cur->upper.next, struct backref_edge, list[LOWER]); - BUG_ON(!list_empty(&edge->list[UPPER])); + ASSERT(list_empty(&edge->list[UPPER])); exist = edge->node[UPPER]; /* * add the upper level block to pending list if we need @@ -831,7 +832,7 @@ again: cur->cowonly = 1; } #else - BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY); + ASSERT(key.type != BTRFS_EXTENT_REF_V0_KEY); if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) { #endif if (key.objectid == key.offset) { @@ -840,7 +841,7 @@ again: * backref of this type. */ root = find_reloc_root(rc, cur->bytenr); - BUG_ON(!root); + ASSERT(root); cur->root = root; break; } @@ -868,7 +869,7 @@ again: } else { upper = rb_entry(rb_node, struct backref_node, rb_node); - BUG_ON(!upper->checked); + ASSERT(upper->checked); INIT_LIST_HEAD(&edge->list[UPPER]); } list_add_tail(&edge->list[LOWER], &cur->upper); @@ -892,7 +893,7 @@ again: if (btrfs_root_level(&root->root_item) == cur->level) { /* tree root */ - BUG_ON(btrfs_root_bytenr(&root->root_item) != + ASSERT(btrfs_root_bytenr(&root->root_item) == cur->bytenr); if (should_ignore_root(root)) list_add(&cur->list, &useless); @@ -927,7 +928,7 @@ again: need_check = true; for (; level < BTRFS_MAX_LEVEL; level++) { if (!path2->nodes[level]) { - BUG_ON(btrfs_root_bytenr(&root->root_item) != + ASSERT(btrfs_root_bytenr(&root->root_item) == lower->bytenr); if (should_ignore_root(root)) list_add(&lower->list, &useless); @@ -976,12 +977,15 @@ again: need_check = false; list_add_tail(&edge->list[UPPER], &list); - } else + } else { + if (upper->checked) + need_check = true; INIT_LIST_HEAD(&edge->list[UPPER]); + } } else { upper = rb_entry(rb_node, struct backref_node, rb_node); - BUG_ON(!upper->checked); + ASSERT(upper->checked); INIT_LIST_HEAD(&edge->list[UPPER]); if (!upper->owner) upper->owner = btrfs_header_owner(eb); @@ -1025,7 +1029,7 @@ next: * everything goes well, connect backref nodes and insert backref nodes * into the cache. */ - BUG_ON(!node->checked); + ASSERT(node->checked); cowonly = node->cowonly; if (!cowonly) { rb_node = tree_insert(&cache->rb_root, node->bytenr, @@ -1061,8 +1065,21 @@ next: continue; } - BUG_ON(!upper->checked); - BUG_ON(cowonly != upper->cowonly); + if (!upper->checked) { + /* + * Still want to blow up for developers since this is a + * logic bug. + */ + ASSERT(0); + err = -EINVAL; + goto out; + } + if (cowonly != upper->cowonly) { + ASSERT(0); + err = -EINVAL; + goto out; + } + if (!cowonly) { rb_node = tree_insert(&cache->rb_root, upper->bytenr, &upper->rb_node); @@ -1085,7 +1102,7 @@ next: while (!list_empty(&useless)) { upper = list_entry(useless.next, struct backref_node, list); list_del_init(&upper->list); - BUG_ON(!list_empty(&upper->upper)); + ASSERT(list_empty(&upper->upper)); if (upper == node) node = NULL; if (upper->lowest) { @@ -1118,29 +1135,45 @@ out: if (err) { while (!list_empty(&useless)) { lower = list_entry(useless.next, - struct backref_node, upper); - list_del_init(&lower->upper); + struct backref_node, list); + list_del_init(&lower->list); } - upper = node; - INIT_LIST_HEAD(&list); - while (upper) { - if (RB_EMPTY_NODE(&upper->rb_node)) { - list_splice_tail(&upper->upper, &list); - free_backref_node(cache, upper); - } - - if (list_empty(&list)) - break; - - edge = list_entry(list.next, struct backref_edge, - list[LOWER]); + while (!list_empty(&list)) { + edge = list_first_entry(&list, struct backref_edge, + list[UPPER]); + list_del(&edge->list[UPPER]); list_del(&edge->list[LOWER]); + lower = edge->node[LOWER]; upper = edge->node[UPPER]; free_backref_edge(cache, edge); + + /* + * Lower is no longer linked to any upper backref nodes + * and isn't in the cache, we can free it ourselves. + */ + if (list_empty(&lower->upper) && + RB_EMPTY_NODE(&lower->rb_node)) + list_add(&lower->list, &useless); + + if (!RB_EMPTY_NODE(&upper->rb_node)) + continue; + + /* Add this guy's upper edges to the list to proces */ + list_for_each_entry(edge, &upper->upper, list[LOWER]) + list_add_tail(&edge->list[UPPER], &list); + if (list_empty(&upper->upper)) + list_add(&upper->list, &useless); + } + + while (!list_empty(&useless)) { + lower = list_entry(useless.next, + struct backref_node, list); + list_del_init(&lower->list); + free_backref_node(cache, lower); } return ERR_PTR(err); } - BUG_ON(node && node->detached); + ASSERT(!node || !node->detached); return node; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index a65ed4c..20d7935 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -4728,7 +4728,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) if (S_ISREG(sctx->cur_inode_mode)) { if (need_send_hole(sctx)) { - if (sctx->cur_inode_last_extent == (u64)-1) { + if (sctx->cur_inode_last_extent == (u64)-1 || + sctx->cur_inode_last_extent < + sctx->cur_inode_size) { ret = get_last_extent(sctx, (u64)-1); if (ret) goto out; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index d04db81..92cbfbf 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -906,6 +906,15 @@ find_root: if (IS_ERR(new_root)) return ERR_CAST(new_root); + if (!(sb->s_flags & MS_RDONLY)) { + int ret; + down_read(&fs_info->cleanup_work_sem); + ret = btrfs_orphan_cleanup(new_root); + up_read(&fs_info->cleanup_work_sem); + if (ret) + return ERR_PTR(ret); + } + dir_id = btrfs_root_dirid(&new_root->root_item); setup_root: location.objectid = dir_id; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index b05bf58..a0b65a0 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -592,7 +592,6 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) if (transid <= root->fs_info->last_trans_committed) goto out; - ret = -EINVAL; /* find specified transaction */ spin_lock(&root->fs_info->trans_lock); list_for_each_entry(t, &root->fs_info->trans_list, list) { @@ -608,9 +607,16 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) } } spin_unlock(&root->fs_info->trans_lock); - /* The specified transaction doesn't exist */ - if (!cur_trans) + + /* + * The specified transaction doesn't exist, or we + * raced with btrfs_commit_transaction + */ + if (!cur_trans) { + if (transid > root->fs_info->last_trans_committed) + ret = -EINVAL; goto out; + } } else { /* find newest transaction that is committing | committed */ spin_lock(&root->fs_info->trans_lock); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 39d83da..ec8b654 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -979,7 +979,7 @@ again: base = btrfs_item_ptr_offset(leaf, path->slots[0]); while (cur_offset < item_size) { - extref = (struct btrfs_inode_extref *)base + cur_offset; + extref = (struct btrfs_inode_extref *)(base + cur_offset); victim_name_len = btrfs_inode_extref_name_len(leaf, extref); @@ -1235,13 +1235,14 @@ out: } static int insert_orphan_item(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 offset) + struct btrfs_root *root, u64 ino) { int ret; - ret = btrfs_find_item(root, NULL, BTRFS_ORPHAN_OBJECTID, - offset, BTRFS_ORPHAN_ITEM_KEY, NULL); - if (ret > 0) - ret = btrfs_insert_orphan_item(trans, root, offset); + + ret = btrfs_insert_orphan_item(trans, root, ino); + if (ret == -EEXIST) + ret = 0; + return ret; } diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h index 7f78cbf..4c29db6 100644 --- a/fs/btrfs/ulist.h +++ b/fs/btrfs/ulist.h @@ -57,6 +57,21 @@ void ulist_free(struct ulist *ulist); int ulist_add(struct ulist *ulist, u64 val, u64 aux, gfp_t gfp_mask); int ulist_add_merge(struct ulist *ulist, u64 val, u64 aux, u64 *old_aux, gfp_t gfp_mask); + +/* just like ulist_add_merge() but take a pointer for the aux data */ +static inline int ulist_add_merge_ptr(struct ulist *ulist, u64 val, void *aux, + void **old_aux, gfp_t gfp_mask) +{ +#if BITS_PER_LONG == 32 + u64 old64 = (uintptr_t)*old_aux; + int ret = ulist_add_merge(ulist, val, (uintptr_t)aux, &old64, gfp_mask); + *old_aux = (void *)((uintptr_t)old64); + return ret; +#else + return ulist_add_merge(ulist, val, (u64)aux, (u64 *)old_aux, gfp_mask); +#endif +} + struct ulist_node *ulist_next(struct ulist *ulist, struct ulist_iterator *uiter); diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index ad8328d..618e86c 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -29,6 +29,7 @@ #include "xattr.h" #include "disk-io.h" #include "props.h" +#include "locking.h" ssize_t __btrfs_getxattr(struct inode *inode, const char *name, @@ -91,7 +92,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const void *value, size_t size, int flags) { - struct btrfs_dir_item *di; + struct btrfs_dir_item *di = NULL; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_path *path; size_t name_len = strlen(name); @@ -103,84 +104,119 @@ static int do_setxattr(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) return -ENOMEM; + path->skip_release_on_error = 1; + + if (!value) { + di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), + name, name_len, -1); + if (!di && (flags & XATTR_REPLACE)) + ret = -ENODATA; + else if (di) + ret = btrfs_delete_one_dir_name(trans, root, path, di); + goto out; + } + /* + * For a replace we can't just do the insert blindly. + * Do a lookup first (read-only btrfs_search_slot), and return if xattr + * doesn't exist. If it exists, fall down below to the insert/replace + * path - we can't race with a concurrent xattr delete, because the VFS + * locks the inode's i_mutex before calling setxattr or removexattr. + */ if (flags & XATTR_REPLACE) { - di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), name, - name_len, -1); - if (IS_ERR(di)) { - ret = PTR_ERR(di); - goto out; - } else if (!di) { + ASSERT(mutex_is_locked(&inode->i_mutex)); + di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), + name, name_len, 0); + if (!di) { ret = -ENODATA; goto out; } - ret = btrfs_delete_one_dir_name(trans, root, path, di); - if (ret) - goto out; btrfs_release_path(path); + di = NULL; + } + ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode), + name, name_len, value, size); + if (ret == -EOVERFLOW) { /* - * remove the attribute + * We have an existing item in a leaf, split_leaf couldn't + * expand it. That item might have or not a dir_item that + * matches our target xattr, so lets check. */ - if (!value) - goto out; - } else { - di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), - name, name_len, 0); - if (IS_ERR(di)) { - ret = PTR_ERR(di); + ret = 0; + btrfs_assert_tree_locked(path->nodes[0]); + di = btrfs_match_dir_item_name(root, path, name, name_len); + if (!di && !(flags & XATTR_REPLACE)) { + ret = -ENOSPC; goto out; } - if (!di && !value) - goto out; - btrfs_release_path(path); + } else if (ret == -EEXIST) { + ret = 0; + di = btrfs_match_dir_item_name(root, path, name, name_len); + ASSERT(di); /* logic error */ + } else if (ret) { + goto out; } -again: - ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode), - name, name_len, value, size); - /* - * If we're setting an xattr to a new value but the new value is say - * exactly BTRFS_MAX_XATTR_SIZE, we could end up with EOVERFLOW getting - * back from split_leaf. This is because it thinks we'll be extending - * the existing item size, but we're asking for enough space to add the - * item itself. So if we get EOVERFLOW just set ret to EEXIST and let - * the rest of the function figure it out. - */ - if (ret == -EOVERFLOW) + if (di && (flags & XATTR_CREATE)) { ret = -EEXIST; + goto out; + } - if (ret == -EEXIST) { - if (flags & XATTR_CREATE) - goto out; + if (di) { /* - * We can't use the path we already have since we won't have the - * proper locking for a delete, so release the path and - * re-lookup to delete the thing. + * We're doing a replace, and it must be atomic, that is, at + * any point in time we have either the old or the new xattr + * value in the tree. We don't want readers (getxattr and + * listxattrs) to miss a value, this is specially important + * for ACLs. */ - btrfs_release_path(path); - di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), - name, name_len, -1); - if (IS_ERR(di)) { - ret = PTR_ERR(di); - goto out; - } else if (!di) { - /* Shouldn't happen but just in case... */ - btrfs_release_path(path); - goto again; + const int slot = path->slots[0]; + struct extent_buffer *leaf = path->nodes[0]; + const u16 old_data_len = btrfs_dir_data_len(leaf, di); + const u32 item_size = btrfs_item_size_nr(leaf, slot); + const u32 data_size = sizeof(*di) + name_len + size; + struct btrfs_item *item; + unsigned long data_ptr; + char *ptr; + + if (size > old_data_len) { + if (btrfs_leaf_free_space(root, leaf) < + (size - old_data_len)) { + ret = -ENOSPC; + goto out; + } } - ret = btrfs_delete_one_dir_name(trans, root, path, di); - if (ret) - goto out; + if (old_data_len + name_len + sizeof(*di) == item_size) { + /* No other xattrs packed in the same leaf item. */ + if (size > old_data_len) + btrfs_extend_item(root, path, + size - old_data_len); + else if (size < old_data_len) + btrfs_truncate_item(root, path, data_size, 1); + } else { + /* There are other xattrs packed in the same item. */ + ret = btrfs_delete_one_dir_name(trans, root, path, di); + if (ret) + goto out; + btrfs_extend_item(root, path, data_size); + } + item = btrfs_item_nr(slot); + ptr = btrfs_item_ptr(leaf, slot, char); + ptr += btrfs_item_size(leaf, item) - data_size; + di = (struct btrfs_dir_item *)ptr; + btrfs_set_dir_data_len(leaf, di, size); + data_ptr = ((unsigned long)(di + 1)) + name_len; + write_extent_buffer(leaf, value, data_ptr, size); + btrfs_mark_buffer_dirty(leaf); + } else { /* - * We have a value to set, so go back and try to insert it now. + * Insert, and we had space for the xattr, so path->slots[0] is + * where our xattr dir_item is and btrfs_insert_xattr_item() + * filled it. */ - if (value) { - btrfs_release_path(path); - goto again; - } } out: btrfs_free_path(path); @@ -324,22 +360,42 @@ const struct xattr_handler *btrfs_xattr_handlers[] = { /* * Check if the attribute is in a supported namespace. * - * This applied after the check for the synthetic attributes in the system + * This is applied after the check for the synthetic attributes in the system * namespace. */ -static bool btrfs_is_valid_xattr(const char *name) +static int btrfs_is_valid_xattr(const char *name) { - return !strncmp(name, XATTR_SECURITY_PREFIX, - XATTR_SECURITY_PREFIX_LEN) || - !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) || - !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) || - !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) || - !strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN); + int len = strlen(name); + int prefixlen = 0; + + if (!strncmp(name, XATTR_SECURITY_PREFIX, + XATTR_SECURITY_PREFIX_LEN)) + prefixlen = XATTR_SECURITY_PREFIX_LEN; + else if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) + prefixlen = XATTR_SYSTEM_PREFIX_LEN; + else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) + prefixlen = XATTR_TRUSTED_PREFIX_LEN; + else if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) + prefixlen = XATTR_USER_PREFIX_LEN; + else if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) + prefixlen = XATTR_BTRFS_PREFIX_LEN; + else + return -EOPNOTSUPP; + + /* + * The name cannot consist of just prefix + */ + if (len <= prefixlen) + return -EINVAL; + + return 0; } ssize_t btrfs_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size) { + int ret; + /* * If this is a request for a synthetic attribute in the system.* * namespace use the generic infrastructure to resolve a handler @@ -348,8 +404,9 @@ ssize_t btrfs_getxattr(struct dentry *dentry, const char *name, if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return generic_getxattr(dentry, name, buffer, size); - if (!btrfs_is_valid_xattr(name)) - return -EOPNOTSUPP; + ret = btrfs_is_valid_xattr(name); + if (ret) + return ret; return __btrfs_getxattr(dentry->d_inode, name, buffer, size); } @@ -357,6 +414,7 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root; + int ret; /* * The permission on security.* and system.* is not checked @@ -373,8 +431,9 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return generic_setxattr(dentry, name, value, size, flags); - if (!btrfs_is_valid_xattr(name)) - return -EOPNOTSUPP; + ret = btrfs_is_valid_xattr(name); + if (ret) + return ret; if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) return btrfs_set_prop(dentry->d_inode, name, @@ -390,6 +449,7 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, int btrfs_removexattr(struct dentry *dentry, const char *name) { struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root; + int ret; /* * The permission on security.* and system.* is not checked @@ -406,8 +466,9 @@ int btrfs_removexattr(struct dentry *dentry, const char *name) if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return generic_removexattr(dentry, name); - if (!btrfs_is_valid_xattr(name)) - return -EOPNOTSUPP; + ret = btrfs_is_valid_xattr(name); + if (ret) + return ret; if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) return btrfs_set_prop(dentry->d_inode, name, diff --git a/fs/buffer.c b/fs/buffer.c index 8c53a2b..f48650c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -227,7 +227,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) int all_mapped = 1; index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits); - page = find_get_page(bd_mapping, index); + page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; @@ -1029,7 +1029,8 @@ grow_dev_page(struct block_device *bdev, sector_t block, bh = page_buffers(page); if (bh->b_size == size) { end_block = init_page_buffers(page, bdev, - index << sizebits, size); + (sector_t)index << sizebits, + size); goto done; } if (!try_to_free_buffers(page)) @@ -1050,7 +1051,8 @@ grow_dev_page(struct block_device *bdev, sector_t block, */ spin_lock(&inode->i_mapping->private_lock); link_dev_buffers(page, bh); - end_block = init_page_buffers(page, bdev, index << sizebits, size); + end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, + size); spin_unlock(&inode->i_mapping->private_lock); done: ret = (block < end_block) ? 1 : -ENXIO; @@ -1366,12 +1368,13 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size) struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { + /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); - } - if (bh) + } else touch_buffer(bh); + return bh; } EXPORT_SYMBOL(__find_get_block); @@ -1483,16 +1486,27 @@ EXPORT_SYMBOL(set_bh_page); /* * Called when truncating a buffer on a page completely. */ + +/* Bits that are cleared during an invalidate */ +#define BUFFER_FLAGS_DISCARD \ + (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ + 1 << BH_Delay | 1 << BH_Unwritten) + static void discard_buffer(struct buffer_head * bh) { + unsigned long b_state, b_state_old; + lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; - clear_buffer_mapped(bh); - clear_buffer_req(bh); - clear_buffer_new(bh); - clear_buffer_delay(bh); - clear_buffer_unwritten(bh); + b_state = bh->b_state; + for (;;) { + b_state_old = cmpxchg(&bh->b_state, b_state, + (b_state & ~BUFFER_FLAGS_DISCARD)); + if (b_state_old == b_state) + break; + b_state = b_state_old; + } unlock_buffer(bh); } @@ -2075,6 +2089,7 @@ int generic_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { struct inode *inode = mapping->host; + loff_t old_size = inode->i_size; int i_size_changed = 0; copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); @@ -2094,6 +2109,8 @@ int generic_write_end(struct file *file, struct address_space *mapping, unlock_page(page); page_cache_release(page); + if (old_size < pos) + pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock @@ -2311,6 +2328,11 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, err = 0; balance_dirty_pages_ratelimited(mapping); + + if (unlikely(fatal_signal_pending(current))) { + err = -EINTR; + goto out; + } } /* page covers the boundary, find the boundary offset */ diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index b53278c..94a85ee 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -676,7 +676,7 @@ static int ceph_writepages_start(struct address_space *mapping, int rc = 0; unsigned wsize = 1 << inode->i_blkbits; struct ceph_osd_request *req = NULL; - int do_sync; + int do_sync = 0; u64 truncate_size, snap_size; u32 truncate_seq; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 5e0982a..18e14cf 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -111,7 +111,7 @@ static int fpos_cmp(loff_t l, loff_t r) /* * When possible, we try to satisfy a readdir by peeking at the * dcache. We make this work by carefully ordering dentries on - * d_u.d_child when we initially get results back from the MDS, and + * d_child when we initially get results back from the MDS, and * falling back to a "normal" sync readdir if any dentries in the dir * are dropped. * @@ -146,11 +146,11 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx) p = parent->d_subdirs.prev; dout(" initial p %p/%p\n", p->prev, p->next); } else { - p = last->d_u.d_child.prev; + p = last->d_child.prev; } more: - dentry = list_entry(p, struct dentry, d_u.d_child); + dentry = list_entry(p, struct dentry, d_child); di = ceph_dentry(dentry); while (1) { dout(" p %p/%p %s d_subdirs %p/%p\n", p->prev, p->next, @@ -172,7 +172,7 @@ more: !dentry->d_inode ? " null" : ""); spin_unlock(&dentry->d_lock); p = p->prev; - dentry = list_entry(p, struct dentry, d_u.d_child); + dentry = list_entry(p, struct dentry, d_child); di = ceph_dentry(dentry); } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 6471f9c..ee24490 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1289,7 +1289,7 @@ retry_lookup: /* reorder parent's d_subdirs */ spin_lock(&parent->d_lock); spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&dn->d_u.d_child, &parent->d_subdirs); + list_move(&dn->d_child, &parent->d_subdirs); spin_unlock(&dn->d_lock); spin_unlock(&parent->d_lock); } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index f4f050a..339c412 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1461,15 +1461,18 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc, dout("discard_cap_releases mds%d\n", session->s_mds); - /* zero out the in-progress message */ - msg = list_first_entry(&session->s_cap_releases, - struct ceph_msg, list_head); - head = msg->front.iov_base; - num = le32_to_cpu(head->num); - dout("discard_cap_releases mds%d %p %u\n", session->s_mds, msg, num); - head->num = cpu_to_le32(0); - msg->front.iov_len = sizeof(*head); - session->s_num_cap_releases += num; + if (!list_empty(&session->s_cap_releases)) { + /* zero out the in-progress message */ + msg = list_first_entry(&session->s_cap_releases, + struct ceph_msg, list_head); + head = msg->front.iov_base; + num = le32_to_cpu(head->num); + dout("discard_cap_releases mds%d %p %u\n", + session->s_mds, msg, num); + head->num = cpu_to_le32(0); + msg->front.iov_len = sizeof(*head); + session->s_num_cap_releases += num; + } /* requeue completed messages */ while (!list_empty(&session->s_cap_releases_done)) { diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 30f6e92..5d12d69 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -70,11 +70,6 @@ #define SERVER_NAME_LENGTH 40 #define SERVER_NAME_LEN_WITH_NULL (SERVER_NAME_LENGTH + 1) -/* used to define string lengths for reversing unicode strings */ -/* (256+1)*2 = 514 */ -/* (max path length + 1 for null) * 2 for unicode */ -#define MAX_NAME 514 - /* SMB echo "timeout" -- FIXME: tunable? */ #define SMB_ECHO_INTERVAL (60 * HZ) @@ -404,6 +399,8 @@ struct smb_version_operations { const struct cifs_fid *, u32 *); int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *, int); + /* check if we need to issue closedir */ + bool (*dir_needs_close)(struct cifsFileInfo *); }; struct smb_version_values { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 87c4dd0..40ddb6e 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -366,6 +366,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) struct cifsLockInfo *li, *tmp; struct cifs_fid fid; struct cifs_pending_open open; + bool oplock_break_cancelled; spin_lock(&cifs_file_list_lock); if (--cifs_file->count > 0) { @@ -397,7 +398,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) } spin_unlock(&cifs_file_list_lock); - cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -409,6 +410,9 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) _free_xid(xid); } + if (oplock_break_cancelled) + cifs_done_oplock_break(cifsi); + cifs_del_pending_open(&open); /* @@ -762,7 +766,7 @@ int cifs_closedir(struct inode *inode, struct file *file) cifs_dbg(FYI, "Freeing private data in close dir\n"); spin_lock(&cifs_file_list_lock); - if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) { + if (server->ops->dir_needs_close(cfile)) { cfile->invalidHandle = true; spin_unlock(&cifs_file_list_lock); if (server->ops->close_dir) @@ -1817,6 +1821,7 @@ refind_writable: cifsFileInfo_put(inv_file); spin_lock(&cifs_file_list_lock); ++refind; + inv_file = NULL; goto refind_writable; } } @@ -2844,7 +2849,7 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server, total_read += result; } - return total_read > 0 ? total_read : result; + return total_read > 0 && result != -EAGAIN ? total_read : result; } static ssize_t @@ -3267,7 +3272,7 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server, total_read += result; } - return total_read > 0 ? total_read : result; + return total_read > 0 && result != -EAGAIN ? total_read : result; } static int cifs_readpages(struct file *file, struct address_space *mapping, diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index aadc2b6..7ee427e 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -883,7 +883,7 @@ inode_has_hashed_dentries(struct inode *inode) struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { if (!d_unhashed(dentry) || IS_ROOT(dentry)) { spin_unlock(&inode->i_lock); return true; @@ -1706,13 +1706,22 @@ cifs_rename(struct inode *source_dir, struct dentry *source_dentry, unlink_target: /* Try unlinking the target dentry if it's not negative */ if (target_dentry->d_inode && (rc == -EACCES || rc == -EEXIST)) { - tmprc = cifs_unlink(target_dir, target_dentry); + if (d_is_dir(target_dentry)) + tmprc = cifs_rmdir(target_dir, target_dentry); + else + tmprc = cifs_unlink(target_dir, target_dentry); if (tmprc) goto cifs_rename_exit; rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); } + /* force revalidate to go get info when needed */ + CIFS_I(source_dir)->time = CIFS_I(target_dir)->time = 0; + + source_dir->i_ctime = source_dir->i_mtime = target_dir->i_ctime = + target_dir->i_mtime = current_fs_time(source_dir->i_sb); + cifs_rename_exit: kfree(info_buf_source); kfree(from_name); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 7749230..dfc9564 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -86,21 +86,16 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, } src_inode = src_file.file->f_dentry->d_inode; + rc = -EINVAL; + if (S_ISDIR(src_inode->i_mode)) + goto out_fput; /* * Note: cifs case is easier than btrfs since server responsible for * checks for proper open modes and file type and if it wants * server could even support copy of range where source = target */ - - /* so we do not deadlock racing two ioctls on same files */ - if (target_inode < src_inode) { - mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD); - } else { - mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_CHILD); - } + lock_two_nondirectories(target_inode, src_inode); /* determine range to clone */ rc = -EINVAL; @@ -124,13 +119,7 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, out_unlock: /* although unlocking in the reverse order from locking is not strictly necessary here it is a little cleaner to be consistent */ - if (target_inode < src_inode) { - mutex_unlock(&src_inode->i_mutex); - mutex_unlock(&target_inode->i_mutex); - } else { - mutex_unlock(&target_inode->i_mutex); - mutex_unlock(&src_inode->i_mutex); - } + unlock_two_nondirectories(src_inode, target_inode); out_fput: fdput(src_file); out_drop_write: diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 68559fd..a5c2812 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -213,8 +213,12 @@ create_mf_symlink(const unsigned int xid, struct cifs_tcon *tcon, if (rc) goto out; - rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon, cifs_sb, - fromName, buf, &bytes_written); + if (tcon->ses->server->ops->create_mf_symlink) + rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon, + cifs_sb, fromName, buf, &bytes_written); + else + rc = -EOPNOTSUPP; + if (rc) goto out; diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index b15862e..b334a89 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -593,11 +593,11 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, /* close and restart search */ cifs_dbg(FYI, "search backing up - close and restart search\n"); spin_lock(&cifs_file_list_lock); - if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) { + if (server->ops->dir_needs_close(cfile)) { cfile->invalidHandle = true; spin_unlock(&cifs_file_list_lock); - if (server->ops->close) - server->ops->close(xid, tcon, &cfile->fid); + if (server->ops->close_dir) + server->ops->close_dir(xid, tcon, &cfile->fid); } else spin_unlock(&cifs_file_list_lock); if (cfile->srch_inf.ntwrk_buf_start) { diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index d1fdfa8..e9ad8d3 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -586,7 +586,7 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, tmprc = CIFS_open(xid, &oparms, &oplock, NULL); if (tmprc == -EOPNOTSUPP) *symlink = true; - else + else if (tmprc == 0) CIFSSMBClose(xid, tcon, fid.netfid); } @@ -1009,6 +1009,12 @@ cifs_is_read_op(__u32 oplock) return oplock == OPLOCK_READ; } +static bool +cifs_dir_needs_close(struct cifsFileInfo *cfile) +{ + return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle; +} + struct smb_version_operations smb1_operations = { .send_cancel = send_nt_cancel, .compare_fids = cifs_compare_fids, @@ -1078,6 +1084,7 @@ struct smb_version_operations smb1_operations = { .query_mf_symlink = cifs_query_mf_symlink, .create_mf_symlink = cifs_create_mf_symlink, .is_read_op = cifs_is_read_op, + .dir_needs_close = cifs_dir_needs_close, #ifdef CONFIG_CIFS_XATTR .query_all_EAs = CIFSSMBQAllEAs, .set_EA = CIFSSMBSetEA, diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 3f17b45..4599294 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -50,7 +50,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, goto out; } - smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2, + smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, GFP_KERNEL); if (smb2_data == NULL) { rc = -ENOMEM; diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 84c012a..215f8d3 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -131,7 +131,7 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, *adjust_tz = false; *symlink = false; - smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2, + smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, GFP_KERNEL); if (smb2_data == NULL) return -ENOMEM; diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index 94bd4fb..a491814 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -214,7 +214,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_BREAKPOINT, -EIO, "STATUS_BREAKPOINT"}, {STATUS_SINGLE_STEP, -EIO, "STATUS_SINGLE_STEP"}, {STATUS_BUFFER_OVERFLOW, -EIO, "STATUS_BUFFER_OVERFLOW"}, - {STATUS_NO_MORE_FILES, -EIO, "STATUS_NO_MORE_FILES"}, + {STATUS_NO_MORE_FILES, -ENODATA, "STATUS_NO_MORE_FILES"}, {STATUS_WAKE_SYSTEM_DEBUGGER, -EIO, "STATUS_WAKE_SYSTEM_DEBUGGER"}, {STATUS_HANDLES_CLOSED, -EIO, "STATUS_HANDLES_CLOSED"}, {STATUS_NO_INHERITANCE, -EIO, "STATUS_NO_INHERITANCE"}, @@ -256,6 +256,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_DLL_MIGHT_BE_INCOMPATIBLE, -EIO, "STATUS_DLL_MIGHT_BE_INCOMPATIBLE"}, {STATUS_STOPPED_ON_SYMLINK, -EOPNOTSUPP, "STATUS_STOPPED_ON_SYMLINK"}, + {STATUS_IO_REPARSE_TAG_NOT_HANDLED, -EOPNOTSUPP, + "STATUS_REPARSE_NOT_HANDLED"}, {STATUS_DEVICE_REQUIRES_CLEANING, -EIO, "STATUS_DEVICE_REQUIRES_CLEANING"}, {STATUS_DEVICE_DOOR_OPEN, -EIO, "STATUS_DEVICE_DOOR_OPEN"}, @@ -605,7 +607,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_MAPPED_FILE_SIZE_ZERO, -EIO, "STATUS_MAPPED_FILE_SIZE_ZERO"}, {STATUS_TOO_MANY_OPENED_FILES, -EMFILE, "STATUS_TOO_MANY_OPENED_FILES"}, {STATUS_CANCELLED, -EIO, "STATUS_CANCELLED"}, - {STATUS_CANNOT_DELETE, -EIO, "STATUS_CANNOT_DELETE"}, + {STATUS_CANNOT_DELETE, -EACCES, "STATUS_CANNOT_DELETE"}, {STATUS_INVALID_COMPUTER_NAME, -EIO, "STATUS_INVALID_COMPUTER_NAME"}, {STATUS_FILE_DELETED, -EIO, "STATUS_FILE_DELETED"}, {STATUS_SPECIAL_ACCOUNT, -EIO, "STATUS_SPECIAL_ACCOUNT"}, diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 35ddc3e..30f3eb5 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -339,7 +339,7 @@ smb2_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, int rc; struct smb2_file_all_info *smb2_data; - smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2, + smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, GFP_KERNEL); if (smb2_data == NULL) return -ENOMEM; @@ -630,7 +630,8 @@ smb2_clone_range(const unsigned int xid, /* No need to change MaxChunks since already set to 1 */ chunk_sizes_updated = true; - } + } else + goto cchunk_out; } cchunk_out: @@ -1102,6 +1103,12 @@ smb3_parse_lease_buf(void *buf, unsigned int *epoch) return le32_to_cpu(lc->lcontext.LeaseState); } +static bool +smb2_dir_needs_close(struct cifsFileInfo *cfile) +{ + return !cfile->invalidHandle; +} + struct smb_version_operations smb20_operations = { .compare_fids = smb2_compare_fids, .setup_request = smb2_setup_request, @@ -1175,6 +1182,7 @@ struct smb_version_operations smb20_operations = { .create_lease_buf = smb2_create_lease_buf, .parse_lease_buf = smb2_parse_lease_buf, .clone_range = smb2_clone_range, + .dir_needs_close = smb2_dir_needs_close, }; struct smb_version_operations smb21_operations = { @@ -1250,6 +1258,7 @@ struct smb_version_operations smb21_operations = { .create_lease_buf = smb2_create_lease_buf, .parse_lease_buf = smb2_parse_lease_buf, .clone_range = smb2_clone_range, + .dir_needs_close = smb2_dir_needs_close, }; struct smb_version_operations smb30_operations = { @@ -1328,6 +1337,7 @@ struct smb_version_operations smb30_operations = { .parse_lease_buf = smb3_parse_lease_buf, .clone_range = smb2_clone_range, .validate_negotiate = smb3_validate_negotiate, + .dir_needs_close = smb2_dir_needs_close, }; struct smb_version_values smb20_values = { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 049a3f2..3487929 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -916,7 +916,8 @@ tcon_exit: tcon_error_exit: if (rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) { cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree); - tcon->bad_network_name = true; + if (tcon) + tcon->bad_network_name = true; } goto tcon_exit; } @@ -1539,7 +1540,7 @@ SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, { return query_info(xid, tcon, persistent_fid, volatile_fid, FILE_ALL_INFORMATION, - sizeof(struct smb2_file_all_info) + MAX_NAME * 2, + sizeof(struct smb2_file_all_info) + PATH_MAX * 2, sizeof(struct smb2_file_all_info), data); } @@ -2135,6 +2136,10 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, rsp = (struct smb2_query_directory_rsp *)iov[0].iov_base; if (rc) { + if (rc == -ENODATA && rsp->hdr.Status == STATUS_NO_MORE_FILES) { + srch_inf->endOfSearch = true; + rc = 0; + } cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE); goto qdir_exit; } @@ -2172,11 +2177,6 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, else cifs_dbg(VFS, "illegal search buffer type\n"); - if (rsp->hdr.Status == STATUS_NO_MORE_FILES) - srch_inf->endOfSearch = 1; - else - srch_inf->endOfSearch = 0; - return rc; qdir_exit: diff --git a/fs/coda/cache.c b/fs/coda/cache.c index 1da168c..9bc1147 100644 --- a/fs/coda/cache.c +++ b/fs/coda/cache.c @@ -92,7 +92,7 @@ static void coda_flag_children(struct dentry *parent, int flag) struct dentry *de; spin_lock(&parent->d_lock); - list_for_each_entry(de, &parent->d_subdirs, d_u.d_child) { + list_for_each_entry(de, &parent->d_subdirs, d_child) { /* don't know what to do with negative dentries */ if (de->d_inode ) coda_flag_inode(de->d_inode, flag); diff --git a/fs/coredump.c b/fs/coredump.c index 0b2528f..a93f7e6 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -306,7 +306,7 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, if (unlikely(nr < 0)) return nr; - tsk->flags = PF_DUMPCORE; + tsk->flags |= PF_DUMPCORE; if (atomic_read(&mm->mm_users) == nr + 1) goto done; /* diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 06610cf..a1f801c 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -195,8 +195,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i struct page *page = NULL; if (blocknr + i < devsize) { - page = read_mapping_page_async(mapping, blocknr + i, - NULL); + page = read_mapping_page(mapping, blocknr + i, NULL); /* synchronous error? */ if (IS_ERR(page)) page = NULL; diff --git a/fs/dcache.c b/fs/dcache.c index 7f3b400..df323f8 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -44,7 +44,7 @@ /* * Usage: * dcache->d_inode->i_lock protects: - * - i_dentry, d_alias, d_inode of aliases + * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_anon bl list spinlock protects: @@ -59,7 +59,7 @@ * - d_unhashed() * - d_parent and d_subdirs * - childrens' d_child and d_parent - * - d_alias, d_inode + * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock @@ -106,8 +106,7 @@ static inline struct hlist_bl_head *d_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; - hash = hash + (hash >> d_hash_shift); - return dentry_hashtable + (hash & d_hash_mask); + return dentry_hashtable + hash_32(hash, d_hash_shift); } /* Statistics gathering. */ @@ -240,22 +239,13 @@ static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); - WARN_ON(!hlist_unhashed(&dentry->d_alias)); if (dname_external(dentry)) kfree(dentry->d_name.name); kmem_cache_free(dentry_cache, dentry); } -/* - * no locks, please. - */ -static void d_free(struct dentry *dentry) +static void dentry_free(struct dentry *dentry) { - BUG_ON((int)dentry->d_lockref.count > 0); - this_cpu_dec(nr_dentry); - if (dentry->d_op && dentry->d_op->d_release) - dentry->d_op->d_release(dentry); - /* if dentry was never visible to RCU, immediate free is OK */ if (!(dentry->d_flags & DCACHE_RCUACCESS)) __d_free(&dentry->d_u.d_rcu); @@ -289,7 +279,7 @@ static void dentry_iput(struct dentry * dentry) struct inode *inode = dentry->d_inode; if (inode) { dentry->d_inode = NULL; - hlist_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_u.d_alias); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -314,7 +304,7 @@ static void dentry_unlink_inode(struct dentry * dentry) struct inode *inode = dentry->d_inode; __d_clear_type(dentry); dentry->d_inode = NULL; - hlist_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_u.d_alias); dentry_rcuwalk_barrier(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); @@ -403,56 +393,6 @@ static void dentry_lru_add(struct dentry *dentry) d_lru_add(dentry); } -/* - * Remove a dentry with references from the LRU. - * - * If we are on the shrink list, then we can get to try_prune_one_dentry() and - * lose our last reference through the parent walk. In this case, we need to - * remove ourselves from the shrink list, not the LRU. - */ -static void dentry_lru_del(struct dentry *dentry) -{ - if (dentry->d_flags & DCACHE_LRU_LIST) { - if (dentry->d_flags & DCACHE_SHRINK_LIST) - return d_shrink_del(dentry); - d_lru_del(dentry); - } -} - -/** - * d_kill - kill dentry and return parent - * @dentry: dentry to kill - * @parent: parent dentry - * - * The dentry must already be unhashed and removed from the LRU. - * - * If this is the root of the dentry tree, return NULL. - * - * dentry->d_lock and parent->d_lock must be held by caller, and are dropped by - * d_kill. - */ -static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent) - __releases(dentry->d_lock) - __releases(parent->d_lock) - __releases(dentry->d_inode->i_lock) -{ - list_del(&dentry->d_u.d_child); - /* - * Inform d_walk() that we are no longer attached to the - * dentry tree - */ - dentry->d_flags |= DCACHE_DENTRY_KILLED; - if (parent) - spin_unlock(&parent->d_lock); - dentry_iput(dentry); - /* - * dentry_iput drops the locks, at which point nobody (except - * transient RCU lookups) can reach this dentry. - */ - d_free(dentry); - return parent; -} - /** * d_drop - drop a dentry * @dentry: dentry to drop @@ -510,7 +450,14 @@ dentry_kill(struct dentry *dentry, int unlock_on_failure) __releases(dentry->d_lock) { struct inode *inode; - struct dentry *parent; + struct dentry *parent = NULL; + bool can_free = true; + + if (unlikely(dentry->d_flags & DCACHE_DENTRY_KILLED)) { + can_free = dentry->d_flags & DCACHE_MAY_FREE; + spin_unlock(&dentry->d_lock); + goto out; + } inode = dentry->d_inode; if (inode && !spin_trylock(&inode->i_lock)) { @@ -521,9 +468,7 @@ relock: } return dentry; /* try again with same dentry */ } - if (IS_ROOT(dentry)) - parent = NULL; - else + if (!IS_ROOT(dentry)) parent = dentry->d_parent; if (parent && !spin_trylock(&parent->d_lock)) { if (inode) @@ -543,10 +488,40 @@ relock: if ((dentry->d_flags & DCACHE_OP_PRUNE) && !d_unhashed(dentry)) dentry->d_op->d_prune(dentry); - dentry_lru_del(dentry); + if (dentry->d_flags & DCACHE_LRU_LIST) { + if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) + d_lru_del(dentry); + } /* if it was on the hash then remove it */ __d_drop(dentry); - return d_kill(dentry, parent); + __list_del_entry(&dentry->d_child); + /* + * Inform d_walk() that we are no longer attached to the + * dentry tree + */ + dentry->d_flags |= DCACHE_DENTRY_KILLED; + if (parent) + spin_unlock(&parent->d_lock); + dentry_iput(dentry); + /* + * dentry_iput drops the locks, at which point nobody (except + * transient RCU lookups) can reach this dentry. + */ + BUG_ON((int)dentry->d_lockref.count > 0); + this_cpu_dec(nr_dentry); + if (dentry->d_op && dentry->d_op->d_release) + dentry->d_op->d_release(dentry); + + spin_lock(&dentry->d_lock); + if (dentry->d_flags & DCACHE_SHRINK_LIST) { + dentry->d_flags |= DCACHE_MAY_FREE; + can_free = false; + } + spin_unlock(&dentry->d_lock); +out: + if (likely(can_free)) + dentry_free(dentry); + return parent; } /* @@ -588,6 +563,9 @@ repeat: if (unlikely(d_unhashed(dentry))) goto kill_it; + if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED)) + goto kill_it; + if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) { if (dentry->d_op->d_delete(dentry)) goto kill_it; @@ -738,7 +716,7 @@ static struct dentry *__d_find_alias(struct inode *inode, int want_discon) again: discon_alias = NULL; - hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) { if (IS_ROOT(alias) && @@ -791,7 +769,7 @@ void d_prune_aliases(struct inode *inode) struct dentry *dentry; restart: spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) { /* @@ -815,65 +793,13 @@ restart: } EXPORT_SYMBOL(d_prune_aliases); -/* - * Try to throw away a dentry - free the inode, dput the parent. - * Requires dentry->d_lock is held, and dentry->d_count == 0. - * Releases dentry->d_lock. - * - * This may fail if locks cannot be acquired no problem, just try again. - */ -static struct dentry * try_prune_one_dentry(struct dentry *dentry) - __releases(dentry->d_lock) -{ - struct dentry *parent; - - parent = dentry_kill(dentry, 0); - /* - * If dentry_kill returns NULL, we have nothing more to do. - * if it returns the same dentry, trylocks failed. In either - * case, just loop again. - * - * Otherwise, we need to prune ancestors too. This is necessary - * to prevent quadratic behavior of shrink_dcache_parent(), but - * is also expected to be beneficial in reducing dentry cache - * fragmentation. - */ - if (!parent) - return NULL; - if (parent == dentry) - return dentry; - - /* Prune ancestors. */ - dentry = parent; - while (dentry) { - if (lockref_put_or_lock(&dentry->d_lockref)) - return NULL; - dentry = dentry_kill(dentry, 1); - } - return NULL; -} - static void shrink_dentry_list(struct list_head *list) { - struct dentry *dentry; + struct dentry *dentry, *parent; - rcu_read_lock(); - for (;;) { - dentry = list_entry_rcu(list->prev, struct dentry, d_lru); - if (&dentry->d_lru == list) - break; /* empty */ - - /* - * Get the dentry lock, and re-verify that the dentry is - * this on the shrinking list. If it is, we know that - * DCACHE_SHRINK_LIST and DCACHE_LRU_LIST are set. - */ + while (!list_empty(list)) { + dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); - if (dentry != list_entry(list->prev, struct dentry, d_lru)) { - spin_unlock(&dentry->d_lock); - continue; - } - /* * The dispose list is isolated and dentries are not accounted * to the LRU here, so we can simply remove it from the list @@ -885,30 +811,38 @@ static void shrink_dentry_list(struct list_head *list) * We found an inuse dentry which was not removed from * the LRU because of laziness during lookup. Do not free it. */ - if (dentry->d_lockref.count) { + if ((int)dentry->d_lockref.count > 0) { spin_unlock(&dentry->d_lock); continue; } - rcu_read_unlock(); + parent = dentry_kill(dentry, 0); /* - * If 'try_to_prune()' returns a dentry, it will - * be the same one we passed in, and d_lock will - * have been held the whole time, so it will not - * have been added to any other lists. We failed - * to get the inode lock. - * - * We just add it back to the shrink list. + * If dentry_kill returns NULL, we have nothing more to do. */ - dentry = try_prune_one_dentry(dentry); + if (!parent) + continue; - rcu_read_lock(); - if (dentry) { + if (unlikely(parent == dentry)) { + /* + * trylocks have failed and d_lock has been held the + * whole time, so it could not have been added to any + * other lists. Just add it back to the shrink list. + */ d_shrink_add(dentry, list); spin_unlock(&dentry->d_lock); + continue; } + /* + * We need to prune ancestors too. This is necessary to prevent + * quadratic behavior of shrink_dcache_parent(), but is also + * expected to be beneficial in reducing dentry cache + * fragmentation. + */ + dentry = parent; + while (dentry && !lockref_put_or_lock(&dentry->d_lockref)) + dentry = dentry_kill(dentry, 1); } - rcu_read_unlock(); } static enum lru_status @@ -1092,7 +1026,7 @@ repeat: resume: while (next != &this_parent->d_subdirs) { struct list_head *tmp = next; - struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); + struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); @@ -1124,33 +1058,31 @@ resume: /* * All done at this level ... ascend and resume the search. */ + rcu_read_lock(); +ascend: if (this_parent != parent) { struct dentry *child = this_parent; this_parent = child->d_parent; - rcu_read_lock(); spin_unlock(&child->d_lock); spin_lock(&this_parent->d_lock); - /* - * might go back up the wrong parent if we have had a rename - * or deletion - */ - if (this_parent != child->d_parent || - (child->d_flags & DCACHE_DENTRY_KILLED) || - need_seqretry(&rename_lock, seq)) { - spin_unlock(&this_parent->d_lock); - rcu_read_unlock(); + /* might go back up the wrong parent if we have had a rename. */ + if (need_seqretry(&rename_lock, seq)) goto rename_retry; - } + /* go into the first sibling still alive */ + do { + next = child->d_child.next; + if (next == &this_parent->d_subdirs) + goto ascend; + child = list_entry(next, struct dentry, d_child); + } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); rcu_read_unlock(); - next = child->d_u.d_child.next; goto resume; } - if (need_seqretry(&rename_lock, seq)) { - spin_unlock(&this_parent->d_lock); + if (need_seqretry(&rename_lock, seq)) goto rename_retry; - } + rcu_read_unlock(); if (finish) finish(data); @@ -1160,6 +1092,9 @@ out_unlock: return; rename_retry: + spin_unlock(&this_parent->d_lock); + rcu_read_unlock(); + BUG_ON(seq & 1); if (!retry) return; seq = 1; @@ -1261,34 +1196,23 @@ static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) if (data->start == dentry) goto out; - /* - * move only zero ref count dentries to the dispose list. - * - * Those which are presently on the shrink list, being processed - * by shrink_dentry_list(), shouldn't be moved. Otherwise the - * loop in shrink_dcache_parent() might not make any progress - * and loop forever. - */ - if (dentry->d_lockref.count) { - dentry_lru_del(dentry); - } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { - /* - * We can't use d_lru_shrink_move() because we - * need to get the global LRU lock and do the - * LRU accounting. - */ - d_lru_del(dentry); - d_shrink_add(dentry, &data->dispose); + if (dentry->d_flags & DCACHE_SHRINK_LIST) { data->found++; - ret = D_WALK_NORETRY; + } else { + if (dentry->d_flags & DCACHE_LRU_LIST) + d_lru_del(dentry); + if (!dentry->d_lockref.count) { + d_shrink_add(dentry, &data->dispose); + data->found++; + } } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ - if (data->found && need_resched()) - ret = D_WALK_QUIT; + if (!list_empty(&data->dispose)) + ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } @@ -1318,45 +1242,35 @@ void shrink_dcache_parent(struct dentry *parent) } EXPORT_SYMBOL(shrink_dcache_parent); -static enum d_walk_ret umount_collect(void *_data, struct dentry *dentry) +static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { - struct select_data *data = _data; - enum d_walk_ret ret = D_WALK_CONTINUE; + /* it has busy descendents; complain about those instead */ + if (!list_empty(&dentry->d_subdirs)) + return D_WALK_CONTINUE; - if (dentry->d_lockref.count) { - dentry_lru_del(dentry); - if (likely(!list_empty(&dentry->d_subdirs))) - goto out; - if (dentry == data->start && dentry->d_lockref.count == 1) - goto out; - printk(KERN_ERR - "BUG: Dentry %p{i=%lx,n=%s}" - " still in use (%d)" - " [unmount of %s %s]\n", + /* root with refcount 1 is fine */ + if (dentry == _data && dentry->d_lockref.count == 1) + return D_WALK_CONTINUE; + + printk(KERN_ERR "BUG: Dentry %p{i=%lx,n=%pd} " + " still in use (%d) [unmount of %s %s]\n", dentry, dentry->d_inode ? dentry->d_inode->i_ino : 0UL, - dentry->d_name.name, + dentry, dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); - BUG(); - } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { - /* - * We can't use d_lru_shrink_move() because we - * need to get the global LRU lock and do the - * LRU accounting. - */ - if (dentry->d_flags & DCACHE_LRU_LIST) - d_lru_del(dentry); - d_shrink_add(dentry, &data->dispose); - data->found++; - ret = D_WALK_NORETRY; - } -out: - if (data->found && need_resched()) - ret = D_WALK_QUIT; - return ret; + WARN_ON(1); + return D_WALK_CONTINUE; +} + +static void do_one_tree(struct dentry *dentry) +{ + shrink_dcache_parent(dentry); + d_walk(dentry, dentry, umount_check, NULL); + d_drop(dentry); + dput(dentry); } /* @@ -1366,40 +1280,15 @@ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; - if (down_read_trylock(&sb->s_umount)) - BUG(); + WARN(down_read_trylock(&sb->s_umount), "s_umount should've been locked"); dentry = sb->s_root; sb->s_root = NULL; - for (;;) { - struct select_data data; - - INIT_LIST_HEAD(&data.dispose); - data.start = dentry; - data.found = 0; - - d_walk(dentry, &data, umount_collect, NULL); - if (!data.found) - break; - - shrink_dentry_list(&data.dispose); - cond_resched(); - } - d_drop(dentry); - dput(dentry); + do_one_tree(dentry); while (!hlist_bl_empty(&sb->s_anon)) { - struct select_data data; - dentry = hlist_bl_entry(hlist_bl_first(&sb->s_anon), struct dentry, d_hash); - - INIT_LIST_HEAD(&data.dispose); - data.start = NULL; - data.found = 0; - - d_walk(dentry, &data, umount_collect, NULL); - if (data.found) - shrink_dentry_list(&data.dispose); - cond_resched(); + dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_anon), struct dentry, d_hash)); + do_one_tree(dentry); } } @@ -1525,8 +1414,8 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); - INIT_HLIST_NODE(&dentry->d_alias); - INIT_LIST_HEAD(&dentry->d_u.d_child); + INIT_HLIST_NODE(&dentry->d_u.d_alias); + INIT_LIST_HEAD(&dentry->d_child); d_set_d_op(dentry, dentry->d_sb->s_d_op); this_cpu_inc(nr_dentry); @@ -1556,7 +1445,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) */ __dget_dlock(parent); dentry->d_parent = parent; - list_add(&dentry->d_u.d_child, &parent->d_subdirs); + list_add(&dentry->d_child, &parent->d_subdirs); spin_unlock(&parent->d_lock); return dentry; @@ -1649,7 +1538,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) spin_lock(&dentry->d_lock); __d_set_type(dentry, add_flags); if (inode) - hlist_add_head(&dentry->d_alias, &inode->i_dentry); + hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); dentry->d_inode = inode; dentry_rcuwalk_barrier(dentry); spin_unlock(&dentry->d_lock); @@ -1673,7 +1562,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) void d_instantiate(struct dentry *entry, struct inode * inode) { - BUG_ON(!hlist_unhashed(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) spin_lock(&inode->i_lock); __d_instantiate(entry, inode); @@ -1712,7 +1601,7 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry, return NULL; } - hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or @@ -1738,7 +1627,7 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode) { struct dentry *result; - BUG_ON(!hlist_unhashed(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) spin_lock(&inode->i_lock); @@ -1769,7 +1658,7 @@ EXPORT_SYMBOL(d_instantiate_unique); */ int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode) { - BUG_ON(!hlist_unhashed(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) { @@ -1808,7 +1697,7 @@ static struct dentry * __d_find_any_alias(struct inode *inode) if (hlist_empty(&inode->i_dentry)) return NULL; - alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); __dget(alias); return alias; } @@ -1885,7 +1774,7 @@ struct dentry *d_obtain_alias(struct inode *inode) spin_lock(&tmp->d_lock); tmp->d_inode = inode; tmp->d_flags |= add_flags; - hlist_add_head(&tmp->d_alias, &inode->i_dentry); + hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry); hlist_bl_lock(&tmp->d_sb->s_anon); hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon); hlist_bl_unlock(&tmp->d_sb->s_anon); @@ -2328,7 +2217,7 @@ int d_validate(struct dentry *dentry, struct dentry *dparent) struct dentry *child; spin_lock(&dparent->d_lock); - list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &dparent->d_subdirs, d_child) { if (dentry == child) { spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); __dget_dlock(dentry); @@ -2575,8 +2464,8 @@ static void __d_move(struct dentry * dentry, struct dentry * target) /* Unhash the target: dput() will then get rid of it */ __d_drop(target); - list_del(&dentry->d_u.d_child); - list_del(&target->d_u.d_child); + list_del(&dentry->d_child); + list_del(&target->d_child); /* Switch the names.. */ switch_names(dentry, target); @@ -2586,15 +2475,15 @@ static void __d_move(struct dentry * dentry, struct dentry * target) if (IS_ROOT(dentry)) { dentry->d_parent = target->d_parent; target->d_parent = target; - INIT_LIST_HEAD(&target->d_u.d_child); + INIT_LIST_HEAD(&target->d_child); } else { swap(dentry->d_parent, target->d_parent); /* And add them back to the (new) parent lists */ - list_add(&target->d_u.d_child, &target->d_parent->d_subdirs); + list_add(&target->d_child, &target->d_parent->d_subdirs); } - list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs); + list_add(&dentry->d_child, &dentry->d_parent->d_subdirs); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); @@ -2701,9 +2590,9 @@ static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon) swap(dentry->d_name.hash, anon->d_name.hash); dentry->d_parent = dentry; - list_del_init(&dentry->d_u.d_child); + list_del_init(&dentry->d_child); anon->d_parent = dparent; - list_move(&anon->d_u.d_child, &dparent->d_subdirs); + list_move(&anon->d_child, &dparent->d_subdirs); write_seqcount_end(&dentry->d_seq); write_seqcount_end(&anon->d_seq); @@ -2825,6 +2714,9 @@ static int prepend(char **buffer, int *buflen, const char *str, int namelen) * the beginning of the name. The sequence number check at the caller will * retry it again when a d_move() does happen. So any garbage in the buffer * due to mismatched pointer and length will be discarded. + * + * Data dependency barrier is needed to make sure that we see that terminating + * NUL. Alpha strikes again, film at 11... */ static int prepend_name(char **buffer, int *buflen, struct qstr *name) { @@ -2832,6 +2724,8 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name) u32 dlen = ACCESS_ONCE(name->len); char *p; + smp_read_barrier_depends(); + *buflen -= dlen + 1; if (*buflen < 0) return -ENAMETOOLONG; @@ -2900,17 +2794,6 @@ restart: vfsmnt = &mnt->mnt; continue; } - /* - * Filesystems needing to implement special "root names" - * should do so with ->d_dname() - */ - if (IS_ROOT(dentry) && - (dentry->d_name.len != 1 || - dentry->d_name.name[0] != '/')) { - WARN(1, "Root dentry has weird name <%.*s>\n", - (int) dentry->d_name.len, - dentry->d_name.name); - } if (!error) error = is_mounted(vfsmnt) ? 1 : 2; break; @@ -3329,7 +3212,7 @@ void d_tmpfile(struct dentry *dentry, struct inode *inode) { inode_dec_link_count(inode); BUG_ON(dentry->d_name.name != dentry->d_iname || - !hlist_unhashed(&dentry->d_alias) || + !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index ca4a08f..ece3842 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -245,10 +245,19 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root) return 0; } +static void debugfs_evict_inode(struct inode *inode) +{ + truncate_inode_pages(&inode->i_data, 0); + clear_inode(inode); + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_private); +} + static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .remount_fs = debugfs_remount, .show_options = debugfs_show_options, + .evict_inode = debugfs_evict_inode, }; static int debug_fill_super(struct super_block *sb, void *data, int silent) @@ -465,23 +474,14 @@ static int __debugfs_remove(struct dentry *dentry, struct dentry *parent) int ret = 0; if (debugfs_positive(dentry)) { - if (dentry->d_inode) { - dget(dentry); - switch (dentry->d_inode->i_mode & S_IFMT) { - case S_IFDIR: - ret = simple_rmdir(parent->d_inode, dentry); - break; - case S_IFLNK: - kfree(dentry->d_inode->i_private); - /* fall through */ - default: - simple_unlink(parent->d_inode, dentry); - break; - } - if (!ret) - d_delete(dentry); - dput(dentry); - } + dget(dentry); + if (S_ISDIR(dentry->d_inode->i_mode)) + ret = simple_rmdir(parent->d_inode, dentry); + else + simple_unlink(parent->d_inode, dentry); + if (!ret) + d_delete(dentry); + dput(dentry); } return ret; } @@ -533,7 +533,7 @@ EXPORT_SYMBOL_GPL(debugfs_remove); */ void debugfs_remove_recursive(struct dentry *dentry) { - struct dentry *child, *next, *parent; + struct dentry *child, *parent; if (IS_ERR_OR_NULL(dentry)) return; @@ -545,30 +545,49 @@ void debugfs_remove_recursive(struct dentry *dentry) parent = dentry; down: mutex_lock(&parent->d_inode->i_mutex); - list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) { + loop: + /* + * The parent->d_subdirs is protected by the d_lock. Outside that + * lock, the child can be unlinked and set to be freed which can + * use the d_u.d_child as the rcu head and corrupt this list. + */ + spin_lock(&parent->d_lock); + list_for_each_entry(child, &parent->d_subdirs, d_child) { if (!debugfs_positive(child)) continue; /* perhaps simple_empty(child) makes more sense */ if (!list_empty(&child->d_subdirs)) { + spin_unlock(&parent->d_lock); mutex_unlock(&parent->d_inode->i_mutex); parent = child; goto down; } - up: + + spin_unlock(&parent->d_lock); + if (!__debugfs_remove(child, parent)) simple_release_fs(&debugfs_mount, &debugfs_mount_count); + + /* + * The parent->d_lock protects agaist child from unlinking + * from d_subdirs. When releasing the parent->d_lock we can + * no longer trust that the next pointer is valid. + * Restart the loop. We'll skip this one with the + * debugfs_positive() check. + */ + goto loop; } + spin_unlock(&parent->d_lock); mutex_unlock(&parent->d_inode->i_mutex); child = parent; parent = parent->d_parent; mutex_lock(&parent->d_inode->i_mutex); - if (child != dentry) { - next = list_next_entry(child, d_u.d_child); - goto up; - } + if (child != dentry) + /* go up */ + goto loop; if (!__debugfs_remove(child, parent)) simple_release_fs(&debugfs_mount, &debugfs_mount_count); diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 2f6735d..31b148f 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1917,7 +1917,6 @@ ecryptfs_decode_from_filename(unsigned char *dst, size_t *dst_size, break; case 2: dst[dst_byte_offset++] |= (src_byte); - dst[dst_byte_offset] = 0; current_bit_offset = 0; break; } diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index b1eaa7a..03df502 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -191,23 +191,11 @@ static int ecryptfs_open(struct inode *inode, struct file *file) { int rc = 0; struct ecryptfs_crypt_stat *crypt_stat = NULL; - struct ecryptfs_mount_crypt_stat *mount_crypt_stat; struct dentry *ecryptfs_dentry = file->f_path.dentry; /* Private value of ecryptfs_dentry allocated in * ecryptfs_lookup() */ struct ecryptfs_file_info *file_info; - mount_crypt_stat = &ecryptfs_superblock_to_private( - ecryptfs_dentry->d_sb)->mount_crypt_stat; - if ((mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) - && ((file->f_flags & O_WRONLY) || (file->f_flags & O_RDWR) - || (file->f_flags & O_CREAT) || (file->f_flags & O_TRUNC) - || (file->f_flags & O_APPEND))) { - printk(KERN_WARNING "Mount has encrypted view enabled; " - "files may only be read\n"); - rc = -EPERM; - goto out; - } /* Released in ecryptfs_release or end of function if failure */ file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL); ecryptfs_set_file_private(file, file_info); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index b167ca4..a85ceb7 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -1039,7 +1039,7 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value, } rc = vfs_setxattr(lower_dentry, name, value, size, flags); - if (!rc) + if (!rc && dentry->d_inode) fsstack_copy_attr_all(dentry->d_inode, lower_dentry->d_inode); out: return rc; diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 1b119d3..34eb843 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -493,6 +493,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags { struct super_block *s; struct ecryptfs_sb_info *sbi; + struct ecryptfs_mount_crypt_stat *mount_crypt_stat; struct ecryptfs_dentry_info *root_info; const char *err = "Getting sb failed"; struct inode *inode; @@ -511,6 +512,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags err = "Error parsing options"; goto out; } + mount_crypt_stat = &sbi->mount_crypt_stat; s = sget(fs_type, NULL, set_anon_super, flags, NULL); if (IS_ERR(s)) { @@ -557,11 +559,19 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags /** * Set the POSIX ACL flag based on whether they're enabled in the lower - * mount. Force a read-only eCryptfs mount if the lower mount is ro. - * Allow a ro eCryptfs mount even when the lower mount is rw. + * mount. */ s->s_flags = flags & ~MS_POSIXACL; - s->s_flags |= path.dentry->d_sb->s_flags & (MS_RDONLY | MS_POSIXACL); + s->s_flags |= path.dentry->d_sb->s_flags & MS_POSIXACL; + + /** + * Force a read-only eCryptfs mount when: + * 1) The lower mount is ro + * 2) The ecryptfs_encrypted_view mount option is specified + */ + if (path.dentry->d_sb->s_flags & MS_RDONLY || + mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) + s->s_flags |= MS_RDONLY; s->s_maxbytes = path.dentry->d_sb->s_maxbytes; s->s_blocksize = path.dentry->d_sb->s_blocksize; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index ead0046..f50d79e 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1852,7 +1852,8 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ - ep_take_care_of_epollwakeup(&epds); + if (ep_op_has_event(op)) + ep_take_care_of_epollwakeup(&epds); /* * We have to check that the file structure underneath the file descriptor diff --git a/fs/exec.c b/fs/exec.c index 31e46b1..05f1942 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -820,7 +821,7 @@ EXPORT_SYMBOL(read_code); static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; - struct mm_struct * old_mm, *active_mm; + struct mm_struct *old_mm, *active_mm; /* Notify parent that we're no longer interested in the old VM */ tsk = current; @@ -846,6 +847,8 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); + tsk->mm->vmacache_seqnum = 0; + vmacache_flush(tsk); task_unlock(tsk); if (old_mm) { up_read(&old_mm->mmap_sem); @@ -1265,6 +1268,53 @@ static void check_unsafe_exec(struct linux_binprm *bprm) spin_unlock(&p->fs->lock); } +static void bprm_fill_uid(struct linux_binprm *bprm) +{ + struct inode *inode; + unsigned int mode; + kuid_t uid; + kgid_t gid; + + /* clear any previous set[ug]id data from a previous binary */ + bprm->cred->euid = current_euid(); + bprm->cred->egid = current_egid(); + + if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) + return; + + if (current->no_new_privs) + return; + + inode = file_inode(bprm->file); + mode = ACCESS_ONCE(inode->i_mode); + if (!(mode & (S_ISUID|S_ISGID))) + return; + + /* Be careful if suid/sgid is set */ + mutex_lock(&inode->i_mutex); + + /* reload atomically mode/uid/gid now that lock held */ + mode = inode->i_mode; + uid = inode->i_uid; + gid = inode->i_gid; + mutex_unlock(&inode->i_mutex); + + /* We ignore suid/sgid if there are no mappings for them in the ns */ + if (!kuid_has_mapping(bprm->cred->user_ns, uid) || + !kgid_has_mapping(bprm->cred->user_ns, gid)) + return; + + if (mode & S_ISUID) { + bprm->per_clear |= PER_CLEAR_ON_SETID; + bprm->cred->euid = uid; + } + + if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { + bprm->per_clear |= PER_CLEAR_ON_SETID; + bprm->cred->egid = gid; + } +} + /* * Fill the binprm structure from the inode. * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes @@ -1273,36 +1323,9 @@ static void check_unsafe_exec(struct linux_binprm *bprm) */ int prepare_binprm(struct linux_binprm *bprm) { - struct inode *inode = file_inode(bprm->file); - umode_t mode = inode->i_mode; int retval; - - /* clear any previous set[ug]id data from a previous binary */ - bprm->cred->euid = current_euid(); - bprm->cred->egid = current_egid(); - - if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) && - !current->no_new_privs && - kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) && - kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) { - /* Set-uid? */ - if (mode & S_ISUID) { - bprm->per_clear |= PER_CLEAR_ON_SETID; - bprm->cred->euid = inode->i_uid; - } - - /* Set-gid? */ - /* - * If setgid is set but no group execute bit then this - * is a candidate for mandatory locking, not a setgid - * executable. - */ - if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { - bprm->per_clear |= PER_CLEAR_ON_SETID; - bprm->cred->egid = inode->i_gid; - } - } + bprm_fill_uid(bprm); /* fill in binprm security blob */ retval = security_bprm_set_creds(bprm); diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 48a359d..831d4f0 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -50,7 +50,7 @@ find_acceptable_alias(struct dentry *result, inode = result->d_inode; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { dget(dentry); spin_unlock(&inode->i_lock); if (toput) diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 37fd31e..0498390 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1354,13 +1354,6 @@ set_qf_format: "not specified."); return 0; } - } else { - if (sbi->s_jquota_fmt) { - ext3_msg(sb, KERN_ERR, "error: journaled quota format " - "specified with no journaling " - "enabled."); - return 0; - } } #endif return 1; diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index 3285aa5..b610779 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -24,8 +24,7 @@ int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, __u32 provided, calculated; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo); @@ -46,8 +45,7 @@ void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); @@ -65,8 +63,7 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct ext4_sb_info *sbi = EXT4_SB(sb); int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo); @@ -91,8 +88,7 @@ void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group, __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 62f024c..2a6830a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2110,6 +2110,7 @@ int do_journal_get_write_access(handle_t *handle, #define CONVERT_INLINE_DATA 2 extern struct inode *ext4_iget(struct super_block *, unsigned long); +extern struct inode *ext4_iget_normal(struct super_block *, unsigned long); extern int ext4_write_inode(struct inode *, struct writeback_control *); extern int ext4_setattr(struct dentry *, struct iattr *); extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, @@ -2340,10 +2341,18 @@ extern int ext4_register_li_request(struct super_block *sb, static inline int ext4_has_group_desc_csum(struct super_block *sb) { return EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_GDT_CSUM | - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM); + EXT4_FEATURE_RO_COMPAT_GDT_CSUM) || + (EXT4_SB(sb)->s_chksum_driver != NULL); } +static inline int ext4_has_metadata_csum(struct super_block *sb) +{ + WARN_ON_ONCE(EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && + !EXT4_SB(sb)->s_chksum_driver); + + return (EXT4_SB(sb)->s_chksum_driver != NULL); +} static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) | diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 3fe29de..ff42208 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -87,6 +87,12 @@ int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) ext4_put_nojournal(handle); return 0; } + + if (!handle->h_transaction) { + err = jbd2_journal_stop(handle); + return handle->h_err ? handle->h_err : err; + } + sb = handle->h_transaction->t_journal->j_private; err = handle->h_err; rc = jbd2_journal_stop(handle); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 4718891..4e237a6 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -74,8 +74,7 @@ static int ext4_extent_block_csum_verify(struct inode *inode, { struct ext4_extent_tail *et; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return 1; et = find_ext4_extent_tail(eh); @@ -89,8 +88,7 @@ static void ext4_extent_block_csum_set(struct inode *inode, { struct ext4_extent_tail *et; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; et = find_ext4_extent_tail(eh); @@ -363,7 +361,7 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) ext4_lblk_t lblock = le32_to_cpu(ext->ee_block); ext4_lblk_t last = lblock + len - 1; - if (lblock > last) + if (len == 0 || lblock > last) return 0; return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); } diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 171b9fa..4e8b79d 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -656,6 +656,14 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, BUG_ON(end < lblk); + if ((status & EXTENT_STATUS_DELAYED) && + (status & EXTENT_STATUS_WRITTEN)) { + ext4_warning(inode->i_sb, "Inserting extent [%u/%u] as " + " delayed and written which can potentially " + " cause data loss.\n", lblk, len); + WARN_ON(1); + } + newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock(&newes, pblk); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 2a8b2e1..589117e 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -100,7 +100,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, struct blk_plug plug; int unaligned_aio = 0; ssize_t ret; - int overwrite = 0; + int *overwrite = iocb->private; size_t length = iov_length(iov, nr_segs); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) && @@ -118,8 +118,6 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, mutex_lock(&inode->i_mutex); blk_start_plug(&plug); - iocb->private = &overwrite; - /* check whether we do a DIO overwrite or not */ if (ext4_should_dioread_nolock(inode) && !unaligned_aio && !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) { @@ -143,7 +141,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, * So we should check these two conditions. */ if (err == len && (map.m_flags & EXT4_MAP_MAPPED)) - overwrite = 1; + *overwrite = 1; } ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); @@ -170,6 +168,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, { struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; + int overwrite = 0; /* * If we have encountered a bitmap-format file, the size limit @@ -190,6 +189,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, } } + iocb->private = &overwrite; if (unlikely(iocb->ki_filp->f_flags & O_DIRECT)) ret = ext4_file_dio_write(iocb, iov, nr_segs, pos); else diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 64bb32f1..a8d1a64 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -864,6 +864,10 @@ got: struct buffer_head *block_bitmap_bh; block_bitmap_bh = ext4_read_block_bitmap(sb, group); + if (!block_bitmap_bh) { + err = -EIO; + goto out; + } BUFFER_TRACE(block_bitmap_bh, "get block bitmap access"); err = ext4_journal_get_write_access(handle, block_bitmap_bh); if (err) { @@ -988,8 +992,7 @@ got: spin_unlock(&sbi->s_next_gen_lock); /* Precompute checksum seed for inode metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(sb)) { __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = cpu_to_le32(inode->i_generation); diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index e6574d7..a7c5277 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -576,7 +576,7 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { EXT4_ERROR_INODE(inode, "Can't allocate blocks for " "non-extent mapped inodes with bigalloc"); - return -ENOSPC; + return -EUCLEAN; } goal = ext4_find_goal(inode, map->m_lblk, partial); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 82edf5b..8c03b74 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1128,8 +1128,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE, inline_size - EXT4_INLINE_DOTDOT_SIZE); - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); inode->i_size = inode->i_sb->s_blocksize; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a7029f4..f9c63ae 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -83,8 +83,7 @@ static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw, if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || - !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + !ext4_has_metadata_csum(inode->i_sb)) return 1; provided = le16_to_cpu(raw->i_checksum_lo); @@ -105,8 +104,7 @@ static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || - !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + !ext4_has_metadata_csum(inode->i_sb)) return; csum = ext4_inode_csum(inode, raw, ei); @@ -571,6 +569,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) && + !(status & EXTENT_STATUS_WRITTEN) && ext4_find_delalloc_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1)) status |= EXTENT_STATUS_DELAYED; @@ -680,6 +679,7 @@ found: status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) && + !(status & EXTENT_STATUS_WRITTEN) && ext4_find_delalloc_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1)) status |= EXTENT_STATUS_DELAYED; @@ -1357,7 +1357,7 @@ static void ext4_da_page_release_reservation(struct page *page, unsigned int offset, unsigned int length) { - int to_release = 0; + int to_release = 0, contiguous_blks = 0; struct buffer_head *head, *bh; unsigned int curr_off = 0; struct inode *inode = page->mapping->host; @@ -1378,14 +1378,23 @@ static void ext4_da_page_release_reservation(struct page *page, if ((offset <= curr_off) && (buffer_delay(bh))) { to_release++; + contiguous_blks++; clear_buffer_delay(bh); + } else if (contiguous_blks) { + lblk = page->index << + (PAGE_CACHE_SHIFT - inode->i_blkbits); + lblk += (curr_off >> inode->i_blkbits) - + contiguous_blks; + ext4_es_remove_extent(inode, lblk, contiguous_blks); + contiguous_blks = 0; } curr_off = next_off; } while ((bh = bh->b_this_page) != head); - if (to_release) { + if (contiguous_blks) { lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - ext4_es_remove_extent(inode, lblk, to_release); + lblk += (curr_off >> inode->i_blkbits) - contiguous_blks; + ext4_es_remove_extent(inode, lblk, contiguous_blks); } /* If we have released all the blocks belonging to a cluster, then we @@ -1744,19 +1753,32 @@ static int __ext4_journalled_writepage(struct page *page, ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one); } - /* As soon as we unlock the page, it can go away, but we have - * references to buffers so we are safe */ + /* + * We need to release the page lock before we start the + * journal, so grab a reference so the page won't disappear + * out from under us. + */ + get_page(page); unlock_page(page); handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, ext4_writepage_trans_blocks(inode)); if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto out; + put_page(page); + goto out_no_pagelock; } - BUG_ON(!ext4_handle_valid(handle)); + lock_page(page); + put_page(page); + if (page->mapping != mapping) { + /* The page got truncated from under us */ + ext4_journal_stop(handle); + ret = 0; + goto out; + } + if (inline_data) { ret = ext4_journal_get_write_access(handle, inode_bh); @@ -1781,6 +1803,8 @@ static int __ext4_journalled_writepage(struct page *page, NULL, bput_one); ext4_set_inode_state(inode, EXT4_STATE_JDATA); out: + unlock_page(page); +out_no_pagelock: brelse(inode_bh); return ret; } @@ -2195,6 +2219,7 @@ static int mpage_map_and_submit_extent(handle_t *handle, struct ext4_map_blocks *map = &mpd->map; int err; loff_t disksize; + int progress = 0; mpd->io_submit.io_end->offset = ((loff_t)map->m_lblk) << inode->i_blkbits; @@ -2211,8 +2236,11 @@ static int mpage_map_and_submit_extent(handle_t *handle, * is non-zero, a commit should free up blocks. */ if ((err == -ENOMEM) || - (err == -ENOSPC && ext4_count_free_clusters(sb))) + (err == -ENOSPC && ext4_count_free_clusters(sb))) { + if (progress) + goto update_disksize; return err; + } ext4_msg(sb, KERN_CRIT, "Delayed block allocation failed for " "inode %lu at logical offset %llu with" @@ -2229,15 +2257,17 @@ static int mpage_map_and_submit_extent(handle_t *handle, *give_up_on_write = true; return err; } + progress = 1; /* * Update buffer state, submit mapped pages, and get us new * extent to map */ err = mpage_map_and_submit_buffers(mpd); if (err < 0) - return err; + goto update_disksize; } while (map->m_len); +update_disksize: /* * Update on-disk size after IO is submitted. Races with * truncate are avoided by checking i_size under i_data_sem. @@ -2627,6 +2657,20 @@ static int ext4_nonda_switch(struct super_block *sb) return 0; } +/* We always reserve for an inode update; the superblock could be there too */ +static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len) +{ + if (likely(EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_LARGE_FILE))) + return 1; + + if (pos + len <= 0x7fffffffULL) + return 1; + + /* We might need to update the superblock to set LARGE_FILE */ + return 2; +} + static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -2677,7 +2721,8 @@ retry_grab: * of file which has an already mapped buffer. */ retry_journal: - handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, 1); + handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, + ext4_da_write_credits(inode, pos, len)); if (IS_ERR(handle)) { page_cache_release(page); return PTR_ERR(handle); @@ -4055,8 +4100,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ei->i_extra_isize = 0; /* Precompute checksum seed for inode metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(sb)) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); @@ -4244,6 +4288,13 @@ bad_inode: return ERR_PTR(ret); } +struct inode *ext4_iget_normal(struct super_block *sb, unsigned long ino) +{ + if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) + return ERR_PTR(-EIO); + return ext4_iget(sb, ino); +} + static int ext4_inode_blocks_set(handle_t *handle, struct ext4_inode *raw_inode, struct ext4_inode_info *ei) @@ -4639,8 +4690,12 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) ext4_orphan_del(NULL, inode); goto err_out; } - } else + } else { + loff_t oldsize = inode->i_size; + i_size_write(inode, attr->ia_size); + pagecache_isize_extended(inode, oldsize, inode->i_size); + } /* * Blocks are going to be removed from the inode. Wait diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index a2a837f..dfe982d 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -343,8 +343,7 @@ flags_out: if (!inode_owner_or_capable(inode)) return -EPERM; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(inode->i_sb)) { ext4_warning(sb, "Setting inode version is not " "supported with metadata_csum enabled."); return -ENOTTY; @@ -544,9 +543,17 @@ group_add_out: } case EXT4_IOC_SWAP_BOOT: + { + int err; if (!(filp->f_mode & FMODE_WRITE)) return -EBADF; - return swap_inode_boot_loader(sb, inode); + err = mnt_want_write_file(filp); + if (err) + return err; + err = swap_inode_boot_loader(sb, inode); + mnt_drop_write_file(filp); + return err; + } case EXT4_IOC_RESIZE_FS: { ext4_fsblk_t n_blocks_count; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 502f0fd..c4a5e4d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1044,6 +1044,8 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) * allocating. If we are looking at the buddy cache we would * have taken a reference using ext4_mb_load_buddy and that * would have pinned buddy page to page cache. + * The call to ext4_mb_get_buddy_page_lock will mark the + * page accessed. */ ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { @@ -1062,7 +1064,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); if (e4b.bd_buddy_page == NULL) { /* @@ -1082,7 +1083,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); err: ext4_mb_put_buddy_page_lock(&e4b); return ret; @@ -1141,7 +1141,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, /* we could use find_or_create_page(), but it locks page * what we'd like to avoid in fast path ... */ - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) /* @@ -1172,15 +1172,16 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_bitmap_page = page; e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); block++; pnum = block / blocks_per_page; poff = block % blocks_per_page; - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) page_cache_release(page); @@ -1201,9 +1202,10 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_buddy_page = page; e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); BUG_ON(e4b->bd_bitmap_page == NULL); BUG_ON(e4b->bd_buddy_page == NULL); @@ -1398,6 +1400,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, int last = first + count - 1; struct super_block *sb = e4b->bd_sb; + if (WARN_ON(count == 0)) + return; BUG_ON(last >= (sb->s_blocksize << 3)); assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); /* Don't bother if the block group is corrupt. */ @@ -3196,8 +3200,30 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; + struct ext4_buddy e4b; + int err; - if (pa && pa->pa_type == MB_INODE_PA) + if (pa == NULL) { + if (ac->ac_f_ex.fe_len == 0) + return; + err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b); + if (err) { + /* + * This should never happen since we pin the + * pages in the ext4_allocation_context so + * ext4_mb_load_buddy() should never fail. + */ + WARN(1, "mb_load_buddy failed (%d)", err); + return; + } + ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group); + mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start, + ac->ac_f_ex.fe_len); + ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group); + ext4_mb_unload_buddy(&e4b); + return; + } + if (pa->pa_type == MB_INODE_PA) pa->pa_free += ac->ac_b_ex.fe_len; } @@ -4767,18 +4793,12 @@ do_more: /* * blocks being freed are metadata. these blocks shouldn't * be used until this transaction is committed + * + * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed + * to fail. */ - retry: - new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS); - if (!new_entry) { - /* - * We use a retry loop because - * ext4_free_blocks() is not allowed to fail. - */ - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); - goto retry; - } + new_entry = kmem_cache_alloc(ext4_free_data_cachep, + GFP_NOFS|__GFP_NOFAIL); new_entry->efd_start_cluster = bit; new_entry->efd_group = block_group; new_entry->efd_count = count_clusters; diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 2ae73a8..be92ed2 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -616,6 +616,7 @@ int ext4_ind_migrate(struct inode *inode) struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_extent *ex; unsigned int i, len; + ext4_lblk_t start, end; ext4_fsblk_t blk; handle_t *handle; int ret; @@ -629,6 +630,14 @@ int ext4_ind_migrate(struct inode *inode) EXT4_FEATURE_RO_COMPAT_BIGALLOC)) return -EOPNOTSUPP; + /* + * In order to get correct extent info, force all delayed allocation + * blocks to be allocated, otherwise delayed allocation blocks may not + * be reflected and bypass the checks on extent header. + */ + if (test_opt(inode->i_sb, DELALLOC)) + ext4_alloc_da_blocks(inode); + handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) return PTR_ERR(handle); @@ -646,11 +655,13 @@ int ext4_ind_migrate(struct inode *inode) goto errout; } if (eh->eh_entries == 0) - blk = len = 0; + blk = len = start = end = 0; else { len = le16_to_cpu(ex->ee_len); blk = ext4_ext_pblock(ex); - if (len > EXT4_NDIR_BLOCKS) { + start = le32_to_cpu(ex->ee_block); + end = start + len - 1; + if (end >= EXT4_NDIR_BLOCKS) { ret = -EOPNOTSUPP; goto errout; } @@ -658,7 +669,7 @@ int ext4_ind_migrate(struct inode *inode) ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); memset(ei->i_data, 0, sizeof(ei->i_data)); - for (i=0; i < len; i++) + for (i = start; i <= end; i++) ei->i_data[i] = cpu_to_le32(blk++); ext4_mark_inode_dirty(handle, inode); errout: diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 04434ad..1268a1b 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -20,8 +20,7 @@ static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp) int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp); @@ -29,8 +28,7 @@ int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp) void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; mmp->mmp_checksum = ext4_mmp_csum(sb, mmp); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d050e04..bc7e37b 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -123,8 +123,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, "directory leaf block found instead of index block"); return ERR_PTR(-EIO); } - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) || + if (!ext4_has_metadata_csum(inode->i_sb) || buffer_verified(bh)) return bh; @@ -339,8 +338,7 @@ int ext4_dirent_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent) { struct ext4_dir_entry_tail *t; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return 1; t = get_dirent_tail(inode, dirent); @@ -361,8 +359,7 @@ static void ext4_dirent_csum_set(struct inode *inode, { struct ext4_dir_entry_tail *t; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; t = get_dirent_tail(inode, dirent); @@ -437,8 +434,7 @@ static int ext4_dx_csum_verify(struct inode *inode, struct dx_tail *t; int count_offset, limit, count; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return 1; c = get_dx_countlimit(inode, dirent, &count_offset); @@ -467,8 +463,7 @@ static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent) struct dx_tail *t; int count_offset, limit, count; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; c = get_dx_countlimit(inode, dirent, &count_offset); @@ -556,8 +551,7 @@ static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize) unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) - EXT4_DIR_REC_LEN(2) - infosize; - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); return entry_space / sizeof(struct dx_entry); } @@ -566,8 +560,7 @@ static inline unsigned dx_node_limit(struct inode *dir) { unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0); - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); return entry_space / sizeof(struct dx_entry); } @@ -1429,7 +1422,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi dentry); return ERR_PTR(-EIO); } - inode = ext4_iget(dir->i_sb, ino); + inode = ext4_iget_normal(dir->i_sb, ino); if (inode == ERR_PTR(-ESTALE)) { EXT4_ERROR_INODE(dir, "deleted inode referenced: %u", @@ -1460,7 +1453,7 @@ struct dentry *ext4_get_parent(struct dentry *child) return ERR_PTR(-EIO); } - return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino)); + return d_obtain_alias(ext4_iget_normal(child->d_inode->i_sb, ino)); } /* @@ -1534,8 +1527,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, int csum_size = 0; int err = 0, i; - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); bh2 = ext4_append(handle, dir, &newblock); @@ -1704,8 +1696,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, int csum_size = 0; int err; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); if (!de) { @@ -1772,8 +1763,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, struct fake_dirent *fde; int csum_size = 0; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); blocksize = dir->i_sb->s_blocksize; @@ -1879,7 +1869,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, struct inode *inode) { struct inode *dir = dentry->d_parent->d_inode; - struct buffer_head *bh; + struct buffer_head *bh = NULL; struct ext4_dir_entry_2 *de; struct ext4_dir_entry_tail *t; struct super_block *sb; @@ -1889,8 +1879,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, ext4_lblk_t block, blocks; int csum_size = 0; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); sb = dir->i_sb; @@ -1904,14 +1893,14 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, return retval; if (retval == 1) { retval = 0; - return retval; + goto out; } } if (is_dx(dir)) { retval = ext4_dx_add_entry(handle, dentry, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) - return retval; + goto out; ext4_clear_inode_flag(dir, EXT4_INODE_INDEX); dx_fallback++; ext4_mark_inode_dirty(handle, dir); @@ -1923,14 +1912,15 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, return PTR_ERR(bh); retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh); - if (retval != -ENOSPC) { - brelse(bh); - return retval; - } + if (retval != -ENOSPC) + goto out; if (blocks == 1 && !dx_fallback && - EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) - return make_indexed_dir(handle, dentry, inode, bh); + EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) { + retval = make_indexed_dir(handle, dentry, inode, bh); + bh = NULL; /* make_indexed_dir releases bh */ + goto out; + } brelse(bh); } bh = ext4_append(handle, dir, &block); @@ -1946,6 +1936,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, } retval = add_dirent_to_buf(handle, dentry, inode, de, bh); +out: brelse(bh); if (retval == 0) ext4_set_inode_state(inode, EXT4_STATE_NEWENTRY); @@ -2152,8 +2143,7 @@ static int ext4_delete_entry(handle_t *handle, return err; } - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); BUFFER_TRACE(bh, "get_write_access"); @@ -2372,8 +2362,7 @@ static int ext4_init_new_dir(handle_t *handle, struct inode *dir, int csum_size = 0; int err; - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index f3b84cd..2400ad1 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1071,7 +1071,7 @@ static void update_backups(struct super_block *sb, int blk_off, char *data, break; if (meta_bg == 0) - backup_block = group * bpg + blk_off; + backup_block = ((ext4_fsblk_t)group) * bpg + blk_off; else backup_block = (ext4_group_first_block_no(sb, group) + ext4_bg_has_super(sb, group)); @@ -1200,8 +1200,7 @@ static int ext4_set_bitmap_checksums(struct super_block *sb, { struct buffer_head *bh; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 0; bh = ext4_get_bitmap(sb, group_data->inode_bitmap); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 25b327e..a07af5b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -140,8 +140,7 @@ static __le32 ext4_superblock_csum(struct super_block *sb, int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; return es->s_checksum == ext4_superblock_csum(sb, es); @@ -151,8 +150,7 @@ void ext4_superblock_csum_set(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; es->s_checksum = ext4_superblock_csum(sb, es); @@ -834,6 +832,7 @@ static void ext4_put_super(struct super_block *sb) dump_orphan_list(sb, sbi); J_ASSERT(list_empty(&sbi->s_orphan)); + sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) { /* @@ -996,7 +995,7 @@ static struct inode *ext4_nfs_get_inode(struct super_block *sb, * Currently we don't know the generation for parent directory, so * a generation of 0 means "accept any" */ - inode = ext4_iget(sb, ino); + inode = ext4_iget_normal(sb, ino); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation && inode->i_generation != generation) { @@ -1706,13 +1705,6 @@ static int parse_options(char *options, struct super_block *sb, "not specified"); return 0; } - } else { - if (sbi->s_jquota_fmt) { - ext4_msg(sb, KERN_ERR, "journaled quota format " - "specified with no journaling " - "enabled"); - return 0; - } } #endif if (test_opt(sb, DIOREAD_NOLOCK)) { @@ -2010,8 +2002,7 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, __u16 crc = 0; __le32 le_group = cpu_to_le32(block_group); - if ((sbi->s_es->s_feature_ro_compat & - cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) { + if (ext4_has_metadata_csum(sbi->s_sb)) { /* Use new metadata_csum algorithm */ __le16 save_csum; __u32 csum32; @@ -2029,6 +2020,10 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, } /* old crc16 code */ + if (!(sbi->s_es->s_feature_ro_compat & + cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM))) + return 0; + offset = offsetof(struct ext4_group_desc, bg_checksum); crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); @@ -3167,11 +3162,10 @@ static int set_journal_csum_feature_set(struct super_block *sb) int compat, incompat; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { - /* journal checksum v2 */ + if (ext4_has_metadata_csum(sb)) { + /* journal checksum v3 */ compat = 0; - incompat = JBD2_FEATURE_INCOMPAT_CSUM_V2; + incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3; } else { /* journal checksum v1 */ compat = JBD2_FEATURE_COMPAT_CHECKSUM; @@ -3193,6 +3187,7 @@ static int set_journal_csum_feature_set(struct super_block *sb) jbd2_journal_clear_features(sbi->s_journal, JBD2_FEATURE_COMPAT_CHECKSUM, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | + JBD2_FEATURE_INCOMPAT_CSUM_V3 | JBD2_FEATURE_INCOMPAT_CSUM_V2); } @@ -3474,8 +3469,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } /* Precompute checksum seed for all metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(sb)) sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, sizeof(es->s_uuid)); @@ -3493,6 +3487,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_EXT4_FS_POSIX_ACL set_opt(sb, POSIX_ACL); #endif + /* don't forget to enable journal_csum when metadata_csum is enabled. */ + if (ext4_has_metadata_csum(sb)) + set_opt(sb, JOURNAL_CHECKSUM); + if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA) set_opt(sb, JOURNAL_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 55e611c..8825154 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -141,8 +141,7 @@ static int ext4_xattr_block_csum_verify(struct inode *inode, sector_t block_nr, struct ext4_xattr_header *hdr) { - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && + if (ext4_has_metadata_csum(inode->i_sb) && (hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr))) return 0; return 1; @@ -152,8 +151,7 @@ static void ext4_xattr_block_csum_set(struct inode *inode, sector_t block_nr, struct ext4_xattr_header *hdr) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr); @@ -189,14 +187,28 @@ ext4_listxattr(struct dentry *dentry, char *buffer, size_t size) } static int -ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end) +ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end, + void *value_start) { - while (!IS_LAST_ENTRY(entry)) { - struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(entry); + struct ext4_xattr_entry *e = entry; + + while (!IS_LAST_ENTRY(e)) { + struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e); if ((void *)next >= end) return -EIO; - entry = next; + e = next; } + + while (!IS_LAST_ENTRY(entry)) { + if (entry->e_value_size != 0 && + (value_start + le16_to_cpu(entry->e_value_offs) < + (void *)e + sizeof(__u32) || + value_start + le16_to_cpu(entry->e_value_offs) + + le32_to_cpu(entry->e_value_size) > end)) + return -EIO; + entry = EXT4_XATTR_NEXT(entry); + } + return 0; } @@ -213,7 +225,8 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh) return -EIO; if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh))) return -EIO; - error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size); + error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size, + bh->b_data); if (!error) set_buffer_verified(bh); return error; @@ -329,7 +342,7 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, header = IHDR(inode, raw_inode); entry = IFIRST(header); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; - error = ext4_xattr_check_names(entry, end); + error = ext4_xattr_check_names(entry, end, entry); if (error) goto cleanup; error = ext4_xattr_find_entry(&entry, name_index, name, @@ -457,7 +470,7 @@ ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size) raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; - error = ext4_xattr_check_names(IFIRST(header), end); + error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header)); if (error) goto cleanup; error = ext4_xattr_list_entries(dentry, IFIRST(header), @@ -972,7 +985,8 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, is->s.here = is->s.first; is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { - error = ext4_xattr_check_names(IFIRST(header), is->s.end); + error = ext4_xattr_check_names(IFIRST(header), is->s.end, + IFIRST(header)); if (error) return error; /* Find the named attribute. */ diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 293d048..5c6fe27 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -71,7 +71,6 @@ repeat: goto repeat; } out: - mark_page_accessed(page); return page; } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index b0649b7..bb6478a 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -969,7 +969,6 @@ repeat: } got_it: f2fs_bug_on(nid != nid_of_node(page)); - mark_page_accessed(page); return page; } @@ -1024,7 +1023,6 @@ page_hit: f2fs_put_page(page, 1); return ERR_PTR(-EIO); } - mark_page_accessed(page); return page; } diff --git a/fs/fhandle.c b/fs/fhandle.c index 999ff5c..d59712d 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -195,8 +195,9 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh, goto out_err; } /* copy the full handle */ - if (copy_from_user(handle, ufh, - sizeof(struct file_handle) + + *handle = f_handle; + if (copy_from_user(&handle->f_handle, + &ufh->f_handle, f_handle.handle_bytes)) { retval = -EFAULT; goto out_handle; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index a163159..23a51f0 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -476,12 +476,28 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * write_inode() */ spin_lock(&inode->i_lock); - /* Clear I_DIRTY_PAGES if we've written out all dirty pages */ - if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) - inode->i_state &= ~I_DIRTY_PAGES; + dirty = inode->i_state & I_DIRTY; - inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC); + inode->i_state &= ~I_DIRTY; + + /* + * Paired with smp_mb() in __mark_inode_dirty(). This allows + * __mark_inode_dirty() to test i_state without grabbing i_lock - + * either they see the I_DIRTY bits cleared or we see the dirtied + * inode. + * + * I_DIRTY_PAGES is always cleared together above even if @mapping + * still has dirty pages. The flag is reinstated after smp_mb() if + * necessary. This guarantees that either __mark_inode_dirty() + * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. + */ + smp_mb(); + + if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) + inode->i_state |= I_DIRTY_PAGES; + spin_unlock(&inode->i_lock); + /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { int err = write_inode(inode, wbc); @@ -1145,12 +1161,11 @@ void __mark_inode_dirty(struct inode *inode, int flags) } /* - * make sure that changes are seen by all cpus before we test i_state - * -- mikulas + * Paired with smp_mb() in __writeback_single_inode() for the + * following lockless i_state test. See there for details. */ smp_mb(); - /* avoid the locking if we can */ if ((inode->i_state & flags) == flags) return; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 0a648bb..499155c 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -819,8 +819,8 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) newpage = buf->page; - if (WARN_ON(!PageUptodate(newpage))) - return -EIO; + if (!PageUptodate(newpage)) + SetPageUptodate(newpage); ClearPageMappedToDisk(newpage); @@ -1614,7 +1614,7 @@ out_finish: static void fuse_retrieve_end(struct fuse_conn *fc, struct fuse_req *req) { - release_pages(req->pages, req->num_pages, 0); + release_pages(req->pages, req->num_pages, false); } static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, @@ -1726,6 +1726,9 @@ copy_finish: static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, unsigned int size, struct fuse_copy_state *cs) { + /* Don't try to move pages (yet) */ + cs->move_pages = 0; + switch (code) { case FUSE_NOTIFY_POLL: return fuse_notify_poll(fc, size, cs); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 77bcc30..d8a6027 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1003,13 +1003,9 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - pagefault_disable(); tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes); - pagefault_enable(); flush_dcache_page(page); - mark_page_accessed(page); - if (!tmp) { unlock_page(page); page_cache_release(page); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 73f6bcb..faf00af 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1026,6 +1026,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) goto err_fput; fuse_conn_init(fc); + fc->release = fuse_free_conn; fc->dev = sb->s_dev; fc->sb = sb; @@ -1040,7 +1041,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fc->dont_mask = 1; sb->s_flags |= MS_POSIXACL; - fc->release = fuse_free_conn; fc->flags = d.flags; fc->user_id = d.user_id; fc->group_id = d.group_id; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 49436fa..4ccb60d 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -517,7 +517,6 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, p = kmap_atomic(page); memcpy(buf + copied, p + offset, amt); kunmap_atomic(p); - mark_page_accessed(page); page_cache_release(page); copied += amt; index++; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 5c52418..bc643b9 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -606,8 +606,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (!IS_ERR(inode)) { d = d_splice_alias(inode, dentry); error = PTR_ERR(d); - if (IS_ERR(d)) + if (IS_ERR(d)) { + inode = ERR_CAST(d); goto fail_gunlock; + } error = 0; if (file) { if (S_ISREG(inode->i_mode)) { @@ -823,7 +825,6 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry, d = d_splice_alias(inode, dentry); if (IS_ERR(d)) { - iput(inode); gfs2_glock_dq_uninit(&gh); return d; } diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index c7f2469..e7b1496 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -97,6 +97,11 @@ const struct address_space_operations gfs2_meta_aops = { .releasepage = gfs2_releasepage, }; +const struct address_space_operations gfs2_rgrp_aops = { + .writepage = gfs2_aspace_writepage, + .releasepage = gfs2_releasepage, +}; + /** * gfs2_getbuf - Get a buffer with a given address space * @gl: the glock @@ -131,7 +136,8 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) yield(); } } else { - page = find_lock_page(mapping, index); + page = find_get_page_flags(mapping, index, + FGP_LOCK|FGP_ACCESSED); if (!page) return NULL; } @@ -148,7 +154,6 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) map_bh(bh, sdp->sd_vfs, blkno); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); return bh; diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index 4823b93..ac5d802 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -38,12 +38,15 @@ static inline void gfs2_buffer_copy_tail(struct buffer_head *to_bh, } extern const struct address_space_operations gfs2_meta_aops; +extern const struct address_space_operations gfs2_rgrp_aops; static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping) { struct inode *inode = mapping->host; if (mapping->a_ops == &gfs2_meta_aops) return (((struct gfs2_glock *)mapping) - 1)->gl_sbd; + else if (mapping->a_ops == &gfs2_rgrp_aops) + return container_of(mapping, struct gfs2_sbd, sd_aspace); else return inode->i_sb->s_fs_info; } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index c6872d0..f6c9d83 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -104,7 +104,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) mapping = &sdp->sd_aspace; address_space_init_once(mapping); - mapping->a_ops = &gfs2_meta_aops; + mapping->a_ops = &gfs2_rgrp_aops; mapping->host = sb->s_bdev->bd_inode; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 6e560d5..754fdf8 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -131,13 +131,16 @@ skip: hfs_bnode_write(node, entry, data_off + key_len, entry_len); hfs_bnode_dump(node); - if (new_node) { - /* update parent key if we inserted a key - * at the start of the first node - */ - if (!rec && new_node != node) - hfs_brec_update_parent(fd); + /* + * update parent key if we inserted a key + * at the start of the node and it is not the new node + */ + if (!rec && new_node != node) { + hfs_bnode_read_key(node, fd->search_key, data_off + size); + hfs_brec_update_parent(fd); + } + if (new_node) { hfs_bnode_put(fd->bnode); if (!new_node->parent) { hfs_btree_inc_height(tree); @@ -168,9 +171,6 @@ skip: goto again; } - if (!rec) - hfs_brec_update_parent(fd); - return 0; } @@ -370,6 +370,8 @@ again: if (IS_ERR(parent)) return PTR_ERR(parent); __hfs_brec_find(parent, fd, hfs_find_rec_by_key); + if (fd->record < 0) + return -ENOENT; hfs_bnode_dump(parent); rec = fd->record; diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 1b39afd..5f60bb2 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -8,6 +8,17 @@ #include #include "hpfs_fn.h" +static void hpfs_update_directory_times(struct inode *dir) +{ + time_t t = get_seconds(); + if (t == dir->i_mtime.tv_sec && + t == dir->i_ctime.tv_sec) + return; + dir->i_mtime.tv_sec = dir->i_ctime.tv_sec = t; + dir->i_mtime.tv_nsec = dir->i_ctime.tv_nsec = 0; + hpfs_write_inode_nolock(dir); +} + static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { const unsigned char *name = dentry->d_name.name; @@ -99,6 +110,7 @@ static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) result->i_mode = mode | S_IFDIR; hpfs_write_inode_nolock(result); } + hpfs_update_directory_times(dir); d_instantiate(dentry, result); hpfs_unlock(dir->i_sb); return 0; @@ -187,6 +199,7 @@ static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, b result->i_mode = mode | S_IFREG; hpfs_write_inode_nolock(result); } + hpfs_update_directory_times(dir); d_instantiate(dentry, result); hpfs_unlock(dir->i_sb); return 0; @@ -262,6 +275,7 @@ static int hpfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, de insert_inode_hash(result); hpfs_write_inode_nolock(result); + hpfs_update_directory_times(dir); d_instantiate(dentry, result); brelse(bh); hpfs_unlock(dir->i_sb); @@ -340,6 +354,7 @@ static int hpfs_symlink(struct inode *dir, struct dentry *dentry, const char *sy insert_inode_hash(result); hpfs_write_inode_nolock(result); + hpfs_update_directory_times(dir); d_instantiate(dentry, result); hpfs_unlock(dir->i_sb); return 0; @@ -423,6 +438,8 @@ again: out1: hpfs_brelse4(&qbh); out: + if (!err) + hpfs_update_directory_times(dir); hpfs_unlock(dir->i_sb); return err; } @@ -477,6 +494,8 @@ static int hpfs_rmdir(struct inode *dir, struct dentry *dentry) out1: hpfs_brelse4(&qbh); out: + if (!err) + hpfs_update_directory_times(dir); hpfs_unlock(dir->i_sb); return err; } @@ -595,7 +614,7 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto end1; } - end: +end: hpfs_i(i)->i_parent_dir = new_dir->i_ino; if (S_ISDIR(i->i_mode)) { inc_nlink(new_dir); @@ -610,6 +629,10 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry, brelse(bh); } end1: + if (!err) { + hpfs_update_directory_times(old_dir); + hpfs_update_directory_times(new_dir); + } hpfs_unlock(i->i_sb); return err; } diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 4534ff6..77b583d 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -52,17 +52,20 @@ static void unmark_dirty(struct super_block *s) } /* Filesystem error... */ -static char err_buf[1024]; - void hpfs_error(struct super_block *s, const char *fmt, ...) { + struct va_format vaf; va_list args; va_start(args, fmt); - vsnprintf(err_buf, sizeof(err_buf), fmt, args); + + vaf.fmt = fmt; + vaf.va = &args; + + pr_err("filesystem error: %pV", &vaf); + va_end(args); - printk("HPFS: filesystem error: %s", err_buf); if (!hpfs_sb(s)->sb_was_error) { if (hpfs_sb(s)->sb_err == 2) { printk("; crashing the system because you wanted it\n"); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d19b30a..a4a8ed5 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1017,6 +1017,11 @@ static int __init init_hugetlbfs_fs(void) int error; int i; + if (!hugepages_supported()) { + pr_info("hugetlbfs: disabling because there are no supported hugepage sizes\n"); + return -ENOTSUPP; + } + error = bdi_init(&hugetlbfs_backing_dev_info); if (error) return error; diff --git a/fs/inode.c b/fs/inode.c index e846a32..644875b 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1631,8 +1631,8 @@ int file_remove_suid(struct file *file) error = security_inode_killpriv(dentry); if (!error && killsuid) error = __remove_suid(dentry, killsuid); - if (!error && (inode->i_sb->s_flags & MS_NOSEC)) - inode->i_flags |= S_NOSEC; + if (!error) + inode_has_no_xattr(inode); return error; } diff --git a/fs/ioprio.c b/fs/ioprio.c index e50170c..31666c9 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -157,14 +157,16 @@ out: int ioprio_best(unsigned short aprio, unsigned short bprio) { - unsigned short aclass = IOPRIO_PRIO_CLASS(aprio); - unsigned short bclass = IOPRIO_PRIO_CLASS(bprio); + unsigned short aclass; + unsigned short bclass; - if (aclass == IOPRIO_CLASS_NONE) - aclass = IOPRIO_CLASS_BE; - if (bclass == IOPRIO_CLASS_NONE) - bclass = IOPRIO_CLASS_BE; + if (!ioprio_valid(aprio)) + aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); + if (!ioprio_valid(bprio)) + bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); + aclass = IOPRIO_PRIO_CLASS(aprio); + bclass = IOPRIO_PRIO_CLASS(bprio); if (aclass == bclass) return min(aprio, bprio); if (aclass > bclass) diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 4a9e10e..a9daccb 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -61,7 +61,7 @@ static void isofs_put_super(struct super_block *sb) return; } -static int isofs_read_inode(struct inode *); +static int isofs_read_inode(struct inode *, int relocated); static int isofs_statfs (struct dentry *, struct kstatfs *); static struct kmem_cache *isofs_inode_cachep; @@ -1258,7 +1258,7 @@ out_toomany: goto out; } -static int isofs_read_inode(struct inode *inode) +static int isofs_read_inode(struct inode *inode, int relocated) { struct super_block *sb = inode->i_sb; struct isofs_sb_info *sbi = ISOFS_SB(sb); @@ -1403,7 +1403,7 @@ static int isofs_read_inode(struct inode *inode) */ if (!high_sierra) { - parse_rock_ridge_inode(de, inode); + parse_rock_ridge_inode(de, inode, relocated); /* if we want uid/gid set, override the rock ridge setting */ if (sbi->s_uid_set) inode->i_uid = sbi->s_uid; @@ -1482,9 +1482,10 @@ static int isofs_iget5_set(struct inode *ino, void *data) * offset that point to the underlying meta-data for the inode. The * code below is otherwise similar to the iget() code in * include/linux/fs.h */ -struct inode *isofs_iget(struct super_block *sb, - unsigned long block, - unsigned long offset) +struct inode *__isofs_iget(struct super_block *sb, + unsigned long block, + unsigned long offset, + int relocated) { unsigned long hashval; struct inode *inode; @@ -1506,7 +1507,7 @@ struct inode *isofs_iget(struct super_block *sb, return ERR_PTR(-ENOMEM); if (inode->i_state & I_NEW) { - ret = isofs_read_inode(inode); + ret = isofs_read_inode(inode, relocated); if (ret < 0) { iget_failed(inode); inode = ERR_PTR(ret); diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h index 9916723..0ac4c1f 100644 --- a/fs/isofs/isofs.h +++ b/fs/isofs/isofs.h @@ -107,7 +107,7 @@ extern int iso_date(char *, int); struct inode; /* To make gcc happy */ -extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *); +extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *, int relocated); extern int get_rock_ridge_filename(struct iso_directory_record *, char *, struct inode *); extern int isofs_name_translate(struct iso_directory_record *, char *, struct inode *); @@ -118,9 +118,24 @@ extern struct dentry *isofs_lookup(struct inode *, struct dentry *, unsigned int extern struct buffer_head *isofs_bread(struct inode *, sector_t); extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long); -extern struct inode *isofs_iget(struct super_block *sb, - unsigned long block, - unsigned long offset); +struct inode *__isofs_iget(struct super_block *sb, + unsigned long block, + unsigned long offset, + int relocated); + +static inline struct inode *isofs_iget(struct super_block *sb, + unsigned long block, + unsigned long offset) +{ + return __isofs_iget(sb, block, offset, 0); +} + +static inline struct inode *isofs_iget_reloc(struct super_block *sb, + unsigned long block, + unsigned long offset) +{ + return __isofs_iget(sb, block, offset, 1); +} /* Because the inode number is no longer relevant to finding the * underlying meta-data for an inode, we are free to choose a more diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index c0bf424..735d752 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -30,6 +30,7 @@ struct rock_state { int cont_size; int cont_extent; int cont_offset; + int cont_loops; struct inode *inode; }; @@ -73,6 +74,9 @@ static void init_rock_state(struct rock_state *rs, struct inode *inode) rs->inode = inode; } +/* Maximum number of Rock Ridge continuation entries */ +#define RR_MAX_CE_ENTRIES 32 + /* * Returns 0 if the caller should continue scanning, 1 if the scan must end * and -ve on error. @@ -105,6 +109,8 @@ static int rock_continue(struct rock_state *rs) goto out; } ret = -EIO; + if (++rs->cont_loops >= RR_MAX_CE_ENTRIES) + goto out; bh = sb_bread(rs->inode->i_sb, rs->cont_extent); if (bh) { memcpy(rs->buffer, bh->b_data + rs->cont_offset, @@ -288,12 +294,16 @@ eio: goto out; } +#define RR_REGARD_XA 1 +#define RR_RELOC_DE 2 + static int parse_rock_ridge_inode_internal(struct iso_directory_record *de, - struct inode *inode, int regard_xa) + struct inode *inode, int flags) { int symlink_len = 0; int cnt, sig; + unsigned int reloc_block; struct inode *reloc; struct rock_ridge *rr; int rootflag; @@ -305,7 +315,7 @@ parse_rock_ridge_inode_internal(struct iso_directory_record *de, init_rock_state(&rs, inode); setup_rock_ridge(de, inode, &rs); - if (regard_xa) { + if (flags & RR_REGARD_XA) { rs.chr += 14; rs.len -= 14; if (rs.len < 0) @@ -352,6 +362,9 @@ repeat: rs.cont_size = isonum_733(rr->u.CE.size); break; case SIG('E', 'R'): + /* Invalid length of ER tag id? */ + if (rr->u.ER.len_id + offsetof(struct rock_ridge, u.ER.data) > rr->len) + goto out; ISOFS_SB(inode->i_sb)->s_rock = 1; printk(KERN_DEBUG "ISO 9660 Extensions: "); { @@ -485,12 +498,22 @@ repeat: "relocated directory\n"); goto out; case SIG('C', 'L'): - ISOFS_I(inode)->i_first_extent = - isonum_733(rr->u.CL.location); - reloc = - isofs_iget(inode->i_sb, - ISOFS_I(inode)->i_first_extent, - 0); + if (flags & RR_RELOC_DE) { + printk(KERN_ERR + "ISOFS: Recursive directory relocation " + "is not supported\n"); + goto eio; + } + reloc_block = isonum_733(rr->u.CL.location); + if (reloc_block == ISOFS_I(inode)->i_iget5_block && + ISOFS_I(inode)->i_iget5_offset == 0) { + printk(KERN_ERR + "ISOFS: Directory relocation points to " + "itself\n"); + goto eio; + } + ISOFS_I(inode)->i_first_extent = reloc_block; + reloc = isofs_iget_reloc(inode->i_sb, reloc_block, 0); if (IS_ERR(reloc)) { ret = PTR_ERR(reloc); goto out; @@ -637,9 +660,11 @@ static char *get_symlink_chunk(char *rpnt, struct rock_ridge *rr, char *plimit) return rpnt; } -int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode) +int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode, + int relocated) { - int result = parse_rock_ridge_inode_internal(de, inode, 0); + int flags = relocated ? RR_RELOC_DE : 0; + int result = parse_rock_ridge_inode_internal(de, inode, flags); /* * if rockridge flag was reset and we didn't look for attributes @@ -647,7 +672,8 @@ int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode) */ if ((ISOFS_SB(inode->i_sb)->s_rock_offset == -1) && (ISOFS_SB(inode->i_sb)->s_rock == 2)) { - result = parse_rock_ridge_inode_internal(de, inode, 14); + result = parse_rock_ridge_inode_internal(de, inode, + flags | RR_REGARD_XA); } return result; } diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 7f34f47..b892355 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -448,7 +448,7 @@ int jbd2_cleanup_journal_tail(journal_t *journal) unsigned long blocknr; if (is_journal_aborted(journal)) - return 1; + return -EIO; if (!jbd2_journal_get_log_tail(journal, &first_tid, &blocknr)) return 1; @@ -463,10 +463,9 @@ int jbd2_cleanup_journal_tail(journal_t *journal) * jbd2_cleanup_journal_tail() doesn't get called all that often. */ if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); + blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS, NULL); - __jbd2_update_log_tail(journal, first_tid, blocknr); - return 0; + return __jbd2_update_log_tail(journal, first_tid, blocknr); } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index cf2fc05..9181c2b 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -97,7 +97,7 @@ static void jbd2_commit_block_csum_set(journal_t *j, struct buffer_head *bh) struct commit_header *h; __u32 csum; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; h = (struct commit_header *)(bh->b_data); @@ -313,11 +313,11 @@ static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh) return checksum; } -static void write_tag_block(int tag_bytes, journal_block_tag_t *tag, +static void write_tag_block(journal_t *j, journal_block_tag_t *tag, unsigned long long block) { tag->t_blocknr = cpu_to_be32(block & (u32)~0); - if (tag_bytes > JBD2_TAG_SIZE32) + if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_64BIT)) tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1); } @@ -327,7 +327,7 @@ static void jbd2_descr_block_csum_set(journal_t *j, struct jbd2_journal_block_tail *tail; __u32 csum; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize - @@ -340,12 +340,13 @@ static void jbd2_descr_block_csum_set(journal_t *j, static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag, struct buffer_head *bh, __u32 sequence) { + journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag; struct page *page = bh->b_page; __u8 *addr; __u32 csum32; __be32 seq; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; seq = cpu_to_be32(sequence); @@ -355,8 +356,10 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag, bh->b_size); kunmap_atomic(addr); - /* We only have space to store the lower 16 bits of the crc32c. */ - tag->t_checksum = cpu_to_be16(csum32); + if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + tag3->t_checksum = cpu_to_be32(csum32); + else + tag->t_checksum = cpu_to_be16(csum32); } /* * jbd2_journal_commit_transaction @@ -396,7 +399,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) LIST_HEAD(io_bufs); LIST_HEAD(log_bufs); - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) csum_size = sizeof(struct jbd2_journal_block_tail); /* @@ -692,7 +695,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) tag_flag |= JBD2_FLAG_SAME_UUID; tag = (journal_block_tag_t *) tagp; - write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr); + write_tag_block(journal, tag, jh2bh(jh)->b_blocknr); tag->t_flags = cpu_to_be16(tag_flag); jbd2_block_tag_csum_set(journal, tag, wbuf[bufs], commit_transaction->t_tid); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 5fa344a..e8d62d7 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -124,7 +124,7 @@ EXPORT_SYMBOL(__jbd2_debug); /* Checksumming functions */ int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb) { - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; return sb->s_checksum_type == JBD2_CRC32C_CHKSUM; @@ -145,7 +145,7 @@ static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb) { - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; return sb->s_checksum == jbd2_superblock_csum(j, sb); @@ -153,7 +153,7 @@ int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb) void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb) { - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; sb->s_checksum = jbd2_superblock_csum(j, sb); @@ -885,9 +885,10 @@ int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, * * Requires j_checkpoint_mutex */ -void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) +int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) { unsigned long freed; + int ret; BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); @@ -897,7 +898,10 @@ void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) * space and if we lose sb update during power failure we'd replay * old transaction with possibly newly overwritten data. */ - jbd2_journal_update_sb_log_tail(journal, tid, block, WRITE_FUA); + ret = jbd2_journal_update_sb_log_tail(journal, tid, block, WRITE_FUA); + if (ret) + goto out; + write_lock(&journal->j_state_lock); freed = block - journal->j_tail; if (block < journal->j_tail) @@ -913,6 +917,9 @@ void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) journal->j_tail_sequence = tid; journal->j_tail = block; write_unlock(&journal->j_state_lock); + +out: + return ret; } /* @@ -1331,7 +1338,7 @@ static int journal_reset(journal_t *journal) return jbd2_journal_start_thread(journal); } -static void jbd2_write_superblock(journal_t *journal, int write_op) +static int jbd2_write_superblock(journal_t *journal, int write_op) { struct buffer_head *bh = journal->j_sb_buffer; journal_superblock_t *sb = journal->j_superblock; @@ -1370,7 +1377,10 @@ static void jbd2_write_superblock(journal_t *journal, int write_op) printk(KERN_ERR "JBD2: Error %d detected when updating " "journal superblock for %s.\n", ret, journal->j_devname); + jbd2_journal_abort(journal, ret); } + + return ret; } /** @@ -1383,10 +1393,11 @@ static void jbd2_write_superblock(journal_t *journal, int write_op) * Update a journal's superblock information about log tail and write it to * disk, waiting for the IO to complete. */ -void jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, +int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, unsigned long tail_block, int write_op) { journal_superblock_t *sb = journal->j_superblock; + int ret; BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", @@ -1395,13 +1406,18 @@ void jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, sb->s_sequence = cpu_to_be32(tail_tid); sb->s_start = cpu_to_be32(tail_block); - jbd2_write_superblock(journal, write_op); + ret = jbd2_write_superblock(journal, write_op); + if (ret) + goto out; /* Log is no longer empty */ write_lock(&journal->j_state_lock); WARN_ON(!sb->s_sequence); journal->j_flags &= ~JBD2_FLUSHED; write_unlock(&journal->j_state_lock); + +out: + return ret; } /** @@ -1522,21 +1538,29 @@ static int journal_get_superblock(journal_t *journal) goto out; } - if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) && - JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + if (jbd2_journal_has_csum_v2or3(journal) && + JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) { /* Can't have checksum v1 and v2 on at the same time! */ printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 " "at the same time!\n"); goto out; } + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) && + JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) { + /* Can't have checksum v2 and v3 at the same time! */ + printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 " + "at the same time!\n"); + goto out; + } + if (!jbd2_verify_csum_type(journal, sb)) { printk(KERN_ERR "JBD2: Unknown checksum type\n"); goto out; } /* Load the checksum driver */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + if (jbd2_journal_has_csum_v2or3(journal)) { journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(journal->j_chksum_driver)) { printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); @@ -1553,7 +1577,7 @@ static int journal_get_superblock(journal_t *journal) } /* Precompute checksum seed for all metadata */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, sizeof(sb->s_uuid)); @@ -1813,8 +1837,14 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, if (!jbd2_journal_check_available_features(journal, compat, ro, incompat)) return 0; - /* Asking for checksumming v2 and v1? Only give them v2. */ - if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2 && + /* If enabling v2 checksums, turn on v3 instead */ + if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) { + incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2; + incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3; + } + + /* Asking for checksumming v3 and v1? Only give them v3. */ + if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 && compat & JBD2_FEATURE_COMPAT_CHECKSUM) compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM; @@ -1823,8 +1853,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, sb = journal->j_superblock; - /* If enabling v2 checksums, update superblock */ - if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + /* If enabling v3 checksums, update superblock */ + if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { sb->s_checksum_type = JBD2_CRC32C_CHKSUM; sb->s_feature_compat &= ~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM); @@ -1842,8 +1872,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, } /* Precompute checksum seed for all metadata */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, sizeof(sb->s_uuid)); @@ -1852,7 +1881,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, /* If enabling v1 checksums, downgrade superblock */ if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM)) sb->s_feature_incompat &= - ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2); + ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 | + JBD2_FEATURE_INCOMPAT_CSUM_V3); sb->s_feature_compat |= cpu_to_be32(compat); sb->s_feature_ro_compat |= cpu_to_be32(ro); @@ -1938,7 +1968,14 @@ int jbd2_journal_flush(journal_t *journal) return -EIO; mutex_lock(&journal->j_checkpoint_mutex); - jbd2_cleanup_journal_tail(journal); + if (!err) { + err = jbd2_cleanup_journal_tail(journal); + if (err < 0) { + mutex_unlock(&journal->j_checkpoint_mutex); + goto out; + } + err = 0; + } /* Finally, mark the journal as really needing no recovery. * This sets s_start==0 in the underlying superblock, which is @@ -1954,7 +1991,8 @@ int jbd2_journal_flush(journal_t *journal) J_ASSERT(journal->j_head == journal->j_tail); J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence); write_unlock(&journal->j_state_lock); - return 0; +out: + return err; } /** @@ -2165,16 +2203,20 @@ int jbd2_journal_blocks_per_page(struct inode *inode) */ size_t journal_tag_bytes(journal_t *journal) { - journal_block_tag_t tag; - size_t x = 0; + size_t sz; + + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + return sizeof(journal_block_tag3_t); + + sz = sizeof(journal_block_tag_t); if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) - x += sizeof(tag.t_checksum); + sz += sizeof(__u16); if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) - return x + JBD2_TAG_SIZE64; + return sz; else - return x + JBD2_TAG_SIZE32; + return sz - sizeof(__u32); } /* diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 3b6bb19..a5f72a3 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -181,7 +181,7 @@ static int jbd2_descr_block_csum_verify(journal_t *j, __be32 provided; __u32 calculated; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; tail = (struct jbd2_journal_block_tail *)(buf + j->j_blocksize - @@ -205,7 +205,7 @@ static int count_tags(journal_t *journal, struct buffer_head *bh) int nr = 0, size = journal->j_blocksize; int tag_bytes = journal_tag_bytes(journal); - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) size -= sizeof(struct jbd2_journal_block_tail); tagp = &bh->b_data[sizeof(journal_header_t)]; @@ -338,10 +338,11 @@ int jbd2_journal_skip_recovery(journal_t *journal) return err; } -static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag) +static inline unsigned long long read_tag_block(journal_t *journal, + journal_block_tag_t *tag) { unsigned long long block = be32_to_cpu(tag->t_blocknr); - if (tag_bytes > JBD2_TAG_SIZE32) + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32; return block; } @@ -384,7 +385,7 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) __be32 provided; __u32 calculated; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; h = buf; @@ -399,17 +400,21 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag, void *buf, __u32 sequence) { + journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag; __u32 csum32; __be32 seq; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; seq = cpu_to_be32(sequence); csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq)); csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize); - return tag->t_checksum == cpu_to_be16(csum32); + if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + return tag3->t_checksum == cpu_to_be32(csum32); + else + return tag->t_checksum == cpu_to_be16(csum32); } static int do_one_pass(journal_t *journal, @@ -426,6 +431,7 @@ static int do_one_pass(journal_t *journal, int tag_bytes = journal_tag_bytes(journal); __u32 crc32_sum = ~0; /* Transactional Checksums */ int descr_csum_size = 0; + int block_error = 0; /* * First thing is to establish what we expect to find in the log @@ -512,14 +518,14 @@ static int do_one_pass(journal_t *journal, switch(blocktype) { case JBD2_DESCRIPTOR_BLOCK: /* Verify checksum first */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) descr_csum_size = sizeof(struct jbd2_journal_block_tail); if (descr_csum_size > 0 && !jbd2_descr_block_csum_verify(journal, bh->b_data)) { err = -EIO; + brelse(bh); goto failed; } @@ -574,7 +580,7 @@ static int do_one_pass(journal_t *journal, unsigned long long blocknr; J_ASSERT(obh != NULL); - blocknr = read_tag_block(tag_bytes, + blocknr = read_tag_block(journal, tag); /* If the block has been @@ -598,7 +604,8 @@ static int do_one_pass(journal_t *journal, "checksum recovering " "block %llu in log\n", blocknr); - continue; + block_error = 1; + goto skip_write; } /* Find a buffer for the new @@ -797,7 +804,8 @@ static int do_one_pass(journal_t *journal, success = -EIO; } } - + if (block_error && success == 0) + success = -EIO; return success; failed: @@ -811,7 +819,7 @@ static int jbd2_revoke_block_csum_verify(journal_t *j, __be32 provided; __u32 calculated; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize - @@ -831,15 +839,23 @@ static int scan_revoke_records(journal_t *journal, struct buffer_head *bh, { jbd2_journal_revoke_header_t *header; int offset, max; + int csum_size = 0; + __u32 rcount; int record_len = 4; header = (jbd2_journal_revoke_header_t *) bh->b_data; offset = sizeof(jbd2_journal_revoke_header_t); - max = be32_to_cpu(header->r_count); + rcount = be32_to_cpu(header->r_count); if (!jbd2_revoke_block_csum_verify(journal, header)) return -EINVAL; + if (jbd2_journal_has_csum_v2or3(journal)) + csum_size = sizeof(struct jbd2_journal_revoke_tail); + if (rcount > journal->j_blocksize - csum_size) + return -EINVAL; + max = rcount; + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) record_len = 8; diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 198c9c1..8ecf9b9 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -91,8 +91,8 @@ #include #include #include -#endif #include +#endif static struct kmem_cache *jbd2_revoke_record_cache; static struct kmem_cache *jbd2_revoke_table_cache; @@ -583,7 +583,7 @@ static void write_one_revoke_record(journal_t *journal, { int csum_size = 0; struct buffer_head *descriptor; - int offset; + int sz, offset; journal_header_t *header; /* If we are already aborting, this all becomes a noop. We @@ -597,12 +597,17 @@ static void write_one_revoke_record(journal_t *journal, offset = *offsetp; /* Do we need to leave space at the end for a checksum? */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) csum_size = sizeof(struct jbd2_journal_revoke_tail); + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) + sz = 8; + else + sz = 4; + /* Make sure we have a descriptor with space left for the record */ if (descriptor) { - if (offset >= journal->j_blocksize - csum_size) { + if (offset + sz > journal->j_blocksize - csum_size) { flush_descriptor(journal, descriptor, offset, write_op); descriptor = NULL; } @@ -625,16 +630,13 @@ static void write_one_revoke_record(journal_t *journal, *descriptorp = descriptor; } - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) { + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) * ((__be64 *)(&descriptor->b_data[offset])) = cpu_to_be64(record->blocknr); - offset += 8; - - } else { + else * ((__be32 *)(&descriptor->b_data[offset])) = cpu_to_be32(record->blocknr); - offset += 4; - } + offset += sz; *offsetp = offset; } @@ -644,7 +646,7 @@ static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh) struct jbd2_journal_revoke_tail *tail; __u32 csum; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize - diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index f8a5d6a..ecc5707 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -551,7 +551,6 @@ int jbd2_journal_extend(handle_t *handle, int nblocks) int result; int wanted; - WARN_ON(!transaction); if (is_handle_aborted(handle)) return -EROFS; journal = transaction->t_journal; @@ -627,7 +626,6 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask) tid_t tid; int need_to_start, ret; - WARN_ON(!transaction); /* If we've had an abort of any type, don't even think about * actually doing the restart! */ if (is_handle_aborted(handle)) @@ -791,7 +789,6 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, int need_copy = 0; unsigned long start_lock, time_lock; - WARN_ON(!transaction); if (is_handle_aborted(handle)) return -EROFS; journal = transaction->t_journal; @@ -1057,7 +1054,6 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) int err; jbd_debug(5, "journal_head %p\n", jh); - WARN_ON(!transaction); err = -EROFS; if (is_handle_aborted(handle)) goto out; @@ -1271,7 +1267,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; int ret = 0; - WARN_ON(!transaction); if (is_handle_aborted(handle)) return -EROFS; journal = transaction->t_journal; @@ -1407,7 +1402,6 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) int err = 0; int was_modified = 0; - WARN_ON(!transaction); if (is_handle_aborted(handle)) return -EROFS; journal = transaction->t_journal; @@ -1538,8 +1532,22 @@ int jbd2_journal_stop(handle_t *handle) tid_t tid; pid_t pid; - if (!transaction) - goto free_and_exit; + if (!transaction) { + /* + * Handle is already detached from the transaction so + * there is nothing to do other than decrease a refcount, + * or free the handle if refcount drops to zero + */ + if (--handle->h_ref > 0) { + jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1, + handle->h_ref); + return err; + } else { + if (handle->h_rsv_handle) + jbd2_free_handle(handle->h_rsv_handle); + goto free_and_exit; + } + } journal = transaction->t_journal; J_ASSERT(journal_current_handle() == handle); @@ -2381,7 +2389,6 @@ int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode) transaction_t *transaction = handle->h_transaction; journal_t *journal; - WARN_ON(!transaction); if (is_handle_aborted(handle)) return -EROFS; journal = transaction->t_journal; diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index a69e426..5b234db 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c, struct inode *inode = OFNI_EDONI_2SFFJ(f); struct page *pg; - pg = read_cache_page_async(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, + pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, (void *)jffs2_do_readpage_unlock, inode); if (IS_ERR(pg)) return (void *)pg; diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h index 413ef89..046fee8 100644 --- a/fs/jffs2/jffs2_fs_sb.h +++ b/fs/jffs2/jffs2_fs_sb.h @@ -134,8 +134,6 @@ struct jffs2_sb_info { struct rw_semaphore wbuf_sem; /* Protects the write buffer */ struct delayed_work wbuf_dwork; /* write-buffer write-out work */ - int wbuf_queued; /* non-zero delayed work is queued */ - spinlock_t wbuf_dwork_lock; /* protects wbuf_dwork and and wbuf_queued */ unsigned char *oobbuf; int oobavail; /* How many bytes are available for JFFS2 in OOB */ diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c index 7654e87..9ad5ba4 100644 --- a/fs/jffs2/scan.c +++ b/fs/jffs2/scan.c @@ -510,6 +510,10 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo sumlen = c->sector_size - je32_to_cpu(sm->offset); sumptr = buf + buf_size - sumlen; + /* sm->offset maybe wrong but MAGIC maybe right */ + if (sumlen > c->sector_size) + goto full_scan; + /* Now, make sure the summary itself is available */ if (sumlen > buf_size) { /* Need to kmalloc for this. */ @@ -544,6 +548,7 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo } } +full_scan: buf_ofs = jeb->offset; if (!buf_size) { diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index a6597d6..09ed551 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -1162,10 +1162,6 @@ static void delayed_wbuf_sync(struct work_struct *work) struct jffs2_sb_info *c = work_to_sb(work); struct super_block *sb = OFNI_BS_2SFFJ(c); - spin_lock(&c->wbuf_dwork_lock); - c->wbuf_queued = 0; - spin_unlock(&c->wbuf_dwork_lock); - if (!(sb->s_flags & MS_RDONLY)) { jffs2_dbg(1, "%s()\n", __func__); jffs2_flush_wbuf_gc(c, 0); @@ -1180,14 +1176,9 @@ void jffs2_dirty_trigger(struct jffs2_sb_info *c) if (sb->s_flags & MS_RDONLY) return; - spin_lock(&c->wbuf_dwork_lock); - if (!c->wbuf_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + if (queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay)) jffs2_dbg(1, "%s()\n", __func__); - delay = msecs_to_jiffies(dirty_writeback_interval * 10); - queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay); - c->wbuf_queued = 1; - } - spin_unlock(&c->wbuf_dwork_lock); } int jffs2_nand_flash_setup(struct jffs2_sb_info *c) @@ -1211,7 +1202,6 @@ int jffs2_nand_flash_setup(struct jffs2_sb_info *c) /* Initialise write buffer */ init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; c->wbuf_ofs = 0xFFFFFFFF; @@ -1251,7 +1241,6 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) { /* Initialize write buffer */ init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->erasesize; @@ -1311,7 +1300,6 @@ int jffs2_nor_wbuf_flash_setup(struct jffs2_sb_info *c) { /* Initialize write buffer */ init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; @@ -1346,7 +1334,6 @@ int jffs2_ubivol_setup(struct jffs2_sb_info *c) { return 0; init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; diff --git a/fs/libfs.c b/fs/libfs.c index a184424..868c0b7 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -113,18 +113,18 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) spin_lock(&dentry->d_lock); /* d_lock not required for cursor */ - list_del(&cursor->d_u.d_child); + list_del(&cursor->d_child); p = dentry->d_subdirs.next; while (n && p != &dentry->d_subdirs) { struct dentry *next; - next = list_entry(p, struct dentry, d_u.d_child); + next = list_entry(p, struct dentry, d_child); spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(next)) n--; spin_unlock(&next->d_lock); p = p->next; } - list_add_tail(&cursor->d_u.d_child, p); + list_add_tail(&cursor->d_child, p); spin_unlock(&dentry->d_lock); } } @@ -149,7 +149,7 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; - struct list_head *p, *q = &cursor->d_u.d_child; + struct list_head *p, *q = &cursor->d_child; if (!dir_emit_dots(file, ctx)) return 0; @@ -158,7 +158,7 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) list_move(q, &dentry->d_subdirs); for (p = q->next; p != &dentry->d_subdirs; p = p->next) { - struct dentry *next = list_entry(p, struct dentry, d_u.d_child); + struct dentry *next = list_entry(p, struct dentry, d_child); spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); if (!simple_positive(next)) { spin_unlock(&next->d_lock); @@ -286,7 +286,7 @@ int simple_empty(struct dentry *dentry) int ret = 0; spin_lock(&dentry->d_lock); - list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &dentry->d_subdirs, d_child) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { spin_unlock(&child->d_lock); diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 1812f02..6ae664b 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -159,6 +159,12 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res, msg.rpc_proc = &clnt->cl_procinfo[proc]; status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN); + if (status == -ECONNREFUSED) { + dprintk("lockd: NSM upcall RPC failed, status=%d, forcing rebind\n", + status); + rpc_force_rebind(clnt); + status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN); + } if (status < 0) dprintk("lockd: NSM upcall RPC failed, status=%d\n", status); diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 6bf06a0..59a53f6 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -137,10 +137,6 @@ lockd(void *vrqstp) dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n"); - if (!nlm_timeout) - nlm_timeout = LOCKD_DFLT_TIMEO; - nlmsvc_timeout = nlm_timeout * HZ; - /* * The main request loop. We don't terminate until the last * NFS mount or NFS daemon has gone away. @@ -253,13 +249,11 @@ static int lockd_up_net(struct svc_serv *serv, struct net *net) error = make_socks(serv, net); if (error < 0) - goto err_socks; + goto err_bind; set_grace_period(net); dprintk("lockd_up_net: per-net data created; net=%p\n", net); return 0; -err_socks: - svc_rpcb_cleanup(serv, net); err_bind: ln->nlmsvc_users--; return error; @@ -348,6 +342,10 @@ static struct svc_serv *lockd_create_svc(void) printk(KERN_WARNING "lockd_up: no pid, %d users??\n", nlmsvc_users); + if (!nlm_timeout) + nlm_timeout = LOCKD_DFLT_TIMEO; + nlmsvc_timeout = nlm_timeout * HZ; + serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL); if (!serv) { printk(KERN_WARNING "lockd_up: create service failed\n"); diff --git a/fs/locks.c b/fs/locks.c index 4dd39b9..2c61c4e 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2235,16 +2235,28 @@ void locks_remove_flock(struct file *filp) while ((fl = *before) != NULL) { if (fl->fl_file == filp) { - if (IS_FLOCK(fl)) { - locks_delete_lock(before); - continue; - } if (IS_LEASE(fl)) { lease_modify(before, F_UNLCK); continue; } - /* What? */ - BUG(); + + /* + * There's a leftover lock on the list of a type that + * we didn't expect to see. Most likely a classic + * POSIX lock that ended up not getting released + * properly, or that raced onto the list somehow. Log + * some info about it and then just remove it from + * the list. + */ + WARN(!IS_FLOCK(fl), + "leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n", + MAJOR(inode->i_sb->s_dev), + MINOR(inode->i_sb->s_dev), inode->i_ino, + fl->fl_type, fl->fl_flags, + fl->fl_start, fl->fl_end); + + locks_delete_lock(before); + continue; } before = &fl->fl_next; } diff --git a/fs/namei.c b/fs/namei.c index 8274c8d..c6fa079 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include "internal.h" @@ -641,24 +642,22 @@ static int complete_walk(struct nameidata *nd) static __always_inline void set_root(struct nameidata *nd) { - if (!nd->root.mnt) - get_fs_root(current->fs, &nd->root); + get_fs_root(current->fs, &nd->root); } static int link_path_walk(const char *, struct nameidata *); -static __always_inline void set_root_rcu(struct nameidata *nd) +static __always_inline unsigned set_root_rcu(struct nameidata *nd) { - if (!nd->root.mnt) { - struct fs_struct *fs = current->fs; - unsigned seq; + struct fs_struct *fs = current->fs; + unsigned seq, res; - do { - seq = read_seqcount_begin(&fs->seq); - nd->root = fs->root; - nd->seq = __read_seqcount_begin(&nd->root.dentry->d_seq); - } while (read_seqcount_retry(&fs->seq, seq)); - } + do { + seq = read_seqcount_begin(&fs->seq); + nd->root = fs->root; + res = __read_seqcount_begin(&nd->root.dentry->d_seq); + } while (read_seqcount_retry(&fs->seq, seq)); + return res; } static void path_put_conditional(struct path *path, struct nameidata *nd) @@ -858,7 +857,8 @@ follow_link(struct path *link, struct nameidata *nd, void **p) return PTR_ERR(s); } if (*s == '/') { - set_root(nd); + if (!nd->root.mnt) + set_root(nd); path_put(&nd->path); nd->path = nd->root; path_get(&nd->root); @@ -1131,7 +1131,8 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, static int follow_dotdot_rcu(struct nameidata *nd) { - set_root_rcu(nd); + if (!nd->root.mnt) + set_root_rcu(nd); while (1) { if (nd->path.dentry == nd->root.dentry && @@ -1243,7 +1244,8 @@ static void follow_mount(struct path *path) static void follow_dotdot(struct nameidata *nd) { - set_root(nd); + if (!nd->root.mnt) + set_root(nd); while(1) { struct dentry *old = nd->path.dentry; @@ -1543,7 +1545,8 @@ static inline int walk_component(struct nameidata *nd, struct path *path, if (should_follow_link(path->dentry, follow)) { if (nd->flags & LOOKUP_RCU) { - if (unlikely(unlazy_walk(nd, path->dentry))) { + if (unlikely(nd->path.mnt != path->mnt || + unlazy_walk(nd, path->dentry))) { err = -ECHILD; goto out_err; } @@ -1624,8 +1627,7 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd) static inline unsigned int fold_hash(unsigned long hash) { - hash += hash >> (8*sizeof(int)); - return hash; + return hash_64(hash, 32); } #else /* 32-bit case */ @@ -1797,7 +1799,7 @@ static int link_path_walk(const char *name, struct nameidata *nd) if (err) return err; } - if (!d_is_directory(nd->path.dentry)) { + if (!d_can_lookup(nd->path.dentry)) { err = -ENOTDIR; break; } @@ -1818,7 +1820,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; if (*name) { - if (!d_is_directory(root)) + if (!d_can_lookup(root)) return -ENOTDIR; retval = inode_permission(inode, MAY_EXEC); if (retval) @@ -1842,7 +1844,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, if (*name=='/') { if (flags & LOOKUP_RCU) { rcu_read_lock(); - set_root_rcu(nd); + nd->seq = set_root_rcu(nd); } else { set_root(nd); path_get(&nd->root); @@ -1874,7 +1876,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, dentry = f.file->f_path.dentry; if (*name) { - if (!d_is_directory(dentry)) { + if (!d_can_lookup(dentry)) { fdput(f); return -ENOTDIR; } @@ -1956,7 +1958,7 @@ static int path_lookupat(int dfd, const char *name, err = complete_walk(nd); if (!err && nd->flags & LOOKUP_DIRECTORY) { - if (!d_is_directory(nd->path.dentry)) { + if (!d_can_lookup(nd->path.dentry)) { path_put(&nd->path); err = -ENOTDIR; } @@ -2247,9 +2249,10 @@ done: goto out; } path->dentry = dentry; - path->mnt = mntget(nd->path.mnt); + path->mnt = nd->path.mnt; if (should_follow_link(dentry, nd->flags & LOOKUP_FOLLOW)) return 1; + mntget(path->mnt); follow_mount(path); error = 0; out: @@ -2415,11 +2418,11 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) IS_IMMUTABLE(inode) || IS_SWAPFILE(inode)) return -EPERM; if (isdir) { - if (!d_is_directory(victim) && !d_is_autodir(victim)) + if (!d_is_dir(victim)) return -ENOTDIR; if (IS_ROOT(victim)) return -EBUSY; - } else if (d_is_directory(victim) || d_is_autodir(victim)) + } else if (d_is_dir(victim)) return -EISDIR; if (IS_DEADDIR(dir)) return -ENOENT; @@ -2990,7 +2993,8 @@ finish_lookup: if (should_follow_link(path->dentry, !symlink_ok)) { if (nd->flags & LOOKUP_RCU) { - if (unlikely(unlazy_walk(nd, path->dentry))) { + if (unlikely(nd->path.mnt != path->mnt || + unlazy_walk(nd, path->dentry))) { error = -ECHILD; goto out; } @@ -3017,11 +3021,10 @@ finish_open: } audit_inode(name, nd->path.dentry, 0); error = -EISDIR; - if ((open_flag & O_CREAT) && - (d_is_directory(nd->path.dentry) || d_is_autodir(nd->path.dentry))) + if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry)) goto out; error = -ENOTDIR; - if ((nd->flags & LOOKUP_DIRECTORY) && !d_is_directory(nd->path.dentry)) + if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) goto out; if (!S_ISREG(nd->inode->i_mode)) will_truncate = false; @@ -3127,7 +3130,8 @@ static int do_tmpfile(int dfd, struct filename *pathname, if (error) goto out2; audit_inode(pathname, nd->path.dentry, 0); - error = may_open(&nd->path, op->acc_mode, op->open_flag); + /* Don't check for other permissions, the inode was just created */ + error = may_open(&nd->path, MAY_OPEN, op->open_flag); if (error) goto out2; file->f_path.mnt = nd->path.mnt; @@ -3167,7 +3171,7 @@ static struct file *path_openat(int dfd, struct filename *pathname, if (unlikely(file->f_flags & __O_TMPFILE)) { error = do_tmpfile(dfd, pathname, nd, flags, op, file, &opened); - goto out; + goto out2; } error = path_init(dfd, pathname->name, flags | LOOKUP_PARENT, nd, &base); @@ -3205,6 +3209,7 @@ out: path_put(&nd->root); if (base) fput(base); +out2: if (!(opened & FILE_OPENED)) { BUG_ON(!error); put_filp(file); @@ -3745,7 +3750,7 @@ exit1: slashes: if (d_is_negative(dentry)) error = -ENOENT; - else if (d_is_directory(dentry) || d_is_autodir(dentry)) + else if (d_is_dir(dentry)) error = -EISDIR; else error = -ENOTDIR; @@ -4124,7 +4129,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode **delegated_inode) { int error; - int is_dir = d_is_directory(old_dentry) || d_is_autodir(old_dentry); + int is_dir = d_is_dir(old_dentry); const unsigned char *old_name; if (old_dentry->d_inode == new_dentry->d_inode) @@ -4217,7 +4222,7 @@ retry_deleg: if (d_is_negative(old_dentry)) goto exit4; /* unless the source is a directory trailing slashes give -ENOTDIR */ - if (!d_is_directory(old_dentry) && !d_is_autodir(old_dentry)) { + if (!d_is_dir(old_dentry)) { error = -ENOTDIR; if (oldnd.last.name[oldnd.last.len]) goto exit4; diff --git a/fs/namespace.c b/fs/namespace.c index 65233a5..fc99d18 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -777,6 +777,20 @@ static void attach_mnt(struct mount *mnt, list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } +static void attach_shadowed(struct mount *mnt, + struct mount *parent, + struct mount *shadows) +{ + if (shadows) { + hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash); + list_add(&mnt->mnt_child, &shadows->mnt_child); + } else { + hlist_add_head_rcu(&mnt->mnt_hash, + m_hash(&parent->mnt, mnt->mnt_mountpoint)); + list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); + } +} + /* * vfsmount lock must be held for write */ @@ -795,12 +809,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows) list_splice(&head, n->list.prev); - if (shadows) - hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash); - else - hlist_add_head_rcu(&mnt->mnt_hash, - m_hash(&parent->mnt, mnt->mnt_mountpoint)); - list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); + attach_shadowed(mnt, parent, shadows); touch_mnt_namespace(n); } @@ -887,8 +896,21 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED); /* Don't allow unprivileged users to change mount flags */ - if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY)) - mnt->mnt.mnt_flags |= MNT_LOCK_READONLY; + if (flag & CL_UNPRIVILEGED) { + mnt->mnt.mnt_flags |= MNT_LOCK_ATIME; + + if (mnt->mnt.mnt_flags & MNT_READONLY) + mnt->mnt.mnt_flags |= MNT_LOCK_READONLY; + + if (mnt->mnt.mnt_flags & MNT_NODEV) + mnt->mnt.mnt_flags |= MNT_LOCK_NODEV; + + if (mnt->mnt.mnt_flags & MNT_NOSUID) + mnt->mnt.mnt_flags |= MNT_LOCK_NOSUID; + + if (mnt->mnt.mnt_flags & MNT_NOEXEC) + mnt->mnt.mnt_flags |= MNT_LOCK_NOEXEC; + } /* Don't allow unprivileged users to reveal what is under a mount */ if ((flag & CL_UNPRIVILEGED) && list_empty(&old->mnt_expire)) @@ -1204,6 +1226,11 @@ static void namespace_unlock(void) head.first->pprev = &head.first; INIT_HLIST_HEAD(&unmounted); + /* undo decrements we'd done in umount_tree() */ + hlist_for_each_entry(mnt, &head, mnt_hash) + if (mnt->mnt_ex_mountpoint.mnt) + mntget(mnt->mnt_ex_mountpoint.mnt); + up_write(&namespace_sem); synchronize_rcu(); @@ -1240,6 +1267,9 @@ void umount_tree(struct mount *mnt, int how) hlist_add_head(&p->mnt_hash, &tmp_list); } + hlist_for_each_entry(p, &tmp_list, mnt_hash) + list_del_init(&p->mnt_child); + if (how) propagate_umount(&tmp_list); @@ -1250,9 +1280,9 @@ void umount_tree(struct mount *mnt, int how) p->mnt_ns = NULL; if (how < 2) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; - list_del_init(&p->mnt_child); if (mnt_has_parent(p)) { put_mountpoint(p->mnt_mp); + mnt_add_count(p->mnt_parent, -1); /* move the reference to mountpoint into ->mnt_ex_mountpoint */ p->mnt_ex_mountpoint.dentry = p->mnt_mountpoint; p->mnt_ex_mountpoint.mnt = &p->mnt_parent->mnt; @@ -1265,6 +1295,8 @@ void umount_tree(struct mount *mnt, int how) } if (last) { last->mnt_hash.next = unmounted.first; + if (unmounted.first) + unmounted.first->pprev = &last->mnt_hash.next; unmounted.first = tmp_list.first; unmounted.first->pprev = &unmounted.first; } @@ -1335,6 +1367,8 @@ static int do_umount(struct mount *mnt, int flags) * Special case for "unmounting" root ... * we just try to remount it readonly. */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; down_write(&sb->s_umount); if (!(sb->s_flags & MS_RDONLY)) retval = do_remount_sb(sb, MS_RDONLY, NULL, 0); @@ -1407,6 +1441,9 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags) goto dput_and_out; if (mnt->mnt.mnt_flags & MNT_LOCKED) goto dput_and_out; + retval = -EPERM; + if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) + goto dput_and_out; retval = do_umount(mnt, flags); dput_and_out: @@ -1483,6 +1520,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, continue; for (s = r; s; s = next_mnt(s, r)) { + struct mount *t = NULL; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { s = skip_mnt_tree(s); @@ -1504,7 +1542,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); - attach_mnt(q, parent, p->mnt_mp); + mnt_set_mountpoint(parent, p->mnt_mp, q); + if (!list_empty(&parent->mnt_mounts)) { + t = list_last_entry(&parent->mnt_mounts, + struct mount, mnt_child); + if (t->mnt_mp != p->mnt_mp) + t = NULL; + } + attach_shadowed(q, parent, t); unlock_mount_hash(); } } @@ -1887,9 +1932,6 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags) if (readonly_request == __mnt_is_readonly(mnt)) return 0; - if (mnt->mnt_flags & MNT_LOCK_READONLY) - return -EPERM; - if (readonly_request) error = mnt_make_readonly(real_mount(mnt)); else @@ -1915,6 +1957,39 @@ static int do_remount(struct path *path, int flags, int mnt_flags, if (path->dentry != path->mnt->mnt_root) return -EINVAL; + /* Don't allow changing of locked mnt flags. + * + * No locks need to be held here while testing the various + * MNT_LOCK flags because those flags can never be cleared + * once they are set. + */ + if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) && + !(mnt_flags & MNT_READONLY)) { + return -EPERM; + } + if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) && + !(mnt_flags & MNT_NODEV)) { + /* Was the nodev implicitly added in mount? */ + if ((mnt->mnt_ns->user_ns != &init_user_ns) && + !(sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT)) { + mnt_flags |= MNT_NODEV; + } else { + return -EPERM; + } + } + if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) && + !(mnt_flags & MNT_NOSUID)) { + return -EPERM; + } + if ((mnt->mnt.mnt_flags & MNT_LOCK_NOEXEC) && + !(mnt_flags & MNT_NOEXEC)) { + return -EPERM; + } + if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) && + ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) { + return -EPERM; + } + err = security_sb_remount(sb, data); if (err) return err; @@ -1928,7 +2003,7 @@ static int do_remount(struct path *path, int flags, int mnt_flags, err = do_remount_sb(sb, flags, data, 0); if (!err) { lock_mount_hash(); - mnt_flags |= mnt->mnt.mnt_flags & MNT_PROPAGATION_MASK; + mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; mnt->mnt.mnt_flags = mnt_flags; touch_mnt_namespace(mnt->mnt_ns); unlock_mount_hash(); @@ -2113,7 +2188,7 @@ static int do_new_mount(struct path *path, const char *fstype, int flags, */ if (!(type->fs_flags & FS_USERNS_DEV_MOUNT)) { flags |= MS_NODEV; - mnt_flags |= MNT_NODEV; + mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV; } } @@ -2427,6 +2502,14 @@ long do_mount(const char *dev_name, const char *dir_name, if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; + /* The default atime for remount is preservation */ + if ((flags & MS_REMOUNT) && + ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME | + MS_STRICTATIME)) == 0)) { + mnt_flags &= ~MNT_ATIME_MASK; + mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK; + } + flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN | MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT | MS_STRICTATIME); @@ -2759,6 +2842,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old.dentry, &new)) goto out4; + /* make certain new is below the root */ + if (!is_path_reachable(new_mnt, new.dentry, &root)) + goto out4; root_mp->m_count++; /* pin it so it won't go away */ lock_mount_hash(); detach_mnt(new_mnt, &parent_path); @@ -2939,11 +3025,21 @@ bool fs_fully_visible(struct file_system_type *type) if (mnt->mnt.mnt_sb->s_type != type) continue; - /* This mount is not fully visible if there are any child mounts - * that cover anything except for empty directories. + /* This mount is not fully visible if it's root directory + * is not the root directory of the filesystem. + */ + if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) + continue; + + /* This mount is not fully visible if there are any + * locked child mounts that cover anything except for + * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; + /* Only worry about locked mounts */ + if (!(mnt->mnt.mnt_flags & MNT_LOCKED)) + continue; if (!S_ISDIR(inode->i_mode)) goto next; if (inode->i_nlink > 2) diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index c320ac5..dc9747d 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -406,7 +406,7 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos) spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { - dent = list_entry(next, struct dentry, d_u.d_child); + dent = list_entry(next, struct dentry, d_child); if ((unsigned long)dent->d_fsdata == fpos) { if (dent->d_inode) dget(dent); diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 60426cc..2f970de 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -448,7 +448,6 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg result = -EIO; } } - result = 0; } mutex_unlock(&server->root_setup_lock); diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h index 32c0658..6d5e7c5 100644 --- a/fs/ncpfs/ncplib_kernel.h +++ b/fs/ncpfs/ncplib_kernel.h @@ -194,7 +194,7 @@ ncp_renew_dentries(struct dentry *parent) spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { - dentry = list_entry(next, struct dentry, d_u.d_child); + dentry = list_entry(next, struct dentry, d_child); if (dentry->d_fsdata == NULL) ncp_age_dentry(server, dentry); @@ -216,7 +216,7 @@ ncp_invalidate_dircache_entries(struct dentry *parent) spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { - dentry = list_entry(next, struct dentry, d_u.d_child); + dentry = list_entry(next, struct dentry, d_child); dentry->d_fsdata = NULL; ncp_age_dentry(server, dentry); next = next->next; diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 56ff823..65d849b 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -1213,7 +1213,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE); if (end != NFS_I(inode)->npages) { rcu_read_lock(); - end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX); + end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX); rcu_read_unlock(); } diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 073b4cf..0a2016b 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -128,22 +128,24 @@ nfs41_callback_svc(void *vrqstp) if (try_to_freeze()) continue; - prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE); + prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE); spin_lock_bh(&serv->sv_cb_lock); if (!list_empty(&serv->sv_cb_list)) { req = list_first_entry(&serv->sv_cb_list, struct rpc_rqst, rq_bc_list); list_del(&req->rq_bc_list); spin_unlock_bh(&serv->sv_cb_lock); + finish_wait(&serv->sv_cb_waitq, &wq); dprintk("Invoking bc_svc_process()\n"); error = bc_svc_process(serv, req, rqstp); dprintk("bc_svc_process() returned w/ error code= %d\n", error); } else { spin_unlock_bh(&serv->sv_cb_lock); - schedule(); + /* schedule_timeout to game the hung task watchdog */ + schedule_timeout(60 * HZ); + finish_wait(&serv->sv_cb_waitq, &wq); } - finish_wait(&serv->sv_cb_waitq, &wq); } return 0; } diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index f4ccfe6..02f8d09 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -464,8 +464,10 @@ static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp, for (i = 0; i < args->csa_nrclists; i++) { status = decode_rc_list(xdr, &args->csa_rclists[i]); - if (status) + if (status) { + args->csa_nrclists = i; goto out_free; + } } } status = 0; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 5d8ccec..2ea3537 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -109,6 +109,8 @@ again: continue; if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) continue; + if (!nfs4_valid_open_stateid(state)) + continue; if (!nfs4_stateid_match(&state->stateid, stateid)) continue; get_nfs_open_context(ctx); @@ -159,8 +161,8 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, &delegation->flags); NFS_I(inode)->delegation_state = delegation->type; spin_unlock(&delegation->lock); - put_rpccred(oldcred); rcu_read_unlock(); + put_rpccred(oldcred); trace_nfs4_reclaim_delegation(inode, res->delegation_type); } else { /* We appear to have raced with a delegation return. */ @@ -177,7 +179,11 @@ static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation * { int res = 0; - res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync); + if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + res = nfs4_proc_delegreturn(inode, + delegation->cred, + &delegation->stateid, + issync); nfs_free_delegation(delegation); return res; } @@ -364,11 +370,13 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation { struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; struct nfs_inode *nfsi = NFS_I(inode); - int err; + int err = 0; if (delegation == NULL) return 0; do { + if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + break; err = nfs_delegation_claim_opens(inode, &delegation->stateid); if (!issync || err != -EAGAIN) break; @@ -589,10 +597,23 @@ static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *cl rcu_read_unlock(); } +static void nfs_revoke_delegation(struct inode *inode) +{ + struct nfs_delegation *delegation; + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (delegation != NULL) { + set_bit(NFS_DELEGATION_REVOKED, &delegation->flags); + nfs_mark_return_delegation(NFS_SERVER(inode), delegation); + } + rcu_read_unlock(); +} + void nfs_remove_bad_delegation(struct inode *inode) { struct nfs_delegation *delegation; + nfs_revoke_delegation(inode); delegation = nfs_inode_detach_delegation(inode); if (delegation) { nfs_inode_find_state_and_recover(inode, &delegation->stateid); diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 9a79c7a..e02b090 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -31,6 +31,7 @@ enum { NFS_DELEGATION_RETURN_IF_CLOSED, NFS_DELEGATION_REFERENCED, NFS_DELEGATION_RETURNING, + NFS_DELEGATION_REVOKED, }; int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index b8797ae..7ececa1 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -123,6 +123,12 @@ static inline int put_dreq(struct nfs_direct_req *dreq) */ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs) { + struct inode *inode = iocb->ki_filp->f_mapping->host; + + /* we only support swap file calling nfs_direct_IO */ + if (!IS_SWAPFILE(inode)) + return 0; + #ifndef CONFIG_NFS_SWAP dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n", iocb->ki_filp, (long long) pos, nr_segs); @@ -178,6 +184,7 @@ static void nfs_direct_req_free(struct kref *kref) { struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref); + nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo); if (dreq->l_ctx != NULL) nfs_put_lock_context(dreq->l_ctx); if (dreq->ctx != NULL) diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 66984a9..5b8ab0e 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -58,7 +58,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i */ spin_lock(&sb->s_root->d_inode->i_lock); spin_lock(&sb->s_root->d_lock); - hlist_del_init(&sb->s_root->d_alias); + hlist_del_init(&sb->s_root->d_u.d_alias); spin_unlock(&sb->s_root->d_lock); spin_unlock(&sb->s_root->d_inode->i_lock); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 15f9d98..6659ce5 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -592,7 +592,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { struct inode *inode = dentry->d_inode; int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME; - int err; + int err = 0; trace_nfs_getattr_enter(inode); /* Flush out writes to the server in order to update c/mtime. */ diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 871d6ed..24c6898 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -129,7 +129,10 @@ static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, .rpc_argp = &args, .rpc_resp = &fattr, }; - int status; + int status = 0; + + if (acl == NULL && (!S_ISDIR(inode->i_mode) || dfacl == NULL)) + goto out; status = -EOPNOTSUPP; if (!nfs_server_capable(inode, NFS_CAP_ACLS)) @@ -247,3 +250,46 @@ const struct xattr_handler *nfs3_xattr_handlers[] = { &posix_acl_default_xattr_handler, NULL, }; + +static int +nfs3_list_one_acl(struct inode *inode, int type, const char *name, void *data, + size_t size, ssize_t *result) +{ + struct posix_acl *acl; + char *p = data + *result; + + acl = get_acl(inode, type); + if (IS_ERR_OR_NULL(acl)) + return 0; + + posix_acl_release(acl); + + *result += strlen(name); + *result += 1; + if (!size) + return 0; + if (*result > size) + return -ERANGE; + + strcpy(p, name); + return 0; +} + +ssize_t +nfs3_listxattr(struct dentry *dentry, char *data, size_t size) +{ + struct inode *inode = dentry->d_inode; + ssize_t result = 0; + int error; + + error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS, + POSIX_ACL_XATTR_ACCESS, data, size, &result); + if (error) + return error; + + error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT, + POSIX_ACL_XATTR_DEFAULT, data, size, &result); + if (error) + return error; + return result; +} diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index a462ef0..8a18b4a 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -926,7 +926,7 @@ static const struct inode_operations nfs3_dir_inode_operations = { .getattr = nfs_getattr, .setattr = nfs_setattr, #ifdef CONFIG_NFS_V3_ACL - .listxattr = generic_listxattr, + .listxattr = nfs3_listxattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, .removexattr = generic_removexattr, @@ -940,7 +940,7 @@ static const struct inode_operations nfs3_file_inode_operations = { .getattr = nfs_getattr, .setattr = nfs_setattr, #ifdef CONFIG_NFS_V3_ACL - .listxattr = generic_listxattr, + .listxattr = nfs3_listxattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, .removexattr = generic_removexattr, diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index fa6d721..4495cad 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1342,7 +1342,7 @@ static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req, if (args->npages != 0) xdr_write_pages(xdr, args->pages, 0, args->len); else - xdr_reserve_space(xdr, NFS_ACL_INLINE_BUFSIZE); + xdr_reserve_space(xdr, args->len); error = nfsacl_encode(xdr->buf, base, args->inode, (args->mask & NFS_ACL) ? diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 0e46d3d..d3f6062 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -482,6 +482,16 @@ int nfs40_walk_client_list(struct nfs_client *new, spin_lock(&nn->nfs_client_lock); list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + + if (pos->rpc_ops != new->rpc_ops) + continue; + + if (pos->cl_proto != new->cl_proto) + continue; + + if (pos->cl_minorversion != new->cl_minorversion) + continue; + /* If "pos" isn't marked ready, we can't trust the * remaining fields in "pos" */ if (pos->cl_cons_state > NFS_CS_READY) { @@ -501,15 +511,6 @@ int nfs40_walk_client_list(struct nfs_client *new, if (pos->cl_cons_state != NFS_CS_READY) continue; - if (pos->rpc_ops != new->rpc_ops) - continue; - - if (pos->cl_proto != new->cl_proto) - continue; - - if (pos->cl_minorversion != new->cl_minorversion) - continue; - if (pos->cl_clientid != new->cl_clientid) continue; @@ -564,20 +565,14 @@ static bool nfs4_match_clientids(struct nfs_client *a, struct nfs_client *b) } /* - * Returns true if the server owners match + * Returns true if the server major ids match */ static bool -nfs4_match_serverowners(struct nfs_client *a, struct nfs_client *b) +nfs4_check_clientid_trunking(struct nfs_client *a, struct nfs_client *b) { struct nfs41_server_owner *o1 = a->cl_serverowner; struct nfs41_server_owner *o2 = b->cl_serverowner; - if (o1->minor_id != o2->minor_id) { - dprintk("NFS: --> %s server owner minor IDs do not match\n", - __func__); - return false; - } - if (o1->major_id_sz != o2->major_id_sz) goto out_major_mismatch; if (memcmp(o1->major_id, o2->major_id, o1->major_id_sz) != 0) @@ -615,6 +610,16 @@ int nfs41_walk_client_list(struct nfs_client *new, spin_lock(&nn->nfs_client_lock); list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + + if (pos->rpc_ops != new->rpc_ops) + continue; + + if (pos->cl_proto != new->cl_proto) + continue; + + if (pos->cl_minorversion != new->cl_minorversion) + continue; + /* If "pos" isn't marked ready, we can't trust the * remaining fields in "pos", especially the client * ID and serverowner fields. Wait for CREATE_SESSION @@ -628,7 +633,7 @@ int nfs41_walk_client_list(struct nfs_client *new, prev = pos; status = nfs_wait_client_init_complete(pos); - if (status == 0) { + if (pos->cl_cons_state == NFS_CS_SESSION_INITING) { nfs4_schedule_lease_recovery(pos); status = nfs4_wait_clnt_recover(pos); } @@ -640,19 +645,15 @@ int nfs41_walk_client_list(struct nfs_client *new, if (pos->cl_cons_state != NFS_CS_READY) continue; - if (pos->rpc_ops != new->rpc_ops) - continue; - - if (pos->cl_proto != new->cl_proto) - continue; - - if (pos->cl_minorversion != new->cl_minorversion) - continue; - if (!nfs4_match_clientids(pos, new)) continue; - if (!nfs4_match_serverowners(pos, new)) + /* + * Note that session trunking is just a special subcase of + * client id trunking. In either case, we want to fall back + * to using the existing nfs_client. + */ + if (!nfs4_check_clientid_trunking(pos, new)) continue; atomic_inc(&pos->cl_count); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index d5d06e8..58258ad 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1587,7 +1587,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs_inode_find_state_and_recover(state->inode, stateid); nfs4_schedule_stateid_recovery(server, state); - return 0; + return -EAGAIN; case -NFS4ERR_DELAY: case -NFS4ERR_GRACE: set_bit(NFS_DELEGATED_STATE, &state->flags); @@ -2034,46 +2034,60 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta return ret; } +static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state) +{ + nfs_remove_bad_delegation(state->inode); + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + write_sequnlock(&state->seqlock); + clear_bit(NFS_DELEGATED_STATE, &state->flags); +} + +static void nfs40_clear_delegation_stateid(struct nfs4_state *state) +{ + if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL) + nfs_finish_clear_delegation_stateid(state); +} + +static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state) +{ + /* NFSv4.0 doesn't allow for delegation recovery on open expire */ + nfs40_clear_delegation_stateid(state); + return nfs4_open_expired(sp, state); +} + #if defined(CONFIG_NFS_V4_1) -static void nfs41_clear_delegation_stateid(struct nfs4_state *state) +static void nfs41_check_delegation_stateid(struct nfs4_state *state) { struct nfs_server *server = NFS_SERVER(state->inode); - nfs4_stateid *stateid = &state->stateid; + nfs4_stateid stateid; struct nfs_delegation *delegation; - struct rpc_cred *cred = NULL; - int status = -NFS4ERR_BAD_STATEID; - - /* If a state reset has been done, test_stateid is unneeded */ - if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) - return; + struct rpc_cred *cred; + int status; /* Get the delegation credential for use by test/free_stateid */ rcu_read_lock(); delegation = rcu_dereference(NFS_I(state->inode)->delegation); - if (delegation != NULL && - nfs4_stateid_match(&delegation->stateid, stateid)) { - cred = get_rpccred(delegation->cred); - rcu_read_unlock(); - status = nfs41_test_stateid(server, stateid, cred); - trace_nfs4_test_delegation_stateid(state, NULL, status); - } else + if (delegation == NULL) { rcu_read_unlock(); + return; + } + + nfs4_stateid_copy(&stateid, &delegation->stateid); + cred = get_rpccred(delegation->cred); + rcu_read_unlock(); + status = nfs41_test_stateid(server, &stateid, cred); + trace_nfs4_test_delegation_stateid(state, NULL, status); if (status != NFS_OK) { /* Free the stateid unless the server explicitly * informs us the stateid is unrecognized. */ if (status != -NFS4ERR_BAD_STATEID) - nfs41_free_stateid(server, stateid, cred); - nfs_remove_bad_delegation(state->inode); - - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs41_free_stateid(server, &stateid, cred); + nfs_finish_clear_delegation_stateid(state); } - if (cred != NULL) - put_rpccred(cred); + put_rpccred(cred); } /** @@ -2117,7 +2131,7 @@ static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st { int status; - nfs41_clear_delegation_stateid(state); + nfs41_check_delegation_stateid(state); status = nfs41_check_open_stateid(state); if (status != NFS_OK) status = nfs4_open_expired(sp, state); @@ -2546,6 +2560,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) struct nfs4_closedata *calldata = data; struct nfs4_state *state = calldata->state; struct inode *inode = calldata->inode; + bool is_rdonly, is_wronly, is_rdwr; int call_close = 0; dprintk("%s: begin!\n", __func__); @@ -2553,21 +2568,27 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) goto out_wait; task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE]; - calldata->arg.fmode = FMODE_READ|FMODE_WRITE; spin_lock(&state->owner->so_lock); + is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags); + is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags); + is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags); /* Calculate the change in open mode */ + calldata->arg.fmode = 0; if (state->n_rdwr == 0) { - if (state->n_rdonly == 0) { - call_close |= test_bit(NFS_O_RDONLY_STATE, &state->flags); - call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags); - calldata->arg.fmode &= ~FMODE_READ; - } - if (state->n_wronly == 0) { - call_close |= test_bit(NFS_O_WRONLY_STATE, &state->flags); - call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags); - calldata->arg.fmode &= ~FMODE_WRITE; - } - } + if (state->n_rdonly == 0) + call_close |= is_rdonly; + else if (is_rdonly) + calldata->arg.fmode |= FMODE_READ; + if (state->n_wronly == 0) + call_close |= is_wronly; + else if (is_wronly) + calldata->arg.fmode |= FMODE_WRITE; + } else if (is_rdwr) + calldata->arg.fmode |= FMODE_READ|FMODE_WRITE; + + if (calldata->arg.fmode == 0) + call_close |= is_rdwr; + if (!nfs4_valid_open_stateid(state)) call_close = 0; spin_unlock(&state->owner->so_lock); @@ -7235,7 +7256,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr int ret = 0; if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0) - return 0; + return -EAGAIN; task = _nfs41_proc_sequence(clp, cred, false); if (IS_ERR(task)) ret = PTR_ERR(task); @@ -7568,6 +7589,9 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) dprintk("--> %s\n", __func__); + /* nfs4_layoutget_release calls pnfs_put_layout_hdr */ + pnfs_get_layout_hdr(NFS_I(inode)->layout); + lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags); if (!lgp->args.layout.pages) { nfs4_layoutget_release(lgp); @@ -7580,9 +7604,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) lgp->res.seq_res.sr_slot = NULL; nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); - /* nfs4_layoutget_release calls pnfs_put_layout_hdr */ - pnfs_get_layout_hdr(NFS_I(inode)->layout); - task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return ERR_CAST(task); @@ -8248,7 +8269,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = { static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = { .owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE, .state_flag_bit = NFS_STATE_RECLAIM_NOGRACE, - .recover_open = nfs4_open_expired, + .recover_open = nfs40_open_expired, .recover_lock = nfs4_lock_expired, .establish_clid = nfs4_init_clientid, }; diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index 1720d32..e1ba58c 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -88,10 +88,18 @@ nfs4_renew_state(struct work_struct *work) } nfs_expire_all_delegations(clp); } else { + int ret; + /* Queue an asynchronous RENEW. */ - ops->sched_state_renewal(clp, cred, renew_flags); + ret = ops->sched_state_renewal(clp, cred, renew_flags); put_rpccred(cred); - goto out_exp; + switch (ret) { + default: + goto out_exp; + case -EAGAIN: + case -ENOMEM: + break; + } } } else { dprintk("%s: failed to call renewd. Reason: lease not expired \n", diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 27f5f85..c402b67 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1482,6 +1482,8 @@ restart: spin_unlock(&state->state_lock); } nfs4_put_open_state(state); + clear_bit(NFS4CLNT_RECLAIM_NOGRACE, + &state->flags); spin_lock(&sp->so_lock); goto restart; } @@ -1732,7 +1734,8 @@ restart: if (status < 0) { set_bit(ops->owner_flag_bit, &sp->so_flags); nfs4_put_state_owner(sp); - return nfs4_recovery_handle_error(clp, status); + status = nfs4_recovery_handle_error(clp, status); + return (status != 0) ? status : -EAGAIN; } nfs4_put_state_owner(sp); @@ -1741,7 +1744,7 @@ restart: spin_unlock(&clp->cl_lock); } rcu_read_unlock(); - return status; + return 0; } static int nfs4_check_lease(struct nfs_client *clp) @@ -1788,7 +1791,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) break; case -NFS4ERR_STALE_CLIENTID: clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); - nfs4_state_clear_reclaim_reboot(clp); nfs4_state_start_reclaim_reboot(clp); break; case -NFS4ERR_CLID_INUSE: @@ -2370,6 +2372,7 @@ static void nfs4_state_manager(struct nfs_client *clp) status = nfs4_check_lease(clp); if (status < 0) goto out_error; + continue; } if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) { @@ -2391,14 +2394,11 @@ static void nfs4_state_manager(struct nfs_client *clp) section = "reclaim reboot"; status = nfs4_do_reclaim(clp, clp->cl_mvops->reboot_recovery_ops); - if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) || - test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)) - continue; - nfs4_state_end_reclaim_reboot(clp); - if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) + if (status == -EAGAIN) continue; if (status < 0) goto out_error; + nfs4_state_end_reclaim_reboot(clp); } /* Now recover expired state... */ @@ -2406,9 +2406,7 @@ static void nfs4_state_manager(struct nfs_client *clp) section = "reclaim nograce"; status = nfs4_do_reclaim(clp, clp->cl_mvops->nograce_recovery_ops); - if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) || - test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) || - test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) + if (status == -EAGAIN) continue; if (status < 0) goto out_error; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 2ffebf2..27d7f27 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -113,7 +113,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c) if (atomic_read(&c->io_count) == 0) break; ret = nfs_wait_bit_killable(&c->flags); - } while (atomic_read(&c->io_count) != 0); + } while (atomic_read(&c->io_count) != 0 && !ret); finish_wait(wq, &q.wait); return ret; } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 3eaa6e3..f42bbe5 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -672,7 +672,8 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; args.prognumber = clp->cl_cb_session->se_cb_prog; - args.protocol = XPRT_TRANSPORT_BC_TCP; + args.protocol = conn->cb_xprt->xpt_class->xcl_ident | + XPRT_TRANSPORT_BC; args.authflavor = ses->se_cb_sec.flavor; } /* Create RPC client */ @@ -783,8 +784,12 @@ static bool nfsd41_cb_get_slot(struct nfs4_client *clp, struct rpc_task *task) { if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) { rpc_sleep_on(&clp->cl_cb_waitq, task, NULL); - dprintk("%s slot is busy\n", __func__); - return false; + /* Race breaker */ + if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) { + dprintk("%s slot is busy\n", __func__); + return false; + } + rpc_wake_up_queued_task(&clp->cl_cb_waitq, task); } return true; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f23a6ca..86f5d3e 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1243,7 +1243,8 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp) */ if (argp->opcnt == resp->opcnt) return false; - + if (next->opnum == OP_ILLEGAL) + return false; nextd = OPDESC(next); /* * Rest of 2.6.3.1.1: certain operations will return WRONGSEC diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 34d2a1f..daa53da 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1209,15 +1209,14 @@ static int copy_cred(struct svc_cred *target, struct svc_cred *source) return 0; } -static long long +static int compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2) { - long long res; - - res = o1->len - o2->len; - if (res) - return res; - return (long long)memcmp(o1->data, o2->data, o1->len); + if (o1->len < o2->len) + return -1; + if (o1->len > o2->len) + return 1; + return memcmp(o1->data, o2->data, o1->len); } static int same_name(const char *n1, const char *n2) @@ -1401,7 +1400,7 @@ add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root) static struct nfs4_client * find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root) { - long long cmp; + int cmp; struct rb_node *node = root->rb_node; struct nfs4_client *clp; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 8657335..dd1afa3 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1809,6 +1809,9 @@ static __be32 nfsd4_encode_components_esc(char sep, char *components, } else end++; + if (found_esc) + end = next; + str = end; } *pp = p; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index f8f060f..6040da8 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -224,13 +224,6 @@ hash_refile(struct svc_cacherep *rp) hlist_add_head(&rp->c_hash, cache_hash + hash_32(rp->c_xid, maskbits)); } -static inline bool -nfsd_cache_entry_expired(struct svc_cacherep *rp) -{ - return rp->c_state != RC_INPROG && - time_after(jiffies, rp->c_timestamp + RC_EXPIRE); -} - /* * Walk the LRU list and prune off entries that are older than RC_EXPIRE. * Also prune the oldest ones when the total exceeds the max number of entries. @@ -242,8 +235,14 @@ prune_cache_entries(void) long freed = 0; list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) { - if (!nfsd_cache_entry_expired(rp) && - num_drc_entries <= max_drc_entries) + /* + * Don't free entries attached to calls that are still + * in-progress, but do keep scanning the list. + */ + if (rp->c_state == RC_INPROG) + continue; + if (num_drc_entries <= max_drc_entries && + time_before(jiffies, rp->c_timestamp + RC_EXPIRE)) break; nfsd_reply_cache_free_locked(rp); freed++; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 479eb68..f417fef 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -328,12 +328,15 @@ void nfsd_lockd_shutdown(void); (NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT) #ifdef CONFIG_NFSD_V4_SECURITY_LABEL -#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \ - (NFSD4_1_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SECURITY_LABEL) +#define NFSD4_2_SECURITY_ATTRS FATTR4_WORD2_SECURITY_LABEL #else -#define NFSD4_2_SUPPORTED_ATTRS_WORD2 0 +#define NFSD4_2_SECURITY_ATTRS 0 #endif +#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \ + (NFSD4_1_SUPPORTED_ATTRS_WORD2 | \ + NFSD4_2_SECURITY_ATTRS) + static inline u32 nfsd_suppattrs0(u32 minorversion) { return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0 diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 9a4a5f9..c34e45d 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -221,7 +221,8 @@ static int nfsd_startup_generic(int nrservs) */ ret = nfsd_racache_init(2*nrservs); if (ret) - return ret; + goto dec_users; + ret = nfs4_state_start(); if (ret) goto out_racache; @@ -229,6 +230,8 @@ static int nfsd_startup_generic(int nrservs) out_racache: nfsd_racache_shutdown(); +dec_users: + nfsd_users--; return ret; } diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index b2e3ff3..090d8ce 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -31,6 +31,8 @@ #include "alloc.h" #include "dat.h" +static void __nilfs_btree_init(struct nilfs_bmap *bmap); + static struct nilfs_btree_path *nilfs_btree_alloc_path(void) { struct nilfs_btree_path *path; @@ -368,6 +370,34 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node, return ret; } +/** + * nilfs_btree_root_broken - verify consistency of btree root node + * @node: btree root node to be examined + * @ino: inode number + * + * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned. + */ +static int nilfs_btree_root_broken(const struct nilfs_btree_node *node, + unsigned long ino) +{ + int level, flags, nchildren; + int ret = 0; + + level = nilfs_btree_node_get_level(node); + flags = nilfs_btree_node_get_flags(node); + nchildren = nilfs_btree_node_get_nchildren(node); + + if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN || + level >= NILFS_BTREE_LEVEL_MAX || + nchildren < 0 || + nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) { + pr_crit("NILFS: bad btree root (inode number=%lu): level = %d, flags = 0x%x, nchildren = %d\n", + ino, level, flags, nchildren); + ret = 1; + } + return ret; +} + int nilfs_btree_broken_node_block(struct buffer_head *bh) { int ret; @@ -1713,7 +1743,7 @@ nilfs_btree_commit_convert_and_insert(struct nilfs_bmap *btree, /* convert and insert */ dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL; - nilfs_btree_init(btree); + __nilfs_btree_init(btree); if (nreq != NULL) { nilfs_bmap_commit_alloc_ptr(btree, dreq, dat); nilfs_bmap_commit_alloc_ptr(btree, nreq, dat); @@ -2294,12 +2324,23 @@ static const struct nilfs_bmap_operations nilfs_btree_ops_gc = { .bop_gather_data = NULL, }; -int nilfs_btree_init(struct nilfs_bmap *bmap) +static void __nilfs_btree_init(struct nilfs_bmap *bmap) { bmap->b_ops = &nilfs_btree_ops; bmap->b_nchildren_per_block = NILFS_BTREE_NODE_NCHILDREN_MAX(nilfs_btree_node_size(bmap)); - return 0; +} + +int nilfs_btree_init(struct nilfs_bmap *bmap) +{ + int ret = 0; + + __nilfs_btree_init(bmap); + + if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap), + bmap->b_inode->i_ino)) + ret = -EIO; + return ret; } void nilfs_btree_init_gc(struct nilfs_bmap *bmap) diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 7e350c5..09480c53 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include "nilfs.h" @@ -48,6 +49,8 @@ struct nilfs_iget_args { int for_gc; }; +static int nilfs_iget_test(struct inode *inode, void *opaque); + void nilfs_inode_add_blocks(struct inode *inode, int n) { struct nilfs_root *root = NILFS_I(inode)->i_root; @@ -219,10 +222,10 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc) static int nilfs_set_page_dirty(struct page *page) { + struct inode *inode = page->mapping->host; int ret = __set_page_dirty_nobuffers(page); if (page_has_buffers(page)) { - struct inode *inode = page->mapping->host; unsigned nr_dirty = 0; struct buffer_head *bh, *head; @@ -245,6 +248,10 @@ static int nilfs_set_page_dirty(struct page *page) if (nr_dirty) nilfs_set_file_dirty(inode, nr_dirty); + } else if (ret) { + unsigned nr_dirty = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits); + + nilfs_set_file_dirty(inode, nr_dirty); } return ret; } @@ -342,6 +349,17 @@ const struct address_space_operations nilfs_aops = { .is_partially_uptodate = block_is_partially_uptodate, }; +static int nilfs_insert_inode_locked(struct inode *inode, + struct nilfs_root *root, + unsigned long ino) +{ + struct nilfs_iget_args args = { + .ino = ino, .root = root, .cno = 0, .for_gc = 0 + }; + + return insert_inode_locked4(inode, ino, nilfs_iget_test, &args); +} + struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) { struct super_block *sb = dir->i_sb; @@ -377,7 +395,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) { err = nilfs_bmap_read(ii->i_bmap, NULL); if (err < 0) - goto failed_bmap; + goto failed_after_creation; set_bit(NILFS_I_BMAP, &ii->i_state); /* No lock is needed; iget() ensures it. */ @@ -393,21 +411,24 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) spin_lock(&nilfs->ns_next_gen_lock); inode->i_generation = nilfs->ns_next_generation++; spin_unlock(&nilfs->ns_next_gen_lock); - insert_inode_hash(inode); + if (nilfs_insert_inode_locked(inode, root, ino) < 0) { + err = -EIO; + goto failed_after_creation; + } err = nilfs_init_acl(inode, dir); if (unlikely(err)) - goto failed_acl; /* never occur. When supporting + goto failed_after_creation; /* never occur. When supporting nilfs_init_acl(), proper cancellation of above jobs should be considered */ return inode; - failed_acl: - failed_bmap: + failed_after_creation: clear_nlink(inode); + unlock_new_inode(inode); iput(inode); /* raw_inode will be deleted through - generic_delete_inode() */ + nilfs_evict_inode() */ goto failed; failed_ifile_create_inode: @@ -455,8 +476,8 @@ int nilfs_read_inode_common(struct inode *inode, inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec); inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); - if (inode->i_nlink == 0 && inode->i_mode == 0) - return -EINVAL; /* this inode is deleted */ + if (inode->i_nlink == 0) + return -ESTALE; /* this inode is deleted */ inode->i_blocks = le64_to_cpu(raw_inode->i_blocks); ii->i_flags = le32_to_cpu(raw_inode->i_flags); diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 9de78f0..0f84b25 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -51,9 +51,11 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode) int err = nilfs_add_link(dentry, inode); if (!err) { d_instantiate(dentry, inode); + unlock_new_inode(inode); return 0; } inode_dec_link_count(inode); + unlock_new_inode(inode); iput(inode); return err; } @@ -182,6 +184,7 @@ out: out_fail: drop_nlink(inode); nilfs_mark_inode_dirty(inode); + unlock_new_inode(inode); iput(inode); goto out; } @@ -201,11 +204,15 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir, inode_inc_link_count(inode); ihold(inode); - err = nilfs_add_nondir(dentry, inode); - if (!err) + err = nilfs_add_link(dentry, inode); + if (!err) { + d_instantiate(dentry, inode); err = nilfs_transaction_commit(dir->i_sb); - else + } else { + inode_dec_link_count(inode); + iput(inode); nilfs_transaction_abort(dir->i_sb); + } return err; } @@ -243,6 +250,7 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) nilfs_mark_inode_dirty(inode); d_instantiate(dentry, inode); + unlock_new_inode(inode); out: if (!err) err = nilfs_transaction_commit(dir->i_sb); @@ -255,6 +263,7 @@ out_fail: drop_nlink(inode); drop_nlink(inode); nilfs_mark_inode_dirty(inode); + unlock_new_inode(inode); iput(inode); out_dir: drop_nlink(dir); diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 9bc72de..b02c202 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -141,7 +141,6 @@ enum { * @ti_save: Backup of journal_info field of task_struct * @ti_flags: Flags * @ti_count: Nest level - * @ti_garbage: List of inode to be put when releasing semaphore */ struct nilfs_transaction_info { u32 ti_magic; @@ -150,7 +149,6 @@ struct nilfs_transaction_info { one of other filesystems has a bug. */ unsigned short ti_flags; unsigned short ti_count; - struct list_head ti_garbage; }; /* ti_magic */ diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index a1a1916..14538a8 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -305,7 +305,6 @@ static void nilfs_transaction_lock(struct super_block *sb, ti->ti_count = 0; ti->ti_save = cur_ti; ti->ti_magic = NILFS_TI_MAGIC; - INIT_LIST_HEAD(&ti->ti_garbage); current->journal_info = ti; for (;;) { @@ -332,8 +331,6 @@ static void nilfs_transaction_unlock(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); current->journal_info = ti->ti_save; - if (!list_empty(&ti->ti_garbage)) - nilfs_dispose_list(nilfs, &ti->ti_garbage, 0); } static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci, @@ -746,6 +743,15 @@ static void nilfs_dispose_list(struct the_nilfs *nilfs, } } +static void nilfs_iput_work_func(struct work_struct *work) +{ + struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info, + sc_iput_work); + struct the_nilfs *nilfs = sci->sc_super->s_fs_info; + + nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0); +} + static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs, struct nilfs_root *root) { @@ -1899,8 +1905,9 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci, static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, struct the_nilfs *nilfs) { - struct nilfs_transaction_info *ti = current->journal_info; struct nilfs_inode_info *ii, *n; + int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE); + int defer_iput = false; spin_lock(&nilfs->ns_inode_lock); list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) { @@ -1911,9 +1918,24 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, clear_bit(NILFS_I_BUSY, &ii->i_state); brelse(ii->i_bh); ii->i_bh = NULL; - list_move_tail(&ii->i_dirty, &ti->ti_garbage); + list_del_init(&ii->i_dirty); + if (!ii->vfs_inode.i_nlink || during_mount) { + /* + * Defer calling iput() to avoid deadlocks if + * i_nlink == 0 or mount is not yet finished. + */ + list_add_tail(&ii->i_dirty, &sci->sc_iput_queue); + defer_iput = true; + } else { + spin_unlock(&nilfs->ns_inode_lock); + iput(&ii->vfs_inode); + spin_lock(&nilfs->ns_inode_lock); + } } spin_unlock(&nilfs->ns_inode_lock); + + if (defer_iput) + schedule_work(&sci->sc_iput_work); } /* @@ -2580,6 +2602,8 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb, INIT_LIST_HEAD(&sci->sc_segbufs); INIT_LIST_HEAD(&sci->sc_write_logs); INIT_LIST_HEAD(&sci->sc_gc_inodes); + INIT_LIST_HEAD(&sci->sc_iput_queue); + INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func); init_timer(&sci->sc_timer); sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT; @@ -2606,6 +2630,8 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci) ret = nilfs_segctor_construct(sci, SC_LSEG_SR); nilfs_transaction_unlock(sci->sc_super); + flush_work(&sci->sc_iput_work); + } while (ret && retrycount-- > 0); } @@ -2630,6 +2656,9 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) || sci->sc_seq_request != sci->sc_seq_done); spin_unlock(&sci->sc_state_lock); + if (flush_work(&sci->sc_iput_work)) + flag = true; + if (flag || !nilfs_segctor_confirm(sci)) nilfs_segctor_write_out(sci); @@ -2639,6 +2668,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1); } + if (!list_empty(&sci->sc_iput_queue)) { + nilfs_warning(sci->sc_super, __func__, + "iput queue is not empty\n"); + nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1); + } + WARN_ON(!list_empty(&sci->sc_segbufs)); WARN_ON(!list_empty(&sci->sc_write_logs)); diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index 38a1d00..a48d6de 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -26,6 +26,7 @@ #include #include #include +#include #include #include "nilfs.h" @@ -92,6 +93,8 @@ struct nilfs_segsum_pointer { * @sc_nblk_inc: Block count of current generation * @sc_dirty_files: List of files to be written * @sc_gc_inodes: List of GC inodes having blocks to be written + * @sc_iput_queue: list of inodes for which iput should be done + * @sc_iput_work: work struct to defer iput call * @sc_freesegs: array of segment numbers to be freed * @sc_nfreesegs: number of segments on @sc_freesegs * @sc_dsync_inode: inode whose data pages are written for a sync operation @@ -135,6 +138,8 @@ struct nilfs_sc_info { struct list_head sc_dirty_files; struct list_head sc_gc_inodes; + struct list_head sc_iput_queue; + struct work_struct sc_iput_work; __u64 *sc_freesegs; size_t sc_nfreesegs; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 287a22c..de6323e 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -71,7 +71,7 @@ static int create_fd(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - client_fd = get_unused_fd(); + client_fd = get_unused_fd_flags(group->fanotify_data.f_flags); if (client_fd < 0) return client_fd; diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index 238a593..9d7e2b9 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -42,7 +42,7 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode) { struct { struct file_handle handle; - u8 pad[64]; + u8 pad[MAX_HANDLE_SZ]; } f; int size, ret, i; @@ -50,7 +50,7 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode) size = f.handle.handle_bytes >> 2; ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, 0); - if ((ret == 255) || (ret == -ENOSPC)) { + if ((ret == FILEID_INVALID) || (ret < 0)) { WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret); return 0; } diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 9d3e9c5..7001299 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -63,14 +63,14 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode) spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ - hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their * d_flags to indicate parental interest (their parent is the * original inode) */ spin_lock(&alias->d_lock); - list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &alias->d_subdirs, d_child) { if (!child->d_inode) continue; diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index 74825be..fbb9dfb 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -288,20 +288,25 @@ void fsnotify_unmount_inodes(struct list_head *list) spin_unlock(&inode->i_lock); /* In case the dropping of a reference would nuke next_i. */ - if ((&next_i->i_sb_list != list) && - atomic_read(&next_i->i_count)) { + while (&next_i->i_sb_list != list) { spin_lock(&next_i->i_lock); - if (!(next_i->i_state & (I_FREEING | I_WILL_FREE))) { + if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) && + atomic_read(&next_i->i_count)) { __iget(next_i); need_iput = next_i; + spin_unlock(&next_i->i_lock); + break; } spin_unlock(&next_i->i_lock); + next_i = list_entry(next_i->i_sb_list.next, + struct inode, i_sb_list); } /* - * We can safely drop inode_sb_list_lock here because we hold - * references on both inode and next_i. Also no new inodes - * will be added since the umount has begun. + * We can safely drop inode_sb_list_lock here because either + * we actually hold references on both inode and next_i or + * end of list. Also no new inodes will be added since the + * umount has begun. */ spin_unlock(&inode_sb_list_lock); diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 923fe4a..6bffc33 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -293,16 +293,36 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, unsigned int flags) { struct fsnotify_mark *lmark, *mark; + LIST_HEAD(to_free); + /* + * We have to be really careful here. Anytime we drop mark_mutex, e.g. + * fsnotify_clear_marks_by_inode() can come and free marks. Even in our + * to_free list so we have to use mark_mutex even when accessing that + * list. And freeing mark requires us to drop mark_mutex. So we can + * reliably free only the first mark in the list. That's why we first + * move marks to free to to_free list in one go and then free marks in + * to_free list one by one. + */ mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { - if (mark->flags & flags) { - fsnotify_get_mark(mark); - fsnotify_destroy_mark_locked(mark, group); - fsnotify_put_mark(mark); - } + if (mark->flags & flags) + list_move(&mark->g_list, &to_free); } mutex_unlock(&group->mark_mutex); + + while (1) { + mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING); + if (list_empty(&to_free)) { + mutex_unlock(&group->mark_mutex); + break; + } + mark = list_first_entry(&to_free, struct fsnotify_mark, g_list); + fsnotify_get_mark(mark); + fsnotify_destroy_mark_locked(mark, group); + mutex_unlock(&group->mark_mutex); + fsnotify_put_mark(mark); + } } /* diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index a27e3fe..250ed5b 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1748,7 +1748,6 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size) if (page) { set_page_dirty(page); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); } ntfs_debug("Done."); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index db9bd8a..86ddab9 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2060,7 +2060,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, } do { unlock_page(pages[--do_pages]); - mark_page_accessed(pages[do_pages]); page_cache_release(pages[do_pages]); } while (do_pages); if (unlikely(status)) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index aeb44e8..bb6ee06 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -899,7 +899,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages) } } -static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc) { int i; @@ -920,7 +920,11 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) page_cache_release(wc->w_target_page); } ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages); +} +static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +{ + ocfs2_unlock_pages(wc); brelse(wc->w_di_bh); kfree(wc); } @@ -2045,11 +2049,19 @@ out_write_size: di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); ocfs2_journal_dirty(handle, wc->w_di_bh); + /* unlock pages before dealloc since it needs acquiring j_trans_barrier + * lock, or it will cause a deadlock since journal commit threads holds + * this lock and will ask for the page lock when flushing the data. + * put it here to preserve the unlock order. + */ + ocfs2_unlock_pages(wc); + ocfs2_commit_trans(osb, handle); ocfs2_run_deallocs(osb, &wc->w_dealloc); - ocfs2_free_write_ctxt(wc); + brelse(wc->w_di_bh); + kfree(wc); return copied; } diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index 0d3a97d..1167485 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -173,7 +173,7 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode, struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) { trace_ocfs2_find_local_alias(dentry->d_name.len, diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index af3f7aa..1dd0bcc 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -650,12 +650,9 @@ void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm, clear_bit(bit, res->refmap); } - -void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, +static void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { - assert_spin_locked(&res->spinlock); - res->inflight_locks++; mlog(0, "%s: res %.*s, inflight++: now %u, %ps()\n", dlm->name, @@ -663,6 +660,13 @@ void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, __builtin_return_address(0)); } +void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res) +{ + assert_spin_locked(&res->spinlock); + __dlm_lockres_grab_inflight_ref(dlm, res); +} + void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { @@ -722,6 +726,19 @@ lookup: if (tmpres) { spin_unlock(&dlm->spinlock); spin_lock(&tmpres->spinlock); + + /* + * Right after dlm spinlock was released, dlm_thread could have + * purged the lockres. Check if lockres got unhashed. If so + * start over. + */ + if (hlist_unhashed(&tmpres->hash_node)) { + spin_unlock(&tmpres->spinlock); + dlm_lockres_put(tmpres); + tmpres = NULL; + goto lookup; + } + /* Wait on the thread that is mastering the resource */ if (tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN) { __dlm_wait_on_lockres(tmpres); @@ -852,10 +869,8 @@ lookup: /* finally add the lockres to its hash bucket */ __dlm_insert_lockres(dlm, res); - /* Grab inflight ref to pin the resource */ - spin_lock(&res->spinlock); - dlm_lockres_grab_inflight_ref(dlm, res); - spin_unlock(&res->spinlock); + /* since this lockres is new it doesn't not require the spinlock */ + __dlm_lockres_grab_inflight_ref(dlm, res); /* get an extra ref on the mle in case this is a BLOCK * if so, the creator of the BLOCK may try to put the last diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 1998695..fa74259 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3973,9 +3973,13 @@ static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) osb->dc_work_sequence = osb->dc_wake_sequence; processed = osb->blocked_lock_count; - while (processed) { - BUG_ON(list_empty(&osb->blocked_lock_list)); - + /* + * blocked lock processing in this loop might call iput which can + * remove items off osb->blocked_lock_list. Downconvert up to + * 'processed' number of locks, but stop short if we had some + * removed in ocfs2_mark_lockres_freeing when downconverting. + */ + while (processed && !list_empty(&osb->blocked_lock_list)) { lockres = list_entry(osb->blocked_lock_list.next, struct ocfs2_lock_res, l_blocked_list); list_del_init(&lockres->l_blocked_list); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 51632c4..35f54bc 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2391,10 +2391,14 @@ out_dio: /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(ret == -EIOCBQUEUED && !(file->f_flags & O_DIRECT)); + if (unlikely(written <= 0)) + goto no_sync; + if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) || ((file->f_flags & O_DIRECT) && !direct_io)) { - ret = filemap_fdatawrite_range(file->f_mapping, *ppos, - *ppos + count - 1); + ret = filemap_fdatawrite_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); if (ret < 0) written = ret; @@ -2407,10 +2411,12 @@ out_dio: } if (!ret) - ret = filemap_fdatawait_range(file->f_mapping, *ppos, - *ppos + count - 1); + ret = filemap_fdatawait_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); } +no_sync: /* * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io * function pointer which is called when o_direct io completes so that @@ -2472,9 +2478,7 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe, struct address_space *mapping = out->f_mapping; struct inode *inode = mapping->host; struct splice_desc sd = { - .total_len = len, .flags = flags, - .pos = *ppos, .u.file = out, }; @@ -2484,6 +2488,12 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe, out->f_path.dentry->d_name.len, out->f_path.dentry->d_name.name, len); + ret = generic_write_checks(out, ppos, &len, 0); + if (ret) + return ret; + sd.total_len = len; + sd.pos = *ppos; + pipe_lock(pipe); splice_from_pipe_begin(&sd); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index feed025f..b242762 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -94,6 +94,14 @@ static int ocfs2_create_symlink_data(struct ocfs2_super *osb, struct inode *inode, const char *symname); +static int ocfs2_double_lock(struct ocfs2_super *osb, + struct buffer_head **bh1, + struct inode *inode1, + struct buffer_head **bh2, + struct inode *inode2, + int rename); + +static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2); /* An orphan dir name is an 8 byte value, printed as a hex string */ #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64))) @@ -656,8 +664,10 @@ static int ocfs2_link(struct dentry *old_dentry, { handle_t *handle; struct inode *inode = old_dentry->d_inode; + struct inode *old_dir = old_dentry->d_parent->d_inode; int err; struct buffer_head *fe_bh = NULL; + struct buffer_head *old_dir_bh = NULL; struct buffer_head *parent_fe_bh = NULL; struct ocfs2_dinode *fe = NULL; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); @@ -674,19 +684,33 @@ static int ocfs2_link(struct dentry *old_dentry, dquot_initialize(dir); - err = ocfs2_inode_lock_nested(dir, &parent_fe_bh, 1, OI_LS_PARENT); + err = ocfs2_double_lock(osb, &old_dir_bh, old_dir, + &parent_fe_bh, dir, 0); if (err < 0) { if (err != -ENOENT) mlog_errno(err); return err; } + /* make sure both dirs have bhs + * get an extra ref on old_dir_bh if old==new */ + if (!parent_fe_bh) { + if (old_dir_bh) { + parent_fe_bh = old_dir_bh; + get_bh(parent_fe_bh); + } else { + mlog(ML_ERROR, "%s: no old_dir_bh!\n", osb->uuid_str); + err = -EIO; + goto out; + } + } + if (!dir->i_nlink) { err = -ENOENT; goto out; } - err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name, + err = ocfs2_lookup_ino_from_name(old_dir, old_dentry->d_name.name, old_dentry->d_name.len, &old_de_ino); if (err) { err = -ENOENT; @@ -779,10 +803,11 @@ out_unlock_inode: ocfs2_inode_unlock(inode, 1); out: - ocfs2_inode_unlock(dir, 1); + ocfs2_double_unlock(old_dir, dir); brelse(fe_bh); brelse(parent_fe_bh); + brelse(old_dir_bh); ocfs2_free_dir_lookup_result(&lookup); @@ -991,14 +1016,15 @@ leave: } /* - * The only place this should be used is rename! + * The only place this should be used is rename and link! * if they have the same id, then the 1st one is the only one locked. */ static int ocfs2_double_lock(struct ocfs2_super *osb, struct buffer_head **bh1, struct inode *inode1, struct buffer_head **bh2, - struct inode *inode2) + struct inode *inode2, + int rename) { int status; struct ocfs2_inode_info *oi1 = OCFS2_I(inode1); @@ -1028,7 +1054,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, } /* lock id2 */ status = ocfs2_inode_lock_nested(inode2, bh2, 1, - OI_LS_RENAME1); + rename == 1 ? OI_LS_RENAME1 : OI_LS_PARENT); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -1037,7 +1063,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, } /* lock id1 */ - status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_RENAME2); + status = ocfs2_inode_lock_nested(inode1, bh1, 1, + rename == 1 ? OI_LS_RENAME2 : OI_LS_PARENT); if (status < 0) { /* * An error return must mean that no cluster locks @@ -1137,7 +1164,7 @@ static int ocfs2_rename(struct inode *old_dir, /* if old and new are the same, this'll just do one lock. */ status = ocfs2_double_lock(osb, &old_dir_bh, old_dir, - &new_dir_bh, new_dir); + &new_dir_bh, new_dir, 1); if (status < 0) { mlog_errno(status); goto bail; diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index d8b0afd..2dba0ca 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -361,7 +361,7 @@ nomem: } enum { - Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask + Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_err }; static const match_table_t tokens = { @@ -370,6 +370,7 @@ static const match_table_t tokens = { {Opt_umask, "umask=%o"}, {Opt_dmask, "dmask=%o"}, {Opt_fmask, "fmask=%o"}, + {Opt_err, NULL}, }; static int parse_options(char *options, struct omfs_sb_info *sbi) diff --git a/fs/open.c b/fs/open.c index 2ed7325..17679f2 100644 --- a/fs/open.c +++ b/fs/open.c @@ -539,6 +539,7 @@ static int chown_common(struct path *path, uid_t user, gid_t group) uid = make_kuid(current_user_ns(), user); gid = make_kgid(current_user_ns(), group); +retry_deleg: newattrs.ia_valid = ATTR_CTIME; if (user != (uid_t) -1) { if (!uid_valid(uid)) @@ -555,7 +556,6 @@ static int chown_common(struct path *path, uid_t user, gid_t group) if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV; -retry_deleg: mutex_lock(&inode->i_mutex); error = security_path_chown(path, uid, gid); if (!error) diff --git a/fs/pipe.c b/fs/pipe.c index 78fd0d0..46f1ab2 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -117,25 +117,27 @@ void pipe_wait(struct pipe_inode_info *pipe) } static int -pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len, - int atomic) +pipe_iov_copy_from_user(void *addr, int *offset, struct iovec *iov, + size_t *remaining, int atomic) { unsigned long copy; - while (len > 0) { + while (*remaining > 0) { while (!iov->iov_len) iov++; - copy = min_t(unsigned long, len, iov->iov_len); + copy = min_t(unsigned long, *remaining, iov->iov_len); if (atomic) { - if (__copy_from_user_inatomic(to, iov->iov_base, copy)) + if (__copy_from_user_inatomic(addr + *offset, + iov->iov_base, copy)) return -EFAULT; } else { - if (copy_from_user(to, iov->iov_base, copy)) + if (copy_from_user(addr + *offset, + iov->iov_base, copy)) return -EFAULT; } - to += copy; - len -= copy; + *offset += copy; + *remaining -= copy; iov->iov_base += copy; iov->iov_len -= copy; } @@ -143,25 +145,27 @@ pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len, } static int -pipe_iov_copy_to_user(struct iovec *iov, const void *from, unsigned long len, - int atomic) +pipe_iov_copy_to_user(struct iovec *iov, void *addr, int *offset, + size_t *remaining, int atomic) { unsigned long copy; - while (len > 0) { + while (*remaining > 0) { while (!iov->iov_len) iov++; - copy = min_t(unsigned long, len, iov->iov_len); + copy = min_t(unsigned long, *remaining, iov->iov_len); if (atomic) { - if (__copy_to_user_inatomic(iov->iov_base, from, copy)) + if (__copy_to_user_inatomic(iov->iov_base, + addr + *offset, copy)) return -EFAULT; } else { - if (copy_to_user(iov->iov_base, from, copy)) + if (copy_to_user(iov->iov_base, + addr + *offset, copy)) return -EFAULT; } - from += copy; - len -= copy; + *offset += copy; + *remaining -= copy; iov->iov_base += copy; iov->iov_len -= copy; } @@ -395,7 +399,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov, struct pipe_buffer *buf = pipe->bufs + curbuf; const struct pipe_buf_operations *ops = buf->ops; void *addr; - size_t chars = buf->len; + size_t chars = buf->len, remaining; int error, atomic; if (chars > total_len) @@ -409,9 +413,11 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov, } atomic = !iov_fault_in_pages_write(iov, chars); + remaining = chars; redo: addr = ops->map(pipe, buf, atomic); - error = pipe_iov_copy_to_user(iov, addr + buf->offset, chars, atomic); + error = pipe_iov_copy_to_user(iov, addr, &buf->offset, + &remaining, atomic); ops->unmap(pipe, buf, addr); if (unlikely(error)) { /* @@ -426,7 +432,6 @@ redo: break; } ret += chars; - buf->offset += chars; buf->len -= chars; /* Was it a packet buffer? Clean up and exit */ @@ -531,6 +536,7 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov, if (ops->can_merge && offset + chars <= PAGE_SIZE) { int error, atomic = 1; void *addr; + size_t remaining = chars; error = ops->confirm(pipe, buf); if (error) @@ -539,8 +545,8 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov, iov_fault_in_pages_read(iov, chars); redo1: addr = ops->map(pipe, buf, atomic); - error = pipe_iov_copy_from_user(offset + addr, iov, - chars, atomic); + error = pipe_iov_copy_from_user(addr, &offset, iov, + &remaining, atomic); ops->unmap(pipe, buf, addr); ret = error; do_wakeup = 1; @@ -575,6 +581,8 @@ redo1: struct page *page = pipe->tmp_page; char *src; int error, atomic = 1; + int offset = 0; + size_t remaining; if (!page) { page = alloc_page(GFP_HIGHUSER); @@ -595,14 +603,15 @@ redo1: chars = total_len; iov_fault_in_pages_read(iov, chars); + remaining = chars; redo2: if (atomic) src = kmap_atomic(page); else src = kmap(page); - error = pipe_iov_copy_from_user(src, iov, chars, - atomic); + error = pipe_iov_copy_from_user(src, &offset, iov, + &remaining, atomic); if (atomic) kunmap_atomic(src); else diff --git a/fs/pnode.c b/fs/pnode.c index a364a70..b7f8310 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -381,6 +381,7 @@ static void __propagate_umount(struct mount *mnt) * other children */ if (child && list_empty(&child->mnt_mounts)) { + list_del_init(&child->mnt_child); hlist_del_init_rcu(&child->mnt_hash); hlist_add_before_rcu(&child->mnt_hash, &mnt->mnt_hash); } diff --git a/fs/proc/array.c b/fs/proc/array.c index 656e401..baf3464 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -297,15 +297,11 @@ static void render_cap_t(struct seq_file *m, const char *header, seq_puts(m, header); CAP_FOR_EACH_U32(__capi) { seq_printf(m, "%08x", - a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]); + a->cap[CAP_LAST_U32 - __capi]); } seq_putc(m, '\n'); } -/* Remove non-existent capabilities */ -#define NORM_CAPS(v) (v.cap[CAP_TO_INDEX(CAP_LAST_CAP)] &= \ - CAP_TO_MASK(CAP_LAST_CAP + 1) - 1) - static inline void task_cap(struct seq_file *m, struct task_struct *p) { const struct cred *cred; @@ -319,11 +315,6 @@ static inline void task_cap(struct seq_file *m, struct task_struct *p) cap_bset = cred->cap_bset; rcu_read_unlock(); - NORM_CAPS(cap_inheritable); - NORM_CAPS(cap_permitted); - NORM_CAPS(cap_effective); - NORM_CAPS(cap_bset); - render_cap_t(m, "CapInh:\t", &cap_inheritable); render_cap_t(m, "CapPrm:\t", &cap_permitted); render_cap_t(m, "CapEff:\t", &cap_effective); diff --git a/fs/proc/base.c b/fs/proc/base.c index b976062..489ba8c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2555,6 +2555,57 @@ static const struct file_operations proc_projid_map_operations = { .llseek = seq_lseek, .release = proc_id_map_release, }; + +static int proc_setgroups_open(struct inode *inode, struct file *file) +{ + struct user_namespace *ns = NULL; + struct task_struct *task; + int ret; + + ret = -ESRCH; + task = get_proc_task(inode); + if (task) { + rcu_read_lock(); + ns = get_user_ns(task_cred_xxx(task, user_ns)); + rcu_read_unlock(); + put_task_struct(task); + } + if (!ns) + goto err; + + if (file->f_mode & FMODE_WRITE) { + ret = -EACCES; + if (!ns_capable(ns, CAP_SYS_ADMIN)) + goto err_put_ns; + } + + ret = single_open(file, &proc_setgroups_show, ns); + if (ret) + goto err_put_ns; + + return 0; +err_put_ns: + put_user_ns(ns); +err: + return ret; +} + +static int proc_setgroups_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + int ret = single_release(inode, file); + put_user_ns(ns); + return ret; +} + +static const struct file_operations proc_setgroups_operations = { + .open = proc_setgroups_open, + .write = proc_setgroups_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_setgroups_release, +}; #endif /* CONFIG_USER_NS */ static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns, @@ -2663,6 +2714,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), + REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif #ifdef CONFIG_CHECKPOINT_RESTORE REG("timers", S_IRUGO, proc_timers_operations), @@ -2998,6 +3050,7 @@ static const struct pid_entry tid_base_stuff[] = { REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), + REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif }; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index b7f268e..2e2d9d5 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include @@ -162,17 +161,6 @@ void proc_free_inum(unsigned int inum) spin_unlock_irqrestore(&proc_inum_lock, flags); } -static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd) -{ - nd_set_link(nd, __PDE_DATA(dentry->d_inode)); - return NULL; -} - -static const struct inode_operations proc_link_inode_operations = { - .readlink = generic_readlink, - .follow_link = proc_follow_link, -}; - /* * Don't create negative dentries here, return -ENOENT by hand * instead. diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 124fc43..2f2815f 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -23,6 +23,7 @@ #include #include #include +#include #include @@ -401,6 +402,26 @@ static const struct file_operations proc_reg_file_ops_no_compat = { }; #endif +static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + struct proc_dir_entry *pde = PDE(dentry->d_inode); + if (unlikely(!use_pde(pde))) + return ERR_PTR(-EINVAL); + nd_set_link(nd, pde->data); + return pde; +} + +static void proc_put_link(struct dentry *dentry, struct nameidata *nd, void *p) +{ + unuse_pde(p); +} + +const struct inode_operations proc_link_inode_operations = { + .readlink = generic_readlink, + .follow_link = proc_follow_link, + .put_link = proc_put_link, +}; + struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) { struct inode *inode = new_inode_pseudo(sb); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 651d09a..8b8ca1d 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -202,6 +202,7 @@ struct pde_opener { int closing; struct completion *c; }; +extern const struct inode_operations proc_link_inode_operations; extern const struct inode_operations proc_pid_link_inode_operations; diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 6f599c6..dbd0272 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -159,7 +159,7 @@ static int show_stat(struct seq_file *p, void *v) /* sum again ? it could be updated? */ for_each_irq_nr(j) - seq_put_decimal_ull(p, ' ', kstat_irqs(j)); + seq_put_decimal_ull(p, ' ', kstat_irqs_usr(j)); seq_printf(p, "\nctxt %llu\n" diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 8f78819..eaa7374 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1,4 +1,5 @@ #include +#include #include #include #include @@ -152,7 +153,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) /* * We remember last_addr rather than next_addr to hit with - * mmap_cache most of the time. We have zero last_addr at + * vmacache most of the time. We have zero last_addr at * the beginning and also after lseek. We will have -1 last_addr * after the end of the vmas. */ @@ -992,9 +993,8 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct vm_area_struct *vma; struct pagemapread *pm = walk->private; spinlock_t *ptl; - pte_t *pte; + pte_t *pte, *orig_pte; int err = 0; - pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2)); /* find the first VMA at or above 'addr' */ vma = find_vma(walk->mm, addr); @@ -1008,6 +1008,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, for (; addr != end; addr += PAGE_SIZE) { unsigned long offset; + pagemap_entry_t pme; offset = (addr & ~PAGEMAP_WALK_MASK) >> PAGE_SHIFT; @@ -1022,32 +1023,55 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, if (pmd_trans_unstable(pmd)) return 0; - for (; addr != end; addr += PAGE_SIZE) { - int flags2; - - /* check to see if we've left 'vma' behind - * and need a new, higher one */ - if (vma && (addr >= vma->vm_end)) { - vma = find_vma(walk->mm, addr); - if (vma && (vma->vm_flags & VM_SOFTDIRTY)) - flags2 = __PM_SOFT_DIRTY; - else - flags2 = 0; - pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2)); + + while (1) { + /* End of address space hole, which we mark as non-present. */ + unsigned long hole_end; + + if (vma) + hole_end = min(end, vma->vm_start); + else + hole_end = end; + + for (; addr < hole_end; addr += PAGE_SIZE) { + pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2)); + + err = add_to_pagemap(addr, &pme, pm); + if (err) + return err; } - /* check that 'vma' actually covers this address, - * and that it isn't a huge page vma */ - if (vma && (vma->vm_start <= addr) && - !is_vm_hugetlb_page(vma)) { - pte = pte_offset_map(pmd, addr); + if (!vma || vma->vm_start >= end) + break; + /* + * We can't possibly be in a hugetlb VMA. In general, + * for a mm_walk with a pmd_entry and a hugetlb_entry, + * the pmd_entry can only be called on addresses in a + * hugetlb if the walk starts in a non-hugetlb VMA and + * spans a hugepage VMA. Since pagemap_read walks are + * PMD-sized and PMD-aligned, this will never be true. + */ + BUG_ON(is_vm_hugetlb_page(vma)); + + /* Addresses in the VMA. */ + orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + for (; addr < min(end, vma->vm_end); pte++, addr += PAGE_SIZE) { + pagemap_entry_t pme; + pte_to_pagemap_entry(&pme, pm, vma, addr, *pte); - /* unmap before userspace copy */ - pte_unmap(pte); + err = add_to_pagemap(addr, &pme, pm); + if (err) + break; } - err = add_to_pagemap(addr, &pme, pm); + pte_unmap_unlock(orig_pte, ptl); + if (err) return err; + + if (addr == end) + break; + + vma = find_vma(walk->mm, addr); } cond_resched(); @@ -1226,6 +1250,9 @@ out: static int pagemap_open(struct inode *inode, struct file *file) { + /* do not disclose physical addresses: attack vector */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about " "to stop being page-shift some time soon. See the " "linux/Documentation/vm/pagemap.txt for details.\n"); diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 1282384..14120a3 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -319,10 +319,10 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, compressed ? ".enc.z" : ""); break; case PSTORE_TYPE_CONSOLE: - sprintf(name, "console-%s", psname); + sprintf(name, "console-%s-%lld", psname, id); break; case PSTORE_TYPE_FTRACE: - sprintf(name, "ftrace-%s", psname); + sprintf(name, "ftrace-%s-%lld", psname, id); break; case PSTORE_TYPE_MCE: sprintf(name, "mce-%s-%lld", psname, id); diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index fa8cef2..fe68d8a 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -61,6 +61,11 @@ module_param(mem_size, ulong, 0400); MODULE_PARM_DESC(mem_size, "size of reserved RAM used to store oops/panic logs"); +static unsigned int mem_type; +module_param(mem_type, uint, 0600); +MODULE_PARM_DESC(mem_type, + "set to 1 to try to use unbuffered memory (default 0)"); + static int dump_oops = 1; module_param(dump_oops, int, 0600); MODULE_PARM_DESC(dump_oops, @@ -79,6 +84,7 @@ struct ramoops_context { struct persistent_ram_zone *fprz; phys_addr_t phys_addr; unsigned long size; + unsigned int memtype; size_t record_size; size_t console_size; size_t ftrace_size; @@ -86,6 +92,7 @@ struct ramoops_context { struct persistent_ram_ecc_info ecc_info; unsigned int max_dump_cnt; unsigned int dump_write_cnt; + /* _read_cnt need clear on ramoops_pstore_open */ unsigned int dump_read_cnt; unsigned int console_read_cnt; unsigned int ftrace_read_cnt; @@ -101,6 +108,7 @@ static int ramoops_pstore_open(struct pstore_info *psi) cxt->dump_read_cnt = 0; cxt->console_read_cnt = 0; + cxt->ftrace_read_cnt = 0; return 0; } @@ -117,13 +125,15 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max, return NULL; prz = przs[i]; + if (!prz) + return NULL; - if (update) { - /* Update old/shadowed buffer. */ + /* Update old/shadowed buffer. */ + if (update) persistent_ram_save_old(prz); - if (!persistent_ram_old_size(prz)) - return NULL; - } + + if (!persistent_ram_old_size(prz)) + return NULL; *typep = type; *id = i; @@ -353,7 +363,8 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt, size_t sz = cxt->record_size; cxt->przs[i] = persistent_ram_new(*paddr, sz, 0, - &cxt->ecc_info); + &cxt->ecc_info, + cxt->memtype); if (IS_ERR(cxt->przs[i])) { err = PTR_ERR(cxt->przs[i]); dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n", @@ -383,7 +394,7 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt, return -ENOMEM; } - *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info); + *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype); if (IS_ERR(*prz)) { int err = PTR_ERR(*prz); @@ -428,9 +439,9 @@ static int ramoops_probe(struct platform_device *pdev) if (pdata->ftrace_size && !is_power_of_2(pdata->ftrace_size)) pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size); - cxt->dump_read_cnt = 0; cxt->size = pdata->mem_size; cxt->phys_addr = pdata->mem_address; + cxt->memtype = pdata->mem_type; cxt->record_size = pdata->record_size; cxt->console_size = pdata->console_size; cxt->ftrace_size = pdata->ftrace_size; @@ -561,6 +572,7 @@ static void ramoops_register_dummy(void) dummy_data->mem_size = mem_size; dummy_data->mem_address = mem_address; + dummy_data->mem_type = 0; dummy_data->record_size = record_size; dummy_data->console_size = ramoops_console_size; dummy_data->ftrace_size = ramoops_ftrace_size; diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index de272d4..bda61a7 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -380,7 +380,8 @@ void persistent_ram_zap(struct persistent_ram_zone *prz) persistent_ram_update_header_ecc(prz); } -static void *persistent_ram_vmap(phys_addr_t start, size_t size) +static void *persistent_ram_vmap(phys_addr_t start, size_t size, + unsigned int memtype) { struct page **pages; phys_addr_t page_start; @@ -392,7 +393,10 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size) page_start = start - offset_in_page(start); page_count = DIV_ROUND_UP(size + offset_in_page(start), PAGE_SIZE); - prot = pgprot_noncached(PAGE_KERNEL); + if (memtype) + prot = pgprot_noncached(PAGE_KERNEL); + else + prot = pgprot_writecombine(PAGE_KERNEL); pages = kmalloc(sizeof(struct page *) * page_count, GFP_KERNEL); if (!pages) { @@ -411,8 +415,11 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size) return vaddr; } -static void *persistent_ram_iomap(phys_addr_t start, size_t size) +static void *persistent_ram_iomap(phys_addr_t start, size_t size, + unsigned int memtype) { + void *va; + if (!request_mem_region(start, size, "persistent_ram")) { pr_err("request mem region (0x%llx@0x%llx) failed\n", (unsigned long long)size, (unsigned long long)start); @@ -422,19 +429,24 @@ static void *persistent_ram_iomap(phys_addr_t start, size_t size) buffer_start_add = buffer_start_add_locked; buffer_size_add = buffer_size_add_locked; - return ioremap(start, size); + if (memtype) + va = ioremap(start, size); + else + va = ioremap_wc(start, size); + + return va; } static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size, - struct persistent_ram_zone *prz) + struct persistent_ram_zone *prz, int memtype) { prz->paddr = start; prz->size = size; if (pfn_valid(start >> PAGE_SHIFT)) - prz->vaddr = persistent_ram_vmap(start, size); + prz->vaddr = persistent_ram_vmap(start, size, memtype); else - prz->vaddr = persistent_ram_iomap(start, size); + prz->vaddr = persistent_ram_iomap(start, size, memtype); if (!prz->vaddr) { pr_err("%s: Failed to map 0x%llx pages at 0x%llx\n", __func__, @@ -502,7 +514,8 @@ void persistent_ram_free(struct persistent_ram_zone *prz) } struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, - u32 sig, struct persistent_ram_ecc_info *ecc_info) + u32 sig, struct persistent_ram_ecc_info *ecc_info, + unsigned int memtype) { struct persistent_ram_zone *prz; int ret = -ENOMEM; @@ -513,7 +526,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, goto err; } - ret = persistent_ram_buffer_map(start, size, prz); + ret = persistent_ram_buffer_map(start, size, prz, memtype); if (ret) goto err; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index ce87c90..89da957 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -637,7 +637,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type) dqstats_inc(DQST_LOOKUPS); err = sb->dq_op->write_dquot(dquot); if (!ret && err) - err = ret; + ret = err; dqput(dquot); spin_lock(&dq_list_lock); } diff --git a/fs/signalfd.c b/fs/signalfd.c index 424b7b6..148f8e7 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -121,8 +121,9 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, * Other callers might not initialize the si_lsb field, * so check explicitly for the right codes here. */ - if (kinfo->si_code == BUS_MCEERR_AR || - kinfo->si_code == BUS_MCEERR_AO) + if (kinfo->si_signo == SIGBUS && + (kinfo->si_code == BUS_MCEERR_AR || + kinfo->si_code == BUS_MCEERR_AO)) err |= __put_user((short) kinfo->si_addr_lsb, &uinfo->ssi_addr_lsb); #endif diff --git a/fs/splice.c b/fs/splice.c index 12028fa..f345d53 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1012,13 +1012,17 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, struct address_space *mapping = out->f_mapping; struct inode *inode = mapping->host; struct splice_desc sd = { - .total_len = len, .flags = flags, - .pos = *ppos, .u.file = out, }; ssize_t ret; + ret = generic_write_checks(out, ppos, &len, S_ISBLK(inode->i_mode)); + if (ret) + return ret; + sd.total_len = len; + sd.pos = *ppos; + pipe_lock(pipe); splice_from_pipe_begin(&sd); diff --git a/fs/super.c b/fs/super.c index 7624267..440ef51 100644 --- a/fs/super.c +++ b/fs/super.c @@ -81,6 +81,8 @@ static unsigned long super_cache_scan(struct shrinker *shrink, inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid); dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid); total_objects = dentries + inodes + fs_objects + 1; + if (!total_objects) + total_objects = 1; /* proportion the scan between the caches */ dentries = mult_frac(sc->nr_to_scan, dentries, total_objects); @@ -112,9 +114,14 @@ static unsigned long super_cache_count(struct shrinker *shrink, sb = container_of(shrink, struct super_block, s_shrink); - if (!grab_super_passive(sb)) - return 0; - + /* + * Don't call grab_super_passive as it is a potential + * scalability bottleneck. The counts could get updated + * between super_cache_count and super_cache_scan anyway. + * Call to super_cache_count with shrinker_rwsem held + * ensures the safety of call to list_lru_count_node() and + * s_op->nr_cached_objects(). + */ if (sb->s_op && sb->s_op->nr_cached_objects) total_objects = sb->s_op->nr_cached_objects(sb, sc->nid); @@ -125,7 +132,6 @@ static unsigned long super_cache_count(struct shrinker *shrink, sc->nid); total_objects = vfs_pressure_ratio(total_objects); - drop_super(sb); return total_objects; } @@ -276,10 +282,8 @@ void deactivate_locked_super(struct super_block *s) struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { cleancache_invalidate_fs(s); - fs->kill_sb(s); - - /* caches are now gone, we can safely kill the shrinker now */ unregister_shrinker(&s->s_shrink); + fs->kill_sb(s); put_filesystem(fs); put_super(s); diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c index ff82293..26b69b2 100644 --- a/fs/ubifs/commit.c +++ b/fs/ubifs/commit.c @@ -166,15 +166,10 @@ static int do_commit(struct ubifs_info *c) err = ubifs_orphan_end_commit(c); if (err) goto out; - old_ltail_lnum = c->ltail_lnum; - err = ubifs_log_end_commit(c, new_ltail_lnum); - if (err) - goto out; err = dbg_check_old_index(c, &zroot); if (err) goto out; - mutex_lock(&c->mst_mutex); c->mst_node->cmt_no = cpu_to_le64(c->cmt_no); c->mst_node->log_lnum = cpu_to_le32(new_ltail_lnum); c->mst_node->root_lnum = cpu_to_le32(zroot.lnum); @@ -203,8 +198,9 @@ static int do_commit(struct ubifs_info *c) c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS); else c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_NO_ORPHS); - err = ubifs_write_master(c); - mutex_unlock(&c->mst_mutex); + + old_ltail_lnum = c->ltail_lnum; + err = ubifs_log_end_commit(c, new_ltail_lnum); if (err) goto out; diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c index a902c59..8d59de8 100644 --- a/fs/ubifs/log.c +++ b/fs/ubifs/log.c @@ -106,10 +106,14 @@ static inline long long empty_log_bytes(const struct ubifs_info *c) h = (long long)c->lhead_lnum * c->leb_size + c->lhead_offs; t = (long long)c->ltail_lnum * c->leb_size; - if (h >= t) + if (h > t) return c->log_bytes - h + t; - else + else if (h != t) return t - h; + else if (c->lhead_lnum != c->ltail_lnum) + return 0; + else + return c->log_bytes; } /** @@ -447,9 +451,9 @@ out: * @ltail_lnum: new log tail LEB number * * This function is called on when the commit operation was finished. It - * moves log tail to new position and unmaps LEBs which contain obsolete data. - * Returns zero in case of success and a negative error code in case of - * failure. + * moves log tail to new position and updates the master node so that it stores + * the new log tail LEB number. Returns zero in case of success and a negative + * error code in case of failure. */ int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum) { @@ -477,7 +481,12 @@ int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum) spin_unlock(&c->buds_lock); err = dbg_check_bud_bytes(c); + if (err) + goto out; + err = ubifs_write_master(c); + +out: mutex_unlock(&c->log_mutex); return err; } diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c index ab83ace..1a4bb9e 100644 --- a/fs/ubifs/master.c +++ b/fs/ubifs/master.c @@ -352,10 +352,9 @@ int ubifs_read_master(struct ubifs_info *c) * ubifs_write_master - write master node. * @c: UBIFS file-system description object * - * This function writes the master node. The caller has to take the - * @c->mst_mutex lock before calling this function. Returns zero in case of - * success and a negative error code in case of failure. The master node is - * written twice to enable recovery. + * This function writes the master node. Returns zero in case of success and a + * negative error code in case of failure. The master node is written twice to + * enable recovery. */ int ubifs_write_master(struct ubifs_info *c) { diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 5ded849..94d9a64 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1957,7 +1957,6 @@ static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi) mutex_init(&c->lp_mutex); mutex_init(&c->tnc_mutex); mutex_init(&c->log_mutex); - mutex_init(&c->mst_mutex); mutex_init(&c->umount_mutex); mutex_init(&c->bu_mutex); mutex_init(&c->write_reserve_mutex); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index e8c8cfe..7ab9c71 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1042,7 +1042,6 @@ struct ubifs_debug_info; * * @mst_node: master node * @mst_offs: offset of valid master node - * @mst_mutex: protects the master node area, @mst_node, and @mst_offs * * @max_bu_buf_len: maximum bulk-read buffer length * @bu_mutex: protects the pre-allocated bulk-read buffer and @c->bu @@ -1282,7 +1281,6 @@ struct ubifs_info { struct ubifs_mst_node *mst_node; int mst_offs; - struct mutex mst_mutex; int max_bu_buf_len; struct mutex bu_mutex; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 982ce05..287cd5f 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1271,13 +1271,22 @@ update_time: return 0; } +/* + * Maximum length of linked list formed by ICB hierarchy. The chosen number is + * arbitrary - just that we hopefully don't limit any real use of rewritten + * inode on write-once media but avoid looping for too long on corrupted media. + */ +#define UDF_MAX_ICB_NESTING 1024 + static void __udf_read_inode(struct inode *inode) { struct buffer_head *bh = NULL; struct fileEntry *fe; uint16_t ident; struct udf_inode_info *iinfo = UDF_I(inode); + unsigned int indirections = 0; +reread: /* * Set defaults, but the inode is still incomplete! * Note: get_new_inode() sets the following on a new inode: @@ -1314,28 +1323,26 @@ static void __udf_read_inode(struct inode *inode) ibh = udf_read_ptagged(inode->i_sb, &iinfo->i_location, 1, &ident); if (ident == TAG_IDENT_IE && ibh) { - struct buffer_head *nbh = NULL; struct kernel_lb_addr loc; struct indirectEntry *ie; ie = (struct indirectEntry *)ibh->b_data; loc = lelb_to_cpu(ie->indirectICB.extLocation); - if (ie->indirectICB.extLength && - (nbh = udf_read_ptagged(inode->i_sb, &loc, 0, - &ident))) { - if (ident == TAG_IDENT_FE || - ident == TAG_IDENT_EFE) { - memcpy(&iinfo->i_location, - &loc, - sizeof(struct kernel_lb_addr)); - brelse(bh); - brelse(ibh); - brelse(nbh); - __udf_read_inode(inode); + if (ie->indirectICB.extLength) { + brelse(bh); + brelse(ibh); + memcpy(&iinfo->i_location, &loc, + sizeof(struct kernel_lb_addr)); + if (++indirections > UDF_MAX_ICB_NESTING) { + udf_err(inode->i_sb, + "too many ICBs in ICB hierarchy" + " (max %d supported)\n", + UDF_MAX_ICB_NESTING); + make_bad_inode(inode); return; } - brelse(nbh); + goto reread; } } brelse(ibh); diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index d7c6dbe..d89f324 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -80,11 +80,17 @@ static int udf_symlink_filler(struct file *file, struct page *page) struct inode *inode = page->mapping->host; struct buffer_head *bh = NULL; unsigned char *symlink; - int err = -EIO; + int err; unsigned char *p = kmap(page); struct udf_inode_info *iinfo; uint32_t pos; + /* We don't support symlinks longer than one block */ + if (inode->i_size > inode->i_sb->s_blocksize) { + err = -ENAMETOOLONG; + goto out_unmap; + } + iinfo = UDF_I(inode); pos = udf_block_map(inode, 0); @@ -94,8 +100,10 @@ static int udf_symlink_filler(struct file *file, struct page *page) } else { bh = sb_bread(inode->i_sb, pos); - if (!bh) - goto out; + if (!bh) { + err = -EIO; + goto out_unlock_inode; + } symlink = bh->b_data; } @@ -109,9 +117,10 @@ static int udf_symlink_filler(struct file *file, struct page *page) unlock_page(page); return 0; -out: +out_unlock_inode: up_read(&iinfo->i_data_sem); SetPageError(page); +out_unmap: kunmap(page); unlock_page(page); return err; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index db2cfb0..0461fbe 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -434,10 +434,22 @@ xfs_start_page_writeback( { ASSERT(PageLocked(page)); ASSERT(!PageWriteback(page)); - if (clear_dirty) + + /* + * if the page was not fully cleaned, we need to ensure that the higher + * layers come back to it correctly. That means we need to keep the page + * dirty, and for WB_SYNC_ALL writeback we need to ensure the + * PAGECACHE_TAG_TOWRITE index mark is not removed so another attempt to + * write this page in this writeback sweep will be made. + */ + if (clear_dirty) { clear_page_dirty_for_io(page); - set_page_writeback(page); + set_page_writeback(page); + } else + set_page_writeback_keepwrite(page); + unlock_page(page); + /* If no buffers on the page are to be written, finish it here */ if (!buffers) end_page_writeback(page); @@ -1660,11 +1672,72 @@ xfs_vm_readpages( return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks); } +/* + * This is basically a copy of __set_page_dirty_buffers() with one + * small tweak: buffers beyond EOF do not get marked dirty. If we mark them + * dirty, we'll never be able to clean them because we don't write buffers + * beyond EOF, and that means we can't invalidate pages that span EOF + * that have been marked dirty. Further, the dirty state can leak into + * the file interior if the file is extended, resulting in all sorts of + * bad things happening as the state does not match the underlying data. + * + * XXX: this really indicates that bufferheads in XFS need to die. Warts like + * this only exist because of bufferheads and how the generic code manages them. + */ +STATIC int +xfs_vm_set_page_dirty( + struct page *page) +{ + struct address_space *mapping = page->mapping; + struct inode *inode = mapping->host; + loff_t end_offset; + loff_t offset; + int newly_dirty; + + if (unlikely(!mapping)) + return !TestSetPageDirty(page); + + end_offset = i_size_read(inode); + offset = page_offset(page); + + spin_lock(&mapping->private_lock); + if (page_has_buffers(page)) { + struct buffer_head *head = page_buffers(page); + struct buffer_head *bh = head; + + do { + if (offset < end_offset) + set_buffer_dirty(bh); + bh = bh->b_this_page; + offset += 1 << inode->i_blkbits; + } while (bh != head); + } + newly_dirty = !TestSetPageDirty(page); + spin_unlock(&mapping->private_lock); + + if (newly_dirty) { + /* sigh - __set_page_dirty() is static, so copy it here, too */ + unsigned long flags; + + spin_lock_irqsave(&mapping->tree_lock, flags); + if (page->mapping) { /* Race with truncate? */ + WARN_ON_ONCE(!PageUptodate(page)); + account_page_dirtied(page, mapping); + radix_tree_tag_set(&mapping->page_tree, + page_index(page), PAGECACHE_TAG_DIRTY); + } + spin_unlock_irqrestore(&mapping->tree_lock, flags); + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + } + return newly_dirty; +} + const struct address_space_operations xfs_address_space_operations = { .readpage = xfs_vm_readpage, .readpages = xfs_vm_readpages, .writepage = xfs_vm_writepage, .writepages = xfs_vm_writepages, + .set_page_dirty = xfs_vm_set_page_dirty, .releasepage = xfs_vm_releasepage, .invalidatepage = xfs_vm_invalidatepage, .write_begin = xfs_vm_write_begin, diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 3314911..645f180 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -319,6 +319,10 @@ xfs_buf_item_format( ASSERT(atomic_read(&bip->bli_refcount) > 0); ASSERT((bip->bli_flags & XFS_BLI_LOGGED) || (bip->bli_flags & XFS_BLI_STALE)); + ASSERT((bip->bli_flags & XFS_BLI_STALE) || + (xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF + && xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF)); + /* * If it is an inode buffer, transfer the in-memory state to the diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 7aeb4c8..95f9448 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -1011,7 +1011,8 @@ xfs_qm_dqflush( * Get the buffer containing the on-disk dquot */ error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno, - mp->m_quotainfo->qi_dqchunklen, 0, &bp, NULL); + mp->m_quotainfo->qi_dqchunklen, 0, &bp, + &xfs_dquot_buf_ops); if (error) goto out_unlock; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 64b48ea..f50def6 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -302,7 +302,16 @@ xfs_file_aio_read( xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL); return ret; } - truncate_pagecache_range(VFS_I(ip), pos, -1); + + /* + * Invalidate whole pages. This can return an error if + * we fail to invalidate a page, but this should never + * happen on XFS. Warn if it does fail. + */ + ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, + pos >> PAGE_CACHE_SHIFT, -1); + WARN_ON_ONCE(ret); + ret = 0; } xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); } @@ -683,7 +692,15 @@ xfs_file_dio_aio_write( pos, -1); if (ret) goto out; - truncate_pagecache_range(VFS_I(ip), pos, -1); + /* + * Invalidate whole pages. This can return an error if + * we fail to invalidate a page, but this should never + * happen on XFS. Warn if it does fail. + */ + ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, + pos >> PAGE_CACHE_SHIFT, -1); + WARN_ON_ONCE(ret); + ret = 0; } /* diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 3a137e9..5d90b8d 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1946,6 +1946,7 @@ xfs_iunlink( agi->agi_unlinked[bucket_index] = cpu_to_be32(agino); offset = offsetof(xfs_agi_t, agi_unlinked) + (sizeof(xfs_agino_t) * bucket_index); + xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF); xfs_trans_log_buf(tp, agibp, offset, (offset + sizeof(xfs_agino_t) - 1)); return 0; @@ -2037,6 +2038,7 @@ xfs_iunlink_remove( agi->agi_unlinked[bucket_index] = cpu_to_be32(next_agino); offset = offsetof(xfs_agi_t, agi_unlinked) + (sizeof(xfs_agino_t) * bucket_index); + xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF); xfs_trans_log_buf(tp, agibp, offset, (offset + sizeof(xfs_agino_t) - 1)); } else { diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index b0f4ef7..bf9781e 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -24,7 +24,8 @@ struct xfs_log_vec { struct xfs_log_iovec *lv_iovecp; /* iovec array */ struct xfs_log_item *lv_item; /* owner */ char *lv_buf; /* formatted buffer */ - int lv_buf_len; /* size of formatted buffer */ + int lv_bytes; /* accounted space in buffer */ + int lv_buf_len; /* aligned size of buffer */ int lv_size; /* size of allocated lv */ }; @@ -52,15 +53,21 @@ xlog_prepare_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp, return vec->i_addr; } +/* + * We need to make sure the next buffer is naturally aligned for the biggest + * basic data type we put into it. We already accounted for this padding when + * sizing the buffer. + * + * However, this padding does not get written into the log, and hence we have to + * track the space used by the log vectors separately to prevent log space hangs + * due to inaccurate accounting (i.e. a leak) of the used log space through the + * CIL context ticket. + */ static inline void xlog_finish_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec *vec, int len) { - /* - * We need to make sure the next buffer is naturally aligned for the - * biggest basic data type we put into it. We already accounted for - * this when sizing the buffer. - */ lv->lv_buf_len += round_up(len, sizeof(uint64_t)); + lv->lv_bytes += len; vec->i_len = len; } diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 4ef6fdb..bcfbaae 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -97,7 +97,7 @@ xfs_cil_prepare_item( { /* Account for the new LV being passed in */ if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED) { - *diff_len += lv->lv_buf_len; + *diff_len += lv->lv_bytes; *diff_iovecs += lv->lv_niovecs; } @@ -111,7 +111,7 @@ xfs_cil_prepare_item( else if (old_lv != lv) { ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED); - *diff_len -= old_lv->lv_buf_len; + *diff_len -= old_lv->lv_bytes; *diff_iovecs -= old_lv->lv_niovecs; kmem_free(old_lv); } @@ -239,7 +239,7 @@ xlog_cil_insert_format_items( * that the space reservation accounting is correct. */ *diff_iovecs -= lv->lv_niovecs; - *diff_len -= lv->lv_buf_len; + *diff_len -= lv->lv_bytes; } else { /* allocate new data chunk */ lv = kmem_zalloc(buf_size, KM_SLEEP|KM_NOFS); @@ -259,6 +259,7 @@ xlog_cil_insert_format_items( /* The allocated data region lies beyond the iovec region */ lv->lv_buf_len = 0; + lv->lv_bytes = 0; lv->lv_buf = (char *)lv + buf_size - nbytes; ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t))); diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index bce53ac..eb26418 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2125,6 +2125,17 @@ xlog_recover_validate_buf_type( __uint16_t magic16; __uint16_t magicda; + /* + * We can only do post recovery validation on items on CRC enabled + * fielsystems as we need to know when the buffer was written to be able + * to determine if we should have replayed the item. If we replay old + * metadata over a newer buffer, then it will enter a temporarily + * inconsistent state resulting in verification failures. Hence for now + * just avoid the verification stage for non-crc filesystems + */ + if (!xfs_sb_version_hascrc(&mp->m_sb)) + return; + magic32 = be32_to_cpu(*(__be32 *)bp->b_addr); magic16 = be16_to_cpu(*(__be16*)bp->b_addr); magicda = be16_to_cpu(info->magic); @@ -2160,8 +2171,6 @@ xlog_recover_validate_buf_type( bp->b_ops = &xfs_agf_buf_ops; break; case XFS_BLFT_AGFL_BUF: - if (!xfs_sb_version_hascrc(&mp->m_sb)) - break; if (magic32 != XFS_AGFL_MAGIC) { xfs_warn(mp, "Bad AGFL block magic!"); ASSERT(0); @@ -2194,10 +2203,6 @@ xlog_recover_validate_buf_type( #endif break; case XFS_BLFT_DINO_BUF: - /* - * we get here with inode allocation buffers, not buffers that - * track unlinked list changes. - */ if (magic16 != XFS_DINODE_MAGIC) { xfs_warn(mp, "Bad INODE block magic!"); ASSERT(0); @@ -2277,8 +2282,6 @@ xlog_recover_validate_buf_type( bp->b_ops = &xfs_attr3_leaf_buf_ops; break; case XFS_BLFT_ATTR_RMT_BUF: - if (!xfs_sb_version_hascrc(&mp->m_sb)) - break; if (magic32 != XFS_ATTR3_RMT_MAGIC) { xfs_warn(mp, "Bad attr remote magic!"); ASSERT(0); @@ -2385,16 +2388,7 @@ xlog_recover_do_reg_buffer( /* Shouldn't be any more regions */ ASSERT(i == item->ri_total); - /* - * We can only do post recovery validation on items on CRC enabled - * fielsystems as we need to know when the buffer was written to be able - * to determine if we should have replayed the item. If we replay old - * metadata over a newer buffer, then it will enter a temporarily - * inconsistent state resulting in verification failures. Hence for now - * just avoid the verification stage for non-crc filesystems - */ - if (xfs_sb_version_hascrc(&mp->m_sb)) - xlog_recover_validate_buf_type(mp, bp, buf_f); + xlog_recover_validate_buf_type(mp, bp, buf_f); } /* @@ -2502,12 +2496,29 @@ xlog_recover_buffer_pass2( } /* - * recover the buffer only if we get an LSN from it and it's less than + * Recover the buffer only if we get an LSN from it and it's less than * the lsn of the transaction we are replaying. + * + * Note that we have to be extremely careful of readahead here. + * Readahead does not attach verfiers to the buffers so if we don't + * actually do any replay after readahead because of the LSN we found + * in the buffer if more recent than that current transaction then we + * need to attach the verifier directly. Failure to do so can lead to + * future recovery actions (e.g. EFI and unlinked list recovery) can + * operate on the buffers and they won't get the verifier attached. This + * can lead to blocks on disk having the correct content but a stale + * CRC. + * + * It is safe to assume these clean buffers are currently up to date. + * If the buffer is dirtied by a later transaction being replayed, then + * the verifier will be reset to match whatever recover turns that + * buffer into. */ lsn = xlog_recover_get_buf_lsn(mp, bp); - if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) + if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) { + xlog_recover_validate_buf_type(mp, bp, buf_f); goto out_release; + } if (buf_f->blf_flags & XFS_BLF_INODE_BUF) { error = xlog_recover_do_inode_buffer(mp, item, bp, buf_f); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index c6ff3cf5..0eaaa2d 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -321,7 +321,6 @@ reread: * Initialize the mount structure from the superblock. */ xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp)); - xfs_sb_quota_from_disk(sbp); /* * If we haven't validated the superblock, do so now before we try diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 348e4d2..1b271f5 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1108,6 +1108,11 @@ xfs_qm_reset_dqcounts( */ xfs_dqcheck(mp, ddq, id+j, type, XFS_QMOPT_DQREPAIR, "xfs_quotacheck"); + /* + * Reset type in case we are reusing group quota file for + * project quotas or vice versa + */ + ddq->d_flags = type; ddq->d_bcount = 0; ddq->d_icount = 0; ddq->d_rtbcount = 0; @@ -1176,6 +1181,12 @@ xfs_qm_dqiter_bufs( if (error) break; + /* + * A corrupt buffer might not have a verifier attached, so + * make sure we have the correct one attached before writeback + * occurs. + */ + bp->b_ops = &xfs_dquot_buf_ops; xfs_qm_reset_dqcounts(mp, bp, firstid, type); xfs_buf_delwri_queue(bp, buffer_list); xfs_buf_relse(bp); @@ -1261,7 +1272,7 @@ xfs_qm_dqiterate( xfs_buf_readahead(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, rablkno), mp->m_quotainfo->qi_dqchunklen, - NULL); + &xfs_dquot_buf_ops); rablkno++; } } diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c index 1e11679..4afd393 100644 --- a/fs/xfs/xfs_sb.c +++ b/fs/xfs/xfs_sb.c @@ -397,10 +397,11 @@ xfs_sb_quota_from_disk(struct xfs_sb *sbp) } } -void -xfs_sb_from_disk( +static void +__xfs_sb_from_disk( struct xfs_sb *to, - xfs_dsb_t *from) + xfs_dsb_t *from, + bool convert_xquota) { to->sb_magicnum = be32_to_cpu(from->sb_magicnum); to->sb_blocksize = be32_to_cpu(from->sb_blocksize); @@ -456,6 +457,17 @@ xfs_sb_from_disk( to->sb_pad = 0; to->sb_pquotino = be64_to_cpu(from->sb_pquotino); to->sb_lsn = be64_to_cpu(from->sb_lsn); + /* Convert on-disk flags to in-memory flags? */ + if (convert_xquota) + xfs_sb_quota_from_disk(to); +} + +void +xfs_sb_from_disk( + struct xfs_sb *to, + xfs_dsb_t *from) +{ + __xfs_sb_from_disk(to, from, true); } static inline void @@ -571,7 +583,11 @@ xfs_sb_verify( struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_sb sb; - xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp)); + /* + * Use call variant which doesn't convert quota flags from disk + * format, because xfs_mount_validate_sb checks the on-disk flags. + */ + __xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false); /* * Only check the in progress field for the primary superblock as diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 14e58f2..98d4948 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -102,7 +102,7 @@ xfs_readlink_bmap( cur_chunk += sizeof(struct xfs_dsymlink_hdr); } - memcpy(link + offset, bp->b_addr, byte_cnt); + memcpy(link + offset, cur_chunk, byte_cnt); pathlen -= byte_cnt; offset += byte_cnt; diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index c812c5c..b626f3d 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -474,6 +474,7 @@ xfs_trans_apply_sb_deltas( whole = 1; } + xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); if (whole) /* * Log the whole thing, the fields are noncontiguous. diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 8256eb4..ac46782 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -118,6 +118,7 @@ struct acpi_device; struct acpi_hotplug_profile { struct kobject kobj; int (*scan_dependent)(struct acpi_device *adev); + void (*notify_online)(struct acpi_device *adev); bool enabled:1; bool demand_offline:1; }; @@ -228,7 +229,6 @@ struct acpi_device_pnp { acpi_device_name device_name; /* Driver-determined */ acpi_device_class device_class; /* " */ union acpi_object *str_obj; /* unicode string for _STR method */ - unsigned long sun; /* _SUN */ }; #define acpi_device_bid(d) ((d)->pnp.bus_id) diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index fea6773..5d51f27 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -175,7 +175,7 @@ acpi_status __init acpi_load_tables(void); */ acpi_status __init acpi_reallocate_root_table(void); -acpi_status __init acpi_find_root_pointer(acpi_size *rsdp_address); +acpi_status __init acpi_find_root_pointer(acpi_physical_address * rsdp_address); acpi_status acpi_unload_table_id(acpi_owner_id id); diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 68a3ada..69afb57 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -198,9 +198,29 @@ typedef int INT32; typedef s32 acpi_native_int; typedef u32 acpi_size; + +#ifdef ACPI_32BIT_PHYSICAL_ADDRESS + +/* + * OSPMs can define this to shrink the size of the structures for 32-bit + * none PAE environment. ASL compiler may always define this to generate + * 32-bit OSPM compliant tables. + */ typedef u32 acpi_io_address; typedef u32 acpi_physical_address; +#else /* ACPI_32BIT_PHYSICAL_ADDRESS */ + +/* + * It is reported that, after some calculations, the physical addresses can + * wrap over the 32-bit boundary on 32-bit PAE environment. + * https://bugzilla.kernel.org/show_bug.cgi?id=87971 + */ +typedef u64 acpi_io_address; +typedef u64 acpi_physical_address; + +#endif /* ACPI_32BIT_PHYSICAL_ADDRESS */ + #define ACPI_MAX_PTR ACPI_UINT32_MAX #define ACPI_SIZE_MAX ACPI_UINT32_MAX @@ -541,6 +561,7 @@ typedef u64 acpi_integer; #define ACPI_NO_ACPI_ENABLE 0x10 #define ACPI_NO_DEVICE_INIT 0x20 #define ACPI_NO_OBJECT_INIT 0x40 +#define ACPI_NO_FACS_INIT 0x80 /* * Initialization state diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h index b402eb6..579912c 100644 --- a/include/acpi/platform/acenv.h +++ b/include/acpi/platform/acenv.h @@ -76,6 +76,7 @@ #define ACPI_LARGE_NAMESPACE_NODE #define ACPI_DATA_TABLE_DISASSEMBLY #define ACPI_SINGLE_THREADED +#define ACPI_32BIT_PHYSICAL_ADDRESS #endif /* acpi_exec configuration. Multithreaded with full AML debugger */ diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index f1a24b5..b58fd66 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -3,6 +3,8 @@ /* References to section boundaries */ +#include + /* * Usage guidelines: * _text, _data: architecture specific, don't use them in arch-independent code @@ -37,6 +39,8 @@ extern char __start_rodata[], __end_rodata[]; /* Start and end of .ctors section - used for constructor calls. */ extern char __ctors_start[], __ctors_end[]; +extern __visible const void __nosave_begin, __nosave_end; + /* function descriptor handling (if any). Override * in asm/sections.h */ #ifndef dereference_function_descriptor diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 49376ae..7e9a0a6 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -17,6 +17,7 @@ {0x1002, 0x1315, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x1316, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x1317, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x1318, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x131B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x131C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x131D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ @@ -73,7 +74,6 @@ {0x1002, 0x4C64, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \ {0x1002, 0x4C66, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \ {0x1002, 0x4C67, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \ - {0x1002, 0x4C6E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280|RADEON_IS_MOBILITY}, \ {0x1002, 0x4E44, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \ {0x1002, 0x4E45, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \ {0x1002, 0x4E46, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \ @@ -164,23 +164,30 @@ {0x1002, 0x6601, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6602, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6603, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6604, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6605, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6606, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6607, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6608, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6610, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6611, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6613, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6617, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6620, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6621, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6623, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6631, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6640, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6641, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6646, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6650, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6651, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6658, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x665c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x665d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x665f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6660, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6663, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6664, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ @@ -297,6 +304,7 @@ {0x1002, 0x6829, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x682A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x682B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x682C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x682D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x682F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ diff --git a/include/dt-bindings/pinctrl/dra.h b/include/dt-bindings/pinctrl/dra.h index 002a285..7448edf 100644 --- a/include/dt-bindings/pinctrl/dra.h +++ b/include/dt-bindings/pinctrl/dra.h @@ -30,7 +30,8 @@ #define MUX_MODE14 0xe #define MUX_MODE15 0xf -#define PULL_ENA (1 << 16) +#define PULL_ENA (0 << 16) +#define PULL_DIS (1 << 16) #define PULL_UP (1 << 17) #define INPUT_EN (1 << 18) #define SLEWCONTROL (1 << 19) @@ -38,10 +39,10 @@ #define WAKEUP_EVENT (1 << 25) /* Active pin states */ -#define PIN_OUTPUT 0 -#define PIN_OUTPUT_PULLUP (PIN_OUTPUT | PULL_ENA | PULL_UP) -#define PIN_OUTPUT_PULLDOWN (PIN_OUTPUT | PULL_ENA) -#define PIN_INPUT INPUT_EN +#define PIN_OUTPUT (0 | PULL_DIS) +#define PIN_OUTPUT_PULLUP (PULL_UP) +#define PIN_OUTPUT_PULLDOWN (0) +#define PIN_INPUT (INPUT_EN | PULL_DIS) #define PIN_INPUT_SLEW (INPUT_EN | SLEWCONTROL) #define PIN_INPUT_PULLUP (PULL_ENA | INPUT_EN | PULL_UP) #define PIN_INPUT_PULLDOWN (PULL_ENA | INPUT_EN) diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 6d9aedd..327b155 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -60,7 +60,8 @@ struct arch_timer_cpu { #ifdef CONFIG_KVM_ARM_TIMER int kvm_timer_hyp_init(void); -int kvm_timer_init(struct kvm *kvm); +void kvm_timer_enable(struct kvm *kvm); +void kvm_timer_init(struct kvm *kvm); void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu, const struct kvm_irq_level *irq); void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu); @@ -73,11 +74,8 @@ static inline int kvm_timer_hyp_init(void) return 0; }; -static inline int kvm_timer_init(struct kvm *kvm) -{ - return 0; -} - +static inline void kvm_timer_enable(struct kvm *kvm) {} +static inline void kvm_timer_init(struct kvm *kvm) {} static inline void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu, const struct kvm_irq_level *irq) {} static inline void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) {} diff --git a/include/linux/acpi.h b/include/linux/acpi.h index cd80aa8..77af621 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -402,6 +402,7 @@ extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, #define ACPI_OST_SC_INSERT_NOT_SUPPORTED 0x82 extern void acpi_early_init(void); +extern void acpi_subsystem_init(void); extern int acpi_nvs_register(__u64 start, __u64 size); @@ -436,6 +437,7 @@ static inline const char *acpi_dev_name(struct acpi_device *adev) } static inline void acpi_early_init(void) { } +static inline void acpi_subsystem_init(void) { } static inline int early_acpi_boot_init(void) { diff --git a/include/linux/audit.h b/include/linux/audit.h index ec1464d..419b7d7 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -47,6 +47,7 @@ struct sk_buff; struct audit_krule { int vers_ops; + u32 pflags; u32 flags; u32 listnr; u32 action; @@ -64,6 +65,9 @@ struct audit_krule { u64 prio; }; +/* Flag to indicate legacy AUDIT_LOGINUID unset usage */ +#define AUDIT_LOGINUID_LEGACY 0x1 + struct audit_field { u32 type; u32 val; diff --git a/include/linux/bitops.h b/include/linux/bitops.h index be5fd38..5d858e0 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -18,8 +18,11 @@ * position @h. For example * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ -#define GENMASK(h, l) (((U32_C(1) << ((h) - (l) + 1)) - 1) << (l)) -#define GENMASK_ULL(h, l) (((U64_C(1) << ((h) - (l) + 1)) - 1) << (l)) +#define GENMASK(h, l) \ + (((~0UL) << (l)) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + +#define GENMASK_ULL(h, l) \ + (((~0ULL) << (l)) & (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index bbc3a6c..33fd7ff 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -180,7 +180,9 @@ enum rq_flag_bits { __REQ_ELVPRIV, /* elevator private data attached */ __REQ_FAILED, /* set if the request failed */ __REQ_QUIET, /* don't worry about errors */ - __REQ_PREEMPT, /* set for "ide_preempt" requests */ + __REQ_PREEMPT, /* set for "ide_preempt" requests and also + for requests for which the SCSI "quiesce" + state must be ignored. */ __REQ_ALLOCED, /* request came from our alloc pool */ __REQ_COPY_USER, /* contains copies of user pages */ __REQ_FLUSH_SEQ, /* request for flush sequence */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4afa4f8..a693c6d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1232,10 +1232,9 @@ static inline int queue_alignment_offset(struct request_queue *q) static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); - unsigned int alignment = (sector << 9) & (granularity - 1); + unsigned int alignment = sector_div(sector, granularity >> 9) << 9; - return (granularity + lim->alignment_offset - alignment) - & (granularity - 1); + return (granularity + lim->alignment_offset - alignment) % granularity; } static inline int bdev_alignment_offset(struct block_device *bdev) diff --git a/include/linux/capability.h b/include/linux/capability.h index 84b13ad..aa93e5e 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -78,8 +78,11 @@ extern const kernel_cap_t __cap_init_eff_set; # error Fix up hand-coded capability macro initializers #else /* HAND-CODED capability initializers */ +#define CAP_LAST_U32 ((_KERNEL_CAPABILITY_U32S) - 1) +#define CAP_LAST_U32_VALID_MASK (CAP_TO_MASK(CAP_LAST_CAP + 1) -1) + # define CAP_EMPTY_SET ((kernel_cap_t){{ 0, 0 }}) -# define CAP_FULL_SET ((kernel_cap_t){{ ~0, ~0 }}) +# define CAP_FULL_SET ((kernel_cap_t){{ ~0, CAP_LAST_U32_VALID_MASK }}) # define CAP_FS_SET ((kernel_cap_t){{ CAP_FS_MASK_B0 \ | CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \ CAP_FS_MASK_B1 } }) diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 67301a4..879065d 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -289,7 +289,7 @@ extern struct clocksource* clocksource_get_next(void); extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_suspend(void); extern void clocksource_resume(void); -extern struct clocksource * __init __weak clocksource_default_clock(void); +extern struct clocksource * __init clocksource_default_clock(void); extern void clocksource_mark_unstable(struct clocksource *cs); extern u64 diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 7e1c76e..01e3132 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -22,7 +22,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask, - bool sync, bool *contended); + enum migrate_mode mode, bool *contended); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order); @@ -91,7 +91,7 @@ static inline bool compaction_restarting(struct zone *zone, int order) #else static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, - bool sync, bool *contended) + enum migrate_mode mode, bool *contended) { return COMPACT_CONTINUE; } diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 50fcbb0..d133817 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -69,7 +69,6 @@ struct cpuidle_device { unsigned int cpu; int last_residency; - int state_count; struct cpuidle_state_usage states_usage[CPUIDLE_STATE_MAX]; struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX]; struct cpuidle_driver_kobj *kobj_driver; diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 3fe661f..ade2390 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -12,10 +12,31 @@ #include #include #include +#include #ifdef CONFIG_CPUSETS -extern int number_of_cpusets; /* How many cpusets are defined in system? */ +extern struct static_key cpusets_enabled_key; +static inline bool cpusets_enabled(void) +{ + return static_key_false(&cpusets_enabled_key); +} + +static inline int nr_cpusets(void) +{ + /* jump label reference count + the top-level cpuset */ + return static_key_count(&cpusets_enabled_key) + 1; +} + +static inline void cpuset_inc(void) +{ + static_key_slow_inc(&cpusets_enabled_key); +} + +static inline void cpuset_dec(void) +{ + static_key_slow_dec(&cpusets_enabled_key); +} extern int cpuset_init(void); extern void cpuset_init_smp(void); @@ -32,13 +53,13 @@ extern int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask); static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) { - return number_of_cpusets <= 1 || + return nr_cpusets() <= 1 || __cpuset_node_allowed_softwall(node, gfp_mask); } static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) { - return number_of_cpusets <= 1 || + return nr_cpusets() <= 1 || __cpuset_node_allowed_hardwall(node, gfp_mask); } @@ -87,25 +108,26 @@ extern void rebuild_sched_domains(void); extern void cpuset_print_task_mems_allowed(struct task_struct *p); /* - * get_mems_allowed is required when making decisions involving mems_allowed - * such as during page allocation. mems_allowed can be updated in parallel - * and depending on the new value an operation can fail potentially causing - * process failure. A retry loop with get_mems_allowed and put_mems_allowed - * prevents these artificial failures. + * read_mems_allowed_begin is required when making decisions involving + * mems_allowed such as during page allocation. mems_allowed can be updated in + * parallel and depending on the new value an operation can fail potentially + * causing process failure. A retry loop with read_mems_allowed_begin and + * read_mems_allowed_retry prevents these artificial failures. */ -static inline unsigned int get_mems_allowed(void) +static inline unsigned int read_mems_allowed_begin(void) { return read_seqcount_begin(¤t->mems_allowed_seq); } /* - * If this returns false, the operation that took place after get_mems_allowed - * may have failed. It is up to the caller to retry the operation if + * If this returns true, the operation that took place after + * read_mems_allowed_begin may have failed artificially due to a concurrent + * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ -static inline bool put_mems_allowed(unsigned int seq) +static inline bool read_mems_allowed_retry(unsigned int seq) { - return !read_seqcount_retry(¤t->mems_allowed_seq, seq); + return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) @@ -123,6 +145,8 @@ static inline void set_mems_allowed(nodemask_t nodemask) #else /* !CONFIG_CPUSETS */ +static inline bool cpusets_enabled(void) { return false; } + static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} @@ -225,14 +249,14 @@ static inline void set_mems_allowed(nodemask_t nodemask) { } -static inline unsigned int get_mems_allowed(void) +static inline unsigned int read_mems_allowed_begin(void) { return 0; } -static inline bool put_mems_allowed(unsigned int seq) +static inline bool read_mems_allowed_retry(unsigned int seq) { - return true; + return false; } #endif /* !CONFIG_CPUSETS */ diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 7032518..60023e5 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -14,14 +14,13 @@ extern unsigned long long elfcorehdr_addr; extern unsigned long long elfcorehdr_size; -extern int __weak elfcorehdr_alloc(unsigned long long *addr, - unsigned long long *size); -extern void __weak elfcorehdr_free(unsigned long long addr); -extern ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos); -extern ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); -extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, - unsigned long from, unsigned long pfn, - unsigned long size, pgprot_t prot); +extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size); +extern void elfcorehdr_free(unsigned long long addr); +extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos); +extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); +extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot); extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); diff --git a/include/linux/cred.h b/include/linux/cred.h index 04421e8..6c58dd7 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -68,6 +68,7 @@ extern void groups_free(struct group_info *); extern int set_current_groups(struct group_info *); extern int set_groups(struct cred *, struct group_info *); extern int groups_search(const struct group_info *, kgid_t); +extern bool may_setgroups(void); /* access the groups "array" with this macro */ #define GROUP_AT(gi, i) \ diff --git a/include/linux/crypto.h b/include/linux/crypto.h index b92eadf..2b00d92 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -26,6 +26,19 @@ #include /* + * Autoloaded crypto modules should only use a prefixed name to avoid allowing + * arbitrary modules to be loaded. Loading from userspace may still need the + * unprefixed names, so retains those aliases as well. + * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3 + * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro + * expands twice on the same line. Instead, use a separate base name for the + * alias. + */ +#define MODULE_ALIAS_CRYPTO(name) \ + __MODULE_INFO(alias, alias_userspace, name); \ + __MODULE_INFO(alias, alias_crypto, "crypto-" name) + +/* * Algorithm masks and types. */ #define CRYPTO_ALG_TYPE_MASK 0x0000000f diff --git a/include/linux/dcache.h b/include/linux/dcache.h index bf72e9a..2a23ecb 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -124,15 +124,15 @@ struct dentry { void *d_fsdata; /* fs-specific data */ struct list_head d_lru; /* LRU list */ + struct list_head d_child; /* child of parent list */ + struct list_head d_subdirs; /* our children */ /* - * d_child and d_rcu can share memory + * d_alias and d_rcu can share memory */ union { - struct list_head d_child; /* child of parent list */ + struct hlist_node d_alias; /* inode alias list */ struct rcu_head d_rcu; } d_u; - struct list_head d_subdirs; /* our children */ - struct hlist_node d_alias; /* inode alias list */ }; /* @@ -221,6 +221,8 @@ struct dentry_operations { #define DCACHE_SYMLINK_TYPE 0x00300000 /* Symlink */ #define DCACHE_FILE_TYPE 0x00400000 /* Other file type */ +#define DCACHE_MAY_FREE 0x00800000 + extern seqlock_t rename_lock; static inline int dname_external(const struct dentry *dentry) @@ -429,7 +431,7 @@ static inline unsigned __d_entry_type(const struct dentry *dentry) return dentry->d_flags & DCACHE_ENTRY_TYPE; } -static inline bool d_is_directory(const struct dentry *dentry) +static inline bool d_can_lookup(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE; } @@ -439,6 +441,11 @@ static inline bool d_is_autodir(const struct dentry *dentry) return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE; } +static inline bool d_is_dir(const struct dentry *dentry) +{ + return d_can_lookup(dentry) || d_is_autodir(dentry); +} + static inline bool d_is_symlink(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE; diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1c804b0..7ee1774 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -101,8 +101,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, new_dir_mask |= FS_ISDIR; } - fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie); - fsnotify(new_dir, new_dir_mask, new_dir, FSNOTIFY_EVENT_INODE, new_name, fs_cookie); + fsnotify(old_dir, old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_name, + fs_cookie); + fsnotify(new_dir, new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_name, + fs_cookie); if (target) fsnotify_link_count(target); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 39b81dc..3824ac6 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -369,8 +369,8 @@ void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); -extern void free_hot_cold_page(struct page *page, int cold); -extern void free_hot_cold_page_list(struct list_head *list, int cold); +extern void free_hot_cold_page(struct page *page, bool cold); +extern void free_hot_cold_page_list(struct list_head *list, bool cold); extern void __free_memcg_kmem_pages(struct page *page, unsigned int order); extern void free_memcg_kmem_pages(unsigned long addr, unsigned int order); diff --git a/include/linux/hid.h b/include/linux/hid.h index 31b9d29..00c88fc 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -286,6 +286,7 @@ struct hid_item { #define HID_QUIRK_HIDINPUT_FORCE 0x00000080 #define HID_QUIRK_NO_EMPTY_INPUT 0x00000100 #define HID_QUIRK_NO_INIT_INPUT_REPORTS 0x00000200 +#define HID_QUIRK_ALWAYS_POLL 0x00000400 #define HID_QUIRK_SKIP_OUTPUT_REPORTS 0x00010000 #define HID_QUIRK_FULLSPEED_INTERVAL 0x10000000 #define HID_QUIRK_NO_INIT_REPORTS 0x20000000 diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b826239..63579cb 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -93,10 +93,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); #endif /* CONFIG_DEBUG_VM */ extern unsigned long transparent_hugepage_flags; -extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pmd_t *dst_pmd, pmd_t *src_pmd, - struct vm_area_struct *vma, - unsigned long addr, unsigned long end); extern int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index bd1e9bc..42b05c4 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -400,6 +400,16 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, return &mm->page_table_lock; } +static inline bool hugepages_supported(void) +{ + /* + * Some platform decide whether they support huge pages at boot + * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when + * there is no such support + */ + return HPAGE_SHIFT != 0; +} + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page_node(h, nid) NULL diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 72ba6f5..2abe67b 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -186,7 +186,6 @@ vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) } extern bool vlan_do_receive(struct sk_buff **skb); -extern struct sk_buff *vlan_untag(struct sk_buff *skb); extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid); extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid); @@ -228,11 +227,6 @@ static inline bool vlan_do_receive(struct sk_buff **skb) return false; } -static inline struct sk_buff *vlan_untag(struct sk_buff *skb) -{ - return skb; -} - static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid) { return 0; diff --git a/include/linux/iio/events.h b/include/linux/iio/events.h index 8bbd7bc..03fa332 100644 --- a/include/linux/iio/events.h +++ b/include/linux/iio/events.h @@ -72,7 +72,7 @@ struct iio_event_data { #define IIO_EVENT_CODE_EXTRACT_TYPE(mask) ((mask >> 56) & 0xFF) -#define IIO_EVENT_CODE_EXTRACT_DIR(mask) ((mask >> 48) & 0xCF) +#define IIO_EVENT_CODE_EXTRACT_DIR(mask) ((mask >> 48) & 0x7F) #define IIO_EVENT_CODE_EXTRACT_CHAN_TYPE(mask) ((mask >> 32) & 0xFF) diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 75a8a20..c2fb6f3 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -593,6 +593,15 @@ int iio_str_to_fixpoint(const char *str, int fract_mult, int *integer, #define IIO_DEGREE_TO_RAD(deg) (((deg) * 314159ULL + 9000000ULL) / 18000000ULL) /** + * IIO_RAD_TO_DEGREE() - Convert rad to degree + * @rad: A value in rad + * + * Returns the given value converted from rad to degree + */ +#define IIO_RAD_TO_DEGREE(rad) \ + (((rad) * 18000000ULL + 314159ULL / 2) / 314159ULL) + +/** * IIO_G_TO_M_S_2() - Convert g to meter / second**2 * @g: A value in g * @@ -600,4 +609,12 @@ int iio_str_to_fixpoint(const char *str, int fract_mult, int *integer, */ #define IIO_G_TO_M_S_2(g) ((g) * 980665ULL / 100000ULL) +/** + * IIO_M_S_2_TO_G() - Convert meter / second**2 to g + * @ms2: A value in meter / second**2 + * + * Returns the given value converted from meter / second**2 to g + */ +#define IIO_M_S_2_TO_G(ms2) (((ms2) * 100000ULL + 980665ULL / 2) / 980665ULL) + #endif /* _INDUSTRIAL_IO_H_ */ diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 369cf2c..68f46cd 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -84,10 +84,12 @@ static inline void iio_trigger_put(struct iio_trigger *trig) put_device(&trig->dev); } -static inline void iio_trigger_get(struct iio_trigger *trig) +static inline struct iio_trigger *iio_trigger_get(struct iio_trigger *trig) { get_device(&trig->dev); __module_get(trig->ops->owner); + + return trig; } /** diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 0068708..0a21fbe 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -242,7 +242,7 @@ static inline void in_dev_put(struct in_device *idev) static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) - return htonl(~((1<<(32-logmask))-1)); + return htonl(~((1U<<(32-logmask))-1)); return 0; } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d5b50a1..e1fb0f6 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -159,7 +159,11 @@ typedef struct journal_header_s * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * - * Checksum v1 and v2 are mutually exclusive features. + * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses + * journal_block_tag3_t to store a full 32-bit checksum. Everything else + * is the same as v2. + * + * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; @@ -179,6 +183,14 @@ struct commit_header { * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ +typedef struct journal_block_tag3_s +{ + __be32 t_blocknr; /* The on-disk block number */ + __be32 t_flags; /* See below */ + __be32 t_blocknr_high; /* most-significant high 32bits. */ + __be32 t_checksum; /* crc32c(uuid+seq+block) */ +} journal_block_tag3_t; + typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ @@ -187,9 +199,6 @@ typedef struct journal_block_tag_s __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; -#define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high)) -#define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t)) - /* Tail of descriptor block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ @@ -284,6 +293,7 @@ typedef struct journal_superblock_s #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 +#define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM @@ -291,7 +301,8 @@ typedef struct journal_superblock_s #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ - JBD2_FEATURE_INCOMPAT_CSUM_V2) + JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ + JBD2_FEATURE_INCOMPAT_CSUM_V3) #ifdef __KERNEL__ @@ -1024,7 +1035,7 @@ struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); -void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); +int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); /* Commit management */ @@ -1146,7 +1157,7 @@ extern int jbd2_journal_recover (journal_t *journal); extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); -extern void jbd2_journal_update_sb_log_tail (journal_t *, tid_t, +extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, int); extern void __jbd2_journal_abort_hard (journal_t *); extern void jbd2_journal_abort (journal_t *, int); @@ -1296,6 +1307,15 @@ static inline int tid_geq(tid_t x, tid_t y) extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); +static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) +{ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) || + JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + return 1; + + return 0; +} + /* * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for * transaction control blocks. diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 1f44466..c367cbd 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -258,23 +258,11 @@ extern unsigned long preset_lpj; #define SEC_JIFFIE_SC (32 - SHIFT_HZ) #endif #define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29) -#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19) #define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) -#define USEC_CONVERSION \ - ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\ - TICK_NSEC -1) / (u64)TICK_NSEC)) -/* - * USEC_ROUND is used in the timeval to jiffie conversion. See there - * for more details. It is the scaled resolution rounding value. Note - * that it is a 64-bit value. Since, when it is applied, we are already - * in jiffies (albit scaled), it is nothing but the bits we will shift - * off. - */ -#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1) /* * The maximum jiffie value is (MAX_INT >> 1). Here we translate that * into seconds. The 64-bit case will overflow if we are not careful, diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 5c1dfb2..784304b 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -69,6 +69,10 @@ struct static_key { # include # define HAVE_JUMP_LABEL +#else +struct static_key { + atomic_t enabled; +}; #endif /* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */ enum jump_label_type { @@ -79,6 +83,12 @@ enum jump_label_type { struct module; #include + +static inline int static_key_count(struct static_key *key) +{ + return atomic_read(&key->enabled); +} + #ifdef HAVE_JUMP_LABEL #define JUMP_LABEL_TYPE_FALSE_BRANCH 0UL @@ -134,10 +144,6 @@ extern void jump_label_apply_nops(struct module *mod); #else /* !HAVE_JUMP_LABEL */ -struct static_key { - atomic_t enabled; -}; - static __always_inline void jump_label_init(void) { static_key_initialized = true; @@ -145,14 +151,14 @@ static __always_inline void jump_label_init(void) static __always_inline bool static_key_false(struct static_key *key) { - if (unlikely(atomic_read(&key->enabled) > 0)) + if (unlikely(static_key_count(key) > 0)) return true; return false; } static __always_inline bool static_key_true(struct static_key *key) { - if (likely(atomic_read(&key->enabled) > 0)) + if (likely(static_key_count(key) > 0)) return true; return false; } @@ -194,7 +200,7 @@ static inline int jump_label_apply_nops(struct module *mod) static inline bool static_key_enabled(struct static_key *key) { - return (atomic_read(&key->enabled) > 0); + return static_key_count(key) > 0; } #endif /* _LINUX_JUMP_LABEL_H */ diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 51c72be..4b2053a 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -74,6 +74,7 @@ static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu) * Number of interrupts per specific IRQ source, since bootup */ extern unsigned int kstat_irqs(unsigned int irq); +extern unsigned int kstat_irqs_usr(unsigned int irq); /* * Number of interrupts per cpu, since bootup diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 6b06d37..e465bb1 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -283,7 +283,7 @@ struct kgdb_io { extern struct kgdb_arch arch_kgdb_ops; -extern unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs); +extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs); #ifdef CONFIG_SERIAL_KGDB_NMI extern int kgdb_register_nmi_console(void); diff --git a/include/linux/libata.h b/include/linux/libata.h index 3fee55e..189c9ff 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -204,6 +204,7 @@ enum { ATA_LFLAG_SW_ACTIVITY = (1 << 7), /* keep activity stats */ ATA_LFLAG_NO_LPM = (1 << 8), /* disable LPM on this link */ ATA_LFLAG_RST_ONCE = (1 << 9), /* limit recovery to one reset */ + ATA_LFLAG_CHANGED = (1 << 10), /* LPM state changed on this link */ /* struct ata_port flags */ ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ @@ -307,6 +308,12 @@ enum { */ ATA_TMOUT_PMP_SRST_WAIT = 5000, + /* When the LPM policy is set to ATA_LPM_MAX_POWER, there might + * be a spurious PHY event, so ignore the first PHY event that + * occurs within 10s after the policy change. + */ + ATA_TMOUT_SPURIOUS_PHY = 10000, + /* ATA bus states */ BUS_UNKNOWN = 0, BUS_DMA = 1, @@ -421,6 +428,7 @@ enum { ATA_HORKAGE_NO_NCQ_TRIM = (1 << 19), /* don't use queued TRIM */ ATA_HORKAGE_NOLPM = (1 << 20), /* don't use LPM */ ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21), /* some WDs have broken LPM */ + ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ @@ -593,6 +601,7 @@ struct ata_host { struct device *dev; void __iomem * const *iomap; unsigned int n_ports; + unsigned int n_tags; /* nr of NCQ tags */ void *private_data; struct ata_port_operations *ops; unsigned long flags; @@ -784,6 +793,8 @@ struct ata_link { struct ata_eh_context eh_context; struct ata_device device[ATA_MAX_DEVICES]; + + unsigned long last_lpm_change; /* when last LPM change happened */ }; #define ATA_LINK_CLEAR_BEGIN offsetof(struct ata_link, active_tag) #define ATA_LINK_CLEAR_END offsetof(struct ata_link, device[0]) @@ -1200,6 +1211,7 @@ extern struct ata_device *ata_dev_pair(struct ata_device *adev); extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev); extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap); extern void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, struct list_head *eh_q); +extern bool sata_lpm_ignore_phy_events(struct ata_link *link); extern int ata_cable_40wire(struct ata_port *ap); extern int ata_cable_80wire(struct ata_port *ap); diff --git a/include/linux/mbus.h b/include/linux/mbus.h index 345b8c5..550c88f 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -73,6 +73,6 @@ int mvebu_mbus_del_window(phys_addr_t base, size_t size); int mvebu_mbus_init(const char *soc, phys_addr_t mbus_phys_base, size_t mbus_size, phys_addr_t sdram_phys_base, size_t sdram_size); -int mvebu_mbus_dt_init(void); +int mvebu_mbus_dt_init(bool is_coherent); #endif /* __LINUX_MBUS_H */ diff --git a/include/linux/memory.h b/include/linux/memory.h index bb7384e..8b8d8d1 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -35,7 +35,7 @@ struct memory_block { }; int arch_get_memory_phys_device(unsigned long start_pfn); -unsigned long __weak memory_block_size_bytes(void); +unsigned long memory_block_size_bytes(void); /* These states are exposed to userspace as text strings in sysfs */ #define MEM_ONLINE (1<<0) /* exposed to userspace */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 84a31ad..a2901c4 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -5,7 +5,9 @@ #include #include -typedef struct page *new_page_t(struct page *, unsigned long private, int **); +typedef struct page *new_page_t(struct page *page, unsigned long private, + int **reason); +typedef void free_page_t(struct page *page, unsigned long private); /* * Return values from addresss_space_operations.migratepage(): @@ -38,7 +40,7 @@ enum migrate_reason { extern void putback_movable_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); -extern int migrate_pages(struct list_head *l, new_page_t x, +extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason); extern int migrate_prep(void); @@ -56,8 +58,9 @@ extern int migrate_page_move_mapping(struct address_space *mapping, #else static inline void putback_movable_pages(struct list_head *l) {} -static inline int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, enum migrate_mode mode, int reason) +static inline int migrate_pages(struct list_head *l, new_page_t new, + free_page_t free, unsigned long private, enum migrate_mode mode, + int reason) { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } diff --git a/include/linux/mm.h b/include/linux/mm.h index c1b7414..a7b311d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1009,6 +1009,7 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */ #define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned small page */ #define VM_FAULT_HWPOISON_LARGE 0x0020 /* Hit poisoned large page. Index encoded in upper bits */ +#define VM_FAULT_SIGSEGV 0x0040 #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ @@ -1017,8 +1018,9 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ -#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \ - VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE) +#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \ + VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \ + VM_FAULT_FALLBACK) /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((x) << 12) @@ -1041,6 +1043,14 @@ extern void show_free_areas(unsigned int flags); extern bool skip_free_areas_node(unsigned int flags, int nid); int shmem_zero_setup(struct vm_area_struct *); +#ifdef CONFIG_SHMEM +bool shmem_mapping(struct address_space *mapping); +#else +static inline bool shmem_mapping(struct address_space *mapping) +{ + return false; +} +#endif extern int can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); @@ -1123,6 +1133,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); +void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); @@ -1847,9 +1858,6 @@ void page_cache_async_readahead(struct address_space *mapping, unsigned long size); unsigned long max_sane_readahead(unsigned long nr); -unsigned long ra_submit(struct file_ra_state *ra, - struct address_space *mapping, - struct file *filp); /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); @@ -1860,7 +1868,7 @@ extern int expand_downwards(struct vm_area_struct *vma, #if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); #else - #define expand_upwards(vma, address) do { } while (0) + #define expand_upwards(vma, address) (0) #endif /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 290901a..2b58d19 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -342,9 +342,9 @@ struct mm_rss_stat { struct kioctx_table; struct mm_struct { - struct vm_area_struct * mmap; /* list of VMAs */ + struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; - struct vm_area_struct * mmap_cache; /* last find_vma result */ + u32 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e6800f0..ac819bf 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -78,10 +78,15 @@ extern int page_group_by_mobility_disabled; #define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1) #define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1) -static inline int get_pageblock_migratetype(struct page *page) +#define get_pageblock_migratetype(page) \ + get_pfnblock_flags_mask(page, page_to_pfn(page), \ + PB_migrate_end, MIGRATETYPE_MASK) + +static inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn) { BUILD_BUG_ON(PB_migrate_end - PB_migrate != 2); - return get_pageblock_flags_mask(page, PB_migrate_end, MIGRATETYPE_MASK); + return get_pfnblock_flags_mask(page, pfn, PB_migrate_end, + MIGRATETYPE_MASK); } struct free_area { @@ -138,6 +143,7 @@ enum zone_stat_item { NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ + NR_PAGES_SCANNED, /* pages scanned since last reclaim */ #ifdef CONFIG_NUMA NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ @@ -316,19 +322,12 @@ enum zone_type { #ifndef __GENERATING_BOUNDS_H struct zone { - /* Fields commonly accessed by the page allocator */ + /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long watermark[NR_WMARK]; /* - * When free pages are below this point, additional steps are taken - * when reading the number of free pages to avoid per-cpu counter - * drift allowing watermarks to be breached - */ - unsigned long percpu_drift_mark; - - /* * We don't know if the memory that we're going to allocate will be freeable * or/and it will be released eventually, so to avoid totally wasting several * GB of ram we must reserve some of the lower zone memory (otherwise we risk @@ -336,40 +335,26 @@ struct zone { * on the higher zones). This array is recalculated at runtime if the * sysctl_lowmem_reserve_ratio sysctl changes. */ - unsigned long lowmem_reserve[MAX_NR_ZONES]; - - /* - * This is a per-zone reserve of pages that should not be - * considered dirtyable memory. - */ - unsigned long dirty_balance_reserve; + long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA int node; +#endif + /* - * zone reclaim becomes active if more unmapped pages exist. + * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on + * this zone's LRU. Maintained by the pageout code. */ - unsigned long min_unmapped_pages; - unsigned long min_slab_pages; -#endif + unsigned int inactive_ratio; + + struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; + /* - * free areas of different sizes + * This is a per-zone reserve of pages that should not be + * considered dirtyable memory. */ - spinlock_t lock; -#if defined CONFIG_COMPACTION || defined CONFIG_CMA - /* Set to true when the PG_migrate_skip bits should be cleared */ - bool compact_blockskip_flush; - - /* pfns where compaction scanners should start */ - unsigned long compact_cached_free_pfn; - unsigned long compact_cached_migrate_pfn; -#endif -#ifdef CONFIG_MEMORY_HOTPLUG - /* see spanned/present_pages for more description */ - seqlock_t span_seqlock; -#endif - struct free_area free_area[MAX_ORDER]; + unsigned long dirty_balance_reserve; #ifndef CONFIG_SPARSEMEM /* @@ -379,71 +364,14 @@ struct zone { unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ -#ifdef CONFIG_COMPACTION - /* - * On compaction failure, 1<> PAGE_SHIFT */ unsigned long zone_start_pfn; @@ -489,9 +417,11 @@ struct zone { * adjust_managed_page_count() should be used instead of directly * touching zone->managed_pages and totalram_pages. */ + unsigned long managed_pages; unsigned long spanned_pages; unsigned long present_pages; - unsigned long managed_pages; + + const char *name; /* * Number of MIGRATE_RESEVE page block. To maintain for just @@ -499,10 +429,91 @@ struct zone { */ int nr_migrate_reserve_block; +#ifdef CONFIG_MEMORY_HOTPLUG + /* see spanned/present_pages for more description */ + seqlock_t span_seqlock; +#endif + /* - * rarely used fields: + * wait_table -- the array holding the hash table + * wait_table_hash_nr_entries -- the size of the hash table array + * wait_table_bits -- wait_table_size == (1 << wait_table_bits) + * + * The purpose of all these is to keep track of the people + * waiting for a page to become available and make them + * runnable again when possible. The trouble is that this + * consumes a lot of space, especially when so few things + * wait on pages at a given time. So instead of using + * per-page waitqueues, we use a waitqueue hash table. + * + * The bucket discipline is to sleep on the same queue when + * colliding and wake all in that wait queue when removing. + * When something wakes, it must check to be sure its page is + * truly available, a la thundering herd. The cost of a + * collision is great, but given the expected load of the + * table, they should be so rare as to be outweighed by the + * benefits from the saved space. + * + * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the + * primary users of these fields, and in mm/page_alloc.c + * free_area_init_core() performs the initialization of them. */ - const char *name; + wait_queue_head_t *wait_table; + unsigned long wait_table_hash_nr_entries; + unsigned long wait_table_bits; + + ZONE_PADDING(_pad1_) + + /* Write-intensive fields used from the page allocator */ + spinlock_t lock; + + /* free areas of different sizes */ + struct free_area free_area[MAX_ORDER]; + + /* zone flags, see below */ + unsigned long flags; + + ZONE_PADDING(_pad2_) + + /* Write-intensive fields used by page reclaim */ + + /* Fields commonly accessed by the page reclaim scanner */ + spinlock_t lru_lock; + struct lruvec lruvec; + + /* + * When free pages are below this point, additional steps are taken + * when reading the number of free pages to avoid per-cpu counter + * drift allowing watermarks to be breached + */ + unsigned long percpu_drift_mark; + +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + /* pfn where compaction free scanner should start */ + unsigned long compact_cached_free_pfn; + /* pfn where async and sync compaction migration scanner should start */ + unsigned long compact_cached_migrate_pfn[2]; +#endif + +#ifdef CONFIG_COMPACTION + /* + * On compaction failure, 1<flags); } +static inline int zone_is_fair_depleted(const struct zone *zone) +{ + return test_bit(ZONE_FAIR_DEPLETED, &zone->flags); +} + static inline int zone_is_oom_locked(const struct zone *zone) { return test_bit(ZONE_OOM_LOCKED, &zone->flags); @@ -806,10 +823,10 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat) extern struct mutex zonelists_mutex; void build_all_zonelists(pg_data_t *pgdat, struct zone *zone); void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); -bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags); -bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags); +bool zone_watermark_ok(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags); +bool zone_watermark_ok_safe(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags); enum memmap_context { MEMMAP_EARLY, MEMMAP_HOTPLUG, diff --git a/include/linux/mount.h b/include/linux/mount.h index 839bac2..b0c1e65 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -42,13 +42,20 @@ struct mnt_namespace; * flag, consider how it interacts with shared mounts. */ #define MNT_SHARED_MASK (MNT_UNBINDABLE) -#define MNT_PROPAGATION_MASK (MNT_SHARED | MNT_UNBINDABLE) +#define MNT_USER_SETTABLE_MASK (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \ + | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \ + | MNT_READONLY) +#define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED) #define MNT_INTERNAL 0x4000 +#define MNT_LOCK_ATIME 0x040000 +#define MNT_LOCK_NOEXEC 0x080000 +#define MNT_LOCK_NOSUID 0x100000 +#define MNT_LOCK_NODEV 0x200000 #define MNT_LOCK_READONLY 0x400000 #define MNT_LOCKED 0x800000 #define MNT_DOOMED 0x1000000 diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 911718f..bf46cc8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1880,6 +1880,12 @@ void netdev_freemem(struct net_device *dev); void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); +DECLARE_PER_CPU(int, xmit_recursion); +static inline int dev_recursion_level(void) +{ + return this_cpu_read(xmit_recursion); +} + struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5624e4e..3a36a2c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1155,7 +1155,7 @@ struct nfs41_state_protection { struct nfs4_op_map allow; }; -#define NFS4_EXCHANGE_ID_LEN (48) +#define NFS4_EXCHANGE_ID_LEN (127) struct nfs41_exchange_id_args { struct nfs_client *client; nfs4_verifier *verifier; @@ -1247,11 +1247,22 @@ struct nfs41_free_stateid_res { unsigned int status; }; +static inline void +nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo) +{ + kfree(cinfo->buckets); +} + #else struct pnfs_ds_commit_info { }; +static inline void +nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo) +{ +} + #endif /* CONFIG_NFS_V4_1 */ struct nfs_page; diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index 9875576..1108aca 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -458,7 +458,7 @@ struct nilfs_btree_node { /* level */ #define NILFS_BTREE_LEVEL_DATA 0 #define NILFS_BTREE_LEVEL_NODE_MIN (NILFS_BTREE_LEVEL_DATA + 1) -#define NILFS_BTREE_LEVEL_MAX 14 +#define NILFS_BTREE_LEVEL_MAX 14 /* Max level (exclusive) */ /** * struct nilfs_palloc_group_desc - block group descriptor diff --git a/include/linux/of.h b/include/linux/of.h index 435cb99..9f2698d 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -215,14 +215,12 @@ extern int of_property_read_u64(const struct device_node *np, extern int of_property_read_string(struct device_node *np, const char *propname, const char **out_string); -extern int of_property_read_string_index(struct device_node *np, - const char *propname, - int index, const char **output); extern int of_property_match_string(struct device_node *np, const char *propname, const char *string); -extern int of_property_count_strings(struct device_node *np, - const char *propname); +extern int of_property_read_string_helper(struct device_node *np, + const char *propname, + const char **out_strs, size_t sz, int index); extern int of_device_is_compatible(const struct device_node *device, const char *); extern int of_device_is_available(const struct device_node *device); @@ -422,15 +420,9 @@ static inline int of_property_read_string(struct device_node *np, return -ENOSYS; } -static inline int of_property_read_string_index(struct device_node *np, - const char *propname, int index, - const char **out_string) -{ - return -ENOSYS; -} - -static inline int of_property_count_strings(struct device_node *np, - const char *propname) +static inline int of_property_read_string_helper(struct device_node *np, + const char *propname, + const char **out_strs, size_t sz, int index) { return -ENOSYS; } @@ -525,7 +517,10 @@ static inline const char *of_prop_next_string(struct property *prop, #if defined(CONFIG_OF) && defined(CONFIG_NUMA) extern int of_node_to_nid(struct device_node *np); #else -static inline int of_node_to_nid(struct device_node *device) { return 0; } +static inline int of_node_to_nid(struct device_node *device) +{ + return NUMA_NO_NODE; +} #endif static inline struct device_node *of_find_matching_node( @@ -536,6 +531,70 @@ static inline struct device_node *of_find_matching_node( } /** + * of_property_read_string_array() - Read an array of strings from a multiple + * strings property. + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_strs: output array of string pointers. + * @sz: number of array elements to read. + * + * Search for a property in a device tree node and retrieve a list of + * terminated string values (pointer to data, not a copy) in that property. + * + * If @out_strs is NULL, the number of strings in the property is returned. + */ +static inline int of_property_read_string_array(struct device_node *np, + const char *propname, const char **out_strs, + size_t sz) +{ + return of_property_read_string_helper(np, propname, out_strs, sz, 0); +} + +/** + * of_property_count_strings() - Find and return the number of strings from a + * multiple strings property. + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * + * Search for a property in a device tree node and retrieve the number of null + * terminated string contain in it. Returns the number of strings on + * success, -EINVAL if the property does not exist, -ENODATA if property + * does not have a value, and -EILSEQ if the string is not null-terminated + * within the length of the property data. + */ +static inline int of_property_count_strings(struct device_node *np, + const char *propname) +{ + return of_property_read_string_helper(np, propname, NULL, 0, 0); +} + +/** + * of_property_read_string_index() - Find and read a string from a multiple + * strings property. + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @index: index of the string in the list of strings + * @out_string: pointer to null terminated return string, modified only if + * return value is 0. + * + * Search for a property in a device tree node and retrieve a null + * terminated string value (pointer to data, not a copy) in the list of strings + * contained in that property. + * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if + * property does not have a value, and -EILSEQ if the string is not + * null-terminated within the length of the property data. + * + * The out_string pointer is modified only if a valid string can be decoded. + */ +static inline int of_property_read_string_index(struct device_node *np, + const char *propname, + int index, const char **output) +{ + int rc = of_property_read_string_helper(np, propname, output, 1, index); + return rc < 0 ? rc : 0; +} + +/** * of_property_read_bool - Findfrom a property * @np: device node from which the property value is to be read. * @propname: name of the property to be searched. diff --git a/include/linux/oom.h b/include/linux/oom.h index 4cd6267..17f0949 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -50,6 +50,9 @@ static inline bool oom_task_origin(const struct task_struct *p) extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); + +extern int oom_kills_count(void); +extern void note_oom_kill(void); extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, unsigned int points, unsigned long totalpages, struct mem_cgroup *memcg, nodemask_t *nodemask, diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index ca71a1d..3c545b4 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -198,6 +198,7 @@ struct page; /* forward declaration */ TESTPAGEFLAG(Locked, locked) PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error) PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) + __SETPAGEFLAG(Referenced, referenced) PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru) PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active) @@ -208,6 +209,7 @@ PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ PAGEFLAG(SavePinned, savepinned); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) + __SETPAGEFLAG(SwapBacked, swapbacked) __PAGEFLAG(SlobFree, slob_free) diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index c08730c..2baeee1 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -65,33 +65,26 @@ extern int pageblock_order; /* Forward declaration */ struct page; -unsigned long get_pageblock_flags_mask(struct page *page, +unsigned long get_pfnblock_flags_mask(struct page *page, + unsigned long pfn, unsigned long end_bitidx, unsigned long mask); -void set_pageblock_flags_mask(struct page *page, + +void set_pfnblock_flags_mask(struct page *page, unsigned long flags, + unsigned long pfn, unsigned long end_bitidx, unsigned long mask); /* Declarations for getting and setting flags. See mm/page_alloc.c */ -static inline unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx) -{ - unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1; - unsigned long mask = (1 << nr_flag_bits) - 1; - - return get_pageblock_flags_mask(page, end_bitidx, mask); -} - -static inline void set_pageblock_flags_group(struct page *page, - unsigned long flags, - int start_bitidx, int end_bitidx) -{ - unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1; - unsigned long mask = (1 << nr_flag_bits) - 1; - - set_pageblock_flags_mask(page, flags, end_bitidx, mask); -} +#define get_pageblock_flags_group(page, start_bitidx, end_bitidx) \ + get_pfnblock_flags_mask(page, page_to_pfn(page), \ + end_bitidx, \ + (1 << (end_bitidx - start_bitidx + 1)) - 1) +#define set_pageblock_flags_group(page, flags, start_bitidx, end_bitidx) \ + set_pfnblock_flags_mask(page, flags, page_to_pfn(page), \ + end_bitidx, \ + (1 << (end_bitidx - start_bitidx + 1)) - 1) #ifdef CONFIG_COMPACTION #define get_pageblock_skip(page) \ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 1710d1b..fcebdda 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -99,7 +99,7 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define page_cache_get(page) get_page(page) #define page_cache_release(page) put_page(page) -void release_pages(struct page **pages, int nr, int cold); +void release_pages(struct page **pages, int nr, bool cold); /* * speculatively take a reference to a page. @@ -243,12 +243,116 @@ static inline struct page *page_cache_alloc_readahead(struct address_space *x) typedef int filler_t(void *, struct page *); -extern struct page * find_get_page(struct address_space *mapping, - pgoff_t index); -extern struct page * find_lock_page(struct address_space *mapping, - pgoff_t index); -extern struct page * find_or_create_page(struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask); +pgoff_t page_cache_next_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan); +pgoff_t page_cache_prev_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan); + +#define FGP_ACCESSED 0x00000001 +#define FGP_LOCK 0x00000002 +#define FGP_CREAT 0x00000004 +#define FGP_WRITE 0x00000008 +#define FGP_NOFS 0x00000010 +#define FGP_NOWAIT 0x00000020 + +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t cache_gfp_mask); + +/** + * find_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. + * + * Otherwise, %NULL is returned. + */ +static inline struct page *find_get_page(struct address_space *mapping, + pgoff_t offset) +{ + return pagecache_get_page(mapping, offset, 0, 0); +} + +static inline struct page *find_get_page_flags(struct address_space *mapping, + pgoff_t offset, int fgp_flags) +{ + return pagecache_get_page(mapping, offset, fgp_flags, 0); +} + +/** + * find_lock_page - locate, pin and lock a pagecache page + * pagecache_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * Otherwise, %NULL is returned. + * + * find_lock_page() may sleep. + */ +static inline struct page *find_lock_page(struct address_space *mapping, + pgoff_t offset) +{ + return pagecache_get_page(mapping, offset, FGP_LOCK, 0); +} + +/** + * find_or_create_page - locate or add a pagecache page + * @mapping: the page's address_space + * @index: the page's index into the mapping + * @gfp_mask: page allocation mode + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the page is not present, a new page is allocated using @gfp_mask + * and added to the page cache and the VM's LRU list. The page is + * returned locked and with an increased refcount. + * + * On memory exhaustion, %NULL is returned. + * + * find_or_create_page() may sleep, even if @gfp_flags specifies an + * atomic allocation! + */ +static inline struct page *find_or_create_page(struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask) +{ + return pagecache_get_page(mapping, offset, + FGP_LOCK|FGP_ACCESSED|FGP_CREAT, + gfp_mask); +} + +/** + * grab_cache_page_nowait - returns locked page at given index in given cache + * @mapping: target address_space + * @index: the page index + * + * Same as grab_cache_page(), but do not wait if the page is unavailable. + * This is intended for speculative data generators, where the data can + * be regenerated if the page couldn't be grabbed. This routine should + * be safe to call while holding the lock for another page. + * + * Clear __GFP_FS when allocating the page to avoid recursion into the fs + * and deadlock against the caller's locked page. + */ +static inline struct page *grab_cache_page_nowait(struct address_space *mapping, + pgoff_t index) +{ + return pagecache_get_page(mapping, index, + FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, + mapping_gfp_mask(mapping)); +} + +struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); +struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); +unsigned find_get_entries(struct address_space *mapping, pgoff_t start, + unsigned int nr_entries, struct page **entries, + pgoff_t *indices); unsigned find_get_pages(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, @@ -268,10 +372,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping, return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } -extern struct page * grab_cache_page_nowait(struct address_space *mapping, - pgoff_t index); -extern struct page * read_cache_page_async(struct address_space *mapping, - pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, @@ -279,14 +379,6 @@ extern struct page * read_cache_page_gfp(struct address_space *mapping, extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); -static inline struct page *read_mapping_page_async( - struct address_space *mapping, - pgoff_t index, void *data) -{ - filler_t *filler = (filler_t *)mapping->a_ops->readpage; - return read_cache_page_async(mapping, index, filler, data); -} - static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, void *data) { diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index e4dbfab..b45d391 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -22,6 +22,11 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); +unsigned pagevec_lookup_entries(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t start, unsigned nr_entries, + pgoff_t *indices); +void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_pages); unsigned pagevec_lookup_tag(struct pagevec *pvec, diff --git a/include/linux/pci.h b/include/linux/pci.h index 33aa2ca..d662546 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -170,6 +170,8 @@ enum pci_dev_flags { PCI_DEV_FLAGS_NO_D3 = (__force pci_dev_flags_t) 2, /* Provide indication device is assigned by a Virtual Machine Manager */ PCI_DEV_FLAGS_ASSIGNED = (__force pci_dev_flags_t) 4, + /* Do not use bus resets for device */ + PCI_DEV_FLAGS_NO_BUS_RESET = (__force pci_dev_flags_t) (1 << 6), }; enum pci_irq_reroute_variant { @@ -324,6 +326,7 @@ struct pci_dev { unsigned int is_added:1; unsigned int is_busmaster:1; /* device is busmaster */ unsigned int no_msi:1; /* device may not use msi */ + unsigned int no_64bit_msi:1; /* device may only use 32-bit MSIs */ unsigned int block_cfg_access:1; /* config space access is blocked */ unsigned int broken_parity_status:1; /* Device generates false positive parity */ unsigned int irq_reroute_variant:2; /* device needs IRQ rerouting variant */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 97fbecd..057c1d8 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2551,6 +2551,7 @@ #define PCI_DEVICE_ID_INTEL_MFD_EMMC0 0x0823 #define PCI_DEVICE_ID_INTEL_MFD_EMMC1 0x0824 #define PCI_DEVICE_ID_INTEL_MRST_SD2 0x084F +#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB 0x095E #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 diff --git a/include/linux/plist.h b/include/linux/plist.h index aa0fb39..8b6c970 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -98,6 +98,13 @@ struct plist_node { } /** + * PLIST_HEAD - declare and init plist_head + * @head: name for struct plist_head variable + */ +#define PLIST_HEAD(head) \ + struct plist_head head = PLIST_HEAD_INIT(head) + +/** * PLIST_NODE_INIT - static struct plist_node initializer * @node: struct plist_node variable name * @__prio: initial node priority @@ -134,6 +141,8 @@ static inline void plist_node_init(struct plist_node *node, int prio) extern void plist_add(struct plist_node *node, struct plist_head *head); extern void plist_del(struct plist_node *node, struct plist_head *head); +extern void plist_requeue(struct plist_node *node, struct plist_head *head); + /** * plist_for_each - iterate over the plist * @pos: the type * to use as a loop counter @@ -143,6 +152,16 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); list_for_each_entry(pos, &(head)->node_list, node_list) /** + * plist_for_each_continue - continue iteration over the plist + * @pos: the type * to use as a loop cursor + * @head: the head for your list + * + * Continue to iterate over plist, continuing after the current position. + */ +#define plist_for_each_continue(pos, head) \ + list_for_each_entry_continue(pos, &(head)->node_list, node_list) + +/** * plist_for_each_safe - iterate safely over a plist of given type * @pos: the type * to use as a loop counter * @n: another type * to use as temporary storage @@ -163,6 +182,18 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); list_for_each_entry(pos, &(head)->node_list, mem.node_list) /** + * plist_for_each_entry_continue - continue iteration over list of given type + * @pos: the type * to use as a loop cursor + * @head: the head for your list + * @m: the name of the list_struct within the struct + * + * Continue to iterate over list of given type, continuing after + * the current position. + */ +#define plist_for_each_entry_continue(pos, head, m) \ + list_for_each_entry_continue(pos, &(head)->node_list, m.node_list) + +/** * plist_for_each_entry_safe - iterate safely over list of given type * @pos: the type * to use as a loop counter * @n: another type * to use as temporary storage @@ -229,6 +260,20 @@ static inline int plist_node_empty(const struct plist_node *node) #endif /** + * plist_next - get the next entry in list + * @pos: the type * to cursor + */ +#define plist_next(pos) \ + list_next_entry(pos, node_list) + +/** + * plist_prev - get the prev entry in list + * @pos: the type * to cursor + */ +#define plist_prev(pos) \ + list_prev_entry(pos, node_list) + +/** * plist_first - return the first node (and thus, highest priority) * @head: the &struct plist_head pointer * diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h index 07e7945..e97fc65 100644 --- a/include/linux/power/charger-manager.h +++ b/include/linux/power/charger-manager.h @@ -253,9 +253,6 @@ struct charger_manager { struct device *dev; struct charger_desc *desc; - struct power_supply *fuel_gauge; - struct power_supply **charger_stat; - #ifdef CONFIG_THERMAL struct thermal_zone_device *tzd_batt; #endif diff --git a/include/linux/printk.h b/include/linux/printk.h index fa47e27..cbf094f 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -132,9 +132,9 @@ asmlinkage __printf(1, 2) __cold int printk(const char *fmt, ...); /* - * Special printk facility for scheduler use only, _DO_NOT_USE_ ! + * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ ! */ -__printf(1, 2) __cold int printk_sched(const char *fmt, ...); +__printf(1, 2) __cold int printk_deferred(const char *fmt, ...); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -169,7 +169,7 @@ int printk(const char *s, ...) return 0; } static inline __printf(1, 2) __cold -int printk_sched(const char *s, ...) +int printk_deferred(const char *s, ...) { return 0; } diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 9974975..4af3fdc 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -53,7 +53,8 @@ struct persistent_ram_zone { }; struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, - u32 sig, struct persistent_ram_ecc_info *ecc_info); + u32 sig, struct persistent_ram_ecc_info *ecc_info, + unsigned int memtype); void persistent_ram_free(struct persistent_ram_zone *prz); void persistent_ram_zap(struct persistent_ram_zone *prz); @@ -76,6 +77,7 @@ ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz, struct ramoops_platform_data { unsigned long mem_size; unsigned long mem_address; + unsigned int mem_type; unsigned long record_size; unsigned long console_size; unsigned long ftrace_size; diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 4039407..e8be53e 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -219,6 +219,7 @@ static inline void radix_tree_replace_slot(void **pslot, void *item) int radix_tree_insert(struct radix_tree_root *, unsigned long, void *); void *radix_tree_lookup(struct radix_tree_root *, unsigned long); void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); +void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, void **results, @@ -226,10 +227,6 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items); -unsigned long radix_tree_next_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan); -unsigned long radix_tree_prev_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); void radix_tree_init(void); diff --git a/include/linux/sched.h b/include/linux/sched.h index ccd0c6f..91fe6a3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -59,6 +59,10 @@ struct sched_param { #define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */ +#define VMACACHE_BITS 2 +#define VMACACHE_SIZE (1U << VMACACHE_BITS) +#define VMACACHE_MASK (VMACACHE_SIZE - 1) + /* * Extended scheduling parameters data structure. * @@ -1228,6 +1232,9 @@ struct task_struct { #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif + /* per-thread vma caching */ + u32 vmacache_seqnum; + struct vm_area_struct *vmacache[VMACACHE_SIZE]; #if defined(SPLIT_RSS_COUNTING) struct task_rss_stat rss_stat; #endif @@ -1688,7 +1695,7 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk) } -static int pid_alive(const struct task_struct *p); +static inline int pid_alive(const struct task_struct *p); static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) { pid_t pid = 0; @@ -1869,11 +1876,13 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) -/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */ +/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags + * __GFP_FS is also cleared as it implies __GFP_IO. + */ static inline gfp_t memalloc_noio_flags(gfp_t flags) { if (unlikely(current->flags & PF_MEMALLOC_NOIO)) - flags &= ~__GFP_IO; + flags &= ~(__GFP_IO | __GFP_FS); return flags; } diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 535f158..8cf3503 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -164,8 +164,6 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s) static inline unsigned raw_seqcount_begin(const seqcount_t *s) { unsigned ret = ACCESS_ONCE(s->sequence); - - seqcount_lockdep_reader_access(s); smp_rmb(); return ret & ~1; } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 9d55438..4d1771c 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -51,6 +51,7 @@ extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern bool shmem_mapping(struct address_space *mapping); extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6b84663..5ab5f97 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -661,6 +661,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); +struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) @@ -2458,6 +2459,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); unsigned int skb_gso_transport_seglen(const struct sk_buff *skb); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); +struct sk_buff *skb_vlan_untag(struct sk_buff *skb); struct skb_checksum_ops { __wsum (*update)(const void *mem, int len, __wsum wsum); diff --git a/include/linux/string.h b/include/linux/string.h index ac889c5..0ed878d 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -129,7 +129,7 @@ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4); #endif extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, - const void *from, size_t available); + const void *from, size_t available); /** * strstarts - does @str start with @prefix? @@ -141,7 +141,8 @@ static inline bool strstarts(const char *str, const char *prefix) return strncmp(str, prefix, strlen(prefix)) == 0; } -extern size_t memweight(const void *ptr, size_t bytes); +size_t memweight(const void *ptr, size_t bytes); +void memzero_explicit(void *s, size_t count); /** * kbasename - return the last part of a pathname. diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index b05963f..f5bfb1a 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -32,6 +32,7 @@ struct svc_xprt_class { struct svc_xprt_ops *xcl_ops; struct list_head xcl_list; u32 xcl_max_payload; + int xcl_ident; }; /* diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 8097b9d..51009d2 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -340,6 +340,7 @@ int xs_swapper(struct rpc_xprt *xprt, int enable); #define XPRT_CONNECTION_ABORT (7) #define XPRT_CONNECTION_CLOSE (8) #define XPRT_CONGESTED (9) +#define XPRT_CONNECTION_REUSE (10) static inline void xprt_set_connected(struct rpc_xprt *xprt) { diff --git a/include/linux/swap.h b/include/linux/swap.h index 46ba0c6..241bf09 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -214,8 +214,9 @@ struct percpu_cluster { struct swap_info_struct { unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ + struct plist_node list; /* entry in swap_active_head */ + struct plist_node avail_list; /* entry in swap_avail_head */ signed char type; /* strange name for an index */ - signed char next; /* next type on the swap list */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ @@ -255,11 +256,6 @@ struct swap_info_struct { struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */ }; -struct swap_list_t { - int head; /* head of priority-ordered swapfile list */ - int next; /* swapfile to be used next */ -}; - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; @@ -272,12 +268,14 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ -extern void __lru_cache_add(struct page *); extern void lru_cache_add(struct page *); +extern void lru_cache_add_anon(struct page *page); +extern void lru_cache_add_file(struct page *page); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); +extern void init_page_accessed(struct page *page); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); @@ -287,22 +285,6 @@ extern void swap_setup(void); extern void add_page_to_unevictable_list(struct page *page); -/** - * lru_cache_add: add a page to the page lists - * @page: the page to add - */ -static inline void lru_cache_add_anon(struct page *page) -{ - ClearPageActive(page); - __lru_cache_add(page); -} - -static inline void lru_cache_add_file(struct page *page) -{ - ClearPageActive(page); - __lru_cache_add(page); -} - /* linux/mm/vmscan.c */ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); @@ -460,7 +442,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) #define free_page_and_swap_cache(page) \ page_cache_release(page) #define free_pages_and_swap_cache(pages, nr) \ - release_pages((pages), (nr), 0); + release_pages((pages), (nr), false); static inline void show_swap_cache_info(void) { diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index e282624..388293a 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -6,7 +6,7 @@ * want to expose them to the dozens of source files that include swap.h */ extern spinlock_t swap_lock; -extern struct swap_list_t swap_list; +extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; extern int try_to_unuse(unsigned int, bool, unsigned long); diff --git a/include/linux/time.h b/include/linux/time.h index d5d229b..7d532a3 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -173,6 +173,19 @@ extern void getboottime(struct timespec *ts); extern void monotonic_to_bootbased(struct timespec *ts); extern void get_monotonic_boottime(struct timespec *ts); +static inline bool timeval_valid(const struct timeval *tv) +{ + /* Dates before 1970 are bogus */ + if (tv->tv_sec < 0) + return false; + + /* Can't have more microseconds then a second */ + if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) + return false; + + return true; +} + extern struct timespec timespec_trunc(struct timespec t, unsigned gran); extern int timekeeping_valid_for_hres(void); extern u64 timekeeping_max_deferment(void); diff --git a/include/linux/tpm.h b/include/linux/tpm.h index fff1d09..8350c53 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -39,6 +39,9 @@ struct tpm_class_ops { int (*send) (struct tpm_chip *chip, u8 *buf, size_t len); void (*cancel) (struct tpm_chip *chip); u8 (*status) (struct tpm_chip *chip); + bool (*update_timeouts)(struct tpm_chip *chip, + unsigned long *timeout_cap); + }; #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) diff --git a/include/linux/usb.h b/include/linux/usb.h index 7f6eb85..49466be 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -206,6 +206,32 @@ void usb_put_intf(struct usb_interface *intf); #define USB_MAXINTERFACES 32 #define USB_MAXIADS (USB_MAXINTERFACES/2) +/* + * USB Resume Timer: Every Host controller driver should drive the resume + * signalling on the bus for the amount of time defined by this macro. + * + * That way we will have a 'stable' behavior among all HCDs supported by Linux. + * + * Note that the USB Specification states we should drive resume for *at least* + * 20 ms, but it doesn't give an upper bound. This creates two possible + * situations which we want to avoid: + * + * (a) sometimes an msleep(20) might expire slightly before 20 ms, which causes + * us to fail USB Electrical Tests, thus failing Certification + * + * (b) Some (many) devices actually need more than 20 ms of resume signalling, + * and while we can argue that's against the USB Specification, we don't have + * control over which devices a certification laboratory will be using for + * certification. If CertLab uses a device which was tested against Windows and + * that happens to have relaxed resume signalling rules, we might fall into + * situations where we fail interoperability and electrical tests. + * + * In order to avoid both conditions, we're using a 40 ms resume timeout, which + * should cope with both LPJ calibration errors and devices not following every + * detail of the USB Specification. + */ +#define USB_RESUME_TIMEOUT 40 /* ms */ + /** * struct usb_interface_cache - long-term representation of a device interface * @num_altsetting: number of altsettings defined. diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index efe8d8a..e34bce3 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -447,6 +447,7 @@ extern const struct dev_pm_ops usb_hcd_pci_pm_ops; #endif /* CONFIG_PCI */ /* pci-ish (pdev null is ok) buffer alloc/mapping support */ +void usb_init_pool_max(void); int hcd_buffer_create(struct usb_hcd *hcd); void hcd_buffer_destroy(struct usb_hcd *hcd); diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 52f944d..8b96ae2 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -30,4 +30,10 @@ descriptor */ #define USB_QUIRK_DELAY_INIT 0x00000040 +/* device generates spurious wakeup, ignore remote wakeup capability */ +#define USB_QUIRK_IGNORE_REMOTE_WAKEUP 0x00000200 + +/* device can't handle device_qualifier descriptor requests */ +#define USB_QUIRK_DEVICE_QUALIFIER 0x00000100 + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 4836ba3..e92abf9 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -17,6 +17,10 @@ struct uid_gid_map { /* 64 bytes -- 1 cache line */ } extent[UID_GID_MAP_MAX_EXTENTS]; }; +#define USERNS_SETGROUPS_ALLOWED 1UL + +#define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED + struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; @@ -27,6 +31,7 @@ struct user_namespace { kuid_t owner; kgid_t group; unsigned int proc_inum; + unsigned long flags; /* Register of per-UID persistent keyrings for this namespace */ #ifdef CONFIG_PERSISTENT_KEYRINGS @@ -63,6 +68,9 @@ extern struct seq_operations proc_projid_seq_operations; extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *); +extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *); +extern int proc_setgroups_show(struct seq_file *m, void *v); +extern bool userns_may_setgroups(const struct user_namespace *ns); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) @@ -87,6 +95,10 @@ static inline void put_user_ns(struct user_namespace *ns) { } +static inline bool userns_may_setgroups(const struct user_namespace *ns) +{ + return true; +} #endif #endif /* _LINUX_USER_H */ diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index 502073a..b483abd 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -64,6 +64,7 @@ int vga_switcheroo_get_client_state(struct pci_dev *dev); void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic); int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain); +void vga_switcheroo_fini_domain_pm_ops(struct device *dev); int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain); #else @@ -82,6 +83,7 @@ static inline int vga_switcheroo_get_client_state(struct pci_dev *dev) { return static inline void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic) {} static inline int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; } +static inline void vga_switcheroo_fini_domain_pm_ops(struct device *dev) {} static inline int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; } #endif diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 704f4f6..bc9d2c2 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -71,7 +71,8 @@ enum { /* data contains off-queue information when !WORK_STRUCT_PWQ */ WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, - WORK_OFFQ_CANCELING = (1 << WORK_OFFQ_FLAG_BASE), + __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE, + WORK_OFFQ_CANCELING = (1 << __WORK_OFFQ_CANCELING), /* * When a work item is off queue, its high bits point to the last @@ -452,7 +453,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \ 1, (name)) #define create_singlethread_workqueue(name) \ - alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, (name)) + alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index bef53ce..b10682c 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -329,6 +329,9 @@ struct v4l2_fh; * @retry_start_streaming: start_streaming() was called, but there were not enough * buffers queued. If set, then retry calling start_streaming when * queuing a new buffer. + * @waiting_for_buffers: used in poll() to check if vb2 is still waiting for + * buffers. Only set for capture queues if qbuf has not yet been + * called since poll() needs to return POLLERR in that situation. * @fileio: file io emulator internal data, used only if emulator is active */ struct vb2_queue { @@ -362,6 +365,7 @@ struct vb2_queue { unsigned int streaming:1; unsigned int retry_start_streaming:1; + unsigned int waiting_for_buffers:1; struct vb2_fileio_data *fileio; }; diff --git a/include/net/dst.h b/include/net/dst.h index 77eb53f..9090328 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -466,6 +466,7 @@ void dst_init(void); /* Flags for xfrm_lookup flags argument. */ enum { XFRM_LOOKUP_ICMP = 1 << 0, + XFRM_LOOKUP_QUEUE = 1 << 1, }; struct flowi; @@ -476,7 +477,16 @@ static inline struct dst_entry *xfrm_lookup(struct net *net, int flags) { return dst_orig; -} +} + +static inline struct dst_entry *xfrm_lookup_route(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, + struct sock *sk, + int flags) +{ + return dst_orig; +} static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) { @@ -488,6 +498,10 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, struct sock *sk, int flags); +struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, struct sock *sk, + int flags); + /* skb attached with this dst needs transformation if dst->xfrm is valid */ static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) { diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c55aeed..cf92728 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -62,6 +62,7 @@ struct inet_connection_sock_af_ops { void (*addr2sockaddr)(struct sock *sk, struct sockaddr *); int (*bind_conflict)(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); + void (*mtu_reduced)(struct sock *sk); }; /** inet_connection_sock - INET connection oriented sock diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 058271b..823ec7b 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -41,14 +41,13 @@ struct inet_peer { struct rcu_head gc_rcu; }; /* - * Once inet_peer is queued for deletion (refcnt == -1), following fields - * are not available: rid, ip_id_count + * Once inet_peer is queued for deletion (refcnt == -1), following field + * is not available: rid * We can share memory with rcu_head to help keep inet_peer small. */ union { struct { atomic_t rid; /* Frag reception counter */ - atomic_t ip_id_count; /* IP ID for the next packet */ }; struct rcu_head rcu; struct inet_peer *gc_next; @@ -165,7 +164,7 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout); void inetpeer_invalidate_tree(struct inet_peer_base *); /* - * temporary check to make sure we dont access rid, ip_id_count, tcp_ts, + * temporary check to make sure we dont access rid, tcp_ts, * tcp_ts_stamp if no refcount is taken on inet_peer */ static inline void inet_peer_refcheck(const struct inet_peer *p) @@ -173,13 +172,4 @@ static inline void inet_peer_refcheck(const struct inet_peer *p) WARN_ON_ONCE(atomic_read(&p->refcnt) <= 0); } - -/* can be called with or without local BH being disabled */ -static inline int inet_getid(struct inet_peer *p, int more) -{ - more++; - inet_peer_refcheck(p); - return atomic_add_return(more, &p->ip_id_count) - more; -} - #endif /* _NET_INETPEER_H */ diff --git a/include/net/ip.h b/include/net/ip.h index 23be0fd..5128fa7 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -38,11 +38,12 @@ struct inet_skb_parm { struct ip_options opt; /* Compiled IP options */ unsigned char flags; -#define IPSKB_FORWARDED 1 -#define IPSKB_XFRM_TUNNEL_SIZE 2 -#define IPSKB_XFRM_TRANSFORMED 4 -#define IPSKB_FRAG_COMPLETE 8 -#define IPSKB_REROUTED 16 +#define IPSKB_FORWARDED BIT(0) +#define IPSKB_XFRM_TUNNEL_SIZE BIT(1) +#define IPSKB_XFRM_TRANSFORMED BIT(2) +#define IPSKB_FRAG_COMPLETE BIT(3) +#define IPSKB_REROUTED BIT(4) +#define IPSKB_DOREDIRECT BIT(5) u16 frag_max_size; }; @@ -174,7 +175,7 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg) return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0; } -void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, +void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len); @@ -297,9 +298,10 @@ static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb) } } -void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more); +u32 ip_idents_reserve(u32 hash, int segs); +void __ip_select_ident(struct iphdr *iph, int segs); -static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk) +static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs) { struct iphdr *iph = ip_hdr(skb); @@ -309,24 +311,20 @@ static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, s * does not change, they drop every other packet in * a TCP stream using header compression. */ - iph->id = (sk && inet_sk(sk)->inet_daddr) ? - htons(inet_sk(sk)->inet_id++) : 0; - } else - __ip_select_ident(iph, dst, 0); -} - -static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk, int more) -{ - struct iphdr *iph = ip_hdr(skb); - - if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) { if (sk && inet_sk(sk)->inet_daddr) { iph->id = htons(inet_sk(sk)->inet_id); - inet_sk(sk)->inet_id += 1 + more; - } else + inet_sk(sk)->inet_id += segs; + } else { iph->id = 0; - } else - __ip_select_ident(iph, dst, more); + } + } else { + __ip_select_ident(iph, segs); + } +} + +static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk) +{ + ip_select_ident_segs(skb, sk, 1); } /* @@ -409,22 +407,6 @@ static __inline__ void inet_reset_saddr(struct sock *sk) #endif -static inline int sk_mc_loop(struct sock *sk) -{ - if (!sk) - return 1; - switch (sk->sk_family) { - case AF_INET: - return inet_sk(sk)->mc_loop; -#if IS_ENABLED(CONFIG_IPV6) - case AF_INET6: - return inet6_sk(sk)->mc_loop; -#endif - } - WARN_ON(1); - return 1; -} - bool ip_call_ra_chain(struct sk_buff *skb); /* diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 2e74c6c..ee2d53a 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -168,7 +168,8 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); static inline int ip6_skb_dst_mtu(struct sk_buff *skb) { - struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; + struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? + inet6_sk(skb->sk) : NULL; return (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) ? skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index e77c104..7b9ec58 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -40,6 +40,7 @@ struct ip_tunnel_prl_entry { struct ip_tunnel_dst { struct dst_entry __rcu *dst; + __be32 saddr; }; struct ip_tunnel { diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 4f541f1..a60948d 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -660,7 +660,7 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt); +void ipv6_proxy_select_ident(struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 80f500a..57c2da9 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -47,6 +47,7 @@ struct netns_ipv4 { struct inet_peer_base *peers; struct tcpm_hash_bucket *tcp_metrics_hash; unsigned int tcp_metrics_hash_log; + struct sock * __percpu *tcp_sk; struct netns_frags frags; #ifdef CONFIG_NETFILTER struct xt_table *iptable_filter; diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index 3573a81..8ba379f 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -31,6 +31,7 @@ struct netns_sctp { struct list_head addr_waitq; struct timer_list addr_wq_timer; struct list_head auto_asconf_splist; + /* Lock that protects both addr_waitq and auto_asconf_splist */ spinlock_t addr_wq_lock; /* Lock that protects the local_addr_list writers */ diff --git a/include/net/regulatory.h b/include/net/regulatory.h index b07cdc9..f103f30 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -160,7 +160,7 @@ struct ieee80211_reg_rule { struct ieee80211_regdomain { struct rcu_head rcu_head; u32 n_reg_rules; - char alpha2[2]; + char alpha2[3]; enum nl80211_dfs_regions dfs_region; struct ieee80211_reg_rule reg_rules[]; }; diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h index 4b7cd69..cfcbc3f 100644 --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -115,7 +115,7 @@ typedef enum { * analysis of the state functions, but in reality just taken from * thin air in the hopes othat we don't trigger a kernel panic. */ -#define SCTP_MAX_NUM_COMMANDS 14 +#define SCTP_MAX_NUM_COMMANDS 20 typedef union { __s32 i32; diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a3353f4..ba41e01 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -433,6 +433,11 @@ static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_associat asoc->pmtu_pending = 0; } +static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk) +{ + return !list_empty(&chunk->list); +} + /* Walk through a list of TLV parameters. Don't trust the * individual parameter lengths and instead depend on * the chunk length to indicate when to stop. Make sure diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 7f4eeb3..72a31db 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -248,9 +248,9 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *, int, __be16); struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc, union sctp_addr *addr); -int sctp_verify_asconf(const struct sctp_association *asoc, - struct sctp_paramhdr *param_hdr, void *chunk_end, - struct sctp_paramhdr **errp); +bool sctp_verify_asconf(const struct sctp_association *asoc, + struct sctp_chunk *chunk, bool addr_param_needed, + struct sctp_paramhdr **errp); struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, struct sctp_chunk *asconf); int sctp_process_asconf_ack(struct sctp_association *asoc, diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 0dfcc92..2c2d388 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -219,6 +219,10 @@ struct sctp_sock { atomic_t pd_mode; /* Receive to here while partial delivery is in effect. */ struct sk_buff_head pd_lobby; + + /* These must be the last fields, as they will skipped on copies, + * like on accept and peeloff operations + */ struct list_head auto_asconf_list; int do_auto_asconf; }; diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index f257486..3f36d45 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -3,8 +3,6 @@ #include -__u32 secure_ip_id(__be32 daddr); -__u32 secure_ipv6_id(const __be32 daddr[4]); u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); diff --git a/include/net/sock.h b/include/net/sock.h index 2f7bc43..0c79a74 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -969,7 +969,6 @@ struct proto { struct sk_buff *skb); void (*release_cb)(struct sock *sk); - void (*mtu_reduced)(struct sock *sk); /* Keeping track of sk's, looking them up, and port selection methods. */ void (*hash)(struct sock *sk); @@ -1816,6 +1815,8 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie); +bool sk_mc_loop(struct sock *sk); + static inline bool sk_can_gso(const struct sock *sk) { return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type); diff --git a/include/net/tcp.h b/include/net/tcp.h index 743acce..1f0d847 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -453,6 +453,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); +void tcp_v4_mtu_reduced(struct sock *sk); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, @@ -720,8 +721,10 @@ struct tcp_skb_cb { #define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ #define TCPCB_LOST 0x04 /* SKB is lost */ #define TCPCB_TAGBITS 0x07 /* All tag bits */ +#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp) */ #define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ -#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS) +#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \ + TCPCB_REPAIRED) __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ /* 1 byte hole */ diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index b4f1eff..409fafb 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -149,6 +149,7 @@ struct scsi_device { unsigned skip_ms_page_8:1; /* do not use MODE SENSE page 0x08 */ unsigned skip_ms_page_3f:1; /* do not use MODE SENSE page 0x3f */ unsigned skip_vpd_pages:1; /* do not read VPD pages */ + unsigned try_vpd_pages:1; /* attempt to read VPD pages */ unsigned use_192_bytes_for_3f:1; /* ask for 192 bytes from page 0x3f */ unsigned no_start_on_add:1; /* do not issue start on add */ unsigned allow_restart:1; /* issue START_UNIT in error handler */ diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h index 447d2d7..183eaab 100644 --- a/include/scsi/scsi_devinfo.h +++ b/include/scsi/scsi_devinfo.h @@ -32,4 +32,9 @@ #define BLIST_ATTACH_PQ3 0x1000000 /* Scan: Attach to PQ3 devices */ #define BLIST_NO_DIF 0x2000000 /* Disable T10 PI (DIF) */ #define BLIST_SKIP_VPD_PAGES 0x4000000 /* Ignore SBC-3 VPD pages */ +#define BLIST_SCSI3LUN 0x8000000 /* Scan more than 256 LUNs + for sequential scan */ +#define BLIST_TRY_VPD_PAGES 0x10000000 /* Attempt to read VPD pages */ +#define BLIST_NO_RSOC 0x20000000 /* don't try to issue RSOC */ + #endif diff --git a/include/sound/ak4113.h b/include/sound/ak4113.h index 2609048..3a34f6e 100644 --- a/include/sound/ak4113.h +++ b/include/sound/ak4113.h @@ -286,7 +286,7 @@ struct ak4113 { ak4113_write_t *write; ak4113_read_t *read; void *private_data; - unsigned int init:1; + atomic_t wq_processing; spinlock_t lock; unsigned char regmap[AK4113_WRITABLE_REGS]; struct snd_kcontrol *kctls[AK4113_CONTROLS]; diff --git a/include/sound/ak4114.h b/include/sound/ak4114.h index 52f02a6..069299a 100644 --- a/include/sound/ak4114.h +++ b/include/sound/ak4114.h @@ -168,7 +168,7 @@ struct ak4114 { ak4114_write_t * write; ak4114_read_t * read; void * private_data; - unsigned int init: 1; + atomic_t wq_processing; spinlock_t lock; unsigned char regmap[6]; unsigned char txcsb[5]; diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h index dfb42ca..8898cde 100644 --- a/include/sound/emu10k1.h +++ b/include/sound/emu10k1.h @@ -41,7 +41,8 @@ #define EMUPAGESIZE 4096 #define MAXREQVOICES 8 -#define MAXPAGES 8192 +#define MAXPAGES0 4096 /* 32 bit mode */ +#define MAXPAGES1 8192 /* 31 bit mode */ #define RESERVED 0 #define NUM_MIDI 16 #define NUM_G 64 /* use all channels */ @@ -50,8 +51,7 @@ /* FIXME? - according to the OSS driver the EMU10K1 needs a 29 bit DMA mask */ #define EMU10K1_DMA_MASK 0x7fffffffUL /* 31bit */ -#define AUDIGY_DMA_MASK 0x7fffffffUL /* 31bit FIXME - 32 should work? */ - /* See ALSA bug #1276 - rlrevell */ +#define AUDIGY_DMA_MASK 0xffffffffUL /* 32bit mode */ #define TMEMSIZE 256*1024 #define TMEMSIZEREG 4 @@ -468,8 +468,11 @@ #define MAPB 0x0d /* Cache map B */ -#define MAP_PTE_MASK 0xffffe000 /* The 19 MSBs of the PTE indexed by the PTI */ -#define MAP_PTI_MASK 0x00001fff /* The 13 bit index to one of the 8192 PTE dwords */ +#define MAP_PTE_MASK0 0xfffff000 /* The 20 MSBs of the PTE indexed by the PTI */ +#define MAP_PTI_MASK0 0x00000fff /* The 12 bit index to one of the 4096 PTE dwords */ + +#define MAP_PTE_MASK1 0xffffe000 /* The 19 MSBs of the PTE indexed by the PTI */ +#define MAP_PTI_MASK1 0x00001fff /* The 13 bit index to one of the 8192 PTE dwords */ /* 0x0e, 0x0f: Not used */ @@ -1706,6 +1709,7 @@ struct snd_emu10k1 { unsigned short model; /* subsystem id */ unsigned int card_type; /* EMU10K1_CARD_* */ unsigned int ecard_ctrl; /* ecard control bits */ + unsigned int address_mode; /* address mode */ unsigned long dma_mask; /* PCI DMA mask */ unsigned int delay_pcm_irq; /* in samples */ int max_cache_pages; /* max memory size / PAGE_SIZE */ diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index 6e89ef6..13412ab 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -302,7 +302,7 @@ struct device; .access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | SNDRV_CTL_ELEM_ACCESS_READWRITE,\ .tlv.p = (tlv_array), \ .get = snd_soc_dapm_get_volsw, .put = snd_soc_dapm_put_volsw, \ - .private_value = SOC_SINGLE_VALUE(reg, shift, max, invert, 0) } + .private_value = SOC_SINGLE_VALUE(reg, shift, max, invert, 1) } #define SOC_DAPM_SINGLE_TLV_VIRT(xname, max, tlv_array) \ SOC_DAPM_SINGLE(xname, SND_SOC_NOPM, 0, max, 0, tlv_array) #define SOC_DAPM_ENUM(xname, xenum) \ diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h index 2883a7a..98f2ade 100644 --- a/include/sound/soc-dpcm.h +++ b/include/sound/soc-dpcm.h @@ -102,6 +102,8 @@ struct snd_soc_dpcm_runtime { /* state and update */ enum snd_soc_dpcm_update runtime_update; enum snd_soc_dpcm_state state; + + int trigger_pending; /* trigger cmd + 1 if pending, 0 if not */ }; /* can this BE stop and free */ diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 1772fad..e4b9e01 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -407,7 +407,7 @@ struct t10_reservation { /* Activate Persistence across Target Power Loss enabled * for SCSI device */ int pr_aptpl_active; -#define PR_APTPL_BUF_LEN 8192 +#define PR_APTPL_BUF_LEN 262144 u32 pr_generation; spinlock_t registration_lock; spinlock_t aptpl_reg_lock; @@ -513,7 +513,7 @@ struct se_cmd { sense_reason_t (*execute_cmd)(struct se_cmd *); sense_reason_t (*execute_rw)(struct se_cmd *, struct scatterlist *, u32, enum dma_data_direction); - sense_reason_t (*transport_complete_callback)(struct se_cmd *); + sense_reason_t (*transport_complete_callback)(struct se_cmd *, bool); unsigned char *t_task_cdb; unsigned char __t_task_cdb[TCM_MAX_COMMAND_SIZE]; diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index 06f544e..c6814b9 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -5,6 +5,7 @@ #define _TRACE_COMPACTION_H #include +#include #include #include @@ -47,10 +48,11 @@ DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages, TRACE_EVENT(mm_compaction_migratepages, - TP_PROTO(unsigned long nr_migrated, - unsigned long nr_failed), + TP_PROTO(unsigned long nr_all, + int migrate_rc, + struct list_head *migratepages), - TP_ARGS(nr_migrated, nr_failed), + TP_ARGS(nr_all, migrate_rc, migratepages), TP_STRUCT__entry( __field(unsigned long, nr_migrated) @@ -58,7 +60,22 @@ TRACE_EVENT(mm_compaction_migratepages, ), TP_fast_assign( - __entry->nr_migrated = nr_migrated; + unsigned long nr_failed = 0; + struct list_head *page_lru; + + /* + * migrate_pages() returns either a non-negative number + * with the number of pages that failed migration, or an + * error code, in which case we need to count the remaining + * pages manually + */ + if (migrate_rc >= 0) + nr_failed = migrate_rc; + else + list_for_each(page_lru, migratepages) + nr_failed++; + + __entry->nr_migrated = nr_all - nr_failed; __entry->nr_failed = nr_failed; ), diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index aece134..4ad10ba 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -268,11 +268,11 @@ TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, - int alloc_migratetype, int fallback_migratetype, int new_migratetype), + int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, - alloc_migratetype, fallback_migratetype, new_migratetype), + alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( struct page *, page ) @@ -289,7 +289,8 @@ TRACE_EVENT(mm_page_alloc_extfrag, __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; - __entry->change_ownership = (new_migratetype == alloc_migratetype); + __entry->change_ownership = (alloc_migratetype == + get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h index 1c9fabd..ce0803b 100644 --- a/include/trace/events/pagemap.h +++ b/include/trace/events/pagemap.h @@ -28,12 +28,10 @@ TRACE_EVENT(mm_lru_insertion, TP_PROTO( struct page *page, - unsigned long pfn, - int lru, - unsigned long flags + int lru ), - TP_ARGS(page, pfn, lru, flags), + TP_ARGS(page, lru), TP_STRUCT__entry( __field(struct page *, page ) @@ -44,9 +42,9 @@ TRACE_EVENT(mm_lru_insertion, TP_fast_assign( __entry->page = page; - __entry->pfn = pfn; + __entry->pfn = page_to_pfn(page); __entry->lru = lru; - __entry->flags = flags; + __entry->flags = trace_pagemap_flags(page); ), /* Flag format is based on page-types.c formatting for pagemap */ @@ -64,9 +62,9 @@ TRACE_EVENT(mm_lru_insertion, TRACE_EVENT(mm_lru_activate, - TP_PROTO(struct page *page, unsigned long pfn), + TP_PROTO(struct page *page), - TP_ARGS(page, pfn), + TP_ARGS(page), TP_STRUCT__entry( __field(struct page *, page ) @@ -75,7 +73,7 @@ TRACE_EVENT(mm_lru_activate, TP_fast_assign( __entry->page = page; - __entry->pfn = pfn; + __entry->pfn = page_to_pfn(page); ), /* Flag format is based on page-types.c formatting for pagemap */ diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 67e1bbf..dc7bb01 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -100,7 +100,7 @@ static inline long __trace_sched_switch_state(struct task_struct *p) /* * For all intents and purposes a preempted task is a running task. */ - if (task_preempt_count(p) & PREEMPT_ACTIVE) + if (preempt_count() & PREEMPT_ACTIVE) state = TASK_RUNNING | TASK_STATE_MAX; #endif diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 87792a5..33b7395 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -29,7 +29,7 @@ #define __VMWGFX_DRM_H__ #ifndef __KERNEL__ -#include +#include #endif #define DRM_VMW_MAX_SURFACE_FACES 6 diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index e9a1d2d..4c399ae 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -149,7 +149,7 @@ struct in6_flowlabel_req { /* * IPV6 socket options */ - +#if __UAPI_DEF_IPV6_OPTIONS #define IPV6_ADDRFORM 1 #define IPV6_2292PKTINFO 2 #define IPV6_2292HOPOPTS 3 @@ -192,6 +192,7 @@ struct in6_flowlabel_req { #define IPV6_IPSEC_POLICY 34 #define IPV6_XFRM_POLICY 35 +#endif /* * Multicast: diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h index c140620..e28807a 100644 --- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -69,6 +69,7 @@ #define __UAPI_DEF_SOCKADDR_IN6 0 #define __UAPI_DEF_IPV6_MREQ 0 #define __UAPI_DEF_IPPROTO_V6 0 +#define __UAPI_DEF_IPV6_OPTIONS 0 #else @@ -82,6 +83,7 @@ #define __UAPI_DEF_SOCKADDR_IN6 1 #define __UAPI_DEF_IPV6_MREQ 1 #define __UAPI_DEF_IPPROTO_V6 1 +#define __UAPI_DEF_IPV6_OPTIONS 1 #endif /* _NETINET_IN_H */ @@ -103,6 +105,7 @@ #define __UAPI_DEF_SOCKADDR_IN6 1 #define __UAPI_DEF_IPV6_MREQ 1 #define __UAPI_DEF_IPPROTO_V6 1 +#define __UAPI_DEF_IPV6_OPTIONS 1 /* Definitions for xattr.h */ #define __UAPI_DEF_XATTR 1 diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h index 5dda450..2ec9fbc 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -6,6 +6,8 @@ #define XT_BPF_MAX_NUM_INSTR 64 +struct sk_filter; + struct xt_bpf_info { __u16 bpf_program_num_elem; struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR]; diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 30db069..788c5aa 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -319,6 +319,7 @@ #define PCI_MSIX_PBA 8 /* Pending Bit Array offset */ #define PCI_MSIX_PBA_BIR 0x00000007 /* BAR index */ #define PCI_MSIX_PBA_OFFSET 0xfffffff8 /* Offset into specified BAR */ +#define PCI_MSIX_FLAGS_BIRMASK PCI_MSIX_PBA_BIR /* deprecated */ #define PCI_CAP_MSIX_SIZEOF 12 /* size of MSIX registers */ /* MSI-X Table entry format */ diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h index 29e9c7a..f279394 100644 --- a/include/uapi/linux/usb/functionfs.h +++ b/include/uapi/linux/usb/functionfs.h @@ -27,24 +27,18 @@ struct usb_endpoint_descriptor_no_audio { __u8 bInterval; } __attribute__((packed)); -/* Legacy format, deprecated as of 3.14. */ -struct usb_functionfs_descs_head { - __le32 magic; - __le32 length; - __le32 fs_count; - __le32 hs_count; -} __attribute__((packed, deprecated)); /* * All numbers must be in little endian order. */ +/* Legacy format, deprecated as of 3.14. */ struct usb_functionfs_descs_head { __le32 magic; __le32 length; __le32 fs_count; __le32 hs_count; -} __attribute__((packed)); +} __attribute__((packed, deprecated)); /* * Descriptors format: diff --git a/include/uapi/linux/usbdevice_fs.h b/include/uapi/linux/usbdevice_fs.h index 0c65e4b..ef29266 100644 --- a/include/uapi/linux/usbdevice_fs.h +++ b/include/uapi/linux/usbdevice_fs.h @@ -125,11 +125,12 @@ struct usbdevfs_hub_portinfo { char port [127]; /* e.g. port 3 connects to device 27 */ }; -/* Device capability flags */ +/* System and bus capability flags */ #define USBDEVFS_CAP_ZERO_PACKET 0x01 #define USBDEVFS_CAP_BULK_CONTINUATION 0x02 #define USBDEVFS_CAP_NO_PACKET_SIZE_LIM 0x04 #define USBDEVFS_CAP_BULK_SCATTER_GATHER 0x08 +#define USBDEVFS_CAP_REAP_AFTER_DISCONNECT 0x10 /* USBDEVFS_DISCONNECT_CLAIM flags & struct */ diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h index c38355c..1590c49 100644 --- a/include/uapi/linux/xattr.h +++ b/include/uapi/linux/xattr.h @@ -13,7 +13,7 @@ #ifndef _UAPI_LINUX_XATTR_H #define _UAPI_LINUX_XATTR_H -#ifdef __UAPI_DEF_XATTR +#if __UAPI_DEF_XATTR #define __USE_KERNEL_XATTR_DEFS #define XATTR_CREATE 0x1 /* set value, fail if attr already exists */ diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h index 99b80ab..3066718 100644 --- a/include/uapi/rdma/rdma_user_cm.h +++ b/include/uapi/rdma/rdma_user_cm.h @@ -34,6 +34,7 @@ #define RDMA_USER_CM_H #include +#include #include #include #include diff --git a/include/xen/events.h b/include/xen/events.h index c9c85cf..5d84cd0 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -14,7 +14,7 @@ int bind_evtchn_to_irqhandler(unsigned int evtchn, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id); -int bind_virq_to_irq(unsigned int virq, unsigned int cpu); +int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu); int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, irq_handler_t handler, unsigned long irqflags, const char *devname, diff --git a/init/Kconfig b/init/Kconfig index 93c5ef0..8b9521a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1389,6 +1389,7 @@ config FUTEX config HAVE_FUTEX_CMPXCHG bool + depends on FUTEX help Architectures should select this if futex_atomic_cmpxchg_inatomic() is implemented and always working. This removes a couple of runtime diff --git a/init/main.c b/init/main.c index 9c7fd4c..008edce 100644 --- a/init/main.c +++ b/init/main.c @@ -617,6 +617,10 @@ asmlinkage void __init start_kernel(void) if (efi_enabled(EFI_RUNTIME_SERVICES)) efi_enter_virtual_mode(); #endif +#ifdef CONFIG_X86_ESPFIX64 + /* Should be run before the first non-init thread is created */ + init_espfix_bsp(); +#endif thread_info_cache_init(); cred_init(); fork_init(totalram_pages); @@ -639,6 +643,7 @@ asmlinkage void __init start_kernel(void) check_bugs(); + acpi_subsystem_init(); sfi_init_late(); if (efi_enabled(EFI_RUNTIME_SERVICES)) { diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 1702864..cadddc8 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -123,7 +123,6 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; - size_t lenp_bef = *lenp; int oldval; int rc; @@ -133,7 +132,7 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos); - if (write && !rc && lenp_bef == *lenp) { + if (write && !rc) { int newval = *((int *)(ipc_table.data)); /* * The file "auto_msgmni" has correctly been set. diff --git a/ipc/mqueue.c b/ipc/mqueue.c index c3b3117..9699d3f 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -143,7 +143,6 @@ static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info) if (!leaf) return -ENOMEM; INIT_LIST_HEAD(&leaf->msg_list); - info->qsize += sizeof(*leaf); } leaf->priority = msg->m_type; rb_link_node(&leaf->rb_node, parent, p); @@ -188,7 +187,6 @@ try_again: "lazy leaf delete!\n"); rb_erase(&leaf->rb_node, &info->msg_tree); if (info->node_cache) { - info->qsize -= sizeof(*leaf); kfree(leaf); } else { info->node_cache = leaf; @@ -201,7 +199,6 @@ try_again: if (list_empty(&leaf->msg_list)) { rb_erase(&leaf->rb_node, &info->msg_tree); if (info->node_cache) { - info->qsize -= sizeof(*leaf); kfree(leaf); } else { info->node_cache = leaf; @@ -1026,7 +1023,6 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, /* Save our speculative allocation into the cache */ INIT_LIST_HEAD(&new_leaf->msg_list); info->node_cache = new_leaf; - info->qsize += sizeof(*new_leaf); new_leaf = NULL; } else { kfree(new_leaf); @@ -1133,7 +1129,6 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr, /* Save our speculative allocation into the cache */ INIT_LIST_HEAD(&new_leaf->msg_list); info->node_cache = new_leaf; - info->qsize += sizeof(*new_leaf); } else { kfree(new_leaf); } diff --git a/ipc/sem.c b/ipc/sem.c index bee5554..e53c96f 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -253,6 +253,16 @@ static void sem_rcu_free(struct rcu_head *head) } /* + * spin_unlock_wait() and !spin_is_locked() are not memory barriers, they + * are only control barriers. + * The code must pair with spin_unlock(&sem->lock) or + * spin_unlock(&sem_perm.lock), thus just the control barrier is insufficient. + * + * smp_rmb() is sufficient, as writes cannot pass the control barrier. + */ +#define ipc_smp_acquire__after_spin_is_unlocked() smp_rmb() + +/* * Wait until all currently ongoing simple ops have completed. * Caller must own sem_perm.lock. * New simple ops cannot start, because simple ops first check @@ -275,6 +285,7 @@ static void sem_wait_array(struct sem_array *sma) sem = sma->sem_base + i; spin_unlock_wait(&sem->lock); } + ipc_smp_acquire__after_spin_is_unlocked(); } /* @@ -326,8 +337,13 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, /* Then check that the global lock is free */ if (!spin_is_locked(&sma->sem_perm.lock)) { - /* spin_is_locked() is not a memory barrier */ - smp_mb(); + /* + * We need a memory barrier with acquire semantics, + * otherwise we can race with another thread that does: + * complex_count++; + * spin_unlock(sem_perm.lock); + */ + ipc_smp_acquire__after_spin_is_unlocked(); /* Now repeat the test of complex_count: * It can't change anymore until we drop sem->lock. @@ -2055,17 +2071,28 @@ void exit_sem(struct task_struct *tsk) rcu_read_lock(); un = list_entry_rcu(ulp->list_proc.next, struct sem_undo, list_proc); - if (&un->list_proc == &ulp->list_proc) - semid = -1; - else - semid = un->semid; + if (&un->list_proc == &ulp->list_proc) { + /* + * We must wait for freeary() before freeing this ulp, + * in case we raced with last sem_undo. There is a small + * possibility where we exit while freeary() didn't + * finish unlocking sem_undo_list. + */ + spin_unlock_wait(&ulp->lock); + rcu_read_unlock(); + break; + } + spin_lock(&ulp->lock); + semid = un->semid; + spin_unlock(&ulp->lock); + /* exit_sem raced with IPC_RMID, nothing to do */ if (semid == -1) { rcu_read_unlock(); - break; + continue; } - sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, un->semid); + sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, semid); /* exit_sem raced with IPC_RMID, nothing to do */ if (IS_ERR(sma)) { rcu_read_unlock(); diff --git a/kernel/audit.c b/kernel/audit.c index 0c9dc86..b45b2da 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -687,7 +687,7 @@ static int audit_get_feature(struct sk_buff *skb) seq = nlmsg_hdr(skb)->nlmsg_seq; - audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af)); + audit_send_reply(skb, seq, AUDIT_GET_FEATURE, 0, 0, &af, sizeof(af)); return 0; } @@ -702,7 +702,7 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE); audit_log_task_info(ab, current); - audit_log_format(ab, "feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d", + audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d", audit_feature_names[which], !!old_feature, !!new_feature, !!old_lock, !!new_lock, res); audit_log_end(ab); @@ -1628,7 +1628,7 @@ void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) audit_log_format(ab, " %s=", prefix); CAP_FOR_EACH_U32(i) { audit_log_format(ab, "%08x", - cap->cap[(_KERNEL_CAPABILITY_U32S-1) - i]); + cap->cap[CAP_LAST_U32 - i]); } } diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 135944a..a79db03 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -154,6 +154,7 @@ static struct audit_chunk *alloc_chunk(int count) chunk->owners[i].index = i; } fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch); + chunk->mark.mask = FS_IN_IGNORED; return chunk; } diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 92062fd..598c1dc 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -429,6 +429,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; f->val = 0; + entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } err = audit_field_valid(entry, f); @@ -604,6 +605,13 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) data->buflen += data->values[i] = audit_pack_string(&bufp, krule->filterkey); break; + case AUDIT_LOGINUID_SET: + if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) { + data->fields[i] = AUDIT_LOGINUID; + data->values[i] = AUDIT_UID_UNSET; + break; + } + /* fallthrough if set */ default: data->values[i] = f->val; } @@ -620,6 +628,7 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) int i; if (a->flags != b->flags || + a->pflags != b->pflags || a->listnr != b->listnr || a->action != b->action || a->field_count != b->field_count) @@ -738,6 +747,7 @@ struct audit_entry *audit_dupe_rule(struct audit_krule *old) new = &entry->rule; new->vers_ops = old->vers_ops; new->flags = old->flags; + new->pflags = old->pflags; new->listnr = old->listnr; new->action = old->action; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) diff --git a/kernel/capability.c b/kernel/capability.c index 1191a44..00adb21 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -268,6 +268,10 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) i++; } + effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + new = prepare_creds(); if (!new) return -ENOMEM; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 0c753dd..18711f3 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -971,7 +971,7 @@ static void cgroup_d_remove_dir(struct dentry *dentry) parent = dentry->d_parent; spin_lock(&parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - list_del_init(&dentry->d_u.d_child); + list_del_init(&dentry->d_child); spin_unlock(&dentry->d_lock); spin_unlock(&parent->d_lock); remove_dir(dentry); @@ -3663,7 +3663,6 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, l = cgroup_pidlist_find_create(cgrp, type); if (!l) { - mutex_unlock(&cgrp->pidlist_mutex); pidlist_free(array); return -ENOMEM; } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 6b27e5c..7b4530b 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -61,12 +61,7 @@ #include #include -/* - * Tracks how many cpusets are currently defined in system. - * When there is only one cpuset (the root cpuset) we can - * short circuit some hooks. - */ -int number_of_cpusets __read_mostly; +struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE; /* See "Frequency meter" comments, below. */ @@ -508,9 +503,6 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr, rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { - if (cp == root_cs) - continue; - /* skip the whole subtree if @cp doesn't have any CPU */ if (cpumask_empty(cp->cpus_allowed)) { pos_css = css_rightmost_descendant(pos_css); @@ -611,7 +603,7 @@ static int generate_sched_domains(cpumask_var_t **domains, goto done; } - csa = kmalloc(number_of_cpusets * sizeof(cp), GFP_KERNEL); + csa = kmalloc(nr_cpusets() * sizeof(cp), GFP_KERNEL); if (!csa) goto done; csn = 0; @@ -1022,7 +1014,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, task_lock(tsk); /* * Determine if a loop is necessary if another thread is doing - * get_mems_allowed(). If at least one node remains unchanged and + * read_mems_allowed_begin(). If at least one node remains unchanged and * tsk does not have a mempolicy, then an empty nodemask will not be * possible when mems_allowed is larger than a word. */ @@ -1961,7 +1953,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) if (is_spread_slab(parent)) set_bit(CS_SPREAD_SLAB, &cs->flags); - number_of_cpusets++; + cpuset_inc(); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; @@ -2012,7 +2004,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) if (is_sched_load_balance(cs)) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); - number_of_cpusets--; + cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); mutex_unlock(&cpuset_mutex); @@ -2067,7 +2059,6 @@ int __init cpuset_init(void) if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)) BUG(); - number_of_cpusets = 1; return 0; } diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 334b398..8865cae 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -224,10 +225,17 @@ static void kgdb_flush_swbreak_addr(unsigned long addr) if (!CACHE_FLUSH_IS_SAFE) return; - if (current->mm && current->mm->mmap_cache) { - flush_cache_range(current->mm->mmap_cache, - addr, addr + BREAK_INSTR_SIZE); + if (current->mm) { + int i; + + for (i = 0; i < VMACACHE_SIZE; i++) { + if (!current->vmacache[i]) + continue; + flush_cache_range(current->vmacache[i], + addr, addr + BREAK_INSTR_SIZE); + } } + /* Force flush instruction cache if it was outside the mm */ flush_icache_range(addr, addr + BREAK_INSTR_SIZE); } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 0b097c8..449518e 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2535,7 +2535,7 @@ static int kdb_summary(int argc, const char **argv) #define K(x) ((x) << (PAGE_SHIFT - 10)) kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n" "Buffers: %8lu kB\n", - val.totalram, val.freeram, val.bufferram); + K(val.totalram), K(val.freeram), K(val.bufferram)); return 0; } diff --git a/kernel/events/core.c b/kernel/events/core.c index f774e93..3bf20e3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -39,6 +39,7 @@ #include #include #include +#include #include "internal.h" @@ -1516,6 +1517,11 @@ retry: */ if (ctx->is_active) { raw_spin_unlock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; goto retry; } @@ -1957,6 +1963,11 @@ retry: */ if (ctx->is_active) { raw_spin_unlock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; goto retry; } @@ -3551,28 +3562,21 @@ static void perf_event_for_each(struct perf_event *event, mutex_unlock(&ctx->mutex); } -static int perf_event_period(struct perf_event *event, u64 __user *arg) -{ - struct perf_event_context *ctx = event->ctx; - int ret = 0, active; +struct period_event { + struct perf_event *event; u64 value; +}; - if (!is_sampling_event(event)) - return -EINVAL; - - if (copy_from_user(&value, arg, sizeof(value))) - return -EFAULT; - - if (!value) - return -EINVAL; +static int __perf_event_period(void *info) +{ + struct period_event *pe = info; + struct perf_event *event = pe->event; + struct perf_event_context *ctx = event->ctx; + u64 value = pe->value; + bool active; - raw_spin_lock_irq(&ctx->lock); + raw_spin_lock(&ctx->lock); if (event->attr.freq) { - if (value > sysctl_perf_event_sample_rate) { - ret = -EINVAL; - goto unlock; - } - event->attr.sample_freq = value; } else { event->attr.sample_period = value; @@ -3591,11 +3595,53 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) event->pmu->start(event, PERF_EF_RELOAD); perf_pmu_enable(ctx->pmu); } + raw_spin_unlock(&ctx->lock); -unlock: + return 0; +} + +static int perf_event_period(struct perf_event *event, u64 __user *arg) +{ + struct period_event pe = { .event = event, }; + struct perf_event_context *ctx = event->ctx; + struct task_struct *task; + u64 value; + + if (!is_sampling_event(event)) + return -EINVAL; + + if (copy_from_user(&value, arg, sizeof(value))) + return -EFAULT; + + if (!value) + return -EINVAL; + + if (event->attr.freq && value > sysctl_perf_event_sample_rate) + return -EINVAL; + + task = ctx->task; + pe.value = value; + + if (!task) { + cpu_function_call(event->cpu, __perf_event_period, &pe); + return 0; + } + +retry: + if (!task_function_call(task, __perf_event_period, &pe)) + return 0; + + raw_spin_lock_irq(&ctx->lock); + if (ctx->is_active) { + raw_spin_unlock_irq(&ctx->lock); + task = ctx->task; + goto retry; + } + + __perf_event_period(&pe); raw_spin_unlock_irq(&ctx->lock); - return ret; + return 0; } static const struct file_operations perf_fops; @@ -3683,6 +3729,26 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return 0; } +#ifdef CONFIG_COMPAT +static long perf_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + switch (_IOC_NR(cmd)) { + case _IOC_NR(PERF_EVENT_IOC_SET_FILTER): + case _IOC_NR(PERF_EVENT_IOC_ID): + /* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */ + if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) { + cmd &= ~IOCSIZE_MASK; + cmd |= sizeof(void *) << IOCSIZE_SHIFT; + } + break; + } + return perf_ioctl(file, cmd, arg); +} +#else +# define perf_compat_ioctl NULL +#endif + int perf_event_task_enable(void) { struct perf_event *event; @@ -4175,7 +4241,7 @@ static const struct file_operations perf_fops = { .read = perf_read, .poll = perf_poll, .unlocked_ioctl = perf_ioctl, - .compat_ioctl = perf_ioctl, + .compat_ioctl = perf_compat_ioctl, .mmap = perf_mmap, .fasync = perf_fasync, }; @@ -4187,12 +4253,20 @@ static const struct file_operations perf_fops = { * to user-space before waking everybody up. */ +static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) +{ + /* only the parent has fasync state */ + if (event->parent) + event = event->parent; + return &event->fasync; +} + void perf_event_wakeup(struct perf_event *event) { ring_buffer_wakeup(event); if (event->pending_kill) { - kill_fasync(&event->fasync, SIGIO, event->pending_kill); + kill_fasync(perf_event_fasync(event), SIGIO, event->pending_kill); event->pending_kill = 0; } } @@ -4201,6 +4275,13 @@ static void perf_pending_event(struct irq_work *entry) { struct perf_event *event = container_of(entry, struct perf_event, pending); + int rctx; + + rctx = perf_swevent_get_recursion_context(); + /* + * If we 'fail' here, that's OK, it means recursion is already disabled + * and we won't recurse 'further'. + */ if (event->pending_disable) { event->pending_disable = 0; @@ -4211,6 +4292,9 @@ static void perf_pending_event(struct irq_work *entry) event->pending_wakeup = 0; perf_event_wakeup(event); } + + if (rctx >= 0) + perf_swevent_put_recursion_context(rctx); } /* @@ -5391,7 +5475,7 @@ static int __perf_event_overflow(struct perf_event *event, else perf_event_output(event, data, regs); - if (event->fasync && event->pending_kill) { + if (*perf_event_fasync(event) && event->pending_kill) { event->pending_wakeup = 1; irq_work_queue(&event->pending); } @@ -7209,11 +7293,11 @@ SYSCALL_DEFINE5(perf_event_open, if (move_group) { synchronize_rcu(); - perf_install_in_context(ctx, group_leader, event->cpu); + perf_install_in_context(ctx, group_leader, group_leader->cpu); get_ctx(ctx); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { - perf_install_in_context(ctx, sibling, event->cpu); + perf_install_in_context(ctx, sibling, sibling->cpu); get_ctx(ctx); } } @@ -7826,8 +7910,10 @@ int perf_event_init_task(struct task_struct *child) for_each_task_context_nr(ctxn) { ret = perf_event_init_context(child, ctxn); - if (ret) + if (ret) { + perf_event_free_task(child); return ret; + } } return 0; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 307d87c..1139b22 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1621,7 +1621,6 @@ bool uprobe_deny_signal(void) if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) { utask->state = UTASK_SSTEP_TRAPPED; set_tsk_thread_flag(t, TIF_UPROBE); - set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); } } diff --git a/kernel/fork.c b/kernel/fork.c index c44bff8..e2c6853 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -28,6 +28,8 @@ #include #include #include +#include +#include #include #include #include @@ -363,7 +365,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) mm->locked_vm = 0; mm->mmap = NULL; - mm->mmap_cache = NULL; + mm->vmacache_seqnum = 0; mm->map_count = 0; cpumask_clear(mm_cpumask(mm)); mm->mm_rb = RB_ROOT; @@ -876,6 +878,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) if (!oldmm) return 0; + /* initialize the new vmacache entries */ + vmacache_flush(tsk); + if (clone_flags & CLONE_VM) { atomic_inc(&oldmm->mm_users); mm = oldmm; @@ -1323,7 +1328,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_policy; retval = audit_alloc(p); if (retval) - goto bad_fork_cleanup_policy; + goto bad_fork_cleanup_perf; /* copy all the process information */ retval = copy_semundo(clone_flags, p); if (retval) @@ -1522,8 +1527,9 @@ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_audit: audit_free(p); -bad_fork_cleanup_policy: +bad_fork_cleanup_perf: perf_event_free_task(p); +bad_fork_cleanup_policy: #ifdef CONFIG_NUMA mpol_put(p->mempolicy); bad_fork_cleanup_cgroup: diff --git a/kernel/freezer.c b/kernel/freezer.c index aa6a8aa..8f9279b 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -42,6 +42,9 @@ bool freezing_slow_path(struct task_struct *p) if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK)) return false; + if (test_thread_flag(TIF_MEMDIE)) + return false; + if (pm_nosig_freezing || cgroup_freezing(p)) return true; diff --git a/kernel/futex.c b/kernel/futex.c index e3087af..fda2950 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -329,6 +329,8 @@ static void get_futex_key_refs(union futex_key *key) case FUT_OFF_MMSHARED: futex_get_mm(key); /* implies MB (B) */ break; + default: + smp_mb(); /* explicit MB (B) */ } } @@ -2614,6 +2616,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * shared futexes. We need to compare the keys: */ if (match_futex(&q.key, &key2)) { + queue_unlock(hb); ret = -EINVAL; goto out_put_keys; } diff --git a/kernel/groups.c b/kernel/groups.c index 90cf1c3..67b4ba3 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -6,6 +6,7 @@ #include #include #include +#include #include /* init to 2 - one for init_task, one to ensure it is never freed */ @@ -223,6 +224,14 @@ out: return i; } +bool may_setgroups(void) +{ + struct user_namespace *user_ns = current_user_ns(); + + return ns_capable(user_ns, CAP_SETGID) && + userns_may_setgroups(user_ns); +} + /* * SMP: Our groups are copy-on-write. We can set them safely * without another task interfering. @@ -233,7 +242,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) struct group_info *group_info; int retval; - if (!ns_capable(current_user_ns(), CAP_SETGID)) + if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index 1ef0606..0296d6f 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -104,7 +104,7 @@ int devm_request_any_context_irq(struct device *dev, unsigned int irq, return -ENOMEM; rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id); - if (rc) { + if (rc < 0) { devres_free(dr); return rc; } @@ -113,7 +113,7 @@ int devm_request_any_context_irq(struct device *dev, unsigned int irq, dr->dev_id = dev_id; devres_add(dev, dr); - return 0; + return rc; } EXPORT_SYMBOL(devm_request_any_context_irq); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 001fa5b..8a160e8 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -74,6 +74,14 @@ extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu); extern void mask_irq(struct irq_desc *desc); extern void unmask_irq(struct irq_desc *desc); +#ifdef CONFIG_SPARSE_IRQ +extern void irq_lock_sparse(void); +extern void irq_unlock_sparse(void); +#else +static inline void irq_lock_sparse(void) { } +static inline void irq_unlock_sparse(void) { } +#endif + extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr); irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 8ab8e93..07d4551 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -131,6 +131,16 @@ static void free_masks(struct irq_desc *desc) static inline void free_masks(struct irq_desc *desc) { } #endif +void irq_lock_sparse(void) +{ + mutex_lock(&sparse_irq_lock); +} + +void irq_unlock_sparse(void) +{ + mutex_unlock(&sparse_irq_lock); +} + static struct irq_desc *alloc_desc(int irq, int node, struct module *owner) { struct irq_desc *desc; @@ -167,6 +177,12 @@ static void free_desc(unsigned int irq) unregister_irq_proc(irq, desc); + /* + * sparse_irq_lock protects also show_interrupts() and + * kstat_irq_usr(). Once we deleted the descriptor from the + * sparse tree we can free it. Access in proc will fail to + * lookup the descriptor. + */ mutex_lock(&sparse_irq_lock); delete_irq_desc(irq); mutex_unlock(&sparse_irq_lock); @@ -489,6 +505,15 @@ void dynamic_irq_cleanup(unsigned int irq) raw_spin_unlock_irqrestore(&desc->lock, flags); } +/** + * kstat_irqs_cpu - Get the statistics for an interrupt on a cpu + * @irq: The interrupt number + * @cpu: The cpu number + * + * Returns the sum of interrupt counts on @cpu since boot for + * @irq. The caller must ensure that the interrupt is not removed + * concurrently. + */ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { struct irq_desc *desc = irq_to_desc(irq); @@ -497,6 +522,14 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) *per_cpu_ptr(desc->kstat_irqs, cpu) : 0; } +/** + * kstat_irqs - Get the statistics for an interrupt + * @irq: The interrupt number + * + * Returns the sum of interrupt counts on all cpus since boot for + * @irq. The caller must ensure that the interrupt is not removed + * concurrently. + */ unsigned int kstat_irqs(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); @@ -509,3 +542,22 @@ unsigned int kstat_irqs(unsigned int irq) sum += *per_cpu_ptr(desc->kstat_irqs, cpu); return sum; } + +/** + * kstat_irqs_usr - Get the statistics for an interrupt + * @irq: The interrupt number + * + * Returns the sum of interrupt counts on all cpus since boot for + * @irq. Contrary to kstat_irqs() this can be called from any + * preemptible context. It's protected against concurrent removal of + * an interrupt descriptor when sparse irqs are enabled. + */ +unsigned int kstat_irqs_usr(unsigned int irq) +{ + int sum; + + irq_lock_sparse(); + sum = kstat_irqs(irq); + irq_unlock_sparse(); + return sum; +} diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 36f6ee1..095cd72 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -15,6 +15,23 @@ #include "internals.h" +/* + * Access rules: + * + * procfs protects read/write of /proc/irq/N/ files against a + * concurrent free of the interrupt descriptor. remove_proc_entry() + * immediately prevents new read/writes to happen and waits for + * already running read/write functions to complete. + * + * We remove the proc entries first and then delete the interrupt + * descriptor from the radix tree and free it. So it is guaranteed + * that irq_to_desc(N) is valid as long as the read/writes are + * permitted by procfs. + * + * The read from /proc/interrupts is a different problem because there + * is no protection. So the lookup and the access to irqdesc + * information must be protected by sparse_irq_lock. + */ static struct proc_dir_entry *root_irq_dir; #ifdef CONFIG_SMP @@ -437,9 +454,10 @@ int show_interrupts(struct seq_file *p, void *v) seq_putc(p, '\n'); } + irq_lock_sparse(); desc = irq_to_desc(i); if (!desc) - return 0; + goto outsparse; raw_spin_lock_irqsave(&desc->lock, flags); for_each_online_cpu(j) @@ -479,6 +497,8 @@ int show_interrupts(struct seq_file *p, void *v) seq_putc(p, '\n'); out: raw_spin_unlock_irqrestore(&desc->lock, flags); +outsparse: + irq_unlock_sparse(); return 0; } #endif diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c index 9065107..7a5237a 100644 --- a/kernel/irq/resend.c +++ b/kernel/irq/resend.c @@ -75,13 +75,21 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq) !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) { #ifdef CONFIG_HARDIRQS_SW_RESEND /* - * If the interrupt has a parent irq and runs - * in the thread context of the parent irq, - * retrigger the parent. + * If the interrupt is running in the thread + * context of the parent irq we need to be + * careful, because we cannot trigger it + * directly. */ - if (desc->parent_irq && - irq_settings_is_nested_thread(desc)) + if (irq_settings_is_nested_thread(desc)) { + /* + * If the parent_irq is valid, we + * retrigger the parent, otherwise we + * do nothing. + */ + if (!desc->parent_irq) + return; irq = desc->parent_irq; + } /* Set it pending and activate the softirq: */ set_bit(irq, irqs_resend); tasklet_schedule(&resend_tasklet); diff --git a/kernel/kcmp.c b/kernel/kcmp.c index e30ac0f..0aa69ea 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -44,11 +44,12 @@ static long kptr_obfuscate(long v, int type) */ static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type) { - long ret; + long t1, t2; - ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type); + t1 = kptr_obfuscate((long)v1, type); + t2 = kptr_obfuscate((long)v2, type); - return (ret < 0) | ((ret > 0) << 1); + return (t1 < t2) | ((t1 > t2) << 1); } /* The caller must have pinned the task */ diff --git a/kernel/module.c b/kernel/module.c index 6716a1f..1d679a6 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1841,7 +1841,9 @@ static void free_module(struct module *mod) /* We leave it in list to prevent duplicate loads, but make sure * that noone uses it while it's being deconstructed. */ + mutex_lock(&module_mutex); mod->state = MODULE_STATE_UNFORMED; + mutex_unlock(&module_mutex); /* Remove dynamic debug info */ ddebug_remove_module(mod->name); diff --git a/kernel/pid.c b/kernel/pid.c index 9b9a266..82430c8 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -341,6 +341,8 @@ out: out_unlock: spin_unlock_irq(&pidmap_lock); + put_pid_ns(ns); + out_free: while (++i <= ns->level) free_pidmap(pid->numbers + i); diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 424c2d4..77e6b83 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -634,6 +634,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock, goto out; } } else { + memset(&event.sigev_value, 0, sizeof(event.sigev_value)); event.sigev_notify = SIGEV_SIGNAL; event.sigev_signo = SIGALRM; event.sigev_value.sival_int = new_timer->it_id; diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 2fac9cc..9d18628 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -191,7 +191,7 @@ config DPM_WATCHDOG config DPM_WATCHDOG_TIMEOUT int "Watchdog timeout in seconds" range 1 120 - default 12 + default 60 depends on DPM_WATCHDOG config PM_TRACE diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 37170d4..126586a 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -492,8 +492,14 @@ int hibernation_restore(int platform_mode) error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { error = resume_target_kernel(platform_mode); - dpm_resume_end(PMSG_RECOVER); + /* + * The above should either succeed and jump to the new kernel, + * or return with an error. Otherwise things are just + * undefined, so let's be paranoid. + */ + BUG_ON(!error); } + dpm_resume_end(PMSG_RECOVER); pm_restore_gfp_mask(); ftrace_start(); resume_console(); diff --git a/kernel/power/main.c b/kernel/power/main.c index 1d1bf63..3ae41cd 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -293,12 +293,12 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, { char *s = buf; #ifdef CONFIG_SUSPEND - int i; + suspend_state_t i; + + for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) + if (pm_states[i].state) + s += sprintf(s,"%s ", pm_states[i].label); - for (i = 0; i < PM_SUSPEND_MAX; i++) { - if (pm_states[i] && valid_state(i)) - s += sprintf(s,"%s ", pm_states[i]); - } #endif #ifdef CONFIG_HIBERNATION s += sprintf(s, "%s\n", "disk"); @@ -314,7 +314,7 @@ static suspend_state_t decode_state(const char *buf, size_t n) { #ifdef CONFIG_SUSPEND suspend_state_t state = PM_SUSPEND_MIN; - const char * const *s; + struct pm_sleep_state *s; #endif char *p; int len; @@ -328,8 +328,9 @@ static suspend_state_t decode_state(const char *buf, size_t n) #ifdef CONFIG_SUSPEND for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) - if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) - return state; + if (s->state && len == strlen(s->label) + && !strncmp(buf, s->label, len)) + return s->state; #endif return PM_SUSPEND_ON; @@ -447,8 +448,8 @@ static ssize_t autosleep_show(struct kobject *kobj, #ifdef CONFIG_SUSPEND if (state < PM_SUSPEND_MAX) - return sprintf(buf, "%s\n", valid_state(state) ? - pm_states[state] : "error"); + return sprintf(buf, "%s\n", pm_states[state].state ? + pm_states[state].label : "error"); #endif #ifdef CONFIG_HIBERNATION return sprintf(buf, "disk\n"); diff --git a/kernel/power/power.h b/kernel/power/power.h index 7d4b7ff..f770cad3 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -175,17 +175,20 @@ extern void swsusp_show_speed(struct timeval *, struct timeval *, unsigned int, char *); #ifdef CONFIG_SUSPEND +struct pm_sleep_state { + const char *label; + suspend_state_t state; +}; + /* kernel/power/suspend.c */ -extern const char *const pm_states[]; +extern struct pm_sleep_state pm_states[]; -extern bool valid_state(suspend_state_t state); extern int suspend_devices_and_enter(suspend_state_t state); #else /* !CONFIG_SUSPEND */ static inline int suspend_devices_and_enter(suspend_state_t state) { return -ENOSYS; } -static inline bool valid_state(suspend_state_t state) { return false; } #endif /* !CONFIG_SUSPEND */ #ifdef CONFIG_PM_TEST_SUSPEND diff --git a/kernel/power/process.c b/kernel/power/process.c index 14f9a8d..f1fe7ec 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -107,6 +107,28 @@ static int try_to_freeze_tasks(bool user_only) return todo ? -EBUSY : 0; } +/* + * Returns true if all freezable tasks (except for current) are frozen already + */ +static bool check_frozen_processes(void) +{ + struct task_struct *g, *p; + bool ret = true; + + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + if (p != current && !freezer_should_skip(p) && + !frozen(p)) { + ret = false; + goto done; + } + } +done: + read_unlock(&tasklist_lock); + + return ret; +} + /** * freeze_processes - Signal user space processes to enter the refrigerator. * The current thread will not be frozen. The same process that calls @@ -117,6 +139,7 @@ static int try_to_freeze_tasks(bool user_only) int freeze_processes(void) { int error; + int oom_kills_saved; error = __usermodehelper_disable(UMH_FREEZING); if (error) @@ -130,12 +153,27 @@ int freeze_processes(void) printk("Freezing user space processes ... "); pm_freezing = true; + oom_kills_saved = oom_kills_count(); error = try_to_freeze_tasks(true); if (!error) { - printk("done."); __usermodehelper_set_disable_depth(UMH_DISABLED); oom_killer_disable(); + + /* + * There might have been an OOM kill while we were + * freezing tasks and the killed task might be still + * on the way out so we have to double check for race. + */ + if (oom_kills_count() != oom_kills_saved && + !check_frozen_processes()) { + __usermodehelper_set_disable_depth(UMH_ENABLED); + printk("OOM in progress."); + error = -EBUSY; + goto done; + } + printk("done."); } +done: printk("\n"); BUG_ON(in_atomic()); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 62ee437..5455d5c 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -29,10 +29,10 @@ #include "power.h" -const char *const pm_states[PM_SUSPEND_MAX] = { - [PM_SUSPEND_FREEZE] = "freeze", - [PM_SUSPEND_STANDBY] = "standby", - [PM_SUSPEND_MEM] = "mem", +struct pm_sleep_state pm_states[PM_SUSPEND_MAX] = { + [PM_SUSPEND_FREEZE] = { .label = "freeze", .state = PM_SUSPEND_FREEZE }, + [PM_SUSPEND_STANDBY] = { .label = "standby", }, + [PM_SUSPEND_MEM] = { .label = "mem", }, }; static const struct platform_suspend_ops *suspend_ops; @@ -62,42 +62,34 @@ void freeze_wake(void) } EXPORT_SYMBOL_GPL(freeze_wake); +static bool valid_state(suspend_state_t state) +{ + /* + * PM_SUSPEND_STANDBY and PM_SUSPEND_MEM states need low level + * support and need to be valid to the low level + * implementation, no valid callback implies that none are valid. + */ + return suspend_ops && suspend_ops->valid && suspend_ops->valid(state); +} + /** * suspend_set_ops - Set the global suspend method table. * @ops: Suspend operations to use. */ void suspend_set_ops(const struct platform_suspend_ops *ops) { + suspend_state_t i; + lock_system_sleep(); + suspend_ops = ops; + for (i = PM_SUSPEND_STANDBY; i <= PM_SUSPEND_MEM; i++) + pm_states[i].state = valid_state(i) ? i : 0; + unlock_system_sleep(); } EXPORT_SYMBOL_GPL(suspend_set_ops); -bool valid_state(suspend_state_t state) -{ - if (state == PM_SUSPEND_FREEZE) { -#ifdef CONFIG_PM_DEBUG - if (pm_test_level != TEST_NONE && - pm_test_level != TEST_FREEZER && - pm_test_level != TEST_DEVICES && - pm_test_level != TEST_PLATFORM) { - printk(KERN_WARNING "Unsupported pm_test mode for " - "freeze state, please choose " - "none/freezer/devices/platform.\n"); - return false; - } -#endif - return true; - } - /* - * PM_SUSPEND_STANDBY and PM_SUSPEND_MEMORY states need lowlevel - * support and need to be valid to the lowlevel - * implementation, no valid callback implies that none are valid. - */ - return suspend_ops && suspend_ops->valid && suspend_ops->valid(state); -} - /** * suspend_valid_only_mem - Generic memory-only valid callback. * @@ -324,9 +316,17 @@ static int enter_state(suspend_state_t state) { int error; - if (!valid_state(state)) - return -ENODEV; - + if (state == PM_SUSPEND_FREEZE) { +#ifdef CONFIG_PM_DEBUG + if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) { + pr_warning("PM: Unsupported test mode for freeze state," + "please choose none/freezer/devices/platform.\n"); + return -EAGAIN; + } +#endif + } else if (!valid_state(state)) { + return -EINVAL; + } if (!mutex_trylock(&pm_mutex)) return -EBUSY; @@ -337,7 +337,7 @@ static int enter_state(suspend_state_t state) sys_sync(); printk("done.\n"); - pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]); + pr_debug("PM: Preparing system for %s sleep\n", pm_states[state].label); error = suspend_prepare(state); if (error) goto Unlock; @@ -345,7 +345,7 @@ static int enter_state(suspend_state_t state) if (suspend_test(TEST_FREEZER)) goto Finish; - pr_debug("PM: Entering %s sleep\n", pm_states[state]); + pr_debug("PM: Entering %s sleep\n", pm_states[state].label); pm_restrict_gfp_mask(); error = suspend_devices_and_enter(state); pm_restore_gfp_mask(); diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c index 9b2a1d5..269b097 100644 --- a/kernel/power/suspend_test.c +++ b/kernel/power/suspend_test.c @@ -92,13 +92,13 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state) } if (state == PM_SUSPEND_MEM) { - printk(info_test, pm_states[state]); + printk(info_test, pm_states[state].label); status = pm_suspend(state); if (status == -ENODEV) state = PM_SUSPEND_STANDBY; } if (state == PM_SUSPEND_STANDBY) { - printk(info_test, pm_states[state]); + printk(info_test, pm_states[state].label); status = pm_suspend(state); } if (status < 0) @@ -136,18 +136,16 @@ static char warn_bad_state[] __initdata = static int __init setup_test_suspend(char *value) { - unsigned i; + suspend_state_t i; /* "=mem" ==> "mem" */ value++; - for (i = 0; i < PM_SUSPEND_MAX; i++) { - if (!pm_states[i]) - continue; - if (strcmp(pm_states[i], value) != 0) - continue; - test_state = (__force suspend_state_t) i; - return 0; - } + for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) + if (!strcmp(pm_states[i].label, value)) { + test_state = pm_states[i].state; + return 0; + } + printk(warn_bad_state, value); return 0; } @@ -164,8 +162,8 @@ static int __init test_suspend(void) /* PM is initialized by now; is that state testable? */ if (test_state == PM_SUSPEND_ON) goto done; - if (!valid_state(test_state)) { - printk(warn_bad_state, pm_states[test_state]); + if (!pm_states[test_state].state) { + printk(warn_bad_state, pm_states[test_state].label); goto done; } diff --git a/kernel/printk/console_cmdline.h b/kernel/printk/console_cmdline.h index cbd69d8..2ca4a8b 100644 --- a/kernel/printk/console_cmdline.h +++ b/kernel/printk/console_cmdline.h @@ -3,7 +3,7 @@ struct console_cmdline { - char name[8]; /* Name of the driver */ + char name[16]; /* Name of the driver */ int index; /* Minor dev. to use */ char *options; /* Options for the driver */ #ifdef CONFIG_A11Y_BRAILLE_CONSOLE diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 4dae9cb..02e7fb4 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -383,11 +383,11 @@ static int check_syslog_permissions(int type, bool from_file) * already done the capabilities checks at open time. */ if (from_file && type != SYSLOG_ACTION_OPEN) - return 0; + goto ok; if (syslog_action_restricted(type)) { if (capable(CAP_SYSLOG)) - return 0; + goto ok; /* * For historical reasons, accept CAP_SYS_ADMIN too, with * a warning. @@ -397,10 +397,11 @@ static int check_syslog_permissions(int type, bool from_file) "CAP_SYS_ADMIN but no CAP_SYSLOG " "(deprecated).\n", current->comm, task_pid_nr(current)); - return 0; + goto ok; } return -EPERM; } +ok: return security_syslog(type); } @@ -1126,10 +1127,6 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) if (error) goto out; - error = security_syslog(type); - if (error) - return error; - switch (type) { case SYSLOG_ACTION_CLOSE: /* Close log */ break; @@ -2280,6 +2277,7 @@ void register_console(struct console *newcon) for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && c->name[0]; i++, c++) { + BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name)); if (strcmp(c->name, newcon->name) != 0) continue; if (newcon->index >= 0 && @@ -2468,7 +2466,7 @@ void wake_up_klogd(void) preempt_enable(); } -int printk_sched(const char *fmt, ...) +int printk_deferred(const char *fmt, ...) { unsigned long flags; va_list args; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 1f4bcb3..be9760f 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -720,6 +720,8 @@ static int ptrace_peek_siginfo(struct task_struct *child, static int ptrace_resume(struct task_struct *child, long request, unsigned long data) { + bool need_siglock; + if (!valid_signal(data)) return -EIO; @@ -747,8 +749,26 @@ static int ptrace_resume(struct task_struct *child, long request, user_disable_single_step(child); } + /* + * Change ->exit_code and ->state under siglock to avoid the race + * with wait_task_stopped() in between; a non-zero ->exit_code will + * wrongly look like another report from tracee. + * + * Note that we need siglock even if ->exit_code == data and/or this + * status was not reported yet, the new status must not be cleared by + * wait_task_stopped() after resume. + * + * If data == 0 we do not care if wait_task_stopped() reports the old + * status and clears the code too; this can't race with the tracee, it + * takes siglock after resume. + */ + need_siglock = data && !thread_group_empty(current); + if (need_siglock) + spin_lock_irq(&child->sighand->siglock); child->exit_code = data; wake_up_state(child, __TASK_TRACED); + if (need_siglock) + spin_unlock_irq(&child->sighand->siglock); return 0; } diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 1254f31..ae359f0 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -284,6 +284,11 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) /* Move the ready-to-invoke callbacks to a local list. */ local_irq_save(flags); + if (rcp->donetail == &rcp->rcucblist) { + /* No callbacks ready, so just leave. */ + local_irq_restore(flags); + return; + } RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1)); list = rcp->rcucblist; rcp->rcucblist = *rcp->donetail; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b3d116c..6705d94 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1228,6 +1228,22 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) } /* + * Awaken the grace-period kthread for the specified flavor of RCU. + * Don't do a self-awaken, and don't bother awakening when there is + * nothing for the grace-period kthread to do (as in several CPUs + * raced to awaken, and we lost), and finally don't try to awaken + * a kthread that has not yet been created. + */ +static void rcu_gp_kthread_wake(struct rcu_state *rsp) +{ + if (current == rsp->gp_kthread || + !ACCESS_ONCE(rsp->gp_flags) || + !rsp->gp_kthread) + return; + wake_up(&rsp->gp_wq); +} + +/* * If there is room, assign a ->completed number to any callbacks on * this CPU that have not already been assigned. Also accelerate any * callbacks that were previously assigned a ->completed number that has @@ -1670,7 +1686,7 @@ static void rsp_wakeup(struct irq_work *work) struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work); /* Wake up rcu_gp_kthread() to start the grace period. */ - wake_up(&rsp->gp_wq); + rcu_gp_kthread_wake(rsp); } /* @@ -1746,7 +1762,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + rcu_gp_kthread_wake(rsp); } /* @@ -2322,7 +2338,7 @@ static void force_quiescent_state(struct rcu_state *rsp) } rsp->gp_flags |= RCU_GP_FLAG_FQS; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + rcu_gp_kthread_wake(rsp); } /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0aae0fc..5e973ef 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1322,7 +1322,7 @@ out: * leave kernel. */ if (p->mm && printk_ratelimit()) { - printk_sched("process %d (%s) no longer affine to cpu%d\n", + printk_deferred("process %d (%s) no longer affine to cpu%d\n", task_pid_nr(p), p->comm, cpu); } } @@ -1895,6 +1895,8 @@ unsigned long to_ratio(u64 period, u64 runtime) #ifdef CONFIG_SMP inline struct dl_bw *dl_bw_of(int i) { + rcu_lockdep_assert(rcu_read_lock_sched_held(), + "sched RCU must be held"); return &cpu_rq(i)->rd->dl_bw; } @@ -1903,6 +1905,8 @@ static inline int dl_bw_cpus(int i) struct root_domain *rd = cpu_rq(i)->rd; int cpus = 0; + rcu_lockdep_assert(rcu_read_lock_sched_held(), + "sched RCU must be held"); for_each_cpu_and(i, rd->span, cpu_active_mask) cpus++; @@ -2976,6 +2980,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio) } else { if (dl_prio(oldprio)) p->dl.dl_boosted = 0; + if (rt_prio(oldprio)) + p->rt.timeout = 0; p->sched_class = &fair_sched_class; } @@ -3511,9 +3517,10 @@ static int _sched_setscheduler(struct task_struct *p, int policy, }; /* - * Fixup the legacy SCHED_RESET_ON_FORK hack + * Fixup the legacy SCHED_RESET_ON_FORK hack, except if + * the policy=-1 was passed by sched_setparam(). */ - if (policy & SCHED_RESET_ON_FORK) { + if ((policy != -1) && (policy & SCHED_RESET_ON_FORK)) { attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; policy &= ~SCHED_RESET_ON_FORK; attr.sched_policy = policy; @@ -3936,13 +3943,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) * root_domain. */ #ifdef CONFIG_SMP - if (task_has_dl_policy(p)) { - const struct cpumask *span = task_rq(p)->rd->span; - - if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) { + if (task_has_dl_policy(p) && dl_bandwidth_enabled()) { + rcu_read_lock(); + if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) { retval = -EBUSY; + rcu_read_unlock(); goto out_unlock; } + rcu_read_unlock(); } #endif again: @@ -7457,6 +7465,8 @@ static int sched_dl_global_constraints(void) int cpu, ret = 0; unsigned long flags; + rcu_read_lock(); + /* * Here we want to check the bandwidth not being set to some * value smaller than the currently allocated bandwidth in @@ -7478,6 +7488,8 @@ static int sched_dl_global_constraints(void) break; } + rcu_read_unlock(); + return ret; } @@ -7493,6 +7505,7 @@ static void sched_dl_do_global(void) if (global_rt_runtime() != RUNTIME_INF) new_bw = to_ratio(global_rt_period(), global_rt_runtime()); + rcu_read_lock(); /* * FIXME: As above... */ @@ -7503,6 +7516,7 @@ static void sched_dl_do_global(void) dl_b->bw = new_bw; raw_spin_unlock_irqrestore(&dl_b->lock, flags); } + rcu_read_unlock(); } static int sched_rt_global_validate(void) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index ce85264..8d3c5dd 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -329,7 +329,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, if (!lag_once) { lag_once = true; - printk_sched("sched: DL replenish lagged to much\n"); + printk_deferred("sched: DL replenish lagged to much\n"); } dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; @@ -550,24 +550,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se) static int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se) { - int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq)); - int rorun = dl_se->runtime <= 0; - - if (!rorun && !dmiss) - return 0; - - /* - * If we are beyond our current deadline and we are still - * executing, then we have already used some of the runtime of - * the next instance. Thus, if we do not account that, we are - * stealing bandwidth from the system at each deadline miss! - */ - if (dmiss) { - dl_se->runtime = rorun ? dl_se->runtime : 0; - dl_se->runtime -= rq_clock(rq) - dl_se->deadline; - } - - return 1; + return (dl_se->runtime <= 0); } extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); @@ -806,10 +789,10 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, * parameters of the task might need updating. Otherwise, * we want a replenishment of its runtime. */ - if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH) - replenish_dl_entity(dl_se, pi_se); - else + if (dl_se->dl_new || flags & ENQUEUE_WAKEUP) update_dl_entity(dl_se, pi_se); + else if (flags & ENQUEUE_REPLENISH) + replenish_dl_entity(dl_se, pi_se); __enqueue_dl_entity(dl_se); } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 1999021..27b8e83 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -837,7 +837,7 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) if (!once) { once = true; - printk_sched("sched: RT throttling activated\n"); + printk_deferred("sched: RT throttling activated\n"); } } else { /* diff --git a/kernel/signal.c b/kernel/signal.c index 5d4b05a..bd57d8d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2768,7 +2768,8 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) * Other callers might not initialize the si_lsb field, * so check explicitly for the right codes here. */ - if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO) + if (from->si_signo == SIGBUS && + (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)) err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); #endif break; @@ -3035,7 +3036,7 @@ COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo, int, sig, struct compat_siginfo __user *, uinfo) { - siginfo_t info; + siginfo_t info = {}; int ret = copy_siginfo_from_user32(&info, uinfo); if (unlikely(ret)) return ret; @@ -3081,7 +3082,7 @@ COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo, int, sig, struct compat_siginfo __user *, uinfo) { - siginfo_t info; + siginfo_t info = {}; if (copy_siginfo_from_user32(&info, uinfo)) return -EFAULT; diff --git a/kernel/smp.c b/kernel/smp.c index ffee35b..ff87d44 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -617,7 +617,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), if (cond_func(cpu, info)) { ret = smp_call_function_single(cpu, func, info, wait); - WARN_ON_ONCE(!ret); + WARN_ON_ONCE(ret); } preempt_enable(); } diff --git a/kernel/smpboot.c b/kernel/smpboot.c index eb89e18..60d35ac5 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -279,6 +279,7 @@ int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) unsigned int cpu; int ret = 0; + get_online_cpus(); mutex_lock(&smpboot_threads_lock); for_each_online_cpu(cpu) { ret = __smpboot_create_thread(plug_thread, cpu); @@ -291,6 +292,7 @@ int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) list_add(&plug_thread->list, &hotplug_threads); out: mutex_unlock(&smpboot_threads_lock); + put_online_cpus(); return ret; } EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread); diff --git a/kernel/softirq.c b/kernel/softirq.c index 490fcbb..93be750 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -657,9 +657,13 @@ static void run_ksoftirqd(unsigned int cpu) * in the task stack here. */ __do_softirq(); - rcu_note_context_switch(cpu); local_irq_enable(); cond_resched(); + + preempt_disable(); + rcu_note_context_switch(cpu); + preempt_enable(); + return; } local_irq_enable(); diff --git a/kernel/time.c b/kernel/time.c index 7c7964c..3eb322e 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -195,6 +195,10 @@ SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv, if (tv) { if (copy_from_user(&user_tv, tv, sizeof(*tv))) return -EFAULT; + + if (!timeval_valid(&user_tv)) + return -EINVAL; + new_ts.tv_sec = user_tv.tv_sec; new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC; } @@ -496,17 +500,20 @@ EXPORT_SYMBOL(usecs_to_jiffies); * that a remainder subtract here would not do the right thing as the * resolution values don't fall on second boundries. I.e. the line: * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. + * Note that due to the small error in the multiplier here, this + * rounding is incorrect for sufficiently large values of tv_nsec, but + * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're + * OK. * * Rather, we just shift the bits off the right. * * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. */ -unsigned long -timespec_to_jiffies(const struct timespec *value) +static unsigned long +__timespec_to_jiffies(unsigned long sec, long nsec) { - unsigned long sec = value->tv_sec; - long nsec = value->tv_nsec + TICK_NSEC - 1; + nsec = nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; @@ -517,6 +524,13 @@ timespec_to_jiffies(const struct timespec *value) (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } + +unsigned long +timespec_to_jiffies(const struct timespec *value) +{ + return __timespec_to_jiffies(value->tv_sec, value->tv_nsec); +} + EXPORT_SYMBOL(timespec_to_jiffies); void @@ -533,31 +547,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value) } EXPORT_SYMBOL(jiffies_to_timespec); -/* Same for "timeval" +/* + * We could use a similar algorithm to timespec_to_jiffies (with a + * different multiplier for usec instead of nsec). But this has a + * problem with rounding: we can't exactly add TICK_NSEC - 1 to the + * usec value, since it's not necessarily integral. * - * Well, almost. The problem here is that the real system resolution is - * in nanoseconds and the value being converted is in micro seconds. - * Also for some machines (those that use HZ = 1024, in-particular), - * there is a LARGE error in the tick size in microseconds. - - * The solution we use is to do the rounding AFTER we convert the - * microsecond part. Thus the USEC_ROUND, the bits to be shifted off. - * Instruction wise, this should cost only an additional add with carry - * instruction above the way it was done above. + * We could instead round in the intermediate scaled representation + * (i.e. in units of 1/2^(large scale) jiffies) but that's also + * perilous: the scaling introduces a small positive error, which + * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1 + * units to the intermediate before shifting) leads to accidental + * overflow and overestimates. + * + * At the cost of one additional multiplication by a constant, just + * use the timespec implementation. */ unsigned long timeval_to_jiffies(const struct timeval *value) { - unsigned long sec = value->tv_sec; - long usec = value->tv_usec; - - if (sec >= MAX_SEC_IN_JIFFIES){ - sec = MAX_SEC_IN_JIFFIES; - usec = 0; - } - return (((u64)sec * SEC_CONVERSION) + - (((u64)usec * USEC_CONVERSION + USEC_ROUND) >> - (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; + return __timespec_to_jiffies(value->tv_sec, + value->tv_usec * NSEC_PER_USEC); } EXPORT_SYMBOL(timeval_to_jiffies); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index fe75444..cd45a07 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -464,18 +464,26 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid) static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, ktime_t now) { + unsigned long flags; struct k_itimer *ptr = container_of(alarm, struct k_itimer, it.alarm.alarmtimer); - if (posix_timer_event(ptr, 0) != 0) - ptr->it_overrun++; + enum alarmtimer_restart result = ALARMTIMER_NORESTART; + + spin_lock_irqsave(&ptr->it_lock, flags); + if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) { + if (posix_timer_event(ptr, 0) != 0) + ptr->it_overrun++; + } /* Re-add periodic timers */ if (ptr->it.alarm.interval.tv64) { ptr->it_overrun += alarm_forward(alarm, now, ptr->it.alarm.interval); - return ALARMTIMER_RESTART; + result = ALARMTIMER_RESTART; } - return ALARMTIMER_NORESTART; + spin_unlock_irqrestore(&ptr->it_lock, flags); + + return result; } /** @@ -541,18 +549,22 @@ static int alarm_timer_create(struct k_itimer *new_timer) * @new_timer: k_itimer pointer * @cur_setting: itimerspec data to fill * - * Copies the itimerspec data out from the k_itimer + * Copies out the current itimerspec data */ static void alarm_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) { - memset(cur_setting, 0, sizeof(struct itimerspec)); + ktime_t relative_expiry_time = + alarm_expires_remaining(&(timr->it.alarm.alarmtimer)); + + if (ktime_to_ns(relative_expiry_time) > 0) { + cur_setting->it_value = ktime_to_timespec(relative_expiry_time); + } else { + cur_setting->it_value.tv_sec = 0; + cur_setting->it_value.tv_nsec = 0; + } - cur_setting->it_interval = - ktime_to_timespec(timr->it.alarm.interval); - cur_setting->it_value = - ktime_to_timespec(timr->it.alarm.alarmtimer.node.expires); - return; + cur_setting->it_interval = ktime_to_timespec(timr->it.alarm.interval); } /** diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 086ad60..60ba1af 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -146,7 +146,8 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev) { /* Nothing to do if we already reached the limit */ if (dev->min_delta_ns >= MIN_DELTA_LIMIT) { - printk(KERN_WARNING "CE: Reprogramming failure. Giving up\n"); + printk_deferred(KERN_WARNING + "CE: Reprogramming failure. Giving up\n"); dev->next_event.tv64 = KTIME_MAX; return -ETIME; } @@ -159,9 +160,10 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev) if (dev->min_delta_ns > MIN_DELTA_LIMIT) dev->min_delta_ns = MIN_DELTA_LIMIT; - printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n", - dev->name ? dev->name : "?", - (unsigned long long) dev->min_delta_ns); + printk_deferred(KERN_WARNING + "CE: %s increased min_delta_ns to %llu nsec\n", + dev->name ? dev->name : "?", + (unsigned long long) dev->min_delta_ns); return 0; } diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index af8d1d4..6211d5d 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -631,6 +631,17 @@ int ntp_validate_timex(struct timex *txc) if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME))) return -EPERM; + /* + * Check for potential multiplication overflows that can + * only happen on 64-bit systems: + */ + if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { + if (LLONG_MIN / PPM_SCALE > txc->freq) + return -EINVAL; + if (LLONG_MAX / PPM_SCALE < txc->freq) + return -EINVAL; + } + return 0; } diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 4d23dc4..313a662 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -204,7 +204,8 @@ void __init sched_clock_postinit(void) static int sched_clock_suspend(void) { - sched_clock_poll(&sched_clock_timer); + update_sched_clock(); + hrtimer_cancel(&sched_clock_timer); cd.suspended = true; return 0; } @@ -212,6 +213,7 @@ static int sched_clock_suspend(void) static void sched_clock_resume(void) { cd.epoch_cyc = read_sched_clock(); + hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL); cd.suspended = false; } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 6558b7a..8c08a6f 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -807,7 +807,6 @@ void tick_nohz_idle_enter(void) local_irq_enable(); } -EXPORT_SYMBOL_GPL(tick_nohz_idle_enter); /** * tick_nohz_irq_exit - update next tick event from interrupt exit @@ -934,7 +933,6 @@ void tick_nohz_idle_exit(void) local_irq_enable(); } -EXPORT_SYMBOL_GPL(tick_nohz_idle_exit); static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now) { diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 0954450..da41de9 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -626,8 +626,22 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, work = &cpu_buffer->irq_work; } - work->waiters_pending = true; poll_wait(filp, &work->waiters, poll_table); + work->waiters_pending = true; + /* + * There's a tight race between setting the waiters_pending and + * checking if the ring buffer is empty. Once the waiters_pending bit + * is set, the next event will wake the task up, but we can get stuck + * if there's only a single event in. + * + * FIXME: Ideally, we need a memory barrier on the writer side as well, + * but adding a memory barrier to all events will cause too much of a + * performance hit in the fast path. We only need a memory barrier when + * the buffer goes from empty to having content. But as this race is + * extremely small, and it's not a problem if another event comes in, we + * will fix it later. + */ + smp_mb(); if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) @@ -1981,7 +1995,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta) /** * rb_update_event - update event type and data - * @event: the even to update + * @event: the event to update * @type: the type of event * @length: the size of the event field in the ring buffer * @@ -2637,7 +2651,7 @@ static DEFINE_PER_CPU(unsigned int, current_context); static __always_inline int trace_recursive_lock(void) { - unsigned int val = this_cpu_read(current_context); + unsigned int val = __this_cpu_read(current_context); int bit; if (in_interrupt()) { @@ -2654,18 +2668,17 @@ static __always_inline int trace_recursive_lock(void) return 1; val |= (1 << bit); - this_cpu_write(current_context, val); + __this_cpu_write(current_context, val); return 0; } static __always_inline void trace_recursive_unlock(void) { - unsigned int val = this_cpu_read(current_context); + unsigned int val = __this_cpu_read(current_context); - val--; - val &= this_cpu_read(current_context); - this_cpu_write(current_context, val); + val &= val & (val - 1); + __this_cpu_write(current_context, val); } #else @@ -3354,21 +3367,16 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; /* Iterator usage is expected to have record disabled */ - if (list_empty(&cpu_buffer->reader_page->list)) { - iter->head_page = rb_set_head_page(cpu_buffer); - if (unlikely(!iter->head_page)) - return; - iter->head = iter->head_page->read; - } else { - iter->head_page = cpu_buffer->reader_page; - iter->head = cpu_buffer->reader_page->read; - } + iter->head_page = cpu_buffer->reader_page; + iter->head = cpu_buffer->reader_page->read; + + iter->cache_reader_page = iter->head_page; + iter->cache_read = cpu_buffer->read; + if (iter->head) iter->read_stamp = cpu_buffer->read_stamp; else iter->read_stamp = iter->head_page->page->time_stamp; - iter->cache_reader_page = cpu_buffer->reader_page; - iter->cache_read = cpu_buffer->read; } /** @@ -3761,12 +3769,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) return NULL; /* - * We repeat when a time extend is encountered. - * Since the time extend is always attached to a data event, - * we should never loop more than once. - * (We never hit the following condition more than twice). + * We repeat when a time extend is encountered or we hit + * the end of the page. Since the time extend is always attached + * to a data event, we should never loop more than three times. + * Once for going to next page, once on time extend, and + * finally once to get the event. + * (We never hit the following condition more than thrice). */ - if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2)) + if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) return NULL; if (rb_per_cpu_empty(cpu_buffer)) diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index a5457d5..6ad2e2d 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -455,7 +455,7 @@ static int __init ring_buffer_benchmark_init(void) if (producer_fifo >= 0) { struct sched_param param = { - .sched_priority = consumer_fifo + .sched_priority = producer_fifo }; sched_setscheduler(producer, SCHED_FIFO, ¶m); } else diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 7e259b2..a2d62b3 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -811,7 +811,7 @@ static struct { { trace_clock_local, "local", 1 }, { trace_clock_global, "global", 1 }, { trace_clock_counter, "counter", 0 }, - { trace_clock_jiffies, "uptime", 1 }, + { trace_clock_jiffies, "uptime", 0 }, { trace_clock, "perf", 1 }, ARCH_TRACE_CLOCKS }; @@ -4694,7 +4694,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, *fpos += written; out_unlock: - for (i = 0; i < nr_pages; i++){ + for (i = nr_pages - 1; i >= 0; i--) { kunmap_atomic(map_page[i]); put_page(pages[i]); } @@ -6158,7 +6158,7 @@ static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t m int ret; /* Paranoid: Make sure the parent is the "instances" directory */ - parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); if (WARN_ON_ONCE(parent != trace_instance_dir)) return -ENOENT; @@ -6185,7 +6185,7 @@ static int instance_rmdir(struct inode *inode, struct dentry *dentry) int ret; /* Paranoid: Make sure the parent is the "instances" directory */ - parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); if (WARN_ON_ONCE(parent != trace_instance_dir)) return -ENOENT; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index c8bd809..c1be95c 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -422,6 +422,7 @@ enum { TRACE_CONTROL_BIT, + TRACE_BRANCH_BIT, /* * Abuse of the trace_recursion. * As we need a way to maintain state if we are tracing the function diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 697fb9b..60850b4 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -37,9 +37,12 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) struct trace_branch *entry; struct ring_buffer *buffer; unsigned long flags; - int cpu, pc; + int pc; const char *p; + if (current->trace_recursion & TRACE_BRANCH_BIT) + return; + /* * I would love to save just the ftrace_likely_data pointer, but * this code can also be used by modules. Ugly things can happen @@ -50,10 +53,10 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) if (unlikely(!tr)) return; - local_irq_save(flags); - cpu = raw_smp_processor_id(); - data = per_cpu_ptr(tr->trace_buffer.data, cpu); - if (atomic_inc_return(&data->disabled) != 1) + raw_local_irq_save(flags); + current->trace_recursion |= TRACE_BRANCH_BIT; + data = this_cpu_ptr(tr->trace_buffer.data); + if (atomic_read(&data->disabled)) goto out; pc = preempt_count(); @@ -82,8 +85,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) __buffer_unlock_commit(buffer, event); out: - atomic_dec(&data->disabled); - local_irq_restore(flags); + current->trace_recursion &= ~TRACE_BRANCH_BIT; + raw_local_irq_restore(flags); } static inline diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index 26dc348..57b67b1 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -59,13 +59,14 @@ u64 notrace trace_clock(void) /* * trace_jiffy_clock(): Simply use jiffies as a clock counter. + * Note that this use of jiffies_64 is not completely safe on + * 32-bit systems. But the window is tiny, and the effect if + * we are affected is that we will have an obviously bogus + * timestamp on a trace event - i.e. not life threatening. */ u64 notrace trace_clock_jiffies(void) { - u64 jiffy = jiffies - INITIAL_JIFFIES; - - /* Return nsecs */ - return (u64)jiffies_to_usecs(jiffy) * 1000ULL; + return jiffies_64_to_clock_t(jiffies_64 - INITIAL_JIFFIES); } /* diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e4c4efc..c6646a5 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -428,7 +428,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file) if (dir) { spin_lock(&dir->d_lock); /* probably unneeded */ - list_for_each_entry(child, &dir->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &dir->d_subdirs, d_child) { if (child->d_inode) /* probably unneeded */ child->d_inode->i_private = NULL; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 8a86319..7b244d0 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1086,6 +1086,9 @@ static void parse_init(struct filter_parse_state *ps, static char infix_next(struct filter_parse_state *ps) { + if (!ps->infix.cnt) + return 0; + ps->infix.cnt--; return ps->infix.string[ps->infix.tail++]; @@ -1101,6 +1104,9 @@ static char infix_peek(struct filter_parse_state *ps) static void infix_advance(struct filter_parse_state *ps) { + if (!ps->infix.cnt) + return; + ps->infix.cnt--; ps->infix.tail++; } @@ -1399,19 +1405,26 @@ static int check_preds(struct filter_parse_state *ps) { int n_normal_preds = 0, n_logical_preds = 0; struct postfix_elt *elt; + int cnt = 0; list_for_each_entry(elt, &ps->postfix, list) { - if (elt->op == OP_NONE) + if (elt->op == OP_NONE) { + cnt++; continue; + } + cnt--; if (elt->op == OP_AND || elt->op == OP_OR) { n_logical_preds++; continue; } n_normal_preds++; + /* all ops should have operands */ + if (cnt < 0) + break; } - if (!n_normal_preds || n_logical_preds >= n_normal_preds) { + if (cnt != 1 || !n_normal_preds || n_logical_preds >= n_normal_preds) { parse_error(ps, FILT_ERR_INVALID_FILTER, 0); return -EINVAL; } diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 759d5e0..7e3cd7a 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -313,7 +313,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) int size; syscall_nr = trace_get_syscall_nr(current, regs); - if (syscall_nr < 0) + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */ @@ -360,7 +360,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) int syscall_nr; syscall_nr = trace_get_syscall_nr(current, regs); - if (syscall_nr < 0) + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */ @@ -567,7 +567,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) int size; syscall_nr = trace_get_syscall_nr(current, regs); - if (syscall_nr < 0) + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; if (!test_bit(syscall_nr, enabled_perf_enter_syscalls)) return; @@ -641,7 +641,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) int size; syscall_nr = trace_get_syscall_nr(current, regs); - if (syscall_nr < 0) + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; if (!test_bit(syscall_nr, enabled_perf_exit_syscalls)) return; diff --git a/kernel/uid16.c b/kernel/uid16.c index 602e5bb..d58cc4d 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -176,7 +176,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist) struct group_info *group_info; int retval; - if (!ns_capable(current_user_ns(), CAP_SETGID)) + if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; diff --git a/kernel/user.c b/kernel/user.c index c006131..c2bbb50 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -51,6 +51,7 @@ struct user_namespace init_user_ns = { .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, .proc_inum = PROC_USER_INIT_INO, + .flags = USERNS_INIT_FLAGS, #ifdef CONFIG_PERSISTENT_KEYRINGS .persistent_keyring_register_sem = __RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem), diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 80a57af..153971e 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -24,6 +24,7 @@ #include static struct kmem_cache *user_ns_cachep __read_mostly; +static DEFINE_MUTEX(userns_state_mutex); static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, @@ -99,6 +100,11 @@ int create_user_ns(struct cred *new) ns->owner = owner; ns->group = group; + /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ + mutex_lock(&userns_state_mutex); + ns->flags = parent_ns->flags; + mutex_unlock(&userns_state_mutex); + set_cred_user_ns(new, ns); #ifdef CONFIG_PERSISTENT_KEYRINGS @@ -581,9 +587,6 @@ static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent return false; } - -static DEFINE_MUTEX(id_map_mutex); - static ssize_t map_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos, int cap_setid, @@ -600,7 +603,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, ssize_t ret = -EINVAL; /* - * The id_map_mutex serializes all writes to any given map. + * The userns_state_mutex serializes all writes to any given map. * * Any map is only ever written once. * @@ -618,7 +621,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, * order and smp_rmb() is guaranteed that we don't have crazy * architectures returning stale data. */ - mutex_lock(&id_map_mutex); + mutex_lock(&userns_state_mutex); ret = -EPERM; /* Only allow one successful write to the map */ @@ -745,7 +748,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, *ppos = count; ret = count; out: - mutex_unlock(&id_map_mutex); + mutex_unlock(&userns_state_mutex); if (page) free_page(page); return ret; @@ -804,17 +807,21 @@ static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { - /* Allow mapping to your own filesystem ids */ - if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1)) { + const struct cred *cred = file->f_cred; + /* Don't allow mappings that would allow anything that wouldn't + * be allowed without the establishment of unprivileged mappings. + */ + if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && + uid_eq(ns->owner, cred->euid)) { u32 id = new_map->extent[0].lower_first; if (cap_setid == CAP_SETUID) { kuid_t uid = make_kuid(ns->parent, id); - if (uid_eq(uid, file->f_cred->fsuid)) + if (uid_eq(uid, cred->euid)) return true; - } - else if (cap_setid == CAP_SETGID) { + } else if (cap_setid == CAP_SETGID) { kgid_t gid = make_kgid(ns->parent, id); - if (gid_eq(gid, file->f_cred->fsgid)) + if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) && + gid_eq(gid, cred->egid)) return true; } } @@ -834,6 +841,100 @@ static bool new_idmap_permitted(const struct file *file, return false; } +int proc_setgroups_show(struct seq_file *seq, void *v) +{ + struct user_namespace *ns = seq->private; + unsigned long userns_flags = ACCESS_ONCE(ns->flags); + + seq_printf(seq, "%s\n", + (userns_flags & USERNS_SETGROUPS_ALLOWED) ? + "allow" : "deny"); + return 0; +} + +ssize_t proc_setgroups_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + char kbuf[8], *pos; + bool setgroups_allowed; + ssize_t ret; + + /* Only allow a very narrow range of strings to be written */ + ret = -EINVAL; + if ((*ppos != 0) || (count >= sizeof(kbuf))) + goto out; + + /* What was written? */ + ret = -EFAULT; + if (copy_from_user(kbuf, buf, count)) + goto out; + kbuf[count] = '\0'; + pos = kbuf; + + /* What is being requested? */ + ret = -EINVAL; + if (strncmp(pos, "allow", 5) == 0) { + pos += 5; + setgroups_allowed = true; + } + else if (strncmp(pos, "deny", 4) == 0) { + pos += 4; + setgroups_allowed = false; + } + else + goto out; + + /* Verify there is not trailing junk on the line */ + pos = skip_spaces(pos); + if (*pos != '\0') + goto out; + + ret = -EPERM; + mutex_lock(&userns_state_mutex); + if (setgroups_allowed) { + /* Enabling setgroups after setgroups has been disabled + * is not allowed. + */ + if (!(ns->flags & USERNS_SETGROUPS_ALLOWED)) + goto out_unlock; + } else { + /* Permanently disabling setgroups after setgroups has + * been enabled by writing the gid_map is not allowed. + */ + if (ns->gid_map.nr_extents != 0) + goto out_unlock; + ns->flags &= ~USERNS_SETGROUPS_ALLOWED; + } + mutex_unlock(&userns_state_mutex); + + /* Report a successful write */ + *ppos = count; + ret = count; +out: + return ret; +out_unlock: + mutex_unlock(&userns_state_mutex); + goto out; +} + +bool userns_may_setgroups(const struct user_namespace *ns) +{ + bool allowed; + + mutex_lock(&userns_state_mutex); + /* It is not safe to use setgroups until a gid mapping in + * the user namespace has been established. + */ + allowed = ns->gid_map.nr_extents != 0; + /* Is setgroups allowed? */ + allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED); + mutex_unlock(&userns_state_mutex); + + return allowed; +} + static void *userns_get(struct task_struct *task) { struct user_namespace *user_ns; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b4defde..423c9e3 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1962,17 +1962,13 @@ static void pool_mayday_timeout(unsigned long __pool) * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. - * - * Return: - * %false if no action was taken and pool->lock stayed locked, %true - * otherwise. */ -static bool maybe_create_worker(struct worker_pool *pool) +static void maybe_create_worker(struct worker_pool *pool) __releases(&pool->lock) __acquires(&pool->lock) { if (!need_to_create_worker(pool)) - return false; + return; restart: spin_unlock_irq(&pool->lock); @@ -1989,7 +1985,7 @@ restart: start_worker(worker); if (WARN_ON_ONCE(need_to_create_worker(pool))) goto restart; - return true; + return; } if (!need_to_create_worker(pool)) @@ -2006,7 +2002,7 @@ restart: spin_lock_irq(&pool->lock); if (need_to_create_worker(pool)) goto restart; - return true; + return; } /** @@ -2019,15 +2015,9 @@ restart: * LOCKING: * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Called only from manager. - * - * Return: - * %false if no action was taken and pool->lock stayed locked, %true - * otherwise. */ -static bool maybe_destroy_workers(struct worker_pool *pool) +static void maybe_destroy_workers(struct worker_pool *pool) { - bool ret = false; - while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; @@ -2041,10 +2031,7 @@ static bool maybe_destroy_workers(struct worker_pool *pool) } destroy_worker(worker); - ret = true; } - - return ret; } /** @@ -2064,16 +2051,14 @@ static bool maybe_destroy_workers(struct worker_pool *pool) * multiple times. Does GFP_KERNEL allocations. * * Return: - * %false if the pool don't need management and the caller can safely start - * processing works, %true indicates that the function released pool->lock - * and reacquired it to perform some management function and that the - * conditions that the caller verified while holding the lock before - * calling the function might no longer be true. + * %false if the pool doesn't need management and the caller can safely + * start processing works, %true if management function was performed and + * the conditions that the caller verified before calling the function may + * no longer be true. */ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; - bool ret = false; /* * Managership is governed by two mutexes - manager_arb and @@ -2097,7 +2082,7 @@ static bool manage_workers(struct worker *worker) * manager_mutex. */ if (!mutex_trylock(&pool->manager_arb)) - return ret; + return false; /* * With manager arbitration won, manager_mutex would be free in @@ -2107,7 +2092,6 @@ static bool manage_workers(struct worker *worker) spin_unlock_irq(&pool->lock); mutex_lock(&pool->manager_mutex); spin_lock_irq(&pool->lock); - ret = true; } pool->flags &= ~POOL_MANAGE_WORKERS; @@ -2116,12 +2100,12 @@ static bool manage_workers(struct worker *worker) * Destroy and then create so that may_start_working() is true * on return. */ - ret |= maybe_destroy_workers(pool); - ret |= maybe_create_worker(pool); + maybe_destroy_workers(pool); + maybe_create_worker(pool); mutex_unlock(&pool->manager_mutex); mutex_unlock(&pool->manager_arb); - return ret; + return true; } /** @@ -2909,19 +2893,57 @@ bool flush_work(struct work_struct *work) } EXPORT_SYMBOL_GPL(flush_work); +struct cwt_wait { + wait_queue_t wait; + struct work_struct *work; +}; + +static int cwt_wakefn(wait_queue_t *wait, unsigned mode, int sync, void *key) +{ + struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait); + + if (cwait->work != key) + return 0; + return autoremove_wake_function(wait, mode, sync, key); +} + static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) { + static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq); unsigned long flags; int ret; do { ret = try_to_grab_pending(work, is_dwork, &flags); /* - * If someone else is canceling, wait for the same event it - * would be waiting for before retrying. + * If someone else is already canceling, wait for it to + * finish. flush_work() doesn't work for PREEMPT_NONE + * because we may get scheduled between @work's completion + * and the other canceling task resuming and clearing + * CANCELING - flush_work() will return false immediately + * as @work is no longer busy, try_to_grab_pending() will + * return -ENOENT as @work is still being canceled and the + * other canceling task won't be able to clear CANCELING as + * we're hogging the CPU. + * + * Let's wait for completion using a waitqueue. As this + * may lead to the thundering herd problem, use a custom + * wake function which matches @work along with exclusive + * wait and wakeup. */ - if (unlikely(ret == -ENOENT)) - flush_work(work); + if (unlikely(ret == -ENOENT)) { + struct cwt_wait cwait; + + init_wait(&cwait.wait); + cwait.wait.func = cwt_wakefn; + cwait.work = work; + + prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait, + TASK_UNINTERRUPTIBLE); + if (work_is_canceling(work)) + schedule(); + finish_wait(&cancel_waitq, &cwait.wait); + } } while (unlikely(ret < 0)); /* tell other tasks trying to grab @work to back off */ @@ -2930,6 +2952,16 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) flush_work(work); clear_work_data(work); + + /* + * Paired with prepare_to_wait() above so that either + * waitqueue_active() is visible here or !work_is_canceling() is + * visible there. + */ + smp_mb(); + if (waitqueue_active(&cancel_waitq)) + __wake_up(&cancel_waitq, TASK_NORMAL, 1, work); + return ret; } diff --git a/lib/assoc_array.c b/lib/assoc_array.c index c0b1007..2404d03 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -1723,11 +1723,13 @@ ascend_old_tree: shortcut = assoc_array_ptr_to_shortcut(ptr); slot = shortcut->parent_slot; cursor = shortcut->back_pointer; + if (!cursor) + goto gc_complete; } else { slot = node->parent_slot; cursor = ptr; } - BUG_ON(!ptr); + BUG_ON(!cursor); node = assoc_array_ptr_to_node(cursor); slot++; goto continue_node; @@ -1735,7 +1737,7 @@ ascend_old_tree: gc_complete: edit->set[0].to = new_root; assoc_array_apply_edit(edit); - edit->array->nr_leaves_on_tree = nr_leaves_on_tree; + array->nr_leaves_on_tree = nr_leaves_on_tree; return 0; enomem: diff --git a/lib/bitmap.c b/lib/bitmap.c index 06f7e4f..c0634aa 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -131,7 +131,9 @@ void __bitmap_shift_right(unsigned long *dst, lower = src[off + k]; if (left && off + k == lim - 1) lower &= mask; - dst[k] = upper << (BITS_PER_LONG - rem) | lower >> rem; + dst[k] = lower >> rem; + if (rem) + dst[k] |= upper << (BITS_PER_LONG - rem); if (left && k == lim - 1) dst[k] &= mask; } @@ -172,7 +174,9 @@ void __bitmap_shift_left(unsigned long *dst, upper = src[k]; if (left && k == lim - 1) upper &= (1UL << left) - 1; - dst[k + off] = lower >> (BITS_PER_LONG - rem) | upper << rem; + dst[k + off] = upper << rem; + if (rem) + dst[k + off] |= lower >> (BITS_PER_LONG - rem); if (left && k + off == lim - 1) dst[k + off] &= (1UL << left) - 1; } @@ -599,12 +603,12 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen, unsigned a, b; int c, old_c, totaldigits; const char __user __force *ubuf = (const char __user __force *)buf; - int exp_digit, in_range; + int at_start, in_range; totaldigits = c = 0; bitmap_zero(maskp, nmaskbits); do { - exp_digit = 1; + at_start = 1; in_range = 0; a = b = 0; @@ -633,11 +637,10 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen, break; if (c == '-') { - if (exp_digit || in_range) + if (at_start || in_range) return -EINVAL; b = 0; in_range = 1; - exp_digit = 1; continue; } @@ -647,16 +650,18 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen, b = b * 10 + (c - '0'); if (!in_range) a = b; - exp_digit = 0; + at_start = 0; totaldigits++; } if (!(a <= b)) return -EINVAL; if (b >= nmaskbits) return -ERANGE; - while (a <= b) { - set_bit(a, maskp); - a++; + if (!at_start) { + while (a <= b) { + set_bit(a, maskp); + a++; + } } } while (buflen && c == ','); return 0; diff --git a/lib/btree.c b/lib/btree.c index f9a4846..4264871 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -198,6 +198,7 @@ EXPORT_SYMBOL_GPL(btree_init); void btree_destroy(struct btree_head *head) { + mempool_free(head->node, head->mempool); mempool_destroy(head->mempool); head->mempool = NULL; } diff --git a/lib/checksum.c b/lib/checksum.c index 129775e..8b39e86 100644 --- a/lib/checksum.c +++ b/lib/checksum.c @@ -181,6 +181,15 @@ csum_partial_copy(const void *src, void *dst, int len, __wsum sum) EXPORT_SYMBOL(csum_partial_copy); #ifndef csum_tcpudp_nofold +static inline u32 from64to32(u64 x) +{ + /* add up 32-bit and 32-bit for 32+c bit */ + x = (x & 0xffffffff) + (x >> 32); + /* add up carry.. */ + x = (x & 0xffffffff) + (x >> 32); + return (u32)x; +} + __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len, unsigned short proto, @@ -195,8 +204,7 @@ __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, #else s += (proto + len) << 8; #endif - s += (s >> 32); - return (__force __wsum)s; + return (__force __wsum)from64to32(s); } EXPORT_SYMBOL(csum_tcpudp_nofold); #endif diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c index 31c5f76..f504027 100644 --- a/lib/decompress_bunzip2.c +++ b/lib/decompress_bunzip2.c @@ -184,7 +184,7 @@ static int INIT get_next_block(struct bunzip_data *bd) if (get_bits(bd, 1)) return RETVAL_OBSOLETE_INPUT; origPtr = get_bits(bd, 24); - if (origPtr > dbufSize) + if (origPtr >= dbufSize) return RETVAL_DATA_ERROR; /* mapping table: if some byte values are never used (encoding things like ascii text), the compression code removes the gaps to have fewer diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 7a85967..f0f5c5c 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -139,6 +139,9 @@ static int lz4_uncompress(const char *source, char *dest, int osize) /* Error: request to write beyond destination buffer */ if (cpy > oend) goto _output_error; + if ((ref + COPYLENGTH) > oend || + (op + COPYLENGTH) > oend) + goto _output_error; LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH)); while (op < cpy) *op++ = *ref++; diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c index 8563081..a1c387f 100644 --- a/lib/lzo/lzo1x_decompress_safe.c +++ b/lib/lzo/lzo1x_decompress_safe.c @@ -19,31 +19,21 @@ #include #include "lzodefs.h" -#define HAVE_IP(t, x) \ - (((size_t)(ip_end - ip) >= (size_t)(t + x)) && \ - (((t + x) >= t) && ((t + x) >= x))) +#define HAVE_IP(x) ((size_t)(ip_end - ip) >= (size_t)(x)) +#define HAVE_OP(x) ((size_t)(op_end - op) >= (size_t)(x)) +#define NEED_IP(x) if (!HAVE_IP(x)) goto input_overrun +#define NEED_OP(x) if (!HAVE_OP(x)) goto output_overrun +#define TEST_LB(m_pos) if ((m_pos) < out) goto lookbehind_overrun -#define HAVE_OP(t, x) \ - (((size_t)(op_end - op) >= (size_t)(t + x)) && \ - (((t + x) >= t) && ((t + x) >= x))) - -#define NEED_IP(t, x) \ - do { \ - if (!HAVE_IP(t, x)) \ - goto input_overrun; \ - } while (0) - -#define NEED_OP(t, x) \ - do { \ - if (!HAVE_OP(t, x)) \ - goto output_overrun; \ - } while (0) - -#define TEST_LB(m_pos) \ - do { \ - if ((m_pos) < out) \ - goto lookbehind_overrun; \ - } while (0) +/* This MAX_255_COUNT is the maximum number of times we can add 255 to a base + * count without overflowing an integer. The multiply will overflow when + * multiplying 255 by more than MAXINT/255. The sum will overflow earlier + * depending on the base count. Since the base count is taken from a u8 + * and a few bits, it is safe to assume that it will always be lower than + * or equal to 2*255, thus we can always prevent any overflow by accepting + * two less 255 steps. See Documentation/lzo.txt for more information. + */ +#define MAX_255_COUNT ((((size_t)~0) / 255) - 2) int lzo1x_decompress_safe(const unsigned char *in, size_t in_len, unsigned char *out, size_t *out_len) @@ -75,17 +65,24 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len, if (t < 16) { if (likely(state == 0)) { if (unlikely(t == 0)) { + size_t offset; + const unsigned char *ip_last = ip; + while (unlikely(*ip == 0)) { - t += 255; ip++; - NEED_IP(1, 0); + NEED_IP(1); } - t += 15 + *ip++; + offset = ip - ip_last; + if (unlikely(offset > MAX_255_COUNT)) + return LZO_E_ERROR; + + offset = (offset << 8) - offset; + t += offset + 15 + *ip++; } t += 3; copy_literal_run: #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) - if (likely(HAVE_IP(t, 15) && HAVE_OP(t, 15))) { + if (likely(HAVE_IP(t + 15) && HAVE_OP(t + 15))) { const unsigned char *ie = ip + t; unsigned char *oe = op + t; do { @@ -101,8 +98,8 @@ copy_literal_run: } else #endif { - NEED_OP(t, 0); - NEED_IP(t, 3); + NEED_OP(t); + NEED_IP(t + 3); do { *op++ = *ip++; } while (--t > 0); @@ -115,7 +112,7 @@ copy_literal_run: m_pos -= t >> 2; m_pos -= *ip++ << 2; TEST_LB(m_pos); - NEED_OP(2, 0); + NEED_OP(2); op[0] = m_pos[0]; op[1] = m_pos[1]; op += 2; @@ -136,13 +133,20 @@ copy_literal_run: } else if (t >= 32) { t = (t & 31) + (3 - 1); if (unlikely(t == 2)) { + size_t offset; + const unsigned char *ip_last = ip; + while (unlikely(*ip == 0)) { - t += 255; ip++; - NEED_IP(1, 0); + NEED_IP(1); } - t += 31 + *ip++; - NEED_IP(2, 0); + offset = ip - ip_last; + if (unlikely(offset > MAX_255_COUNT)) + return LZO_E_ERROR; + + offset = (offset << 8) - offset; + t += offset + 31 + *ip++; + NEED_IP(2); } m_pos = op - 1; next = get_unaligned_le16(ip); @@ -154,13 +158,20 @@ copy_literal_run: m_pos -= (t & 8) << 11; t = (t & 7) + (3 - 1); if (unlikely(t == 2)) { + size_t offset; + const unsigned char *ip_last = ip; + while (unlikely(*ip == 0)) { - t += 255; ip++; - NEED_IP(1, 0); + NEED_IP(1); } - t += 7 + *ip++; - NEED_IP(2, 0); + offset = ip - ip_last; + if (unlikely(offset > MAX_255_COUNT)) + return LZO_E_ERROR; + + offset = (offset << 8) - offset; + t += offset + 7 + *ip++; + NEED_IP(2); } next = get_unaligned_le16(ip); ip += 2; @@ -174,7 +185,7 @@ copy_literal_run: #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) if (op - m_pos >= 8) { unsigned char *oe = op + t; - if (likely(HAVE_OP(t, 15))) { + if (likely(HAVE_OP(t + 15))) { do { COPY8(op, m_pos); op += 8; @@ -184,7 +195,7 @@ copy_literal_run: m_pos += 8; } while (op < oe); op = oe; - if (HAVE_IP(6, 0)) { + if (HAVE_IP(6)) { state = next; COPY4(op, ip); op += next; @@ -192,7 +203,7 @@ copy_literal_run: continue; } } else { - NEED_OP(t, 0); + NEED_OP(t); do { *op++ = *m_pos++; } while (op < oe); @@ -201,7 +212,7 @@ copy_literal_run: #endif { unsigned char *oe = op + t; - NEED_OP(t, 0); + NEED_OP(t); op[0] = m_pos[0]; op[1] = m_pos[1]; op += 2; @@ -214,15 +225,15 @@ match_next: state = next; t = next; #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) - if (likely(HAVE_IP(6, 0) && HAVE_OP(4, 0))) { + if (likely(HAVE_IP(6) && HAVE_OP(4))) { COPY4(op, ip); op += t; ip += t; } else #endif { - NEED_IP(t, 3); - NEED_OP(t, 0); + NEED_IP(t + 3); + NEED_OP(t); while (t > 0) { *op++ = *ip++; t--; diff --git a/lib/plist.c b/lib/plist.c index 1ebc95f..0f2084d 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -134,6 +134,46 @@ void plist_del(struct plist_node *node, struct plist_head *head) plist_check_head(head); } +/** + * plist_requeue - Requeue @node at end of same-prio entries. + * + * This is essentially an optimized plist_del() followed by + * plist_add(). It moves an entry already in the plist to + * after any other same-priority entries. + * + * @node: &struct plist_node pointer - entry to be moved + * @head: &struct plist_head pointer - list head + */ +void plist_requeue(struct plist_node *node, struct plist_head *head) +{ + struct plist_node *iter; + struct list_head *node_next = &head->node_list; + + plist_check_head(head); + BUG_ON(plist_head_empty(head)); + BUG_ON(plist_node_empty(node)); + + if (node == plist_last(head)) + return; + + iter = plist_next(node); + + if (node->prio != iter->prio) + return; + + plist_del(node, head); + + plist_for_each_continue(iter, head) { + if (node->prio != iter->prio) { + node_next = &iter->node_list; + break; + } + } + list_add_tail(&node->node_list, node_next); + + plist_check_head(head); +} + #ifdef CONFIG_DEBUG_PI_LIST #include #include @@ -170,6 +210,14 @@ static void __init plist_test_check(int nr_expect) BUG_ON(prio_pos->prio_list.next != &first->prio_list); } +static void __init plist_test_requeue(struct plist_node *node) +{ + plist_requeue(node, &test_head); + + if (node != plist_last(&test_head)) + BUG_ON(node->prio == plist_next(node)->prio); +} + static int __init plist_test(void) { int nr_expect = 0, i, loop; @@ -193,6 +241,10 @@ static int __init plist_test(void) nr_expect--; } plist_test_check(nr_expect); + if (!plist_node_empty(test_node + i)) { + plist_test_requeue(test_node + i); + plist_test_check(nr_expect); + } } for (i = 0; i < ARRAY_SIZE(test_node); i++) { diff --git a/lib/radix-tree.c b/lib/radix-tree.c index bd4a8df..7e30d2a 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -946,81 +946,6 @@ next: } EXPORT_SYMBOL(radix_tree_range_tag_if_tagged); - -/** - * radix_tree_next_hole - find the next hole (not-present entry) - * @root: tree root - * @index: index key - * @max_scan: maximum range to search - * - * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the lowest - * indexed hole. - * - * Returns: the index of the hole if found, otherwise returns an index - * outside of the set specified (in which case 'return - index >= max_scan' - * will be true). In rare cases of index wrap-around, 0 will be returned. - * - * radix_tree_next_hole may be called under rcu_read_lock. However, like - * radix_tree_gang_lookup, this will not atomically search a snapshot of - * the tree at a single point in time. For example, if a hole is created - * at index 5, then subsequently a hole is created at index 10, - * radix_tree_next_hole covering both indexes may return 10 if called - * under rcu_read_lock. - */ -unsigned long radix_tree_next_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan) -{ - unsigned long i; - - for (i = 0; i < max_scan; i++) { - if (!radix_tree_lookup(root, index)) - break; - index++; - if (index == 0) - break; - } - - return index; -} -EXPORT_SYMBOL(radix_tree_next_hole); - -/** - * radix_tree_prev_hole - find the prev hole (not-present entry) - * @root: tree root - * @index: index key - * @max_scan: maximum range to search - * - * Search backwards in the range [max(index-max_scan+1, 0), index] - * for the first hole. - * - * Returns: the index of the hole if found, otherwise returns an index - * outside of the set specified (in which case 'index - return >= max_scan' - * will be true). In rare cases of wrap-around, ULONG_MAX will be returned. - * - * radix_tree_next_hole may be called under rcu_read_lock. However, like - * radix_tree_gang_lookup, this will not atomically search a snapshot of - * the tree at a single point in time. For example, if a hole is created - * at index 10, then subsequently a hole is created at index 5, - * radix_tree_prev_hole covering both indexes may return 5 if called under - * rcu_read_lock. - */ -unsigned long radix_tree_prev_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan) -{ - unsigned long i; - - for (i = 0; i < max_scan; i++) { - if (!radix_tree_lookup(root, index)) - break; - index--; - if (index == ULONG_MAX) - break; - } - - return index; -} -EXPORT_SYMBOL(radix_tree_prev_hole); - /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root @@ -1337,15 +1262,18 @@ static inline void radix_tree_shrink(struct radix_tree_root *root) } /** - * radix_tree_delete - delete an item from a radix tree + * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key + * @item: expected item * - * Remove the item at @index from the radix tree rooted at @root. + * Remove @item at @index from the radix tree rooted at @root. * - * Returns the address of the deleted item, or NULL if it was not present. + * Returns the address of the deleted item, or NULL if it was not present + * or the entry at the given @index was not @item. */ -void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) +void *radix_tree_delete_item(struct radix_tree_root *root, + unsigned long index, void *item) { struct radix_tree_node *node = NULL; struct radix_tree_node *slot = NULL; @@ -1380,6 +1308,11 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) if (slot == NULL) goto out; + if (item && slot != item) { + slot = NULL; + goto out; + } + /* * Clear all tags associated with the item to be deleted. * This way of doing it would be inefficient, but seldom is any set. @@ -1424,6 +1357,21 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) out: return slot; } +EXPORT_SYMBOL(radix_tree_delete_item); + +/** + * radix_tree_delete - delete an item from a radix tree + * @root: radix tree root + * @index: index key + * + * Remove the item at @index from the radix tree rooted at @root. + * + * Returns the address of the deleted item, or NULL if it was not present. + */ +void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) +{ + return radix_tree_delete_item(root, index, NULL); +} EXPORT_SYMBOL(radix_tree_delete); /** diff --git a/lib/string.c b/lib/string.c index e5878de..cb9ea21 100644 --- a/lib/string.c +++ b/lib/string.c @@ -586,6 +586,22 @@ void *memset(void *s, int c, size_t count) EXPORT_SYMBOL(memset); #endif +/** + * memzero_explicit - Fill a region of memory (e.g. sensitive + * keying data) with 0s. + * @s: Pointer to the start of the area. + * @count: The size of the area. + * + * memzero_explicit() doesn't need an arch-specific version as + * it just invokes the one of memset() implicitly. + */ +void memzero_explicit(void *s, size_t count) +{ + memset(s, 0, count); + barrier(); +} +EXPORT_SYMBOL(memzero_explicit); + #ifndef __HAVE_ARCH_MEMCPY /** * memcpy - Copy one area of memory to another diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index a28df52..1164961 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -57,7 +57,8 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, return res + find_zero(data) + 1 - align; } res += sizeof(unsigned long); - if (unlikely(max < sizeof(unsigned long))) + /* We already handled 'unsigned long' bytes. Did we do it all ? */ + if (unlikely(max <= sizeof(unsigned long))) break; max -= sizeof(unsigned long); if (unlikely(__get_user(c,(unsigned long __user *)(src+res)))) diff --git a/mm/Makefile b/mm/Makefile index b2aa3cc..2bad2e00 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -16,7 +16,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ - compaction.o balloon_compaction.o \ + compaction.o balloon_compaction.o vmacache.o \ interval_tree.o list_lru.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/compaction.c b/mm/compaction.c index 5f702ef..a522208 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -89,7 +89,8 @@ static void __reset_isolation_suitable(struct zone *zone) unsigned long end_pfn = zone_end_pfn(zone); unsigned long pfn; - zone->compact_cached_migrate_pfn = start_pfn; + zone->compact_cached_migrate_pfn[0] = start_pfn; + zone->compact_cached_migrate_pfn[1] = start_pfn; zone->compact_cached_free_pfn = end_pfn; zone->compact_blockskip_flush = false; @@ -131,9 +132,10 @@ void reset_isolation_suitable(pg_data_t *pgdat) */ static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, - bool migrate_scanner) + bool set_unsuitable, bool migrate_scanner) { struct zone *zone = cc->zone; + unsigned long pfn; if (cc->ignore_skip_hint) return; @@ -141,20 +143,32 @@ static void update_pageblock_skip(struct compact_control *cc, if (!page) return; - if (!nr_isolated) { - unsigned long pfn = page_to_pfn(page); + if (nr_isolated) + return; + + /* + * Only skip pageblocks when all forms of compaction will be known to + * fail in the near future. + */ + if (set_unsuitable) set_pageblock_skip(page); - /* Update where compaction should restart */ - if (migrate_scanner) { - if (!cc->finished_update_migrate && - pfn > zone->compact_cached_migrate_pfn) - zone->compact_cached_migrate_pfn = pfn; - } else { - if (!cc->finished_update_free && - pfn < zone->compact_cached_free_pfn) - zone->compact_cached_free_pfn = pfn; - } + pfn = page_to_pfn(page); + + /* Update where async and sync compaction should restart */ + if (migrate_scanner) { + if (cc->finished_update_migrate) + return; + if (pfn > zone->compact_cached_migrate_pfn[0]) + zone->compact_cached_migrate_pfn[0] = pfn; + if (cc->mode != MIGRATE_ASYNC && + pfn > zone->compact_cached_migrate_pfn[1]) + zone->compact_cached_migrate_pfn[1] = pfn; + } else { + if (cc->finished_update_free) + return; + if (pfn < zone->compact_cached_free_pfn) + zone->compact_cached_free_pfn = pfn; } } #else @@ -166,7 +180,7 @@ static inline bool isolation_suitable(struct compact_control *cc, static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, - bool migrate_scanner) + bool set_unsuitable, bool migrate_scanner) { } #endif /* CONFIG_COMPACTION */ @@ -195,7 +209,7 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags, } /* async aborts if taking too long or contended */ - if (!cc->sync) { + if (cc->mode == MIGRATE_ASYNC) { cc->contended = true; return false; } @@ -208,30 +222,39 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags, return true; } -static inline bool compact_trylock_irqsave(spinlock_t *lock, - unsigned long *flags, struct compact_control *cc) +/* + * Aside from avoiding lock contention, compaction also periodically checks + * need_resched() and either schedules in sync compaction or aborts async + * compaction. This is similar to what compact_checklock_irqsave() does, but + * is used where no lock is concerned. + * + * Returns false when no scheduling was needed, or sync compaction scheduled. + * Returns true when async compaction should abort. + */ +static inline bool compact_should_abort(struct compact_control *cc) { - return compact_checklock_irqsave(lock, flags, false, cc); + /* async compaction aborts if contended */ + if (need_resched()) { + if (cc->mode == MIGRATE_ASYNC) { + cc->contended = true; + return true; + } + + cond_resched(); + } + + return false; } /* Returns true if the page is within a block suitable for migration to */ static bool suitable_migration_target(struct page *page) { - int migratetype = get_pageblock_migratetype(page); - - /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ - if (migratetype == MIGRATE_RESERVE) - return false; - - if (is_migrate_isolate(migratetype)) - return false; - - /* If the page is a large free page, then allow migration */ + /* If the page is a large free page, then disallow migration */ if (PageBuddy(page) && page_order(page) >= pageblock_order) - return true; + return false; /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ - if (migrate_async_suitable(migratetype)) + if (migrate_async_suitable(get_pageblock_migratetype(page))) return true; /* Otherwise skip the block */ @@ -253,6 +276,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, struct page *cursor, *valid_page = NULL; unsigned long flags; bool locked = false; + bool checked_pageblock = false; cursor = pfn_to_page(blockpfn); @@ -284,8 +308,16 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, break; /* Recheck this is a suitable migration target under lock */ - if (!strict && !suitable_migration_target(page)) - break; + if (!strict && !checked_pageblock) { + /* + * We need to check suitability of pageblock only once + * and this isolate_freepages_block() is called with + * pageblock range, so just check once is sufficient. + */ + checked_pageblock = true; + if (!suitable_migration_target(page)) + break; + } /* Recheck this is a buddy page under lock */ if (!PageBuddy(page)) @@ -329,7 +361,8 @@ isolate_fail: /* Update the pageblock-skip if the whole pageblock was scanned */ if (blockpfn == end_pfn) - update_pageblock_skip(cc, valid_page, total_isolated, false); + update_pageblock_skip(cc, valid_page, total_isolated, true, + false); count_compact_events(COMPACTFREE_SCANNED, nr_scanned); if (total_isolated) @@ -460,12 +493,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, unsigned long last_pageblock_nr = 0, pageblock_nr; unsigned long nr_scanned = 0, nr_isolated = 0; struct list_head *migratelist = &cc->migratepages; - isolate_mode_t mode = 0; struct lruvec *lruvec; unsigned long flags; bool locked = false; struct page *page = NULL, *valid_page = NULL; - bool skipped_async_unsuitable = false; + bool set_unsuitable = true; + const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ? + ISOLATE_ASYNC_MIGRATE : 0) | + (unevictable ? ISOLATE_UNEVICTABLE : 0); /* * Ensure that there are not too many pages isolated from the LRU @@ -474,7 +509,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, */ while (unlikely(too_many_isolated(zone))) { /* async migration should just abort */ - if (!cc->sync) + if (cc->mode == MIGRATE_ASYNC) return 0; congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -483,11 +518,13 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, return 0; } + if (compact_should_abort(cc)) + return 0; + /* Time to isolate some pages for migration */ - cond_resched(); for (; low_pfn < end_pfn; low_pfn++) { /* give a chance to irqs before checking need_resched() */ - if (locked && !((low_pfn+1) % SWAP_CLUSTER_MAX)) { + if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) { if (should_release_lock(&zone->lru_lock)) { spin_unlock_irqrestore(&zone->lru_lock, flags); locked = false; @@ -526,8 +563,25 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, /* If isolation recently failed, do not retry */ pageblock_nr = low_pfn >> pageblock_order; - if (!isolation_suitable(cc, page)) - goto next_pageblock; + if (last_pageblock_nr != pageblock_nr) { + int mt; + + last_pageblock_nr = pageblock_nr; + if (!isolation_suitable(cc, page)) + goto next_pageblock; + + /* + * For async migration, also only scan in MOVABLE + * blocks. Async migration is optimistic to see if + * the minimum amount of work satisfies the allocation + */ + mt = get_pageblock_migratetype(page); + if (cc->mode == MIGRATE_ASYNC && + !migrate_async_suitable(mt)) { + set_unsuitable = false; + goto next_pageblock; + } + } /* * Skip if free. page_order cannot be used without zone->lock @@ -537,18 +591,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; /* - * For async migration, also only scan in MOVABLE blocks. Async - * migration is optimistic to see if the minimum amount of work - * satisfies the allocation - */ - if (!cc->sync && last_pageblock_nr != pageblock_nr && - !migrate_async_suitable(get_pageblock_migratetype(page))) { - cc->finished_update_migrate = true; - skipped_async_unsuitable = true; - goto next_pageblock; - } - - /* * Check may be lockless but that's ok as we recheck later. * It's possible to migrate LRU pages and balloon pages * Skip any other type of page @@ -557,11 +599,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, if (unlikely(balloon_page_movable(page))) { if (locked && balloon_page_isolate(page)) { /* Successfully isolated */ - cc->finished_update_migrate = true; - list_add(&page->lru, migratelist); - cc->nr_migratepages++; - nr_isolated++; - goto check_compact_cluster; + goto isolate_success; } } continue; @@ -584,6 +622,15 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } + /* + * Migration will fail if an anonymous page is pinned in memory, + * so avoid taking lru_lock and isolating it unnecessarily in an + * admittedly racy check. + */ + if (!page_mapping(page) && + page_count(page) > page_mapcount(page)) + continue; + /* Check if it is ok to still hold the lock */ locked = compact_checklock_irqsave(&zone->lru_lock, &flags, locked, cc); @@ -598,12 +645,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } - if (!cc->sync) - mode |= ISOLATE_ASYNC_MIGRATE; - - if (unevictable) - mode |= ISOLATE_UNEVICTABLE; - lruvec = mem_cgroup_page_lruvec(page, zone); /* Try isolate the page */ @@ -613,13 +654,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, VM_BUG_ON_PAGE(PageTransCompound(page), page); /* Successfully isolated */ - cc->finished_update_migrate = true; del_page_from_lru_list(page, lruvec, page_lru(page)); + +isolate_success: + cc->finished_update_migrate = true; list_add(&page->lru, migratelist); cc->nr_migratepages++; nr_isolated++; -check_compact_cluster: /* Avoid isolating too much */ if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) { ++low_pfn; @@ -630,7 +672,6 @@ check_compact_cluster: next_pageblock: low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1; - last_pageblock_nr = pageblock_nr; } acct_isolated(zone, locked, cc); @@ -641,11 +682,10 @@ next_pageblock: /* * Update the pageblock-skip information and cached scanner pfn, * if the whole pageblock was scanned without isolating any page. - * This is not done when pageblock was skipped due to being unsuitable - * for async compaction, so that eventual sync compaction can try. */ - if (low_pfn == end_pfn && !skipped_async_unsuitable) - update_pageblock_skip(cc, valid_page, nr_isolated, true); + if (low_pfn == end_pfn) + update_pageblock_skip(cc, valid_page, nr_isolated, + set_unsuitable, true); trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); @@ -666,7 +706,9 @@ static void isolate_freepages(struct zone *zone, struct compact_control *cc) { struct page *page; - unsigned long high_pfn, low_pfn, pfn, z_end_pfn; + unsigned long block_start_pfn; /* start of current pageblock */ + unsigned long block_end_pfn; /* end of current pageblock */ + unsigned long low_pfn; /* lowest pfn scanner is able to scan */ int nr_freepages = cc->nr_freepages; struct list_head *freelist = &cc->freepages; @@ -674,41 +716,38 @@ static void isolate_freepages(struct zone *zone, * Initialise the free scanner. The starting point is where we last * successfully isolated from, zone-cached value, or the end of the * zone when isolating for the first time. We need this aligned to - * the pageblock boundary, because we do pfn -= pageblock_nr_pages - * in the for loop. + * the pageblock boundary, because we do + * block_start_pfn -= pageblock_nr_pages in the for loop. + * For ending point, take care when isolating in last pageblock of a + * a zone which ends in the middle of a pageblock. * The low boundary is the end of the pageblock the migration scanner * is using. */ - pfn = cc->free_pfn & ~(pageblock_nr_pages-1); + block_start_pfn = cc->free_pfn & ~(pageblock_nr_pages-1); + block_end_pfn = min(block_start_pfn + pageblock_nr_pages, + zone_end_pfn(zone)); low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages); /* - * Take care that if the migration scanner is at the end of the zone - * that the free scanner does not accidentally move to the next zone - * in the next isolation cycle. - */ - high_pfn = min(low_pfn, pfn); - - z_end_pfn = zone_end_pfn(zone); - - /* * Isolate free pages until enough are available to migrate the * pages on cc->migratepages. We stop searching if the migrate * and free page scanners meet or enough free pages are isolated. */ - for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages; - pfn -= pageblock_nr_pages) { + for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages; + block_end_pfn = block_start_pfn, + block_start_pfn -= pageblock_nr_pages) { unsigned long isolated; - unsigned long end_pfn; /* * This can iterate a massively long zone without finding any * suitable migration targets, so periodically check if we need - * to schedule. + * to schedule, or even abort async compaction. */ - cond_resched(); + if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages)) + && compact_should_abort(cc)) + break; - if (!pfn_valid(pfn)) + if (!pfn_valid(block_start_pfn)) continue; /* @@ -718,7 +757,7 @@ static void isolate_freepages(struct zone *zone, * i.e. it's possible that all pages within a zones range of * pages do not belong to a single zone. */ - page = pfn_to_page(pfn); + page = pfn_to_page(block_start_pfn); if (page_zone(page) != zone) continue; @@ -731,26 +770,26 @@ static void isolate_freepages(struct zone *zone, continue; /* Found a block suitable for isolating free pages from */ - isolated = 0; + cc->free_pfn = block_start_pfn; + isolated = isolate_freepages_block(cc, block_start_pfn, + block_end_pfn, freelist, false); + nr_freepages += isolated; /* - * Take care when isolating in last pageblock of a zone which - * ends in the middle of a pageblock. + * Set a flag that we successfully isolated in this pageblock. + * In the next loop iteration, zone->compact_cached_free_pfn + * will not be updated and thus it will effectively contain the + * highest pageblock we isolated pages from. */ - end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn); - isolated = isolate_freepages_block(cc, pfn, end_pfn, - freelist, false); - nr_freepages += isolated; + if (isolated) + cc->finished_update_free = true; /* - * Record the highest PFN we isolated pages from. When next - * looking for free pages, the search will restart here as - * page migration may have returned some pages to the allocator + * isolate_freepages_block() might have aborted due to async + * compaction being contended */ - if (isolated) { - cc->finished_update_free = true; - high_pfn = max(high_pfn, pfn); - } + if (cc->contended) + break; } /* split_free_page does not map the pages */ @@ -760,10 +799,9 @@ static void isolate_freepages(struct zone *zone, * If we crossed the migrate scanner, we want to keep it that way * so that compact_finished() may detect this */ - if (pfn < low_pfn) - cc->free_pfn = max(pfn, zone->zone_start_pfn); - else - cc->free_pfn = high_pfn; + if (block_start_pfn < low_pfn) + cc->free_pfn = cc->migrate_pfn; + cc->nr_freepages = nr_freepages; } @@ -778,9 +816,13 @@ static struct page *compaction_alloc(struct page *migratepage, struct compact_control *cc = (struct compact_control *)data; struct page *freepage; - /* Isolate free pages if necessary */ + /* + * Isolate free pages if necessary, and if we are not aborting due to + * contention. + */ if (list_empty(&cc->freepages)) { - isolate_freepages(cc->zone, cc); + if (!cc->contended) + isolate_freepages(cc->zone, cc); if (list_empty(&cc->freepages)) return NULL; @@ -794,23 +836,16 @@ static struct page *compaction_alloc(struct page *migratepage, } /* - * We cannot control nr_migratepages and nr_freepages fully when migration is - * running as migrate_pages() has no knowledge of compact_control. When - * migration is complete, we count the number of pages on the lists by hand. + * This is a migrate-callback that "frees" freepages back to the isolated + * freelist. All pages on the freelist are from the same zone, so there is no + * special handling needed for NUMA. */ -static void update_nr_listpages(struct compact_control *cc) +static void compaction_free(struct page *page, unsigned long data) { - int nr_migratepages = 0; - int nr_freepages = 0; - struct page *page; - - list_for_each_entry(page, &cc->migratepages, lru) - nr_migratepages++; - list_for_each_entry(page, &cc->freepages, lru) - nr_freepages++; + struct compact_control *cc = (struct compact_control *)data; - cc->nr_migratepages = nr_migratepages; - cc->nr_freepages = nr_freepages; + list_add(&page->lru, &cc->freepages); + cc->nr_freepages++; } /* possible outcome of isolate_migratepages */ @@ -857,13 +892,14 @@ static int compact_finished(struct zone *zone, unsigned int order; unsigned long watermark; - if (fatal_signal_pending(current)) + if (cc->contended || fatal_signal_pending(current)) return COMPACT_PARTIAL; /* Compaction run completes if the migrate and free scanner meet */ if (cc->free_pfn <= cc->migrate_pfn) { /* Let the next compaction start anew. */ - zone->compact_cached_migrate_pfn = zone->zone_start_pfn; + zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn; + zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn; zone->compact_cached_free_pfn = zone_end_pfn(zone); /* @@ -901,7 +937,7 @@ static int compact_finished(struct zone *zone, return COMPACT_PARTIAL; /* Job done if allocation would set block type */ - if (cc->order >= pageblock_order && area->nr_free) + if (order >= pageblock_order && area->nr_free) return COMPACT_PARTIAL; } @@ -963,6 +999,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) int ret; unsigned long start_pfn = zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(zone); + const bool sync = cc->mode != MIGRATE_ASYNC; ret = compaction_suitable(zone, cc->order); switch (ret) { @@ -988,7 +1025,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) * information on where the scanners should start but check that it * is initialised by ensuring the values are within zone boundaries. */ - cc->migrate_pfn = zone->compact_cached_migrate_pfn; + cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync]; cc->free_pfn = zone->compact_cached_free_pfn; if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) { cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1); @@ -996,7 +1033,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) { cc->migrate_pfn = start_pfn; - zone->compact_cached_migrate_pfn = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; } trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn); @@ -1004,7 +1042,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) migrate_prep_local(); while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) { - unsigned long nr_migrate, nr_remaining; int err; switch (isolate_migratepages(zone, cc)) { @@ -1019,21 +1056,20 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) ; } - nr_migrate = cc->nr_migratepages; + if (!cc->nr_migratepages) + continue; + err = migrate_pages(&cc->migratepages, compaction_alloc, - (unsigned long)cc, - cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC, + compaction_free, (unsigned long)cc, cc->mode, MR_COMPACTION); - update_nr_listpages(cc); - nr_remaining = cc->nr_migratepages; - trace_mm_compaction_migratepages(nr_migrate - nr_remaining, - nr_remaining); + trace_mm_compaction_migratepages(cc->nr_migratepages, err, + &cc->migratepages); - /* Release isolated pages not migrated */ + /* All pages were either migrated or will be released */ + cc->nr_migratepages = 0; if (err) { putback_movable_pages(&cc->migratepages); - cc->nr_migratepages = 0; /* * migrate_pages() may return -ENOMEM when scanners meet * and we want compact_finished() to detect it @@ -1055,9 +1091,8 @@ out: return ret; } -static unsigned long compact_zone_order(struct zone *zone, - int order, gfp_t gfp_mask, - bool sync, bool *contended) +static unsigned long compact_zone_order(struct zone *zone, int order, + gfp_t gfp_mask, enum migrate_mode mode, bool *contended) { unsigned long ret; struct compact_control cc = { @@ -1066,7 +1101,7 @@ static unsigned long compact_zone_order(struct zone *zone, .order = order, .migratetype = allocflags_to_migratetype(gfp_mask), .zone = zone, - .sync = sync, + .mode = mode, }; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); @@ -1088,7 +1123,7 @@ int sysctl_extfrag_threshold = 500; * @order: The order of the current allocation * @gfp_mask: The GFP mask of the current allocation * @nodemask: The allowed nodes to allocate from - * @sync: Whether migration is synchronous or not + * @mode: The migration mode for async, sync light, or sync migration * @contended: Return value that is true if compaction was aborted due to lock contention * @page: Optionally capture a free page of the requested order during compaction * @@ -1096,7 +1131,7 @@ int sysctl_extfrag_threshold = 500; */ unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, - bool sync, bool *contended) + enum migrate_mode mode, bool *contended) { enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; @@ -1121,7 +1156,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, nodemask) { int status; - status = compact_zone_order(zone, order, gfp_mask, sync, + status = compact_zone_order(zone, order, gfp_mask, mode, contended); rc = max(status, rc); @@ -1160,9 +1195,6 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) if (zone_watermark_ok(zone, cc->order, low_wmark_pages(zone), 0, 0)) compaction_defer_reset(zone, cc->order, false); - /* Currently async compaction is never deferred. */ - else if (cc->sync) - defer_compaction(zone, cc->order); } VM_BUG_ON(!list_empty(&cc->freepages)); @@ -1174,7 +1206,7 @@ void compact_pgdat(pg_data_t *pgdat, int order) { struct compact_control cc = { .order = order, - .sync = false, + .mode = MIGRATE_ASYNC, }; if (!order) @@ -1187,7 +1219,8 @@ static void compact_node(int nid) { struct compact_control cc = { .order = -1, - .sync = true, + .mode = MIGRATE_SYNC, + .ignore_skip_hint = true, }; __compact_pgdat(NODE_DATA(nid), &cc); diff --git a/mm/filemap.c b/mm/filemap.c index 7a13f6a..217cfd3 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -192,9 +192,11 @@ static int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ - if (test_and_clear_bit(AS_ENOSPC, &mapping->flags)) + if (test_bit(AS_ENOSPC, &mapping->flags) && + test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; - if (test_and_clear_bit(AS_EIO, &mapping->flags)) + if (test_bit(AS_EIO, &mapping->flags) && + test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } @@ -446,6 +448,29 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); +static int page_cache_tree_insert(struct address_space *mapping, + struct page *page) +{ + void **slot; + int error; + + slot = radix_tree_lookup_slot(&mapping->page_tree, page->index); + if (slot) { + void *p; + + p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); + if (!radix_tree_exceptional_entry(p)) + return -EEXIST; + radix_tree_replace_slot(slot, page); + mapping->nrpages++; + return 0; + } + error = radix_tree_insert(&mapping->page_tree, page->index, page); + if (!error) + mapping->nrpages++; + return error; +} + /** * add_to_page_cache_locked - add a locked page to the pagecache * @page: page to add @@ -480,11 +505,10 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, page->index = offset; spin_lock_irq(&mapping->tree_lock); - error = radix_tree_insert(&mapping->page_tree, offset, page); + error = page_cache_tree_insert(mapping, page); radix_tree_preload_end(); if (unlikely(error)) goto err_insert; - mapping->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); spin_unlock_irq(&mapping->tree_lock); trace_mm_filemap_add_to_page_cache(page); @@ -520,10 +544,10 @@ struct page *__page_cache_alloc(gfp_t gfp) if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); page = alloc_pages_exact_node(n, gfp, 0); - } while (!put_mems_allowed(cpuset_mems_cookie) && !page); + } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); return page; } @@ -620,8 +644,17 @@ EXPORT_SYMBOL(unlock_page); */ void end_page_writeback(struct page *page) { - if (TestClearPageReclaim(page)) + /* + * TestClearPageReclaim could be used here but it is an atomic + * operation and overkill in this particular case. Failing to + * shuffle a page marked for immediate reclaim is too mild to + * justify taking an atomic operation penalty at the end of + * ever page writeback. + */ + if (PageReclaim(page)) { + ClearPageReclaim(page); rotate_reclaimable_page(page); + } if (!test_clear_page_writeback(page)) BUG(); @@ -686,14 +719,101 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, } /** - * find_get_page - find and get a page reference + * page_cache_next_hole - find the next hole (not-present entry) + * @mapping: mapping + * @index: index + * @max_scan: maximum range to search + * + * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the + * lowest indexed hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'return - index >= + * max_scan' will be true). In rare cases of index wrap-around, 0 will + * be returned. + * + * page_cache_next_hole may be called under rcu_read_lock. However, + * like radix_tree_gang_lookup, this will not atomically search a + * snapshot of the tree at a single point in time. For example, if a + * hole is created at index 5, then subsequently a hole is created at + * index 10, page_cache_next_hole covering both indexes may return 10 + * if called under rcu_read_lock. + */ +pgoff_t page_cache_next_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + struct page *page; + + page = radix_tree_lookup(&mapping->page_tree, index); + if (!page || radix_tree_exceptional_entry(page)) + break; + index++; + if (index == 0) + break; + } + + return index; +} +EXPORT_SYMBOL(page_cache_next_hole); + +/** + * page_cache_prev_hole - find the prev hole (not-present entry) + * @mapping: mapping + * @index: index + * @max_scan: maximum range to search + * + * Search backwards in the range [max(index-max_scan+1, 0), index] for + * the first hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'index - return >= + * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX + * will be returned. + * + * page_cache_prev_hole may be called under rcu_read_lock. However, + * like radix_tree_gang_lookup, this will not atomically search a + * snapshot of the tree at a single point in time. For example, if a + * hole is created at index 10, then subsequently a hole is created at + * index 5, page_cache_prev_hole covering both indexes may return 5 if + * called under rcu_read_lock. + */ +pgoff_t page_cache_prev_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + struct page *page; + + page = radix_tree_lookup(&mapping->page_tree, index); + if (!page || radix_tree_exceptional_entry(page)) + break; + index--; + if (index == ULONG_MAX) + break; + } + + return index; +} +EXPORT_SYMBOL(page_cache_prev_hole); + +/** + * find_get_entry - find and get a page cache entry * @mapping: the address_space to search - * @offset: the page index + * @offset: the page cache index * - * Is there a pagecache struct page at the given (mapping, offset) tuple? - * If yes, increment its refcount and return it; if no, return NULL. + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. + * + * If the slot holds a shadow entry of a previously evicted page, it + * is returned. + * + * Otherwise, %NULL is returned. */ -struct page *find_get_page(struct address_space *mapping, pgoff_t offset) +struct page *find_get_entry(struct address_space *mapping, pgoff_t offset) { void **pagep; struct page *page; @@ -734,24 +854,30 @@ out: return page; } -EXPORT_SYMBOL(find_get_page); +EXPORT_SYMBOL(find_get_entry); /** - * find_lock_page - locate, pin and lock a pagecache page + * find_lock_entry - locate, pin and lock a page cache entry * @mapping: the address_space to search - * @offset: the page index + * @offset: the page cache index * - * Locates the desired pagecache page, locks it, increments its reference - * count and returns its address. + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. * - * Returns zero if the page was not present. find_lock_page() may sleep. + * If the slot holds a shadow entry of a previously evicted page, it + * is returned. + * + * Otherwise, %NULL is returned. + * + * find_lock_entry() may sleep. */ -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) +struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset) { struct page *page; repeat: - page = find_get_page(mapping, offset); + page = find_get_entry(mapping, offset); if (page && !radix_tree_exception(page)) { lock_page(page); /* Has the page been truncated? */ @@ -764,44 +890,86 @@ repeat: } return page; } -EXPORT_SYMBOL(find_lock_page); +EXPORT_SYMBOL(find_lock_entry); /** - * find_or_create_page - locate or add a pagecache page - * @mapping: the page's address_space - * @index: the page's index into the mapping - * @gfp_mask: page allocation mode + * pagecache_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * @fgp_flags: PCG flags + * @gfp_mask: gfp mask to use for the page cache data page allocation + * + * Looks up the page cache slot at @mapping & @offset. * - * Locates a page in the pagecache. If the page is not present, a new page - * is allocated using @gfp_mask and is added to the pagecache and to the VM's - * LRU list. The returned page is locked and has its reference count - * incremented. + * PCG flags modify how the page is returned * - * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic - * allocation! + * FGP_ACCESSED: the page will be marked accessed + * FGP_LOCK: Page is return locked + * FGP_CREAT: If page is not present then a new page is allocated using + * @gfp_mask and added to the page cache and the VM's LRU + * list. The page is returned locked and with an increased + * refcount. Otherwise, %NULL is returned. * - * find_or_create_page() returns the desired page's address, or zero on - * memory exhaustion. + * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even + * if the GFP flags specified for FGP_CREAT are atomic. + * + * If there is a page cache page, it is returned with an increased refcount. */ -struct page *find_or_create_page(struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask) +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t gfp_mask) { struct page *page; - int err; + repeat: - page = find_lock_page(mapping, index); - if (!page) { + page = find_get_entry(mapping, offset); + if (radix_tree_exceptional_entry(page)) + page = NULL; + if (!page) + goto no_page; + + if (fgp_flags & FGP_LOCK) { + if (fgp_flags & FGP_NOWAIT) { + if (!trylock_page(page)) { + page_cache_release(page); + return NULL; + } + } else { + lock_page(page); + } + + /* Has the page been truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + page_cache_release(page); + goto repeat; + } + VM_BUG_ON(page->index != offset); + } + + if (page && (fgp_flags & FGP_ACCESSED)) + mark_page_accessed(page); + +no_page: + if (!page && (fgp_flags & FGP_CREAT)) { + int err; + if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping)) + gfp_mask |= __GFP_WRITE; + if (fgp_flags & FGP_NOFS) + gfp_mask &= ~__GFP_FS; + page = __page_cache_alloc(gfp_mask); if (!page) return NULL; - /* - * We want a regular kernel memory (not highmem or DMA etc) - * allocation for the radix tree nodes, but we need to honour - * the context-specific requirements the caller has asked for. - * GFP_RECLAIM_MASK collects those requirements. - */ - err = add_to_page_cache_lru(page, mapping, index, - (gfp_mask & GFP_RECLAIM_MASK)); + + if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK))) + fgp_flags |= FGP_LOCK; + + /* Init accessed so avoit atomic mark_page_accessed later */ + if (fgp_flags & FGP_ACCESSED) + init_page_accessed(page); + + err = add_to_page_cache_lru(page, mapping, offset, + gfp_mask & GFP_RECLAIM_MASK); if (unlikely(err)) { page_cache_release(page); page = NULL; @@ -809,9 +977,80 @@ repeat: goto repeat; } } + return page; } -EXPORT_SYMBOL(find_or_create_page); +EXPORT_SYMBOL(pagecache_get_page); + +/** + * find_get_entries - gang pagecache lookup + * @mapping: The address_space to search + * @start: The starting page cache index + * @nr_entries: The maximum number of entries + * @entries: Where the resulting entries are placed + * @indices: The cache indices corresponding to the entries in @entries + * + * find_get_entries() will search for and return a group of up to + * @nr_entries entries in the mapping. The entries are placed at + * @entries. find_get_entries() takes a reference against any actual + * pages it returns. + * + * The search returns a group of mapping-contiguous page cache entries + * with ascending indexes. There may be holes in the indices due to + * not-present pages. + * + * Any shadow entries of evicted pages are included in the returned + * array. + * + * find_get_entries() returns the number of pages and shadow entries + * which were found. + */ +unsigned find_get_entries(struct address_space *mapping, + pgoff_t start, unsigned int nr_entries, + struct page **entries, pgoff_t *indices) +{ + void **slot; + unsigned int ret = 0; + struct radix_tree_iter iter; + + if (!nr_entries) + return 0; + + rcu_read_lock(); +restart: + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + struct page *page; +repeat: + page = radix_tree_deref_slot(slot); + if (unlikely(!page)) + continue; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + goto restart; + /* + * Otherwise, we must be storing a swap entry + * here as an exceptional entry: so return it + * without attempting to raise page count. + */ + goto export; + } + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *slot)) { + page_cache_release(page); + goto repeat; + } +export: + indices[ret] = iter.index; + entries[ret] = page; + if (++ret == nr_entries) + break; + } + rcu_read_unlock(); + return ret; +} /** * find_get_pages - gang pagecache lookup @@ -1031,39 +1270,6 @@ repeat: } EXPORT_SYMBOL(find_get_pages_tag); -/** - * grab_cache_page_nowait - returns locked page at given index in given cache - * @mapping: target address_space - * @index: the page index - * - * Same as grab_cache_page(), but do not wait if the page is unavailable. - * This is intended for speculative data generators, where the data can - * be regenerated if the page couldn't be grabbed. This routine should - * be safe to call while holding the lock for another page. - * - * Clear __GFP_FS when allocating the page to avoid recursion into the fs - * and deadlock against the caller's locked page. - */ -struct page * -grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) -{ - struct page *page = find_get_page(mapping, index); - - if (page) { - if (trylock_page(page)) - return page; - page_cache_release(page); - return NULL; - } - page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS); - if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) { - page_cache_release(page); - page = NULL; - } - return page; -} -EXPORT_SYMBOL(grab_cache_page_nowait); - /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: @@ -1795,6 +2001,18 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); +static struct page *wait_on_page_read(struct page *page) +{ + if (!IS_ERR(page)) { + wait_on_page_locked(page); + if (!PageUptodate(page)) { + page_cache_release(page); + page = ERR_PTR(-EIO); + } + } + return page; +} + static struct page *__read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), @@ -1821,6 +2039,8 @@ repeat: if (err < 0) { page_cache_release(page); page = ERR_PTR(err); + } else { + page = wait_on_page_read(page); } } return page; @@ -1857,6 +2077,10 @@ retry: if (err < 0) { page_cache_release(page); return ERR_PTR(err); + } else { + page = wait_on_page_read(page); + if (IS_ERR(page)) + return page; } out: mark_page_accessed(page); @@ -1864,40 +2088,25 @@ out: } /** - * read_cache_page_async - read into page cache, fill it if needed + * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read * @data: first arg to filler(data, page) function, often left as NULL * - * Same as read_cache_page, but don't wait for page to become unlocked - * after submitting it to the filler. - * * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page but don't wait for it to become unlocked. + * not set, try to fill the page and wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. */ -struct page *read_cache_page_async(struct address_space *mapping, +struct page *read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); } -EXPORT_SYMBOL(read_cache_page_async); - -static struct page *wait_on_page_read(struct page *page) -{ - if (!IS_ERR(page)) { - wait_on_page_locked(page); - if (!PageUptodate(page)) { - page_cache_release(page); - page = ERR_PTR(-EIO); - } - } - return page; -} +EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. @@ -1916,31 +2125,10 @@ struct page *read_cache_page_gfp(struct address_space *mapping, { filler_t *filler = (filler_t *)mapping->a_ops->readpage; - return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp)); + return do_read_cache_page(mapping, index, filler, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); -/** - * read_cache_page - read into page cache, fill it if needed - * @mapping: the page's address_space - * @index: the page index - * @filler: function to perform the read - * @data: first arg to filler(data, page) function, often left as NULL - * - * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page then wait for it to become unlocked. - * - * If the page does not get brought uptodate, return -EIO. - */ -struct page *read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data) -{ - return wait_on_page_read(read_cache_page_async(mapping, index, filler, data)); -} -EXPORT_SYMBOL(read_cache_page); - static size_t __iovec_copy_from_user_inatomic(char *vaddr, const struct iovec *iov, size_t base, size_t bytes) { @@ -1974,7 +2162,6 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, char *kaddr; size_t copied; - BUG_ON(!in_atomic()); kaddr = kmap_atomic(page); if (likely(i->nr_segs == 1)) { int left; @@ -2184,7 +2371,6 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, { const struct address_space_operations *aops = mapping->a_ops; - mark_page_accessed(page); return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); @@ -2266,34 +2452,17 @@ EXPORT_SYMBOL(generic_file_direct_write); struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { - int status; - gfp_t gfp_mask; struct page *page; - gfp_t gfp_notmask = 0; + int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT; - gfp_mask = mapping_gfp_mask(mapping); - if (mapping_cap_account_dirty(mapping)) - gfp_mask |= __GFP_WRITE; if (flags & AOP_FLAG_NOFS) - gfp_notmask = __GFP_FS; -repeat: - page = find_lock_page(mapping, index); + fgp_flags |= FGP_NOFS; + + page = pagecache_get_page(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); if (page) - goto found; + wait_for_stable_page(page); - page = __page_cache_alloc(gfp_mask & ~gfp_notmask); - if (!page) - return NULL; - status = add_to_page_cache_lru(page, mapping, index, - GFP_KERNEL & ~gfp_notmask); - if (unlikely(status)) { - page_cache_release(page); - if (status == -EEXIST) - goto repeat; - return NULL; - } -found: - wait_for_stable_page(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); @@ -2342,18 +2511,15 @@ again: status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); - if (unlikely(status)) + if (unlikely(status < 0)) break; if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); - pagefault_enable(); flush_dcache_page(page); - mark_page_accessed(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) diff --git a/mm/frontswap.c b/mm/frontswap.c index 1b24bdc..f2a3571 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -244,8 +244,10 @@ int __frontswap_store(struct page *page) the (older) page from frontswap */ inc_frontswap_failed_stores(); - if (dup) + if (dup) { __frontswap_clear(sis, offset); + frontswap_ops->invalidate_page(type, offset); + } } if (frontswap_writethrough_enabled) /* report failure so swap also writes to swap device */ @@ -327,15 +329,12 @@ EXPORT_SYMBOL(__frontswap_invalidate_area); static unsigned long __frontswap_curr_pages(void) { - int type; unsigned long totalpages = 0; struct swap_info_struct *si = NULL; assert_spin_locked(&swap_lock); - for (type = swap_list.head; type >= 0; type = si->next) { - si = swap_info[type]; + plist_for_each_entry(si, &swap_active_head, list) totalpages += atomic_read(&si->frontswap_pages); - } return totalpages; } @@ -347,11 +346,9 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, int si_frontswap_pages; unsigned long total_pages_to_unuse = total; unsigned long pages = 0, pages_to_unuse = 0; - int type; assert_spin_locked(&swap_lock); - for (type = swap_list.head; type >= 0; type = si->next) { - si = swap_info[type]; + plist_for_each_entry(si, &swap_active_head, list) { si_frontswap_pages = atomic_read(&si->frontswap_pages); if (total_pages_to_unuse < si_frontswap_pages) { pages = pages_to_unuse = total_pages_to_unuse; @@ -366,7 +363,7 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, } vm_unacct_memory(pages); *unused = pages_to_unuse; - *swapid = type; + *swapid = si->type; ret = 0; break; } @@ -413,7 +410,7 @@ void frontswap_shrink(unsigned long target_pages) /* * we don't want to hold swap_lock while doing a very * lengthy try_to_unuse, but swap_list may change - * so restart scan from swap_list.head each time + * so restart scan from swap_active_head each time */ spin_lock(&swap_lock); ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1c42d0c..adce656 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -199,7 +199,7 @@ retry: preempt_disable(); if (cmpxchg(&huge_zero_page, NULL, zero_page)) { preempt_enable(); - __free_page(zero_page); + __free_pages(zero_page, compound_order(zero_page)); goto retry; } @@ -231,7 +231,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); - __free_page(zero_page); + __free_pages(zero_page, compound_order(zero_page)); return HPAGE_PMD_NR; } @@ -1819,21 +1819,24 @@ static int __split_huge_page_map(struct page *page, if (pmd) { pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); + if (pmd_write(*pmd)) + BUG_ON(page_mapcount(page) != 1); haddr = address; for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { pte_t *pte, entry; BUG_ON(PageCompound(page+i)); + /* + * Note that pmd_numa is not transferred deliberately + * to avoid any possibility that pte_numa leaks to + * a PROT_NONE VMA by accident. + */ entry = mk_pte(page + i, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (!pmd_write(*pmd)) entry = pte_wrprotect(entry); - else - BUG_ON(page_mapcount(page) != 1); if (!pmd_young(*pmd)) entry = pte_mkold(entry); - if (pmd_numa(*pmd)) - entry = pte_mknuma(entry); pte = pte_offset_map(&_pmd, haddr); BUG_ON(!pte_none(*pte)); set_pte_at(mm, haddr, pte, entry); @@ -2270,6 +2273,30 @@ static void khugepaged_alloc_sleep(void) static int khugepaged_node_load[MAX_NUMNODES]; +static bool khugepaged_scan_abort(int nid) +{ + int i; + + /* + * If zone_reclaim_mode is disabled, then no extra effort is made to + * allocate memory locally. + */ + if (!zone_reclaim_mode) + return false; + + /* If there is a count for this node already, it must be acceptable */ + if (khugepaged_node_load[nid]) + return false; + + for (i = 0; i < MAX_NUMNODES; i++) { + if (!khugepaged_node_load[i]) + continue; + if (node_distance(nid, i) > RECLAIM_DISTANCE) + return true; + } + return false; +} + #ifdef CONFIG_NUMA static int khugepaged_find_target_node(void) { @@ -2586,6 +2613,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, * hit record. */ node = page_to_nid(page); + if (khugepaged_scan_abort(node)) + goto out_unmap; khugepaged_node_load[node]++; VM_BUG_ON_PAGE(PageCompound(page), page); if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 30dd626..c3e8660 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -540,7 +540,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, goto err; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = huge_zonelist(vma, address, htlb_alloc_mask(h), &mpol, &nodemask); @@ -562,7 +562,7 @@ retry_cpuset: } mpol_cond_put(mpol); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -2071,6 +2071,9 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, unsigned long tmp; int ret; + if (!hugepages_supported()) + return -ENOTSUPP; + tmp = h->max_huge_pages; if (write && h->order >= MAX_ORDER) @@ -2124,6 +2127,9 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, unsigned long tmp; int ret; + if (!hugepages_supported()) + return -ENOTSUPP; + tmp = h->nr_overcommit_huge_pages; if (write && h->order >= MAX_ORDER) @@ -2149,6 +2155,8 @@ out: void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h = &default_hstate; + if (!hugepages_supported()) + return; seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" @@ -2165,6 +2173,8 @@ void hugetlb_report_meminfo(struct seq_file *m) int hugetlb_report_node_meminfo(int nid, char *buf) { struct hstate *h = &default_hstate; + if (!hugepages_supported()) + return 0; return sprintf(buf, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" @@ -2179,6 +2189,9 @@ void hugetlb_show_meminfo(void) struct hstate *h; int nid; + if (!hugepages_supported()) + return; + for_each_node_state(nid, N_MEMORY) for_each_hstate(h) pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", @@ -2422,6 +2435,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, } else { if (cow) huge_ptep_set_wrprotect(src, addr, src_pte); + entry = huge_ptep_get(src_pte); ptepage = pte_page(entry); get_page(ptepage); page_dup_rmap(ptepage); @@ -2474,9 +2488,10 @@ again: goto unlock; /* - * HWPoisoned hugepage is already unmapped and dropped reference + * Migrating hugepage or HWPoisoned hugepage is already + * unmapped and its refcount is dropped, so just clear pte here. */ - if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { + if (unlikely(!pte_present(pte))) { huge_pte_clear(mm, address, ptep); goto unlock; } @@ -3149,7 +3164,26 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, spin_unlock(ptl); continue; } - if (!huge_pte_none(huge_ptep_get(ptep))) { + pte = huge_ptep_get(ptep); + if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { + spin_unlock(ptl); + continue; + } + if (unlikely(is_hugetlb_entry_migration(pte))) { + swp_entry_t entry = pte_to_swp_entry(pte); + + if (is_write_migration_entry(entry)) { + pte_t newpte; + + make_migration_entry_read(&entry); + newpte = swp_entry_to_pte(entry); + set_huge_pte_at(mm, address, ptep, newpte); + pages++; + } + spin_unlock(ptl); + continue; + } + if (!huge_pte_none(pte)) { pte = huge_ptep_get_and_clear(mm, address, ptep); pte = pte_mkhuge(huge_pte_modify(pte, newprot)); pte = arch_make_huge_pte(pte, vma, NULL, 0); @@ -3442,6 +3476,8 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, { struct page *page; + if (!pmd_present(*pmd)) + return NULL; page = pte_page(*(pte_t *)pmd); if (page) page += ((address & ~PMD_MASK) >> PAGE_SHIFT); diff --git a/mm/internal.h b/mm/internal.h index 3e91000..1a8a0d4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -11,6 +11,7 @@ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H +#include #include void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, @@ -21,6 +22,20 @@ static inline void set_page_count(struct page *page, int v) atomic_set(&page->_count, v); } +extern int __do_page_cache_readahead(struct address_space *mapping, + struct file *filp, pgoff_t offset, unsigned long nr_to_read, + unsigned long lookahead_size); + +/* + * Submit IO for the read-ahead request in file_ra_state. + */ +static inline unsigned long ra_submit(struct file_ra_state *ra, + struct address_space *mapping, struct file *filp) +{ + return __do_page_cache_readahead(mapping, filp, + ra->start, ra->size, ra->async_size); +} + /* * Turn a non-refcounted page (->_count == 0) into refcounted with * a count of one. @@ -119,7 +134,7 @@ struct compact_control { unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ - bool sync; /* Synchronous migration */ + enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool finished_update_free; /* True when the zone cached pfns are * no longer being updated @@ -129,7 +144,10 @@ struct compact_control { int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; - bool contended; /* True if a lock was contended */ + bool contended; /* True if a lock was contended, or + * need_resched() true during async + * compaction + */ }; unsigned long diff --git a/mm/ksm.c b/mm/ksm.c index 68710e8..5e706e3 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -376,7 +376,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) else ret = VM_FAULT_WRITE; put_page(page); - } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM))); + } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); /* * We must loop because handle_mm_fault() may back out if there's * any difficulty e.g. if pte accessed bit gets updated concurrently. diff --git a/mm/madvise.c b/mm/madvise.c index 539eeb9..a402f8f 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -195,7 +195,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, for (; start < end; start += PAGE_SIZE) { index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - page = find_get_page(mapping, index); + page = find_get_entry(mapping, index); if (!radix_tree_exceptional_entry(page)) { if (page) page_cache_release(page); diff --git a/mm/memblock.c b/mm/memblock.c index f3a07a4..dfee4aa 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -183,8 +183,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid) { - int ret; - phys_addr_t kernel_end; + phys_addr_t kernel_end, ret; /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5b6b003..b58d4fb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -292,6 +292,9 @@ struct mem_cgroup { /* vmpressure notifications */ struct vmpressure vmpressure; + /* css_online() has been completed */ + int initialized; + /* * the counter to account for mem+swap usage. */ @@ -1127,9 +1130,21 @@ skip_node: * skipping css reference should be safe. */ if (next_css) { - if ((next_css == &root->css) || - ((next_css->flags & CSS_ONLINE) && css_tryget(next_css))) - return mem_cgroup_from_css(next_css); + struct mem_cgroup *memcg = mem_cgroup_from_css(next_css); + + if (next_css == &root->css) + return memcg; + + if (css_tryget(next_css)) { + /* + * Make sure the memcg is initialized: + * mem_cgroup_css_online() orders the the + * initialization against setting the flag. + */ + if (smp_load_acquire(&memcg->initialized)) + return memcg; + css_put(next_css); + } prev_css = next_css; goto skip_node; @@ -5670,8 +5685,12 @@ static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg) { struct mem_cgroup_eventfd_list *ev; + spin_lock(&memcg_oom_lock); + list_for_each_entry(ev, &memcg->oom_notify, list) eventfd_signal(ev->eventfd, 1); + + spin_unlock(&memcg_oom_lock); return 0; } @@ -6534,6 +6553,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css)); + int ret; if (css->cgroup->id > MEM_CGROUP_ID_MAX) return -ENOSPC; @@ -6570,7 +6590,18 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) } mutex_unlock(&memcg_create_mutex); - return memcg_init_kmem(memcg, &mem_cgroup_subsys); + ret = memcg_init_kmem(memcg, &mem_cgroup_subsys); + if (ret) + return ret; + + /* + * Make sure the memcg is initialized: mem_cgroup_iter() + * orders reading memcg->initialized against its callers + * reading the memcg members. + */ + smp_store_release(&memcg->initialized, 1); + + return 0; } /* diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 33365e9..42aeb84 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1149,10 +1149,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * The check (unnecessarily) ignores LRU pages being isolated and * walked by the page reclaim code, however that's not a big loss. */ - if (!PageHuge(p) && !PageTransTail(p)) { - if (!PageLRU(p)) - shake_page(p, 0); - if (!PageLRU(p)) { + if (!PageHuge(p)) { + if (!PageLRU(hpage)) + shake_page(hpage, 0); + if (!PageLRU(hpage)) { /* * shake_page could have turned it free. */ @@ -1510,6 +1510,8 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) */ ret = __get_any_page(page, pfn, 0); if (!PageLRU(page)) { + /* Drop page reference which is from __get_any_page() */ + put_page(page); pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", pfn, page->flags); return -EIO; @@ -1540,7 +1542,7 @@ static int soft_offline_huge_page(struct page *page, int flags) /* Keep page count to indicate a given hugepage is isolated. */ list_move(&hpage->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { pr_info("soft offline: %#lx: migration failed %d, type %lx\n", @@ -1621,7 +1623,7 @@ static int __soft_offline_page(struct page *page, int flags) inc_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); list_add(&page->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { if (!list_empty(&pagelist)) { @@ -1645,8 +1647,6 @@ static int __soft_offline_page(struct page *page, int flags) * setting PG_hwpoison. */ if (!is_free_buddy_page(page)) - lru_add_drain_all(); - if (!is_free_buddy_page(page)) drain_all_pages(); SetPageHWPoison(page); if (!is_free_buddy_page(page)) @@ -1725,12 +1725,12 @@ int soft_offline_page(struct page *page, int flags) } else if (ret == 0) { /* for free pages */ if (PageHuge(page)) { set_page_hwpoison_huge_page(hpage); - dequeue_hwpoisoned_huge_page(hpage); - atomic_long_add(1 << compound_order(hpage), + if (!dequeue_hwpoisoned_huge_page(hpage)) + atomic_long_add(1 << compound_order(hpage), &num_poisoned_pages); } else { - SetPageHWPoison(page); - atomic_long_inc(&num_poisoned_pages); + if (!TestSetPageHWPoison(page)) + atomic_long_inc(&num_poisoned_pages); } } unset_migratetype_isolate(page, MIGRATE_MOVABLE); diff --git a/mm/memory.c b/mm/memory.c index 2121d8b8..e9ddc7a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -808,20 +808,20 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (!pte_file(pte)) { swp_entry_t entry = pte_to_swp_entry(pte); - if (swap_duplicate(entry) < 0) - return entry.val; - - /* make sure dst_mm is on swapoff's mmlist. */ - if (unlikely(list_empty(&dst_mm->mmlist))) { - spin_lock(&mmlist_lock); - if (list_empty(&dst_mm->mmlist)) - list_add(&dst_mm->mmlist, - &src_mm->mmlist); - spin_unlock(&mmlist_lock); - } - if (likely(!non_swap_entry(entry))) + if (likely(!non_swap_entry(entry))) { + if (swap_duplicate(entry) < 0) + return entry.val; + + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } rss[MM_SWAPENTS]++; - else if (is_migration_entry(entry)) { + } else if (is_migration_entry(entry)) { page = migration_entry_to_page(entry); if (PageAnon(page)) @@ -878,7 +878,7 @@ out_set_pte: return 0; } -int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, +static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { @@ -1120,7 +1120,7 @@ again: addr) != page->index) { pte_t ptfile = pgoff_to_pte(page->index); if (pte_soft_dirty(ptent)) - pte_file_mksoft_dirty(ptfile); + ptfile = pte_file_mksoft_dirty(ptfile); set_pte_at(mm, addr, pte, ptfile); } if (PageAnon(page)) @@ -1836,7 +1836,8 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, else return -EFAULT; } - if (ret & VM_FAULT_SIGBUS) + if (ret & (VM_FAULT_SIGBUS | + VM_FAULT_SIGSEGV)) return i ? i : -EFAULT; BUG(); } @@ -1946,7 +1947,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, return -ENOMEM; if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return -EHWPOISON; - if (ret & VM_FAULT_SIGBUS) + if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; BUG(); } @@ -3204,7 +3205,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo if (prev && prev->vm_end == address) return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM; - expand_downwards(vma, address - PAGE_SIZE); + return expand_downwards(vma, address - PAGE_SIZE); } if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { struct vm_area_struct *next = vma->vm_next; @@ -3213,7 +3214,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo if (next && next->vm_start == address + PAGE_SIZE) return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM; - expand_upwards(vma, address + PAGE_SIZE); + return expand_upwards(vma, address + PAGE_SIZE); } return 0; } @@ -3233,9 +3234,13 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, pte_unmap(page_table); + /* File mapping without ->vm_ops ? */ + if (vma->vm_flags & VM_SHARED) + return VM_FAULT_SIGBUS; + /* Check if we need to add a guard page to the stack */ if (check_stack_guard_page(vma, address) < 0) - return VM_FAULT_SIGBUS; + return VM_FAULT_SIGSEGV; /* Use the zero-page for reads */ if (!(flags & FAULT_FLAG_WRITE)) { @@ -3501,6 +3506,9 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; pte_unmap(page_table); + /* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ + if (!vma->vm_ops->fault) + return VM_FAULT_SIGBUS; return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } @@ -3646,14 +3654,12 @@ static int handle_pte_fault(struct mm_struct *mm, pte_t entry; spinlock_t *ptl; - entry = *pte; + entry = ACCESS_ONCE(*pte); if (!pte_present(entry)) { if (pte_none(entry)) { - if (vma->vm_ops) { - if (likely(vma->vm_ops->fault)) - return do_linear_fault(mm, vma, address, + if (vma->vm_ops) + return do_linear_fault(mm, vma, address, pte, pmd, flags, entry); - } return do_anonymous_page(mm, vma, address, pte, pmd, flags); } @@ -4024,7 +4030,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, if (follow_phys(vma, addr, write, &prot, &phys_addr)) return -EINVAL; - maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot); + maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (write) memcpy_toio(maddr + offset, buf, len); else diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a650db2..5bba3b3 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1016,6 +1016,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) return NULL; arch_refresh_nodedata(nid, pgdat); + } else { + /* Reset the nr_zones and classzone_idx to 0 before reuse */ + pgdat->nr_zones = 0; + pgdat->classzone_idx = 0; } /* we can use NODE_DATA(nid) from here */ @@ -1332,7 +1336,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) * alloc_migrate_target should be improooooved!! * migrate_pages returns # of failed pages. */ - ret = migrate_pages(&source, alloc_migrate_target, 0, + ret = migrate_pages(&source, alloc_migrate_target, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) putback_movable_pages(&source); @@ -1860,18 +1864,11 @@ void try_offline_node(int nid) * wait_table may be allocated from boot memory, * here only free if it's allocated by vmalloc. */ - if (is_vmalloc_addr(zone->wait_table)) + if (is_vmalloc_addr(zone->wait_table)) { vfree(zone->wait_table); + zone->wait_table = NULL; + } } - - /* - * Since there is no way to guarentee the address of pgdat/zone is not - * on stack of any kernel threads or used by other kernel objects - * without reference counting or other symchronizing method, do not - * reset node_data and free pgdat here. Just reset it to 0 and reuse - * the memory when the node is online again. - */ - memset(pgdat, 0, sizeof(*pgdat)); } EXPORT_SYMBOL(try_offline_node); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 15a8ea0..936866e 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1060,7 +1060,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_node_page, dest, + err = migrate_pages(&pagelist, new_node_page, NULL, dest, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); @@ -1306,7 +1306,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); - nr_failed = migrate_pages(&pagelist, new_page, + nr_failed = migrate_pages(&pagelist, new_page, NULL, start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_movable_pages(&pagelist); @@ -1897,7 +1897,7 @@ int node_random(const nodemask_t *maskp) * If the effective policy is 'BIND, returns a pointer to the mempolicy's * @nodemask for filtering the zonelist. * - * Must be protected by get_mems_allowed() + * Must be protected by read_mems_allowed_begin() */ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, @@ -2061,7 +2061,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, retry_cpuset: pol = get_vma_policy(current, vma, addr); - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); if (unlikely(pol->mode == MPOL_INTERLEAVE)) { unsigned nid; @@ -2069,7 +2069,7 @@ retry_cpuset: nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -2079,7 +2079,7 @@ retry_cpuset: policy_nodemask(gfp, pol)); if (unlikely(mpol_needs_cond_ref(pol))) __mpol_put(pol); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; } @@ -2113,7 +2113,7 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) pol = &default_policy; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); /* * No reference counting needed for current->mempolicy @@ -2126,7 +2126,7 @@ retry_cpuset: policy_zonelist(gfp, pol, numa_node_id()), policy_nodemask(gfp, pol)); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -2663,7 +2663,7 @@ static void __init check_numabalancing_enable(void) if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); - if (nr_node_ids > 1 && !numabalancing_override) { + if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. " "Configure with numa_balancing= or the " "kernel.numa_balancing sysctl", diff --git a/mm/migrate.c b/mm/migrate.c index bed4880..3acac4a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -148,8 +148,11 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); if (pte_swp_soft_dirty(*ptep)) pte = pte_mksoft_dirty(pte); + + /* Recheck VMA as permissions can change since migration started */ if (is_write_migration_entry(entry)) - pte = pte_mkwrite(pte); + pte = maybe_mkwrite(pte, vma); + #ifdef CONFIG_HUGETLB_PAGE if (PageHuge(new)) { pte = pte_mkhuge(pte); @@ -938,8 +941,9 @@ out: * Obtain the lock on page, remove all ptes and migrate the page * to the newly allocated page in newpage. */ -static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, enum migrate_mode mode) +static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page, + unsigned long private, struct page *page, int force, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -983,11 +987,18 @@ out: page_is_file_cache(page)); putback_lru_page(page); } + /* - * Move the new page to the LRU. If migration was not successful - * then this will free the page. + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, putback_lru_page() will drop the reference grabbed + * during isolation. */ - putback_lru_page(newpage); + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) { + ClearPageSwapBacked(newpage); + put_new_page(newpage, private); + } else + putback_lru_page(newpage); + if (result) { if (rc) *result = rc; @@ -1016,8 +1027,9 @@ out: * will wait in the page fault for migration to complete. */ static int unmap_and_move_huge_page(new_page_t get_new_page, - unsigned long private, struct page *hpage, - int force, enum migrate_mode mode) + free_page_t put_new_page, unsigned long private, + struct page *hpage, int force, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -1056,20 +1068,30 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (!page_mapped(hpage)) rc = move_to_new_page(new_hpage, hpage, 1, mode); - if (rc) + if (rc != MIGRATEPAGE_SUCCESS) remove_migration_ptes(hpage, hpage); if (anon_vma) put_anon_vma(anon_vma); - if (!rc) + if (rc == MIGRATEPAGE_SUCCESS) hugetlb_cgroup_migrate(hpage, new_hpage); unlock_page(hpage); out: if (rc != -EAGAIN) putback_active_hugepage(hpage); - put_page(new_hpage); + + /* + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, put_page() will drop the reference grabbed during + * isolation. + */ + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) + put_new_page(new_hpage, private); + else + put_page(new_hpage); + if (result) { if (rc) *result = rc; @@ -1086,6 +1108,8 @@ out: * @from: The list of pages to be migrated. * @get_new_page: The function used to allocate free pages to be used * as the target of the page migration. + * @put_new_page: The function used to free target pages if migration + * fails, or NULL if no special handling is necessary. * @private: Private data to be passed on to get_new_page() * @mode: The migration mode that specifies the constraints for * page migration, if any. @@ -1099,7 +1123,8 @@ out: * Returns the number of pages that were not migrated, or an error code. */ int migrate_pages(struct list_head *from, new_page_t get_new_page, - unsigned long private, enum migrate_mode mode, int reason) + free_page_t put_new_page, unsigned long private, + enum migrate_mode mode, int reason) { int retry = 1; int nr_failed = 0; @@ -1121,10 +1146,11 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, if (PageHuge(page)) rc = unmap_and_move_huge_page(get_new_page, - private, page, pass > 2, mode); + put_new_page, private, page, + pass > 2, mode); else - rc = unmap_and_move(get_new_page, private, - page, pass > 2, mode); + rc = unmap_and_move(get_new_page, put_new_page, + private, page, pass > 2, mode); switch(rc) { case -ENOMEM: @@ -1273,7 +1299,7 @@ set_status: err = 0; if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_page_node, + err = migrate_pages(&pagelist, new_page_node, NULL, (unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); @@ -1729,7 +1755,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, list_add(&page->lru, &migratepages); nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, - node, MIGRATE_ASYNC, MR_NUMA_MISPLACED); + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); diff --git a/mm/mincore.c b/mm/mincore.c index 1016233..725c809 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -70,13 +70,21 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) * any other file mapping (ie. marked !present and faulted in with * tmpfs's .fault). So swapped out tmpfs mappings are tested here. */ - page = find_get_page(mapping, pgoff); #ifdef CONFIG_SWAP - /* shmem/tmpfs may return swap: account for swapcache page too. */ - if (radix_tree_exceptional_entry(page)) { - swp_entry_t swap = radix_to_swp_entry(page); - page = find_get_page(swap_address_space(swap), swap.val); - } + if (shmem_mapping(mapping)) { + page = find_get_entry(mapping, pgoff); + /* + * shmem/tmpfs may return swap: account for swapcache + * page too. + */ + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swp = radix_to_swp_entry(page); + page = find_get_page(swap_address_space(swp), swp.val); + } + } else + page = find_get_page(mapping, pgoff); +#else + page = find_get_page(mapping, pgoff); #endif if (page) { present = PageUptodate(page); diff --git a/mm/mmap.c b/mm/mmap.c index 20ff0c3..d4c97ba 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -128,7 +129,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed); */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { - unsigned long free, allowed, reserve; + long free, allowed, reserve; vm_acct_memory(pages); @@ -192,7 +193,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) */ if (mm) { reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); - allowed -= min(mm->total_vm / 32, reserve); + allowed -= min_t(long, mm->total_vm / 32, reserve); } if (percpu_counter_read_positive(&vm_committed_as) < allowed) @@ -681,8 +682,9 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, prev->vm_next = next = vma->vm_next; if (next) next->vm_prev = prev; - if (mm->mmap_cache == vma) - mm->mmap_cache = prev; + + /* Kill the cache */ + vmacache_invalidate(mm); } /* @@ -743,8 +745,11 @@ again: remove_next = 1 + (end > next->vm_end); * shrinking vma had, to cover any anon pages imported. */ if (exporter && exporter->anon_vma && !importer->anon_vma) { - if (anon_vma_clone(importer, exporter)) - return -ENOMEM; + int error; + + error = anon_vma_clone(importer, exporter); + if (error) + return error; importer->anon_vma = exporter->anon_vma; } } @@ -1989,34 +1994,33 @@ EXPORT_SYMBOL(get_unmapped_area); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { - struct vm_area_struct *vma = NULL; + struct rb_node *rb_node; + struct vm_area_struct *vma; /* Check the cache first. */ - /* (Cache hit rate is typically around 35%.) */ - vma = ACCESS_ONCE(mm->mmap_cache); - if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) { - struct rb_node *rb_node; + vma = vmacache_find(mm, addr); + if (likely(vma)) + return vma; - rb_node = mm->mm_rb.rb_node; - vma = NULL; + rb_node = mm->mm_rb.rb_node; + vma = NULL; - while (rb_node) { - struct vm_area_struct *vma_tmp; - - vma_tmp = rb_entry(rb_node, - struct vm_area_struct, vm_rb); - - if (vma_tmp->vm_end > addr) { - vma = vma_tmp; - if (vma_tmp->vm_start <= addr) - break; - rb_node = rb_node->rb_left; - } else - rb_node = rb_node->rb_right; - } - if (vma) - mm->mmap_cache = vma; + while (rb_node) { + struct vm_area_struct *tmp; + + tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); + + if (tmp->vm_end > addr) { + vma = tmp; + if (tmp->vm_start <= addr) + break; + rb_node = rb_node->rb_left; + } else + rb_node = rb_node->rb_right; } + + if (vma) + vmacache_update(addr, vma); return vma; } @@ -2054,14 +2058,17 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns { struct mm_struct *mm = vma->vm_mm; struct rlimit *rlim = current->signal->rlim; - unsigned long new_start; + unsigned long new_start, actual_size; /* address space limit tests */ if (!may_expand_vm(mm, grow)) return -ENOMEM; /* Stack limit test */ - if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) + actual_size = size; + if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN))) + actual_size -= PAGE_SIZE; + if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) return -ENOMEM; /* mlock limit tests */ @@ -2388,7 +2395,9 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, } else mm->highest_vm_end = prev ? prev->vm_end : 0; tail_vma->vm_next = NULL; - mm->mmap_cache = NULL; /* Kill the cache. */ + + /* Kill the cache */ + vmacache_invalidate(mm); } /* @@ -2425,7 +2434,8 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, if (err) goto out_free_vma; - if (anon_vma_clone(new, vma)) + err = anon_vma_clone(new, vma); + if (err) goto out_free_mpol; if (new->vm_file) diff --git a/mm/nommu.c b/mm/nommu.c index 8740213..76b3f90 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -15,6 +15,7 @@ #include #include +#include #include #include #include @@ -768,16 +769,23 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) */ static void delete_vma_from_mm(struct vm_area_struct *vma) { + int i; struct address_space *mapping; struct mm_struct *mm = vma->vm_mm; + struct task_struct *curr = current; kenter("%p", vma); protect_vma(vma, 0); mm->map_count--; - if (mm->mmap_cache == vma) - mm->mmap_cache = NULL; + for (i = 0; i < VMACACHE_SIZE; i++) { + /* if the vma is cached, invalidate the entire cache */ + if (curr->vmacache[i] == vma) { + vmacache_invalidate(curr->mm); + break; + } + } /* remove the VMA from the mapping */ if (vma->vm_file) { @@ -825,8 +833,8 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) struct vm_area_struct *vma; /* check the cache first */ - vma = ACCESS_ONCE(mm->mmap_cache); - if (vma && vma->vm_start <= addr && vma->vm_end > addr) + vma = vmacache_find(mm, addr); + if (likely(vma)) return vma; /* trawl the list (there may be multiple mappings in which addr @@ -835,7 +843,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) if (vma->vm_start > addr) return NULL; if (vma->vm_end > addr) { - mm->mmap_cache = vma; + vmacache_update(addr, vma); return vma; } } @@ -874,8 +882,8 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, unsigned long end = addr + len; /* check the cache first */ - vma = mm->mmap_cache; - if (vma && vma->vm_start == addr && vma->vm_end == end) + vma = vmacache_find_exact(mm, addr, end); + if (vma) return vma; /* trawl the list (there may be multiple mappings in which addr @@ -886,7 +894,7 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, if (vma->vm_start > addr) return NULL; if (vma->vm_end == end) { - mm->mmap_cache = vma; + vmacache_update(addr, vma); return vma; } } @@ -1897,7 +1905,7 @@ EXPORT_SYMBOL(unmap_mapping_range); */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { - unsigned long free, allowed, reserve; + long free, allowed, reserve; vm_acct_memory(pages); @@ -1961,7 +1969,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) */ if (mm) { reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); - allowed -= min(mm->total_vm / 32, reserve); + allowed -= min_t(long, mm->total_vm / 32, reserve); } if (percpu_counter_read_positive(&vm_committed_as) < allowed) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 3291e82..171c00f 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -406,6 +406,23 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, dump_tasks(memcg, nodemask); } +/* + * Number of OOM killer invocations (including memcg OOM killer). + * Primarily used by PM freezer to check for potential races with + * OOM killed frozen task. + */ +static atomic_t oom_kills = ATOMIC_INIT(0); + +int oom_kills_count(void) +{ + return atomic_read(&oom_kills); +} + +void note_oom_kill(void) +{ + atomic_inc(&oom_kills); +} + #define K(x) ((x) << (PAGE_SHIFT-10)) /* * Must be called while holding a reference to p, which will be released upon diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d013dba..656a549 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -601,7 +601,7 @@ static long long pos_ratio_polynom(unsigned long setpoint, long x; x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, - limit - setpoint + 1); + (limit - setpoint) | 1); pos_ratio = x; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; @@ -828,7 +828,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, * scale global setpoint to bdi's: * bdi_setpoint = setpoint * bdi_thresh / thresh */ - x = div_u64((u64)bdi_thresh << 16, thresh + 1); + x = div_u64((u64)bdi_thresh << 16, thresh | 1); bdi_setpoint = setpoint * (u64)x >> 16; /* * Use span=(8*write_bw) in single bdi case as indicated by @@ -843,7 +843,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, if (bdi_dirty < x_intercept - span / 4) { pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty), - x_intercept - bdi_setpoint + 1); + (x_intercept - bdi_setpoint) | 1); } else pos_ratio /= 4; @@ -878,8 +878,11 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period + * + * @written may have decreased due to account_page_redirty(). + * Avoid underflowing @bw calculation. */ - bw = written - bdi->written_stamp; + bw = written - min(written, bdi->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { do_div(bw, elapsed); @@ -943,7 +946,7 @@ static void global_update_bandwidth(unsigned long thresh, unsigned long now) { static DEFINE_SPINLOCK(dirty_lock); - static unsigned long update_time; + static unsigned long update_time = INITIAL_JIFFIES; /* * check locklessly first to optimize away locking for the most time @@ -1324,9 +1327,9 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi, *bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); if (bdi_bg_thresh) - *bdi_bg_thresh = div_u64((u64)*bdi_thresh * - background_thresh, - dirty_thresh); + *bdi_bg_thresh = dirty_thresh ? div_u64((u64)*bdi_thresh * + background_thresh, + dirty_thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7e7f947..0479732 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -408,7 +408,8 @@ static int destroy_compound_page(struct page *page, unsigned long order) return bad; } -static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags) +static inline void prep_zero_page(struct page *page, unsigned int order, + gfp_t gfp_flags) { int i; @@ -452,7 +453,7 @@ static inline void set_page_guard_flag(struct page *page) { } static inline void clear_page_guard_flag(struct page *page) { } #endif -static inline void set_page_order(struct page *page, int order) +static inline void set_page_order(struct page *page, unsigned int order) { set_page_private(page, order); __SetPageBuddy(page); @@ -503,21 +504,31 @@ __find_buddy_index(unsigned long page_idx, unsigned int order) * For recording page's order, we use page_private(page). */ static inline int page_is_buddy(struct page *page, struct page *buddy, - int order) + unsigned int order) { if (!pfn_valid_within(page_to_pfn(buddy))) return 0; - if (page_zone_id(page) != page_zone_id(buddy)) - return 0; - if (page_is_guard(buddy) && page_order(buddy) == order) { VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + return 1; } if (PageBuddy(buddy) && page_order(buddy) == order) { VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + + /* + * zone check is done late to avoid uselessly + * calculating zone/node ids for pages that could + * never merge. + */ + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + return 1; } return 0; @@ -549,6 +560,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, */ static inline void __free_one_page(struct page *page, + unsigned long pfn, struct zone *zone, unsigned int order, int migratetype) { @@ -565,7 +577,7 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON(migratetype == -1); - page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); + page_idx = pfn & ((1 << MAX_ORDER) - 1); VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page); VM_BUG_ON_PAGE(bad_range(zone, page), page); @@ -666,9 +678,12 @@ static void free_pcppages_bulk(struct zone *zone, int count, int migratetype = 0; int batch_free = 0; int to_free = count; + unsigned long nr_scanned; spin_lock(&zone->lock); - zone->pages_scanned = 0; + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); while (to_free) { struct page *page; @@ -700,7 +715,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, list_del(&page->lru); mt = get_freepage_migratetype(page); /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ - __free_one_page(page, zone, 0, mt); + __free_one_page(page, page_to_pfn(page), zone, 0, mt); trace_mm_page_pcpu_drain(page, 0, mt); if (likely(!is_migrate_isolate_page(page))) { __mod_zone_page_state(zone, NR_FREE_PAGES, 1); @@ -712,13 +727,18 @@ static void free_pcppages_bulk(struct zone *zone, int count, spin_unlock(&zone->lock); } -static void free_one_page(struct zone *zone, struct page *page, int order, +static void free_one_page(struct zone *zone, + struct page *page, unsigned long pfn, + unsigned int order, int migratetype) { + unsigned long nr_scanned; spin_lock(&zone->lock); - zone->pages_scanned = 0; + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); - __free_one_page(page, zone, order, migratetype); + __free_one_page(page, pfn, zone, order, migratetype); if (unlikely(!is_migrate_isolate(migratetype))) __mod_zone_freepage_state(zone, 1 << order, migratetype); spin_unlock(&zone->lock); @@ -755,15 +775,16 @@ static void __free_pages_ok(struct page *page, unsigned int order) { unsigned long flags; int migratetype; + unsigned long pfn = page_to_pfn(page); if (!free_pages_prepare(page, order)) return; + migratetype = get_pfnblock_migratetype(page, pfn); local_irq_save(flags); __count_vm_events(PGFREE, 1 << order); - migratetype = get_pageblock_migratetype(page); set_freepage_migratetype(page, migratetype); - free_one_page(page_zone(page), page, order, migratetype); + free_one_page(page_zone(page), page, pfn, order, migratetype); local_irq_restore(flags); } @@ -894,7 +915,7 @@ static inline int check_new_page(struct page *page) return 0; } -static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) +static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags) { int i; @@ -943,6 +964,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, rmv_page_order(page); area->nr_free--; expand(zone, page, order, current_order, area, migratetype); + set_freepage_migratetype(page, migratetype); return page; } @@ -1059,8 +1081,8 @@ static void change_pageblock_range(struct page *pageblock_page, * nor move CMA pages to different free lists. We don't want unmovable pages * to be allocated from MIGRATE_CMA areas. * - * Returns the new migratetype of the pageblock (or the same old migratetype - * if it was unchanged). + * Returns the allocation migratetype if free pages were stolen, or the + * fallback migratetype if it was decided not to steal. */ static int try_to_steal_freepages(struct zone *zone, struct page *page, int start_type, int fallback_type) @@ -1069,7 +1091,9 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, /* * When borrowing from MIGRATE_CMA, we need to release the excess - * buddy pages to CMA itself. + * buddy pages to CMA itself. We also ensure the freepage_migratetype + * is set to CMA so it is returned to the correct freelist in case + * the page ends up being not actually allocated from the pcp lists. */ if (is_migrate_cma(fallback_type)) return fallback_type; @@ -1089,12 +1113,10 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, /* Claim the whole block if over half of it is free */ if (pages >= (1 << (pageblock_order-1)) || - page_group_by_mobility_disabled) { - + page_group_by_mobility_disabled) set_pageblock_migratetype(page, start_type); - return start_type; - } + return start_type; } return fallback_type; @@ -1102,16 +1124,17 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, /* Remove an element from the buddy allocator from the fallback list */ static inline struct page * -__rmqueue_fallback(struct zone *zone, int order, int start_migratetype) +__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) { struct free_area *area; - int current_order; + unsigned int current_order; struct page *page; int migratetype, new_type, i; /* Find the largest possible block of pages in the other list */ - for (current_order = MAX_ORDER-1; current_order >= order; - --current_order) { + for (current_order = MAX_ORDER-1; + current_order >= order && current_order <= MAX_ORDER-1; + --current_order) { for (i = 0;; i++) { migratetype = fallbacks[start_migratetype][i]; @@ -1137,9 +1160,15 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) expand(zone, page, order, current_order, area, new_type); + /* The freepage_migratetype may differ from pageblock's + * migratetype depending on the decisions in + * try_to_steal_freepages. This is OK as long as it does + * not differ for MIGRATE_CMA type. + */ + set_freepage_migratetype(page, new_type); trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, migratetype, new_type); + start_migratetype, migratetype); return page; } @@ -1185,9 +1214,9 @@ retry_reserve: */ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, - int migratetype, int cold) + int migratetype, bool cold) { - int mt = migratetype, i; + int i; spin_lock(&zone->lock); for (i = 0; i < count; ++i) { @@ -1204,18 +1233,12 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * merge IO requests if the physical pages are ordered * properly. */ - if (likely(cold == 0)) + if (likely(!cold)) list_add(&page->lru, list); else list_add_tail(&page->lru, list); - if (IS_ENABLED(CONFIG_CMA)) { - mt = get_pageblock_migratetype(page); - if (!is_migrate_cma(mt) && !is_migrate_isolate(mt)) - mt = migratetype; - } - set_freepage_migratetype(page, mt); list = &page->lru; - if (is_migrate_cma(mt)) + if (is_migrate_cma(get_freepage_migratetype(page))) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, -(1 << order)); } @@ -1339,7 +1362,7 @@ void mark_free_pages(struct zone *zone) { unsigned long pfn, max_zone_pfn; unsigned long flags; - int order, t; + unsigned int order, t; struct list_head *curr; if (zone_is_empty(zone)) @@ -1371,19 +1394,20 @@ void mark_free_pages(struct zone *zone) /* * Free a 0-order page - * cold == 1 ? free a cold page : free a hot page + * cold == true ? free a cold page : free a hot page */ -void free_hot_cold_page(struct page *page, int cold) +void free_hot_cold_page(struct page *page, bool cold) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; unsigned long flags; + unsigned long pfn = page_to_pfn(page); int migratetype; if (!free_pages_prepare(page, 0)) return; - migratetype = get_pageblock_migratetype(page); + migratetype = get_pfnblock_migratetype(page, pfn); set_freepage_migratetype(page, migratetype); local_irq_save(flags); __count_vm_event(PGFREE); @@ -1397,17 +1421,17 @@ void free_hot_cold_page(struct page *page, int cold) */ if (migratetype >= MIGRATE_PCPTYPES) { if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(zone, page, 0, migratetype); + free_one_page(zone, page, pfn, 0, migratetype); goto out; } migratetype = MIGRATE_MOVABLE; } pcp = &this_cpu_ptr(zone->pageset)->pcp; - if (cold) - list_add_tail(&page->lru, &pcp->lists[migratetype]); - else + if (!cold) list_add(&page->lru, &pcp->lists[migratetype]); + else + list_add_tail(&page->lru, &pcp->lists[migratetype]); pcp->count++; if (pcp->count >= pcp->high) { unsigned long batch = ACCESS_ONCE(pcp->batch); @@ -1422,7 +1446,7 @@ out: /* * Free a list of 0-order pages */ -void free_hot_cold_page_list(struct list_head *list, int cold) +void free_hot_cold_page_list(struct list_head *list, bool cold) { struct page *page, *next; @@ -1534,12 +1558,12 @@ int split_free_page(struct page *page) */ static inline struct page *buffered_rmqueue(struct zone *preferred_zone, - struct zone *zone, int order, gfp_t gfp_flags, - int migratetype) + struct zone *zone, unsigned int order, + gfp_t gfp_flags, int migratetype) { unsigned long flags; struct page *page; - int cold = !!(gfp_flags & __GFP_COLD); + bool cold = ((gfp_flags & __GFP_COLD) != 0); again: if (likely(order == 0)) { @@ -1584,10 +1608,13 @@ again: if (!page) goto failed; __mod_zone_freepage_state(zone, -(1 << order), - get_pageblock_migratetype(page)); + get_freepage_migratetype(page)); } __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); + if (zone_page_state(zone, NR_ALLOC_BATCH) == 0 && + !zone_is_fair_depleted(zone)) + zone_set_flag(zone, ZONE_FAIR_DEPLETED); __count_zone_vm_events(PGALLOC, zone, 1 << order); zone_statistics(preferred_zone, zone, gfp_flags); @@ -1684,12 +1711,12 @@ static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) * Return true if free pages are above 'mark'. This takes into account the order * of the allocation. */ -static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags, long free_pages) +static bool __zone_watermark_ok(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags, + long free_pages) { /* free_pages my go negative - that's OK */ long min = mark; - long lowmem_reserve = z->lowmem_reserve[classzone_idx]; int o; long free_cma = 0; @@ -1704,7 +1731,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, free_cma = zone_page_state(z, NR_FREE_CMA_PAGES); #endif - if (free_pages - free_cma <= min + lowmem_reserve) + if (free_pages - free_cma <= min + z->lowmem_reserve[classzone_idx]) return false; for (o = 0; o < order; o++) { /* At the next order, this order's pages become unavailable */ @@ -1719,15 +1746,15 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, return true; } -bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, +bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, int alloc_flags) { return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, zone_page_state(z, NR_FREE_PAGES)); } -bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags) +bool zone_watermark_ok_safe(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags) { long free_pages = zone_page_state(z, NR_FREE_PAGES); @@ -1869,7 +1896,7 @@ static void __paginginit init_zone_allows_reclaim(int nid) { int i; - for_each_online_node(i) + for_each_node_state(i, N_MEMORY) if (node_distance(nid, i) <= RECLAIM_DISTANCE) node_set(i, NODE_DATA(nid)->reclaim_nodes); else @@ -1912,6 +1939,18 @@ static inline void init_zone_allows_reclaim(int nid) } #endif /* CONFIG_NUMA */ +static void reset_alloc_batches(struct zone *preferred_zone) +{ + struct zone *zone = preferred_zone->zone_pgdat->node_zones; + + do { + mod_zone_page_state(zone, NR_ALLOC_BATCH, + high_wmark_pages(zone) - low_wmark_pages(zone) - + atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); + zone_clear_flag(zone, ZONE_FAIR_DEPLETED); + } while (zone++ != preferred_zone); +} + /* * get_page_from_freelist goes through the zonelist trying to allocate * a page. @@ -1919,18 +1958,22 @@ static inline void init_zone_allows_reclaim(int nid) static struct page * get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order, struct zonelist *zonelist, int high_zoneidx, int alloc_flags, - struct zone *preferred_zone, int migratetype) + struct zone *preferred_zone, int classzone_idx, int migratetype) { struct zoneref *z; struct page *page = NULL; - int classzone_idx; struct zone *zone; nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */ int zlc_active = 0; /* set if using zonelist_cache */ int did_zlc_setup = 0; /* just call zlc_setup() one time */ + bool consider_zone_dirty = (alloc_flags & ALLOC_WMARK_LOW) && + (gfp_mask & __GFP_WRITE); + int nr_fair_skipped = 0; + bool zonelist_rescan; - classzone_idx = zone_idx(preferred_zone); zonelist_scan: + zonelist_rescan = false; + /* * Scan zonelist, looking for a zone with enough free. * See also __cpuset_node_allowed_softwall() comment in kernel/cpuset.c. @@ -1942,12 +1985,10 @@ zonelist_scan: if (IS_ENABLED(CONFIG_NUMA) && zlc_active && !zlc_zone_worth_trying(zonelist, z, allowednodes)) continue; - if ((alloc_flags & ALLOC_CPUSET) && + if (cpusets_enabled() && + (alloc_flags & ALLOC_CPUSET) && !cpuset_zone_allowed_softwall(zone, gfp_mask)) continue; - BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); - if (unlikely(alloc_flags & ALLOC_NO_WATERMARKS)) - goto try_this_zone; /* * Distribute pages in proportion to the individual * zone size to ensure fair page aging. The zone a @@ -1956,9 +1997,11 @@ zonelist_scan: */ if (alloc_flags & ALLOC_FAIR) { if (!zone_local(preferred_zone, zone)) + break; + if (zone_is_fair_depleted(zone)) { + nr_fair_skipped++; continue; - if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0) - continue; + } } /* * When allocating a page cache page for writing, we @@ -1986,15 +2029,19 @@ zonelist_scan: * will require awareness of zones in the * dirty-throttling and the flusher threads. */ - if ((alloc_flags & ALLOC_WMARK_LOW) && - (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone)) - goto this_zone_full; + if (consider_zone_dirty && !zone_dirty_ok(zone)) + continue; mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; if (!zone_watermark_ok(zone, order, mark, classzone_idx, alloc_flags)) { int ret; + /* Checked here to keep the fast path fast */ + BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); + if (alloc_flags & ALLOC_NO_WATERMARKS) + goto try_this_zone; + if (IS_ENABLED(CONFIG_NUMA) && !did_zlc_setup && nr_online_nodes > 1) { /* @@ -2056,17 +2103,11 @@ try_this_zone: if (page) break; this_zone_full: - if (IS_ENABLED(CONFIG_NUMA)) + if (IS_ENABLED(CONFIG_NUMA) && zlc_active) zlc_mark_zone_full(zonelist, z); } - if (unlikely(IS_ENABLED(CONFIG_NUMA) && page == NULL && zlc_active)) { - /* Disable zlc cache for second zonelist scan */ - zlc_active = 0; - goto zonelist_scan; - } - - if (page) + if (page) { /* * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was * necessary to allocate the page. The expectation is @@ -2075,8 +2116,37 @@ this_zone_full: * for !PFMEMALLOC purposes. */ page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS); + return page; + } - return page; + /* + * The first pass makes sure allocations are spread fairly within the + * local node. However, the local node might have free pages left + * after the fairness batches are exhausted, and remote zones haven't + * even been considered yet. Try once more without fairness, and + * include remote zones now, before entering the slowpath and waking + * kswapd: prefer spilling to a remote zone over swapping locally. + */ + if (alloc_flags & ALLOC_FAIR) { + alloc_flags &= ~ALLOC_FAIR; + if (nr_fair_skipped) { + zonelist_rescan = true; + reset_alloc_batches(preferred_zone); + } + if (nr_online_nodes > 1) + zonelist_rescan = true; + } + + if (unlikely(IS_ENABLED(CONFIG_NUMA) && zlc_active)) { + /* Disable zlc cache for second zonelist scan */ + zlc_active = 0; + zonelist_rescan = true; + } + + if (zonelist_rescan) + goto zonelist_scan; + + return NULL; } /* @@ -2185,7 +2255,7 @@ static inline struct page * __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { struct page *page; @@ -2196,6 +2266,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, } /* + * PM-freezer should be notified that there might be an OOM killer on + * its way to kill and wake somebody up. This is too early and we might + * end up not killing anything but false positives are acceptable. + * See freeze_processes. + */ + note_oom_kill(); + + /* * Go through the zonelist yet one more time, keep very high watermark * here, this is only to catch a parallel oom killing, we must fail if * we're still under heavy pressure. @@ -2203,7 +2281,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, ALLOC_WMARK_HIGH|ALLOC_CPUSET, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) goto out; @@ -2238,7 +2316,7 @@ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, + int classzone_idx, int migratetype, enum migrate_mode mode, bool *contended_compaction, bool *deferred_compaction, unsigned long *did_some_progress) { @@ -2252,7 +2330,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, current->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, - nodemask, sync_migration, + nodemask, mode, contended_compaction); current->flags &= ~PF_MEMALLOC; @@ -2266,7 +2344,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) { preferred_zone->compact_blockskip_flush = false; compaction_defer_reset(preferred_zone, order, true); @@ -2285,7 +2363,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, * As async compaction considers a subset of pageblocks, only * defer if the failure was a sync compaction failure. */ - if (sync_migration) + if (mode != MIGRATE_ASYNC) defer_compaction(preferred_zone, order); cond_resched(); @@ -2298,9 +2376,9 @@ static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, - bool *contended_compaction, bool *deferred_compaction, - unsigned long *did_some_progress) + int classzone_idx, int migratetype, + enum migrate_mode mode, bool *contended_compaction, + bool *deferred_compaction, unsigned long *did_some_progress) { return NULL; } @@ -2339,7 +2417,7 @@ static inline struct page * __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) + int classzone_idx, int migratetype, unsigned long *did_some_progress) { struct page *page = NULL; bool drained = false; @@ -2357,7 +2435,8 @@ retry: page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, + migratetype); /* * If an allocation failed after direct reclaim, it could be because @@ -2380,14 +2459,14 @@ static inline struct page * __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { struct page *page; do { page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (!page && gfp_mask & __GFP_NOFAIL) wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); @@ -2396,28 +2475,6 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, return page; } -static void reset_alloc_batches(struct zonelist *zonelist, - enum zone_type high_zoneidx, - struct zone *preferred_zone) -{ - struct zoneref *z; - struct zone *zone; - - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { - /* - * Only reset the batches of zones that were actually - * considered in the fairness pass, we don't want to - * trash fairness information for zones that are not - * actually part of this zonelist's round-robin cycle. - */ - if (!zone_local(preferred_zone, zone)) - continue; - mod_zone_page_state(zone, NR_ALLOC_BATCH, - high_wmark_pages(zone) - low_wmark_pages(zone) - - atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); - } -} - static void wake_all_kswapds(unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, @@ -2434,7 +2491,7 @@ static inline int gfp_to_alloc_flags(gfp_t gfp_mask) { int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - const gfp_t wait = gfp_mask & __GFP_WAIT; + const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD)); /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); @@ -2443,20 +2500,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * The caller may dip into page reserves a bit more if the caller * cannot run direct reclaim, or if the caller has realtime scheduling * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will - * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). + * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH). */ alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); - if (!wait) { + if (atomic) { /* - * Not worth trying to allocate harder for - * __GFP_NOMEMALLOC even if it can't schedule. + * Not worth trying to allocate harder for __GFP_NOMEMALLOC even + * if it can't schedule. */ - if (!(gfp_mask & __GFP_NOMEMALLOC)) + if (!(gfp_mask & __GFP_NOMEMALLOC)) alloc_flags |= ALLOC_HARDER; /* - * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the + * comment for __cpuset_node_allowed_softwall(). */ alloc_flags &= ~ALLOC_CPUSET; } else if (unlikely(rt_task(current)) && !in_interrupt()) @@ -2488,14 +2545,14 @@ static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { const gfp_t wait = gfp_mask & __GFP_WAIT; struct page *page = NULL; int alloc_flags; unsigned long pages_reclaimed = 0; unsigned long did_some_progress; - bool sync_migration = false; + enum migrate_mode migration_mode = MIGRATE_ASYNC; bool deferred_compaction = false; bool contended_compaction = false; @@ -2537,15 +2594,19 @@ restart: * Find the true preferred zone if the allocation is unconstrained by * cpusets. */ - if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) - first_zones_zonelist(zonelist, high_zoneidx, NULL, - &preferred_zone); + if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) { + struct zoneref *preferred_zoneref; + preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx, + NULL, + &preferred_zone); + classzone_idx = zonelist_zone_idx(preferred_zoneref); + } rebalance: /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) goto got_pg; @@ -2560,7 +2621,7 @@ rebalance: page = __alloc_pages_high_priority(gfp_mask, order, zonelist, high_zoneidx, nodemask, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) { goto got_pg; } @@ -2589,17 +2650,16 @@ rebalance: * Try direct compaction. The first pass is asynchronous. Subsequent * attempts after direct reclaim are synchronous */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, + classzone_idx, migratetype, + migration_mode, &contended_compaction, &deferred_compaction, &did_some_progress); if (page) goto got_pg; - sync_migration = true; + migration_mode = MIGRATE_SYNC_LIGHT; /* * If compaction is deferred for high-order allocations, it is because @@ -2616,7 +2676,8 @@ rebalance: zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress); + classzone_idx, migratetype, + &did_some_progress); if (page) goto got_pg; @@ -2635,7 +2696,7 @@ rebalance: page = __alloc_pages_may_oom(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, - migratetype); + classzone_idx, migratetype); if (page) goto got_pg; @@ -2674,12 +2735,11 @@ rebalance: * direct reclaim and reclaim/compaction depends on compaction * being called after reclaim so call directly if necessary */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, + classzone_idx, migratetype, + migration_mode, &contended_compaction, &deferred_compaction, &did_some_progress); if (page) @@ -2705,11 +2765,13 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, { enum zone_type high_zoneidx = gfp_zone(gfp_mask); struct zone *preferred_zone; + struct zoneref *preferred_zoneref; struct page *page = NULL; int migratetype = allocflags_to_migratetype(gfp_mask); unsigned int cpuset_mems_cookie; int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR; struct mem_cgroup *memcg = NULL; + int classzone_idx; gfp_mask &= gfp_allowed_mask; @@ -2736,42 +2798,26 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, return NULL; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); /* The preferred zone is used for statistics later */ - first_zones_zonelist(zonelist, high_zoneidx, + preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx, nodemask ? : &cpuset_current_mems_allowed, &preferred_zone); if (!preferred_zone) goto out; + classzone_idx = zonelist_zone_idx(preferred_zoneref); #ifdef CONFIG_CMA if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) alloc_flags |= ALLOC_CMA; #endif -retry: /* First allocation attempt */ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, alloc_flags, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (unlikely(!page)) { /* - * The first pass makes sure allocations are spread - * fairly within the local node. However, the local - * node might have free pages left after the fairness - * batches are exhausted, and remote zones haven't - * even been considered yet. Try once more without - * fairness, and include remote zones now, before - * entering the slowpath and waking kswapd: prefer - * spilling to a remote zone over swapping locally. - */ - if (alloc_flags & ALLOC_FAIR) { - reset_alloc_batches(zonelist, high_zoneidx, - preferred_zone); - alloc_flags &= ~ALLOC_FAIR; - goto retry; - } - /* * Runtime PM, block IO and its error handling path * can deadlock because I/O on the device might not * complete. @@ -2779,7 +2825,7 @@ retry: gfp_mask = memalloc_noio_flags(gfp_mask); page = __alloc_pages_slowpath(gfp_mask, order, zonelist, high_zoneidx, nodemask, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); } trace_mm_page_alloc(page, order, gfp_mask, migratetype); @@ -2791,7 +2837,7 @@ out: * the mask is being updated. If a page allocation is about to fail, * check if the cpuset changed during allocation and if so, retry. */ - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; memcg_kmem_commit_charge(page, memcg, order); @@ -2830,7 +2876,7 @@ void __free_pages(struct page *page, unsigned int order) { if (put_page_testzero(page)) { if (order == 0) - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); else __free_pages_ok(page, order); } @@ -3059,9 +3105,9 @@ bool skip_free_areas_node(unsigned int flags, int nid) goto out; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); ret = !node_isset(nid, cpuset_current_mems_allowed); - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); out: return ret; } @@ -3214,12 +3260,12 @@ void show_free_areas(unsigned int filter) K(zone_page_state(zone, NR_BOUNCE)), K(zone_page_state(zone, NR_FREE_CMA_PAGES)), K(zone_page_state(zone, NR_WRITEBACK_TEMP)), - zone->pages_scanned, + K(zone_page_state(zone, NR_PAGES_SCANNED)), (!zone_reclaimable(zone) ? "yes" : "no") ); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) - printk(" %lu", zone->lowmem_reserve[i]); + printk(" %ld", zone->lowmem_reserve[i]); printk("\n"); } @@ -4107,7 +4153,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, static void __meminit zone_init_free_lists(struct zone *zone) { - int order, t; + unsigned int order, t; for_each_migratetype_order(order, t) { INIT_LIST_HEAD(&zone->free_area[order].free_list[t]); zone->free_area[order].nr_free = 0; @@ -4933,7 +4979,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; - init_zone_allows_reclaim(nid); + if (node_state(nid, N_MEMORY)) + init_zone_allows_reclaim(nid); #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); #endif @@ -5546,7 +5593,7 @@ static void calculate_totalreserve_pages(void) for_each_online_pgdat(pgdat) { for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; - unsigned long max = 0; + long max = 0; /* Find valid and maximum lowmem_reserve in the zone */ for (j = i; j < MAX_NR_ZONES; j++) { @@ -5661,9 +5708,8 @@ static void __setup_per_zone_wmarks(void) zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); __mod_zone_page_state(zone, NR_ALLOC_BATCH, - high_wmark_pages(zone) - - low_wmark_pages(zone) - - zone_page_state(zone, NR_ALLOC_BATCH)); + high_wmark_pages(zone) - low_wmark_pages(zone) - + atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); @@ -6035,17 +6081,16 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn) * @end_bitidx: The last bit of interest * returns pageblock_bits flags */ -unsigned long get_pageblock_flags_mask(struct page *page, +unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, unsigned long end_bitidx, unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx, word_bitidx; + unsigned long bitidx, word_bitidx; unsigned long word; zone = page_zone(page); - pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); word_bitidx = bitidx / BITS_PER_LONG; @@ -6057,25 +6102,25 @@ unsigned long get_pageblock_flags_mask(struct page *page, } /** - * set_pageblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages + * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages * @page: The page within the block of interest * @start_bitidx: The first bit of interest * @end_bitidx: The last bit of interest * @flags: The flags to set */ -void set_pageblock_flags_mask(struct page *page, unsigned long flags, +void set_pfnblock_flags_mask(struct page *page, unsigned long flags, + unsigned long pfn, unsigned long end_bitidx, unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx, word_bitidx; + unsigned long bitidx, word_bitidx; unsigned long old_word, word; BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); zone = page_zone(page); - pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); word_bitidx = bitidx / BITS_PER_LONG; @@ -6253,7 +6298,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, cc->nr_migratepages -= nr_reclaimed; ret = migrate_pages(&cc->migratepages, alloc_migrate_target, - 0, MIGRATE_SYNC, MR_CMA); + NULL, 0, cc->mode, MR_CMA); } if (ret < 0) { putback_movable_pages(&cc->migratepages); @@ -6292,7 +6337,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, .nr_migratepages = 0, .order = -1, .zone = page_zone(pfn_to_page(start)), - .sync = true, + .mode = MIGRATE_SYNC, .ignore_skip_hint = true, }; INIT_LIST_HEAD(&cc.migratepages); @@ -6447,7 +6492,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) { struct page *page; struct zone *zone; - int order, i; + unsigned int order, i; unsigned long pfn; unsigned long flags; /* find the first valid pfn */ @@ -6499,7 +6544,7 @@ bool is_free_buddy_page(struct page *page) struct zone *zone = page_zone(page); unsigned long pfn = page_to_pfn(page); unsigned long flags; - int order; + unsigned int order; spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index cfd1628..0e9a319 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -171,6 +171,7 @@ static void free_page_cgroup(void *addr) sizeof(struct page_cgroup) * PAGES_PER_SECTION; BUG_ON(PageReserved(page)); + kmemleak_free(addr); free_pages_exact(addr, table_size); } } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 2beeabf..9056d22 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -199,7 +199,10 @@ int walk_page_range(unsigned long addr, unsigned long end, */ if ((vma->vm_start <= addr) && (vma->vm_flags & VM_PFNMAP)) { - next = vma->vm_end; + if (walk->pte_hole) + err = walk->pte_hole(addr, next, walk); + if (err) + break; pgd = pgd_offset(walk->mm, next); continue; } diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 3707c71..5110816 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -108,7 +108,7 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, int page_start, int page_end) { const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; - unsigned int cpu; + unsigned int cpu, tcpu; int i; for_each_possible_cpu(cpu) { @@ -116,14 +116,23 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); - if (!*pagep) { - pcpu_free_pages(chunk, pages, populated, - page_start, page_end); - return -ENOMEM; - } + if (!*pagep) + goto err; } } return 0; + +err: + while (--i >= page_start) + __free_page(pages[pcpu_page_idx(cpu, i)]); + + for_each_possible_cpu(tcpu) { + if (tcpu == cpu) + break; + for (i = page_start; i < page_end; i++) + __free_page(pages[pcpu_page_idx(tcpu, i)]); + } + return -ENOMEM; } /** @@ -263,6 +272,7 @@ err: __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), page_end - page_start); } + pcpu_post_unmap_tlb_flush(chunk, page_start, page_end); return err; } diff --git a/mm/readahead.c b/mm/readahead.c index 0de2360..0ca36a7 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -8,9 +8,7 @@ */ #include -#include #include -#include #include #include #include @@ -20,6 +18,8 @@ #include #include +#include "internal.h" + /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. @@ -149,8 +149,7 @@ out: * * Returns the number of pages requested, or the maximum amount of I/O allowed. */ -static int -__do_page_cache_readahead(struct address_space *mapping, struct file *filp, +int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read, unsigned long lookahead_size) { @@ -179,7 +178,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp, rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, page_offset); rcu_read_unlock(); - if (page) + if (page && !radix_tree_exceptional_entry(page)) continue; page = page_cache_alloc_readahead(mapping); @@ -233,28 +232,14 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, return 0; } +#define MAX_READAHEAD ((512*4096)/PAGE_CACHE_SIZE) /* * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a * sensible upper limit. */ unsigned long max_sane_readahead(unsigned long nr) { - return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE) - + node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2); -} - -/* - * Submit IO for the read-ahead request in file_ra_state. - */ -unsigned long ra_submit(struct file_ra_state *ra, - struct address_space *mapping, struct file *filp) -{ - int actual; - - actual = __do_page_cache_readahead(mapping, filp, - ra->start, ra->size, ra->async_size); - - return actual; + return min(nr, MAX_READAHEAD); } /* @@ -347,7 +332,7 @@ static pgoff_t count_history_pages(struct address_space *mapping, pgoff_t head; rcu_read_lock(); - head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max); + head = page_cache_prev_hole(mapping, offset - 1, max); rcu_read_unlock(); return offset - 1 - head; @@ -427,7 +412,7 @@ ondemand_readahead(struct address_space *mapping, pgoff_t start; rcu_read_lock(); - start = radix_tree_next_hole(&mapping->page_tree, offset+1,max); + start = page_cache_next_hole(mapping, offset + 1, max); rcu_read_unlock(); if (!start || start - offset > max) diff --git a/mm/rmap.c b/mm/rmap.c index cdbd312..cab9820 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -274,6 +274,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; + int error; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) @@ -283,8 +284,9 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ - if (anon_vma_clone(vma, pvma)) - return -ENOMEM; + error = anon_vma_clone(vma, pvma); + if (error) + return error; /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); diff --git a/mm/shmem.c b/mm/shmem.c index ff85863..85d8a1a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -243,19 +243,17 @@ static int shmem_radix_tree_replace(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { void **pslot; - void *item = NULL; + void *item; VM_BUG_ON(!expected); + VM_BUG_ON(!replacement); pslot = radix_tree_lookup_slot(&mapping->page_tree, index); - if (pslot) - item = radix_tree_deref_slot_protected(pslot, - &mapping->tree_lock); + if (!pslot) + return -ENOENT; + item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock); if (item != expected) return -ENOENT; - if (replacement) - radix_tree_replace_slot(pslot, replacement); - else - radix_tree_delete(&mapping->page_tree, index); + radix_tree_replace_slot(pslot, replacement); return 0; } @@ -332,84 +330,20 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) } /* - * Like find_get_pages, but collecting swap entries as well as pages. - */ -static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping, - pgoff_t start, unsigned int nr_pages, - struct page **pages, pgoff_t *indices) -{ - void **slot; - unsigned int ret = 0; - struct radix_tree_iter iter; - - if (!nr_pages) - return 0; - - rcu_read_lock(); -restart: - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { - struct page *page; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) - continue; - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) - goto restart; - /* - * Otherwise, we must be storing a swap entry - * here as an exceptional entry: so return it - * without attempting to raise page count. - */ - goto export; - } - if (!page_cache_get_speculative(page)) - goto repeat; - - /* Has the page moved? */ - if (unlikely(page != *slot)) { - page_cache_release(page); - goto repeat; - } -export: - indices[ret] = iter.index; - pages[ret] = page; - if (++ret == nr_pages) - break; - } - rcu_read_unlock(); - return ret; -} - -/* * Remove swap entry from radix tree, free the swap and its page cache. */ static int shmem_free_swap(struct address_space *mapping, pgoff_t index, void *radswap) { - int error; + void *old; spin_lock_irq(&mapping->tree_lock); - error = shmem_radix_tree_replace(mapping, index, radswap, NULL); + old = radix_tree_delete_item(&mapping->page_tree, index, radswap); spin_unlock_irq(&mapping->tree_lock); - if (!error) - free_swap_and_cache(radix_to_swp_entry(radswap)); - return error; -} - -/* - * Pagevec may contain swap entries, so shuffle up pages before releasing. - */ -static void shmem_deswap_pagevec(struct pagevec *pvec) -{ - int i, j; - - for (i = 0, j = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; - if (!radix_tree_exceptional_entry(page)) - pvec->pages[j++] = page; - } - pvec->nr = j; + if (old != radswap) + return -ENOENT; + free_swap_and_cache(radix_to_swp_entry(radswap)); + return 0; } /* @@ -430,12 +364,12 @@ void shmem_unlock_mapping(struct address_space *mapping) * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it * has finished, if it hits a row of PAGEVEC_SIZE swap entries. */ - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - PAGEVEC_SIZE, pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + PAGEVEC_SIZE, pvec.pages, indices); if (!pvec.nr) break; index = indices[pvec.nr - 1] + 1; - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); check_move_unevictable_pages(pvec.pages, pvec.nr); pagevec_release(&pvec); cond_resched(); @@ -467,9 +401,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, pagevec_init(&pvec, 0); index = start; while (index < end) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + pvec.pages, indices); if (!pvec.nr) break; mem_cgroup_uncharge_start(); @@ -498,7 +432,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -536,9 +470,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index = start; while (index < end) { cond_resched(); - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + + pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.pages, indices); if (!pvec.nr) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) @@ -581,7 +516,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -1088,7 +1023,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, return -EFBIG; repeat: swap.val = 0; - page = find_lock_page(mapping, index); + page = find_lock_entry(mapping, index); if (radix_tree_exceptional_entry(page)) { swap = radix_to_swp_entry(page); page = NULL; @@ -1100,6 +1035,9 @@ repeat: goto failed; } + if (page && sgp == SGP_WRITE) + mark_page_accessed(page); + /* fallocated page? */ if (page && !PageUptodate(page)) { if (sgp != SGP_READ) @@ -1181,6 +1119,9 @@ repeat: shmem_recalc_inode(inode); spin_unlock(&info->lock); + if (sgp == SGP_WRITE) + mark_page_accessed(page); + delete_from_swap_cache(page); set_page_dirty(page); swap_free(swap); @@ -1205,8 +1146,11 @@ repeat: goto decused; } - SetPageSwapBacked(page); + __SetPageSwapBacked(page); __set_page_locked(page); + if (sgp == SGP_WRITE) + init_page_accessed(page); + error = mem_cgroup_cache_charge(page, current->mm, gfp & GFP_RECLAIM_MASK); if (error) @@ -1483,6 +1427,11 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode return inode; } +bool shmem_mapping(struct address_space *mapping) +{ + return mapping->backing_dev_info == &shmem_backing_dev_info; +} + #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; @@ -1795,7 +1744,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, pagevec_init(&pvec, 0); pvec.nr = 1; /* start small: we may be there already */ while (!done) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + pvec.nr = find_get_entries(mapping, index, pvec.nr, pvec.pages, indices); if (!pvec.nr) { if (whence == SEEK_DATA) @@ -1822,7 +1771,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, break; } } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); pvec.nr = PAGEVEC_SIZE; cond_resched(); @@ -2143,8 +2092,10 @@ static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct if (new_dentry->d_inode) { (void) shmem_unlink(new_dir, new_dentry); - if (they_are_dirs) + if (they_are_dirs) { + drop_nlink(new_dentry->d_inode); drop_nlink(old_dir); + } } else if (they_are_dirs) { drop_nlink(old_dir); inc_nlink(new_dir); diff --git a/mm/slab.c b/mm/slab.c index 6dd8d5f..0b1c2a5 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2189,7 +2189,8 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) int __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) { - size_t left_over, freelist_size, ralign; + size_t left_over, freelist_size; + size_t ralign = BYTES_PER_WORD; gfp_t gfp; int err; size_t size = cachep->size; @@ -2222,14 +2223,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) size &= ~(BYTES_PER_WORD - 1); } - /* - * Redzoning and user store require word alignment or possibly larger. - * Note this will be overridden by architecture or caller mandated - * alignment if either is greater than BYTES_PER_WORD. - */ - if (flags & SLAB_STORE_USER) - ralign = BYTES_PER_WORD; - if (flags & SLAB_RED_ZONE) { ralign = REDZONE_ALIGN; /* If redzoning, ensure that the second redzone is suitably @@ -3129,7 +3122,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(slab_node(), flags); retry: @@ -3187,7 +3180,7 @@ retry: } } - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj)) + if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return obj; } diff --git a/mm/slab_common.c b/mm/slab_common.c index 1ec3c61..f149e67 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -56,7 +56,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, continue; } -#if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON) +#if !defined(CONFIG_SLUB) /* * For simplicity, we won't check this in the list of memcg * caches. We have control over memcg naming, and if there diff --git a/mm/slub.c b/mm/slub.c index 25f14ad..7611f14 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1684,7 +1684,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, return NULL; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(slab_node(), flags); for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { struct kmem_cache_node *n; @@ -1696,19 +1696,17 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, object = get_partial_node(s, n, c, flags); if (object) { /* - * Return the object even if - * put_mems_allowed indicated that - * the cpuset mems_allowed was - * updated in parallel. It's a - * harmless race between the alloc - * and the cpuset update. + * Don't check read_mems_allowed_retry() + * here - if mems_allowed was updated in + * parallel, that was a harmless race + * between allocation and the cpuset + * update */ - put_mems_allowed(cpuset_mems_cookie); return object; } } } - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); #endif return NULL; } diff --git a/mm/swap.c b/mm/swap.c index 0092097..d2ceddf 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -67,7 +67,7 @@ static void __page_cache_release(struct page *page) static void __put_single_page(struct page *page) { __page_cache_release(page); - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); } static void __put_compound_page(struct page *page) @@ -469,7 +469,7 @@ static void __activate_page(struct page *page, struct lruvec *lruvec, SetPageActive(page); lru += LRU_ACTIVE; add_page_to_lru_list(page, lruvec, lru); - trace_mm_lru_activate(page, page_to_pfn(page)); + trace_mm_lru_activate(page); __count_vm_event(PGACTIVATE); update_page_reclaim_stat(lruvec, file, 1); @@ -581,12 +581,17 @@ void mark_page_accessed(struct page *page) EXPORT_SYMBOL(mark_page_accessed); /* - * Queue the page for addition to the LRU via pagevec. The decision on whether - * to add the page to the [in]active [file|anon] list is deferred until the - * pagevec is drained. This gives a chance for the caller of __lru_cache_add() - * have the page added to the active list using mark_page_accessed(). + * Used to mark_page_accessed(page) that is not visible yet and when it is + * still safe to use non-atomic ops */ -void __lru_cache_add(struct page *page) +void init_page_accessed(struct page *page) +{ + if (!PageReferenced(page)) + __SetPageReferenced(page); +} +EXPORT_SYMBOL(init_page_accessed); + +static void __lru_cache_add(struct page *page) { struct pagevec *pvec = &get_cpu_var(lru_add_pvec); @@ -596,11 +601,34 @@ void __lru_cache_add(struct page *page) pagevec_add(pvec, page); put_cpu_var(lru_add_pvec); } -EXPORT_SYMBOL(__lru_cache_add); + +/** + * lru_cache_add: add a page to the page lists + * @page: the page to add + */ +void lru_cache_add_anon(struct page *page) +{ + if (PageActive(page)) + ClearPageActive(page); + __lru_cache_add(page); +} + +void lru_cache_add_file(struct page *page) +{ + if (PageActive(page)) + ClearPageActive(page); + __lru_cache_add(page); +} +EXPORT_SYMBOL(lru_cache_add_file); /** * lru_cache_add - add a page to a page list * @page: the page to be added to the LRU. + * + * Queue the page for addition to the LRU via pagevec. The decision on whether + * to add the page to the [in]active [file|anon] list is deferred until the + * pagevec is drained. This gives a chance for the caller of lru_cache_add() + * have the page added to the active list using mark_page_accessed(). */ void lru_cache_add(struct page *page) { @@ -811,7 +839,7 @@ void lru_add_drain_all(void) * grabbed the page via the LRU. If it did, give up: shrink_inactive_list() * will free it. */ -void release_pages(struct page **pages, int nr, int cold) +void release_pages(struct page **pages, int nr, bool cold) { int i; LIST_HEAD(pages_to_free); @@ -852,7 +880,7 @@ void release_pages(struct page **pages, int nr, int cold) } /* Clear Active bit in case of parallel mark_page_accessed */ - ClearPageActive(page); + __ClearPageActive(page); list_add(&page->lru, &pages_to_free); } @@ -934,7 +962,7 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, SetPageLRU(page); add_page_to_lru_list(page, lruvec, lru); update_page_reclaim_stat(lruvec, file, active); - trace_mm_lru_insertion(page, page_to_pfn(page), lru, trace_pagemap_flags(page)); + trace_mm_lru_insertion(page, lru); } /* @@ -948,6 +976,57 @@ void __pagevec_lru_add(struct pagevec *pvec) EXPORT_SYMBOL(__pagevec_lru_add); /** + * pagevec_lookup_entries - gang pagecache lookup + * @pvec: Where the resulting entries are placed + * @mapping: The address_space to search + * @start: The starting entry index + * @nr_entries: The maximum number of entries + * @indices: The cache indices corresponding to the entries in @pvec + * + * pagevec_lookup_entries() will search for and return a group of up + * to @nr_entries pages and shadow entries in the mapping. All + * entries are placed in @pvec. pagevec_lookup_entries() takes a + * reference against actual pages in @pvec. + * + * The search returns a group of mapping-contiguous entries with + * ascending indexes. There may be holes in the indices due to + * not-present entries. + * + * pagevec_lookup_entries() returns the number of entries which were + * found. + */ +unsigned pagevec_lookup_entries(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t start, unsigned nr_pages, + pgoff_t *indices) +{ + pvec->nr = find_get_entries(mapping, start, nr_pages, + pvec->pages, indices); + return pagevec_count(pvec); +} + +/** + * pagevec_remove_exceptionals - pagevec exceptionals pruning + * @pvec: The pagevec to prune + * + * pagevec_lookup_entries() fills both pages and exceptional radix + * tree entries into the pagevec. This function prunes all + * exceptionals from @pvec without leaving holes, so that it can be + * passed on to page-only pagevec operations. + */ +void pagevec_remove_exceptionals(struct pagevec *pvec) +{ + int i, j; + + for (i = 0, j = 0; i < pagevec_count(pvec); i++) { + struct page *page = pvec->pages[i]; + if (!radix_tree_exceptional_entry(page)) + pvec->pages[j++] = page; + } + pvec->nr = j; +} + +/** * pagevec_lookup - gang pagecache lookup * @pvec: Where the resulting pages are placed * @mapping: The address_space to search diff --git a/mm/swap_state.c b/mm/swap_state.c index e76ace3..2972eee 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -270,7 +270,7 @@ void free_pages_and_swap_cache(struct page **pages, int nr) for (i = 0; i < todo; i++) free_swap_cache(pagep[i]); - release_pages(pagep, todo, 0); + release_pages(pagep, todo, false); pagep += todo; nr -= todo; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 4a7f7e6..beeeef8 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -51,14 +51,32 @@ atomic_long_t nr_swap_pages; /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority; -static atomic_t highest_priority_index = ATOMIC_INIT(-1); static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; -struct swap_list_t swap_list = {-1, -1}; +/* + * all active swap_info_structs + * protected with swap_lock, and ordered by priority. + */ +PLIST_HEAD(swap_active_head); + +/* + * all available (active, not full) swap_info_structs + * protected with swap_avail_lock, ordered by priority. + * This is used by get_swap_page() instead of swap_active_head + * because swap_active_head includes all swap_info_structs, + * but get_swap_page() doesn't need to look at full ones. + * This uses its own lock instead of swap_lock because when a + * swap_info_struct changes between not-full/full, it needs to + * add/remove itself to/from this list, but the swap_info_struct->lock + * is held and the locking order requires swap_lock to be taken + * before any swap_info_struct->lock. + */ +static PLIST_HEAD(swap_avail_head); +static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; @@ -591,6 +609,9 @@ checks: if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; + spin_lock(&swap_avail_lock); + plist_del(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); } si->swap_map[offset] = usage; inc_cluster_info_page(si, si->cluster_info, offset); @@ -640,71 +661,65 @@ no_page: swp_entry_t get_swap_page(void) { - struct swap_info_struct *si; + struct swap_info_struct *si, *next; pgoff_t offset; - int type, next; - int wrapped = 0; - int hp_index; - spin_lock(&swap_lock); if (atomic_long_read(&nr_swap_pages) <= 0) goto noswap; atomic_long_dec(&nr_swap_pages); - for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) { - hp_index = atomic_xchg(&highest_priority_index, -1); - /* - * highest_priority_index records current highest priority swap - * type which just frees swap entries. If its priority is - * higher than that of swap_list.next swap type, we use it. It - * isn't protected by swap_lock, so it can be an invalid value - * if the corresponding swap type is swapoff. We double check - * the flags here. It's even possible the swap type is swapoff - * and swapon again and its priority is changed. In such rare - * case, low prority swap type might be used, but eventually - * high priority swap will be used after several rounds of - * swap. - */ - if (hp_index != -1 && hp_index != type && - swap_info[type]->prio < swap_info[hp_index]->prio && - (swap_info[hp_index]->flags & SWP_WRITEOK)) { - type = hp_index; - swap_list.next = type; - } - - si = swap_info[type]; - next = si->next; - if (next < 0 || - (!wrapped && si->prio != swap_info[next]->prio)) { - next = swap_list.head; - wrapped++; - } + spin_lock(&swap_avail_lock); +start_over: + plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) { + /* requeue si to after same-priority siblings */ + plist_requeue(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); spin_lock(&si->lock); - if (!si->highest_bit) { + if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + if (plist_node_empty(&si->avail_list)) { + spin_unlock(&si->lock); + goto nextsi; + } + WARN(!si->highest_bit, + "swap_info %d in list but !highest_bit\n", + si->type); + WARN(!(si->flags & SWP_WRITEOK), + "swap_info %d in list but !SWP_WRITEOK\n", + si->type); + plist_del(&si->avail_list, &swap_avail_head); spin_unlock(&si->lock); - continue; + goto nextsi; } - if (!(si->flags & SWP_WRITEOK)) { - spin_unlock(&si->lock); - continue; - } - - swap_list.next = next; - spin_unlock(&swap_lock); /* This is called for allocating swap entry for cache */ offset = scan_swap_map(si, SWAP_HAS_CACHE); spin_unlock(&si->lock); if (offset) - return swp_entry(type, offset); - spin_lock(&swap_lock); - next = swap_list.next; + return swp_entry(si->type, offset); + pr_debug("scan_swap_map of si %d failed to find offset\n", + si->type); + spin_lock(&swap_avail_lock); +nextsi: + /* + * if we got here, it's likely that si was almost full before, + * and since scan_swap_map() can drop the si->lock, multiple + * callers probably all tried to get a page from the same si + * and it filled up before we could get one; or, the si filled + * up between us dropping swap_avail_lock and taking si->lock. + * Since we dropped the swap_avail_lock, the swap_avail_head + * list may have been modified; so if next is still in the + * swap_avail_head list then try it, otherwise start over. + */ + if (plist_node_empty(&next->avail_list)) + goto start_over; } + spin_unlock(&swap_avail_lock); + atomic_long_inc(&nr_swap_pages); noswap: - spin_unlock(&swap_lock); return (swp_entry_t) {0}; } @@ -766,27 +781,6 @@ out: return NULL; } -/* - * This swap type frees swap entry, check if it is the highest priority swap - * type which just frees swap entry. get_swap_page() uses - * highest_priority_index to search highest priority swap type. The - * swap_info_struct.lock can't protect us if there are multiple swap types - * active, so we use atomic_cmpxchg. - */ -static void set_highest_priority_index(int type) -{ - int old_hp_index, new_hp_index; - - do { - old_hp_index = atomic_read(&highest_priority_index); - if (old_hp_index != -1 && - swap_info[old_hp_index]->prio >= swap_info[type]->prio) - break; - new_hp_index = type; - } while (atomic_cmpxchg(&highest_priority_index, - old_hp_index, new_hp_index) != old_hp_index); -} - static unsigned char swap_entry_free(struct swap_info_struct *p, swp_entry_t entry, unsigned char usage) { @@ -828,9 +822,18 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, dec_cluster_info_page(p, p->cluster_info, offset); if (offset < p->lowest_bit) p->lowest_bit = offset; - if (offset > p->highest_bit) + if (offset > p->highest_bit) { + bool was_full = !p->highest_bit; p->highest_bit = offset; - set_highest_priority_index(p->type); + if (was_full && (p->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + WARN_ON(!plist_node_empty(&p->avail_list)); + if (plist_node_empty(&p->avail_list)) + plist_add(&p->avail_list, + &swap_avail_head); + spin_unlock(&swap_avail_lock); + } + } atomic_long_inc(&nr_swap_pages); p->inuse_pages--; frontswap_invalidate_page(p->type, offset); @@ -1765,30 +1768,37 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { - int i, prev; - if (prio >= 0) p->prio = prio; else p->prio = --least_priority; + /* + * the plist prio is negated because plist ordering is + * low-to-high, while swap ordering is high-to-low + */ + p->list.prio = -p->prio; + p->avail_list.prio = -p->prio; p->swap_map = swap_map; p->cluster_info = cluster_info; p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; - /* insert swap space into swap_list: */ - prev = -1; - for (i = swap_list.head; i >= 0; i = swap_info[i]->next) { - if (p->prio >= swap_info[i]->prio) - break; - prev = i; - } - p->next = i; - if (prev < 0) - swap_list.head = swap_list.next = p->type; - else - swap_info[prev]->next = p->type; + assert_spin_locked(&swap_lock); + /* + * both lists are plists, and thus priority ordered. + * swap_active_head needs to be priority ordered for swapoff(), + * which on removal of any swap_info_struct with an auto-assigned + * (i.e. negative) priority increments the auto-assigned priority + * of any lower-priority swap_info_structs. + * swap_avail_head needs to be priority ordered for get_swap_page(), + * which allocates swap pages from the highest available priority + * swap_info_struct. + */ + plist_add(&p->list, &swap_active_head); + spin_lock(&swap_avail_lock); + plist_add(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); } static void enable_swap_info(struct swap_info_struct *p, int prio, @@ -1823,8 +1833,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct address_space *mapping; struct inode *inode; struct filename *pathname; - int i, type, prev; - int err; + int err, found = 0; unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) @@ -1842,17 +1851,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out; mapping = victim->f_mapping; - prev = -1; spin_lock(&swap_lock); - for (type = swap_list.head; type >= 0; type = swap_info[type]->next) { - p = swap_info[type]; + plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { - if (p->swap_file->f_mapping == mapping) + if (p->swap_file->f_mapping == mapping) { + found = 1; break; + } } - prev = type; } - if (type < 0) { + if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; @@ -1864,20 +1872,21 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - if (prev < 0) - swap_list.head = p->next; - else - swap_info[prev]->next = p->next; - if (type == swap_list.next) { - /* just pick something that's safe... */ - swap_list.next = swap_list.head; - } + spin_lock(&swap_avail_lock); + plist_del(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); spin_lock(&p->lock); if (p->prio < 0) { - for (i = p->next; i >= 0; i = swap_info[i]->next) - swap_info[i]->prio = p->prio--; + struct swap_info_struct *si = p; + + plist_for_each_entry_continue(si, &swap_active_head, list) { + si->prio++; + si->list.prio--; + si->avail_list.prio--; + } least_priority++; } + plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; @@ -1885,7 +1894,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); set_current_oom_origin(); - err = try_to_unuse(type, false, 0); /* force all pages to be unused */ + err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ clear_current_oom_origin(); if (err) { @@ -1926,7 +1935,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); - frontswap_invalidate_area(type); + frontswap_invalidate_area(p->type); frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); @@ -1935,7 +1944,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) vfree(cluster_info); vfree(frontswap_map); /* Destroy swap account information */ - swap_cgroup_swapoff(type); + swap_cgroup_swapoff(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { @@ -2142,8 +2151,9 @@ static struct swap_info_struct *alloc_swap_info(void) */ } INIT_LIST_HEAD(&p->first_swap_extent.list); + plist_node_init(&p->list, 0); + plist_node_init(&p->avail_list, 0); p->flags = SWP_USED; - p->next = -1; spin_unlock(&swap_lock); spin_lock_init(&p->lock); diff --git a/mm/truncate.c b/mm/truncate.c index 353b683..827ad8d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -20,8 +20,25 @@ #include /* grr. try_to_release_page, do_invalidatepage */ #include +#include #include "internal.h" +static void clear_exceptional_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + /* Handled by shmem itself */ + if (shmem_mapping(mapping)) + return; + + spin_lock_irq(&mapping->tree_lock); + /* + * Regular page slots are stabilized by the page lock even + * without the tree itself locked. These unlocked entries + * need verification under the tree lock. + */ + radix_tree_delete_item(&mapping->page_tree, index, entry); + spin_unlock_irq(&mapping->tree_lock); +} /** * do_invalidatepage - invalidate part or all of a page @@ -208,6 +225,7 @@ void truncate_inode_pages_range(struct address_space *mapping, unsigned int partial_start; /* inclusive */ unsigned int partial_end; /* exclusive */ struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; @@ -238,17 +256,23 @@ void truncate_inode_pages_range(struct address_space *mapping, pagevec_init(&pvec, 0); index = start; - while (index < end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE))) { + while (index < end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index >= end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + if (!trylock_page(page)) continue; WARN_ON(page->index != index); @@ -259,6 +283,7 @@ void truncate_inode_pages_range(struct address_space *mapping, truncate_inode_page(mapping, page); unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -307,14 +332,16 @@ void truncate_inode_pages_range(struct address_space *mapping, index = start; for ( ; ; ) { cond_resched(); - if (!pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE))) { + if (!pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { if (index == start) break; index = start; continue; } - if (index == start && pvec.pages[0]->index >= end) { + if (index == start && indices[0] >= end) { + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); break; } @@ -323,16 +350,22 @@ void truncate_inode_pages_range(struct address_space *mapping, struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index >= end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + lock_page(page); WARN_ON(page->index != index); wait_on_page_writeback(page); truncate_inode_page(mapping, page); unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -375,6 +408,7 @@ EXPORT_SYMBOL(truncate_inode_pages); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { + pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index = start; unsigned long ret; @@ -390,17 +424,23 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, */ pagevec_init(&pvec, 0); - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index > end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + if (!trylock_page(page)) continue; WARN_ON(page->index != index); @@ -414,6 +454,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, deactivate_page(page); count += ret; } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -481,6 +522,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page) int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { + pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index; int i; @@ -491,17 +533,23 @@ int invalidate_inode_pages2_range(struct address_space *mapping, cleancache_invalidate_inode(mapping); pagevec_init(&pvec, 0); index = start; - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index > end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + lock_page(page); WARN_ON(page->index != index); if (page->mapping != mapping) { @@ -539,6 +587,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, ret = ret2; unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -613,12 +662,67 @@ EXPORT_SYMBOL(truncate_pagecache); */ void truncate_setsize(struct inode *inode, loff_t newsize) { + loff_t oldsize = inode->i_size; + i_size_write(inode, newsize); + if (newsize > oldsize) + pagecache_isize_extended(inode, oldsize, newsize); truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); /** + * pagecache_isize_extended - update pagecache after extension of i_size + * @inode: inode for which i_size was extended + * @from: original inode size + * @to: new inode size + * + * Handle extension of inode size either caused by extending truncate or by + * write starting after current i_size. We mark the page straddling current + * i_size RO so that page_mkwrite() is called on the nearest write access to + * the page. This way filesystem can be sure that page_mkwrite() is called on + * the page before user writes to the page via mmap after the i_size has been + * changed. + * + * The function must be called after i_size is updated so that page fault + * coming after we unlock the page will already see the new i_size. + * The function must be called while we still hold i_mutex - this not only + * makes sure i_size is stable but also that userspace cannot observe new + * i_size value before we are prepared to store mmap writes at new inode size. + */ +void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) +{ + int bsize = 1 << inode->i_blkbits; + loff_t rounded_from; + struct page *page; + pgoff_t index; + + WARN_ON(to > inode->i_size); + + if (from >= to || bsize == PAGE_CACHE_SIZE) + return; + /* Page straddling @from will not have any hole block created? */ + rounded_from = round_up(from, bsize); + if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1))) + return; + + index = from >> PAGE_CACHE_SHIFT; + page = find_lock_page(inode->i_mapping, index); + /* Page not cached? Nothing to do */ + if (!page) + return; + /* + * See clear_page_dirty_for_io() for details why set_page_dirty() + * is needed. + */ + if (page_mkclean(page)) + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); +} +EXPORT_SYMBOL(pagecache_isize_extended); + +/** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode * @lstart: offset of beginning of hole diff --git a/mm/util.c b/mm/util.c index a24aa22..c1010cb 100644 --- a/mm/util.c +++ b/mm/util.c @@ -275,17 +275,14 @@ pid_t vm_is_stack(struct task_struct *task, if (in_group) { struct task_struct *t; - rcu_read_lock(); - if (!pid_alive(task)) - goto done; - t = task; - do { + rcu_read_lock(); + for_each_thread(task, t) { if (vm_is_stack_for_task(t, vma)) { ret = t->pid; goto done; } - } while_each_thread(task, t); + } done: rcu_read_unlock(); } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 0fdf968..aa3891e 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2681,14 +2681,14 @@ void get_vmalloc_info(struct vmalloc_info *vmi) prev_end = VMALLOC_START; - spin_lock(&vmap_area_lock); + rcu_read_lock(); if (list_empty(&vmap_area_list)) { vmi->largest_chunk = VMALLOC_TOTAL; goto out; } - list_for_each_entry(va, &vmap_area_list, list) { + list_for_each_entry_rcu(va, &vmap_area_list, list) { unsigned long addr = va->va_start; /* @@ -2715,7 +2715,7 @@ void get_vmalloc_info(struct vmalloc_info *vmi) vmi->largest_chunk = VMALLOC_END - prev_end; out: - spin_unlock(&vmap_area_lock); + rcu_read_unlock(); } #endif diff --git a/mm/vmpressure.c b/mm/vmpressure.c index d4042e7..c5afd57 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -165,6 +165,7 @@ static void vmpressure_work_fn(struct work_struct *work) unsigned long scanned; unsigned long reclaimed; + spin_lock(&vmpr->sr_lock); /* * Several contexts might be calling vmpressure(), so it is * possible that the work was rescheduled again before the old @@ -173,11 +174,12 @@ static void vmpressure_work_fn(struct work_struct *work) * here. No need for any locks here since we don't care if * vmpr->reclaimed is in sync. */ - if (!vmpr->scanned) + scanned = vmpr->scanned; + if (!scanned) { + spin_unlock(&vmpr->sr_lock); return; + } - spin_lock(&vmpr->sr_lock); - scanned = vmpr->scanned; reclaimed = vmpr->reclaimed; vmpr->scanned = 0; vmpr->reclaimed = 0; diff --git a/mm/vmscan.c b/mm/vmscan.c index 6ef484f..88edf53 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -163,7 +163,8 @@ static unsigned long zone_reclaimable_pages(struct zone *zone) bool zone_reclaimable(struct zone *zone) { - return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; + return zone_page_state(zone, NR_PAGES_SCANNED) < + zone_reclaimable_pages(zone) * 6; } static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) @@ -224,15 +225,15 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, unsigned long freed = 0; unsigned long long delta; long total_scan; - long max_pass; + long freeable; long nr; long new_nr; int nid = shrinkctl->nid; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; - max_pass = shrinker->count_objects(shrinker, shrinkctl); - if (max_pass == 0) + freeable = shrinker->count_objects(shrinker, shrinkctl); + if (freeable == 0) return 0; /* @@ -244,14 +245,14 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, total_scan = nr; delta = (4 * nr_pages_scanned) / shrinker->seeks; - delta *= max_pass; + delta *= freeable; do_div(delta, lru_pages + 1); total_scan += delta; if (total_scan < 0) { printk(KERN_ERR "shrink_slab: %pF negative objects to delete nr=%ld\n", shrinker->scan_objects, total_scan); - total_scan = max_pass; + total_scan = freeable; } /* @@ -260,26 +261,26 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, * shrinkers to return -1 all the time. This results in a large * nr being built up so when a shrink that can do some work * comes along it empties the entire cache due to nr >>> - * max_pass. This is bad for sustaining a working set in + * freeable. This is bad for sustaining a working set in * memory. * * Hence only allow the shrinker to scan the entire cache when * a large delta change is calculated directly. */ - if (delta < max_pass / 4) - total_scan = min(total_scan, max_pass / 2); + if (delta < freeable / 4) + total_scan = min(total_scan, freeable / 2); /* * Avoid risking looping forever due to too large nr value: * never try to free more than twice the estimate number of * freeable entries. */ - if (total_scan > max_pass * 2) - total_scan = max_pass * 2; + if (total_scan > freeable * 2) + total_scan = freeable * 2; trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, nr_pages_scanned, lru_pages, - max_pass, delta, total_scan); + freeable, delta, total_scan); /* * Normally, we should not scan less than batch_size objects in one @@ -292,12 +293,12 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, * * We detect the "tight on memory" situations by looking at the total * number of objects we want to scan (total_scan). If it is greater - * than the total number of objects on slab (max_pass), we must be + * than the total number of objects on slab (freeable), we must be * scanning at high prio and therefore should try to reclaim as much as * possible. */ while (total_scan >= batch_size || - total_scan >= max_pass) { + total_scan >= freeable) { unsigned long ret; unsigned long nr_to_scan = min(batch_size, total_scan); @@ -870,21 +871,17 @@ static unsigned long shrink_page_list(struct list_head *page_list, * * 2) Global reclaim encounters a page, memcg encounters a * page that is not marked for immediate reclaim or - * the caller does not have __GFP_IO. In this case mark + * the caller does not have __GFP_FS (or __GFP_IO if it's + * simply going to swap, not to fs). In this case mark * the page for immediate reclaim and continue scanning. * - * __GFP_IO is checked because a loop driver thread might + * Require may_enter_fs because we would wait on fs, which + * may not have submitted IO yet. And the loop driver might * enter reclaim, and deadlock if it waits on a page for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * - * Don't require __GFP_FS, since we're not going into the - * FS, just waiting on its writeback completion. Worryingly, - * ext4 gfs2 and xfs allocate pages with - * grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so testing - * may_enter_fs here is liable to OOM on them. - * * 3) memcg encounters a page that is not already marked * PageReclaim. memcg does not have any dirty pages * throttling so we could easily OOM just because too many @@ -901,7 +898,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, /* Case 2 above */ } else if (global_reclaim(sc) || - !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) { + !PageReclaim(page) || !may_enter_fs) { /* * This is slightly racy - end_page_writeback() * might have just cleared PageReclaim, then @@ -1107,7 +1104,7 @@ keep: VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } - free_hot_cold_page_list(&free_pages, 1); + free_hot_cold_page_list(&free_pages, true); list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); @@ -1144,7 +1141,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, TTU_UNMAP|TTU_IGNORE_ACCESS, &dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true); list_splice(&clean_pages, page_list); - __mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); + mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); return ret; } @@ -1470,7 +1467,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken); if (global_reclaim(sc)) { - zone->pages_scanned += nr_scanned; + __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); if (current_is_kswapd()) __count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned); else @@ -1505,7 +1502,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, spin_unlock_irq(&zone->lru_lock); - free_hot_cold_page_list(&page_list, 1); + free_hot_cold_page_list(&page_list, true); /* * If reclaim is isolating dirty pages under writeback, it implies @@ -1659,7 +1656,7 @@ static void shrink_active_list(unsigned long nr_to_scan, nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, isolate_mode, lru); if (global_reclaim(sc)) - zone->pages_scanned += nr_scanned; + __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); reclaim_stat->recent_scanned[file] += nr_taken; @@ -1725,7 +1722,7 @@ static void shrink_active_list(unsigned long nr_to_scan, __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&zone->lru_lock); - free_hot_cold_page_list(&l_hold, 1); + free_hot_cold_page_list(&l_hold, true); } #ifdef CONFIG_SWAP @@ -1847,7 +1844,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, struct zone *zone = lruvec_zone(lruvec); unsigned long anon_prio, file_prio; enum scan_balance scan_balance; - unsigned long anon, file, free; + unsigned long anon, file; bool force_scan = false; unsigned long ap, fp; enum lru_list lru; @@ -1895,11 +1892,6 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, goto out; } - anon = get_lru_size(lruvec, LRU_ACTIVE_ANON) + - get_lru_size(lruvec, LRU_INACTIVE_ANON); - file = get_lru_size(lruvec, LRU_ACTIVE_FILE) + - get_lru_size(lruvec, LRU_INACTIVE_FILE); - /* * If it's foreseeable that reclaiming the file cache won't be * enough to get the zone back into a desirable shape, we have @@ -1907,8 +1899,14 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * thrashing - remaining file pages alone. */ if (global_reclaim(sc)) { - free = zone_page_state(zone, NR_FREE_PAGES); - if (unlikely(file + free <= high_wmark_pages(zone))) { + unsigned long zonefile; + unsigned long zonefree; + + zonefree = zone_page_state(zone, NR_FREE_PAGES); + zonefile = zone_page_state(zone, NR_ACTIVE_FILE) + + zone_page_state(zone, NR_INACTIVE_FILE); + + if (unlikely(zonefile + zonefree <= high_wmark_pages(zone))) { scan_balance = SCAN_ANON; goto out; } @@ -1943,6 +1941,12 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * * anon in [0], file in [1] */ + + anon = get_lru_size(lruvec, LRU_ACTIVE_ANON) + + get_lru_size(lruvec, LRU_INACTIVE_ANON); + file = get_lru_size(lruvec, LRU_ACTIVE_FILE) + + get_lru_size(lruvec, LRU_INACTIVE_FILE); + spin_lock_irq(&zone->lru_lock); if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) { reclaim_stat->recent_scanned[0] /= 2; @@ -2018,13 +2022,27 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; struct blk_plug plug; - bool scan_adjusted = false; + bool scan_adjusted; get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); + /* + * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal + * event that can occur when there is little memory pressure e.g. + * multiple streaming readers/writers. Hence, we do not abort scanning + * when the requested number of pages are reclaimed when scanning at + * DEF_PRIORITY on the assumption that the fact we are direct + * reclaiming implies that kswapd is not keeping up and it is best to + * do a batch of work at once. For memcg reclaim one check is made to + * abort proportional reclaim if either the file or anon lru has already + * dropped to zero at the first pass. + */ + scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() && + sc->priority == DEF_PRIORITY); + blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { @@ -2045,17 +2063,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) continue; /* - * For global direct reclaim, reclaim only the number of pages - * requested. Less care is taken to scan proportionally as it - * is more important to minimise direct reclaim stall latency - * than it is to properly age the LRU lists. - */ - if (global_reclaim(sc) && !current_is_kswapd()) - break; - - /* * For kswapd and memcg, reclaim at least the number of pages - * requested. Ensure that the anon and file LRUs shrink + * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. @@ -2063,6 +2072,15 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; + /* + * It's just vindictive to attack the larger once the smaller + * has gone to zero. And given the way we stop scanning the + * smaller below, this makes sure that we only make one nudge + * towards proportionality once we've got nr_to_reclaim. + */ + if (!nr_file || !nr_anon) + break; + if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; @@ -2424,8 +2442,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, unsigned long lru_pages = 0; nodes_clear(shrink->nodes_to_scan); - for_each_zone_zonelist(zone, z, zonelist, - gfp_zone(sc->gfp_mask)) { + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_zone(sc->gfp_mask), sc->nodemask) { if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; @@ -2846,18 +2864,20 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, return false; /* - * There is a potential race between when kswapd checks its watermarks - * and a process gets throttled. There is also a potential race if - * processes get throttled, kswapd wakes, a large process exits therby - * balancing the zones that causes kswapd to miss a wakeup. If kswapd - * is going to sleep, no process should be sleeping on pfmemalloc_wait - * so wake them now if necessary. If necessary, processes will wake - * kswapd and get throttled again + * The throttled processes are normally woken up in balance_pgdat() as + * soon as pfmemalloc_watermark_ok() is true. But there is a potential + * race between when kswapd checks the watermarks and a process gets + * throttled. There is also a potential race if processes get + * throttled, kswapd wakes, a large process exits thereby balancing the + * zones, which causes kswapd to exit balance_pgdat() before reaching + * the wake up checks. If kswapd is going to sleep, no process should + * be sleeping on pfmemalloc_wait, so wake them now if necessary. If + * the wake up is premature, processes will wake kswapd and get + * throttled again. The difference from wake ups in balance_pgdat() is + * that here we are under prepare_to_wait(). */ - if (waitqueue_active(&pgdat->pfmemalloc_wait)) { - wake_up(&pgdat->pfmemalloc_wait); - return false; - } + if (waitqueue_active(&pgdat->pfmemalloc_wait)) + wake_up_all(&pgdat->pfmemalloc_wait); return pgdat_balanced(pgdat, order, classzone_idx); } diff --git a/mm/vmstat.c b/mm/vmstat.c index def5dd2..eded190 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -200,7 +200,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, continue; threshold = (*calculate_pressure)(zone); - for_each_possible_cpu(cpu) + for_each_online_cpu(cpu) per_cpu_ptr(zone->pageset, cpu)->stat_threshold = threshold; } @@ -761,6 +761,7 @@ const char * const vmstat_text[] = { "nr_shmem", "nr_dirtied", "nr_written", + "nr_pages_scanned", #ifdef CONFIG_NUMA "numa_hit", @@ -1055,7 +1056,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), - zone->pages_scanned, + zone_page_state(zone, NR_PAGES_SCANNED), zone->spanned_pages, zone->present_pages, zone->managed_pages); @@ -1065,10 +1066,10 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, zone_page_state(zone, i)); seq_printf(m, - "\n protection: (%lu", + "\n protection: (%ld", zone->lowmem_reserve[0]); for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++) - seq_printf(m, ", %lu", zone->lowmem_reserve[i]); + seq_printf(m, ", %ld", zone->lowmem_reserve[i]); seq_printf(m, ")" "\n pagesets"); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 7e57135..5d56e05 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -106,59 +106,6 @@ u16 vlan_dev_vlan_id(const struct net_device *dev) } EXPORT_SYMBOL(vlan_dev_vlan_id); -static struct sk_buff *vlan_reorder_header(struct sk_buff *skb) -{ - if (skb_cow(skb, skb_headroom(skb)) < 0) { - kfree_skb(skb); - return NULL; - } - - memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); - skb->mac_header += VLAN_HLEN; - return skb; -} - -struct sk_buff *vlan_untag(struct sk_buff *skb) -{ - struct vlan_hdr *vhdr; - u16 vlan_tci; - - if (unlikely(vlan_tx_tag_present(skb))) { - /* vlan_tci is already set-up so leave this for another time */ - return skb; - } - - skb = skb_share_check(skb, GFP_ATOMIC); - if (unlikely(!skb)) - goto err_free; - - if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) - goto err_free; - - vhdr = (struct vlan_hdr *) skb->data; - vlan_tci = ntohs(vhdr->h_vlan_TCI); - __vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci); - - skb_pull_rcsum(skb, VLAN_HLEN); - vlan_set_encap_proto(skb, vhdr); - - skb = vlan_reorder_header(skb); - if (unlikely(!skb)) - goto err_free; - - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - skb_reset_mac_len(skb); - - return skb; - -err_free: - kfree_skb(skb); - return NULL; -} -EXPORT_SYMBOL(vlan_untag); - - /* * vlan info and vid list */ diff --git a/net/9p/client.c b/net/9p/client.c index 9186550..08046f3 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -839,7 +839,8 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type, if (err < 0) { if (err == -EIO) c->status = Disconnected; - goto reterr; + if (err != -ERESTARTSYS) + goto reterr; } if (req->status == REQ_STATUS_ERROR) { p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err); diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index cc1cfd6..e5c5f57 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -128,6 +128,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, { struct batadv_frag_table_entry *chain; struct batadv_frag_list_entry *frag_entry_new = NULL, *frag_entry_curr; + struct batadv_frag_list_entry *frag_entry_last = NULL; struct batadv_frag_packet *frag_packet; uint8_t bucket; uint16_t seqno, hdr_size = sizeof(struct batadv_frag_packet); @@ -180,11 +181,14 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, ret = true; goto out; } + + /* store current entry because it could be the last in list */ + frag_entry_last = frag_entry_curr; } - /* Reached the end of the list, so insert after 'frag_entry_curr'. */ - if (likely(frag_entry_curr)) { - hlist_add_after(&frag_entry_curr->list, &frag_entry_new->list); + /* Reached the end of the list, so insert after 'frag_entry_last'. */ + if (likely(frag_entry_last)) { + hlist_add_after(&frag_entry_last->list, &frag_entry_new->list); chain->size += skb->len - hdr_size; chain->timestamp = jiffies; ret = true; @@ -247,7 +251,7 @@ batadv_frag_merge_packets(struct hlist_head *chain, struct sk_buff *skb) kfree(entry); /* Make room for the rest of the fragments. */ - if (pskb_expand_head(skb_out, 0, size - skb->len, GFP_ATOMIC) < 0) { + if (pskb_expand_head(skb_out, 0, size - skb_out->len, GFP_ATOMIC) < 0) { kfree_skb(skb_out); skb_out = NULL; goto free; @@ -430,7 +434,7 @@ bool batadv_frag_send_packet(struct sk_buff *skb, * fragments larger than BATADV_FRAG_MAX_FRAG_SIZE */ mtu = min_t(unsigned, mtu, BATADV_FRAG_MAX_FRAG_SIZE); - max_fragment_size = (mtu - header_size - ETH_HLEN); + max_fragment_size = mtu - header_size; max_packet_size = max_fragment_size * BATADV_FRAG_MAX_FRAGMENTS; /* Don't even try to fragment, if we need more than 16 fragments */ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 36b9ae6..2393ea7 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -812,7 +812,7 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, goto out; gw_node = batadv_gw_node_get(bat_priv, orig_dst_node); - if (!gw_node->bandwidth_down == 0) + if (!gw_node) goto out; switch (atomic_read(&bat_priv->gw_mode)) { diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index b851cc5..fbda6b5 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -83,7 +83,7 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) return true; /* no more parents..stop recursion */ - if (net_dev->iflink == net_dev->ifindex) + if (net_dev->iflink == 0 || net_dev->iflink == net_dev->ifindex) return false; /* recurse over the parent device */ diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 6afa3b4..0007c9e 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -2608,12 +2608,8 @@ static int l2cap_segment_le_sdu(struct l2cap_chan *chan, BT_DBG("chan %p, msg %p, len %zu", chan, msg, len); - pdu_len = chan->conn->mtu - L2CAP_HDR_SIZE; - - pdu_len = min_t(size_t, pdu_len, chan->remote_mps); - sdu_len = len; - pdu_len -= L2CAP_SDULEN_SIZE; + pdu_len = chan->remote_mps - L2CAP_SDULEN_SIZE; while (len > 0) { if (len <= pdu_len) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 27ae841..06a7a76 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1112,7 +1112,8 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) l2cap_chan_close(chan, 0); lock_sock(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index facd8a7..b088651 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1859,10 +1859,13 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s) /* Get data directly from socket receive queue without copying it. */ while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); - if (!skb_linearize(skb)) + if (!skb_linearize(skb)) { s = rfcomm_recv_frame(s, skb); - else + if (!s) + break; + } else { kfree_skb(skb); + } } if (s && (sk->sk_state == BT_CLOSED)) diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 3c2d3e4..a0050de 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -898,7 +898,8 @@ static int rfcomm_sock_shutdown(struct socket *sock, int how) sk->sk_shutdown = SHUTDOWN_MASK; __rfcomm_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } release_sock(sk); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 24fa396..316dd4e 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -909,7 +909,8 @@ static int sco_sock_shutdown(struct socket *sock, int how) sco_sock_clear_timer(sk); __sco_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } @@ -929,7 +930,8 @@ static int sco_sock_release(struct socket *sock) sco_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) { + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) { lock_sock(sk); err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); release_sock(sk); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 9203d5a..09152d1 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -705,9 +705,11 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p, int err = 0; if (ndm->ndm_flags & NTF_USE) { + local_bh_disable(); rcu_read_lock(); br_fdb_update(p->br, p, addr, vid, true); rcu_read_unlock(); + local_bh_enable(); } else { spin_lock_bh(&p->br->hash_lock); err = fdb_add_entry(p, addr, ndm->ndm_state, diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index a9a4a1b..8d423bc 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -247,9 +247,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; - spin_lock_bh(&br->lock); br_stp_set_bridge_priority(br, args[1]); - spin_unlock_bh(&br->lock); return 0; case BRCTL_SET_PORT_PRIORITY: diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 93067ec..7bbc8fe 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1056,7 +1056,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, vid); - if (!err) + if (err) break; } @@ -1086,6 +1086,9 @@ static void br_multicast_add_router(struct net_bridge *br, struct net_bridge_port *p; struct hlist_node *slot = NULL; + if (!hlist_unhashed(&port->rlist)) + return; + hlist_for_each_entry(p, &br->router_list, rlist) { if ((unsigned long) port >= (unsigned long) p) break; @@ -1113,12 +1116,8 @@ static void br_multicast_mark_router(struct net_bridge *br, if (port->multicast_router != 1) return; - if (!hlist_unhashed(&port->rlist)) - goto timer; - br_multicast_add_router(br, port); -timer: mod_timer(&port->multicast_router_timer, now + br->multicast_querier_interval); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index f2d254b..4acfc3e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -302,6 +302,9 @@ struct br_input_skb_cb { int igmp; int mrouters_only; #endif +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + bool vlan_filtered; +#endif }; #define BR_INPUT_SKB_CB(__skb) ((struct br_input_skb_cb *)(__skb)->cb) diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 189ba1e..9a0005a 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -243,12 +243,13 @@ bool br_stp_recalculate_bridge_id(struct net_bridge *br) return true; } -/* called under bridge lock */ +/* Acquires and releases bridge lock */ void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio) { struct net_bridge_port *p; int wasroot; + spin_lock_bh(&br->lock); wasroot = br_is_root_bridge(br); list_for_each_entry(p, &br->port_list, list) { @@ -266,6 +267,7 @@ void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio) br_port_state_selection(br); if (br_is_root_bridge(br) && !wasroot) br_become_root_bridge(br); + spin_unlock_bh(&br->lock); } /* called under bridge lock */ diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index b1c6372..e1bd253 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -125,7 +125,8 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, { u16 vid; - if (!br->vlan_enabled) + /* If this packet was not filtered at input, let it pass */ + if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) goto out; /* Vlan filter table must be configured at this point. The @@ -163,8 +164,10 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, /* If VLAN filtering is disabled on the bridge, all packets are * permitted. */ - if (!br->vlan_enabled) + if (!br->vlan_enabled) { + BR_INPUT_SKB_CB(skb)->vlan_filtered = false; return true; + } /* If there are no vlan in the permitted list, all packets are * rejected. @@ -172,6 +175,8 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, if (!v) goto drop; + BR_INPUT_SKB_CB(skb)->vlan_filtered = true; + /* If vlan tx offload is disabled on bridge device and frame was * sent from vlan device on the bridge device, it does not have * HW accelerated vlan tag. @@ -179,7 +184,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, if (unlikely(!vlan_tx_tag_present(skb) && (skb->protocol == htons(ETH_P_8021Q) || skb->protocol == htons(ETH_P_8021AD)))) { - skb = vlan_untag(skb); + skb = skb_vlan_untag(skb); if (unlikely(!skb)) return false; } @@ -228,7 +233,8 @@ bool br_allowed_egress(struct net_bridge *br, { u16 vid; - if (!br->vlan_enabled) + /* If this packet was not filtered at input, let it pass */ + if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) return true; if (!v) @@ -247,6 +253,7 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) struct net_bridge *br = p->br; struct net_port_vlans *v; + /* If filtering was disabled at input, let it pass. */ if (!br->vlan_enabled) return true; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index d6be3ed..afeb8e0 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -283,7 +283,7 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock, int copylen; ret = -EOPNOTSUPP; - if (m->msg_flags&MSG_OOB) + if (flags & MSG_OOB) goto read_error; skb = skb_recv_datagram(sk, flags, 0 , &ret); @@ -332,6 +332,10 @@ static long caif_stream_data_wait(struct sock *sk, long timeo) release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); + + if (sock_flag(sk, SOCK_DEAD)) + break; + clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); } @@ -376,6 +380,10 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock, struct sk_buff *skb; lock_sock(sk); + if (sock_flag(sk, SOCK_DEAD)) { + err = -ECONNRESET; + goto unlock; + } skb = skb_dequeue(&sk->sk_receive_queue); caif_check_flow_release(sk); diff --git a/net/can/af_can.c b/net/can/af_can.c index a27f8aa..5e9a227 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -262,6 +262,9 @@ int can_send(struct sk_buff *skb, int loop) goto inval_skb; } + skb->ip_summed = CHECKSUM_UNNECESSARY; + + skb_reset_mac_header(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 96238ba..de6662b 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -13,8 +13,6 @@ #include "auth_x.h" #include "auth_x_protocol.h" -#define TEMP_TICKET_BUF_LEN 256 - static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed); static int ceph_x_is_authenticated(struct ceph_auth_client *ac) @@ -64,7 +62,7 @@ static int ceph_x_encrypt(struct ceph_crypto_key *secret, } static int ceph_x_decrypt(struct ceph_crypto_key *secret, - void **p, void *end, void *obuf, size_t olen) + void **p, void *end, void **obuf, size_t olen) { struct ceph_x_encrypt_header head; size_t head_len = sizeof(head); @@ -75,8 +73,14 @@ static int ceph_x_decrypt(struct ceph_crypto_key *secret, return -EINVAL; dout("ceph_x_decrypt len %d\n", len); - ret = ceph_decrypt2(secret, &head, &head_len, obuf, &olen, - *p, len); + if (*obuf == NULL) { + *obuf = kmalloc(len, GFP_NOFS); + if (!*obuf) + return -ENOMEM; + olen = len; + } + + ret = ceph_decrypt2(secret, &head, &head_len, *obuf, &olen, *p, len); if (ret) return ret; if (head.struct_v != 1 || le64_to_cpu(head.magic) != CEPHX_ENC_MAGIC) @@ -129,139 +133,120 @@ static void remove_ticket_handler(struct ceph_auth_client *ac, kfree(th); } -static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac, - struct ceph_crypto_key *secret, - void *buf, void *end) +static int process_one_ticket(struct ceph_auth_client *ac, + struct ceph_crypto_key *secret, + void **p, void *end) { struct ceph_x_info *xi = ac->private; - int num; - void *p = buf; + int type; + u8 tkt_struct_v, blob_struct_v; + struct ceph_x_ticket_handler *th; + void *dbuf = NULL; + void *dp, *dend; + int dlen; + char is_enc; + struct timespec validity; + struct ceph_crypto_key old_key; + void *ticket_buf = NULL; + void *tp, *tpend; + struct ceph_timespec new_validity; + struct ceph_crypto_key new_session_key; + struct ceph_buffer *new_ticket_blob; + unsigned long new_expires, new_renew_after; + u64 new_secret_id; int ret; - char *dbuf; - char *ticket_buf; - u8 reply_struct_v; - dbuf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS); - if (!dbuf) - return -ENOMEM; + ceph_decode_need(p, end, sizeof(u32) + 1, bad); - ret = -ENOMEM; - ticket_buf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS); - if (!ticket_buf) - goto out_dbuf; + type = ceph_decode_32(p); + dout(" ticket type %d %s\n", type, ceph_entity_type_name(type)); - ceph_decode_need(&p, end, 1 + sizeof(u32), bad); - reply_struct_v = ceph_decode_8(&p); - if (reply_struct_v != 1) + tkt_struct_v = ceph_decode_8(p); + if (tkt_struct_v != 1) goto bad; - num = ceph_decode_32(&p); - dout("%d tickets\n", num); - while (num--) { - int type; - u8 tkt_struct_v, blob_struct_v; - struct ceph_x_ticket_handler *th; - void *dp, *dend; - int dlen; - char is_enc; - struct timespec validity; - struct ceph_crypto_key old_key; - void *tp, *tpend; - struct ceph_timespec new_validity; - struct ceph_crypto_key new_session_key; - struct ceph_buffer *new_ticket_blob; - unsigned long new_expires, new_renew_after; - u64 new_secret_id; - - ceph_decode_need(&p, end, sizeof(u32) + 1, bad); - - type = ceph_decode_32(&p); - dout(" ticket type %d %s\n", type, ceph_entity_type_name(type)); - - tkt_struct_v = ceph_decode_8(&p); - if (tkt_struct_v != 1) - goto bad; - - th = get_ticket_handler(ac, type); - if (IS_ERR(th)) { - ret = PTR_ERR(th); - goto out; - } - /* blob for me */ - dlen = ceph_x_decrypt(secret, &p, end, dbuf, - TEMP_TICKET_BUF_LEN); - if (dlen <= 0) { - ret = dlen; - goto out; - } - dout(" decrypted %d bytes\n", dlen); - dend = dbuf + dlen; - dp = dbuf; + th = get_ticket_handler(ac, type); + if (IS_ERR(th)) { + ret = PTR_ERR(th); + goto out; + } - tkt_struct_v = ceph_decode_8(&dp); - if (tkt_struct_v != 1) - goto bad; + /* blob for me */ + dlen = ceph_x_decrypt(secret, p, end, &dbuf, 0); + if (dlen <= 0) { + ret = dlen; + goto out; + } + dout(" decrypted %d bytes\n", dlen); + dp = dbuf; + dend = dp + dlen; - memcpy(&old_key, &th->session_key, sizeof(old_key)); - ret = ceph_crypto_key_decode(&new_session_key, &dp, dend); - if (ret) - goto out; + tkt_struct_v = ceph_decode_8(&dp); + if (tkt_struct_v != 1) + goto bad; - ceph_decode_copy(&dp, &new_validity, sizeof(new_validity)); - ceph_decode_timespec(&validity, &new_validity); - new_expires = get_seconds() + validity.tv_sec; - new_renew_after = new_expires - (validity.tv_sec / 4); - dout(" expires=%lu renew_after=%lu\n", new_expires, - new_renew_after); + memcpy(&old_key, &th->session_key, sizeof(old_key)); + ret = ceph_crypto_key_decode(&new_session_key, &dp, dend); + if (ret) + goto out; - /* ticket blob for service */ - ceph_decode_8_safe(&p, end, is_enc, bad); - tp = ticket_buf; - if (is_enc) { - /* encrypted */ - dout(" encrypted ticket\n"); - dlen = ceph_x_decrypt(&old_key, &p, end, ticket_buf, - TEMP_TICKET_BUF_LEN); - if (dlen < 0) { - ret = dlen; - goto out; - } - dlen = ceph_decode_32(&tp); - } else { - /* unencrypted */ - ceph_decode_32_safe(&p, end, dlen, bad); - ceph_decode_need(&p, end, dlen, bad); - ceph_decode_copy(&p, ticket_buf, dlen); + ceph_decode_copy(&dp, &new_validity, sizeof(new_validity)); + ceph_decode_timespec(&validity, &new_validity); + new_expires = get_seconds() + validity.tv_sec; + new_renew_after = new_expires - (validity.tv_sec / 4); + dout(" expires=%lu renew_after=%lu\n", new_expires, + new_renew_after); + + /* ticket blob for service */ + ceph_decode_8_safe(p, end, is_enc, bad); + if (is_enc) { + /* encrypted */ + dout(" encrypted ticket\n"); + dlen = ceph_x_decrypt(&old_key, p, end, &ticket_buf, 0); + if (dlen < 0) { + ret = dlen; + goto out; } - tpend = tp + dlen; - dout(" ticket blob is %d bytes\n", dlen); - ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad); - blob_struct_v = ceph_decode_8(&tp); - new_secret_id = ceph_decode_64(&tp); - ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend); - if (ret) + tp = ticket_buf; + dlen = ceph_decode_32(&tp); + } else { + /* unencrypted */ + ceph_decode_32_safe(p, end, dlen, bad); + ticket_buf = kmalloc(dlen, GFP_NOFS); + if (!ticket_buf) { + ret = -ENOMEM; goto out; - - /* all is well, update our ticket */ - ceph_crypto_key_destroy(&th->session_key); - if (th->ticket_blob) - ceph_buffer_put(th->ticket_blob); - th->session_key = new_session_key; - th->ticket_blob = new_ticket_blob; - th->validity = new_validity; - th->secret_id = new_secret_id; - th->expires = new_expires; - th->renew_after = new_renew_after; - dout(" got ticket service %d (%s) secret_id %lld len %d\n", - type, ceph_entity_type_name(type), th->secret_id, - (int)th->ticket_blob->vec.iov_len); - xi->have_keys |= th->service; + } + tp = ticket_buf; + ceph_decode_need(p, end, dlen, bad); + ceph_decode_copy(p, ticket_buf, dlen); } + tpend = tp + dlen; + dout(" ticket blob is %d bytes\n", dlen); + ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad); + blob_struct_v = ceph_decode_8(&tp); + new_secret_id = ceph_decode_64(&tp); + ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend); + if (ret) + goto out; + + /* all is well, update our ticket */ + ceph_crypto_key_destroy(&th->session_key); + if (th->ticket_blob) + ceph_buffer_put(th->ticket_blob); + th->session_key = new_session_key; + th->ticket_blob = new_ticket_blob; + th->validity = new_validity; + th->secret_id = new_secret_id; + th->expires = new_expires; + th->renew_after = new_renew_after; + dout(" got ticket service %d (%s) secret_id %lld len %d\n", + type, ceph_entity_type_name(type), th->secret_id, + (int)th->ticket_blob->vec.iov_len); + xi->have_keys |= th->service; - ret = 0; out: kfree(ticket_buf); -out_dbuf: kfree(dbuf); return ret; @@ -270,6 +255,34 @@ bad: goto out; } +static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac, + struct ceph_crypto_key *secret, + void *buf, void *end) +{ + void *p = buf; + u8 reply_struct_v; + u32 num; + int ret; + + ceph_decode_8_safe(&p, end, reply_struct_v, bad); + if (reply_struct_v != 1) + return -EINVAL; + + ceph_decode_32_safe(&p, end, num, bad); + dout("%d tickets\n", num); + + while (num--) { + ret = process_one_ticket(ac, secret, &p, end); + if (ret) + return ret; + } + + return 0; + +bad: + return -EINVAL; +} + static int ceph_x_build_authorizer(struct ceph_auth_client *ac, struct ceph_x_ticket_handler *th, struct ceph_x_authorizer *au) @@ -583,13 +596,14 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac, struct ceph_x_ticket_handler *th; int ret = 0; struct ceph_x_authorize_reply reply; + void *preply = &reply; void *p = au->reply_buf; void *end = p + sizeof(au->reply_buf); th = get_ticket_handler(ac, au->service); if (IS_ERR(th)) return PTR_ERR(th); - ret = ceph_x_decrypt(&th->session_key, &p, end, &reply, sizeof(reply)); + ret = ceph_x_decrypt(&th->session_key, &p, end, &preply, sizeof(reply)); if (ret < 0) return ret; if (ret != sizeof(reply)) diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 074bb2a..0a08902 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -290,6 +290,7 @@ static int is_out(const struct crush_map *map, * @type: the type of item to choose * @out: pointer to output vector * @outpos: our position in that vector + * @out_size: size of the out vector * @tries: number of attempts to make * @recurse_tries: number of attempts to have recursive chooseleaf make * @local_retries: localized retries @@ -302,6 +303,7 @@ static int crush_choose_firstn(const struct crush_map *map, const __u32 *weight, int weight_max, int x, int numrep, int type, int *out, int outpos, + int out_size, unsigned int tries, unsigned int recurse_tries, unsigned int local_retries, @@ -318,11 +320,12 @@ static int crush_choose_firstn(const struct crush_map *map, int item = 0; int itemtype; int collide, reject; + int count = out_size; dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "", bucket->id, x, outpos, numrep); - for (rep = outpos; rep < numrep; rep++) { + for (rep = outpos; rep < numrep && count > 0 ; rep++) { /* keep trying until we get a non-out, non-colliding item */ ftotal = 0; skip_rep = 0; @@ -391,7 +394,7 @@ static int crush_choose_firstn(const struct crush_map *map, map->buckets[-1-item], weight, weight_max, x, outpos+1, 0, - out2, outpos, + out2, outpos, count, recurse_tries, 0, local_retries, local_fallback_retries, @@ -449,6 +452,7 @@ reject: dprintk("CHOOSE got %d\n", item); out[outpos] = item; outpos++; + count--; } dprintk("CHOOSE returns %d\n", outpos); @@ -640,6 +644,7 @@ int crush_do_rule(const struct crush_map *map, __u32 step; int i, j; int numrep; + int out_size; /* * the original choose_total_tries value was off by one (it * counted "retries" and not "tries"). add one. @@ -740,6 +745,7 @@ int crush_do_rule(const struct crush_map *map, x, numrep, curstep->arg2, o+osize, j, + result_max-osize, choose_tries, recurse_tries, choose_local_retries, @@ -747,11 +753,13 @@ int crush_do_rule(const struct crush_map *map, recurse_to_leaf, c+osize); } else { + out_size = ((numrep < (result_max-osize)) ? + numrep : (result_max-osize)); crush_choose_indep( map, map->buckets[-1-w[i]], weight, weight_max, - x, numrep, numrep, + x, out_size, numrep, curstep->arg2, o+osize, j, choose_tries, @@ -760,7 +768,7 @@ int crush_do_rule(const struct crush_map *map, recurse_to_leaf, c+osize, 0); - osize += numrep; + osize += out_size; } } diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 6e7a236..06f19b9 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -89,11 +89,82 @@ static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void) static const u8 *aes_iv = (u8 *)CEPH_AES_IV; +/* + * Should be used for buffers allocated with ceph_kvmalloc(). + * Currently these are encrypt out-buffer (ceph_buffer) and decrypt + * in-buffer (msg front). + * + * Dispose of @sgt with teardown_sgtable(). + * + * @prealloc_sg is to avoid memory allocation inside sg_alloc_table() + * in cases where a single sg is sufficient. No attempt to reduce the + * number of sgs by squeezing physically contiguous pages together is + * made though, for simplicity. + */ +static int setup_sgtable(struct sg_table *sgt, struct scatterlist *prealloc_sg, + const void *buf, unsigned int buf_len) +{ + struct scatterlist *sg; + const bool is_vmalloc = is_vmalloc_addr(buf); + unsigned int off = offset_in_page(buf); + unsigned int chunk_cnt = 1; + unsigned int chunk_len = PAGE_ALIGN(off + buf_len); + int i; + int ret; + + if (buf_len == 0) { + memset(sgt, 0, sizeof(*sgt)); + return -EINVAL; + } + + if (is_vmalloc) { + chunk_cnt = chunk_len >> PAGE_SHIFT; + chunk_len = PAGE_SIZE; + } + + if (chunk_cnt > 1) { + ret = sg_alloc_table(sgt, chunk_cnt, GFP_NOFS); + if (ret) + return ret; + } else { + WARN_ON(chunk_cnt != 1); + sg_init_table(prealloc_sg, 1); + sgt->sgl = prealloc_sg; + sgt->nents = sgt->orig_nents = 1; + } + + for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) { + struct page *page; + unsigned int len = min(chunk_len - off, buf_len); + + if (is_vmalloc) + page = vmalloc_to_page(buf); + else + page = virt_to_page(buf); + + sg_set_page(sg, page, len, off); + + off = 0; + buf += len; + buf_len -= len; + } + WARN_ON(buf_len != 0); + + return 0; +} + +static void teardown_sgtable(struct sg_table *sgt) +{ + if (sgt->orig_nents > 1) + sg_free_table(sgt); +} + static int ceph_aes_encrypt(const void *key, int key_len, void *dst, size_t *dst_len, const void *src, size_t src_len) { - struct scatterlist sg_in[2], sg_out[1]; + struct scatterlist sg_in[2], prealloc_sg; + struct sg_table sg_out; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; int ret; @@ -109,16 +180,18 @@ static int ceph_aes_encrypt(const void *key, int key_len, *dst_len = src_len + zero_padding; - crypto_blkcipher_setkey((void *)tfm, key, key_len); sg_init_table(sg_in, 2); sg_set_buf(&sg_in[0], src, src_len); sg_set_buf(&sg_in[1], pad, zero_padding); - sg_init_table(sg_out, 1); - sg_set_buf(sg_out, dst, *dst_len); + ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len); + if (ret) + goto out_tfm; + + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); + /* print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, key, key_len, 1); @@ -127,16 +200,22 @@ static int ceph_aes_encrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, pad, zero_padding, 1); */ - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, + ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in, src_len + zero_padding); - crypto_free_blkcipher(tfm); - if (ret < 0) + if (ret < 0) { pr_err("ceph_aes_crypt failed %d\n", ret); + goto out_sg; + } /* print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_out); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, @@ -144,7 +223,8 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, const void *src1, size_t src1_len, const void *src2, size_t src2_len) { - struct scatterlist sg_in[3], sg_out[1]; + struct scatterlist sg_in[3], prealloc_sg; + struct sg_table sg_out; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; int ret; @@ -160,17 +240,19 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, *dst_len = src1_len + src2_len + zero_padding; - crypto_blkcipher_setkey((void *)tfm, key, key_len); sg_init_table(sg_in, 3); sg_set_buf(&sg_in[0], src1, src1_len); sg_set_buf(&sg_in[1], src2, src2_len); sg_set_buf(&sg_in[2], pad, zero_padding); - sg_init_table(sg_out, 1); - sg_set_buf(sg_out, dst, *dst_len); + ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len); + if (ret) + goto out_tfm; + + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); + /* print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, key, key_len, 1); @@ -181,23 +263,30 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, pad, zero_padding, 1); */ - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, + ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in, src1_len + src2_len + zero_padding); - crypto_free_blkcipher(tfm); - if (ret < 0) + if (ret < 0) { pr_err("ceph_aes_crypt2 failed %d\n", ret); + goto out_sg; + } /* print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_out); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_decrypt(const void *key, int key_len, void *dst, size_t *dst_len, const void *src, size_t src_len) { - struct scatterlist sg_in[1], sg_out[2]; + struct sg_table sg_in; + struct scatterlist sg_out[2], prealloc_sg; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm }; char pad[16]; @@ -209,16 +298,16 @@ static int ceph_aes_decrypt(const void *key, int key_len, if (IS_ERR(tfm)) return PTR_ERR(tfm); - crypto_blkcipher_setkey((void *)tfm, key, key_len); - sg_init_table(sg_in, 1); sg_init_table(sg_out, 2); - sg_set_buf(sg_in, src, src_len); sg_set_buf(&sg_out[0], dst, *dst_len); sg_set_buf(&sg_out[1], pad, sizeof(pad)); + ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len); + if (ret) + goto out_tfm; + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); /* @@ -227,12 +316,10 @@ static int ceph_aes_decrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, src, src_len, 1); */ - - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); - crypto_free_blkcipher(tfm); + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len); if (ret < 0) { pr_err("ceph_aes_decrypt failed %d\n", ret); - return ret; + goto out_sg; } if (src_len <= *dst_len) @@ -250,7 +337,12 @@ static int ceph_aes_decrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_in); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_decrypt2(const void *key, int key_len, @@ -258,7 +350,8 @@ static int ceph_aes_decrypt2(const void *key, int key_len, void *dst2, size_t *dst2_len, const void *src, size_t src_len) { - struct scatterlist sg_in[1], sg_out[3]; + struct sg_table sg_in; + struct scatterlist sg_out[3], prealloc_sg; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm }; char pad[16]; @@ -270,17 +363,17 @@ static int ceph_aes_decrypt2(const void *key, int key_len, if (IS_ERR(tfm)) return PTR_ERR(tfm); - sg_init_table(sg_in, 1); - sg_set_buf(sg_in, src, src_len); sg_init_table(sg_out, 3); sg_set_buf(&sg_out[0], dst1, *dst1_len); sg_set_buf(&sg_out[1], dst2, *dst2_len); sg_set_buf(&sg_out[2], pad, sizeof(pad)); + ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len); + if (ret) + goto out_tfm; crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); /* @@ -289,12 +382,10 @@ static int ceph_aes_decrypt2(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, src, src_len, 1); */ - - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); - crypto_free_blkcipher(tfm); + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len); if (ret < 0) { pr_err("ceph_aes_decrypt failed %d\n", ret); - return ret; + goto out_sg; } if (src_len <= *dst1_len) @@ -324,7 +415,11 @@ static int ceph_aes_decrypt2(const void *key, int key_len, dst2, *dst2_len, 1); */ - return 0; +out_sg: + teardown_sgtable(&sg_in); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 988721a..2e87eec 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -291,7 +291,11 @@ int ceph_msgr_init(void) if (ceph_msgr_slab_init()) return -ENOMEM; - ceph_msgr_wq = alloc_workqueue("ceph-msgr", 0, 0); + /* + * The number of active work items is limited by the number of + * connections, so leave @max_active at default. + */ + ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_MEM_RECLAIM, 0); if (ceph_msgr_wq) return 0; @@ -900,7 +904,7 @@ static void ceph_msg_data_pages_cursor_init(struct ceph_msg_data_cursor *cursor, BUG_ON(page_count > (int)USHRT_MAX); cursor->page_count = (unsigned short)page_count; BUG_ON(length > SIZE_MAX - cursor->page_offset); - cursor->last_piece = (size_t)cursor->page_offset + length <= PAGE_SIZE; + cursor->last_piece = cursor->page_offset + cursor->resid <= PAGE_SIZE; } static struct page * diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 2ac9ef3..dbcbf5a 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1041,7 +1041,15 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con, if (!m) { pr_info("alloc_msg unknown type %d\n", type); *skip = 1; + } else if (front_len > m->front_alloc_len) { + pr_warning("mon_alloc_msg front %d > prealloc %d (%u#%llu)\n", + front_len, m->front_alloc_len, + (unsigned int)con->peer_name.type, + le64_to_cpu(con->peer_name.num)); + ceph_msg_put(m); + m = ceph_msg_new(type, front_len, GFP_NOFS, false); } + return m; } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 0676f2b..5b7ef5b 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -977,12 +977,24 @@ static void put_osd(struct ceph_osd *osd) */ static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) { - dout("__remove_osd %p\n", osd); - BUG_ON(!list_empty(&osd->o_requests)); - rb_erase(&osd->o_node, &osdc->osds); + dout("%s %p osd%d\n", __func__, osd, osd->o_osd); + WARN_ON(!list_empty(&osd->o_requests)); + WARN_ON(!list_empty(&osd->o_linger_requests)); + list_del_init(&osd->o_osd_lru); - ceph_con_close(&osd->o_con); - put_osd(osd); + rb_erase(&osd->o_node, &osdc->osds); + RB_CLEAR_NODE(&osd->o_node); +} + +static void remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) +{ + dout("%s %p osd%d\n", __func__, osd, osd->o_osd); + + if (!RB_EMPTY_NODE(&osd->o_node)) { + ceph_con_close(&osd->o_con); + __remove_osd(osdc, osd); + put_osd(osd); + } } static void remove_all_osds(struct ceph_osd_client *osdc) @@ -992,7 +1004,7 @@ static void remove_all_osds(struct ceph_osd_client *osdc) while (!RB_EMPTY_ROOT(&osdc->osds)) { struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds), struct ceph_osd, o_node); - __remove_osd(osdc, osd); + remove_osd(osdc, osd); } mutex_unlock(&osdc->request_mutex); } @@ -1022,7 +1034,7 @@ static void remove_old_osds(struct ceph_osd_client *osdc) list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) { if (time_before(jiffies, osd->lru_ttl)) break; - __remove_osd(osdc, osd); + remove_osd(osdc, osd); } mutex_unlock(&osdc->request_mutex); } @@ -1037,8 +1049,7 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) dout("__reset_osd %p osd%d\n", osd, osd->o_osd); if (list_empty(&osd->o_requests) && list_empty(&osd->o_linger_requests)) { - __remove_osd(osdc, osd); - + remove_osd(osdc, osd); return -ENODEV; } @@ -1840,6 +1851,7 @@ static void reset_changed_osds(struct ceph_osd_client *osdc) { struct rb_node *p, *n; + dout("%s %p\n", __func__, osdc); for (p = rb_first(&osdc->osds); p; p = n) { struct ceph_osd *osd = rb_entry(p, struct ceph_osd, o_node); @@ -1920,20 +1932,29 @@ static void kick_requests(struct ceph_osd_client *osdc, bool force_resend, err = __map_request(osdc, req, force_resend || force_resend_writes); dout("__map_request returned %d\n", err); - if (err == 0) - continue; /* no change and no osd was specified */ if (err < 0) continue; /* hrm! */ - if (req->r_osd == NULL) { - dout("tid %llu maps to no valid osd\n", req->r_tid); - needmap++; /* request a newer map */ - continue; - } + if (req->r_osd == NULL || err > 0) { + if (req->r_osd == NULL) { + dout("lingering %p tid %llu maps to no osd\n", + req, req->r_tid); + /* + * A homeless lingering request makes + * no sense, as it's job is to keep + * a particular OSD connection open. + * Request a newer map and kick the + * request, knowing that it won't be + * resent until we actually get a map + * that can tell us where to send it. + */ + needmap++; + } - dout("kicking lingering %p tid %llu osd%d\n", req, req->r_tid, - req->r_osd ? req->r_osd->o_osd : -1); - __register_request(osdc, req); - __unregister_linger_request(osdc, req); + dout("kicking lingering %p tid %llu osd%d\n", req, + req->r_tid, req->r_osd ? req->r_osd->o_osd : -1); + __register_request(osdc, req); + __unregister_linger_request(osdc, req); + } } reset_changed_osds(osdc); mutex_unlock(&osdc->request_mutex); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index aade4a5..bde94d8 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -89,7 +89,7 @@ static int crush_decode_tree_bucket(void **p, void *end, { int j; dout("crush_decode_tree_bucket %p to %p\n", *p, end); - ceph_decode_32_safe(p, end, b->num_nodes, bad); + ceph_decode_8_safe(p, end, b->num_nodes, bad); b->node_weights = kcalloc(b->num_nodes, sizeof(u32), GFP_NOFS); if (b->node_weights == NULL) return -ENOMEM; diff --git a/net/compat.c b/net/compat.c index f50161f..d125290 100644 --- a/net/compat.c +++ b/net/compat.c @@ -71,6 +71,13 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg) __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || __get_user(kmsg->msg_flags, &umsg->msg_flags)) return -EFAULT; + + if (!tmp1) + kmsg->msg_namelen = 0; + + if (kmsg->msg_namelen < 0) + return -EINVAL; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); kmsg->msg_name = compat_ptr(tmp1); @@ -85,7 +92,7 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov, { int tot_len; - if (kern_msg->msg_namelen) { + if (kern_msg->msg_name && kern_msg->msg_namelen) { if (mode == VERIFY_READ) { int err = move_addr_to_kernel(kern_msg->msg_name, kern_msg->msg_namelen, @@ -93,10 +100,11 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov, if (err < 0) return err; } - if (kern_msg->msg_name) - kern_msg->msg_name = kern_address; - } else + kern_msg->msg_name = kern_address; + } else { kern_msg->msg_name = NULL; + kern_msg->msg_namelen = 0; + } tot_len = iov_from_user_compat_to_kern(kern_iov, (struct compat_iovec __user *)kern_msg->msg_iov, @@ -737,24 +745,18 @@ static unsigned char nas[21] = { asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; return __sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; return __sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } @@ -777,9 +779,6 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, int datagrams; struct timespec ktspec; - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; - if (timeout == NULL) return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, NULL); diff --git a/net/core/dev.c b/net/core/dev.c index 62f13f3..47a95f1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -940,7 +940,7 @@ bool dev_valid_name(const char *name) return false; while (*name) { - if (*name == '/' || isspace(*name)) + if (*name == '/' || *name == ':' || isspace(*name)) return false; name++; } @@ -1709,6 +1709,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) skb_scrub_packet(skb, true); skb->protocol = eth_type_trans(skb, dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); return netif_rx_internal(skb); } @@ -2529,11 +2530,14 @@ netdev_features_t netif_skb_dev_features(struct sk_buff *skb, if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; - if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { - struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; - protocol = veh->h_vlan_encapsulated_proto; - } else if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, dev, features); + if (!vlan_tx_tag_present(skb)) { + if (unlikely(protocol == htons(ETH_P_8021Q) || + protocol == htons(ETH_P_8021AD))) { + struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; + protocol = veh->h_vlan_encapsulated_proto; + } else { + return harmonize_features(skb, dev, features); + } } features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | @@ -2771,7 +2775,9 @@ static void skb_update_prio(struct sk_buff *skb) #define skb_update_prio(skb) #endif -static DEFINE_PER_CPU(int, xmit_recursion); +DEFINE_PER_CPU(int, xmit_recursion); +EXPORT_SYMBOL(xmit_recursion); + #define RECURSION_LIMIT 10 /** @@ -3554,7 +3560,7 @@ another_round: if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || skb->protocol == cpu_to_be16(ETH_P_8021AD)) { - skb = vlan_untag(skb); + skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto unlock; } @@ -4701,9 +4707,14 @@ static void netdev_adjacent_sysfs_del(struct net_device *dev, sysfs_remove_link(&(dev->dev.kobj), linkname); } -#define netdev_adjacent_is_neigh_list(dev, dev_list) \ - (dev_list == &dev->adj_list.upper || \ - dev_list == &dev->adj_list.lower) +static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) +{ + return (dev_list == &dev->adj_list.upper || + dev_list == &dev->adj_list.lower) && + net_eq(dev_net(dev), dev_net(adj_dev)); +} static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, @@ -4733,7 +4744,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, pr_debug("dev_hold for %s, because of link added from %s to %s\n", adj_dev->name, dev->name, adj_dev->name); - if (netdev_adjacent_is_neigh_list(dev, dev_list)) { + if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) { ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); if (ret) goto free_adj; @@ -4754,7 +4765,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, return 0; remove_symlinks: - if (netdev_adjacent_is_neigh_list(dev, dev_list)) + if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: kfree(adj); @@ -4787,7 +4798,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, if (adj->master) sysfs_remove_link(&(dev->dev.kobj), "master"); - if (netdev_adjacent_is_neigh_list(dev, dev_list)) + if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); list_del_rcu(&adj->list); @@ -4892,7 +4903,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper)) return -EBUSY; - if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper)) + if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper)) return -EEXIST; if (master && netdev_master_upper_dev_get(dev)) @@ -5057,11 +5068,65 @@ void netdev_upper_dev_unlink(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_dev_unlink); +void netdev_adjacent_add_links(struct net_device *dev) +{ + struct netdev_adjacent *iter; + + struct net *net = dev_net(dev); + + list_for_each_entry(iter, &dev->adj_list.upper, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_add(dev, iter->dev, + &dev->adj_list.upper); + } + + list_for_each_entry(iter, &dev->adj_list.lower, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_add(dev, iter->dev, + &dev->adj_list.lower); + } +} + +void netdev_adjacent_del_links(struct net_device *dev) +{ + struct netdev_adjacent *iter; + + struct net *net = dev_net(dev); + + list_for_each_entry(iter, &dev->adj_list.upper, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_del(iter->dev, dev->name, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_del(dev, iter->dev->name, + &dev->adj_list.upper); + } + + list_for_each_entry(iter, &dev->adj_list.lower, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_del(iter->dev, dev->name, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_del(dev, iter->dev->name, + &dev->adj_list.lower); + } +} + void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) { struct netdev_adjacent *iter; + struct net *net = dev_net(dev); + list_for_each_entry(iter, &dev->adj_list.upper, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(iter->dev, dev, @@ -5069,6 +5134,8 @@ void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) } list_for_each_entry(iter, &dev->adj_list.lower, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(iter->dev, dev, @@ -6675,6 +6742,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Send a netdev-removed uevent to the old namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); + netdev_adjacent_del_links(dev); /* Actually switch the network namespace */ dev_net_set(dev, net); @@ -6689,6 +6757,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Send a netdev-add uevent to the new namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_ADD); + netdev_adjacent_add_links(dev); /* Fixup kobjects */ err = device_rename(&dev->dev, dev->name); @@ -6745,10 +6814,20 @@ static int dev_cpu_callback(struct notifier_block *nfb, oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } - /* Append NAPI poll list from offline CPU. */ - if (!list_empty(&oldsd->poll_list)) { - list_splice_init(&oldsd->poll_list, &sd->poll_list); - raise_softirq_irqoff(NET_RX_SOFTIRQ); + /* Append NAPI poll list from offline CPU, with one exception : + * process_backlog() must be called by cpu owning percpu backlog. + * We properly handle process_queue & input_pkt_queue later. + */ + while (!list_empty(&oldsd->poll_list)) { + struct napi_struct *napi = list_first_entry(&oldsd->poll_list, + struct napi_struct, + poll_list); + + list_del_init(&napi->poll_list); + if (napi->poll == process_backlog) + napi->state = 0; + else + ____napi_schedule(sd, napi); } raise_softirq_irqoff(NET_TX_SOFTIRQ); @@ -6759,7 +6838,7 @@ static int dev_cpu_callback(struct notifier_block *nfb, netif_rx_internal(skb); input_queue_head_incr(oldsd); } - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { + while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx_internal(skb); input_queue_head_incr(oldsd); } diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 9d3d9e7..372ac66 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -32,6 +32,9 @@ gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size) return 0; nla_put_failure: + kfree(d->xstats); + d->xstats = NULL; + d->xstats_len = 0; spin_unlock_bh(d->lock); return -1; } @@ -217,7 +220,9 @@ int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) { if (d->compat_xstats) { - d->xstats = st; + d->xstats = kmemdup(st, len, GFP_ATOMIC); + if (!d->xstats) + goto err_out; d->xstats_len = len; } @@ -225,6 +230,11 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) return gnet_stats_copy(d, TCA_STATS_APP, st, len); return 0; + +err_out: + d->xstats_len = 0; + spin_unlock_bh(d->lock); + return -1; } EXPORT_SYMBOL(gnet_stats_copy_app); @@ -257,6 +267,9 @@ gnet_stats_finish_copy(struct gnet_dump *d) return -1; } + kfree(d->xstats); + d->xstats = NULL; + d->xstats_len = 0; spin_unlock_bh(d->lock); return 0; } diff --git a/net/core/iovec.c b/net/core/iovec.c index b618694..26dc006 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -39,7 +39,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a { int size, ct, err; - if (m->msg_namelen) { + if (m->msg_name && m->msg_namelen) { if (mode == VERIFY_READ) { void __user *namep; namep = (void __user __force *) m->msg_name; @@ -48,10 +48,10 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a if (err < 0) return err; } - if (m->msg_name) - m->msg_name = address; + m->msg_name = address; } else { m->msg_name = NULL; + m->msg_namelen = 0; } size = m->msg_iovlen * sizeof(struct iovec); @@ -107,6 +107,10 @@ EXPORT_SYMBOL(memcpy_toiovecend); int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, int offset, int len) { + /* No data? Done! */ + if (len == 0) + return 0; + /* Skip over the finished iovecs */ while (offset >= iov->iov_len) { offset -= iov->iov_len; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 7d95f69..0f062c6 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -976,6 +976,8 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) rc = 0; if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE)) goto out_unlock_bh; + if (neigh->dead) + goto out_dead; if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) { if (NEIGH_VAR(neigh->parms, MCAST_PROBES) + @@ -1032,6 +1034,13 @@ out_unlock_bh: write_unlock(&neigh->lock); local_bh_enable(); return rc; + +out_dead: + if (neigh->nud_state & NUD_STALE) + goto out_unlock_bh; + write_unlock_bh(&neigh->lock); + kfree_skb(skb); + return 1; } EXPORT_SYMBOL(__neigh_event_send); @@ -1095,6 +1104,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, if (!(flags & NEIGH_UPDATE_F_ADMIN) && (old & (NUD_NOARP | NUD_PERMANENT))) goto out; + if (neigh->dead) + goto out; if (!(new & NUD_VALID)) { neigh_del_timer(neigh); @@ -1244,6 +1255,8 @@ EXPORT_SYMBOL(neigh_update); */ void __neigh_set_probe_once(struct neighbour *neigh) { + if (neigh->dead) + return; neigh->updated = jiffies; if (!(neigh->nud_state & NUD_FAILED)) return; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index df9e6b1..723fa7d 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -788,7 +788,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) } if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { - skb = vlan_untag(skb); + skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index fdac61c..ca68d32 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2812,25 +2812,25 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, skb->dev = odev; skb->pkt_type = PACKET_HOST; + pktgen_finalize_skb(pkt_dev, skb, datalen); + if (!(pkt_dev->flags & F_UDPCSUM)) { skb->ip_summed = CHECKSUM_NONE; } else if (odev->features & NETIF_F_V4_CSUM) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - udp4_hwcsum(skb, udph->source, udph->dest); + udp4_hwcsum(skb, iph->saddr, iph->daddr); } else { - __wsum csum = udp_csum(skb); + __wsum csum = skb_checksum(skb, skb_transport_offset(skb), datalen + 8, 0); /* add protocol-dependent pseudo-header */ - udph->check = csum_tcpudp_magic(udph->source, udph->dest, + udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, datalen + 8, IPPROTO_UDP, csum); if (udph->check == 0) udph->check = CSUM_MANGLED_0; } - pktgen_finalize_skb(pkt_dev, skb, datalen); - #ifdef CONFIG_XFRM if (!process_ipsec(pkt_dev, skb, protocol)) return NULL; @@ -2946,6 +2946,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb->dev = odev; skb->pkt_type = PACKET_HOST; + pktgen_finalize_skb(pkt_dev, skb, datalen); + if (!(pkt_dev->flags & F_UDPCSUM)) { skb->ip_summed = CHECKSUM_NONE; } else if (odev->features & NETIF_F_V6_CSUM) { @@ -2954,7 +2956,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb->csum_offset = offsetof(struct udphdr, check); udph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, 0); } else { - __wsum csum = udp_csum(skb); + __wsum csum = skb_checksum(skb, skb_transport_offset(skb), udplen, 0); /* add protocol-dependent pseudo-header */ udph->check = csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, csum); @@ -2963,8 +2965,6 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, udph->check = CSUM_MANGLED_0; } - pktgen_finalize_skb(pkt_dev, skb, datalen); - return skb; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f19d2f2..c1bfd5a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -799,7 +799,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, (nla_total_size(sizeof(struct ifla_vf_mac)) + nla_total_size(sizeof(struct ifla_vf_vlan)) + nla_total_size(sizeof(struct ifla_vf_tx_rate)) + - nla_total_size(sizeof(struct ifla_vf_spoofchk))); + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + + nla_total_size(sizeof(struct ifla_vf_link_state))); return size; } else return 0; @@ -1196,14 +1197,10 @@ static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = { }; static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { - [IFLA_VF_MAC] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_mac) }, - [IFLA_VF_VLAN] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_vlan) }, - [IFLA_VF_TX_RATE] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_tx_rate) }, - [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_spoofchk) }, + [IFLA_VF_MAC] = { .len = sizeof(struct ifla_vf_mac) }, + [IFLA_VF_VLAN] = { .len = sizeof(struct ifla_vf_vlan) }, + [IFLA_VF_TX_RATE] = { .len = sizeof(struct ifla_vf_tx_rate) }, + [IFLA_VF_SPOOFCHK] = { .len = sizeof(struct ifla_vf_spoofchk) }, }; static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { @@ -1440,6 +1437,7 @@ static int do_setlink(const struct sk_buff *skb, goto errout; } if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); err = -EPERM; goto errout; } @@ -2020,8 +2018,16 @@ replay: } } err = rtnl_configure_link(dev, ifm); - if (err < 0) - unregister_netdevice(dev); + if (err < 0) { + if (ops->newlink) { + LIST_HEAD(list_kill); + + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + } else { + unregister_netdevice(dev); + } + } out: put_net(dest_net); return err; @@ -2635,12 +2641,16 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags) goto errout; } + if (!skb->len) + goto errout; + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return 0; errout: WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - rtnl_set_sk_err(net, RTNLGRP_LINK, err); + if (err) + rtnl_set_sk_err(net, RTNLGRP_LINK, err); return err; } diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 897da56..ba71212 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -85,31 +85,6 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET -__u32 secure_ip_id(__be32 daddr) -{ - u32 hash[MD5_DIGEST_WORDS]; - - net_secret_init(); - hash[0] = (__force __u32) daddr; - hash[1] = net_secret[13]; - hash[2] = net_secret[14]; - hash[3] = net_secret[15]; - - md5_transform(hash, net_secret); - - return hash[0]; -} - -__u32 secure_ipv6_id(const __be32 daddr[4]) -{ - __u32 hash[4]; - - net_secret_init(); - memcpy(hash, daddr, 16); - md5_transform(hash, net_secret); - - return hash[0]; -} __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7f2e1fc..8207f8d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -62,6 +62,7 @@ #include #include #include +#include #include #include @@ -277,13 +278,14 @@ nodata: EXPORT_SYMBOL(__alloc_skb); /** - * build_skb - build a network buffer + * __build_skb - build a network buffer * @data: data buffer provided by caller - * @frag_size: size of fragment, or 0 if head was kmalloced + * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if - * @frag_size is 0, otherwise data should come from the page allocator. + * @frag_size is 0, otherwise data should come from the page allocator + * or vmalloc() * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : @@ -294,7 +296,7 @@ EXPORT_SYMBOL(__alloc_skb); * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ -struct sk_buff *build_skb(void *data, unsigned int frag_size) +struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; struct sk_buff *skb; @@ -308,7 +310,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) memset(skb, 0, offsetof(struct sk_buff, tail)); skb->truesize = SKB_TRUESIZE(size); - skb->head_frag = frag_size != 0; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -325,6 +326,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) return skb; } + +/* build_skb() is wrapper over __build_skb(), that specifically + * takes care of skb->head and skb->pfmemalloc + * This means that if @frag_size is not zero, then @data must be backed + * by a page fragment, not kmalloc() or vmalloc() + */ +struct sk_buff *build_skb(void *data, unsigned int frag_size) +{ + struct sk_buff *skb = __build_skb(data, frag_size); + + if (skb && frag_size) { + skb->head_frag = 1; + if (virt_to_head_page(data)->pfmemalloc) + skb->pfmemalloc = 1; + } + return skb; +} EXPORT_SYMBOL(build_skb); struct netdev_alloc_cache { @@ -350,8 +368,11 @@ refill: for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) { gfp_t gfp = gfp_mask; - if (order) - gfp |= __GFP_COMP | __GFP_NOWARN; + if (order) { + gfp |= __GFP_COMP | __GFP_NOWARN | + __GFP_NOMEMALLOC; + gfp &= ~__GFP_WAIT; + } nc->frag.page = alloc_pages(gfp, order); if (likely(nc->frag.page)) break; @@ -2968,9 +2989,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, tail = nskb; __copy_skb_header(nskb, head_skb); - nskb->mac_len = head_skb->mac_len; skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); + skb_reset_mac_len(nskb); skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, nskb->data - tnl_hlen, @@ -3139,6 +3160,9 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; } + /* switch back to head shinfo */ + pinfo = skb_shinfo(p); + if (pinfo->frag_list) goto merge; if (skb_gro_len(p) != pinfo->gso_size) @@ -3933,6 +3957,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->local_df = 0; skb_dst_drop(skb); skb->mark = 0; + skb_init_secmark(skb); secpath_reset(skb); nf_reset(skb); nf_reset_trace(skb); @@ -3963,3 +3988,55 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) return shinfo->gso_size; } EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); + +static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) +{ + if (skb_cow(skb, skb_headroom(skb)) < 0) { + kfree_skb(skb); + return NULL; + } + + memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); + skb->mac_header += VLAN_HLEN; + return skb; +} + +struct sk_buff *skb_vlan_untag(struct sk_buff *skb) +{ + struct vlan_hdr *vhdr; + u16 vlan_tci; + + if (unlikely(vlan_tx_tag_present(skb))) { + /* vlan_tci is already set-up so leave this for another time */ + return skb; + } + + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + goto err_free; + + if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) + goto err_free; + + vhdr = (struct vlan_hdr *)skb->data; + vlan_tci = ntohs(vhdr->h_vlan_TCI); + __vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci); + + skb_pull_rcsum(skb, VLAN_HLEN); + vlan_set_encap_proto(skb, vhdr); + + skb = skb_reorder_vlan_header(skb); + if (unlikely(!skb)) + goto err_free; + + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + skb_reset_mac_len(skb); + + return skb; + +err_free: + kfree_skb(skb); + return NULL; +} +EXPORT_SYMBOL(skb_vlan_untag); diff --git a/net/core/sock.c b/net/core/sock.c index c806956..8ebfa52 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -659,6 +659,25 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) sock_reset_flag(sk, bit); } +bool sk_mc_loop(struct sock *sk) +{ + if (dev_recursion_level()) + return false; + if (!sk) + return true; + switch (sk->sk_family) { + case AF_INET: + return inet_sk(sk)->mc_loop; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + return inet6_sk(sk)->mc_loop; +#endif + } + WARN_ON(1); + return true; +} +EXPORT_SYMBOL(sk_mc_loop); + /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. @@ -1895,8 +1914,10 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio) do { gfp_t gfp = prio; - if (order) + if (order) { gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; + gfp &= ~__GFP_WAIT; + } pfrag->page = alloc_pages(gfp, order); if (likely(pfrag->page)) { pfrag->offset = 0; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index cf9cd13..e731c96 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -25,6 +25,8 @@ static int zero = 0; static int one = 1; static int ushort_max = USHRT_MAX; +static int min_sndbuf = SOCK_MIN_SNDBUF; +static int min_rcvbuf = SOCK_MIN_RCVBUF; #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(struct ctl_table *table, int write, @@ -223,7 +225,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "rmem_max", @@ -231,7 +233,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "wmem_default", @@ -239,7 +241,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "rmem_default", @@ -247,7 +249,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "dev_weight", diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 07bd8ed..951fe55 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -228,6 +228,8 @@ int inet_listen(struct socket *sock, int backlog) err = 0; if (err) goto out; + + tcp_fastopen_init_key_once(true); } err = inet_csk_listen_start(sk, backlog); if (err) diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index f2e1573..8f7bd56 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -62,6 +62,10 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res) else res->tclassid = 0; #endif + + if (err == -ESRCH) + err = -ENETUNREACH; + return err; } EXPORT_SYMBOL_GPL(__fib_lookup); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 9d43468..017fa5e 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -535,7 +535,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) return 1; attrlen = rtnh_attrlen(rtnh); - if (attrlen < 0) { + if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 2d24f29..278836f 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -50,7 +50,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, greh = (struct gre_base_hdr *)skb_transport_header(skb); - ghl = skb_inner_network_header(skb) - skb_transport_header(skb); + ghl = skb_inner_mac_header(skb) - skb_transport_header(skb); if (unlikely(ghl < sizeof(*greh))) goto out; @@ -271,6 +271,9 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff) err = ptype->callbacks.gro_complete(skb, nhoff + grehlen); rcu_read_unlock(); + + skb_set_inner_mac_header(skb, nhoff + grehlen); + return err; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 9db3b87..0ffcd4d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -369,7 +369,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; @@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e34dccb..4eeba4e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -71,6 +71,20 @@ static inline void inet_diag_unlock_handler( mutex_unlock(&inet_diag_table_mutex); } +static size_t inet_sk_attr_size(void) +{ + return nla_total_size(sizeof(struct tcp_info)) + + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + + nla_total_size(1) /* INET_DIAG_TOS */ + + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(sizeof(struct inet_diag_meminfo)) + + nla_total_size(sizeof(struct inet_diag_msg)) + + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + + nla_total_size(TCP_CA_NAME_MAX) + + nla_total_size(sizeof(struct tcpvegas_info)) + + 64; +} + int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, struct inet_diag_req_v2 *req, struct user_namespace *user_ns, @@ -324,9 +338,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s if (err) goto out; - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + - sizeof(struct tcp_info) + 64, GFP_KERNEL); + rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL); if (!rep) { err = -ENOMEM; goto out; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 48f4244..bf2cb4a 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -26,20 +26,7 @@ * Theory of operations. * We keep one entry for each peer IP address. The nodes contains long-living * information about the peer which doesn't depend on routes. - * At this moment this information consists only of ID field for the next - * outgoing IP packet. This field is incremented with each packet as encoded - * in inet_getid() function (include/net/inetpeer.h). - * At the moment of writing this notes identifier of IP packets is generated - * to be unpredictable using this code only for packets subjected - * (actually or potentially) to defragmentation. I.e. DF packets less than - * PMTU in size when local fragmentation is disabled use a constant ID and do - * not use this code (see ip_select_ident() in include/net/ip.h). * - * Route cache entries hold references to our nodes. - * New cache entries get references via lookup by destination IP address in - * the avl tree. The reference is grabbed only when it's needed i.e. only - * when we try to output IP packet which needs an unpredictable ID (see - * __ip_select_ident() in net/ipv4/route.c). * Nodes are removed only when reference counter goes to 0. * When it's happened the node may be removed when a sufficient amount of * time has been passed since its last use. The less-recently-used entry can @@ -62,7 +49,6 @@ * refcnt: atomically against modifications on other CPU; * usually under some other lock to prevent node disappearing * daddr: unchangeable - * ip_id_count: atomic value (no lock needed) */ static struct kmem_cache *peer_cachep __read_mostly; @@ -497,10 +483,6 @@ relookup: p->daddr = *daddr; atomic_set(&p->refcnt, 1); atomic_set(&p->rid, 0); - atomic_set(&p->ip_id_count, - (daddr->family == AF_INET) ? - secure_ip_id(daddr->addr.a4) : - secure_ipv6_id(daddr->addr.a6)); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; /* 60*HZ is arbitrary, but chosen enough high so that the first diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 1c6bd43..57075c4 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -127,6 +127,9 @@ int ip_forward(struct sk_buff *skb) struct rtable *rt; /* Route we use */ struct ip_options *opt = &(IPCB(skb)->opt); + if (unlikely(skb->sk)) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -178,7 +181,8 @@ int ip_forward(struct sk_buff *skb) * We now generate an ICMP HOST REDIRECT giving the route * we calculated. */ - if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb)) + if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr && + !skb_sec_path(skb)) ip_rt_send_redirect(skb); skb->priority = rt_tos2priority(iph->tos); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index c10a3ce..9ff497d 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -679,27 +679,30 @@ EXPORT_SYMBOL(ip_defrag); struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) { struct iphdr iph; + int netoff; u32 len; if (skb->protocol != htons(ETH_P_IP)) return skb; - if (!skb_copy_bits(skb, 0, &iph, sizeof(iph))) + netoff = skb_network_offset(skb); + + if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0) return skb; if (iph.ihl < 5 || iph.version != 4) return skb; len = ntohs(iph.tot_len); - if (skb->len < len || len < (iph.ihl * 4)) + if (skb->len < netoff + len || len < (iph.ihl * 4)) return skb; if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { - if (!pskb_may_pull(skb, iph.ihl*4)) + if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) return skb; - if (pskb_trim_rcsum(skb, len)) + if (pskb_trim_rcsum(skb, netoff + len)) return skb; memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(skb, user)) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 94213c8..b40b90d 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -250,10 +250,6 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; - skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM)); - if (IS_ERR(skb)) - goto out; - if (dev->header_ops) { /* Need space for new headers */ if (skb_cow_head(skb, dev->needed_headroom - @@ -266,6 +262,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, * to gre header. */ skb_pull(skb, tunnel->hlen + sizeof(struct iphdr)); + skb_reset_mac_header(skb); } else { if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; @@ -273,6 +270,10 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, tnl_params = &tunnel->parms.iph; } + skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM)); + if (IS_ERR(skb)) + goto out; + __gre_xmit(skb, dev, tnl_params, skb->protocol); return NETDEV_TX_OK; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 73c6b63..05686c4 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - ip_select_ident(skb, &rt->dst, sk); + ip_select_ident(skb, sk); if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; @@ -386,8 +386,7 @@ packet_routed: ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } - ip_select_ident_more(skb, &rt->dst, sk, - (skb_shinfo(skb)->gso_segs ?: 1) - 1); + ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; @@ -844,7 +843,8 @@ static int __ip_append_data(struct sock *sk, cork->length += length; if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) { + (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && + (sk->sk_type == SOCK_DGRAM)) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, maxfraglen, flags); @@ -1338,7 +1338,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); - ip_select_ident(skb, &rt->dst, sk); + ip_select_ident(skb, sk); if (opt) { iph->ihl += opt->optlen>>2; @@ -1461,23 +1461,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset, /* * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. - * - * Use a fake percpu inet socket to avoid false sharing and contention. */ -static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = { - .sk = { - .__sk_common = { - .skc_refcnt = ATOMIC_INIT(1), - }, - .sk_wmem_alloc = ATOMIC_INIT(1), - .sk_allocation = GFP_ATOMIC, - .sk_flags = (1UL << SOCK_USE_WRITE_QUEUE), - }, - .pmtudisc = IP_PMTUDISC_WANT, - .uc_ttl = -1, -}; - -void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, +void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len) { @@ -1485,9 +1470,9 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, struct ipcm_cookie ipc; struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); + struct net *net = sock_net(sk); struct sk_buff *nskb; - struct sock *sk; - struct inet_sock *inet; + int err; if (ip_options_echo(&replyopts.opt.opt, skb)) return; @@ -1516,18 +1501,19 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, if (IS_ERR(rt)) return; - inet = &get_cpu_var(unicast_sock); + inet_sk(sk)->tos = arg->tos; - inet->tos = arg->tos; - sk = &inet->sk; sk->sk_priority = skb->priority; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; - sock_net_set(sk, net); - __skb_queue_head_init(&sk->sk_write_queue); sk->sk_sndbuf = sysctl_wmem_default; - ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, - &ipc, &rt, MSG_DONTWAIT); + err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, + len, 0, &ipc, &rt, MSG_DONTWAIT); + if (unlikely(err)) { + ip_flush_pending_frames(sk); + goto out; + } + nskb = skb_peek(&sk->sk_write_queue); if (nskb) { if (arg->csumoffset >= 0) @@ -1535,13 +1521,10 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; - skb_orphan(nskb); skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb)); ip_push_pending_frames(sk, &fl4); } - - put_cpu_var(unicast_sock); - +out: ip_rt_put(rt); } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 580dd96..135045e 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -426,15 +426,11 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; - sin->sin_family = AF_UNSPEC; + memset(sin, 0, sizeof(*sin)); if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { - struct inet_sock *inet = inet_sk(sk); - sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; - sin->sin_port = 0; - memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); - if (inet->cmsg_flags) + if (inet_sk(sk)->cmsg_flags) ip_cmsg_recv(msg, skb); } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 62cd9e0..0a4af09 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -69,23 +69,25 @@ static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) } static void __tunnel_dst_set(struct ip_tunnel_dst *idst, - struct dst_entry *dst) + struct dst_entry *dst, __be32 saddr) { struct dst_entry *old_dst; dst_clone(dst); old_dst = xchg((__force struct dst_entry **)&idst->dst, dst); dst_release(old_dst); + idst->saddr = saddr; } -static void tunnel_dst_set(struct ip_tunnel *t, struct dst_entry *dst) +static void tunnel_dst_set(struct ip_tunnel *t, + struct dst_entry *dst, __be32 saddr) { - __tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst); + __tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst, saddr); } static void tunnel_dst_reset(struct ip_tunnel *t) { - tunnel_dst_set(t, NULL); + tunnel_dst_set(t, NULL, 0); } void ip_tunnel_dst_reset_all(struct ip_tunnel *t) @@ -93,20 +95,25 @@ void ip_tunnel_dst_reset_all(struct ip_tunnel *t) int i; for_each_possible_cpu(i) - __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL); + __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL, 0); } EXPORT_SYMBOL(ip_tunnel_dst_reset_all); -static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) +static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, + u32 cookie, __be32 *saddr) { + struct ip_tunnel_dst *idst; struct dst_entry *dst; rcu_read_lock(); - dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst); + idst = this_cpu_ptr(t->dst_cache); + dst = rcu_dereference(idst->dst); if (dst && !atomic_inc_not_zero(&dst->__refcnt)) dst = NULL; if (dst) { - if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + if (!dst->obsolete || dst->ops->check(dst, cookie)) { + *saddr = idst->saddr; + } else { tunnel_dst_reset(t); dst_release(dst); dst = NULL; @@ -362,7 +369,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) if (!IS_ERR(rt)) { tdev = rt->dst.dev; - tunnel_dst_set(tunnel, &rt->dst); + tunnel_dst_set(tunnel, &rt->dst, fl4.saddr); ip_rt_put(rt); } if (dev->type != ARPHRD_ETHER) @@ -606,7 +613,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link); - rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL; + rt = connected ? tunnel_rtable_get(tunnel, 0, &fl4.saddr) : NULL; if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); @@ -616,7 +623,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } if (connected) - tunnel_dst_set(tunnel, &rt->dst); + tunnel_dst_set(tunnel, &rt->dst, fl4.saddr); } if (rt->dst.dev == dev) { diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 8d69626..791a419 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -74,7 +74,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb, iph->daddr = dst; iph->saddr = src; iph->ttl = ttl; - __ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1); + __ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1); err = ip_local_out(skb); if (unlikely(net_xmit_eval(err))) @@ -91,11 +91,12 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) skb_pull_rcsum(skb, hdr_len); if (inner_proto == htons(ETH_P_TEB)) { - struct ethhdr *eh = (struct ethhdr *)skb->data; + struct ethhdr *eh; if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) return -ENOMEM; + eh = (struct ethhdr *)skb->data; if (likely(ntohs(eh->h_proto) >= ETH_P_802_3_MIN)) skb->protocol = eh->h_proto; else diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index e4a8f76..b0a9cb4 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -369,6 +369,7 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = { .validate = vti_tunnel_validate, .newlink = vti_newlink, .changelink = vti_changelink, + .dellink = ip_tunnel_dellink, .get_size = vti_get_size, .fill_info = vti_fill_info, }; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 2886357..1149fc2 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1663,7 +1663,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(skb, skb_dst(skb), NULL); + ip_select_ident(skb, NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index e21934b..1e2e9bf 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -158,6 +158,7 @@ void ping_unhash(struct sock *sk) if (sk_hashed(sk)) { write_lock_bh(&ping_table.lock); hlist_nulls_del(&sk->sk_nulls_node); + sk_nulls_node_init(&sk->sk_nulls_node); sock_put(sk); isk->inet_num = 0; isk->inet_sport = 0; @@ -217,6 +218,8 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) &ipv6_hdr(skb)->daddr)) continue; #endif + } else { + continue; } if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) @@ -257,6 +260,10 @@ int ping_init_sock(struct sock *sk) kgid_t low, high; int ret = 0; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + inet6_sk(sk)->ipv6only = 1; +#endif inet_get_ping_group_range_net(net, &low, &high); if (gid_lte(low, group) && gid_lte(group, high)) return 0; @@ -303,6 +310,11 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, if (addr_len < sizeof(*addr)) return -EINVAL; + if (addr->sin_family != AF_INET && + !(addr->sin_family == AF_UNSPEC && + addr->sin_addr.s_addr == htonl(INADDR_ANY))) + return -EAFNOSUPPORT; + pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); @@ -328,7 +340,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, return -EINVAL; if (addr->sin6_family != AF_INET6) - return -EINVAL; + return -EAFNOSUPPORT; pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n", sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port)); @@ -714,7 +726,7 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) - return -EINVAL; + return -EAFNOSUPPORT; daddr = usin->sin_addr.s_addr; /* no remote port */ } else { @@ -971,8 +983,11 @@ void ping_rcv(struct sk_buff *skb) sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); if (sk != NULL) { + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + pr_debug("rcv on socket %p\n", sk); - ping_queue_rcv_skb(sk, skb_get(skb)); + if (skb2) + ping_queue_rcv_skb(sk, skb2); sock_put(sk); return; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index c04518f..11c8d81 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -389,7 +389,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, iph->check = 0; iph->tot_len = htons(length); if (!iph->id) - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 031553f..625615c 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -89,6 +89,7 @@ #include #include #include +#include #include #include #include @@ -462,39 +463,45 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, return neigh_create(&arp_tbl, pkey, dev); } -/* - * Peer allocation may fail only in serious out-of-memory conditions. However - * we still can generate some output. - * Random ID selection looks a bit dangerous because we have no chances to - * select ID being unique in a reasonable period of time. - * But broken packet identifier may be better than no packet at all. +#define IP_IDENTS_SZ 2048u +struct ip_ident_bucket { + atomic_t id; + u32 stamp32; +}; + +static struct ip_ident_bucket *ip_idents __read_mostly; + +/* In order to protect privacy, we add a perturbation to identifiers + * if one generator is seldom used. This makes hard for an attacker + * to infer how many packets were sent between two points in time. */ -static void ip_select_fb_ident(struct iphdr *iph) +u32 ip_idents_reserve(u32 hash, int segs) { - static DEFINE_SPINLOCK(ip_fb_id_lock); - static u32 ip_fallback_id; - u32 salt; + struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ; + u32 old = ACCESS_ONCE(bucket->stamp32); + u32 now = (u32)jiffies; + u32 delta = 0; + + if (old != now && cmpxchg(&bucket->stamp32, old, now) == old) + delta = prandom_u32_max(now - old); - spin_lock_bh(&ip_fb_id_lock); - salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr); - iph->id = htons(salt & 0xFFFF); - ip_fallback_id = salt; - spin_unlock_bh(&ip_fb_id_lock); + return atomic_add_return(segs + delta, &bucket->id) - segs; } +EXPORT_SYMBOL(ip_idents_reserve); -void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) +void __ip_select_ident(struct iphdr *iph, int segs) { - struct net *net = dev_net(dst->dev); - struct inet_peer *peer; + static u32 ip_idents_hashrnd __read_mostly; + u32 hash, id; - peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1); - if (peer) { - iph->id = htons(inet_getid(peer, more)); - inet_putpeer(peer); - return; - } + net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd)); - ip_select_fb_ident(iph); + hash = jhash_3words((__force u32)iph->daddr, + (__force u32)iph->saddr, + iph->protocol, + ip_idents_hashrnd); + id = ip_idents_reserve(hash, segs); + iph->id = htons(id); } EXPORT_SYMBOL(__ip_select_ident); @@ -903,6 +910,10 @@ static int ip_error(struct sk_buff *skb) bool send; int code; + /* IP on this device is disabled. */ + if (!in_dev) + goto out; + net = dev_net(rt->dst.dev); if (!IN_DEV_FORWARD(in_dev)) { switch (rt->dst.error) { @@ -1547,11 +1558,10 @@ static int __mkroute_input(struct sk_buff *skb, do_cache = res->fi && !itag; if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && + skb->protocol == htons(ETH_P_IP) && (IN_DEV_SHARED_MEDIA(out_dev) || - inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) { - flags |= RTCF_DOREDIRECT; - do_cache = false; - } + inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) + IPCB(skb)->flags |= IPSKB_DOREDIRECT; if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is @@ -2261,9 +2271,9 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, return rt; if (flp4->flowi4_proto) - rt = (struct rtable *) xfrm_lookup(net, &rt->dst, - flowi4_to_flowi(flp4), - sk, 0); + rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst, + flowi4_to_flowi(flp4), + sk, 0); return rt; } @@ -2298,6 +2308,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; + if (IPCB(skb)->flags & IPSKB_DOREDIRECT) + r->rtm_flags |= RTCF_DOREDIRECT; if (nla_put_be32(skb, RTA_DST, dst)) goto nla_put_failure; @@ -2718,6 +2730,12 @@ int __init ip_rt_init(void) { int rc = 0; + ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL); + if (!ip_idents) + panic("IP: failed to allocate ip_idents\n"); + + prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents)); + #ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b48fba0..dc45221 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1175,13 +1175,6 @@ new_segment: goto wait_for_memory; /* - * All packets are restored as if they have - * already been sent. - */ - if (tp->repair) - TCP_SKB_CB(skb)->when = tcp_time_stamp; - - /* * Check whether we can use HW checksum. */ if (sk->sk_route_caps & NETIF_F_ALL_CSUM) @@ -1190,6 +1183,13 @@ new_segment: skb_entail(sk, skb); copy = size_goal; max = size_goal; + + /* All packets are restored as if they have + * already been sent. skb_mstamp isn't set to + * avoid wrong rtt estimation. + */ + if (tp->repair) + TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED; } /* Try to append data to the end of skb. */ @@ -2684,10 +2684,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_FASTOPEN: if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | - TCPF_LISTEN))) + TCPF_LISTEN))) { + tcp_fastopen_init_key_once(true); + err = fastopen_init_queue(sk, val); - else + } else { err = -EINVAL; + } break; case TCP_TIMESTAMP: if (!tp->repair) @@ -2954,61 +2957,42 @@ EXPORT_SYMBOL(compat_tcp_getsockopt); #endif #ifdef CONFIG_TCP_MD5SIG -static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool __read_mostly; +static DEFINE_PER_CPU(struct tcp_md5sig_pool, tcp_md5sig_pool); static DEFINE_MUTEX(tcp_md5sig_mutex); - -static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool) -{ - int cpu; - - for_each_possible_cpu(cpu) { - struct tcp_md5sig_pool *p = per_cpu_ptr(pool, cpu); - - if (p->md5_desc.tfm) - crypto_free_hash(p->md5_desc.tfm); - } - free_percpu(pool); -} +static bool tcp_md5sig_pool_populated = false; static void __tcp_alloc_md5sig_pool(void) { int cpu; - struct tcp_md5sig_pool __percpu *pool; - - pool = alloc_percpu(struct tcp_md5sig_pool); - if (!pool) - return; for_each_possible_cpu(cpu) { - struct crypto_hash *hash; - - hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR_OR_NULL(hash)) - goto out_free; + if (!per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm) { + struct crypto_hash *hash; - per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash; + hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR_OR_NULL(hash)) + return; + per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash; + } } - /* before setting tcp_md5sig_pool, we must commit all writes - * to memory. See ACCESS_ONCE() in tcp_get_md5sig_pool() + /* before setting tcp_md5sig_pool_populated, we must commit all writes + * to memory. See smp_rmb() in tcp_get_md5sig_pool() */ smp_wmb(); - tcp_md5sig_pool = pool; - return; -out_free: - __tcp_free_md5sig_pool(pool); + tcp_md5sig_pool_populated = true; } bool tcp_alloc_md5sig_pool(void) { - if (unlikely(!tcp_md5sig_pool)) { + if (unlikely(!tcp_md5sig_pool_populated)) { mutex_lock(&tcp_md5sig_mutex); - if (!tcp_md5sig_pool) + if (!tcp_md5sig_pool_populated) __tcp_alloc_md5sig_pool(); mutex_unlock(&tcp_md5sig_mutex); } - return tcp_md5sig_pool != NULL; + return tcp_md5sig_pool_populated; } EXPORT_SYMBOL(tcp_alloc_md5sig_pool); @@ -3022,13 +3006,13 @@ EXPORT_SYMBOL(tcp_alloc_md5sig_pool); */ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) { - struct tcp_md5sig_pool __percpu *p; - local_bh_disable(); - p = ACCESS_ONCE(tcp_md5sig_pool); - if (p) - return __this_cpu_ptr(p); + if (tcp_md5sig_pool_populated) { + /* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */ + smp_rmb(); + return this_cpu_ptr(&tcp_md5sig_pool); + } local_bh_enable(); return NULL; } diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index f195d93..ee6518d 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -84,8 +84,6 @@ void tcp_fastopen_cookie_gen(__be32 src, __be32 dst, __be32 path[4] = { src, dst, 0, 0 }; struct tcp_fastopen_context *ctx; - tcp_fastopen_init_key_once(true); - rcu_read_lock(); ctx = rcu_dereference(tcp_fastopen_ctx); if (ctx) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3898694..9fbd69e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2678,7 +2678,6 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) */ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) { - struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); @@ -2704,12 +2703,9 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) if (recovered) { /* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */ - icsk->icsk_retransmits = 0; tcp_try_undo_recovery(sk); return; } - if (flag & FLAG_DATA_ACKED) - icsk->icsk_retransmits = 0; if (tcp_is_reno(tp)) { /* A Reno DUPACK means new data in F-RTO step 2.b above are * delivered. Lower inflight to clock out (re)tranmissions. @@ -3068,10 +3064,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (seq_rtt < 0) { seq_rtt = ca_seq_rtt; } - if (!(sacked & TCPCB_SACKED_ACKED)) + if (!(sacked & TCPCB_SACKED_ACKED)) { reord = min(pkts_acked, reord); - if (!after(scb->end_seq, tp->high_seq)) - flag |= FLAG_ORIG_SACK_ACKED; + if (!after(scb->end_seq, tp->high_seq)) + flag |= FLAG_ORIG_SACK_ACKED; + } } if (sacked & TCPCB_SACKED_ACKED) @@ -3398,8 +3395,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); - if (after(ack, prior_snd_una)) + if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; + icsk->icsk_retransmits = 0; + } prior_fackets = tp->fackets_out; prior_in_flight = tcp_packets_in_flight(tp); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1e4eac7..e2f8bd0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -269,7 +269,7 @@ EXPORT_SYMBOL(tcp_v4_connect); * It can be called through tcp_release_cb() if socket was owned by user * at the time tcp_v4_err() was called to handle ICMP message. */ -static void tcp_v4_mtu_reduced(struct sock *sk) +void tcp_v4_mtu_reduced(struct sock *sk) { struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); @@ -300,6 +300,7 @@ static void tcp_v4_mtu_reduced(struct sock *sk) tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ } +EXPORT_SYMBOL(tcp_v4_mtu_reduced); static void do_redirect(struct sk_buff *skb, struct sock *sk) { @@ -690,7 +691,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) net = dev_net(skb_dst(skb)->dev); arg.tos = ip_hdr(skb)->tos; - ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -773,7 +775,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, if (oif) arg.bound_dev_if = oif; arg.tos = tos; - ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -1872,7 +1875,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst = ACCESS_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); @@ -2117,6 +2120,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = { .compat_setsockopt = compat_ip_setsockopt, .compat_getsockopt = compat_ip_getsockopt, #endif + .mtu_reduced = tcp_v4_mtu_reduced, }; EXPORT_SYMBOL(ipv4_specific); @@ -2736,7 +2740,6 @@ struct proto tcp_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, - .mtu_reduced = tcp_v4_mtu_reduced, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, @@ -2768,14 +2771,39 @@ struct proto tcp_prot = { }; EXPORT_SYMBOL(tcp_prot); +static void __net_exit tcp_sk_exit(struct net *net) +{ + int cpu; + + for_each_possible_cpu(cpu) + inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); + free_percpu(net->ipv4.tcp_sk); +} + static int __net_init tcp_sk_init(struct net *net) { + int res, cpu; + + net->ipv4.tcp_sk = alloc_percpu(struct sock *); + if (!net->ipv4.tcp_sk) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct sock *sk; + + res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, + IPPROTO_TCP, net); + if (res) + goto fail; + *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; + } net->ipv4.sysctl_tcp_ecn = 2; return 0; -} -static void __net_exit tcp_sk_exit(struct net *net) -{ +fail: + tcp_sk_exit(net); + + return res; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7a436c5..9128d0a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -297,7 +297,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_v6_daddr = sk->sk_v6_daddr; tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr; tw->tw_tclass = np->tclass; - tw->tw_flowlabel = np->flow_label >> 12; + tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK); tw->tw_ipv6only = np->ipv6only; } #endif diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b3d1add..a68cd71 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -787,7 +787,7 @@ void tcp_release_cb(struct sock *sk) __sock_put(sk); } if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) { - sk->sk_prot->mtu_reduced(sk); + inet_csk(sk)->icsk_af_ops->mtu_reduced(sk); __sock_put(sk); } } @@ -1876,8 +1876,11 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); - if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) + if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { + /* "when" is used as a start point for the retransmit timer */ + TCP_SKB_CB(skb)->when = tcp_time_stamp; goto repair; /* Skip network transmission */ + } cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) { @@ -1891,7 +1894,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) break; - if (tso_segs == 1) { + if (tso_segs == 1 || !sk->sk_gso_max_segs) { if (unlikely(!tcp_nagle_test(tp, skb, mss_now, (tcp_skb_is_last(sk, skb) ? nonagle : TCP_NAGLE_PUSH)))) @@ -1928,7 +1931,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } limit = mss_now; - if (tso_segs > 1 && !tcp_urg_mode(tp)) + if (tso_segs > 1 && sk->sk_gso_max_segs && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, min_t(unsigned int, cwnd_quota, @@ -2066,9 +2069,7 @@ void tcp_send_loss_probe(struct sock *sk) if (WARN_ON(!skb || !tcp_skb_pcount(skb))) goto rearm_timer; - /* Probe with zero data doesn't trigger fast recovery. */ - if (skb->len > 0) - err = __tcp_retransmit_skb(sk, skb); + err = __tcp_retransmit_skb(sk, skb); /* Record snd_nxt for loss detection. */ if (likely(!err)) @@ -2594,43 +2595,65 @@ begin_fwd: } } -/* Send a fin. The caller locks the socket for us. This cannot be - * allowed to fail queueing a FIN frame under any circumstances. +/* We allow to exceed memory limits for FIN packets to expedite + * connection tear down and (memory) recovery. + * Otherwise tcp_send_fin() could be tempted to either delay FIN + * or even be forced to close flow without any FIN. + */ +static void sk_forced_wmem_schedule(struct sock *sk, int size) +{ + int amt, status; + + if (size <= sk->sk_forward_alloc) + return; + amt = sk_mem_pages(size); + sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; + sk_memory_allocated_add(sk, amt, &status); +} + +/* Send a FIN. The caller locks the socket for us. + * We should try to send a FIN packet really hard, but eventually give up. */ void tcp_send_fin(struct sock *sk) { + struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb = tcp_write_queue_tail(sk); - int mss_now; - /* Optimization, tack on the FIN if we have a queue of - * unsent frames. But be careful about outgoing SACKS - * and IP options. + /* Optimization, tack on the FIN if we have one skb in write queue and + * this skb was not yet sent, or we are under memory pressure. + * Note: in the latter case, FIN packet will be sent after a timeout, + * as TCP stack thinks it has already been transmitted. */ - mss_now = tcp_current_mss(sk); - - if (tcp_send_head(sk) != NULL) { - TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN; - TCP_SKB_CB(skb)->end_seq++; + if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) { +coalesce: + TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; + TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; + if (!tcp_send_head(sk)) { + /* This means tskb was already sent. + * Pretend we included the FIN on previous transmit. + * We need to set tp->snd_nxt to the value it would have + * if FIN had been sent. This is because retransmit path + * does not change tp->snd_nxt. + */ + tp->snd_nxt++; + return; + } } else { - /* Socket is locked, keep trying until memory is available. */ - for (;;) { - skb = alloc_skb_fclone(MAX_TCP_HEADER, - sk->sk_allocation); - if (skb) - break; - yield(); + skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + if (unlikely(!skb)) { + if (tskb) + goto coalesce; + return; } - - /* Reserve space for headers and prepare control bits. */ skb_reserve(skb, MAX_TCP_HEADER); + sk_forced_wmem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } - __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF); + __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); } /* We get here when a process closes a file descriptor (either due to @@ -2799,6 +2822,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, } #endif + /* Do not fool tcpdump (if any), clean our debris */ + skb->tstamp.tv64 = 0; return skb; } EXPORT_SYMBOL(tcp_make_synack); @@ -2898,9 +2923,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; - int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen; - struct sk_buff *syn_data = NULL, *data; + int syn_loss = 0, space, err = 0; unsigned long last_syn_loss = 0; + struct sk_buff *syn_data; tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */ tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie, @@ -2931,42 +2956,39 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) /* limit to order-0 allocations */ space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); - syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space, - sk->sk_allocation); - if (syn_data == NULL) + syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation); + if (!syn_data) + goto fallback; + syn_data->ip_summed = CHECKSUM_PARTIAL; + memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); + skb_shinfo(syn_data)->gso_segs = 1; + if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space), + fo->data->msg_iov, 0, space))) { + kfree_skb(syn_data); goto fallback; + } - for (i = 0; i < iovlen && syn_data->len < space; ++i) { - struct iovec *iov = &fo->data->msg_iov[i]; - unsigned char __user *from = iov->iov_base; - int len = iov->iov_len; + /* No more data pending in inet_wait_for_connect() */ + if (space == fo->size) + fo->data = NULL; + fo->copied = space; - if (syn_data->len + len > space) - len = space - syn_data->len; - else if (i + 1 == iovlen) - /* No more data pending in inet_wait_for_connect() */ - fo->data = NULL; + tcp_connect_queue_skb(sk, syn_data); - if (skb_add_data(syn_data, from, len)) - goto fallback; - } + err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); - /* Queue a data-only packet after the regular SYN for retransmission */ - data = pskb_copy(syn_data, sk->sk_allocation); - if (data == NULL) - goto fallback; - TCP_SKB_CB(data)->seq++; - TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN; - TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH); - tcp_connect_queue_skb(sk, data); - fo->copied = data->len; - - if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { + /* Now full SYN+DATA was cloned and sent (or not), + * remove the SYN from the original skb (syn_data) + * we keep in write queue in case of a retransmit, as we + * also have the SYN packet (with no data) in the same queue. + */ + TCP_SKB_CB(syn_data)->seq++; + TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH; + if (!err) { tp->syn_data = (fo->copied > 0); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); goto done; } - syn_data = NULL; fallback: /* Send a regular SYN with Fast Open cookie request option */ @@ -2975,7 +2997,6 @@ fallback: err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation); if (err) tp->syn_fastopen = 0; - kfree_skb(syn_data); done: fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */ return err; @@ -2995,13 +3016,10 @@ int tcp_connect(struct sock *sk) return 0; } - buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation); - if (unlikely(buff == NULL)) + buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); + if (unlikely(!buff)) return -ENOBUFS; - /* Reserve space for headers. */ - skb_reserve(buff, MAX_TCP_HEADER); - tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp; tcp_connect_queue_skb(sk, buff); diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 06cae62..6b1a5fd 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -219,7 +219,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked, * This is: * (actual rate in segments) * baseRTT */ - target_cwnd = tp->snd_cwnd * vegas->baseRTT / rtt; + target_cwnd = (u64)tp->snd_cwnd * vegas->baseRTT; + do_div(target_cwnd, rtt); /* Calculate the difference between the window we had, * and the window we would like to have. This quantity diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 326475a..603ad49 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -145,7 +145,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked, rtt = veno->minrtt; - target_cwnd = (tp->snd_cwnd * veno->basertt); + target_cwnd = (u64)tp->snd_cwnd * veno->basertt; target_cwnd <<= V_PARAM_SHIFT; do_div(target_cwnd, rtt); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index b25e852..21a3a9e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -90,6 +90,7 @@ #include #include #include +#include #include #include #include @@ -1317,10 +1318,8 @@ csum_copy_err: } unlock_sock_fast(sk, slow); - if (noblock) - return -EAGAIN; - - /* starting over for a new packet */ + /* starting over for a new packet, but check if we need to yield */ + cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } @@ -1924,6 +1923,7 @@ void udp_v4_early_demux(struct sk_buff *skb) struct sock *sk; struct dst_entry *dst; int dif = skb->dev->ifindex; + int ours; /* validate the packet */ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) @@ -1933,14 +1933,24 @@ void udp_v4_early_demux(struct sk_buff *skb) uh = udp_hdr(skb); if (skb->pkt_type == PACKET_BROADCAST || - skb->pkt_type == PACKET_MULTICAST) + skb->pkt_type == PACKET_MULTICAST) { + struct in_device *in_dev = __in_dev_get_rcu(skb->dev); + + if (!in_dev) + return; + + ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, + iph->protocol); + if (!ours) + return; sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif); - else if (skb->pkt_type == PACKET_HOST) + } else if (skb->pkt_type == PACKET_HOST) { sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif); - else + } else { return; + } if (!sk) return; diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 7927db0..4a000f1 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -99,11 +99,13 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin s_slot = cb->args[0]; num = s_num = cb->args[1]; - for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) { + for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) { struct sock *sk; struct hlist_nulls_node *node; struct udp_hslot *hslot = &table->hash[slot]; + num = 0; + if (hlist_nulls_empty(&hslot->head)) continue; diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 31b1815..1f564a1 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -117,12 +117,12 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); - ip_select_ident(skb, dst->child, NULL); top_iph->ttl = ip4_dst_hoplimit(dst->child); top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; + ip_select_ident(skb, NULL); return 0; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6c7fa08..3f0ec06 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1684,14 +1684,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) addrconf_mod_dad_work(ifp, 0); } -/* Join to solicited addr multicast group. */ - +/* Join to solicited addr multicast group. + * caller must hold RTNL */ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) { struct in6_addr maddr; - ASSERT_RTNL(); - if (dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1699,12 +1697,11 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) ipv6_dev_mc_inc(dev, &maddr); } +/* caller must hold RTNL */ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) { struct in6_addr maddr; - ASSERT_RTNL(); - if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1712,12 +1709,11 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) __ipv6_dev_mc_dec(idev, &maddr); } +/* caller must hold RTNL */ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; - ASSERT_RTNL(); - if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); @@ -1726,12 +1722,11 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) ipv6_dev_ac_inc(ifp->idev->dev, &addr); } +/* caller must hold RTNL */ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; - ASSERT_RTNL(); - if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 2101832..ff2de7d 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -77,6 +77,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) pac->acl_next = NULL; pac->acl_addr = *addr; + rtnl_lock(); rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -137,6 +138,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) error: rcu_read_unlock(); + rtnl_unlock(); if (pac) sock_kfree_s(sk, pac, sizeof(*pac)); return err; @@ -171,11 +173,13 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) spin_unlock_bh(&ipv6_sk_ac_lock); + rtnl_lock(); rcu_read_lock(); dev = dev_get_by_index_rcu(net, pac->acl_ifindex); if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, pac, sizeof(*pac)); return 0; @@ -198,6 +202,7 @@ void ipv6_sock_ac_close(struct sock *sk) spin_unlock_bh(&ipv6_sk_ac_lock); prev_index = 0; + rtnl_lock(); rcu_read_lock(); while (pac) { struct ipv6_ac_socklist *next = pac->acl_next; @@ -212,6 +217,7 @@ void ipv6_sock_ac_close(struct sock *sk) pac = next; } rcu_read_unlock(); + rtnl_unlock(); } static void aca_put(struct ifacaddr6 *ac) @@ -233,6 +239,8 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr) struct rt6_info *rt; int err; + ASSERT_RTNL(); + idev = in6_dev_get(dev); if (idev == NULL) @@ -302,6 +310,8 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca, *prev_aca; + ASSERT_RTNL(); + write_lock_bh(&idev->lock); prev_aca = NULL; for (aca = idev->ac_list; aca; aca = aca->aca_next) { diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index c3bf2d2..841cfa2 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -382,11 +382,10 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; - sin->sin6_family = AF_UNSPEC; + memset(sin, 0, sizeof(*sin)); + if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { sin->sin6_family = AF_INET6; - sin->sin6_flowinfo = 0; - sin->sin6_port = 0; if (np->rxopt.all) ip6_datagram_recv_common_ctl(sk, msg, skb); if (skb->protocol == htons(ETH_P_IPV6)) { @@ -397,12 +396,9 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); } else { - struct inet_sock *inet = inet_sk(sk); - ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin->sin6_addr); - sin->sin6_scope_id = 0; - if (inet->cmsg_flags) + if (inet_sk(sk)->cmsg_flags) ip_cmsg_recv(msg, skb); } } diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b4d5e1d..27ca796 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -104,6 +104,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, goto again; flp6->saddr = saddr; } + err = rt->dst.error; goto out; } again: diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1e55f5e..7daaeaf 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -638,6 +638,29 @@ static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt) RTF_GATEWAY; } +static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, + struct net *net) +{ + if (atomic_read(&rt->rt6i_ref) != 1) { + /* This route is used as dummy address holder in some split + * nodes. It is not leaked, but it still holds other resources, + * which must be released in time. So, scan ascendant nodes + * and replace dummy references to this route with references + * to still alive ones. + */ + while (fn) { + if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { + fn->leaf = fib6_find_prefix(net, fn); + atomic_inc(&fn->leaf->rt6i_ref); + rt6_release(rt); + } + fn = fn->parent; + } + /* No more references are possible at this point. */ + BUG_ON(atomic_read(&rt->rt6i_ref) != 1); + } +} + /* * Insert routing information in a node. */ @@ -775,11 +798,12 @@ add: rt->dst.rt6_next = iter->dst.rt6_next; atomic_inc(&rt->rt6i_ref); inet6_rt_notify(RTM_NEWROUTE, rt, info); - rt6_release(iter); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } + fib6_purge_rt(iter, fn, info->nl_net); + rt6_release(iter); } return 0; @@ -1284,24 +1308,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, fn = fib6_repair_tree(net, fn); } - if (atomic_read(&rt->rt6i_ref) != 1) { - /* This route is used as dummy address holder in some split - * nodes. It is not leaked, but it still holds other resources, - * which must be released in time. So, scan ascendant nodes - * and replace dummy references to this route with references - * to still alive ones. - */ - while (fn) { - if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { - fn->leaf = fib6_find_prefix(net, fn); - atomic_inc(&fn->leaf->rt6i_ref); - rt6_release(rt); - } - fn = fn->parent; - } - /* No more references are possible at this point. */ - BUG_ON(atomic_read(&rt->rt6i_ref) != 1); - } + fib6_purge_rt(rt, fn, net); inet6_rt_notify(RTM_DELROUTE, rt, info); rt6_release(rt); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 2465d18..4a230b1 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -508,11 +508,11 @@ static int ip6gre_rcv(struct sk_buff *skb) skb->protocol = gre_proto; /* WCCP version 1 and 2 protocol decoding. - * - Change protocol to IP + * - Change protocol to IPv6 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header */ if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) { - skb->protocol = htons(ETH_P_IP); + skb->protocol = htons(ETH_P_IPV6); if ((*(h + offset) & 0xF0) != 0x40) offset += 4; } @@ -787,7 +787,7 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) encap_limit = t->parms.encap_limit; memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_IPIP; + fl6.flowi6_proto = IPPROTO_GRE; dsfield = ipv4_get_dsfield(iph); @@ -837,7 +837,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) encap_limit = t->parms.encap_limit; memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_IPV6; + fl6.flowi6_proto = IPPROTO_GRE; dsfield = ipv6_get_dsfield(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) @@ -962,8 +962,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) else dev->flags &= ~IFF_POINTOPOINT; - dev->iflink = p->link; - /* Precalculate GRE options length */ if (t->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) { if (t->parms.o_flags&GRE_CSUM) @@ -1273,6 +1271,7 @@ static int ip6gre_tunnel_init(struct net_device *dev) u64_stats_init(&ip6gre_tunnel_stats->syncp); } + dev->iflink = tunnel->parms.link; return 0; } @@ -1474,6 +1473,8 @@ static int ip6gre_tap_init(struct net_device *dev) u64_stats_init(&ip6gre_tap_stats->syncp); } + dev->iflink = tunnel->parms.link; + return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a62b610..066d0b0 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -537,11 +537,26 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } +static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +{ + static u32 ip6_idents_hashrnd __read_mostly; + u32 hash, id; + + net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); + + hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd); + hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash); + + id = ip_idents_reserve(hash, 1); + fhdr->identification = htonl(id); +} + int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = (struct rt6_info*)skb_dst(skb); - struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; + struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? + inet6_sk(skb->sk) : NULL; struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; unsigned int mtu, hlen, left, len; @@ -994,7 +1009,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); @@ -1026,7 +1041,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); @@ -1280,7 +1295,8 @@ emsgsize: if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO)) { + (rt->dst.dev->features & NETIF_F_UFO) && + (sk->sk_type == SOCK_DGRAM)) { err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, mtu, flags, rt); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 9120339..657639d 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -272,9 +272,6 @@ static int ip6_tnl_create2(struct net_device *dev) int err; t = netdev_priv(dev); - err = ip6_tnl_dev_init(dev); - if (err < 0) - goto out; err = register_netdevice(dev); if (err < 0) @@ -1456,6 +1453,7 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) static const struct net_device_ops ip6_tnl_netdev_ops = { + .ndo_init = ip6_tnl_dev_init, .ndo_uninit = ip6_tnl_dev_uninit, .ndo_start_xmit = ip6_tnl_xmit, .ndo_do_ioctl = ip6_tnl_ioctl, @@ -1547,16 +1545,10 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - int err = ip6_tnl_dev_init_gen(dev); - - if (err) - return err; t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - ip6_tnl_link_config(t); - rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 2d19272..28456c9 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -172,10 +172,6 @@ static int vti6_tnl_create2(struct net_device *dev) struct vti6_net *ip6n = net_generic(net, vti6_net_id); int err; - err = vti6_dev_init(dev); - if (err < 0) - goto out; - err = register_netdevice(dev); if (err < 0) goto out; @@ -693,6 +689,7 @@ static int vti6_change_mtu(struct net_device *dev, int new_mtu) } static const struct net_device_ops vti6_netdev_ops = { + .ndo_init = vti6_dev_init, .ndo_uninit = vti6_dev_uninit, .ndo_start_xmit = vti6_tnl_xmit, .ndo_do_ioctl = vti6_ioctl, @@ -772,16 +769,10 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); - int err = vti6_dev_init_gen(dev); - - if (err) - return err; t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - vti6_link_config(t); - rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } @@ -834,6 +825,15 @@ static int vti6_newlink(struct net *src_net, struct net_device *dev, return vti6_tnl_create2(dev); } +static void vti6_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + if (dev != ip6n->fb_tnl_dev) + unregister_netdevice_queue(dev, head); +} + static int vti6_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { @@ -909,6 +909,7 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = { .setup = vti6_dev_setup, .validate = vti6_validate, .newlink = vti6_newlink, + .dellink = vti6_dellink, .changelink = vti6_changelink, .get_size = vti6_get_size, .fill_info = vti6_fill_info, @@ -954,6 +955,7 @@ static int __net_init vti6_init_net(struct net *net) if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); + ip6n->fb_tnl_dev->rtnl_link_ops = &vti6_link_ops; err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 08b367c..761e458 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -172,6 +172,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) mc_lst->next = NULL; mc_lst->addr = *addr; + rtnl_lock(); rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -185,6 +186,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (dev == NULL) { rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } @@ -202,6 +204,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (err) { rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } @@ -212,6 +215,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) spin_unlock(&ipv6_sk_mc_lock); rcu_read_unlock(); + rtnl_unlock(); return 0; } @@ -229,6 +233,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) if (!ipv6_addr_is_multicast(addr)) return -EINVAL; + rtnl_lock(); spin_lock(&ipv6_sk_mc_lock); for (lnk = &np->ipv6_mc_list; (mc_lst = rcu_dereference_protected(*lnk, @@ -252,12 +257,15 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); rcu_read_unlock(); + rtnl_unlock(); + atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); return 0; } } spin_unlock(&ipv6_sk_mc_lock); + rtnl_unlock(); return -EADDRNOTAVAIL; } @@ -302,6 +310,7 @@ void ipv6_sock_mc_close(struct sock *sk) if (!rcu_access_pointer(np->ipv6_mc_list)) return; + rtnl_lock(); spin_lock(&ipv6_sk_mc_lock); while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list, lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) { @@ -328,6 +337,7 @@ void ipv6_sock_mc_close(struct sock *sk) spin_lock(&ipv6_sk_mc_lock); } spin_unlock(&ipv6_sk_mc_lock); + rtnl_unlock(); } int ip6_mc_source(int add, int omode, struct sock *sk, @@ -845,6 +855,8 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) struct ifmcaddr6 *mc; struct inet6_dev *idev; + ASSERT_RTNL(); + /* we need to take a reference on idev */ idev = in6_dev_get(dev); @@ -916,6 +928,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifmcaddr6 *ma, **map; + ASSERT_RTNL(); + write_lock_bh(&idev->lock); for (map = &idev->mc_list; (ma=*map) != NULL; map = &ma->next) { if (ipv6_addr_equal(&ma->mca_addr, addr)) { diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 09a22f4..bcd6518 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1193,7 +1193,14 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt) rt6_set_expires(rt, jiffies + (HZ * lifetime)); if (ra_msg->icmph.icmp6_hop_limit) { - in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + /* Only set hop_limit on the interface if it is higher than + * the current hop_limit. + */ + if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) { + in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + } else { + ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n"); + } if (rt) dst_metric_set(&rt->dst, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index b31a012..ae4a06b 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -3,33 +3,43 @@ * not configured or static. These functions are needed by GSO/GRO implementation. */ #include +#include #include #include #include -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +/* This function exists only for tap drivers that must support broken + * clients requesting UFO without specifying an IPv6 fragment ID. + * + * This is similar to ipv6_select_ident() but we use an independent hash + * seed to limit information leakage. + * + * The network header must be set before calling this. + */ +void ipv6_proxy_select_ident(struct sk_buff *skb) { - static atomic_t ipv6_fragmentation_id; - int ident; - -#if IS_ENABLED(CONFIG_IPV6) - if (rt && !(rt->dst.flags & DST_NOPEER)) { - struct inet_peer *peer; - struct net *net; - - net = dev_net(rt->dst.dev); - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); - if (peer) { - fhdr->identification = htonl(inet_getid(peer, 0)); - inet_putpeer(peer); - return; - } - } -#endif - ident = atomic_inc_return(&ipv6_fragmentation_id); - fhdr->identification = htonl(ident); + static u32 ip6_proxy_idents_hashrnd __read_mostly; + struct in6_addr buf[2]; + struct in6_addr *addrs; + u32 hash, id; + + addrs = skb_header_pointer(skb, + skb_network_offset(skb) + + offsetof(struct ipv6hdr, saddr), + sizeof(buf), buf); + if (!addrs) + return; + + net_get_random_once(&ip6_proxy_idents_hashrnd, + sizeof(ip6_proxy_idents_hashrnd)); + + hash = __ipv6_addr_jhash(&addrs[1], ip6_proxy_idents_hashrnd); + hash = __ipv6_addr_jhash(&addrs[0], hash); + + id = ip_idents_reserve(hash, 1); + skb_shinfo(skb)->ip6_frag_id = htonl(id); } -EXPORT_SYMBOL(ipv6_select_ident); +EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index bda7429..4611995 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -103,9 +103,10 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name); - if (msg->msg_namelen < sizeof(struct sockaddr_in6) || - u->sin6_family != AF_INET6) { + if (msg->msg_namelen < sizeof(*u)) return -EINVAL; + if (u->sin6_family != AF_INET6) { + return -EAFNOSUPPORT; } if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != u->sin6_scope_id) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7cc1102..3809ca2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -141,7 +141,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) u32 *p = NULL; if (!(rt->dst.flags & DST_HOST)) - return NULL; + return dst_cow_metrics_generic(dst, old); peer = rt6_get_peer_create(rt); if (peer) { @@ -1160,12 +1160,9 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct net *net = dev_net(dst->dev); rt6->rt6i_flags |= RTF_MODIFIED; - if (mtu < IPV6_MIN_MTU) { - u32 features = dst_metric(dst, RTAX_FEATURES); + if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - features |= RTAX_FEATURE_ALLFRAG; - dst_metric_set(dst, RTAX_FEATURES, features); - } + dst_metric_set(dst, RTAX_MTU, mtu); rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index fe548ba..317b6db 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -101,19 +101,19 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } @@ -195,10 +195,8 @@ static int ipip6_tunnel_create(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); int err; - err = ipip6_tunnel_init(dev); - if (err < 0) - goto out; - ipip6_tunnel_clone_6rd(dev, sitn); + memcpy(dev->dev_addr, &t->parms.iph.saddr, 4); + memcpy(dev->broadcast, &t->parms.iph.daddr, 4); if ((__force u16)t->parms.i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; @@ -207,7 +205,8 @@ static int ipip6_tunnel_create(struct net_device *dev) if (err < 0) goto out; - strcpy(t->parms.name, dev->name); + ipip6_tunnel_clone_6rd(dev, sitn); + dev->rtnl_link_ops = &sit_link_ops; dev_hold(dev); @@ -1321,6 +1320,7 @@ static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu) } static const struct net_device_ops ipip6_netdev_ops = { + .ndo_init = ipip6_tunnel_init, .ndo_uninit = ipip6_tunnel_uninit, .ndo_start_xmit = sit_tunnel_xmit, .ndo_do_ioctl = ipip6_tunnel_ioctl, @@ -1367,9 +1367,7 @@ static int ipip6_tunnel_init(struct net_device *dev) tunnel->dev = dev; tunnel->net = dev_net(dev); - - memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); - memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); + strcpy(tunnel->parms.name, dev->name); ipip6_tunnel_bind_dev(dev); dev->tstats = alloc_percpu(struct pcpu_sw_netstats); @@ -1401,7 +1399,6 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) tunnel->dev = dev; tunnel->net = dev_net(dev); - strcpy(tunnel->parms.name, dev->name); iph->version = 4; iph->protocol = IPPROTO_IPV6; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 889079b..b50ae29 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -905,7 +905,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw), - tw->tw_tclass, (tw->tw_flowlabel << 12)); + tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel)); inet_twsk_put(tw); } @@ -1633,7 +1633,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst = ACCESS_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); @@ -1668,6 +1668,7 @@ static const struct inet_connection_sock_af_ops ipv6_specific = { .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, #endif + .mtu_reduced = tcp_v6_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG @@ -1699,6 +1700,7 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, #endif + .mtu_reduced = tcp_v4_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG @@ -1935,7 +1937,6 @@ struct proto tcpv6_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, - .mtu_reduced = tcp_v6_mtu_reduced, .hash = tcp_v6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 20b63d2..38625a9 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -515,10 +515,8 @@ csum_copy_err: } unlock_sock_fast(sk, slow); - if (noblock) - return -EAGAIN; - - /* starting over for a new packet */ + /* starting over for a new packet, but check if we need to yield */ + cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 00b2a6d..d65aea2 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1763,6 +1763,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, struct ipxhdr *ipx = NULL; struct sk_buff *skb; int copied, rc; + bool locked = true; lock_sock(sk); /* put the autobinding in */ @@ -1789,6 +1790,8 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, if (sock_flag(sk, SOCK_ZAPPED)) goto out; + release_sock(sk); + locked = false; skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &rc); if (!skb) @@ -1822,7 +1825,8 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, out_free: skb_free_datagram(sk, skb); out: - release_sock(sk); + if (locked) + release_sock(sk); return rc; } diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index 2ba8b97..fdcb968 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -818,7 +818,9 @@ static void ircomm_tty_wait_until_sent(struct tty_struct *tty, int timeout) orig_jiffies = jiffies; /* Set poll time to 200 ms */ - poll_time = IRDA_MIN(timeout, msecs_to_jiffies(200)); + poll_time = msecs_to_jiffies(200); + if (timeout) + poll_time = min_t(unsigned long, timeout, poll_time); spin_lock_irqsave(&self->spinlock, flags); while (self->tx_skb && self->tx_skb->len) { diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index ec66063..da8d067 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -758,7 +758,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, /* If PMTU discovery was enabled, use the MTU that was discovered */ dst = sk_dst_get(tunnel->sock); if (dst != NULL) { - u32 pmtu = dst_mtu(__sk_dst_get(tunnel->sock)); + u32 pmtu = dst_mtu(dst); + if (pmtu != 0) session->mtu = session->mru = pmtu - PPPOL2TP_HEADER_OVERHEAD; @@ -1368,7 +1369,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, int err; if (level != SOL_PPPOL2TP) - return udp_prot.setsockopt(sk, level, optname, optval, optlen); + return -EINVAL; if (optlen < sizeof(int)) return -EINVAL; @@ -1494,7 +1495,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, struct pppol2tp_session *ps; if (level != SOL_PPPOL2TP) - return udp_prot.getsockopt(sk, level, optname, optval, optlen); + return -EINVAL; if (get_user(len, optlen)) return -EFAULT; diff --git a/net/llc/sysctl_net_llc.c b/net/llc/sysctl_net_llc.c index 612a5dd..799bafc 100644 --- a/net/llc/sysctl_net_llc.c +++ b/net/llc/sysctl_net_llc.c @@ -18,28 +18,28 @@ static struct ctl_table llc2_timeout_table[] = { { .procname = "ack", .data = &sysctl_llc2_ack_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(sysctl_llc2_ack_timeout), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "busy", .data = &sysctl_llc2_busy_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(sysctl_llc2_busy_timeout), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "p", .data = &sysctl_llc2_p_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(sysctl_llc2_p_timeout), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "rej", .data = &sysctl_llc2_rej_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(sysctl_llc2_rej_timeout), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c index 7c7df47..f056f9ed 100644 --- a/net/mac80211/aes_ccm.c +++ b/net/mac80211/aes_ccm.c @@ -54,6 +54,9 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, memset(&aead_req, 0, sizeof(aead_req)); + if (data_len == 0) + return -EINVAL; + sg_init_one(&pt, data, data_len); sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad)); sg_init_table(ct, 2); diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 653ce5d..5d8bc1f 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -712,6 +712,7 @@ void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata) debugfs_remove_recursive(sdata->vif.debugfs_dir); sdata->vif.debugfs_dir = NULL; + sdata->debugfs.subdir_stations = NULL; } void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index e09f10a..82fbf32 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -815,7 +815,7 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, memset(¶ms, 0, sizeof(params)); memset(&csa_ie, 0, sizeof(csa_ie)); - err = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, + err = ieee80211_parse_ch_switch_ie(sdata, elems, ifibss->chandef.chan->band, sta_flags, ifibss->bssid, &csa_ie); /* can't switch to destination channel, fail */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b127902..e278c64 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -57,13 +57,24 @@ struct ieee80211_local; #define IEEE80211_UNSET_POWER_LEVEL INT_MIN /* - * Some APs experience problems when working with U-APSD. Decrease the - * probability of that happening by using legacy mode for all ACs but VO. - * The AP that caused us trouble was a Cisco 4410N. It ignores our - * setting, and always treats non-VO ACs as legacy. + * Some APs experience problems when working with U-APSD. Decreasing the + * probability of that happening by using legacy mode for all ACs but VO isn't + * enough. + * + * Cisco 4410N originally forced us to enable VO by default only because it + * treated non-VO ACs as legacy. + * + * However some APs (notably Netgear R7000) silently reclassify packets to + * different ACs. Since u-APSD ACs require trigger frames for frame retrieval + * clients would never see some frames (e.g. ARP responses) or would fetch them + * accidentally after a long time. + * + * It makes little sense to enable u-APSD queues by default because it needs + * userspace applications to be aware of it to actually take advantage of the + * possible additional powersavings. Implicitly depending on driver autotrigger + * frame support doesn't make much sense. */ -#define IEEE80211_DEFAULT_UAPSD_QUEUES \ - IEEE80211_WMM_IE_STA_QOSINFO_AC_VO +#define IEEE80211_DEFAULT_UAPSD_QUEUES 0 #define IEEE80211_DEFAULT_MAX_SP_LEN \ IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL @@ -1569,7 +1580,6 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, * ieee80211_parse_ch_switch_ie - parses channel switch IEs * @sdata: the sdata of the interface which has received the frame * @elems: parsed 802.11 elements received with the frame - * @beacon: indicates if the frame was a beacon or probe response * @current_band: indicates the current band * @sta_flags: contains information about own capabilities and restrictions * to decide which channel switch announcements can be accepted. Only the @@ -1583,7 +1593,7 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, * Return: 0 on success, <0 on error and >0 if there is nothing to parse. */ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, - struct ieee802_11_elems *elems, bool beacon, + struct ieee802_11_elems *elems, enum ieee80211_band current_band, u32 sta_flags, u8 *bssid, struct ieee80211_csa_ie *csa_ie); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 8f7fabc..06f5de4 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -760,10 +760,12 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, int i, flushed; struct ps_data *ps; struct cfg80211_chan_def chandef; + bool cancel_scan; clear_bit(SDATA_STATE_RUNNING, &sdata->state); - if (rcu_access_pointer(local->scan_sdata) == sdata) + cancel_scan = rcu_access_pointer(local->scan_sdata) == sdata; + if (cancel_scan) ieee80211_scan_cancel(local); /* @@ -973,6 +975,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ieee80211_recalc_ps(local, -1); + if (cancel_scan) + flush_delayed_work(&local->scan_work); + if (local->open_count == 0) { ieee80211_stop_device(local); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 6ff65a1..d78b37a 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -652,7 +652,7 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local, int i; mutex_lock(&local->key_mtx); - for (i = 0; i < NUM_DEFAULT_KEYS; i++) { + for (i = 0; i < ARRAY_SIZE(sta->gtk); i++) { key = key_mtx_dereference(local, sta->gtk[i]); if (!key) continue; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index c7a7a86..9e58c99 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -248,6 +248,7 @@ static void ieee80211_restart_work(struct work_struct *work) { struct ieee80211_local *local = container_of(work, struct ieee80211_local, restart_work); + struct ieee80211_sub_if_data *sdata; /* wait for scan work complete */ flush_workqueue(local->workqueue); @@ -256,6 +257,8 @@ static void ieee80211_restart_work(struct work_struct *work) "%s called with hardware scan in progress\n", __func__); rtnl_lock(); + list_for_each_entry(sdata, &local->interfaces, list) + flush_delayed_work(&sdata->dec_tailroom_needed_wk); ieee80211_scan_cancel(local); ieee80211_reconfig(local); rtnl_unlock(); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 5b919ca..3d52d1d 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -885,7 +885,7 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, memset(¶ms, 0, sizeof(params)); memset(&csa_ie, 0, sizeof(csa_ie)); - err = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, band, + err = ieee80211_parse_ch_switch_ie(sdata, elems, band, sta_flags, sdata->vif.addr, &csa_ie); if (err < 0) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e6a84cb..c9535a9 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1001,7 +1001,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, current_band = cbss->channel->band; memset(&csa_ie, 0, sizeof(csa_ie)); - res = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, current_band, + res = ieee80211_parse_ch_switch_ie(sdata, elems, current_band, ifmgd->flags, ifmgd->associated->bssid, &csa_ie); if (res < 0) @@ -1086,7 +1086,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, ieee80211_queue_work(&local->hw, &ifmgd->chswitch_work); else mod_timer(&ifmgd->chswitch_timer, - TU_TO_EXP_TIME(csa_ie.count * cbss->beacon_interval)); + TU_TO_EXP_TIME((csa_ie.count - 1) * + cbss->beacon_interval)); } static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, @@ -4240,8 +4241,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); if (bss->wmm_used && bss->uapsd_supported && - (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD) && - sdata->wmm_acm != 0xff) { + (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) { assoc_data->uapsd = true; ifmgd->flags |= IEEE80211_STA_UAPSD_ENABLED; } else { diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 22b223f..74350c3 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -462,7 +462,7 @@ static void rate_fixup_ratelist(struct ieee80211_vif *vif, */ if (!(rates[0].flags & IEEE80211_TX_RC_MCS)) { u32 basic_rates = vif->bss_conf.basic_rates; - s8 baserate = basic_rates ? ffs(basic_rates - 1) : 0; + s8 baserate = basic_rates ? ffs(basic_rates) - 1 : 0; rate = &sband->bitrates[rates[0].idx]; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3e57f96..9abb445 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -261,7 +261,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, else if (rate && rate->flags & IEEE80211_RATE_ERP_G) channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ; else if (rate) - channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ; + channel_flags |= IEEE80211_CHAN_CCK | IEEE80211_CHAN_2GHZ; else channel_flags |= IEEE80211_CHAN_2GHZ; put_unaligned_le16(channel_flags, pos); @@ -1679,11 +1679,14 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sc = le16_to_cpu(hdr->seq_ctrl); frag = sc & IEEE80211_SCTL_FRAG; - if (likely((!ieee80211_has_morefrags(fc) && frag == 0) || - is_multicast_ether_addr(hdr->addr1))) { - /* not fragmented */ - goto out; + if (is_multicast_ether_addr(hdr->addr1)) { + rx->local->dot11MulticastReceivedFrameCount++; + goto out_no_led; } + + if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) + goto out; + I802_DEBUG_INC(rx->local->rx_handlers_fragments); if (skb_linearize(rx->skb)) @@ -1774,12 +1777,10 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) status->rx_flags |= IEEE80211_RX_FRAGMENTED; out: + ieee80211_led_rx(rx->local); + out_no_led: if (rx->sta) rx->sta->rx_packets++; - if (is_multicast_ether_addr(hdr->addr1)) - rx->local->dot11MulticastReceivedFrameCount++; - else - ieee80211_led_rx(rx->local); return RX_CONTINUE; } @@ -2106,6 +2107,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) hdr = (struct ieee80211_hdr *) skb->data; mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); + if (ieee80211_drop_unencrypted(rx, hdr->frame_control)) + return RX_DROP_MONITOR; + /* frame is in RMC, don't forward */ if (ieee80211_is_data(hdr->frame_control) && is_multicast_ether_addr(hdr->addr1) && diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index 6ab0090..efeba56 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -22,7 +22,7 @@ #include "wme.h" int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, - struct ieee802_11_elems *elems, bool beacon, + struct ieee802_11_elems *elems, enum ieee80211_band current_band, u32 sta_flags, u8 *bssid, struct ieee80211_csa_ie *csa_ie) @@ -91,19 +91,13 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, return -EINVAL; } - if (!beacon && sec_chan_offs) { + if (sec_chan_offs) { secondary_channel_offset = sec_chan_offs->sec_chan_offs; - } else if (beacon && ht_oper) { - secondary_channel_offset = - ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET; } else if (!(sta_flags & IEEE80211_STA_DISABLE_HT)) { - /* If it's not a beacon, HT is enabled and the IE not present, - * it's 20 MHz, 802.11-2012 8.5.2.6: - * This element [the Secondary Channel Offset Element] is - * present when switching to a 40 MHz channel. It may be - * present when switching to a 20 MHz channel (in which - * case the secondary channel offset is set to SCN). - */ + /* If the secondary channel offset IE is not present, + * we can't know what's the post-CSA offset, so the + * best we can do is use 20MHz. + */ secondary_channel_offset = IEEE80211_HT_PARAM_CHA_SEC_NONE; } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index c14c16a..dca076f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -414,6 +414,9 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) if (ieee80211_has_order(hdr->frame_control)) return TX_CONTINUE; + if (ieee80211_is_probe_req(hdr->frame_control)) + return TX_CONTINUE; + if (tx->local->hw.flags & IEEE80211_HW_QUEUE_CONTROL) info->hw_queue = tx->sdata->vif.cab_queue; @@ -464,6 +467,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) { struct sta_info *sta = tx->sta; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; struct ieee80211_local *local = tx->local; if (unlikely(!sta)) @@ -474,6 +478,15 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) !(info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER))) { int ac = skb_get_queue_mapping(tx->skb); + /* only deauth, disassoc and action are bufferable MMPDUs */ + if (ieee80211_is_mgmt(hdr->frame_control) && + !ieee80211_is_deauth(hdr->frame_control) && + !ieee80211_is_disassoc(hdr->frame_control) && + !ieee80211_is_action(hdr->frame_control)) { + info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; + return TX_CONTINUE; + } + ps_dbg(sta->sdata, "STA %pM aid %d: PS buffer for AC %d\n", sta->sta.addr, sta->sta.aid, ac); if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) @@ -532,22 +545,8 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) static ieee80211_tx_result debug_noinline ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; - if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED)) return TX_CONTINUE; - - /* only deauth, disassoc and action are bufferable MMPDUs */ - if (ieee80211_is_mgmt(hdr->frame_control) && - !ieee80211_is_deauth(hdr->frame_control) && - !ieee80211_is_disassoc(hdr->frame_control) && - !ieee80211_is_action(hdr->frame_control)) { - if (tx->flags & IEEE80211_TX_UNICAST) - info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; - return TX_CONTINUE; - } - if (tx->flags & IEEE80211_TX_UNICAST) return ieee80211_tx_h_unicast_ps_buf(tx); else @@ -563,6 +562,7 @@ ieee80211_tx_h_check_control_port_protocol(struct ieee80211_tx_data *tx) if (tx->sdata->control_port_no_encrypt) info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; info->control.flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO; + info->flags |= IEEE80211_TX_CTL_USE_MINRATE; } return TX_CONTINUE; diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c index 6ee2b58..f21b142 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -98,8 +98,7 @@ static u8 *ieee80211_wep_add_iv(struct ieee80211_local *local, hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); - if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN || - skb_headroom(skb) < IEEE80211_WEP_IV_LEN)) + if (WARN_ON(skb_headroom(skb) < IEEE80211_WEP_IV_LEN)) return NULL; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -169,6 +168,9 @@ int ieee80211_wep_encrypt(struct ieee80211_local *local, size_t len; u8 rc4key[3 + WLAN_KEY_LEN_WEP104]; + if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN)) + return -1; + iv = ieee80211_wep_add_iv(local, skb, keylen, keyidx); if (!iv) return -1; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index de770ec..53ea164 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -636,7 +636,7 @@ ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index) struct ip_set *set; struct ip_set_net *inst = ip_set_pernet(net); - if (index > inst->ip_set_max) + if (index >= inst->ip_set_max) return IPSET_INVALID_ID; nfnl_lock(NFNL_SUBSYS_IPSET); @@ -1839,6 +1839,12 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) if (*op < IP_SET_OP_VERSION) { /* Check the version at the beginning of operations */ struct ip_set_req_version *req_version = data; + + if (*len < sizeof(struct ip_set_req_version)) { + ret = -EINVAL; + goto done; + } + if (req_version->version != IPSET_PROTOCOL) { ret = -EPROTO; goto done; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index a8eb0a8..610e19c 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -797,7 +797,6 @@ static void ip_vs_conn_expire(unsigned long data) ip_vs_control_del(cp); if (cp->flags & IP_VS_CONN_F_NFCT) { - ip_vs_conn_drop_conntrack(cp); /* Do not access conntracks during subsys cleanup * because nf_conntrack_find_get can not be used after * conntrack cleanup for the net. diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 3d2d2c8..847d2a2 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -658,16 +658,24 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user) return err; } -static int ip_vs_route_me_harder(int af, struct sk_buff *skb) +static int ip_vs_route_me_harder(int af, struct sk_buff *skb, + unsigned int hooknum) { + if (!sysctl_snat_reroute(skb)) + return 0; + /* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */ + if (NF_INET_LOCAL_IN == hooknum) + return 0; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (sysctl_snat_reroute(skb) && ip6_route_me_harder(skb) != 0) + struct dst_entry *dst = skb_dst(skb); + + if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && + ip6_route_me_harder(skb) != 0) return 1; } else #endif - if ((sysctl_snat_reroute(skb) || - skb_rtable(skb)->rt_flags & RTCF_LOCAL) && + if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(skb, RTN_LOCAL) != 0) return 1; @@ -790,7 +798,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, union nf_inet_addr *snet, __u8 protocol, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, - unsigned int offset, unsigned int ihl) + unsigned int offset, unsigned int ihl, + unsigned int hooknum) { unsigned int verdict = NF_DROP; @@ -820,7 +829,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, #endif ip_vs_nat_icmp(skb, pp, cp, 1); - if (ip_vs_route_me_harder(af, skb)) + if (ip_vs_route_me_harder(af, skb, hooknum)) goto out; /* do the statistics and put it back */ @@ -915,7 +924,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, snet.ip = iph->saddr; return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, - pp, ciph.len, ihl); + pp, ciph.len, ihl, hooknum); } #ifdef CONFIG_IP_VS_IPV6 @@ -980,7 +989,8 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, snet.in6 = ciph.saddr.in6; writable = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, - pp, writable, sizeof(struct ipv6hdr)); + pp, writable, sizeof(struct ipv6hdr), + hooknum); } #endif @@ -1039,7 +1049,8 @@ static inline bool is_new_conn(const struct sk_buff *skb, */ static unsigned int handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, - struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph, + unsigned int hooknum) { struct ip_vs_protocol *pp = pd->pp; @@ -1077,7 +1088,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, * if it came from this machine itself. So re-compute * the routing information. */ - if (ip_vs_route_me_harder(af, skb)) + if (ip_vs_route_me_harder(af, skb, hooknum)) goto drop; IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT"); @@ -1180,7 +1191,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) cp = pp->conn_out_get(af, skb, &iph, 0); if (likely(cp)) - return handle_response(af, skb, pd, cp, &iph); + return handle_response(af, skb, pd, cp, &iph, hooknum); if (sysctl_nat_icmp_send(net) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || @@ -1906,7 +1917,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_local_reply6, .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 77c1732..4a662f1 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -183,6 +183,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, struct nf_conn *ct; struct net *net; + *diff = 0; + #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, * so turn this into a no-op for IPv6 packets @@ -191,8 +193,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, return 1; #endif - *diff = 0; - /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; @@ -321,6 +321,9 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, struct ip_vs_conn *n_cp; struct net *net; + /* no diff required for incoming packets */ + *diff = 0; + #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, * so turn this into a no-op for IPv6 packets @@ -329,9 +332,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, return 1; #endif - /* no diff required for incoming packets */ - *diff = 0; - /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index db80126..a8027e7 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -891,6 +891,8 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, IP_VS_DBG(2, "BACKUP, add new conn. failed\n"); return; } + if (!(flags & IP_VS_CONN_F_TEMPLATE)) + kfree(param->pe_data); } if (opt) @@ -1164,6 +1166,7 @@ static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end) (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) ); #endif + ip_vs_pe_put(param.pe); return 0; /* Error exit */ out: diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index c47444e..1692e75 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -883,7 +883,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->daddr = cp->daddr.ip; iph->saddr = saddr; iph->ttl = old_iph->ttl; - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -967,8 +967,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, iph->nexthdr = IPPROTO_IPV6; iph->payload_len = old_iph->payload_len; be16_add_cpu(&iph->payload_len, sizeof(*old_iph)); - iph->priority = old_iph->priority; memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl)); + ipv6_change_dsfield(iph, 0, ipv6_get_dsfield(old_iph)); iph->daddr = cp->daddr.in6; iph->saddr = saddr; iph->hop_limit = old_iph->hop_limit; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index d25f293..957c1db 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -14,6 +14,30 @@ static unsigned int nf_ct_generic_timeout __read_mostly = 600*HZ; +static bool nf_generic_should_process(u8 proto) +{ + switch (proto) { +#ifdef CONFIG_NF_CT_PROTO_SCTP_MODULE + case IPPROTO_SCTP: + return false; +#endif +#ifdef CONFIG_NF_CT_PROTO_DCCP_MODULE + case IPPROTO_DCCP: + return false; +#endif +#ifdef CONFIG_NF_CT_PROTO_GRE_MODULE + case IPPROTO_GRE: + return false; +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE_MODULE + case IPPROTO_UDPLITE: + return false; +#endif + default: + return true; + } +} + static inline struct nf_generic_net *generic_pernet(struct net *net) { return &net->ct.nf_ct_proto.generic; @@ -67,7 +91,7 @@ static int generic_packet(struct nf_conn *ct, static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, unsigned int *timeouts) { - return true; + return nf_generic_should_process(nf_ct_protonum(ct)); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c68e5e0..99de240 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -855,7 +855,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, if (nla[NFTA_CHAIN_POLICY]) { if ((chain != NULL && - !(chain->flags & NFT_BASE_CHAIN)) || + !(chain->flags & NFT_BASE_CHAIN))) + return -EOPNOTSUPP; + + if (chain == NULL && nla[NFTA_CHAIN_HOOK] == NULL) return -EOPNOTSUPP; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index bf8a108..6cf2f07 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -265,7 +265,8 @@ replay: nlh = nlmsg_hdr(skb); err = 0; - if (nlh->nlmsg_len < NLMSG_HDRLEN) { + if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) || + skb->len < nlh->nlmsg_len) { err = -EINVAL; goto ack; } diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 9e287cb..54330fb 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -77,6 +77,9 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple, if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM]) return -EINVAL; + /* Not all fields are initialized so first zero the tuple */ + memset(tuple, 0, sizeof(struct nf_conntrack_tuple)); + tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM])); tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]); @@ -86,7 +89,7 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple, static int nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct) { - const struct nf_conn_help *help = nfct_help(ct); + struct nf_conn_help *help = nfct_help(ct); if (attr == NULL) return -EINVAL; @@ -94,7 +97,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct) if (help->helper->data_len == 0) return -EINVAL; - memcpy(&help->data, nla_data(attr), help->helper->data_len); + memcpy(help->data, nla_data(attr), help->helper->data_len); return 0; } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index a155d19..6ff12a1 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -45,7 +45,8 @@ #define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ -#define NFULNL_COPY_RANGE_MAX 0xFFFF /* max packet size is limited by 16-bit struct nfattr nfa_len field */ +/* max packet size is limited by 16-bit struct nfattr nfa_len field */ +#define NFULNL_COPY_RANGE_MAX (0xFFFF - NLA_HDRLEN) #define PRINTR(x, args...) do { if (net_ratelimit()) \ printk(x, ## args); } while (0); @@ -255,6 +256,8 @@ nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode, case NFULNL_COPY_PACKET: inst->copy_mode = mode; + if (range == 0) + range = NFULNL_COPY_RANGE_MAX; inst->copy_range = min_t(unsigned int, range, NFULNL_COPY_RANGE_MAX); break; @@ -346,26 +349,25 @@ nfulnl_alloc_skb(struct net *net, u32 peer_portid, unsigned int inst_size, return skb; } -static int +static void __nfulnl_send(struct nfulnl_instance *inst) { - int status = -1; - if (inst->qlen > 1) { struct nlmsghdr *nlh = nlmsg_put(inst->skb, 0, 0, NLMSG_DONE, sizeof(struct nfgenmsg), 0); - if (!nlh) + if (WARN_ONCE(!nlh, "bad nlskb size: %u, tailroom %d\n", + inst->skb->len, skb_tailroom(inst->skb))) { + kfree_skb(inst->skb); goto out; + } } - status = nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid, - MSG_DONTWAIT); - + nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid, + MSG_DONTWAIT); +out: inst->qlen = 0; inst->skb = NULL; -out: - return status; } static void @@ -652,7 +654,8 @@ nfulnl_log_packet(struct net *net, + nla_total_size(sizeof(u_int32_t)) /* gid */ + nla_total_size(plen) /* prefix */ + nla_total_size(sizeof(struct nfulnl_msg_packet_hw)) - + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)); + + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)) + + nla_total_size(sizeof(struct nfgenmsg)); /* NLMSG_DONE */ if (in && skb_mac_header_was_set(skb)) { size += nla_total_size(skb->dev->hard_header_len) @@ -681,8 +684,7 @@ nfulnl_log_packet(struct net *net, break; case NFULNL_COPY_PACKET: - if (inst->copy_range == 0 - || inst->copy_range > skb->len) + if (inst->copy_range > skb->len) data_len = skb->len; else data_len = inst->copy_range; @@ -695,8 +697,7 @@ nfulnl_log_packet(struct net *net, goto unlock_and_release; } - if (inst->skb && - size > skb_tailroom(inst->skb) - sizeof(struct nfgenmsg)) { + if (inst->skb && size > skb_tailroom(inst->skb)) { /* either the queue len is too high or we don't have * enough room in the skb left. flush to userspace. */ __nfulnl_flush(inst); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 82cb823..9695895 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -82,6 +82,9 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par, entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0; break; case AF_INET6: + if (proto) + entry->e6.ipv6.flags |= IP6T_F_PROTO; + entry->e6.ipv6.proto = proto; entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0; break; @@ -313,6 +316,9 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx, entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0; break; case AF_INET6: + if (proto) + entry->e6.ipv6.flags |= IP6T_F_PROTO; + entry->e6.ipv6.proto = proto; entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0; break; @@ -611,8 +617,12 @@ nft_match_select_ops(const struct nft_ctx *ctx, struct xt_match *match = nft_match->ops.data; if (strcmp(match->name, mt_name) == 0 && - match->revision == rev && match->family == family) + match->revision == rev && match->family == family) { + if (!try_module_get(match->me)) + return ERR_PTR(-ENOENT); + return &nft_match->ops; + } } match = xt_request_find_match(family, mt_name, rev); @@ -678,12 +688,16 @@ nft_target_select_ops(const struct nft_ctx *ctx, family = ctx->afi->family; /* Re-use the existing target if it's already loaded. */ - list_for_each_entry(nft_target, &nft_match_list, head) { + list_for_each_entry(nft_target, &nft_target_list, head) { struct xt_target *target = nft_target->ops.data; if (strcmp(target->name, tg_name) == 0 && - target->revision == rev && target->family == family) + target->revision == rev && target->family == family) { + if (!try_module_get(target->me)) + return ERR_PTR(-ENOENT); + return &nft_target->ops; + } } target = xt_request_find_target(family, tg_name, rev); diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index 9a8e77e7..ef5c75a 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -31,7 +31,7 @@ static int cgroup_mt_check(const struct xt_mtchk_param *par) if (info->invert & ~1) return -EINVAL; - return info->id ? 0 : -EINVAL; + return 0; } static bool diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index a3910fc..47dc683 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -104,7 +104,7 @@ struct xt_hashlimit_htable { spinlock_t lock; /* lock for list_head */ u_int32_t rnd; /* random seed for hash */ unsigned int count; /* number entries in table */ - struct timer_list timer; /* timer for gc */ + struct delayed_work gc_work; /* seq_file stuff */ struct proc_dir_entry *pde; @@ -213,7 +213,7 @@ dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent) call_rcu_bh(&ent->rcu, dsthash_free_rcu); ht->count--; } -static void htable_gc(unsigned long htlong); +static void htable_gc(struct work_struct *work); static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, u_int8_t family) @@ -273,9 +273,9 @@ static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, } hinfo->net = net; - setup_timer(&hinfo->timer, htable_gc, (unsigned long)hinfo); - hinfo->timer.expires = jiffies + msecs_to_jiffies(hinfo->cfg.gc_interval); - add_timer(&hinfo->timer); + INIT_DEFERRABLE_WORK(&hinfo->gc_work, htable_gc); + queue_delayed_work(system_power_efficient_wq, &hinfo->gc_work, + msecs_to_jiffies(hinfo->cfg.gc_interval)); hlist_add_head(&hinfo->node, &hashlimit_net->htables); @@ -300,29 +300,30 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, { unsigned int i; - /* lock hash table and iterate over it */ - spin_lock_bh(&ht->lock); for (i = 0; i < ht->cfg.size; i++) { struct dsthash_ent *dh; struct hlist_node *n; + + spin_lock_bh(&ht->lock); hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) { if ((*select)(ht, dh)) dsthash_free(ht, dh); } + spin_unlock_bh(&ht->lock); + cond_resched(); } - spin_unlock_bh(&ht->lock); } -/* hash table garbage collector, run by timer */ -static void htable_gc(unsigned long htlong) +static void htable_gc(struct work_struct *work) { - struct xt_hashlimit_htable *ht = (struct xt_hashlimit_htable *)htlong; + struct xt_hashlimit_htable *ht; + + ht = container_of(work, struct xt_hashlimit_htable, gc_work.work); htable_selective_cleanup(ht, select_gc); - /* re-add the timer accordingly */ - ht->timer.expires = jiffies + msecs_to_jiffies(ht->cfg.gc_interval); - add_timer(&ht->timer); + queue_delayed_work(system_power_efficient_wq, + &ht->gc_work, msecs_to_jiffies(ht->cfg.gc_interval)); } static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) @@ -341,7 +342,7 @@ static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) static void htable_destroy(struct xt_hashlimit_htable *hinfo) { - del_timer_sync(&hinfo->timer); + cancel_delayed_work_sync(&hinfo->gc_work); htable_remove_proc_entry(hinfo); htable_selective_cleanup(hinfo, select_all); kfree(hinfo->name); diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 1ba6793..13332db 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -243,12 +243,13 @@ static int extract_icmp6_fields(const struct sk_buff *skb, unsigned int outside_hdrlen, int *protocol, - struct in6_addr **raddr, - struct in6_addr **laddr, + const struct in6_addr **raddr, + const struct in6_addr **laddr, __be16 *rport, - __be16 *lport) + __be16 *lport, + struct ipv6hdr *ipv6_var) { - struct ipv6hdr *inside_iph, _inside_iph; + const struct ipv6hdr *inside_iph; struct icmp6hdr *icmph, _icmph; __be16 *ports, _ports[2]; u8 inside_nexthdr; @@ -263,12 +264,14 @@ extract_icmp6_fields(const struct sk_buff *skb, if (icmph->icmp6_type & ICMPV6_INFOMSG_MASK) return 1; - inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph), sizeof(_inside_iph), &_inside_iph); + inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph), + sizeof(*ipv6_var), ipv6_var); if (inside_iph == NULL) return 1; inside_nexthdr = inside_iph->nexthdr; - inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + sizeof(_inside_iph), + inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + + sizeof(*ipv6_var), &inside_nexthdr, &inside_fragoff); if (inside_hdrlen < 0) return 1; /* hjm: Packet has no/incomplete transport layer headers. */ @@ -315,10 +318,10 @@ xt_socket_get_sock_v6(struct net *net, const u8 protocol, static bool socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) { - struct ipv6hdr *iph = ipv6_hdr(skb); + struct ipv6hdr ipv6_var, *iph = ipv6_hdr(skb); struct udphdr _hdr, *hp = NULL; struct sock *sk = skb->sk; - struct in6_addr *daddr = NULL, *saddr = NULL; + const struct in6_addr *daddr = NULL, *saddr = NULL; __be16 uninitialized_var(dport), uninitialized_var(sport); int thoff = 0, uninitialized_var(tproto); const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; @@ -342,7 +345,7 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) } else if (tproto == IPPROTO_ICMPV6) { if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr, - &sport, &dport)) + &sport, &dport, &ipv6_var)) return false; } else { return false; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 0dfe894..a0b0ea9 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -205,7 +205,7 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb, nskb->protocol = htons((u16) sk->sk_protocol); nskb->pkt_type = netlink_is_kernel(sk) ? PACKET_KERNEL : PACKET_USER; - + skb_reset_network_header(nskb); ret = dev_queue_xmit(nskb); if (unlikely(ret > 0)) ret = net_xmit_errno(ret); @@ -510,14 +510,14 @@ out: return err; } -static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr) +static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr, unsigned int nm_len) { #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 struct page *p_start, *p_end; /* First page is flushed through netlink_{get,set}_status */ p_start = pgvec_to_page(hdr + PAGE_SIZE); - p_end = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + hdr->nm_len - 1); + p_end = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + nm_len - 1); while (p_start <= p_end) { flush_dcache_page(p_start); p_start++; @@ -535,9 +535,9 @@ static enum nl_mmap_status netlink_get_status(const struct nl_mmap_hdr *hdr) static void netlink_set_status(struct nl_mmap_hdr *hdr, enum nl_mmap_status status) { + smp_mb(); hdr->nm_status = status; flush_dcache_page(pgvec_to_page(hdr)); - smp_wmb(); } static struct nl_mmap_hdr * @@ -699,24 +699,16 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg, struct nl_mmap_hdr *hdr; struct sk_buff *skb; unsigned int maxlen; - bool excl = true; int err = 0, len = 0; - /* Netlink messages are validated by the receiver before processing. - * In order to avoid userspace changing the contents of the message - * after validation, the socket and the ring may only be used by a - * single process, otherwise we fall back to copying. - */ - if (atomic_long_read(&sk->sk_socket->file->f_count) > 2 || - atomic_read(&nlk->mapped) > 1) - excl = false; - mutex_lock(&nlk->pg_vec_lock); ring = &nlk->tx_ring; maxlen = ring->frame_size - NL_MMAP_HDRLEN; do { + unsigned int nm_len; + hdr = netlink_current_frame(ring, NL_MMAP_STATUS_VALID); if (hdr == NULL) { if (!(msg->msg_flags & MSG_DONTWAIT) && @@ -724,35 +716,23 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg, schedule(); continue; } - if (hdr->nm_len > maxlen) { + + nm_len = ACCESS_ONCE(hdr->nm_len); + if (nm_len > maxlen) { err = -EINVAL; goto out; } - netlink_frame_flush_dcache(hdr); + netlink_frame_flush_dcache(hdr, nm_len); - if (likely(dst_portid == 0 && dst_group == 0 && excl)) { - skb = alloc_skb_head(GFP_KERNEL); - if (skb == NULL) { - err = -ENOBUFS; - goto out; - } - sock_hold(sk); - netlink_ring_setup_skb(skb, sk, ring, hdr); - NETLINK_CB(skb).flags |= NETLINK_SKB_TX; - __skb_put(skb, hdr->nm_len); - netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED); - atomic_inc(&ring->pending); - } else { - skb = alloc_skb(hdr->nm_len, GFP_KERNEL); - if (skb == NULL) { - err = -ENOBUFS; - goto out; - } - __skb_put(skb, hdr->nm_len); - memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, hdr->nm_len); - netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED); + skb = alloc_skb(nm_len, GFP_KERNEL); + if (skb == NULL) { + err = -ENOBUFS; + goto out; } + __skb_put(skb, nm_len); + memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, nm_len); + netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED); netlink_increment_head(ring); @@ -798,7 +778,7 @@ static void netlink_queue_mmaped_skb(struct sock *sk, struct sk_buff *skb) hdr->nm_pid = NETLINK_CB(skb).creds.pid; hdr->nm_uid = from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid); hdr->nm_gid = from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid); - netlink_frame_flush_dcache(hdr); + netlink_frame_flush_dcache(hdr, hdr->nm_len); netlink_set_status(hdr, NL_MMAP_STATUS_VALID); NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED; @@ -1644,13 +1624,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size, if (data == NULL) return NULL; - skb = build_skb(data, size); + skb = __build_skb(data, size); if (skb == NULL) vfree(data); - else { - skb->head_frag = 0; + else skb->destructor = netlink_skb_destructor; - } return skb; } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2c77e7b..600c764 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -42,6 +42,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, static int make_writable(struct sk_buff *skb, int write_len) { + if (!pskb_may_pull(skb, write_len)) + return -ENOMEM; + if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; @@ -70,6 +73,8 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci) vlan_set_encap_proto(skb, vhdr); skb->mac_header += VLAN_HLEN; + if (skb_network_offset(skb) < ETH_HLEN) + skb_set_network_header(skb, ETH_HLEN); skb_reset_mac_len(skb); return 0; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 48a6a93..84a60b8 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -635,6 +635,7 @@ static void init_prb_bdqc(struct packet_sock *po, p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; + p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); prb_setup_retire_blk_timer(po, tx_ring); prb_open_block(p1, pbd); @@ -1263,16 +1264,6 @@ static void packet_sock_destruct(struct sock *sk) sk_refcnt_debug_dec(sk); } -static int fanout_rr_next(struct packet_fanout *f, unsigned int num) -{ - int x = atomic_read(&f->rr_cur) + 1; - - if (x >= num) - x = 0; - - return x; -} - static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) @@ -1284,13 +1275,9 @@ static unsigned int fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { - int cur, old; + unsigned int val = atomic_inc_return(&f->rr_cur); - cur = atomic_read(&f->rr_cur); - while ((old = atomic_cmpxchg(&f->rr_cur, cur, - fanout_rr_next(f, num))) != cur) - cur = old; - return cur; + return val % num; } static unsigned int fanout_demux_cpu(struct packet_fanout *f, @@ -1344,7 +1331,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct packet_fanout *f = pt->af_packet_priv; - unsigned int num = f->num_members; + unsigned int num = ACCESS_ONCE(f->num_members); struct packet_sock *po; unsigned int idx; @@ -1946,6 +1933,18 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if ((int)snaplen < 0) snaplen = 0; } + } else if (unlikely(macoff + snaplen > + GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) { + u32 nval; + + nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff; + pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n", + snaplen, nval, macoff); + snaplen = nval; + if (unlikely((int)snaplen < 0)) { + snaplen = 0; + macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len; + } } spin_lock(&sk->sk_receive_queue.lock); h.raw = packet_current_rx_frame(po, skb, @@ -3779,6 +3778,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; if (unlikely(req->tp_block_size & (PAGE_SIZE - 1))) goto out; + if (po->tp_version >= TPACKET_V3 && + (int)(req->tp_block_size - + BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0) + goto out; if (unlikely(req->tp_frame_size < po->tp_hdrlen + po->tp_reserve)) goto out; diff --git a/net/packet/internal.h b/net/packet/internal.h index eb9580a..cdddf6a 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -29,6 +29,7 @@ struct tpacket_kbdq_core { char *pkblk_start; char *pkblk_end; int kblk_size; + unsigned int max_frame_len; unsigned int knum_blocks; uint64_t knxt_seq_num; char *prev; diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index e8fdb17..a985158 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -759,8 +759,10 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, } ibmr = rds_ib_alloc_fmr(rds_ibdev); - if (IS_ERR(ibmr)) + if (IS_ERR(ibmr)) { + rds_ib_dev_put(rds_ibdev); return ibmr; + } ret = rds_ib_map_fmr(rds_ibdev, ibmr, sg, nents); if (ret == 0) diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index a817705..dba8d08 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -88,7 +88,9 @@ static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool, int *unpinned); static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr); -static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwdev, struct rdma_cm_id **cm_id) +static int rds_iw_get_device(struct sockaddr_in *src, struct sockaddr_in *dst, + struct rds_iw_device **rds_iwdev, + struct rdma_cm_id **cm_id) { struct rds_iw_device *iwdev; struct rds_iw_cm_id *i_cm_id; @@ -112,15 +114,15 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd src_addr->sin_port, dst_addr->sin_addr.s_addr, dst_addr->sin_port, - rs->rs_bound_addr, - rs->rs_bound_port, - rs->rs_conn_addr, - rs->rs_conn_port); + src->sin_addr.s_addr, + src->sin_port, + dst->sin_addr.s_addr, + dst->sin_port); #ifdef WORKING_TUPLE_DETECTION - if (src_addr->sin_addr.s_addr == rs->rs_bound_addr && - src_addr->sin_port == rs->rs_bound_port && - dst_addr->sin_addr.s_addr == rs->rs_conn_addr && - dst_addr->sin_port == rs->rs_conn_port) { + if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr && + src_addr->sin_port == src->sin_port && + dst_addr->sin_addr.s_addr == dst->sin_addr.s_addr && + dst_addr->sin_port == dst->sin_port) { #else /* FIXME - needs to compare the local and remote * ipaddr/port tuple, but the ipaddr is the only @@ -128,7 +130,7 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd * zero'ed. It doesn't appear to be properly populated * during connection setup... */ - if (src_addr->sin_addr.s_addr == rs->rs_bound_addr) { + if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr) { #endif spin_unlock_irq(&iwdev->spinlock); *rds_iwdev = iwdev; @@ -180,19 +182,13 @@ int rds_iw_update_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_i { struct sockaddr_in *src_addr, *dst_addr; struct rds_iw_device *rds_iwdev_old; - struct rds_sock rs; struct rdma_cm_id *pcm_id; int rc; src_addr = (struct sockaddr_in *)&cm_id->route.addr.src_addr; dst_addr = (struct sockaddr_in *)&cm_id->route.addr.dst_addr; - rs.rs_bound_addr = src_addr->sin_addr.s_addr; - rs.rs_bound_port = src_addr->sin_port; - rs.rs_conn_addr = dst_addr->sin_addr.s_addr; - rs.rs_conn_port = dst_addr->sin_port; - - rc = rds_iw_get_device(&rs, &rds_iwdev_old, &pcm_id); + rc = rds_iw_get_device(src_addr, dst_addr, &rds_iwdev_old, &pcm_id); if (rc) rds_iw_remove_cm_id(rds_iwdev, cm_id); @@ -598,9 +594,17 @@ void *rds_iw_get_mr(struct scatterlist *sg, unsigned long nents, struct rds_iw_device *rds_iwdev; struct rds_iw_mr *ibmr = NULL; struct rdma_cm_id *cm_id; + struct sockaddr_in src = { + .sin_addr.s_addr = rs->rs_bound_addr, + .sin_port = rs->rs_bound_port, + }; + struct sockaddr_in dst = { + .sin_addr.s_addr = rs->rs_conn_addr, + .sin_port = rs->rs_conn_port, + }; int ret; - ret = rds_iw_get_device(rs, &rds_iwdev, &cm_id); + ret = rds_iw_get_device(&src, &dst, &rds_iwdev, &cm_id); if (ret || !cm_id) { ret = -ENODEV; goto out; diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c index b5cb2aa..35773ad 100644 --- a/net/rds/sysctl.c +++ b/net/rds/sysctl.c @@ -71,14 +71,14 @@ static struct ctl_table rds_sysctl_rds_table[] = { { .procname = "max_unacked_packets", .data = &rds_sysctl_max_unacked_packets, - .maxlen = sizeof(unsigned long), + .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_unacked_bytes", .data = &rds_sysctl_max_unacked_bytes, - .maxlen = sizeof(unsigned long), + .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 34b5490..4949f75 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -87,7 +87,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) { /* nothing remains on the queue */ if (copied && - (msg->msg_flags & MSG_PEEK || timeo == 0)) + (flags & MSG_PEEK || timeo == 0)) goto out; /* wait for a message to turn up */ diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 3a633de..a2abc44 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -227,6 +227,7 @@ static int tcf_em_validate(struct tcf_proto *tp, * to replay the request. */ module_put(em->ops->owner); + em->ops = NULL; err = -EAGAIN; } #endif diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 98532cf..bdaed31 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -812,10 +812,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (dev->flags & IFF_UP) dev_deactivate(dev); - if (new && new->ops->attach) { - new->ops->attach(new); - num_q = 0; - } + if (new && new->ops->attach) + goto skip; for (i = 0; i < num_q; i++) { struct netdev_queue *dev_queue = dev_ingress_queue(dev); @@ -831,12 +829,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, qdisc_destroy(old); } +skip: if (!ingress) { notify_and_destroy(net, skb, n, classid, dev->qdisc, new); if (new && !new->ops->attach) atomic_inc(&new->refcnt); dev->qdisc = new ? : &noop_qdisc; + + if (new && new->ops->attach) + new->ops->attach(new); } else { notify_and_destroy(net, skb, n, classid, old, new); } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index a4d5701..abc0922 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1151,6 +1151,7 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->c = new->c; asoc->peer.rwnd = new->peer.rwnd; asoc->peer.sack_needed = new->peer.sack_needed; + asoc->peer.auth_capable = new->peer.auth_capable; asoc->peer.i = new->peer.i; sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, asoc->peer.i.initial_tsn, GFP_ATOMIC); @@ -1234,7 +1235,6 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->peer.peer_hmacs = new->peer.peer_hmacs; new->peer.peer_hmacs = NULL; - sctp_auth_key_put(asoc->asoc_shared_key); sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC); } @@ -1626,6 +1626,8 @@ struct sctp_chunk *sctp_assoc_lookup_asconf_ack( * ack chunk whose serial number matches that of the request. */ list_for_each_entry(ack, &asoc->asconf_ack_list, transmitted_list) { + if (sctp_chunk_pending(ack)) + continue; if (ack->subh.addip_hdr->serial == serial) { sctp_chunk_hold(ack); return ack; diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 0e85291..fb7976a 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -862,8 +862,6 @@ int sctp_auth_set_key(struct sctp_endpoint *ep, list_add(&cur_key->key_list, sh_keys); cur_key->key = key; - sctp_auth_key_hold(key); - return 0; nomem: if (!replace) diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 4de12af..7e8a16c 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -140,18 +140,9 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) } else { /* Nothing to do. Next chunk in the packet, please. */ ch = (sctp_chunkhdr_t *) chunk->chunk_end; - /* Force chunk->skb->data to chunk->chunk_end. */ - skb_pull(chunk->skb, - chunk->chunk_end - chunk->skb->data); - - /* Verify that we have at least chunk headers - * worth of buffer left. - */ - if (skb_headlen(chunk->skb) < sizeof(sctp_chunkhdr_t)) { - sctp_chunk_free(chunk); - chunk = queue->in_progress = NULL; - } + skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data); + /* We are guaranteed to pull a SCTP header. */ } } @@ -187,24 +178,14 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - if (chunk->chunk_end < skb_tail_pointer(chunk->skb)) { + if (chunk->chunk_end + sizeof(sctp_chunkhdr_t) < + skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { - /* RFC 2960, Section 6.10 Bundling - * - * Partial chunks MUST NOT be placed in an SCTP packet. - * If the receiver detects a partial chunk, it MUST drop - * the chunk. - * - * Since the end of the chunk is past the end of our buffer - * (which contains the whole packet, we can freely discard - * the whole packet. - */ - sctp_chunk_free(chunk); - chunk = queue->in_progress = NULL; - - return NULL; + /* Discard inside state machine. */ + chunk->pdiscard = 1; + chunk->chunk_end = skb_tail_pointer(chunk->skb); } else { /* We are at the end of the packet, so mark the chunk * in case we need to send a SACK. diff --git a/net/sctp/output.c b/net/sctp/output.c index 0f4d15f..e39e6d5 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -401,12 +401,12 @@ int sctp_packet_transmit(struct sctp_packet *packet) sk = chunk->skb->sk; /* Allocate the new skb. */ - nskb = alloc_skb(packet->size + LL_MAX_HEADER, GFP_ATOMIC); + nskb = alloc_skb(packet->size + MAX_HEADER, GFP_ATOMIC); if (!nskb) goto nomem; /* Make sure the outbound skb has enough header room reserved. */ - skb_reserve(nskb, packet->overhead + LL_MAX_HEADER); + skb_reserve(nskb, packet->overhead + MAX_HEADER); /* Set the owning socket so that we know where to get the * destination IP address. @@ -599,7 +599,9 @@ out: return err; no_route: kfree_skb(nskb); - IP_INC_STATS_BH(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); + + if (asoc) + IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); /* FIXME: Returning the 'err' will effect all the associations * associated with a socket, although only one of the paths of the diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index fee5552..df06b13 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2608,7 +2608,10 @@ do_addr_param: addr_param = param.v + sizeof(sctp_addip_param_t); - af = sctp_get_af_specific(param_type2af(param.p->type)); + af = sctp_get_af_specific(param_type2af(addr_param->p.type)); + if (af == NULL) + break; + af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0); @@ -3110,50 +3113,63 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, return SCTP_ERROR_NO_ERROR; } -/* Verify the ASCONF packet before we process it. */ -int sctp_verify_asconf(const struct sctp_association *asoc, - struct sctp_paramhdr *param_hdr, void *chunk_end, - struct sctp_paramhdr **errp) { - sctp_addip_param_t *asconf_param; +/* Verify the ASCONF packet before we process it. */ +bool sctp_verify_asconf(const struct sctp_association *asoc, + struct sctp_chunk *chunk, bool addr_param_needed, + struct sctp_paramhdr **errp) +{ + sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) chunk->chunk_hdr; union sctp_params param; - int length, plen; + bool addr_param_seen = false; - param.v = (sctp_paramhdr_t *) param_hdr; - while (param.v <= chunk_end - sizeof(sctp_paramhdr_t)) { - length = ntohs(param.p->length); - *errp = param.p; - - if (param.v > chunk_end - length || - length < sizeof(sctp_paramhdr_t)) - return 0; + sctp_walk_params(param, addip, addip_hdr.params) { + size_t length = ntohs(param.p->length); + *errp = param.p; switch (param.p->type) { + case SCTP_PARAM_ERR_CAUSE: + break; + case SCTP_PARAM_IPV4_ADDRESS: + if (length != sizeof(sctp_ipv4addr_param_t)) + return false; + addr_param_seen = true; + break; + case SCTP_PARAM_IPV6_ADDRESS: + if (length != sizeof(sctp_ipv6addr_param_t)) + return false; + addr_param_seen = true; + break; case SCTP_PARAM_ADD_IP: case SCTP_PARAM_DEL_IP: case SCTP_PARAM_SET_PRIMARY: - asconf_param = (sctp_addip_param_t *)param.v; - plen = ntohs(asconf_param->param_hdr.length); - if (plen < sizeof(sctp_addip_param_t) + - sizeof(sctp_paramhdr_t)) - return 0; + /* In ASCONF chunks, these need to be first. */ + if (addr_param_needed && !addr_param_seen) + return false; + length = ntohs(param.addip->param_hdr.length); + if (length < sizeof(sctp_addip_param_t) + + sizeof(sctp_paramhdr_t)) + return false; break; case SCTP_PARAM_SUCCESS_REPORT: case SCTP_PARAM_ADAPTATION_LAYER_IND: if (length != sizeof(sctp_addip_param_t)) - return 0; - + return false; break; default: - break; + /* This is unkown to us, reject! */ + return false; } - - param.v += WORD_ROUND(length); } - if (param.v != chunk_end) - return 0; + /* Remaining sanity checks. */ + if (addr_param_needed && !addr_param_seen) + return false; + if (!addr_param_needed && addr_param_seen) + return false; + if (param.v != chunk->chunk_end) + return false; - return 1; + return true; } /* Process an incoming ASCONF chunk with the next expected serial no. and @@ -3162,16 +3178,17 @@ int sctp_verify_asconf(const struct sctp_association *asoc, struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, struct sctp_chunk *asconf) { + sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) asconf->chunk_hdr; + bool all_param_pass = true; + union sctp_params param; sctp_addiphdr_t *hdr; union sctp_addr_param *addr_param; sctp_addip_param_t *asconf_param; struct sctp_chunk *asconf_ack; - __be16 err_code; int length = 0; int chunk_len; __u32 serial; - int all_param_pass = 1; chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t); hdr = (sctp_addiphdr_t *)asconf->skb->data; @@ -3199,9 +3216,14 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, goto done; /* Process the TLVs contained within the ASCONF chunk. */ - while (chunk_len > 0) { + sctp_walk_params(param, addip, addip_hdr.params) { + /* Skip preceeding address parameters. */ + if (param.p->type == SCTP_PARAM_IPV4_ADDRESS || + param.p->type == SCTP_PARAM_IPV6_ADDRESS) + continue; + err_code = sctp_process_asconf_param(asoc, asconf, - asconf_param); + param.addip); /* ADDIP 4.1 A7) * If an error response is received for a TLV parameter, * all TLVs with no response before the failed TLV are @@ -3209,28 +3231,20 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, * the failed response are considered unsuccessful unless * a specific success indication is present for the parameter. */ - if (SCTP_ERROR_NO_ERROR != err_code) - all_param_pass = 0; - + if (err_code != SCTP_ERROR_NO_ERROR) + all_param_pass = false; if (!all_param_pass) - sctp_add_asconf_response(asconf_ack, - asconf_param->crr_id, err_code, - asconf_param); + sctp_add_asconf_response(asconf_ack, param.addip->crr_id, + err_code, param.addip); /* ADDIP 4.3 D11) When an endpoint receiving an ASCONF to add * an IP address sends an 'Out of Resource' in its response, it * MUST also fail any subsequent add or delete requests bundled * in the ASCONF. */ - if (SCTP_ERROR_RSRC_LOW == err_code) + if (err_code == SCTP_ERROR_RSRC_LOW) goto done; - - /* Move to the next ASCONF param. */ - length = ntohs(asconf_param->param_hdr.length); - asconf_param = (void *)asconf_param + length; - chunk_len -= length; } - done: asoc->peer.addip_serial++; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 5170a1f..3e287a3 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -170,6 +170,9 @@ sctp_chunk_length_valid(struct sctp_chunk *chunk, { __u16 chunk_length = ntohs(chunk->chunk_hdr->length); + /* Previously already marked? */ + if (unlikely(chunk->pdiscard)) + return 0; if (unlikely(chunk_length < required_length)) return 0; @@ -1775,9 +1778,22 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net, /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); - sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, - SCTP_STATE(SCTP_STATE_ESTABLISHED)); - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + if (sctp_state(asoc, SHUTDOWN_PENDING) && + (sctp_sstate(asoc->base.sk, CLOSING) || + sock_flag(asoc->base.sk, SOCK_DEAD))) { + /* if were currently in SHUTDOWN_PENDING, but the socket + * has been closed by user, don't transition to ESTABLISHED. + * Instead trigger SHUTDOWN bundled with COOKIE_ACK. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + return sctp_sf_do_9_2_start_shutdown(net, ep, asoc, + SCTP_ST_CHUNK(0), NULL, + commands); + } else { + sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, + SCTP_STATE(SCTP_STATE_ESTABLISHED)); + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + } return SCTP_DISPOSITION_CONSUME; nomem_ev: @@ -3578,9 +3594,7 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net, struct sctp_chunk *asconf_ack = NULL; struct sctp_paramhdr *err_param = NULL; sctp_addiphdr_t *hdr; - union sctp_addr_param *addr_param; __u32 serial; - int length; if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, @@ -3605,17 +3619,8 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net, hdr = (sctp_addiphdr_t *)chunk->skb->data; serial = ntohl(hdr->serial); - addr_param = (union sctp_addr_param *)hdr->params; - length = ntohs(addr_param->p.length); - if (length < sizeof(sctp_paramhdr_t)) - return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, - (void *)addr_param, commands); - /* Verify the ASCONF chunk before processing it. */ - if (!sctp_verify_asconf(asoc, - (sctp_paramhdr_t *)((void *)addr_param + length), - (void *)chunk->chunk_end, - &err_param)) + if (!sctp_verify_asconf(asoc, chunk, true, &err_param)) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, (void *)err_param, commands); @@ -3732,10 +3737,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net, rcvd_serial = ntohl(addip_hdr->serial); /* Verify the ASCONF-ACK chunk before processing it. */ - if (!sctp_verify_asconf(asoc, - (sctp_paramhdr_t *)addip_hdr->params, - (void *)asconf_ack->chunk_end, - &err_param)) + if (!sctp_verify_asconf(asoc, asconf_ack, false, &err_param)) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, (void *)err_param, commands); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 604a6ac..f940fdc 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1532,8 +1532,10 @@ static void sctp_close(struct sock *sk, long timeout) /* Supposedly, no process has access to the socket, but * the net layers still may. + * Also, sctp_destroy_sock() needs to be called with addr_wq_lock + * held and that should be grabbed before socket lock. */ - local_bh_disable(); + spin_lock_bh(&net->sctp.addr_wq_lock); bh_lock_sock(sk); /* Hold the sock, since sk_common_release() will put sock_put() @@ -1543,7 +1545,7 @@ static void sctp_close(struct sock *sk, long timeout) sk_common_release(sk); bh_unlock_sock(sk); - local_bh_enable(); + spin_unlock_bh(&net->sctp.addr_wq_lock); sock_put(sk); @@ -3511,6 +3513,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval, if ((val && sp->do_auto_asconf) || (!val && !sp->do_auto_asconf)) return 0; + spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock); if (val == 0 && sp->do_auto_asconf) { list_del(&sp->auto_asconf_list); sp->do_auto_asconf = 0; @@ -3519,6 +3522,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval, &sock_net(sk)->sctp.auto_asconf_splist); sp->do_auto_asconf = 1; } + spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock); return 0; } @@ -4009,18 +4013,28 @@ static int sctp_init_sock(struct sock *sk) local_bh_disable(); percpu_counter_inc(&sctp_sockets_allocated); sock_prot_inuse_add(net, sk->sk_prot, 1); + + /* Nothing can fail after this block, otherwise + * sctp_destroy_sock() will be called without addr_wq_lock held + */ if (net->sctp.default_auto_asconf) { + spin_lock(&sock_net(sk)->sctp.addr_wq_lock); list_add_tail(&sp->auto_asconf_list, &net->sctp.auto_asconf_splist); sp->do_auto_asconf = 1; - } else + spin_unlock(&sock_net(sk)->sctp.addr_wq_lock); + } else { sp->do_auto_asconf = 0; + } + local_bh_enable(); return 0; } -/* Cleanup any SCTP per socket resources. */ +/* Cleanup any SCTP per socket resources. Must be called with + * sock_net(sk)->sctp.addr_wq_lock held if sp->do_auto_asconf is true + */ static void sctp_destroy_sock(struct sock *sk) { struct sctp_sock *sp; @@ -6973,6 +6987,19 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->mc_list = NULL; } +static inline void sctp_copy_descendant(struct sock *sk_to, + const struct sock *sk_from) +{ + int ancestor_size = sizeof(struct inet_sock) + + sizeof(struct sctp_sock) - + offsetof(struct sctp_sock, auto_asconf_list); + + if (sk_from->sk_family == PF_INET6) + ancestor_size += sizeof(struct ipv6_pinfo); + + __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size); +} + /* Populate the fields of the newsk from the oldsk and migrate the assoc * and its messages to the newsk. */ @@ -6987,7 +7014,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sk_buff *skb, *tmp; struct sctp_ulpevent *event; struct sctp_bind_hashbucket *head; - struct list_head tmplist; /* Migrate socket buffer sizes and all the socket level options to the * new socket. @@ -6995,12 +7021,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, newsk->sk_sndbuf = oldsk->sk_sndbuf; newsk->sk_rcvbuf = oldsk->sk_rcvbuf; /* Brute force copy old sctp opt. */ - if (oldsp->do_auto_asconf) { - memcpy(&tmplist, &newsp->auto_asconf_list, sizeof(tmplist)); - inet_sk_copy_descendant(newsk, oldsk); - memcpy(&newsp->auto_asconf_list, &tmplist, sizeof(tmplist)); - } else - inet_sk_copy_descendant(newsk, oldsk); + sctp_copy_descendant(newsk, oldsk); /* Restore the ep value that was overwritten with the above structure * copy. diff --git a/net/socket.c b/net/socket.c index a19ae19..b72fc13 100644 --- a/net/socket.c +++ b/net/socket.c @@ -886,9 +886,6 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, struct sock_iocb *siocb) { - if (!is_sync_kiocb(iocb)) - BUG(); - siocb->kiocb = iocb; iocb->private = siocb; return siocb; @@ -2010,14 +2007,12 @@ static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg, int err, ctl_len, total_len; err = -EFAULT; - if (MSG_CMSG_COMPAT & flags) { - if (get_compat_msghdr(msg_sys, msg_compat)) - return -EFAULT; - } else { + if (MSG_CMSG_COMPAT & flags) + err = get_compat_msghdr(msg_sys, msg_compat); + else err = copy_msghdr_from_user(msg_sys, msg); - if (err) - return err; - } + if (err) + return err; if (msg_sys->msg_iovlen > UIO_FASTIOV) { err = -EMSGSIZE; @@ -2222,14 +2217,12 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, struct sockaddr __user *uaddr; int __user *uaddr_len; - if (MSG_CMSG_COMPAT & flags) { - if (get_compat_msghdr(msg_sys, msg_compat)) - return -EFAULT; - } else { + if (MSG_CMSG_COMPAT & flags) + err = get_compat_msghdr(msg_sys, msg_compat); + else err = copy_msghdr_from_user(msg_sys, msg); - if (err) - return err; - } + if (err) + return err; if (msg_sys->msg_iovlen > UIO_FASTIOV) { err = -EMSGSIZE; diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 1ec19f6..eeeba5a 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -793,20 +793,26 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, { u32 value_follows; int err; + struct page *scratch; + + scratch = alloc_page(GFP_KERNEL); + if (!scratch) + return -ENOMEM; + xdr_set_scratch_buffer(xdr, page_address(scratch), PAGE_SIZE); /* res->status */ err = gssx_dec_status(xdr, &res->status); if (err) - return err; + goto out_free; /* res->context_handle */ err = gssx_dec_bool(xdr, &value_follows); if (err) - return err; + goto out_free; if (value_follows) { err = gssx_dec_ctx(xdr, res->context_handle); if (err) - return err; + goto out_free; } else { res->context_handle = NULL; } @@ -814,11 +820,11 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, /* res->output_token */ err = gssx_dec_bool(xdr, &value_follows); if (err) - return err; + goto out_free; if (value_follows) { err = gssx_dec_buffer(xdr, res->output_token); if (err) - return err; + goto out_free; } else { res->output_token = NULL; } @@ -826,14 +832,17 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, /* res->delegated_cred_handle */ err = gssx_dec_bool(xdr, &value_follows); if (err) - return err; + goto out_free; if (value_follows) { /* we do not support upcall servers sending this data. */ - return -EINVAL; + err = -EINVAL; + goto out_free; } /* res->options */ err = gssx_dec_option_array(xdr, &res->options); +out_free: + __free_page(scratch); return err; } diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index e860d4f..ab21968 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -60,7 +60,7 @@ static void xprt_free_allocation(struct rpc_rqst *req) dprintk("RPC: free allocations for req= %p\n", req); WARN_ON_ONCE(test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state)); - xbufp = &req->rq_private_buf; + xbufp = &req->rq_rcv_buf; free_page((unsigned long)xbufp->head[0].iov_base); xbufp = &req->rq_snd_buf; free_page((unsigned long)xbufp->head[0].iov_base); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index ae333c1..0adc66c 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -920,7 +920,7 @@ static unsigned int cache_poll(struct file *filp, poll_table *wait, poll_wait(filp, &queue_wait, wait); /* alway allow write */ - mask = POLL_OUT | POLLWRNORM; + mask = POLLOUT | POLLWRNORM; if (!rp) return mask; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 3ea5cda..5ff8b87 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -533,6 +533,8 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) if (args->flags & RPC_CLNT_CREATE_AUTOBIND) clnt->cl_autobind = 1; + if (args->flags & RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT) + clnt->cl_noretranstimeo = 1; if (args->flags & RPC_CLNT_CREATE_DISCRTRY) clnt->cl_discrtry = 1; if (!(args->flags & RPC_CLNT_CREATE_QUIET)) @@ -571,6 +573,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, /* Turn off autobind on clones */ new->cl_autobind = 0; new->cl_softrtry = clnt->cl_softrtry; + new->cl_noretranstimeo = clnt->cl_noretranstimeo; new->cl_discrtry = clnt->cl_discrtry; new->cl_chatty = clnt->cl_chatty; return new; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index d06cb87..5e8fe77 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -685,6 +685,7 @@ static struct svc_xprt_class svc_udp_class = { .xcl_owner = THIS_MODULE, .xcl_ops = &svc_udp_ops, .xcl_max_payload = RPCSVC_MAXPAYLOAD_UDP, + .xcl_ident = XPRT_TRANSPORT_UDP, }; static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) @@ -1279,6 +1280,7 @@ static struct svc_xprt_class svc_tcp_class = { .xcl_owner = THIS_MODULE, .xcl_ops = &svc_tcp_ops, .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, + .xcl_ident = XPRT_TRANSPORT_TCP, }; void svc_init_xprt_sock(void) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 7d4df99..03ac884 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1316,7 +1316,7 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args) } } spin_unlock(&xprt_list_lock); - printk(KERN_ERR "RPC: transport (%d) not supported\n", args->ident); + dprintk("RPC: transport (%d) not supported\n", args->ident); return ERR_PTR(-EIO); found: diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 62e4f9b..ed36cb5 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -89,6 +89,7 @@ struct svc_xprt_class svc_rdma_class = { .xcl_owner = THIS_MODULE, .xcl_ops = &svc_rdma_ops, .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, + .xcl_ident = XPRT_TRANSPORT_RDMA, }; struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0addefc..41c2f9d 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -842,6 +842,8 @@ static void xs_error_report(struct sock *sk) dprintk("RPC: xs_error_report client %p, error=%d...\n", xprt, -err); trace_rpc_socket_error(xprt, sk->sk_socket, err); + if (test_bit(XPRT_CONNECTION_REUSE, &xprt->state)) + goto out; xprt_wake_pending_tasks(xprt, err); out: read_unlock_bh(&sk->sk_callback_lock); @@ -2251,7 +2253,9 @@ static void xs_tcp_setup_socket(struct work_struct *work) abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); /* "close" the socket, preserving the local port */ + set_bit(XPRT_CONNECTION_REUSE, &xprt->state); xs_tcp_reuse_connection(transport); + clear_bit(XPRT_CONNECTION_REUSE, &xprt->state); if (abort_and_exit) goto out_eagain; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 94404f1..4757f1c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1893,6 +1893,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, unix_state_unlock(sk); timeo = freezable_schedule_timeout(timeo); unix_state_lock(sk); + + if (sock_flag(sk, SOCK_DEAD)) + break; + clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); } @@ -1957,6 +1961,10 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, struct sk_buff *skb, *last; unix_state_lock(sk); + if (sock_flag(sk, SOCK_DEAD)) { + err = -ECONNRESET; + goto unlock; + } last = skb = skb_peek(&sk->sk_receive_queue); again: if (skb == NULL) { diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 78559b5..27157a78 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -516,7 +516,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, { struct ieee80211_sta_ht_cap *ht_cap; struct ieee80211_sta_vht_cap *vht_cap; - u32 width, control_freq; + u32 width, control_freq, cap; if (WARN_ON(!cfg80211_chandef_valid(chandef))) return false; @@ -554,7 +554,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, return false; break; case NL80211_CHAN_WIDTH_80P80: - if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)) + cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; + if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) return false; case NL80211_CHAN_WIDTH_80: if (!vht_cap->vht_supported) @@ -565,7 +566,9 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, case NL80211_CHAN_WIDTH_160: if (!vht_cap->vht_supported) return false; - if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ)) + cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; + if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && + cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) return false; prohibited_flags |= IEEE80211_CHAN_NO_160MHZ; width = 160; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4fe2e6e..c260243 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1450,18 +1450,17 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev, } CMD(start_p2p_device, START_P2P_DEVICE); CMD(set_mcast_rate, SET_MCAST_RATE); +#ifdef CONFIG_NL80211_TESTMODE + CMD(testmode_cmd, TESTMODE); +#endif if (state->split) { CMD(crit_proto_start, CRIT_PROTOCOL_START); CMD(crit_proto_stop, CRIT_PROTOCOL_STOP); if (dev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH) CMD(channel_switch, CHANNEL_SWITCH); + CMD(set_qos_map, SET_QOS_MAP); } - CMD(set_qos_map, SET_QOS_MAP); - -#ifdef CONFIG_NL80211_TESTMODE - CMD(testmode_cmd, TESTMODE); -#endif - + /* add into the if now */ #undef CMD if (dev->ops->connect || dev->ops->auth) { @@ -2698,6 +2697,9 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->get_key) return -EOPNOTSUPP; + if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) + return -ENOENT; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -2717,10 +2719,6 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr)) goto nla_put_failure; - if (pairwise && mac_addr && - !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) - return -ENOENT; - err = rdev_get_key(rdev, dev, key_idx, pairwise, mac_addr, &cookie, get_key_callback); @@ -2891,7 +2889,7 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) wdev_lock(dev->ieee80211_ptr); err = nl80211_key_allowed(dev->ieee80211_ptr); - if (key.type == NL80211_KEYTYPE_PAIRWISE && mac_addr && + if (key.type == NL80211_KEYTYPE_GROUP && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) err = -ENOENT; @@ -4192,6 +4190,16 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (parse_station_flags(info, dev->ieee80211_ptr->iftype, ¶ms)) return -EINVAL; + /* HT/VHT requires QoS, but if we don't have that just ignore HT/VHT + * as userspace might just pass through the capabilities from the IEs + * directly, rather than enforcing this restriction and returning an + * error in this case. + */ + if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) { + params.ht_capa = NULL; + params.vht_capa = NULL; + } + /* When you run into this, adjust the code below for the new flag */ BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7); @@ -6797,6 +6805,9 @@ void __cfg80211_send_event_skb(struct sk_buff *skb, gfp_t gfp) struct nlattr *data = ((void **)skb->cb)[2]; enum nl80211_multicast_groups mcgrp = NL80211_MCGRP_TESTMODE; + /* clear CB data for netlink core to own from now on */ + memset(skb->cb, 0, sizeof(skb->cb)); + nla_nest_end(skb, data); genlmsg_end(skb, hdr); @@ -9076,6 +9087,9 @@ int cfg80211_vendor_cmd_reply(struct sk_buff *skb) void *hdr = ((void **)skb->cb)[1]; struct nlattr *data = ((void **)skb->cb)[2]; + /* clear CB data for netlink core to own from now on */ + memset(skb->cb, 0, sizeof(skb->cb)); + if (WARN_ON(!rdev->cur_cmd_info)) { kfree_skb(skb); return -EINVAL; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 338794e..04d5305 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1547,7 +1547,7 @@ static enum reg_request_treatment reg_process_hint_driver(struct wiphy *wiphy, struct regulatory_request *driver_request) { - const struct ieee80211_regdomain *regd; + const struct ieee80211_regdomain *regd, *tmp; enum reg_request_treatment treatment; treatment = __reg_process_hint_driver(driver_request); @@ -1566,7 +1566,10 @@ reg_process_hint_driver(struct wiphy *wiphy, kfree(driver_request); return REG_REQ_IGNORE; } + + tmp = get_wiphy_regdom(wiphy); rcu_assign_pointer(wiphy->regd, regd); + rcu_free_regdom(tmp); } @@ -1625,11 +1628,8 @@ __reg_process_hint_country_ie(struct wiphy *wiphy, return REG_REQ_IGNORE; return REG_REQ_ALREADY_SET; } - /* - * Two consecutive Country IE hints on the same wiphy. - * This should be picked up early by the driver/stack - */ - if (WARN_ON(regdom_changes(country_ie_request->alpha2))) + + if (regdom_changes(country_ie_request->alpha2)) return REG_REQ_OK; return REG_REQ_ALREADY_SET; } diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 5eaeed5..815a3b7 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2068,7 +2068,8 @@ TRACE_EVENT(cfg80211_michael_mic_failure, MAC_ASSIGN(addr, addr); __entry->key_type = key_type; __entry->key_id = key_id; - memcpy(__entry->tsc, tsc, 6); + if (tsc) + memcpy(__entry->tsc, tsc, 6); ), TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT ", key type: %d, key id: %d, tsc: %pm", NETDEV_PR_ARG, MAC_PR_ARG(addr), __entry->key_type, diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 5661a54..ae1fe6f 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -1331,6 +1331,8 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) memcpy(bssid, wdev->current_bss->pub.bssid, ETH_ALEN); wdev_unlock(wdev); + memset(&sinfo, 0, sizeof(sinfo)); + if (rdev_get_station(rdev, dev, bssid, &sinfo)) return NULL; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 1d5c7bf..59cf325 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -41,6 +41,11 @@ static struct dst_entry *xfrm_policy_sk_bundles; +struct xfrm_flo { + struct dst_entry *dst_orig; + u8 flags; +}; + static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO] __read_mostly; @@ -1889,13 +1894,14 @@ static int xdst_queue_output(struct sk_buff *skb) } static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, - struct dst_entry *dst, + struct xfrm_flo *xflo, const struct flowi *fl, int num_xfrms, u16 family) { int err; struct net_device *dev; + struct dst_entry *dst; struct dst_entry *dst1; struct xfrm_dst *xdst; @@ -1903,9 +1909,12 @@ static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, if (IS_ERR(xdst)) return xdst; - if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0) + if (!(xflo->flags & XFRM_LOOKUP_QUEUE) || + net->xfrm.sysctl_larval_drop || + num_xfrms <= 0) return xdst; + dst = xflo->dst_orig; dst1 = &xdst->u.dst; dst_hold(dst); xdst->route = dst; @@ -1947,7 +1956,7 @@ static struct flow_cache_object * xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct flow_cache_object *oldflo, void *ctx) { - struct dst_entry *dst_orig = (struct dst_entry *)ctx; + struct xfrm_flo *xflo = (struct xfrm_flo *)ctx; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; struct xfrm_dst *xdst, *new_xdst; int num_pols = 0, num_xfrms = 0, i, err, pol_dead; @@ -1988,7 +1997,8 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, goto make_dummy_bundle; } - new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, dst_orig); + new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, + xflo->dst_orig); if (IS_ERR(new_xdst)) { err = PTR_ERR(new_xdst); if (err != -EAGAIN) @@ -2022,7 +2032,7 @@ make_dummy_bundle: /* We found policies, but there's no bundles to instantiate: * either because the policy blocks, has no transformations or * we could not build template (no xfrm_states).*/ - xdst = xfrm_create_dummy_bundle(net, dst_orig, fl, num_xfrms, family); + xdst = xfrm_create_dummy_bundle(net, xflo, fl, num_xfrms, family); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); return ERR_CAST(xdst); @@ -2121,13 +2131,18 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, } if (xdst == NULL) { + struct xfrm_flo xflo; + + xflo.dst_orig = dst_orig; + xflo.flags = flags; + /* To accelerate a bit... */ if ((dst_orig->flags & DST_NOXFRM) || !net->xfrm.policy_count[XFRM_POLICY_OUT]) goto nopol; flo = flow_cache_lookup(net, fl, family, dir, - xfrm_bundle_lookup, dst_orig); + xfrm_bundle_lookup, &xflo); if (flo == NULL) goto nopol; if (IS_ERR(flo)) { @@ -2155,7 +2170,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, xfrm_pols_put(pols, drop_pols); XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); - return make_blackhole(net, family, dst_orig); + return ERR_PTR(-EREMOTE); } err = -EAGAIN; @@ -2212,6 +2227,23 @@ dropdst: } EXPORT_SYMBOL(xfrm_lookup); +/* Callers of xfrm_lookup_route() must ensure a call to dst_output(). + * Otherwise we may send out blackholed packets. + */ +struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, + struct sock *sk, int flags) +{ + struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, + flags | XFRM_LOOKUP_QUEUE); + + if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE) + return make_blackhole(net, dst_orig->ops->family, dst_orig); + + return dst; +} +EXPORT_SYMBOL(xfrm_lookup_route); + static inline int xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) { @@ -2477,7 +2509,7 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) skb_dst_force(skb); - dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, 0); + dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) { res = 0; dst = NULL; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index b10d04f..3bea4dd 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -176,9 +176,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, attrs[XFRMA_ALG_AEAD] || attrs[XFRMA_ALG_CRYPT] || attrs[XFRMA_ALG_COMP] || - attrs[XFRMA_TFCPAD] || - (ntohl(p->id.spi) >= 0x10000)) - + attrs[XFRMA_TFCPAD]) goto out; break; @@ -206,7 +204,8 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, attrs[XFRMA_ALG_AUTH] || attrs[XFRMA_ALG_AUTH_TRUNC] || attrs[XFRMA_ALG_CRYPT] || - attrs[XFRMA_TFCPAD]) + attrs[XFRMA_TFCPAD] || + (ntohl(p->id.spi) >= 0x10000)) goto out; break; diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index db1512a..f53542b 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -545,7 +545,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop, { int i, j; struct menu *submenu[8], *menu, *location = NULL; - struct jump_key *jump; + struct jump_key *jump = NULL; str_printf(r, _("Prompt: %s\n"), _(prop->text)); menu = prop->menu->parent; @@ -583,7 +583,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop, str_printf(r, _(" Location:\n")); for (j = 4; --i >= 0; j += 2) { menu = submenu[i]; - if (head && location && menu == location) + if (jump && menu == location) jump->offset = strlen(r->s); str_printf(r, "%*c-> %s", j, ' ', _(menu_get_prompt(menu))); diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl index 3133172..9969fee 100644 --- a/scripts/kconfig/streamline_config.pl +++ b/scripts/kconfig/streamline_config.pl @@ -137,7 +137,7 @@ my $ksource = ($ARGV[0] ? $ARGV[0] : '.'); my $kconfig = $ARGV[1]; my $lsmod_file = $ENV{'LSMOD'}; -my @makefiles = `find $ksource -name Makefile 2>/dev/null`; +my @makefiles = `find $ksource -name Makefile -or -name Kbuild 2>/dev/null`; chomp @makefiles; my %depends; diff --git a/scripts/kernel-doc b/scripts/kernel-doc index da058da..2438cc3 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1753,7 +1753,7 @@ sub dump_struct($$) { # strip kmemcheck_bitfield_{begin,end}.*; $members =~ s/kmemcheck_bitfield_.*?;//gos; # strip attributes - $members =~ s/__aligned\s*\(.+\)//gos; + $members =~ s/__aligned\s*\([^;]*\)//gos; create_parameterlist($members, ';', $file); check_sections($file, $declaration_name, "struct", $sectcheck, $struct_actual, $nested); diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 397b6b8..e28f38e 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -262,7 +262,6 @@ if ($arch eq "x86_64") { # force flags for this arch $ld .= " -m shlelf_linux"; $objcopy .= " -O elf32-sh-linux"; - $cc .= " -m32"; } elsif ($arch eq "powerpc") { $local_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)"; diff --git a/security/commoncap.c b/security/commoncap.c index b9d613e..963dc59 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -421,6 +421,9 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data cpu_caps->inheritable.cap[i] = le32_to_cpu(caps.data[i].inheritable); } + cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + return 0; } diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index 3c5cbb9..048550a 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include "evm.h" @@ -269,6 +270,24 @@ static int evm_protect_xattr(struct dentry *dentry, const char *xattr_name, goto out; } evm_status = evm_verify_current_integrity(dentry); + if (evm_status == INTEGRITY_NOXATTRS) { + struct integrity_iint_cache *iint; + + iint = integrity_iint_find(dentry->d_inode); + if (iint && (iint->flags & IMA_NEW_FILE)) + return 0; + + /* exception for pseudo filesystems */ + if (dentry->d_inode->i_sb->s_magic == TMPFS_MAGIC + || dentry->d_inode->i_sb->s_magic == SYSFS_MAGIC) + return 0; + + integrity_audit_msg(AUDIT_INTEGRITY_METADATA, + dentry->d_inode, dentry->d_name.name, + "update_metadata", + integrity_status_msg[evm_status], + -EPERM, 0); + } out: if (evm_status != INTEGRITY_PASS) integrity_audit_msg(AUDIT_INTEGRITY_METADATA, dentry->d_inode, @@ -296,9 +315,12 @@ int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name, { const struct evm_ima_xattr_data *xattr_data = xattr_value; - if ((strcmp(xattr_name, XATTR_NAME_EVM) == 0) - && (xattr_data->type == EVM_XATTR_HMAC)) - return -EPERM; + if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) { + if (!xattr_value_len) + return -EINVAL; + if (xattr_data->type != EVM_IMA_XATTR_DIGSIG) + return -EPERM; + } return evm_protect_xattr(dentry, xattr_name, xattr_value, xattr_value_len); } diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index f79fa8b..5cb7de9 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -106,7 +106,7 @@ void ima_add_violation(struct file *file, const unsigned char *filename, const char *op, const char *cause); int ima_init_crypto(void); void ima_putc(struct seq_file *m, void *data, int datalen); -void ima_print_digest(struct seq_file *m, u8 *digest, int size); +void ima_print_digest(struct seq_file *m, u8 *digest, u32 size); struct ima_template_desc *ima_template_desc_current(void); int ima_init_template(void); diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 734e946..6df1b25 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -194,8 +194,11 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint, goto out; cause = "missing-hash"; - status = - (inode->i_size == 0) ? INTEGRITY_PASS : INTEGRITY_NOLABEL; + status = INTEGRITY_NOLABEL; + if (inode->i_size == 0) { + iint->flags |= IMA_NEW_FILE; + status = INTEGRITY_PASS; + } goto out; } diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c index 468a3ba..35f3c90 100644 --- a/security/integrity/ima/ima_fs.c +++ b/security/integrity/ima/ima_fs.c @@ -186,9 +186,9 @@ static const struct file_operations ima_measurements_ops = { .release = seq_release, }; -void ima_print_digest(struct seq_file *m, u8 *digest, int size) +void ima_print_digest(struct seq_file *m, u8 *digest, u32 size) { - int i; + u32 i; for (i = 0; i < size; i++) seq_printf(m, "%02x", *(digest + i)); diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 76d8aad..9f70efd 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -131,11 +131,13 @@ static void ima_check_last_writer(struct integrity_iint_cache *iint, return; mutex_lock(&inode->i_mutex); - if (atomic_read(&inode->i_writecount) == 1 && - iint->version != inode->i_version) { - iint->flags &= ~IMA_DONE_MASK; - if (iint->flags & IMA_APPRAISE) - ima_update_xattr(iint, file); + if (atomic_read(&inode->i_writecount) == 1) { + if ((iint->version != inode->i_version) || + (iint->flags & IMA_NEW_FILE)) { + iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE); + if (iint->flags & IMA_APPRAISE) + ima_update_xattr(iint, file); + } } mutex_unlock(&inode->i_mutex); } diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 085c496..9d8e420 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -27,6 +27,8 @@ #define IMA_UID 0x0008 #define IMA_FOWNER 0x0010 #define IMA_FSUUID 0x0020 +#define IMA_INMASK 0x0040 +#define IMA_EUID 0x0080 #define UNKNOWN 0 #define MEASURE 0x0001 /* same as IMA_MEASURE */ @@ -171,6 +173,9 @@ static bool ima_match_rules(struct ima_rule_entry *rule, return false; if ((rule->flags & IMA_MASK) && rule->mask != mask) return false; + if ((rule->flags & IMA_INMASK) && + (!(rule->mask & mask) && func != POST_SETATTR)) + return false; if ((rule->flags & IMA_FSMAGIC) && rule->fsmagic != inode->i_sb->s_magic) return false; @@ -179,6 +184,16 @@ static bool ima_match_rules(struct ima_rule_entry *rule, return false; if ((rule->flags & IMA_UID) && !uid_eq(rule->uid, cred->uid)) return false; + if (rule->flags & IMA_EUID) { + if (has_capability_noaudit(current, CAP_SETUID)) { + if (!uid_eq(rule->uid, cred->euid) + && !uid_eq(rule->uid, cred->suid) + && !uid_eq(rule->uid, cred->uid)) + return false; + } else if (!uid_eq(rule->uid, cred->euid)) + return false; + } + if ((rule->flags & IMA_FOWNER) && !uid_eq(rule->fowner, inode->i_uid)) return false; for (i = 0; i < MAX_LSM_RULES; i++) { @@ -350,7 +365,8 @@ enum { Opt_audit, Opt_obj_user, Opt_obj_role, Opt_obj_type, Opt_subj_user, Opt_subj_role, Opt_subj_type, - Opt_func, Opt_mask, Opt_fsmagic, Opt_uid, Opt_fowner, + Opt_func, Opt_mask, Opt_fsmagic, + Opt_uid, Opt_euid, Opt_fowner, Opt_appraise_type, Opt_fsuuid, Opt_permit_directio }; @@ -371,6 +387,7 @@ static match_table_t policy_tokens = { {Opt_fsmagic, "fsmagic=%s"}, {Opt_fsuuid, "fsuuid=%s"}, {Opt_uid, "uid=%s"}, + {Opt_euid, "euid=%s"}, {Opt_fowner, "fowner=%s"}, {Opt_appraise_type, "appraise_type=%s"}, {Opt_permit_directio, "permit_directio"}, @@ -412,6 +429,7 @@ static void ima_log_string(struct audit_buffer *ab, char *key, char *value) static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) { struct audit_buffer *ab; + char *from; char *p; int result = 0; @@ -500,18 +518,23 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) if (entry->mask) result = -EINVAL; - if ((strcmp(args[0].from, "MAY_EXEC")) == 0) + from = args[0].from; + if (*from == '^') + from++; + + if ((strcmp(from, "MAY_EXEC")) == 0) entry->mask = MAY_EXEC; - else if (strcmp(args[0].from, "MAY_WRITE") == 0) + else if (strcmp(from, "MAY_WRITE") == 0) entry->mask = MAY_WRITE; - else if (strcmp(args[0].from, "MAY_READ") == 0) + else if (strcmp(from, "MAY_READ") == 0) entry->mask = MAY_READ; - else if (strcmp(args[0].from, "MAY_APPEND") == 0) + else if (strcmp(from, "MAY_APPEND") == 0) entry->mask = MAY_APPEND; else result = -EINVAL; if (!result) - entry->flags |= IMA_MASK; + entry->flags |= (*args[0].from == '^') + ? IMA_INMASK : IMA_MASK; break; case Opt_fsmagic: ima_log_string(ab, "fsmagic", args[0].from); @@ -542,6 +565,9 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) break; case Opt_uid: ima_log_string(ab, "uid", args[0].from); + case Opt_euid: + if (token == Opt_euid) + ima_log_string(ab, "euid", args[0].from); if (uid_valid(entry->uid)) { result = -EINVAL; @@ -550,11 +576,14 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) result = strict_strtoul(args[0].from, 10, &lnum); if (!result) { - entry->uid = make_kuid(current_user_ns(), (uid_t)lnum); - if (!uid_valid(entry->uid) || (((uid_t)lnum) != lnum)) + entry->uid = make_kuid(current_user_ns(), + (uid_t) lnum); + if (!uid_valid(entry->uid) || + (uid_t)lnum != lnum) result = -EINVAL; else - entry->flags |= IMA_UID; + entry->flags |= (token == Opt_uid) + ? IMA_UID : IMA_EUID; } break; case Opt_fowner: diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c index e8592e7..dcf77b7 100644 --- a/security/integrity/ima/ima_template_lib.c +++ b/security/integrity/ima/ima_template_lib.c @@ -79,7 +79,8 @@ static void ima_show_template_data_ascii(struct seq_file *m, enum data_formats datafmt, struct ima_field_data *field_data) { - u8 *buf_ptr = field_data->data, buflen = field_data->len; + u8 *buf_ptr = field_data->data; + u32 buflen = field_data->len; switch (datafmt) { case DATA_FMT_DIGEST_WITH_ALGO: diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index 33c0a70..2f8715d 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -31,6 +31,7 @@ #define IMA_DIGSIG 0x01000000 #define IMA_DIGSIG_REQUIRED 0x02000000 #define IMA_PERMIT_DIRECTIO 0x04000000 +#define IMA_NEW_FILE 0x08000000 #define IMA_DO_MASK (IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \ IMA_APPRAISE_SUBMASK) diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c index 9e1e005..c4c8df4 100644 --- a/security/keys/encrypted-keys/encrypted.c +++ b/security/keys/encrypted-keys/encrypted.c @@ -1018,10 +1018,13 @@ static int __init init_encrypted(void) ret = encrypted_shash_alloc(); if (ret < 0) return ret; + ret = aes_get_sizes(); + if (ret < 0) + goto out; ret = register_key_type(&key_type_encrypted); if (ret < 0) goto out; - return aes_get_sizes(); + return 0; out: encrypted_shash_release(); return ret; diff --git a/security/keys/gc.c b/security/keys/gc.c index d3222b6..009d937 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -157,12 +157,12 @@ static noinline void key_gc_unused_keys(struct list_head *keys) if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) atomic_dec(&key->user->nikeys); - key_user_put(key->user); - /* now throw away the key memory */ if (key->type->destroy) key->type->destroy(key); + key_user_put(key->user); + kfree(key->description); #ifdef KEY_DEBUGGING diff --git a/security/keys/keyring.c b/security/keys/keyring.c index 2fb2576..04d0d7c 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -1151,9 +1151,11 @@ void __key_link_end(struct key *keyring, if (index_key->type == &key_type_keyring) up_write(&keyring_serialise_link_sem); - if (edit && !edit->dead_leaf) { - key_payload_reserve(keyring, - keyring->datalen - KEYQUOTA_LINK_BYTES); + if (edit) { + if (!edit->dead_leaf) { + key_payload_reserve(keyring, + keyring->datalen - KEYQUOTA_LINK_BYTES); + } assoc_array_cancel_edit(edit); } up_write(&keyring->sem); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index e294b86..47b5c69 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -470,6 +470,7 @@ next_inode: list_entry(sbsec->isec_head.next, struct inode_security_struct, list); struct inode *inode = isec->inode; + list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); inode = igrab(inode); if (inode) { @@ -478,7 +479,6 @@ next_inode: iput(inode); } spin_lock(&sbsec->isec_lock); - list_del_init(&isec->list); goto next_inode; } spin_unlock(&sbsec->isec_lock); diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index d60c0ee..fc68bf6 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -152,7 +152,7 @@ static ssize_t sel_write_enforce(struct file *file, const char __user *buf, goto out; /* No partial writes. */ - length = EINVAL; + length = -EINVAL; if (*ppos != 0) goto out; @@ -1200,7 +1200,7 @@ static void sel_remove_entries(struct dentry *de) spin_lock(&de->d_lock); node = de->d_subdirs.next; while (node != &de->d_subdirs) { - struct dentry *d = list_entry(node, struct dentry, d_u.d_child); + struct dentry *d = list_entry(node, struct dentry, d_child); spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); list_del_init(node); @@ -1674,12 +1674,12 @@ static void sel_remove_classes(void) list_for_each(class_node, &class_dir->d_subdirs) { struct dentry *class_subdir = list_entry(class_node, - struct dentry, d_u.d_child); + struct dentry, d_child); struct list_head *class_subdir_node; list_for_each(class_subdir_node, &class_subdir->d_subdirs) { struct dentry *d = list_entry(class_subdir_node, - struct dentry, d_u.d_child); + struct dentry, d_child); if (d->d_inode) if (d->d_inode->i_mode & S_IFDIR) diff --git a/sound/core/control.c b/sound/core/control.c index 98a29b2..f2082a3 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1168,6 +1168,10 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, if (info->count < 1) return -EINVAL; + if (!*info->id.name) + return -EINVAL; + if (strnlen(info->id.name, sizeof(info->id.name)) >= sizeof(info->id.name)) + return -EINVAL; access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE : (info->access & (SNDRV_CTL_ELEM_ACCESS_READWRITE| SNDRV_CTL_ELEM_ACCESS_INACTIVE| diff --git a/sound/core/info.c b/sound/core/info.c index e79baa1..08070e1 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -679,7 +679,7 @@ int snd_info_card_free(struct snd_card *card) * snd_info_get_line - read one line from the procfs buffer * @buffer: the procfs buffer * @line: the buffer to store - * @len: the max. buffer size - 1 + * @len: the max. buffer size * * Reads one line from the buffer and stores the string. * @@ -699,7 +699,7 @@ int snd_info_get_line(struct snd_info_buffer *buffer, char *line, int len) buffer->stop = 1; if (c == '\n') break; - if (len) { + if (len > 1) { len--; *line++ = c; } diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index af49721..c4ac3c1 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -206,6 +206,8 @@ static int snd_pcm_status_user_compat(struct snd_pcm_substream *substream, if (err < 0) return err; + if (clear_user(src, sizeof(*src))) + return -EFAULT; if (put_user(status.state, &src->state) || compat_put_timespec(&status.trigger_tstamp, &src->trigger_tstamp) || compat_put_timespec(&status.tstamp, &src->tstamp) || diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index a210467..e1ef106 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1783,14 +1783,16 @@ static int snd_pcm_lib_ioctl_fifo_size(struct snd_pcm_substream *substream, { struct snd_pcm_hw_params *params = arg; snd_pcm_format_t format; - int channels, width; + int channels; + ssize_t frame_size; params->fifo_size = substream->runtime->hw.fifo_size; if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_FIFO_IN_FRAMES)) { format = params_format(params); channels = params_channels(params); - width = snd_pcm_format_physical_width(format); - params->fifo_size /= width * channels; + frame_size = snd_pcm_format_size(format, channels); + if (frame_size > 0) + params->fifo_size /= (unsigned)frame_size; } return 0; } diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 01a5e05..ee24057 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -1404,6 +1404,8 @@ static int snd_pcm_do_drain_init(struct snd_pcm_substream *substream, int state) if (! snd_pcm_playback_empty(substream)) { snd_pcm_do_start(substream, SNDRV_PCM_STATE_DRAINING); snd_pcm_post_start(substream, SNDRV_PCM_STATE_DRAINING); + } else { + runtime->status->state = SNDRV_PCM_STATE_SETUP; } break; case SNDRV_PCM_STATE_RUNNING: @@ -3189,7 +3191,7 @@ static const struct vm_operations_struct snd_pcm_vm_ops_data_fault = { #ifndef ARCH_HAS_DMA_MMAP_COHERENT /* This should be defined / handled globally! */ -#ifdef CONFIG_ARM +#if defined(CONFIG_ARM) || defined(CONFIG_ARM64) #define ARCH_HAS_DMA_MMAP_COHERENT #endif #endif diff --git a/sound/core/seq/seq_dummy.c b/sound/core/seq/seq_dummy.c index dbc5507..f60d814 100644 --- a/sound/core/seq/seq_dummy.c +++ b/sound/core/seq/seq_dummy.c @@ -82,36 +82,6 @@ struct snd_seq_dummy_port { static int my_client = -1; /* - * unuse callback - send ALL_SOUNDS_OFF and RESET_CONTROLLERS events - * to subscribers. - * Note: this callback is called only after all subscribers are removed. - */ -static int -dummy_unuse(void *private_data, struct snd_seq_port_subscribe *info) -{ - struct snd_seq_dummy_port *p; - int i; - struct snd_seq_event ev; - - p = private_data; - memset(&ev, 0, sizeof(ev)); - if (p->duplex) - ev.source.port = p->connect; - else - ev.source.port = p->port; - ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS; - ev.type = SNDRV_SEQ_EVENT_CONTROLLER; - for (i = 0; i < 16; i++) { - ev.data.control.channel = i; - ev.data.control.param = MIDI_CTL_ALL_SOUNDS_OFF; - snd_seq_kernel_client_dispatch(p->client, &ev, 0, 0); - ev.data.control.param = MIDI_CTL_RESET_CONTROLLERS; - snd_seq_kernel_client_dispatch(p->client, &ev, 0, 0); - } - return 0; -} - -/* * event input callback - just redirect events to subscribers */ static int @@ -175,7 +145,6 @@ create_port(int idx, int type) | SNDRV_SEQ_PORT_TYPE_PORT; memset(&pcb, 0, sizeof(pcb)); pcb.owner = THIS_MODULE; - pcb.unuse = dummy_unuse; pcb.event_input = dummy_input; pcb.private_free = dummy_free; pcb.private_data = rec; diff --git a/sound/i2c/other/ak4113.c b/sound/i2c/other/ak4113.c index e04e750..7a9149b 100644 --- a/sound/i2c/other/ak4113.c +++ b/sound/i2c/other/ak4113.c @@ -56,8 +56,7 @@ static inline unsigned char reg_read(struct ak4113 *ak4113, unsigned char reg) static void snd_ak4113_free(struct ak4113 *chip) { - chip->init = 1; /* don't schedule new work */ - mb(); + atomic_inc(&chip->wq_processing); /* don't schedule new work */ cancel_delayed_work_sync(&chip->work); kfree(chip); } @@ -89,6 +88,7 @@ int snd_ak4113_create(struct snd_card *card, ak4113_read_t *read, chip->write = write; chip->private_data = private_data; INIT_DELAYED_WORK(&chip->work, ak4113_stats); + atomic_set(&chip->wq_processing, 0); for (reg = 0; reg < AK4113_WRITABLE_REGS ; reg++) chip->regmap[reg] = pgm[reg]; @@ -139,13 +139,11 @@ static void ak4113_init_regs(struct ak4113 *chip) void snd_ak4113_reinit(struct ak4113 *chip) { - chip->init = 1; - mb(); - flush_delayed_work(&chip->work); + if (atomic_inc_return(&chip->wq_processing) == 1) + cancel_delayed_work_sync(&chip->work); ak4113_init_regs(chip); /* bring up statistics / event queing */ - chip->init = 0; - if (chip->kctls[0]) + if (atomic_dec_and_test(&chip->wq_processing)) schedule_delayed_work(&chip->work, HZ / 10); } EXPORT_SYMBOL_GPL(snd_ak4113_reinit); @@ -632,8 +630,9 @@ static void ak4113_stats(struct work_struct *work) { struct ak4113 *chip = container_of(work, struct ak4113, work.work); - if (!chip->init) + if (atomic_inc_return(&chip->wq_processing) == 1) snd_ak4113_check_rate_and_errors(chip, chip->check_flags); - schedule_delayed_work(&chip->work, HZ / 10); + if (atomic_dec_and_test(&chip->wq_processing)) + schedule_delayed_work(&chip->work, HZ / 10); } diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c index 15ae025..bf515db 100644 --- a/sound/i2c/other/ak4114.c +++ b/sound/i2c/other/ak4114.c @@ -66,8 +66,7 @@ static void reg_dump(struct ak4114 *ak4114) static void snd_ak4114_free(struct ak4114 *chip) { - chip->init = 1; /* don't schedule new work */ - mb(); + atomic_inc(&chip->wq_processing); /* don't schedule new work */ cancel_delayed_work_sync(&chip->work); kfree(chip); } @@ -100,6 +99,7 @@ int snd_ak4114_create(struct snd_card *card, chip->write = write; chip->private_data = private_data; INIT_DELAYED_WORK(&chip->work, ak4114_stats); + atomic_set(&chip->wq_processing, 0); for (reg = 0; reg < 6; reg++) chip->regmap[reg] = pgm[reg]; @@ -152,13 +152,11 @@ static void ak4114_init_regs(struct ak4114 *chip) void snd_ak4114_reinit(struct ak4114 *chip) { - chip->init = 1; - mb(); - flush_delayed_work(&chip->work); + if (atomic_inc_return(&chip->wq_processing) == 1) + cancel_delayed_work_sync(&chip->work); ak4114_init_regs(chip); /* bring up statistics / event queing */ - chip->init = 0; - if (chip->kctls[0]) + if (atomic_dec_and_test(&chip->wq_processing)) schedule_delayed_work(&chip->work, HZ / 10); } @@ -612,10 +610,10 @@ static void ak4114_stats(struct work_struct *work) { struct ak4114 *chip = container_of(work, struct ak4114, work.work); - if (!chip->init) + if (atomic_inc_return(&chip->wq_processing) == 1) snd_ak4114_check_rate_and_errors(chip, chip->check_flags); - - schedule_delayed_work(&chip->work, HZ / 10); + if (atomic_dec_and_test(&chip->wq_processing)) + schedule_delayed_work(&chip->work, HZ / 10); } EXPORT_SYMBOL(snd_ak4114_create); diff --git a/sound/oss/sequencer.c b/sound/oss/sequencer.c index 9b9f7d3..1010ca1 100644 --- a/sound/oss/sequencer.c +++ b/sound/oss/sequencer.c @@ -683,13 +683,8 @@ static int seq_timing_event(unsigned char *event_rec) break; case TMR_ECHO: - if (seq_mode == SEQ_2) - seq_copy_to_input(event_rec, 8); - else - { - parm = (parm << 8 | SEQ_ECHO); - seq_copy_to_input((unsigned char *) &parm, 4); - } + parm = (parm << 8 | SEQ_ECHO); + seq_copy_to_input((unsigned char *) &parm, 4); break; default:; @@ -1330,7 +1325,6 @@ int sequencer_ioctl(int dev, struct file *file, unsigned int cmd, void __user *a int mode = translate_mode(file); struct synth_info inf; struct seq_event_rec event_rec; - unsigned long flags; int __user *p = arg; orig_dev = dev = dev >> 4; @@ -1485,9 +1479,7 @@ int sequencer_ioctl(int dev, struct file *file, unsigned int cmd, void __user *a case SNDCTL_SEQ_OUTOFBAND: if (copy_from_user(&event_rec, arg, sizeof(event_rec))) return -EFAULT; - spin_lock_irqsave(&lock,flags); play_event(event_rec.arr); - spin_unlock_irqrestore(&lock,flags); return 0; case SNDCTL_MIDI_INFO: diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig index 8756c8e..46e5630 100644 --- a/sound/pci/Kconfig +++ b/sound/pci/Kconfig @@ -859,8 +859,8 @@ config SND_VIRTUOSO select SND_JACK if INPUT=y || INPUT=SND help Say Y here to include support for sound cards based on the - Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS, - Essence ST (Deluxe), and Essence STX. + Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS, DSX, + Essence ST (Deluxe), and Essence STX (II). Support for the HDAV1.3 (Deluxe) and HDAV1.3 Slim is experimental; for the Xense, missing. diff --git a/sound/pci/emu10k1/emu10k1.c b/sound/pci/emu10k1/emu10k1.c index 9e1bd0c..6757458 100644 --- a/sound/pci/emu10k1/emu10k1.c +++ b/sound/pci/emu10k1/emu10k1.c @@ -181,8 +181,10 @@ static int snd_card_emu10k1_probe(struct pci_dev *pci, } #endif - strcpy(card->driver, emu->card_capabilities->driver); - strcpy(card->shortname, emu->card_capabilities->name); + strlcpy(card->driver, emu->card_capabilities->driver, + sizeof(card->driver)); + strlcpy(card->shortname, emu->card_capabilities->name, + sizeof(card->shortname)); snprintf(card->longname, sizeof(card->longname), "%s (rev.%d, serial:0x%x) at 0x%lx, irq %i", card->shortname, emu->revision, emu->serial, emu->port, emu->irq); diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c index cae3659..f8a6549 100644 --- a/sound/pci/emu10k1/emu10k1_callback.c +++ b/sound/pci/emu10k1/emu10k1_callback.c @@ -85,6 +85,8 @@ snd_emu10k1_ops_setup(struct snd_emux *emux) * get more voice for pcm * * terminate most inactive voice and give it as a pcm voice. + * + * voice_lock is already held. */ int snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw) @@ -92,12 +94,10 @@ snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw) struct snd_emux *emu; struct snd_emux_voice *vp; struct best_voice best[V_END]; - unsigned long flags; int i; emu = hw->synth; - spin_lock_irqsave(&emu->voice_lock, flags); lookup_voices(emu, hw, best, 1); /* no OFF voices */ for (i = 0; i < V_END; i++) { if (best[i].voice >= 0) { @@ -113,11 +113,9 @@ snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw) vp->emu->num_voices--; vp->ch = -1; vp->state = SNDRV_EMUX_ST_OFF; - spin_unlock_irqrestore(&emu->voice_lock, flags); return ch; } } - spin_unlock_irqrestore(&emu->voice_lock, flags); /* not found */ return -ENOMEM; @@ -417,7 +415,7 @@ start_voice(struct snd_emux_voice *vp) snd_emu10k1_ptr_write(hw, Z2, ch, 0); /* invalidate maps */ - temp = (hw->silent_page.addr << 1) | MAP_PTI_MASK; + temp = (hw->silent_page.addr << hw->address_mode) | (hw->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); snd_emu10k1_ptr_write(hw, MAPA, ch, temp); snd_emu10k1_ptr_write(hw, MAPB, ch, temp); #if 0 @@ -438,7 +436,7 @@ start_voice(struct snd_emux_voice *vp) snd_emu10k1_ptr_write(hw, CDF, ch, sample); /* invalidate maps */ - temp = ((unsigned int)hw->silent_page.addr << 1) | MAP_PTI_MASK; + temp = ((unsigned int)hw->silent_page.addr << hw_address_mode) | (hw->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); snd_emu10k1_ptr_write(hw, MAPA, ch, temp); snd_emu10k1_ptr_write(hw, MAPB, ch, temp); diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c index bdd888e..a131092 100644 --- a/sound/pci/emu10k1/emu10k1_main.c +++ b/sound/pci/emu10k1/emu10k1_main.c @@ -282,7 +282,7 @@ static int snd_emu10k1_init(struct snd_emu10k1 *emu, int enable_ir, int resume) snd_emu10k1_ptr_write(emu, TCB, 0, 0); /* taken from original driver */ snd_emu10k1_ptr_write(emu, TCBS, 0, 4); /* taken from original driver */ - silent_page = (emu->silent_page.addr << 1) | MAP_PTI_MASK; + silent_page = (emu->silent_page.addr << emu->address_mode) | (emu->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); for (ch = 0; ch < NUM_G; ch++) { snd_emu10k1_ptr_write(emu, MAPA, ch, silent_page); snd_emu10k1_ptr_write(emu, MAPB, ch, silent_page); @@ -348,6 +348,11 @@ static int snd_emu10k1_init(struct snd_emu10k1 *emu, int enable_ir, int resume) outl(reg | A_IOCFG_GPOUT0, emu->port + A_IOCFG); } + if (emu->address_mode == 0) { + /* use 16M in 4G */ + outl(inl(emu->port + HCFG) | HCFG_EXPANDED_MEM, emu->port + HCFG); + } + return 0; } @@ -1411,7 +1416,7 @@ static struct snd_emu_chip_details emu_chip_details[] = { * */ {.vendor = 0x1102, .device = 0x0008, .subsystem = 0x20011102, - .driver = "Audigy2", .name = "SB Audigy 2 ZS Notebook [SB0530]", + .driver = "Audigy2", .name = "Audigy 2 ZS Notebook [SB0530]", .id = "Audigy2", .emu10k2_chip = 1, .ca0108_chip = 1, @@ -1561,7 +1566,7 @@ static struct snd_emu_chip_details emu_chip_details[] = { .adc_1361t = 1, /* 24 bit capture instead of 16bit */ .ac97_chip = 1} , {.vendor = 0x1102, .device = 0x0004, .subsystem = 0x10051102, - .driver = "Audigy2", .name = "SB Audigy 2 Platinum EX [SB0280]", + .driver = "Audigy2", .name = "Audigy 2 Platinum EX [SB0280]", .id = "Audigy2", .emu10k2_chip = 1, .ca0102_chip = 1, @@ -1865,8 +1870,10 @@ int snd_emu10k1_create(struct snd_card *card, is_audigy = emu->audigy = c->emu10k2_chip; + /* set addressing mode */ + emu->address_mode = is_audigy ? 0 : 1; /* set the DMA transfer mask */ - emu->dma_mask = is_audigy ? AUDIGY_DMA_MASK : EMU10K1_DMA_MASK; + emu->dma_mask = emu->address_mode ? EMU10K1_DMA_MASK : AUDIGY_DMA_MASK; if (pci_set_dma_mask(pci, emu->dma_mask) < 0 || pci_set_consistent_dma_mask(pci, emu->dma_mask) < 0) { snd_printk(KERN_ERR "architecture does not support PCI busmaster DMA with mask 0x%lx\n", emu->dma_mask); @@ -1889,7 +1896,7 @@ int snd_emu10k1_create(struct snd_card *card, emu->max_cache_pages = max_cache_bytes >> PAGE_SHIFT; if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci), - 32 * 1024, &emu->ptb_pages) < 0) { + (emu->address_mode ? 32 : 16) * 1024, &emu->ptb_pages) < 0) { err = -ENOMEM; goto error; } @@ -1988,8 +1995,8 @@ int snd_emu10k1_create(struct snd_card *card, /* Clear silent pages and set up pointers */ memset(emu->silent_page.area, 0, PAGE_SIZE); - silent_page = emu->silent_page.addr << 1; - for (idx = 0; idx < MAXPAGES; idx++) + silent_page = emu->silent_page.addr << emu->address_mode; + for (idx = 0; idx < (emu->address_mode ? MAXPAGES1 : MAXPAGES0); idx++) ((u32 *)emu->ptb_pages.area)[idx] = cpu_to_le32(silent_page | idx); /* set up voice indices */ diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c index 5ae1d04..7581019 100644 --- a/sound/pci/emu10k1/emupcm.c +++ b/sound/pci/emu10k1/emupcm.c @@ -379,7 +379,7 @@ static void snd_emu10k1_pcm_init_voice(struct snd_emu10k1 *emu, snd_emu10k1_ptr_write(emu, Z1, voice, 0); snd_emu10k1_ptr_write(emu, Z2, voice, 0); /* invalidate maps */ - silent_page = ((unsigned int)emu->silent_page.addr << 1) | MAP_PTI_MASK; + silent_page = ((unsigned int)emu->silent_page.addr << emu->address_mode) | (emu->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); snd_emu10k1_ptr_write(emu, MAPA, voice, silent_page); snd_emu10k1_ptr_write(emu, MAPB, voice, silent_page); /* modulation envelope */ diff --git a/sound/pci/emu10k1/emuproc.c b/sound/pci/emu10k1/emuproc.c index 2ca9f2e..53745f4 100644 --- a/sound/pci/emu10k1/emuproc.c +++ b/sound/pci/emu10k1/emuproc.c @@ -241,31 +241,22 @@ static void snd_emu10k1_proc_spdif_read(struct snd_info_entry *entry, struct snd_emu10k1 *emu = entry->private_data; u32 value; u32 value2; - unsigned long flags; u32 rate; if (emu->card_capabilities->emu_model) { - spin_lock_irqsave(&emu->emu_lock, flags); snd_emu1010_fpga_read(emu, 0x38, &value); - spin_unlock_irqrestore(&emu->emu_lock, flags); if ((value & 0x1) == 0) { - spin_lock_irqsave(&emu->emu_lock, flags); snd_emu1010_fpga_read(emu, 0x2a, &value); snd_emu1010_fpga_read(emu, 0x2b, &value2); - spin_unlock_irqrestore(&emu->emu_lock, flags); rate = 0x1770000 / (((value << 5) | value2)+1); snd_iprintf(buffer, "ADAT Locked : %u\n", rate); } else { snd_iprintf(buffer, "ADAT Unlocked\n"); } - spin_lock_irqsave(&emu->emu_lock, flags); snd_emu1010_fpga_read(emu, 0x20, &value); - spin_unlock_irqrestore(&emu->emu_lock, flags); if ((value & 0x4) == 0) { - spin_lock_irqsave(&emu->emu_lock, flags); snd_emu1010_fpga_read(emu, 0x28, &value); snd_emu1010_fpga_read(emu, 0x29, &value2); - spin_unlock_irqrestore(&emu->emu_lock, flags); rate = 0x1770000 / (((value << 5) | value2)+1); snd_iprintf(buffer, "SPDIF Locked : %d\n", rate); } else { @@ -410,14 +401,11 @@ static void snd_emu_proc_emu1010_reg_read(struct snd_info_entry *entry, { struct snd_emu10k1 *emu = entry->private_data; u32 value; - unsigned long flags; int i; snd_iprintf(buffer, "EMU1010 Registers:\n\n"); for(i = 0; i < 0x40; i+=1) { - spin_lock_irqsave(&emu->emu_lock, flags); snd_emu1010_fpga_read(emu, i, &value); - spin_unlock_irqrestore(&emu->emu_lock, flags); snd_iprintf(buffer, "%02X: %08X, %02X\n", i, value, (value >> 8) & 0x7f); } } diff --git a/sound/pci/emu10k1/memory.c b/sound/pci/emu10k1/memory.c index ae709c1..d514458 100644 --- a/sound/pci/emu10k1/memory.c +++ b/sound/pci/emu10k1/memory.c @@ -34,10 +34,11 @@ * aligned pages in others */ #define __set_ptb_entry(emu,page,addr) \ - (((u32 *)(emu)->ptb_pages.area)[page] = cpu_to_le32(((addr) << 1) | (page))) + (((u32 *)(emu)->ptb_pages.area)[page] = cpu_to_le32(((addr) << (emu->address_mode)) | (page))) #define UNIT_PAGES (PAGE_SIZE / EMUPAGESIZE) -#define MAX_ALIGN_PAGES (MAXPAGES / UNIT_PAGES) +#define MAX_ALIGN_PAGES0 (MAXPAGES0 / UNIT_PAGES) +#define MAX_ALIGN_PAGES1 (MAXPAGES1 / UNIT_PAGES) /* get aligned page from offset address */ #define get_aligned_page(offset) ((offset) >> PAGE_SHIFT) /* get offset address from aligned page */ @@ -124,7 +125,7 @@ static int search_empty_map_area(struct snd_emu10k1 *emu, int npages, struct lis } page = blk->mapped_page + blk->pages; } - size = MAX_ALIGN_PAGES - page; + size = (emu->address_mode ? MAX_ALIGN_PAGES1 : MAX_ALIGN_PAGES0) - page; if (size >= max_size) { *nextp = pos; return page; @@ -181,7 +182,7 @@ static int unmap_memblk(struct snd_emu10k1 *emu, struct snd_emu10k1_memblk *blk) q = get_emu10k1_memblk(p, mapped_link); end_page = q->mapped_page; } else - end_page = MAX_ALIGN_PAGES; + end_page = (emu->address_mode ? MAX_ALIGN_PAGES1 : MAX_ALIGN_PAGES0); /* remove links */ list_del(&blk->mapped_link); @@ -305,7 +306,7 @@ snd_emu10k1_alloc_pages(struct snd_emu10k1 *emu, struct snd_pcm_substream *subst if (snd_BUG_ON(!emu)) return NULL; if (snd_BUG_ON(runtime->dma_bytes <= 0 || - runtime->dma_bytes >= MAXPAGES * EMUPAGESIZE)) + runtime->dma_bytes >= (emu->address_mode ? MAXPAGES1 : MAXPAGES0) * EMUPAGESIZE)) return NULL; hdr = emu->memhdr; if (snd_BUG_ON(!hdr)) diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index dafcf82..97ebc10 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -338,8 +338,10 @@ int snd_hda_get_sub_nodes(struct hda_codec *codec, hda_nid_t nid, unsigned int parm; parm = snd_hda_param_read(codec, nid, AC_PAR_NODE_COUNT); - if (parm == -1) + if (parm == -1) { + *start_id = 0; return 0; + } *start_id = (parm >> 16) & 0x7fff; return (int)(parm & 0x7fff); } @@ -2080,6 +2082,16 @@ static void put_vol_mute(struct hda_codec *codec, unsigned int amp_caps, snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_AMP_GAIN_MUTE, parm); } +/* meta hook to call each driver's vmaster hook */ +static void vmaster_hook(void *private_data, int enabled) +{ + struct hda_vmaster_mute_hook *hook = private_data; + + if (hook->mute_mode != HDA_VMUTE_FOLLOW_MASTER) + enabled = hook->mute_mode; + hook->hook(hook->codec, enabled); +} + /** * snd_hda_codec_amp_read - Read AMP value * @codec: HD-audio codec @@ -2915,9 +2927,9 @@ int snd_hda_add_vmaster_hook(struct hda_codec *codec, if (!hook->hook || !hook->sw_kctl) return 0; - snd_ctl_add_vmaster_hook(hook->sw_kctl, hook->hook, codec); hook->codec = codec; hook->mute_mode = HDA_VMUTE_FOLLOW_MASTER; + snd_ctl_add_vmaster_hook(hook->sw_kctl, vmaster_hook, hook); if (!expose_enum_ctl) return 0; kctl = snd_ctl_new1(&vmaster_mute_mode, hook); @@ -2940,14 +2952,7 @@ void snd_hda_sync_vmaster_hook(struct hda_vmaster_mute_hook *hook) */ if (hook->codec->bus->shutdown) return; - switch (hook->mute_mode) { - case HDA_VMUTE_FOLLOW_MASTER: - snd_ctl_sync_vmaster_hook(hook->sw_kctl); - break; - default: - hook->hook(hook->codec, hook->mute_mode); - break; - } + snd_ctl_sync_vmaster_hook(hook->sw_kctl); } EXPORT_SYMBOL_GPL(snd_hda_sync_vmaster_hook); diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index d9a09bd..9a23bde 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -653,12 +653,45 @@ static int get_amp_val_to_activate(struct hda_codec *codec, hda_nid_t nid, return val; } +/* is this a stereo widget or a stereo-to-mono mix? */ +static bool is_stereo_amps(struct hda_codec *codec, hda_nid_t nid, int dir) +{ + unsigned int wcaps = get_wcaps(codec, nid); + hda_nid_t conn; + + if (wcaps & AC_WCAP_STEREO) + return true; + if (dir != HDA_INPUT || get_wcaps_type(wcaps) != AC_WID_AUD_MIX) + return false; + if (snd_hda_get_num_conns(codec, nid) != 1) + return false; + if (snd_hda_get_connections(codec, nid, &conn, 1) < 0) + return false; + return !!(get_wcaps(codec, conn) & AC_WCAP_STEREO); +} + /* initialize the amp value (only at the first time) */ static void init_amp(struct hda_codec *codec, hda_nid_t nid, int dir, int idx) { unsigned int caps = query_amp_caps(codec, nid, dir); int val = get_amp_val_to_activate(codec, nid, dir, caps, false); - snd_hda_codec_amp_init_stereo(codec, nid, dir, idx, 0xff, val); + + if (is_stereo_amps(codec, nid, dir)) + snd_hda_codec_amp_init_stereo(codec, nid, dir, idx, 0xff, val); + else + snd_hda_codec_amp_init(codec, nid, 0, dir, idx, 0xff, val); +} + +/* update the amp, doing in stereo or mono depending on NID */ +static int update_amp(struct hda_codec *codec, hda_nid_t nid, int dir, int idx, + unsigned int mask, unsigned int val) +{ + if (is_stereo_amps(codec, nid, dir)) + return snd_hda_codec_amp_stereo(codec, nid, dir, idx, + mask, val); + else + return snd_hda_codec_amp_update(codec, nid, 0, dir, idx, + mask, val); } /* calculate amp value mask we can modify; @@ -698,7 +731,7 @@ static void activate_amp(struct hda_codec *codec, hda_nid_t nid, int dir, return; val &= mask; - snd_hda_codec_amp_stereo(codec, nid, dir, idx, mask, val); + update_amp(codec, nid, dir, idx, mask, val); } static void activate_amp_out(struct hda_codec *codec, struct nid_path *path, @@ -4337,13 +4370,11 @@ static void mute_all_mixer_nid(struct hda_codec *codec, hda_nid_t mix) has_amp = nid_has_mute(codec, mix, HDA_INPUT); for (i = 0; i < nums; i++) { if (has_amp) - snd_hda_codec_amp_stereo(codec, mix, - HDA_INPUT, i, - 0xff, HDA_AMP_MUTE); + update_amp(codec, mix, HDA_INPUT, i, + 0xff, HDA_AMP_MUTE); else if (nid_has_volume(codec, conn[i], HDA_OUTPUT)) - snd_hda_codec_amp_stereo(codec, conn[i], - HDA_OUTPUT, 0, - 0xff, HDA_AMP_MUTE); + update_amp(codec, conn[i], HDA_OUTPUT, 0, + 0xff, HDA_AMP_MUTE); } } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 7ec9142..84e8879 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -959,7 +959,7 @@ static unsigned int azx_rirb_get_response(struct hda_bus *bus, } } - if (!bus->no_response_fallback) + if (bus->no_response_fallback) return -1; if (!chip->polling_mode && chip->poll_count < 2) { @@ -3984,7 +3984,7 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = { .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH_NOPM }, /* Panther Point */ { PCI_DEVICE(0x8086, 0x1e20), - .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, + .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH_NOPM }, /* Lynx Point */ { PCI_DEVICE(0x8086, 0x8c20), .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, @@ -4027,6 +4027,9 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = { /* BayTrail */ { PCI_DEVICE(0x8086, 0x0f04), .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH_NOPM }, + /* Braswell */ + { PCI_DEVICE(0x8086, 0x2284), + .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, /* ICH */ { PCI_DEVICE(0x8086, 0x2668), .driver_data = AZX_DRIVER_ICH | AZX_DCAPS_OLD_SSYNC | diff --git a/sound/pci/hda/hda_proc.c b/sound/pci/hda/hda_proc.c index ce5a6da..05e19f7 100644 --- a/sound/pci/hda/hda_proc.c +++ b/sound/pci/hda/hda_proc.c @@ -134,13 +134,38 @@ static void print_amp_caps(struct snd_info_buffer *buffer, (caps & AC_AMPCAP_MUTE) >> AC_AMPCAP_MUTE_SHIFT); } +/* is this a stereo widget or a stereo-to-mono mix? */ +static bool is_stereo_amps(struct hda_codec *codec, hda_nid_t nid, + int dir, unsigned int wcaps, int indices) +{ + hda_nid_t conn; + + if (wcaps & AC_WCAP_STEREO) + return true; + /* check for a stereo-to-mono mix; it must be: + * only a single connection, only for input, and only a mixer widget + */ + if (indices != 1 || dir != HDA_INPUT || + get_wcaps_type(wcaps) != AC_WID_AUD_MIX) + return false; + + if (snd_hda_get_raw_connections(codec, nid, &conn, 1) < 0) + return false; + /* the connection source is a stereo? */ + wcaps = snd_hda_param_read(codec, conn, AC_PAR_AUDIO_WIDGET_CAP); + return !!(wcaps & AC_WCAP_STEREO); +} + static void print_amp_vals(struct snd_info_buffer *buffer, struct hda_codec *codec, hda_nid_t nid, - int dir, int stereo, int indices) + int dir, unsigned int wcaps, int indices) { unsigned int val; + bool stereo; int i; + stereo = is_stereo_amps(codec, nid, dir, wcaps, indices); + dir = dir == HDA_OUTPUT ? AC_AMP_GET_OUTPUT : AC_AMP_GET_INPUT; for (i = 0; i < indices; i++) { snd_iprintf(buffer, " ["); @@ -757,12 +782,10 @@ static void print_codec_info(struct snd_info_entry *entry, (codec->single_adc_amp && wid_type == AC_WID_AUD_IN)) print_amp_vals(buffer, codec, nid, HDA_INPUT, - wid_caps & AC_WCAP_STEREO, - 1); + wid_caps, 1); else print_amp_vals(buffer, codec, nid, HDA_INPUT, - wid_caps & AC_WCAP_STEREO, - conn_len); + wid_caps, conn_len); } if (wid_caps & AC_WCAP_OUT_AMP) { snd_iprintf(buffer, " Amp-Out caps: "); @@ -771,11 +794,10 @@ static void print_codec_info(struct snd_info_entry *entry, if (wid_type == AC_WID_PIN && codec->pin_amp_workaround) print_amp_vals(buffer, codec, nid, HDA_OUTPUT, - wid_caps & AC_WCAP_STEREO, - conn_len); + wid_caps, conn_len); else print_amp_vals(buffer, codec, nid, HDA_OUTPUT, - wid_caps & AC_WCAP_STEREO, 1); + wid_caps, 1); } switch (wid_type) { diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c index eaf64ea..1a05efa 100644 --- a/sound/pci/hda/patch_analog.c +++ b/sound/pci/hda/patch_analog.c @@ -333,6 +333,7 @@ static const struct hda_fixup ad1986a_fixups[] = { static const struct snd_pci_quirk ad1986a_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x30af, "HP B2800", AD1986A_FIXUP_LAPTOP_IMIC), + SND_PCI_QUIRK(0x1043, 0x1443, "ASUS Z99He", AD1986A_FIXUP_EAPD), SND_PCI_QUIRK(0x1043, 0x1447, "ASUS A8JN", AD1986A_FIXUP_EAPD), SND_PCI_QUIRK_MASK(0x1043, 0xff00, 0x8100, "ASUS P5", AD1986A_FIXUP_3STACK), SND_PCI_QUIRK_MASK(0x1043, 0xff00, 0x8200, "ASUS M2", AD1986A_FIXUP_3STACK), diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 46ecdbb..d5843da 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -4379,6 +4379,9 @@ static void ca0132_download_dsp(struct hda_codec *codec) return; /* NOP */ #endif + if (spec->dsp_state == DSP_DOWNLOAD_FAILED) + return; /* don't retry failures */ + chipio_enable_clocks(codec); spec->dsp_state = DSP_DOWNLOADING; if (!ca0132_download_dsp_images(codec)) @@ -4555,7 +4558,8 @@ static int ca0132_init(struct hda_codec *codec) struct auto_pin_cfg *cfg = &spec->autocfg; int i; - spec->dsp_state = DSP_DOWNLOAD_INIT; + if (spec->dsp_state != DSP_DOWNLOAD_FAILED) + spec->dsp_state = DSP_DOWNLOAD_INIT; spec->curr_chip_addx = INVALID_CHIP_ADDRESS; snd_hda_power_up(codec); @@ -4666,6 +4670,7 @@ static int patch_ca0132(struct hda_codec *codec) codec->spec = spec; spec->codec = codec; + spec->dsp_state = DSP_DOWNLOAD_INIT; spec->num_mixers = 1; spec->mixers[0] = ca0132_mixer; diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index fc492ac..7b0aac9 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -396,6 +396,7 @@ static const struct snd_pci_quirk cs420x_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x1c00, "MacBookPro 8,1", CS420X_MBP81), SND_PCI_QUIRK(0x106b, 0x2000, "iMac 12,2", CS420X_IMAC27_122), SND_PCI_QUIRK(0x106b, 0x2800, "MacBookPro 10,1", CS420X_MBP101), + SND_PCI_QUIRK(0x106b, 0x5600, "MacBookAir 5,2", CS420X_MBP81), SND_PCI_QUIRK(0x106b, 0x5b00, "MacBookAir 4,2", CS420X_MBA42), SND_PCI_QUIRK_VENDOR(0x106b, "Apple", CS420X_APPLE), {} /* terminator */ @@ -587,6 +588,7 @@ static int patch_cs420x(struct hda_codec *codec) return -ENOMEM; spec->gen.automute_hook = cs_automute; + codec->single_adc_amp = 1; snd_hda_pick_fixup(codec, cs420x_models, cs420x_fixup_tbl, cs420x_fixups); @@ -1000,9 +1002,7 @@ static void cs4210_spdif_automute(struct hda_codec *codec, spec->spdif_present = spdif_present; /* SPDIF TX on/off */ - if (spdif_present) - snd_hda_set_pin_ctl(codec, spdif_pin, - spdif_present ? PIN_OUT : 0); + snd_hda_set_pin_ctl(codec, spdif_pin, spdif_present ? PIN_OUT : 0); cs_automute(codec); } diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index bcf91be..50981b1 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -3232,11 +3232,13 @@ enum { CXT_PINCFG_LENOVO_TP410, CXT_PINCFG_LEMOTE_A1004, CXT_PINCFG_LEMOTE_A1205, + CXT_PINCFG_COMPAQ_CQ60, CXT_FIXUP_STEREO_DMIC, CXT_FIXUP_INC_MIC_BOOST, CXT_FIXUP_HEADPHONE_MIC_PIN, CXT_FIXUP_HEADPHONE_MIC, CXT_FIXUP_GPIO1, + CXT_FIXUP_ASPIRE_DMIC, CXT_FIXUP_THINKPAD_ACPI, }; @@ -3367,6 +3369,15 @@ static const struct hda_fixup cxt_fixups[] = { .type = HDA_FIXUP_PINS, .v.pins = cxt_pincfg_lemote, }, + [CXT_PINCFG_COMPAQ_CQ60] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + /* 0x17 was falsely set up as a mic, it should 0x1d */ + { 0x17, 0x400001f0 }, + { 0x1d, 0x97a70120 }, + { } + } + }, [CXT_FIXUP_STEREO_DMIC] = { .type = HDA_FIXUP_FUNC, .v.func = cxt_fixup_stereo_dmic, @@ -3397,6 +3408,12 @@ static const struct hda_fixup cxt_fixups[] = { { } }, }, + [CXT_FIXUP_ASPIRE_DMIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = cxt_fixup_stereo_dmic, + .chained = true, + .chain_id = CXT_FIXUP_GPIO1, + }, [CXT_FIXUP_THINKPAD_ACPI] = { .type = HDA_FIXUP_FUNC, .v.func = hda_fixup_thinkpad_acpi, @@ -3404,13 +3421,14 @@ static const struct hda_fixup cxt_fixups[] = { }; static const struct snd_pci_quirk cxt5051_fixups[] = { + SND_PCI_QUIRK(0x103c, 0x360b, "Compaq CQ60", CXT_PINCFG_COMPAQ_CQ60), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo X200", CXT_PINCFG_LENOVO_X200), {} }; static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x1025, 0x0543, "Acer Aspire One 522", CXT_FIXUP_STEREO_DMIC), - SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_GPIO1), + SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_ASPIRE_DMIC), SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410), @@ -3573,6 +3591,14 @@ static const struct hda_codec_preset snd_hda_preset_conexant[] = { .patch = patch_conexant_auto }, { .id = 0x14f150b9, .name = "CX20665", .patch = patch_conexant_auto }, + { .id = 0x14f150f1, .name = "CX20721", + .patch = patch_conexant_auto }, + { .id = 0x14f150f2, .name = "CX20722", + .patch = patch_conexant_auto }, + { .id = 0x14f150f3, .name = "CX20723", + .patch = patch_conexant_auto }, + { .id = 0x14f150f4, .name = "CX20724", + .patch = patch_conexant_auto }, { .id = 0x14f1510f, .name = "CX20751/2", .patch = patch_conexant_auto }, { .id = 0x14f15110, .name = "CX20751/2", @@ -3607,6 +3633,10 @@ MODULE_ALIAS("snd-hda-codec-id:14f150ab"); MODULE_ALIAS("snd-hda-codec-id:14f150ac"); MODULE_ALIAS("snd-hda-codec-id:14f150b8"); MODULE_ALIAS("snd-hda-codec-id:14f150b9"); +MODULE_ALIAS("snd-hda-codec-id:14f150f1"); +MODULE_ALIAS("snd-hda-codec-id:14f150f2"); +MODULE_ALIAS("snd-hda-codec-id:14f150f3"); +MODULE_ALIAS("snd-hda-codec-id:14f150f4"); MODULE_ALIAS("snd-hda-codec-id:14f1510f"); MODULE_ALIAS("snd-hda-codec-id:14f15110"); MODULE_ALIAS("snd-hda-codec-id:14f15111"); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index d135c90..611110a 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1557,19 +1557,22 @@ static bool hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll) } } - if (pin_eld->eld_valid && !eld->eld_valid) { - update_eld = true; + if (pin_eld->eld_valid != eld->eld_valid) eld_changed = true; - } + + if (pin_eld->eld_valid && !eld->eld_valid) + update_eld = true; + if (update_eld) { bool old_eld_valid = pin_eld->eld_valid; pin_eld->eld_valid = eld->eld_valid; - eld_changed = pin_eld->eld_size != eld->eld_size || + if (pin_eld->eld_size != eld->eld_size || memcmp(pin_eld->eld_buffer, eld->eld_buffer, - eld->eld_size) != 0; - if (eld_changed) + eld->eld_size) != 0) { memcpy(pin_eld->eld_buffer, eld->eld_buffer, eld->eld_size); + eld_changed = true; + } pin_eld->eld_size = eld->eld_size; pin_eld->info = eld->info; @@ -3314,6 +3317,7 @@ static const struct hda_codec_preset snd_hda_preset_hdmi[] = { { .id = 0x80862808, .name = "Broadwell HDMI", .patch = patch_generic_hdmi }, { .id = 0x80862880, .name = "CedarTrail HDMI", .patch = patch_generic_hdmi }, { .id = 0x80862882, .name = "Valleyview2 HDMI", .patch = patch_generic_hdmi }, +{ .id = 0x80862883, .name = "Braswell HDMI", .patch = patch_generic_hdmi }, { .id = 0x808629fb, .name = "Crestline HDMI", .patch = patch_generic_hdmi }, {} /* terminator */ }; @@ -3370,6 +3374,7 @@ MODULE_ALIAS("snd-hda-codec-id:80862807"); MODULE_ALIAS("snd-hda-codec-id:80862808"); MODULE_ALIAS("snd-hda-codec-id:80862880"); MODULE_ALIAS("snd-hda-codec-id:80862882"); +MODULE_ALIAS("snd-hda-codec-id:80862883"); MODULE_ALIAS("snd-hda-codec-id:808629fb"); MODULE_LICENSE("GPL"); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2a16a90..907371d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -180,6 +180,8 @@ static void alc_fix_pll(struct hda_codec *codec) spec->pll_coef_idx); val = snd_hda_codec_read(codec, spec->pll_nid, 0, AC_VERB_GET_PROC_COEF, 0); + if (val == -1) + return; snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_COEF_INDEX, spec->pll_coef_idx); snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_PROC_COEF, @@ -269,7 +271,7 @@ static void alc_auto_setup_eapd(struct hda_codec *codec, bool on) { /* We currently only handle front, HP */ static hda_nid_t pins[] = { - 0x0f, 0x10, 0x14, 0x15, 0 + 0x0f, 0x10, 0x14, 0x15, 0x17, 0 }; hda_nid_t *p; for (p = pins; *p; p++) @@ -325,6 +327,7 @@ static void alc_auto_init_amp(struct hda_codec *codec, int type) case 0x10ec0885: case 0x10ec0887: /*case 0x10ec0889:*/ /* this causes an SPDIF problem */ + case 0x10ec0900: alc889_coef_init(codec); break; case 0x10ec0888: @@ -2223,6 +2226,7 @@ static const struct hda_fixup alc882_fixups[] = { static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x006c, "Acer Aspire 9810", ALC883_FIXUP_ACER_EAPD), SND_PCI_QUIRK(0x1025, 0x0090, "Acer Aspire", ALC883_FIXUP_ACER_EAPD), + SND_PCI_QUIRK(0x1025, 0x0107, "Acer Aspire", ALC883_FIXUP_ACER_EAPD), SND_PCI_QUIRK(0x1025, 0x010a, "Acer Ferrari 5000", ALC883_FIXUP_ACER_EAPD), SND_PCI_QUIRK(0x1025, 0x0110, "Acer Aspire", ALC883_FIXUP_ACER_EAPD), SND_PCI_QUIRK(0x1025, 0x0112, "Acer Aspire 9303", ALC883_FIXUP_ACER_EAPD), @@ -2278,7 +2282,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x4300, "iMac 9,1", ALC889_FIXUP_IMAC91_VREF), SND_PCI_QUIRK(0x106b, 0x4600, "MacbookPro 5,2", ALC889_FIXUP_IMAC91_VREF), SND_PCI_QUIRK(0x106b, 0x4900, "iMac 9,1 Aluminum", ALC889_FIXUP_IMAC91_VREF), - SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC889_FIXUP_IMAC91_VREF), + SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC889_FIXUP_MBA11_VREF), SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD), @@ -2328,6 +2332,7 @@ static int patch_alc882(struct hda_codec *codec) switch (codec->vendor_id) { case 0x10ec0882: case 0x10ec0885: + case 0x10ec0900: break; default: /* ALC883 and variants */ @@ -2765,6 +2770,8 @@ static int alc269_parse_auto_config(struct hda_codec *codec) static void alc269vb_toggle_power_output(struct hda_codec *codec, int power_up) { int val = alc_read_coef_idx(codec, 0x04); + if (val == -1) + return; if (power_up) val |= 1 << 11; else @@ -2879,6 +2886,8 @@ static void alc283_init(struct hda_codec *codec) if (!hp_pin) return; + + msleep(30); hp_pin_sense = snd_hda_jack_detect(codec, hp_pin); /* Index 0x43 Direct Drive HP AMP LPM Control 1 */ @@ -2920,6 +2929,9 @@ static void alc283_shutup(struct hda_codec *codec) alc_write_coef_idx(codec, 0x43, 0x9004); + /*depop hp during suspend*/ + alc_write_coef_idx(codec, 0x06, 0x2100); + snd_hda_codec_write(codec, hp_pin, 0, AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); @@ -3064,6 +3076,15 @@ static int alc269_resume(struct hda_codec *codec) snd_hda_codec_resume_cache(codec); alc_inv_dmic_sync(codec, true); hda_call_check_power_status(codec, 0x01); + + /* on some machine, the BIOS will clear the codec gpio data when enter + * suspend, and won't restore the data after resume, so we restore it + * in the driver. + */ + if (spec->gpio_led) + snd_hda_codec_write(codec, codec->afg, 0, AC_VERB_SET_GPIO_DATA, + spec->gpio_led); + if (spec->has_alc5505_dsp) alc5505_dsp_resume(codec); @@ -3933,6 +3954,8 @@ enum { ALC269_FIXUP_QUANTA_MUTE, ALC269_FIXUP_LIFEBOOK, ALC269_FIXUP_LIFEBOOK_EXTMIC, + ALC269_FIXUP_LIFEBOOK_HP_PIN, + ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT, ALC269_FIXUP_AMIC, ALC269_FIXUP_DMIC, ALC269VB_FIXUP_AMIC, @@ -3951,6 +3974,7 @@ enum { ALC269_FIXUP_DELL3_MIC_NO_PRESENCE, ALC269_FIXUP_HEADSET_MODE, ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, + ALC269_FIXUP_ASPIRE_HEADSET_MIC, ALC269_FIXUP_ASUS_X101_FUNC, ALC269_FIXUP_ASUS_X101_VERB, ALC269_FIXUP_ASUS_X101, @@ -4067,6 +4091,17 @@ static const struct hda_fixup alc269_fixups[] = { { } }, }, + [ALC269_FIXUP_LIFEBOOK_HP_PIN] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x21, 0x0221102f }, /* HP out */ + { } + }, + }, + [ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc269_fixup_pincfg_no_hp_to_lineout, + }, [ALC269_FIXUP_AMIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -4185,6 +4220,15 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_headset_mode_no_hp_mic, }, + [ALC269_FIXUP_ASPIRE_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x01a1913c }, /* headset mic w/o jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE, + }, [ALC286_FIXUP_SONY_MIC_NO_PRESENCE] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -4368,6 +4412,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x029b, "Acer 1810TZ", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1025, 0x0349, "Acer AOD260", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1025, 0x047c, "Acer AC700", ALC269_FIXUP_ACER_AC700), + SND_PCI_QUIRK(0x1025, 0x072d, "Acer Aspire V5-571G", ALC269_FIXUP_ASPIRE_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x0740, "Acer AO725", ALC271_FIXUP_HP_GATE_MIC_JACK), SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK), SND_PCI_QUIRK_VENDOR(0x1025, "Acer Aspire", ALC271_FIXUP_DMIC), @@ -4435,6 +4481,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED), /* ALC282 */ + SND_PCI_QUIRK(0x103c, 0x2191, "HP Touchsmart 14", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2192, "HP Touchsmart 15", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x220d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x220e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), @@ -4518,6 +4566,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x104d, 0x9084, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ), SND_PCI_QUIRK_VENDOR(0x104d, "Sony VAIO", ALC269_FIXUP_SONY_VAIO), SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK), + SND_PCI_QUIRK(0x10cf, 0x159f, "Lifebook E780", ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT), + SND_PCI_QUIRK(0x10cf, 0x15dc, "Lifebook T731", ALC269_FIXUP_LIFEBOOK_HP_PIN), + SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), @@ -4534,6 +4585,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC), @@ -4633,27 +4685,30 @@ static void alc269_fill_coef(struct hda_codec *codec) if ((alc_get_coef0(codec) & 0x00ff) == 0x017) { val = alc_read_coef_idx(codec, 0x04); /* Power up output pin */ - alc_write_coef_idx(codec, 0x04, val | (1<<11)); + if (val != -1) + alc_write_coef_idx(codec, 0x04, val | (1<<11)); } if ((alc_get_coef0(codec) & 0x00ff) == 0x018) { val = alc_read_coef_idx(codec, 0xd); - if ((val & 0x0c00) >> 10 != 0x1) { + if (val != -1 && (val & 0x0c00) >> 10 != 0x1) { /* Capless ramp up clock control */ alc_write_coef_idx(codec, 0xd, val | (1<<10)); } val = alc_read_coef_idx(codec, 0x17); - if ((val & 0x01c0) >> 6 != 0x4) { + if (val != -1 && (val & 0x01c0) >> 6 != 0x4) { /* Class D power on reset */ alc_write_coef_idx(codec, 0x17, val | (1<<7)); } } val = alc_read_coef_idx(codec, 0xd); /* Class D */ - alc_write_coef_idx(codec, 0xd, val | (1<<14)); + if (val != -1) + alc_write_coef_idx(codec, 0xd, val | (1<<14)); val = alc_read_coef_idx(codec, 0x4); /* HP */ - alc_write_coef_idx(codec, 0x4, val | (1<<11)); + if (val != -1) + alc_write_coef_idx(codec, 0x4, val | (1<<11)); } /* diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 3bc29c9..231b264 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -84,6 +84,8 @@ enum { STAC_DELL_EQ, STAC_ALIENWARE_M17X, STAC_92HD89XX_HP_FRONT_JACK, + STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK, + STAC_92HD73XX_ASUS_MOBO, STAC_92HD73XX_MODELS }; @@ -558,8 +560,8 @@ static void stac_init_power_map(struct hda_codec *codec) if (snd_hda_jack_tbl_get(codec, nid)) continue; if (def_conf == AC_JACK_PORT_COMPLEX && - !(spec->vref_mute_led_nid == nid || - is_jack_detectable(codec, nid))) { + spec->vref_mute_led_nid != nid && + is_jack_detectable(codec, nid)) { snd_hda_jack_detect_enable_callback(codec, nid, STAC_PWR_EVENT, jack_update_power); @@ -592,9 +594,9 @@ static void stac_store_hints(struct hda_codec *codec) spec->gpio_mask; } if (get_int_hint(codec, "gpio_dir", &spec->gpio_dir)) - spec->gpio_mask &= spec->gpio_mask; - if (get_int_hint(codec, "gpio_data", &spec->gpio_data)) spec->gpio_dir &= spec->gpio_mask; + if (get_int_hint(codec, "gpio_data", &spec->gpio_data)) + spec->gpio_data &= spec->gpio_mask; if (get_int_hint(codec, "eapd_mask", &spec->eapd_mask)) spec->eapd_mask &= spec->gpio_mask; if (get_int_hint(codec, "gpio_mute", &spec->gpio_mute)) @@ -1803,6 +1805,11 @@ static const struct hda_pintbl stac92hd89xx_hp_front_jack_pin_configs[] = { {} }; +static const struct hda_pintbl stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs[] = { + { 0x0e, 0x400000f0 }, + {} +}; + static void stac92hd73xx_fixup_ref(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -1925,7 +1932,22 @@ static const struct hda_fixup stac92hd73xx_fixups[] = { [STAC_92HD89XX_HP_FRONT_JACK] = { .type = HDA_FIXUP_PINS, .v.pins = stac92hd89xx_hp_front_jack_pin_configs, - } + }, + [STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK] = { + .type = HDA_FIXUP_PINS, + .v.pins = stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs, + }, + [STAC_92HD73XX_ASUS_MOBO] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + /* enable 5.1 and SPDIF out */ + { 0x0c, 0x01014411 }, + { 0x0d, 0x01014410 }, + { 0x0e, 0x01014412 }, + { 0x22, 0x014b1180 }, + { } + } + }, }; static const struct hda_model_fixup stac92hd73xx_models[] = { @@ -1937,6 +1959,7 @@ static const struct hda_model_fixup stac92hd73xx_models[] = { { .id = STAC_DELL_M6_BOTH, .name = "dell-m6" }, { .id = STAC_DELL_EQ, .name = "dell-eq" }, { .id = STAC_ALIENWARE_M17X, .name = "alienware" }, + { .id = STAC_92HD73XX_ASUS_MOBO, .name = "asus-mobo" }, {} }; @@ -1985,8 +2008,12 @@ static const struct snd_pci_quirk stac92hd73xx_fixup_tbl[] = { "Alienware M17x", STAC_ALIENWARE_M17X), SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0490, "Alienware M17x R3", STAC_DELL_EQ), + SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1927, + "HP Z1 G2", STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK), SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x2b17, "unknown HP", STAC_92HD89XX_HP_FRONT_JACK), + SND_PCI_QUIRK(PCI_VENDOR_ID_ASUSTEK, 0x83f8, "ASUS AT4NM10", + STAC_92HD73XX_ASUS_MOBO), {} /* terminator */ }; @@ -4200,11 +4227,18 @@ static int stac_parse_auto_config(struct hda_codec *codec) return err; } - stac_init_power_map(codec); - return 0; } +static int stac_build_controls(struct hda_codec *codec) +{ + int err = snd_hda_gen_build_controls(codec); + + if (err < 0) + return err; + stac_init_power_map(codec); + return 0; +} static int stac_init(struct hda_codec *codec) { @@ -4316,7 +4350,7 @@ static int stac_suspend(struct hda_codec *codec) #endif /* CONFIG_PM */ static const struct hda_codec_ops stac_patch_ops = { - .build_controls = snd_hda_gen_build_controls, + .build_controls = stac_build_controls, .build_pcms = snd_hda_gen_build_pcms, .init = stac_init, .free = stac_free, diff --git a/sound/pci/oxygen/virtuoso.c b/sound/pci/oxygen/virtuoso.c index 64b9fda..dbbbacf 100644 --- a/sound/pci/oxygen/virtuoso.c +++ b/sound/pci/oxygen/virtuoso.c @@ -53,6 +53,7 @@ static DEFINE_PCI_DEVICE_TABLE(xonar_ids) = { { OXYGEN_PCI_SUBID(0x1043, 0x835e) }, { OXYGEN_PCI_SUBID(0x1043, 0x838e) }, { OXYGEN_PCI_SUBID(0x1043, 0x8522) }, + { OXYGEN_PCI_SUBID(0x1043, 0x85f4) }, { OXYGEN_PCI_SUBID_BROKEN_EEPROM }, { } }; diff --git a/sound/pci/oxygen/xonar_pcm179x.c b/sound/pci/oxygen/xonar_pcm179x.c index c8c7f2c..e026059 100644 --- a/sound/pci/oxygen/xonar_pcm179x.c +++ b/sound/pci/oxygen/xonar_pcm179x.c @@ -100,8 +100,8 @@ */ /* - * Xonar Essence ST (Deluxe)/STX - * ----------------------------- + * Xonar Essence ST (Deluxe)/STX (II) + * ---------------------------------- * * CMI8788: * @@ -1138,6 +1138,14 @@ int get_xonar_pcm179x_model(struct oxygen *chip, chip->model.resume = xonar_stx_resume; chip->model.set_dac_params = set_pcm1796_params; break; + case 0x85f4: + chip->model = model_xonar_st; + /* TODO: daughterboard support */ + chip->model.shortname = "Xonar STX II"; + chip->model.init = xonar_stx_init; + chip->model.resume = xonar_stx_resume; + chip->model.set_dac_params = set_pcm1796_params; + break; default: return -EINVAL; } diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c index 56cc891..d99c8d3 100644 --- a/sound/pci/riptide/riptide.c +++ b/sound/pci/riptide/riptide.c @@ -2032,32 +2032,43 @@ snd_riptide_joystick_probe(struct pci_dev *pci, const struct pci_device_id *id) { static int dev; struct gameport *gameport; + int ret; if (dev >= SNDRV_CARDS) return -ENODEV; + if (!enable[dev]) { - dev++; - return -ENOENT; + ret = -ENOENT; + goto inc_dev; } - if (!joystick_port[dev++]) - return 0; + if (!joystick_port[dev]) { + ret = 0; + goto inc_dev; + } gameport = gameport_allocate_port(); - if (!gameport) - return -ENOMEM; + if (!gameport) { + ret = -ENOMEM; + goto inc_dev; + } if (!request_region(joystick_port[dev], 8, "Riptide gameport")) { snd_printk(KERN_WARNING "Riptide: cannot grab gameport 0x%x\n", joystick_port[dev]); gameport_free_port(gameport); - return -EBUSY; + ret = -EBUSY; + goto inc_dev; } gameport->io = joystick_port[dev]; gameport_register_port(gameport); pci_set_drvdata(pci, gameport); - return 0; + + ret = 0; +inc_dev: + dev++; + return ret; } static void snd_riptide_joystick_remove(struct pci_dev *pci) diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index e98dc00..2116750 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -6102,6 +6102,9 @@ static int snd_hdspm_playback_open(struct snd_pcm_substream *substream) snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, 64, 8192); + snd_pcm_hw_constraint_minmax(runtime, + SNDRV_PCM_HW_PARAM_PERIODS, + 2, 2); break; } @@ -6176,6 +6179,9 @@ static int snd_hdspm_capture_open(struct snd_pcm_substream *substream) snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, 64, 8192); + snd_pcm_hw_constraint_minmax(runtime, + SNDRV_PCM_HW_PARAM_PERIODS, + 2, 2); break; } diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c index 1ead3c9..f20e703 100644 --- a/sound/soc/atmel/atmel_ssc_dai.c +++ b/sound/soc/atmel/atmel_ssc_dai.c @@ -344,7 +344,6 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, struct atmel_pcm_dma_params *dma_params; int dir, channels, bits; u32 tfmr, rfmr, tcmr, rcmr; - int start_event; int ret; /* @@ -451,19 +450,10 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, * The SSC transmit clock is obtained from the BCLK signal on * on the TK line, and the SSC receive clock is * generated from the transmit clock. - * - * For single channel data, one sample is transferred - * on the falling edge of the LRC clock. - * For two channel data, one sample is - * transferred on both edges of the LRC clock. */ - start_event = ((channels == 1) - ? SSC_START_FALLING_RF - : SSC_START_EDGE_RF); - rcmr = SSC_BF(RCMR_PERIOD, 0) | SSC_BF(RCMR_STTDLY, START_DELAY) - | SSC_BF(RCMR_START, start_event) + | SSC_BF(RCMR_START, SSC_START_FALLING_RF) | SSC_BF(RCMR_CKI, SSC_CKI_RISING) | SSC_BF(RCMR_CKO, SSC_CKO_NONE) | SSC_BF(RCMR_CKS, SSC_CKS_CLOCK); @@ -471,14 +461,14 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, rfmr = SSC_BF(RFMR_FSEDGE, SSC_FSEDGE_POSITIVE) | SSC_BF(RFMR_FSOS, SSC_FSOS_NONE) | SSC_BF(RFMR_FSLEN, 0) - | SSC_BF(RFMR_DATNB, 0) + | SSC_BF(RFMR_DATNB, (channels - 1)) | SSC_BIT(RFMR_MSBF) | SSC_BF(RFMR_LOOP, 0) | SSC_BF(RFMR_DATLEN, (bits - 1)); tcmr = SSC_BF(TCMR_PERIOD, 0) | SSC_BF(TCMR_STTDLY, START_DELAY) - | SSC_BF(TCMR_START, start_event) + | SSC_BF(TCMR_START, SSC_START_FALLING_RF) | SSC_BF(TCMR_CKI, SSC_CKI_FALLING) | SSC_BF(TCMR_CKO, SSC_CKO_NONE) | SSC_BF(TCMR_CKS, SSC_CKS_PIN); @@ -487,7 +477,7 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, | SSC_BF(TFMR_FSDEN, 0) | SSC_BF(TFMR_FSOS, SSC_FSOS_NONE) | SSC_BF(TFMR_FSLEN, 0) - | SSC_BF(TFMR_DATNB, 0) + | SSC_BF(TFMR_DATNB, (channels - 1)) | SSC_BIT(TFMR_MSBF) | SSC_BF(TFMR_DATDEF, 0) | SSC_BF(TFMR_DATLEN, (bits - 1)); diff --git a/sound/soc/blackfin/bf5xx-i2s-pcm.c b/sound/soc/blackfin/bf5xx-i2s-pcm.c index a3881c4..bcf5913 100644 --- a/sound/soc/blackfin/bf5xx-i2s-pcm.c +++ b/sound/soc/blackfin/bf5xx-i2s-pcm.c @@ -290,19 +290,19 @@ static int bf5xx_pcm_silence(struct snd_pcm_substream *substream, unsigned int sample_size = runtime->sample_bits / 8; void *buf = runtime->dma_area; struct bf5xx_i2s_pcm_data *dma_data; - unsigned int offset, size; + unsigned int offset, samples; dma_data = snd_soc_dai_get_dma_data(rtd->cpu_dai, substream); if (dma_data->tdm_mode) { offset = pos * 8 * sample_size; - size = count * 8 * sample_size; + samples = count * 8; } else { offset = frames_to_bytes(runtime, pos); - size = frames_to_bytes(runtime, count); + samples = count * runtime->channels; } - snd_pcm_format_set_silence(runtime->format, buf + offset, size); + snd_pcm_format_set_silence(runtime->format, buf + offset, samples); return 0; } diff --git a/sound/soc/codecs/adau1701.c b/sound/soc/codecs/adau1701.c index d71c59c..370b742 100644 --- a/sound/soc/codecs/adau1701.c +++ b/sound/soc/codecs/adau1701.c @@ -230,8 +230,10 @@ static int adau1701_reg_read(void *context, unsigned int reg, *value = 0; - for (i = 0; i < size; i++) - *value |= recv_buf[i] << (i * 8); + for (i = 0; i < size; i++) { + *value <<= 8; + *value |= recv_buf[i]; + } return 0; } diff --git a/sound/soc/codecs/adav80x.c b/sound/soc/codecs/adav80x.c index f78b27a..23454e9 100644 --- a/sound/soc/codecs/adav80x.c +++ b/sound/soc/codecs/adav80x.c @@ -319,7 +319,7 @@ static int adav80x_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec); - unsigned int deemph = ucontrol->value.enumerated.item[0]; + unsigned int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; @@ -335,7 +335,7 @@ static int adav80x_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = adav80x->deemph; + ucontrol->value.integer.value[0] = adav80x->deemph; return 0; }; diff --git a/sound/soc/codecs/ak4641.c b/sound/soc/codecs/ak4641.c index 94cbe50..d718472 100644 --- a/sound/soc/codecs/ak4641.c +++ b/sound/soc/codecs/ak4641.c @@ -76,7 +76,7 @@ static int ak4641_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; @@ -92,7 +92,7 @@ static int ak4641_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = ak4641->deemph; + ucontrol->value.integer.value[0] = ak4641->deemph; return 0; }; diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c index ce05fd9..a0ad41a 100644 --- a/sound/soc/codecs/cs4271.c +++ b/sound/soc/codecs/cs4271.c @@ -288,7 +288,7 @@ static int cs4271_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = cs4271->deemph; + ucontrol->value.integer.value[0] = cs4271->deemph; return 0; } @@ -298,7 +298,7 @@ static int cs4271_put_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec); - cs4271->deemph = ucontrol->value.enumerated.item[0]; + cs4271->deemph = ucontrol->value.integer.value[0]; return cs4271_set_deemph(codec); } diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index b3f7c90..9dd260f 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -1378,8 +1378,8 @@ static const struct snd_soc_dapm_route max98090_dapm_routes[] = { {"STENL Mux", "Sidetone Left", "DMICL"}, {"STENR Mux", "Sidetone Right", "ADCR"}, {"STENR Mux", "Sidetone Right", "DMICR"}, - {"DACL", "NULL", "STENL Mux"}, - {"DACR", "NULL", "STENL Mux"}, + {"DACL", NULL, "STENL Mux"}, + {"DACR", NULL, "STENL Mux"}, {"AIFINL", NULL, "SHDN"}, {"AIFINR", NULL, "SHDN"}, @@ -2250,7 +2250,7 @@ static int max98090_probe(struct snd_soc_codec *codec) /* Register for interrupts */ dev_dbg(codec->dev, "irq = %d\n", max98090->irq); - ret = request_threaded_irq(max98090->irq, NULL, + ret = devm_request_threaded_irq(codec->dev, max98090->irq, NULL, max98090_interrupt, IRQF_TRIGGER_FALLING | IRQF_ONESHOT, "max98090_interrupt", codec); if (ret < 0) { diff --git a/sound/soc/codecs/mc13783.c b/sound/soc/codecs/mc13783.c index 582c2bb..b852293 100644 --- a/sound/soc/codecs/mc13783.c +++ b/sound/soc/codecs/mc13783.c @@ -634,14 +634,14 @@ static int mc13783_probe(struct snd_soc_codec *codec) AUDIO_SSI_SEL, 0); else mc13xxx_reg_rmw(priv->mc13xxx, MC13783_AUDIO_CODEC, - 0, AUDIO_SSI_SEL); + AUDIO_SSI_SEL, AUDIO_SSI_SEL); if (priv->dac_ssi_port == MC13783_SSI1_PORT) mc13xxx_reg_rmw(priv->mc13xxx, MC13783_AUDIO_DAC, AUDIO_SSI_SEL, 0); else mc13xxx_reg_rmw(priv->mc13xxx, MC13783_AUDIO_DAC, - 0, AUDIO_SSI_SEL); + AUDIO_SSI_SEL, AUDIO_SSI_SEL); return 0; } diff --git a/sound/soc/codecs/pcm1681.c b/sound/soc/codecs/pcm1681.c index 73f9c36..dfa9755 100644 --- a/sound/soc/codecs/pcm1681.c +++ b/sound/soc/codecs/pcm1681.c @@ -102,7 +102,7 @@ static int pcm1681_set_deemph(struct snd_soc_codec *codec) if (val != -1) { regmap_update_bits(priv->regmap, PCM1681_DEEMPH_CONTROL, - PCM1681_DEEMPH_RATE_MASK, val); + PCM1681_DEEMPH_RATE_MASK, val << 3); enable = 1; } else enable = 0; @@ -118,7 +118,7 @@ static int pcm1681_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct pcm1681_private *priv = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = priv->deemph; + ucontrol->value.integer.value[0] = priv->deemph; return 0; } @@ -129,7 +129,7 @@ static int pcm1681_put_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct pcm1681_private *priv = snd_soc_codec_get_drvdata(codec); - priv->deemph = ucontrol->value.enumerated.item[0]; + priv->deemph = ucontrol->value.integer.value[0]; return pcm1681_set_deemph(codec); } diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index 8869249..5cb515b 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -2071,6 +2071,7 @@ static struct snd_soc_codec_driver soc_codec_dev_rt5640 = { static const struct regmap_config rt5640_regmap = { .reg_bits = 8, .val_bits = 16, + .use_single_rw = true, .max_register = RT5640_VENDOR_ID2 + 1 + (ARRAY_SIZE(rt5640_ranges) * RT5640_PR_SPACING), diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index 893c95b..5ea3b4e 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -1379,8 +1379,7 @@ static int sgtl5000_probe(struct snd_soc_codec *codec) /* enable small pop, introduce 400ms delay in turning off */ snd_soc_update_bits(codec, SGTL5000_CHIP_REF_CTRL, - SGTL5000_SMALL_POP, - SGTL5000_SMALL_POP); + SGTL5000_SMALL_POP, 1); /* disable short cut detector */ snd_soc_write(codec, SGTL5000_CHIP_SHORT_CTRL, 0); @@ -1534,6 +1533,9 @@ static int sgtl5000_i2c_probe(struct i2c_client *client, if (ret) return ret; + /* Need 8 clocks before I2C accesses */ + udelay(1); + /* read chip information */ ret = regmap_read(sgtl5000->regmap, SGTL5000_CHIP_ID, ®); if (ret) diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h index 2f8c889..bd7a344 100644 --- a/sound/soc/codecs/sgtl5000.h +++ b/sound/soc/codecs/sgtl5000.h @@ -275,7 +275,7 @@ #define SGTL5000_BIAS_CTRL_MASK 0x000e #define SGTL5000_BIAS_CTRL_SHIFT 1 #define SGTL5000_BIAS_CTRL_WIDTH 3 -#define SGTL5000_SMALL_POP 0x0001 +#define SGTL5000_SMALL_POP 0 /* * SGTL5000_CHIP_MIC_CTRL diff --git a/sound/soc/codecs/sigmadsp.c b/sound/soc/codecs/sigmadsp.c index 4068f24..bb3878c 100644 --- a/sound/soc/codecs/sigmadsp.c +++ b/sound/soc/codecs/sigmadsp.c @@ -176,6 +176,13 @@ static int _process_sigma_firmware(struct device *dev, goto done; } + if (ssfw_head->version != 1) { + dev_err(dev, + "Failed to load firmware: Invalid version %d. Supported firmware versions: 1\n", + ssfw_head->version); + goto done; + } + crc = crc32(0, fw->data + sizeof(*ssfw_head), fw->size - sizeof(*ssfw_head)); pr_debug("%s: crc=%x\n", __func__, crc); diff --git a/sound/soc/codecs/tas5086.c b/sound/soc/codecs/tas5086.c index a895a5e..c6c6500 100644 --- a/sound/soc/codecs/tas5086.c +++ b/sound/soc/codecs/tas5086.c @@ -275,7 +275,7 @@ static int tas5086_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = priv->deemph; + ucontrol->value.integer.value[0] = priv->deemph; return 0; } @@ -286,7 +286,7 @@ static int tas5086_put_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec); - priv->deemph = ucontrol->value.enumerated.item[0]; + priv->deemph = ucontrol->value.integer.value[0]; return tas5086_set_deemph(codec); } diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index eb241c6..fd53d37 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -1121,6 +1121,7 @@ static int aic3x_regulator_event(struct notifier_block *nb, static int aic3x_set_power(struct snd_soc_codec *codec, int power) { struct aic3x_priv *aic3x = snd_soc_codec_get_drvdata(codec); + unsigned int pll_c, pll_d; int ret; if (power) { @@ -1138,6 +1139,18 @@ static int aic3x_set_power(struct snd_soc_codec *codec, int power) /* Sync reg_cache with the hardware */ regcache_cache_only(aic3x->regmap, false); regcache_sync(aic3x->regmap); + + /* Rewrite paired PLL D registers in case cached sync skipped + * writing one of them and thus caused other one also not + * being written + */ + pll_c = snd_soc_read(codec, AIC3X_PLL_PROGC_REG); + pll_d = snd_soc_read(codec, AIC3X_PLL_PROGD_REG); + if (pll_c == aic3x_reg[AIC3X_PLL_PROGC_REG].def || + pll_d == aic3x_reg[AIC3X_PLL_PROGD_REG].def) { + snd_soc_write(codec, AIC3X_PLL_PROGC_REG, pll_c); + snd_soc_write(codec, AIC3X_PLL_PROGD_REG, pll_d); + } } else { /* * Do soft reset to this codec instance in order to clear diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c index 8ae5027..1a9f457 100644 --- a/sound/soc/codecs/wm2000.c +++ b/sound/soc/codecs/wm2000.c @@ -610,7 +610,7 @@ static int wm2000_anc_mode_get(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev); - ucontrol->value.enumerated.item[0] = wm2000->anc_active; + ucontrol->value.integer.value[0] = wm2000->anc_active; return 0; } @@ -620,7 +620,7 @@ static int wm2000_anc_mode_put(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev); - int anc_active = ucontrol->value.enumerated.item[0]; + int anc_active = ucontrol->value.integer.value[0]; int ret; if (anc_active > 1) @@ -643,7 +643,7 @@ static int wm2000_speaker_get(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev); - ucontrol->value.enumerated.item[0] = wm2000->spk_ena; + ucontrol->value.integer.value[0] = wm2000->spk_ena; return 0; } @@ -653,7 +653,7 @@ static int wm2000_speaker_put(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev); - int val = ucontrol->value.enumerated.item[0]; + int val = ucontrol->value.integer.value[0]; int ret; if (val > 1) diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c index ce9c8e1..fbee45c 100644 --- a/sound/soc/codecs/wm5102.c +++ b/sound/soc/codecs/wm5102.c @@ -41,7 +41,7 @@ struct wm5102_priv { static DECLARE_TLV_DB_SCALE(ana_tlv, 0, 100, 0); static DECLARE_TLV_DB_SCALE(eq_tlv, -1200, 100, 0); static DECLARE_TLV_DB_SCALE(digital_tlv, -6400, 50, 0); -static DECLARE_TLV_DB_SCALE(noise_tlv, 0, 600, 0); +static DECLARE_TLV_DB_SCALE(noise_tlv, -13200, 600, 0); static DECLARE_TLV_DB_SCALE(ng_tlv, -10200, 600, 0); static const struct wm_adsp_region wm5102_dsp1_regions[] = { diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c index 2c3c962..0fce853 100644 --- a/sound/soc/codecs/wm5110.c +++ b/sound/soc/codecs/wm5110.c @@ -167,7 +167,7 @@ static int wm5110_sysclk_ev(struct snd_soc_dapm_widget *w, static DECLARE_TLV_DB_SCALE(ana_tlv, 0, 100, 0); static DECLARE_TLV_DB_SCALE(eq_tlv, -1200, 100, 0); static DECLARE_TLV_DB_SCALE(digital_tlv, -6400, 50, 0); -static DECLARE_TLV_DB_SCALE(noise_tlv, 0, 600, 0); +static DECLARE_TLV_DB_SCALE(noise_tlv, -13200, 600, 0); static DECLARE_TLV_DB_SCALE(ng_tlv, -10200, 600, 0); #define WM5110_NG_SRC(name, base) \ diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c index 0297203..e593722 100644 --- a/sound/soc/codecs/wm8731.c +++ b/sound/soc/codecs/wm8731.c @@ -122,7 +122,7 @@ static int wm8731_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8731->deemph; + ucontrol->value.integer.value[0] = wm8731->deemph; return 0; } @@ -132,7 +132,7 @@ static int wm8731_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; int ret = 0; if (deemph > 1) diff --git a/sound/soc/codecs/wm8737.c b/sound/soc/codecs/wm8737.c index 2f167a8..62bacb8 100644 --- a/sound/soc/codecs/wm8737.c +++ b/sound/soc/codecs/wm8737.c @@ -494,7 +494,8 @@ static int wm8737_set_bias_level(struct snd_soc_codec *codec, /* Fast VMID ramp at 2*2.5k */ snd_soc_update_bits(codec, WM8737_MISC_BIAS_CONTROL, - WM8737_VMIDSEL_MASK, 0x4); + WM8737_VMIDSEL_MASK, + 2 << WM8737_VMIDSEL_SHIFT); /* Bring VMID up */ snd_soc_update_bits(codec, WM8737_POWER_MANAGEMENT, @@ -508,7 +509,8 @@ static int wm8737_set_bias_level(struct snd_soc_codec *codec, /* VMID at 2*300k */ snd_soc_update_bits(codec, WM8737_MISC_BIAS_CONTROL, - WM8737_VMIDSEL_MASK, 2); + WM8737_VMIDSEL_MASK, + 1 << WM8737_VMIDSEL_SHIFT); break; diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c index eebcb1d..ae7d76e 100644 --- a/sound/soc/codecs/wm8903.c +++ b/sound/soc/codecs/wm8903.c @@ -442,7 +442,7 @@ static int wm8903_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8903->deemph; + ucontrol->value.integer.value[0] = wm8903->deemph; return 0; } @@ -452,7 +452,7 @@ static int wm8903_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; int ret = 0; if (deemph > 1) diff --git a/sound/soc/codecs/wm8903.h b/sound/soc/codecs/wm8903.h index db94931..0bb4a64 100644 --- a/sound/soc/codecs/wm8903.h +++ b/sound/soc/codecs/wm8903.h @@ -172,7 +172,7 @@ extern int wm8903_mic_detect(struct snd_soc_codec *codec, #define WM8903_VMID_BUF_ENA_WIDTH 1 /* VMID_BUF_ENA */ #define WM8903_VMID_RES_50K 2 -#define WM8903_VMID_RES_250K 3 +#define WM8903_VMID_RES_250K 4 #define WM8903_VMID_RES_5K 6 /* diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c index 53bbfac..66cb9e9 100644 --- a/sound/soc/codecs/wm8904.c +++ b/sound/soc/codecs/wm8904.c @@ -523,7 +523,7 @@ static int wm8904_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8904->deemph; + ucontrol->value.integer.value[0] = wm8904->deemph; return 0; } @@ -532,7 +532,7 @@ static int wm8904_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; diff --git a/sound/soc/codecs/wm8955.c b/sound/soc/codecs/wm8955.c index 82c8ba9..475fc24 100644 --- a/sound/soc/codecs/wm8955.c +++ b/sound/soc/codecs/wm8955.c @@ -298,7 +298,7 @@ static int wm8955_configure_clocking(struct snd_soc_codec *codec) snd_soc_update_bits(codec, WM8955_PLL_CONTROL_2, WM8955_K_17_9_MASK, (pll.k >> 9) & WM8955_K_17_9_MASK); - snd_soc_update_bits(codec, WM8955_PLL_CONTROL_2, + snd_soc_update_bits(codec, WM8955_PLL_CONTROL_3, WM8955_K_8_0_MASK, pll.k & WM8955_K_8_0_MASK); if (pll.k) @@ -393,7 +393,7 @@ static int wm8955_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8955->deemph; + ucontrol->value.integer.value[0] = wm8955->deemph; return 0; } @@ -402,7 +402,7 @@ static int wm8955_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c index f156010..e04dbaa 100644 --- a/sound/soc/codecs/wm8960.c +++ b/sound/soc/codecs/wm8960.c @@ -181,7 +181,7 @@ static int wm8960_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8960->deemph; + ucontrol->value.integer.value[0] = wm8960->deemph; return 0; } @@ -190,7 +190,7 @@ static int wm8960_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; @@ -242,7 +242,7 @@ SOC_SINGLE("PCM Playback -6dB Switch", WM8960_DACCTL1, 7, 1, 0), SOC_ENUM("ADC Polarity", wm8960_enum[0]), SOC_SINGLE("ADC High Pass Filter Switch", WM8960_DACCTL1, 0, 1, 0), -SOC_ENUM("DAC Polarity", wm8960_enum[2]), +SOC_ENUM("DAC Polarity", wm8960_enum[1]), SOC_SINGLE_BOOL_EXT("DAC Deemphasis Switch", 0, wm8960_get_deemph, wm8960_put_deemph), @@ -392,7 +392,7 @@ static const struct snd_soc_dapm_route audio_paths[] = { { "Right Input Mixer", "Boost Switch", "Right Boost Mixer", }, { "Right Input Mixer", NULL, "RINPUT1", }, /* Really Boost Switch */ { "Right Input Mixer", NULL, "RINPUT2" }, - { "Right Input Mixer", NULL, "LINPUT3" }, + { "Right Input Mixer", NULL, "RINPUT3" }, { "Left ADC", NULL, "Left Input Mixer" }, { "Right ADC", NULL, "Right Input Mixer" }, @@ -555,7 +555,7 @@ static struct { { 22050, 2 }, { 24000, 2 }, { 16000, 3 }, - { 11250, 4 }, + { 11025, 4 }, { 12000, 4 }, { 8000, 5 }, }; diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index adb7206..66aec0c 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -2745,7 +2745,7 @@ static struct { }; static int fs_ratios[] = { - 64, 128, 192, 256, 348, 512, 768, 1024, 1408, 1536 + 64, 128, 192, 256, 384, 512, 768, 1024, 1408, 1536 }; static int bclk_divs[] = { @@ -3497,6 +3497,7 @@ static irqreturn_t wm8994_mic_irq(int irq, void *data) return IRQ_HANDLED; } +/* Should be called with accdet_lock held */ static void wm1811_micd_stop(struct snd_soc_codec *codec) { struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); @@ -3504,14 +3505,10 @@ static void wm1811_micd_stop(struct snd_soc_codec *codec) if (!wm8994->jackdet) return; - mutex_lock(&wm8994->accdet_lock); - snd_soc_update_bits(codec, WM8958_MIC_DETECT_1, WM8958_MICD_ENA, 0); wm1811_jackdet_set_mode(codec, WM1811_JACKDET_MODE_JACK); - mutex_unlock(&wm8994->accdet_lock); - if (wm8994->wm8994->pdata.jd_ext_cap) snd_soc_dapm_disable_pin(&codec->dapm, "MICBIAS2"); @@ -3552,10 +3549,10 @@ static void wm8958_open_circuit_work(struct work_struct *work) open_circuit_work.work); struct device *dev = wm8994->wm8994->dev; - wm1811_micd_stop(wm8994->hubs.codec); - mutex_lock(&wm8994->accdet_lock); + wm1811_micd_stop(wm8994->hubs.codec); + dev_dbg(dev, "Reporting open circuit\n"); wm8994->jack_mic = false; diff --git a/sound/soc/codecs/wm8997.c b/sound/soc/codecs/wm8997.c index 555115e..1461ae61 100644 --- a/sound/soc/codecs/wm8997.c +++ b/sound/soc/codecs/wm8997.c @@ -40,7 +40,7 @@ struct wm8997_priv { static DECLARE_TLV_DB_SCALE(ana_tlv, 0, 100, 0); static DECLARE_TLV_DB_SCALE(eq_tlv, -1200, 100, 0); static DECLARE_TLV_DB_SCALE(digital_tlv, -6400, 50, 0); -static DECLARE_TLV_DB_SCALE(noise_tlv, 0, 600, 0); +static DECLARE_TLV_DB_SCALE(noise_tlv, -13200, 600, 0); static DECLARE_TLV_DB_SCALE(ng_tlv, -10200, 600, 0); static const struct reg_default wm8997_sysclk_reva_patch[] = { diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 444626f..0502e3f 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1341,6 +1341,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp) file, blocks, pos - firmware->size); out_fw: + regmap_async_complete(regmap); release_firmware(firmware); wm_adsp_buf_free(&buf_list); out: @@ -1745,3 +1746,5 @@ int wm_adsp2_init(struct wm_adsp *adsp, bool dvfs) return 0; } EXPORT_SYMBOL_GPL(wm_adsp2_init); + +MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/davinci/davinci-evm.c b/sound/soc/davinci/davinci-evm.c index 5e3bc3c..f40a7a4 100644 --- a/sound/soc/davinci/davinci-evm.c +++ b/sound/soc/davinci/davinci-evm.c @@ -384,18 +384,8 @@ static int davinci_evm_probe(struct platform_device *pdev) return ret; } -static int davinci_evm_remove(struct platform_device *pdev) -{ - struct snd_soc_card *card = platform_get_drvdata(pdev); - - snd_soc_unregister_card(card); - - return 0; -} - static struct platform_driver davinci_evm_driver = { .probe = davinci_evm_probe, - .remove = davinci_evm_remove, .driver = { .name = "davinci_evm", .owner = THIS_MODULE, diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c index 670afa2..7350ebb 100644 --- a/sound/soc/davinci/davinci-mcasp.c +++ b/sound/soc/davinci/davinci-mcasp.c @@ -418,8 +418,17 @@ static int davinci_config_channel_size(struct davinci_mcasp *mcasp, { u32 fmt; u32 tx_rotate = (word_length / 4) & 0x7; - u32 rx_rotate = (32 - word_length) / 4; u32 mask = (1ULL << word_length) - 1; + /* + * For captured data we should not rotate, inversion and masking is + * enoguh to get the data to the right position: + * Format data from bus after reverse (XRBUF) + * S16_LE: |LSB|MSB|xxx|xxx| |xxx|xxx|MSB|LSB| + * S24_3LE: |LSB|DAT|MSB|xxx| |xxx|MSB|DAT|LSB| + * S24_LE: |LSB|DAT|MSB|xxx| |xxx|MSB|DAT|LSB| + * S32_LE: |LSB|DAT|DAT|MSB| |MSB|DAT|DAT|LSB| + */ + u32 rx_rotate = 0; /* * if s BCLK-to-LRCLK ratio has been configured via the set_clkdiv() diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c index 25c31f1..2f63575 100644 --- a/sound/soc/dwc/designware_i2s.c +++ b/sound/soc/dwc/designware_i2s.c @@ -263,6 +263,19 @@ static void dw_i2s_shutdown(struct snd_pcm_substream *substream, snd_soc_dai_set_dma_data(dai, substream, NULL); } +static int dw_i2s_prepare(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(dai); + + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + i2s_write_reg(dev->i2s_base, TXFFR, 1); + else + i2s_write_reg(dev->i2s_base, RXFFR, 1); + + return 0; +} + static int dw_i2s_trigger(struct snd_pcm_substream *substream, int cmd, struct snd_soc_dai *dai) { @@ -294,6 +307,7 @@ static struct snd_soc_dai_ops dw_i2s_dai_ops = { .startup = dw_i2s_startup, .shutdown = dw_i2s_shutdown, .hw_params = dw_i2s_hw_params, + .prepare = dw_i2s_prepare, .trigger = dw_i2s_trigger, }; diff --git a/sound/soc/fsl/fsl_esai.h b/sound/soc/fsl/fsl_esai.h index 75e1403..dfdbaa0 100644 --- a/sound/soc/fsl/fsl_esai.h +++ b/sound/soc/fsl/fsl_esai.h @@ -302,7 +302,7 @@ #define ESAI_xCCR_xFP_MASK (((1 << ESAI_xCCR_xFP_WIDTH) - 1) << ESAI_xCCR_xFP_SHIFT) #define ESAI_xCCR_xFP(v) ((((v) - 1) << ESAI_xCCR_xFP_SHIFT) & ESAI_xCCR_xFP_MASK) #define ESAI_xCCR_xDC_SHIFT 9 -#define ESAI_xCCR_xDC_WIDTH 4 +#define ESAI_xCCR_xDC_WIDTH 5 #define ESAI_xCCR_xDC_MASK (((1 << ESAI_xCCR_xDC_WIDTH) - 1) << ESAI_xCCR_xDC_SHIFT) #define ESAI_xCCR_xDC(v) ((((v) - 1) << ESAI_xCCR_xDC_SHIFT) & ESAI_xCCR_xDC_MASK) #define ESAI_xCCR_xPSR_SHIFT 8 diff --git a/sound/soc/fsl/imx-wm8962.c b/sound/soc/fsl/imx-wm8962.c index fdd28a7..274c220 100644 --- a/sound/soc/fsl/imx-wm8962.c +++ b/sound/soc/fsl/imx-wm8962.c @@ -439,7 +439,7 @@ static int imx_wm8962_probe(struct platform_device *pdev) dev_err(&pdev->dev, "audmux internal port setup failed\n"); return ret; } - imx_audmux_v2_configure_port(ext_port, + ret = imx_audmux_v2_configure_port(ext_port, IMX_AUDMUX_V2_PTCR_SYN, IMX_AUDMUX_V2_PDCR_RXDSEL(int_port)); if (ret) { diff --git a/sound/soc/jz4740/Makefile b/sound/soc/jz4740/Makefile index be873c1..d32c540 100644 --- a/sound/soc/jz4740/Makefile +++ b/sound/soc/jz4740/Makefile @@ -1,10 +1,8 @@ # # Jz4740 Platform Support # -snd-soc-jz4740-objs := jz4740-pcm.o snd-soc-jz4740-i2s-objs := jz4740-i2s.o -obj-$(CONFIG_SND_JZ4740_SOC) += snd-soc-jz4740.o obj-$(CONFIG_SND_JZ4740_SOC_I2S) += snd-soc-jz4740-i2s.o # Jz4740 Machine Support diff --git a/sound/soc/omap/omap-mcbsp.c b/sound/soc/omap/omap-mcbsp.c index 6c19bba..6a339fb 100644 --- a/sound/soc/omap/omap-mcbsp.c +++ b/sound/soc/omap/omap-mcbsp.c @@ -436,7 +436,7 @@ static int omap_mcbsp_dai_set_dai_fmt(struct snd_soc_dai *cpu_dai, case SND_SOC_DAIFMT_CBM_CFS: /* McBSP slave. FS clock as output */ regs->srgr2 |= FSGM; - regs->pcr0 |= FSXM; + regs->pcr0 |= FSXM | FSRM; break; case SND_SOC_DAIFMT_CBM_CFM: /* McBSP slave */ diff --git a/sound/soc/omap/omap-pcm.c b/sound/soc/omap/omap-pcm.c index 07b8b7b..81f6a75 100644 --- a/sound/soc/omap/omap-pcm.c +++ b/sound/soc/omap/omap-pcm.c @@ -200,7 +200,7 @@ static int omap_pcm_new(struct snd_soc_pcm_runtime *rtd) struct snd_pcm *pcm = rtd->pcm; int ret; - ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(64)); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); if (ret) return ret; diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c index a3119a0..6c6b35e 100644 --- a/sound/soc/pxa/pxa-ssp.c +++ b/sound/soc/pxa/pxa-ssp.c @@ -725,7 +725,8 @@ static int pxa_ssp_probe(struct snd_soc_dai *dai) ssp_handle = of_parse_phandle(dev->of_node, "port", 0); if (!ssp_handle) { dev_err(dev, "unable to get 'port' phandle\n"); - return -ENODEV; + ret = -ENODEV; + goto err_priv; } priv->ssp = pxa_ssp_request_of(ssp_handle, "SoC audio"); @@ -766,9 +767,7 @@ static int pxa_ssp_remove(struct snd_soc_dai *dai) SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_64000 | \ SNDRV_PCM_RATE_88200 | SNDRV_PCM_RATE_96000) -#define PXA_SSP_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\ - SNDRV_PCM_FMTBIT_S24_LE | \ - SNDRV_PCM_FMTBIT_S32_LE) +#define PXA_SSP_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S32_LE) static const struct snd_soc_dai_ops pxa_ssp_dai_ops = { .startup = pxa_ssp_startup, diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c index 0a9b44c..5dae660 100644 --- a/sound/soc/samsung/i2s.c +++ b/sound/soc/samsung/i2s.c @@ -915,11 +915,9 @@ static int i2s_suspend(struct snd_soc_dai *dai) { struct i2s_dai *i2s = to_info(dai); - if (dai->active) { - i2s->suspend_i2smod = readl(i2s->addr + I2SMOD); - i2s->suspend_i2scon = readl(i2s->addr + I2SCON); - i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR); - } + i2s->suspend_i2smod = readl(i2s->addr + I2SMOD); + i2s->suspend_i2scon = readl(i2s->addr + I2SCON); + i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR); return 0; } @@ -928,11 +926,9 @@ static int i2s_resume(struct snd_soc_dai *dai) { struct i2s_dai *i2s = to_info(dai); - if (dai->active) { - writel(i2s->suspend_i2scon, i2s->addr + I2SCON); - writel(i2s->suspend_i2smod, i2s->addr + I2SMOD); - writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR); - } + writel(i2s->suspend_i2scon, i2s->addr + I2SCON); + writel(i2s->suspend_i2smod, i2s->addr + I2SMOD); + writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR); return 0; } diff --git a/sound/soc/sh/fsi.c b/sound/soc/sh/fsi.c index 1967f44..9d0c59c 100644 --- a/sound/soc/sh/fsi.c +++ b/sound/soc/sh/fsi.c @@ -1785,8 +1785,7 @@ static const struct snd_soc_dai_ops fsi_dai_ops = { static struct snd_pcm_hardware fsi_pcm_hardware = { .info = SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_MMAP | - SNDRV_PCM_INFO_MMAP_VALID | - SNDRV_PCM_INFO_PAUSE, + SNDRV_PCM_INFO_MMAP_VALID, .buffer_bytes_max = 64 * 1024, .period_bytes_min = 32, .period_bytes_max = 8192, diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index 743de5e..37fcd93 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -626,8 +626,7 @@ static void rsnd_dai_remove(struct platform_device *pdev, static struct snd_pcm_hardware rsnd_pcm_hardware = { .info = SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_MMAP | - SNDRV_PCM_INFO_MMAP_VALID | - SNDRV_PCM_INFO_PAUSE, + SNDRV_PCM_INFO_MMAP_VALID, .buffer_bytes_max = 64 * 1024, .period_bytes_min = 32, .period_bytes_max = 8192, diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index 5e9690c..4f98ff1 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -696,7 +696,8 @@ int soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) rtd->dai_link->stream_name); ret = snd_pcm_new_internal(rtd->card->snd_card, new_name, num, - 1, 0, &be_pcm); + rtd->dai_link->dpcm_playback, + rtd->dai_link->dpcm_capture, &be_pcm); if (ret < 0) { dev_err(rtd->card->dev, "ASoC: can't create compressed for %s\n", rtd->dai_link->name); @@ -705,8 +706,10 @@ int soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) rtd->pcm = be_pcm; rtd->fe_compr = 1; - be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd; - be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd; + if (rtd->dai_link->dpcm_playback) + be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd; + else if (rtd->dai_link->dpcm_capture) + be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd; memcpy(compr->ops, &soc_compr_dyn_ops, sizeof(soc_compr_dyn_ops)); } else memcpy(compr->ops, &soc_compr_ops, sizeof(soc_compr_ops)); diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 731d47b..e4da224 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -689,9 +689,9 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w, int shared; struct snd_kcontrol *kcontrol; bool wname_in_long_name, kcname_in_long_name; - char *long_name; + char *long_name = NULL; const char *name; - int ret; + int ret = 0; if (dapm->codec) prefix = dapm->codec->name_prefix; @@ -756,15 +756,17 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w, kcontrol = snd_soc_cnew(&w->kcontrol_news[kci], NULL, name, prefix); - kfree(long_name); - if (!kcontrol) - return -ENOMEM; + if (!kcontrol) { + ret = -ENOMEM; + goto exit_free; + } + kcontrol->private_free = dapm_kcontrol_free; ret = dapm_kcontrol_data_alloc(w, kcontrol); if (ret) { snd_ctl_free_one(kcontrol); - return ret; + goto exit_free; } ret = snd_ctl_add(card, kcontrol); @@ -772,17 +774,18 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w, dev_err(dapm->dev, "ASoC: failed to add widget %s dapm kcontrol %s: %d\n", w->name, name, ret); - return ret; + goto exit_free; } } ret = dapm_kcontrol_add_widget(kcontrol, w); - if (ret) - return ret; + if (ret == 0) + w->kcontrols[kci] = kcontrol; - w->kcontrols[kci] = kcontrol; +exit_free: + kfree(long_name); - return 0; + return ret; } /* create new dapm mixer control */ diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 8fa7cd3..18984c4 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1258,13 +1258,36 @@ static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream) dpcm_init_runtime_hw(runtime, &cpu_dai_drv->capture); } +static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd); + +/* Set FE's runtime_update state; the state is protected via PCM stream lock + * for avoiding the race with trigger callback. + * If the state is unset and a trigger is pending while the previous operation, + * process the pending trigger action here. + */ +static void dpcm_set_fe_update_state(struct snd_soc_pcm_runtime *fe, + int stream, enum snd_soc_dpcm_update state) +{ + struct snd_pcm_substream *substream = + snd_soc_dpcm_get_substream(fe, stream); + + snd_pcm_stream_lock_irq(substream); + if (state == SND_SOC_DPCM_UPDATE_NO && fe->dpcm[stream].trigger_pending) { + dpcm_fe_dai_do_trigger(substream, + fe->dpcm[stream].trigger_pending - 1); + fe->dpcm[stream].trigger_pending = 0; + } + fe->dpcm[stream].runtime_update = state; + snd_pcm_stream_unlock_irq(substream); +} + static int dpcm_fe_dai_startup(struct snd_pcm_substream *fe_substream) { struct snd_soc_pcm_runtime *fe = fe_substream->private_data; struct snd_pcm_runtime *runtime = fe_substream->runtime; int stream = fe_substream->stream, ret = 0; - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE); ret = dpcm_be_dai_startup(fe, fe_substream->stream); if (ret < 0) { @@ -1286,13 +1309,13 @@ static int dpcm_fe_dai_startup(struct snd_pcm_substream *fe_substream) dpcm_set_fe_runtime(fe_substream); snd_pcm_limit_hw_rates(runtime); - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); return 0; unwind: dpcm_be_dai_startup_unwind(fe, fe_substream->stream); be_err: - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); return ret; } @@ -1339,7 +1362,7 @@ static int dpcm_fe_dai_shutdown(struct snd_pcm_substream *substream) struct snd_soc_pcm_runtime *fe = substream->private_data; int stream = substream->stream; - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE); /* shutdown the BEs */ dpcm_be_dai_shutdown(fe, substream->stream); @@ -1353,7 +1376,7 @@ static int dpcm_fe_dai_shutdown(struct snd_pcm_substream *substream) dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_STOP); fe->dpcm[stream].state = SND_SOC_DPCM_STATE_CLOSE; - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); return 0; } @@ -1401,7 +1424,7 @@ static int dpcm_fe_dai_hw_free(struct snd_pcm_substream *substream) int err, stream = substream->stream; mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME); - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE); dev_dbg(fe->dev, "ASoC: hw_free FE %s\n", fe->dai_link->name); @@ -1416,7 +1439,7 @@ static int dpcm_fe_dai_hw_free(struct snd_pcm_substream *substream) err = dpcm_be_dai_hw_free(fe, stream); fe->dpcm[stream].state = SND_SOC_DPCM_STATE_HW_FREE; - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); mutex_unlock(&fe->card->mutex); return 0; @@ -1509,7 +1532,7 @@ static int dpcm_fe_dai_hw_params(struct snd_pcm_substream *substream, int ret, stream = substream->stream; mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME); - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE); memcpy(&fe->dpcm[substream->stream].hw_params, params, sizeof(struct snd_pcm_hw_params)); @@ -1532,7 +1555,7 @@ static int dpcm_fe_dai_hw_params(struct snd_pcm_substream *substream, fe->dpcm[stream].state = SND_SOC_DPCM_STATE_HW_PARAMS; out: - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); mutex_unlock(&fe->card->mutex); return ret; } @@ -1646,7 +1669,7 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream, } EXPORT_SYMBOL_GPL(dpcm_be_dai_trigger); -static int dpcm_fe_dai_trigger(struct snd_pcm_substream *substream, int cmd) +static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd) { struct snd_soc_pcm_runtime *fe = substream->private_data; int stream = substream->stream, ret; @@ -1720,6 +1743,23 @@ out: return ret; } +static int dpcm_fe_dai_trigger(struct snd_pcm_substream *substream, int cmd) +{ + struct snd_soc_pcm_runtime *fe = substream->private_data; + int stream = substream->stream; + + /* if FE's runtime_update is already set, we're in race; + * process this trigger later at exit + */ + if (fe->dpcm[stream].runtime_update != SND_SOC_DPCM_UPDATE_NO) { + fe->dpcm[stream].trigger_pending = cmd + 1; + return 0; /* delayed, assuming it's successful */ + } + + /* we're alone, let's trigger */ + return dpcm_fe_dai_do_trigger(substream, cmd); +} + int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream) { struct snd_soc_dpcm *dpcm; @@ -1763,7 +1803,7 @@ static int dpcm_fe_dai_prepare(struct snd_pcm_substream *substream) dev_dbg(fe->dev, "ASoC: prepare FE %s\n", fe->dai_link->name); - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE); /* there is no point preparing this FE if there are no BEs */ if (list_empty(&fe->dpcm[stream].be_clients)) { @@ -1790,7 +1830,7 @@ static int dpcm_fe_dai_prepare(struct snd_pcm_substream *substream) fe->dpcm[stream].state = SND_SOC_DPCM_STATE_PREPARE; out: - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); mutex_unlock(&fe->card->mutex); return ret; @@ -1937,11 +1977,11 @@ static int dpcm_run_new_update(struct snd_soc_pcm_runtime *fe, int stream) { int ret; - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_BE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_BE); ret = dpcm_run_update_startup(fe, stream); if (ret < 0) dev_err(fe->dev, "ASoC: failed to startup some BEs\n"); - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); return ret; } @@ -1950,11 +1990,11 @@ static int dpcm_run_old_update(struct snd_soc_pcm_runtime *fe, int stream) { int ret; - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_BE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_BE); ret = dpcm_run_update_shutdown(fe, stream); if (ret < 0) dev_err(fe->dev, "ASoC: failed to shutdown some BEs\n"); - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); return ret; } @@ -2011,6 +2051,7 @@ int soc_dpcm_runtime_update(struct snd_soc_card *card) dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_PLAYBACK); } + dpcm_path_put(&list); capture: /* skip if FE doesn't have capture capability */ if (!fe->cpu_dai->driver->capture.channels_min) diff --git a/sound/synth/emux/emux_oss.c b/sound/synth/emux/emux_oss.c index 319754c..daf61ab 100644 --- a/sound/synth/emux/emux_oss.c +++ b/sound/synth/emux/emux_oss.c @@ -118,12 +118,8 @@ snd_emux_open_seq_oss(struct snd_seq_oss_arg *arg, void *closure) if (snd_BUG_ON(!arg || !emu)) return -ENXIO; - mutex_lock(&emu->register_mutex); - - if (!snd_emux_inc_count(emu)) { - mutex_unlock(&emu->register_mutex); + if (!snd_emux_inc_count(emu)) return -EFAULT; - } memset(&callback, 0, sizeof(callback)); callback.owner = THIS_MODULE; @@ -135,7 +131,6 @@ snd_emux_open_seq_oss(struct snd_seq_oss_arg *arg, void *closure) if (p == NULL) { snd_printk(KERN_ERR "can't create port\n"); snd_emux_dec_count(emu); - mutex_unlock(&emu->register_mutex); return -ENOMEM; } @@ -148,8 +143,6 @@ snd_emux_open_seq_oss(struct snd_seq_oss_arg *arg, void *closure) reset_port_mode(p, arg->seq_mode); snd_emux_reset_port(p); - - mutex_unlock(&emu->register_mutex); return 0; } @@ -195,13 +188,11 @@ snd_emux_close_seq_oss(struct snd_seq_oss_arg *arg) if (snd_BUG_ON(!emu)) return -ENXIO; - mutex_lock(&emu->register_mutex); snd_emux_sounds_off_all(p); snd_soundfont_close_check(emu->sflist, SF_CLIENT_NO(p->chset.port)); snd_seq_event_port_detach(p->chset.client, p->chset.port); snd_emux_dec_count(emu); - mutex_unlock(&emu->register_mutex); return 0; } diff --git a/sound/synth/emux/emux_seq.c b/sound/synth/emux/emux_seq.c index 7778b8e..a020920 100644 --- a/sound/synth/emux/emux_seq.c +++ b/sound/synth/emux/emux_seq.c @@ -124,12 +124,10 @@ snd_emux_detach_seq(struct snd_emux *emu) if (emu->voices) snd_emux_terminate_all(emu); - mutex_lock(&emu->register_mutex); if (emu->client >= 0) { snd_seq_delete_kernel_client(emu->client); emu->client = -1; } - mutex_unlock(&emu->register_mutex); } @@ -269,8 +267,8 @@ snd_emux_event_input(struct snd_seq_event *ev, int direct, void *private_data, /* * increment usage count */ -int -snd_emux_inc_count(struct snd_emux *emu) +static int +__snd_emux_inc_count(struct snd_emux *emu) { emu->used++; if (!try_module_get(emu->ops.owner)) @@ -284,12 +282,21 @@ snd_emux_inc_count(struct snd_emux *emu) return 1; } +int snd_emux_inc_count(struct snd_emux *emu) +{ + int ret; + + mutex_lock(&emu->register_mutex); + ret = __snd_emux_inc_count(emu); + mutex_unlock(&emu->register_mutex); + return ret; +} /* * decrease usage count */ -void -snd_emux_dec_count(struct snd_emux *emu) +static void +__snd_emux_dec_count(struct snd_emux *emu) { module_put(emu->card->module); emu->used--; @@ -298,6 +305,12 @@ snd_emux_dec_count(struct snd_emux *emu) module_put(emu->ops.owner); } +void snd_emux_dec_count(struct snd_emux *emu) +{ + mutex_lock(&emu->register_mutex); + __snd_emux_dec_count(emu); + mutex_unlock(&emu->register_mutex); +} /* * Routine that is called upon a first use of a particular port @@ -317,7 +330,7 @@ snd_emux_use(void *private_data, struct snd_seq_port_subscribe *info) mutex_lock(&emu->register_mutex); snd_emux_init_port(p); - snd_emux_inc_count(emu); + __snd_emux_inc_count(emu); mutex_unlock(&emu->register_mutex); return 0; } @@ -340,7 +353,7 @@ snd_emux_unuse(void *private_data, struct snd_seq_port_subscribe *info) mutex_lock(&emu->register_mutex); snd_emux_sounds_off_all(p); - snd_emux_dec_count(emu); + __snd_emux_dec_count(emu); mutex_unlock(&emu->register_mutex); return 0; } diff --git a/sound/usb/card.c b/sound/usb/card.c index af19560..ab433a0 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -586,18 +586,19 @@ static void snd_usb_audio_disconnect(struct usb_device *dev, { struct snd_card *card; struct list_head *p; + bool was_shutdown; if (chip == (void *)-1L) return; card = chip->card; down_write(&chip->shutdown_rwsem); + was_shutdown = chip->shutdown; chip->shutdown = 1; up_write(&chip->shutdown_rwsem); mutex_lock(®ister_mutex); - chip->num_interfaces--; - if (chip->num_interfaces <= 0) { + if (!was_shutdown) { struct snd_usb_endpoint *ep; snd_card_disconnect(card); @@ -617,6 +618,10 @@ static void snd_usb_audio_disconnect(struct usb_device *dev, list_for_each(p, &chip->mixer_list) { snd_usb_mixer_disconnect(p); } + } + + chip->num_interfaces--; + if (chip->num_interfaces <= 0) { usb_chip[chip->index] = NULL; mutex_unlock(®ister_mutex); snd_card_free_when_closed(card); diff --git a/sound/usb/midi.c b/sound/usb/midi.c index b901f46..c7aa71e 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -364,6 +364,8 @@ static void snd_usbmidi_error_timer(unsigned long data) if (in && in->error_resubmit) { in->error_resubmit = 0; for (j = 0; j < INPUT_URBS; ++j) { + if (atomic_read(&in->urbs[j]->use_count)) + continue; in->urbs[j]->dev = umidi->dev; snd_usbmidi_submit_urb(in->urbs[j], GFP_ATOMIC); } diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 1bed780..c601033 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -886,10 +886,12 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval, case USB_ID(0x046d, 0x0807): /* Logitech Webcam C500 */ case USB_ID(0x046d, 0x0808): case USB_ID(0x046d, 0x0809): + case USB_ID(0x046d, 0x0819): /* Logitech Webcam C210 */ case USB_ID(0x046d, 0x081b): /* HD Webcam c310 */ case USB_ID(0x046d, 0x081d): /* HD Webcam c510 */ case USB_ID(0x046d, 0x0825): /* HD Webcam c270 */ case USB_ID(0x046d, 0x0826): /* HD Webcam c525 */ + case USB_ID(0x046d, 0x08ca): /* Logitech Quickcam Fusion */ case USB_ID(0x046d, 0x0991): /* Most audio usb devices lie about volume resolution. * Most Logitech webcams have res = 384. diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index d1d72ff..9a3e107 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -328,11 +328,28 @@ static struct usbmix_name_map gamecom780_map[] = { {} }; -static const struct usbmix_name_map kef_x300a_map[] = { - { 10, NULL }, /* firmware locks up (?) when we try to access this FU */ +/* some (all?) SCMS USB3318 devices are affected by a firmware lock up + * when anything attempts to access FU 10 (control) + */ +static const struct usbmix_name_map scms_usb3318_map[] = { + { 10, NULL }, { 0 } }; +/* Bose companion 5, the dB conversion factor is 16 instead of 256 */ +static struct usbmix_dB_map bose_companion5_dB = {-5006, -6}; +static struct usbmix_name_map bose_companion5_map[] = { + { 3, NULL, .dB = &bose_companion5_dB }, + { 0 } /* terminator */ +}; + +/* Dragonfly DAC 1.2, the dB conversion factor is 1 instead of 256 */ +static struct usbmix_dB_map dragonfly_1_2_dB = {0, 5000}; +static struct usbmix_name_map dragonfly_1_2_map[] = { + { 7, NULL, .dB = &dragonfly_1_2_dB }, + { 0 } /* terminator */ +}; + /* * Control map entries */ @@ -425,8 +442,29 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = { .map = ebox44_map, }, { + /* MAYA44 USB+ */ + .id = USB_ID(0x2573, 0x0008), + .map = maya44_map, + }, + { + /* KEF X300A */ .id = USB_ID(0x27ac, 0x1000), - .map = kef_x300a_map, + .map = scms_usb3318_map, + }, + { + /* Arcam rPAC */ + .id = USB_ID(0x25c4, 0x0003), + .map = scms_usb3318_map, + }, + { + /* Bose Companion 5 */ + .id = USB_ID(0x05a7, 0x1020), + .map = bose_companion5_map, + }, + { + /* Dragonfly DAC 1.2 */ + .id = USB_ID(0x21b4, 0x0081), + .map = dragonfly_1_2_map, }, { 0 } /* terminator */ }; diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index f4b12c2..a82ec53 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -178,6 +178,7 @@ static const struct rc_config { { USB_ID(0x041e, 0x3040), 2, 2, 6, 6, 2, 0x6e91 }, /* Live! 24-bit */ { USB_ID(0x041e, 0x3042), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 */ { USB_ID(0x041e, 0x30df), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 Pro */ + { USB_ID(0x041e, 0x3237), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 Pro */ { USB_ID(0x041e, 0x3048), 2, 2, 6, 6, 2, 0x6e91 }, /* Toshiba SB0500 */ }; @@ -885,6 +886,11 @@ static int snd_ftu_eff_switch_put(struct snd_kcontrol *kctl, return changed; } +static void kctl_private_value_free(struct snd_kcontrol *kctl) +{ + kfree((void *)kctl->private_value); +} + static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer, int validx, int bUnitID) { @@ -919,6 +925,7 @@ static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer, return -ENOMEM; } + kctl->private_free = kctl_private_value_free; err = snd_ctl_add(mixer->chip->card, kctl); if (err < 0) return err; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index f652b10..7c24088 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -385,6 +385,36 @@ YAMAHA_DEVICE(0x105d, NULL), } }, { + USB_DEVICE(0x0499, 0x1509), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + /* .vendor_name = "Yamaha", */ + /* .product_name = "Steinberg UR22", */ + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 3, + .type = QUIRK_MIDI_YAMAHA + }, + { + .ifnum = 4, + .type = QUIRK_IGNORE_INTERFACE + }, + { + .ifnum = -1 + } + } + } +}, +{ USB_DEVICE(0x0499, 0x150a), .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { /* .vendor_name = "Yamaha", */ @@ -1581,6 +1611,35 @@ YAMAHA_DEVICE(0x7010, "UB99"), } }, { + /* BOSS ME-25 */ + USB_DEVICE(0x0582, 0x0113), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_MIDI_FIXED_ENDPOINT, + .data = & (const struct snd_usb_midi_endpoint_info) { + .out_cables = 0x0001, + .in_cables = 0x0001 + } + }, + { + .ifnum = -1 + } + } + } +}, +{ /* only 44.1 kHz works at the moment */ USB_DEVICE(0x0582, 0x0120), .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { @@ -1714,6 +1773,36 @@ YAMAHA_DEVICE(0x7010, "UB99"), } } }, +{ + USB_DEVICE(0x0582, 0x0159), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + /* .vendor_name = "Roland", */ + /* .product_name = "UA-22", */ + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_MIDI_FIXED_ENDPOINT, + .data = & (const struct snd_usb_midi_endpoint_info) { + .out_cables = 0x0001, + .in_cables = 0x0001 + } + }, + { + .ifnum = -1 + } + } + } +}, /* this catches most recent vendor-specific Roland devices */ { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | @@ -2427,6 +2516,74 @@ YAMAHA_DEVICE(0x7010, "UB99"), } }, +/* Steinberg devices */ +{ + /* Steinberg MI2 */ + USB_DEVICE_VENDOR_SPEC(0x0a4e, 0x2040), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = & (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 3, + .type = QUIRK_MIDI_FIXED_ENDPOINT, + .data = &(const struct snd_usb_midi_endpoint_info) { + .out_cables = 0x0001, + .in_cables = 0x0001 + } + }, + { + .ifnum = -1 + } + } + } +}, +{ + /* Steinberg MI4 */ + USB_DEVICE_VENDOR_SPEC(0x0a4e, 0x4040), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = & (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 3, + .type = QUIRK_MIDI_FIXED_ENDPOINT, + .data = &(const struct snd_usb_midi_endpoint_info) { + .out_cables = 0x0001, + .in_cables = 0x0001 + } + }, + { + .ifnum = -1 + } + } + } +}, + /* TerraTec devices */ { USB_DEVICE_VENDOR_SPEC(0x0ccd, 0x0012), @@ -2745,133 +2902,45 @@ YAMAHA_DEVICE(0x7010, "UB99"), } }, -/* Hauppauge HVR-950Q and HVR-850 */ -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x7200), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x7210), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x7217), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x721b), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x721e), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x721f), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x7240), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-850", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x7280), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x0fd9, 0x0008), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, +/* + * Auvitek au0828 devices with audio interface. + * This should be kept in sync with drivers/media/usb/au0828/au0828-cards.c + * Please notice that some drivers are DVB only, and don't need to be + * here. That's the case, for example, of DVICO_FUSIONHDTV7. + */ + +#define AU0828_DEVICE(vid, pid, vname, pname) { \ + USB_DEVICE_VENDOR_SPEC(vid, pid), \ + .match_flags = USB_DEVICE_ID_MATCH_DEVICE | \ + USB_DEVICE_ID_MATCH_INT_CLASS | \ + USB_DEVICE_ID_MATCH_INT_SUBCLASS, \ + .bInterfaceClass = USB_CLASS_AUDIO, \ + .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, \ + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { \ + .vendor_name = vname, \ + .product_name = pname, \ + .ifnum = QUIRK_ANY_INTERFACE, \ + .type = QUIRK_AUDIO_ALIGN_TRANSFER, \ + } \ +} + +AU0828_DEVICE(0x2040, 0x7200, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x7240, "Hauppauge", "HVR-850"), +AU0828_DEVICE(0x2040, 0x7210, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x7217, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x721b, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x721e, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x721f, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x7280, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x0fd9, 0x0008, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x7201, "Hauppauge", "HVR-950Q-MXL"), +AU0828_DEVICE(0x2040, 0x7211, "Hauppauge", "HVR-950Q-MXL"), +AU0828_DEVICE(0x2040, 0x7281, "Hauppauge", "HVR-950Q-MXL"), +AU0828_DEVICE(0x05e1, 0x0480, "Hauppauge", "Woodbury"), +AU0828_DEVICE(0x2040, 0x8200, "Hauppauge", "Woodbury"), +AU0828_DEVICE(0x2040, 0x7260, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x7213, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), /* Digidesign Mbox */ { diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 8973070..827d404 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -666,7 +666,7 @@ static int snd_usb_gamecon780_boot_quirk(struct usb_device *dev) /* set the initial volume and don't change; other values are either * too loud or silent due to firmware bug (bko#65251) */ - u8 buf[2] = { 0x74, 0xdc }; + u8 buf[2] = { 0x74, 0xe3 }; return snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC_SET_CUR, USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_OUT, UAC_FU_VOLUME << 8, 9 << 8, buf, 2); @@ -1142,6 +1142,20 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, if ((le16_to_cpu(dev->descriptor.idVendor) == 0x23ba) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) mdelay(20); + + /* Marantz/Denon devices with USB DAC functionality need a delay + * after each class compliant request + */ + if ((le16_to_cpu(dev->descriptor.idVendor) == 0x154e) && + (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) { + + switch (le16_to_cpu(dev->descriptor.idProduct)) { + case 0x3005: /* Marantz HD-DAC1 */ + case 0x3006: /* Marantz SA-14S1 */ + mdelay(20); + break; + } + } } /* diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c index dcc6652..deb3569 100644 --- a/tools/lib/traceevent/kbuffer-parse.c +++ b/tools/lib/traceevent/kbuffer-parse.c @@ -372,7 +372,6 @@ translate_data(struct kbuffer *kbuf, void *data, void **rptr, switch (type_len) { case KBUFFER_TYPE_PADDING: *length = read_4(kbuf, data); - data += *length; break; case KBUFFER_TYPE_TIME_EXTEND: diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index a59743f..0001c9a 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -36,6 +36,7 @@ struct events_stats { u32 nr_invalid_chains; u32 nr_unknown_id; u32 nr_unprocessable_samples; + u32 nr_unordered_events; }; enum hist_column { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 5da6ce7..c1f20e9 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -638,8 +638,7 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event, return -ETIME; if (timestamp < s->ordered_samples.last_flush) { - printf("Warning: Timestamp below last timeslice flush\n"); - return -EINVAL; + s->stats.nr_unordered_events++; } if (!list_empty(sc)) { @@ -1135,6 +1134,8 @@ static void perf_session__warn_about_errors(const struct perf_session *session, "Do you have a KVM guest running and not using 'perf kvm'?\n", session->stats.nr_unprocessable_samples); } + if (session->stats.nr_unordered_events != 0) + ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events); } volatile int session_done; diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index d1b3a36..4039854 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -1,8 +1,12 @@ CC = $(CROSS_COMPILE)gcc -BUILD_OUTPUT := $(PWD) +BUILD_OUTPUT := $(CURDIR) PREFIX := /usr DESTDIR := +ifeq ("$(origin O)", "command line") + BUILD_OUTPUT := $(O) +endif + turbostat : turbostat.c CFLAGS += -Wall CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"' diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 32487ed..3d5979b2 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -4,6 +4,7 @@ TARGETS += efivarfs TARGETS += kcmp TARGETS += memory-hotplug TARGETS += mqueue +TARGETS += mount TARGETS += net TARGETS += ptrace TARGETS += timers diff --git a/tools/vm/Makefile b/tools/vm/Makefile index 3d907da..c604f3e 100644 --- a/tools/vm/Makefile +++ b/tools/vm/Makefile @@ -3,7 +3,7 @@ TARGETS=page-types slabinfo LIB_DIR = ../lib/api -LIBS = $(LIB_DIR)/libapikfs.a +LIBS = $(LIB_DIR)/libapi.a CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall -Wextra -I../lib/ diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 5081e80..c6fe405 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -61,12 +61,14 @@ static void timer_disarm(struct arch_timer_cpu *timer) static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu) { + int ret; struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; timer->cntv_ctl |= ARCH_TIMER_CTRL_IT_MASK; - kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, - timer->irq->irq, - timer->irq->level); + ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, + timer->irq->irq, + timer->irq->level); + WARN_ON(ret); } static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) @@ -307,12 +309,24 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) timer_disarm(timer); } -int kvm_timer_init(struct kvm *kvm) +void kvm_timer_enable(struct kvm *kvm) { - if (timecounter && wqueue) { - kvm->arch.timer.cntvoff = kvm_phys_timer_read(); + if (kvm->arch.timer.enabled) + return; + + /* + * There is a potential race here between VCPUs starting for the first + * time, which may be enabling the timer multiple times. That doesn't + * hurt though, because we're just setting a variable to the same + * variable that it already was. The important thing is that all + * VCPUs have the enabled variable set, before entering the guest, if + * the arch timers are enabled. + */ + if (timecounter && wqueue) kvm->arch.timer.enabled = 1; - } +} - return 0; +void kvm_timer_init(struct kvm *kvm) +{ + kvm->arch.timer.cntvoff = kvm_phys_timer_read(); } diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 26954a7..152ec76 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -548,11 +548,10 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu, u32 val; u32 *reg; - offset >>= 1; reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg, - vcpu->vcpu_id, offset); + vcpu->vcpu_id, offset >> 1); - if (offset & 2) + if (offset & 4) val = *reg >> 16; else val = *reg & 0xffff; @@ -561,13 +560,13 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu, vgic_reg_access(mmio, &val, offset, ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); if (mmio->is_write) { - if (offset < 4) { + if (offset < 8) { *reg = ~0U; /* Force PPIs/SGIs to 1 */ return false; } val = vgic_cfg_compress(val); - if (offset & 2) { + if (offset & 4) { *reg &= 0xffff; *reg |= val << 16; } else { @@ -675,7 +674,7 @@ static bool read_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu, { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; int sgi; - int min_sgi = (offset & ~0x3) * 4; + int min_sgi = (offset & ~0x3); int max_sgi = min_sgi + 3; int vcpu_id = vcpu->vcpu_id; u32 reg = 0; @@ -696,7 +695,7 @@ static bool write_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu, { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; int sgi; - int min_sgi = (offset & ~0x3) * 4; + int min_sgi = (offset & ~0x3); int max_sgi = min_sgi + 3; int vcpu_id = vcpu->vcpu_id; u32 reg; @@ -1043,6 +1042,7 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) lr, irq, vgic_cpu->vgic_lr[lr]); BUG_ON(!test_bit(lr, vgic_cpu->lr_used)); vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT; + __clear_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr); return true; } @@ -1056,6 +1056,7 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) vgic_cpu->vgic_lr[lr] = MK_LR_PEND(sgi_source_id, irq); vgic_cpu->vgic_irq_lr_map[irq] = lr; set_bit(lr, vgic_cpu->lr_used); + __clear_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr); if (!vgic_irq_is_edge(vcpu, irq)) vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI; @@ -1210,6 +1211,14 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) if (vgic_cpu->vgic_misr & GICH_MISR_U) vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE; + /* + * In the next iterations of the vcpu loop, if we sync the vgic state + * after flushing it, but before entering the guest (this happens for + * pending signals and vmid rollovers), then make sure we don't pick + * up any old maintenance interrupts here. + */ + memset(vgic_cpu->vgic_eisr, 0, sizeof(vgic_cpu->vgic_eisr[0]) * 2); + return level_pending; } @@ -1388,7 +1397,8 @@ out: int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, bool level) { - if (vgic_update_irq_state(kvm, cpuid, irq_num, level)) + if (likely(vgic_initialized(kvm)) && + vgic_update_irq_state(kvm, cpuid, irq_num, level)) vgic_kick_vcpus(kvm); return 0; @@ -1527,17 +1537,33 @@ int kvm_vgic_hyp_init(void) goto out_unmap; } - kvm_info("%s@%llx IRQ%d\n", vgic_node->name, - vctrl_res.start, vgic_maint_irq); - on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1); - if (of_address_to_resource(vgic_node, 3, &vcpu_res)) { kvm_err("Cannot obtain VCPU resource\n"); ret = -ENXIO; goto out_unmap; } + + if (!PAGE_ALIGNED(vcpu_res.start)) { + kvm_err("GICV physical address 0x%llx not page aligned\n", + (unsigned long long)vcpu_res.start); + ret = -ENXIO; + goto out_unmap; + } + + if (!PAGE_ALIGNED(resource_size(&vcpu_res))) { + kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n", + (unsigned long long)resource_size(&vcpu_res), + PAGE_SIZE); + ret = -ENXIO; + goto out_unmap; + } + vgic_vcpu_base = vcpu_res.start; + kvm_info("%s@%llx IRQ%d\n", vgic_node->name, + vctrl_res.start, vgic_maint_irq); + on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1); + goto out; out_unmap: @@ -1595,7 +1621,7 @@ out: int kvm_vgic_create(struct kvm *kvm) { - int i, vcpu_lock_idx = -1, ret = 0; + int i, vcpu_lock_idx = -1, ret; struct kvm_vcpu *vcpu; mutex_lock(&kvm->lock); @@ -1610,6 +1636,7 @@ int kvm_vgic_create(struct kvm *kvm) * vcpu->mutex. By grabbing the vcpu->mutex of all VCPUs we ensure * that no other VCPUs are run while we create the vgic. */ + ret = -EBUSY; kvm_for_each_vcpu(i, vcpu, kvm) { if (!mutex_trylock(&vcpu->mutex)) goto out_unlock; @@ -1617,11 +1644,10 @@ int kvm_vgic_create(struct kvm *kvm) } kvm_for_each_vcpu(i, vcpu, kvm) { - if (vcpu->arch.has_run_once) { - ret = -EBUSY; + if (vcpu->arch.has_run_once) goto out_unlock; - } } + ret = 0; spin_lock_init(&kvm->arch.vgic.lock); kvm->arch.vgic.vctrl_base = vgic_vctrl_base; @@ -1639,7 +1665,7 @@ out: return ret; } -static bool vgic_ioaddr_overlap(struct kvm *kvm) +static int vgic_ioaddr_overlap(struct kvm *kvm) { phys_addr_t dist = kvm->arch.vgic.vgic_dist_base; phys_addr_t cpu = kvm->arch.vgic.vgic_cpu_base; @@ -1668,10 +1694,11 @@ static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr, if (addr + size < addr) return -EINVAL; + *ioaddr = addr; ret = vgic_ioaddr_overlap(kvm); if (ret) - return ret; - *ioaddr = addr; + *ioaddr = VGIC_ADDR_UNDEF; + return ret; } diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 8c805a0..b47541d 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -203,10 +203,9 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap, spin_lock(&ioapic->lock); for (index = 0; index < IOAPIC_NUM_PINS; index++) { e = &ioapic->redirtbl[index]; - if (!e->fields.mask && - (e->fields.trig_mode == IOAPIC_LEVEL_TRIG || - kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, - index) || index == RTC_GSI)) { + if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG || + kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) || + index == RTC_GSI) { if (kvm_apic_match_dest(vcpu, NULL, 0, e->fields.dest_id, e->fields.dest_mode)) { __set_bit(e->fields.vector, diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index 0df7d4b..1f0dc1e 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -43,13 +43,13 @@ static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages); static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, - unsigned long size) + unsigned long npages) { gfn_t end_gfn; pfn_t pfn; pfn = gfn_to_pfn_memslot(slot, gfn); - end_gfn = gfn + (size >> PAGE_SHIFT); + end_gfn = gfn + npages; gfn += 1; if (is_error_noslot_pfn(pfn)) @@ -61,6 +61,14 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, return pfn; } +static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) +{ + unsigned long i; + + for (i = 0; i < npages; ++i) + kvm_release_pfn_clean(pfn + i); +} + int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) { gfn_t gfn, end_gfn; @@ -111,7 +119,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) * Pin all pages we are about to map in memory. This is * important because we unmap and unpin in 4kb steps later. */ - pfn = kvm_pin_pages(slot, gfn, page_size); + pfn = kvm_pin_pages(slot, gfn, page_size >> PAGE_SHIFT); if (is_error_noslot_pfn(pfn)) { gfn += 1; continue; @@ -123,6 +131,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) if (r) { printk(KERN_ERR "kvm_iommu_map_address:" "iommu failed to map pfn=%llx\n", pfn); + kvm_unpin_pages(kvm, pfn, page_size >> PAGE_SHIFT); goto unmap_pages; } @@ -134,7 +143,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) return 0; unmap_pages: - kvm_iommu_put_pages(kvm, slot->base_gfn, gfn); + kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn); return r; } @@ -266,14 +275,6 @@ out_unlock: return r; } -static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) -{ - unsigned long i; - - for (i = 0; i < npages; ++i) - kvm_release_pfn_clean(pfn + i); -} - static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages) { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 03a0381..eed250e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -52,6 +52,7 @@ #include #include +#include #include #include @@ -95,8 +96,6 @@ static int hardware_enable_all(void); static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); -static void update_memslots(struct kvm_memslots *slots, - struct kvm_memory_slot *new, u64 last_generation); static void kvm_release_pfn_dirty(pfn_t pfn); static void mark_page_dirty_in_slot(struct kvm *kvm, @@ -682,8 +681,7 @@ static void sort_memslots(struct kvm_memslots *slots) } static void update_memslots(struct kvm_memslots *slots, - struct kvm_memory_slot *new, - u64 last_generation) + struct kvm_memory_slot *new) { if (new) { int id = new->id; @@ -694,8 +692,6 @@ static void update_memslots(struct kvm_memslots *slots, if (new->npages != npages) sort_memslots(slots); } - - slots->generation = last_generation + 1; } static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) @@ -717,10 +713,24 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, { struct kvm_memslots *old_memslots = kvm->memslots; - update_memslots(slots, new, kvm->memslots->generation); + /* + * Set the low bit in the generation, which disables SPTE caching + * until the end of synchronize_srcu_expedited. + */ + WARN_ON(old_memslots->generation & 1); + slots->generation = old_memslots->generation + 1; + + update_memslots(slots, new); rcu_assign_pointer(kvm->memslots, slots); synchronize_srcu_expedited(&kvm->srcu); + /* + * Increment the new memslot generation a second time. This prevents + * vm exits that race with memslot updates from caching a memslot + * generation that will (potentially) be valid forever. + */ + slots->generation++; + kvm_arch_memslots_updated(kvm); return old_memslots; @@ -1539,8 +1549,8 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, ghc->generation = slots->generation; ghc->len = len; ghc->memslot = gfn_to_memslot(kvm, start_gfn); - ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail); - if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) { + ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, NULL); + if (!kvm_is_error_hva(ghc->hva) && nr_pages_needed <= 1) { ghc->hva += offset; } else { /* @@ -1970,6 +1980,9 @@ static long kvm_vcpu_ioctl(struct file *filp, if (vcpu->kvm->mm != current->mm) return -EIO; + if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) + return -EINVAL; + #if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS) /* * Special cases: vcpu ioctls that are asynchronous to vcpu execution,