From ffffbb9cd07723da2e7bdc368a1431648584a2be Mon Sep 17 00:00:00 2001 From: Igor Pecovnik Date: Mon, 20 May 2019 15:17:40 +0200 Subject: [PATCH] [ odroidn2 ] Remove deprecated patches, kernel config adjustements, added AUFS -> docker support, adding mainline targets which needs further adjustements ... --- config/boards/odroidn2.conf | 2 +- .../bootscripts/boot-odroid-n2-mainline.ini | 19 + config/kernel/linux-odroidn2-default.config | 350 +- config/kernel/linux-odroidn2-next.config | 6740 +++ config/sources/odroidn2.conf | 20 +- lib/compilation.sh | 1 + .../0001-aufs4.9-20180730.patch | 38575 ++++++++++++++++ .../odroidn2-default/patch-4.9.170-171.patch | 1956 - .../odroidn2-default/patch-4.9.171-172.patch | 3013 -- .../odroidn2-default/patch-4.9.172-173.patch | 881 - .../patch-4.9.173-174.patch.disabled | 2517 - .../general-packaging-4.20-dev.patch | 221 + .../general-packaging-4.20-dev.patch | 221 + 13 files changed, 45982 insertions(+), 8534 deletions(-) create mode 100644 config/bootscripts/boot-odroid-n2-mainline.ini create mode 100644 config/kernel/linux-odroidn2-next.config create mode 100644 patch/kernel/odroidn2-default/0001-aufs4.9-20180730.patch delete mode 100644 patch/kernel/odroidn2-default/patch-4.9.170-171.patch delete mode 100644 patch/kernel/odroidn2-default/patch-4.9.171-172.patch delete mode 100644 patch/kernel/odroidn2-default/patch-4.9.172-173.patch delete mode 100644 patch/kernel/odroidn2-default/patch-4.9.173-174.patch.disabled create mode 100644 patch/kernel/odroidn2-dev/general-packaging-4.20-dev.patch create mode 100644 patch/kernel/odroidn2-next/general-packaging-4.20-dev.patch diff --git a/config/boards/odroidn2.conf b/config/boards/odroidn2.conf index 6482b92c58..b83f6bdf90 100644 --- a/config/boards/odroidn2.conf +++ b/config/boards/odroidn2.conf @@ -6,7 +6,7 @@ BOOTCONFIG="odroidn2_config" MODULES="" MODULES_NEXT="" # -KERNEL_TARGET="default" +KERNEL_TARGET="default,dev" CLI_TARGET="stretch,bionic:default" DESKTOP_TARGET="stretch,bionic:default" # diff --git a/config/bootscripts/boot-odroid-n2-mainline.ini b/config/bootscripts/boot-odroid-n2-mainline.ini new file mode 100644 index 0000000000..7fc6a83420 --- /dev/null +++ b/config/bootscripts/boot-odroid-n2-mainline.ini @@ -0,0 +1,19 @@ +ODROIDN2-UBOOT-CONFIG + +setenv dtb_name "/dtb/meson-g12b-odroid-n2.dtb" +setenv bootargs "root=LABEL=ROOTFS rootflags=data=writeback rw console=ttyAML0,115200n8 console=tty0 no_console_suspend consoleblank=0 fsck.fix=yes fsck.repair=yes net.ifnames=0" + +# Set load addresses +setenv dtb_loadaddr "0x1000000" +setenv k_addr "0x1100000" +setenv loadaddr "0x1B00000" +setenv initrd_loadaddr "0x3700000" + +# Load kernel, dtb +fatload mmc ${devno}:1 ${k_addr} zImage +fatload mmc ${devno}:1 ${initrd_loadaddr} uInitrd +fatload mmc ${devno}:1 ${dtb_loadaddr} ${dtb_name} +fdt addr ${dtb_loadaddr} + +# boot +booti ${k_addr} ${initrd_loadaddr} ${dtb_loadaddr} diff --git a/config/kernel/linux-odroidn2-default.config b/config/kernel/linux-odroidn2-default.config index 0c295a5317..12f032fcd2 100644 --- a/config/kernel/linux-odroidn2-default.config +++ b/config/kernel/linux-odroidn2-default.config @@ -1,6 +1,6 @@ # # Automatically generated file; DO NOT EDIT. -# Linux/arm64 4.9.173 Kernel Configuration +# Linux/arm64 4.9.177 Kernel Configuration # CONFIG_ARM64=y CONFIG_64BIT=y @@ -126,7 +126,7 @@ CONFIG_LOG_CPU_MAX_BUF_SHIFT=12 CONFIG_GENERIC_SCHED_CLOCK=y CONFIG_ARCH_SUPPORTS_NUMA_BALANCING=y CONFIG_CGROUPS=y -CONFIG_CGROUP_DEBUG=y +# CONFIG_CGROUP_DEBUG is not set CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_DEVICE=y @@ -143,9 +143,10 @@ CONFIG_BLK_CGROUP=y CONFIG_CGROUP_WRITEBACK=y CONFIG_CGROUP_SCHED=y CONFIG_FAIR_GROUP_SCHED=y -# CONFIG_CFS_BANDWIDTH is not set +CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y -# CONFIG_CGROUP_PERF is not set +CONFIG_CGROUP_HUGETLB=y +CONFIG_CGROUP_PERF=y CONFIG_CGROUP_BPF=y CONFIG_SOCK_CGROUP_DATA=y # CONFIG_CHECKPOINT_RESTORE is not set @@ -447,7 +448,7 @@ CONFIG_DEFAULT_MMAP_MIN_ADDR=32768 # CONFIG_FRONTSWAP is not set CONFIG_CMA=y # CONFIG_CMA_DEBUG is not set -CONFIG_CMA_DEBUGFS=y +# CONFIG_CMA_DEBUGFS is not set CONFIG_CMA_AREAS=15 # CONFIG_ZPOOL is not set # CONFIG_ZBUD is not set @@ -670,7 +671,7 @@ CONFIG_TCP_CONG_BBR=m CONFIG_DEFAULT_RENO=y CONFIG_DEFAULT_TCP_CONG="reno" CONFIG_TCP_MD5SIG=y -CONFIG_IPV6=m +CONFIG_IPV6=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y CONFIG_IPV6_OPTIMISTIC_DAD=y @@ -698,7 +699,6 @@ CONFIG_IPV6_SUBTREES=y CONFIG_IPV6_MROUTE=y CONFIG_IPV6_MROUTE_MULTIPLE_TABLES=y CONFIG_IPV6_PIMSM_V2=y -CONFIG_NETLABEL=y # CONFIG_ANDROID_PARANOID_NETWORK is not set CONFIG_NETWORK_SECMARK=y CONFIG_NET_PTP_CLASSIFY=y @@ -971,7 +971,6 @@ CONFIG_IP_NF_TARGET_CLUSTERIP=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_SECURITY=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m @@ -1009,7 +1008,6 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_IP6_NF_SECURITY=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m @@ -1204,12 +1202,12 @@ CONFIG_NET_MPLS_GSO=m # CONFIG_MPLS_ROUTING is not set # CONFIG_HSR is not set CONFIG_NET_SWITCHDEV=y -# CONFIG_NET_L3_MASTER_DEV is not set +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_NET_NCSI is not set CONFIG_RPS=y CONFIG_RFS_ACCEL=y CONFIG_XPS=y -# CONFIG_CGROUP_NET_PRIO is not set +CONFIG_CGROUP_NET_PRIO=y CONFIG_CGROUP_NET_CLASSID=y CONFIG_NET_RX_BUSY_POLL=y CONFIG_BQL=y @@ -1819,8 +1817,7 @@ CONFIG_AMLOGIC_GPIO_IRQ=y # Amlogic ATV driver # CONFIG_AMLOGIC_ATV_DEMOD=y -CONFIG_AMLOGIC_DEBUG=y -CONFIG_AMLOGIC_DEBUG_LOCKUP=y +# CONFIG_AMLOGIC_DEBUG is not set # # Amlogic defend img file update support @@ -2174,9 +2171,9 @@ CONFIG_BCACHE=m CONFIG_BLK_DEV_DM_BUILTIN=y CONFIG_BLK_DEV_DM=m CONFIG_DM_MQ_DEFAULT=y -CONFIG_DM_DEBUG=y +# CONFIG_DM_DEBUG is not set CONFIG_DM_BUFIO=m -CONFIG_DM_DEBUG_BLOCK_STACK_TRACING=y +# CONFIG_DM_DEBUG_BLOCK_STACK_TRACING is not set CONFIG_DM_BIO_PRISON=m CONFIG_DM_PERSISTENT_DATA=m CONFIG_DM_CRYPT=m @@ -2220,6 +2217,7 @@ CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m CONFIG_GTP=m @@ -2233,6 +2231,7 @@ CONFIG_TUN_VNET_CROSS_LE=y CONFIG_VETH=y CONFIG_VIRTIO_NET=m # CONFIG_NLMON is not set +CONFIG_NET_VRF=m CONFIG_ATM_DRIVERS=y # CONFIG_ATM_DUMMY is not set CONFIG_ATM_TCP=m @@ -2441,7 +2440,22 @@ CONFIG_WCN36XX=m CONFIG_WLAN_VENDOR_ATMEL=y CONFIG_AT76C50X_USB=m CONFIG_WLAN_VENDOR_BROADCOM=y -# CONFIG_B43 is not set +CONFIG_B43=m +CONFIG_B43_BCMA=y +CONFIG_B43_SSB=y +CONFIG_B43_BUSES_BCMA_AND_SSB=y +# CONFIG_B43_BUSES_BCMA is not set +# CONFIG_B43_BUSES_SSB is not set +# CONFIG_B43_SDIO is not set +CONFIG_B43_BCMA_PIO=y +CONFIG_B43_PIO=y +CONFIG_B43_PHY_G=y +CONFIG_B43_PHY_N=y +CONFIG_B43_PHY_LP=y +CONFIG_B43_PHY_HT=y +CONFIG_B43_LEDS=y +CONFIG_B43_HWRNG=y +# CONFIG_B43_DEBUG is not set # CONFIG_B43LEGACY is not set # CONFIG_BRCMSMAC is not set # CONFIG_BRCMFMAC is not set @@ -3216,13 +3230,24 @@ CONFIG_SSB_POSSIBLE=y # # Sonics Silicon Backplane # -# CONFIG_SSB is not set +CONFIG_SSB=m +CONFIG_SSB_BLOCKIO=y +CONFIG_SSB_SDIOHOST_POSSIBLE=y +# CONFIG_SSB_SDIOHOST is not set +# CONFIG_SSB_SILENT is not set +# CONFIG_SSB_DEBUG is not set +# CONFIG_SSB_DRIVER_GPIO is not set CONFIG_BCMA_POSSIBLE=y # # Broadcom specific AMBA # -# CONFIG_BCMA is not set +CONFIG_BCMA=m +CONFIG_BCMA_BLOCKIO=y +# CONFIG_BCMA_HOST_SOC is not set +# CONFIG_BCMA_DRIVER_GMAC_CMN is not set +# CONFIG_BCMA_DRIVER_GPIO is not set +# CONFIG_BCMA_DEBUG is not set # # Multifunction device drivers @@ -3489,7 +3514,7 @@ CONFIG_VIDEO_USBTV=m CONFIG_VIDEO_PVRUSB2=m CONFIG_VIDEO_PVRUSB2_SYSFS=y CONFIG_VIDEO_PVRUSB2_DVB=y -CONFIG_VIDEO_PVRUSB2_DEBUGIFC=y +# CONFIG_VIDEO_PVRUSB2_DEBUGIFC is not set CONFIG_VIDEO_HDPVR=m CONFIG_VIDEO_USBVISION=m CONFIG_VIDEO_STK1160_COMMON=m @@ -3518,7 +3543,7 @@ CONFIG_VIDEO_TM6000_DVB=m # Digital TV USB devices # CONFIG_DVB_USB=m -CONFIG_DVB_USB_DEBUG=y +# CONFIG_DVB_USB_DEBUG is not set CONFIG_DVB_USB_DIB3000MC=m CONFIG_DVB_USB_A800=m CONFIG_DVB_USB_DIBUSB_MB=m @@ -3560,7 +3585,7 @@ CONFIG_DVB_USB_RTL28XXU=m CONFIG_DVB_USB_DVBSKY=m CONFIG_SMS_USB_DRV=m CONFIG_DVB_B2C2_FLEXCOP_USB=m -CONFIG_DVB_B2C2_FLEXCOP_USB_DEBUG=y +# CONFIG_DVB_B2C2_FLEXCOP_USB_DEBUG is not set CONFIG_DVB_AS102=m # @@ -3614,7 +3639,6 @@ CONFIG_VIDEO_CX2341X=m CONFIG_VIDEO_TVEEPROM=m CONFIG_CYPRESS_FIRMWARE=m CONFIG_DVB_B2C2_FLEXCOP=m -CONFIG_DVB_B2C2_FLEXCOP_DEBUG=y CONFIG_SMS_SIANO_MDTV=m CONFIG_SMS_SIANO_RC=y @@ -4019,6 +4043,7 @@ CONFIG_SND_USB_PODHD=m CONFIG_SND_USB_TONEPORT=m CONFIG_SND_USB_VARIAX=m CONFIG_SND_SOC=y +CONFIG_SND_SOC_AC97_BUS=y # CONFIG_SND_SOC_AMD_ACP is not set # CONFIG_SND_ATMEL_SOC is not set # CONFIG_SND_DESIGNWARE_I2S is not set @@ -4043,86 +4068,98 @@ CONFIG_SND_SOC_I2C_AND_SPI=y # # CODEC drivers # -# CONFIG_SND_SOC_AC97_CODEC is not set -# CONFIG_SND_SOC_ADAU1701 is not set -# CONFIG_SND_SOC_ADAU7002 is not set -# CONFIG_SND_SOC_AK4104 is not set -# CONFIG_SND_SOC_AK4554 is not set -# CONFIG_SND_SOC_AK4613 is not set -# CONFIG_SND_SOC_AK4642 is not set -# CONFIG_SND_SOC_AK5386 is not set -# CONFIG_SND_SOC_ALC5623 is not set -# CONFIG_SND_SOC_BT_SCO is not set -# CONFIG_SND_SOC_CS35L32 is not set -# CONFIG_SND_SOC_CS35L33 is not set -# CONFIG_SND_SOC_CS42L51_I2C is not set -# CONFIG_SND_SOC_CS42L52 is not set -# CONFIG_SND_SOC_CS42L56 is not set -# CONFIG_SND_SOC_CS42L73 is not set -# CONFIG_SND_SOC_CS4265 is not set -# CONFIG_SND_SOC_CS4270 is not set -# CONFIG_SND_SOC_CS4271_I2C is not set -# CONFIG_SND_SOC_CS4271_SPI is not set -# CONFIG_SND_SOC_CS42XX8_I2C is not set -# CONFIG_SND_SOC_CS4349 is not set -# CONFIG_SND_SOC_CS53L30 is not set -# CONFIG_SND_SOC_ES8328 is not set -# CONFIG_SND_SOC_GTM601 is not set -# CONFIG_SND_SOC_INNO_RK3036 is not set -# CONFIG_SND_SOC_MAX98504 is not set -# CONFIG_SND_SOC_MAX9860 is not set -# CONFIG_SND_SOC_PCM1681 is not set -# CONFIG_SND_SOC_PCM179X_I2C is not set -# CONFIG_SND_SOC_PCM179X_SPI is not set -# CONFIG_SND_SOC_PCM3168A_I2C is not set -# CONFIG_SND_SOC_PCM3168A_SPI is not set -# CONFIG_SND_SOC_PCM512x_I2C is not set -# CONFIG_SND_SOC_PCM512x_SPI is not set -# CONFIG_SND_SOC_RT5616 is not set -# CONFIG_SND_SOC_RT5631 is not set +CONFIG_SND_SOC_AC97_CODEC=m +CONFIG_SND_SOC_ADAU1701=m +CONFIG_SND_SOC_ADAU7002=m +CONFIG_SND_SOC_AK4104=m +CONFIG_SND_SOC_AK4554=m +CONFIG_SND_SOC_AK4613=m +CONFIG_SND_SOC_AK4642=m +CONFIG_SND_SOC_AK5386=m +CONFIG_SND_SOC_ALC5623=m +CONFIG_SND_SOC_BT_SCO=m +CONFIG_SND_SOC_CS35L32=m +CONFIG_SND_SOC_CS35L33=m +CONFIG_SND_SOC_CS42L51=m +CONFIG_SND_SOC_CS42L51_I2C=m +CONFIG_SND_SOC_CS42L52=m +CONFIG_SND_SOC_CS42L56=m +CONFIG_SND_SOC_CS42L73=m +CONFIG_SND_SOC_CS4265=m +CONFIG_SND_SOC_CS4270=m +CONFIG_SND_SOC_CS4271=m +CONFIG_SND_SOC_CS4271_I2C=m +CONFIG_SND_SOC_CS4271_SPI=m +CONFIG_SND_SOC_CS42XX8=m +CONFIG_SND_SOC_CS42XX8_I2C=m +CONFIG_SND_SOC_CS4349=m +CONFIG_SND_SOC_CS53L30=m +CONFIG_SND_SOC_ES8328=m +CONFIG_SND_SOC_GTM601=m +CONFIG_SND_SOC_INNO_RK3036=m +CONFIG_SND_SOC_MAX98504=m +CONFIG_SND_SOC_MAX9860=m +CONFIG_SND_SOC_PCM1681=m +CONFIG_SND_SOC_PCM179X=m +CONFIG_SND_SOC_PCM179X_I2C=m +CONFIG_SND_SOC_PCM179X_SPI=m +CONFIG_SND_SOC_PCM3168A=m +CONFIG_SND_SOC_PCM3168A_I2C=m +CONFIG_SND_SOC_PCM3168A_SPI=m +CONFIG_SND_SOC_PCM512x=m +CONFIG_SND_SOC_PCM512x_I2C=m +CONFIG_SND_SOC_PCM512x_SPI=m +CONFIG_SND_SOC_RL6231=m +CONFIG_SND_SOC_RT5616=m +CONFIG_SND_SOC_RT5631=m # CONFIG_SND_SOC_RT5677_SPI is not set -# CONFIG_SND_SOC_SGTL5000 is not set -# CONFIG_SND_SOC_SIRF_AUDIO_CODEC is not set +CONFIG_SND_SOC_SGTL5000=m +CONFIG_SND_SOC_SIGMADSP=m +CONFIG_SND_SOC_SIGMADSP_I2C=m +CONFIG_SND_SOC_SIRF_AUDIO_CODEC=m CONFIG_SND_SOC_SPDIF=y -# CONFIG_SND_SOC_SSM2602_SPI is not set -# CONFIG_SND_SOC_SSM2602_I2C is not set -# CONFIG_SND_SOC_SSM4567 is not set -# CONFIG_SND_SOC_STA32X is not set -# CONFIG_SND_SOC_STA350 is not set -# CONFIG_SND_SOC_STI_SAS is not set -# CONFIG_SND_SOC_TAS2552 is not set -# CONFIG_SND_SOC_TAS5086 is not set -# CONFIG_SND_SOC_TAS571X is not set -# CONFIG_SND_SOC_TAS5720 is not set -# CONFIG_SND_SOC_TAS5805 is not set -# CONFIG_SND_SOC_TFA9879 is not set -# CONFIG_SND_SOC_TLV320AIC23_I2C is not set -# CONFIG_SND_SOC_TLV320AIC23_SPI is not set -# CONFIG_SND_SOC_TLV320AIC31XX is not set -# CONFIG_SND_SOC_TLV320AIC3X is not set -# CONFIG_SND_SOC_TS3A227E is not set -# CONFIG_SND_SOC_WM8510 is not set -# CONFIG_SND_SOC_WM8523 is not set -# CONFIG_SND_SOC_WM8580 is not set -# CONFIG_SND_SOC_WM8711 is not set -# CONFIG_SND_SOC_WM8728 is not set -# CONFIG_SND_SOC_WM8731 is not set -# CONFIG_SND_SOC_WM8737 is not set -# CONFIG_SND_SOC_WM8741 is not set -# CONFIG_SND_SOC_WM8750 is not set -# CONFIG_SND_SOC_WM8753 is not set -# CONFIG_SND_SOC_WM8770 is not set -# CONFIG_SND_SOC_WM8776 is not set -# CONFIG_SND_SOC_WM8804_I2C is not set -# CONFIG_SND_SOC_WM8804_SPI is not set -# CONFIG_SND_SOC_WM8903 is not set -# CONFIG_SND_SOC_WM8960 is not set -# CONFIG_SND_SOC_WM8962 is not set -# CONFIG_SND_SOC_WM8974 is not set -# CONFIG_SND_SOC_WM8978 is not set -# CONFIG_SND_SOC_WM8985 is not set -# CONFIG_SND_SOC_NAU8810 is not set -# CONFIG_SND_SOC_TPA6130A2 is not set +CONFIG_SND_SOC_SSM2602=m +CONFIG_SND_SOC_SSM2602_SPI=m +CONFIG_SND_SOC_SSM2602_I2C=m +CONFIG_SND_SOC_SSM4567=m +CONFIG_SND_SOC_STA32X=m +CONFIG_SND_SOC_STA350=m +CONFIG_SND_SOC_STI_SAS=m +CONFIG_SND_SOC_TAS2552=m +CONFIG_SND_SOC_TAS5086=m +CONFIG_SND_SOC_TAS571X=m +CONFIG_SND_SOC_TAS5720=m +CONFIG_SND_SOC_TAS5805=m +CONFIG_SND_SOC_TFA9879=m +CONFIG_SND_SOC_TLV320AIC23=m +CONFIG_SND_SOC_TLV320AIC23_I2C=m +CONFIG_SND_SOC_TLV320AIC23_SPI=m +CONFIG_SND_SOC_TLV320AIC31XX=m +CONFIG_SND_SOC_TLV320AIC3X=m +CONFIG_SND_SOC_TS3A227E=m +CONFIG_SND_SOC_WM8510=m +CONFIG_SND_SOC_WM8523=m +CONFIG_SND_SOC_WM8580=m +CONFIG_SND_SOC_WM8711=m +CONFIG_SND_SOC_WM8728=m +CONFIG_SND_SOC_WM8731=m +CONFIG_SND_SOC_WM8737=m +CONFIG_SND_SOC_WM8741=m +CONFIG_SND_SOC_WM8750=m +CONFIG_SND_SOC_WM8753=m +CONFIG_SND_SOC_WM8770=m +CONFIG_SND_SOC_WM8776=m +CONFIG_SND_SOC_WM8804=m +CONFIG_SND_SOC_WM8804_I2C=m +CONFIG_SND_SOC_WM8804_SPI=m +CONFIG_SND_SOC_WM8903=m +CONFIG_SND_SOC_WM8960=m +CONFIG_SND_SOC_WM8962=m +CONFIG_SND_SOC_WM8974=m +CONFIG_SND_SOC_WM8978=m +CONFIG_SND_SOC_WM8985=m +CONFIG_SND_SOC_NAU8810=m +CONFIG_SND_SOC_TPA6130A2=m CONFIG_AMLOGIC_SND_SOC_CODECS=y CONFIG_AMLOGIC_SND_CODEC_DUMMY_CODEC=y CONFIG_AMLOGIC_SND_CODEC_PCM2BT=y @@ -4151,7 +4188,7 @@ CONFIG_AMLOGIC_SND_SPLIT_MODE=y # CONFIG_AMLOGIC_SND_SPLIT_MODE_MMAP is not set CONFIG_AMLOGIC_SND_SOC_COMMON=y # CONFIG_SOUND_PRIME is not set -CONFIG_AC97_BUS=m +CONFIG_AC97_BUS=y # # HID support @@ -4304,6 +4341,8 @@ CONFIG_USB_OHCI_HCD=y # CONFIG_USB_OHCI_HCD_PLATFORM is not set # CONFIG_USB_SL811_HCD is not set # CONFIG_USB_R8A66597_HCD is not set +# CONFIG_USB_HCD_BCMA is not set +# CONFIG_USB_HCD_SSB is not set # CONFIG_USB_HCD_TEST_MODE is not set # @@ -4426,7 +4465,7 @@ CONFIG_USB_SERIAL_XSENS_MT=m CONFIG_USB_SERIAL_WISHBONE=m CONFIG_USB_SERIAL_SSU100=m CONFIG_USB_SERIAL_QT2=m -CONFIG_USB_SERIAL_DEBUG=m +# CONFIG_USB_SERIAL_DEBUG is not set # # USB Miscellaneous drivers @@ -5408,7 +5447,9 @@ CONFIG_EFI_ARMSTUB=y CONFIG_DCACHE_WORD_ACCESS=y CONFIG_FS_IOMAP=y CONFIG_EXT2_FS=y -# CONFIG_EXT2_FS_XATTR is not set +CONFIG_EXT2_FS_XATTR=y +# CONFIG_EXT2_FS_POSIX_ACL is not set +# CONFIG_EXT2_FS_SECURITY is not set CONFIG_EXT3_FS=y CONFIG_EXT3_FS_POSIX_ACL=y CONFIG_EXT3_FS_SECURITY=y @@ -5421,18 +5462,18 @@ CONFIG_EXT4_FS_ENCRYPTION=y CONFIG_JBD2=y # CONFIG_JBD2_DEBUG is not set CONFIG_FS_MBCACHE=y -CONFIG_REISERFS_FS=m +CONFIG_REISERFS_FS=y # CONFIG_REISERFS_CHECK is not set CONFIG_REISERFS_PROC_INFO=y CONFIG_REISERFS_FS_XATTR=y CONFIG_REISERFS_FS_POSIX_ACL=y CONFIG_REISERFS_FS_SECURITY=y -CONFIG_JFS_FS=m +CONFIG_JFS_FS=y CONFIG_JFS_POSIX_ACL=y CONFIG_JFS_SECURITY=y # CONFIG_JFS_DEBUG is not set CONFIG_JFS_STATISTICS=y -CONFIG_XFS_FS=m +CONFIG_XFS_FS=y CONFIG_XFS_QUOTA=y CONFIG_XFS_POSIX_ACL=y CONFIG_XFS_RT=y @@ -5440,7 +5481,7 @@ CONFIG_XFS_RT=y # CONFIG_XFS_DEBUG is not set # CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set -CONFIG_BTRFS_FS=m +CONFIG_BTRFS_FS=y CONFIG_BTRFS_FS_POSIX_ACL=y # CONFIG_BTRFS_FS_CHECK_INTEGRITY is not set CONFIG_BTRFS_FS_RUN_SANITY_TESTS=y @@ -5467,7 +5508,6 @@ CONFIG_FSNOTIFY=y CONFIG_DNOTIFY=y CONFIG_INOTIFY_USER=y CONFIG_FANOTIFY=y -# CONFIG_FANOTIFY_ACCESS_PERMISSIONS is not set CONFIG_QUOTA=y CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_PRINT_QUOTA_WARNING=y @@ -5487,7 +5527,7 @@ CONFIG_OVERLAY_FS=m CONFIG_FSCACHE=m CONFIG_FSCACHE_STATS=y CONFIG_FSCACHE_HISTOGRAM=y -CONFIG_FSCACHE_DEBUG=y +# CONFIG_FSCACHE_DEBUG is not set CONFIG_FSCACHE_OBJECT_LIST=y CONFIG_CACHEFILES=m # CONFIG_CACHEFILES_DEBUG is not set @@ -5518,7 +5558,7 @@ CONFIG_EXFAT_DELAYED_SYNC=y # CONFIG_EXFAT_DEBUG_MSG is not set CONFIG_EXFAT_DEFAULT_CODEPAGE=437 CONFIG_EXFAT_DEFAULT_IOCHARSET="utf8" -CONFIG_NTFS_FS=m +CONFIG_NTFS_FS=y # CONFIG_NTFS_DEBUG is not set CONFIG_NTFS_RW=y @@ -5536,8 +5576,8 @@ CONFIG_SYSFS=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_TMPFS_XATTR=y -# CONFIG_HUGETLBFS is not set -# CONFIG_HUGETLB_PAGE is not set +CONFIG_HUGETLBFS=y +CONFIG_HUGETLB_PAGE=y CONFIG_ARCH_HAS_GIGANTIC_PAGE=y CONFIG_CONFIGFS_FS=y CONFIG_EFIVAR_FS=m @@ -5558,19 +5598,13 @@ CONFIG_JFFS2_FS=m CONFIG_JFFS2_FS_DEBUG=0 CONFIG_JFFS2_FS_WRITEBUFFER=y # CONFIG_JFFS2_FS_WBUF_VERIFY is not set -CONFIG_JFFS2_SUMMARY=y -CONFIG_JFFS2_FS_XATTR=y -CONFIG_JFFS2_FS_POSIX_ACL=y -CONFIG_JFFS2_FS_SECURITY=y -CONFIG_JFFS2_COMPRESSION_OPTIONS=y +# CONFIG_JFFS2_SUMMARY is not set +# CONFIG_JFFS2_FS_XATTR is not set +# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set CONFIG_JFFS2_ZLIB=y -CONFIG_JFFS2_LZO=y +# CONFIG_JFFS2_LZO is not set CONFIG_JFFS2_RTIME=y -CONFIG_JFFS2_RUBIN=y -# CONFIG_JFFS2_CMODE_NONE is not set -CONFIG_JFFS2_CMODE_PRIORITY=y -# CONFIG_JFFS2_CMODE_SIZE is not set -# CONFIG_JFFS2_CMODE_FAVOURLZO is not set +# CONFIG_JFFS2_RUBIN is not set CONFIG_UBIFS_FS=m # CONFIG_UBIFS_FS_ADVANCED_COMPR is not set CONFIG_UBIFS_FS_LZO=y @@ -5610,6 +5644,24 @@ CONFIG_PSTORE_RAM=y # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set # CONFIG_EXOFS_FS is not set +CONFIG_AUFS_FS=m +CONFIG_AUFS_BRANCH_MAX_127=y +# CONFIG_AUFS_BRANCH_MAX_511 is not set +# CONFIG_AUFS_BRANCH_MAX_1023 is not set +# CONFIG_AUFS_BRANCH_MAX_32767 is not set +CONFIG_AUFS_SBILIST=y +# CONFIG_AUFS_HNOTIFY is not set +# CONFIG_AUFS_EXPORT is not set +# CONFIG_AUFS_XATTR is not set +# CONFIG_AUFS_FHSM is not set +# CONFIG_AUFS_RDU is not set +# CONFIG_AUFS_DIRREN is not set +# CONFIG_AUFS_SHWH is not set +# CONFIG_AUFS_BR_RAMFS is not set +# CONFIG_AUFS_BR_FUSE is not set +CONFIG_AUFS_BR_HFSPLUS=y +CONFIG_AUFS_BDEV_LOOP=y +# CONFIG_AUFS_DEBUG is not set CONFIG_ORE=m CONFIG_NETWORK_FILESYSTEMS=y CONFIG_NFS_FS=m @@ -5626,10 +5678,8 @@ CONFIG_PNFS_OBJLAYOUT=m CONFIG_PNFS_FLEXFILE_LAYOUT=m CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN="kernel.org" CONFIG_NFS_V4_1_MIGRATION=y -CONFIG_NFS_V4_SECURITY_LABEL=y CONFIG_NFS_FSCACHE=y CONFIG_NFS_USE_LEGACY_DNS=y -CONFIG_NFS_DEBUG=y CONFIG_NFSD=m CONFIG_NFSD_V2_ACL=y CONFIG_NFSD_V3=y @@ -5639,7 +5689,6 @@ CONFIG_NFSD_PNFS=y CONFIG_NFSD_BLOCKLAYOUT=y CONFIG_NFSD_SCSILAYOUT=y CONFIG_NFSD_FLEXFILELAYOUT=y -CONFIG_NFSD_V4_SECURITY_LABEL=y CONFIG_NFSD_FAULT_INJECTION=y CONFIG_GRACE_PERIOD=m CONFIG_LOCKD=m @@ -5651,7 +5700,7 @@ CONFIG_SUNRPC_GSS=m CONFIG_SUNRPC_BACKCHANNEL=y CONFIG_SUNRPC_SWAP=y CONFIG_RPCSEC_GSS_KRB5=m -CONFIG_SUNRPC_DEBUG=y +# CONFIG_SUNRPC_DEBUG is not set CONFIG_CEPH_FS=m CONFIG_CEPH_FSCACHE=y CONFIG_CEPH_FS_POSIX_ACL=y @@ -5663,8 +5712,7 @@ CONFIG_CIFS_UPCALL=y CONFIG_CIFS_XATTR=y # CONFIG_CIFS_POSIX is not set CONFIG_CIFS_ACL=y -CONFIG_CIFS_DEBUG=y -# CONFIG_CIFS_DEBUG2 is not set +# CONFIG_CIFS_DEBUG is not set CONFIG_CIFS_DFS_UPCALL=y CONFIG_CIFS_SMB2=y CONFIG_CIFS_SMB311=y @@ -5829,7 +5877,7 @@ CONFIG_TIMER_STATS=y # CONFIG_DEBUG_LOCK_ALLOC is not set # CONFIG_PROVE_LOCKING is not set # CONFIG_LOCK_STAT is not set -CONFIG_DEBUG_ATOMIC_SLEEP=y +# CONFIG_DEBUG_ATOMIC_SLEEP is not set # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set # CONFIG_LOCK_TORTURE_TEST is not set CONFIG_STACKTRACE=y @@ -5953,40 +6001,14 @@ CONFIG_KEYS=y # CONFIG_KEY_DH_OPERATIONS is not set CONFIG_SECURITY_DMESG_RESTRICT=y CONFIG_SECURITY_PERF_EVENTS_RESTRICT=y -CONFIG_SECURITY=y -CONFIG_SECURITYFS=y -CONFIG_SECURITY_NETWORK=y -# CONFIG_SECURITY_NETWORK_XFRM is not set -CONFIG_SECURITY_PATH=y -CONFIG_LSM_MMAP_MIN_ADDR=0 +# CONFIG_SECURITY is not set +# CONFIG_SECURITYFS is not set CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR=y CONFIG_HAVE_ARCH_HARDENED_USERCOPY=y -CONFIG_HARDENED_USERCOPY=y -# CONFIG_HARDENED_USERCOPY_PAGESPAN is not set -CONFIG_SECURITY_SELINUX=y -# CONFIG_SECURITY_SELINUX_BOOTPARAM is not set -# CONFIG_SECURITY_SELINUX_DISABLE is not set -CONFIG_SECURITY_SELINUX_DEVELOP=y -CONFIG_SECURITY_SELINUX_AVC_STATS=y -CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=0 -CONFIG_SECURITY_SMACK=y -# CONFIG_SECURITY_SMACK_BRINGUP is not set -# CONFIG_SECURITY_SMACK_NETFILTER is not set -# CONFIG_SECURITY_SMACK_APPEND_SIGNALS is not set -# CONFIG_SECURITY_TOMOYO is not set -# CONFIG_SECURITY_APPARMOR is not set -# CONFIG_SECURITY_LOADPIN is not set -# CONFIG_SECURITY_YAMA is not set -CONFIG_INTEGRITY=y -# CONFIG_INTEGRITY_SIGNATURE is not set -CONFIG_INTEGRITY_AUDIT=y -# CONFIG_IMA is not set -# CONFIG_EVM is not set -CONFIG_DEFAULT_SECURITY_SELINUX=y -# CONFIG_DEFAULT_SECURITY_SMACK is not set -# CONFIG_DEFAULT_SECURITY_DAC is not set -CONFIG_DEFAULT_SECURITY="selinux" -CONFIG_XOR_BLOCKS=m +# CONFIG_HARDENED_USERCOPY is not set +CONFIG_DEFAULT_SECURITY_DAC=y +CONFIG_DEFAULT_SECURITY="" +CONFIG_XOR_BLOCKS=y CONFIG_ASYNC_CORE=m CONFIG_ASYNC_MEMCPY=m CONFIG_ASYNC_XOR=m @@ -6155,7 +6177,7 @@ CONFIG_BINARY_PRINTF=y # # Library routines # -CONFIG_RAID6_PQ=m +CONFIG_RAID6_PQ=y CONFIG_BITREVERSE=y CONFIG_HAVE_ARCH_BITREVERSE=y CONFIG_RATIONAL=y @@ -6186,6 +6208,8 @@ CONFIG_ZLIB_INFLATE=y CONFIG_ZLIB_DEFLATE=y CONFIG_LZO_COMPRESS=y CONFIG_LZO_DECOMPRESS=y +CONFIG_LZ4_COMPRESS=y +CONFIG_LZ4HC_COMPRESS=y CONFIG_LZ4_DECOMPRESS=y CONFIG_XZ_DEC=y CONFIG_XZ_DEC_X86=y diff --git a/config/kernel/linux-odroidn2-next.config b/config/kernel/linux-odroidn2-next.config new file mode 100644 index 0000000000..1af4c6709e --- /dev/null +++ b/config/kernel/linux-odroidn2-next.config @@ -0,0 +1,6740 @@ +# +# Automatically generated file; DO NOT EDIT. +# Linux/arm64 5.1.0 Kernel Configuration +# + +# +# Compiler: aarch64-linux-gnu-gcc (Linaro GCC 7.4-2019.02) 7.4.1 20181213 [linaro-7.4-2019.02 revision 56ec6f6b99cc167ff0c2f8e1a2eed33b1edc85d4] +# +CONFIG_CC_IS_GCC=y +CONFIG_GCC_VERSION=70401 +CONFIG_CLANG_VERSION=0 +CONFIG_CC_HAS_ASM_GOTO=y +CONFIG_CC_HAS_WARN_MAYBE_UNINITIALIZED=y +CONFIG_IRQ_WORK=y +CONFIG_BUILDTIME_EXTABLE_SORT=y +CONFIG_THREAD_INFO_IN_TASK=y + +# +# General setup +# +CONFIG_INIT_ENV_ARG_LIMIT=32 +# CONFIG_COMPILE_TEST is not set +CONFIG_LOCALVERSION="" +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_BUILD_SALT="" +CONFIG_DEFAULT_HOSTNAME="(none)" +CONFIG_SWAP=y +CONFIG_SYSVIPC=y +CONFIG_SYSVIPC_SYSCTL=y +CONFIG_POSIX_MQUEUE=y +CONFIG_POSIX_MQUEUE_SYSCTL=y +CONFIG_CROSS_MEMORY_ATTACH=y +# CONFIG_USELIB is not set +CONFIG_AUDIT=y +CONFIG_HAVE_ARCH_AUDITSYSCALL=y +CONFIG_AUDITSYSCALL=y + +# +# IRQ subsystem +# +CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_GENERIC_IRQ_SHOW=y +CONFIG_GENERIC_IRQ_SHOW_LEVEL=y +CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK=y +CONFIG_GENERIC_IRQ_MIGRATION=y +CONFIG_HARDIRQS_SW_RESEND=y +CONFIG_GENERIC_IRQ_CHIP=y +CONFIG_IRQ_DOMAIN=y +CONFIG_IRQ_DOMAIN_HIERARCHY=y +CONFIG_GENERIC_MSI_IRQ=y +CONFIG_GENERIC_MSI_IRQ_DOMAIN=y +CONFIG_HANDLE_DOMAIN_IRQ=y +CONFIG_IRQ_FORCED_THREADING=y +CONFIG_SPARSE_IRQ=y +# CONFIG_GENERIC_IRQ_DEBUGFS is not set +CONFIG_GENERIC_IRQ_MULTI_HANDLER=y +CONFIG_ARCH_CLOCKSOURCE_DATA=y +CONFIG_GENERIC_TIME_VSYSCALL=y +CONFIG_GENERIC_CLOCKEVENTS=y +CONFIG_ARCH_HAS_TICK_BROADCAST=y +CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y + +# +# Timers subsystem +# +CONFIG_TICK_ONESHOT=y +CONFIG_NO_HZ_COMMON=y +# CONFIG_HZ_PERIODIC is not set +CONFIG_NO_HZ_IDLE=y +# CONFIG_NO_HZ_FULL is not set +# CONFIG_NO_HZ is not set +CONFIG_HIGH_RES_TIMERS=y +# CONFIG_PREEMPT_NONE is not set +# CONFIG_PREEMPT_VOLUNTARY is not set +CONFIG_PREEMPT=y +CONFIG_PREEMPT_COUNT=y + +# +# CPU/Task time and stats accounting +# +CONFIG_TICK_CPU_ACCOUNTING=y +# CONFIG_VIRT_CPU_ACCOUNTING_GEN is not set +CONFIG_IRQ_TIME_ACCOUNTING=y +CONFIG_HAVE_SCHED_AVG_IRQ=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_BSD_PROCESS_ACCT_V3=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +# CONFIG_PSI is not set +CONFIG_CPU_ISOLATION=y + +# +# RCU Subsystem +# +CONFIG_PREEMPT_RCU=y +# CONFIG_RCU_EXPERT is not set +CONFIG_SRCU=y +CONFIG_TREE_SRCU=y +CONFIG_TASKS_RCU=y +CONFIG_RCU_STALL_COMMON=y +CONFIG_RCU_NEED_SEGCBLIST=y +CONFIG_BUILD_BIN2C=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=17 +CONFIG_LOG_CPU_MAX_BUF_SHIFT=12 +CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=13 +CONFIG_GENERIC_SCHED_CLOCK=y +CONFIG_ARCH_SUPPORTS_NUMA_BALANCING=y +CONFIG_ARCH_SUPPORTS_INT128=y +CONFIG_CGROUPS=y +CONFIG_PAGE_COUNTER=y +CONFIG_MEMCG=y +CONFIG_MEMCG_SWAP=y +CONFIG_MEMCG_SWAP_ENABLED=y +CONFIG_MEMCG_KMEM=y +CONFIG_BLK_CGROUP=y +# CONFIG_DEBUG_BLK_CGROUP is not set +CONFIG_CGROUP_WRITEBACK=y +CONFIG_CGROUP_SCHED=y +CONFIG_FAIR_GROUP_SCHED=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_RDMA=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_HUGETLB=y +CONFIG_CPUSETS=y +CONFIG_PROC_PID_CPUSET=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y +CONFIG_CGROUP_BPF=y +# CONFIG_CGROUP_DEBUG is not set +CONFIG_SOCK_CGROUP_DATA=y +CONFIG_NAMESPACES=y +CONFIG_UTS_NS=y +CONFIG_IPC_NS=y +CONFIG_USER_NS=y +CONFIG_PID_NS=y +CONFIG_NET_NS=y +# CONFIG_CHECKPOINT_RESTORE is not set +CONFIG_SCHED_AUTOGROUP=y +# CONFIG_SYSFS_DEPRECATED is not set +CONFIG_RELAY=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="" +CONFIG_RD_GZIP=y +CONFIG_RD_BZIP2=y +CONFIG_RD_LZMA=y +CONFIG_RD_XZ=y +CONFIG_RD_LZO=y +CONFIG_RD_LZ4=y +CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y +# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set +CONFIG_SYSCTL=y +CONFIG_ANON_INODES=y +CONFIG_HAVE_UID16=y +CONFIG_SYSCTL_EXCEPTION_TRACE=y +CONFIG_BPF=y +CONFIG_EXPERT=y +CONFIG_UID16=y +CONFIG_MULTIUSER=y +CONFIG_SGETMASK_SYSCALL=y +CONFIG_SYSFS_SYSCALL=y +CONFIG_SYSCTL_SYSCALL=y +CONFIG_FHANDLE=y +CONFIG_POSIX_TIMERS=y +CONFIG_PRINTK=y +CONFIG_PRINTK_NMI=y +CONFIG_BUG=y +CONFIG_ELF_CORE=y +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_FUTEX_PI=y +CONFIG_EPOLL=y +CONFIG_SIGNALFD=y +CONFIG_TIMERFD=y +CONFIG_EVENTFD=y +CONFIG_SHMEM=y +CONFIG_AIO=y +CONFIG_IO_URING=y +CONFIG_ADVISE_SYSCALLS=y +CONFIG_MEMBARRIER=y +CONFIG_KALLSYMS=y +CONFIG_KALLSYMS_ALL=y +CONFIG_KALLSYMS_BASE_RELATIVE=y +CONFIG_BPF_SYSCALL=y +# CONFIG_BPF_JIT_ALWAYS_ON is not set +# CONFIG_USERFAULTFD is not set +CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE=y +CONFIG_RSEQ=y +# CONFIG_DEBUG_RSEQ is not set +# CONFIG_EMBEDDED is not set +CONFIG_HAVE_PERF_EVENTS=y +# CONFIG_PC104 is not set + +# +# Kernel Performance Events And Counters +# +CONFIG_PERF_EVENTS=y +# CONFIG_DEBUG_PERF_USE_VMALLOC is not set +CONFIG_VM_EVENT_COUNTERS=y +CONFIG_SLUB_DEBUG=y +# CONFIG_SLUB_MEMCG_SYSFS_ON is not set +# CONFIG_COMPAT_BRK is not set +# CONFIG_SLAB is not set +CONFIG_SLUB=y +# CONFIG_SLOB is not set +CONFIG_SLAB_MERGE_DEFAULT=y +# CONFIG_SLAB_FREELIST_RANDOM is not set +# CONFIG_SLAB_FREELIST_HARDENED is not set +CONFIG_SLUB_CPU_PARTIAL=y +CONFIG_SYSTEM_DATA_VERIFICATION=y +CONFIG_PROFILING=y +CONFIG_ARM64=y +CONFIG_64BIT=y +CONFIG_MMU=y +CONFIG_ARM64_PAGE_SHIFT=12 +CONFIG_ARM64_CONT_SHIFT=4 +CONFIG_ARCH_MMAP_RND_BITS_MIN=18 +CONFIG_ARCH_MMAP_RND_BITS_MAX=33 +CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN=11 +CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX=16 +CONFIG_NO_IOPORT_MAP=y +CONFIG_STACKTRACE_SUPPORT=y +CONFIG_ILLEGAL_POINTER_VALUE=0xdead000000000000 +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_TRACE_IRQFLAGS_SUPPORT=y +CONFIG_RWSEM_XCHGADD_ALGORITHM=y +CONFIG_GENERIC_BUG=y +CONFIG_GENERIC_BUG_RELATIVE_POINTERS=y +CONFIG_GENERIC_HWEIGHT=y +CONFIG_GENERIC_CSUM=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_ZONE_DMA32=y +CONFIG_HAVE_GENERIC_GUP=y +CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y +CONFIG_SMP=y +CONFIG_KERNEL_MODE_NEON=y +CONFIG_FIX_EARLYCON_MEM=y +CONFIG_PGTABLE_LEVELS=4 +CONFIG_ARCH_SUPPORTS_UPROBES=y +CONFIG_ARCH_PROC_KCORE_TEXT=y + +# +# Platform selection +# +# CONFIG_ARCH_ACTIONS is not set +# CONFIG_ARCH_SUNXI is not set +# CONFIG_ARCH_ALPINE is not set +# CONFIG_ARCH_BCM2835 is not set +# CONFIG_ARCH_BCM_IPROC is not set +# CONFIG_ARCH_BERLIN is not set +# CONFIG_ARCH_BITMAIN is not set +# CONFIG_ARCH_BRCMSTB is not set +# CONFIG_ARCH_EXYNOS is not set +# CONFIG_ARCH_K3 is not set +# CONFIG_ARCH_LAYERSCAPE is not set +# CONFIG_ARCH_LG1K is not set +# CONFIG_ARCH_HISI is not set +# CONFIG_ARCH_MEDIATEK is not set +CONFIG_ARCH_MESON=y +# CONFIG_ARCH_MVEBU is not set +# CONFIG_ARCH_MXC is not set +# CONFIG_ARCH_QCOM is not set +# CONFIG_ARCH_REALTEK is not set +# CONFIG_ARCH_RENESAS is not set +# CONFIG_ARCH_ROCKCHIP is not set +# CONFIG_ARCH_SEATTLE is not set +# CONFIG_ARCH_STRATIX10 is not set +# CONFIG_ARCH_SYNQUACER is not set +# CONFIG_ARCH_TEGRA is not set +# CONFIG_ARCH_SPRD is not set +# CONFIG_ARCH_THUNDER is not set +# CONFIG_ARCH_THUNDER2 is not set +# CONFIG_ARCH_UNIPHIER is not set +# CONFIG_ARCH_VEXPRESS is not set +# CONFIG_ARCH_XGENE is not set +# CONFIG_ARCH_ZX is not set +# CONFIG_ARCH_ZYNQMP is not set + +# +# Kernel Features +# + +# +# ARM errata workarounds via the alternatives framework +# +CONFIG_ARM64_WORKAROUND_CLEAN_CACHE=y +CONFIG_ARM64_ERRATUM_826319=y +CONFIG_ARM64_ERRATUM_827319=y +CONFIG_ARM64_ERRATUM_824069=y +CONFIG_ARM64_ERRATUM_819472=y +CONFIG_ARM64_ERRATUM_832075=y +CONFIG_ARM64_ERRATUM_834220=y +CONFIG_ARM64_ERRATUM_845719=y +CONFIG_ARM64_ERRATUM_843419=y +CONFIG_ARM64_ERRATUM_1024718=y +CONFIG_ARM64_ERRATUM_1188873=y +CONFIG_ARM64_ERRATUM_1165522=y +CONFIG_ARM64_ERRATUM_1286807=y +CONFIG_CAVIUM_ERRATUM_22375=y +CONFIG_CAVIUM_ERRATUM_23154=y +CONFIG_CAVIUM_ERRATUM_27456=y +CONFIG_CAVIUM_ERRATUM_30115=y +# CONFIG_QCOM_FALKOR_ERRATUM_1003 is not set +CONFIG_ARM64_WORKAROUND_REPEAT_TLBI=y +# CONFIG_QCOM_FALKOR_ERRATUM_1009 is not set +# CONFIG_QCOM_QDF2400_ERRATUM_0065 is not set +CONFIG_SOCIONEXT_SYNQUACER_PREITS=y +CONFIG_HISILICON_ERRATUM_161600802=y +CONFIG_QCOM_FALKOR_ERRATUM_E1041=y +CONFIG_FUJITSU_ERRATUM_010001=y +CONFIG_ARM64_4K_PAGES=y +# CONFIG_ARM64_16K_PAGES is not set +# CONFIG_ARM64_64K_PAGES is not set +# CONFIG_ARM64_VA_BITS_39 is not set +CONFIG_ARM64_VA_BITS_48=y +CONFIG_ARM64_VA_BITS=48 +CONFIG_ARM64_PA_BITS_48=y +CONFIG_ARM64_PA_BITS=48 +# CONFIG_CPU_BIG_ENDIAN is not set +CONFIG_SCHED_MC=y +# CONFIG_SCHED_SMT is not set +CONFIG_NR_CPUS=64 +CONFIG_HOTPLUG_CPU=y +# CONFIG_NUMA is not set +CONFIG_HOLES_IN_ZONE=y +# CONFIG_HZ_100 is not set +CONFIG_HZ_250=y +# CONFIG_HZ_300 is not set +# CONFIG_HZ_1000 is not set +CONFIG_HZ=250 +CONFIG_SCHED_HRTICK=y +CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y +CONFIG_ARCH_SPARSEMEM_ENABLE=y +CONFIG_ARCH_SPARSEMEM_DEFAULT=y +CONFIG_ARCH_SELECT_MEMORY_MODEL=y +CONFIG_ARCH_FLATMEM_ENABLE=y +CONFIG_HAVE_ARCH_PFN_VALID=y +CONFIG_HW_PERF_EVENTS=y +CONFIG_SYS_SUPPORTS_HUGETLBFS=y +CONFIG_ARCH_WANT_HUGE_PMD_SHARE=y +CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y +CONFIG_SECCOMP=y +CONFIG_PARAVIRT=y +# CONFIG_PARAVIRT_TIME_ACCOUNTING is not set +CONFIG_KEXEC=y +# CONFIG_KEXEC_FILE is not set +# CONFIG_CRASH_DUMP is not set +# CONFIG_XEN is not set +CONFIG_FORCE_MAX_ZONEORDER=11 +CONFIG_UNMAP_KERNEL_AT_EL0=y +CONFIG_HARDEN_BRANCH_PREDICTOR=y +CONFIG_HARDEN_EL2_VECTORS=y +CONFIG_ARM64_SSBD=y +CONFIG_RODATA_FULL_DEFAULT_ENABLED=y +# CONFIG_ARMV8_DEPRECATED is not set +# CONFIG_ARM64_SW_TTBR0_PAN is not set + +# +# ARMv8.1 architectural features +# +CONFIG_ARM64_HW_AFDBM=y +CONFIG_ARM64_PAN=y +# CONFIG_ARM64_LSE_ATOMICS is not set +CONFIG_ARM64_VHE=y + +# +# ARMv8.2 architectural features +# +CONFIG_ARM64_UAO=y +# CONFIG_ARM64_PMEM is not set +CONFIG_ARM64_RAS_EXTN=y +CONFIG_ARM64_CNP=y + +# +# ARMv8.3 architectural features +# +CONFIG_ARM64_PTR_AUTH=y +CONFIG_ARM64_SVE=y +CONFIG_ARM64_MODULE_PLTS=y +# CONFIG_ARM64_PSEUDO_NMI is not set +# CONFIG_RANDOMIZE_BASE is not set + +# +# Boot options +# +CONFIG_CMDLINE="" +# CONFIG_CMDLINE_FORCE is not set +# CONFIG_EFI is not set +CONFIG_COMPAT=y +CONFIG_SYSVIPC_COMPAT=y +CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION=y + +# +# Power management options +# +CONFIG_SUSPEND=y +CONFIG_SUSPEND_FREEZER=y +# CONFIG_SUSPEND_SKIP_SYNC is not set +CONFIG_HIBERNATE_CALLBACKS=y +CONFIG_HIBERNATION=y +CONFIG_PM_STD_PARTITION="" +CONFIG_PM_SLEEP=y +CONFIG_PM_SLEEP_SMP=y +# CONFIG_PM_AUTOSLEEP is not set +# CONFIG_PM_WAKELOCKS is not set +CONFIG_PM=y +# CONFIG_PM_DEBUG is not set +CONFIG_PM_CLK=y +CONFIG_PM_GENERIC_DOMAINS=y +# CONFIG_WQ_POWER_EFFICIENT_DEFAULT is not set +CONFIG_PM_GENERIC_DOMAINS_SLEEP=y +CONFIG_PM_GENERIC_DOMAINS_OF=y +CONFIG_CPU_PM=y +# CONFIG_ENERGY_MODEL is not set +CONFIG_ARCH_HIBERNATION_POSSIBLE=y +CONFIG_ARCH_HIBERNATION_HEADER=y +CONFIG_ARCH_SUSPEND_POSSIBLE=y + +# +# CPU Power Management +# + +# +# CPU Idle +# +CONFIG_CPU_IDLE=y +CONFIG_CPU_IDLE_MULTIPLE_DRIVERS=y +# CONFIG_CPU_IDLE_GOV_LADDER is not set +CONFIG_CPU_IDLE_GOV_MENU=y +# CONFIG_CPU_IDLE_GOV_TEO is not set +CONFIG_DT_IDLE_STATES=y + +# +# ARM CPU Idle Drivers +# +CONFIG_ARM_CPUIDLE=y + +# +# CPU Frequency scaling +# +CONFIG_CPU_FREQ=y +CONFIG_CPU_FREQ_GOV_ATTR_SET=y +CONFIG_CPU_FREQ_GOV_COMMON=y +CONFIG_CPU_FREQ_STAT=y +# CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set +# CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set +# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set +CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y +# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set +# CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL is not set +CONFIG_CPU_FREQ_GOV_PERFORMANCE=y +CONFIG_CPU_FREQ_GOV_POWERSAVE=y +CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_CPU_FREQ_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y +CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y + +# +# CPU frequency scaling drivers +# +CONFIG_CPUFREQ_DT=y +CONFIG_CPUFREQ_DT_PLATDEV=y +CONFIG_ARM_SCPI_CPUFREQ=y +# CONFIG_QORIQ_CPUFREQ is not set + +# +# Firmware Drivers +# +CONFIG_ARM_PSCI_FW=y +# CONFIG_ARM_PSCI_CHECKER is not set +# CONFIG_ARM_SCMI_PROTOCOL is not set +CONFIG_ARM_SCPI_PROTOCOL=y +CONFIG_ARM_SCPI_POWER_DOMAIN=y +# CONFIG_ARM_SDE_INTERFACE is not set +# CONFIG_FIRMWARE_MEMMAP is not set +CONFIG_HAVE_ARM_SMCCC=y +# CONFIG_GOOGLE_FIRMWARE is not set +CONFIG_EFI_EARLYCON=y +CONFIG_MESON_SM=y + +# +# Tegra firmware driver +# +CONFIG_HAVE_KVM_IRQCHIP=y +CONFIG_HAVE_KVM_IRQFD=y +CONFIG_HAVE_KVM_IRQ_ROUTING=y +CONFIG_HAVE_KVM_EVENTFD=y +CONFIG_KVM_MMIO=y +CONFIG_HAVE_KVM_MSI=y +CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT=y +CONFIG_KVM_VFIO=y +CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL=y +CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT=y +CONFIG_HAVE_KVM_IRQ_BYPASS=y +CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE=y +CONFIG_IRQ_BYPASS_MANAGER=y +CONFIG_VIRTUALIZATION=y +CONFIG_KVM=y +CONFIG_KVM_ARM_HOST=y +CONFIG_KVM_ARM_PMU=y +CONFIG_KVM_INDIRECT_VECTORS=y +# CONFIG_VHOST_NET is not set +# CONFIG_VHOST_SCSI is not set +# CONFIG_VHOST_VSOCK is not set +# CONFIG_VHOST_CROSS_ENDIAN_LEGACY is not set +CONFIG_ARM64_CRYPTO=y +CONFIG_CRYPTO_SHA256_ARM64=y +CONFIG_CRYPTO_SHA512_ARM64=m +CONFIG_CRYPTO_SHA1_ARM64_CE=y +CONFIG_CRYPTO_SHA2_ARM64_CE=y +CONFIG_CRYPTO_SHA512_ARM64_CE=m +CONFIG_CRYPTO_SHA3_ARM64=m +CONFIG_CRYPTO_SM3_ARM64_CE=m +# CONFIG_CRYPTO_SM4_ARM64_CE is not set +CONFIG_CRYPTO_GHASH_ARM64_CE=y +CONFIG_CRYPTO_CRCT10DIF_ARM64_CE=m +CONFIG_CRYPTO_AES_ARM64=y +CONFIG_CRYPTO_AES_ARM64_CE=y +CONFIG_CRYPTO_AES_ARM64_CE_CCM=y +CONFIG_CRYPTO_AES_ARM64_CE_BLK=y +CONFIG_CRYPTO_AES_ARM64_NEON_BLK=y +CONFIG_CRYPTO_CHACHA20_NEON=y +# CONFIG_CRYPTO_NHPOLY1305_NEON is not set +CONFIG_CRYPTO_AES_ARM64_BS=y + +# +# General architecture-dependent options +# +CONFIG_CRASH_CORE=y +CONFIG_KEXEC_CORE=y +# CONFIG_KPROBES is not set +CONFIG_JUMP_LABEL=y +# CONFIG_STATIC_KEYS_SELFTEST is not set +CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y +CONFIG_HAVE_KPROBES=y +CONFIG_HAVE_KRETPROBES=y +CONFIG_HAVE_NMI=y +CONFIG_HAVE_ARCH_TRACEHOOK=y +CONFIG_HAVE_DMA_CONTIGUOUS=y +CONFIG_GENERIC_SMP_IDLE_THREAD=y +CONFIG_GENERIC_IDLE_POLL_SETUP=y +CONFIG_ARCH_HAS_FORTIFY_SOURCE=y +CONFIG_ARCH_HAS_SET_MEMORY=y +CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST=y +CONFIG_HAVE_REGS_AND_STACK_ACCESS_API=y +CONFIG_HAVE_RSEQ=y +CONFIG_HAVE_CLK=y +CONFIG_HAVE_HW_BREAKPOINT=y +CONFIG_HAVE_PERF_REGS=y +CONFIG_HAVE_PERF_USER_STACK_DUMP=y +CONFIG_HAVE_ARCH_JUMP_LABEL=y +CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE=y +CONFIG_HAVE_RCU_TABLE_FREE=y +CONFIG_HAVE_RCU_TABLE_INVALIDATE=y +CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG=y +CONFIG_HAVE_ALIGNED_STRUCT_PAGE=y +CONFIG_HAVE_CMPXCHG_LOCAL=y +CONFIG_HAVE_CMPXCHG_DOUBLE=y +CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION=y +CONFIG_HAVE_ARCH_SECCOMP_FILTER=y +CONFIG_SECCOMP_FILTER=y +CONFIG_HAVE_ARCH_STACKLEAK=y +CONFIG_HAVE_STACKPROTECTOR=y +CONFIG_CC_HAS_STACKPROTECTOR_NONE=y +CONFIG_STACKPROTECTOR=y +CONFIG_STACKPROTECTOR_STRONG=y +CONFIG_HAVE_CONTEXT_TRACKING=y +CONFIG_HAVE_VIRT_CPU_ACCOUNTING_GEN=y +CONFIG_HAVE_IRQ_TIME_ACCOUNTING=y +CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE=y +CONFIG_HAVE_ARCH_HUGE_VMAP=y +CONFIG_HAVE_MOD_ARCH_SPECIFIC=y +CONFIG_MODULES_USE_ELF_RELA=y +CONFIG_ARCH_HAS_ELF_RANDOMIZE=y +CONFIG_HAVE_ARCH_MMAP_RND_BITS=y +CONFIG_ARCH_MMAP_RND_BITS=18 +CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS=y +CONFIG_ARCH_MMAP_RND_COMPAT_BITS=11 +CONFIG_CLONE_BACKWARDS=y +CONFIG_OLD_SIGSUSPEND3=y +CONFIG_COMPAT_OLD_SIGACTION=y +CONFIG_COMPAT_32BIT_TIME=y +CONFIG_HAVE_ARCH_VMAP_STACK=y +CONFIG_VMAP_STACK=y +CONFIG_ARCH_HAS_STRICT_KERNEL_RWX=y +CONFIG_STRICT_KERNEL_RWX=y +CONFIG_ARCH_HAS_STRICT_MODULE_RWX=y +CONFIG_STRICT_MODULE_RWX=y +CONFIG_REFCOUNT_FULL=y +CONFIG_HAVE_ARCH_PREL32_RELOCATIONS=y +CONFIG_ARCH_USE_MEMREMAP_PROT=y + +# +# GCOV-based kernel profiling +# +# CONFIG_GCOV_KERNEL is not set +CONFIG_ARCH_HAS_GCOV_PROFILE_ALL=y +CONFIG_PLUGIN_HOSTCC="" +CONFIG_HAVE_GCC_PLUGINS=y +CONFIG_RT_MUTEXES=y +CONFIG_BASE_SMALL=0 +CONFIG_MODULES=y +# CONFIG_MODULE_FORCE_LOAD is not set +CONFIG_MODULE_UNLOAD=y +# CONFIG_MODULE_FORCE_UNLOAD is not set +# CONFIG_MODVERSIONS is not set +# CONFIG_MODULE_SRCVERSION_ALL is not set +# CONFIG_MODULE_SIG is not set +# CONFIG_MODULE_COMPRESS is not set +# CONFIG_TRIM_UNUSED_KSYMS is not set +CONFIG_MODULES_TREE_LOOKUP=y +CONFIG_BLOCK=y +CONFIG_BLK_SCSI_REQUEST=y +CONFIG_BLK_DEV_BSG=y +CONFIG_BLK_DEV_BSGLIB=y +CONFIG_BLK_DEV_INTEGRITY=y +# CONFIG_BLK_DEV_ZONED is not set +CONFIG_BLK_DEV_THROTTLING=y +CONFIG_BLK_DEV_THROTTLING_LOW=y +CONFIG_BLK_CMDLINE_PARSER=y +CONFIG_BLK_WBT=y +# CONFIG_BLK_CGROUP_IOLATENCY is not set +CONFIG_BLK_WBT_MQ=y +# CONFIG_BLK_DEBUG_FS is not set +# CONFIG_BLK_SED_OPAL is not set + +# +# Partition Types +# +# CONFIG_PARTITION_ADVANCED is not set +CONFIG_MSDOS_PARTITION=y +CONFIG_EFI_PARTITION=y +CONFIG_BLOCK_COMPAT=y +CONFIG_BLK_MQ_VIRTIO=y +CONFIG_BLK_PM=y + +# +# IO Schedulers +# +CONFIG_MQ_IOSCHED_DEADLINE=y +CONFIG_MQ_IOSCHED_KYBER=y +CONFIG_IOSCHED_BFQ=y +CONFIG_BFQ_GROUP_IOSCHED=y +CONFIG_PREEMPT_NOTIFIERS=y +CONFIG_PADATA=y +CONFIG_ASN1=y +CONFIG_UNINLINE_SPIN_UNLOCK=y +CONFIG_ARCH_SUPPORTS_ATOMIC_RMW=y +CONFIG_MUTEX_SPIN_ON_OWNER=y +CONFIG_RWSEM_SPIN_ON_OWNER=y +CONFIG_LOCK_SPIN_ON_OWNER=y +CONFIG_ARCH_USE_QUEUED_SPINLOCKS=y +CONFIG_QUEUED_SPINLOCKS=y +CONFIG_ARCH_USE_QUEUED_RWLOCKS=y +CONFIG_QUEUED_RWLOCKS=y +CONFIG_ARCH_HAS_SYSCALL_WRAPPER=y +CONFIG_FREEZER=y + +# +# Executable file formats +# +CONFIG_BINFMT_ELF=y +CONFIG_COMPAT_BINFMT_ELF=y +CONFIG_ELFCORE=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_BINFMT_SCRIPT=y +# CONFIG_BINFMT_MISC is not set +CONFIG_COREDUMP=y + +# +# Memory Management options +# +CONFIG_SELECT_MEMORY_MODEL=y +# CONFIG_FLATMEM_MANUAL is not set +CONFIG_SPARSEMEM_MANUAL=y +CONFIG_SPARSEMEM=y +CONFIG_HAVE_MEMORY_PRESENT=y +CONFIG_SPARSEMEM_EXTREME=y +CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y +CONFIG_SPARSEMEM_VMEMMAP=y +CONFIG_MEMORY_ISOLATION=y +# CONFIG_MEMORY_HOTPLUG is not set +CONFIG_SPLIT_PTLOCK_CPUS=4 +CONFIG_MEMORY_BALLOON=y +CONFIG_BALLOON_COMPACTION=y +CONFIG_COMPACTION=y +CONFIG_MIGRATION=y +CONFIG_PHYS_ADDR_T_64BIT=y +CONFIG_MMU_NOTIFIER=y +CONFIG_KSM=y +CONFIG_DEFAULT_MMAP_MIN_ADDR=4096 +CONFIG_ARCH_SUPPORTS_MEMORY_FAILURE=y +CONFIG_MEMORY_FAILURE=y +# CONFIG_HWPOISON_INJECT is not set +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS=y +# CONFIG_TRANSPARENT_HUGEPAGE_MADVISE is not set +CONFIG_TRANSPARENT_HUGE_PAGECACHE=y +CONFIG_CLEANCACHE=y +CONFIG_FRONTSWAP=y +CONFIG_CMA=y +# CONFIG_CMA_DEBUG is not set +# CONFIG_CMA_DEBUGFS is not set +CONFIG_CMA_AREAS=7 +CONFIG_ZSWAP=y +CONFIG_ZPOOL=y +CONFIG_ZBUD=y +CONFIG_Z3FOLD=y +CONFIG_ZSMALLOC=y +CONFIG_PGTABLE_MAPPING=y +# CONFIG_ZSMALLOC_STAT is not set +CONFIG_GENERIC_EARLY_IOREMAP=y +# CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set +# CONFIG_IDLE_PAGE_TRACKING is not set +CONFIG_FRAME_VECTOR=y +# CONFIG_PERCPU_STATS is not set +# CONFIG_GUP_BENCHMARK is not set +CONFIG_ARCH_HAS_PTE_SPECIAL=y +CONFIG_NET=y +CONFIG_COMPAT_NETLINK_MESSAGES=y +CONFIG_NET_INGRESS=y +CONFIG_NET_EGRESS=y +CONFIG_SKB_EXTENSIONS=y + +# +# Networking options +# +CONFIG_PACKET=y +CONFIG_PACKET_DIAG=m +CONFIG_UNIX=y +CONFIG_UNIX_SCM=y +CONFIG_UNIX_DIAG=m +CONFIG_TLS=m +# CONFIG_TLS_DEVICE is not set +CONFIG_XFRM=y +CONFIG_XFRM_OFFLOAD=y +CONFIG_XFRM_ALGO=m +CONFIG_XFRM_USER=m +CONFIG_XFRM_INTERFACE=m +CONFIG_XFRM_SUB_POLICY=y +CONFIG_XFRM_MIGRATE=y +CONFIG_XFRM_STATISTICS=y +CONFIG_XFRM_IPCOMP=m +CONFIG_NET_KEY=m +# CONFIG_NET_KEY_MIGRATE is not set +CONFIG_XDP_SOCKETS=y +# CONFIG_XDP_SOCKETS_DIAG is not set +CONFIG_INET=y +CONFIG_WIREGUARD=m +# CONFIG_WIREGUARD_DEBUG is not set +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_FIB_TRIE_STATS=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_MULTIPATH=y +CONFIG_IP_ROUTE_VERBOSE=y +CONFIG_IP_ROUTE_CLASSID=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +CONFIG_NET_IPIP=m +CONFIG_NET_IPGRE_DEMUX=m +CONFIG_NET_IP_TUNNEL=y +CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_BROADCAST=y +CONFIG_IP_MROUTE_COMMON=y +CONFIG_IP_MROUTE=y +CONFIG_IP_MROUTE_MULTIPLE_TABLES=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_SYN_COOKIES=y +CONFIG_NET_IPVTI=m +CONFIG_NET_UDP_TUNNEL=y +CONFIG_NET_FOU=y +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_INET_AH=m +CONFIG_INET_ESP=m +CONFIG_INET_ESP_OFFLOAD=m +CONFIG_INET_IPCOMP=m +CONFIG_INET_XFRM_TUNNEL=m +CONFIG_INET_TUNNEL=m +CONFIG_INET_XFRM_MODE_TRANSPORT=y +CONFIG_INET_XFRM_MODE_TUNNEL=y +CONFIG_INET_XFRM_MODE_BEET=y +CONFIG_INET_DIAG=y +CONFIG_INET_TCP_DIAG=y +CONFIG_INET_UDP_DIAG=m +CONFIG_INET_RAW_DIAG=m +CONFIG_INET_DIAG_DESTROY=y +CONFIG_TCP_CONG_ADVANCED=y +CONFIG_TCP_CONG_BIC=m +CONFIG_TCP_CONG_CUBIC=y +CONFIG_TCP_CONG_WESTWOOD=m +CONFIG_TCP_CONG_HTCP=m +CONFIG_TCP_CONG_HSTCP=m +CONFIG_TCP_CONG_HYBLA=m +CONFIG_TCP_CONG_VEGAS=m +CONFIG_TCP_CONG_NV=m +CONFIG_TCP_CONG_SCALABLE=m +CONFIG_TCP_CONG_LP=m +CONFIG_TCP_CONG_VENO=m +CONFIG_TCP_CONG_YEAH=m +CONFIG_TCP_CONG_ILLINOIS=m +CONFIG_TCP_CONG_DCTCP=m +CONFIG_TCP_CONG_CDG=m +CONFIG_TCP_CONG_BBR=m +CONFIG_DEFAULT_CUBIC=y +# CONFIG_DEFAULT_RENO is not set +CONFIG_DEFAULT_TCP_CONG="cubic" +CONFIG_TCP_MD5SIG=y +CONFIG_IPV6=m +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_AH=m +CONFIG_INET6_ESP=m +CONFIG_INET6_ESP_OFFLOAD=m +CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_MIP6=m +CONFIG_IPV6_ILA=m +CONFIG_INET6_XFRM_TUNNEL=m +CONFIG_INET6_TUNNEL=m +CONFIG_INET6_XFRM_MODE_TRANSPORT=m +CONFIG_INET6_XFRM_MODE_TUNNEL=m +CONFIG_INET6_XFRM_MODE_BEET=m +CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m +CONFIG_IPV6_VTI=m +CONFIG_IPV6_SIT=m +CONFIG_IPV6_SIT_6RD=y +CONFIG_IPV6_NDISC_NODETYPE=y +CONFIG_IPV6_TUNNEL=m +CONFIG_IPV6_GRE=m +CONFIG_IPV6_FOU=m +CONFIG_IPV6_FOU_TUNNEL=m +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_IPV6_SUBTREES=y +CONFIG_IPV6_MROUTE=y +CONFIG_IPV6_MROUTE_MULTIPLE_TABLES=y +CONFIG_IPV6_PIMSM_V2=y +CONFIG_IPV6_SEG6_LWTUNNEL=y +CONFIG_IPV6_SEG6_HMAC=y +CONFIG_NETLABEL=y +CONFIG_NETWORK_SECMARK=y +CONFIG_NET_PTP_CLASSIFY=y +CONFIG_NETWORK_PHY_TIMESTAMPING=y +CONFIG_NETFILTER=y +CONFIG_NETFILTER_ADVANCED=y +CONFIG_BRIDGE_NETFILTER=m + +# +# Core Netfilter Configuration +# +CONFIG_NETFILTER_INGRESS=y +CONFIG_NETFILTER_NETLINK=m +CONFIG_NETFILTER_FAMILY_BRIDGE=y +CONFIG_NETFILTER_FAMILY_ARP=y +CONFIG_NETFILTER_NETLINK_ACCT=m +CONFIG_NETFILTER_NETLINK_QUEUE=m +CONFIG_NETFILTER_NETLINK_LOG=m +CONFIG_NETFILTER_NETLINK_OSF=m +CONFIG_NF_CONNTRACK=m +CONFIG_NF_LOG_COMMON=m +CONFIG_NF_LOG_NETDEV=m +CONFIG_NETFILTER_CONNCOUNT=m +CONFIG_NF_CONNTRACK_MARK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_ZONES=y +CONFIG_NF_CONNTRACK_PROCFS=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CONNTRACK_TIMEOUT=y +CONFIG_NF_CONNTRACK_TIMESTAMP=y +CONFIG_NF_CONNTRACK_LABELS=y +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_GRE=y +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y +CONFIG_NF_CONNTRACK_AMANDA=m +CONFIG_NF_CONNTRACK_FTP=m +CONFIG_NF_CONNTRACK_H323=m +CONFIG_NF_CONNTRACK_IRC=m +CONFIG_NF_CONNTRACK_BROADCAST=m +CONFIG_NF_CONNTRACK_NETBIOS_NS=m +CONFIG_NF_CONNTRACK_SNMP=m +CONFIG_NF_CONNTRACK_PPTP=m +CONFIG_NF_CONNTRACK_SANE=m +CONFIG_NF_CONNTRACK_SIP=m +CONFIG_NF_CONNTRACK_TFTP=m +CONFIG_NF_CT_NETLINK=m +CONFIG_NF_CT_NETLINK_TIMEOUT=m +CONFIG_NF_CT_NETLINK_HELPER=m +CONFIG_NETFILTER_NETLINK_GLUE_CT=y +CONFIG_NF_NAT=m +CONFIG_NF_NAT_NEEDED=y +CONFIG_NF_NAT_AMANDA=m +CONFIG_NF_NAT_FTP=m +CONFIG_NF_NAT_IRC=m +CONFIG_NF_NAT_SIP=m +CONFIG_NF_NAT_TFTP=m +CONFIG_NF_NAT_REDIRECT=y +CONFIG_NF_NAT_MASQUERADE=y +CONFIG_NETFILTER_SYNPROXY=m +CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m +CONFIG_NF_TABLES_INET=y +CONFIG_NF_TABLES_NETDEV=y +CONFIG_NFT_NUMGEN=m +CONFIG_NFT_CT=m +CONFIG_NFT_FLOW_OFFLOAD=m +CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m +CONFIG_NFT_LOG=m +CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m +CONFIG_NFT_NAT=m +CONFIG_NFT_TUNNEL=m +CONFIG_NFT_OBJREF=m +CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m +CONFIG_NFT_REJECT=m +CONFIG_NFT_REJECT_INET=m +CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m +CONFIG_NFT_FIB=m +# CONFIG_NFT_FIB_INET is not set +# CONFIG_NFT_XFRM is not set +CONFIG_NFT_SOCKET=m +CONFIG_NFT_OSF=m +CONFIG_NFT_TPROXY=m +CONFIG_NF_DUP_NETDEV=m +CONFIG_NFT_DUP_NETDEV=m +CONFIG_NFT_FWD_NETDEV=m +# CONFIG_NFT_FIB_NETDEV is not set +CONFIG_NF_FLOW_TABLE_INET=m +CONFIG_NF_FLOW_TABLE=m +CONFIG_NETFILTER_XTABLES=m + +# +# Xtables combined modules +# +CONFIG_NETFILTER_XT_MARK=m +CONFIG_NETFILTER_XT_CONNMARK=m +CONFIG_NETFILTER_XT_SET=m + +# +# Xtables targets +# +CONFIG_NETFILTER_XT_TARGET_AUDIT=m +CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m +CONFIG_NETFILTER_XT_TARGET_CONNMARK=m +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m +CONFIG_NETFILTER_XT_TARGET_CT=m +CONFIG_NETFILTER_XT_TARGET_DSCP=m +CONFIG_NETFILTER_XT_TARGET_HL=m +CONFIG_NETFILTER_XT_TARGET_HMARK=m +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m +CONFIG_NETFILTER_XT_TARGET_LED=m +CONFIG_NETFILTER_XT_TARGET_LOG=m +CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_NAT=m +CONFIG_NETFILTER_XT_TARGET_NETMAP=m +CONFIG_NETFILTER_XT_TARGET_NFLOG=m +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m +CONFIG_NETFILTER_XT_TARGET_NOTRACK=m +CONFIG_NETFILTER_XT_TARGET_RATEEST=m +CONFIG_NETFILTER_XT_TARGET_REDIRECT=m +CONFIG_NETFILTER_XT_TARGET_TEE=m +CONFIG_NETFILTER_XT_TARGET_TPROXY=m +CONFIG_NETFILTER_XT_TARGET_TRACE=m +CONFIG_NETFILTER_XT_TARGET_SECMARK=m +CONFIG_NETFILTER_XT_TARGET_TCPMSS=m +CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m + +# +# Xtables matches +# +CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m +CONFIG_NETFILTER_XT_MATCH_BPF=m +CONFIG_NETFILTER_XT_MATCH_CGROUP=m +CONFIG_NETFILTER_XT_MATCH_CLUSTER=m +CONFIG_NETFILTER_XT_MATCH_COMMENT=m +CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m +CONFIG_NETFILTER_XT_MATCH_CONNLABEL=m +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m +CONFIG_NETFILTER_XT_MATCH_CONNMARK=m +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m +CONFIG_NETFILTER_XT_MATCH_CPU=m +CONFIG_NETFILTER_XT_MATCH_DCCP=m +CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m +CONFIG_NETFILTER_XT_MATCH_DSCP=m +CONFIG_NETFILTER_XT_MATCH_ECN=m +CONFIG_NETFILTER_XT_MATCH_ESP=m +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m +CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_HL=m +CONFIG_NETFILTER_XT_MATCH_IPCOMP=m +CONFIG_NETFILTER_XT_MATCH_IPRANGE=m +CONFIG_NETFILTER_XT_MATCH_IPVS=m +CONFIG_NETFILTER_XT_MATCH_L2TP=m +CONFIG_NETFILTER_XT_MATCH_LENGTH=m +CONFIG_NETFILTER_XT_MATCH_LIMIT=m +CONFIG_NETFILTER_XT_MATCH_MAC=m +CONFIG_NETFILTER_XT_MATCH_MARK=m +CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m +CONFIG_NETFILTER_XT_MATCH_NFACCT=m +CONFIG_NETFILTER_XT_MATCH_OSF=m +CONFIG_NETFILTER_XT_MATCH_OWNER=m +CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m +CONFIG_NETFILTER_XT_MATCH_QUOTA=m +CONFIG_NETFILTER_XT_MATCH_RATEEST=m +CONFIG_NETFILTER_XT_MATCH_REALM=m +CONFIG_NETFILTER_XT_MATCH_RECENT=m +CONFIG_NETFILTER_XT_MATCH_SCTP=m +CONFIG_NETFILTER_XT_MATCH_SOCKET=m +CONFIG_NETFILTER_XT_MATCH_STATE=m +CONFIG_NETFILTER_XT_MATCH_STATISTIC=m +CONFIG_NETFILTER_XT_MATCH_STRING=m +CONFIG_NETFILTER_XT_MATCH_TCPMSS=m +CONFIG_NETFILTER_XT_MATCH_TIME=m +CONFIG_NETFILTER_XT_MATCH_U32=m +CONFIG_IP_SET=m +CONFIG_IP_SET_MAX=256 +CONFIG_IP_SET_BITMAP_IP=m +CONFIG_IP_SET_BITMAP_IPMAC=m +CONFIG_IP_SET_BITMAP_PORT=m +CONFIG_IP_SET_HASH_IP=m +CONFIG_IP_SET_HASH_IPMARK=m +CONFIG_IP_SET_HASH_IPPORT=m +CONFIG_IP_SET_HASH_IPPORTIP=m +CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_IPMAC=m +CONFIG_IP_SET_HASH_MAC=m +CONFIG_IP_SET_HASH_NETPORTNET=m +CONFIG_IP_SET_HASH_NET=m +CONFIG_IP_SET_HASH_NETNET=m +CONFIG_IP_SET_HASH_NETPORT=m +CONFIG_IP_SET_HASH_NETIFACE=m +CONFIG_IP_SET_LIST_SET=m +CONFIG_IP_VS=m +CONFIG_IP_VS_IPV6=y +# CONFIG_IP_VS_DEBUG is not set +CONFIG_IP_VS_TAB_BITS=12 + +# +# IPVS transport protocol load balancing support +# +CONFIG_IP_VS_PROTO_TCP=y +CONFIG_IP_VS_PROTO_UDP=y +CONFIG_IP_VS_PROTO_AH_ESP=y +CONFIG_IP_VS_PROTO_ESP=y +CONFIG_IP_VS_PROTO_AH=y +CONFIG_IP_VS_PROTO_SCTP=y + +# +# IPVS scheduler +# +CONFIG_IP_VS_RR=m +CONFIG_IP_VS_WRR=m +CONFIG_IP_VS_LC=m +CONFIG_IP_VS_WLC=m +CONFIG_IP_VS_FO=m +CONFIG_IP_VS_OVF=m +CONFIG_IP_VS_LBLC=m +CONFIG_IP_VS_LBLCR=m +CONFIG_IP_VS_DH=m +CONFIG_IP_VS_SH=m +CONFIG_IP_VS_MH=m +CONFIG_IP_VS_SED=m +CONFIG_IP_VS_NQ=m + +# +# IPVS SH scheduler +# +CONFIG_IP_VS_SH_TAB_BITS=8 + +# +# IPVS MH scheduler +# +CONFIG_IP_VS_MH_TAB_INDEX=12 + +# +# IPVS application helper +# +CONFIG_IP_VS_FTP=m +CONFIG_IP_VS_NFCT=y +CONFIG_IP_VS_PE_SIP=m + +# +# IP: Netfilter Configuration +# +CONFIG_NF_DEFRAG_IPV4=m +CONFIG_NF_SOCKET_IPV4=m +CONFIG_NF_TPROXY_IPV4=m +CONFIG_NF_TABLES_IPV4=y +CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_REJECT_IPV4=m +CONFIG_NFT_DUP_IPV4=m +CONFIG_NFT_FIB_IPV4=m +CONFIG_NF_TABLES_ARP=y +CONFIG_NF_FLOW_TABLE_IPV4=m +CONFIG_NF_DUP_IPV4=m +CONFIG_NF_LOG_ARP=m +CONFIG_NF_LOG_IPV4=m +CONFIG_NF_REJECT_IPV4=m +CONFIG_NF_NAT_SNMP_BASIC=m +CONFIG_NF_NAT_PPTP=m +CONFIG_NF_NAT_H323=m +CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_MATCH_AH=m +CONFIG_IP_NF_MATCH_ECN=m +CONFIG_IP_NF_MATCH_RPFILTER=m +CONFIG_IP_NF_MATCH_TTL=m +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_TARGET_SYNPROXY=m +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_TARGET_MASQUERADE=m +CONFIG_IP_NF_TARGET_NETMAP=m +CONFIG_IP_NF_TARGET_REDIRECT=m +CONFIG_IP_NF_MANGLE=m +CONFIG_IP_NF_TARGET_CLUSTERIP=m +CONFIG_IP_NF_TARGET_ECN=m +CONFIG_IP_NF_TARGET_TTL=m +CONFIG_IP_NF_RAW=m +CONFIG_IP_NF_SECURITY=m +CONFIG_IP_NF_ARPTABLES=m +CONFIG_IP_NF_ARPFILTER=m +CONFIG_IP_NF_ARP_MANGLE=m + +# +# IPv6: Netfilter Configuration +# +CONFIG_NF_SOCKET_IPV6=m +CONFIG_NF_TPROXY_IPV6=m +CONFIG_NF_TABLES_IPV6=y +CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_REJECT_IPV6=m +CONFIG_NFT_DUP_IPV6=m +CONFIG_NFT_FIB_IPV6=m +CONFIG_NF_FLOW_TABLE_IPV6=m +CONFIG_NF_DUP_IPV6=m +CONFIG_NF_REJECT_IPV6=m +CONFIG_NF_LOG_IPV6=m +CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_MATCH_AH=m +CONFIG_IP6_NF_MATCH_EUI64=m +CONFIG_IP6_NF_MATCH_FRAG=m +CONFIG_IP6_NF_MATCH_OPTS=m +CONFIG_IP6_NF_MATCH_HL=m +CONFIG_IP6_NF_MATCH_IPV6HEADER=m +CONFIG_IP6_NF_MATCH_MH=m +CONFIG_IP6_NF_MATCH_RPFILTER=m +CONFIG_IP6_NF_MATCH_RT=m +CONFIG_IP6_NF_MATCH_SRH=m +CONFIG_IP6_NF_TARGET_HL=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_REJECT=m +CONFIG_IP6_NF_TARGET_SYNPROXY=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_RAW=m +CONFIG_IP6_NF_SECURITY=m +CONFIG_IP6_NF_NAT=m +CONFIG_IP6_NF_TARGET_MASQUERADE=m +CONFIG_IP6_NF_TARGET_NPT=m +CONFIG_NF_DEFRAG_IPV6=m + +# +# DECnet: Netfilter Configuration +# +CONFIG_DECNET_NF_GRABULATOR=m +CONFIG_NF_TABLES_BRIDGE=y +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m +CONFIG_BPFILTER=y +CONFIG_BPFILTER_UMH=m +CONFIG_IP_DCCP=m +CONFIG_INET_DCCP_DIAG=m + +# +# DCCP CCIDs Configuration +# +# CONFIG_IP_DCCP_CCID2_DEBUG is not set +CONFIG_IP_DCCP_CCID3=y +# CONFIG_IP_DCCP_CCID3_DEBUG is not set +CONFIG_IP_DCCP_TFRC_LIB=y + +# +# DCCP Kernel Hacking +# +# CONFIG_IP_DCCP_DEBUG is not set +CONFIG_IP_SCTP=m +CONFIG_SCTP_DBG_OBJCNT=y +CONFIG_SCTP_DEFAULT_COOKIE_HMAC_MD5=y +# CONFIG_SCTP_DEFAULT_COOKIE_HMAC_SHA1 is not set +# CONFIG_SCTP_DEFAULT_COOKIE_HMAC_NONE is not set +CONFIG_SCTP_COOKIE_HMAC_MD5=y +CONFIG_SCTP_COOKIE_HMAC_SHA1=y +CONFIG_INET_SCTP_DIAG=m +CONFIG_RDS=m +CONFIG_RDS_TCP=m +# CONFIG_RDS_DEBUG is not set +CONFIG_TIPC=m +CONFIG_TIPC_MEDIA_UDP=y +CONFIG_TIPC_DIAG=m +CONFIG_ATM=m +CONFIG_ATM_CLIP=m +CONFIG_ATM_CLIP_NO_ICMP=y +CONFIG_ATM_LANE=m +CONFIG_ATM_MPOA=m +CONFIG_ATM_BR2684=m +CONFIG_ATM_BR2684_IPFILTER=y +CONFIG_L2TP=m +CONFIG_L2TP_DEBUGFS=m +CONFIG_L2TP_V3=y +CONFIG_L2TP_IP=m +CONFIG_L2TP_ETH=m +CONFIG_STP=m +CONFIG_GARP=m +CONFIG_MRP=m +CONFIG_BRIDGE=m +CONFIG_BRIDGE_IGMP_SNOOPING=y +CONFIG_BRIDGE_VLAN_FILTERING=y +CONFIG_HAVE_NET_DSA=y +CONFIG_NET_DSA=m +CONFIG_NET_DSA_LEGACY=y +CONFIG_VLAN_8021Q=m +CONFIG_VLAN_8021Q_GVRP=y +CONFIG_VLAN_8021Q_MVRP=y +CONFIG_DECNET=m +CONFIG_DECNET_ROUTER=y +CONFIG_LLC=m +CONFIG_LLC2=m +CONFIG_ATALK=m +CONFIG_DEV_APPLETALK=m +CONFIG_IPDDP=m +CONFIG_IPDDP_ENCAP=y +CONFIG_X25=m +CONFIG_LAPB=m +CONFIG_PHONET=m +CONFIG_6LOWPAN=m +# CONFIG_6LOWPAN_DEBUGFS is not set +CONFIG_6LOWPAN_NHC=m +CONFIG_6LOWPAN_NHC_DEST=m +CONFIG_6LOWPAN_NHC_FRAGMENT=m +CONFIG_6LOWPAN_NHC_HOP=m +CONFIG_6LOWPAN_NHC_IPV6=m +CONFIG_6LOWPAN_NHC_MOBILITY=m +CONFIG_6LOWPAN_NHC_ROUTING=m +CONFIG_6LOWPAN_NHC_UDP=m +# CONFIG_6LOWPAN_GHC_EXT_HDR_HOP is not set +# CONFIG_6LOWPAN_GHC_UDP is not set +# CONFIG_6LOWPAN_GHC_ICMPV6 is not set +# CONFIG_6LOWPAN_GHC_EXT_HDR_DEST is not set +# CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG is not set +# CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE is not set +CONFIG_IEEE802154=m +CONFIG_IEEE802154_NL802154_EXPERIMENTAL=y +CONFIG_IEEE802154_SOCKET=m +CONFIG_IEEE802154_6LOWPAN=m +CONFIG_MAC802154=m +CONFIG_NET_SCHED=y + +# +# Queueing/Scheduling +# +CONFIG_NET_SCH_CBQ=m +CONFIG_NET_SCH_HTB=m +CONFIG_NET_SCH_HFSC=m +CONFIG_NET_SCH_ATM=m +CONFIG_NET_SCH_PRIO=m +CONFIG_NET_SCH_MULTIQ=m +CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_SFB=m +CONFIG_NET_SCH_SFQ=m +CONFIG_NET_SCH_TEQL=m +CONFIG_NET_SCH_TBF=m +CONFIG_NET_SCH_CBS=m +CONFIG_NET_SCH_ETF=m +# CONFIG_NET_SCH_TAPRIO is not set +CONFIG_NET_SCH_GRED=m +CONFIG_NET_SCH_DSMARK=m +CONFIG_NET_SCH_NETEM=m +CONFIG_NET_SCH_DRR=m +CONFIG_NET_SCH_MQPRIO=m +CONFIG_NET_SCH_SKBPRIO=m +CONFIG_NET_SCH_CHOKE=m +CONFIG_NET_SCH_QFQ=m +CONFIG_NET_SCH_CODEL=m +CONFIG_NET_SCH_FQ_CODEL=m +CONFIG_NET_SCH_CAKE=m +CONFIG_NET_SCH_FQ=m +CONFIG_NET_SCH_HHF=m +CONFIG_NET_SCH_PIE=m +CONFIG_NET_SCH_INGRESS=m +CONFIG_NET_SCH_PLUG=m +# CONFIG_NET_SCH_DEFAULT is not set + +# +# Classification +# +CONFIG_NET_CLS=y +CONFIG_NET_CLS_BASIC=m +CONFIG_NET_CLS_TCINDEX=m +CONFIG_NET_CLS_ROUTE4=m +CONFIG_NET_CLS_FW=m +CONFIG_NET_CLS_U32=m +CONFIG_CLS_U32_PERF=y +CONFIG_CLS_U32_MARK=y +CONFIG_NET_CLS_RSVP=m +CONFIG_NET_CLS_RSVP6=m +CONFIG_NET_CLS_FLOW=m +CONFIG_NET_CLS_CGROUP=m +CONFIG_NET_CLS_BPF=m +CONFIG_NET_CLS_FLOWER=m +CONFIG_NET_CLS_MATCHALL=m +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_STACK=32 +CONFIG_NET_EMATCH_CMP=m +CONFIG_NET_EMATCH_NBYTE=m +CONFIG_NET_EMATCH_U32=m +CONFIG_NET_EMATCH_META=m +CONFIG_NET_EMATCH_TEXT=m +CONFIG_NET_EMATCH_CANID=m +CONFIG_NET_EMATCH_IPSET=m +CONFIG_NET_EMATCH_IPT=m +CONFIG_NET_CLS_ACT=y +CONFIG_NET_ACT_POLICE=m +CONFIG_NET_ACT_GACT=m +CONFIG_GACT_PROB=y +CONFIG_NET_ACT_MIRRED=m +# CONFIG_NET_ACT_SAMPLE is not set +CONFIG_NET_ACT_IPT=m +CONFIG_NET_ACT_NAT=m +CONFIG_NET_ACT_PEDIT=m +CONFIG_NET_ACT_SIMP=m +CONFIG_NET_ACT_SKBEDIT=m +CONFIG_NET_ACT_CSUM=m +CONFIG_NET_ACT_VLAN=m +CONFIG_NET_ACT_BPF=m +CONFIG_NET_ACT_CONNMARK=m +# CONFIG_NET_ACT_SKBMOD is not set +# CONFIG_NET_ACT_IFE is not set +# CONFIG_NET_ACT_TUNNEL_KEY is not set +CONFIG_NET_CLS_IND=y +CONFIG_NET_SCH_FIFO=y +CONFIG_DCB=y +CONFIG_DNS_RESOLVER=y +CONFIG_BATMAN_ADV=m +CONFIG_BATMAN_ADV_BATMAN_V=y +CONFIG_BATMAN_ADV_BLA=y +CONFIG_BATMAN_ADV_DAT=y +CONFIG_BATMAN_ADV_NC=y +CONFIG_BATMAN_ADV_MCAST=y +CONFIG_BATMAN_ADV_DEBUGFS=y +# CONFIG_BATMAN_ADV_DEBUG is not set +CONFIG_OPENVSWITCH=m +CONFIG_OPENVSWITCH_GRE=m +CONFIG_OPENVSWITCH_VXLAN=m +CONFIG_OPENVSWITCH_GENEVE=m +CONFIG_VSOCKETS=m +CONFIG_VSOCKETS_DIAG=m +CONFIG_VIRTIO_VSOCKETS=m +CONFIG_VIRTIO_VSOCKETS_COMMON=m +CONFIG_NETLINK_DIAG=m +CONFIG_MPLS=y +CONFIG_NET_MPLS_GSO=m +CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_NSH=m +CONFIG_HSR=m +CONFIG_NET_SWITCHDEV=y +CONFIG_NET_L3_MASTER_DEV=y +# CONFIG_NET_NCSI is not set +CONFIG_RPS=y +CONFIG_RFS_ACCEL=y +CONFIG_XPS=y +CONFIG_CGROUP_NET_PRIO=y +CONFIG_CGROUP_NET_CLASSID=y +CONFIG_NET_RX_BUSY_POLL=y +CONFIG_BQL=y +CONFIG_BPF_JIT=y +CONFIG_BPF_STREAM_PARSER=y +CONFIG_NET_FLOW_LIMIT=y + +# +# Network testing +# +CONFIG_NET_PKTGEN=m +CONFIG_HAMRADIO=y + +# +# Packet Radio protocols +# +CONFIG_AX25=m +CONFIG_AX25_DAMA_SLAVE=y +CONFIG_NETROM=m +CONFIG_ROSE=m + +# +# AX.25 network device drivers +# +CONFIG_MKISS=m +CONFIG_6PACK=m +CONFIG_BPQETHER=m +CONFIG_BAYCOM_SER_FDX=m +CONFIG_BAYCOM_SER_HDX=m +CONFIG_BAYCOM_PAR=m +CONFIG_YAM=m +CONFIG_CAN=m +CONFIG_CAN_RAW=m +CONFIG_CAN_BCM=m +CONFIG_CAN_GW=m + +# +# CAN Device Drivers +# +CONFIG_CAN_VCAN=m +CONFIG_CAN_VXCAN=m +CONFIG_CAN_SLCAN=m +CONFIG_CAN_DEV=m +CONFIG_CAN_CALC_BITTIMING=y +# CONFIG_CAN_FLEXCAN is not set +CONFIG_CAN_GRCAN=m +CONFIG_CAN_XILINXCAN=m +CONFIG_CAN_C_CAN=m +CONFIG_CAN_C_CAN_PLATFORM=m +CONFIG_CAN_CC770=m +CONFIG_CAN_CC770_ISA=m +CONFIG_CAN_CC770_PLATFORM=m +# CONFIG_CAN_IFI_CANFD is not set +CONFIG_CAN_M_CAN=m +CONFIG_CAN_SJA1000=m +CONFIG_CAN_SJA1000_ISA=m +CONFIG_CAN_SJA1000_PLATFORM=m +CONFIG_CAN_SOFTING=m + +# +# CAN SPI interfaces +# +CONFIG_CAN_HI311X=m +CONFIG_CAN_MCP251X=m + +# +# CAN USB interfaces +# +CONFIG_CAN_8DEV_USB=m +CONFIG_CAN_EMS_USB=m +CONFIG_CAN_ESD_USB2=m +CONFIG_CAN_GS_USB=m +CONFIG_CAN_KVASER_USB=m +CONFIG_CAN_MCBA_USB=m +CONFIG_CAN_PEAK_USB=m +# CONFIG_CAN_UCAN is not set +# CONFIG_CAN_DEBUG_DEVICES is not set +CONFIG_BT=m +CONFIG_BT_BREDR=y +CONFIG_BT_RFCOMM=m +CONFIG_BT_RFCOMM_TTY=y +CONFIG_BT_BNEP=m +CONFIG_BT_BNEP_MC_FILTER=y +CONFIG_BT_BNEP_PROTO_FILTER=y +CONFIG_BT_HIDP=m +CONFIG_BT_HS=y +CONFIG_BT_LE=y +CONFIG_BT_6LOWPAN=m +CONFIG_BT_LEDS=y +CONFIG_BT_SELFTEST=y +CONFIG_BT_SELFTEST_ECDH=y +CONFIG_BT_SELFTEST_SMP=y +# CONFIG_BT_DEBUGFS is not set + +# +# Bluetooth device drivers +# +CONFIG_BT_INTEL=m +CONFIG_BT_BCM=m +CONFIG_BT_RTL=m +CONFIG_BT_QCA=m +CONFIG_BT_HCIBTUSB=m +# CONFIG_BT_HCIBTUSB_AUTOSUSPEND is not set +CONFIG_BT_HCIBTUSB_BCM=y +CONFIG_BT_HCIBTUSB_RTL=y +CONFIG_BT_HCIBTSDIO=m +CONFIG_BT_HCIUART=m +CONFIG_BT_HCIUART_SERDEV=y +CONFIG_BT_HCIUART_H4=y +CONFIG_BT_HCIUART_NOKIA=m +CONFIG_BT_HCIUART_BCSP=y +CONFIG_BT_HCIUART_ATH3K=y +CONFIG_BT_HCIUART_LL=y +CONFIG_BT_HCIUART_3WIRE=y +CONFIG_BT_HCIUART_INTEL=y +CONFIG_BT_HCIUART_BCM=y +CONFIG_BT_HCIUART_QCA=y +CONFIG_BT_HCIUART_AG6XX=y +CONFIG_BT_HCIUART_MRVL=y +CONFIG_BT_HCIBCM203X=m +CONFIG_BT_HCIBPA10X=m +CONFIG_BT_HCIBFUSB=m +CONFIG_BT_HCIVHCI=m +CONFIG_BT_MRVL=m +CONFIG_BT_MRVL_SDIO=m +CONFIG_BT_ATH3K=m +CONFIG_BT_MTKUART=m +CONFIG_BT_HCIRSI=m +# CONFIG_AF_RXRPC is not set +# CONFIG_AF_KCM is not set +CONFIG_STREAM_PARSER=y +CONFIG_FIB_RULES=y +CONFIG_WIRELESS=y +CONFIG_WIRELESS_EXT=y +CONFIG_WEXT_CORE=y +CONFIG_WEXT_PROC=y +CONFIG_WEXT_SPY=y +CONFIG_WEXT_PRIV=y +CONFIG_CFG80211=m +# CONFIG_NL80211_TESTMODE is not set +# CONFIG_CFG80211_DEVELOPER_WARNINGS is not set +CONFIG_CFG80211_CERTIFICATION_ONUS=y +CONFIG_CFG80211_REQUIRE_SIGNED_REGDB=y +CONFIG_CFG80211_USE_KERNEL_REGDB_KEYS=y +CONFIG_CFG80211_EXTRA_REGDB_KEYDIR="" +CONFIG_CFG80211_REG_CELLULAR_HINTS=y +CONFIG_CFG80211_REG_RELAX_NO_IR=y +CONFIG_CFG80211_DEFAULT_PS=y +# CONFIG_CFG80211_DEBUGFS is not set +CONFIG_CFG80211_CRDA_SUPPORT=y +CONFIG_CFG80211_WEXT=y +CONFIG_LIB80211=m +CONFIG_LIB80211_CRYPT_WEP=m +CONFIG_LIB80211_CRYPT_CCMP=m +CONFIG_LIB80211_CRYPT_TKIP=m +CONFIG_LIB80211_DEBUG=y +CONFIG_MAC80211=m +CONFIG_MAC80211_HAS_RC=y +CONFIG_MAC80211_RC_MINSTREL=y +CONFIG_MAC80211_RC_DEFAULT_MINSTREL=y +CONFIG_MAC80211_RC_DEFAULT="minstrel_ht" +CONFIG_MAC80211_MESH=y +CONFIG_MAC80211_LEDS=y +# CONFIG_MAC80211_DEBUGFS is not set +# CONFIG_MAC80211_MESSAGE_TRACING is not set +# CONFIG_MAC80211_DEBUG_MENU is not set +CONFIG_MAC80211_STA_HASH_MAX_SIZE=0 +CONFIG_WIMAX=m +CONFIG_WIMAX_DEBUG_LEVEL=8 +CONFIG_RFKILL=m +CONFIG_RFKILL_LEDS=y +CONFIG_RFKILL_INPUT=y +CONFIG_RFKILL_GPIO=m +CONFIG_NET_9P=m +CONFIG_NET_9P_VIRTIO=m +# CONFIG_NET_9P_DEBUG is not set +CONFIG_CAIF=m +# CONFIG_CAIF_DEBUG is not set +CONFIG_CAIF_NETDEV=m +CONFIG_CAIF_USB=m +CONFIG_CEPH_LIB=m +# CONFIG_CEPH_LIB_PRETTYDEBUG is not set +CONFIG_CEPH_LIB_USE_DNS_RESOLVER=y +CONFIG_NFC=m +CONFIG_NFC_DIGITAL=m +CONFIG_NFC_NCI=m +CONFIG_NFC_NCI_SPI=m +CONFIG_NFC_NCI_UART=m +CONFIG_NFC_HCI=m +CONFIG_NFC_SHDLC=y + +# +# Near Field Communication (NFC) devices +# +CONFIG_NFC_TRF7970A=m +CONFIG_NFC_SIM=m +CONFIG_NFC_PORT100=m +CONFIG_NFC_FDP=m +CONFIG_NFC_FDP_I2C=m +# CONFIG_NFC_PN544_I2C is not set +CONFIG_NFC_PN533=m +CONFIG_NFC_PN533_USB=m +CONFIG_NFC_PN533_I2C=m +# CONFIG_NFC_MICROREAD_I2C is not set +CONFIG_NFC_MRVL=m +CONFIG_NFC_MRVL_USB=m +CONFIG_NFC_MRVL_UART=m +CONFIG_NFC_MRVL_I2C=m +CONFIG_NFC_MRVL_SPI=m +CONFIG_NFC_ST21NFCA=m +CONFIG_NFC_ST21NFCA_I2C=m +CONFIG_NFC_ST_NCI=m +CONFIG_NFC_ST_NCI_I2C=m +CONFIG_NFC_ST_NCI_SPI=m +CONFIG_NFC_NXP_NCI=m +CONFIG_NFC_NXP_NCI_I2C=m +CONFIG_NFC_S3FWRN5=m +CONFIG_NFC_S3FWRN5_I2C=m +CONFIG_NFC_ST95HF=m +CONFIG_PSAMPLE=m +CONFIG_NET_IFE=m +CONFIG_LWTUNNEL=y +CONFIG_LWTUNNEL_BPF=y +CONFIG_DST_CACHE=y +CONFIG_GRO_CELLS=y +CONFIG_NET_SOCK_MSG=y +# CONFIG_NET_DEVLINK is not set +CONFIG_FAILOVER=y +CONFIG_HAVE_EBPF_JIT=y + +# +# Device Drivers +# +CONFIG_ARM_AMBA=y +CONFIG_HAVE_PCI=y +# CONFIG_PCI is not set +# CONFIG_PCCARD is not set + +# +# Generic Driver Options +# +# CONFIG_UEVENT_HELPER is not set +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_STANDALONE=y +CONFIG_PREVENT_FIRMWARE_BUILD=y + +# +# Firmware loader +# +CONFIG_FW_LOADER=y +CONFIG_EXTRA_FIRMWARE="" +# CONFIG_FW_LOADER_USER_HELPER is not set +CONFIG_WANT_DEV_COREDUMP=y +CONFIG_ALLOW_DEV_COREDUMP=y +CONFIG_DEV_COREDUMP=y +# CONFIG_DEBUG_DRIVER is not set +# CONFIG_DEBUG_DEVRES is not set +# CONFIG_DEBUG_TEST_DRIVER_REMOVE is not set +# CONFIG_TEST_ASYNC_DRIVER_PROBE is not set +CONFIG_GENERIC_CPU_AUTOPROBE=y +CONFIG_SOC_BUS=y +CONFIG_REGMAP=y +CONFIG_REGMAP_I2C=y +CONFIG_REGMAP_SPI=y +CONFIG_REGMAP_MMIO=y +CONFIG_REGMAP_IRQ=y +CONFIG_DMA_SHARED_BUFFER=y +# CONFIG_DMA_FENCE_TRACE is not set +CONFIG_GENERIC_ARCH_TOPOLOGY=y + +# +# Bus devices +# +CONFIG_ARM_CCI=y +CONFIG_BRCMSTB_GISB_ARB=y +CONFIG_SIMPLE_PM_BUS=y +CONFIG_VEXPRESS_CONFIG=y +CONFIG_CONNECTOR=m +# CONFIG_GNSS is not set +CONFIG_MTD=y +# CONFIG_MTD_TESTS is not set +# CONFIG_MTD_CMDLINE_PARTS is not set +# CONFIG_MTD_AFS_PARTS is not set +CONFIG_MTD_OF_PARTS=y +# CONFIG_MTD_AR7_PARTS is not set + +# +# Partition parsers +# +# CONFIG_MTD_REDBOOT_PARTS is not set + +# +# User Modules And Translation Layers +# +CONFIG_MTD_BLKDEVS=y +CONFIG_MTD_BLOCK=y +# CONFIG_FTL is not set +# CONFIG_NFTL is not set +# CONFIG_INFTL is not set +# CONFIG_RFD_FTL is not set +# CONFIG_SSFDC is not set +# CONFIG_SM_FTL is not set +# CONFIG_MTD_OOPS is not set +# CONFIG_MTD_SWAP is not set +# CONFIG_MTD_PARTITIONED_MASTER is not set + +# +# RAM/ROM/Flash chip drivers +# +# CONFIG_MTD_CFI is not set +# CONFIG_MTD_JEDECPROBE is not set +CONFIG_MTD_MAP_BANK_WIDTH_1=y +CONFIG_MTD_MAP_BANK_WIDTH_2=y +CONFIG_MTD_MAP_BANK_WIDTH_4=y +CONFIG_MTD_CFI_I1=y +CONFIG_MTD_CFI_I2=y +# CONFIG_MTD_RAM is not set +# CONFIG_MTD_ROM is not set +# CONFIG_MTD_ABSENT is not set + +# +# Mapping drivers for chip access +# +# CONFIG_MTD_COMPLEX_MAPPINGS is not set +# CONFIG_MTD_PLATRAM is not set + +# +# Self-contained MTD device drivers +# +# CONFIG_MTD_DATAFLASH is not set +CONFIG_MTD_M25P80=y +CONFIG_MTD_MCHP23K256=m +# CONFIG_MTD_SST25L is not set +# CONFIG_MTD_SLRAM is not set +# CONFIG_MTD_PHRAM is not set +# CONFIG_MTD_MTDRAM is not set +# CONFIG_MTD_BLOCK2MTD is not set + +# +# Disk-On-Chip Device Drivers +# +# CONFIG_MTD_DOCG3 is not set +# CONFIG_MTD_ONENAND is not set +CONFIG_MTD_NAND_ECC=y +# CONFIG_MTD_NAND_ECC_SMC is not set +CONFIG_MTD_NAND=y +# CONFIG_MTD_NAND_ECC_BCH is not set +CONFIG_MTD_NAND_DENALI=y +CONFIG_MTD_NAND_DENALI_DT=y +# CONFIG_MTD_NAND_GPIO is not set +# CONFIG_MTD_NAND_DISKONCHIP is not set +# CONFIG_MTD_NAND_NANDSIM is not set +# CONFIG_MTD_NAND_BRCMNAND is not set +# CONFIG_MTD_NAND_PLATFORM is not set +CONFIG_MTD_NAND_MESON=m +# CONFIG_MTD_SPI_NAND is not set + +# +# LPDDR & LPDDR2 PCM memory drivers +# +# CONFIG_MTD_LPDDR is not set +CONFIG_MTD_SPI_NOR=y +CONFIG_MTD_SPI_NOR_USE_4K_SECTORS=y +CONFIG_SPI_CADENCE_QUADSPI=m +# CONFIG_SPI_MTK_QUADSPI is not set +# CONFIG_MTD_UBI is not set +CONFIG_DTC=y +CONFIG_OF=y +# CONFIG_OF_UNITTEST is not set +CONFIG_OF_FLATTREE=y +CONFIG_OF_EARLY_FLATTREE=y +CONFIG_OF_KOBJ=y +CONFIG_OF_DYNAMIC=y +CONFIG_OF_ADDRESS=y +CONFIG_OF_IRQ=y +CONFIG_OF_NET=y +CONFIG_OF_MDIO=y +CONFIG_OF_RESERVED_MEM=y +CONFIG_OF_RESOLVE=y +CONFIG_OF_OVERLAY=y +CONFIG_PARPORT=m +CONFIG_PARPORT_AX88796=m +# CONFIG_PARPORT_1284 is not set +CONFIG_PARPORT_NOT_PC=y +CONFIG_BLK_DEV=y +# CONFIG_BLK_DEV_NULL_BLK is not set +CONFIG_CDROM=y +CONFIG_ZRAM=m +CONFIG_ZRAM_WRITEBACK=y +# CONFIG_ZRAM_MEMORY_TRACKING is not set +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_LOOP_MIN_COUNT=8 +CONFIG_BLK_DEV_CRYPTOLOOP=m +CONFIG_BLK_DEV_DRBD=m +# CONFIG_DRBD_FAULT_INJECTION is not set +CONFIG_BLK_DEV_NBD=m +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=4 +CONFIG_BLK_DEV_RAM_SIZE=4096 +# CONFIG_CDROM_PKTCDVD is not set +CONFIG_ATA_OVER_ETH=m +CONFIG_VIRTIO_BLK=y +# CONFIG_VIRTIO_BLK_SCSI is not set +# CONFIG_BLK_DEV_RBD is not set + +# +# NVME Support +# +# CONFIG_NVME_FC is not set +# CONFIG_NVME_TARGET is not set + +# +# Misc devices +# +# CONFIG_AD525X_DPOT is not set +# CONFIG_DUMMY_IRQ is not set +# CONFIG_ICS932S401 is not set +# CONFIG_ENCLOSURE_SERVICES is not set +# CONFIG_APDS9802ALS is not set +# CONFIG_ISL29003 is not set +# CONFIG_ISL29020 is not set +# CONFIG_SENSORS_TSL2550 is not set +# CONFIG_SENSORS_BH1770 is not set +# CONFIG_SENSORS_APDS990X is not set +# CONFIG_HMC6352 is not set +# CONFIG_DS1682 is not set +# CONFIG_USB_SWITCH_FSA9480 is not set +# CONFIG_LATTICE_ECP3_CONFIG is not set +CONFIG_SRAM=y +CONFIG_VEXPRESS_SYSCFG=y +CONFIG_MISC_RTSX=m +# CONFIG_PVPANIC is not set +# CONFIG_C2PORT is not set + +# +# EEPROM support +# +# CONFIG_EEPROM_AT24 is not set +CONFIG_EEPROM_AT25=m +# CONFIG_EEPROM_LEGACY is not set +# CONFIG_EEPROM_MAX6875 is not set +CONFIG_EEPROM_93CX6=m +# CONFIG_EEPROM_93XX46 is not set +# CONFIG_EEPROM_IDT_89HPESX is not set +# CONFIG_EEPROM_EE1004 is not set + +# +# Texas Instruments shared transport line discipline +# +# CONFIG_TI_ST is not set +# CONFIG_SENSORS_LIS3_SPI is not set +# CONFIG_SENSORS_LIS3_I2C is not set +# CONFIG_ALTERA_STAPL is not set + +# +# Intel MIC & related support +# + +# +# Intel MIC Bus Driver +# + +# +# SCIF Bus Driver +# + +# +# VOP Bus Driver +# +# CONFIG_VOP_BUS is not set + +# +# Intel MIC Host Driver +# + +# +# Intel MIC Card Driver +# + +# +# SCIF Driver +# + +# +# Intel MIC Coprocessor State Management (COSM) Drivers +# + +# +# VOP Driver +# +# CONFIG_ECHO is not set +CONFIG_MISC_RTSX_USB=m + +# +# SCSI device support +# +CONFIG_SCSI_MOD=y +# CONFIG_RAID_ATTRS is not set +CONFIG_SCSI=y +CONFIG_SCSI_DMA=y +# CONFIG_SCSI_PROC_FS is not set + +# +# SCSI support type (disk, tape, CD-ROM) +# +CONFIG_BLK_DEV_SD=y +# CONFIG_CHR_DEV_ST is not set +# CONFIG_CHR_DEV_OSST is not set +CONFIG_BLK_DEV_SR=y +# CONFIG_BLK_DEV_SR_VENDOR is not set +# CONFIG_CHR_DEV_SG is not set +# CONFIG_CHR_DEV_SCH is not set +# CONFIG_SCSI_CONSTANTS is not set +# CONFIG_SCSI_LOGGING is not set +# CONFIG_SCSI_SCAN_ASYNC is not set + +# +# SCSI Transports +# +# CONFIG_SCSI_SPI_ATTRS is not set +# CONFIG_SCSI_FC_ATTRS is not set +CONFIG_SCSI_ISCSI_ATTRS=m +CONFIG_SCSI_SAS_ATTRS=y +CONFIG_SCSI_SAS_LIBSAS=y +CONFIG_SCSI_SAS_HOST_SMP=y +# CONFIG_SCSI_SRP_ATTRS is not set +CONFIG_SCSI_LOWLEVEL=y +CONFIG_ISCSI_TCP=m +CONFIG_ISCSI_BOOT_SYSFS=m +# CONFIG_SCSI_UFSHCD is not set +# CONFIG_SCSI_DEBUG is not set +# CONFIG_SCSI_VIRTIO is not set +# CONFIG_SCSI_DH is not set +CONFIG_HAVE_PATA_PLATFORM=y +# CONFIG_ATA is not set +CONFIG_MD=y +CONFIG_BLK_DEV_MD=m +CONFIG_MD_LINEAR=m +CONFIG_MD_RAID0=m +CONFIG_MD_RAID1=m +CONFIG_MD_RAID10=m +CONFIG_MD_RAID456=m +CONFIG_MD_MULTIPATH=m +CONFIG_MD_FAULTY=m +CONFIG_BCACHE=m +# CONFIG_BCACHE_DEBUG is not set +# CONFIG_BCACHE_CLOSURES_DEBUG is not set +CONFIG_BLK_DEV_DM_BUILTIN=y +CONFIG_BLK_DEV_DM=m +# CONFIG_DM_DEBUG is not set +CONFIG_DM_BUFIO=m +# CONFIG_DM_DEBUG_BLOCK_MANAGER_LOCKING is not set +CONFIG_DM_BIO_PRISON=m +CONFIG_DM_PERSISTENT_DATA=m +# CONFIG_DM_UNSTRIPED is not set +CONFIG_DM_CRYPT=m +CONFIG_DM_SNAPSHOT=m +CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_CACHE=m +CONFIG_DM_CACHE_SMQ=m +# CONFIG_DM_WRITECACHE is not set +CONFIG_DM_ERA=m +CONFIG_DM_MIRROR=m +CONFIG_DM_LOG_USERSPACE=m +CONFIG_DM_RAID=m +CONFIG_DM_ZERO=m +CONFIG_DM_MULTIPATH=m +CONFIG_DM_MULTIPATH_QL=m +CONFIG_DM_MULTIPATH_ST=m +CONFIG_DM_DELAY=m +# CONFIG_DM_UEVENT is not set +# CONFIG_DM_FLAKEY is not set +CONFIG_DM_VERITY=m +# CONFIG_DM_VERITY_FEC is not set +CONFIG_DM_SWITCH=m +CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m +CONFIG_TARGET_CORE=m +# CONFIG_TCM_IBLOCK is not set +# CONFIG_TCM_FILEIO is not set +# CONFIG_TCM_PSCSI is not set +# CONFIG_TCM_USER2 is not set +# CONFIG_LOOPBACK_TARGET is not set +CONFIG_ISCSI_TARGET=m +CONFIG_NETDEVICES=y +CONFIG_MII=y +CONFIG_NET_CORE=y +CONFIG_BONDING=m +CONFIG_DUMMY=m +# CONFIG_EQUALIZER is not set +# CONFIG_IFB is not set +CONFIG_NET_TEAM=m +CONFIG_NET_TEAM_MODE_BROADCAST=m +CONFIG_NET_TEAM_MODE_ROUNDROBIN=m +CONFIG_NET_TEAM_MODE_RANDOM=m +CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m +CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN_L3S=y +CONFIG_IPVLAN=m +CONFIG_IPVTAP=m +CONFIG_VXLAN=m +CONFIG_GENEVE=m +CONFIG_GTP=m +CONFIG_MACSEC=m +CONFIG_NETCONSOLE=m +CONFIG_NETCONSOLE_DYNAMIC=y +CONFIG_NETPOLL=y +CONFIG_NET_POLL_CONTROLLER=y +CONFIG_TUN=y +CONFIG_TAP=m +CONFIG_TUN_VNET_CROSS_LE=y +CONFIG_VETH=m +CONFIG_VIRTIO_NET=y +CONFIG_NLMON=m +# CONFIG_NET_VRF is not set +CONFIG_ATM_DRIVERS=y +# CONFIG_ATM_DUMMY is not set +# CONFIG_ATM_TCP is not set + +# +# CAIF transport drivers +# +# CONFIG_CAIF_TTY is not set +# CONFIG_CAIF_SPI_SLAVE is not set +# CONFIG_CAIF_HSI is not set +# CONFIG_CAIF_VIRTIO is not set + +# +# Distributed Switch Architecture drivers +# +# CONFIG_B53 is not set +# CONFIG_NET_DSA_BCM_SF2 is not set +# CONFIG_NET_DSA_LOOP is not set +# CONFIG_NET_DSA_LANTIQ_GSWIP is not set +# CONFIG_NET_DSA_MT7530 is not set +# CONFIG_NET_DSA_MV88E6060 is not set +# CONFIG_NET_DSA_MICROCHIP_KSZ9477 is not set +# CONFIG_NET_DSA_MV88E6XXX is not set +# CONFIG_NET_DSA_QCA8K is not set +# CONFIG_NET_DSA_REALTEK_SMI is not set +# CONFIG_NET_DSA_SMSC_LAN9303_I2C is not set +# CONFIG_NET_DSA_SMSC_LAN9303_MDIO is not set +# CONFIG_NET_DSA_VITESSE_VSC73XX is not set +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_ALACRITECH=y +# CONFIG_ALTERA_TSE is not set +CONFIG_NET_VENDOR_AMAZON=y +CONFIG_NET_VENDOR_AMD=y +CONFIG_AMD_XGBE=y +# CONFIG_AMD_XGBE_DCB is not set +CONFIG_NET_VENDOR_AQUANTIA=y +CONFIG_NET_VENDOR_ARC=y +CONFIG_NET_VENDOR_AURORA=y +# CONFIG_AURORA_NB8800 is not set +CONFIG_NET_VENDOR_BROADCOM=y +CONFIG_B44=m +CONFIG_BCMGENET=m +CONFIG_SYSTEMPORT=m +CONFIG_NET_VENDOR_CADENCE=y +CONFIG_MACB=y +CONFIG_MACB_USE_HWSTAMP=y +CONFIG_NET_VENDOR_CAVIUM=y +CONFIG_NET_VENDOR_CORTINA=y +# CONFIG_GEMINI_ETHERNET is not set +# CONFIG_DNET is not set +CONFIG_NET_VENDOR_EZCHIP=y +# CONFIG_EZCHIP_NPS_MANAGEMENT_ENET is not set +CONFIG_NET_VENDOR_HISILICON=y +CONFIG_HIX5HD2_GMAC=y +# CONFIG_HISI_FEMAC is not set +# CONFIG_HIP04_ETH is not set +CONFIG_HNS_MDIO=y +CONFIG_HNS=y +CONFIG_HNS_DSAF=y +CONFIG_HNS_ENET=y +CONFIG_NET_VENDOR_HUAWEI=y +CONFIG_NET_VENDOR_I825XX=y +CONFIG_NET_VENDOR_INTEL=y +CONFIG_NET_VENDOR_MARVELL=y +CONFIG_MVMDIO=y +CONFIG_NET_VENDOR_MELLANOX=y +# CONFIG_MLXSW_CORE is not set +# CONFIG_MLXFW is not set +CONFIG_NET_VENDOR_MICREL=y +# CONFIG_KS8842 is not set +# CONFIG_KS8851 is not set +# CONFIG_KS8851_MLL is not set +CONFIG_NET_VENDOR_MICROCHIP=y +# CONFIG_ENC28J60 is not set +# CONFIG_ENCX24J600 is not set +CONFIG_NET_VENDOR_MICROSEMI=y +# CONFIG_MSCC_OCELOT_SWITCH is not set +CONFIG_NET_VENDOR_NATSEMI=y +CONFIG_NET_VENDOR_NETRONOME=y +CONFIG_NET_VENDOR_NI=y +# CONFIG_NI_XGE_MANAGEMENT_ENET is not set +CONFIG_NET_VENDOR_8390=y +# CONFIG_ETHOC is not set +CONFIG_NET_VENDOR_QUALCOMM=y +# CONFIG_QCA7000_SPI is not set +# CONFIG_QCA7000_UART is not set +CONFIG_QCOM_EMAC=m +# CONFIG_RMNET is not set +CONFIG_NET_VENDOR_RENESAS=y +CONFIG_NET_VENDOR_ROCKER=y +CONFIG_NET_VENDOR_SAMSUNG=y +# CONFIG_SXGBE_ETH is not set +CONFIG_NET_VENDOR_SEEQ=y +CONFIG_NET_VENDOR_SOLARFLARE=y +CONFIG_NET_VENDOR_SMSC=y +CONFIG_SMC91X=y +CONFIG_SMSC911X=y +CONFIG_NET_VENDOR_SOCIONEXT=y +CONFIG_NET_VENDOR_STMICRO=y +CONFIG_STMMAC_ETH=y +CONFIG_STMMAC_PLATFORM=y +# CONFIG_DWMAC_DWC_QOS_ETH is not set +CONFIG_DWMAC_GENERIC=y +CONFIG_DWMAC_MESON=y +CONFIG_NET_VENDOR_SYNOPSYS=y +# CONFIG_DWC_XLGMAC is not set +CONFIG_NET_VENDOR_VIA=y +# CONFIG_VIA_RHINE is not set +# CONFIG_VIA_VELOCITY is not set +CONFIG_NET_VENDOR_WIZNET=y +# CONFIG_WIZNET_W5100 is not set +# CONFIG_WIZNET_W5300 is not set +CONFIG_MDIO_DEVICE=y +CONFIG_MDIO_BUS=y +CONFIG_MDIO_BCM_UNIMAC=m +CONFIG_MDIO_BITBANG=y +CONFIG_MDIO_BUS_MUX=y +# CONFIG_MDIO_BUS_MUX_GPIO is not set +CONFIG_MDIO_BUS_MUX_MESON_G12A=m +CONFIG_MDIO_BUS_MUX_MMIOREG=y +CONFIG_MDIO_BUS_MUX_MULTIPLEXER=m +CONFIG_MDIO_GPIO=m +# CONFIG_MDIO_HISI_FEMAC is not set +# CONFIG_MDIO_MSCC_MIIM is not set +# CONFIG_MDIO_OCTEON is not set +CONFIG_PHYLINK=m +CONFIG_PHYLIB=y +CONFIG_SWPHY=y +CONFIG_LED_TRIGGER_PHY=y + +# +# MII PHY device drivers +# +# CONFIG_SFP is not set +# CONFIG_AMD_PHY is not set +# CONFIG_AQUANTIA_PHY is not set +# CONFIG_ASIX_PHY is not set +CONFIG_AT803X_PHY=m +CONFIG_BCM7XXX_PHY=m +# CONFIG_BCM87XX_PHY is not set +CONFIG_BCM_NET_PHYLIB=m +# CONFIG_BROADCOM_PHY is not set +# CONFIG_CICADA_PHY is not set +# CONFIG_CORTINA_PHY is not set +# CONFIG_DAVICOM_PHY is not set +# CONFIG_DP83822_PHY is not set +# CONFIG_DP83TC811_PHY is not set +# CONFIG_DP83848_PHY is not set +# CONFIG_DP83867_PHY is not set +CONFIG_FIXED_PHY=y +# CONFIG_ICPLUS_PHY is not set +# CONFIG_INTEL_XWAY_PHY is not set +# CONFIG_LSI_ET1011C_PHY is not set +# CONFIG_LXT_PHY is not set +# CONFIG_MARVELL_PHY is not set +# CONFIG_MARVELL_10G_PHY is not set +CONFIG_MESON_GXL_PHY=y +CONFIG_MICREL_PHY=y +CONFIG_MICROCHIP_PHY=m +# CONFIG_MICROCHIP_T1_PHY is not set +# CONFIG_MICROSEMI_PHY is not set +# CONFIG_NATIONAL_PHY is not set +# CONFIG_QSEMI_PHY is not set +CONFIG_REALTEK_PHY=y +# CONFIG_RENESAS_PHY is not set +# CONFIG_ROCKCHIP_PHY is not set +# CONFIG_SMSC_PHY is not set +# CONFIG_STE10XP is not set +# CONFIG_TERANETICS_PHY is not set +# CONFIG_VITESSE_PHY is not set +# CONFIG_XILINX_GMII2RGMII is not set +# CONFIG_MICREL_KS8995MA is not set +# CONFIG_PLIP is not set +CONFIG_PPP=m +CONFIG_PPP_BSDCOMP=m +CONFIG_PPP_DEFLATE=m +CONFIG_PPP_FILTER=y +CONFIG_PPP_MPPE=m +# CONFIG_PPP_MULTILINK is not set +# CONFIG_PPPOATM is not set +CONFIG_PPPOE=m +CONFIG_PPTP=m +CONFIG_PPPOL2TP=m +CONFIG_PPP_ASYNC=m +CONFIG_PPP_SYNC_TTY=m +CONFIG_SLIP=m +CONFIG_SLHC=m +CONFIG_SLIP_COMPRESSED=y +CONFIG_SLIP_SMART=y +CONFIG_SLIP_MODE_SLIP6=y +CONFIG_USB_NET_DRIVERS=m +CONFIG_USB_CATC=m +CONFIG_USB_KAWETH=m +CONFIG_USB_PEGASUS=m +CONFIG_USB_RTL8150=m +CONFIG_USB_RTL8152=m +CONFIG_USB_LAN78XX=m +CONFIG_USB_USBNET=m +CONFIG_USB_NET_AX8817X=m +CONFIG_USB_NET_AX88179_178A=m +CONFIG_USB_NET_CDCETHER=m +CONFIG_USB_NET_CDC_EEM=m +CONFIG_USB_NET_CDC_NCM=m +CONFIG_USB_NET_HUAWEI_CDC_NCM=m +CONFIG_USB_NET_CDC_MBIM=m +CONFIG_USB_NET_DM9601=m +CONFIG_USB_NET_SR9700=m +CONFIG_USB_NET_SR9800=m +CONFIG_USB_NET_SMSC75XX=m +CONFIG_USB_NET_SMSC95XX=m +CONFIG_USB_NET_GL620A=m +CONFIG_USB_NET_NET1080=m +CONFIG_USB_NET_PLUSB=m +CONFIG_USB_NET_MCS7830=m +CONFIG_USB_NET_RNDIS_HOST=m +CONFIG_USB_NET_CDC_SUBSET_ENABLE=m +CONFIG_USB_NET_CDC_SUBSET=m +CONFIG_USB_ALI_M5632=y +CONFIG_USB_AN2720=y +CONFIG_USB_BELKIN=y +CONFIG_USB_ARMLINUX=y +CONFIG_USB_EPSON2888=y +CONFIG_USB_KC2190=y +CONFIG_USB_NET_ZAURUS=m +CONFIG_USB_NET_CX82310_ETH=m +CONFIG_USB_NET_KALMIA=m +CONFIG_USB_NET_QMI_WWAN=m +CONFIG_USB_HSO=m +CONFIG_USB_NET_INT51X1=m +CONFIG_USB_CDC_PHONET=m +CONFIG_USB_IPHETH=m +CONFIG_USB_SIERRA_NET=m +CONFIG_USB_VL600=m +CONFIG_USB_NET_CH9200=m +# CONFIG_USB_NET_AQC111 is not set +CONFIG_WLAN=y +CONFIG_WIRELESS_WDS=y +CONFIG_WLAN_VENDOR_ADMTEK=y +CONFIG_ATH_COMMON=m +CONFIG_WLAN_VENDOR_ATH=y +# CONFIG_ATH_DEBUG is not set +CONFIG_ATH_REG_DYNAMIC_USER_REG_HINTS=y +CONFIG_ATH_REG_DYNAMIC_USER_CERT_TESTING=y +CONFIG_ATH9K_HW=m +CONFIG_ATH9K_COMMON=m +CONFIG_ATH9K_BTCOEX_SUPPORT=y +CONFIG_ATH9K=m +CONFIG_ATH9K_AHB=y +# CONFIG_ATH9K_DEBUGFS is not set +CONFIG_ATH9K_DFS_CERTIFIED=y +CONFIG_ATH9K_DYNACK=y +CONFIG_ATH9K_WOW=y +CONFIG_ATH9K_RFKILL=y +CONFIG_ATH9K_CHANNEL_CONTEXT=y +CONFIG_ATH9K_PCOEM=y +CONFIG_ATH9K_HTC=m +# CONFIG_ATH9K_HTC_DEBUGFS is not set +CONFIG_ATH9K_HWRNG=y +CONFIG_CARL9170=m +CONFIG_CARL9170_LEDS=y +CONFIG_CARL9170_WPC=y +CONFIG_CARL9170_HWRNG=y +CONFIG_ATH6KL=m +CONFIG_ATH6KL_SDIO=m +CONFIG_ATH6KL_USB=m +# CONFIG_ATH6KL_DEBUG is not set +CONFIG_ATH6KL_REGDOMAIN=y +CONFIG_AR5523=m +CONFIG_ATH10K=m +CONFIG_ATH10K_CE=y +CONFIG_ATH10K_SDIO=m +CONFIG_ATH10K_USB=m +# CONFIG_ATH10K_DEBUG is not set +# CONFIG_ATH10K_DEBUGFS is not set +CONFIG_ATH10K_DFS_CERTIFIED=y +CONFIG_WCN36XX=m +# CONFIG_WCN36XX_DEBUGFS is not set +CONFIG_WLAN_VENDOR_ATMEL=y +CONFIG_AT76C50X_USB=m +CONFIG_WLAN_VENDOR_BROADCOM=y +CONFIG_B43=m +CONFIG_B43_BCMA=y +CONFIG_B43_SSB=y +CONFIG_B43_BUSES_BCMA_AND_SSB=y +# CONFIG_B43_BUSES_BCMA is not set +# CONFIG_B43_BUSES_SSB is not set +CONFIG_B43_SDIO=y +CONFIG_B43_BCMA_PIO=y +CONFIG_B43_PIO=y +CONFIG_B43_PHY_G=y +CONFIG_B43_PHY_N=y +CONFIG_B43_PHY_LP=y +CONFIG_B43_PHY_HT=y +CONFIG_B43_LEDS=y +CONFIG_B43_HWRNG=y +CONFIG_B43_DEBUG=y +CONFIG_B43LEGACY=m +CONFIG_B43LEGACY_LEDS=y +CONFIG_B43LEGACY_HWRNG=y +CONFIG_B43LEGACY_DEBUG=y +CONFIG_B43LEGACY_DMA=y +CONFIG_B43LEGACY_PIO=y +CONFIG_B43LEGACY_DMA_AND_PIO_MODE=y +# CONFIG_B43LEGACY_DMA_MODE is not set +# CONFIG_B43LEGACY_PIO_MODE is not set +CONFIG_BRCMUTIL=m +CONFIG_BRCMSMAC=m +CONFIG_BRCMFMAC=m +CONFIG_BRCMFMAC_PROTO_BCDC=y +CONFIG_BRCMFMAC_SDIO=y +CONFIG_BRCMFMAC_USB=y +CONFIG_BRCM_TRACING=y +CONFIG_BRCMDBG=y +CONFIG_WLAN_VENDOR_CISCO=y +CONFIG_WLAN_VENDOR_INTEL=y +CONFIG_WLAN_VENDOR_INTERSIL=y +CONFIG_HOSTAP=m +CONFIG_HOSTAP_FIRMWARE=y +CONFIG_HOSTAP_FIRMWARE_NVRAM=y +CONFIG_P54_COMMON=m +CONFIG_P54_USB=m +CONFIG_P54_SPI=m +CONFIG_P54_SPI_DEFAULT_EEPROM=y +CONFIG_P54_LEDS=y +CONFIG_WLAN_VENDOR_MARVELL=y +CONFIG_LIBERTAS=m +CONFIG_LIBERTAS_USB=m +CONFIG_LIBERTAS_SDIO=m +CONFIG_LIBERTAS_SPI=m +# CONFIG_LIBERTAS_DEBUG is not set +CONFIG_LIBERTAS_MESH=y +CONFIG_LIBERTAS_THINFIRM=m +# CONFIG_LIBERTAS_THINFIRM_DEBUG is not set +CONFIG_LIBERTAS_THINFIRM_USB=m +CONFIG_MWIFIEX=m +CONFIG_MWIFIEX_SDIO=m +CONFIG_MWIFIEX_USB=m +CONFIG_WLAN_VENDOR_MEDIATEK=y +CONFIG_MT7601U=m +CONFIG_MT76_CORE=m +CONFIG_MT76_LEDS=y +CONFIG_MT76_USB=m +CONFIG_MT76x02_LIB=m +CONFIG_MT76x02_USB=m +CONFIG_MT76x0_COMMON=m +CONFIG_MT76x0U=m +CONFIG_MT76x2_COMMON=m +CONFIG_MT76x2U=m +CONFIG_WLAN_VENDOR_RALINK=y +CONFIG_RT2X00=m +CONFIG_RT2500USB=m +CONFIG_RT73USB=m +CONFIG_RT2800USB=m +CONFIG_RT2800USB_RT33XX=y +CONFIG_RT2800USB_RT35XX=y +CONFIG_RT2800USB_RT3573=y +CONFIG_RT2800USB_RT53XX=y +CONFIG_RT2800USB_RT55XX=y +CONFIG_RT2800USB_UNKNOWN=y +CONFIG_RT2800_LIB=m +CONFIG_RT2X00_LIB_USB=m +CONFIG_RT2X00_LIB=m +CONFIG_RT2X00_LIB_FIRMWARE=y +CONFIG_RT2X00_LIB_CRYPTO=y +CONFIG_RT2X00_LIB_LEDS=y +# CONFIG_RT2X00_DEBUG is not set +CONFIG_WLAN_VENDOR_REALTEK=y +CONFIG_RTL8187=m +CONFIG_RTL8187_LEDS=y +CONFIG_RTL_CARDS=m +CONFIG_RTL8192CU=m +CONFIG_RTLWIFI=m +CONFIG_RTLWIFI_USB=m +CONFIG_RTLWIFI_DEBUG=y +CONFIG_RTL8192C_COMMON=m +CONFIG_RTL8XXXU=m +CONFIG_RTL8XXXU_UNTESTED=y +CONFIG_WLAN_VENDOR_RSI=y +CONFIG_RSI_91X=m +CONFIG_RSI_DEBUGFS=y +CONFIG_RSI_SDIO=m +CONFIG_RSI_USB=m +CONFIG_RSI_COEX=y +CONFIG_WLAN_VENDOR_ST=y +CONFIG_CW1200=m +CONFIG_CW1200_WLAN_SDIO=m +CONFIG_CW1200_WLAN_SPI=m +CONFIG_WLAN_VENDOR_TI=y +CONFIG_WL1251=m +CONFIG_WL1251_SPI=m +CONFIG_WL1251_SDIO=m +CONFIG_WL12XX=m +CONFIG_WL18XX=m +CONFIG_WLCORE=m +CONFIG_WLCORE_SPI=m +CONFIG_WLCORE_SDIO=m +CONFIG_WILINK_PLATFORM_DATA=y +CONFIG_RTL8812AU=m +CONFIG_WLAN_VENDOR_ZYDAS=y +CONFIG_USB_ZD1201=m +CONFIG_ZD1211RW=m +# CONFIG_ZD1211RW_DEBUG is not set +CONFIG_WLAN_VENDOR_QUANTENNA=y +CONFIG_MAC80211_HWSIM=m +CONFIG_USB_NET_RNDIS_WLAN=m +CONFIG_VIRT_WIFI=m + +# +# WiMAX Wireless Broadband devices +# +# CONFIG_WIMAX_I2400M_USB is not set +CONFIG_WAN=y +CONFIG_HDLC=m +CONFIG_HDLC_RAW=m +CONFIG_HDLC_RAW_ETH=m +CONFIG_HDLC_CISCO=m +CONFIG_HDLC_FR=m +CONFIG_HDLC_PPP=m +# CONFIG_HDLC_X25 is not set +CONFIG_DLCI=m +CONFIG_DLCI_MAX=8 +# CONFIG_LAPBETHER is not set +# CONFIG_X25_ASY is not set +CONFIG_IEEE802154_DRIVERS=m +# CONFIG_IEEE802154_FAKELB is not set +# CONFIG_IEEE802154_AT86RF230 is not set +# CONFIG_IEEE802154_MRF24J40 is not set +# CONFIG_IEEE802154_CC2520 is not set +# CONFIG_IEEE802154_ATUSB is not set +# CONFIG_IEEE802154_ADF7242 is not set +# CONFIG_IEEE802154_CA8210 is not set +# CONFIG_IEEE802154_MCR20A is not set +# CONFIG_IEEE802154_HWSIM is not set +# CONFIG_NETDEVSIM is not set +CONFIG_NET_FAILOVER=y +# CONFIG_ISDN is not set +# CONFIG_NVM is not set + +# +# Input device support +# +CONFIG_INPUT=y +CONFIG_INPUT_LEDS=y +CONFIG_INPUT_FF_MEMLESS=y +CONFIG_INPUT_POLLDEV=m +# CONFIG_INPUT_SPARSEKMAP is not set +CONFIG_INPUT_MATRIXKMAP=y + +# +# Userland interfaces +# +CONFIG_INPUT_MOUSEDEV=y +CONFIG_INPUT_MOUSEDEV_PSAUX=y +CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 +CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 +CONFIG_INPUT_JOYDEV=y +CONFIG_INPUT_EVDEV=y +# CONFIG_INPUT_EVBUG is not set + +# +# Input Device Drivers +# +CONFIG_INPUT_KEYBOARD=y +CONFIG_KEYBOARD_ADC=m +# CONFIG_KEYBOARD_ADP5588 is not set +# CONFIG_KEYBOARD_ADP5589 is not set +CONFIG_KEYBOARD_ATKBD=y +# CONFIG_KEYBOARD_QT1070 is not set +# CONFIG_KEYBOARD_QT2160 is not set +# CONFIG_KEYBOARD_DLINK_DIR685 is not set +# CONFIG_KEYBOARD_LKKBD is not set +CONFIG_KEYBOARD_GPIO=y +# CONFIG_KEYBOARD_GPIO_POLLED is not set +# CONFIG_KEYBOARD_TCA6416 is not set +# CONFIG_KEYBOARD_TCA8418 is not set +# CONFIG_KEYBOARD_MATRIX is not set +# CONFIG_KEYBOARD_LM8323 is not set +# CONFIG_KEYBOARD_LM8333 is not set +# CONFIG_KEYBOARD_MAX7359 is not set +# CONFIG_KEYBOARD_MCS is not set +# CONFIG_KEYBOARD_MPR121 is not set +# CONFIG_KEYBOARD_NEWTON is not set +# CONFIG_KEYBOARD_OPENCORES is not set +# CONFIG_KEYBOARD_SAMSUNG is not set +# CONFIG_KEYBOARD_STOWAWAY is not set +# CONFIG_KEYBOARD_SUNKBD is not set +# CONFIG_KEYBOARD_OMAP4 is not set +# CONFIG_KEYBOARD_TM2_TOUCHKEY is not set +# CONFIG_KEYBOARD_XTKBD is not set +CONFIG_KEYBOARD_CROS_EC=y +# CONFIG_KEYBOARD_CAP11XX is not set +# CONFIG_KEYBOARD_BCM is not set +CONFIG_INPUT_MOUSE=y +CONFIG_MOUSE_PS2=y +CONFIG_MOUSE_PS2_ALPS=y +CONFIG_MOUSE_PS2_BYD=y +CONFIG_MOUSE_PS2_LOGIPS2PP=y +CONFIG_MOUSE_PS2_SYNAPTICS=y +CONFIG_MOUSE_PS2_SYNAPTICS_SMBUS=y +CONFIG_MOUSE_PS2_CYPRESS=y +CONFIG_MOUSE_PS2_TRACKPOINT=y +# CONFIG_MOUSE_PS2_ELANTECH is not set +# CONFIG_MOUSE_PS2_SENTELIC is not set +# CONFIG_MOUSE_PS2_TOUCHKIT is not set +CONFIG_MOUSE_PS2_FOCALTECH=y +CONFIG_MOUSE_PS2_SMBUS=y +# CONFIG_MOUSE_SERIAL is not set +# CONFIG_MOUSE_APPLETOUCH is not set +# CONFIG_MOUSE_BCM5974 is not set +# CONFIG_MOUSE_CYAPA is not set +# CONFIG_MOUSE_ELAN_I2C is not set +# CONFIG_MOUSE_VSXXXAA is not set +# CONFIG_MOUSE_GPIO is not set +# CONFIG_MOUSE_SYNAPTICS_I2C is not set +# CONFIG_MOUSE_SYNAPTICS_USB is not set +CONFIG_INPUT_JOYSTICK=y +# CONFIG_JOYSTICK_ANALOG is not set +# CONFIG_JOYSTICK_A3D is not set +# CONFIG_JOYSTICK_ADI is not set +# CONFIG_JOYSTICK_COBRA is not set +# CONFIG_JOYSTICK_GF2K is not set +# CONFIG_JOYSTICK_GRIP is not set +# CONFIG_JOYSTICK_GRIP_MP is not set +# CONFIG_JOYSTICK_GUILLEMOT is not set +# CONFIG_JOYSTICK_INTERACT is not set +# CONFIG_JOYSTICK_SIDEWINDER is not set +# CONFIG_JOYSTICK_TMDC is not set +# CONFIG_JOYSTICK_IFORCE is not set +# CONFIG_JOYSTICK_WARRIOR is not set +# CONFIG_JOYSTICK_MAGELLAN is not set +# CONFIG_JOYSTICK_SPACEORB is not set +# CONFIG_JOYSTICK_SPACEBALL is not set +# CONFIG_JOYSTICK_STINGER is not set +# CONFIG_JOYSTICK_TWIDJOY is not set +# CONFIG_JOYSTICK_ZHENHUA is not set +CONFIG_JOYSTICK_DB9=m +CONFIG_JOYSTICK_GAMECON=m +CONFIG_JOYSTICK_TURBOGRAFX=m +# CONFIG_JOYSTICK_AS5011 is not set +# CONFIG_JOYSTICK_JOYDUMP is not set +CONFIG_JOYSTICK_XPAD=m +CONFIG_JOYSTICK_XPAD_FF=y +CONFIG_JOYSTICK_XPAD_LEDS=y +CONFIG_JOYSTICK_WALKERA0701=m +# CONFIG_JOYSTICK_PSXPAD_SPI is not set +# CONFIG_JOYSTICK_PXRC is not set +# CONFIG_INPUT_TABLET is not set +CONFIG_INPUT_TOUCHSCREEN=y +CONFIG_TOUCHSCREEN_PROPERTIES=y +# CONFIG_TOUCHSCREEN_ADS7846 is not set +# CONFIG_TOUCHSCREEN_AD7877 is not set +# CONFIG_TOUCHSCREEN_AD7879 is not set +# CONFIG_TOUCHSCREEN_ADC is not set +# CONFIG_TOUCHSCREEN_AR1021_I2C is not set +CONFIG_TOUCHSCREEN_ATMEL_MXT=m +# CONFIG_TOUCHSCREEN_ATMEL_MXT_T37 is not set +# CONFIG_TOUCHSCREEN_AUO_PIXCIR is not set +# CONFIG_TOUCHSCREEN_BU21013 is not set +# CONFIG_TOUCHSCREEN_BU21029 is not set +# CONFIG_TOUCHSCREEN_CHIPONE_ICN8318 is not set +# CONFIG_TOUCHSCREEN_CY8CTMG110 is not set +# CONFIG_TOUCHSCREEN_CYTTSP_CORE is not set +# CONFIG_TOUCHSCREEN_CYTTSP4_CORE is not set +# CONFIG_TOUCHSCREEN_DYNAPRO is not set +# CONFIG_TOUCHSCREEN_HAMPSHIRE is not set +# CONFIG_TOUCHSCREEN_EETI is not set +# CONFIG_TOUCHSCREEN_EGALAX is not set +# CONFIG_TOUCHSCREEN_EGALAX_SERIAL is not set +# CONFIG_TOUCHSCREEN_EXC3000 is not set +# CONFIG_TOUCHSCREEN_FUJITSU is not set +# CONFIG_TOUCHSCREEN_GOODIX is not set +# CONFIG_TOUCHSCREEN_HIDEEP is not set +# CONFIG_TOUCHSCREEN_ILI210X is not set +# CONFIG_TOUCHSCREEN_S6SY761 is not set +# CONFIG_TOUCHSCREEN_GUNZE is not set +# CONFIG_TOUCHSCREEN_EKTF2127 is not set +# CONFIG_TOUCHSCREEN_ELAN is not set +# CONFIG_TOUCHSCREEN_ELO is not set +# CONFIG_TOUCHSCREEN_WACOM_W8001 is not set +# CONFIG_TOUCHSCREEN_WACOM_I2C is not set +# CONFIG_TOUCHSCREEN_MAX11801 is not set +# CONFIG_TOUCHSCREEN_MCS5000 is not set +# CONFIG_TOUCHSCREEN_MMS114 is not set +# CONFIG_TOUCHSCREEN_MELFAS_MIP4 is not set +# CONFIG_TOUCHSCREEN_MTOUCH is not set +# CONFIG_TOUCHSCREEN_IMX6UL_TSC is not set +# CONFIG_TOUCHSCREEN_INEXIO is not set +# CONFIG_TOUCHSCREEN_MK712 is not set +# CONFIG_TOUCHSCREEN_PENMOUNT is not set +# CONFIG_TOUCHSCREEN_EDT_FT5X06 is not set +# CONFIG_TOUCHSCREEN_TOUCHRIGHT is not set +# CONFIG_TOUCHSCREEN_TOUCHWIN is not set +# CONFIG_TOUCHSCREEN_PIXCIR is not set +# CONFIG_TOUCHSCREEN_WDT87XX_I2C is not set +# CONFIG_TOUCHSCREEN_WM97XX is not set +# CONFIG_TOUCHSCREEN_USB_COMPOSITE is not set +# CONFIG_TOUCHSCREEN_TOUCHIT213 is not set +# CONFIG_TOUCHSCREEN_TSC_SERIO is not set +# CONFIG_TOUCHSCREEN_TSC2004 is not set +# CONFIG_TOUCHSCREEN_TSC2005 is not set +# CONFIG_TOUCHSCREEN_TSC2007 is not set +# CONFIG_TOUCHSCREEN_RM_TS is not set +# CONFIG_TOUCHSCREEN_SILEAD is not set +# CONFIG_TOUCHSCREEN_SIS_I2C is not set +# CONFIG_TOUCHSCREEN_ST1232 is not set +# CONFIG_TOUCHSCREEN_STMFTS is not set +# CONFIG_TOUCHSCREEN_SUR40 is not set +# CONFIG_TOUCHSCREEN_SURFACE3_SPI is not set +# CONFIG_TOUCHSCREEN_SX8654 is not set +# CONFIG_TOUCHSCREEN_TPS6507X is not set +# CONFIG_TOUCHSCREEN_ZET6223 is not set +# CONFIG_TOUCHSCREEN_ZFORCE is not set +# CONFIG_TOUCHSCREEN_ROHM_BU21023 is not set +CONFIG_INPUT_MISC=y +# CONFIG_INPUT_AD714X is not set +# CONFIG_INPUT_ATMEL_CAPTOUCH is not set +# CONFIG_INPUT_BMA150 is not set +# CONFIG_INPUT_E3X0_BUTTON is not set +# CONFIG_INPUT_MSM_VIBRATOR is not set +# CONFIG_INPUT_MMA8450 is not set +# CONFIG_INPUT_GP2A is not set +# CONFIG_INPUT_GPIO_BEEPER is not set +# CONFIG_INPUT_GPIO_DECODER is not set +# CONFIG_INPUT_ATI_REMOTE2 is not set +# CONFIG_INPUT_KEYSPAN_REMOTE is not set +# CONFIG_INPUT_KXTJ9 is not set +# CONFIG_INPUT_POWERMATE is not set +# CONFIG_INPUT_YEALINK is not set +# CONFIG_INPUT_CM109 is not set +# CONFIG_INPUT_REGULATOR_HAPTIC is not set +CONFIG_INPUT_UINPUT=y +# CONFIG_INPUT_PCF8574 is not set +# CONFIG_INPUT_PWM_BEEPER is not set +# CONFIG_INPUT_PWM_VIBRA is not set +# CONFIG_INPUT_RK805_PWRKEY is not set +# CONFIG_INPUT_GPIO_ROTARY_ENCODER is not set +# CONFIG_INPUT_ADXL34X is not set +# CONFIG_INPUT_IMS_PCU is not set +# CONFIG_INPUT_CMA3000 is not set +# CONFIG_INPUT_SOC_BUTTON_ARRAY is not set +# CONFIG_INPUT_DRV260X_HAPTICS is not set +# CONFIG_INPUT_DRV2665_HAPTICS is not set +# CONFIG_INPUT_DRV2667_HAPTICS is not set +CONFIG_RMI4_CORE=m +CONFIG_RMI4_I2C=m +CONFIG_RMI4_SPI=m +CONFIG_RMI4_SMB=m +CONFIG_RMI4_F03=y +CONFIG_RMI4_F03_SERIO=m +CONFIG_RMI4_2D_SENSOR=y +CONFIG_RMI4_F11=y +CONFIG_RMI4_F12=y +CONFIG_RMI4_F30=y +CONFIG_RMI4_F34=y +CONFIG_RMI4_F54=y +CONFIG_RMI4_F55=y + +# +# Hardware I/O ports +# +CONFIG_SERIO=y +CONFIG_SERIO_SERPORT=m +CONFIG_SERIO_PARKBD=m +CONFIG_SERIO_AMBAKMI=y +CONFIG_SERIO_LIBPS2=y +# CONFIG_SERIO_RAW is not set +# CONFIG_SERIO_ALTERA_PS2 is not set +# CONFIG_SERIO_PS2MULT is not set +# CONFIG_SERIO_ARC_PS2 is not set +# CONFIG_SERIO_APBPS2 is not set +# CONFIG_SERIO_OLPC_APSP is not set +# CONFIG_SERIO_GPIO_PS2 is not set +# CONFIG_USERIO is not set +# CONFIG_GAMEPORT is not set + +# +# Character devices +# +CONFIG_TTY=y +CONFIG_VT=y +CONFIG_CONSOLE_TRANSLATIONS=y +CONFIG_VT_CONSOLE=y +CONFIG_VT_CONSOLE_SLEEP=y +CONFIG_HW_CONSOLE=y +CONFIG_VT_HW_CONSOLE_BINDING=y +CONFIG_UNIX98_PTYS=y +CONFIG_LEGACY_PTYS=y +CONFIG_LEGACY_PTY_COUNT=16 +# CONFIG_SERIAL_NONSTANDARD is not set +# CONFIG_N_GSM is not set +# CONFIG_TRACE_SINK is not set +CONFIG_LDISC_AUTOLOAD=y +CONFIG_DEVMEM=y + +# +# Serial drivers +# +CONFIG_SERIAL_EARLYCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_DEPRECATED_OPTIONS=y +# CONFIG_SERIAL_8250_FINTEK is not set +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_DMA=y +CONFIG_SERIAL_8250_NR_UARTS=4 +CONFIG_SERIAL_8250_RUNTIME_UARTS=4 +CONFIG_SERIAL_8250_EXTENDED=y +# CONFIG_SERIAL_8250_MANY_PORTS is not set +# CONFIG_SERIAL_8250_ASPEED_VUART is not set +CONFIG_SERIAL_8250_SHARE_IRQ=y +# CONFIG_SERIAL_8250_DETECT_IRQ is not set +# CONFIG_SERIAL_8250_RSA is not set +CONFIG_SERIAL_8250_FSL=y +CONFIG_SERIAL_8250_DW=y +# CONFIG_SERIAL_8250_RT288X is not set +CONFIG_SERIAL_OF_PLATFORM=y + +# +# Non-8250 serial port support +# +CONFIG_SERIAL_AMBA_PL010=y +CONFIG_SERIAL_AMBA_PL010_CONSOLE=y +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_SERIAL_EARLYCON_ARM_SEMIHOST=y +CONFIG_SERIAL_MESON=y +CONFIG_SERIAL_MESON_CONSOLE=y +# CONFIG_SERIAL_MAX3100 is not set +# CONFIG_SERIAL_MAX310X is not set +# CONFIG_SERIAL_UARTLITE is not set +CONFIG_SERIAL_CORE=y +CONFIG_SERIAL_CORE_CONSOLE=y +# CONFIG_SERIAL_SCCNXP is not set +# CONFIG_SERIAL_SC16IS7XX is not set +# CONFIG_SERIAL_ALTERA_JTAGUART is not set +# CONFIG_SERIAL_ALTERA_UART is not set +# CONFIG_SERIAL_IFX6X60 is not set +CONFIG_SERIAL_XILINX_PS_UART=y +CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y +# CONFIG_SERIAL_ARC is not set +# CONFIG_SERIAL_FSL_LPUART is not set +# CONFIG_SERIAL_CONEXANT_DIGICOLOR is not set +CONFIG_SERIAL_DEV_BUS=y +CONFIG_SERIAL_DEV_CTRL_TTYPORT=y +# CONFIG_TTY_PRINTK is not set +CONFIG_PRINTER=m +# CONFIG_LP_CONSOLE is not set +CONFIG_PPDEV=m +CONFIG_HVC_DRIVER=y +# CONFIG_HVC_DCC is not set +CONFIG_VIRTIO_CONSOLE=y +# CONFIG_IPMI_HANDLER is not set +CONFIG_HW_RANDOM=m +# CONFIG_HW_RANDOM_TIMERIOMEM is not set +# CONFIG_HW_RANDOM_VIRTIO is not set +CONFIG_HW_RANDOM_MESON=m +CONFIG_HW_RANDOM_OPTEE=m +# CONFIG_RAW_DRIVER is not set +CONFIG_TCG_TPM=y +# CONFIG_TCG_TIS is not set +# CONFIG_TCG_TIS_SPI is not set +# CONFIG_TCG_TIS_I2C_ATMEL is not set +CONFIG_TCG_TIS_I2C_INFINEON=y +# CONFIG_TCG_TIS_I2C_NUVOTON is not set +# CONFIG_TCG_VTPM_PROXY is not set +# CONFIG_TCG_TIS_ST33ZP24_I2C is not set +# CONFIG_TCG_TIS_ST33ZP24_SPI is not set +# CONFIG_XILLYBUS is not set + +# +# I2C support +# +CONFIG_I2C=y +CONFIG_I2C_BOARDINFO=y +CONFIG_I2C_COMPAT=y +CONFIG_I2C_CHARDEV=y +CONFIG_I2C_MUX=y + +# +# Multiplexer I2C Chip support +# +# CONFIG_I2C_ARB_GPIO_CHALLENGE is not set +# CONFIG_I2C_MUX_GPIO is not set +# CONFIG_I2C_MUX_GPMUX is not set +# CONFIG_I2C_MUX_LTC4306 is not set +# CONFIG_I2C_MUX_PCA9541 is not set +CONFIG_I2C_MUX_PCA954x=y +# CONFIG_I2C_MUX_PINCTRL is not set +# CONFIG_I2C_MUX_REG is not set +# CONFIG_I2C_DEMUX_PINCTRL is not set +# CONFIG_I2C_MUX_MLXCPLD is not set +CONFIG_I2C_HELPER_AUTO=y +CONFIG_I2C_SMBUS=m +CONFIG_I2C_ALGOBIT=y + +# +# I2C Hardware Bus support +# + +# +# I2C system bus drivers (mostly embedded / system-on-chip) +# +# CONFIG_I2C_CADENCE is not set +# CONFIG_I2C_CBUS_GPIO is not set +CONFIG_I2C_DESIGNWARE_CORE=y +CONFIG_I2C_DESIGNWARE_PLATFORM=y +# CONFIG_I2C_DESIGNWARE_SLAVE is not set +# CONFIG_I2C_EMEV2 is not set +# CONFIG_I2C_GPIO is not set +CONFIG_I2C_MESON=y +# CONFIG_I2C_NOMADIK is not set +# CONFIG_I2C_OCORES is not set +# CONFIG_I2C_PCA_PLATFORM is not set +CONFIG_I2C_RK3X=y +# CONFIG_I2C_SIMTEC is not set +# CONFIG_I2C_XILINX is not set + +# +# External I2C/SMBus adapter drivers +# +# CONFIG_I2C_DIOLAN_U2C is not set +CONFIG_I2C_PARPORT=m +# CONFIG_I2C_PARPORT_LIGHT is not set +# CONFIG_I2C_ROBOTFUZZ_OSIF is not set +# CONFIG_I2C_TAOS_EVM is not set +# CONFIG_I2C_TINY_USB is not set + +# +# Other I2C/SMBus bus drivers +# +CONFIG_I2C_CROS_EC_TUNNEL=y +# CONFIG_I2C_STUB is not set +CONFIG_I2C_SLAVE=y +# CONFIG_I2C_SLAVE_EEPROM is not set +# CONFIG_I2C_DEBUG_CORE is not set +# CONFIG_I2C_DEBUG_ALGO is not set +# CONFIG_I2C_DEBUG_BUS is not set +# CONFIG_I3C is not set +CONFIG_SPI=y +# CONFIG_SPI_DEBUG is not set +CONFIG_SPI_MASTER=y +CONFIG_SPI_MEM=y + +# +# SPI Master Controller Drivers +# +# CONFIG_SPI_ALTERA is not set +# CONFIG_SPI_AXI_SPI_ENGINE is not set +CONFIG_SPI_BITBANG=m +CONFIG_SPI_BUTTERFLY=m +# CONFIG_SPI_CADENCE is not set +# CONFIG_SPI_DESIGNWARE is not set +# CONFIG_SPI_NXP_FLEXSPI is not set +CONFIG_SPI_GPIO=m +CONFIG_SPI_LM70_LLP=m +# CONFIG_SPI_FSL_SPI is not set +CONFIG_SPI_MESON_SPICC=y +CONFIG_SPI_MESON_SPIFC=y +# CONFIG_SPI_OC_TINY is not set +CONFIG_SPI_PL022=y +# CONFIG_SPI_ROCKCHIP is not set +# CONFIG_SPI_SC18IS602 is not set +# CONFIG_SPI_SIFIVE is not set +# CONFIG_SPI_MXIC is not set +# CONFIG_SPI_XCOMM is not set +# CONFIG_SPI_XILINX is not set +# CONFIG_SPI_ZYNQMP_GQSPI is not set + +# +# SPI Protocol Masters +# +CONFIG_SPI_SPIDEV=m +# CONFIG_SPI_LOOPBACK_TEST is not set +# CONFIG_SPI_TLE62X0 is not set +# CONFIG_SPI_SLAVE is not set +CONFIG_SPMI=y +# CONFIG_HSI is not set +CONFIG_PPS=y +# CONFIG_PPS_DEBUG is not set + +# +# PPS clients support +# +# CONFIG_PPS_CLIENT_KTIMER is not set +# CONFIG_PPS_CLIENT_LDISC is not set +CONFIG_PPS_CLIENT_PARPORT=m +# CONFIG_PPS_CLIENT_GPIO is not set + +# +# PPS generators support +# + +# +# PTP clock support +# +CONFIG_PTP_1588_CLOCK=y +CONFIG_DP83640_PHY=m +CONFIG_PINCTRL=y +CONFIG_GENERIC_PINCTRL_GROUPS=y +CONFIG_PINMUX=y +CONFIG_GENERIC_PINMUX_FUNCTIONS=y +CONFIG_PINCONF=y +CONFIG_GENERIC_PINCONF=y +# CONFIG_DEBUG_PINCTRL is not set +# CONFIG_PINCTRL_AMD is not set +# CONFIG_PINCTRL_MCP23S08 is not set +CONFIG_PINCTRL_SINGLE=y +# CONFIG_PINCTRL_SX150X is not set +CONFIG_PINCTRL_MAX77620=y +# CONFIG_PINCTRL_RK805 is not set +# CONFIG_PINCTRL_OCELOT is not set +CONFIG_PINCTRL_MESON=y +CONFIG_PINCTRL_MESON_GXBB=y +CONFIG_PINCTRL_MESON_GXL=y +CONFIG_PINCTRL_MESON8_PMX=y +CONFIG_PINCTRL_MESON_AXG=y +CONFIG_PINCTRL_MESON_AXG_PMX=y +CONFIG_PINCTRL_MESON_G12A=y +CONFIG_GPIOLIB=y +CONFIG_GPIOLIB_FASTPATH_LIMIT=512 +CONFIG_OF_GPIO=y +CONFIG_GPIOLIB_IRQCHIP=y +# CONFIG_DEBUG_GPIO is not set +CONFIG_GPIO_SYSFS=y +CONFIG_GPIO_GENERIC=y + +# +# Memory mapped GPIO drivers +# +# CONFIG_GPIO_74XX_MMIO is not set +# CONFIG_GPIO_ALTERA is not set +# CONFIG_GPIO_CADENCE is not set +CONFIG_GPIO_DWAPB=y +# CONFIG_GPIO_FTGPIO010 is not set +CONFIG_GPIO_GENERIC_PLATFORM=y +# CONFIG_GPIO_GRGPIO is not set +CONFIG_GPIO_HLWD=m +CONFIG_GPIO_MB86S7X=y +# CONFIG_GPIO_MOCKUP is not set +CONFIG_GPIO_PL061=y +# CONFIG_GPIO_SAMA5D2_PIOBU is not set +# CONFIG_GPIO_SYSCON is not set +CONFIG_GPIO_XGENE=y +# CONFIG_GPIO_XILINX is not set +# CONFIG_GPIO_AMD_FCH is not set + +# +# I2C GPIO expanders +# +# CONFIG_GPIO_ADP5588 is not set +# CONFIG_GPIO_ADNP is not set +# CONFIG_GPIO_GW_PLD is not set +# CONFIG_GPIO_MAX7300 is not set +# CONFIG_GPIO_MAX732X is not set +CONFIG_GPIO_PCA953X=y +CONFIG_GPIO_PCA953X_IRQ=y +# CONFIG_GPIO_PCF857X is not set +# CONFIG_GPIO_TPIC2810 is not set + +# +# MFD GPIO expanders +# +# CONFIG_GPIO_BD9571MWV is not set +CONFIG_GPIO_MAX77620=y + +# +# SPI GPIO expanders +# +# CONFIG_GPIO_74X164 is not set +# CONFIG_GPIO_MAX3191X is not set +# CONFIG_GPIO_MAX7301 is not set +# CONFIG_GPIO_MC33880 is not set +# CONFIG_GPIO_PISOSR is not set +# CONFIG_GPIO_XRA1403 is not set + +# +# USB GPIO expanders +# +# CONFIG_W1 is not set +CONFIG_POWER_AVS=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_BRCMSTB=y +# CONFIG_POWER_RESET_GPIO is not set +# CONFIG_POWER_RESET_GPIO_RESTART is not set +# CONFIG_POWER_RESET_LTC2952 is not set +CONFIG_POWER_RESET_RESTART=y +# CONFIG_POWER_RESET_VEXPRESS is not set +# CONFIG_POWER_RESET_XGENE is not set +CONFIG_POWER_RESET_SYSCON=y +CONFIG_POWER_RESET_SYSCON_POWEROFF=y +CONFIG_REBOOT_MODE=y +CONFIG_SYSCON_REBOOT_MODE=y +CONFIG_POWER_SUPPLY=y +# CONFIG_POWER_SUPPLY_DEBUG is not set +# CONFIG_PDA_POWER is not set +# CONFIG_GENERIC_ADC_BATTERY is not set +# CONFIG_TEST_POWER is not set +# CONFIG_CHARGER_ADP5061 is not set +# CONFIG_BATTERY_DS2780 is not set +# CONFIG_BATTERY_DS2781 is not set +# CONFIG_BATTERY_DS2782 is not set +# CONFIG_BATTERY_LEGO_EV3 is not set +CONFIG_BATTERY_SBS=m +# CONFIG_CHARGER_SBS is not set +# CONFIG_MANAGER_SBS is not set +CONFIG_BATTERY_BQ27XXX=y +CONFIG_BATTERY_BQ27XXX_I2C=y +# CONFIG_BATTERY_BQ27XXX_DT_UPDATES_NVM is not set +# CONFIG_BATTERY_MAX17040 is not set +# CONFIG_BATTERY_MAX17042 is not set +# CONFIG_CHARGER_ISP1704 is not set +# CONFIG_CHARGER_MAX8903 is not set +# CONFIG_CHARGER_LP8727 is not set +# CONFIG_CHARGER_GPIO is not set +# CONFIG_CHARGER_MANAGER is not set +# CONFIG_CHARGER_LTC3651 is not set +# CONFIG_CHARGER_DETECTOR_MAX14656 is not set +# CONFIG_CHARGER_BQ2415X is not set +# CONFIG_CHARGER_BQ24190 is not set +# CONFIG_CHARGER_BQ24257 is not set +# CONFIG_CHARGER_BQ24735 is not set +# CONFIG_CHARGER_BQ25890 is not set +# CONFIG_CHARGER_SMB347 is not set +# CONFIG_BATTERY_GAUGE_LTC2941 is not set +# CONFIG_CHARGER_RT9455 is not set +# CONFIG_CHARGER_CROS_USBPD is not set +CONFIG_HWMON=y +CONFIG_HWMON_VID=m +# CONFIG_HWMON_DEBUG_CHIP is not set + +# +# Native drivers +# +CONFIG_SENSORS_AD7314=m +CONFIG_SENSORS_AD7414=m +CONFIG_SENSORS_AD7418=m +CONFIG_SENSORS_ADM1021=m +CONFIG_SENSORS_ADM1025=m +CONFIG_SENSORS_ADM1026=m +CONFIG_SENSORS_ADM1029=m +CONFIG_SENSORS_ADM1031=m +CONFIG_SENSORS_ADM9240=m +CONFIG_SENSORS_ADT7X10=m +CONFIG_SENSORS_ADT7310=m +CONFIG_SENSORS_ADT7410=m +CONFIG_SENSORS_ADT7411=m +CONFIG_SENSORS_ADT7462=m +CONFIG_SENSORS_ADT7470=m +CONFIG_SENSORS_ADT7475=m +CONFIG_SENSORS_ASC7621=m +CONFIG_SENSORS_ARM_SCPI=m +# CONFIG_SENSORS_ASPEED is not set +CONFIG_SENSORS_ATXP1=m +CONFIG_SENSORS_DS620=m +CONFIG_SENSORS_DS1621=m +CONFIG_SENSORS_F71805F=m +CONFIG_SENSORS_F71882FG=m +CONFIG_SENSORS_F75375S=m +CONFIG_SENSORS_FTSTEUTATES=m +CONFIG_SENSORS_GL518SM=m +CONFIG_SENSORS_GL520SM=m +CONFIG_SENSORS_G760A=m +CONFIG_SENSORS_G762=m +CONFIG_SENSORS_GPIO_FAN=m +CONFIG_SENSORS_HIH6130=m +# CONFIG_SENSORS_IIO_HWMON is not set +CONFIG_SENSORS_IT87=m +CONFIG_SENSORS_JC42=m +CONFIG_SENSORS_POWR1220=m +CONFIG_SENSORS_LINEAGE=m +CONFIG_SENSORS_LTC2945=m +CONFIG_SENSORS_LTC2990=m +CONFIG_SENSORS_LTC4151=m +CONFIG_SENSORS_LTC4215=m +CONFIG_SENSORS_LTC4222=m +CONFIG_SENSORS_LTC4245=m +CONFIG_SENSORS_LTC4260=m +CONFIG_SENSORS_LTC4261=m +CONFIG_SENSORS_MAX1111=m +CONFIG_SENSORS_MAX16065=m +CONFIG_SENSORS_MAX1619=m +CONFIG_SENSORS_MAX1668=m +CONFIG_SENSORS_MAX197=m +CONFIG_SENSORS_MAX31722=m +# CONFIG_SENSORS_MAX6621 is not set +CONFIG_SENSORS_MAX6639=m +CONFIG_SENSORS_MAX6642=m +CONFIG_SENSORS_MAX6650=m +CONFIG_SENSORS_MAX6697=m +CONFIG_SENSORS_MAX31790=m +CONFIG_SENSORS_MCP3021=m +# CONFIG_SENSORS_TC654 is not set +CONFIG_SENSORS_ADCXX=m +CONFIG_SENSORS_LM63=m +CONFIG_SENSORS_LM70=m +CONFIG_SENSORS_LM73=m +CONFIG_SENSORS_LM75=m +CONFIG_SENSORS_LM77=m +CONFIG_SENSORS_LM78=m +CONFIG_SENSORS_LM80=m +CONFIG_SENSORS_LM83=m +CONFIG_SENSORS_LM85=m +CONFIG_SENSORS_LM87=m +CONFIG_SENSORS_LM90=m +CONFIG_SENSORS_LM92=m +CONFIG_SENSORS_LM93=m +CONFIG_SENSORS_LM95234=m +CONFIG_SENSORS_LM95241=m +CONFIG_SENSORS_LM95245=m +CONFIG_SENSORS_PC87360=m +CONFIG_SENSORS_PC87427=m +CONFIG_SENSORS_NTC_THERMISTOR=m +CONFIG_SENSORS_NCT6683=m +CONFIG_SENSORS_NCT6775=m +CONFIG_SENSORS_NCT7802=m +CONFIG_SENSORS_NCT7904=m +CONFIG_SENSORS_NPCM7XX=m +# CONFIG_SENSORS_OCC_P8_I2C is not set +CONFIG_SENSORS_PCF8591=m +# CONFIG_PMBUS is not set +CONFIG_SENSORS_PWM_FAN=m +CONFIG_SENSORS_SHT15=m +CONFIG_SENSORS_SHT21=m +CONFIG_SENSORS_SHT3x=m +CONFIG_SENSORS_SHTC1=m +CONFIG_SENSORS_DME1737=m +CONFIG_SENSORS_EMC1403=m +CONFIG_SENSORS_EMC2103=m +CONFIG_SENSORS_EMC6W201=m +CONFIG_SENSORS_SMSC47M1=m +CONFIG_SENSORS_SMSC47M192=m +CONFIG_SENSORS_SMSC47B397=m +CONFIG_SENSORS_SCH56XX_COMMON=m +CONFIG_SENSORS_SCH5627=m +CONFIG_SENSORS_SCH5636=m +CONFIG_SENSORS_STTS751=m +CONFIG_SENSORS_SMM665=m +CONFIG_SENSORS_ADC128D818=m +CONFIG_SENSORS_ADS1015=m +CONFIG_SENSORS_ADS7828=m +CONFIG_SENSORS_ADS7871=m +CONFIG_SENSORS_AMC6821=m +CONFIG_SENSORS_INA209=m +CONFIG_SENSORS_INA2XX=m +CONFIG_SENSORS_INA3221=m +CONFIG_SENSORS_TC74=m +CONFIG_SENSORS_THMC50=m +CONFIG_SENSORS_TMP102=m +CONFIG_SENSORS_TMP103=m +# CONFIG_SENSORS_TMP108 is not set +CONFIG_SENSORS_TMP401=m +CONFIG_SENSORS_TMP421=m +CONFIG_SENSORS_VEXPRESS=m +CONFIG_SENSORS_VT1211=m +CONFIG_SENSORS_W83773G=m +CONFIG_SENSORS_W83781D=m +CONFIG_SENSORS_W83791D=m +CONFIG_SENSORS_W83792D=m +CONFIG_SENSORS_W83793=m +CONFIG_SENSORS_W83795=m +# CONFIG_SENSORS_W83795_FANCTRL is not set +CONFIG_SENSORS_W83L785TS=m +CONFIG_SENSORS_W83L786NG=m +CONFIG_SENSORS_W83627HF=m +CONFIG_SENSORS_W83627EHF=m +CONFIG_THERMAL=y +# CONFIG_THERMAL_STATISTICS is not set +CONFIG_THERMAL_EMERGENCY_POWEROFF_DELAY_MS=0 +CONFIG_THERMAL_HWMON=y +CONFIG_THERMAL_OF=y +# CONFIG_THERMAL_WRITABLE_TRIPS is not set +CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE=y +# CONFIG_THERMAL_DEFAULT_GOV_FAIR_SHARE is not set +# CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE is not set +# CONFIG_THERMAL_DEFAULT_GOV_POWER_ALLOCATOR is not set +# CONFIG_THERMAL_GOV_FAIR_SHARE is not set +CONFIG_THERMAL_GOV_STEP_WISE=y +# CONFIG_THERMAL_GOV_BANG_BANG is not set +# CONFIG_THERMAL_GOV_USER_SPACE is not set +CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y +CONFIG_CPU_THERMAL=y +# CONFIG_CLOCK_THERMAL is not set +# CONFIG_DEVFREQ_THERMAL is not set +CONFIG_THERMAL_EMULATION=y +# CONFIG_MAX77620_THERMAL is not set +# CONFIG_QORIQ_THERMAL is not set +# CONFIG_GENERIC_ADC_THERMAL is not set +CONFIG_WATCHDOG=y +CONFIG_WATCHDOG_CORE=y +# CONFIG_WATCHDOG_NOWAYOUT is not set +CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED=y +# CONFIG_WATCHDOG_SYSFS is not set + +# +# Watchdog Device Drivers +# +CONFIG_SOFT_WATCHDOG=m +# CONFIG_GPIO_WATCHDOG is not set +# CONFIG_XILINX_WATCHDOG is not set +# CONFIG_ZIIRAVE_WATCHDOG is not set +CONFIG_ARM_SP805_WATCHDOG=y +# CONFIG_ARM_SBSA_WATCHDOG is not set +# CONFIG_CADENCE_WATCHDOG is not set +# CONFIG_DW_WATCHDOG is not set +# CONFIG_MAX63XX_WATCHDOG is not set +# CONFIG_MAX77620_WATCHDOG is not set +CONFIG_MESON_GXBB_WATCHDOG=y +CONFIG_MESON_WATCHDOG=y +# CONFIG_MEN_A21_WDT is not set + +# +# USB-based Watchdog Cards +# +# CONFIG_USBPCWATCHDOG is not set + +# +# Watchdog Pretimeout Governors +# +# CONFIG_WATCHDOG_PRETIMEOUT_GOV is not set +CONFIG_SSB_POSSIBLE=y +CONFIG_SSB=m +CONFIG_SSB_BLOCKIO=y +CONFIG_SSB_SDIOHOST_POSSIBLE=y +CONFIG_SSB_SDIOHOST=y +# CONFIG_SSB_DRIVER_GPIO is not set +CONFIG_BCMA_POSSIBLE=y +CONFIG_BCMA=m +CONFIG_BCMA_BLOCKIO=y +CONFIG_BCMA_HOST_SOC=y +CONFIG_BCMA_SFLASH=y +CONFIG_BCMA_DRIVER_GMAC_CMN=y +CONFIG_BCMA_DRIVER_GPIO=y +CONFIG_BCMA_DEBUG=y + +# +# Multifunction device drivers +# +CONFIG_MFD_CORE=y +# CONFIG_MFD_ACT8945A is not set +# CONFIG_MFD_AS3711 is not set +# CONFIG_MFD_AS3722 is not set +# CONFIG_PMIC_ADP5520 is not set +# CONFIG_MFD_AAT2870_CORE is not set +# CONFIG_MFD_ATMEL_FLEXCOM is not set +# CONFIG_MFD_ATMEL_HLCDC is not set +# CONFIG_MFD_BCM590XX is not set +CONFIG_MFD_BD9571MWV=y +# CONFIG_MFD_AXP20X_I2C is not set +CONFIG_MFD_CROS_EC=y +CONFIG_MFD_CROS_EC_CHARDEV=m +# CONFIG_MFD_MADERA is not set +# CONFIG_PMIC_DA903X is not set +# CONFIG_MFD_DA9052_SPI is not set +# CONFIG_MFD_DA9052_I2C is not set +# CONFIG_MFD_DA9055 is not set +# CONFIG_MFD_DA9062 is not set +# CONFIG_MFD_DA9063 is not set +# CONFIG_MFD_DA9150 is not set +# CONFIG_MFD_DLN2 is not set +# CONFIG_MFD_MC13XXX_SPI is not set +# CONFIG_MFD_MC13XXX_I2C is not set +CONFIG_MFD_HI6421_PMIC=y +# CONFIG_HTC_PASIC3 is not set +# CONFIG_HTC_I2CPLD is not set +# CONFIG_MFD_KEMPLD is not set +# CONFIG_MFD_88PM800 is not set +# CONFIG_MFD_88PM805 is not set +# CONFIG_MFD_88PM860X is not set +# CONFIG_MFD_MAX14577 is not set +CONFIG_MFD_MAX77620=y +# CONFIG_MFD_MAX77686 is not set +# CONFIG_MFD_MAX77693 is not set +# CONFIG_MFD_MAX77843 is not set +# CONFIG_MFD_MAX8907 is not set +# CONFIG_MFD_MAX8925 is not set +# CONFIG_MFD_MAX8997 is not set +# CONFIG_MFD_MAX8998 is not set +# CONFIG_MFD_MT6397 is not set +# CONFIG_MFD_MENF21BMC is not set +# CONFIG_EZX_PCAP is not set +# CONFIG_MFD_CPCAP is not set +# CONFIG_MFD_VIPERBOARD is not set +# CONFIG_MFD_RETU is not set +# CONFIG_MFD_PCF50633 is not set +# CONFIG_UCB1400_CORE is not set +# CONFIG_MFD_RT5033 is not set +# CONFIG_MFD_RC5T583 is not set +CONFIG_MFD_RK808=y +# CONFIG_MFD_RN5T618 is not set +CONFIG_MFD_SEC_CORE=y +# CONFIG_MFD_SI476X_CORE is not set +# CONFIG_MFD_SM501 is not set +# CONFIG_MFD_SKY81452 is not set +# CONFIG_MFD_SMSC is not set +# CONFIG_ABX500_CORE is not set +# CONFIG_MFD_STMPE is not set +CONFIG_MFD_SYSCON=y +# CONFIG_MFD_TI_AM335X_TSCADC is not set +# CONFIG_MFD_LP3943 is not set +# CONFIG_MFD_LP8788 is not set +# CONFIG_MFD_TI_LMU is not set +# CONFIG_MFD_PALMAS is not set +# CONFIG_TPS6105X is not set +# CONFIG_TPS65010 is not set +# CONFIG_TPS6507X is not set +# CONFIG_MFD_TPS65086 is not set +# CONFIG_MFD_TPS65090 is not set +# CONFIG_MFD_TPS65217 is not set +# CONFIG_MFD_TI_LP873X is not set +# CONFIG_MFD_TI_LP87565 is not set +# CONFIG_MFD_TPS65218 is not set +# CONFIG_MFD_TPS6586X is not set +# CONFIG_MFD_TPS65910 is not set +# CONFIG_MFD_TPS65912_I2C is not set +# CONFIG_MFD_TPS65912_SPI is not set +# CONFIG_MFD_TPS80031 is not set +# CONFIG_TWL4030_CORE is not set +# CONFIG_TWL6040_CORE is not set +# CONFIG_MFD_WL1273_CORE is not set +# CONFIG_MFD_LM3533 is not set +# CONFIG_MFD_TC3589X is not set +# CONFIG_MFD_TQMX86 is not set +# CONFIG_MFD_LOCHNAGAR is not set +# CONFIG_MFD_ARIZONA_I2C is not set +# CONFIG_MFD_ARIZONA_SPI is not set +# CONFIG_MFD_WM8400 is not set +# CONFIG_MFD_WM831X_I2C is not set +# CONFIG_MFD_WM831X_SPI is not set +# CONFIG_MFD_WM8350_I2C is not set +# CONFIG_MFD_WM8994 is not set +# CONFIG_MFD_ROHM_BD718XX is not set +# CONFIG_MFD_STPMIC1 is not set +CONFIG_MFD_VEXPRESS_SYSREG=y +# CONFIG_RAVE_SP_CORE is not set +CONFIG_REGULATOR=y +# CONFIG_REGULATOR_DEBUG is not set +CONFIG_REGULATOR_FIXED_VOLTAGE=y +# CONFIG_REGULATOR_VIRTUAL_CONSUMER is not set +# CONFIG_REGULATOR_USERSPACE_CONSUMER is not set +# CONFIG_REGULATOR_88PG86X is not set +# CONFIG_REGULATOR_ACT8865 is not set +# CONFIG_REGULATOR_AD5398 is not set +# CONFIG_REGULATOR_ANATOP is not set +CONFIG_REGULATOR_BD9571MWV=y +# CONFIG_REGULATOR_DA9210 is not set +# CONFIG_REGULATOR_DA9211 is not set +CONFIG_REGULATOR_FAN53555=y +CONFIG_REGULATOR_GPIO=y +# CONFIG_REGULATOR_HI6421 is not set +CONFIG_REGULATOR_HI6421V530=y +# CONFIG_REGULATOR_ISL9305 is not set +# CONFIG_REGULATOR_ISL6271A is not set +# CONFIG_REGULATOR_LP3971 is not set +# CONFIG_REGULATOR_LP3972 is not set +# CONFIG_REGULATOR_LP872X is not set +# CONFIG_REGULATOR_LP8755 is not set +# CONFIG_REGULATOR_LTC3589 is not set +# CONFIG_REGULATOR_LTC3676 is not set +# CONFIG_REGULATOR_MAX1586 is not set +CONFIG_REGULATOR_MAX77620=y +# CONFIG_REGULATOR_MAX8649 is not set +# CONFIG_REGULATOR_MAX8660 is not set +# CONFIG_REGULATOR_MAX8952 is not set +# CONFIG_REGULATOR_MAX8973 is not set +# CONFIG_REGULATOR_MCP16502 is not set +# CONFIG_REGULATOR_MT6311 is not set +# CONFIG_REGULATOR_PFUZE100 is not set +# CONFIG_REGULATOR_PV88060 is not set +# CONFIG_REGULATOR_PV88080 is not set +# CONFIG_REGULATOR_PV88090 is not set +CONFIG_REGULATOR_PWM=y +CONFIG_REGULATOR_QCOM_SPMI=y +CONFIG_REGULATOR_RK808=y +# CONFIG_REGULATOR_S2MPA01 is not set +CONFIG_REGULATOR_S2MPS11=y +# CONFIG_REGULATOR_S5M8767 is not set +# CONFIG_REGULATOR_SY8106A is not set +# CONFIG_REGULATOR_TPS51632 is not set +# CONFIG_REGULATOR_TPS62360 is not set +# CONFIG_REGULATOR_TPS65023 is not set +# CONFIG_REGULATOR_TPS6507X is not set +# CONFIG_REGULATOR_TPS65132 is not set +# CONFIG_REGULATOR_TPS6524X is not set +CONFIG_REGULATOR_VCTRL=m +# CONFIG_REGULATOR_VEXPRESS is not set +CONFIG_CEC_CORE=y +CONFIG_CEC_NOTIFIER=y +CONFIG_CEC_PIN=y +CONFIG_RC_CORE=y +CONFIG_RC_MAP=y +CONFIG_LIRC=y +# CONFIG_BPF_LIRC_MODE2 is not set +CONFIG_RC_DECODERS=y +CONFIG_IR_NEC_DECODER=m +CONFIG_IR_RC5_DECODER=m +CONFIG_IR_RC6_DECODER=m +CONFIG_IR_JVC_DECODER=m +CONFIG_IR_SONY_DECODER=m +CONFIG_IR_SANYO_DECODER=m +CONFIG_IR_SHARP_DECODER=m +CONFIG_IR_MCE_KBD_DECODER=m +CONFIG_IR_XMP_DECODER=m +CONFIG_IR_IMON_DECODER=m +CONFIG_IR_RCMM_DECODER=m +CONFIG_RC_DEVICES=y +# CONFIG_RC_ATI_REMOTE is not set +# CONFIG_IR_HIX5HD2 is not set +# CONFIG_IR_IMON is not set +# CONFIG_IR_IMON_RAW is not set +CONFIG_IR_MCEUSB=m +CONFIG_IR_MESON=m +# CONFIG_IR_REDRAT3 is not set +CONFIG_IR_SPI=m +# CONFIG_IR_STREAMZAP is not set +# CONFIG_IR_IGORPLUGUSB is not set +# CONFIG_IR_IGUANA is not set +# CONFIG_IR_TTUSBIR is not set +CONFIG_RC_LOOPBACK=m +CONFIG_IR_GPIO_CIR=m +CONFIG_IR_GPIO_TX=m +CONFIG_IR_PWM_TX=m +# CONFIG_IR_SERIAL is not set +# CONFIG_IR_SIR is not set +CONFIG_RC_XBOX_DVD=m +CONFIG_MEDIA_SUPPORT=m + +# +# Multimedia core support +# +CONFIG_MEDIA_CAMERA_SUPPORT=y +CONFIG_MEDIA_ANALOG_TV_SUPPORT=y +CONFIG_MEDIA_DIGITAL_TV_SUPPORT=y +CONFIG_MEDIA_RADIO_SUPPORT=y +CONFIG_MEDIA_SDR_SUPPORT=y +CONFIG_MEDIA_CEC_SUPPORT=y +CONFIG_MEDIA_CEC_RC=y +CONFIG_CEC_PIN_ERROR_INJ=y +CONFIG_MEDIA_CONTROLLER=y +CONFIG_MEDIA_CONTROLLER_DVB=y +CONFIG_VIDEO_DEV=m +CONFIG_VIDEO_V4L2_SUBDEV_API=y +CONFIG_VIDEO_V4L2=m +CONFIG_VIDEO_ADV_DEBUG=y +CONFIG_VIDEO_FIXED_MINOR_RANGES=y +CONFIG_VIDEO_TUNER=m +CONFIG_V4L2_MEM2MEM_DEV=m +CONFIG_V4L2_FWNODE=m +CONFIG_VIDEOBUF_GEN=m +CONFIG_VIDEOBUF_VMALLOC=m +CONFIG_DVB_CORE=m +CONFIG_DVB_MMAP=y +CONFIG_DVB_NET=y +CONFIG_TTPCI_EEPROM=m +CONFIG_DVB_MAX_ADAPTERS=16 +CONFIG_DVB_DYNAMIC_MINORS=y +CONFIG_DVB_DEMUX_SECTION_LOSS_LOG=y +CONFIG_DVB_ULE_DEBUG=y + +# +# Media drivers +# +CONFIG_MEDIA_USB_SUPPORT=y + +# +# Webcam devices +# +CONFIG_USB_VIDEO_CLASS=m +CONFIG_USB_VIDEO_CLASS_INPUT_EVDEV=y +CONFIG_USB_GSPCA=m +CONFIG_USB_M5602=m +CONFIG_USB_STV06XX=m +CONFIG_USB_GL860=m +CONFIG_USB_GSPCA_BENQ=m +CONFIG_USB_GSPCA_CONEX=m +CONFIG_USB_GSPCA_CPIA1=m +CONFIG_USB_GSPCA_DTCS033=m +CONFIG_USB_GSPCA_ETOMS=m +CONFIG_USB_GSPCA_FINEPIX=m +CONFIG_USB_GSPCA_JEILINJ=m +CONFIG_USB_GSPCA_JL2005BCD=m +CONFIG_USB_GSPCA_KINECT=m +CONFIG_USB_GSPCA_KONICA=m +CONFIG_USB_GSPCA_MARS=m +CONFIG_USB_GSPCA_MR97310A=m +CONFIG_USB_GSPCA_NW80X=m +CONFIG_USB_GSPCA_OV519=m +CONFIG_USB_GSPCA_OV534=m +CONFIG_USB_GSPCA_OV534_9=m +CONFIG_USB_GSPCA_PAC207=m +CONFIG_USB_GSPCA_PAC7302=m +CONFIG_USB_GSPCA_PAC7311=m +CONFIG_USB_GSPCA_SE401=m +CONFIG_USB_GSPCA_SN9C2028=m +CONFIG_USB_GSPCA_SN9C20X=m +CONFIG_USB_GSPCA_SONIXB=m +CONFIG_USB_GSPCA_SONIXJ=m +CONFIG_USB_GSPCA_SPCA500=m +CONFIG_USB_GSPCA_SPCA501=m +CONFIG_USB_GSPCA_SPCA505=m +CONFIG_USB_GSPCA_SPCA506=m +CONFIG_USB_GSPCA_SPCA508=m +CONFIG_USB_GSPCA_SPCA561=m +CONFIG_USB_GSPCA_SPCA1528=m +CONFIG_USB_GSPCA_SQ905=m +CONFIG_USB_GSPCA_SQ905C=m +CONFIG_USB_GSPCA_SQ930X=m +CONFIG_USB_GSPCA_STK014=m +CONFIG_USB_GSPCA_STK1135=m +CONFIG_USB_GSPCA_STV0680=m +CONFIG_USB_GSPCA_SUNPLUS=m +CONFIG_USB_GSPCA_T613=m +CONFIG_USB_GSPCA_TOPRO=m +CONFIG_USB_GSPCA_TOUPTEK=m +CONFIG_USB_GSPCA_TV8532=m +CONFIG_USB_GSPCA_VC032X=m +CONFIG_USB_GSPCA_VICAM=m +CONFIG_USB_GSPCA_XIRLINK_CIT=m +CONFIG_USB_GSPCA_ZC3XX=m +CONFIG_USB_PWC=m +# CONFIG_USB_PWC_DEBUG is not set +CONFIG_USB_PWC_INPUT_EVDEV=y +CONFIG_VIDEO_CPIA2=m +CONFIG_USB_ZR364XX=m +CONFIG_USB_STKWEBCAM=m +CONFIG_USB_S2255=m +CONFIG_VIDEO_USBTV=m + +# +# Analog TV USB devices +# +CONFIG_VIDEO_PVRUSB2=m +CONFIG_VIDEO_PVRUSB2_SYSFS=y +CONFIG_VIDEO_PVRUSB2_DVB=y +# CONFIG_VIDEO_PVRUSB2_DEBUGIFC is not set +CONFIG_VIDEO_HDPVR=m +CONFIG_VIDEO_USBVISION=m +CONFIG_VIDEO_STK1160_COMMON=m +CONFIG_VIDEO_STK1160=m +# CONFIG_VIDEO_GO7007 is not set + +# +# Analog/digital TV USB devices +# +CONFIG_VIDEO_AU0828=m +CONFIG_VIDEO_AU0828_V4L2=y +# CONFIG_VIDEO_AU0828_RC is not set +CONFIG_VIDEO_CX231XX=m +CONFIG_VIDEO_CX231XX_RC=y +CONFIG_VIDEO_CX231XX_ALSA=m +CONFIG_VIDEO_CX231XX_DVB=m +CONFIG_VIDEO_TM6000=m +CONFIG_VIDEO_TM6000_ALSA=m +CONFIG_VIDEO_TM6000_DVB=m + +# +# Digital TV USB devices +# +CONFIG_DVB_USB=m +# CONFIG_DVB_USB_DEBUG is not set +CONFIG_DVB_USB_DIB3000MC=m +CONFIG_DVB_USB_A800=m +CONFIG_DVB_USB_DIBUSB_MB=m +CONFIG_DVB_USB_DIBUSB_MB_FAULTY=y +CONFIG_DVB_USB_DIBUSB_MC=m +CONFIG_DVB_USB_DIB0700=m +CONFIG_DVB_USB_UMT_010=m +CONFIG_DVB_USB_CXUSB=m +CONFIG_DVB_USB_M920X=m +CONFIG_DVB_USB_DIGITV=m +CONFIG_DVB_USB_VP7045=m +CONFIG_DVB_USB_VP702X=m +CONFIG_DVB_USB_GP8PSK=m +CONFIG_DVB_USB_NOVA_T_USB2=m +CONFIG_DVB_USB_TTUSB2=m +CONFIG_DVB_USB_DTT200U=m +CONFIG_DVB_USB_OPERA1=m +CONFIG_DVB_USB_AF9005=m +CONFIG_DVB_USB_AF9005_REMOTE=m +CONFIG_DVB_USB_PCTV452E=m +CONFIG_DVB_USB_DW2102=m +CONFIG_DVB_USB_CINERGY_T2=m +CONFIG_DVB_USB_DTV5100=m +CONFIG_DVB_USB_AZ6027=m +CONFIG_DVB_USB_TECHNISAT_USB2=m +CONFIG_DVB_USB_V2=m +CONFIG_DVB_USB_AF9015=m +CONFIG_DVB_USB_AF9035=m +CONFIG_DVB_USB_ANYSEE=m +CONFIG_DVB_USB_AU6610=m +CONFIG_DVB_USB_AZ6007=m +CONFIG_DVB_USB_CE6230=m +CONFIG_DVB_USB_EC168=m +CONFIG_DVB_USB_GL861=m +CONFIG_DVB_USB_LME2510=m +CONFIG_DVB_USB_MXL111SF=m +CONFIG_DVB_USB_RTL28XXU=m +CONFIG_DVB_USB_DVBSKY=m +CONFIG_DVB_USB_ZD1301=m +CONFIG_SMS_USB_DRV=m +CONFIG_DVB_B2C2_FLEXCOP_USB=m +# CONFIG_DVB_B2C2_FLEXCOP_USB_DEBUG is not set +CONFIG_DVB_AS102=m + +# +# Webcam, TV (analog/digital) USB devices +# +CONFIG_VIDEO_EM28XX=m +CONFIG_VIDEO_EM28XX_V4L2=m +CONFIG_VIDEO_EM28XX_ALSA=m +CONFIG_VIDEO_EM28XX_DVB=m +CONFIG_VIDEO_EM28XX_RC=m + +# +# Software defined radio USB devices +# +CONFIG_USB_AIRSPY=m +CONFIG_USB_HACKRF=m +CONFIG_USB_MSI2500=m + +# +# USB HDMI CEC adapters +# +CONFIG_USB_PULSE8_CEC=m +CONFIG_USB_RAINSHADOW_CEC=m +CONFIG_V4L_PLATFORM_DRIVERS=y +CONFIG_VIDEO_CADENCE=y +CONFIG_VIDEO_CADENCE_CSI2RX=m +CONFIG_VIDEO_CADENCE_CSI2TX=m +# CONFIG_VIDEO_ASPEED is not set +CONFIG_VIDEO_MUX=m +# CONFIG_VIDEO_XILINX is not set +CONFIG_V4L_MEM2MEM_DRIVERS=y +CONFIG_VIDEO_MEM2MEM_DEINTERLACE=m +# CONFIG_VIDEO_SH_VEU is not set +CONFIG_VIDEO_MESON_VDEC=m +CONFIG_V4L_TEST_DRIVERS=y +CONFIG_VIDEO_VIMC=m +CONFIG_VIDEO_VIVID=m +CONFIG_VIDEO_VIVID_CEC=y +CONFIG_VIDEO_VIVID_MAX_DEVS=64 +CONFIG_VIDEO_VIM2M=m +CONFIG_VIDEO_VICODEC=m +CONFIG_DVB_PLATFORM_DRIVERS=y +CONFIG_CEC_PLATFORM_DRIVERS=y +# CONFIG_VIDEO_CROS_EC_CEC is not set +CONFIG_VIDEO_MESON_AO_CEC=m +CONFIG_VIDEO_MESON_G12A_AO_CEC=m +CONFIG_CEC_GPIO=m +# CONFIG_SDR_PLATFORM_DRIVERS is not set + +# +# Supported MMC/SDIO adapters +# +# CONFIG_SMS_SDIO_DRV is not set +CONFIG_RADIO_ADAPTERS=y +# CONFIG_RADIO_SI470X is not set +# CONFIG_RADIO_SI4713 is not set +# CONFIG_USB_MR800 is not set +# CONFIG_USB_DSBR is not set +# CONFIG_RADIO_SHARK is not set +# CONFIG_RADIO_SHARK2 is not set +# CONFIG_USB_KEENE is not set +# CONFIG_USB_RAREMONO is not set +# CONFIG_USB_MA901 is not set +# CONFIG_RADIO_TEA5764 is not set +# CONFIG_RADIO_SAA7706H is not set +# CONFIG_RADIO_TEF6862 is not set +# CONFIG_RADIO_WL1273 is not set + +# +# Texas Instruments WL128x FM driver (ST based) +# +CONFIG_MEDIA_COMMON_OPTIONS=y + +# +# common driver options +# +CONFIG_VIDEO_CX2341X=m +CONFIG_VIDEO_TVEEPROM=m +CONFIG_CYPRESS_FIRMWARE=m +CONFIG_VIDEOBUF2_CORE=m +CONFIG_VIDEOBUF2_V4L2=m +CONFIG_VIDEOBUF2_MEMOPS=m +CONFIG_VIDEOBUF2_DMA_CONTIG=m +CONFIG_VIDEOBUF2_VMALLOC=m +CONFIG_DVB_B2C2_FLEXCOP=m +CONFIG_SMS_SIANO_MDTV=m +CONFIG_SMS_SIANO_RC=y +CONFIG_VIDEO_V4L2_TPG=m + +# +# Media ancillary drivers (tuners, sensors, i2c, spi, frontends) +# +CONFIG_MEDIA_SUBDRV_AUTOSELECT=y +CONFIG_MEDIA_ATTACH=y +CONFIG_VIDEO_IR_I2C=m + +# +# Audio decoders, processors and mixers +# +CONFIG_VIDEO_MSP3400=m +CONFIG_VIDEO_CS53L32A=m +CONFIG_VIDEO_WM8775=m + +# +# RDS decoders +# + +# +# Video decoders +# +CONFIG_VIDEO_SAA711X=m +CONFIG_VIDEO_TVP5150=m + +# +# Video and audio decoders +# +CONFIG_VIDEO_CX25840=m + +# +# Video encoders +# + +# +# Camera sensor devices +# +CONFIG_VIDEO_OV2640=m +CONFIG_VIDEO_MT9V011=m + +# +# Flash devices +# + +# +# Video improvement chips +# + +# +# Audio/Video compression chips +# + +# +# SDR tuner chips +# + +# +# Miscellaneous helper chips +# + +# +# Media SPI Adapters +# +CONFIG_CXD2880_SPI_DRV=m +CONFIG_MEDIA_TUNER=m +CONFIG_MEDIA_TUNER_SIMPLE=m +CONFIG_MEDIA_TUNER_TDA18250=m +CONFIG_MEDIA_TUNER_TDA8290=m +CONFIG_MEDIA_TUNER_TDA827X=m +CONFIG_MEDIA_TUNER_TDA18271=m +CONFIG_MEDIA_TUNER_TDA9887=m +CONFIG_MEDIA_TUNER_TEA5761=m +CONFIG_MEDIA_TUNER_TEA5767=m +CONFIG_MEDIA_TUNER_MSI001=m +CONFIG_MEDIA_TUNER_MT20XX=m +CONFIG_MEDIA_TUNER_MT2060=m +CONFIG_MEDIA_TUNER_MT2063=m +CONFIG_MEDIA_TUNER_MT2266=m +CONFIG_MEDIA_TUNER_QT1010=m +CONFIG_MEDIA_TUNER_XC2028=m +CONFIG_MEDIA_TUNER_XC5000=m +CONFIG_MEDIA_TUNER_XC4000=m +CONFIG_MEDIA_TUNER_MXL5005S=m +CONFIG_MEDIA_TUNER_MXL5007T=m +CONFIG_MEDIA_TUNER_MC44S803=m +CONFIG_MEDIA_TUNER_MAX2165=m +CONFIG_MEDIA_TUNER_TDA18218=m +CONFIG_MEDIA_TUNER_FC0011=m +CONFIG_MEDIA_TUNER_FC0012=m +CONFIG_MEDIA_TUNER_FC0013=m +CONFIG_MEDIA_TUNER_TDA18212=m +CONFIG_MEDIA_TUNER_E4000=m +CONFIG_MEDIA_TUNER_FC2580=m +CONFIG_MEDIA_TUNER_TUA9001=m +CONFIG_MEDIA_TUNER_SI2157=m +CONFIG_MEDIA_TUNER_IT913X=m +CONFIG_MEDIA_TUNER_R820T=m +CONFIG_MEDIA_TUNER_QM1D1C0042=m + +# +# Multistandard (satellite) frontends +# +CONFIG_DVB_STB0899=m +CONFIG_DVB_STB6100=m +CONFIG_DVB_STV090x=m +CONFIG_DVB_STV6110x=m +CONFIG_DVB_M88DS3103=m + +# +# Multistandard (cable + terrestrial) frontends +# +CONFIG_DVB_DRXK=m +CONFIG_DVB_TDA18271C2DD=m +CONFIG_DVB_SI2165=m +CONFIG_DVB_MN88472=m +CONFIG_DVB_MN88473=m + +# +# DVB-S (satellite) frontends +# +CONFIG_DVB_CX24123=m +CONFIG_DVB_MT312=m +CONFIG_DVB_ZL10039=m +CONFIG_DVB_S5H1420=m +CONFIG_DVB_STV0288=m +CONFIG_DVB_STB6000=m +CONFIG_DVB_STV0299=m +CONFIG_DVB_STV6110=m +CONFIG_DVB_STV0900=m +CONFIG_DVB_TDA10086=m +CONFIG_DVB_TUNER_ITD1000=m +CONFIG_DVB_TUNER_CX24113=m +CONFIG_DVB_TDA826X=m +CONFIG_DVB_CX24116=m +CONFIG_DVB_CX24120=m +CONFIG_DVB_SI21XX=m +CONFIG_DVB_TS2020=m +CONFIG_DVB_DS3000=m +CONFIG_DVB_TDA10071=m + +# +# DVB-T (terrestrial) frontends +# +CONFIG_DVB_CX22702=m +CONFIG_DVB_DRXD=m +CONFIG_DVB_TDA1004X=m +CONFIG_DVB_NXT6000=m +CONFIG_DVB_MT352=m +CONFIG_DVB_ZL10353=m +CONFIG_DVB_DIB3000MB=m +CONFIG_DVB_DIB3000MC=m +CONFIG_DVB_DIB7000M=m +CONFIG_DVB_DIB7000P=m +CONFIG_DVB_TDA10048=m +CONFIG_DVB_AF9013=m +CONFIG_DVB_EC100=m +CONFIG_DVB_CXD2820R=m +CONFIG_DVB_CXD2841ER=m +CONFIG_DVB_RTL2830=m +CONFIG_DVB_RTL2832=m +CONFIG_DVB_RTL2832_SDR=m +CONFIG_DVB_SI2168=m +CONFIG_DVB_AS102_FE=m +CONFIG_DVB_ZD1301_DEMOD=m +CONFIG_DVB_GP8PSK_FE=m + +# +# DVB-C (cable) frontends +# +CONFIG_DVB_TDA10023=m +CONFIG_DVB_STV0297=m + +# +# ATSC (North American/Korean Terrestrial/Cable DTV) frontends +# +CONFIG_DVB_NXT200X=m +CONFIG_DVB_BCM3510=m +CONFIG_DVB_LGDT330X=m +CONFIG_DVB_LGDT3305=m +CONFIG_DVB_LGDT3306A=m +CONFIG_DVB_LG2160=m +CONFIG_DVB_S5H1409=m +CONFIG_DVB_AU8522=m +CONFIG_DVB_AU8522_DTV=m +CONFIG_DVB_AU8522_V4L=m +CONFIG_DVB_S5H1411=m + +# +# ISDB-T (terrestrial) frontends +# +CONFIG_DVB_S921=m +CONFIG_DVB_DIB8000=m +CONFIG_DVB_MB86A20S=m + +# +# ISDB-S (satellite) & ISDB-T (terrestrial) frontends +# +CONFIG_DVB_TC90522=m + +# +# Digital terrestrial only tuners/PLL +# +CONFIG_DVB_PLL=m +CONFIG_DVB_TUNER_DIB0070=m +CONFIG_DVB_TUNER_DIB0090=m + +# +# SEC control devices for DVB-S +# +CONFIG_DVB_DRX39XYJ=m +CONFIG_DVB_LNBP21=m +CONFIG_DVB_LNBP22=m +CONFIG_DVB_ISL6421=m +CONFIG_DVB_ISL6423=m +CONFIG_DVB_A8293=m +CONFIG_DVB_LGS8GXX=m +CONFIG_DVB_ATBM8830=m +CONFIG_DVB_IX2505V=m +CONFIG_DVB_M88RS2000=m +CONFIG_DVB_AF9033=m + +# +# Common Interface (EN50221) controller drivers +# +CONFIG_DVB_SP2=m + +# +# Tools to develop new frontends +# + +# +# Graphics support +# +CONFIG_DRM=y +CONFIG_DRM_MIPI_DSI=y +# CONFIG_DRM_DP_AUX_CHARDEV is not set +# CONFIG_DRM_DEBUG_MM is not set +# CONFIG_DRM_DEBUG_SELFTEST is not set +CONFIG_DRM_KMS_HELPER=y +CONFIG_DRM_KMS_FB_HELPER=y +CONFIG_DRM_FBDEV_EMULATION=y +CONFIG_DRM_FBDEV_OVERALLOC=100 +# CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM is not set +CONFIG_DRM_LOAD_EDID_FIRMWARE=y +CONFIG_DRM_DP_CEC=y +CONFIG_DRM_GEM_CMA_HELPER=y +CONFIG_DRM_KMS_CMA_HELPER=y +CONFIG_DRM_GEM_SHMEM_HELPER=y +CONFIG_DRM_SCHED=m + +# +# I2C encoder or helper chips +# +CONFIG_DRM_I2C_CH7006=m +CONFIG_DRM_I2C_SIL164=m +# CONFIG_DRM_I2C_NXP_TDA998X is not set +# CONFIG_DRM_I2C_NXP_TDA9950 is not set + +# +# ARM devices +# +CONFIG_DRM_HDLCD=m +CONFIG_DRM_HDLCD_SHOW_UNDERRUN=y +CONFIG_DRM_MALI_DISPLAY=m +# CONFIG_DRM_KOMEDA is not set + +# +# ACP (Audio CoProcessor) Configuration +# + +# +# AMD Library routines +# +# CONFIG_DRM_VGEM is not set +# CONFIG_DRM_VKMS is not set +# CONFIG_DRM_UDL is not set +# CONFIG_DRM_RCAR_DW_HDMI is not set +# CONFIG_DRM_RCAR_LVDS is not set +# CONFIG_DRM_VIRTIO_GPU is not set +CONFIG_DRM_PANEL=y + +# +# Display Panels +# +CONFIG_DRM_PANEL_ARM_VERSATILE=m +CONFIG_DRM_PANEL_LVDS=m +CONFIG_DRM_PANEL_SIMPLE=m +# CONFIG_DRM_PANEL_ILITEK_IL9322 is not set +# CONFIG_DRM_PANEL_ILITEK_ILI9881C is not set +# CONFIG_DRM_PANEL_INNOLUX_P079ZCA is not set +# CONFIG_DRM_PANEL_JDI_LT070ME05000 is not set +# CONFIG_DRM_PANEL_KINGDISPLAY_KD097D04 is not set +# CONFIG_DRM_PANEL_SAMSUNG_LD9040 is not set +# CONFIG_DRM_PANEL_LG_LG4573 is not set +# CONFIG_DRM_PANEL_OLIMEX_LCD_OLINUXINO is not set +# CONFIG_DRM_PANEL_ORISETECH_OTM8009A is not set +# CONFIG_DRM_PANEL_PANASONIC_VVX10F034N00 is not set +# CONFIG_DRM_PANEL_RASPBERRYPI_TOUCHSCREEN is not set +# CONFIG_DRM_PANEL_RAYDIUM_RM68200 is not set +# CONFIG_DRM_PANEL_SAMSUNG_S6D16D0 is not set +# CONFIG_DRM_PANEL_SAMSUNG_S6E3HA2 is not set +# CONFIG_DRM_PANEL_SAMSUNG_S6E63J0X03 is not set +# CONFIG_DRM_PANEL_SAMSUNG_S6E8AA0 is not set +# CONFIG_DRM_PANEL_SEIKO_43WVF1G is not set +# CONFIG_DRM_PANEL_SHARP_LQ101R1SX01 is not set +# CONFIG_DRM_PANEL_SHARP_LS043T1LE01 is not set +# CONFIG_DRM_PANEL_SITRONIX_ST7701 is not set +# CONFIG_DRM_PANEL_SITRONIX_ST7789V is not set +# CONFIG_DRM_PANEL_TPO_TPG110 is not set +# CONFIG_DRM_PANEL_TRULY_NT35597_WQXGA is not set +CONFIG_DRM_BRIDGE=y +CONFIG_DRM_PANEL_BRIDGE=y + +# +# Display Interface Bridges +# +# CONFIG_DRM_ANALOGIX_ANX78XX is not set +# CONFIG_DRM_CDNS_DSI is not set +# CONFIG_DRM_DUMB_VGA_DAC is not set +# CONFIG_DRM_LVDS_ENCODER is not set +# CONFIG_DRM_MEGACHIPS_STDPXXXX_GE_B850V3_FW is not set +# CONFIG_DRM_NXP_PTN3460 is not set +# CONFIG_DRM_PARADE_PS8622 is not set +# CONFIG_DRM_SIL_SII8620 is not set +# CONFIG_DRM_SII902X is not set +# CONFIG_DRM_SII9234 is not set +# CONFIG_DRM_THINE_THC63LVD1024 is not set +# CONFIG_DRM_TOSHIBA_TC358764 is not set +# CONFIG_DRM_TOSHIBA_TC358767 is not set +# CONFIG_DRM_TI_TFP410 is not set +# CONFIG_DRM_TI_SN65DSI86 is not set +CONFIG_DRM_I2C_ADV7511=m +# CONFIG_DRM_I2C_ADV7511_AUDIO is not set +CONFIG_DRM_I2C_ADV7533=y +CONFIG_DRM_I2C_ADV7511_CEC=y +CONFIG_DRM_DW_HDMI=y +# CONFIG_DRM_DW_HDMI_AHB_AUDIO is not set +CONFIG_DRM_DW_HDMI_I2S_AUDIO=y +CONFIG_DRM_DW_HDMI_CEC=m +# CONFIG_DRM_ETNAVIV is not set +# CONFIG_DRM_ARCPGU is not set +# CONFIG_DRM_HISI_KIRIN is not set +# CONFIG_DRM_MXSFB is not set +CONFIG_DRM_MESON=y +CONFIG_DRM_MESON_DW_HDMI=y +# CONFIG_DRM_TINYDRM is not set +# CONFIG_DRM_PL111 is not set +CONFIG_DRM_LIMA=m +CONFIG_DRM_PANFROST=m +# CONFIG_DRM_LEGACY is not set +CONFIG_DRM_PANEL_ORIENTATION_QUIRKS=y + +# +# Frame buffer Devices +# +CONFIG_FB_CMDLINE=y +CONFIG_FB_NOTIFY=y +CONFIG_FB=y +# CONFIG_FIRMWARE_EDID is not set +CONFIG_FB_CFB_FILLRECT=y +CONFIG_FB_CFB_COPYAREA=y +CONFIG_FB_CFB_IMAGEBLIT=y +CONFIG_FB_SYS_FILLRECT=y +CONFIG_FB_SYS_COPYAREA=y +CONFIG_FB_SYS_IMAGEBLIT=y +# CONFIG_FB_FOREIGN_ENDIAN is not set +CONFIG_FB_SYS_FOPS=y +CONFIG_FB_DEFERRED_IO=y +CONFIG_FB_MODE_HELPERS=y +# CONFIG_FB_TILEBLITTING is not set + +# +# Frame buffer hardware drivers +# +CONFIG_FB_ARMCLCD=y +CONFIG_FB_UVESA=m +# CONFIG_FB_OPENCORES is not set +# CONFIG_FB_S1D13XXX is not set +# CONFIG_FB_SMSCUFX is not set +# CONFIG_FB_UDL is not set +# CONFIG_FB_IBM_GXT4500 is not set +# CONFIG_FB_VIRTUAL is not set +# CONFIG_FB_METRONOME is not set +# CONFIG_FB_SIMPLE is not set +# CONFIG_FB_SSD1307 is not set +CONFIG_BACKLIGHT_LCD_SUPPORT=y +CONFIG_LCD_CLASS_DEVICE=m +# CONFIG_LCD_L4F00242T03 is not set +# CONFIG_LCD_LMS283GF05 is not set +# CONFIG_LCD_LTV350QV is not set +# CONFIG_LCD_ILI922X is not set +# CONFIG_LCD_ILI9320 is not set +# CONFIG_LCD_TDO24M is not set +# CONFIG_LCD_VGG2432A4 is not set +# CONFIG_LCD_PLATFORM is not set +# CONFIG_LCD_AMS369FG06 is not set +# CONFIG_LCD_LMS501KF03 is not set +# CONFIG_LCD_HX8357 is not set +# CONFIG_LCD_OTM3225A is not set +CONFIG_BACKLIGHT_CLASS_DEVICE=y +CONFIG_BACKLIGHT_GENERIC=m +CONFIG_BACKLIGHT_PWM=m +# CONFIG_BACKLIGHT_PM8941_WLED is not set +# CONFIG_BACKLIGHT_ADP8860 is not set +# CONFIG_BACKLIGHT_ADP8870 is not set +# CONFIG_BACKLIGHT_LM3630A is not set +# CONFIG_BACKLIGHT_LM3639 is not set +CONFIG_BACKLIGHT_LP855X=m +# CONFIG_BACKLIGHT_GPIO is not set +# CONFIG_BACKLIGHT_LV5207LP is not set +# CONFIG_BACKLIGHT_BD6107 is not set +# CONFIG_BACKLIGHT_ARCXCNN is not set +CONFIG_VIDEOMODE_HELPERS=y +CONFIG_HDMI=y + +# +# Console display driver support +# +CONFIG_DUMMY_CONSOLE=y +CONFIG_DUMMY_CONSOLE_COLUMNS=80 +CONFIG_DUMMY_CONSOLE_ROWS=25 +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y +CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y +CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER=y +CONFIG_LOGO=y +CONFIG_LOGO_LINUX_MONO=y +CONFIG_LOGO_LINUX_VGA16=y +CONFIG_LOGO_LINUX_CLUT224=y +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_SND_TIMER=y +CONFIG_SND_PCM=y +CONFIG_SND_PCM_ELD=y +CONFIG_SND_PCM_IEC958=y +CONFIG_SND_DMAENGINE_PCM=y +CONFIG_SND_HWDEP=m +CONFIG_SND_RAWMIDI=m +CONFIG_SND_JACK=y +CONFIG_SND_JACK_INPUT_DEV=y +# CONFIG_SND_OSSEMUL is not set +CONFIG_SND_PCM_TIMER=y +# CONFIG_SND_HRTIMER is not set +# CONFIG_SND_DYNAMIC_MINORS is not set +CONFIG_SND_SUPPORT_OLD_API=y +CONFIG_SND_PROC_FS=y +CONFIG_SND_VERBOSE_PROCFS=y +# CONFIG_SND_VERBOSE_PRINTK is not set +# CONFIG_SND_DEBUG is not set +CONFIG_SND_VMASTER=y +# CONFIG_SND_SEQUENCER is not set +CONFIG_SND_MPU401_UART=m +CONFIG_SND_AC97_CODEC=m +CONFIG_SND_DRIVERS=y +CONFIG_SND_DUMMY=m +CONFIG_SND_ALOOP=m +CONFIG_SND_MTPAV=m +CONFIG_SND_MTS64=m +CONFIG_SND_SERIAL_U16550=m +CONFIG_SND_MPU401=m +CONFIG_SND_PORTMAN2X4=m +# CONFIG_SND_AC97_POWER_SAVE is not set + +# +# HD-Audio +# +CONFIG_SND_HDA_PREALLOC_SIZE=2048 +CONFIG_SND_SPI=y +CONFIG_SND_USB=y +CONFIG_SND_USB_AUDIO=m +CONFIG_SND_USB_UA101=m +CONFIG_SND_USB_CAIAQ=m +CONFIG_SND_USB_CAIAQ_INPUT=y +CONFIG_SND_USB_6FIRE=m +CONFIG_SND_USB_HIFACE=m +CONFIG_SND_BCD2000=m +CONFIG_SND_USB_LINE6=m +CONFIG_SND_USB_POD=m +CONFIG_SND_USB_PODHD=m +CONFIG_SND_USB_TONEPORT=m +CONFIG_SND_USB_VARIAX=m +CONFIG_SND_SOC=y +CONFIG_SND_SOC_AC97_BUS=y +CONFIG_SND_SOC_GENERIC_DMAENGINE_PCM=y +CONFIG_SND_SOC_AMD_ACP=m +CONFIG_SND_SOC_AMD_CZ_DA7219MX98357_MACH=m +CONFIG_SND_SOC_AMD_CZ_RT5645_MACH=m +CONFIG_SND_ATMEL_SOC=m +CONFIG_SND_SOC_MIKROE_PROTO=m +CONFIG_SND_DESIGNWARE_I2S=m +CONFIG_SND_DESIGNWARE_PCM=y + +# +# SoC Audio for Freescale CPUs +# + +# +# Common SoC Audio options for Freescale CPUs: +# +CONFIG_SND_SOC_FSL_ASRC=m +CONFIG_SND_SOC_FSL_SAI=m +CONFIG_SND_SOC_FSL_SSI=m +CONFIG_SND_SOC_FSL_SPDIF=m +CONFIG_SND_SOC_FSL_ESAI=m +CONFIG_SND_SOC_FSL_MICFIL=m +CONFIG_SND_SOC_IMX_AUDMUX=m +CONFIG_SND_I2S_HI6210_I2S=m +# CONFIG_SND_SOC_IMG is not set +CONFIG_SND_SOC_MTK_BTCVSD=m + +# +# ASoC support for Amlogic platforms +# +CONFIG_SND_MESON_AXG_FIFO=m +CONFIG_SND_MESON_AXG_FRDDR=m +CONFIG_SND_MESON_AXG_TODDR=m +CONFIG_SND_MESON_AXG_TDM_FORMATTER=m +CONFIG_SND_MESON_AXG_TDM_INTERFACE=m +CONFIG_SND_MESON_AXG_TDMIN=m +CONFIG_SND_MESON_AXG_TDMOUT=m +CONFIG_SND_MESON_AXG_SOUND_CARD=m +CONFIG_SND_MESON_AXG_SPDIFOUT=m +CONFIG_SND_MESON_AXG_SPDIFIN=m +CONFIG_SND_MESON_AXG_PDM=m +CONFIG_SND_SOC_MESON_GX=m +CONFIG_SND_SOC_MESON_GX_I2S=m +CONFIG_SND_SOC_MESON_GX_SPDIF=m + +# +# STMicroelectronics STM32 SOC audio support +# +CONFIG_SND_SOC_XILINX_I2S=m +CONFIG_SND_SOC_XILINX_AUDIO_FORMATTER=m +CONFIG_SND_SOC_XILINX_SPDIF=m +CONFIG_SND_SOC_XTFPGA_I2S=m +CONFIG_ZX_TDM=m +CONFIG_SND_SOC_I2C_AND_SPI=y + +# +# CODEC drivers +# +CONFIG_SND_SOC_AC97_CODEC=m +CONFIG_SND_SOC_ADAU_UTILS=m +CONFIG_SND_SOC_ADAU1701=m +CONFIG_SND_SOC_ADAU17X1=m +CONFIG_SND_SOC_ADAU1761=m +CONFIG_SND_SOC_ADAU1761_I2C=m +CONFIG_SND_SOC_ADAU1761_SPI=m +CONFIG_SND_SOC_ADAU7002=m +CONFIG_SND_SOC_AK4104=m +CONFIG_SND_SOC_AK4118=m +CONFIG_SND_SOC_AK4458=m +CONFIG_SND_SOC_AK4554=m +CONFIG_SND_SOC_AK4613=m +CONFIG_SND_SOC_AK4642=m +CONFIG_SND_SOC_AK5386=m +CONFIG_SND_SOC_AK5558=m +CONFIG_SND_SOC_ALC5623=m +CONFIG_SND_SOC_BD28623=m +CONFIG_SND_SOC_BT_SCO=m +CONFIG_SND_SOC_CROS_EC_CODEC=m +CONFIG_SND_SOC_CS35L32=m +CONFIG_SND_SOC_CS35L33=m +CONFIG_SND_SOC_CS35L34=m +CONFIG_SND_SOC_CS35L35=m +CONFIG_SND_SOC_CS35L36=m +CONFIG_SND_SOC_CS42L42=m +CONFIG_SND_SOC_CS42L51=m +CONFIG_SND_SOC_CS42L51_I2C=m +CONFIG_SND_SOC_CS42L52=m +CONFIG_SND_SOC_CS42L56=m +CONFIG_SND_SOC_CS42L73=m +CONFIG_SND_SOC_CS4265=m +CONFIG_SND_SOC_CS4270=m +CONFIG_SND_SOC_CS4271=m +CONFIG_SND_SOC_CS4271_I2C=m +CONFIG_SND_SOC_CS4271_SPI=m +CONFIG_SND_SOC_CS42XX8=m +CONFIG_SND_SOC_CS42XX8_I2C=m +CONFIG_SND_SOC_CS43130=m +CONFIG_SND_SOC_CS4341=m +CONFIG_SND_SOC_CS4349=m +CONFIG_SND_SOC_CS53L30=m +CONFIG_SND_SOC_DA7219=m +CONFIG_SND_SOC_DMIC=m +CONFIG_SND_SOC_HDMI_CODEC=y +CONFIG_SND_SOC_ES7134=m +CONFIG_SND_SOC_ES7241=m +CONFIG_SND_SOC_ES8316=m +CONFIG_SND_SOC_ES8328=m +CONFIG_SND_SOC_ES8328_I2C=m +CONFIG_SND_SOC_ES8328_SPI=m +CONFIG_SND_SOC_GTM601=m +CONFIG_SND_SOC_INNO_RK3036=m +CONFIG_SND_SOC_MAX98088=m +CONFIG_SND_SOC_MAX98357A=m +CONFIG_SND_SOC_MAX98504=m +CONFIG_SND_SOC_MAX9867=m +CONFIG_SND_SOC_MAX98927=m +CONFIG_SND_SOC_MAX98373=m +CONFIG_SND_SOC_MAX9860=m +CONFIG_SND_SOC_MSM8916_WCD_ANALOG=m +CONFIG_SND_SOC_MSM8916_WCD_DIGITAL=m +CONFIG_SND_SOC_PCM1681=m +CONFIG_SND_SOC_PCM1789=m +CONFIG_SND_SOC_PCM1789_I2C=m +CONFIG_SND_SOC_PCM179X=m +CONFIG_SND_SOC_PCM179X_I2C=m +CONFIG_SND_SOC_PCM179X_SPI=m +CONFIG_SND_SOC_PCM186X=m +CONFIG_SND_SOC_PCM186X_I2C=m +CONFIG_SND_SOC_PCM186X_SPI=m +CONFIG_SND_SOC_PCM3060=m +CONFIG_SND_SOC_PCM3060_I2C=m +CONFIG_SND_SOC_PCM3060_SPI=m +CONFIG_SND_SOC_PCM3168A=m +CONFIG_SND_SOC_PCM3168A_I2C=m +CONFIG_SND_SOC_PCM3168A_SPI=m +CONFIG_SND_SOC_PCM512x=m +CONFIG_SND_SOC_PCM512x_I2C=m +CONFIG_SND_SOC_PCM512x_SPI=m +CONFIG_SND_SOC_RK3328=m +CONFIG_SND_SOC_RL6231=m +CONFIG_SND_SOC_RT5616=m +CONFIG_SND_SOC_RT5631=m +CONFIG_SND_SOC_RT5645=m +CONFIG_SND_SOC_SGTL5000=m +CONFIG_SND_SOC_SIGMADSP=m +CONFIG_SND_SOC_SIGMADSP_I2C=m +CONFIG_SND_SOC_SIGMADSP_REGMAP=m +CONFIG_SND_SOC_SIMPLE_AMPLIFIER=m +CONFIG_SND_SOC_SIRF_AUDIO_CODEC=m +CONFIG_SND_SOC_SPDIF=m +CONFIG_SND_SOC_SSM2305=m +CONFIG_SND_SOC_SSM2602=m +CONFIG_SND_SOC_SSM2602_SPI=m +CONFIG_SND_SOC_SSM2602_I2C=m +CONFIG_SND_SOC_SSM4567=m +CONFIG_SND_SOC_STA32X=m +CONFIG_SND_SOC_STA350=m +CONFIG_SND_SOC_STI_SAS=m +CONFIG_SND_SOC_TAS2552=m +CONFIG_SND_SOC_TAS5086=m +CONFIG_SND_SOC_TAS571X=m +CONFIG_SND_SOC_TAS5720=m +CONFIG_SND_SOC_TAS6424=m +CONFIG_SND_SOC_TDA7419=m +CONFIG_SND_SOC_TFA9879=m +CONFIG_SND_SOC_TLV320AIC23=m +CONFIG_SND_SOC_TLV320AIC23_I2C=m +CONFIG_SND_SOC_TLV320AIC23_SPI=m +CONFIG_SND_SOC_TLV320AIC31XX=m +CONFIG_SND_SOC_TLV320AIC32X4=m +CONFIG_SND_SOC_TLV320AIC32X4_I2C=m +CONFIG_SND_SOC_TLV320AIC32X4_SPI=m +CONFIG_SND_SOC_TLV320AIC3X=m +CONFIG_SND_SOC_TS3A227E=m +CONFIG_SND_SOC_TSCS42XX=m +CONFIG_SND_SOC_TSCS454=m +CONFIG_SND_SOC_WM8510=m +CONFIG_SND_SOC_WM8523=m +CONFIG_SND_SOC_WM8524=m +CONFIG_SND_SOC_WM8580=m +CONFIG_SND_SOC_WM8711=m +CONFIG_SND_SOC_WM8728=m +CONFIG_SND_SOC_WM8731=m +CONFIG_SND_SOC_WM8737=m +CONFIG_SND_SOC_WM8741=m +CONFIG_SND_SOC_WM8750=m +CONFIG_SND_SOC_WM8753=m +CONFIG_SND_SOC_WM8770=m +CONFIG_SND_SOC_WM8776=m +CONFIG_SND_SOC_WM8782=m +CONFIG_SND_SOC_WM8804=m +CONFIG_SND_SOC_WM8804_I2C=m +CONFIG_SND_SOC_WM8804_SPI=m +CONFIG_SND_SOC_WM8903=m +CONFIG_SND_SOC_WM8904=m +CONFIG_SND_SOC_WM8960=m +CONFIG_SND_SOC_WM8962=m +CONFIG_SND_SOC_WM8974=m +CONFIG_SND_SOC_WM8978=m +CONFIG_SND_SOC_WM8985=m +CONFIG_SND_SOC_ZX_AUD96P22=m +CONFIG_SND_SOC_MAX9759=m +CONFIG_SND_SOC_MT6351=m +CONFIG_SND_SOC_MT6358=m +CONFIG_SND_SOC_NAU8540=m +CONFIG_SND_SOC_NAU8810=m +CONFIG_SND_SOC_NAU8822=m +CONFIG_SND_SOC_NAU8824=m +CONFIG_SND_SOC_TPA6130A2=m +CONFIG_SND_SIMPLE_CARD_UTILS=y +CONFIG_SND_SIMPLE_CARD=y +CONFIG_SND_AUDIO_GRAPH_CARD=m +CONFIG_AC97_BUS=y + +# +# HID support +# +CONFIG_HID=y +CONFIG_HID_BATTERY_STRENGTH=y +CONFIG_HIDRAW=y +CONFIG_UHID=y +CONFIG_HID_GENERIC=y + +# +# Special HID drivers +# +CONFIG_HID_A4TECH=m +CONFIG_HID_ACCUTOUCH=m +CONFIG_HID_ACRUX=m +CONFIG_HID_ACRUX_FF=y +CONFIG_HID_APPLE=m +CONFIG_HID_APPLEIR=m +# CONFIG_HID_ASUS is not set +CONFIG_HID_AUREAL=m +CONFIG_HID_BELKIN=m +CONFIG_HID_BETOP_FF=m +# CONFIG_HID_BIGBEN_FF is not set +CONFIG_HID_CHERRY=m +CONFIG_HID_CHICONY=m +CONFIG_HID_CORSAIR=m +CONFIG_HID_COUGAR=m +CONFIG_HID_PRODIKEYS=m +# CONFIG_HID_CMEDIA is not set +CONFIG_HID_CP2112=m +CONFIG_HID_CYPRESS=y +CONFIG_HID_DRAGONRISE=m +CONFIG_DRAGONRISE_FF=y +CONFIG_HID_EMS_FF=m +CONFIG_HID_ELAN=m +CONFIG_HID_ELECOM=m +CONFIG_HID_ELO=m +CONFIG_HID_EZKEY=y +CONFIG_HID_GEMBIRD=m +CONFIG_HID_GFRM=m +CONFIG_HID_HOLTEK=m +CONFIG_HOLTEK_FF=y +# CONFIG_HID_GOOGLE_HAMMER is not set +CONFIG_HID_GT683R=m +CONFIG_HID_KEYTOUCH=m +CONFIG_HID_KYE=m +CONFIG_HID_UCLOGIC=m +CONFIG_HID_WALTOP=m +CONFIG_HID_VIEWSONIC=m +CONFIG_HID_GYRATION=m +CONFIG_HID_ICADE=m +# CONFIG_HID_ITE is not set +# CONFIG_HID_JABRA is not set +CONFIG_HID_TWINHAN=m +CONFIG_HID_KENSINGTON=m +CONFIG_HID_LCPOWER=m +CONFIG_HID_LED=m +CONFIG_HID_LENOVO=m +CONFIG_HID_LOGITECH=m +CONFIG_HID_LOGITECH_DJ=m +CONFIG_HID_LOGITECH_HIDPP=m +CONFIG_LOGITECH_FF=y +CONFIG_LOGIRUMBLEPAD2_FF=y +CONFIG_LOGIG940_FF=y +CONFIG_LOGIWHEELS_FF=y +CONFIG_HID_MAGICMOUSE=m +CONFIG_HID_MALTRON=m +# CONFIG_HID_MAYFLASH is not set +CONFIG_HID_REDRAGON=m +CONFIG_HID_MICROSOFT=m +CONFIG_HID_MONTEREY=m +CONFIG_HID_MULTITOUCH=m +CONFIG_HID_NTI=m +CONFIG_HID_NTRIG=m +CONFIG_HID_ORTEK=m +CONFIG_HID_OUYA=m +CONFIG_HID_PANTHERLORD=m +CONFIG_PANTHERLORD_FF=y +CONFIG_HID_PENMOUNT=m +CONFIG_HID_PETALYNX=m +CONFIG_HID_PICOLCD=m +CONFIG_HID_PICOLCD_FB=y +CONFIG_HID_PICOLCD_BACKLIGHT=y +CONFIG_HID_PICOLCD_LCD=y +CONFIG_HID_PICOLCD_LEDS=y +# CONFIG_HID_PICOLCD_CIR is not set +CONFIG_HID_PLANTRONICS=m +CONFIG_HID_PRIMAX=m +# CONFIG_HID_RETRODE is not set +CONFIG_HID_ROCCAT=m +CONFIG_HID_SAITEK=m +CONFIG_HID_SAMSUNG=m +CONFIG_HID_SONY=y +CONFIG_SONY_FF=y +CONFIG_HID_SPEEDLINK=m +CONFIG_HID_STEAM=m +CONFIG_HID_STEELSERIES=m +CONFIG_HID_SUNPLUS=m +CONFIG_HID_RMI=m +CONFIG_HID_GREENASIA=m +CONFIG_GREENASIA_FF=y +CONFIG_HID_SMARTJOYPLUS=m +CONFIG_SMARTJOYPLUS_FF=y +CONFIG_HID_TIVO=m +CONFIG_HID_TOPSEED=m +CONFIG_HID_THINGM=m +CONFIG_HID_THRUSTMASTER=m +CONFIG_THRUSTMASTER_FF=y +# CONFIG_HID_UDRAW_PS3 is not set +CONFIG_HID_WACOM=m +CONFIG_HID_WIIMOTE=m +CONFIG_HID_XINMO=m +CONFIG_HID_ZEROPLUS=m +CONFIG_ZEROPLUS_FF=y +CONFIG_HID_ZYDACRON=m +CONFIG_HID_SENSOR_HUB=m +CONFIG_HID_SENSOR_CUSTOM_SENSOR=m +CONFIG_HID_ALPS=m + +# +# USB HID support +# +CONFIG_USB_HID=y +CONFIG_HID_PID=y +CONFIG_USB_HIDDEV=y + +# +# I2C HID support +# +CONFIG_I2C_HID=m +CONFIG_USB_OHCI_LITTLE_ENDIAN=y +CONFIG_USB_SUPPORT=y +CONFIG_USB_COMMON=y +CONFIG_USB_ARCH_HAS_HCD=y +CONFIG_USB=y +CONFIG_USB_ANNOUNCE_NEW_DEVICES=y + +# +# Miscellaneous USB options +# +CONFIG_USB_DEFAULT_PERSIST=y +# CONFIG_USB_DYNAMIC_MINORS is not set +CONFIG_USB_OTG=y +# CONFIG_USB_OTG_WHITELIST is not set +# CONFIG_USB_OTG_BLACKLIST_HUB is not set +CONFIG_USB_OTG_FSM=m +# CONFIG_USB_LEDS_TRIGGER_USBPORT is not set +CONFIG_USB_AUTOSUSPEND_DELAY=2 +# CONFIG_USB_MON is not set +# CONFIG_USB_WUSB_CBAF is not set + +# +# USB Host Controller Drivers +# +# CONFIG_USB_C67X00_HCD is not set +CONFIG_USB_XHCI_HCD=y +# CONFIG_USB_XHCI_DBGCAP is not set +CONFIG_USB_XHCI_PLATFORM=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_EHCI_ROOT_HUB_TT=y +CONFIG_USB_EHCI_TT_NEWSCHED=y +# CONFIG_USB_EHCI_FSL is not set +CONFIG_USB_EHCI_HCD_PLATFORM=y +CONFIG_USB_OXU210HP_HCD=m +CONFIG_USB_ISP116X_HCD=m +CONFIG_USB_FOTG210_HCD=m +CONFIG_USB_MAX3421_HCD=m +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PLATFORM=y +CONFIG_USB_SL811_HCD=m +CONFIG_USB_SL811_HCD_ISO=y +CONFIG_USB_R8A66597_HCD=m +CONFIG_USB_HCD_BCMA=m +CONFIG_USB_HCD_SSB=m +CONFIG_USB_HCD_TEST_MODE=y + +# +# USB Device Class drivers +# +CONFIG_USB_ACM=m +CONFIG_USB_PRINTER=m +CONFIG_USB_WDM=m +CONFIG_USB_TMC=m + +# +# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may +# + +# +# also be needed; see USB_STORAGE Help for more info +# +CONFIG_USB_STORAGE=y +CONFIG_USB_STORAGE_DEBUG=y +CONFIG_USB_STORAGE_REALTEK=m +CONFIG_REALTEK_AUTOPM=y +CONFIG_USB_STORAGE_DATAFAB=m +CONFIG_USB_STORAGE_FREECOM=m +CONFIG_USB_STORAGE_ISD200=m +CONFIG_USB_STORAGE_USBAT=m +CONFIG_USB_STORAGE_SDDR09=m +CONFIG_USB_STORAGE_SDDR55=m +CONFIG_USB_STORAGE_JUMPSHOT=m +CONFIG_USB_STORAGE_ALAUDA=m +CONFIG_USB_STORAGE_ONETOUCH=m +CONFIG_USB_STORAGE_KARMA=m +CONFIG_USB_STORAGE_CYPRESS_ATACB=m +CONFIG_USB_STORAGE_ENE_UB6250=m +CONFIG_USB_UAS=m + +# +# USB Imaging devices +# +CONFIG_USB_MDC800=m +CONFIG_USB_MICROTEK=m +CONFIG_USBIP_CORE=m +CONFIG_USBIP_VHCI_HCD=m +CONFIG_USBIP_VHCI_HC_PORTS=8 +CONFIG_USBIP_VHCI_NR_HCS=1 +CONFIG_USBIP_HOST=m +CONFIG_USBIP_VUDC=m +# CONFIG_USBIP_DEBUG is not set +CONFIG_USB_MUSB_HDRC=y +# CONFIG_USB_MUSB_HOST is not set +# CONFIG_USB_MUSB_GADGET is not set +CONFIG_USB_MUSB_DUAL_ROLE=y + +# +# Platform Glue Layer +# + +# +# MUSB DMA mode +# +# CONFIG_MUSB_PIO_ONLY is not set +CONFIG_USB_DWC3=y +CONFIG_USB_DWC3_ULPI=y +# CONFIG_USB_DWC3_HOST is not set +# CONFIG_USB_DWC3_GADGET is not set +CONFIG_USB_DWC3_DUAL_ROLE=y + +# +# Platform Glue Driver Support +# +CONFIG_USB_DWC3_MESON_G12A=m +CONFIG_USB_DWC3_OF_SIMPLE=y +CONFIG_USB_DWC2=y +# CONFIG_USB_DWC2_HOST is not set + +# +# Gadget/Dual-role mode requires USB Gadget support to be enabled +# +# CONFIG_USB_DWC2_PERIPHERAL is not set +CONFIG_USB_DWC2_DUAL_ROLE=y +# CONFIG_USB_DWC2_DEBUG is not set +# CONFIG_USB_DWC2_TRACK_MISSED_SOFS is not set +CONFIG_USB_CHIPIDEA=y +CONFIG_USB_CHIPIDEA_OF=y +CONFIG_USB_CHIPIDEA_UDC=y +CONFIG_USB_CHIPIDEA_HOST=y +CONFIG_USB_ISP1760=y +CONFIG_USB_ISP1760_HCD=y +CONFIG_USB_ISP1761_UDC=y +# CONFIG_USB_ISP1760_HOST_ROLE is not set +# CONFIG_USB_ISP1760_GADGET_ROLE is not set +CONFIG_USB_ISP1760_DUAL_ROLE=y + +# +# USB port drivers +# +CONFIG_USB_USS720=m +CONFIG_USB_SERIAL=m +CONFIG_USB_SERIAL_GENERIC=y +CONFIG_USB_SERIAL_SIMPLE=m +CONFIG_USB_SERIAL_AIRCABLE=m +CONFIG_USB_SERIAL_ARK3116=m +CONFIG_USB_SERIAL_BELKIN=m +CONFIG_USB_SERIAL_CH341=m +CONFIG_USB_SERIAL_WHITEHEAT=m +CONFIG_USB_SERIAL_DIGI_ACCELEPORT=m +CONFIG_USB_SERIAL_CP210X=m +CONFIG_USB_SERIAL_CYPRESS_M8=m +CONFIG_USB_SERIAL_EMPEG=m +CONFIG_USB_SERIAL_FTDI_SIO=m +CONFIG_USB_SERIAL_VISOR=m +CONFIG_USB_SERIAL_IPAQ=m +CONFIG_USB_SERIAL_IR=m +CONFIG_USB_SERIAL_EDGEPORT=m +CONFIG_USB_SERIAL_EDGEPORT_TI=m +CONFIG_USB_SERIAL_F81232=m +# CONFIG_USB_SERIAL_F8153X is not set +CONFIG_USB_SERIAL_GARMIN=m +CONFIG_USB_SERIAL_IPW=m +CONFIG_USB_SERIAL_IUU=m +CONFIG_USB_SERIAL_KEYSPAN_PDA=m +CONFIG_USB_SERIAL_KEYSPAN=m +CONFIG_USB_SERIAL_KLSI=m +CONFIG_USB_SERIAL_KOBIL_SCT=m +CONFIG_USB_SERIAL_MCT_U232=m +CONFIG_USB_SERIAL_METRO=m +CONFIG_USB_SERIAL_MOS7720=m +# CONFIG_USB_SERIAL_MOS7715_PARPORT is not set +CONFIG_USB_SERIAL_MOS7840=m +CONFIG_USB_SERIAL_MXUPORT=m +CONFIG_USB_SERIAL_NAVMAN=m +CONFIG_USB_SERIAL_PL2303=m +CONFIG_USB_SERIAL_OTI6858=m +CONFIG_USB_SERIAL_QCAUX=m +CONFIG_USB_SERIAL_QUALCOMM=m +CONFIG_USB_SERIAL_SPCP8X5=m +CONFIG_USB_SERIAL_SAFE=m +# CONFIG_USB_SERIAL_SAFE_PADDED is not set +CONFIG_USB_SERIAL_SIERRAWIRELESS=m +CONFIG_USB_SERIAL_SYMBOL=m +CONFIG_USB_SERIAL_TI=m +CONFIG_USB_SERIAL_CYBERJACK=m +CONFIG_USB_SERIAL_XIRCOM=m +CONFIG_USB_SERIAL_WWAN=m +CONFIG_USB_SERIAL_OPTION=m +CONFIG_USB_SERIAL_OMNINET=m +CONFIG_USB_SERIAL_OPTICON=m +CONFIG_USB_SERIAL_XSENS_MT=m +CONFIG_USB_SERIAL_WISHBONE=m +CONFIG_USB_SERIAL_SSU100=m +CONFIG_USB_SERIAL_QT2=m +CONFIG_USB_SERIAL_UPD78F0730=m +CONFIG_USB_SERIAL_DEBUG=m + +# +# USB Miscellaneous drivers +# +# CONFIG_USB_EMI62 is not set +# CONFIG_USB_EMI26 is not set +# CONFIG_USB_ADUTUX is not set +# CONFIG_USB_SEVSEG is not set +# CONFIG_USB_RIO500 is not set +# CONFIG_USB_LEGOTOWER is not set +# CONFIG_USB_LCD is not set +# CONFIG_USB_CYPRESS_CY7C63 is not set +# CONFIG_USB_CYTHERM is not set +# CONFIG_USB_IDMOUSE is not set +# CONFIG_USB_FTDI_ELAN is not set +# CONFIG_USB_APPLEDISPLAY is not set +# CONFIG_USB_SISUSBVGA is not set +# CONFIG_USB_LD is not set +# CONFIG_USB_TRANCEVIBRATOR is not set +# CONFIG_USB_IOWARRIOR is not set +# CONFIG_USB_TEST is not set +# CONFIG_USB_EHSET_TEST_FIXTURE is not set +# CONFIG_USB_ISIGHTFW is not set +# CONFIG_USB_YUREX is not set +CONFIG_USB_EZUSB_FX2=m +# CONFIG_USB_HUB_USB251XB is not set +CONFIG_USB_HSIC_USB3503=y +# CONFIG_USB_HSIC_USB4604 is not set +# CONFIG_USB_LINK_LAYER_TEST is not set +# CONFIG_USB_CHAOSKEY is not set +CONFIG_USB_ATM=m +# CONFIG_USB_SPEEDTOUCH is not set +# CONFIG_USB_CXACRU is not set +# CONFIG_USB_UEAGLEATM is not set +# CONFIG_USB_XUSBATM is not set + +# +# USB Physical Layer drivers +# +CONFIG_USB_PHY=y +CONFIG_NOP_USB_XCEIV=y +# CONFIG_USB_GPIO_VBUS is not set +# CONFIG_USB_ISP1301 is not set +CONFIG_USB_ULPI=y +CONFIG_USB_ULPI_VIEWPORT=y +CONFIG_USB_GADGET=y +# CONFIG_USB_GADGET_DEBUG is not set +# CONFIG_USB_GADGET_DEBUG_FILES is not set +# CONFIG_USB_GADGET_DEBUG_FS is not set +CONFIG_USB_GADGET_VBUS_DRAW=2 +CONFIG_USB_GADGET_STORAGE_NUM_BUFFERS=2 + +# +# USB Peripheral Controller +# +# CONFIG_USB_FOTG210_UDC is not set +# CONFIG_USB_GR_UDC is not set +# CONFIG_USB_R8A66597 is not set +# CONFIG_USB_PXA27X is not set +# CONFIG_USB_MV_UDC is not set +# CONFIG_USB_MV_U3D is not set +CONFIG_USB_SNP_CORE=y +CONFIG_USB_SNP_UDC_PLAT=y +# CONFIG_USB_M66592 is not set +CONFIG_USB_BDC_UDC=y + +# +# Platform Support +# +# CONFIG_USB_NET2272 is not set +# CONFIG_USB_GADGET_XILINX is not set +# CONFIG_USB_DUMMY_HCD is not set +# CONFIG_USB_CONFIGFS is not set +CONFIG_TYPEC=m +CONFIG_TYPEC_TCPM=m +CONFIG_TYPEC_TCPCI=m +CONFIG_TYPEC_RT1711H=m +CONFIG_TYPEC_FUSB302=m +CONFIG_TYPEC_UCSI=m +CONFIG_UCSI_CCG=m +CONFIG_TYPEC_TPS6598X=m + +# +# USB Type-C Multiplexer/DeMultiplexer Switch support +# +CONFIG_TYPEC_MUX_PI3USB30532=m + +# +# USB Type-C Alternate Mode drivers +# +CONFIG_TYPEC_DP_ALTMODE=m +CONFIG_USB_ROLE_SWITCH=y +# CONFIG_USB_LED_TRIG is not set +CONFIG_USB_ULPI_BUS=y +# CONFIG_UWB is not set +CONFIG_MMC=y +CONFIG_PWRSEQ_EMMC=y +# CONFIG_PWRSEQ_SD8787 is not set +CONFIG_PWRSEQ_SIMPLE=y +CONFIG_MMC_BLOCK=y +CONFIG_MMC_BLOCK_MINORS=32 +# CONFIG_SDIO_UART is not set +# CONFIG_MMC_TEST is not set + +# +# MMC/SD/SDIO Host Controller Drivers +# +# CONFIG_MMC_DEBUG is not set +CONFIG_MMC_ARMMMCI=y +CONFIG_MMC_STM32_SDMMC=y +CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PLTFM=y +CONFIG_MMC_SDHCI_OF_ARASAN=y +# CONFIG_MMC_SDHCI_OF_AT91 is not set +# CONFIG_MMC_SDHCI_OF_DWCMSHC is not set +CONFIG_MMC_SDHCI_CADENCE=y +CONFIG_MMC_SDHCI_F_SDH30=y +CONFIG_MMC_MESON_GX=y +CONFIG_MMC_MESON_MX_SDIO=y +CONFIG_MMC_SPI=y +CONFIG_MMC_DW=y +CONFIG_MMC_DW_PLTFM=y +# CONFIG_MMC_DW_BLUEFIELD is not set +CONFIG_MMC_DW_EXYNOS=y +CONFIG_MMC_DW_HI3798CV200=y +CONFIG_MMC_DW_K3=y +# CONFIG_MMC_VUB300 is not set +# CONFIG_MMC_USHC is not set +# CONFIG_MMC_USDHI6ROL0 is not set +CONFIG_MMC_REALTEK_USB=m +CONFIG_MMC_CQHCI=y +# CONFIG_MMC_MTK is not set +CONFIG_MMC_SDHCI_XENON=y +# CONFIG_MMC_SDHCI_OMAP is not set +# CONFIG_MMC_SDHCI_AM654 is not set +# CONFIG_MEMSTICK is not set +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y +# CONFIG_LEDS_CLASS_FLASH is not set +# CONFIG_LEDS_BRIGHTNESS_HW_CHANGED is not set + +# +# LED drivers +# +# CONFIG_LEDS_AN30259A is not set +# CONFIG_LEDS_BCM6328 is not set +# CONFIG_LEDS_BCM6358 is not set +CONFIG_LEDS_CR0014114=m +# CONFIG_LEDS_LM3530 is not set +# CONFIG_LEDS_LM3642 is not set +CONFIG_LEDS_LM3692X=m +# CONFIG_LEDS_PCA9532 is not set +CONFIG_LEDS_GPIO=y +# CONFIG_LEDS_LP3944 is not set +# CONFIG_LEDS_LP3952 is not set +# CONFIG_LEDS_LP5521 is not set +# CONFIG_LEDS_LP5523 is not set +# CONFIG_LEDS_LP5562 is not set +# CONFIG_LEDS_LP8501 is not set +# CONFIG_LEDS_LP8860 is not set +# CONFIG_LEDS_PCA955X is not set +# CONFIG_LEDS_PCA963X is not set +# CONFIG_LEDS_DAC124S085 is not set +CONFIG_LEDS_PWM=y +# CONFIG_LEDS_REGULATOR is not set +# CONFIG_LEDS_BD2802 is not set +# CONFIG_LEDS_LT3593 is not set +# CONFIG_LEDS_TCA6507 is not set +# CONFIG_LEDS_TLC591XX is not set +# CONFIG_LEDS_LM355x is not set +# CONFIG_LEDS_IS31FL319X is not set +# CONFIG_LEDS_IS31FL32XX is not set + +# +# LED driver for blink(1) USB RGB LED is under Special HID drivers (HID_THINGM) +# +# CONFIG_LEDS_BLINKM is not set +CONFIG_LEDS_SYSCON=y +CONFIG_LEDS_MLXREG=m +CONFIG_LEDS_USER=y + +# +# LED Triggers +# +CONFIG_LEDS_TRIGGERS=y +# CONFIG_LEDS_TRIGGER_TIMER is not set +# CONFIG_LEDS_TRIGGER_ONESHOT is not set +# CONFIG_LEDS_TRIGGER_MTD is not set +CONFIG_LEDS_TRIGGER_HEARTBEAT=y +# CONFIG_LEDS_TRIGGER_BACKLIGHT is not set +CONFIG_LEDS_TRIGGER_CPU=y +CONFIG_LEDS_TRIGGER_ACTIVITY=m +# CONFIG_LEDS_TRIGGER_GPIO is not set +CONFIG_LEDS_TRIGGER_DEFAULT_ON=y + +# +# iptables trigger is under Netfilter config (LED target) +# +# CONFIG_LEDS_TRIGGER_TRANSIENT is not set +# CONFIG_LEDS_TRIGGER_CAMERA is not set +CONFIG_LEDS_TRIGGER_PANIC=y +# CONFIG_LEDS_TRIGGER_NETDEV is not set +# CONFIG_LEDS_TRIGGER_PATTERN is not set +# CONFIG_LEDS_TRIGGER_AUDIO is not set +# CONFIG_ACCESSIBILITY is not set +# CONFIG_INFINIBAND is not set +CONFIG_EDAC_SUPPORT=y +CONFIG_EDAC=y +CONFIG_EDAC_LEGACY_SYSFS=y +# CONFIG_EDAC_DEBUG is not set +# CONFIG_EDAC_XGENE is not set +CONFIG_RTC_LIB=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_HCTOSYS=y +CONFIG_RTC_HCTOSYS_DEVICE="rtc0" +CONFIG_RTC_SYSTOHC=y +CONFIG_RTC_SYSTOHC_DEVICE="rtc0" +# CONFIG_RTC_DEBUG is not set +CONFIG_RTC_NVMEM=y + +# +# RTC interfaces +# +CONFIG_RTC_INTF_SYSFS=y +CONFIG_RTC_INTF_PROC=y +CONFIG_RTC_INTF_DEV=y +# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set +# CONFIG_RTC_DRV_TEST is not set + +# +# I2C RTC drivers +# +# CONFIG_RTC_DRV_ABB5ZES3 is not set +# CONFIG_RTC_DRV_ABEOZ9 is not set +# CONFIG_RTC_DRV_ABX80X is not set +# CONFIG_RTC_DRV_DS1307 is not set +# CONFIG_RTC_DRV_DS1374 is not set +# CONFIG_RTC_DRV_DS1672 is not set +# CONFIG_RTC_DRV_HYM8563 is not set +# CONFIG_RTC_DRV_MAX6900 is not set +CONFIG_RTC_DRV_MAX77686=y +CONFIG_RTC_DRV_RK808=m +# CONFIG_RTC_DRV_RS5C372 is not set +# CONFIG_RTC_DRV_ISL1208 is not set +# CONFIG_RTC_DRV_ISL12022 is not set +CONFIG_RTC_DRV_ISL12026=m +# CONFIG_RTC_DRV_X1205 is not set +# CONFIG_RTC_DRV_PCF8523 is not set +# CONFIG_RTC_DRV_PCF85063 is not set +CONFIG_RTC_DRV_PCF85363=m +CONFIG_RTC_DRV_PCF8563=m +# CONFIG_RTC_DRV_PCF8583 is not set +# CONFIG_RTC_DRV_M41T80 is not set +# CONFIG_RTC_DRV_BQ32K is not set +# CONFIG_RTC_DRV_S35390A is not set +# CONFIG_RTC_DRV_FM3130 is not set +# CONFIG_RTC_DRV_RX8010 is not set +# CONFIG_RTC_DRV_RX8581 is not set +# CONFIG_RTC_DRV_RX8025 is not set +# CONFIG_RTC_DRV_EM3027 is not set +# CONFIG_RTC_DRV_RV3028 is not set +# CONFIG_RTC_DRV_RV8803 is not set +CONFIG_RTC_DRV_S5M=y +# CONFIG_RTC_DRV_SD3078 is not set + +# +# SPI RTC drivers +# +CONFIG_RTC_DRV_M41T93=m +CONFIG_RTC_DRV_M41T94=m +CONFIG_RTC_DRV_DS1302=m +CONFIG_RTC_DRV_DS1305=m +CONFIG_RTC_DRV_DS1343=m +CONFIG_RTC_DRV_DS1347=m +CONFIG_RTC_DRV_DS1390=m +CONFIG_RTC_DRV_MAX6916=m +CONFIG_RTC_DRV_R9701=m +CONFIG_RTC_DRV_RX4581=m +CONFIG_RTC_DRV_RX6110=m +CONFIG_RTC_DRV_RS5C348=m +CONFIG_RTC_DRV_MAX6902=m +CONFIG_RTC_DRV_PCF2123=m +CONFIG_RTC_DRV_MCP795=m +CONFIG_RTC_I2C_AND_SPI=y + +# +# SPI and I2C RTC drivers +# +CONFIG_RTC_DRV_DS3232=y +CONFIG_RTC_DRV_DS3232_HWMON=y +# CONFIG_RTC_DRV_PCF2127 is not set +# CONFIG_RTC_DRV_RV3029C2 is not set + +# +# Platform RTC drivers +# +# CONFIG_RTC_DRV_DS1286 is not set +# CONFIG_RTC_DRV_DS1511 is not set +# CONFIG_RTC_DRV_DS1553 is not set +# CONFIG_RTC_DRV_DS1685_FAMILY is not set +# CONFIG_RTC_DRV_DS1742 is not set +# CONFIG_RTC_DRV_DS2404 is not set +# CONFIG_RTC_DRV_STK17TA8 is not set +# CONFIG_RTC_DRV_M48T86 is not set +# CONFIG_RTC_DRV_M48T35 is not set +# CONFIG_RTC_DRV_M48T59 is not set +# CONFIG_RTC_DRV_MSM6242 is not set +# CONFIG_RTC_DRV_BQ4802 is not set +# CONFIG_RTC_DRV_RP5C01 is not set +# CONFIG_RTC_DRV_V3020 is not set +# CONFIG_RTC_DRV_ZYNQMP is not set +CONFIG_RTC_DRV_CROS_EC=y + +# +# on-CPU RTC drivers +# +# CONFIG_RTC_DRV_PL030 is not set +CONFIG_RTC_DRV_PL031=y +# CONFIG_RTC_DRV_CADENCE is not set +# CONFIG_RTC_DRV_FTRTC010 is not set +# CONFIG_RTC_DRV_SNVS is not set +# CONFIG_RTC_DRV_R7301 is not set + +# +# HID Sensor RTC drivers +# +# CONFIG_RTC_DRV_HID_SENSOR_TIME is not set +CONFIG_DMADEVICES=y +# CONFIG_DMADEVICES_DEBUG is not set + +# +# DMA Devices +# +CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH=y +CONFIG_DMA_ENGINE=y +CONFIG_DMA_OF=y +# CONFIG_ALTERA_MSGDMA is not set +# CONFIG_AMBA_PL08X is not set +CONFIG_BCM_SBA_RAID=m +# CONFIG_DW_AXI_DMAC is not set +# CONFIG_FSL_EDMA is not set +# CONFIG_FSL_QDMA is not set +# CONFIG_INTEL_IDMA64 is not set +CONFIG_MV_XOR_V2=y +CONFIG_PL330_DMA=y +# CONFIG_XILINX_DMA is not set +# CONFIG_XILINX_ZYNQMP_DMA is not set +CONFIG_QCOM_HIDMA_MGMT=y +CONFIG_QCOM_HIDMA=y +# CONFIG_DW_DMAC is not set + +# +# DMA Clients +# +# CONFIG_ASYNC_TX_DMA is not set +# CONFIG_DMATEST is not set +CONFIG_DMA_ENGINE_RAID=y + +# +# DMABUF options +# +CONFIG_SYNC_FILE=y +# CONFIG_SW_SYNC is not set +# CONFIG_UDMABUF is not set +# CONFIG_AUXDISPLAY is not set +# CONFIG_PANEL is not set +CONFIG_UIO=m +# CONFIG_UIO_PDRV_GENIRQ is not set +# CONFIG_UIO_DMEM_GENIRQ is not set +# CONFIG_UIO_PRUSS is not set +CONFIG_VFIO_IOMMU_TYPE1=y +CONFIG_VFIO=y +# CONFIG_VFIO_NOIOMMU is not set +# CONFIG_VFIO_PLATFORM is not set +# CONFIG_VFIO_MDEV is not set +# CONFIG_VIRT_DRIVERS is not set +CONFIG_VIRTIO=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_BALLOON=y +# CONFIG_VIRTIO_INPUT is not set +CONFIG_VIRTIO_MMIO=y +# CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES is not set + +# +# Microsoft Hyper-V guest support +# +CONFIG_STAGING=y +# CONFIG_PRISM2_USB is not set +# CONFIG_COMEDI is not set +CONFIG_RTLLIB=m +CONFIG_RTLLIB_CRYPTO_CCMP=m +CONFIG_RTLLIB_CRYPTO_TKIP=m +CONFIG_RTLLIB_CRYPTO_WEP=m +CONFIG_RTL8723BS=m +CONFIG_R8712U=m +CONFIG_R8188EU=m +CONFIG_88EU_AP_MODE=y +CONFIG_VT6656=m + +# +# IIO staging drivers +# + +# +# Accelerometers +# +# CONFIG_ADIS16203 is not set +# CONFIG_ADIS16240 is not set + +# +# Analog to digital converters +# +# CONFIG_AD7780 is not set +# CONFIG_AD7816 is not set +# CONFIG_AD7192 is not set +# CONFIG_AD7280 is not set + +# +# Analog digital bi-direction converters +# +# CONFIG_ADT7316 is not set + +# +# Capacitance to digital converters +# +# CONFIG_AD7150 is not set +# CONFIG_AD7746 is not set + +# +# Direct Digital Synthesis +# +# CONFIG_AD9832 is not set +# CONFIG_AD9834 is not set + +# +# Network Analyzer, Impedance Converters +# +# CONFIG_AD5933 is not set + +# +# Active energy metering IC +# +# CONFIG_ADE7854 is not set + +# +# Resolver to digital converters +# +# CONFIG_AD2S1210 is not set + +# +# Speakup console speech +# +# CONFIG_SPEAKUP is not set +# CONFIG_STAGING_MEDIA is not set + +# +# Android +# +# CONFIG_STAGING_BOARD is not set +# CONFIG_LTE_GDM724X is not set +# CONFIG_GS_FPGABOOT is not set +# CONFIG_UNISYSSPAR is not set +# CONFIG_COMMON_CLK_XLNX_CLKWZRD is not set +# CONFIG_FB_TFT is not set +# CONFIG_WILC1000_SDIO is not set +# CONFIG_WILC1000_SPI is not set +# CONFIG_MOST is not set +# CONFIG_KS7010 is not set +# CONFIG_GREYBUS is not set +# CONFIG_PI433 is not set + +# +# Gasket devices +# +# CONFIG_XIL_AXIS_FIFO is not set +# CONFIG_EROFS_FS is not set +# CONFIG_GOLDFISH is not set +CONFIG_CHROME_PLATFORMS=y +CONFIG_CROS_EC_I2C=y +CONFIG_CROS_EC_SPI=y +CONFIG_CROS_EC_PROTO=y +CONFIG_CROS_EC_LIGHTBAR=m +CONFIG_CROS_EC_VBC=m +CONFIG_CROS_EC_DEBUGFS=m +CONFIG_CROS_EC_SYSFS=m +CONFIG_CLKDEV_LOOKUP=y +CONFIG_HAVE_CLK_PREPARE=y +CONFIG_COMMON_CLK=y + +# +# Common Clock Framework +# +CONFIG_COMMON_CLK_VERSATILE=y +CONFIG_CLK_SP810=y +CONFIG_CLK_VEXPRESS_OSC=y +# CONFIG_CLK_HSDK is not set +# CONFIG_COMMON_CLK_MAX77686 is not set +# CONFIG_COMMON_CLK_MAX9485 is not set +CONFIG_COMMON_CLK_RK808=y +CONFIG_COMMON_CLK_SCPI=y +# CONFIG_COMMON_CLK_SI5351 is not set +# CONFIG_COMMON_CLK_SI514 is not set +# CONFIG_COMMON_CLK_SI544 is not set +# CONFIG_COMMON_CLK_SI570 is not set +# CONFIG_COMMON_CLK_CDCE706 is not set +# CONFIG_COMMON_CLK_CDCE925 is not set +CONFIG_COMMON_CLK_CS2000_CP=y +CONFIG_COMMON_CLK_S2MPS11=y +CONFIG_CLK_QORIQ=y +CONFIG_COMMON_CLK_XGENE=y +CONFIG_COMMON_CLK_PWM=y +# CONFIG_COMMON_CLK_VC5 is not set +# CONFIG_COMMON_CLK_FIXED_MMIO is not set +CONFIG_COMMON_CLK_MESON_INPUT=y +CONFIG_COMMON_CLK_MESON_REGMAP=y +CONFIG_COMMON_CLK_MESON_DUALDIV=y +CONFIG_COMMON_CLK_MESON_MPLL=y +CONFIG_COMMON_CLK_MESON_PHASE=y +CONFIG_COMMON_CLK_MESON_PLL=y +CONFIG_COMMON_CLK_MESON_SCLK_DIV=y +CONFIG_COMMON_CLK_MESON_VID_PLL_DIV=y +CONFIG_COMMON_CLK_MESON_AO_CLKC=y +CONFIG_COMMON_CLK_MESON_EE_CLKC=y +CONFIG_COMMON_CLK_GXBB=y +CONFIG_COMMON_CLK_AXG=y +CONFIG_COMMON_CLK_AXG_AUDIO=y +CONFIG_COMMON_CLK_G12A=y +# CONFIG_HWSPINLOCK is not set + +# +# Clock Source drivers +# +CONFIG_TIMER_OF=y +CONFIG_TIMER_PROBE=y +CONFIG_CLKSRC_MMIO=y +CONFIG_ARM_ARCH_TIMER=y +CONFIG_ARM_ARCH_TIMER_EVTSTREAM=y +CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND=y +CONFIG_FSL_ERRATUM_A008585=y +# CONFIG_HISILICON_ERRATUM_161010101 is not set +# CONFIG_ARM64_ERRATUM_858921 is not set +CONFIG_ARM_TIMER_SP804=y +CONFIG_CLKSRC_VERSATILE=y +CONFIG_MAILBOX=y +CONFIG_ARM_MHU=y +CONFIG_PLATFORM_MHU=y +# CONFIG_PL320_MBOX is not set +# CONFIG_ALTERA_MBOX is not set +# CONFIG_MAILBOX_TEST is not set +CONFIG_IOMMU_IOVA=y +CONFIG_IOMMU_API=y +CONFIG_IOMMU_SUPPORT=y + +# +# Generic IOMMU Pagetable Support +# +CONFIG_IOMMU_IO_PGTABLE=y +CONFIG_IOMMU_IO_PGTABLE_LPAE=y +# CONFIG_IOMMU_IO_PGTABLE_LPAE_SELFTEST is not set +# CONFIG_IOMMU_IO_PGTABLE_ARMV7S is not set +# CONFIG_IOMMU_DEBUGFS is not set +# CONFIG_IOMMU_DEFAULT_PASSTHROUGH is not set +CONFIG_OF_IOMMU=y +CONFIG_IOMMU_DMA=y +CONFIG_ARM_SMMU=y +CONFIG_ARM_SMMU_V3=y + +# +# Remoteproc drivers +# +# CONFIG_REMOTEPROC is not set + +# +# Rpmsg drivers +# +CONFIG_RPMSG=y +# CONFIG_RPMSG_CHAR is not set +CONFIG_RPMSG_QCOM_GLINK_NATIVE=y +CONFIG_RPMSG_QCOM_GLINK_RPM=y +# CONFIG_RPMSG_VIRTIO is not set +# CONFIG_SOUNDWIRE is not set + +# +# SOC (System On Chip) specific Drivers +# + +# +# Amlogic SoC drivers +# +CONFIG_MESON_CANVAS=y +CONFIG_MESON_CLK_MEASURE=y +CONFIG_MESON_GX_SOCINFO=y +CONFIG_MESON_GX_PM_DOMAINS=y +CONFIG_MESON_MX_SOCINFO=y + +# +# Broadcom SoC drivers +# +CONFIG_SOC_BRCMSTB=y + +# +# NXP/Freescale QorIQ SoC drivers +# + +# +# i.MX SoC drivers +# + +# +# Qualcomm SoC drivers +# +CONFIG_SOC_TI=y + +# +# Xilinx SoC drivers +# +# CONFIG_XILINX_VCU is not set +CONFIG_PM_DEVFREQ=y + +# +# DEVFREQ Governors +# +CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y +# CONFIG_DEVFREQ_GOV_PERFORMANCE is not set +# CONFIG_DEVFREQ_GOV_POWERSAVE is not set +# CONFIG_DEVFREQ_GOV_USERSPACE is not set +# CONFIG_DEVFREQ_GOV_PASSIVE is not set + +# +# DEVFREQ Drivers +# +# CONFIG_PM_DEVFREQ_EVENT is not set +CONFIG_EXTCON=y + +# +# Extcon Device Drivers +# +# CONFIG_EXTCON_ADC_JACK is not set +# CONFIG_EXTCON_GPIO is not set +# CONFIG_EXTCON_MAX3355 is not set +# CONFIG_EXTCON_PTN5150 is not set +# CONFIG_EXTCON_RT8973A is not set +# CONFIG_EXTCON_SM5502 is not set +CONFIG_EXTCON_USB_GPIO=y +CONFIG_EXTCON_USBC_CROS_EC=y +CONFIG_MEMORY=y +# CONFIG_ARM_PL172_MPMC is not set +CONFIG_IIO=y +CONFIG_IIO_BUFFER=y +# CONFIG_IIO_BUFFER_CB is not set +# CONFIG_IIO_BUFFER_HW_CONSUMER is not set +CONFIG_IIO_KFIFO_BUF=y +CONFIG_IIO_TRIGGERED_BUFFER=y +# CONFIG_IIO_CONFIGFS is not set +CONFIG_IIO_TRIGGER=y +CONFIG_IIO_CONSUMERS_PER_TRIGGER=2 +# CONFIG_IIO_SW_DEVICE is not set +# CONFIG_IIO_SW_TRIGGER is not set + +# +# Accelerometers +# +# CONFIG_ADIS16201 is not set +# CONFIG_ADIS16209 is not set +CONFIG_ADXL345=m +CONFIG_ADXL345_I2C=m +CONFIG_ADXL345_SPI=m +# CONFIG_ADXL372_SPI is not set +# CONFIG_ADXL372_I2C is not set +CONFIG_BMA180=m +CONFIG_BMA220=m +CONFIG_BMC150_ACCEL=m +CONFIG_BMC150_ACCEL_I2C=m +CONFIG_BMC150_ACCEL_SPI=m +CONFIG_DA280=m +CONFIG_DA311=m +CONFIG_DMARD06=m +CONFIG_DMARD09=m +CONFIG_DMARD10=m +CONFIG_HID_SENSOR_ACCEL_3D=m +CONFIG_IIO_CROS_EC_ACCEL_LEGACY=m +CONFIG_IIO_ST_ACCEL_3AXIS=m +CONFIG_IIO_ST_ACCEL_I2C_3AXIS=m +CONFIG_IIO_ST_ACCEL_SPI_3AXIS=m +CONFIG_KXSD9=m +CONFIG_KXSD9_SPI=m +CONFIG_KXSD9_I2C=m +CONFIG_KXCJK1013=m +CONFIG_MC3230=m +CONFIG_MMA7455=m +CONFIG_MMA7455_I2C=m +CONFIG_MMA7455_SPI=m +CONFIG_MMA7660=m +CONFIG_MMA8452=m +CONFIG_MMA9551_CORE=m +CONFIG_MMA9551=m +CONFIG_MMA9553=m +CONFIG_MXC4005=m +CONFIG_MXC6255=m +CONFIG_SCA3000=m +CONFIG_STK8312=m +CONFIG_STK8BA50=m + +# +# Analog to digital converters +# +CONFIG_AD_SIGMA_DELTA=m +CONFIG_AD7124=m +# CONFIG_AD7266 is not set +# CONFIG_AD7291 is not set +# CONFIG_AD7298 is not set +# CONFIG_AD7476 is not set +# CONFIG_AD7606_IFACE_PARALLEL is not set +# CONFIG_AD7606_IFACE_SPI is not set +# CONFIG_AD7766 is not set +# CONFIG_AD7768_1 is not set +# CONFIG_AD7791 is not set +# CONFIG_AD7793 is not set +# CONFIG_AD7887 is not set +# CONFIG_AD7923 is not set +# CONFIG_AD7949 is not set +# CONFIG_AD799X is not set +# CONFIG_CC10001_ADC is not set +# CONFIG_ENVELOPE_DETECTOR is not set +# CONFIG_HI8435 is not set +# CONFIG_HX711 is not set +# CONFIG_INA2XX_ADC is not set +# CONFIG_LTC2471 is not set +# CONFIG_LTC2485 is not set +# CONFIG_LTC2497 is not set +# CONFIG_MAX1027 is not set +# CONFIG_MAX11100 is not set +# CONFIG_MAX1118 is not set +# CONFIG_MAX1363 is not set +# CONFIG_MAX9611 is not set +# CONFIG_MCP320X is not set +# CONFIG_MCP3422 is not set +# CONFIG_MCP3911 is not set +CONFIG_MESON_SARADC=y +# CONFIG_NAU7802 is not set +# CONFIG_QCOM_SPMI_IADC is not set +# CONFIG_QCOM_SPMI_VADC is not set +# CONFIG_QCOM_SPMI_ADC5 is not set +# CONFIG_SD_ADC_MODULATOR is not set +# CONFIG_TI_ADC081C is not set +# CONFIG_TI_ADC0832 is not set +# CONFIG_TI_ADC084S021 is not set +# CONFIG_TI_ADC12138 is not set +# CONFIG_TI_ADC108S102 is not set +# CONFIG_TI_ADC128S052 is not set +# CONFIG_TI_ADC161S626 is not set +# CONFIG_TI_ADS1015 is not set +# CONFIG_TI_ADS7950 is not set +# CONFIG_TI_ADS8688 is not set +# CONFIG_TI_ADS124S08 is not set +# CONFIG_TI_TLC4541 is not set +# CONFIG_VF610_ADC is not set + +# +# Analog Front Ends +# +# CONFIG_IIO_RESCALE is not set + +# +# Amplifiers +# +# CONFIG_AD8366 is not set + +# +# Chemical Sensors +# +# CONFIG_ATLAS_PH_SENSOR is not set +# CONFIG_BME680 is not set +# CONFIG_CCS811 is not set +# CONFIG_IAQCORE is not set +# CONFIG_PMS7003 is not set +# CONFIG_SENSIRION_SGP30 is not set +# CONFIG_SPS30 is not set +# CONFIG_VZ89X is not set +CONFIG_IIO_CROS_EC_SENSORS_CORE=m +CONFIG_IIO_CROS_EC_SENSORS=m + +# +# Hid Sensor IIO Common +# +CONFIG_HID_SENSOR_IIO_COMMON=m +CONFIG_HID_SENSOR_IIO_TRIGGER=m + +# +# SSP Sensor Common +# +# CONFIG_IIO_SSP_SENSORHUB is not set +CONFIG_IIO_ST_SENSORS_I2C=m +CONFIG_IIO_ST_SENSORS_SPI=m +CONFIG_IIO_ST_SENSORS_CORE=m + +# +# Counters +# + +# +# Digital to analog converters +# +# CONFIG_AD5064 is not set +# CONFIG_AD5360 is not set +# CONFIG_AD5380 is not set +# CONFIG_AD5421 is not set +# CONFIG_AD5446 is not set +# CONFIG_AD5449 is not set +# CONFIG_AD5592R is not set +# CONFIG_AD5593R is not set +# CONFIG_AD5504 is not set +# CONFIG_AD5624R_SPI is not set +# CONFIG_LTC1660 is not set +# CONFIG_LTC2632 is not set +CONFIG_AD5686=m +CONFIG_AD5686_SPI=m +# CONFIG_AD5696_I2C is not set +# CONFIG_AD5755 is not set +# CONFIG_AD5758 is not set +# CONFIG_AD5761 is not set +# CONFIG_AD5764 is not set +# CONFIG_AD5791 is not set +# CONFIG_AD7303 is not set +# CONFIG_AD8801 is not set +# CONFIG_DPOT_DAC is not set +# CONFIG_DS4424 is not set +# CONFIG_M62332 is not set +# CONFIG_MAX517 is not set +# CONFIG_MAX5821 is not set +# CONFIG_MCP4725 is not set +# CONFIG_MCP4922 is not set +# CONFIG_TI_DAC082S085 is not set +CONFIG_TI_DAC5571=m +# CONFIG_TI_DAC7311 is not set +# CONFIG_TI_DAC7612 is not set +# CONFIG_VF610_DAC is not set + +# +# IIO dummy driver +# + +# +# Frequency Synthesizers DDS/PLL +# + +# +# Clock Generator/Distribution +# +# CONFIG_AD9523 is not set + +# +# Phase-Locked Loop (PLL) frequency synthesizers +# +# CONFIG_ADF4350 is not set + +# +# Digital gyroscope sensors +# +CONFIG_ADIS16080=m +CONFIG_ADIS16130=m +CONFIG_ADIS16136=m +CONFIG_ADIS16260=m +CONFIG_ADXRS450=m +CONFIG_BMG160=m +CONFIG_BMG160_I2C=m +CONFIG_BMG160_SPI=m +CONFIG_HID_SENSOR_GYRO_3D=m +CONFIG_MPU3050=m +CONFIG_MPU3050_I2C=m +CONFIG_IIO_ST_GYRO_3AXIS=m +CONFIG_IIO_ST_GYRO_I2C_3AXIS=m +CONFIG_IIO_ST_GYRO_SPI_3AXIS=m +CONFIG_ITG3200=m + +# +# Health Sensors +# + +# +# Heart Rate Monitors +# +# CONFIG_AFE4403 is not set +# CONFIG_AFE4404 is not set +# CONFIG_MAX30100 is not set +# CONFIG_MAX30102 is not set + +# +# Humidity sensors +# +# CONFIG_AM2315 is not set +CONFIG_DHT11=m +# CONFIG_HDC100X is not set +# CONFIG_HID_SENSOR_HUMIDITY is not set +# CONFIG_HTS221 is not set +# CONFIG_HTU21 is not set +CONFIG_SI7005=m +CONFIG_SI7020=m + +# +# Inertial measurement units +# +# CONFIG_ADIS16400 is not set +# CONFIG_ADIS16480 is not set +# CONFIG_BMI160_I2C is not set +# CONFIG_BMI160_SPI is not set +# CONFIG_KMX61 is not set +# CONFIG_INV_MPU6050_I2C is not set +# CONFIG_INV_MPU6050_SPI is not set +# CONFIG_IIO_ST_LSM6DSX is not set +CONFIG_IIO_ADIS_LIB=m +CONFIG_IIO_ADIS_LIB_BUFFER=y + +# +# Light sensors +# +CONFIG_ADJD_S311=m +CONFIG_AL3320A=m +CONFIG_APDS9300=m +CONFIG_APDS9960=m +CONFIG_BH1750=m +CONFIG_BH1780=m +CONFIG_CM32181=m +CONFIG_CM3232=m +CONFIG_CM3323=m +CONFIG_CM3605=m +CONFIG_CM36651=m +# CONFIG_IIO_CROS_EC_LIGHT_PROX is not set +CONFIG_GP2AP020A00F=m +CONFIG_SENSORS_ISL29018=m +CONFIG_SENSORS_ISL29028=m +CONFIG_ISL29125=m +CONFIG_HID_SENSOR_ALS=m +CONFIG_HID_SENSOR_PROX=m +CONFIG_JSA1212=m +CONFIG_RPR0521=m +CONFIG_LTR501=m +CONFIG_LV0104CS=m +CONFIG_MAX44000=m +CONFIG_MAX44009=m +CONFIG_OPT3001=m +CONFIG_PA12203001=m +CONFIG_SI1133=m +CONFIG_SI1145=m +CONFIG_STK3310=m +CONFIG_ST_UVIS25=m +CONFIG_ST_UVIS25_I2C=m +CONFIG_ST_UVIS25_SPI=m +CONFIG_TCS3414=m +CONFIG_TCS3472=m +CONFIG_SENSORS_TSL2563=m +CONFIG_TSL2583=m +CONFIG_TSL2772=m +CONFIG_TSL4531=m +CONFIG_US5182D=m +CONFIG_VCNL4000=m +# CONFIG_VCNL4035 is not set +CONFIG_VEML6070=m +CONFIG_VL6180=m +CONFIG_ZOPT2201=m + +# +# Magnetometer sensors +# +# CONFIG_AK8974 is not set +# CONFIG_AK8975 is not set +# CONFIG_AK09911 is not set +# CONFIG_BMC150_MAGN_I2C is not set +# CONFIG_BMC150_MAGN_SPI is not set +# CONFIG_MAG3110 is not set +CONFIG_HID_SENSOR_MAGNETOMETER_3D=m +# CONFIG_MMC35240 is not set +# CONFIG_IIO_ST_MAGN_3AXIS is not set +# CONFIG_SENSORS_HMC5843_I2C is not set +# CONFIG_SENSORS_HMC5843_SPI is not set +# CONFIG_SENSORS_RM3100_I2C is not set +# CONFIG_SENSORS_RM3100_SPI is not set + +# +# Multiplexers +# +# CONFIG_IIO_MUX is not set + +# +# Inclinometer sensors +# +CONFIG_HID_SENSOR_INCLINOMETER_3D=m +CONFIG_HID_SENSOR_DEVICE_ROTATION=m + +# +# Triggers - standalone +# +CONFIG_IIO_INTERRUPT_TRIGGER=m +CONFIG_IIO_SYSFS_TRIGGER=m + +# +# Digital potentiometers +# +CONFIG_AD5272=m +# CONFIG_DS1803 is not set +# CONFIG_MAX5481 is not set +# CONFIG_MAX5487 is not set +# CONFIG_MCP4018 is not set +# CONFIG_MCP4131 is not set +# CONFIG_MCP4531 is not set +# CONFIG_MCP41010 is not set +# CONFIG_TPL0102 is not set + +# +# Digital potentiostats +# +# CONFIG_LMP91000 is not set + +# +# Pressure sensors +# +# CONFIG_ABP060MG is not set +CONFIG_BMP280=m +CONFIG_BMP280_I2C=m +CONFIG_BMP280_SPI=m +# CONFIG_IIO_CROS_EC_BARO is not set +# CONFIG_HID_SENSOR_PRESS is not set +# CONFIG_HP03 is not set +# CONFIG_MPL115_I2C is not set +# CONFIG_MPL115_SPI is not set +# CONFIG_MPL3115 is not set +# CONFIG_MS5611 is not set +# CONFIG_MS5637 is not set +# CONFIG_IIO_ST_PRESS is not set +# CONFIG_T5403 is not set +# CONFIG_HP206C is not set +# CONFIG_ZPA2326 is not set + +# +# Lightning sensors +# +# CONFIG_AS3935 is not set + +# +# Proximity and distance sensors +# +# CONFIG_ISL29501 is not set +# CONFIG_LIDAR_LITE_V2 is not set +# CONFIG_RFD77402 is not set +# CONFIG_SRF04 is not set +# CONFIG_SX9500 is not set +# CONFIG_SRF08 is not set +# CONFIG_VL53L0X_I2C is not set + +# +# Resolver to digital converters +# +# CONFIG_AD2S90 is not set +# CONFIG_AD2S1200 is not set + +# +# Temperature sensors +# +# CONFIG_MAXIM_THERMOCOUPLE is not set +# CONFIG_HID_SENSOR_TEMP is not set +# CONFIG_MLX90614 is not set +# CONFIG_MLX90632 is not set +# CONFIG_TMP006 is not set +# CONFIG_TMP007 is not set +# CONFIG_TSYS01 is not set +# CONFIG_TSYS02D is not set +CONFIG_PWM=y +CONFIG_PWM_SYSFS=y +CONFIG_PWM_CROS_EC=m +# CONFIG_PWM_FSL_FTM is not set +CONFIG_PWM_MESON=m +# CONFIG_PWM_PCA9685 is not set + +# +# IRQ chip support +# +CONFIG_IRQCHIP=y +CONFIG_ARM_GIC=y +CONFIG_ARM_GIC_MAX_NR=1 +CONFIG_ARM_GIC_V3=y +CONFIG_ARM_GIC_V3_ITS=y +CONFIG_PARTITION_PERCPU=y +CONFIG_MESON_IRQ_GPIO=y +# CONFIG_IPACK_BUS is not set +CONFIG_RESET_CONTROLLER=y +CONFIG_RESET_MESON=y +CONFIG_RESET_MESON_AUDIO_ARB=y +# CONFIG_RESET_TI_SYSCON is not set +# CONFIG_FMC is not set + +# +# PHY Subsystem +# +CONFIG_GENERIC_PHY=y +CONFIG_PHY_XGENE=y +CONFIG_PHY_MESON8B_USB2=y +CONFIG_PHY_MESON_GXL_USB2=y +CONFIG_PHY_MESON_GXL_USB3=y +CONFIG_PHY_MESON_G12A_USB2=y +CONFIG_PHY_MESON_G12A_USB3_PCIE=y +# CONFIG_BCM_KONA_USB2_PHY is not set +# CONFIG_PHY_CADENCE_DP is not set +# CONFIG_PHY_CADENCE_DPHY is not set +# CONFIG_PHY_CADENCE_SIERRA is not set +# CONFIG_PHY_FSL_IMX8MQ_USB is not set +# CONFIG_PHY_PXA_28NM_HSIC is not set +# CONFIG_PHY_PXA_28NM_USB2 is not set +# CONFIG_PHY_CPCAP_USB is not set +# CONFIG_PHY_MAPPHONE_MDM6600 is not set +# CONFIG_PHY_OCELOT_SERDES is not set +CONFIG_PHY_QCOM_USB_HS=y +# CONFIG_PHY_QCOM_USB_HSIC is not set +CONFIG_PHY_SAMSUNG_USB2=y +CONFIG_PHY_TUSB1210=m +# CONFIG_POWERCAP is not set +# CONFIG_MCB is not set + +# +# Performance monitor support +# +CONFIG_ARM_CCI_PMU=m +# CONFIG_ARM_CCI400_PMU is not set +# CONFIG_ARM_CCI5xx_PMU is not set +# CONFIG_ARM_CCN is not set +CONFIG_ARM_PMU=y +# CONFIG_ARM_DSU_PMU is not set +# CONFIG_ARM_SPE_PMU is not set +CONFIG_RAS=y + +# +# Android +# +# CONFIG_ANDROID is not set +# CONFIG_LIBNVDIMM is not set +CONFIG_DAX=m +CONFIG_DEV_DAX=m +CONFIG_NVMEM=y +CONFIG_MESON_EFUSE=y +CONFIG_MESON_MX_EFUSE=y + +# +# HW tracing support +# +# CONFIG_STM is not set +# CONFIG_INTEL_TH is not set +# CONFIG_FPGA is not set +# CONFIG_FSI is not set +CONFIG_TEE=y + +# +# TEE drivers +# +CONFIG_OPTEE=y +CONFIG_OPTEE_SHM_NUM_PRIV_PAGES=1 +CONFIG_MULTIPLEXER=m + +# +# Multiplexer drivers +# +# CONFIG_MUX_ADG792A is not set +# CONFIG_MUX_ADGS1408 is not set +# CONFIG_MUX_GPIO is not set +# CONFIG_MUX_MMIO is not set +CONFIG_PM_OPP=y +# CONFIG_SIOX is not set +# CONFIG_SLIMBUS is not set +# CONFIG_INTERCONNECT is not set + +# +# File systems +# +CONFIG_DCACHE_WORD_ACCESS=y +CONFIG_VALIDATE_FS_PARSER=y +CONFIG_FS_IOMAP=y +CONFIG_EXT2_FS=y +# CONFIG_EXT2_FS_XATTR is not set +CONFIG_EXT3_FS=y +# CONFIG_EXT3_FS_POSIX_ACL is not set +CONFIG_EXT3_FS_SECURITY=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +# CONFIG_EXT4_DEBUG is not set +CONFIG_JBD2=y +# CONFIG_JBD2_DEBUG is not set +CONFIG_FS_MBCACHE=y +CONFIG_REISERFS_FS=y +# CONFIG_REISERFS_CHECK is not set +CONFIG_REISERFS_PROC_INFO=y +# CONFIG_REISERFS_FS_XATTR is not set +CONFIG_JFS_FS=y +CONFIG_JFS_POSIX_ACL=y +# CONFIG_JFS_SECURITY is not set +# CONFIG_JFS_DEBUG is not set +# CONFIG_JFS_STATISTICS is not set +CONFIG_XFS_FS=y +CONFIG_XFS_QUOTA=y +CONFIG_XFS_POSIX_ACL=y +CONFIG_XFS_RT=y +# CONFIG_XFS_ONLINE_SCRUB is not set +# CONFIG_XFS_WARN is not set +# CONFIG_XFS_DEBUG is not set +CONFIG_GFS2_FS=y +CONFIG_OCFS2_FS=y +CONFIG_OCFS2_FS_O2CB=y +CONFIG_OCFS2_FS_STATS=y +CONFIG_OCFS2_DEBUG_MASKLOG=y +# CONFIG_OCFS2_DEBUG_FS is not set +CONFIG_BTRFS_FS=y +CONFIG_BTRFS_FS_POSIX_ACL=y +# CONFIG_BTRFS_FS_CHECK_INTEGRITY is not set +# CONFIG_BTRFS_FS_RUN_SANITY_TESTS is not set +# CONFIG_BTRFS_DEBUG is not set +# CONFIG_BTRFS_ASSERT is not set +# CONFIG_BTRFS_FS_REF_VERIFY is not set +CONFIG_NILFS2_FS=m +CONFIG_F2FS_FS=y +CONFIG_F2FS_STAT_FS=y +CONFIG_F2FS_FS_XATTR=y +CONFIG_F2FS_FS_POSIX_ACL=y +CONFIG_F2FS_FS_SECURITY=y +# CONFIG_F2FS_CHECK_FS is not set +# CONFIG_F2FS_FAULT_INJECTION is not set +# CONFIG_FS_DAX is not set +CONFIG_FS_POSIX_ACL=y +CONFIG_EXPORTFS=y +# CONFIG_EXPORTFS_BLOCK_OPS is not set +CONFIG_FILE_LOCKING=y +CONFIG_MANDATORY_FILE_LOCKING=y +CONFIG_FS_ENCRYPTION=y +CONFIG_FSNOTIFY=y +CONFIG_DNOTIFY=y +CONFIG_INOTIFY_USER=y +CONFIG_FANOTIFY=y +CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y +CONFIG_QUOTA=y +CONFIG_QUOTA_NETLINK_INTERFACE=y +CONFIG_PRINT_QUOTA_WARNING=y +# CONFIG_QUOTA_DEBUG is not set +CONFIG_QUOTA_TREE=y +CONFIG_QFMT_V1=m +CONFIG_QFMT_V2=m +CONFIG_QUOTACTL=y +CONFIG_AUTOFS4_FS=y +CONFIG_AUTOFS_FS=y +CONFIG_FUSE_FS=m +CONFIG_CUSE=m +CONFIG_OVERLAY_FS=y +# CONFIG_OVERLAY_FS_REDIRECT_DIR is not set +CONFIG_OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW=y +# CONFIG_OVERLAY_FS_INDEX is not set +# CONFIG_OVERLAY_FS_XINO_AUTO is not set +# CONFIG_OVERLAY_FS_METACOPY is not set + +# +# Caches +# +CONFIG_FSCACHE=y +# CONFIG_FSCACHE_STATS is not set +# CONFIG_FSCACHE_HISTOGRAM is not set +# CONFIG_FSCACHE_DEBUG is not set +# CONFIG_FSCACHE_OBJECT_LIST is not set +CONFIG_CACHEFILES=m +# CONFIG_CACHEFILES_DEBUG is not set +# CONFIG_CACHEFILES_HISTOGRAM is not set + +# +# CD-ROM/DVD Filesystems +# +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_UDF_FS=y + +# +# DOS/FAT/NT Filesystems +# +CONFIG_FAT_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_FAT_DEFAULT_CODEPAGE=437 +CONFIG_FAT_DEFAULT_IOCHARSET="ascii" +CONFIG_FAT_DEFAULT_UTF8=y +CONFIG_NTFS_FS=y +# CONFIG_NTFS_DEBUG is not set +CONFIG_NTFS_RW=y + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +# CONFIG_PROC_KCORE is not set +CONFIG_PROC_SYSCTL=y +CONFIG_PROC_PAGE_MONITOR=y +CONFIG_PROC_CHILDREN=y +CONFIG_KERNFS=y +CONFIG_SYSFS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_TMPFS_XATTR=y +CONFIG_HUGETLBFS=y +CONFIG_HUGETLB_PAGE=y +CONFIG_MEMFD_CREATE=y +CONFIG_ARCH_HAS_GIGANTIC_PAGE=y +CONFIG_CONFIGFS_FS=y +CONFIG_MISC_FILESYSTEMS=y +# CONFIG_ORANGEFS_FS is not set +# CONFIG_ADFS_FS is not set +# CONFIG_AFFS_FS is not set +CONFIG_ECRYPT_FS=m +# CONFIG_ECRYPT_FS_MESSAGING is not set +CONFIG_HFS_FS=m +CONFIG_HFSPLUS_FS=m +# CONFIG_BEFS_FS is not set +# CONFIG_BFS_FS is not set +# CONFIG_EFS_FS is not set +CONFIG_JFFS2_FS=m +CONFIG_JFFS2_FS_DEBUG=0 +CONFIG_JFFS2_FS_WRITEBUFFER=y +# CONFIG_JFFS2_FS_WBUF_VERIFY is not set +# CONFIG_JFFS2_SUMMARY is not set +# CONFIG_JFFS2_FS_XATTR is not set +# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set +CONFIG_JFFS2_ZLIB=y +CONFIG_JFFS2_RTIME=y +# CONFIG_CRAMFS is not set +CONFIG_SQUASHFS=y +# CONFIG_SQUASHFS_FILE_CACHE is not set +CONFIG_SQUASHFS_FILE_DIRECT=y +# CONFIG_SQUASHFS_DECOMP_SINGLE is not set +# CONFIG_SQUASHFS_DECOMP_MULTI is not set +CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU=y +CONFIG_SQUASHFS_XATTR=y +CONFIG_SQUASHFS_ZLIB=y +CONFIG_SQUASHFS_LZ4=y +CONFIG_SQUASHFS_LZO=y +CONFIG_SQUASHFS_XZ=y +CONFIG_SQUASHFS_ZSTD=y +CONFIG_SQUASHFS_4K_DEVBLK_SIZE=y +CONFIG_SQUASHFS_EMBEDDED=y +CONFIG_SQUASHFS_FRAGMENT_CACHE_SIZE=3 +# CONFIG_VXFS_FS is not set +# CONFIG_MINIX_FS is not set +# CONFIG_OMFS_FS is not set +# CONFIG_HPFS_FS is not set +# CONFIG_QNX4FS_FS is not set +# CONFIG_QNX6FS_FS is not set +# CONFIG_ROMFS_FS is not set +CONFIG_PSTORE=y +CONFIG_PSTORE_DEFLATE_COMPRESS=y +# CONFIG_PSTORE_LZO_COMPRESS is not set +# CONFIG_PSTORE_LZ4_COMPRESS is not set +# CONFIG_PSTORE_LZ4HC_COMPRESS is not set +# CONFIG_PSTORE_842_COMPRESS is not set +# CONFIG_PSTORE_ZSTD_COMPRESS is not set +CONFIG_PSTORE_COMPRESS=y +CONFIG_PSTORE_DEFLATE_COMPRESS_DEFAULT=y +CONFIG_PSTORE_COMPRESS_DEFAULT="deflate" +# CONFIG_PSTORE_CONSOLE is not set +# CONFIG_PSTORE_PMSG is not set +# CONFIG_PSTORE_RAM is not set +# CONFIG_SYSV_FS is not set +# CONFIG_UFS_FS is not set +CONFIG_NETWORK_FILESYSTEMS=y +CONFIG_NFS_FS=y +CONFIG_NFS_V2=y +CONFIG_NFS_V3=y +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=y +CONFIG_NFS_SWAP=y +CONFIG_NFS_V4_1=y +CONFIG_NFS_V4_2=y +CONFIG_PNFS_FILE_LAYOUT=y +CONFIG_PNFS_BLOCK=m +CONFIG_PNFS_FLEXFILE_LAYOUT=m +CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN="kernel.org" +CONFIG_NFS_V4_1_MIGRATION=y +CONFIG_NFS_V4_SECURITY_LABEL=y +CONFIG_ROOT_NFS=y +CONFIG_NFS_FSCACHE=y +# CONFIG_NFS_USE_LEGACY_DNS is not set +CONFIG_NFS_USE_KERNEL_DNS=y +CONFIG_NFSD=y +CONFIG_NFSD_V2_ACL=y +CONFIG_NFSD_V3=y +CONFIG_NFSD_V3_ACL=y +CONFIG_NFSD_V4=y +# CONFIG_NFSD_BLOCKLAYOUT is not set +# CONFIG_NFSD_SCSILAYOUT is not set +# CONFIG_NFSD_FLEXFILELAYOUT is not set +# CONFIG_NFSD_V4_SECURITY_LABEL is not set +# CONFIG_NFSD_FAULT_INJECTION is not set +CONFIG_GRACE_PERIOD=y +CONFIG_LOCKD=y +CONFIG_LOCKD_V4=y +CONFIG_NFS_ACL_SUPPORT=y +CONFIG_NFS_COMMON=y +CONFIG_SUNRPC=y +CONFIG_SUNRPC_GSS=y +CONFIG_SUNRPC_BACKCHANNEL=y +CONFIG_SUNRPC_SWAP=y +CONFIG_RPCSEC_GSS_KRB5=m +# CONFIG_CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES is not set +# CONFIG_SUNRPC_DEBUG is not set +# CONFIG_CEPH_FS is not set +CONFIG_CIFS=y +CONFIG_CIFS_STATS2=y +CONFIG_CIFS_ALLOW_INSECURE_LEGACY=y +# CONFIG_CIFS_WEAK_PW_HASH is not set +CONFIG_CIFS_UPCALL=y +CONFIG_CIFS_XATTR=y +CONFIG_CIFS_POSIX=y +CONFIG_CIFS_ACL=y +# CONFIG_CIFS_DEBUG is not set +# CONFIG_CIFS_DFS_UPCALL is not set +CONFIG_CIFS_FSCACHE=y +# CONFIG_CODA_FS is not set +# CONFIG_AFS_FS is not set +CONFIG_9P_FS=m +# CONFIG_9P_FSCACHE is not set +# CONFIG_9P_FS_POSIX_ACL is not set +# CONFIG_9P_FS_SECURITY is not set +CONFIG_NLS=y +CONFIG_NLS_DEFAULT="utf-8" +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_CODEPAGE_737=m +CONFIG_NLS_CODEPAGE_775=m +CONFIG_NLS_CODEPAGE_850=m +CONFIG_NLS_CODEPAGE_852=m +CONFIG_NLS_CODEPAGE_855=m +CONFIG_NLS_CODEPAGE_857=m +CONFIG_NLS_CODEPAGE_860=m +CONFIG_NLS_CODEPAGE_861=m +CONFIG_NLS_CODEPAGE_862=m +CONFIG_NLS_CODEPAGE_863=m +CONFIG_NLS_CODEPAGE_864=m +CONFIG_NLS_CODEPAGE_865=m +CONFIG_NLS_CODEPAGE_866=m +CONFIG_NLS_CODEPAGE_869=m +CONFIG_NLS_CODEPAGE_936=m +CONFIG_NLS_CODEPAGE_950=m +CONFIG_NLS_CODEPAGE_932=m +CONFIG_NLS_CODEPAGE_949=m +CONFIG_NLS_CODEPAGE_874=m +CONFIG_NLS_ISO8859_8=m +CONFIG_NLS_CODEPAGE_1250=m +CONFIG_NLS_CODEPAGE_1251=m +CONFIG_NLS_ASCII=y +CONFIG_NLS_ISO8859_1=y +CONFIG_NLS_ISO8859_2=m +CONFIG_NLS_ISO8859_3=m +CONFIG_NLS_ISO8859_4=m +CONFIG_NLS_ISO8859_5=m +CONFIG_NLS_ISO8859_6=m +CONFIG_NLS_ISO8859_7=m +CONFIG_NLS_ISO8859_9=m +CONFIG_NLS_ISO8859_13=m +CONFIG_NLS_ISO8859_14=m +CONFIG_NLS_ISO8859_15=m +CONFIG_NLS_KOI8_R=m +CONFIG_NLS_KOI8_U=m +CONFIG_NLS_MAC_ROMAN=m +CONFIG_NLS_MAC_CELTIC=m +CONFIG_NLS_MAC_CENTEURO=m +CONFIG_NLS_MAC_CROATIAN=m +CONFIG_NLS_MAC_CYRILLIC=m +CONFIG_NLS_MAC_GAELIC=m +CONFIG_NLS_MAC_GREEK=m +CONFIG_NLS_MAC_ICELAND=m +CONFIG_NLS_MAC_INUIT=m +CONFIG_NLS_MAC_ROMANIAN=m +CONFIG_NLS_MAC_TURKISH=m +CONFIG_NLS_UTF8=y +# CONFIG_DLM is not set + +# +# Security options +# +CONFIG_KEYS=y +CONFIG_KEYS_COMPAT=y +# CONFIG_PERSISTENT_KEYRINGS is not set +# CONFIG_BIG_KEYS is not set +# CONFIG_TRUSTED_KEYS is not set +CONFIG_ENCRYPTED_KEYS=y +# CONFIG_KEY_DH_OPERATIONS is not set +# CONFIG_SECURITY_DMESG_RESTRICT is not set +CONFIG_SECURITY=y +CONFIG_SECURITYFS=y +CONFIG_SECURITY_NETWORK=y +# CONFIG_SECURITY_NETWORK_XFRM is not set +CONFIG_SECURITY_PATH=y +CONFIG_LSM_MMAP_MIN_ADDR=32768 +CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR=y +# CONFIG_HARDENED_USERCOPY is not set +# CONFIG_FORTIFY_SOURCE is not set +# CONFIG_STATIC_USERMODEHELPER is not set +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_BOOTPARAM=y +# CONFIG_SECURITY_SELINUX_DISABLE is not set +CONFIG_SECURITY_SELINUX_DEVELOP=y +CONFIG_SECURITY_SELINUX_AVC_STATS=y +CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=0 +# CONFIG_SECURITY_SMACK is not set +# CONFIG_SECURITY_TOMOYO is not set +CONFIG_SECURITY_APPARMOR=y +CONFIG_SECURITY_APPARMOR_HASH=y +CONFIG_SECURITY_APPARMOR_HASH_DEFAULT=y +# CONFIG_SECURITY_APPARMOR_DEBUG is not set +# CONFIG_SECURITY_LOADPIN is not set +# CONFIG_SECURITY_YAMA is not set +# CONFIG_SECURITY_SAFESETID is not set +CONFIG_INTEGRITY=y +# CONFIG_INTEGRITY_SIGNATURE is not set +CONFIG_INTEGRITY_AUDIT=y +# CONFIG_IMA is not set +# CONFIG_EVM is not set +CONFIG_DEFAULT_SECURITY_SELINUX=y +# CONFIG_DEFAULT_SECURITY_APPARMOR is not set +# CONFIG_DEFAULT_SECURITY_DAC is not set +CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" +CONFIG_XOR_BLOCKS=y +CONFIG_ASYNC_CORE=m +CONFIG_ASYNC_MEMCPY=m +CONFIG_ASYNC_XOR=m +CONFIG_ASYNC_PQ=m +CONFIG_ASYNC_RAID6_RECOV=m +CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA=y +CONFIG_ASYNC_TX_DISABLE_XOR_VAL_DMA=y +CONFIG_CRYPTO=y + +# +# Crypto core or helper +# +CONFIG_CRYPTO_ALGAPI=y +CONFIG_CRYPTO_ALGAPI2=y +CONFIG_CRYPTO_AEAD=y +CONFIG_CRYPTO_AEAD2=y +CONFIG_CRYPTO_BLKCIPHER=y +CONFIG_CRYPTO_BLKCIPHER2=y +CONFIG_CRYPTO_HASH=y +CONFIG_CRYPTO_HASH2=y +CONFIG_CRYPTO_RNG=y +CONFIG_CRYPTO_RNG2=y +CONFIG_CRYPTO_RNG_DEFAULT=y +CONFIG_CRYPTO_AKCIPHER2=y +CONFIG_CRYPTO_AKCIPHER=y +CONFIG_CRYPTO_KPP2=y +CONFIG_CRYPTO_KPP=m +CONFIG_CRYPTO_ACOMP2=y +CONFIG_CRYPTO_RSA=y +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m +CONFIG_CRYPTO_MANAGER=y +CONFIG_CRYPTO_MANAGER2=y +CONFIG_CRYPTO_USER=m +CONFIG_CRYPTO_MANAGER_DISABLE_TESTS=y +CONFIG_CRYPTO_GF128MUL=y +CONFIG_CRYPTO_NULL=y +CONFIG_CRYPTO_NULL2=y +CONFIG_CRYPTO_PCRYPT=y +CONFIG_CRYPTO_WORKQUEUE=y +CONFIG_CRYPTO_CRYPTD=y +CONFIG_CRYPTO_AUTHENC=m +# CONFIG_CRYPTO_TEST is not set +CONFIG_CRYPTO_SIMD=y +CONFIG_CRYPTO_ENGINE=m + +# +# Authenticated Encryption with Associated Data +# +CONFIG_CRYPTO_CCM=y +CONFIG_CRYPTO_GCM=m +# CONFIG_CRYPTO_CHACHA20POLY1305 is not set +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m +CONFIG_CRYPTO_SEQIV=y +CONFIG_CRYPTO_ECHAINIV=y + +# +# Block modes +# +CONFIG_CRYPTO_CBC=y +CONFIG_CRYPTO_CFB=m +CONFIG_CRYPTO_CTR=y +CONFIG_CRYPTO_CTS=y +CONFIG_CRYPTO_ECB=y +CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_OFB=m +CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_XTS=y +CONFIG_CRYPTO_KEYWRAP=m +# CONFIG_CRYPTO_ADIANTUM is not set + +# +# Hash modes +# +CONFIG_CRYPTO_CMAC=y +CONFIG_CRYPTO_HMAC=y +CONFIG_CRYPTO_XCBC=m +CONFIG_CRYPTO_VMAC=m + +# +# Digest +# +CONFIG_CRYPTO_CRC32C=y +CONFIG_CRYPTO_CRC32=y +CONFIG_CRYPTO_CRCT10DIF=y +CONFIG_CRYPTO_GHASH=m +CONFIG_CRYPTO_POLY1305=m +CONFIG_CRYPTO_MD4=y +CONFIG_CRYPTO_MD5=y +CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_RMD128=m +CONFIG_CRYPTO_RMD160=m +CONFIG_CRYPTO_RMD256=m +CONFIG_CRYPTO_RMD320=m +CONFIG_CRYPTO_SHA1=y +CONFIG_CRYPTO_SHA256=y +CONFIG_CRYPTO_SHA512=y +CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m +# CONFIG_CRYPTO_STREEBOG is not set +CONFIG_CRYPTO_TGR192=m +CONFIG_CRYPTO_WP512=m + +# +# Ciphers +# +CONFIG_CRYPTO_AES=y +CONFIG_CRYPTO_AES_TI=y +CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_ARC4=y +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_BLOWFISH_COMMON=m +CONFIG_CRYPTO_CAMELLIA=m +CONFIG_CRYPTO_CAST_COMMON=m +CONFIG_CRYPTO_CAST5=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_DES=y +CONFIG_CRYPTO_FCRYPT=m +CONFIG_CRYPTO_KHAZAD=m +CONFIG_CRYPTO_SALSA20=m +CONFIG_CRYPTO_CHACHA20=y +CONFIG_CRYPTO_SEED=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_SM4=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_TWOFISH_COMMON=m + +# +# Compression +# +CONFIG_CRYPTO_DEFLATE=y +CONFIG_CRYPTO_LZO=y +CONFIG_CRYPTO_842=m +CONFIG_CRYPTO_LZ4=m +CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m + +# +# Random Number Generation +# +CONFIG_CRYPTO_ANSI_CPRNG=y +CONFIG_CRYPTO_DRBG_MENU=y +CONFIG_CRYPTO_DRBG_HMAC=y +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y +CONFIG_CRYPTO_DRBG=y +CONFIG_CRYPTO_JITTERENTROPY=y +CONFIG_CRYPTO_USER_API=m +CONFIG_CRYPTO_USER_API_HASH=m +CONFIG_CRYPTO_USER_API_SKCIPHER=m +CONFIG_CRYPTO_USER_API_RNG=m +CONFIG_CRYPTO_USER_API_AEAD=m +# CONFIG_CRYPTO_STATS is not set +CONFIG_CRYPTO_HASH_INFO=y +CONFIG_CRYPTO_HW=y +# CONFIG_CRYPTO_DEV_CCP is not set +CONFIG_CRYPTO_DEV_VIRTIO=m +CONFIG_CRYPTO_DEV_CCREE=m +# CONFIG_CRYPTO_DEV_HISI_SEC is not set +CONFIG_ASYMMETRIC_KEY_TYPE=y +CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y +CONFIG_X509_CERTIFICATE_PARSER=y +# CONFIG_PKCS8_PRIVATE_KEY_PARSER is not set +CONFIG_PKCS7_MESSAGE_PARSER=y +CONFIG_PKCS7_TEST_KEY=m +# CONFIG_SIGNED_PE_FILE_VERIFICATION is not set + +# +# Certificates for signature checking +# +CONFIG_SYSTEM_TRUSTED_KEYRING=y +CONFIG_SYSTEM_TRUSTED_KEYS="" +# CONFIG_SYSTEM_EXTRA_CERTIFICATE is not set +# CONFIG_SECONDARY_TRUSTED_KEYRING is not set +# CONFIG_SYSTEM_BLACKLIST_KEYRING is not set + +# +# Library routines +# +CONFIG_RAID6_PQ=y +# CONFIG_RAID6_PQ_BENCHMARK is not set +CONFIG_BITREVERSE=y +CONFIG_HAVE_ARCH_BITREVERSE=y +CONFIG_RATIONAL=y +CONFIG_GENERIC_STRNCPY_FROM_USER=y +CONFIG_GENERIC_STRNLEN_USER=y +CONFIG_GENERIC_NET_UTILS=y +CONFIG_GENERIC_PCI_IOMAP=y +CONFIG_ARCH_USE_CMPXCHG_LOCKREF=y +CONFIG_ARCH_HAS_FAST_MULTIPLIER=y +CONFIG_INDIRECT_PIO=y +CONFIG_CRC_CCITT=m +CONFIG_CRC16=y +CONFIG_CRC_T10DIF=y +CONFIG_CRC_ITU_T=y +CONFIG_CRC32=y +# CONFIG_CRC32_SELFTEST is not set +CONFIG_CRC32_SLICEBY8=y +# CONFIG_CRC32_SLICEBY4 is not set +# CONFIG_CRC32_SARWATE is not set +# CONFIG_CRC32_BIT is not set +CONFIG_CRC64=m +# CONFIG_CRC4 is not set +CONFIG_CRC7=y +CONFIG_LIBCRC32C=y +CONFIG_CRC8=m +CONFIG_XXHASH=y +CONFIG_AUDIT_GENERIC=y +CONFIG_AUDIT_ARCH_COMPAT_GENERIC=y +CONFIG_AUDIT_COMPAT_GENERIC=y +# CONFIG_RANDOM32_SELFTEST is not set +CONFIG_842_COMPRESS=m +CONFIG_842_DECOMPRESS=m +CONFIG_ZLIB_INFLATE=y +CONFIG_ZLIB_DEFLATE=y +CONFIG_LZO_COMPRESS=y +CONFIG_LZO_DECOMPRESS=y +CONFIG_LZ4_COMPRESS=m +CONFIG_LZ4HC_COMPRESS=m +CONFIG_LZ4_DECOMPRESS=y +CONFIG_ZSTD_COMPRESS=y +CONFIG_ZSTD_DECOMPRESS=y +CONFIG_XZ_DEC=y +CONFIG_XZ_DEC_X86=y +CONFIG_XZ_DEC_POWERPC=y +CONFIG_XZ_DEC_IA64=y +CONFIG_XZ_DEC_ARM=y +CONFIG_XZ_DEC_ARMTHUMB=y +CONFIG_XZ_DEC_SPARC=y +CONFIG_XZ_DEC_BCJ=y +# CONFIG_XZ_DEC_TEST is not set +CONFIG_DECOMPRESS_GZIP=y +CONFIG_DECOMPRESS_BZIP2=y +CONFIG_DECOMPRESS_LZMA=y +CONFIG_DECOMPRESS_XZ=y +CONFIG_DECOMPRESS_LZO=y +CONFIG_DECOMPRESS_LZ4=y +CONFIG_GENERIC_ALLOCATOR=y +CONFIG_TEXTSEARCH=y +CONFIG_TEXTSEARCH_KMP=m +CONFIG_TEXTSEARCH_BM=m +CONFIG_TEXTSEARCH_FSM=m +CONFIG_XARRAY_MULTI=y +CONFIG_ASSOCIATIVE_ARRAY=y +CONFIG_HAS_IOMEM=y +CONFIG_HAS_DMA=y +CONFIG_NEED_SG_DMA_LENGTH=y +CONFIG_NEED_DMA_MAP_STATE=y +CONFIG_ARCH_DMA_ADDR_T_64BIT=y +CONFIG_DMA_DECLARE_COHERENT=y +CONFIG_ARCH_HAS_SETUP_DMA_OPS=y +CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS=y +CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE=y +CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU=y +CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN=y +CONFIG_ARCH_HAS_DMA_MMAP_PGPROT=y +CONFIG_SWIOTLB=y +CONFIG_DMA_REMAP=y +CONFIG_DMA_DIRECT_REMAP=y +CONFIG_DMA_CMA=y + +# +# Default contiguous memory area size: +# +CONFIG_CMA_SIZE_MBYTES=256 +CONFIG_CMA_SIZE_SEL_MBYTES=y +# CONFIG_CMA_SIZE_SEL_PERCENTAGE is not set +# CONFIG_CMA_SIZE_SEL_MIN is not set +# CONFIG_CMA_SIZE_SEL_MAX is not set +CONFIG_CMA_ALIGNMENT=8 +# CONFIG_DMA_API_DEBUG is not set +CONFIG_SGL_ALLOC=y +CONFIG_CPU_RMAP=y +CONFIG_DQL=y +CONFIG_GLOB=y +# CONFIG_GLOB_SELFTEST is not set +CONFIG_NLATTR=y +CONFIG_LRU_CACHE=m +CONFIG_CLZ_TAB=y +CONFIG_CORDIC=m +# CONFIG_DDR is not set +# CONFIG_IRQ_POLL is not set +CONFIG_MPILIB=y +CONFIG_LIBFDT=y +CONFIG_OID_REGISTRY=y +CONFIG_FONT_SUPPORT=y +# CONFIG_FONTS is not set +CONFIG_FONT_8x8=y +CONFIG_FONT_8x16=y +CONFIG_SG_POOL=y +CONFIG_SBITMAP=y +# CONFIG_STRING_SELFTEST is not set + +# +# Kernel hacking +# + +# +# printk and dmesg options +# +CONFIG_PRINTK_TIME=y +# CONFIG_PRINTK_CALLER is not set +CONFIG_CONSOLE_LOGLEVEL_DEFAULT=7 +CONFIG_CONSOLE_LOGLEVEL_QUIET=4 +CONFIG_MESSAGE_LOGLEVEL_DEFAULT=4 +# CONFIG_BOOT_PRINTK_DELAY is not set +CONFIG_DYNAMIC_DEBUG=y + +# +# Compile-time checks and compiler options +# +# CONFIG_DEBUG_INFO is not set +CONFIG_ENABLE_MUST_CHECK=y +CONFIG_FRAME_WARN=2048 +CONFIG_STRIP_ASM_SYMS=y +# CONFIG_READABLE_ASM is not set +# CONFIG_UNUSED_SYMBOLS is not set +CONFIG_DEBUG_FS=y +# CONFIG_HEADERS_CHECK is not set +# CONFIG_DEBUG_SECTION_MISMATCH is not set +CONFIG_SECTION_MISMATCH_WARN_ONLY=y +CONFIG_ARCH_WANT_FRAME_POINTERS=y +CONFIG_FRAME_POINTER=y +# CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set +CONFIG_MAGIC_SYSRQ=y +CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE=0x1 +CONFIG_MAGIC_SYSRQ_SERIAL=y +CONFIG_DEBUG_KERNEL=y + +# +# Memory Debugging +# +# CONFIG_PAGE_EXTENSION is not set +# CONFIG_DEBUG_PAGEALLOC is not set +# CONFIG_PAGE_OWNER is not set +# CONFIG_PAGE_POISONING is not set +# CONFIG_DEBUG_RODATA_TEST is not set +# CONFIG_DEBUG_OBJECTS is not set +# CONFIG_SLUB_DEBUG_ON is not set +# CONFIG_SLUB_STATS is not set +CONFIG_HAVE_DEBUG_KMEMLEAK=y +# CONFIG_DEBUG_KMEMLEAK is not set +# CONFIG_DEBUG_STACK_USAGE is not set +# CONFIG_DEBUG_VM is not set +CONFIG_ARCH_HAS_DEBUG_VIRTUAL=y +# CONFIG_DEBUG_VIRTUAL is not set +# CONFIG_DEBUG_MEMORY_INIT is not set +# CONFIG_DEBUG_PER_CPU_MAPS is not set +CONFIG_HAVE_ARCH_KASAN=y +CONFIG_HAVE_ARCH_KASAN_SW_TAGS=y +CONFIG_CC_HAS_KASAN_GENERIC=y +# CONFIG_KASAN is not set +CONFIG_KASAN_STACK=1 +CONFIG_ARCH_HAS_KCOV=y +CONFIG_CC_HAS_SANCOV_TRACE_PC=y +# CONFIG_KCOV is not set +# CONFIG_DEBUG_SHIRQ is not set + +# +# Debug Lockups and Hangs +# +# CONFIG_SOFTLOCKUP_DETECTOR is not set +CONFIG_DETECT_HUNG_TASK=y +CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=120 +# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set +CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0 +# CONFIG_WQ_WATCHDOG is not set +# CONFIG_PANIC_ON_OOPS is not set +CONFIG_PANIC_ON_OOPS_VALUE=0 +CONFIG_PANIC_TIMEOUT=0 +# CONFIG_SCHED_DEBUG is not set +CONFIG_SCHED_INFO=y +# CONFIG_SCHEDSTATS is not set +# CONFIG_SCHED_STACK_END_CHECK is not set +# CONFIG_DEBUG_TIMEKEEPING is not set +# CONFIG_DEBUG_PREEMPT is not set + +# +# Lock Debugging (spinlocks, mutexes, etc...) +# +CONFIG_LOCK_DEBUGGING_SUPPORT=y +# CONFIG_PROVE_LOCKING is not set +# CONFIG_LOCK_STAT is not set +# CONFIG_DEBUG_RT_MUTEXES is not set +# CONFIG_DEBUG_SPINLOCK is not set +# CONFIG_DEBUG_MUTEXES is not set +# CONFIG_DEBUG_WW_MUTEX_SLOWPATH is not set +# CONFIG_DEBUG_RWSEMS is not set +# CONFIG_DEBUG_LOCK_ALLOC is not set +# CONFIG_DEBUG_ATOMIC_SLEEP is not set +# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set +# CONFIG_LOCK_TORTURE_TEST is not set +# CONFIG_WW_MUTEX_SELFTEST is not set +# CONFIG_STACKTRACE is not set +# CONFIG_WARN_ALL_UNSEEDED_RANDOM is not set +# CONFIG_DEBUG_KOBJECT is not set +CONFIG_HAVE_DEBUG_BUGVERBOSE=y +CONFIG_DEBUG_BUGVERBOSE=y +# CONFIG_DEBUG_LIST is not set +# CONFIG_DEBUG_PI_LIST is not set +# CONFIG_DEBUG_SG is not set +# CONFIG_DEBUG_NOTIFIERS is not set +# CONFIG_DEBUG_CREDENTIALS is not set + +# +# RCU Debugging +# +# CONFIG_RCU_PERF_TEST is not set +# CONFIG_RCU_TORTURE_TEST is not set +CONFIG_RCU_CPU_STALL_TIMEOUT=21 +# CONFIG_RCU_TRACE is not set +# CONFIG_RCU_EQS_DEBUG is not set +# CONFIG_DEBUG_WQ_FORCE_RR_CPU is not set +# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set +# CONFIG_CPU_HOTPLUG_STATE_CONTROL is not set +# CONFIG_NOTIFIER_ERROR_INJECTION is not set +# CONFIG_FAULT_INJECTION is not set +# CONFIG_LATENCYTOP is not set +CONFIG_HAVE_FUNCTION_TRACER=y +CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y +CONFIG_HAVE_DYNAMIC_FTRACE=y +CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y +CONFIG_HAVE_SYSCALL_TRACEPOINTS=y +CONFIG_HAVE_C_RECORDMCOUNT=y +CONFIG_TRACING_SUPPORT=y +# CONFIG_FTRACE is not set +CONFIG_RUNTIME_TESTING_MENU=y +# CONFIG_LKDTM is not set +# CONFIG_TEST_LIST_SORT is not set +# CONFIG_TEST_SORT is not set +# CONFIG_BACKTRACE_SELF_TEST is not set +# CONFIG_RBTREE_TEST is not set +# CONFIG_INTERVAL_TREE_TEST is not set +# CONFIG_PERCPU_TEST is not set +# CONFIG_ATOMIC64_SELFTEST is not set +# CONFIG_ASYNC_RAID6_TEST is not set +# CONFIG_TEST_HEXDUMP is not set +# CONFIG_TEST_STRING_HELPERS is not set +# CONFIG_TEST_KSTRTOX is not set +# CONFIG_TEST_PRINTF is not set +# CONFIG_TEST_BITMAP is not set +# CONFIG_TEST_BITFIELD is not set +# CONFIG_TEST_UUID is not set +# CONFIG_TEST_XARRAY is not set +# CONFIG_TEST_OVERFLOW is not set +# CONFIG_TEST_RHASHTABLE is not set +# CONFIG_TEST_HASH is not set +# CONFIG_TEST_IDA is not set +# CONFIG_TEST_LKM is not set +# CONFIG_TEST_VMALLOC is not set +# CONFIG_TEST_USER_COPY is not set +# CONFIG_TEST_BPF is not set +# CONFIG_FIND_BIT_BENCHMARK is not set +# CONFIG_TEST_FIRMWARE is not set +# CONFIG_TEST_SYSCTL is not set +# CONFIG_TEST_UDELAY is not set +# CONFIG_TEST_STATIC_KEYS is not set +# CONFIG_TEST_KMOD is not set +# CONFIG_TEST_MEMCAT_P is not set +# CONFIG_TEST_STACKINIT is not set +CONFIG_MEMTEST=y +# CONFIG_BUG_ON_DATA_CORRUPTION is not set +# CONFIG_SAMPLES is not set +CONFIG_HAVE_ARCH_KGDB=y +# CONFIG_KGDB is not set +CONFIG_ARCH_HAS_UBSAN_SANITIZE_ALL=y +# CONFIG_UBSAN is not set +CONFIG_UBSAN_ALIGNMENT=y +CONFIG_ARCH_HAS_DEVMEM_IS_ALLOWED=y +# CONFIG_STRICT_DEVMEM is not set +# CONFIG_ARM64_PTDUMP_DEBUGFS is not set +# CONFIG_PID_IN_CONTEXTIDR is not set +# CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET is not set +# CONFIG_DEBUG_WX is not set +# CONFIG_DEBUG_ALIGN_RODATA is not set +# CONFIG_ARM64_RELOC_TEST is not set +# CONFIG_CORESIGHT is not set diff --git a/config/sources/odroidn2.conf b/config/sources/odroidn2.conf index 4a2c56b67a..4a2e84bf48 100644 --- a/config/sources/odroidn2.conf +++ b/config/sources/odroidn2.conf @@ -2,13 +2,13 @@ BOOTSOURCE='https://github.com/hardkernel/u-boot.git' BOOTBRANCH='branch:odroidn2-v2015.01' BOOTDIR='u-boot-odroidn2' UBOOT_USE_GCC='< 4.9' -BOOTSCRIPT="boot-odroid-n2.ini:boot.ini" + UBOOT_TOOLCHAIN2="arm-none-eabi-:< 5.0" UBOOT_COMPILER="aarch64-none-elf-" ARCH=arm64 -SERIALCON=ttyS0 +KERNEL_USE_GCC='> 7.0' UBOOT_TARGET_MAP=';;sd_fuse/u-boot.bin' - +BOOTSCRIPT="boot-odroid-n2.ini:boot.ini" KERNEL_IMAGE_TYPE=Image case $BRANCH in @@ -18,6 +18,20 @@ case $BRANCH in KERNELDIR='linux-odroidn2' KERNEL_COMPILER='aarch64-linux-gnu-' KERNEL_USE_GCC='< 7.0' + SERIALCON=ttyS0 + ;; + next) + SRC_LOADADDR='LOADADDR=0x00208000' + KERNELSOURCE=$MAINLINE_KERNEL_SOURCE + KERNELBRANCH='branch:linux-5.1.y' + KERNELDIR=$MAINLINE_KERNEL_DIR + ;; + dev) + SRC_LOADADDR='LOADADDR=0x00208000' + KERNELDIR='linux-aml-default' + KERNELSOURCE='https://github.com/150balbes/Amlogic_s905-kernel' + KERNELBRANCH='tag:20190514' + LINUXCONFIG="linux-odroidn2-next" ;; esac diff --git a/lib/compilation.sh b/lib/compilation.sh index a81972dd29..7a35cc5c15 100644 --- a/lib/compilation.sh +++ b/lib/compilation.sh @@ -395,6 +395,7 @@ compile_kernel() eval CCACHE_BASEDIR="$(pwd)" env PATH=$toolchain:$PATH \ 'make $CTHREADS ARCH=$ARCHITECTURE \ CROSS_COMPILE="$CCACHE $KERNEL_COMPILER" \ + $SRC_LOADADDR \ LOCALVERSION="-$LINUXFAMILY" \ $KERNEL_IMAGE_TYPE modules dtbs 2>>$DEST/debug/compilation.log' \ ${PROGRESS_LOG_TO_FILE:+' | tee -a $DEST/debug/compilation.log'} \ diff --git a/patch/kernel/odroidn2-default/0001-aufs4.9-20180730.patch b/patch/kernel/odroidn2-default/0001-aufs4.9-20180730.patch new file mode 100644 index 0000000000..a0d3865207 --- /dev/null +++ b/patch/kernel/odroidn2-default/0001-aufs4.9-20180730.patch @@ -0,0 +1,38575 @@ +diff --git a/Documentation/ABI/testing/debugfs-aufs b/Documentation/ABI/testing/debugfs-aufs +new file mode 100644 +index 00000000..4a669419 +--- /dev/null ++++ b/Documentation/ABI/testing/debugfs-aufs +@@ -0,0 +1,55 @@ ++What: /debug/aufs/si_/ ++Date: March 2009 ++Contact: J. R. Okajima ++Description: ++ Under /debug/aufs, a directory named si_ is created ++ per aufs mount, where is a unique id generated ++ internally. ++ ++What: /debug/aufs/si_/plink ++Date: Apr 2013 ++Contact: J. R. Okajima ++Description: ++ It has three lines and shows the information about the ++ pseudo-link. The first line is a single number ++ representing a number of buckets. The second line is a ++ number of pseudo-links per buckets (separated by a ++ blank). The last line is a single number representing a ++ total number of psedo-links. ++ When the aufs mount option 'noplink' is specified, it ++ will show "1\n0\n0\n". ++ ++What: /debug/aufs/si_/xib ++Date: March 2009 ++Contact: J. R. Okajima ++Description: ++ It shows the consumed blocks by xib (External Inode Number ++ Bitmap), its block size and file size. ++ When the aufs mount option 'noxino' is specified, it ++ will be empty. About XINO files, see the aufs manual. ++ ++What: /debug/aufs/si_/xi0, xi1 ... xiN and xiN-N ++Date: March 2009 ++Contact: J. R. Okajima ++Description: ++ It shows the consumed blocks by xino (External Inode Number ++ Translation Table), its link count, block size and file ++ size. ++ Due to the file size limit, there may exist multiple ++ xino files per branch. In this case, "-N" is added to ++ the filename and it corresponds to the index of the ++ internal xino array. "-0" is omitted. ++ When the aufs mount option 'noxino' is specified, Those ++ entries won't exist. About XINO files, see the aufs ++ manual. ++ ++What: /debug/aufs/si_/xigen ++Date: March 2009 ++Contact: J. R. Okajima ++Description: ++ It shows the consumed blocks by xigen (External Inode ++ Generation Table), its block size and file size. ++ If CONFIG_AUFS_EXPORT is disabled, this entry will not ++ be created. ++ When the aufs mount option 'noxino' is specified, it ++ will be empty. About XINO files, see the aufs manual. +diff --git a/Documentation/ABI/testing/sysfs-aufs b/Documentation/ABI/testing/sysfs-aufs +new file mode 100644 +index 00000000..82f95184 +--- /dev/null ++++ b/Documentation/ABI/testing/sysfs-aufs +@@ -0,0 +1,31 @@ ++What: /sys/fs/aufs/si_/ ++Date: March 2009 ++Contact: J. R. Okajima ++Description: ++ Under /sys/fs/aufs, a directory named si_ is created ++ per aufs mount, where is a unique id generated ++ internally. ++ ++What: /sys/fs/aufs/si_/br0, br1 ... brN ++Date: March 2009 ++Contact: J. R. Okajima ++Description: ++ It shows the abolute path of a member directory (which ++ is called branch) in aufs, and its permission. ++ ++What: /sys/fs/aufs/si_/brid0, brid1 ... bridN ++Date: July 2013 ++Contact: J. R. Okajima ++Description: ++ It shows the id of a member directory (which is called ++ branch) in aufs. ++ ++What: /sys/fs/aufs/si_/xi_path ++Date: March 2009 ++Contact: J. R. Okajima ++Description: ++ It shows the abolute path of XINO (External Inode Number ++ Bitmap, Translation Table and Generation Table) file ++ even if it is the default path. ++ When the aufs mount option 'noxino' is specified, it ++ will be empty. About XINO files, see the aufs manual. +diff --git a/Documentation/filesystems/aufs/README b/Documentation/filesystems/aufs/README +new file mode 100644 +index 00000000..013ea14d +--- /dev/null ++++ b/Documentation/filesystems/aufs/README +@@ -0,0 +1,393 @@ ++ ++Aufs4 -- advanced multi layered unification filesystem version 4.x ++http://aufs.sf.net ++Junjiro R. Okajima ++ ++ ++0. Introduction ++---------------------------------------- ++In the early days, aufs was entirely re-designed and re-implemented ++Unionfs Version 1.x series. Adding many original ideas, approaches, ++improvements and implementations, it becomes totally different from ++Unionfs while keeping the basic features. ++Recently, Unionfs Version 2.x series begin taking some of the same ++approaches to aufs1's. ++Unionfs is being developed by Professor Erez Zadok at Stony Brook ++University and his team. ++ ++Aufs4 supports linux-4.0 and later, and for linux-3.x series try aufs3. ++If you want older kernel version support, try aufs2-2.6.git or ++aufs2-standalone.git repository, aufs1 from CVS on SourceForge. ++ ++Note: it becomes clear that "Aufs was rejected. Let's give it up." ++ According to Christoph Hellwig, linux rejects all union-type ++ filesystems but UnionMount. ++ ++ ++PS. Al Viro seems have a plan to merge aufs as well as overlayfs and ++ UnionMount, and he pointed out an issue around a directory mutex ++ lock and aufs addressed it. But it is still unsure whether aufs will ++ be merged (or any other union solution). ++ ++ ++ ++1. Features ++---------------------------------------- ++- unite several directories into a single virtual filesystem. The member ++ directory is called as a branch. ++- you can specify the permission flags to the branch, which are 'readonly', ++ 'readwrite' and 'whiteout-able.' ++- by upper writable branch, internal copyup and whiteout, files/dirs on ++ readonly branch are modifiable logically. ++- dynamic branch manipulation, add, del. ++- etc... ++ ++Also there are many enhancements in aufs, such as: ++- test only the highest one for the directory permission (dirperm1) ++- copyup on open (coo=) ++- 'move' policy for copy-up between two writable branches, after ++ checking free space. ++- xattr, acl ++- readdir(3) in userspace. ++- keep inode number by external inode number table ++- keep the timestamps of file/dir in internal copyup operation ++- seekable directory, supporting NFS readdir. ++- whiteout is hardlinked in order to reduce the consumption of inodes ++ on branch ++- do not copyup, nor create a whiteout when it is unnecessary ++- revert a single systemcall when an error occurs in aufs ++- remount interface instead of ioctl ++- maintain /etc/mtab by an external command, /sbin/mount.aufs. ++- loopback mounted filesystem as a branch ++- kernel thread for removing the dir who has a plenty of whiteouts ++- support copyup sparse file (a file which has a 'hole' in it) ++- default permission flags for branches ++- selectable permission flags for ro branch, whether whiteout can ++ exist or not ++- export via NFS. ++- support /fs/aufs and /aufs. ++- support multiple writable branches, some policies to select one ++ among multiple writable branches. ++- a new semantics for link(2) and rename(2) to support multiple ++ writable branches. ++- no glibc changes are required. ++- pseudo hardlink (hardlink over branches) ++- allow a direct access manually to a file on branch, e.g. bypassing aufs. ++ including NFS or remote filesystem branch. ++- userspace wrapper for pathconf(3)/fpathconf(3) with _PC_LINK_MAX. ++- and more... ++ ++Currently these features are dropped temporary from aufs4. ++See design/08plan.txt in detail. ++- nested mount, i.e. aufs as readonly no-whiteout branch of another aufs ++ (robr) ++- statistics of aufs thread (/sys/fs/aufs/stat) ++ ++Features or just an idea in the future (see also design/*.txt), ++- reorder the branch index without del/re-add. ++- permanent xino files for NFSD ++- an option for refreshing the opened files after add/del branches ++- light version, without branch manipulation. (unnecessary?) ++- copyup in userspace ++- inotify in userspace ++- readv/writev ++ ++ ++2. Download ++---------------------------------------- ++There are three GIT trees for aufs4, aufs4-linux.git, ++aufs4-standalone.git, and aufs-util.git. Note that there is no "4" in ++"aufs-util.git." ++While the aufs-util is always necessary, you need either of aufs4-linux ++or aufs4-standalone. ++ ++The aufs4-linux tree includes the whole linux mainline GIT tree, ++git://git.kernel.org/.../torvalds/linux.git. ++And you cannot select CONFIG_AUFS_FS=m for this version, eg. you cannot ++build aufs4 as an external kernel module. ++Several extra patches are not included in this tree. Only ++aufs4-standalone tree contains them. They are described in the later ++section "Configuration and Compilation." ++ ++On the other hand, the aufs4-standalone tree has only aufs source files ++and necessary patches, and you can select CONFIG_AUFS_FS=m. ++But you need to apply all aufs patches manually. ++ ++You will find GIT branches whose name is in form of "aufs4.x" where "x" ++represents the linux kernel version, "linux-4.x". For instance, ++"aufs4.0" is for linux-4.0. For latest "linux-4.x-rcN", use ++"aufs4.x-rcN" branch. ++ ++o aufs4-linux tree ++$ git clone --reference /your/linux/git/tree \ ++ git://github.com/sfjro/aufs4-linux.git aufs4-linux.git ++- if you don't have linux GIT tree, then remove "--reference ..." ++$ cd aufs4-linux.git ++$ git checkout origin/aufs4.0 ++ ++Or You may want to directly git-pull aufs into your linux GIT tree, and ++leave the patch-work to GIT. ++$ cd /your/linux/git/tree ++$ git remote add aufs4 git://github.com/sfjro/aufs4-linux.git ++$ git fetch aufs4 ++$ git checkout -b my4.0 v4.0 ++$ (add your local change...) ++$ git pull aufs4 aufs4.0 ++- now you have v4.0 + your_changes + aufs4.0 in you my4.0 branch. ++- you may need to solve some conflicts between your_changes and ++ aufs4.0. in this case, git-rerere is recommended so that you can ++ solve the similar conflicts automatically when you upgrade to 4.1 or ++ later in the future. ++ ++o aufs4-standalone tree ++$ git clone git://github.com/sfjro/aufs4-standalone.git aufs4-standalone.git ++$ cd aufs4-standalone.git ++$ git checkout origin/aufs4.0 ++ ++o aufs-util tree ++$ git clone git://git.code.sf.net/p/aufs/aufs-util aufs-util.git ++- note that the public aufs-util.git is on SourceForge instead of ++ GitHUB. ++$ cd aufs-util.git ++$ git checkout origin/aufs4.0 ++ ++Note: The 4.x-rcN branch is to be used with `rc' kernel versions ONLY. ++The minor version number, 'x' in '4.x', of aufs may not always ++follow the minor version number of the kernel. ++Because changes in the kernel that cause the use of a new ++minor version number do not always require changes to aufs-util. ++ ++Since aufs-util has its own minor version number, you may not be ++able to find a GIT branch in aufs-util for your kernel's ++exact minor version number. ++In this case, you should git-checkout the branch for the ++nearest lower number. ++ ++For (an unreleased) example: ++If you are using "linux-4.10" and the "aufs4.10" branch ++does not exist in aufs-util repository, then "aufs4.9", "aufs4.8" ++or something numerically smaller is the branch for your kernel. ++ ++Also you can view all branches by ++ $ git branch -a ++ ++ ++3. Configuration and Compilation ++---------------------------------------- ++Make sure you have git-checkout'ed the correct branch. ++ ++For aufs4-linux tree, ++- enable CONFIG_AUFS_FS. ++- set other aufs configurations if necessary. ++ ++For aufs4-standalone tree, ++There are several ways to build. ++ ++1. ++- apply ./aufs4-kbuild.patch to your kernel source files. ++- apply ./aufs4-base.patch too. ++- apply ./aufs4-mmap.patch too. ++- apply ./aufs4-standalone.patch too, if you have a plan to set ++ CONFIG_AUFS_FS=m. otherwise you don't need ./aufs4-standalone.patch. ++- copy ./{Documentation,fs,include/uapi/linux/aufs_type.h} files to your ++ kernel source tree. Never copy $PWD/include/uapi/linux/Kbuild. ++- enable CONFIG_AUFS_FS, you can select either ++ =m or =y. ++- and build your kernel as usual. ++- install the built kernel. ++ Note: Since linux-3.9, every filesystem module requires an alias ++ "fs-". You should make sure that "fs-aufs" is listed in your ++ modules.aliases file if you set CONFIG_AUFS_FS=m. ++- install the header files too by "make headers_install" to the ++ directory where you specify. By default, it is $PWD/usr. ++ "make help" shows a brief note for headers_install. ++- and reboot your system. ++ ++2. ++- module only (CONFIG_AUFS_FS=m). ++- apply ./aufs4-base.patch to your kernel source files. ++- apply ./aufs4-mmap.patch too. ++- apply ./aufs4-standalone.patch too. ++- build your kernel, don't forget "make headers_install", and reboot. ++- edit ./config.mk and set other aufs configurations if necessary. ++ Note: You should read $PWD/fs/aufs/Kconfig carefully which describes ++ every aufs configurations. ++- build the module by simple "make". ++ Note: Since linux-3.9, every filesystem module requires an alias ++ "fs-". You should make sure that "fs-aufs" is listed in your ++ modules.aliases file. ++- you can specify ${KDIR} make variable which points to your kernel ++ source tree. ++- install the files ++ + run "make install" to install the aufs module, or copy the built ++ $PWD/aufs.ko to /lib/modules/... and run depmod -a (or reboot simply). ++ + run "make install_headers" (instead of headers_install) to install ++ the modified aufs header file (you can specify DESTDIR which is ++ available in aufs standalone version's Makefile only), or copy ++ $PWD/usr/include/linux/aufs_type.h to /usr/include/linux or wherever ++ you like manually. By default, the target directory is $PWD/usr. ++- no need to apply aufs4-kbuild.patch, nor copying source files to your ++ kernel source tree. ++ ++Note: The header file aufs_type.h is necessary to build aufs-util ++ as well as "make headers_install" in the kernel source tree. ++ headers_install is subject to be forgotten, but it is essentially ++ necessary, not only for building aufs-util. ++ You may not meet problems without headers_install in some older ++ version though. ++ ++And then, ++- read README in aufs-util, build and install it ++- note that your distribution may contain an obsoleted version of ++ aufs_type.h in /usr/include/linux or something. When you build aufs ++ utilities, make sure that your compiler refers the correct aufs header ++ file which is built by "make headers_install." ++- if you want to use readdir(3) in userspace or pathconf(3) wrapper, ++ then run "make install_ulib" too. And refer to the aufs manual in ++ detail. ++ ++There several other patches in aufs4-standalone.git. They are all ++optional. When you meet some problems, they will help you. ++- aufs4-loopback.patch ++ Supports a nested loopback mount in a branch-fs. This patch is ++ unnecessary until aufs produces a message like "you may want to try ++ another patch for loopback file". ++- vfs-ino.patch ++ Modifies a system global kernel internal function get_next_ino() in ++ order to stop assigning 0 for an inode-number. Not directly related to ++ aufs, but recommended generally. ++- tmpfs-idr.patch ++ Keeps the tmpfs inode number as the lowest value. Effective to reduce ++ the size of aufs XINO files for tmpfs branch. Also it prevents the ++ duplication of inode number, which is important for backup tools and ++ other utilities. When you find aufs XINO files for tmpfs branch ++ growing too much, try this patch. ++- lockdep-debug.patch ++ Because aufs is not only an ordinary filesystem (callee of VFS), but ++ also a caller of VFS functions for branch filesystems, subclassing of ++ the internal locks for LOCKDEP is necessary. LOCKDEP is a debugging ++ feature of linux kernel. If you enable CONFIG_LOCKDEP, then you will ++ need to apply this debug patch to expand several constant values. ++ If don't know what LOCKDEP, then you don't have apply this patch. ++ ++ ++4. Usage ++---------------------------------------- ++At first, make sure aufs-util are installed, and please read the aufs ++manual, aufs.5 in aufs-util.git tree. ++$ man -l aufs.5 ++ ++And then, ++$ mkdir /tmp/rw /tmp/aufs ++# mount -t aufs -o br=/tmp/rw:${HOME} none /tmp/aufs ++ ++Here is another example. The result is equivalent. ++# mount -t aufs -o br=/tmp/rw=rw:${HOME}=ro none /tmp/aufs ++ Or ++# mount -t aufs -o br:/tmp/rw none /tmp/aufs ++# mount -o remount,append:${HOME} /tmp/aufs ++ ++Then, you can see whole tree of your home dir through /tmp/aufs. If ++you modify a file under /tmp/aufs, the one on your home directory is ++not affected, instead the same named file will be newly created under ++/tmp/rw. And all of your modification to a file will be applied to ++the one under /tmp/rw. This is called the file based Copy on Write ++(COW) method. ++Aufs mount options are described in aufs.5. ++If you run chroot or something and make your aufs as a root directory, ++then you need to customize the shutdown script. See the aufs manual in ++detail. ++ ++Additionally, there are some sample usages of aufs which are a ++diskless system with network booting, and LiveCD over NFS. ++See sample dir in CVS tree on SourceForge. ++ ++ ++5. Contact ++---------------------------------------- ++When you have any problems or strange behaviour in aufs, please let me ++know with: ++- /proc/mounts (instead of the output of mount(8)) ++- /sys/module/aufs/* ++- /sys/fs/aufs/* (if you have them) ++- /debug/aufs/* (if you have them) ++- linux kernel version ++ if your kernel is not plain, for example modified by distributor, ++ the url where i can download its source is necessary too. ++- aufs version which was printed at loading the module or booting the ++ system, instead of the date you downloaded. ++- configuration (define/undefine CONFIG_AUFS_xxx) ++- kernel configuration or /proc/config.gz (if you have it) ++- behaviour which you think to be incorrect ++- actual operation, reproducible one is better ++- mailto: aufs-users at lists.sourceforge.net ++ ++Usually, I don't watch the Public Areas(Bugs, Support Requests, Patches, ++and Feature Requests) on SourceForge. Please join and write to ++aufs-users ML. ++ ++ ++6. Acknowledgements ++---------------------------------------- ++Thanks to everyone who have tried and are using aufs, whoever ++have reported a bug or any feedback. ++ ++Especially donators: ++Tomas Matejicek(slax.org) made a donation (much more than once). ++ Since Apr 2010, Tomas M (the author of Slax and Linux Live ++ scripts) is making "doubling" donations. ++ Unfortunately I cannot list all of the donators, but I really ++ appreciate. ++ It ends Aug 2010, but the ordinary donation URL is still available. ++ ++Dai Itasaka made a donation (2007/8). ++Chuck Smith made a donation (2008/4, 10 and 12). ++Henk Schoneveld made a donation (2008/9). ++Chih-Wei Huang, ASUS, CTC donated Eee PC 4G (2008/10). ++Francois Dupoux made a donation (2008/11). ++Bruno Cesar Ribas and Luis Carlos Erpen de Bona, C3SL serves public ++ aufs2 GIT tree (2009/2). ++William Grant made a donation (2009/3). ++Patrick Lane made a donation (2009/4). ++The Mail Archive (mail-archive.com) made donations (2009/5). ++Nippy Networks (Ed Wildgoose) made a donation (2009/7). ++New Dream Network, LLC (www.dreamhost.com) made a donation (2009/11). ++Pavel Pronskiy made a donation (2011/2). ++Iridium and Inmarsat satellite phone retailer (www.mailasail.com), Nippy ++ Networks (Ed Wildgoose) made a donation for hardware (2011/3). ++Max Lekomcev (DOM-TV project) made a donation (2011/7, 12, 2012/3, 6 and ++11). ++Sam Liddicott made a donation (2011/9). ++Era Scarecrow made a donation (2013/4). ++Bor Ratajc made a donation (2013/4). ++Alessandro Gorreta made a donation (2013/4). ++POIRETTE Marc made a donation (2013/4). ++Alessandro Gorreta made a donation (2013/4). ++lauri kasvandik made a donation (2013/5). ++"pemasu from Finland" made a donation (2013/7). ++The Parted Magic Project made a donation (2013/9 and 11). ++Pavel Barta made a donation (2013/10). ++Nikolay Pertsev made a donation (2014/5). ++James B made a donation (2014/7 and 2015/7). ++Stefano Di Biase made a donation (2014/8). ++Daniel Epellei made a donation (2015/1). ++OmegaPhil made a donation (2016/1, 2018/4). ++Tomasz Szewczyk made a donation (2016/4). ++James Burry made a donation (2016/12). ++ ++Thank you very much. ++Donations are always, including future donations, very important and ++helpful for me to keep on developing aufs. ++ ++ ++7. ++---------------------------------------- ++If you are an experienced user, no explanation is needed. Aufs is ++just a linux filesystem. ++ ++ ++Enjoy! ++ ++# Local variables: ; ++# mode: text; ++# End: ; +diff --git a/Documentation/filesystems/aufs/design/01intro.txt b/Documentation/filesystems/aufs/design/01intro.txt +new file mode 100644 +index 00000000..aa105298 +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/01intro.txt +@@ -0,0 +1,171 @@ ++ ++# Copyright (C) 2005-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++Introduction ++---------------------------------------- ++ ++aufs [ei ju: ef es] | /ey-yoo-ef-es/ | [a u f s] ++1. abbrev. for "advanced multi-layered unification filesystem". ++2. abbrev. for "another unionfs". ++3. abbrev. for "auf das" in German which means "on the" in English. ++ Ex. "Butter aufs Brot"(G) means "butter onto bread"(E). ++ But "Filesystem aufs Filesystem" is hard to understand. ++4. abbrev. for "African Urban Fashion Show". ++ ++AUFS is a filesystem with features: ++- multi layered stackable unification filesystem, the member directory ++ is called as a branch. ++- branch permission and attribute, 'readonly', 'real-readonly', ++ 'readwrite', 'whiteout-able', 'link-able whiteout', etc. and their ++ combination. ++- internal "file copy-on-write". ++- logical deletion, whiteout. ++- dynamic branch manipulation, adding, deleting and changing permission. ++- allow bypassing aufs, user's direct branch access. ++- external inode number translation table and bitmap which maintains the ++ persistent aufs inode number. ++- seekable directory, including NFS readdir. ++- file mapping, mmap and sharing pages. ++- pseudo-link, hardlink over branches. ++- loopback mounted filesystem as a branch. ++- several policies to select one among multiple writable branches. ++- revert a single systemcall when an error occurs in aufs. ++- and more... ++ ++ ++Multi Layered Stackable Unification Filesystem ++---------------------------------------------------------------------- ++Most people already knows what it is. ++It is a filesystem which unifies several directories and provides a ++merged single directory. When users access a file, the access will be ++passed/re-directed/converted (sorry, I am not sure which English word is ++correct) to the real file on the member filesystem. The member ++filesystem is called 'lower filesystem' or 'branch' and has a mode ++'readonly' and 'readwrite.' And the deletion for a file on the lower ++readonly branch is handled by creating 'whiteout' on the upper writable ++branch. ++ ++On LKML, there have been discussions about UnionMount (Jan Blunck, ++Bharata B Rao and Valerie Aurora) and Unionfs (Erez Zadok). They took ++different approaches to implement the merged-view. ++The former tries putting it into VFS, and the latter implements as a ++separate filesystem. ++(If I misunderstand about these implementations, please let me know and ++I shall correct it. Because it is a long time ago when I read their ++source files last time). ++ ++UnionMount's approach will be able to small, but may be hard to share ++branches between several UnionMount since the whiteout in it is ++implemented in the inode on branch filesystem and always ++shared. According to Bharata's post, readdir does not seems to be ++finished yet. ++There are several missing features known in this implementations such as ++- for users, the inode number may change silently. eg. copy-up. ++- link(2) may break by copy-up. ++- read(2) may get an obsoleted filedata (fstat(2) too). ++- fcntl(F_SETLK) may be broken by copy-up. ++- unnecessary copy-up may happen, for example mmap(MAP_PRIVATE) after ++ open(O_RDWR). ++ ++In linux-3.18, "overlay" filesystem (formerly known as "overlayfs") was ++merged into mainline. This is another implementation of UnionMount as a ++separated filesystem. All the limitations and known problems which ++UnionMount are equally inherited to "overlay" filesystem. ++ ++Unionfs has a longer history. When I started implementing a stackable ++filesystem (Aug 2005), it already existed. It has virtual super_block, ++inode, dentry and file objects and they have an array pointing lower ++same kind objects. After contributing many patches for Unionfs, I ++re-started my project AUFS (Jun 2006). ++ ++In AUFS, the structure of filesystem resembles to Unionfs, but I ++implemented my own ideas, approaches and enhancements and it became ++totally different one. ++ ++Comparing DM snapshot and fs based implementation ++- the number of bytes to be copied between devices is much smaller. ++- the type of filesystem must be one and only. ++- the fs must be writable, no readonly fs, even for the lower original ++ device. so the compression fs will not be usable. but if we use ++ loopback mount, we may address this issue. ++ for instance, ++ mount /cdrom/squashfs.img /sq ++ losetup /sq/ext2.img ++ losetup /somewhere/cow ++ dmsetup "snapshot /dev/loop0 /dev/loop1 ..." ++- it will be difficult (or needs more operations) to extract the ++ difference between the original device and COW. ++- DM snapshot-merge may help a lot when users try merging. in the ++ fs-layer union, users will use rsync(1). ++ ++You may want to read my old paper "Filesystems in LiveCD" ++(http://aufs.sourceforge.net/aufs2/report/sq/sq.pdf). ++ ++ ++Several characters/aspects/persona of aufs ++---------------------------------------------------------------------- ++ ++Aufs has several characters, aspects or persona. ++1. a filesystem, callee of VFS helper ++2. sub-VFS, caller of VFS helper for branches ++3. a virtual filesystem which maintains persistent inode number ++4. reader/writer of files on branches such like an application ++ ++1. Callee of VFS Helper ++As an ordinary linux filesystem, aufs is a callee of VFS. For instance, ++unlink(2) from an application reaches sys_unlink() kernel function and ++then vfs_unlink() is called. vfs_unlink() is one of VFS helper and it ++calls filesystem specific unlink operation. Actually aufs implements the ++unlink operation but it behaves like a redirector. ++ ++2. Caller of VFS Helper for Branches ++aufs_unlink() passes the unlink request to the branch filesystem as if ++it were called from VFS. So the called unlink operation of the branch ++filesystem acts as usual. As a caller of VFS helper, aufs should handle ++every necessary pre/post operation for the branch filesystem. ++- acquire the lock for the parent dir on a branch ++- lookup in a branch ++- revalidate dentry on a branch ++- mnt_want_write() for a branch ++- vfs_unlink() for a branch ++- mnt_drop_write() for a branch ++- release the lock on a branch ++ ++3. Persistent Inode Number ++One of the most important issue for a filesystem is to maintain inode ++numbers. This is particularly important to support exporting a ++filesystem via NFS. Aufs is a virtual filesystem which doesn't have a ++backend block device for its own. But some storage is necessary to ++keep and maintain the inode numbers. It may be a large space and may not ++suit to keep in memory. Aufs rents some space from its first writable ++branch filesystem (by default) and creates file(s) on it. These files ++are created by aufs internally and removed soon (currently) keeping ++opened. ++Note: Because these files are removed, they are totally gone after ++ unmounting aufs. It means the inode numbers are not persistent ++ across unmount or reboot. I have a plan to make them really ++ persistent which will be important for aufs on NFS server. ++ ++4. Read/Write Files Internally (copy-on-write) ++Because a branch can be readonly, when you write a file on it, aufs will ++"copy-up" it to the upper writable branch internally. And then write the ++originally requested thing to the file. Generally kernel doesn't ++open/read/write file actively. In aufs, even a single write may cause a ++internal "file copy". This behaviour is very similar to cp(1) command. ++ ++Some people may think it is better to pass such work to user space ++helper, instead of doing in kernel space. Actually I am still thinking ++about it. But currently I have implemented it in kernel space. +diff --git a/Documentation/filesystems/aufs/design/02struct.txt b/Documentation/filesystems/aufs/design/02struct.txt +new file mode 100644 +index 00000000..f5fb6a8a +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/02struct.txt +@@ -0,0 +1,258 @@ ++ ++# Copyright (C) 2005-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++Basic Aufs Internal Structure ++ ++Superblock/Inode/Dentry/File Objects ++---------------------------------------------------------------------- ++As like an ordinary filesystem, aufs has its own ++superblock/inode/dentry/file objects. All these objects have a ++dynamically allocated array and store the same kind of pointers to the ++lower filesystem, branch. ++For example, when you build a union with one readwrite branch and one ++readonly, mounted /au, /rw and /ro respectively. ++- /au = /rw + /ro ++- /ro/fileA exists but /rw/fileA ++ ++Aufs lookup operation finds /ro/fileA and gets dentry for that. These ++pointers are stored in a aufs dentry. The array in aufs dentry will be, ++- [0] = NULL (because /rw/fileA doesn't exist) ++- [1] = /ro/fileA ++ ++This style of an array is essentially same to the aufs ++superblock/inode/dentry/file objects. ++ ++Because aufs supports manipulating branches, ie. add/delete/change ++branches dynamically, these objects has its own generation. When ++branches are changed, the generation in aufs superblock is ++incremented. And a generation in other object are compared when it is ++accessed. When a generation in other objects are obsoleted, aufs ++refreshes the internal array. ++ ++ ++Superblock ++---------------------------------------------------------------------- ++Additionally aufs superblock has some data for policies to select one ++among multiple writable branches, XIB files, pseudo-links and kobject. ++See below in detail. ++About the policies which supports copy-down a directory, see ++wbr_policy.txt too. ++ ++ ++Branch and XINO(External Inode Number Translation Table) ++---------------------------------------------------------------------- ++Every branch has its own xino (external inode number translation table) ++file. The xino file is created and unlinked by aufs internally. When two ++members of a union exist on the same filesystem, they share the single ++xino file. ++The struct of a xino file is simple, just a sequence of aufs inode ++numbers which is indexed by the lower inode number. ++In the above sample, assume the inode number of /ro/fileA is i111 and ++aufs assigns the inode number i999 for fileA. Then aufs writes 999 as ++4(8) bytes at 111 * 4(8) bytes offset in the xino file. ++ ++When the inode numbers are not contiguous, the xino file will be sparse ++which has a hole in it and doesn't consume as much disk space as it ++might appear. If your branch filesystem consumes disk space for such ++holes, then you should specify 'xino=' option at mounting aufs. ++ ++Aufs has a mount option to free the disk blocks for such holes in XINO ++files on tmpfs or ramdisk. But it is not so effective actually. If you ++meet a problem of disk shortage due to XINO files, then you should try ++"tmpfs-ino.patch" (and "vfs-ino.patch" too) in aufs4-standalone.git. ++The patch localizes the assignment inumbers per tmpfs-mount and avoid ++the holes in XINO files. ++ ++Also a writable branch has three kinds of "whiteout bases". All these ++are existed when the branch is joined to aufs, and their names are ++whiteout-ed doubly, so that users will never see their names in aufs ++hierarchy. ++1. a regular file which will be hardlinked to all whiteouts. ++2. a directory to store a pseudo-link. ++3. a directory to store an "orphan"-ed file temporary. ++ ++1. Whiteout Base ++ When you remove a file on a readonly branch, aufs handles it as a ++ logical deletion and creates a whiteout on the upper writable branch ++ as a hardlink of this file in order not to consume inode on the ++ writable branch. ++2. Pseudo-link Dir ++ See below, Pseudo-link. ++3. Step-Parent Dir ++ When "fileC" exists on the lower readonly branch only and it is ++ opened and removed with its parent dir, and then user writes ++ something into it, then aufs copies-up fileC to this ++ directory. Because there is no other dir to store fileC. After ++ creating a file under this dir, the file is unlinked. ++ ++Because aufs supports manipulating branches, ie. add/delete/change ++dynamically, a branch has its own id. When the branch order changes, ++aufs finds the new index by searching the branch id. ++ ++ ++Pseudo-link ++---------------------------------------------------------------------- ++Assume "fileA" exists on the lower readonly branch only and it is ++hardlinked to "fileB" on the branch. When you write something to fileA, ++aufs copies-up it to the upper writable branch. Additionally aufs ++creates a hardlink under the Pseudo-link Directory of the writable ++branch. The inode of a pseudo-link is kept in aufs super_block as a ++simple list. If fileB is read after unlinking fileA, aufs returns ++filedata from the pseudo-link instead of the lower readonly ++branch. Because the pseudo-link is based upon the inode, to keep the ++inode number by xino (see above) is essentially necessary. ++ ++All the hardlinks under the Pseudo-link Directory of the writable branch ++should be restored in a proper location later. Aufs provides a utility ++to do this. The userspace helpers executed at remounting and unmounting ++aufs by default. ++During this utility is running, it puts aufs into the pseudo-link ++maintenance mode. In this mode, only the process which began the ++maintenance mode (and its child processes) is allowed to operate in ++aufs. Some other processes which are not related to the pseudo-link will ++be allowed to run too, but the rest have to return an error or wait ++until the maintenance mode ends. If a process already acquires an inode ++mutex (in VFS), it has to return an error. ++ ++ ++XIB(external inode number bitmap) ++---------------------------------------------------------------------- ++Addition to the xino file per a branch, aufs has an external inode number ++bitmap in a superblock object. It is also an internal file such like a ++xino file. ++It is a simple bitmap to mark whether the aufs inode number is in-use or ++not. ++To reduce the file I/O, aufs prepares a single memory page to cache xib. ++ ++As well as XINO files, aufs has a feature to truncate/refresh XIB to ++reduce the number of consumed disk blocks for these files. ++ ++ ++Virtual or Vertical Dir, and Readdir in Userspace ++---------------------------------------------------------------------- ++In order to support multiple layers (branches), aufs readdir operation ++constructs a virtual dir block on memory. For readdir, aufs calls ++vfs_readdir() internally for each dir on branches, merges their entries ++with eliminating the whiteout-ed ones, and sets it to file (dir) ++object. So the file object has its entry list until it is closed. The ++entry list will be updated when the file position is zero and becomes ++obsoleted. This decision is made in aufs automatically. ++ ++The dynamically allocated memory block for the name of entries has a ++unit of 512 bytes (by default) and stores the names contiguously (no ++padding). Another block for each entry is handled by kmem_cache too. ++During building dir blocks, aufs creates hash list and judging whether ++the entry is whiteouted by its upper branch or already listed. ++The merged result is cached in the corresponding inode object and ++maintained by a customizable life-time option. ++ ++Some people may call it can be a security hole or invite DoS attack ++since the opened and once readdir-ed dir (file object) holds its entry ++list and becomes a pressure for system memory. But I'd say it is similar ++to files under /proc or /sys. The virtual files in them also holds a ++memory page (generally) while they are opened. When an idea to reduce ++memory for them is introduced, it will be applied to aufs too. ++For those who really hate this situation, I've developed readdir(3) ++library which operates this merging in userspace. You just need to set ++LD_PRELOAD environment variable, and aufs will not consume no memory in ++kernel space for readdir(3). ++ ++ ++Workqueue ++---------------------------------------------------------------------- ++Aufs sometimes requires privilege access to a branch. For instance, ++in copy-up/down operation. When a user process is going to make changes ++to a file which exists in the lower readonly branch only, and the mode ++of one of ancestor directories may not be writable by a user ++process. Here aufs copy-up the file with its ancestors and they may ++require privilege to set its owner/group/mode/etc. ++This is a typical case of a application character of aufs (see ++Introduction). ++ ++Aufs uses workqueue synchronously for this case. It creates its own ++workqueue. The workqueue is a kernel thread and has privilege. Aufs ++passes the request to call mkdir or write (for example), and wait for ++its completion. This approach solves a problem of a signal handler ++simply. ++If aufs didn't adopt the workqueue and changed the privilege of the ++process, then the process may receive the unexpected SIGXFSZ or other ++signals. ++ ++Also aufs uses the system global workqueue ("events" kernel thread) too ++for asynchronous tasks, such like handling inotify/fsnotify, re-creating a ++whiteout base and etc. This is unrelated to a privilege. ++Most of aufs operation tries acquiring a rw_semaphore for aufs ++superblock at the beginning, at the same time waits for the completion ++of all queued asynchronous tasks. ++ ++ ++Whiteout ++---------------------------------------------------------------------- ++The whiteout in aufs is very similar to Unionfs's. That is represented ++by its filename. UnionMount takes an approach of a file mode, but I am ++afraid several utilities (find(1) or something) will have to support it. ++ ++Basically the whiteout represents "logical deletion" which stops aufs to ++lookup further, but also it represents "dir is opaque" which also stop ++further lookup. ++ ++In aufs, rmdir(2) and rename(2) for dir uses whiteout alternatively. ++In order to make several functions in a single systemcall to be ++revertible, aufs adopts an approach to rename a directory to a temporary ++unique whiteouted name. ++For example, in rename(2) dir where the target dir already existed, aufs ++renames the target dir to a temporary unique whiteouted name before the ++actual rename on a branch, and then handles other actions (make it opaque, ++update the attributes, etc). If an error happens in these actions, aufs ++simply renames the whiteouted name back and returns an error. If all are ++succeeded, aufs registers a function to remove the whiteouted unique ++temporary name completely and asynchronously to the system global ++workqueue. ++ ++ ++Copy-up ++---------------------------------------------------------------------- ++It is a well-known feature or concept. ++When user modifies a file on a readonly branch, aufs operate "copy-up" ++internally and makes change to the new file on the upper writable branch. ++When the trigger systemcall does not update the timestamps of the parent ++dir, aufs reverts it after copy-up. ++ ++ ++Move-down (aufs3.9 and later) ++---------------------------------------------------------------------- ++"Copy-up" is one of the essential feature in aufs. It copies a file from ++the lower readonly branch to the upper writable branch when a user ++changes something about the file. ++"Move-down" is an opposite action of copy-up. Basically this action is ++ran manually instead of automatically and internally. ++For desgin and implementation, aufs has to consider these issues. ++- whiteout for the file may exist on the lower branch. ++- ancestor directories may not exist on the lower branch. ++- diropq for the ancestor directories may exist on the upper branch. ++- free space on the lower branch will reduce. ++- another access to the file may happen during moving-down, including ++ UDBA (see "Revalidate Dentry and UDBA"). ++- the file should not be hard-linked nor pseudo-linked. they should be ++ handled by auplink utility later. ++ ++Sometimes users want to move-down a file from the upper writable branch ++to the lower readonly or writable branch. For instance, ++- the free space of the upper writable branch is going to run out. ++- create a new intermediate branch between the upper and lower branch. ++- etc. ++ ++For this purpose, use "aumvdown" command in aufs-util.git. +diff --git a/Documentation/filesystems/aufs/design/03atomic_open.txt b/Documentation/filesystems/aufs/design/03atomic_open.txt +new file mode 100644 +index 00000000..1b0699f8 +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/03atomic_open.txt +@@ -0,0 +1,85 @@ ++ ++# Copyright (C) 2015-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++Support for a branch who has its ->atomic_open() ++---------------------------------------------------------------------- ++The filesystems who implement its ->atomic_open() are not majority. For ++example NFSv4 does, and aufs should call NFSv4 ->atomic_open, ++particularly for open(O_CREAT|O_EXCL, 0400) case. Other than ++->atomic_open(), NFSv4 returns an error for this open(2). While I am not ++sure whether all filesystems who have ->atomic_open() behave like this, ++but NFSv4 surely returns the error. ++ ++In order to support ->atomic_open() for aufs, there are a few ++approaches. ++ ++A. Introduce aufs_atomic_open() ++ - calls one of VFS:do_last(), lookup_open() or atomic_open() for ++ branch fs. ++B. Introduce aufs_atomic_open() calling create, open and chmod. this is ++ an aufs user Pip Cet's approach ++ - calls aufs_create(), VFS finish_open() and notify_change(). ++ - pass fake-mode to finish_open(), and then correct the mode by ++ notify_change(). ++C. Extend aufs_open() to call branch fs's ->atomic_open() ++ - no aufs_atomic_open(). ++ - aufs_lookup() registers the TID to an aufs internal object. ++ - aufs_create() does nothing when the matching TID is registered, but ++ registers the mode. ++ - aufs_open() calls branch fs's ->atomic_open() when the matching ++ TID is registered. ++D. Extend aufs_open() to re-try branch fs's ->open() with superuser's ++ credential ++ - no aufs_atomic_open(). ++ - aufs_create() registers the TID to an internal object. this info ++ represents "this process created this file just now." ++ - when aufs gets EACCES from branch fs's ->open(), then confirm the ++ registered TID and re-try open() with superuser's credential. ++ ++Pros and cons for each approach. ++ ++A. ++ - straightforward but highly depends upon VFS internal. ++ - the atomic behavaiour is kept. ++ - some of parameters such as nameidata are hard to reproduce for ++ branch fs. ++ - large overhead. ++B. ++ - easy to implement. ++ - the atomic behavaiour is lost. ++C. ++ - the atomic behavaiour is kept. ++ - dirty and tricky. ++ - VFS checks whether the file is created correctly after calling ++ ->create(), which means this approach doesn't work. ++D. ++ - easy to implement. ++ - the atomic behavaiour is lost. ++ - to open a file with superuser's credential and give it to a user ++ process is a bad idea, since the file object keeps the credential ++ in it. It may affect LSM or something. This approach doesn't work ++ either. ++ ++The approach A is ideal, but it hard to implement. So here is a ++variation of A, which is to be implemented. ++ ++A-1. Introduce aufs_atomic_open() ++ - calls branch fs ->atomic_open() if exists. otherwise calls ++ vfs_create() and finish_open(). ++ - the demerit is that the several checks after branch fs ++ ->atomic_open() are lost. in the ordinary case, the checks are ++ done by VFS:do_last(), lookup_open() and atomic_open(). some can ++ be implemented in aufs, but not all I am afraid. +diff --git a/Documentation/filesystems/aufs/design/03lookup.txt b/Documentation/filesystems/aufs/design/03lookup.txt +new file mode 100644 +index 00000000..80ae63bc +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/03lookup.txt +@@ -0,0 +1,113 @@ ++ ++# Copyright (C) 2005-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++Lookup in a Branch ++---------------------------------------------------------------------- ++Since aufs has a character of sub-VFS (see Introduction), it operates ++lookup for branches as VFS does. It may be a heavy work. But almost all ++lookup operation in aufs is the simplest case, ie. lookup only an entry ++directly connected to its parent. Digging down the directory hierarchy ++is unnecessary. VFS has a function lookup_one_len() for that use, and ++aufs calls it. ++ ++When a branch is a remote filesystem, aufs basically relies upon its ++->d_revalidate(), also aufs forces the hardest revalidate tests for ++them. ++For d_revalidate, aufs implements three levels of revalidate tests. See ++"Revalidate Dentry and UDBA" in detail. ++ ++ ++Test Only the Highest One for the Directory Permission (dirperm1 option) ++---------------------------------------------------------------------- ++Let's try case study. ++- aufs has two branches, upper readwrite and lower readonly. ++ /au = /rw + /ro ++- "dirA" exists under /ro, but /rw. and its mode is 0700. ++- user invoked "chmod a+rx /au/dirA" ++- the internal copy-up is activated and "/rw/dirA" is created and its ++ permission bits are set to world readable. ++- then "/au/dirA" becomes world readable? ++ ++In this case, /ro/dirA is still 0700 since it exists in readonly branch, ++or it may be a natively readonly filesystem. If aufs respects the lower ++branch, it should not respond readdir request from other users. But user ++allowed it by chmod. Should really aufs rejects showing the entries ++under /ro/dirA? ++ ++To be honest, I don't have a good solution for this case. So aufs ++implements 'dirperm1' and 'nodirperm1' mount options, and leave it to ++users. ++When dirperm1 is specified, aufs checks only the highest one for the ++directory permission, and shows the entries. Otherwise, as usual, checks ++every dir existing on all branches and rejects the request. ++ ++As a side effect, dirperm1 option improves the performance of aufs ++because the number of permission check is reduced when the number of ++branch is many. ++ ++ ++Revalidate Dentry and UDBA (User's Direct Branch Access) ++---------------------------------------------------------------------- ++Generally VFS helpers re-validate a dentry as a part of lookup. ++0. digging down the directory hierarchy. ++1. lock the parent dir by its i_mutex. ++2. lookup the final (child) entry. ++3. revalidate it. ++4. call the actual operation (create, unlink, etc.) ++5. unlock the parent dir ++ ++If the filesystem implements its ->d_revalidate() (step 3), then it is ++called. Actually aufs implements it and checks the dentry on a branch is ++still valid. ++But it is not enough. Because aufs has to release the lock for the ++parent dir on a branch at the end of ->lookup() (step 2) and ++->d_revalidate() (step 3) while the i_mutex of the aufs dir is still ++held by VFS. ++If the file on a branch is changed directly, eg. bypassing aufs, after ++aufs released the lock, then the subsequent operation may cause ++something unpleasant result. ++ ++This situation is a result of VFS architecture, ->lookup() and ++->d_revalidate() is separated. But I never say it is wrong. It is a good ++design from VFS's point of view. It is just not suitable for sub-VFS ++character in aufs. ++ ++Aufs supports such case by three level of revalidation which is ++selectable by user. ++1. Simple Revalidate ++ Addition to the native flow in VFS's, confirm the child-parent ++ relationship on the branch just after locking the parent dir on the ++ branch in the "actual operation" (step 4). When this validation ++ fails, aufs returns EBUSY. ->d_revalidate() (step 3) in aufs still ++ checks the validation of the dentry on branches. ++2. Monitor Changes Internally by Inotify/Fsnotify ++ Addition to above, in the "actual operation" (step 4) aufs re-lookup ++ the dentry on the branch, and returns EBUSY if it finds different ++ dentry. ++ Additionally, aufs sets the inotify/fsnotify watch for every dir on branches ++ during it is in cache. When the event is notified, aufs registers a ++ function to kernel 'events' thread by schedule_work(). And the ++ function sets some special status to the cached aufs dentry and inode ++ private data. If they are not cached, then aufs has nothing to ++ do. When the same file is accessed through aufs (step 0-3) later, ++ aufs will detect the status and refresh all necessary data. ++ In this mode, aufs has to ignore the event which is fired by aufs ++ itself. ++3. No Extra Validation ++ This is the simplest test and doesn't add any additional revalidation ++ test, and skip the revalidation in step 4. It is useful and improves ++ aufs performance when system surely hide the aufs branches from user, ++ by over-mounting something (or another method). +diff --git a/Documentation/filesystems/aufs/design/04branch.txt b/Documentation/filesystems/aufs/design/04branch.txt +new file mode 100644 +index 00000000..0c128973 +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/04branch.txt +@@ -0,0 +1,74 @@ ++ ++# Copyright (C) 2005-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++Branch Manipulation ++ ++Since aufs supports dynamic branch manipulation, ie. add/remove a branch ++and changing its permission/attribute, there are a lot of works to do. ++ ++ ++Add a Branch ++---------------------------------------------------------------------- ++o Confirm the adding dir exists outside of aufs, including loopback ++ mount, and its various attributes. ++o Initialize the xino file and whiteout bases if necessary. ++ See struct.txt. ++ ++o Check the owner/group/mode of the directory ++ When the owner/group/mode of the adding directory differs from the ++ existing branch, aufs issues a warning because it may impose a ++ security risk. ++ For example, when a upper writable branch has a world writable empty ++ top directory, a malicious user can create any files on the writable ++ branch directly, like copy-up and modify manually. If something like ++ /etc/{passwd,shadow} exists on the lower readonly branch but the upper ++ writable branch, and the writable branch is world-writable, then a ++ malicious guy may create /etc/passwd on the writable branch directly ++ and the infected file will be valid in aufs. ++ I am afraid it can be a security issue, but aufs can do nothing except ++ producing a warning. ++ ++ ++Delete a Branch ++---------------------------------------------------------------------- ++o Confirm the deleting branch is not busy ++ To be general, there is one merit to adopt "remount" interface to ++ manipulate branches. It is to discard caches. At deleting a branch, ++ aufs checks the still cached (and connected) dentries and inodes. If ++ there are any, then they are all in-use. An inode without its ++ corresponding dentry can be alive alone (for example, inotify/fsnotify case). ++ ++ For the cached one, aufs checks whether the same named entry exists on ++ other branches. ++ If the cached one is a directory, because aufs provides a merged view ++ to users, as long as one dir is left on any branch aufs can show the ++ dir to users. In this case, the branch can be removed from aufs. ++ Otherwise aufs rejects deleting the branch. ++ ++ If any file on the deleting branch is opened by aufs, then aufs ++ rejects deleting. ++ ++ ++Modify the Permission of a Branch ++---------------------------------------------------------------------- ++o Re-initialize or remove the xino file and whiteout bases if necessary. ++ See struct.txt. ++ ++o rw --> ro: Confirm the modifying branch is not busy ++ Aufs rejects the request if any of these conditions are true. ++ - a file on the branch is mmap-ed. ++ - a regular file on the branch is opened for write and there is no ++ same named entry on the upper branch. +diff --git a/Documentation/filesystems/aufs/design/05wbr_policy.txt b/Documentation/filesystems/aufs/design/05wbr_policy.txt +new file mode 100644 +index 00000000..cc5b7979 +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/05wbr_policy.txt +@@ -0,0 +1,64 @@ ++ ++# Copyright (C) 2005-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++Policies to Select One among Multiple Writable Branches ++---------------------------------------------------------------------- ++When the number of writable branch is more than one, aufs has to decide ++the target branch for file creation or copy-up. By default, the highest ++writable branch which has the parent (or ancestor) dir of the target ++file is chosen (top-down-parent policy). ++By user's request, aufs implements some other policies to select the ++writable branch, for file creation several policies, round-robin, ++most-free-space, and other policies. For copy-up, top-down-parent, ++bottom-up-parent, bottom-up and others. ++ ++As expected, the round-robin policy selects the branch in circular. When ++you have two writable branches and creates 10 new files, 5 files will be ++created for each branch. mkdir(2) systemcall is an exception. When you ++create 10 new directories, all will be created on the same branch. ++And the most-free-space policy selects the one which has most free ++space among the writable branches. The amount of free space will be ++checked by aufs internally, and users can specify its time interval. ++ ++The policies for copy-up is more simple, ++top-down-parent is equivalent to the same named on in create policy, ++bottom-up-parent selects the writable branch where the parent dir ++exists and the nearest upper one from the copyup-source, ++bottom-up selects the nearest upper writable branch from the ++copyup-source, regardless the existence of the parent dir. ++ ++There are some rules or exceptions to apply these policies. ++- If there is a readonly branch above the policy-selected branch and ++ the parent dir is marked as opaque (a variation of whiteout), or the ++ target (creating) file is whiteout-ed on the upper readonly branch, ++ then the result of the policy is ignored and the target file will be ++ created on the nearest upper writable branch than the readonly branch. ++- If there is a writable branch above the policy-selected branch and ++ the parent dir is marked as opaque or the target file is whiteouted ++ on the branch, then the result of the policy is ignored and the target ++ file will be created on the highest one among the upper writable ++ branches who has diropq or whiteout. In case of whiteout, aufs removes ++ it as usual. ++- link(2) and rename(2) systemcalls are exceptions in every policy. ++ They try selecting the branch where the source exists as possible ++ since copyup a large file will take long time. If it can't be, ++ ie. the branch where the source exists is readonly, then they will ++ follow the copyup policy. ++- There is an exception for rename(2) when the target exists. ++ If the rename target exists, aufs compares the index of the branches ++ where the source and the target exists and selects the higher ++ one. If the selected branch is readonly, then aufs follows the ++ copyup policy. +diff --git a/Documentation/filesystems/aufs/design/06dirren.dot b/Documentation/filesystems/aufs/design/06dirren.dot +new file mode 100644 +index 00000000..2d62bb6d +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/06dirren.dot +@@ -0,0 +1,31 @@ ++ ++// to view this graph, run dot(1) command in GRAPHVIZ. ++ ++digraph G { ++node [shape=box]; ++whinfo [label="detailed info file\n(lower_brid_root-hinum, h_inum, namelen, old name)"]; ++ ++node [shape=oval]; ++ ++aufs_rename -> whinfo [label="store/remove"]; ++ ++node [shape=oval]; ++inode_list [label="h_inum list in branch\ncache"]; ++ ++node [shape=box]; ++whinode [label="h_inum list file"]; ++ ++node [shape=oval]; ++brmgmt [label="br_add/del/mod/umount"]; ++ ++brmgmt -> inode_list [label="create/remove"]; ++brmgmt -> whinode [label="load/store"]; ++ ++inode_list -> whinode [style=dashed,dir=both]; ++ ++aufs_rename -> inode_list [label="add/del"]; ++ ++aufs_lookup -> inode_list [label="search"]; ++ ++aufs_lookup -> whinfo [label="load/remove"]; ++} +diff --git a/Documentation/filesystems/aufs/design/06dirren.txt b/Documentation/filesystems/aufs/design/06dirren.txt +new file mode 100644 +index 00000000..1f3cb86d +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/06dirren.txt +@@ -0,0 +1,102 @@ ++ ++# Copyright (C) 2017-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++Special handling for renaming a directory (DIRREN) ++---------------------------------------------------------------------- ++First, let's assume we have a simple usecase. ++ ++- /u = /rw + /ro ++- /rw/dirA exists ++- /ro/dirA and /ro/dirA/file exist too ++- there is no dirB on both branches ++- a user issues rename("dirA", "dirB") ++ ++Now, what should aufs behave against this rename(2)? ++There are a few possible cases. ++ ++A. returns EROFS. ++ since dirA exists on a readonly branch which cannot be renamed. ++B. returns EXDEV. ++ it is possible to copy-up dirA (only the dir itself), but the child ++ entries ("file" in this case) should not be. it must be a bad ++ approach to copy-up recursively. ++C. returns a success. ++ even the branch /ro is readonly, aufs tries renaming it. Obviously it ++ is a violation of aufs' policy. ++D. construct an extra information which indicates that /ro/dirA should ++ be handled as the name of dirB. ++ overlayfs has a similar feature called REDIRECT. ++ ++Until now, aufs implements the case B only which returns EXDEV, and ++expects the userspace application behaves like mv(1) which tries ++issueing rename(2) recursively. ++ ++A new aufs feature called DIRREN is introduced which implements the case ++D. There are several "extra information" added. ++ ++1. detailed info per renamed directory ++ path: /rw/dirB/$AUFS_WH_DR_INFO_PFX. ++2. the inode-number list of directories on a branch ++ path: /rw/dirB/$AUFS_WH_DR_BRHINO ++ ++The filename of "detailed info per directory" represents the lower ++branch, and its format is ++- a type of the branch id ++ one of these. ++ + uuid (not implemented yet) ++ + fsid ++ + dev ++- the inode-number of the branch root dir ++ ++And it contains these info in a single regular file. ++- magic number ++- branch's inode-number of the logically renamed dir ++- the name of the before-renamed dir ++ ++The "detailed info per directory" file is created in aufs rename(2), and ++loaded in any lookup. ++The info is considered in lookup for the matching case only. Here ++"matching" means that the root of branch (in the info filename) is same ++to the current looking-up branch. After looking-up the before-renamed ++name, the inode-number is compared. And the matched dentry is used. ++ ++The "inode-number list of directories" is a regular file which contains ++simply the inode-numbers on the branch. The file is created or updated ++in removing the branch, and loaded in adding the branch. Its lifetime is ++equal to the branch. ++The list is refered in lookup, and when the current target inode is ++found in the list, the aufs tries loading the "detailed info per ++directory" and get the changed and valid name of the dir. ++ ++Theoretically these "extra informaiton" may be able to be put into XATTR ++in the dir inode. But aufs doesn't choose this way because ++1. XATTR may not be supported by the branch (or its configuration) ++2. XATTR may have its size limit. ++3. XATTR may be less easy to convert than a regular file, when the ++ format of the info is changed in the future. ++At the same time, I agree that the regular file approach is much slower ++than XATTR approach. So, in the future, aufs may take the XATTR or other ++better approach. ++ ++This DIRREN feature is enabled by aufs configuration, and is activated ++by a new mount option. ++ ++For the more complicated case, there is a work with UDBA option, which ++is to dected the direct access to the branches (by-passing aufs) and to ++maintain the cashes in aufs. Since a single cached aufs dentry may ++contains two names, before- and after-rename, the name comparision in ++UDBA handler may not work correctly. In this case, the behaviour will be ++equivalen to udba=reval case. +diff --git a/Documentation/filesystems/aufs/design/06fhsm.txt b/Documentation/filesystems/aufs/design/06fhsm.txt +new file mode 100644 +index 00000000..ddfebecd +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/06fhsm.txt +@@ -0,0 +1,120 @@ ++ ++# Copyright (C) 2011-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program; if not, write to the Free Software ++# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA ++ ++ ++File-based Hierarchical Storage Management (FHSM) ++---------------------------------------------------------------------- ++Hierarchical Storage Management (or HSM) is a well-known feature in the ++storage world. Aufs provides this feature as file-based with multiple ++writable branches, based upon the principle of "Colder, the Lower". ++Here the word "colder" means that the less used files, and "lower" means ++that the position in the order of the stacked branches vertically. ++These multiple writable branches are prioritized, ie. the topmost one ++should be the fastest drive and be used heavily. ++ ++o Characters in aufs FHSM story ++- aufs itself and a new branch attribute. ++- a new ioctl interface to move-down and to establish a connection with ++ the daemon ("move-down" is a converse of "copy-up"). ++- userspace tool and daemon. ++ ++The userspace daemon establishes a connection with aufs and waits for ++the notification. The notified information is very similar to struct ++statfs containing the number of consumed blocks and inodes. ++When the consumed blocks/inodes of a branch exceeds the user-specified ++upper watermark, the daemon activates its move-down process until the ++consumed blocks/inodes reaches the user-specified lower watermark. ++ ++The actual move-down is done by aufs based upon the request from ++user-space since we need to maintain the inode number and the internal ++pointer arrays in aufs. ++ ++Currently aufs FHSM handles the regular files only. Additionally they ++must not be hard-linked nor pseudo-linked. ++ ++ ++o Cowork of aufs and the user-space daemon ++ During the userspace daemon established the connection, aufs sends a ++ small notification to it whenever aufs writes something into the ++ writable branch. But it may cost high since aufs issues statfs(2) ++ internally. So user can specify a new option to cache the ++ info. Actually the notification is controlled by these factors. ++ + the specified cache time. ++ + classified as "force" by aufs internally. ++ Until the specified time expires, aufs doesn't send the info ++ except the forced cases. When aufs decide forcing, the info is always ++ notified to userspace. ++ For example, the number of free inodes is generally large enough and ++ the shortage of it happens rarely. So aufs doesn't force the ++ notification when creating a new file, directory and others. This is ++ the typical case which aufs doesn't force. ++ When aufs writes the actual filedata and the files consumes any of new ++ blocks, the aufs forces notifying. ++ ++ ++o Interfaces in aufs ++- New branch attribute. ++ + fhsm ++ Specifies that the branch is managed by FHSM feature. In other word, ++ participant in the FHSM. ++ When nofhsm is set to the branch, it will not be the source/target ++ branch of the move-down operation. This attribute is set ++ independently from coo and moo attributes, and if you want full ++ FHSM, you should specify them as well. ++- New mount option. ++ + fhsm_sec ++ Specifies a second to suppress many less important info to be ++ notified. ++- New ioctl. ++ + AUFS_CTL_FHSM_FD ++ create a new file descriptor which userspace can read the notification ++ (a subset of struct statfs) from aufs. ++- Module parameter 'brs' ++ It has to be set to 1. Otherwise the new mount option 'fhsm' will not ++ be set. ++- mount helpers /sbin/mount.aufs and /sbin/umount.aufs ++ When there are two or more branches with fhsm attributes, ++ /sbin/mount.aufs invokes the user-space daemon and /sbin/umount.aufs ++ terminates it. As a result of remounting and branch-manipulation, the ++ number of branches with fhsm attribute can be one. In this case, ++ /sbin/mount.aufs will terminate the user-space daemon. ++ ++ ++Finally the operation is done as these steps in kernel-space. ++- make sure that, ++ + no one else is using the file. ++ + the file is not hard-linked. ++ + the file is not pseudo-linked. ++ + the file is a regular file. ++ + the parent dir is not opaqued. ++- find the target writable branch. ++- make sure the file is not whiteout-ed by the upper (than the target) ++ branch. ++- make the parent dir on the target branch. ++- mutex lock the inode on the branch. ++- unlink the whiteout on the target branch (if exists). ++- lookup and create the whiteout-ed temporary name on the target branch. ++- copy the file as the whiteout-ed temporary name on the target branch. ++- rename the whiteout-ed temporary name to the original name. ++- unlink the file on the source branch. ++- maintain the internal pointer array and the external inode number ++ table (XINO). ++- maintain the timestamps and other attributes of the parent dir and the ++ file. ++ ++And of course, in every step, an error may happen. So the operation ++should restore the original file state after an error happens. +diff --git a/Documentation/filesystems/aufs/design/06mmap.txt b/Documentation/filesystems/aufs/design/06mmap.txt +new file mode 100644 +index 00000000..9a0a096b +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/06mmap.txt +@@ -0,0 +1,72 @@ ++ ++# Copyright (C) 2005-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++mmap(2) -- File Memory Mapping ++---------------------------------------------------------------------- ++In aufs, the file-mapped pages are handled by a branch fs directly, no ++interaction with aufs. It means aufs_mmap() calls the branch fs's ++->mmap(). ++This approach is simple and good, but there is one problem. ++Under /proc, several entries show the mmapped files by its path (with ++device and inode number), and the printed path will be the path on the ++branch fs's instead of virtual aufs's. ++This is not a problem in most cases, but some utilities lsof(1) (and its ++user) may expect the path on aufs. ++ ++To address this issue, aufs adds a new member called vm_prfile in struct ++vm_area_struct (and struct vm_region). The original vm_file points to ++the file on the branch fs in order to handle everything correctly as ++usual. The new vm_prfile points to a virtual file in aufs, and the ++show-functions in procfs refers to vm_prfile if it is set. ++Also we need to maintain several other places where touching vm_file ++such like ++- fork()/clone() copies vma and the reference count of vm_file is ++ incremented. ++- merging vma maintains the ref count too. ++ ++This is not a good approach. It just fakes the printed path. But it ++leaves all behaviour around f_mapping unchanged. This is surely an ++advantage. ++Actually aufs had adopted another complicated approach which calls ++generic_file_mmap() and handles struct vm_operations_struct. In this ++approach, aufs met a hard problem and I could not solve it without ++switching the approach. ++ ++There may be one more another approach which is ++- bind-mount the branch-root onto the aufs-root internally ++- grab the new vfsmount (ie. struct mount) ++- lazy-umount the branch-root internally ++- in open(2) the aufs-file, open the branch-file with the hidden ++ vfsmount (instead of the original branch's vfsmount) ++- ideally this "bind-mount and lazy-umount" should be done atomically, ++ but it may be possible from userspace by the mount helper. ++ ++Adding the internal hidden vfsmount and using it in opening a file, the ++file path under /proc will be printed correctly. This approach looks ++smarter, but is not possible I am afraid. ++- aufs-root may be bind-mount later. when it happens, another hidden ++ vfsmount will be required. ++- it is hard to get the chance to bind-mount and lazy-umount ++ + in kernel-space, FS can have vfsmount in open(2) via ++ file->f_path, and aufs can know its vfsmount. But several locks are ++ already acquired, and if aufs tries to bind-mount and lazy-umount ++ here, then it may cause a deadlock. ++ + in user-space, bind-mount doesn't invoke the mount helper. ++- since /proc shows dev and ino, aufs has to give vma these info. it ++ means a new member vm_prinode will be necessary. this is essentially ++ equivalent to vm_prfile described above. ++ ++I have to give up this "looks-smater" approach. +diff --git a/Documentation/filesystems/aufs/design/06xattr.txt b/Documentation/filesystems/aufs/design/06xattr.txt +new file mode 100644 +index 00000000..be441e8d +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/06xattr.txt +@@ -0,0 +1,96 @@ ++ ++# Copyright (C) 2014-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program; if not, write to the Free Software ++# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA ++ ++ ++Listing XATTR/EA and getting the value ++---------------------------------------------------------------------- ++For the inode standard attributes (owner, group, timestamps, etc.), aufs ++shows the values from the topmost existing file. This behaviour is good ++for the non-dir entries since the bahaviour exactly matches the shown ++information. But for the directories, aufs considers all the same named ++entries on the lower branches. Which means, if one of the lower entry ++rejects readdir call, then aufs returns an error even if the topmost ++entry allows it. This behaviour is necessary to respect the branch fs's ++security, but can make users confused since the user-visible standard ++attributes don't match the behaviour. ++To address this issue, aufs has a mount option called dirperm1 which ++checks the permission for the topmost entry only, and ignores the lower ++entry's permission. ++ ++A similar issue can happen around XATTR. ++getxattr(2) and listxattr(2) families behave as if dirperm1 option is ++always set. Otherwise these very unpleasant situation would happen. ++- listxattr(2) may return the duplicated entries. ++- users may not be able to remove or reset the XATTR forever, ++ ++ ++XATTR/EA support in the internal (copy,move)-(up,down) ++---------------------------------------------------------------------- ++Generally the extended attributes of inode are categorized as these. ++- "security" for LSM and capability. ++- "system" for posix ACL, 'acl' mount option is required for the branch ++ fs generally. ++- "trusted" for userspace, CAP_SYS_ADMIN is required. ++- "user" for userspace, 'user_xattr' mount option is required for the ++ branch fs generally. ++ ++Moreover there are some other categories. Aufs handles these rather ++unpopular categories as the ordinary ones, ie. there is no special ++condition nor exception. ++ ++In copy-up, the support for XATTR on the dst branch may differ from the ++src branch. In this case, the copy-up operation will get an error and ++the original user operation which triggered the copy-up will fail. It ++can happen that even all copy-up will fail. ++When both of src and dst branches support XATTR and if an error occurs ++during copying XATTR, then the copy-up should fail obviously. That is a ++good reason and aufs should return an error to userspace. But when only ++the src branch support that XATTR, aufs should not return an error. ++For example, the src branch supports ACL but the dst branch doesn't ++because the dst branch may natively un-support it or temporary ++un-support it due to "noacl" mount option. Of course, the dst branch fs ++may NOT return an error even if the XATTR is not supported. It is ++totally up to the branch fs. ++ ++Anyway when the aufs internal copy-up gets an error from the dst branch ++fs, then aufs tries removing the just copied entry and returns the error ++to the userspace. The worst case of this situation will be all copy-up ++will fail. ++ ++For the copy-up operation, there two basic approaches. ++- copy the specified XATTR only (by category above), and return the ++ error unconditionally if it happens. ++- copy all XATTR, and ignore the error on the specified category only. ++ ++In order to support XATTR and to implement the correct behaviour, aufs ++chooses the latter approach and introduces some new branch attributes, ++"icexsec", "icexsys", "icextr", "icexusr", and "icexoth". ++They correspond to the XATTR namespaces (see above). Additionally, to be ++convenient, "icex" is also provided which means all "icex*" attributes ++are set (here the word "icex" stands for "ignore copy-error on XATTR"). ++ ++The meaning of these attributes is to ignore the error from setting ++XATTR on that branch. ++Note that aufs tries copying all XATTR unconditionally, and ignores the ++error from the dst branch according to the specified attributes. ++ ++Some XATTR may have its default value. The default value may come from ++the parent dir or the environment. If the default value is set at the ++file creating-time, it will be overwritten by copy-up. ++Some contradiction may happen I am afraid. ++Do we need another attribute to stop copying XATTR? I am unsure. For ++now, aufs implements the branch attributes to ignore the error. +diff --git a/Documentation/filesystems/aufs/design/07export.txt b/Documentation/filesystems/aufs/design/07export.txt +new file mode 100644 +index 00000000..bb700cb1 +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/07export.txt +@@ -0,0 +1,58 @@ ++ ++# Copyright (C) 2005-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++Export Aufs via NFS ++---------------------------------------------------------------------- ++Here is an approach. ++- like xino/xib, add a new file 'xigen' which stores aufs inode ++ generation. ++- iget_locked(): initialize aufs inode generation for a new inode, and ++ store it in xigen file. ++- destroy_inode(): increment aufs inode generation and store it in xigen ++ file. it is necessary even if it is not unlinked, because any data of ++ inode may be changed by UDBA. ++- encode_fh(): for a root dir, simply return FILEID_ROOT. otherwise ++ build file handle by ++ + branch id (4 bytes) ++ + superblock generation (4 bytes) ++ + inode number (4 or 8 bytes) ++ + parent dir inode number (4 or 8 bytes) ++ + inode generation (4 bytes)) ++ + return value of exportfs_encode_fh() for the parent on a branch (4 ++ bytes) ++ + file handle for a branch (by exportfs_encode_fh()) ++- fh_to_dentry(): ++ + find the index of a branch from its id in handle, and check it is ++ still exist in aufs. ++ + 1st level: get the inode number from handle and search it in cache. ++ + 2nd level: if not found in cache, get the parent inode number from ++ the handle and search it in cache. and then open the found parent ++ dir, find the matching inode number by vfs_readdir() and get its ++ name, and call lookup_one_len() for the target dentry. ++ + 3rd level: if the parent dir is not cached, call ++ exportfs_decode_fh() for a branch and get the parent on a branch, ++ build a pathname of it, convert it a pathname in aufs, call ++ path_lookup(). now aufs gets a parent dir dentry, then handle it as ++ the 2nd level. ++ + to open the dir, aufs needs struct vfsmount. aufs keeps vfsmount ++ for every branch, but not itself. to get this, (currently) aufs ++ searches in current->nsproxy->mnt_ns list. it may not be a good ++ idea, but I didn't get other approach. ++ + test the generation of the gotten inode. ++- every inode operation: they may get EBUSY due to UDBA. in this case, ++ convert it into ESTALE for NFSD. ++- readdir(): call lockdep_on/off() because filldir in NFSD calls ++ lookup_one_len(), vfs_getattr(), encode_fh() and others. +diff --git a/Documentation/filesystems/aufs/design/08shwh.txt b/Documentation/filesystems/aufs/design/08shwh.txt +new file mode 100644 +index 00000000..1dad573f +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/08shwh.txt +@@ -0,0 +1,52 @@ ++ ++# Copyright (C) 2005-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++Show Whiteout Mode (shwh) ++---------------------------------------------------------------------- ++Generally aufs hides the name of whiteouts. But in some cases, to show ++them is very useful for users. For instance, creating a new middle layer ++(branch) by merging existing layers. ++ ++(borrowing aufs1 HOW-TO from a user, Michael Towers) ++When you have three branches, ++- Bottom: 'system', squashfs (underlying base system), read-only ++- Middle: 'mods', squashfs, read-only ++- Top: 'overlay', ram (tmpfs), read-write ++ ++The top layer is loaded at boot time and saved at shutdown, to preserve ++the changes made to the system during the session. ++When larger changes have been made, or smaller changes have accumulated, ++the size of the saved top layer data grows. At this point, it would be ++nice to be able to merge the two overlay branches ('mods' and 'overlay') ++and rewrite the 'mods' squashfs, clearing the top layer and thus ++restoring save and load speed. ++ ++This merging is simplified by the use of another aufs mount, of just the ++two overlay branches using the 'shwh' option. ++# mount -t aufs -o ro,shwh,br:/livesys/overlay=ro+wh:/livesys/mods=rr+wh \ ++ aufs /livesys/merge_union ++ ++A merged view of these two branches is then available at ++/livesys/merge_union, and the new feature is that the whiteouts are ++visible! ++Note that in 'shwh' mode the aufs mount must be 'ro', which will disable ++writing to all branches. Also the default mode for all branches is 'ro'. ++It is now possible to save the combined contents of the two overlay ++branches to a new squashfs, e.g.: ++# mksquashfs /livesys/merge_union /path/to/newmods.squash ++ ++This new squashfs archive can be stored on the boot device and the ++initramfs will use it to replace the old one at the next boot. +diff --git a/Documentation/filesystems/aufs/design/10dynop.txt b/Documentation/filesystems/aufs/design/10dynop.txt +new file mode 100644 +index 00000000..710313c0 +--- /dev/null ++++ b/Documentation/filesystems/aufs/design/10dynop.txt +@@ -0,0 +1,47 @@ ++ ++# Copyright (C) 2010-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++Dynamically customizable FS operations ++---------------------------------------------------------------------- ++Generally FS operations (struct inode_operations, struct ++address_space_operations, struct file_operations, etc.) are defined as ++"static const", but it never means that FS have only one set of ++operation. Some FS have multiple sets of them. For instance, ext2 has ++three sets, one for XIP, for NOBH, and for normal. ++Since aufs overrides and redirects these operations, sometimes aufs has ++to change its behaviour according to the branch FS type. More importantly ++VFS acts differently if a function (member in the struct) is set or ++not. It means aufs should have several sets of operations and select one ++among them according to the branch FS definition. ++ ++In order to solve this problem and not to affect the behaviour of VFS, ++aufs defines these operations dynamically. For instance, aufs defines ++dummy direct_IO function for struct address_space_operations, but it may ++not be set to the address_space_operations actually. When the branch FS ++doesn't have it, aufs doesn't set it to its address_space_operations ++while the function definition itself is still alive. So the behaviour ++itself will not change, and it will return an error when direct_IO is ++not set. ++ ++The lifetime of these dynamically generated operation object is ++maintained by aufs branch object. When the branch is removed from aufs, ++the reference counter of the object is decremented. When it reaches ++zero, the dynamically generated operation object will be freed. ++ ++This approach is designed to support AIO (io_submit), Direct I/O and ++XIP (DAX) mainly. ++Currently this approach is applied to address_space_operations for ++regular files only. +diff --git a/MAINTAINERS b/MAINTAINERS +index ceaa88a5..b73c7f6c 100644 +--- a/MAINTAINERS ++++ b/MAINTAINERS +@@ -2293,6 +2293,19 @@ F: include/linux/audit.h + F: include/uapi/linux/audit.h + F: kernel/audit* + ++AUFS (advanced multi layered unification filesystem) FILESYSTEM ++M: "J. R. Okajima" ++L: linux-unionfs@vger.kernel.org ++L: aufs-users@lists.sourceforge.net (members only) ++W: http://aufs.sourceforge.net ++T: git://github.com/sfjro/aufs4-linux.git ++S: Supported ++F: Documentation/filesystems/aufs/ ++F: Documentation/ABI/testing/debugfs-aufs ++F: Documentation/ABI/testing/sysfs-aufs ++F: fs/aufs/ ++F: include/uapi/linux/aufs_type.h ++ + AUXILIARY DISPLAY DRIVERS + M: Miguel Ojeda Sandonis + W: http://miguelojeda.es/auxdisplay.htm +diff --git a/drivers/block/loop.c b/drivers/block/loop.c +index 833f9c0b..25655006 100644 +--- a/drivers/block/loop.c ++++ b/drivers/block/loop.c +@@ -732,6 +732,24 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, + return error; + } + ++/* ++ * for AUFS ++ * no get/put for file. ++ */ ++struct file *loop_backing_file(struct super_block *sb) ++{ ++ struct file *ret; ++ struct loop_device *l; ++ ++ ret = NULL; ++ if (MAJOR(sb->s_dev) == LOOP_MAJOR) { ++ l = sb->s_bdev->bd_disk->private_data; ++ ret = l->lo_backing_file; ++ } ++ return ret; ++} ++EXPORT_SYMBOL_GPL(loop_backing_file); ++ + /* loop sysfs attributes */ + + static ssize_t loop_attr_show(struct device *dev, char *page, +diff --git a/fs/Kconfig b/fs/Kconfig +index 5cc3f289..4a1aef02 100644 +--- a/fs/Kconfig ++++ b/fs/Kconfig +@@ -251,6 +251,7 @@ source "fs/pstore/Kconfig" + source "fs/sysv/Kconfig" + source "fs/ufs/Kconfig" + source "fs/exofs/Kconfig" ++source "fs/aufs/Kconfig" + + endif # MISC_FILESYSTEMS + +diff --git a/fs/Makefile b/fs/Makefile +index f2db9450..59b5e87b 100644 +--- a/fs/Makefile ++++ b/fs/Makefile +@@ -131,3 +131,4 @@ obj-y += exofs/ # Multiple modules + obj-$(CONFIG_CEPH_FS) += ceph/ + obj-$(CONFIG_PSTORE) += pstore/ + obj-$(CONFIG_EFIVAR_FS) += efivarfs/ ++obj-$(CONFIG_AUFS_FS) += aufs/ +diff --git a/fs/aufs/Kconfig b/fs/aufs/Kconfig +new file mode 100644 +index 00000000..bef60e21 +--- /dev/null ++++ b/fs/aufs/Kconfig +@@ -0,0 +1,198 @@ ++config AUFS_FS ++ tristate "Aufs (Advanced multi layered unification filesystem) support" ++ help ++ Aufs is a stackable unification filesystem such as Unionfs, ++ which unifies several directories and provides a merged single ++ directory. ++ In the early days, aufs was entirely re-designed and ++ re-implemented Unionfs Version 1.x series. Introducing many ++ original ideas, approaches and improvements, it becomes totally ++ different from Unionfs while keeping the basic features. ++ ++if AUFS_FS ++choice ++ prompt "Maximum number of branches" ++ default AUFS_BRANCH_MAX_127 ++ help ++ Specifies the maximum number of branches (or member directories) ++ in a single aufs. The larger value consumes more system ++ resources and has a minor impact to performance. ++config AUFS_BRANCH_MAX_127 ++ bool "127" ++ help ++ Specifies the maximum number of branches (or member directories) ++ in a single aufs. The larger value consumes more system ++ resources and has a minor impact to performance. ++config AUFS_BRANCH_MAX_511 ++ bool "511" ++ help ++ Specifies the maximum number of branches (or member directories) ++ in a single aufs. The larger value consumes more system ++ resources and has a minor impact to performance. ++config AUFS_BRANCH_MAX_1023 ++ bool "1023" ++ help ++ Specifies the maximum number of branches (or member directories) ++ in a single aufs. The larger value consumes more system ++ resources and has a minor impact to performance. ++config AUFS_BRANCH_MAX_32767 ++ bool "32767" ++ help ++ Specifies the maximum number of branches (or member directories) ++ in a single aufs. The larger value consumes more system ++ resources and has a minor impact to performance. ++endchoice ++ ++config AUFS_SBILIST ++ bool ++ depends on AUFS_MAGIC_SYSRQ || PROC_FS ++ default y ++ help ++ Automatic configuration for internal use. ++ When aufs supports Magic SysRq or /proc, enabled automatically. ++ ++config AUFS_HNOTIFY ++ bool "Detect direct branch access (bypassing aufs)" ++ help ++ If you want to modify files on branches directly, eg. bypassing aufs, ++ and want aufs to detect the changes of them fully, then enable this ++ option and use 'udba=notify' mount option. ++ Currently there is only one available configuration, "fsnotify". ++ It will have a negative impact to the performance. ++ See detail in aufs.5. ++ ++choice ++ prompt "method" if AUFS_HNOTIFY ++ default AUFS_HFSNOTIFY ++config AUFS_HFSNOTIFY ++ bool "fsnotify" ++ select FSNOTIFY ++endchoice ++ ++config AUFS_EXPORT ++ bool "NFS-exportable aufs" ++ depends on EXPORTFS ++ help ++ If you want to export your mounted aufs via NFS, then enable this ++ option. There are several requirements for this configuration. ++ See detail in aufs.5. ++ ++config AUFS_INO_T_64 ++ bool ++ depends on AUFS_EXPORT ++ depends on 64BIT && !(ALPHA || S390) ++ default y ++ help ++ Automatic configuration for internal use. ++ /* typedef unsigned long/int __kernel_ino_t */ ++ /* alpha and s390x are int */ ++ ++config AUFS_XATTR ++ bool "support for XATTR/EA (including Security Labels)" ++ help ++ If your branch fs supports XATTR/EA and you want to make them ++ available in aufs too, then enable this opsion and specify the ++ branch attributes for EA. ++ See detail in aufs.5. ++ ++config AUFS_FHSM ++ bool "File-based Hierarchical Storage Management" ++ help ++ Hierarchical Storage Management (or HSM) is a well-known feature ++ in the storage world. Aufs provides this feature as file-based. ++ with multiple branches. ++ These multiple branches are prioritized, ie. the topmost one ++ should be the fastest drive and be used heavily. ++ ++config AUFS_RDU ++ bool "Readdir in userspace" ++ help ++ Aufs has two methods to provide a merged view for a directory, ++ by a user-space library and by kernel-space natively. The latter ++ is always enabled but sometimes large and slow. ++ If you enable this option, install the library in aufs2-util ++ package, and set some environment variables for your readdir(3), ++ then the work will be handled in user-space which generally ++ shows better performance in most cases. ++ See detail in aufs.5. ++ ++config AUFS_DIRREN ++ bool "Workaround for rename(2)-ing a directory" ++ help ++ By default, aufs returns EXDEV error in renameing a dir who has ++ his child on the lower branch, since it is a bad idea to issue ++ rename(2) internally for every lower branch. But user may not ++ accept this behaviour. So here is a workaround to allow such ++ rename(2) and store some extra infromation on the writable ++ branch. Obviously this costs high (and I don't like it). ++ To use this feature, you need to enable this configuration AND ++ to specify the mount option `dirren.' ++ See details in aufs.5 and the design documents. ++ ++config AUFS_SHWH ++ bool "Show whiteouts" ++ help ++ If you want to make the whiteouts in aufs visible, then enable ++ this option and specify 'shwh' mount option. Although it may ++ sounds like philosophy or something, but in technically it ++ simply shows the name of whiteout with keeping its behaviour. ++ ++config AUFS_BR_RAMFS ++ bool "Ramfs (initramfs/rootfs) as an aufs branch" ++ help ++ If you want to use ramfs as an aufs branch fs, then enable this ++ option. Generally tmpfs is recommended. ++ Aufs prohibited them to be a branch fs by default, because ++ initramfs becomes unusable after switch_root or something ++ generally. If you sets initramfs as an aufs branch and boot your ++ system by switch_root, you will meet a problem easily since the ++ files in initramfs may be inaccessible. ++ Unless you are going to use ramfs as an aufs branch fs without ++ switch_root or something, leave it N. ++ ++config AUFS_BR_FUSE ++ bool "Fuse fs as an aufs branch" ++ depends on FUSE_FS ++ select AUFS_POLL ++ help ++ If you want to use fuse-based userspace filesystem as an aufs ++ branch fs, then enable this option. ++ It implements the internal poll(2) operation which is ++ implemented by fuse only (curretnly). ++ ++config AUFS_POLL ++ bool ++ help ++ Automatic configuration for internal use. ++ ++config AUFS_BR_HFSPLUS ++ bool "Hfsplus as an aufs branch" ++ depends on HFSPLUS_FS ++ default y ++ help ++ If you want to use hfsplus fs as an aufs branch fs, then enable ++ this option. This option introduces a small overhead at ++ copying-up a file on hfsplus. ++ ++config AUFS_BDEV_LOOP ++ bool ++ depends on BLK_DEV_LOOP ++ default y ++ help ++ Automatic configuration for internal use. ++ Convert =[ym] into =y. ++ ++config AUFS_DEBUG ++ bool "Debug aufs" ++ help ++ Enable this to compile aufs internal debug code. ++ It will have a negative impact to the performance. ++ ++config AUFS_MAGIC_SYSRQ ++ bool ++ depends on AUFS_DEBUG && MAGIC_SYSRQ ++ default y ++ help ++ Automatic configuration for internal use. ++ When aufs supports Magic SysRq, enabled automatically. ++endif +diff --git a/fs/aufs/Makefile b/fs/aufs/Makefile +new file mode 100644 +index 00000000..7c77aa19 +--- /dev/null ++++ b/fs/aufs/Makefile +@@ -0,0 +1,45 @@ ++ ++include ${src}/magic.mk ++ifeq (${CONFIG_AUFS_FS},m) ++include ${src}/conf.mk ++endif ++-include ${src}/priv_def.mk ++ ++# cf. include/linux/kernel.h ++# enable pr_debug ++ccflags-y += -DDEBUG ++# sparse requires the full pathname ++ifdef M ++ccflags-y += -include ${M}/../../include/uapi/linux/aufs_type.h ++else ++ccflags-y += -include ${srctree}/include/uapi/linux/aufs_type.h ++endif ++ ++obj-$(CONFIG_AUFS_FS) += aufs.o ++aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o \ ++ wkq.o vfsub.o dcsub.o \ ++ cpup.o whout.o wbr_policy.o \ ++ dinfo.o dentry.o \ ++ dynop.o \ ++ finfo.o file.o f_op.o \ ++ dir.o vdir.o \ ++ iinfo.o inode.o i_op.o i_op_add.o i_op_del.o i_op_ren.o \ ++ mvdown.o ioctl.o ++ ++# all are boolean ++aufs-$(CONFIG_PROC_FS) += procfs.o plink.o ++aufs-$(CONFIG_SYSFS) += sysfs.o ++aufs-$(CONFIG_DEBUG_FS) += dbgaufs.o ++aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o ++aufs-$(CONFIG_AUFS_HNOTIFY) += hnotify.o ++aufs-$(CONFIG_AUFS_HFSNOTIFY) += hfsnotify.o ++aufs-$(CONFIG_AUFS_EXPORT) += export.o ++aufs-$(CONFIG_AUFS_XATTR) += xattr.o ++aufs-$(CONFIG_FS_POSIX_ACL) += posix_acl.o ++aufs-$(CONFIG_AUFS_DIRREN) += dirren.o ++aufs-$(CONFIG_AUFS_FHSM) += fhsm.o ++aufs-$(CONFIG_AUFS_POLL) += poll.o ++aufs-$(CONFIG_AUFS_RDU) += rdu.o ++aufs-$(CONFIG_AUFS_BR_HFSPLUS) += hfsplus.o ++aufs-$(CONFIG_AUFS_DEBUG) += debug.o ++aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o +diff --git a/fs/aufs/aufs.h b/fs/aufs/aufs.h +new file mode 100644 +index 00000000..bcf0a2e4 +--- /dev/null ++++ b/fs/aufs/aufs.h +@@ -0,0 +1,60 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * all header files ++ */ ++ ++#ifndef __AUFS_H__ ++#define __AUFS_H__ ++ ++#ifdef __KERNEL__ ++ ++#define AuStub(type, name, body, ...) \ ++ static inline type name(__VA_ARGS__) { body; } ++ ++#define AuStubVoid(name, ...) \ ++ AuStub(void, name, , __VA_ARGS__) ++#define AuStubInt0(name, ...) \ ++ AuStub(int, name, return 0, __VA_ARGS__) ++ ++#include "debug.h" ++ ++#include "branch.h" ++#include "cpup.h" ++#include "dcsub.h" ++#include "dbgaufs.h" ++#include "dentry.h" ++#include "dir.h" ++#include "dirren.h" ++#include "dynop.h" ++#include "file.h" ++#include "fstype.h" ++#include "hbl.h" ++#include "inode.h" ++#include "loop.h" ++#include "module.h" ++#include "opts.h" ++#include "rwsem.h" ++#include "super.h" ++#include "sysaufs.h" ++#include "vfsub.h" ++#include "whout.h" ++#include "wkq.h" ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_H__ */ +diff --git a/fs/aufs/branch.c b/fs/aufs/branch.c +new file mode 100644 +index 00000000..916b5b78 +--- /dev/null ++++ b/fs/aufs/branch.c +@@ -0,0 +1,1421 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * branch management ++ */ ++ ++#include ++#include ++#include "aufs.h" ++ ++/* ++ * free a single branch ++ */ ++static void au_br_do_free(struct au_branch *br) ++{ ++ int i; ++ struct au_wbr *wbr; ++ struct au_dykey **key; ++ ++ au_hnotify_fin_br(br); ++ /* always, regardless the mount option */ ++ au_dr_hino_free(&br->br_dirren); ++ au_xino_put(br); ++ ++ AuDebugOn(au_br_count(br)); ++ au_br_count_fin(br); ++ ++ wbr = br->br_wbr; ++ if (wbr) { ++ for (i = 0; i < AuBrWh_Last; i++) ++ dput(wbr->wbr_wh[i]); ++ AuDebugOn(atomic_read(&wbr->wbr_wh_running)); ++ AuRwDestroy(&wbr->wbr_wh_rwsem); ++ } ++ ++ if (br->br_fhsm) { ++ au_br_fhsm_fin(br->br_fhsm); ++ kfree(br->br_fhsm); ++ } ++ ++ key = br->br_dykey; ++ for (i = 0; i < AuBrDynOp; i++, key++) ++ if (*key) ++ au_dy_put(*key); ++ else ++ break; ++ ++ /* recursive lock, s_umount of branch's */ ++ lockdep_off(); ++ path_put(&br->br_path); ++ lockdep_on(); ++ kfree(wbr); ++ kfree(br); ++} ++ ++/* ++ * frees all branches ++ */ ++void au_br_free(struct au_sbinfo *sbinfo) ++{ ++ aufs_bindex_t bmax; ++ struct au_branch **br; ++ ++ AuRwMustWriteLock(&sbinfo->si_rwsem); ++ ++ bmax = sbinfo->si_bbot + 1; ++ br = sbinfo->si_branch; ++ while (bmax--) ++ au_br_do_free(*br++); ++} ++ ++/* ++ * find the index of a branch which is specified by @br_id. ++ */ ++int au_br_index(struct super_block *sb, aufs_bindex_t br_id) ++{ ++ aufs_bindex_t bindex, bbot; ++ ++ bbot = au_sbbot(sb); ++ for (bindex = 0; bindex <= bbot; bindex++) ++ if (au_sbr_id(sb, bindex) == br_id) ++ return bindex; ++ return -1; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * add a branch ++ */ ++ ++static int test_overlap(struct super_block *sb, struct dentry *h_adding, ++ struct dentry *h_root) ++{ ++ if (unlikely(h_adding == h_root ++ || au_test_loopback_overlap(sb, h_adding))) ++ return 1; ++ if (h_adding->d_sb != h_root->d_sb) ++ return 0; ++ return au_test_subdir(h_adding, h_root) ++ || au_test_subdir(h_root, h_adding); ++} ++ ++/* ++ * returns a newly allocated branch. @new_nbranch is a number of branches ++ * after adding a branch. ++ */ ++static struct au_branch *au_br_alloc(struct super_block *sb, int new_nbranch, ++ int perm) ++{ ++ struct au_branch *add_branch; ++ struct dentry *root; ++ struct inode *inode; ++ int err; ++ ++ err = -ENOMEM; ++ add_branch = kzalloc(sizeof(*add_branch), GFP_NOFS); ++ if (unlikely(!add_branch)) ++ goto out; ++ add_branch->br_xino = au_xino_alloc(); ++ if (unlikely(!add_branch->br_xino)) ++ goto out_br; ++ err = au_hnotify_init_br(add_branch, perm); ++ if (unlikely(err)) ++ goto out_xino; ++ ++ if (au_br_writable(perm)) { ++ /* may be freed separately at changing the branch permission */ ++ add_branch->br_wbr = kzalloc(sizeof(*add_branch->br_wbr), ++ GFP_NOFS); ++ if (unlikely(!add_branch->br_wbr)) ++ goto out_hnotify; ++ } ++ ++ if (au_br_fhsm(perm)) { ++ err = au_fhsm_br_alloc(add_branch); ++ if (unlikely(err)) ++ goto out_wbr; ++ } ++ ++ root = sb->s_root; ++ err = au_sbr_realloc(au_sbi(sb), new_nbranch, /*may_shrink*/0); ++ if (!err) ++ err = au_di_realloc(au_di(root), new_nbranch, /*may_shrink*/0); ++ if (!err) { ++ inode = d_inode(root); ++ err = au_hinode_realloc(au_ii(inode), new_nbranch, ++ /*may_shrink*/0); ++ } ++ if (!err) ++ return add_branch; /* success */ ++ ++out_wbr: ++ kfree(add_branch->br_wbr); ++out_hnotify: ++ au_hnotify_fin_br(add_branch); ++out_xino: ++ au_xino_put(add_branch); ++out_br: ++ kfree(add_branch); ++out: ++ return ERR_PTR(err); ++} ++ ++/* ++ * test if the branch permission is legal or not. ++ */ ++static int test_br(struct inode *inode, int brperm, char *path) ++{ ++ int err; ++ ++ err = (au_br_writable(brperm) && IS_RDONLY(inode)); ++ if (!err) ++ goto out; ++ ++ err = -EINVAL; ++ pr_err("write permission for readonly mount or inode, %s\n", path); ++ ++out: ++ return err; ++} ++ ++/* ++ * returns: ++ * 0: success, the caller will add it ++ * plus: success, it is already unified, the caller should ignore it ++ * minus: error ++ */ ++static int test_add(struct super_block *sb, struct au_opt_add *add, int remount) ++{ ++ int err; ++ aufs_bindex_t bbot, bindex; ++ struct dentry *root, *h_dentry; ++ struct inode *inode, *h_inode; ++ ++ root = sb->s_root; ++ bbot = au_sbbot(sb); ++ if (unlikely(bbot >= 0 ++ && au_find_dbindex(root, add->path.dentry) >= 0)) { ++ err = 1; ++ if (!remount) { ++ err = -EINVAL; ++ pr_err("%s duplicated\n", add->pathname); ++ } ++ goto out; ++ } ++ ++ err = -ENOSPC; /* -E2BIG; */ ++ if (unlikely(AUFS_BRANCH_MAX <= add->bindex ++ || AUFS_BRANCH_MAX - 1 <= bbot)) { ++ pr_err("number of branches exceeded %s\n", add->pathname); ++ goto out; ++ } ++ ++ err = -EDOM; ++ if (unlikely(add->bindex < 0 || bbot + 1 < add->bindex)) { ++ pr_err("bad index %d\n", add->bindex); ++ goto out; ++ } ++ ++ inode = d_inode(add->path.dentry); ++ err = -ENOENT; ++ if (unlikely(!inode->i_nlink)) { ++ pr_err("no existence %s\n", add->pathname); ++ goto out; ++ } ++ ++ err = -EINVAL; ++ if (unlikely(inode->i_sb == sb)) { ++ pr_err("%s must be outside\n", add->pathname); ++ goto out; ++ } ++ ++ if (unlikely(au_test_fs_unsuppoted(inode->i_sb))) { ++ pr_err("unsupported filesystem, %s (%s)\n", ++ add->pathname, au_sbtype(inode->i_sb)); ++ goto out; ++ } ++ ++ if (unlikely(inode->i_sb->s_stack_depth)) { ++ pr_err("already stacked, %s (%s)\n", ++ add->pathname, au_sbtype(inode->i_sb)); ++ goto out; ++ } ++ ++ err = test_br(d_inode(add->path.dentry), add->perm, add->pathname); ++ if (unlikely(err)) ++ goto out; ++ ++ if (bbot < 0) ++ return 0; /* success */ ++ ++ err = -EINVAL; ++ for (bindex = 0; bindex <= bbot; bindex++) ++ if (unlikely(test_overlap(sb, add->path.dentry, ++ au_h_dptr(root, bindex)))) { ++ pr_err("%s is overlapped\n", add->pathname); ++ goto out; ++ } ++ ++ err = 0; ++ if (au_opt_test(au_mntflags(sb), WARN_PERM)) { ++ h_dentry = au_h_dptr(root, 0); ++ h_inode = d_inode(h_dentry); ++ if ((h_inode->i_mode & S_IALLUGO) != (inode->i_mode & S_IALLUGO) ++ || !uid_eq(h_inode->i_uid, inode->i_uid) ++ || !gid_eq(h_inode->i_gid, inode->i_gid)) ++ pr_warn("uid/gid/perm %s %u/%u/0%o, %u/%u/0%o\n", ++ add->pathname, ++ i_uid_read(inode), i_gid_read(inode), ++ (inode->i_mode & S_IALLUGO), ++ i_uid_read(h_inode), i_gid_read(h_inode), ++ (h_inode->i_mode & S_IALLUGO)); ++ } ++ ++out: ++ return err; ++} ++ ++/* ++ * initialize or clean the whiteouts for an adding branch ++ */ ++static int au_br_init_wh(struct super_block *sb, struct au_branch *br, ++ int new_perm) ++{ ++ int err, old_perm; ++ aufs_bindex_t bindex; ++ struct inode *h_inode; ++ struct au_wbr *wbr; ++ struct au_hinode *hdir; ++ struct dentry *h_dentry; ++ ++ err = vfsub_mnt_want_write(au_br_mnt(br)); ++ if (unlikely(err)) ++ goto out; ++ ++ wbr = br->br_wbr; ++ old_perm = br->br_perm; ++ br->br_perm = new_perm; ++ hdir = NULL; ++ h_inode = NULL; ++ bindex = au_br_index(sb, br->br_id); ++ if (0 <= bindex) { ++ hdir = au_hi(d_inode(sb->s_root), bindex); ++ au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); ++ } else { ++ h_dentry = au_br_dentry(br); ++ h_inode = d_inode(h_dentry); ++ inode_lock_nested(h_inode, AuLsc_I_PARENT); ++ } ++ if (!wbr) ++ err = au_wh_init(br, sb); ++ else { ++ wbr_wh_write_lock(wbr); ++ err = au_wh_init(br, sb); ++ wbr_wh_write_unlock(wbr); ++ } ++ if (hdir) ++ au_hn_inode_unlock(hdir); ++ else ++ inode_unlock(h_inode); ++ vfsub_mnt_drop_write(au_br_mnt(br)); ++ br->br_perm = old_perm; ++ ++ if (!err && wbr && !au_br_writable(new_perm)) { ++ kfree(wbr); ++ br->br_wbr = NULL; ++ } ++ ++out: ++ return err; ++} ++ ++static int au_wbr_init(struct au_branch *br, struct super_block *sb, ++ int perm) ++{ ++ int err; ++ struct kstatfs kst; ++ struct au_wbr *wbr; ++ ++ wbr = br->br_wbr; ++ au_rw_init(&wbr->wbr_wh_rwsem); ++ atomic_set(&wbr->wbr_wh_running, 0); ++ ++ /* ++ * a limit for rmdir/rename a dir ++ * cf. AUFS_MAX_NAMELEN in include/uapi/linux/aufs_type.h ++ */ ++ err = vfs_statfs(&br->br_path, &kst); ++ if (unlikely(err)) ++ goto out; ++ err = -EINVAL; ++ if (kst.f_namelen >= NAME_MAX) ++ err = au_br_init_wh(sb, br, perm); ++ else ++ pr_err("%pd(%s), unsupported namelen %ld\n", ++ au_br_dentry(br), ++ au_sbtype(au_br_dentry(br)->d_sb), kst.f_namelen); ++ ++out: ++ return err; ++} ++ ++/* initialize a new branch */ ++static int au_br_init(struct au_branch *br, struct super_block *sb, ++ struct au_opt_add *add) ++{ ++ int err; ++ struct au_branch *brbase; ++ struct file *xf; ++ struct inode *h_inode; ++ ++ err = 0; ++ br->br_perm = add->perm; ++ br->br_path = add->path; /* set first, path_get() later */ ++ spin_lock_init(&br->br_dykey_lock); ++ au_br_count_init(br); ++ br->br_id = au_new_br_id(sb); ++ AuDebugOn(br->br_id < 0); ++ ++ /* always, regardless the given option */ ++ err = au_dr_br_init(sb, br, &add->path); ++ if (unlikely(err)) ++ goto out_err; ++ ++ if (au_br_writable(add->perm)) { ++ err = au_wbr_init(br, sb, add->perm); ++ if (unlikely(err)) ++ goto out_err; ++ } ++ ++ if (au_opt_test(au_mntflags(sb), XINO)) { ++ brbase = au_sbr(sb, 0); ++ xf = au_xino_file(brbase); ++ AuDebugOn(!xf); ++ h_inode = d_inode(add->path.dentry); ++ err = au_xino_init_br(sb, br, h_inode->i_ino, &xf->f_path); ++ if (unlikely(err)) { ++ AuDebugOn(au_xino_file(br)); ++ goto out_err; ++ } ++ } ++ ++ sysaufs_br_init(br); ++ path_get(&br->br_path); ++ goto out; /* success */ ++ ++out_err: ++ memset(&br->br_path, 0, sizeof(br->br_path)); ++out: ++ return err; ++} ++ ++static void au_br_do_add_brp(struct au_sbinfo *sbinfo, aufs_bindex_t bindex, ++ struct au_branch *br, aufs_bindex_t bbot, ++ aufs_bindex_t amount) ++{ ++ struct au_branch **brp; ++ ++ AuRwMustWriteLock(&sbinfo->si_rwsem); ++ ++ brp = sbinfo->si_branch + bindex; ++ memmove(brp + 1, brp, sizeof(*brp) * amount); ++ *brp = br; ++ sbinfo->si_bbot++; ++ if (unlikely(bbot < 0)) ++ sbinfo->si_bbot = 0; ++} ++ ++static void au_br_do_add_hdp(struct au_dinfo *dinfo, aufs_bindex_t bindex, ++ aufs_bindex_t bbot, aufs_bindex_t amount) ++{ ++ struct au_hdentry *hdp; ++ ++ AuRwMustWriteLock(&dinfo->di_rwsem); ++ ++ hdp = au_hdentry(dinfo, bindex); ++ memmove(hdp + 1, hdp, sizeof(*hdp) * amount); ++ au_h_dentry_init(hdp); ++ dinfo->di_bbot++; ++ if (unlikely(bbot < 0)) ++ dinfo->di_btop = 0; ++} ++ ++static void au_br_do_add_hip(struct au_iinfo *iinfo, aufs_bindex_t bindex, ++ aufs_bindex_t bbot, aufs_bindex_t amount) ++{ ++ struct au_hinode *hip; ++ ++ AuRwMustWriteLock(&iinfo->ii_rwsem); ++ ++ hip = au_hinode(iinfo, bindex); ++ memmove(hip + 1, hip, sizeof(*hip) * amount); ++ au_hinode_init(hip); ++ iinfo->ii_bbot++; ++ if (unlikely(bbot < 0)) ++ iinfo->ii_btop = 0; ++} ++ ++static void au_br_do_add(struct super_block *sb, struct au_branch *br, ++ aufs_bindex_t bindex) ++{ ++ struct dentry *root, *h_dentry; ++ struct inode *root_inode, *h_inode; ++ aufs_bindex_t bbot, amount; ++ ++ root = sb->s_root; ++ root_inode = d_inode(root); ++ bbot = au_sbbot(sb); ++ amount = bbot + 1 - bindex; ++ h_dentry = au_br_dentry(br); ++ au_sbilist_lock(); ++ au_br_do_add_brp(au_sbi(sb), bindex, br, bbot, amount); ++ au_br_do_add_hdp(au_di(root), bindex, bbot, amount); ++ au_br_do_add_hip(au_ii(root_inode), bindex, bbot, amount); ++ au_set_h_dptr(root, bindex, dget(h_dentry)); ++ h_inode = d_inode(h_dentry); ++ au_set_h_iptr(root_inode, bindex, au_igrab(h_inode), /*flags*/0); ++ au_sbilist_unlock(); ++} ++ ++int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount) ++{ ++ int err; ++ aufs_bindex_t bbot, add_bindex; ++ struct dentry *root, *h_dentry; ++ struct inode *root_inode; ++ struct au_branch *add_branch; ++ struct file *xf; ++ ++ root = sb->s_root; ++ root_inode = d_inode(root); ++ IMustLock(root_inode); ++ IiMustWriteLock(root_inode); ++ err = test_add(sb, add, remount); ++ if (unlikely(err < 0)) ++ goto out; ++ if (err) { ++ err = 0; ++ goto out; /* success */ ++ } ++ ++ bbot = au_sbbot(sb); ++ add_branch = au_br_alloc(sb, bbot + 2, add->perm); ++ err = PTR_ERR(add_branch); ++ if (IS_ERR(add_branch)) ++ goto out; ++ ++ err = au_br_init(add_branch, sb, add); ++ if (unlikely(err)) { ++ au_br_do_free(add_branch); ++ goto out; ++ } ++ ++ add_bindex = add->bindex; ++ sysaufs_brs_del(sb, add_bindex); /* remove successors */ ++ au_br_do_add(sb, add_branch, add_bindex); ++ sysaufs_brs_add(sb, add_bindex); /* append successors */ ++ dbgaufs_brs_add(sb, add_bindex, /*topdown*/0); /* rename successors */ ++ ++ h_dentry = add->path.dentry; ++ if (!add_bindex) { ++ au_cpup_attr_all(root_inode, /*force*/1); ++ sb->s_maxbytes = h_dentry->d_sb->s_maxbytes; ++ } else ++ au_add_nlink(root_inode, d_inode(h_dentry)); ++ ++ /* ++ * this test/set prevents aufs from handling unnecessary notify events ++ * of xino files, in case of re-adding a writable branch which was ++ * once detached from aufs. ++ */ ++ if (au_xino_brid(sb) < 0 ++ && au_br_writable(add_branch->br_perm) ++ && !au_test_fs_bad_xino(h_dentry->d_sb)) { ++ xf = au_xino_file(add_branch); ++ if (xf && xf->f_path.dentry->d_parent == h_dentry) ++ au_xino_brid_set(sb, add_branch->br_id); ++ } ++ ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static unsigned long long au_farray_cb(struct super_block *sb, void *a, ++ unsigned long long max __maybe_unused, ++ void *arg) ++{ ++ unsigned long long n; ++ struct file **p, *f; ++ struct hlist_bl_head *files; ++ struct hlist_bl_node *pos; ++ struct au_finfo *finfo; ++ ++ n = 0; ++ p = a; ++ files = &au_sbi(sb)->si_files; ++ hlist_bl_lock(files); ++ hlist_bl_for_each_entry(finfo, pos, files, fi_hlist) { ++ f = finfo->fi_file; ++ if (file_count(f) ++ && !special_file(file_inode(f)->i_mode)) { ++ get_file(f); ++ *p++ = f; ++ n++; ++ AuDebugOn(n > max); ++ } ++ } ++ hlist_bl_unlock(files); ++ ++ return n; ++} ++ ++static struct file **au_farray_alloc(struct super_block *sb, ++ unsigned long long *max) ++{ ++ *max = au_nfiles(sb); ++ return au_array_alloc(max, au_farray_cb, sb, /*arg*/NULL); ++} ++ ++static void au_farray_free(struct file **a, unsigned long long max) ++{ ++ unsigned long long ull; ++ ++ for (ull = 0; ull < max; ull++) ++ if (a[ull]) ++ fput(a[ull]); ++ kvfree(a); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * delete a branch ++ */ ++ ++/* to show the line number, do not make it inlined function */ ++#define AuVerbose(do_info, fmt, ...) do { \ ++ if (do_info) \ ++ pr_info(fmt, ##__VA_ARGS__); \ ++} while (0) ++ ++static int au_test_ibusy(struct inode *inode, aufs_bindex_t btop, ++ aufs_bindex_t bbot) ++{ ++ return (inode && !S_ISDIR(inode->i_mode)) || btop == bbot; ++} ++ ++static int au_test_dbusy(struct dentry *dentry, aufs_bindex_t btop, ++ aufs_bindex_t bbot) ++{ ++ return au_test_ibusy(d_inode(dentry), btop, bbot); ++} ++ ++/* ++ * test if the branch is deletable or not. ++ */ ++static int test_dentry_busy(struct dentry *root, aufs_bindex_t bindex, ++ unsigned int sigen, const unsigned int verbose) ++{ ++ int err, i, j, ndentry; ++ aufs_bindex_t btop, bbot; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry *d; ++ ++ err = au_dpages_init(&dpages, GFP_NOFS); ++ if (unlikely(err)) ++ goto out; ++ err = au_dcsub_pages(&dpages, root, NULL, NULL); ++ if (unlikely(err)) ++ goto out_dpages; ++ ++ for (i = 0; !err && i < dpages.ndpage; i++) { ++ dpage = dpages.dpages + i; ++ ndentry = dpage->ndentry; ++ for (j = 0; !err && j < ndentry; j++) { ++ d = dpage->dentries[j]; ++ AuDebugOn(au_dcount(d) <= 0); ++ if (!au_digen_test(d, sigen)) { ++ di_read_lock_child(d, AuLock_IR); ++ if (unlikely(au_dbrange_test(d))) { ++ di_read_unlock(d, AuLock_IR); ++ continue; ++ } ++ } else { ++ di_write_lock_child(d); ++ if (unlikely(au_dbrange_test(d))) { ++ di_write_unlock(d); ++ continue; ++ } ++ err = au_reval_dpath(d, sigen); ++ if (!err) ++ di_downgrade_lock(d, AuLock_IR); ++ else { ++ di_write_unlock(d); ++ break; ++ } ++ } ++ ++ /* AuDbgDentry(d); */ ++ btop = au_dbtop(d); ++ bbot = au_dbbot(d); ++ if (btop <= bindex ++ && bindex <= bbot ++ && au_h_dptr(d, bindex) ++ && au_test_dbusy(d, btop, bbot)) { ++ err = -EBUSY; ++ AuVerbose(verbose, "busy %pd\n", d); ++ AuDbgDentry(d); ++ } ++ di_read_unlock(d, AuLock_IR); ++ } ++ } ++ ++out_dpages: ++ au_dpages_free(&dpages); ++out: ++ return err; ++} ++ ++static int test_inode_busy(struct super_block *sb, aufs_bindex_t bindex, ++ unsigned int sigen, const unsigned int verbose) ++{ ++ int err; ++ unsigned long long max, ull; ++ struct inode *i, **array; ++ aufs_bindex_t btop, bbot; ++ ++ array = au_iarray_alloc(sb, &max); ++ err = PTR_ERR(array); ++ if (IS_ERR(array)) ++ goto out; ++ ++ err = 0; ++ AuDbg("b%d\n", bindex); ++ for (ull = 0; !err && ull < max; ull++) { ++ i = array[ull]; ++ if (unlikely(!i)) ++ break; ++ if (i->i_ino == AUFS_ROOT_INO) ++ continue; ++ ++ /* AuDbgInode(i); */ ++ if (au_iigen(i, NULL) == sigen) ++ ii_read_lock_child(i); ++ else { ++ ii_write_lock_child(i); ++ err = au_refresh_hinode_self(i); ++ au_iigen_dec(i); ++ if (!err) ++ ii_downgrade_lock(i); ++ else { ++ ii_write_unlock(i); ++ break; ++ } ++ } ++ ++ btop = au_ibtop(i); ++ bbot = au_ibbot(i); ++ if (btop <= bindex ++ && bindex <= bbot ++ && au_h_iptr(i, bindex) ++ && au_test_ibusy(i, btop, bbot)) { ++ err = -EBUSY; ++ AuVerbose(verbose, "busy i%lu\n", i->i_ino); ++ AuDbgInode(i); ++ } ++ ii_read_unlock(i); ++ } ++ au_iarray_free(array, max); ++ ++out: ++ return err; ++} ++ ++static int test_children_busy(struct dentry *root, aufs_bindex_t bindex, ++ const unsigned int verbose) ++{ ++ int err; ++ unsigned int sigen; ++ ++ sigen = au_sigen(root->d_sb); ++ DiMustNoWaiters(root); ++ IiMustNoWaiters(d_inode(root)); ++ di_write_unlock(root); ++ err = test_dentry_busy(root, bindex, sigen, verbose); ++ if (!err) ++ err = test_inode_busy(root->d_sb, bindex, sigen, verbose); ++ di_write_lock_child(root); /* aufs_write_lock() calls ..._child() */ ++ ++ return err; ++} ++ ++static int test_dir_busy(struct file *file, aufs_bindex_t br_id, ++ struct file **to_free, int *idx) ++{ ++ int err; ++ unsigned char matched, root; ++ aufs_bindex_t bindex, bbot; ++ struct au_fidir *fidir; ++ struct au_hfile *hfile; ++ ++ err = 0; ++ root = IS_ROOT(file->f_path.dentry); ++ if (root) { ++ get_file(file); ++ to_free[*idx] = file; ++ (*idx)++; ++ goto out; ++ } ++ ++ matched = 0; ++ fidir = au_fi(file)->fi_hdir; ++ AuDebugOn(!fidir); ++ bbot = au_fbbot_dir(file); ++ for (bindex = au_fbtop(file); bindex <= bbot; bindex++) { ++ hfile = fidir->fd_hfile + bindex; ++ if (!hfile->hf_file) ++ continue; ++ ++ if (hfile->hf_br->br_id == br_id) { ++ matched = 1; ++ break; ++ } ++ } ++ if (matched) ++ err = -EBUSY; ++ ++out: ++ return err; ++} ++ ++static int test_file_busy(struct super_block *sb, aufs_bindex_t br_id, ++ struct file **to_free, int opened) ++{ ++ int err, idx; ++ unsigned long long ull, max; ++ aufs_bindex_t btop; ++ struct file *file, **array; ++ struct dentry *root; ++ struct au_hfile *hfile; ++ ++ array = au_farray_alloc(sb, &max); ++ err = PTR_ERR(array); ++ if (IS_ERR(array)) ++ goto out; ++ ++ err = 0; ++ idx = 0; ++ root = sb->s_root; ++ di_write_unlock(root); ++ for (ull = 0; ull < max; ull++) { ++ file = array[ull]; ++ if (unlikely(!file)) ++ break; ++ ++ /* AuDbg("%pD\n", file); */ ++ fi_read_lock(file); ++ btop = au_fbtop(file); ++ if (!d_is_dir(file->f_path.dentry)) { ++ hfile = &au_fi(file)->fi_htop; ++ if (hfile->hf_br->br_id == br_id) ++ err = -EBUSY; ++ } else ++ err = test_dir_busy(file, br_id, to_free, &idx); ++ fi_read_unlock(file); ++ if (unlikely(err)) ++ break; ++ } ++ di_write_lock_child(root); ++ au_farray_free(array, max); ++ AuDebugOn(idx > opened); ++ ++out: ++ return err; ++} ++ ++static void br_del_file(struct file **to_free, unsigned long long opened, ++ aufs_bindex_t br_id) ++{ ++ unsigned long long ull; ++ aufs_bindex_t bindex, btop, bbot, bfound; ++ struct file *file; ++ struct au_fidir *fidir; ++ struct au_hfile *hfile; ++ ++ for (ull = 0; ull < opened; ull++) { ++ file = to_free[ull]; ++ if (unlikely(!file)) ++ break; ++ ++ /* AuDbg("%pD\n", file); */ ++ AuDebugOn(!d_is_dir(file->f_path.dentry)); ++ bfound = -1; ++ fidir = au_fi(file)->fi_hdir; ++ AuDebugOn(!fidir); ++ fi_write_lock(file); ++ btop = au_fbtop(file); ++ bbot = au_fbbot_dir(file); ++ for (bindex = btop; bindex <= bbot; bindex++) { ++ hfile = fidir->fd_hfile + bindex; ++ if (!hfile->hf_file) ++ continue; ++ ++ if (hfile->hf_br->br_id == br_id) { ++ bfound = bindex; ++ break; ++ } ++ } ++ AuDebugOn(bfound < 0); ++ au_set_h_fptr(file, bfound, NULL); ++ if (bfound == btop) { ++ for (btop++; btop <= bbot; btop++) ++ if (au_hf_dir(file, btop)) { ++ au_set_fbtop(file, btop); ++ break; ++ } ++ } ++ fi_write_unlock(file); ++ } ++} ++ ++static void au_br_do_del_brp(struct au_sbinfo *sbinfo, ++ const aufs_bindex_t bindex, ++ const aufs_bindex_t bbot) ++{ ++ struct au_branch **brp, **p; ++ ++ AuRwMustWriteLock(&sbinfo->si_rwsem); ++ ++ brp = sbinfo->si_branch + bindex; ++ if (bindex < bbot) ++ memmove(brp, brp + 1, sizeof(*brp) * (bbot - bindex)); ++ sbinfo->si_branch[0 + bbot] = NULL; ++ sbinfo->si_bbot--; ++ ++ p = au_krealloc(sbinfo->si_branch, sizeof(*p) * bbot, AuGFP_SBILIST, ++ /*may_shrink*/1); ++ if (p) ++ sbinfo->si_branch = p; ++ /* harmless error */ ++} ++ ++static void au_br_do_del_hdp(struct au_dinfo *dinfo, const aufs_bindex_t bindex, ++ const aufs_bindex_t bbot) ++{ ++ struct au_hdentry *hdp, *p; ++ ++ AuRwMustWriteLock(&dinfo->di_rwsem); ++ ++ hdp = au_hdentry(dinfo, bindex); ++ if (bindex < bbot) ++ memmove(hdp, hdp + 1, sizeof(*hdp) * (bbot - bindex)); ++ /* au_h_dentry_init(au_hdentry(dinfo, bbot); */ ++ dinfo->di_bbot--; ++ ++ p = au_krealloc(dinfo->di_hdentry, sizeof(*p) * bbot, AuGFP_SBILIST, ++ /*may_shrink*/1); ++ if (p) ++ dinfo->di_hdentry = p; ++ /* harmless error */ ++} ++ ++static void au_br_do_del_hip(struct au_iinfo *iinfo, const aufs_bindex_t bindex, ++ const aufs_bindex_t bbot) ++{ ++ struct au_hinode *hip, *p; ++ ++ AuRwMustWriteLock(&iinfo->ii_rwsem); ++ ++ hip = au_hinode(iinfo, bindex); ++ if (bindex < bbot) ++ memmove(hip, hip + 1, sizeof(*hip) * (bbot - bindex)); ++ /* au_hinode_init(au_hinode(iinfo, bbot)); */ ++ iinfo->ii_bbot--; ++ ++ p = au_krealloc(iinfo->ii_hinode, sizeof(*p) * bbot, AuGFP_SBILIST, ++ /*may_shrink*/1); ++ if (p) ++ iinfo->ii_hinode = p; ++ /* harmless error */ ++} ++ ++static void au_br_do_del(struct super_block *sb, aufs_bindex_t bindex, ++ struct au_branch *br) ++{ ++ aufs_bindex_t bbot; ++ struct au_sbinfo *sbinfo; ++ struct dentry *root, *h_root; ++ struct inode *inode, *h_inode; ++ struct au_hinode *hinode; ++ ++ SiMustWriteLock(sb); ++ ++ root = sb->s_root; ++ inode = d_inode(root); ++ sbinfo = au_sbi(sb); ++ bbot = sbinfo->si_bbot; ++ ++ h_root = au_h_dptr(root, bindex); ++ hinode = au_hi(inode, bindex); ++ h_inode = au_igrab(hinode->hi_inode); ++ au_hiput(hinode); ++ ++ au_sbilist_lock(); ++ au_br_do_del_brp(sbinfo, bindex, bbot); ++ au_br_do_del_hdp(au_di(root), bindex, bbot); ++ au_br_do_del_hip(au_ii(inode), bindex, bbot); ++ au_sbilist_unlock(); ++ ++ /* ignore an error */ ++ au_dr_br_fin(sb, br); /* always, regardless the mount option */ ++ ++ dput(h_root); ++ iput(h_inode); ++ au_br_do_free(br); ++} ++ ++static unsigned long long empty_cb(struct super_block *sb, void *array, ++ unsigned long long max, void *arg) ++{ ++ return max; ++} ++ ++int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount) ++{ ++ int err, rerr, i; ++ unsigned long long opened; ++ unsigned int mnt_flags; ++ aufs_bindex_t bindex, bbot, br_id; ++ unsigned char do_wh, verbose; ++ struct au_branch *br; ++ struct au_wbr *wbr; ++ struct dentry *root; ++ struct file **to_free; ++ ++ err = 0; ++ opened = 0; ++ to_free = NULL; ++ root = sb->s_root; ++ bindex = au_find_dbindex(root, del->h_path.dentry); ++ if (bindex < 0) { ++ if (remount) ++ goto out; /* success */ ++ err = -ENOENT; ++ pr_err("%s no such branch\n", del->pathname); ++ goto out; ++ } ++ AuDbg("bindex b%d\n", bindex); ++ ++ err = -EBUSY; ++ mnt_flags = au_mntflags(sb); ++ verbose = !!au_opt_test(mnt_flags, VERBOSE); ++ bbot = au_sbbot(sb); ++ if (unlikely(!bbot)) { ++ AuVerbose(verbose, "no more branches left\n"); ++ goto out; ++ } ++ br = au_sbr(sb, bindex); ++ AuDebugOn(!path_equal(&br->br_path, &del->h_path)); ++ ++ br_id = br->br_id; ++ opened = au_br_count(br); ++ if (unlikely(opened)) { ++ to_free = au_array_alloc(&opened, empty_cb, sb, NULL); ++ err = PTR_ERR(to_free); ++ if (IS_ERR(to_free)) ++ goto out; ++ ++ err = test_file_busy(sb, br_id, to_free, opened); ++ if (unlikely(err)) { ++ AuVerbose(verbose, "%llu file(s) opened\n", opened); ++ goto out; ++ } ++ } ++ ++ wbr = br->br_wbr; ++ do_wh = wbr && (wbr->wbr_whbase || wbr->wbr_plink || wbr->wbr_orph); ++ if (do_wh) { ++ /* instead of WbrWhMustWriteLock(wbr) */ ++ SiMustWriteLock(sb); ++ for (i = 0; i < AuBrWh_Last; i++) { ++ dput(wbr->wbr_wh[i]); ++ wbr->wbr_wh[i] = NULL; ++ } ++ } ++ ++ err = test_children_busy(root, bindex, verbose); ++ if (unlikely(err)) { ++ if (do_wh) ++ goto out_wh; ++ goto out; ++ } ++ ++ err = 0; ++ if (to_free) { ++ /* ++ * now we confirmed the branch is deletable. ++ * let's free the remaining opened dirs on the branch. ++ */ ++ di_write_unlock(root); ++ br_del_file(to_free, opened, br_id); ++ di_write_lock_child(root); ++ } ++ ++ sysaufs_brs_del(sb, bindex); /* remove successors */ ++ dbgaufs_xino_del(br); /* remove one */ ++ au_br_do_del(sb, bindex, br); ++ sysaufs_brs_add(sb, bindex); /* append successors */ ++ dbgaufs_brs_add(sb, bindex, /*topdown*/1); /* rename successors */ ++ ++ if (!bindex) { ++ au_cpup_attr_all(d_inode(root), /*force*/1); ++ sb->s_maxbytes = au_sbr_sb(sb, 0)->s_maxbytes; ++ } else ++ au_sub_nlink(d_inode(root), d_inode(del->h_path.dentry)); ++ if (au_opt_test(mnt_flags, PLINK)) ++ au_plink_half_refresh(sb, br_id); ++ ++ if (au_xino_brid(sb) == br_id) ++ au_xino_brid_set(sb, -1); ++ goto out; /* success */ ++ ++out_wh: ++ /* revert */ ++ rerr = au_br_init_wh(sb, br, br->br_perm); ++ if (rerr) ++ pr_warn("failed re-creating base whiteout, %s. (%d)\n", ++ del->pathname, rerr); ++out: ++ if (to_free) ++ au_farray_free(to_free, opened); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_ibusy(struct super_block *sb, struct aufs_ibusy __user *arg) ++{ ++ int err; ++ aufs_bindex_t btop, bbot; ++ struct aufs_ibusy ibusy; ++ struct inode *inode, *h_inode; ++ ++ err = -EPERM; ++ if (unlikely(!capable(CAP_SYS_ADMIN))) ++ goto out; ++ ++ err = copy_from_user(&ibusy, arg, sizeof(ibusy)); ++ if (!err) ++ err = !access_ok(VERIFY_WRITE, &arg->h_ino, sizeof(arg->h_ino)); ++ if (unlikely(err)) { ++ err = -EFAULT; ++ AuTraceErr(err); ++ goto out; ++ } ++ ++ err = -EINVAL; ++ si_read_lock(sb, AuLock_FLUSH); ++ if (unlikely(ibusy.bindex < 0 || ibusy.bindex > au_sbbot(sb))) ++ goto out_unlock; ++ ++ err = 0; ++ ibusy.h_ino = 0; /* invalid */ ++ inode = ilookup(sb, ibusy.ino); ++ if (!inode ++ || inode->i_ino == AUFS_ROOT_INO ++ || au_is_bad_inode(inode)) ++ goto out_unlock; ++ ++ ii_read_lock_child(inode); ++ btop = au_ibtop(inode); ++ bbot = au_ibbot(inode); ++ if (btop <= ibusy.bindex && ibusy.bindex <= bbot) { ++ h_inode = au_h_iptr(inode, ibusy.bindex); ++ if (h_inode && au_test_ibusy(inode, btop, bbot)) ++ ibusy.h_ino = h_inode->i_ino; ++ } ++ ii_read_unlock(inode); ++ iput(inode); ++ ++out_unlock: ++ si_read_unlock(sb); ++ if (!err) { ++ err = __put_user(ibusy.h_ino, &arg->h_ino); ++ if (unlikely(err)) { ++ err = -EFAULT; ++ AuTraceErr(err); ++ } ++ } ++out: ++ return err; ++} ++ ++long au_ibusy_ioctl(struct file *file, unsigned long arg) ++{ ++ return au_ibusy(file->f_path.dentry->d_sb, (void __user *)arg); ++} ++ ++#ifdef CONFIG_COMPAT ++long au_ibusy_compat_ioctl(struct file *file, unsigned long arg) ++{ ++ return au_ibusy(file->f_path.dentry->d_sb, compat_ptr(arg)); ++} ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * change a branch permission ++ */ ++ ++static void au_warn_ima(void) ++{ ++#ifdef CONFIG_IMA ++ /* since it doesn't support mark_files_ro() */ ++ AuWarn1("RW -> RO makes IMA to produce wrong message\n"); ++#endif ++} ++ ++static int do_need_sigen_inc(int a, int b) ++{ ++ return au_br_whable(a) && !au_br_whable(b); ++} ++ ++static int need_sigen_inc(int old, int new) ++{ ++ return do_need_sigen_inc(old, new) ++ || do_need_sigen_inc(new, old); ++} ++ ++static int au_br_mod_files_ro(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ int err, do_warn; ++ unsigned int mnt_flags; ++ unsigned long long ull, max; ++ aufs_bindex_t br_id; ++ unsigned char verbose, writer; ++ struct file *file, *hf, **array; ++ struct au_hfile *hfile; ++ ++ mnt_flags = au_mntflags(sb); ++ verbose = !!au_opt_test(mnt_flags, VERBOSE); ++ ++ array = au_farray_alloc(sb, &max); ++ err = PTR_ERR(array); ++ if (IS_ERR(array)) ++ goto out; ++ ++ do_warn = 0; ++ br_id = au_sbr_id(sb, bindex); ++ for (ull = 0; ull < max; ull++) { ++ file = array[ull]; ++ if (unlikely(!file)) ++ break; ++ ++ /* AuDbg("%pD\n", file); */ ++ fi_read_lock(file); ++ if (unlikely(au_test_mmapped(file))) { ++ err = -EBUSY; ++ AuVerbose(verbose, "mmapped %pD\n", file); ++ AuDbgFile(file); ++ FiMustNoWaiters(file); ++ fi_read_unlock(file); ++ goto out_array; ++ } ++ ++ hfile = &au_fi(file)->fi_htop; ++ hf = hfile->hf_file; ++ if (!d_is_reg(file->f_path.dentry) ++ || !(file->f_mode & FMODE_WRITE) ++ || hfile->hf_br->br_id != br_id ++ || !(hf->f_mode & FMODE_WRITE)) ++ array[ull] = NULL; ++ else { ++ do_warn = 1; ++ get_file(file); ++ } ++ ++ FiMustNoWaiters(file); ++ fi_read_unlock(file); ++ fput(file); ++ } ++ ++ err = 0; ++ if (do_warn) ++ au_warn_ima(); ++ ++ for (ull = 0; ull < max; ull++) { ++ file = array[ull]; ++ if (!file) ++ continue; ++ ++ /* todo: already flushed? */ ++ /* ++ * fs/super.c:mark_files_ro() is gone, but aufs keeps its ++ * approach which resets f_mode and calls mnt_drop_write() and ++ * file_release_write() for each file, because the branch ++ * attribute in aufs world is totally different from the native ++ * fs rw/ro mode. ++ */ ++ /* fi_read_lock(file); */ ++ hfile = &au_fi(file)->fi_htop; ++ hf = hfile->hf_file; ++ /* fi_read_unlock(file); */ ++ spin_lock(&hf->f_lock); ++ writer = !!(hf->f_mode & FMODE_WRITER); ++ hf->f_mode &= ~(FMODE_WRITE | FMODE_WRITER); ++ spin_unlock(&hf->f_lock); ++ if (writer) { ++ put_write_access(file_inode(hf)); ++ __mnt_drop_write(hf->f_path.mnt); ++ } ++ } ++ ++out_array: ++ au_farray_free(array, max); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount, ++ int *do_refresh) ++{ ++ int err, rerr; ++ aufs_bindex_t bindex; ++ struct dentry *root; ++ struct au_branch *br; ++ struct au_br_fhsm *bf; ++ ++ root = sb->s_root; ++ bindex = au_find_dbindex(root, mod->h_root); ++ if (bindex < 0) { ++ if (remount) ++ return 0; /* success */ ++ err = -ENOENT; ++ pr_err("%s no such branch\n", mod->path); ++ goto out; ++ } ++ AuDbg("bindex b%d\n", bindex); ++ ++ err = test_br(d_inode(mod->h_root), mod->perm, mod->path); ++ if (unlikely(err)) ++ goto out; ++ ++ br = au_sbr(sb, bindex); ++ AuDebugOn(mod->h_root != au_br_dentry(br)); ++ if (br->br_perm == mod->perm) ++ return 0; /* success */ ++ ++ /* pre-allocate for non-fhsm --> fhsm */ ++ bf = NULL; ++ if (!au_br_fhsm(br->br_perm) && au_br_fhsm(mod->perm)) { ++ err = au_fhsm_br_alloc(br); ++ if (unlikely(err)) ++ goto out; ++ bf = br->br_fhsm; ++ br->br_fhsm = NULL; ++ } ++ ++ if (au_br_writable(br->br_perm)) { ++ /* remove whiteout base */ ++ err = au_br_init_wh(sb, br, mod->perm); ++ if (unlikely(err)) ++ goto out_bf; ++ ++ if (!au_br_writable(mod->perm)) { ++ /* rw --> ro, file might be mmapped */ ++ DiMustNoWaiters(root); ++ IiMustNoWaiters(d_inode(root)); ++ di_write_unlock(root); ++ err = au_br_mod_files_ro(sb, bindex); ++ /* aufs_write_lock() calls ..._child() */ ++ di_write_lock_child(root); ++ ++ if (unlikely(err)) { ++ rerr = -ENOMEM; ++ br->br_wbr = kzalloc(sizeof(*br->br_wbr), ++ GFP_NOFS); ++ if (br->br_wbr) ++ rerr = au_wbr_init(br, sb, br->br_perm); ++ if (unlikely(rerr)) { ++ AuIOErr("nested error %d (%d)\n", ++ rerr, err); ++ br->br_perm = mod->perm; ++ } ++ } ++ } ++ } else if (au_br_writable(mod->perm)) { ++ /* ro --> rw */ ++ err = -ENOMEM; ++ br->br_wbr = kzalloc(sizeof(*br->br_wbr), GFP_NOFS); ++ if (br->br_wbr) { ++ err = au_wbr_init(br, sb, mod->perm); ++ if (unlikely(err)) { ++ kfree(br->br_wbr); ++ br->br_wbr = NULL; ++ } ++ } ++ } ++ if (unlikely(err)) ++ goto out_bf; ++ ++ if (au_br_fhsm(br->br_perm)) { ++ if (!au_br_fhsm(mod->perm)) { ++ /* fhsm --> non-fhsm */ ++ au_br_fhsm_fin(br->br_fhsm); ++ kfree(br->br_fhsm); ++ br->br_fhsm = NULL; ++ } ++ } else if (au_br_fhsm(mod->perm)) ++ /* non-fhsm --> fhsm */ ++ br->br_fhsm = bf; ++ ++ *do_refresh |= need_sigen_inc(br->br_perm, mod->perm); ++ br->br_perm = mod->perm; ++ goto out; /* success */ ++ ++out_bf: ++ kfree(bf); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs) ++{ ++ int err; ++ struct kstatfs kstfs; ++ ++ err = vfs_statfs(&br->br_path, &kstfs); ++ if (!err) { ++ stfs->f_blocks = kstfs.f_blocks; ++ stfs->f_bavail = kstfs.f_bavail; ++ stfs->f_files = kstfs.f_files; ++ stfs->f_ffree = kstfs.f_ffree; ++ } ++ ++ return err; ++} +diff --git a/fs/aufs/branch.h b/fs/aufs/branch.h +new file mode 100644 +index 00000000..5fd8a9dd +--- /dev/null ++++ b/fs/aufs/branch.h +@@ -0,0 +1,364 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * branch filesystems and xino for them ++ */ ++ ++#ifndef __AUFS_BRANCH_H__ ++#define __AUFS_BRANCH_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include "dirren.h" ++#include "dynop.h" ++#include "rwsem.h" ++#include "super.h" ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* a xino file */ ++struct au_xino { ++ struct file *xi_file; ++ struct { ++ spinlock_t spin; ++ ino_t *array; ++ int total; ++ /* reserved for future use */ ++ /* unsigned long *bitmap; */ ++ wait_queue_head_t wqh; ++ } xi_nondir; ++ ++ atomic_t xi_truncating; ++ ++ struct kref xi_kref; ++ ++ /* todo: make xino files an array to support huge inode number */ ++}; ++ ++/* File-based Hierarchical Storage Management */ ++struct au_br_fhsm { ++#ifdef CONFIG_AUFS_FHSM ++ struct mutex bf_lock; ++ unsigned long bf_jiffy; ++ struct aufs_stfs bf_stfs; ++ int bf_readable; ++#endif ++}; ++ ++/* members for writable branch only */ ++enum {AuBrWh_BASE, AuBrWh_PLINK, AuBrWh_ORPH, AuBrWh_Last}; ++struct au_wbr { ++ struct au_rwsem wbr_wh_rwsem; ++ struct dentry *wbr_wh[AuBrWh_Last]; ++ atomic_t wbr_wh_running; ++#define wbr_whbase wbr_wh[AuBrWh_BASE] /* whiteout base */ ++#define wbr_plink wbr_wh[AuBrWh_PLINK] /* pseudo-link dir */ ++#define wbr_orph wbr_wh[AuBrWh_ORPH] /* dir for orphans */ ++ ++ /* mfs mode */ ++ unsigned long long wbr_bytes; ++}; ++ ++/* ext2 has 3 types of operations at least, ext3 has 4 */ ++#define AuBrDynOp (AuDyLast * 4) ++ ++#ifdef CONFIG_AUFS_HFSNOTIFY ++/* support for asynchronous destruction */ ++struct au_br_hfsnotify { ++ struct fsnotify_group *hfsn_group; ++}; ++#endif ++ ++/* sysfs entries */ ++struct au_brsysfs { ++ char name[16]; ++ struct attribute attr; ++}; ++ ++enum { ++ AuBrSysfs_BR, ++ AuBrSysfs_BRID, ++ AuBrSysfs_Last ++}; ++ ++/* protected by superblock rwsem */ ++struct au_branch { ++ struct au_xino *br_xino; ++ ++ aufs_bindex_t br_id; ++ ++ int br_perm; ++ struct path br_path; ++ spinlock_t br_dykey_lock; ++ struct au_dykey *br_dykey[AuBrDynOp]; ++ struct percpu_counter br_count; ++ ++ struct au_wbr *br_wbr; ++ struct au_br_fhsm *br_fhsm; ++ ++#ifdef CONFIG_AUFS_HFSNOTIFY ++ struct au_br_hfsnotify *br_hfsn; ++#endif ++ ++#ifdef CONFIG_SYSFS ++ /* entries under sysfs per mount-point */ ++ struct au_brsysfs br_sysfs[AuBrSysfs_Last]; ++#endif ++ ++#ifdef CONFIG_DEBUG_FS ++ struct dentry *br_dbgaufs; /* xino */ ++#endif ++ ++ struct au_dr_br br_dirren; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct vfsmount *au_br_mnt(struct au_branch *br) ++{ ++ return br->br_path.mnt; ++} ++ ++static inline struct dentry *au_br_dentry(struct au_branch *br) ++{ ++ return br->br_path.dentry; ++} ++ ++static inline struct super_block *au_br_sb(struct au_branch *br) ++{ ++ return au_br_mnt(br)->mnt_sb; ++} ++ ++static inline void au_br_get(struct au_branch *br) ++{ ++ percpu_counter_inc(&br->br_count); ++} ++ ++static inline void au_br_put(struct au_branch *br) ++{ ++ percpu_counter_dec(&br->br_count); ++} ++ ++static inline s64 au_br_count(struct au_branch *br) ++{ ++ return percpu_counter_sum(&br->br_count); ++} ++ ++static inline void au_br_count_init(struct au_branch *br) ++{ ++ percpu_counter_init(&br->br_count, 0, GFP_NOFS); ++} ++ ++static inline void au_br_count_fin(struct au_branch *br) ++{ ++ percpu_counter_destroy(&br->br_count); ++} ++ ++static inline int au_br_rdonly(struct au_branch *br) ++{ ++ return ((au_br_sb(br)->s_flags & MS_RDONLY) ++ || !au_br_writable(br->br_perm)) ++ ? -EROFS : 0; ++} ++ ++static inline int au_br_hnotifyable(int brperm __maybe_unused) ++{ ++#ifdef CONFIG_AUFS_HNOTIFY ++ return !(brperm & AuBrPerm_RR); ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_br_test_oflag(int oflag, struct au_branch *br) ++{ ++ int err, exec_flag; ++ ++ err = 0; ++ exec_flag = oflag & __FMODE_EXEC; ++ if (unlikely(exec_flag && path_noexec(&br->br_path))) ++ err = -EACCES; ++ ++ return err; ++} ++ ++static inline void au_xino_get(struct au_branch *br) ++{ ++ struct au_xino *xi; ++ ++ xi = br->br_xino; ++ if (xi) ++ kref_get(&xi->xi_kref); ++} ++ ++static inline int au_xino_count(struct au_branch *br) ++{ ++ int v; ++ struct au_xino *xi; ++ ++ v = 0; ++ xi = br->br_xino; ++ if (xi) ++ v = atomic_read(&xi->xi_kref.refcount); ++ ++ return v; ++} ++ ++static inline struct file *au_xino_file(struct au_branch *br) ++{ ++ struct au_xino *xi; ++ ++ xi = br->br_xino; ++ return xi ? xi->xi_file : NULL; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* branch.c */ ++struct au_sbinfo; ++void au_br_free(struct au_sbinfo *sinfo); ++int au_br_index(struct super_block *sb, aufs_bindex_t br_id); ++struct au_opt_add; ++int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount); ++struct au_opt_del; ++int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount); ++long au_ibusy_ioctl(struct file *file, unsigned long arg); ++#ifdef CONFIG_COMPAT ++long au_ibusy_compat_ioctl(struct file *file, unsigned long arg); ++#endif ++struct au_opt_mod; ++int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount, ++ int *do_refresh); ++struct aufs_stfs; ++int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs); ++ ++/* xino.c */ ++static const loff_t au_loff_max = LLONG_MAX; ++ ++struct file *au_xino_create(struct super_block *sb, char *fpath, int silent); ++struct file *au_xino_create2(struct super_block *sb, struct path *base, ++ struct file *copy_src); ++ ++int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ ino_t *ino); ++int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ ino_t ino); ++ssize_t xino_fread(vfs_readf_t func, struct file *file, void *buf, size_t size, ++ loff_t *pos); ++ssize_t xino_fwrite(vfs_writef_t func, struct file *file, void *buf, ++ size_t size, loff_t *pos); ++ ++int au_xib_trunc(struct super_block *sb); ++int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex); ++ ++struct au_xino *au_xino_alloc(void); ++int au_xino_put(struct au_branch *br); ++void au_xino_file_set(struct au_branch *br, struct file *file); ++ ++struct au_opt_xino; ++void au_xino_clr(struct super_block *sb); ++int au_xino_set(struct super_block *sb, struct au_opt_xino *xiopt, int remount); ++struct file *au_xino_def(struct super_block *sb); ++int au_xino_init_br(struct super_block *sb, struct au_branch *br, ino_t hino, ++ struct path *base); ++ ++ino_t au_xino_new_ino(struct super_block *sb); ++void au_xino_delete_inode(struct inode *inode, const int unlinked); ++ ++void au_xinondir_leave(struct super_block *sb, aufs_bindex_t bindex, ++ ino_t h_ino, int idx); ++int au_xinondir_enter(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ int *idx); ++ ++int au_xino_path(struct seq_file *seq, struct file *file); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* Superblock to branch */ ++static inline ++aufs_bindex_t au_sbr_id(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_sbr(sb, bindex)->br_id; ++} ++ ++static inline ++struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_br_mnt(au_sbr(sb, bindex)); ++} ++ ++static inline ++struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_br_sb(au_sbr(sb, bindex)); ++} ++ ++static inline void au_sbr_get(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ au_br_get(au_sbr(sb, bindex)); ++} ++ ++static inline void au_sbr_put(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ au_br_put(au_sbr(sb, bindex)); ++} ++ ++static inline int au_sbr_perm(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_sbr(sb, bindex)->br_perm; ++} ++ ++static inline int au_sbr_whable(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_br_whable(au_sbr_perm(sb, bindex)); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * wbr_wh_read_lock, wbr_wh_write_lock ++ * wbr_wh_read_unlock, wbr_wh_write_unlock, wbr_wh_downgrade_lock ++ */ ++AuSimpleRwsemFuncs(wbr_wh, struct au_wbr *wbr, &wbr->wbr_wh_rwsem); ++ ++#define WbrWhMustNoWaiters(wbr) AuRwMustNoWaiters(&wbr->wbr_wh_rwsem) ++#define WbrWhMustAnyLock(wbr) AuRwMustAnyLock(&wbr->wbr_wh_rwsem) ++#define WbrWhMustWriteLock(wbr) AuRwMustWriteLock(&wbr->wbr_wh_rwsem) ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_FHSM ++static inline void au_br_fhsm_init(struct au_br_fhsm *brfhsm) ++{ ++ mutex_init(&brfhsm->bf_lock); ++ brfhsm->bf_jiffy = 0; ++ brfhsm->bf_readable = 0; ++} ++ ++static inline void au_br_fhsm_fin(struct au_br_fhsm *brfhsm) ++{ ++ mutex_destroy(&brfhsm->bf_lock); ++} ++#else ++AuStubVoid(au_br_fhsm_init, struct au_br_fhsm *brfhsm) ++AuStubVoid(au_br_fhsm_fin, struct au_br_fhsm *brfhsm) ++#endif ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_BRANCH_H__ */ +diff --git a/fs/aufs/conf.mk b/fs/aufs/conf.mk +new file mode 100644 +index 00000000..bf3c3a4f +--- /dev/null ++++ b/fs/aufs/conf.mk +@@ -0,0 +1,39 @@ ++ ++AuConfStr = CONFIG_AUFS_FS=${CONFIG_AUFS_FS} ++ ++define AuConf ++ifdef ${1} ++AuConfStr += ${1}=${${1}} ++endif ++endef ++ ++AuConfAll = BRANCH_MAX_127 BRANCH_MAX_511 BRANCH_MAX_1023 BRANCH_MAX_32767 \ ++ SBILIST \ ++ HNOTIFY HFSNOTIFY \ ++ EXPORT INO_T_64 \ ++ XATTR \ ++ FHSM \ ++ RDU \ ++ DIRREN \ ++ SHWH \ ++ BR_RAMFS \ ++ BR_FUSE POLL \ ++ BR_HFSPLUS \ ++ BDEV_LOOP \ ++ DEBUG MAGIC_SYSRQ ++$(foreach i, ${AuConfAll}, \ ++ $(eval $(call AuConf,CONFIG_AUFS_${i}))) ++ ++AuConfName = ${obj}/conf.str ++${AuConfName}.tmp: FORCE ++ @echo ${AuConfStr} | tr ' ' '\n' | sed -e 's/^/"/' -e 's/$$/\\n"/' > $@ ++${AuConfName}: ${AuConfName}.tmp ++ @diff -q $< $@ > /dev/null 2>&1 || { \ ++ echo ' GEN ' $@; \ ++ cp -p $< $@; \ ++ } ++FORCE: ++clean-files += ${AuConfName} ${AuConfName}.tmp ++${obj}/sysfs.o: ${AuConfName} ++ ++-include ${srctree}/${src}/conf_priv.mk +diff --git a/fs/aufs/cpup.c b/fs/aufs/cpup.c +new file mode 100644 +index 00000000..98258a95 +--- /dev/null ++++ b/fs/aufs/cpup.c +@@ -0,0 +1,1413 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * copy-up functions, see wbr_policy.c for copy-down ++ */ ++ ++#include ++#include ++#include ++#include "aufs.h" ++ ++void au_cpup_attr_flags(struct inode *dst, unsigned int iflags) ++{ ++ const unsigned int mask = S_DEAD | S_SWAPFILE | S_PRIVATE ++ | S_NOATIME | S_NOCMTIME | S_AUTOMOUNT; ++ ++ BUILD_BUG_ON(sizeof(iflags) != sizeof(dst->i_flags)); ++ ++ dst->i_flags |= iflags & ~mask; ++ if (au_test_fs_notime(dst->i_sb)) ++ dst->i_flags |= S_NOATIME | S_NOCMTIME; ++} ++ ++void au_cpup_attr_timesizes(struct inode *inode) ++{ ++ struct inode *h_inode; ++ ++ h_inode = au_h_iptr(inode, au_ibtop(inode)); ++ fsstack_copy_attr_times(inode, h_inode); ++ fsstack_copy_inode_size(inode, h_inode); ++} ++ ++void au_cpup_attr_nlink(struct inode *inode, int force) ++{ ++ struct inode *h_inode; ++ struct super_block *sb; ++ aufs_bindex_t bindex, bbot; ++ ++ sb = inode->i_sb; ++ bindex = au_ibtop(inode); ++ h_inode = au_h_iptr(inode, bindex); ++ if (!force ++ && !S_ISDIR(h_inode->i_mode) ++ && au_opt_test(au_mntflags(sb), PLINK) ++ && au_plink_test(inode)) ++ return; ++ ++ /* ++ * 0 can happen in revalidating. ++ * h_inode->i_mutex may not be held here, but it is harmless since once ++ * i_nlink reaches 0, it will never become positive except O_TMPFILE ++ * case. ++ * todo: O_TMPFILE+linkat(AT_SYMLINK_FOLLOW) bypassing aufs may cause ++ * the incorrect link count. ++ */ ++ set_nlink(inode, h_inode->i_nlink); ++ ++ /* ++ * fewer nlink makes find(1) noisy, but larger nlink doesn't. ++ * it may includes whplink directory. ++ */ ++ if (S_ISDIR(h_inode->i_mode)) { ++ bbot = au_ibbot(inode); ++ for (bindex++; bindex <= bbot; bindex++) { ++ h_inode = au_h_iptr(inode, bindex); ++ if (h_inode) ++ au_add_nlink(inode, h_inode); ++ } ++ } ++} ++ ++void au_cpup_attr_changeable(struct inode *inode) ++{ ++ struct inode *h_inode; ++ ++ h_inode = au_h_iptr(inode, au_ibtop(inode)); ++ inode->i_mode = h_inode->i_mode; ++ inode->i_uid = h_inode->i_uid; ++ inode->i_gid = h_inode->i_gid; ++ au_cpup_attr_timesizes(inode); ++ au_cpup_attr_flags(inode, h_inode->i_flags); ++} ++ ++void au_cpup_igen(struct inode *inode, struct inode *h_inode) ++{ ++ struct au_iinfo *iinfo = au_ii(inode); ++ ++ IiMustWriteLock(inode); ++ ++ iinfo->ii_higen = h_inode->i_generation; ++ iinfo->ii_hsb1 = h_inode->i_sb; ++} ++ ++void au_cpup_attr_all(struct inode *inode, int force) ++{ ++ struct inode *h_inode; ++ ++ h_inode = au_h_iptr(inode, au_ibtop(inode)); ++ au_cpup_attr_changeable(inode); ++ if (inode->i_nlink > 0) ++ au_cpup_attr_nlink(inode, force); ++ inode->i_rdev = h_inode->i_rdev; ++ inode->i_blkbits = h_inode->i_blkbits; ++ au_cpup_igen(inode, h_inode); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* Note: dt_dentry and dt_h_dentry are not dget/dput-ed */ ++ ++/* keep the timestamps of the parent dir when cpup */ ++void au_dtime_store(struct au_dtime *dt, struct dentry *dentry, ++ struct path *h_path) ++{ ++ struct inode *h_inode; ++ ++ dt->dt_dentry = dentry; ++ dt->dt_h_path = *h_path; ++ h_inode = d_inode(h_path->dentry); ++ dt->dt_atime = h_inode->i_atime; ++ dt->dt_mtime = h_inode->i_mtime; ++ /* smp_mb(); */ ++} ++ ++void au_dtime_revert(struct au_dtime *dt) ++{ ++ struct iattr attr; ++ int err; ++ ++ attr.ia_atime = dt->dt_atime; ++ attr.ia_mtime = dt->dt_mtime; ++ attr.ia_valid = ATTR_FORCE | ATTR_MTIME | ATTR_MTIME_SET ++ | ATTR_ATIME | ATTR_ATIME_SET; ++ ++ /* no delegation since this is a directory */ ++ err = vfsub_notify_change(&dt->dt_h_path, &attr, /*delegated*/NULL); ++ if (unlikely(err)) ++ pr_warn("restoring timestamps failed(%d). ignored\n", err); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* internal use only */ ++struct au_cpup_reg_attr { ++ int valid; ++ struct kstat st; ++ unsigned int iflags; /* inode->i_flags */ ++}; ++ ++static noinline_for_stack ++int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src, ++ struct au_cpup_reg_attr *h_src_attr) ++{ ++ int err, sbits, icex; ++ unsigned int mnt_flags; ++ unsigned char verbose; ++ struct iattr ia; ++ struct path h_path; ++ struct inode *h_isrc, *h_idst; ++ struct kstat *h_st; ++ struct au_branch *br; ++ ++ h_path.dentry = au_h_dptr(dst, bindex); ++ h_idst = d_inode(h_path.dentry); ++ br = au_sbr(dst->d_sb, bindex); ++ h_path.mnt = au_br_mnt(br); ++ h_isrc = d_inode(h_src); ++ ia.ia_valid = ATTR_FORCE | ATTR_UID | ATTR_GID ++ | ATTR_ATIME | ATTR_MTIME ++ | ATTR_ATIME_SET | ATTR_MTIME_SET; ++ if (h_src_attr && h_src_attr->valid) { ++ h_st = &h_src_attr->st; ++ ia.ia_uid = h_st->uid; ++ ia.ia_gid = h_st->gid; ++ ia.ia_atime = h_st->atime; ++ ia.ia_mtime = h_st->mtime; ++ if (h_idst->i_mode != h_st->mode ++ && !S_ISLNK(h_idst->i_mode)) { ++ ia.ia_valid |= ATTR_MODE; ++ ia.ia_mode = h_st->mode; ++ } ++ sbits = !!(h_st->mode & (S_ISUID | S_ISGID)); ++ au_cpup_attr_flags(h_idst, h_src_attr->iflags); ++ } else { ++ ia.ia_uid = h_isrc->i_uid; ++ ia.ia_gid = h_isrc->i_gid; ++ ia.ia_atime = h_isrc->i_atime; ++ ia.ia_mtime = h_isrc->i_mtime; ++ if (h_idst->i_mode != h_isrc->i_mode ++ && !S_ISLNK(h_idst->i_mode)) { ++ ia.ia_valid |= ATTR_MODE; ++ ia.ia_mode = h_isrc->i_mode; ++ } ++ sbits = !!(h_isrc->i_mode & (S_ISUID | S_ISGID)); ++ au_cpup_attr_flags(h_idst, h_isrc->i_flags); ++ } ++ /* no delegation since it is just created */ ++ err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL); ++ ++ /* is this nfs only? */ ++ if (!err && sbits && au_test_nfs(h_path.dentry->d_sb)) { ++ ia.ia_valid = ATTR_FORCE | ATTR_MODE; ++ ia.ia_mode = h_isrc->i_mode; ++ err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL); ++ } ++ ++ icex = br->br_perm & AuBrAttr_ICEX; ++ if (!err) { ++ mnt_flags = au_mntflags(dst->d_sb); ++ verbose = !!au_opt_test(mnt_flags, VERBOSE); ++ err = au_cpup_xattr(h_path.dentry, h_src, icex, verbose); ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_do_copy_file(struct file *dst, struct file *src, loff_t len, ++ char *buf, unsigned long blksize) ++{ ++ int err; ++ size_t sz, rbytes, wbytes; ++ unsigned char all_zero; ++ char *p, *zp; ++ struct inode *h_inode; ++ /* reduce stack usage */ ++ struct iattr *ia; ++ ++ zp = page_address(ZERO_PAGE(0)); ++ if (unlikely(!zp)) ++ return -ENOMEM; /* possible? */ ++ ++ err = 0; ++ all_zero = 0; ++ while (len) { ++ AuDbg("len %lld\n", len); ++ sz = blksize; ++ if (len < blksize) ++ sz = len; ++ ++ rbytes = 0; ++ /* todo: signal_pending? */ ++ while (!rbytes || err == -EAGAIN || err == -EINTR) { ++ rbytes = vfsub_read_k(src, buf, sz, &src->f_pos); ++ err = rbytes; ++ } ++ if (unlikely(err < 0)) ++ break; ++ ++ all_zero = 0; ++ if (len >= rbytes && rbytes == blksize) ++ all_zero = !memcmp(buf, zp, rbytes); ++ if (!all_zero) { ++ wbytes = rbytes; ++ p = buf; ++ while (wbytes) { ++ size_t b; ++ ++ b = vfsub_write_k(dst, p, wbytes, &dst->f_pos); ++ err = b; ++ /* todo: signal_pending? */ ++ if (unlikely(err == -EAGAIN || err == -EINTR)) ++ continue; ++ if (unlikely(err < 0)) ++ break; ++ wbytes -= b; ++ p += b; ++ } ++ if (unlikely(err < 0)) ++ break; ++ } else { ++ loff_t res; ++ ++ AuLabel(hole); ++ res = vfsub_llseek(dst, rbytes, SEEK_CUR); ++ err = res; ++ if (unlikely(res < 0)) ++ break; ++ } ++ len -= rbytes; ++ err = 0; ++ } ++ ++ /* the last block may be a hole */ ++ if (!err && all_zero) { ++ AuLabel(last hole); ++ ++ err = 1; ++ if (au_test_nfs(dst->f_path.dentry->d_sb)) { ++ /* nfs requires this step to make last hole */ ++ /* is this only nfs? */ ++ do { ++ /* todo: signal_pending? */ ++ err = vfsub_write_k(dst, "\0", 1, &dst->f_pos); ++ } while (err == -EAGAIN || err == -EINTR); ++ if (err == 1) ++ dst->f_pos--; ++ } ++ ++ if (err == 1) { ++ ia = (void *)buf; ++ ia->ia_size = dst->f_pos; ++ ia->ia_valid = ATTR_SIZE | ATTR_FILE; ++ ia->ia_file = dst; ++ h_inode = file_inode(dst); ++ inode_lock_nested(h_inode, AuLsc_I_CHILD2); ++ /* no delegation since it is just created */ ++ err = vfsub_notify_change(&dst->f_path, ia, ++ /*delegated*/NULL); ++ inode_unlock(h_inode); ++ } ++ } ++ ++ return err; ++} ++ ++int au_copy_file(struct file *dst, struct file *src, loff_t len) ++{ ++ int err; ++ unsigned long blksize; ++ unsigned char do_kfree; ++ char *buf; ++ ++ err = -ENOMEM; ++ blksize = dst->f_path.dentry->d_sb->s_blocksize; ++ if (!blksize || PAGE_SIZE < blksize) ++ blksize = PAGE_SIZE; ++ AuDbg("blksize %lu\n", blksize); ++ do_kfree = (blksize != PAGE_SIZE && blksize >= sizeof(struct iattr *)); ++ if (do_kfree) ++ buf = kmalloc(blksize, GFP_NOFS); ++ else ++ buf = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!buf)) ++ goto out; ++ ++ if (len > (1 << 22)) ++ AuDbg("copying a large file %lld\n", (long long)len); ++ ++ src->f_pos = 0; ++ dst->f_pos = 0; ++ err = au_do_copy_file(dst, src, len, buf, blksize); ++ if (do_kfree) ++ kfree(buf); ++ else ++ free_page((unsigned long)buf); ++ ++out: ++ return err; ++} ++ ++/* ++ * to support a sparse file which is opened with O_APPEND, ++ * we need to close the file. ++ */ ++static int au_cp_regular(struct au_cp_generic *cpg) ++{ ++ int err, i; ++ enum { SRC, DST }; ++ struct { ++ aufs_bindex_t bindex; ++ unsigned int flags; ++ struct dentry *dentry; ++ int force_wr; ++ struct file *file; ++ void *label; ++ } *f, file[] = { ++ { ++ .bindex = cpg->bsrc, ++ .flags = O_RDONLY | O_NOATIME | O_LARGEFILE, ++ .label = &&out ++ }, ++ { ++ .bindex = cpg->bdst, ++ .flags = O_WRONLY | O_NOATIME | O_LARGEFILE, ++ .force_wr = !!au_ftest_cpup(cpg->flags, RWDST), ++ .label = &&out_src ++ } ++ }; ++ struct super_block *sb, *h_src_sb; ++ struct inode *h_src_inode; ++ struct task_struct *tsk = current; ++ ++ /* bsrc branch can be ro/rw. */ ++ sb = cpg->dentry->d_sb; ++ f = file; ++ for (i = 0; i < 2; i++, f++) { ++ f->dentry = au_h_dptr(cpg->dentry, f->bindex); ++ f->file = au_h_open(cpg->dentry, f->bindex, f->flags, ++ /*file*/NULL, f->force_wr); ++ err = PTR_ERR(f->file); ++ if (IS_ERR(f->file)) ++ goto *f->label; ++ } ++ ++ /* try stopping to update while we copyup */ ++ h_src_inode = d_inode(file[SRC].dentry); ++ h_src_sb = h_src_inode->i_sb; ++ if (!au_test_nfs(h_src_sb)) ++ IMustLock(h_src_inode); ++ ++ if (h_src_sb != file_inode(file[DST].file)->i_sb ++ || !file[DST].file->f_op->clone_file_range) ++ err = au_copy_file(file[DST].file, file[SRC].file, cpg->len); ++ else { ++ if (!au_test_nfs(h_src_sb)) { ++ inode_unlock_shared(h_src_inode); ++ err = vfsub_clone_file_range(file[SRC].file, ++ file[DST].file, cpg->len); ++ vfsub_inode_lock_shared_nested(h_src_inode, ++ AuLsc_I_CHILD); ++ } else ++ err = vfsub_clone_file_range(file[SRC].file, ++ file[DST].file, cpg->len); ++ if (unlikely(err == -EOPNOTSUPP && au_test_nfs(h_src_sb))) ++ /* the backend fs on NFS may not support cloning */ ++ err = au_copy_file(file[DST].file, file[SRC].file, ++ cpg->len); ++ AuTraceErr(err); ++ } ++ ++ /* i wonder if we had O_NO_DELAY_FPUT flag */ ++ if (tsk->flags & PF_KTHREAD) ++ __fput_sync(file[DST].file); ++ else { ++ /* it happened actually */ ++ fput(file[DST].file); ++ /* ++ * too bad. ++ * we have to call both since we don't know which place the file ++ * was added to. ++ */ ++ task_work_run(); ++ flush_delayed_fput(); ++ } ++ au_sbr_put(sb, file[DST].bindex); ++ ++out_src: ++ fput(file[SRC].file); ++ au_sbr_put(sb, file[SRC].bindex); ++out: ++ return err; ++} ++ ++static int au_do_cpup_regular(struct au_cp_generic *cpg, ++ struct au_cpup_reg_attr *h_src_attr) ++{ ++ int err, rerr; ++ loff_t l; ++ struct path h_path; ++ struct inode *h_src_inode, *h_dst_inode; ++ ++ err = 0; ++ h_src_inode = au_h_iptr(d_inode(cpg->dentry), cpg->bsrc); ++ l = i_size_read(h_src_inode); ++ if (cpg->len == -1 || l < cpg->len) ++ cpg->len = l; ++ if (cpg->len) { ++ /* try stopping to update while we are referencing */ ++ vfsub_inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD); ++ au_pin_hdir_unlock(cpg->pin); ++ ++ h_path.dentry = au_h_dptr(cpg->dentry, cpg->bsrc); ++ h_path.mnt = au_sbr_mnt(cpg->dentry->d_sb, cpg->bsrc); ++ h_src_attr->iflags = h_src_inode->i_flags; ++ if (!au_test_nfs(h_src_inode->i_sb)) ++ err = vfs_getattr(&h_path, &h_src_attr->st); ++ else { ++ inode_unlock_shared(h_src_inode); ++ err = vfs_getattr(&h_path, &h_src_attr->st); ++ vfsub_inode_lock_shared_nested(h_src_inode, ++ AuLsc_I_CHILD); ++ } ++ if (unlikely(err)) { ++ inode_unlock_shared(h_src_inode); ++ goto out; ++ } ++ h_src_attr->valid = 1; ++ if (!au_test_nfs(h_src_inode->i_sb)) { ++ err = au_cp_regular(cpg); ++ inode_unlock_shared(h_src_inode); ++ } else { ++ inode_unlock_shared(h_src_inode); ++ err = au_cp_regular(cpg); ++ } ++ rerr = au_pin_hdir_relock(cpg->pin); ++ if (!err && rerr) ++ err = rerr; ++ } ++ if (!err && (h_src_inode->i_state & I_LINKABLE)) { ++ h_path.dentry = au_h_dptr(cpg->dentry, cpg->bdst); ++ h_dst_inode = d_inode(h_path.dentry); ++ spin_lock(&h_dst_inode->i_lock); ++ h_dst_inode->i_state |= I_LINKABLE; ++ spin_unlock(&h_dst_inode->i_lock); ++ } ++ ++out: ++ return err; ++} ++ ++static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src, ++ struct inode *h_dir) ++{ ++ int err, symlen; ++ mm_segment_t old_fs; ++ union { ++ char *k; ++ char __user *u; ++ } sym; ++ struct inode *h_inode = d_inode(h_src); ++ const struct inode_operations *h_iop = h_inode->i_op; ++ ++ err = -ENOSYS; ++ if (unlikely(!h_iop->readlink)) ++ goto out; ++ ++ err = -ENOMEM; ++ sym.k = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!sym.k)) ++ goto out; ++ ++ /* unnecessary to support mmap_sem since symlink is not mmap-able */ ++ old_fs = get_fs(); ++ set_fs(KERNEL_DS); ++ symlen = h_iop->readlink(h_src, sym.u, PATH_MAX); ++ err = symlen; ++ set_fs(old_fs); ++ ++ if (symlen > 0) { ++ sym.k[symlen] = 0; ++ err = vfsub_symlink(h_dir, h_path, sym.k); ++ } ++ free_page((unsigned long)sym.k); ++ ++out: ++ return err; ++} ++ ++/* ++ * regardless 'acl' option, reset all ACL. ++ * All ACL will be copied up later from the original entry on the lower branch. ++ */ ++static int au_reset_acl(struct inode *h_dir, struct path *h_path, umode_t mode) ++{ ++ int err; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ ++ h_dentry = h_path->dentry; ++ h_inode = d_inode(h_dentry); ++ /* forget_all_cached_acls(h_inode)); */ ++ err = vfsub_removexattr(h_dentry, XATTR_NAME_POSIX_ACL_ACCESS); ++ AuTraceErr(err); ++ if (err == -EOPNOTSUPP) ++ err = 0; ++ if (!err) ++ err = vfsub_acl_chmod(h_inode, mode); ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++static int au_do_cpup_dir(struct au_cp_generic *cpg, struct dentry *dst_parent, ++ struct inode *h_dir, struct path *h_path) ++{ ++ int err; ++ struct inode *dir, *inode; ++ ++ err = vfsub_removexattr(h_path->dentry, XATTR_NAME_POSIX_ACL_DEFAULT); ++ AuTraceErr(err); ++ if (err == -EOPNOTSUPP) ++ err = 0; ++ if (unlikely(err)) ++ goto out; ++ ++ /* ++ * strange behaviour from the users view, ++ * particularry setattr case ++ */ ++ dir = d_inode(dst_parent); ++ if (au_ibtop(dir) == cpg->bdst) ++ au_cpup_attr_nlink(dir, /*force*/1); ++ inode = d_inode(cpg->dentry); ++ au_cpup_attr_nlink(inode, /*force*/1); ++ ++out: ++ return err; ++} ++ ++static noinline_for_stack ++int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent, ++ struct au_cpup_reg_attr *h_src_attr) ++{ ++ int err; ++ umode_t mode; ++ unsigned int mnt_flags; ++ unsigned char isdir, isreg, force; ++ const unsigned char do_dt = !!au_ftest_cpup(cpg->flags, DTIME); ++ struct au_dtime dt; ++ struct path h_path; ++ struct dentry *h_src, *h_dst, *h_parent; ++ struct inode *h_inode, *h_dir; ++ struct super_block *sb; ++ ++ /* bsrc branch can be ro/rw. */ ++ h_src = au_h_dptr(cpg->dentry, cpg->bsrc); ++ h_inode = d_inode(h_src); ++ AuDebugOn(h_inode != au_h_iptr(d_inode(cpg->dentry), cpg->bsrc)); ++ ++ /* try stopping to be referenced while we are creating */ ++ h_dst = au_h_dptr(cpg->dentry, cpg->bdst); ++ if (au_ftest_cpup(cpg->flags, RENAME)) ++ AuDebugOn(strncmp(h_dst->d_name.name, AUFS_WH_PFX, ++ AUFS_WH_PFX_LEN)); ++ h_parent = h_dst->d_parent; /* dir inode is locked */ ++ h_dir = d_inode(h_parent); ++ IMustLock(h_dir); ++ AuDebugOn(h_parent != h_dst->d_parent); ++ ++ sb = cpg->dentry->d_sb; ++ h_path.mnt = au_sbr_mnt(sb, cpg->bdst); ++ if (do_dt) { ++ h_path.dentry = h_parent; ++ au_dtime_store(&dt, dst_parent, &h_path); ++ } ++ h_path.dentry = h_dst; ++ ++ isreg = 0; ++ isdir = 0; ++ mode = h_inode->i_mode; ++ switch (mode & S_IFMT) { ++ case S_IFREG: ++ isreg = 1; ++ err = vfsub_create(h_dir, &h_path, 0600, /*want_excl*/true); ++ if (!err) ++ err = au_do_cpup_regular(cpg, h_src_attr); ++ break; ++ case S_IFDIR: ++ isdir = 1; ++ err = vfsub_mkdir(h_dir, &h_path, mode); ++ if (!err) ++ err = au_do_cpup_dir(cpg, dst_parent, h_dir, &h_path); ++ break; ++ case S_IFLNK: ++ err = au_do_cpup_symlink(&h_path, h_src, h_dir); ++ break; ++ case S_IFCHR: ++ case S_IFBLK: ++ AuDebugOn(!capable(CAP_MKNOD)); ++ /*FALLTHROUGH*/ ++ case S_IFIFO: ++ case S_IFSOCK: ++ err = vfsub_mknod(h_dir, &h_path, mode, h_inode->i_rdev); ++ break; ++ default: ++ AuIOErr("Unknown inode type 0%o\n", mode); ++ err = -EIO; ++ } ++ if (!err) ++ err = au_reset_acl(h_dir, &h_path, mode); ++ ++ mnt_flags = au_mntflags(sb); ++ if (!au_opt_test(mnt_flags, UDBA_NONE) ++ && !isdir ++ && au_opt_test(mnt_flags, XINO) ++ && (h_inode->i_nlink == 1 ++ || (h_inode->i_state & I_LINKABLE)) ++ /* todo: unnecessary? */ ++ /* && d_inode(cpg->dentry)->i_nlink == 1 */ ++ && cpg->bdst < cpg->bsrc ++ && !au_ftest_cpup(cpg->flags, KEEPLINO)) ++ au_xino_write(sb, cpg->bsrc, h_inode->i_ino, /*ino*/0); ++ /* ignore this error */ ++ ++ if (!err) { ++ force = 0; ++ if (isreg) { ++ force = !!cpg->len; ++ if (cpg->len == -1) ++ force = !!i_size_read(h_inode); ++ } ++ au_fhsm_wrote(sb, cpg->bdst, force); ++ } ++ ++ if (do_dt) ++ au_dtime_revert(&dt); ++ return err; ++} ++ ++static int au_do_ren_after_cpup(struct au_cp_generic *cpg, struct path *h_path) ++{ ++ int err; ++ struct dentry *dentry, *h_dentry, *h_parent, *parent; ++ struct inode *h_dir; ++ aufs_bindex_t bdst; ++ ++ dentry = cpg->dentry; ++ bdst = cpg->bdst; ++ h_dentry = au_h_dptr(dentry, bdst); ++ if (!au_ftest_cpup(cpg->flags, OVERWRITE)) { ++ dget(h_dentry); ++ au_set_h_dptr(dentry, bdst, NULL); ++ err = au_lkup_neg(dentry, bdst, /*wh*/0); ++ if (!err) ++ h_path->dentry = dget(au_h_dptr(dentry, bdst)); ++ au_set_h_dptr(dentry, bdst, h_dentry); ++ } else { ++ err = 0; ++ parent = dget_parent(dentry); ++ h_parent = au_h_dptr(parent, bdst); ++ dput(parent); ++ h_path->dentry = vfsub_lkup_one(&dentry->d_name, h_parent); ++ if (IS_ERR(h_path->dentry)) ++ err = PTR_ERR(h_path->dentry); ++ } ++ if (unlikely(err)) ++ goto out; ++ ++ h_parent = h_dentry->d_parent; /* dir inode is locked */ ++ h_dir = d_inode(h_parent); ++ IMustLock(h_dir); ++ AuDbg("%pd %pd\n", h_dentry, h_path->dentry); ++ /* no delegation since it is just created */ ++ err = vfsub_rename(h_dir, h_dentry, h_dir, h_path, /*delegated*/NULL, ++ /*flags*/0); ++ dput(h_path->dentry); ++ ++out: ++ return err; ++} ++ ++/* ++ * copyup the @dentry from @bsrc to @bdst. ++ * the caller must set the both of lower dentries. ++ * @len is for truncating when it is -1 copyup the entire file. ++ * in link/rename cases, @dst_parent may be different from the real one. ++ * basic->bsrc can be larger than basic->bdst. ++ * aufs doesn't touch the credential so ++ * security_inode_copy_up{,_xattr}() are unnecrssary. ++ */ ++static int au_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent) ++{ ++ int err, rerr; ++ aufs_bindex_t old_ibtop; ++ unsigned char isdir, plink; ++ struct dentry *h_src, *h_dst, *h_parent; ++ struct inode *dst_inode, *h_dir, *inode, *delegated, *src_inode; ++ struct super_block *sb; ++ struct au_branch *br; ++ /* to reuduce stack size */ ++ struct { ++ struct au_dtime dt; ++ struct path h_path; ++ struct au_cpup_reg_attr h_src_attr; ++ } *a; ++ ++ err = -ENOMEM; ++ a = kmalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ a->h_src_attr.valid = 0; ++ ++ sb = cpg->dentry->d_sb; ++ br = au_sbr(sb, cpg->bdst); ++ a->h_path.mnt = au_br_mnt(br); ++ h_dst = au_h_dptr(cpg->dentry, cpg->bdst); ++ h_parent = h_dst->d_parent; /* dir inode is locked */ ++ h_dir = d_inode(h_parent); ++ IMustLock(h_dir); ++ ++ h_src = au_h_dptr(cpg->dentry, cpg->bsrc); ++ inode = d_inode(cpg->dentry); ++ ++ if (!dst_parent) ++ dst_parent = dget_parent(cpg->dentry); ++ else ++ dget(dst_parent); ++ ++ plink = !!au_opt_test(au_mntflags(sb), PLINK); ++ dst_inode = au_h_iptr(inode, cpg->bdst); ++ if (dst_inode) { ++ if (unlikely(!plink)) { ++ err = -EIO; ++ AuIOErr("hi%lu(i%lu) exists on b%d " ++ "but plink is disabled\n", ++ dst_inode->i_ino, inode->i_ino, cpg->bdst); ++ goto out_parent; ++ } ++ ++ if (dst_inode->i_nlink) { ++ const int do_dt = au_ftest_cpup(cpg->flags, DTIME); ++ ++ h_src = au_plink_lkup(inode, cpg->bdst); ++ err = PTR_ERR(h_src); ++ if (IS_ERR(h_src)) ++ goto out_parent; ++ if (unlikely(d_is_negative(h_src))) { ++ err = -EIO; ++ AuIOErr("i%lu exists on b%d " ++ "but not pseudo-linked\n", ++ inode->i_ino, cpg->bdst); ++ dput(h_src); ++ goto out_parent; ++ } ++ ++ if (do_dt) { ++ a->h_path.dentry = h_parent; ++ au_dtime_store(&a->dt, dst_parent, &a->h_path); ++ } ++ ++ a->h_path.dentry = h_dst; ++ delegated = NULL; ++ err = vfsub_link(h_src, h_dir, &a->h_path, &delegated); ++ if (!err && au_ftest_cpup(cpg->flags, RENAME)) ++ err = au_do_ren_after_cpup(cpg, &a->h_path); ++ if (do_dt) ++ au_dtime_revert(&a->dt); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal link\n"); ++ iput(delegated); ++ } ++ dput(h_src); ++ goto out_parent; ++ } else ++ /* todo: cpup_wh_file? */ ++ /* udba work */ ++ au_update_ibrange(inode, /*do_put_zero*/1); ++ } ++ ++ isdir = S_ISDIR(inode->i_mode); ++ old_ibtop = au_ibtop(inode); ++ err = cpup_entry(cpg, dst_parent, &a->h_src_attr); ++ if (unlikely(err)) ++ goto out_rev; ++ dst_inode = d_inode(h_dst); ++ inode_lock_nested(dst_inode, AuLsc_I_CHILD2); ++ /* todo: necessary? */ ++ /* au_pin_hdir_unlock(cpg->pin); */ ++ ++ err = cpup_iattr(cpg->dentry, cpg->bdst, h_src, &a->h_src_attr); ++ if (unlikely(err)) { ++ /* todo: necessary? */ ++ /* au_pin_hdir_relock(cpg->pin); */ /* ignore an error */ ++ inode_unlock(dst_inode); ++ goto out_rev; ++ } ++ ++ if (cpg->bdst < old_ibtop) { ++ if (S_ISREG(inode->i_mode)) { ++ err = au_dy_iaop(inode, cpg->bdst, dst_inode); ++ if (unlikely(err)) { ++ /* ignore an error */ ++ /* au_pin_hdir_relock(cpg->pin); */ ++ inode_unlock(dst_inode); ++ goto out_rev; ++ } ++ } ++ au_set_ibtop(inode, cpg->bdst); ++ } else ++ au_set_ibbot(inode, cpg->bdst); ++ au_set_h_iptr(inode, cpg->bdst, au_igrab(dst_inode), ++ au_hi_flags(inode, isdir)); ++ ++ /* todo: necessary? */ ++ /* err = au_pin_hdir_relock(cpg->pin); */ ++ inode_unlock(dst_inode); ++ if (unlikely(err)) ++ goto out_rev; ++ ++ src_inode = d_inode(h_src); ++ if (!isdir ++ && (src_inode->i_nlink > 1 ++ || src_inode->i_state & I_LINKABLE) ++ && plink) ++ au_plink_append(inode, cpg->bdst, h_dst); ++ ++ if (au_ftest_cpup(cpg->flags, RENAME)) { ++ a->h_path.dentry = h_dst; ++ err = au_do_ren_after_cpup(cpg, &a->h_path); ++ } ++ if (!err) ++ goto out_parent; /* success */ ++ ++ /* revert */ ++out_rev: ++ a->h_path.dentry = h_parent; ++ au_dtime_store(&a->dt, dst_parent, &a->h_path); ++ a->h_path.dentry = h_dst; ++ rerr = 0; ++ if (d_is_positive(h_dst)) { ++ if (!isdir) { ++ /* no delegation since it is just created */ ++ rerr = vfsub_unlink(h_dir, &a->h_path, ++ /*delegated*/NULL, /*force*/0); ++ } else ++ rerr = vfsub_rmdir(h_dir, &a->h_path); ++ } ++ au_dtime_revert(&a->dt); ++ if (rerr) { ++ AuIOErr("failed removing broken entry(%d, %d)\n", err, rerr); ++ err = -EIO; ++ } ++out_parent: ++ dput(dst_parent); ++ kfree(a); ++out: ++ return err; ++} ++ ++#if 0 /* reserved */ ++struct au_cpup_single_args { ++ int *errp; ++ struct au_cp_generic *cpg; ++ struct dentry *dst_parent; ++}; ++ ++static void au_call_cpup_single(void *args) ++{ ++ struct au_cpup_single_args *a = args; ++ ++ au_pin_hdir_acquire_nest(a->cpg->pin); ++ *a->errp = au_cpup_single(a->cpg, a->dst_parent); ++ au_pin_hdir_release(a->cpg->pin); ++} ++#endif ++ ++/* ++ * prevent SIGXFSZ in copy-up. ++ * testing CAP_MKNOD is for generic fs, ++ * but CAP_FSETID is for xfs only, currently. ++ */ ++static int au_cpup_sio_test(struct au_pin *pin, umode_t mode) ++{ ++ int do_sio; ++ struct super_block *sb; ++ struct inode *h_dir; ++ ++ do_sio = 0; ++ sb = au_pinned_parent(pin)->d_sb; ++ if (!au_wkq_test() ++ && (!au_sbi(sb)->si_plink_maint_pid ++ || au_plink_maint(sb, AuLock_NOPLM))) { ++ switch (mode & S_IFMT) { ++ case S_IFREG: ++ /* no condition about RLIMIT_FSIZE and the file size */ ++ do_sio = 1; ++ break; ++ case S_IFCHR: ++ case S_IFBLK: ++ do_sio = !capable(CAP_MKNOD); ++ break; ++ } ++ if (!do_sio) ++ do_sio = ((mode & (S_ISUID | S_ISGID)) ++ && !capable(CAP_FSETID)); ++ /* this workaround may be removed in the future */ ++ if (!do_sio) { ++ h_dir = au_pinned_h_dir(pin); ++ do_sio = h_dir->i_mode & S_ISVTX; ++ } ++ } ++ ++ return do_sio; ++} ++ ++#if 0 /* reserved */ ++int au_sio_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent) ++{ ++ int err, wkq_err; ++ struct dentry *h_dentry; ++ ++ h_dentry = au_h_dptr(cpg->dentry, cpg->bsrc); ++ if (!au_cpup_sio_test(pin, d_inode(h_dentry)->i_mode)) ++ err = au_cpup_single(cpg, dst_parent); ++ else { ++ struct au_cpup_single_args args = { ++ .errp = &err, ++ .cpg = cpg, ++ .dst_parent = dst_parent ++ }; ++ wkq_err = au_wkq_wait(au_call_cpup_single, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ return err; ++} ++#endif ++ ++/* ++ * copyup the @dentry from the first active lower branch to @bdst, ++ * using au_cpup_single(). ++ */ ++static int au_cpup_simple(struct au_cp_generic *cpg) ++{ ++ int err; ++ unsigned int flags_orig; ++ struct dentry *dentry; ++ ++ AuDebugOn(cpg->bsrc < 0); ++ ++ dentry = cpg->dentry; ++ DiMustWriteLock(dentry); ++ ++ err = au_lkup_neg(dentry, cpg->bdst, /*wh*/1); ++ if (!err) { ++ flags_orig = cpg->flags; ++ au_fset_cpup(cpg->flags, RENAME); ++ err = au_cpup_single(cpg, NULL); ++ cpg->flags = flags_orig; ++ if (!err) ++ return 0; /* success */ ++ ++ /* revert */ ++ au_set_h_dptr(dentry, cpg->bdst, NULL); ++ au_set_dbtop(dentry, cpg->bsrc); ++ } ++ ++ return err; ++} ++ ++struct au_cpup_simple_args { ++ int *errp; ++ struct au_cp_generic *cpg; ++}; ++ ++static void au_call_cpup_simple(void *args) ++{ ++ struct au_cpup_simple_args *a = args; ++ ++ au_pin_hdir_acquire_nest(a->cpg->pin); ++ *a->errp = au_cpup_simple(a->cpg); ++ au_pin_hdir_release(a->cpg->pin); ++} ++ ++static int au_do_sio_cpup_simple(struct au_cp_generic *cpg) ++{ ++ int err, wkq_err; ++ struct dentry *dentry, *parent; ++ struct file *h_file; ++ struct inode *h_dir; ++ ++ dentry = cpg->dentry; ++ h_file = NULL; ++ if (au_ftest_cpup(cpg->flags, HOPEN)) { ++ AuDebugOn(cpg->bsrc < 0); ++ h_file = au_h_open_pre(dentry, cpg->bsrc, /*force_wr*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ } ++ ++ parent = dget_parent(dentry); ++ h_dir = au_h_iptr(d_inode(parent), cpg->bdst); ++ if (!au_test_h_perm_sio(h_dir, MAY_EXEC | MAY_WRITE) ++ && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode)) ++ err = au_cpup_simple(cpg); ++ else { ++ struct au_cpup_simple_args args = { ++ .errp = &err, ++ .cpg = cpg ++ }; ++ wkq_err = au_wkq_wait(au_call_cpup_simple, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ dput(parent); ++ if (h_file) ++ au_h_open_post(dentry, cpg->bsrc, h_file); ++ ++out: ++ return err; ++} ++ ++int au_sio_cpup_simple(struct au_cp_generic *cpg) ++{ ++ aufs_bindex_t bsrc, bbot; ++ struct dentry *dentry, *h_dentry; ++ ++ if (cpg->bsrc < 0) { ++ dentry = cpg->dentry; ++ bbot = au_dbbot(dentry); ++ for (bsrc = cpg->bdst + 1; bsrc <= bbot; bsrc++) { ++ h_dentry = au_h_dptr(dentry, bsrc); ++ if (h_dentry) { ++ AuDebugOn(d_is_negative(h_dentry)); ++ break; ++ } ++ } ++ AuDebugOn(bsrc > bbot); ++ cpg->bsrc = bsrc; ++ } ++ AuDebugOn(cpg->bsrc <= cpg->bdst); ++ return au_do_sio_cpup_simple(cpg); ++} ++ ++int au_sio_cpdown_simple(struct au_cp_generic *cpg) ++{ ++ AuDebugOn(cpg->bdst <= cpg->bsrc); ++ return au_do_sio_cpup_simple(cpg); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * copyup the deleted file for writing. ++ */ ++static int au_do_cpup_wh(struct au_cp_generic *cpg, struct dentry *wh_dentry, ++ struct file *file) ++{ ++ int err; ++ unsigned int flags_orig; ++ aufs_bindex_t bsrc_orig; ++ struct au_dinfo *dinfo; ++ struct { ++ struct au_hdentry *hd; ++ struct dentry *h_dentry; ++ } hdst, hsrc; ++ ++ dinfo = au_di(cpg->dentry); ++ AuRwMustWriteLock(&dinfo->di_rwsem); ++ ++ bsrc_orig = cpg->bsrc; ++ cpg->bsrc = dinfo->di_btop; ++ hdst.hd = au_hdentry(dinfo, cpg->bdst); ++ hdst.h_dentry = hdst.hd->hd_dentry; ++ hdst.hd->hd_dentry = wh_dentry; ++ dinfo->di_btop = cpg->bdst; ++ ++ hsrc.h_dentry = NULL; ++ if (file) { ++ hsrc.hd = au_hdentry(dinfo, cpg->bsrc); ++ hsrc.h_dentry = hsrc.hd->hd_dentry; ++ hsrc.hd->hd_dentry = au_hf_top(file)->f_path.dentry; ++ } ++ flags_orig = cpg->flags; ++ cpg->flags = !AuCpup_DTIME; ++ err = au_cpup_single(cpg, /*h_parent*/NULL); ++ cpg->flags = flags_orig; ++ if (file) { ++ if (!err) ++ err = au_reopen_nondir(file); ++ hsrc.hd->hd_dentry = hsrc.h_dentry; ++ } ++ hdst.hd->hd_dentry = hdst.h_dentry; ++ dinfo->di_btop = cpg->bsrc; ++ cpg->bsrc = bsrc_orig; ++ ++ return err; ++} ++ ++static int au_cpup_wh(struct au_cp_generic *cpg, struct file *file) ++{ ++ int err; ++ aufs_bindex_t bdst; ++ struct au_dtime dt; ++ struct dentry *dentry, *parent, *h_parent, *wh_dentry; ++ struct au_branch *br; ++ struct path h_path; ++ ++ dentry = cpg->dentry; ++ bdst = cpg->bdst; ++ br = au_sbr(dentry->d_sb, bdst); ++ parent = dget_parent(dentry); ++ h_parent = au_h_dptr(parent, bdst); ++ wh_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out; ++ ++ h_path.dentry = h_parent; ++ h_path.mnt = au_br_mnt(br); ++ au_dtime_store(&dt, parent, &h_path); ++ err = au_do_cpup_wh(cpg, wh_dentry, file); ++ if (unlikely(err)) ++ goto out_wh; ++ ++ dget(wh_dentry); ++ h_path.dentry = wh_dentry; ++ if (!d_is_dir(wh_dentry)) { ++ /* no delegation since it is just created */ ++ err = vfsub_unlink(d_inode(h_parent), &h_path, ++ /*delegated*/NULL, /*force*/0); ++ } else ++ err = vfsub_rmdir(d_inode(h_parent), &h_path); ++ if (unlikely(err)) { ++ AuIOErr("failed remove copied-up tmp file %pd(%d)\n", ++ wh_dentry, err); ++ err = -EIO; ++ } ++ au_dtime_revert(&dt); ++ au_set_hi_wh(d_inode(dentry), bdst, wh_dentry); ++ ++out_wh: ++ dput(wh_dentry); ++out: ++ dput(parent); ++ return err; ++} ++ ++struct au_cpup_wh_args { ++ int *errp; ++ struct au_cp_generic *cpg; ++ struct file *file; ++}; ++ ++static void au_call_cpup_wh(void *args) ++{ ++ struct au_cpup_wh_args *a = args; ++ ++ au_pin_hdir_acquire_nest(a->cpg->pin); ++ *a->errp = au_cpup_wh(a->cpg, a->file); ++ au_pin_hdir_release(a->cpg->pin); ++} ++ ++int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file) ++{ ++ int err, wkq_err; ++ aufs_bindex_t bdst; ++ struct dentry *dentry, *parent, *h_orph, *h_parent; ++ struct inode *dir, *h_dir, *h_tmpdir; ++ struct au_wbr *wbr; ++ struct au_pin wh_pin, *pin_orig; ++ ++ dentry = cpg->dentry; ++ bdst = cpg->bdst; ++ parent = dget_parent(dentry); ++ dir = d_inode(parent); ++ h_orph = NULL; ++ h_parent = NULL; ++ h_dir = au_igrab(au_h_iptr(dir, bdst)); ++ h_tmpdir = h_dir; ++ pin_orig = NULL; ++ if (!h_dir->i_nlink) { ++ wbr = au_sbr(dentry->d_sb, bdst)->br_wbr; ++ h_orph = wbr->wbr_orph; ++ ++ h_parent = dget(au_h_dptr(parent, bdst)); ++ au_set_h_dptr(parent, bdst, dget(h_orph)); ++ h_tmpdir = d_inode(h_orph); ++ au_set_h_iptr(dir, bdst, au_igrab(h_tmpdir), /*flags*/0); ++ ++ inode_lock_nested(h_tmpdir, AuLsc_I_PARENT3); ++ /* todo: au_h_open_pre()? */ ++ ++ pin_orig = cpg->pin; ++ au_pin_init(&wh_pin, dentry, bdst, AuLsc_DI_PARENT, ++ AuLsc_I_PARENT3, cpg->pin->udba, AuPin_DI_LOCKED); ++ cpg->pin = &wh_pin; ++ } ++ ++ if (!au_test_h_perm_sio(h_tmpdir, MAY_EXEC | MAY_WRITE) ++ && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode)) ++ err = au_cpup_wh(cpg, file); ++ else { ++ struct au_cpup_wh_args args = { ++ .errp = &err, ++ .cpg = cpg, ++ .file = file ++ }; ++ wkq_err = au_wkq_wait(au_call_cpup_wh, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ if (h_orph) { ++ inode_unlock(h_tmpdir); ++ /* todo: au_h_open_post()? */ ++ au_set_h_iptr(dir, bdst, au_igrab(h_dir), /*flags*/0); ++ au_set_h_dptr(parent, bdst, h_parent); ++ AuDebugOn(!pin_orig); ++ cpg->pin = pin_orig; ++ } ++ iput(h_dir); ++ dput(parent); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * generic routine for both of copy-up and copy-down. ++ */ ++/* cf. revalidate function in file.c */ ++int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst, ++ int (*cp)(struct dentry *dentry, aufs_bindex_t bdst, ++ struct au_pin *pin, ++ struct dentry *h_parent, void *arg), ++ void *arg) ++{ ++ int err; ++ struct au_pin pin; ++ struct dentry *d, *parent, *h_parent, *real_parent, *h_dentry; ++ ++ err = 0; ++ parent = dget_parent(dentry); ++ if (IS_ROOT(parent)) ++ goto out; ++ ++ au_pin_init(&pin, dentry, bdst, AuLsc_DI_PARENT2, AuLsc_I_PARENT2, ++ au_opt_udba(dentry->d_sb), AuPin_MNT_WRITE); ++ ++ /* do not use au_dpage */ ++ real_parent = parent; ++ while (1) { ++ dput(parent); ++ parent = dget_parent(dentry); ++ h_parent = au_h_dptr(parent, bdst); ++ if (h_parent) ++ goto out; /* success */ ++ ++ /* find top dir which is necessary to cpup */ ++ do { ++ d = parent; ++ dput(parent); ++ parent = dget_parent(d); ++ di_read_lock_parent3(parent, !AuLock_IR); ++ h_parent = au_h_dptr(parent, bdst); ++ di_read_unlock(parent, !AuLock_IR); ++ } while (!h_parent); ++ ++ if (d != real_parent) ++ di_write_lock_child3(d); ++ ++ /* somebody else might create while we were sleeping */ ++ h_dentry = au_h_dptr(d, bdst); ++ if (!h_dentry || d_is_negative(h_dentry)) { ++ if (h_dentry) ++ au_update_dbtop(d); ++ ++ au_pin_set_dentry(&pin, d); ++ err = au_do_pin(&pin); ++ if (!err) { ++ err = cp(d, bdst, &pin, h_parent, arg); ++ au_unpin(&pin); ++ } ++ } ++ ++ if (d != real_parent) ++ di_write_unlock(d); ++ if (unlikely(err)) ++ break; ++ } ++ ++out: ++ dput(parent); ++ return err; ++} ++ ++static int au_cpup_dir(struct dentry *dentry, aufs_bindex_t bdst, ++ struct au_pin *pin, ++ struct dentry *h_parent __maybe_unused, ++ void *arg __maybe_unused) ++{ ++ struct au_cp_generic cpg = { ++ .dentry = dentry, ++ .bdst = bdst, ++ .bsrc = -1, ++ .len = 0, ++ .pin = pin, ++ .flags = AuCpup_DTIME ++ }; ++ return au_sio_cpup_simple(&cpg); ++} ++ ++int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) ++{ ++ return au_cp_dirs(dentry, bdst, au_cpup_dir, NULL); ++} ++ ++int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) ++{ ++ int err; ++ struct dentry *parent; ++ struct inode *dir; ++ ++ parent = dget_parent(dentry); ++ dir = d_inode(parent); ++ err = 0; ++ if (au_h_iptr(dir, bdst)) ++ goto out; ++ ++ di_read_unlock(parent, AuLock_IR); ++ di_write_lock_parent(parent); ++ /* someone else might change our inode while we were sleeping */ ++ if (!au_h_iptr(dir, bdst)) ++ err = au_cpup_dirs(dentry, bdst); ++ di_downgrade_lock(parent, AuLock_IR); ++ ++out: ++ dput(parent); ++ return err; ++} +diff --git a/fs/aufs/cpup.h b/fs/aufs/cpup.h +new file mode 100644 +index 00000000..99295266 +--- /dev/null ++++ b/fs/aufs/cpup.h +@@ -0,0 +1,99 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * copy-up/down functions ++ */ ++ ++#ifndef __AUFS_CPUP_H__ ++#define __AUFS_CPUP_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++ ++struct inode; ++struct file; ++struct au_pin; ++ ++void au_cpup_attr_flags(struct inode *dst, unsigned int iflags); ++void au_cpup_attr_timesizes(struct inode *inode); ++void au_cpup_attr_nlink(struct inode *inode, int force); ++void au_cpup_attr_changeable(struct inode *inode); ++void au_cpup_igen(struct inode *inode, struct inode *h_inode); ++void au_cpup_attr_all(struct inode *inode, int force); ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_cp_generic { ++ struct dentry *dentry; ++ aufs_bindex_t bdst, bsrc; ++ loff_t len; ++ struct au_pin *pin; ++ unsigned int flags; ++}; ++ ++/* cpup flags */ ++#define AuCpup_DTIME 1 /* do dtime_store/revert */ ++#define AuCpup_KEEPLINO (1 << 1) /* do not clear the lower xino, ++ for link(2) */ ++#define AuCpup_RENAME (1 << 2) /* rename after cpup */ ++#define AuCpup_HOPEN (1 << 3) /* call h_open_pre/post() in ++ cpup */ ++#define AuCpup_OVERWRITE (1 << 4) /* allow overwriting the ++ existing entry */ ++#define AuCpup_RWDST (1 << 5) /* force write target even if ++ the branch is marked as RO */ ++ ++#ifndef CONFIG_AUFS_BR_HFSPLUS ++#undef AuCpup_HOPEN ++#define AuCpup_HOPEN 0 ++#endif ++ ++#define au_ftest_cpup(flags, name) ((flags) & AuCpup_##name) ++#define au_fset_cpup(flags, name) \ ++ do { (flags) |= AuCpup_##name; } while (0) ++#define au_fclr_cpup(flags, name) \ ++ do { (flags) &= ~AuCpup_##name; } while (0) ++ ++int au_copy_file(struct file *dst, struct file *src, loff_t len); ++int au_sio_cpup_simple(struct au_cp_generic *cpg); ++int au_sio_cpdown_simple(struct au_cp_generic *cpg); ++int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file); ++ ++int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst, ++ int (*cp)(struct dentry *dentry, aufs_bindex_t bdst, ++ struct au_pin *pin, ++ struct dentry *h_parent, void *arg), ++ void *arg); ++int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst); ++int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* keep timestamps when copyup */ ++struct au_dtime { ++ struct dentry *dt_dentry; ++ struct path dt_h_path; ++ struct timespec dt_atime, dt_mtime; ++}; ++void au_dtime_store(struct au_dtime *dt, struct dentry *dentry, ++ struct path *h_path); ++void au_dtime_revert(struct au_dtime *dt); ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_CPUP_H__ */ +diff --git a/fs/aufs/dbgaufs.c b/fs/aufs/dbgaufs.c +new file mode 100644 +index 00000000..0977f4a9 +--- /dev/null ++++ b/fs/aufs/dbgaufs.c +@@ -0,0 +1,477 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * debugfs interface ++ */ ++ ++#include ++#include "aufs.h" ++ ++#ifndef CONFIG_SYSFS ++#error DEBUG_FS depends upon SYSFS ++#endif ++ ++static struct dentry *dbgaufs; ++static const mode_t dbgaufs_mode = 0444; ++ ++/* 20 is max digits length of ulong 64 */ ++struct dbgaufs_arg { ++ int n; ++ char a[20 * 4]; ++}; ++ ++/* ++ * common function for all XINO files ++ */ ++static int dbgaufs_xi_release(struct inode *inode __maybe_unused, ++ struct file *file) ++{ ++ kfree(file->private_data); ++ return 0; ++} ++ ++static int dbgaufs_xi_open(struct file *xf, struct file *file, int do_fcnt, ++ int cnt) ++{ ++ int err; ++ struct kstat st; ++ struct dbgaufs_arg *p; ++ ++ err = -ENOMEM; ++ p = kmalloc(sizeof(*p), GFP_NOFS); ++ if (unlikely(!p)) ++ goto out; ++ ++ err = 0; ++ p->n = 0; ++ file->private_data = p; ++ if (!xf) ++ goto out; ++ ++ err = vfs_getattr(&xf->f_path, &st); ++ if (!err) { ++ if (do_fcnt) ++ p->n = snprintf ++ (p->a, sizeof(p->a), "%d, %llux%lu %lld\n", ++ cnt, st.blocks, st.blksize, ++ (long long)st.size); ++ else ++ p->n = snprintf(p->a, sizeof(p->a), "%llux%lu %lld\n", ++ st.blocks, st.blksize, ++ (long long)st.size); ++ AuDebugOn(p->n >= sizeof(p->a)); ++ } else { ++ p->n = snprintf(p->a, sizeof(p->a), "err %d\n", err); ++ err = 0; ++ } ++ ++out: ++ return err; ++ ++} ++ ++static ssize_t dbgaufs_xi_read(struct file *file, char __user *buf, ++ size_t count, loff_t *ppos) ++{ ++ struct dbgaufs_arg *p; ++ ++ p = file->private_data; ++ return simple_read_from_buffer(buf, count, ppos, p->a, p->n); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct dbgaufs_plink_arg { ++ int n; ++ char a[]; ++}; ++ ++static int dbgaufs_plink_release(struct inode *inode __maybe_unused, ++ struct file *file) ++{ ++ free_page((unsigned long)file->private_data); ++ return 0; ++} ++ ++static int dbgaufs_plink_open(struct inode *inode, struct file *file) ++{ ++ int err, i, limit; ++ unsigned long n, sum; ++ struct dbgaufs_plink_arg *p; ++ struct au_sbinfo *sbinfo; ++ struct super_block *sb; ++ struct hlist_bl_head *hbl; ++ ++ err = -ENOMEM; ++ p = (void *)get_zeroed_page(GFP_NOFS); ++ if (unlikely(!p)) ++ goto out; ++ ++ err = -EFBIG; ++ sbinfo = inode->i_private; ++ sb = sbinfo->si_sb; ++ si_noflush_read_lock(sb); ++ if (au_opt_test(au_mntflags(sb), PLINK)) { ++ limit = PAGE_SIZE - sizeof(p->n); ++ ++ /* the number of buckets */ ++ n = snprintf(p->a + p->n, limit, "%d\n", AuPlink_NHASH); ++ p->n += n; ++ limit -= n; ++ ++ sum = 0; ++ for (i = 0, hbl = sbinfo->si_plink; i < AuPlink_NHASH; ++ i++, hbl++) { ++ n = au_hbl_count(hbl); ++ sum += n; ++ ++ n = snprintf(p->a + p->n, limit, "%lu ", n); ++ p->n += n; ++ limit -= n; ++ if (unlikely(limit <= 0)) ++ goto out_free; ++ } ++ p->a[p->n - 1] = '\n'; ++ ++ /* the sum of plinks */ ++ n = snprintf(p->a + p->n, limit, "%lu\n", sum); ++ p->n += n; ++ limit -= n; ++ if (unlikely(limit <= 0)) ++ goto out_free; ++ } else { ++#define str "1\n0\n0\n" ++ p->n = sizeof(str) - 1; ++ strcpy(p->a, str); ++#undef str ++ } ++ si_read_unlock(sb); ++ ++ err = 0; ++ file->private_data = p; ++ goto out; /* success */ ++ ++out_free: ++ free_page((unsigned long)p); ++out: ++ return err; ++} ++ ++static ssize_t dbgaufs_plink_read(struct file *file, char __user *buf, ++ size_t count, loff_t *ppos) ++{ ++ struct dbgaufs_plink_arg *p; ++ ++ p = file->private_data; ++ return simple_read_from_buffer(buf, count, ppos, p->a, p->n); ++} ++ ++static const struct file_operations dbgaufs_plink_fop = { ++ .owner = THIS_MODULE, ++ .open = dbgaufs_plink_open, ++ .release = dbgaufs_plink_release, ++ .read = dbgaufs_plink_read ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int dbgaufs_xib_open(struct inode *inode, struct file *file) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ struct super_block *sb; ++ ++ sbinfo = inode->i_private; ++ sb = sbinfo->si_sb; ++ si_noflush_read_lock(sb); ++ err = dbgaufs_xi_open(sbinfo->si_xib, file, /*do_fcnt*/0, /*cnt*/0); ++ si_read_unlock(sb); ++ return err; ++} ++ ++static const struct file_operations dbgaufs_xib_fop = { ++ .owner = THIS_MODULE, ++ .open = dbgaufs_xib_open, ++ .release = dbgaufs_xi_release, ++ .read = dbgaufs_xi_read ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++#define DbgaufsXi_PREFIX "xi" ++ ++static int dbgaufs_xino_open(struct inode *inode, struct file *file) ++{ ++ int err; ++ long l; ++ struct au_sbinfo *sbinfo; ++ struct super_block *sb; ++ struct file *xf; ++ struct qstr *name; ++ struct au_branch *br; ++ ++ err = -ENOENT; ++ xf = NULL; ++ name = &file->f_path.dentry->d_name; ++ if (unlikely(name->len < sizeof(DbgaufsXi_PREFIX) ++ || memcmp(name->name, DbgaufsXi_PREFIX, ++ sizeof(DbgaufsXi_PREFIX) - 1))) ++ goto out; ++ err = kstrtol(name->name + sizeof(DbgaufsXi_PREFIX) - 1, 10, &l); ++ if (unlikely(err)) ++ goto out; ++ ++ sbinfo = inode->i_private; ++ sb = sbinfo->si_sb; ++ si_noflush_read_lock(sb); ++ if (l <= au_sbbot(sb)) { ++ br = au_sbr(sb, (aufs_bindex_t)l); ++ xf = au_xino_file(br); ++ err = dbgaufs_xi_open(xf, file, /*do_fcnt*/1, ++ au_xino_count(br)); ++ } else ++ err = -ENOENT; ++ si_read_unlock(sb); ++ ++out: ++ return err; ++} ++ ++static const struct file_operations dbgaufs_xino_fop = { ++ .owner = THIS_MODULE, ++ .open = dbgaufs_xino_open, ++ .release = dbgaufs_xi_release, ++ .read = dbgaufs_xi_read ++}; ++ ++void dbgaufs_xino_del(struct au_branch *br) ++{ ++ struct dentry *dbgaufs; ++ ++ dbgaufs = br->br_dbgaufs; ++ if (!dbgaufs) ++ return; ++ ++ br->br_dbgaufs = NULL; ++ /* debugfs acquires the parent i_mutex */ ++ lockdep_off(); ++ debugfs_remove(dbgaufs); ++ lockdep_on(); ++} ++ ++void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ aufs_bindex_t bbot; ++ struct au_branch *br; ++ ++ if (!au_sbi(sb)->si_dbgaufs) ++ return; ++ ++ bbot = au_sbbot(sb); ++ for (; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ dbgaufs_xino_del(br); ++ } ++} ++ ++static void dbgaufs_br_add(struct super_block *sb, aufs_bindex_t bindex, ++ struct dentry *parent, struct au_sbinfo *sbinfo) ++{ ++ struct au_branch *br; ++ struct dentry *d; ++ char name[sizeof(DbgaufsXi_PREFIX) + 5]; /* "xi" bindex NULL */ ++ ++ snprintf(name, sizeof(name), DbgaufsXi_PREFIX "%d", bindex); ++ br = au_sbr(sb, bindex); ++ if (br->br_dbgaufs) { ++ struct qstr qstr = QSTR_INIT(name, strlen(name)); ++ ++ if (!au_qstreq(&br->br_dbgaufs->d_name, &qstr)) { ++ /* debugfs acquires the parent i_mutex */ ++ lockdep_off(); ++ d = debugfs_rename(parent, br->br_dbgaufs, parent, ++ name); ++ lockdep_on(); ++ if (unlikely(!d)) ++ pr_warn("failed renaming %pd/%s, ignored.\n", ++ parent, name); ++ } ++ } else { ++ lockdep_off(); ++ br->br_dbgaufs = debugfs_create_file(name, dbgaufs_mode, parent, ++ sbinfo, &dbgaufs_xino_fop); ++ lockdep_on(); ++ if (unlikely(!br->br_dbgaufs)) ++ pr_warn("failed creaiting %pd/%s, ignored.\n", ++ parent, name); ++ } ++} ++ ++void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex, int topdown) ++{ ++ struct au_sbinfo *sbinfo; ++ struct dentry *parent; ++ aufs_bindex_t bbot; ++ ++ if (!au_opt_test(au_mntflags(sb), XINO)) ++ return; ++ ++ sbinfo = au_sbi(sb); ++ parent = sbinfo->si_dbgaufs; ++ if (!parent) ++ return; ++ ++ bbot = au_sbbot(sb); ++ if (topdown) ++ for (; bindex <= bbot; bindex++) ++ dbgaufs_br_add(sb, bindex, parent, sbinfo); ++ else ++ for (; bbot >= bindex; bbot--) ++ dbgaufs_br_add(sb, bbot, parent, sbinfo); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_EXPORT ++static int dbgaufs_xigen_open(struct inode *inode, struct file *file) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ struct super_block *sb; ++ ++ sbinfo = inode->i_private; ++ sb = sbinfo->si_sb; ++ si_noflush_read_lock(sb); ++ err = dbgaufs_xi_open(sbinfo->si_xigen, file, /*do_fcnt*/0, /*cnt*/0); ++ si_read_unlock(sb); ++ return err; ++} ++ ++static const struct file_operations dbgaufs_xigen_fop = { ++ .owner = THIS_MODULE, ++ .open = dbgaufs_xigen_open, ++ .release = dbgaufs_xi_release, ++ .read = dbgaufs_xi_read ++}; ++ ++static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) ++{ ++ int err; ++ ++ /* ++ * This function is a dynamic '__init' function actually, ++ * so the tiny check for si_rwsem is unnecessary. ++ */ ++ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ ++ ++ err = -EIO; ++ sbinfo->si_dbgaufs_xigen = debugfs_create_file ++ ("xigen", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, ++ &dbgaufs_xigen_fop); ++ if (sbinfo->si_dbgaufs_xigen) ++ err = 0; ++ ++ return err; ++} ++#else ++static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) ++{ ++ return 0; ++} ++#endif /* CONFIG_AUFS_EXPORT */ ++ ++/* ---------------------------------------------------------------------- */ ++ ++void dbgaufs_si_fin(struct au_sbinfo *sbinfo) ++{ ++ /* ++ * This function is a dynamic '__fin' function actually, ++ * so the tiny check for si_rwsem is unnecessary. ++ */ ++ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ ++ ++ debugfs_remove_recursive(sbinfo->si_dbgaufs); ++ sbinfo->si_dbgaufs = NULL; ++} ++ ++int dbgaufs_si_init(struct au_sbinfo *sbinfo) ++{ ++ int err; ++ char name[SysaufsSiNameLen]; ++ ++ /* ++ * This function is a dynamic '__init' function actually, ++ * so the tiny check for si_rwsem is unnecessary. ++ */ ++ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ ++ ++ err = -ENOENT; ++ if (!dbgaufs) { ++ AuErr1("/debug/aufs is uninitialized\n"); ++ goto out; ++ } ++ ++ err = -EIO; ++ sysaufs_name(sbinfo, name); ++ sbinfo->si_dbgaufs = debugfs_create_dir(name, dbgaufs); ++ if (unlikely(!sbinfo->si_dbgaufs)) ++ goto out; ++ ++ /* regardless plink/noplink option */ ++ sbinfo->si_dbgaufs_plink = debugfs_create_file ++ ("plink", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, ++ &dbgaufs_plink_fop); ++ if (unlikely(!sbinfo->si_dbgaufs_plink)) ++ goto out_dir; ++ ++ /* regardless xino/noxino option */ ++ sbinfo->si_dbgaufs_xib = debugfs_create_file ++ ("xib", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, ++ &dbgaufs_xib_fop); ++ if (unlikely(!sbinfo->si_dbgaufs_xib)) ++ goto out_dir; ++ ++ err = dbgaufs_xigen_init(sbinfo); ++ if (!err) ++ goto out; /* success */ ++ ++out_dir: ++ dbgaufs_si_fin(sbinfo); ++out: ++ if (unlikely(err)) ++ pr_err("debugfs/aufs failed\n"); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void dbgaufs_fin(void) ++{ ++ debugfs_remove(dbgaufs); ++} ++ ++int __init dbgaufs_init(void) ++{ ++ int err; ++ ++ err = -EIO; ++ dbgaufs = debugfs_create_dir(AUFS_NAME, NULL); ++ if (dbgaufs) ++ err = 0; ++ return err; ++} +diff --git a/fs/aufs/dbgaufs.h b/fs/aufs/dbgaufs.h +new file mode 100644 +index 00000000..dcb0522e +--- /dev/null ++++ b/fs/aufs/dbgaufs.h +@@ -0,0 +1,52 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * debugfs interface ++ */ ++ ++#ifndef __DBGAUFS_H__ ++#define __DBGAUFS_H__ ++ ++#ifdef __KERNEL__ ++ ++struct super_block; ++struct au_sbinfo; ++struct au_branch; ++ ++#ifdef CONFIG_DEBUG_FS ++/* dbgaufs.c */ ++void dbgaufs_xino_del(struct au_branch *br); ++void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex); ++void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex, int topdown); ++void dbgaufs_si_fin(struct au_sbinfo *sbinfo); ++int dbgaufs_si_init(struct au_sbinfo *sbinfo); ++void dbgaufs_fin(void); ++int __init dbgaufs_init(void); ++#else ++AuStubVoid(dbgaufs_xino_del, struct au_branch *br) ++AuStubVoid(dbgaufs_brs_del, struct super_block *sb, aufs_bindex_t bindex) ++AuStubVoid(dbgaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex, ++ int topdown) ++AuStubVoid(dbgaufs_si_fin, struct au_sbinfo *sbinfo) ++AuStubInt0(dbgaufs_si_init, struct au_sbinfo *sbinfo) ++AuStubVoid(dbgaufs_fin, void) ++AuStubInt0(__init dbgaufs_init, void) ++#endif /* CONFIG_DEBUG_FS */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __DBGAUFS_H__ */ +diff --git a/fs/aufs/dcsub.c b/fs/aufs/dcsub.c +new file mode 100644 +index 00000000..61c1a255 +--- /dev/null ++++ b/fs/aufs/dcsub.c +@@ -0,0 +1,225 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * sub-routines for dentry cache ++ */ ++ ++#include "aufs.h" ++ ++static void au_dpage_free(struct au_dpage *dpage) ++{ ++ int i; ++ struct dentry **p; ++ ++ p = dpage->dentries; ++ for (i = 0; i < dpage->ndentry; i++) ++ dput(*p++); ++ free_page((unsigned long)dpage->dentries); ++} ++ ++int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp) ++{ ++ int err; ++ void *p; ++ ++ err = -ENOMEM; ++ dpages->dpages = kmalloc(sizeof(*dpages->dpages), gfp); ++ if (unlikely(!dpages->dpages)) ++ goto out; ++ ++ p = (void *)__get_free_page(gfp); ++ if (unlikely(!p)) ++ goto out_dpages; ++ ++ dpages->dpages[0].ndentry = 0; ++ dpages->dpages[0].dentries = p; ++ dpages->ndpage = 1; ++ return 0; /* success */ ++ ++out_dpages: ++ kfree(dpages->dpages); ++out: ++ return err; ++} ++ ++void au_dpages_free(struct au_dcsub_pages *dpages) ++{ ++ int i; ++ struct au_dpage *p; ++ ++ p = dpages->dpages; ++ for (i = 0; i < dpages->ndpage; i++) ++ au_dpage_free(p++); ++ kfree(dpages->dpages); ++} ++ ++static int au_dpages_append(struct au_dcsub_pages *dpages, ++ struct dentry *dentry, gfp_t gfp) ++{ ++ int err, sz; ++ struct au_dpage *dpage; ++ void *p; ++ ++ dpage = dpages->dpages + dpages->ndpage - 1; ++ sz = PAGE_SIZE / sizeof(dentry); ++ if (unlikely(dpage->ndentry >= sz)) { ++ AuLabel(new dpage); ++ err = -ENOMEM; ++ sz = dpages->ndpage * sizeof(*dpages->dpages); ++ p = au_kzrealloc(dpages->dpages, sz, ++ sz + sizeof(*dpages->dpages), gfp, ++ /*may_shrink*/0); ++ if (unlikely(!p)) ++ goto out; ++ ++ dpages->dpages = p; ++ dpage = dpages->dpages + dpages->ndpage; ++ p = (void *)__get_free_page(gfp); ++ if (unlikely(!p)) ++ goto out; ++ ++ dpage->ndentry = 0; ++ dpage->dentries = p; ++ dpages->ndpage++; ++ } ++ ++ AuDebugOn(au_dcount(dentry) <= 0); ++ dpage->dentries[dpage->ndentry++] = dget_dlock(dentry); ++ return 0; /* success */ ++ ++out: ++ return err; ++} ++ ++/* todo: BAD approach */ ++/* copied from linux/fs/dcache.c */ ++enum d_walk_ret { ++ D_WALK_CONTINUE, ++ D_WALK_QUIT, ++ D_WALK_NORETRY, ++ D_WALK_SKIP, ++}; ++ ++extern void d_walk(struct dentry *parent, void *data, ++ enum d_walk_ret (*enter)(void *, struct dentry *), ++ void (*finish)(void *)); ++ ++struct ac_dpages_arg { ++ int err; ++ struct au_dcsub_pages *dpages; ++ struct super_block *sb; ++ au_dpages_test test; ++ void *arg; ++}; ++ ++static enum d_walk_ret au_call_dpages_append(void *_arg, struct dentry *dentry) ++{ ++ enum d_walk_ret ret; ++ struct ac_dpages_arg *arg = _arg; ++ ++ ret = D_WALK_CONTINUE; ++ if (dentry->d_sb == arg->sb ++ && !IS_ROOT(dentry) ++ && au_dcount(dentry) > 0 ++ && au_di(dentry) ++ && (!arg->test || arg->test(dentry, arg->arg))) { ++ arg->err = au_dpages_append(arg->dpages, dentry, GFP_ATOMIC); ++ if (unlikely(arg->err)) ++ ret = D_WALK_QUIT; ++ } ++ ++ return ret; ++} ++ ++int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root, ++ au_dpages_test test, void *arg) ++{ ++ struct ac_dpages_arg args = { ++ .err = 0, ++ .dpages = dpages, ++ .sb = root->d_sb, ++ .test = test, ++ .arg = arg ++ }; ++ ++ d_walk(root, &args, au_call_dpages_append, NULL); ++ ++ return args.err; ++} ++ ++int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry, ++ int do_include, au_dpages_test test, void *arg) ++{ ++ int err; ++ ++ err = 0; ++ write_seqlock(&rename_lock); ++ spin_lock(&dentry->d_lock); ++ if (do_include ++ && au_dcount(dentry) > 0 ++ && (!test || test(dentry, arg))) ++ err = au_dpages_append(dpages, dentry, GFP_ATOMIC); ++ spin_unlock(&dentry->d_lock); ++ if (unlikely(err)) ++ goto out; ++ ++ /* ++ * RCU for vfsmount is unnecessary since this is a traverse in a single ++ * mount ++ */ ++ while (!IS_ROOT(dentry)) { ++ dentry = dentry->d_parent; /* rename_lock is locked */ ++ spin_lock(&dentry->d_lock); ++ if (au_dcount(dentry) > 0 ++ && (!test || test(dentry, arg))) ++ err = au_dpages_append(dpages, dentry, GFP_ATOMIC); ++ spin_unlock(&dentry->d_lock); ++ if (unlikely(err)) ++ break; ++ } ++ ++out: ++ write_sequnlock(&rename_lock); ++ return err; ++} ++ ++static inline int au_dcsub_dpages_aufs(struct dentry *dentry, void *arg) ++{ ++ return au_di(dentry) && dentry->d_sb == arg; ++} ++ ++int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages, ++ struct dentry *dentry, int do_include) ++{ ++ return au_dcsub_pages_rev(dpages, dentry, do_include, ++ au_dcsub_dpages_aufs, dentry->d_sb); ++} ++ ++int au_test_subdir(struct dentry *d1, struct dentry *d2) ++{ ++ struct path path[2] = { ++ { ++ .dentry = d1 ++ }, ++ { ++ .dentry = d2 ++ } ++ }; ++ ++ return path_is_under(path + 0, path + 1); ++} +diff --git a/fs/aufs/dcsub.h b/fs/aufs/dcsub.h +new file mode 100644 +index 00000000..50e81bf6 +--- /dev/null ++++ b/fs/aufs/dcsub.h +@@ -0,0 +1,136 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * sub-routines for dentry cache ++ */ ++ ++#ifndef __AUFS_DCSUB_H__ ++#define __AUFS_DCSUB_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include ++ ++struct au_dpage { ++ int ndentry; ++ struct dentry **dentries; ++}; ++ ++struct au_dcsub_pages { ++ int ndpage; ++ struct au_dpage *dpages; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* dcsub.c */ ++int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp); ++void au_dpages_free(struct au_dcsub_pages *dpages); ++typedef int (*au_dpages_test)(struct dentry *dentry, void *arg); ++int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root, ++ au_dpages_test test, void *arg); ++int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry, ++ int do_include, au_dpages_test test, void *arg); ++int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages, ++ struct dentry *dentry, int do_include); ++int au_test_subdir(struct dentry *d1, struct dentry *d2); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * todo: in linux-3.13, several similar (but faster) helpers are added to ++ * include/linux/dcache.h. Try them (in the future). ++ */ ++ ++static inline int au_d_hashed_positive(struct dentry *d) ++{ ++ int err; ++ struct inode *inode = d_inode(d); ++ ++ err = 0; ++ if (unlikely(d_unhashed(d) ++ || d_is_negative(d) ++ || !inode->i_nlink)) ++ err = -ENOENT; ++ return err; ++} ++ ++static inline int au_d_linkable(struct dentry *d) ++{ ++ int err; ++ struct inode *inode = d_inode(d); ++ ++ err = au_d_hashed_positive(d); ++ if (err ++ && d_is_positive(d) ++ && (inode->i_state & I_LINKABLE)) ++ err = 0; ++ return err; ++} ++ ++static inline int au_d_alive(struct dentry *d) ++{ ++ int err; ++ struct inode *inode; ++ ++ err = 0; ++ if (!IS_ROOT(d)) ++ err = au_d_hashed_positive(d); ++ else { ++ inode = d_inode(d); ++ if (unlikely(d_unlinked(d) ++ || d_is_negative(d) ++ || !inode->i_nlink)) ++ err = -ENOENT; ++ } ++ return err; ++} ++ ++static inline int au_alive_dir(struct dentry *d) ++{ ++ int err; ++ ++ err = au_d_alive(d); ++ if (unlikely(err || IS_DEADDIR(d_inode(d)))) ++ err = -ENOENT; ++ return err; ++} ++ ++static inline int au_qstreq(struct qstr *a, struct qstr *b) ++{ ++ return a->len == b->len ++ && !memcmp(a->name, b->name, a->len); ++} ++ ++/* ++ * by the commit ++ * 360f547 2015-01-25 dcache: let the dentry count go down to zero without ++ * taking d_lock ++ * the type of d_lockref.count became int, but the inlined function d_count() ++ * still returns unsigned int. ++ * I don't know why. Maybe it is for every d_count() users? ++ * Anyway au_dcount() lives on. ++ */ ++static inline int au_dcount(struct dentry *d) ++{ ++ return (int)d_count(d); ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DCSUB_H__ */ +diff --git a/fs/aufs/debug.c b/fs/aufs/debug.c +new file mode 100644 +index 00000000..be995252 +--- /dev/null ++++ b/fs/aufs/debug.c +@@ -0,0 +1,440 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * debug print functions ++ */ ++ ++#include "aufs.h" ++ ++/* Returns 0, or -errno. arg is in kp->arg. */ ++static int param_atomic_t_set(const char *val, const struct kernel_param *kp) ++{ ++ int err, n; ++ ++ err = kstrtoint(val, 0, &n); ++ if (!err) { ++ if (n > 0) ++ au_debug_on(); ++ else ++ au_debug_off(); ++ } ++ return err; ++} ++ ++/* Returns length written or -errno. Buffer is 4k (ie. be short!) */ ++static int param_atomic_t_get(char *buffer, const struct kernel_param *kp) ++{ ++ atomic_t *a; ++ ++ a = kp->arg; ++ return sprintf(buffer, "%d", atomic_read(a)); ++} ++ ++static struct kernel_param_ops param_ops_atomic_t = { ++ .set = param_atomic_t_set, ++ .get = param_atomic_t_get ++ /* void (*free)(void *arg) */ ++}; ++ ++atomic_t aufs_debug = ATOMIC_INIT(0); ++MODULE_PARM_DESC(debug, "debug print"); ++module_param_named(debug, aufs_debug, atomic_t, 0664); ++ ++DEFINE_MUTEX(au_dbg_mtx); /* just to serialize the dbg msgs */ ++char *au_plevel = KERN_DEBUG; ++#define dpri(fmt, ...) do { \ ++ if ((au_plevel \ ++ && strcmp(au_plevel, KERN_DEBUG)) \ ++ || au_debug_test()) \ ++ printk("%s" fmt, au_plevel, ##__VA_ARGS__); \ ++} while (0) ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_dpri_whlist(struct au_nhash *whlist) ++{ ++ unsigned long ul, n; ++ struct hlist_head *head; ++ struct au_vdir_wh *pos; ++ ++ n = whlist->nh_num; ++ head = whlist->nh_head; ++ for (ul = 0; ul < n; ul++) { ++ hlist_for_each_entry(pos, head, wh_hash) ++ dpri("b%d, %.*s, %d\n", ++ pos->wh_bindex, ++ pos->wh_str.len, pos->wh_str.name, ++ pos->wh_str.len); ++ head++; ++ } ++} ++ ++void au_dpri_vdir(struct au_vdir *vdir) ++{ ++ unsigned long ul; ++ union au_vdir_deblk_p p; ++ unsigned char *o; ++ ++ if (!vdir || IS_ERR(vdir)) { ++ dpri("err %ld\n", PTR_ERR(vdir)); ++ return; ++ } ++ ++ dpri("deblk %u, nblk %lu, deblk %p, last{%lu, %p}, ver %lu\n", ++ vdir->vd_deblk_sz, vdir->vd_nblk, vdir->vd_deblk, ++ vdir->vd_last.ul, vdir->vd_last.p.deblk, vdir->vd_version); ++ for (ul = 0; ul < vdir->vd_nblk; ul++) { ++ p.deblk = vdir->vd_deblk[ul]; ++ o = p.deblk; ++ dpri("[%lu]: %p\n", ul, o); ++ } ++} ++ ++static int do_pri_inode(aufs_bindex_t bindex, struct inode *inode, int hn, ++ struct dentry *wh) ++{ ++ char *n = NULL; ++ int l = 0; ++ ++ if (!inode || IS_ERR(inode)) { ++ dpri("i%d: err %ld\n", bindex, PTR_ERR(inode)); ++ return -1; ++ } ++ ++ /* the type of i_blocks depends upon CONFIG_LBDAF */ ++ BUILD_BUG_ON(sizeof(inode->i_blocks) != sizeof(unsigned long) ++ && sizeof(inode->i_blocks) != sizeof(u64)); ++ if (wh) { ++ n = (void *)wh->d_name.name; ++ l = wh->d_name.len; ++ } ++ ++ dpri("i%d: %p, i%lu, %s, cnt %d, nl %u, 0%o, sz %llu, blk %llu," ++ " hn %d, ct %lld, np %lu, st 0x%lx, f 0x%x, v %llu, g %x%s%.*s\n", ++ bindex, inode, ++ inode->i_ino, inode->i_sb ? au_sbtype(inode->i_sb) : "??", ++ atomic_read(&inode->i_count), inode->i_nlink, inode->i_mode, ++ i_size_read(inode), (unsigned long long)inode->i_blocks, ++ hn, (long long)timespec_to_ns(&inode->i_ctime) & 0x0ffff, ++ inode->i_mapping ? inode->i_mapping->nrpages : 0, ++ inode->i_state, inode->i_flags, inode->i_version, ++ inode->i_generation, ++ l ? ", wh " : "", l, n); ++ return 0; ++} ++ ++void au_dpri_inode(struct inode *inode) ++{ ++ struct au_iinfo *iinfo; ++ struct au_hinode *hi; ++ aufs_bindex_t bindex; ++ int err, hn; ++ ++ err = do_pri_inode(-1, inode, -1, NULL); ++ if (err || !au_test_aufs(inode->i_sb) || au_is_bad_inode(inode)) ++ return; ++ ++ iinfo = au_ii(inode); ++ dpri("i-1: btop %d, bbot %d, gen %d\n", ++ iinfo->ii_btop, iinfo->ii_bbot, au_iigen(inode, NULL)); ++ if (iinfo->ii_btop < 0) ++ return; ++ hn = 0; ++ for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot; bindex++) { ++ hi = au_hinode(iinfo, bindex); ++ hn = !!au_hn(hi); ++ do_pri_inode(bindex, hi->hi_inode, hn, hi->hi_whdentry); ++ } ++} ++ ++void au_dpri_dalias(struct inode *inode) ++{ ++ struct dentry *d; ++ ++ spin_lock(&inode->i_lock); ++ hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) ++ au_dpri_dentry(d); ++ spin_unlock(&inode->i_lock); ++} ++ ++static int do_pri_dentry(aufs_bindex_t bindex, struct dentry *dentry) ++{ ++ struct dentry *wh = NULL; ++ int hn; ++ struct inode *inode; ++ struct au_iinfo *iinfo; ++ struct au_hinode *hi; ++ ++ if (!dentry || IS_ERR(dentry)) { ++ dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry)); ++ return -1; ++ } ++ /* do not call dget_parent() here */ ++ /* note: access d_xxx without d_lock */ ++ dpri("d%d: %p, %pd2?, %s, cnt %d, flags 0x%x, %shashed\n", ++ bindex, dentry, dentry, ++ dentry->d_sb ? au_sbtype(dentry->d_sb) : "??", ++ au_dcount(dentry), dentry->d_flags, ++ d_unhashed(dentry) ? "un" : ""); ++ hn = -1; ++ inode = NULL; ++ if (d_is_positive(dentry)) ++ inode = d_inode(dentry); ++ if (inode ++ && au_test_aufs(dentry->d_sb) ++ && bindex >= 0 ++ && !au_is_bad_inode(inode)) { ++ iinfo = au_ii(inode); ++ hi = au_hinode(iinfo, bindex); ++ hn = !!au_hn(hi); ++ wh = hi->hi_whdentry; ++ } ++ do_pri_inode(bindex, inode, hn, wh); ++ return 0; ++} ++ ++void au_dpri_dentry(struct dentry *dentry) ++{ ++ struct au_dinfo *dinfo; ++ aufs_bindex_t bindex; ++ int err; ++ ++ err = do_pri_dentry(-1, dentry); ++ if (err || !au_test_aufs(dentry->d_sb)) ++ return; ++ ++ dinfo = au_di(dentry); ++ if (!dinfo) ++ return; ++ dpri("d-1: btop %d, bbot %d, bwh %d, bdiropq %d, gen %d, tmp %d\n", ++ dinfo->di_btop, dinfo->di_bbot, ++ dinfo->di_bwh, dinfo->di_bdiropq, au_digen(dentry), ++ dinfo->di_tmpfile); ++ if (dinfo->di_btop < 0) ++ return; ++ for (bindex = dinfo->di_btop; bindex <= dinfo->di_bbot; bindex++) ++ do_pri_dentry(bindex, au_hdentry(dinfo, bindex)->hd_dentry); ++} ++ ++static int do_pri_file(aufs_bindex_t bindex, struct file *file) ++{ ++ char a[32]; ++ ++ if (!file || IS_ERR(file)) { ++ dpri("f%d: err %ld\n", bindex, PTR_ERR(file)); ++ return -1; ++ } ++ a[0] = 0; ++ if (bindex < 0 ++ && !IS_ERR_OR_NULL(file->f_path.dentry) ++ && au_test_aufs(file->f_path.dentry->d_sb) ++ && au_fi(file)) ++ snprintf(a, sizeof(a), ", gen %d, mmapped %d", ++ au_figen(file), atomic_read(&au_fi(file)->fi_mmapped)); ++ dpri("f%d: mode 0x%x, flags 0%o, cnt %ld, v %llu, pos %llu%s\n", ++ bindex, file->f_mode, file->f_flags, (long)file_count(file), ++ file->f_version, file->f_pos, a); ++ if (!IS_ERR_OR_NULL(file->f_path.dentry)) ++ do_pri_dentry(bindex, file->f_path.dentry); ++ return 0; ++} ++ ++void au_dpri_file(struct file *file) ++{ ++ struct au_finfo *finfo; ++ struct au_fidir *fidir; ++ struct au_hfile *hfile; ++ aufs_bindex_t bindex; ++ int err; ++ ++ err = do_pri_file(-1, file); ++ if (err ++ || IS_ERR_OR_NULL(file->f_path.dentry) ++ || !au_test_aufs(file->f_path.dentry->d_sb)) ++ return; ++ ++ finfo = au_fi(file); ++ if (!finfo) ++ return; ++ if (finfo->fi_btop < 0) ++ return; ++ fidir = finfo->fi_hdir; ++ if (!fidir) ++ do_pri_file(finfo->fi_btop, finfo->fi_htop.hf_file); ++ else ++ for (bindex = finfo->fi_btop; ++ bindex >= 0 && bindex <= fidir->fd_bbot; ++ bindex++) { ++ hfile = fidir->fd_hfile + bindex; ++ do_pri_file(bindex, hfile ? hfile->hf_file : NULL); ++ } ++} ++ ++static int do_pri_br(aufs_bindex_t bindex, struct au_branch *br) ++{ ++ struct vfsmount *mnt; ++ struct super_block *sb; ++ ++ if (!br || IS_ERR(br)) ++ goto out; ++ mnt = au_br_mnt(br); ++ if (!mnt || IS_ERR(mnt)) ++ goto out; ++ sb = mnt->mnt_sb; ++ if (!sb || IS_ERR(sb)) ++ goto out; ++ ++ dpri("s%d: {perm 0x%x, id %d, cnt %lld, wbr %p}, " ++ "%s, dev 0x%02x%02x, flags 0x%lx, cnt %d, active %d, " ++ "xino %d\n", ++ bindex, br->br_perm, br->br_id, au_br_count(br), ++ br->br_wbr, au_sbtype(sb), MAJOR(sb->s_dev), MINOR(sb->s_dev), ++ sb->s_flags, sb->s_count, ++ atomic_read(&sb->s_active), !!au_xino_file(br)); ++ return 0; ++ ++out: ++ dpri("s%d: err %ld\n", bindex, PTR_ERR(br)); ++ return -1; ++} ++ ++void au_dpri_sb(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ aufs_bindex_t bindex; ++ int err; ++ /* to reuduce stack size */ ++ struct { ++ struct vfsmount mnt; ++ struct au_branch fake; ++ } *a; ++ ++ /* this function can be called from magic sysrq */ ++ a = kzalloc(sizeof(*a), GFP_ATOMIC); ++ if (unlikely(!a)) { ++ dpri("no memory\n"); ++ return; ++ } ++ ++ a->mnt.mnt_sb = sb; ++ a->fake.br_path.mnt = &a->mnt; ++ au_br_count_init(&a->fake); ++ err = do_pri_br(-1, &a->fake); ++ au_br_count_fin(&a->fake); ++ kfree(a); ++ dpri("dev 0x%x\n", sb->s_dev); ++ if (err || !au_test_aufs(sb)) ++ return; ++ ++ sbinfo = au_sbi(sb); ++ if (!sbinfo) ++ return; ++ dpri("nw %d, gen %u, kobj %d\n", ++ atomic_read(&sbinfo->si_nowait.nw_len), sbinfo->si_generation, ++ atomic_read(&sbinfo->si_kobj.kref.refcount)); ++ for (bindex = 0; bindex <= sbinfo->si_bbot; bindex++) ++ do_pri_br(bindex, sbinfo->si_branch[0 + bindex]); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line) ++{ ++ struct inode *h_inode, *inode = d_inode(dentry); ++ struct dentry *h_dentry; ++ aufs_bindex_t bindex, bbot, bi; ++ ++ if (!inode /* || au_di(dentry)->di_lsc == AuLsc_DI_TMP */) ++ return; ++ ++ bbot = au_dbbot(dentry); ++ bi = au_ibbot(inode); ++ if (bi < bbot) ++ bbot = bi; ++ bindex = au_dbtop(dentry); ++ bi = au_ibtop(inode); ++ if (bi > bindex) ++ bindex = bi; ++ ++ for (; bindex <= bbot; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ h_inode = au_h_iptr(inode, bindex); ++ if (unlikely(h_inode != d_inode(h_dentry))) { ++ au_debug_on(); ++ AuDbg("b%d, %s:%d\n", bindex, func, line); ++ AuDbgDentry(dentry); ++ AuDbgInode(inode); ++ au_debug_off(); ++ BUG(); ++ } ++ } ++} ++ ++void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen) ++{ ++ int err, i, j; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry **dentries; ++ ++ err = au_dpages_init(&dpages, GFP_NOFS); ++ AuDebugOn(err); ++ err = au_dcsub_pages_rev_aufs(&dpages, parent, /*do_include*/1); ++ AuDebugOn(err); ++ for (i = dpages.ndpage - 1; !err && i >= 0; i--) { ++ dpage = dpages.dpages + i; ++ dentries = dpage->dentries; ++ for (j = dpage->ndentry - 1; !err && j >= 0; j--) ++ AuDebugOn(au_digen_test(dentries[j], sigen)); ++ } ++ au_dpages_free(&dpages); ++} ++ ++void au_dbg_verify_kthread(void) ++{ ++ if (au_wkq_test()) { ++ au_dbg_blocked(); ++ /* ++ * It may be recursive, but udba=notify between two aufs mounts, ++ * where a single ro branch is shared, is not a problem. ++ */ ++ /* WARN_ON(1); */ ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int __init au_debug_init(void) ++{ ++ aufs_bindex_t bindex; ++ struct au_vdir_destr destr; ++ ++ bindex = -1; ++ AuDebugOn(bindex >= 0); ++ ++ destr.len = -1; ++ AuDebugOn(destr.len < NAME_MAX); ++ ++#ifdef CONFIG_4KSTACKS ++ pr_warn("CONFIG_4KSTACKS is defined.\n"); ++#endif ++ ++ return 0; ++} +diff --git a/fs/aufs/debug.h b/fs/aufs/debug.h +new file mode 100644 +index 00000000..c1325b13 +--- /dev/null ++++ b/fs/aufs/debug.h +@@ -0,0 +1,225 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * debug print functions ++ */ ++ ++#ifndef __AUFS_DEBUG_H__ ++#define __AUFS_DEBUG_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include ++#include ++#include ++ ++#ifdef CONFIG_AUFS_DEBUG ++#define AuDebugOn(a) BUG_ON(a) ++ ++/* module parameter */ ++extern atomic_t aufs_debug; ++static inline void au_debug_on(void) ++{ ++ atomic_inc(&aufs_debug); ++} ++static inline void au_debug_off(void) ++{ ++ atomic_dec_if_positive(&aufs_debug); ++} ++ ++static inline int au_debug_test(void) ++{ ++ return atomic_read(&aufs_debug) > 0; ++} ++#else ++#define AuDebugOn(a) do {} while (0) ++AuStubVoid(au_debug_on, void) ++AuStubVoid(au_debug_off, void) ++AuStubInt0(au_debug_test, void) ++#endif /* CONFIG_AUFS_DEBUG */ ++ ++#define param_check_atomic_t(name, p) __param_check(name, p, atomic_t) ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* debug print */ ++ ++#define AuDbg(fmt, ...) do { \ ++ if (au_debug_test()) \ ++ pr_debug("DEBUG: " fmt, ##__VA_ARGS__); \ ++} while (0) ++#define AuLabel(l) AuDbg(#l "\n") ++#define AuIOErr(fmt, ...) pr_err("I/O Error, " fmt, ##__VA_ARGS__) ++#define AuWarn1(fmt, ...) do { \ ++ static unsigned char _c; \ ++ if (!_c++) \ ++ pr_warn(fmt, ##__VA_ARGS__); \ ++} while (0) ++ ++#define AuErr1(fmt, ...) do { \ ++ static unsigned char _c; \ ++ if (!_c++) \ ++ pr_err(fmt, ##__VA_ARGS__); \ ++} while (0) ++ ++#define AuIOErr1(fmt, ...) do { \ ++ static unsigned char _c; \ ++ if (!_c++) \ ++ AuIOErr(fmt, ##__VA_ARGS__); \ ++} while (0) ++ ++#define AuUnsupportMsg "This operation is not supported." \ ++ " Please report this application to aufs-users ML." ++#define AuUnsupport(fmt, ...) do { \ ++ pr_err(AuUnsupportMsg "\n" fmt, ##__VA_ARGS__); \ ++ dump_stack(); \ ++} while (0) ++ ++#define AuTraceErr(e) do { \ ++ if (unlikely((e) < 0)) \ ++ AuDbg("err %d\n", (int)(e)); \ ++} while (0) ++ ++#define AuTraceErrPtr(p) do { \ ++ if (IS_ERR(p)) \ ++ AuDbg("err %ld\n", PTR_ERR(p)); \ ++} while (0) ++ ++/* dirty macros for debug print, use with "%.*s" and caution */ ++#define AuLNPair(qstr) (qstr)->len, (qstr)->name ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct dentry; ++#ifdef CONFIG_AUFS_DEBUG ++extern struct mutex au_dbg_mtx; ++extern char *au_plevel; ++struct au_nhash; ++void au_dpri_whlist(struct au_nhash *whlist); ++struct au_vdir; ++void au_dpri_vdir(struct au_vdir *vdir); ++struct inode; ++void au_dpri_inode(struct inode *inode); ++void au_dpri_dalias(struct inode *inode); ++void au_dpri_dentry(struct dentry *dentry); ++struct file; ++void au_dpri_file(struct file *filp); ++struct super_block; ++void au_dpri_sb(struct super_block *sb); ++ ++#define au_dbg_verify_dinode(d) __au_dbg_verify_dinode(d, __func__, __LINE__) ++void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line); ++void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen); ++void au_dbg_verify_kthread(void); ++ ++int __init au_debug_init(void); ++ ++#define AuDbgWhlist(w) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#w "\n"); \ ++ au_dpri_whlist(w); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) ++ ++#define AuDbgVdir(v) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#v "\n"); \ ++ au_dpri_vdir(v); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) ++ ++#define AuDbgInode(i) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#i "\n"); \ ++ au_dpri_inode(i); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) ++ ++#define AuDbgDAlias(i) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#i "\n"); \ ++ au_dpri_dalias(i); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) ++ ++#define AuDbgDentry(d) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#d "\n"); \ ++ au_dpri_dentry(d); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) ++ ++#define AuDbgFile(f) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#f "\n"); \ ++ au_dpri_file(f); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) ++ ++#define AuDbgSb(sb) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#sb "\n"); \ ++ au_dpri_sb(sb); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) ++ ++#define AuDbgSym(addr) do { \ ++ char sym[KSYM_SYMBOL_LEN]; \ ++ sprint_symbol(sym, (unsigned long)addr); \ ++ AuDbg("%s\n", sym); \ ++} while (0) ++#else ++AuStubVoid(au_dbg_verify_dinode, struct dentry *dentry) ++AuStubVoid(au_dbg_verify_gen, struct dentry *parent, unsigned int sigen) ++AuStubVoid(au_dbg_verify_kthread, void) ++AuStubInt0(__init au_debug_init, void) ++ ++#define AuDbgWhlist(w) do {} while (0) ++#define AuDbgVdir(v) do {} while (0) ++#define AuDbgInode(i) do {} while (0) ++#define AuDbgDAlias(i) do {} while (0) ++#define AuDbgDentry(d) do {} while (0) ++#define AuDbgFile(f) do {} while (0) ++#define AuDbgSb(sb) do {} while (0) ++#define AuDbgSym(addr) do {} while (0) ++#endif /* CONFIG_AUFS_DEBUG */ ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_MAGIC_SYSRQ ++int __init au_sysrq_init(void); ++void au_sysrq_fin(void); ++ ++#ifdef CONFIG_HW_CONSOLE ++#define au_dbg_blocked() do { \ ++ WARN_ON(1); \ ++ handle_sysrq('w'); \ ++} while (0) ++#else ++AuStubVoid(au_dbg_blocked, void) ++#endif ++ ++#else ++AuStubInt0(__init au_sysrq_init, void) ++AuStubVoid(au_sysrq_fin, void) ++AuStubVoid(au_dbg_blocked, void) ++#endif /* CONFIG_AUFS_MAGIC_SYSRQ */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DEBUG_H__ */ +diff --git a/fs/aufs/dentry.c b/fs/aufs/dentry.c +new file mode 100644 +index 00000000..51b84632 +--- /dev/null ++++ b/fs/aufs/dentry.c +@@ -0,0 +1,1152 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * lookup and dentry operations ++ */ ++ ++#include ++#include "aufs.h" ++ ++/* ++ * returns positive/negative dentry, NULL or an error. ++ * NULL means whiteout-ed or not-found. ++ */ ++static struct dentry* ++au_do_lookup(struct dentry *h_parent, struct dentry *dentry, ++ aufs_bindex_t bindex, struct au_do_lookup_args *args) ++{ ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ struct au_branch *br; ++ int wh_found, opq; ++ unsigned char wh_able; ++ const unsigned char allow_neg = !!au_ftest_lkup(args->flags, ALLOW_NEG); ++ const unsigned char ignore_perm = !!au_ftest_lkup(args->flags, ++ IGNORE_PERM); ++ ++ wh_found = 0; ++ br = au_sbr(dentry->d_sb, bindex); ++ wh_able = !!au_br_whable(br->br_perm); ++ if (wh_able) ++ wh_found = au_wh_test(h_parent, &args->whname, ignore_perm); ++ h_dentry = ERR_PTR(wh_found); ++ if (!wh_found) ++ goto real_lookup; ++ if (unlikely(wh_found < 0)) ++ goto out; ++ ++ /* We found a whiteout */ ++ /* au_set_dbbot(dentry, bindex); */ ++ au_set_dbwh(dentry, bindex); ++ if (!allow_neg) ++ return NULL; /* success */ ++ ++real_lookup: ++ if (!ignore_perm) ++ h_dentry = vfsub_lkup_one(args->name, h_parent); ++ else ++ h_dentry = au_sio_lkup_one(args->name, h_parent); ++ if (IS_ERR(h_dentry)) { ++ if (PTR_ERR(h_dentry) == -ENAMETOOLONG ++ && !allow_neg) ++ h_dentry = NULL; ++ goto out; ++ } ++ ++ h_inode = d_inode(h_dentry); ++ if (d_is_negative(h_dentry)) { ++ if (!allow_neg) ++ goto out_neg; ++ } else if (wh_found ++ || (args->type && args->type != (h_inode->i_mode & S_IFMT))) ++ goto out_neg; ++ else if (au_ftest_lkup(args->flags, DIRREN) ++ /* && h_inode */ ++ && !au_dr_lkup_h_ino(args, bindex, h_inode->i_ino)) { ++ AuDbg("b%d %pd ignored hi%llu\n", bindex, h_dentry, ++ (unsigned long long)h_inode->i_ino); ++ goto out_neg; ++ } ++ ++ if (au_dbbot(dentry) <= bindex) ++ au_set_dbbot(dentry, bindex); ++ if (au_dbtop(dentry) < 0 || bindex < au_dbtop(dentry)) ++ au_set_dbtop(dentry, bindex); ++ au_set_h_dptr(dentry, bindex, h_dentry); ++ ++ if (!d_is_dir(h_dentry) ++ || !wh_able ++ || (d_really_is_positive(dentry) && !d_is_dir(dentry))) ++ goto out; /* success */ ++ ++ vfsub_inode_lock_shared_nested(h_inode, AuLsc_I_CHILD); ++ opq = au_diropq_test(h_dentry); ++ inode_unlock_shared(h_inode); ++ if (opq > 0) ++ au_set_dbdiropq(dentry, bindex); ++ else if (unlikely(opq < 0)) { ++ au_set_h_dptr(dentry, bindex, NULL); ++ h_dentry = ERR_PTR(opq); ++ } ++ goto out; ++ ++out_neg: ++ dput(h_dentry); ++ h_dentry = NULL; ++out: ++ return h_dentry; ++} ++ ++static int au_test_shwh(struct super_block *sb, const struct qstr *name) ++{ ++ if (unlikely(!au_opt_test(au_mntflags(sb), SHWH) ++ && !strncmp(name->name, AUFS_WH_PFX, AUFS_WH_PFX_LEN))) ++ return -EPERM; ++ return 0; ++} ++ ++/* ++ * returns the number of lower positive dentries, ++ * otherwise an error. ++ * can be called at unlinking with @type is zero. ++ */ ++int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop, ++ unsigned int flags) ++{ ++ int npositive, err; ++ aufs_bindex_t bindex, btail, bdiropq; ++ unsigned char isdir, dirperm1, dirren; ++ struct au_do_lookup_args args = { ++ .flags = flags, ++ .name = &dentry->d_name ++ }; ++ struct dentry *parent; ++ struct super_block *sb; ++ ++ sb = dentry->d_sb; ++ err = au_test_shwh(sb, args.name); ++ if (unlikely(err)) ++ goto out; ++ ++ err = au_wh_name_alloc(&args.whname, args.name); ++ if (unlikely(err)) ++ goto out; ++ ++ isdir = !!d_is_dir(dentry); ++ dirperm1 = !!au_opt_test(au_mntflags(sb), DIRPERM1); ++ dirren = !!au_opt_test(au_mntflags(sb), DIRREN); ++ if (dirren) ++ au_fset_lkup(args.flags, DIRREN); ++ ++ npositive = 0; ++ parent = dget_parent(dentry); ++ btail = au_dbtaildir(parent); ++ for (bindex = btop; bindex <= btail; bindex++) { ++ struct dentry *h_parent, *h_dentry; ++ struct inode *h_inode, *h_dir; ++ struct au_branch *br; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry) { ++ if (d_is_positive(h_dentry)) ++ npositive++; ++ break; ++ } ++ h_parent = au_h_dptr(parent, bindex); ++ if (!h_parent || !d_is_dir(h_parent)) ++ continue; ++ ++ if (dirren) { ++ /* if the inum matches, then use the prepared name */ ++ err = au_dr_lkup_name(&args, bindex); ++ if (unlikely(err)) ++ goto out_parent; ++ } ++ ++ h_dir = d_inode(h_parent); ++ vfsub_inode_lock_shared_nested(h_dir, AuLsc_I_PARENT); ++ h_dentry = au_do_lookup(h_parent, dentry, bindex, &args); ++ inode_unlock_shared(h_dir); ++ err = PTR_ERR(h_dentry); ++ if (IS_ERR(h_dentry)) ++ goto out_parent; ++ if (h_dentry) ++ au_fclr_lkup(args.flags, ALLOW_NEG); ++ if (dirperm1) ++ au_fset_lkup(args.flags, IGNORE_PERM); ++ ++ if (au_dbwh(dentry) == bindex) ++ break; ++ if (!h_dentry) ++ continue; ++ if (d_is_negative(h_dentry)) ++ continue; ++ h_inode = d_inode(h_dentry); ++ npositive++; ++ if (!args.type) ++ args.type = h_inode->i_mode & S_IFMT; ++ if (args.type != S_IFDIR) ++ break; ++ else if (isdir) { ++ /* the type of lower may be different */ ++ bdiropq = au_dbdiropq(dentry); ++ if (bdiropq >= 0 && bdiropq <= bindex) ++ break; ++ } ++ br = au_sbr(sb, bindex); ++ if (dirren ++ && au_dr_hino_test_add(&br->br_dirren, h_inode->i_ino, ++ /*add_ent*/NULL)) { ++ /* prepare next name to lookup */ ++ err = au_dr_lkup(&args, dentry, bindex); ++ if (unlikely(err)) ++ goto out_parent; ++ } ++ } ++ ++ if (npositive) { ++ AuLabel(positive); ++ au_update_dbtop(dentry); ++ } ++ err = npositive; ++ if (unlikely(!au_opt_test(au_mntflags(sb), UDBA_NONE) ++ && au_dbtop(dentry) < 0)) { ++ err = -EIO; ++ AuIOErr("both of real entry and whiteout found, %pd, err %d\n", ++ dentry, err); ++ } ++ ++out_parent: ++ dput(parent); ++ kfree(args.whname.name); ++ if (dirren) ++ au_dr_lkup_fin(&args); ++out: ++ return err; ++} ++ ++struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent) ++{ ++ struct dentry *dentry; ++ int wkq_err; ++ ++ if (!au_test_h_perm_sio(d_inode(parent), MAY_EXEC)) ++ dentry = vfsub_lkup_one(name, parent); ++ else { ++ struct vfsub_lkup_one_args args = { ++ .errp = &dentry, ++ .name = name, ++ .parent = parent ++ }; ++ ++ wkq_err = au_wkq_wait(vfsub_call_lkup_one, &args); ++ if (unlikely(wkq_err)) ++ dentry = ERR_PTR(wkq_err); ++ } ++ ++ return dentry; ++} ++ ++/* ++ * lookup @dentry on @bindex which should be negative. ++ */ ++int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh) ++{ ++ int err; ++ struct dentry *parent, *h_parent, *h_dentry; ++ struct au_branch *br; ++ ++ parent = dget_parent(dentry); ++ h_parent = au_h_dptr(parent, bindex); ++ br = au_sbr(dentry->d_sb, bindex); ++ if (wh) ++ h_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name); ++ else ++ h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent); ++ err = PTR_ERR(h_dentry); ++ if (IS_ERR(h_dentry)) ++ goto out; ++ if (unlikely(d_is_positive(h_dentry))) { ++ err = -EIO; ++ AuIOErr("%pd should be negative on b%d.\n", h_dentry, bindex); ++ dput(h_dentry); ++ goto out; ++ } ++ ++ err = 0; ++ if (bindex < au_dbtop(dentry)) ++ au_set_dbtop(dentry, bindex); ++ if (au_dbbot(dentry) < bindex) ++ au_set_dbbot(dentry, bindex); ++ au_set_h_dptr(dentry, bindex, h_dentry); ++ ++out: ++ dput(parent); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* subset of struct inode */ ++struct au_iattr { ++ unsigned long i_ino; ++ /* unsigned int i_nlink; */ ++ kuid_t i_uid; ++ kgid_t i_gid; ++ u64 i_version; ++/* ++ loff_t i_size; ++ blkcnt_t i_blocks; ++*/ ++ umode_t i_mode; ++}; ++ ++static void au_iattr_save(struct au_iattr *ia, struct inode *h_inode) ++{ ++ ia->i_ino = h_inode->i_ino; ++ /* ia->i_nlink = h_inode->i_nlink; */ ++ ia->i_uid = h_inode->i_uid; ++ ia->i_gid = h_inode->i_gid; ++ ia->i_version = h_inode->i_version; ++/* ++ ia->i_size = h_inode->i_size; ++ ia->i_blocks = h_inode->i_blocks; ++*/ ++ ia->i_mode = (h_inode->i_mode & S_IFMT); ++} ++ ++static int au_iattr_test(struct au_iattr *ia, struct inode *h_inode) ++{ ++ return ia->i_ino != h_inode->i_ino ++ /* || ia->i_nlink != h_inode->i_nlink */ ++ || !uid_eq(ia->i_uid, h_inode->i_uid) ++ || !gid_eq(ia->i_gid, h_inode->i_gid) ++ || ia->i_version != h_inode->i_version ++/* ++ || ia->i_size != h_inode->i_size ++ || ia->i_blocks != h_inode->i_blocks ++*/ ++ || ia->i_mode != (h_inode->i_mode & S_IFMT); ++} ++ ++static int au_h_verify_dentry(struct dentry *h_dentry, struct dentry *h_parent, ++ struct au_branch *br) ++{ ++ int err; ++ struct au_iattr ia; ++ struct inode *h_inode; ++ struct dentry *h_d; ++ struct super_block *h_sb; ++ ++ err = 0; ++ memset(&ia, -1, sizeof(ia)); ++ h_sb = h_dentry->d_sb; ++ h_inode = NULL; ++ if (d_is_positive(h_dentry)) { ++ h_inode = d_inode(h_dentry); ++ au_iattr_save(&ia, h_inode); ++ } else if (au_test_nfs(h_sb) || au_test_fuse(h_sb)) ++ /* nfs d_revalidate may return 0 for negative dentry */ ++ /* fuse d_revalidate always return 0 for negative dentry */ ++ goto out; ++ ++ /* main purpose is namei.c:cached_lookup() and d_revalidate */ ++ h_d = vfsub_lkup_one(&h_dentry->d_name, h_parent); ++ err = PTR_ERR(h_d); ++ if (IS_ERR(h_d)) ++ goto out; ++ ++ err = 0; ++ if (unlikely(h_d != h_dentry ++ || d_inode(h_d) != h_inode ++ || (h_inode && au_iattr_test(&ia, h_inode)))) ++ err = au_busy_or_stale(); ++ dput(h_d); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, ++ struct dentry *h_parent, struct au_branch *br) ++{ ++ int err; ++ ++ err = 0; ++ if (udba == AuOpt_UDBA_REVAL ++ && !au_test_fs_remote(h_dentry->d_sb)) { ++ IMustLock(h_dir); ++ err = (d_inode(h_dentry->d_parent) != h_dir); ++ } else if (udba != AuOpt_UDBA_NONE) ++ err = au_h_verify_dentry(h_dentry, h_parent, br); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_do_refresh_hdentry(struct dentry *dentry, struct dentry *parent) ++{ ++ int err; ++ aufs_bindex_t new_bindex, bindex, bbot, bwh, bdiropq; ++ struct au_hdentry tmp, *p, *q; ++ struct au_dinfo *dinfo; ++ struct super_block *sb; ++ ++ DiMustWriteLock(dentry); ++ ++ sb = dentry->d_sb; ++ dinfo = au_di(dentry); ++ bbot = dinfo->di_bbot; ++ bwh = dinfo->di_bwh; ++ bdiropq = dinfo->di_bdiropq; ++ bindex = dinfo->di_btop; ++ p = au_hdentry(dinfo, bindex); ++ for (; bindex <= bbot; bindex++, p++) { ++ if (!p->hd_dentry) ++ continue; ++ ++ new_bindex = au_br_index(sb, p->hd_id); ++ if (new_bindex == bindex) ++ continue; ++ ++ if (dinfo->di_bwh == bindex) ++ bwh = new_bindex; ++ if (dinfo->di_bdiropq == bindex) ++ bdiropq = new_bindex; ++ if (new_bindex < 0) { ++ au_hdput(p); ++ p->hd_dentry = NULL; ++ continue; ++ } ++ ++ /* swap two lower dentries, and loop again */ ++ q = au_hdentry(dinfo, new_bindex); ++ tmp = *q; ++ *q = *p; ++ *p = tmp; ++ if (tmp.hd_dentry) { ++ bindex--; ++ p--; ++ } ++ } ++ ++ dinfo->di_bwh = -1; ++ if (bwh >= 0 && bwh <= au_sbbot(sb) && au_sbr_whable(sb, bwh)) ++ dinfo->di_bwh = bwh; ++ ++ dinfo->di_bdiropq = -1; ++ if (bdiropq >= 0 ++ && bdiropq <= au_sbbot(sb) ++ && au_sbr_whable(sb, bdiropq)) ++ dinfo->di_bdiropq = bdiropq; ++ ++ err = -EIO; ++ dinfo->di_btop = -1; ++ dinfo->di_bbot = -1; ++ bbot = au_dbbot(parent); ++ bindex = 0; ++ p = au_hdentry(dinfo, bindex); ++ for (; bindex <= bbot; bindex++, p++) ++ if (p->hd_dentry) { ++ dinfo->di_btop = bindex; ++ break; ++ } ++ ++ if (dinfo->di_btop >= 0) { ++ bindex = bbot; ++ p = au_hdentry(dinfo, bindex); ++ for (; bindex >= 0; bindex--, p--) ++ if (p->hd_dentry) { ++ dinfo->di_bbot = bindex; ++ err = 0; ++ break; ++ } ++ } ++ ++ return err; ++} ++ ++static void au_do_hide(struct dentry *dentry) ++{ ++ struct inode *inode; ++ ++ if (d_really_is_positive(dentry)) { ++ inode = d_inode(dentry); ++ if (!d_is_dir(dentry)) { ++ if (inode->i_nlink && !d_unhashed(dentry)) ++ drop_nlink(inode); ++ } else { ++ clear_nlink(inode); ++ /* stop next lookup */ ++ inode->i_flags |= S_DEAD; ++ } ++ smp_mb(); /* necessary? */ ++ } ++ d_drop(dentry); ++} ++ ++static int au_hide_children(struct dentry *parent) ++{ ++ int err, i, j, ndentry; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry *dentry; ++ ++ err = au_dpages_init(&dpages, GFP_NOFS); ++ if (unlikely(err)) ++ goto out; ++ err = au_dcsub_pages(&dpages, parent, NULL, NULL); ++ if (unlikely(err)) ++ goto out_dpages; ++ ++ /* in reverse order */ ++ for (i = dpages.ndpage - 1; i >= 0; i--) { ++ dpage = dpages.dpages + i; ++ ndentry = dpage->ndentry; ++ for (j = ndentry - 1; j >= 0; j--) { ++ dentry = dpage->dentries[j]; ++ if (dentry != parent) ++ au_do_hide(dentry); ++ } ++ } ++ ++out_dpages: ++ au_dpages_free(&dpages); ++out: ++ return err; ++} ++ ++static void au_hide(struct dentry *dentry) ++{ ++ int err; ++ ++ AuDbgDentry(dentry); ++ if (d_is_dir(dentry)) { ++ /* shrink_dcache_parent(dentry); */ ++ err = au_hide_children(dentry); ++ if (unlikely(err)) ++ AuIOErr("%pd, failed hiding children, ignored %d\n", ++ dentry, err); ++ } ++ au_do_hide(dentry); ++} ++ ++/* ++ * By adding a dirty branch, a cached dentry may be affected in various ways. ++ * ++ * a dirty branch is added ++ * - on the top of layers ++ * - in the middle of layers ++ * - to the bottom of layers ++ * ++ * on the added branch there exists ++ * - a whiteout ++ * - a diropq ++ * - a same named entry ++ * + exist ++ * * negative --> positive ++ * * positive --> positive ++ * - type is unchanged ++ * - type is changed ++ * + doesn't exist ++ * * negative --> negative ++ * * positive --> negative (rejected by au_br_del() for non-dir case) ++ * - none ++ */ ++static int au_refresh_by_dinfo(struct dentry *dentry, struct au_dinfo *dinfo, ++ struct au_dinfo *tmp) ++{ ++ int err; ++ aufs_bindex_t bindex, bbot; ++ struct { ++ struct dentry *dentry; ++ struct inode *inode; ++ mode_t mode; ++ } orig_h, tmp_h = { ++ .dentry = NULL ++ }; ++ struct au_hdentry *hd; ++ struct inode *inode, *h_inode; ++ struct dentry *h_dentry; ++ ++ err = 0; ++ AuDebugOn(dinfo->di_btop < 0); ++ orig_h.mode = 0; ++ orig_h.dentry = au_hdentry(dinfo, dinfo->di_btop)->hd_dentry; ++ orig_h.inode = NULL; ++ if (d_is_positive(orig_h.dentry)) { ++ orig_h.inode = d_inode(orig_h.dentry); ++ orig_h.mode = orig_h.inode->i_mode & S_IFMT; ++ } ++ if (tmp->di_btop >= 0) { ++ tmp_h.dentry = au_hdentry(tmp, tmp->di_btop)->hd_dentry; ++ if (d_is_positive(tmp_h.dentry)) { ++ tmp_h.inode = d_inode(tmp_h.dentry); ++ tmp_h.mode = tmp_h.inode->i_mode & S_IFMT; ++ } ++ } ++ ++ inode = NULL; ++ if (d_really_is_positive(dentry)) ++ inode = d_inode(dentry); ++ if (!orig_h.inode) { ++ AuDbg("nagative originally\n"); ++ if (inode) { ++ au_hide(dentry); ++ goto out; ++ } ++ AuDebugOn(inode); ++ AuDebugOn(dinfo->di_btop != dinfo->di_bbot); ++ AuDebugOn(dinfo->di_bdiropq != -1); ++ ++ if (!tmp_h.inode) { ++ AuDbg("negative --> negative\n"); ++ /* should have only one negative lower */ ++ if (tmp->di_btop >= 0 ++ && tmp->di_btop < dinfo->di_btop) { ++ AuDebugOn(tmp->di_btop != tmp->di_bbot); ++ AuDebugOn(dinfo->di_btop != dinfo->di_bbot); ++ au_set_h_dptr(dentry, dinfo->di_btop, NULL); ++ au_di_cp(dinfo, tmp); ++ hd = au_hdentry(tmp, tmp->di_btop); ++ au_set_h_dptr(dentry, tmp->di_btop, ++ dget(hd->hd_dentry)); ++ } ++ au_dbg_verify_dinode(dentry); ++ } else { ++ AuDbg("negative --> positive\n"); ++ /* ++ * similar to the behaviour of creating with bypassing ++ * aufs. ++ * unhash it in order to force an error in the ++ * succeeding create operation. ++ * we should not set S_DEAD here. ++ */ ++ d_drop(dentry); ++ /* au_di_swap(tmp, dinfo); */ ++ au_dbg_verify_dinode(dentry); ++ } ++ } else { ++ AuDbg("positive originally\n"); ++ /* inode may be NULL */ ++ AuDebugOn(inode && (inode->i_mode & S_IFMT) != orig_h.mode); ++ if (!tmp_h.inode) { ++ AuDbg("positive --> negative\n"); ++ /* or bypassing aufs */ ++ au_hide(dentry); ++ if (tmp->di_bwh >= 0 && tmp->di_bwh <= dinfo->di_btop) ++ dinfo->di_bwh = tmp->di_bwh; ++ if (inode) ++ err = au_refresh_hinode_self(inode); ++ au_dbg_verify_dinode(dentry); ++ } else if (orig_h.mode == tmp_h.mode) { ++ AuDbg("positive --> positive, same type\n"); ++ if (!S_ISDIR(orig_h.mode) ++ && dinfo->di_btop > tmp->di_btop) { ++ /* ++ * similar to the behaviour of removing and ++ * creating. ++ */ ++ au_hide(dentry); ++ if (inode) ++ err = au_refresh_hinode_self(inode); ++ au_dbg_verify_dinode(dentry); ++ } else { ++ /* fill empty slots */ ++ if (dinfo->di_btop > tmp->di_btop) ++ dinfo->di_btop = tmp->di_btop; ++ if (dinfo->di_bbot < tmp->di_bbot) ++ dinfo->di_bbot = tmp->di_bbot; ++ dinfo->di_bwh = tmp->di_bwh; ++ dinfo->di_bdiropq = tmp->di_bdiropq; ++ bbot = dinfo->di_bbot; ++ bindex = tmp->di_btop; ++ hd = au_hdentry(tmp, bindex); ++ for (; bindex <= bbot; bindex++, hd++) { ++ if (au_h_dptr(dentry, bindex)) ++ continue; ++ h_dentry = hd->hd_dentry; ++ if (!h_dentry) ++ continue; ++ AuDebugOn(d_is_negative(h_dentry)); ++ h_inode = d_inode(h_dentry); ++ AuDebugOn(orig_h.mode ++ != (h_inode->i_mode ++ & S_IFMT)); ++ au_set_h_dptr(dentry, bindex, ++ dget(h_dentry)); ++ } ++ if (inode) ++ err = au_refresh_hinode(inode, dentry); ++ au_dbg_verify_dinode(dentry); ++ } ++ } else { ++ AuDbg("positive --> positive, different type\n"); ++ /* similar to the behaviour of removing and creating */ ++ au_hide(dentry); ++ if (inode) ++ err = au_refresh_hinode_self(inode); ++ au_dbg_verify_dinode(dentry); ++ } ++ } ++ ++out: ++ return err; ++} ++ ++void au_refresh_dop(struct dentry *dentry, int force_reval) ++{ ++ const struct dentry_operations *dop ++ = force_reval ? &aufs_dop : dentry->d_sb->s_d_op; ++ static const unsigned int mask ++ = DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE; ++ ++ BUILD_BUG_ON(sizeof(mask) != sizeof(dentry->d_flags)); ++ ++ if (dentry->d_op == dop) ++ return; ++ ++ AuDbg("%pd\n", dentry); ++ spin_lock(&dentry->d_lock); ++ if (dop == &aufs_dop) ++ dentry->d_flags |= mask; ++ else ++ dentry->d_flags &= ~mask; ++ dentry->d_op = dop; ++ spin_unlock(&dentry->d_lock); ++} ++ ++int au_refresh_dentry(struct dentry *dentry, struct dentry *parent) ++{ ++ int err, ebrange, nbr; ++ unsigned int sigen; ++ struct au_dinfo *dinfo, *tmp; ++ struct super_block *sb; ++ struct inode *inode; ++ ++ DiMustWriteLock(dentry); ++ AuDebugOn(IS_ROOT(dentry)); ++ AuDebugOn(d_really_is_negative(parent)); ++ ++ sb = dentry->d_sb; ++ sigen = au_sigen(sb); ++ err = au_digen_test(parent, sigen); ++ if (unlikely(err)) ++ goto out; ++ ++ nbr = au_sbbot(sb) + 1; ++ dinfo = au_di(dentry); ++ err = au_di_realloc(dinfo, nbr, /*may_shrink*/0); ++ if (unlikely(err)) ++ goto out; ++ ebrange = au_dbrange_test(dentry); ++ if (!ebrange) ++ ebrange = au_do_refresh_hdentry(dentry, parent); ++ ++ if (d_unhashed(dentry) || ebrange /* || dinfo->di_tmpfile */) { ++ AuDebugOn(au_dbtop(dentry) < 0 && au_dbbot(dentry) >= 0); ++ if (d_really_is_positive(dentry)) { ++ inode = d_inode(dentry); ++ err = au_refresh_hinode_self(inode); ++ } ++ au_dbg_verify_dinode(dentry); ++ if (!err) ++ goto out_dgen; /* success */ ++ goto out; ++ } ++ ++ /* temporary dinfo */ ++ AuDbgDentry(dentry); ++ err = -ENOMEM; ++ tmp = au_di_alloc(sb, AuLsc_DI_TMP); ++ if (unlikely(!tmp)) ++ goto out; ++ au_di_swap(tmp, dinfo); ++ /* returns the number of positive dentries */ ++ /* ++ * if current working dir is removed, it returns an error. ++ * but the dentry is legal. ++ */ ++ err = au_lkup_dentry(dentry, /*btop*/0, AuLkup_ALLOW_NEG); ++ AuDbgDentry(dentry); ++ au_di_swap(tmp, dinfo); ++ if (err == -ENOENT) ++ err = 0; ++ if (err >= 0) { ++ /* compare/refresh by dinfo */ ++ AuDbgDentry(dentry); ++ err = au_refresh_by_dinfo(dentry, dinfo, tmp); ++ au_dbg_verify_dinode(dentry); ++ AuTraceErr(err); ++ } ++ au_di_realloc(dinfo, nbr, /*may_shrink*/1); /* harmless if err */ ++ au_rw_write_unlock(&tmp->di_rwsem); ++ au_di_free(tmp); ++ if (unlikely(err)) ++ goto out; ++ ++out_dgen: ++ au_update_digen(dentry); ++out: ++ if (unlikely(err && !(dentry->d_flags & DCACHE_NFSFS_RENAMED))) { ++ AuIOErr("failed refreshing %pd, %d\n", dentry, err); ++ AuDbgDentry(dentry); ++ } ++ AuTraceErr(err); ++ return err; ++} ++ ++static int au_do_h_d_reval(struct dentry *h_dentry, unsigned int flags, ++ struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ int err, valid; ++ ++ err = 0; ++ if (!(h_dentry->d_flags & DCACHE_OP_REVALIDATE)) ++ goto out; ++ ++ AuDbg("b%d\n", bindex); ++ /* ++ * gave up supporting LOOKUP_CREATE/OPEN for lower fs, ++ * due to whiteout and branch permission. ++ */ ++ flags &= ~(/*LOOKUP_PARENT |*/ LOOKUP_OPEN | LOOKUP_CREATE ++ | LOOKUP_FOLLOW | LOOKUP_EXCL); ++ /* it may return tri-state */ ++ valid = h_dentry->d_op->d_revalidate(h_dentry, flags); ++ ++ if (unlikely(valid < 0)) ++ err = valid; ++ else if (!valid) ++ err = -EINVAL; ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* todo: remove this */ ++static int h_d_revalidate(struct dentry *dentry, struct inode *inode, ++ unsigned int flags, int do_udba, int dirren) ++{ ++ int err; ++ umode_t mode, h_mode; ++ aufs_bindex_t bindex, btail, btop, ibs, ibe; ++ unsigned char plus, unhashed, is_root, h_plus, h_nfs, tmpfile; ++ struct inode *h_inode, *h_cached_inode; ++ struct dentry *h_dentry; ++ struct qstr *name, *h_name; ++ ++ err = 0; ++ plus = 0; ++ mode = 0; ++ ibs = -1; ++ ibe = -1; ++ unhashed = !!d_unhashed(dentry); ++ is_root = !!IS_ROOT(dentry); ++ name = &dentry->d_name; ++ tmpfile = au_di(dentry)->di_tmpfile; ++ ++ /* ++ * Theoretically, REVAL test should be unnecessary in case of ++ * {FS,I}NOTIFY. ++ * But {fs,i}notify doesn't fire some necessary events, ++ * IN_ATTRIB for atime/nlink/pageio ++ * Let's do REVAL test too. ++ */ ++ if (do_udba && inode) { ++ mode = (inode->i_mode & S_IFMT); ++ plus = (inode->i_nlink > 0); ++ ibs = au_ibtop(inode); ++ ibe = au_ibbot(inode); ++ } ++ ++ btop = au_dbtop(dentry); ++ btail = btop; ++ if (inode && S_ISDIR(inode->i_mode)) ++ btail = au_dbtaildir(dentry); ++ for (bindex = btop; bindex <= btail; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ ++ AuDbg("b%d, %pd\n", bindex, h_dentry); ++ h_nfs = !!au_test_nfs(h_dentry->d_sb); ++ spin_lock(&h_dentry->d_lock); ++ h_name = &h_dentry->d_name; ++ if (unlikely(do_udba ++ && !is_root ++ && ((!h_nfs ++ && (unhashed != !!d_unhashed(h_dentry) ++ || (!tmpfile && !dirren ++ && !au_qstreq(name, h_name)) ++ )) ++ || (h_nfs ++ && !(flags & LOOKUP_OPEN) ++ && (h_dentry->d_flags ++ & DCACHE_NFSFS_RENAMED))) ++ )) { ++ int h_unhashed; ++ ++ h_unhashed = d_unhashed(h_dentry); ++ spin_unlock(&h_dentry->d_lock); ++ AuDbg("unhash 0x%x 0x%x, %pd %pd\n", ++ unhashed, h_unhashed, dentry, h_dentry); ++ goto err; ++ } ++ spin_unlock(&h_dentry->d_lock); ++ ++ err = au_do_h_d_reval(h_dentry, flags, dentry, bindex); ++ if (unlikely(err)) ++ /* do not goto err, to keep the errno */ ++ break; ++ ++ /* todo: plink too? */ ++ if (!do_udba) ++ continue; ++ ++ /* UDBA tests */ ++ if (unlikely(!!inode != d_is_positive(h_dentry))) ++ goto err; ++ ++ h_inode = NULL; ++ if (d_is_positive(h_dentry)) ++ h_inode = d_inode(h_dentry); ++ h_plus = plus; ++ h_mode = mode; ++ h_cached_inode = h_inode; ++ if (h_inode) { ++ h_mode = (h_inode->i_mode & S_IFMT); ++ h_plus = (h_inode->i_nlink > 0); ++ } ++ if (inode && ibs <= bindex && bindex <= ibe) ++ h_cached_inode = au_h_iptr(inode, bindex); ++ ++ if (!h_nfs) { ++ if (unlikely(plus != h_plus && !tmpfile)) ++ goto err; ++ } else { ++ if (unlikely(!(h_dentry->d_flags & DCACHE_NFSFS_RENAMED) ++ && !is_root ++ && !IS_ROOT(h_dentry) ++ && unhashed != d_unhashed(h_dentry))) ++ goto err; ++ } ++ if (unlikely(mode != h_mode ++ || h_cached_inode != h_inode)) ++ goto err; ++ continue; ++ ++err: ++ err = -EINVAL; ++ break; ++ } ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++/* todo: consolidate with do_refresh() and au_reval_for_attr() */ ++static int simple_reval_dpath(struct dentry *dentry, unsigned int sigen) ++{ ++ int err; ++ struct dentry *parent; ++ ++ if (!au_digen_test(dentry, sigen)) ++ return 0; ++ ++ parent = dget_parent(dentry); ++ di_read_lock_parent(parent, AuLock_IR); ++ AuDebugOn(au_digen_test(parent, sigen)); ++ au_dbg_verify_gen(parent, sigen); ++ err = au_refresh_dentry(dentry, parent); ++ di_read_unlock(parent, AuLock_IR); ++ dput(parent); ++ AuTraceErr(err); ++ return err; ++} ++ ++int au_reval_dpath(struct dentry *dentry, unsigned int sigen) ++{ ++ int err; ++ struct dentry *d, *parent; ++ ++ if (!au_ftest_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR)) ++ return simple_reval_dpath(dentry, sigen); ++ ++ /* slow loop, keep it simple and stupid */ ++ /* cf: au_cpup_dirs() */ ++ err = 0; ++ parent = NULL; ++ while (au_digen_test(dentry, sigen)) { ++ d = dentry; ++ while (1) { ++ dput(parent); ++ parent = dget_parent(d); ++ if (!au_digen_test(parent, sigen)) ++ break; ++ d = parent; ++ } ++ ++ if (d != dentry) ++ di_write_lock_child2(d); ++ ++ /* someone might update our dentry while we were sleeping */ ++ if (au_digen_test(d, sigen)) { ++ /* ++ * todo: consolidate with simple_reval_dpath(), ++ * do_refresh() and au_reval_for_attr(). ++ */ ++ di_read_lock_parent(parent, AuLock_IR); ++ err = au_refresh_dentry(d, parent); ++ di_read_unlock(parent, AuLock_IR); ++ } ++ ++ if (d != dentry) ++ di_write_unlock(d); ++ dput(parent); ++ if (unlikely(err)) ++ break; ++ } ++ ++ return err; ++} ++ ++/* ++ * if valid returns 1, otherwise 0. ++ */ ++static int aufs_d_revalidate(struct dentry *dentry, unsigned int flags) ++{ ++ int valid, err; ++ unsigned int sigen; ++ unsigned char do_udba, dirren; ++ struct super_block *sb; ++ struct inode *inode; ++ ++ /* todo: support rcu-walk? */ ++ if (flags & LOOKUP_RCU) ++ return -ECHILD; ++ ++ valid = 0; ++ if (unlikely(!au_di(dentry))) ++ goto out; ++ ++ valid = 1; ++ sb = dentry->d_sb; ++ /* ++ * todo: very ugly ++ * i_mutex of parent dir may be held, ++ * but we should not return 'invalid' due to busy. ++ */ ++ err = aufs_read_lock(dentry, AuLock_FLUSH | AuLock_DW | AuLock_NOPLM); ++ if (unlikely(err)) { ++ valid = err; ++ AuTraceErr(err); ++ goto out; ++ } ++ inode = NULL; ++ if (d_really_is_positive(dentry)) ++ inode = d_inode(dentry); ++ if (unlikely(inode && au_is_bad_inode(inode))) { ++ err = -EINVAL; ++ AuTraceErr(err); ++ goto out_dgrade; ++ } ++ if (unlikely(au_dbrange_test(dentry))) { ++ err = -EINVAL; ++ AuTraceErr(err); ++ goto out_dgrade; ++ } ++ ++ sigen = au_sigen(sb); ++ if (au_digen_test(dentry, sigen)) { ++ AuDebugOn(IS_ROOT(dentry)); ++ err = au_reval_dpath(dentry, sigen); ++ if (unlikely(err)) { ++ AuTraceErr(err); ++ goto out_dgrade; ++ } ++ } ++ di_downgrade_lock(dentry, AuLock_IR); ++ ++ err = -EINVAL; ++ if (!(flags & (LOOKUP_OPEN | LOOKUP_EMPTY)) ++ && inode ++ && !(inode->i_state && I_LINKABLE) ++ && (IS_DEADDIR(inode) || !inode->i_nlink)) { ++ AuTraceErr(err); ++ goto out_inval; ++ } ++ ++ do_udba = !au_opt_test(au_mntflags(sb), UDBA_NONE); ++ if (do_udba && inode) { ++ aufs_bindex_t btop = au_ibtop(inode); ++ struct inode *h_inode; ++ ++ if (btop >= 0) { ++ h_inode = au_h_iptr(inode, btop); ++ if (h_inode && au_test_higen(inode, h_inode)) { ++ AuTraceErr(err); ++ goto out_inval; ++ } ++ } ++ } ++ ++ dirren = !!au_opt_test(au_mntflags(sb), DIRREN); ++ err = h_d_revalidate(dentry, inode, flags, do_udba, dirren); ++ if (unlikely(!err && do_udba && au_dbtop(dentry) < 0)) { ++ err = -EIO; ++ AuDbg("both of real entry and whiteout found, %p, err %d\n", ++ dentry, err); ++ } ++ goto out_inval; ++ ++out_dgrade: ++ di_downgrade_lock(dentry, AuLock_IR); ++out_inval: ++ aufs_read_unlock(dentry, AuLock_IR); ++ AuTraceErr(err); ++ valid = !err; ++out: ++ if (!valid) { ++ AuDbg("%pd invalid, %d\n", dentry, valid); ++ d_drop(dentry); ++ } ++ return valid; ++} ++ ++static void aufs_d_release(struct dentry *dentry) ++{ ++ if (au_di(dentry)) { ++ au_di_fin(dentry); ++ au_hn_di_reinit(dentry); ++ } ++} ++ ++const struct dentry_operations aufs_dop = { ++ .d_revalidate = aufs_d_revalidate, ++ .d_weak_revalidate = aufs_d_revalidate, ++ .d_release = aufs_d_release ++}; ++ ++/* aufs_dop without d_revalidate */ ++const struct dentry_operations aufs_dop_noreval = { ++ .d_release = aufs_d_release ++}; +diff --git a/fs/aufs/dentry.h b/fs/aufs/dentry.h +new file mode 100644 +index 00000000..8f20b51d +--- /dev/null ++++ b/fs/aufs/dentry.h +@@ -0,0 +1,266 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * lookup and dentry operations ++ */ ++ ++#ifndef __AUFS_DENTRY_H__ ++#define __AUFS_DENTRY_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include "dirren.h" ++#include "rwsem.h" ++ ++struct au_hdentry { ++ struct dentry *hd_dentry; ++ aufs_bindex_t hd_id; ++}; ++ ++struct au_dinfo { ++ atomic_t di_generation; ++ ++ struct au_rwsem di_rwsem; ++ aufs_bindex_t di_btop, di_bbot, di_bwh, di_bdiropq; ++ unsigned char di_tmpfile; /* to allow the different name */ ++ struct au_hdentry *di_hdentry; ++} ____cacheline_aligned_in_smp; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* flags for au_lkup_dentry() */ ++#define AuLkup_ALLOW_NEG 1 ++#define AuLkup_IGNORE_PERM (1 << 1) ++#define AuLkup_DIRREN (1 << 2) ++#define au_ftest_lkup(flags, name) ((flags) & AuLkup_##name) ++#define au_fset_lkup(flags, name) \ ++ do { (flags) |= AuLkup_##name; } while (0) ++#define au_fclr_lkup(flags, name) \ ++ do { (flags) &= ~AuLkup_##name; } while (0) ++ ++#ifndef CONFIG_AUFS_DIRREN ++#undef AuLkup_DIRREN ++#define AuLkup_DIRREN 0 ++#endif ++ ++struct au_do_lookup_args { ++ unsigned int flags; ++ mode_t type; ++ struct qstr whname, *name; ++ struct au_dr_lookup dirren; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* dentry.c */ ++extern const struct dentry_operations aufs_dop, aufs_dop_noreval; ++struct au_branch; ++struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent); ++int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, ++ struct dentry *h_parent, struct au_branch *br); ++ ++int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop, ++ unsigned int flags); ++int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh); ++int au_refresh_dentry(struct dentry *dentry, struct dentry *parent); ++int au_reval_dpath(struct dentry *dentry, unsigned int sigen); ++void au_refresh_dop(struct dentry *dentry, int force_reval); ++ ++/* dinfo.c */ ++void au_di_init_once(void *_di); ++struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc); ++void au_di_free(struct au_dinfo *dinfo); ++void au_di_swap(struct au_dinfo *a, struct au_dinfo *b); ++void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src); ++int au_di_init(struct dentry *dentry); ++void au_di_fin(struct dentry *dentry); ++int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink); ++ ++void di_read_lock(struct dentry *d, int flags, unsigned int lsc); ++void di_read_unlock(struct dentry *d, int flags); ++void di_downgrade_lock(struct dentry *d, int flags); ++void di_write_lock(struct dentry *d, unsigned int lsc); ++void di_write_unlock(struct dentry *d); ++void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir); ++void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir); ++void di_write_unlock2(struct dentry *d1, struct dentry *d2); ++ ++struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex); ++struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex); ++aufs_bindex_t au_dbtail(struct dentry *dentry); ++aufs_bindex_t au_dbtaildir(struct dentry *dentry); ++ ++void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_dentry); ++int au_digen_test(struct dentry *dentry, unsigned int sigen); ++int au_dbrange_test(struct dentry *dentry); ++void au_update_digen(struct dentry *dentry); ++void au_update_dbrange(struct dentry *dentry, int do_put_zero); ++void au_update_dbtop(struct dentry *dentry); ++void au_update_dbbot(struct dentry *dentry); ++int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct au_dinfo *au_di(struct dentry *dentry) ++{ ++ return dentry->d_fsdata; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* lock subclass for dinfo */ ++enum { ++ AuLsc_DI_CHILD, /* child first */ ++ AuLsc_DI_CHILD2, /* rename(2), link(2), and cpup at hnotify */ ++ AuLsc_DI_CHILD3, /* copyup dirs */ ++ AuLsc_DI_PARENT, ++ AuLsc_DI_PARENT2, ++ AuLsc_DI_PARENT3, ++ AuLsc_DI_TMP /* temp for replacing dinfo */ ++}; ++ ++/* ++ * di_read_lock_child, di_write_lock_child, ++ * di_read_lock_child2, di_write_lock_child2, ++ * di_read_lock_child3, di_write_lock_child3, ++ * di_read_lock_parent, di_write_lock_parent, ++ * di_read_lock_parent2, di_write_lock_parent2, ++ * di_read_lock_parent3, di_write_lock_parent3, ++ */ ++#define AuReadLockFunc(name, lsc) \ ++static inline void di_read_lock_##name(struct dentry *d, int flags) \ ++{ di_read_lock(d, flags, AuLsc_DI_##lsc); } ++ ++#define AuWriteLockFunc(name, lsc) \ ++static inline void di_write_lock_##name(struct dentry *d) \ ++{ di_write_lock(d, AuLsc_DI_##lsc); } ++ ++#define AuRWLockFuncs(name, lsc) \ ++ AuReadLockFunc(name, lsc) \ ++ AuWriteLockFunc(name, lsc) ++ ++AuRWLockFuncs(child, CHILD); ++AuRWLockFuncs(child2, CHILD2); ++AuRWLockFuncs(child3, CHILD3); ++AuRWLockFuncs(parent, PARENT); ++AuRWLockFuncs(parent2, PARENT2); ++AuRWLockFuncs(parent3, PARENT3); ++ ++#undef AuReadLockFunc ++#undef AuWriteLockFunc ++#undef AuRWLockFuncs ++ ++#define DiMustNoWaiters(d) AuRwMustNoWaiters(&au_di(d)->di_rwsem) ++#define DiMustAnyLock(d) AuRwMustAnyLock(&au_di(d)->di_rwsem) ++#define DiMustWriteLock(d) AuRwMustWriteLock(&au_di(d)->di_rwsem) ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* todo: memory barrier? */ ++static inline unsigned int au_digen(struct dentry *d) ++{ ++ return atomic_read(&au_di(d)->di_generation); ++} ++ ++static inline void au_h_dentry_init(struct au_hdentry *hdentry) ++{ ++ hdentry->hd_dentry = NULL; ++} ++ ++static inline struct au_hdentry *au_hdentry(struct au_dinfo *di, ++ aufs_bindex_t bindex) ++{ ++ return di->di_hdentry + bindex; ++} ++ ++static inline void au_hdput(struct au_hdentry *hd) ++{ ++ if (hd) ++ dput(hd->hd_dentry); ++} ++ ++static inline aufs_bindex_t au_dbtop(struct dentry *dentry) ++{ ++ DiMustAnyLock(dentry); ++ return au_di(dentry)->di_btop; ++} ++ ++static inline aufs_bindex_t au_dbbot(struct dentry *dentry) ++{ ++ DiMustAnyLock(dentry); ++ return au_di(dentry)->di_bbot; ++} ++ ++static inline aufs_bindex_t au_dbwh(struct dentry *dentry) ++{ ++ DiMustAnyLock(dentry); ++ return au_di(dentry)->di_bwh; ++} ++ ++static inline aufs_bindex_t au_dbdiropq(struct dentry *dentry) ++{ ++ DiMustAnyLock(dentry); ++ return au_di(dentry)->di_bdiropq; ++} ++ ++/* todo: hard/soft set? */ ++static inline void au_set_dbtop(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ DiMustWriteLock(dentry); ++ au_di(dentry)->di_btop = bindex; ++} ++ ++static inline void au_set_dbbot(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ DiMustWriteLock(dentry); ++ au_di(dentry)->di_bbot = bindex; ++} ++ ++static inline void au_set_dbwh(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ DiMustWriteLock(dentry); ++ /* dbwh can be outside of btop - bbot range */ ++ au_di(dentry)->di_bwh = bindex; ++} ++ ++static inline void au_set_dbdiropq(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ DiMustWriteLock(dentry); ++ au_di(dentry)->di_bdiropq = bindex; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_HNOTIFY ++static inline void au_digen_dec(struct dentry *d) ++{ ++ atomic_dec(&au_di(d)->di_generation); ++} ++ ++static inline void au_hn_di_reinit(struct dentry *dentry) ++{ ++ dentry->d_fsdata = NULL; ++} ++#else ++AuStubVoid(au_hn_di_reinit, struct dentry *dentry __maybe_unused) ++#endif /* CONFIG_AUFS_HNOTIFY */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DENTRY_H__ */ +diff --git a/fs/aufs/dinfo.c b/fs/aufs/dinfo.c +new file mode 100644 +index 00000000..75b7ea4a +--- /dev/null ++++ b/fs/aufs/dinfo.c +@@ -0,0 +1,553 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * dentry private data ++ */ ++ ++#include "aufs.h" ++ ++void au_di_init_once(void *_dinfo) ++{ ++ struct au_dinfo *dinfo = _dinfo; ++ ++ au_rw_init(&dinfo->di_rwsem); ++} ++ ++struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc) ++{ ++ struct au_dinfo *dinfo; ++ int nbr, i; ++ ++ dinfo = au_cache_alloc_dinfo(); ++ if (unlikely(!dinfo)) ++ goto out; ++ ++ nbr = au_sbbot(sb) + 1; ++ if (nbr <= 0) ++ nbr = 1; ++ dinfo->di_hdentry = kcalloc(nbr, sizeof(*dinfo->di_hdentry), GFP_NOFS); ++ if (dinfo->di_hdentry) { ++ au_rw_write_lock_nested(&dinfo->di_rwsem, lsc); ++ dinfo->di_btop = -1; ++ dinfo->di_bbot = -1; ++ dinfo->di_bwh = -1; ++ dinfo->di_bdiropq = -1; ++ dinfo->di_tmpfile = 0; ++ for (i = 0; i < nbr; i++) ++ dinfo->di_hdentry[i].hd_id = -1; ++ goto out; ++ } ++ ++ au_cache_free_dinfo(dinfo); ++ dinfo = NULL; ++ ++out: ++ return dinfo; ++} ++ ++void au_di_free(struct au_dinfo *dinfo) ++{ ++ struct au_hdentry *p; ++ aufs_bindex_t bbot, bindex; ++ ++ /* dentry may not be revalidated */ ++ bindex = dinfo->di_btop; ++ if (bindex >= 0) { ++ bbot = dinfo->di_bbot; ++ p = au_hdentry(dinfo, bindex); ++ while (bindex++ <= bbot) ++ au_hdput(p++); ++ } ++ kfree(dinfo->di_hdentry); ++ au_cache_free_dinfo(dinfo); ++} ++ ++void au_di_swap(struct au_dinfo *a, struct au_dinfo *b) ++{ ++ struct au_hdentry *p; ++ aufs_bindex_t bi; ++ ++ AuRwMustWriteLock(&a->di_rwsem); ++ AuRwMustWriteLock(&b->di_rwsem); ++ ++#define DiSwap(v, name) \ ++ do { \ ++ v = a->di_##name; \ ++ a->di_##name = b->di_##name; \ ++ b->di_##name = v; \ ++ } while (0) ++ ++ DiSwap(p, hdentry); ++ DiSwap(bi, btop); ++ DiSwap(bi, bbot); ++ DiSwap(bi, bwh); ++ DiSwap(bi, bdiropq); ++ /* smp_mb(); */ ++ ++#undef DiSwap ++} ++ ++void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src) ++{ ++ AuRwMustWriteLock(&dst->di_rwsem); ++ AuRwMustWriteLock(&src->di_rwsem); ++ ++ dst->di_btop = src->di_btop; ++ dst->di_bbot = src->di_bbot; ++ dst->di_bwh = src->di_bwh; ++ dst->di_bdiropq = src->di_bdiropq; ++ /* smp_mb(); */ ++} ++ ++int au_di_init(struct dentry *dentry) ++{ ++ int err; ++ struct super_block *sb; ++ struct au_dinfo *dinfo; ++ ++ err = 0; ++ sb = dentry->d_sb; ++ dinfo = au_di_alloc(sb, AuLsc_DI_CHILD); ++ if (dinfo) { ++ atomic_set(&dinfo->di_generation, au_sigen(sb)); ++ /* smp_mb(); */ /* atomic_set */ ++ dentry->d_fsdata = dinfo; ++ } else ++ err = -ENOMEM; ++ ++ return err; ++} ++ ++void au_di_fin(struct dentry *dentry) ++{ ++ struct au_dinfo *dinfo; ++ ++ dinfo = au_di(dentry); ++ AuRwDestroy(&dinfo->di_rwsem); ++ au_di_free(dinfo); ++} ++ ++int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink) ++{ ++ int err, sz; ++ struct au_hdentry *hdp; ++ ++ AuRwMustWriteLock(&dinfo->di_rwsem); ++ ++ err = -ENOMEM; ++ sz = sizeof(*hdp) * (dinfo->di_bbot + 1); ++ if (!sz) ++ sz = sizeof(*hdp); ++ hdp = au_kzrealloc(dinfo->di_hdentry, sz, sizeof(*hdp) * nbr, GFP_NOFS, ++ may_shrink); ++ if (hdp) { ++ dinfo->di_hdentry = hdp; ++ err = 0; ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void do_ii_write_lock(struct inode *inode, unsigned int lsc) ++{ ++ switch (lsc) { ++ case AuLsc_DI_CHILD: ++ ii_write_lock_child(inode); ++ break; ++ case AuLsc_DI_CHILD2: ++ ii_write_lock_child2(inode); ++ break; ++ case AuLsc_DI_CHILD3: ++ ii_write_lock_child3(inode); ++ break; ++ case AuLsc_DI_PARENT: ++ ii_write_lock_parent(inode); ++ break; ++ case AuLsc_DI_PARENT2: ++ ii_write_lock_parent2(inode); ++ break; ++ case AuLsc_DI_PARENT3: ++ ii_write_lock_parent3(inode); ++ break; ++ default: ++ BUG(); ++ } ++} ++ ++static void do_ii_read_lock(struct inode *inode, unsigned int lsc) ++{ ++ switch (lsc) { ++ case AuLsc_DI_CHILD: ++ ii_read_lock_child(inode); ++ break; ++ case AuLsc_DI_CHILD2: ++ ii_read_lock_child2(inode); ++ break; ++ case AuLsc_DI_CHILD3: ++ ii_read_lock_child3(inode); ++ break; ++ case AuLsc_DI_PARENT: ++ ii_read_lock_parent(inode); ++ break; ++ case AuLsc_DI_PARENT2: ++ ii_read_lock_parent2(inode); ++ break; ++ case AuLsc_DI_PARENT3: ++ ii_read_lock_parent3(inode); ++ break; ++ default: ++ BUG(); ++ } ++} ++ ++void di_read_lock(struct dentry *d, int flags, unsigned int lsc) ++{ ++ struct inode *inode; ++ ++ au_rw_read_lock_nested(&au_di(d)->di_rwsem, lsc); ++ if (d_really_is_positive(d)) { ++ inode = d_inode(d); ++ if (au_ftest_lock(flags, IW)) ++ do_ii_write_lock(inode, lsc); ++ else if (au_ftest_lock(flags, IR)) ++ do_ii_read_lock(inode, lsc); ++ } ++} ++ ++void di_read_unlock(struct dentry *d, int flags) ++{ ++ struct inode *inode; ++ ++ if (d_really_is_positive(d)) { ++ inode = d_inode(d); ++ if (au_ftest_lock(flags, IW)) { ++ au_dbg_verify_dinode(d); ++ ii_write_unlock(inode); ++ } else if (au_ftest_lock(flags, IR)) { ++ au_dbg_verify_dinode(d); ++ ii_read_unlock(inode); ++ } ++ } ++ au_rw_read_unlock(&au_di(d)->di_rwsem); ++} ++ ++void di_downgrade_lock(struct dentry *d, int flags) ++{ ++ if (d_really_is_positive(d) && au_ftest_lock(flags, IR)) ++ ii_downgrade_lock(d_inode(d)); ++ au_rw_dgrade_lock(&au_di(d)->di_rwsem); ++} ++ ++void di_write_lock(struct dentry *d, unsigned int lsc) ++{ ++ au_rw_write_lock_nested(&au_di(d)->di_rwsem, lsc); ++ if (d_really_is_positive(d)) ++ do_ii_write_lock(d_inode(d), lsc); ++} ++ ++void di_write_unlock(struct dentry *d) ++{ ++ au_dbg_verify_dinode(d); ++ if (d_really_is_positive(d)) ++ ii_write_unlock(d_inode(d)); ++ au_rw_write_unlock(&au_di(d)->di_rwsem); ++} ++ ++void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir) ++{ ++ AuDebugOn(d1 == d2 ++ || d_inode(d1) == d_inode(d2) ++ || d1->d_sb != d2->d_sb); ++ ++ if ((isdir && au_test_subdir(d1, d2)) ++ || d1 < d2) { ++ di_write_lock_child(d1); ++ di_write_lock_child2(d2); ++ } else { ++ di_write_lock_child(d2); ++ di_write_lock_child2(d1); ++ } ++} ++ ++void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir) ++{ ++ AuDebugOn(d1 == d2 ++ || d_inode(d1) == d_inode(d2) ++ || d1->d_sb != d2->d_sb); ++ ++ if ((isdir && au_test_subdir(d1, d2)) ++ || d1 < d2) { ++ di_write_lock_parent(d1); ++ di_write_lock_parent2(d2); ++ } else { ++ di_write_lock_parent(d2); ++ di_write_lock_parent2(d1); ++ } ++} ++ ++void di_write_unlock2(struct dentry *d1, struct dentry *d2) ++{ ++ di_write_unlock(d1); ++ if (d_inode(d1) == d_inode(d2)) ++ au_rw_write_unlock(&au_di(d2)->di_rwsem); ++ else ++ di_write_unlock(d2); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ struct dentry *d; ++ ++ DiMustAnyLock(dentry); ++ ++ if (au_dbtop(dentry) < 0 || bindex < au_dbtop(dentry)) ++ return NULL; ++ AuDebugOn(bindex < 0); ++ d = au_hdentry(au_di(dentry), bindex)->hd_dentry; ++ AuDebugOn(d && au_dcount(d) <= 0); ++ return d; ++} ++ ++/* ++ * extended version of au_h_dptr(). ++ * returns a hashed and positive (or linkable) h_dentry in bindex, NULL, or ++ * error. ++ */ ++struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ struct dentry *h_dentry; ++ struct inode *inode, *h_inode; ++ ++ AuDebugOn(d_really_is_negative(dentry)); ++ ++ h_dentry = NULL; ++ if (au_dbtop(dentry) <= bindex ++ && bindex <= au_dbbot(dentry)) ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry && !au_d_linkable(h_dentry)) { ++ dget(h_dentry); ++ goto out; /* success */ ++ } ++ ++ inode = d_inode(dentry); ++ AuDebugOn(bindex < au_ibtop(inode)); ++ AuDebugOn(au_ibbot(inode) < bindex); ++ h_inode = au_h_iptr(inode, bindex); ++ h_dentry = d_find_alias(h_inode); ++ if (h_dentry) { ++ if (!IS_ERR(h_dentry)) { ++ if (!au_d_linkable(h_dentry)) ++ goto out; /* success */ ++ dput(h_dentry); ++ } else ++ goto out; ++ } ++ ++ if (au_opt_test(au_mntflags(dentry->d_sb), PLINK)) { ++ h_dentry = au_plink_lkup(inode, bindex); ++ AuDebugOn(!h_dentry); ++ if (!IS_ERR(h_dentry)) { ++ if (!au_d_hashed_positive(h_dentry)) ++ goto out; /* success */ ++ dput(h_dentry); ++ h_dentry = NULL; ++ } ++ } ++ ++out: ++ AuDbgDentry(h_dentry); ++ return h_dentry; ++} ++ ++aufs_bindex_t au_dbtail(struct dentry *dentry) ++{ ++ aufs_bindex_t bbot, bwh; ++ ++ bbot = au_dbbot(dentry); ++ if (0 <= bbot) { ++ bwh = au_dbwh(dentry); ++ if (!bwh) ++ return bwh; ++ if (0 < bwh && bwh < bbot) ++ return bwh - 1; ++ } ++ return bbot; ++} ++ ++aufs_bindex_t au_dbtaildir(struct dentry *dentry) ++{ ++ aufs_bindex_t bbot, bopq; ++ ++ bbot = au_dbtail(dentry); ++ if (0 <= bbot) { ++ bopq = au_dbdiropq(dentry); ++ if (0 <= bopq && bopq < bbot) ++ bbot = bopq; ++ } ++ return bbot; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_dentry) ++{ ++ struct au_dinfo *dinfo; ++ struct au_hdentry *hd; ++ struct au_branch *br; ++ ++ DiMustWriteLock(dentry); ++ ++ dinfo = au_di(dentry); ++ hd = au_hdentry(dinfo, bindex); ++ au_hdput(hd); ++ hd->hd_dentry = h_dentry; ++ if (h_dentry) { ++ br = au_sbr(dentry->d_sb, bindex); ++ hd->hd_id = br->br_id; ++ } ++} ++ ++int au_dbrange_test(struct dentry *dentry) ++{ ++ int err; ++ aufs_bindex_t btop, bbot; ++ ++ err = 0; ++ btop = au_dbtop(dentry); ++ bbot = au_dbbot(dentry); ++ if (btop >= 0) ++ AuDebugOn(bbot < 0 && btop > bbot); ++ else { ++ err = -EIO; ++ AuDebugOn(bbot >= 0); ++ } ++ ++ return err; ++} ++ ++int au_digen_test(struct dentry *dentry, unsigned int sigen) ++{ ++ int err; ++ ++ err = 0; ++ if (unlikely(au_digen(dentry) != sigen ++ || au_iigen_test(d_inode(dentry), sigen))) ++ err = -EIO; ++ ++ return err; ++} ++ ++void au_update_digen(struct dentry *dentry) ++{ ++ atomic_set(&au_di(dentry)->di_generation, au_sigen(dentry->d_sb)); ++ /* smp_mb(); */ /* atomic_set */ ++} ++ ++void au_update_dbrange(struct dentry *dentry, int do_put_zero) ++{ ++ struct au_dinfo *dinfo; ++ struct dentry *h_d; ++ struct au_hdentry *hdp; ++ aufs_bindex_t bindex, bbot; ++ ++ DiMustWriteLock(dentry); ++ ++ dinfo = au_di(dentry); ++ if (!dinfo || dinfo->di_btop < 0) ++ return; ++ ++ if (do_put_zero) { ++ bbot = dinfo->di_bbot; ++ bindex = dinfo->di_btop; ++ hdp = au_hdentry(dinfo, bindex); ++ for (; bindex <= bbot; bindex++, hdp++) { ++ h_d = hdp->hd_dentry; ++ if (h_d && d_is_negative(h_d)) ++ au_set_h_dptr(dentry, bindex, NULL); ++ } ++ } ++ ++ dinfo->di_btop = 0; ++ hdp = au_hdentry(dinfo, dinfo->di_btop); ++ for (; dinfo->di_btop <= dinfo->di_bbot; dinfo->di_btop++, hdp++) ++ if (hdp->hd_dentry) ++ break; ++ if (dinfo->di_btop > dinfo->di_bbot) { ++ dinfo->di_btop = -1; ++ dinfo->di_bbot = -1; ++ return; ++ } ++ ++ hdp = au_hdentry(dinfo, dinfo->di_bbot); ++ for (; dinfo->di_bbot >= 0; dinfo->di_bbot--, hdp--) ++ if (hdp->hd_dentry) ++ break; ++ AuDebugOn(dinfo->di_btop > dinfo->di_bbot || dinfo->di_bbot < 0); ++} ++ ++void au_update_dbtop(struct dentry *dentry) ++{ ++ aufs_bindex_t bindex, bbot; ++ struct dentry *h_dentry; ++ ++ bbot = au_dbbot(dentry); ++ for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ if (d_is_positive(h_dentry)) { ++ au_set_dbtop(dentry, bindex); ++ return; ++ } ++ au_set_h_dptr(dentry, bindex, NULL); ++ } ++} ++ ++void au_update_dbbot(struct dentry *dentry) ++{ ++ aufs_bindex_t bindex, btop; ++ struct dentry *h_dentry; ++ ++ btop = au_dbtop(dentry); ++ for (bindex = au_dbbot(dentry); bindex >= btop; bindex--) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ if (d_is_positive(h_dentry)) { ++ au_set_dbbot(dentry, bindex); ++ return; ++ } ++ au_set_h_dptr(dentry, bindex, NULL); ++ } ++} ++ ++int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry) ++{ ++ aufs_bindex_t bindex, bbot; ++ ++ bbot = au_dbbot(dentry); ++ for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) ++ if (au_h_dptr(dentry, bindex) == h_dentry) ++ return bindex; ++ return -1; ++} +diff --git a/fs/aufs/dir.c b/fs/aufs/dir.c +new file mode 100644 +index 00000000..cd9e4aaf +--- /dev/null ++++ b/fs/aufs/dir.c +@@ -0,0 +1,759 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * directory operations ++ */ ++ ++#include ++#include "aufs.h" ++ ++void au_add_nlink(struct inode *dir, struct inode *h_dir) ++{ ++ unsigned int nlink; ++ ++ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); ++ ++ nlink = dir->i_nlink; ++ nlink += h_dir->i_nlink - 2; ++ if (h_dir->i_nlink < 2) ++ nlink += 2; ++ smp_mb(); /* for i_nlink */ ++ /* 0 can happen in revaliding */ ++ set_nlink(dir, nlink); ++} ++ ++void au_sub_nlink(struct inode *dir, struct inode *h_dir) ++{ ++ unsigned int nlink; ++ ++ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); ++ ++ nlink = dir->i_nlink; ++ nlink -= h_dir->i_nlink - 2; ++ if (h_dir->i_nlink < 2) ++ nlink -= 2; ++ smp_mb(); /* for i_nlink */ ++ /* nlink == 0 means the branch-fs is broken */ ++ set_nlink(dir, nlink); ++} ++ ++loff_t au_dir_size(struct file *file, struct dentry *dentry) ++{ ++ loff_t sz; ++ aufs_bindex_t bindex, bbot; ++ struct file *h_file; ++ struct dentry *h_dentry; ++ ++ sz = 0; ++ if (file) { ++ AuDebugOn(!d_is_dir(file->f_path.dentry)); ++ ++ bbot = au_fbbot_dir(file); ++ for (bindex = au_fbtop(file); ++ bindex <= bbot && sz < KMALLOC_MAX_SIZE; ++ bindex++) { ++ h_file = au_hf_dir(file, bindex); ++ if (h_file && file_inode(h_file)) ++ sz += vfsub_f_size_read(h_file); ++ } ++ } else { ++ AuDebugOn(!dentry); ++ AuDebugOn(!d_is_dir(dentry)); ++ ++ bbot = au_dbtaildir(dentry); ++ for (bindex = au_dbtop(dentry); ++ bindex <= bbot && sz < KMALLOC_MAX_SIZE; ++ bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry && d_is_positive(h_dentry)) ++ sz += i_size_read(d_inode(h_dentry)); ++ } ++ } ++ if (sz < KMALLOC_MAX_SIZE) ++ sz = roundup_pow_of_two(sz); ++ if (sz > KMALLOC_MAX_SIZE) ++ sz = KMALLOC_MAX_SIZE; ++ else if (sz < NAME_MAX) { ++ BUILD_BUG_ON(AUFS_RDBLK_DEF < NAME_MAX); ++ sz = AUFS_RDBLK_DEF; ++ } ++ return sz; ++} ++ ++struct au_dir_ts_arg { ++ struct dentry *dentry; ++ aufs_bindex_t brid; ++}; ++ ++static void au_do_dir_ts(void *arg) ++{ ++ struct au_dir_ts_arg *a = arg; ++ struct au_dtime dt; ++ struct path h_path; ++ struct inode *dir, *h_dir; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct au_hinode *hdir; ++ int err; ++ aufs_bindex_t btop, bindex; ++ ++ sb = a->dentry->d_sb; ++ if (d_really_is_negative(a->dentry)) ++ goto out; ++ /* no dir->i_mutex lock */ ++ aufs_read_lock(a->dentry, AuLock_DW); /* noflush */ ++ ++ dir = d_inode(a->dentry); ++ btop = au_ibtop(dir); ++ bindex = au_br_index(sb, a->brid); ++ if (bindex < btop) ++ goto out_unlock; ++ ++ br = au_sbr(sb, bindex); ++ h_path.dentry = au_h_dptr(a->dentry, bindex); ++ if (!h_path.dentry) ++ goto out_unlock; ++ h_path.mnt = au_br_mnt(br); ++ au_dtime_store(&dt, a->dentry, &h_path); ++ ++ br = au_sbr(sb, btop); ++ if (!au_br_writable(br->br_perm)) ++ goto out_unlock; ++ h_path.dentry = au_h_dptr(a->dentry, btop); ++ h_path.mnt = au_br_mnt(br); ++ err = vfsub_mnt_want_write(h_path.mnt); ++ if (err) ++ goto out_unlock; ++ hdir = au_hi(dir, btop); ++ au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); ++ h_dir = au_h_iptr(dir, btop); ++ if (h_dir->i_nlink ++ && timespec_compare(&h_dir->i_mtime, &dt.dt_mtime) < 0) { ++ dt.dt_h_path = h_path; ++ au_dtime_revert(&dt); ++ } ++ au_hn_inode_unlock(hdir); ++ vfsub_mnt_drop_write(h_path.mnt); ++ au_cpup_attr_timesizes(dir); ++ ++out_unlock: ++ aufs_read_unlock(a->dentry, AuLock_DW); ++out: ++ dput(a->dentry); ++ au_nwt_done(&au_sbi(sb)->si_nowait); ++ kfree(arg); ++} ++ ++void au_dir_ts(struct inode *dir, aufs_bindex_t bindex) ++{ ++ int perm, wkq_err; ++ aufs_bindex_t btop; ++ struct au_dir_ts_arg *arg; ++ struct dentry *dentry; ++ struct super_block *sb; ++ ++ IMustLock(dir); ++ ++ dentry = d_find_any_alias(dir); ++ AuDebugOn(!dentry); ++ sb = dentry->d_sb; ++ btop = au_ibtop(dir); ++ if (btop == bindex) { ++ au_cpup_attr_timesizes(dir); ++ goto out; ++ } ++ ++ perm = au_sbr_perm(sb, btop); ++ if (!au_br_writable(perm)) ++ goto out; ++ ++ arg = kmalloc(sizeof(*arg), GFP_NOFS); ++ if (!arg) ++ goto out; ++ ++ arg->dentry = dget(dentry); /* will be dput-ted by au_do_dir_ts() */ ++ arg->brid = au_sbr_id(sb, bindex); ++ wkq_err = au_wkq_nowait(au_do_dir_ts, arg, sb, /*flags*/0); ++ if (unlikely(wkq_err)) { ++ pr_err("wkq %d\n", wkq_err); ++ dput(dentry); ++ kfree(arg); ++ } ++ ++out: ++ dput(dentry); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int reopen_dir(struct file *file) ++{ ++ int err; ++ unsigned int flags; ++ aufs_bindex_t bindex, btail, btop; ++ struct dentry *dentry, *h_dentry; ++ struct file *h_file; ++ ++ /* open all lower dirs */ ++ dentry = file->f_path.dentry; ++ btop = au_dbtop(dentry); ++ for (bindex = au_fbtop(file); bindex < btop; bindex++) ++ au_set_h_fptr(file, bindex, NULL); ++ au_set_fbtop(file, btop); ++ ++ btail = au_dbtaildir(dentry); ++ for (bindex = au_fbbot_dir(file); btail < bindex; bindex--) ++ au_set_h_fptr(file, bindex, NULL); ++ au_set_fbbot_dir(file, btail); ++ ++ flags = vfsub_file_flags(file); ++ for (bindex = btop; bindex <= btail; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ h_file = au_hf_dir(file, bindex); ++ if (h_file) ++ continue; ++ ++ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; /* close all? */ ++ au_set_h_fptr(file, bindex, h_file); ++ } ++ au_update_figen(file); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ err = 0; ++ ++out: ++ return err; ++} ++ ++static int do_open_dir(struct file *file, int flags, struct file *h_file) ++{ ++ int err; ++ aufs_bindex_t bindex, btail; ++ struct dentry *dentry, *h_dentry; ++ struct vfsmount *mnt; ++ ++ FiMustWriteLock(file); ++ AuDebugOn(h_file); ++ ++ err = 0; ++ mnt = file->f_path.mnt; ++ dentry = file->f_path.dentry; ++ file->f_version = d_inode(dentry)->i_version; ++ bindex = au_dbtop(dentry); ++ au_set_fbtop(file, bindex); ++ btail = au_dbtaildir(dentry); ++ au_set_fbbot_dir(file, btail); ++ for (; !err && bindex <= btail; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ ++ err = vfsub_test_mntns(mnt, h_dentry->d_sb); ++ if (unlikely(err)) ++ break; ++ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); ++ if (IS_ERR(h_file)) { ++ err = PTR_ERR(h_file); ++ break; ++ } ++ au_set_h_fptr(file, bindex, h_file); ++ } ++ au_update_figen(file); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ if (!err) ++ return 0; /* success */ ++ ++ /* close all */ ++ for (bindex = au_fbtop(file); bindex <= btail; bindex++) ++ au_set_h_fptr(file, bindex, NULL); ++ au_set_fbtop(file, -1); ++ au_set_fbbot_dir(file, -1); ++ ++ return err; ++} ++ ++static int aufs_open_dir(struct inode *inode __maybe_unused, ++ struct file *file) ++{ ++ int err; ++ struct super_block *sb; ++ struct au_fidir *fidir; ++ ++ err = -ENOMEM; ++ sb = file->f_path.dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ fidir = au_fidir_alloc(sb); ++ if (fidir) { ++ struct au_do_open_args args = { ++ .open = do_open_dir, ++ .fidir = fidir ++ }; ++ err = au_do_open(file, &args); ++ if (unlikely(err)) ++ kfree(fidir); ++ } ++ si_read_unlock(sb); ++ return err; ++} ++ ++static int aufs_release_dir(struct inode *inode __maybe_unused, ++ struct file *file) ++{ ++ struct au_vdir *vdir_cache; ++ struct au_finfo *finfo; ++ struct au_fidir *fidir; ++ struct au_hfile *hf; ++ aufs_bindex_t bindex, bbot; ++ ++ finfo = au_fi(file); ++ fidir = finfo->fi_hdir; ++ if (fidir) { ++ au_hbl_del(&finfo->fi_hlist, ++ &au_sbi(file->f_path.dentry->d_sb)->si_files); ++ vdir_cache = fidir->fd_vdir_cache; /* lock-free */ ++ if (vdir_cache) ++ au_vdir_free(vdir_cache); ++ ++ bindex = finfo->fi_btop; ++ if (bindex >= 0) { ++ hf = fidir->fd_hfile + bindex; ++ /* ++ * calls fput() instead of filp_close(), ++ * since no dnotify or lock for the lower file. ++ */ ++ bbot = fidir->fd_bbot; ++ for (; bindex <= bbot; bindex++, hf++) ++ if (hf->hf_file) ++ au_hfput(hf, /*execed*/0); ++ } ++ kfree(fidir); ++ finfo->fi_hdir = NULL; ++ } ++ au_finfo_fin(file); ++ return 0; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_do_flush_dir(struct file *file, fl_owner_t id) ++{ ++ int err; ++ aufs_bindex_t bindex, bbot; ++ struct file *h_file; ++ ++ err = 0; ++ bbot = au_fbbot_dir(file); ++ for (bindex = au_fbtop(file); !err && bindex <= bbot; bindex++) { ++ h_file = au_hf_dir(file, bindex); ++ if (h_file) ++ err = vfsub_flush(h_file, id); ++ } ++ return err; ++} ++ ++static int aufs_flush_dir(struct file *file, fl_owner_t id) ++{ ++ return au_do_flush(file, id, au_do_flush_dir); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_do_fsync_dir_no_file(struct dentry *dentry, int datasync) ++{ ++ int err; ++ aufs_bindex_t bbot, bindex; ++ struct inode *inode; ++ struct super_block *sb; ++ ++ err = 0; ++ sb = dentry->d_sb; ++ inode = d_inode(dentry); ++ IMustLock(inode); ++ bbot = au_dbbot(dentry); ++ for (bindex = au_dbtop(dentry); !err && bindex <= bbot; bindex++) { ++ struct path h_path; ++ ++ if (au_test_ro(sb, bindex, inode)) ++ continue; ++ h_path.dentry = au_h_dptr(dentry, bindex); ++ if (!h_path.dentry) ++ continue; ++ ++ h_path.mnt = au_sbr_mnt(sb, bindex); ++ err = vfsub_fsync(NULL, &h_path, datasync); ++ } ++ ++ return err; ++} ++ ++static int au_do_fsync_dir(struct file *file, int datasync) ++{ ++ int err; ++ aufs_bindex_t bbot, bindex; ++ struct file *h_file; ++ struct super_block *sb; ++ struct inode *inode; ++ ++ err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0); ++ if (unlikely(err)) ++ goto out; ++ ++ inode = file_inode(file); ++ sb = inode->i_sb; ++ bbot = au_fbbot_dir(file); ++ for (bindex = au_fbtop(file); !err && bindex <= bbot; bindex++) { ++ h_file = au_hf_dir(file, bindex); ++ if (!h_file || au_test_ro(sb, bindex, inode)) ++ continue; ++ ++ err = vfsub_fsync(h_file, &h_file->f_path, datasync); ++ } ++ ++out: ++ return err; ++} ++ ++/* ++ * @file may be NULL ++ */ ++static int aufs_fsync_dir(struct file *file, loff_t start, loff_t end, ++ int datasync) ++{ ++ int err; ++ struct dentry *dentry; ++ struct inode *inode; ++ struct super_block *sb; ++ ++ err = 0; ++ dentry = file->f_path.dentry; ++ inode = d_inode(dentry); ++ inode_lock(inode); ++ sb = dentry->d_sb; ++ si_noflush_read_lock(sb); ++ if (file) ++ err = au_do_fsync_dir(file, datasync); ++ else { ++ di_write_lock_child(dentry); ++ err = au_do_fsync_dir_no_file(dentry, datasync); ++ } ++ au_cpup_attr_timesizes(inode); ++ di_write_unlock(dentry); ++ if (file) ++ fi_write_unlock(file); ++ ++ si_read_unlock(sb); ++ inode_unlock(inode); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int aufs_iterate_shared(struct file *file, struct dir_context *ctx) ++{ ++ int err; ++ struct dentry *dentry; ++ struct inode *inode, *h_inode; ++ struct super_block *sb; ++ ++ AuDbg("%pD, ctx{%pf, %llu}\n", file, ctx->actor, ctx->pos); ++ ++ dentry = file->f_path.dentry; ++ inode = d_inode(dentry); ++ IMustLock(inode); ++ ++ sb = dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0); ++ if (unlikely(err)) ++ goto out; ++ err = au_alive_dir(dentry); ++ if (!err) ++ err = au_vdir_init(file); ++ di_downgrade_lock(dentry, AuLock_IR); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ h_inode = au_h_iptr(inode, au_ibtop(inode)); ++ if (!au_test_nfsd()) { ++ err = au_vdir_fill_de(file, ctx); ++ fsstack_copy_attr_atime(inode, h_inode); ++ } else { ++ /* ++ * nfsd filldir may call lookup_one_len(), vfs_getattr(), ++ * encode_fh() and others. ++ */ ++ atomic_inc(&h_inode->i_count); ++ di_read_unlock(dentry, AuLock_IR); ++ si_read_unlock(sb); ++ err = au_vdir_fill_de(file, ctx); ++ fsstack_copy_attr_atime(inode, h_inode); ++ fi_write_unlock(file); ++ iput(h_inode); ++ ++ AuTraceErr(err); ++ return err; ++ } ++ ++out_unlock: ++ di_read_unlock(dentry, AuLock_IR); ++ fi_write_unlock(file); ++out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#define AuTestEmpty_WHONLY 1 ++#define AuTestEmpty_CALLED (1 << 1) ++#define AuTestEmpty_SHWH (1 << 2) ++#define au_ftest_testempty(flags, name) ((flags) & AuTestEmpty_##name) ++#define au_fset_testempty(flags, name) \ ++ do { (flags) |= AuTestEmpty_##name; } while (0) ++#define au_fclr_testempty(flags, name) \ ++ do { (flags) &= ~AuTestEmpty_##name; } while (0) ++ ++#ifndef CONFIG_AUFS_SHWH ++#undef AuTestEmpty_SHWH ++#define AuTestEmpty_SHWH 0 ++#endif ++ ++struct test_empty_arg { ++ struct dir_context ctx; ++ struct au_nhash *whlist; ++ unsigned int flags; ++ int err; ++ aufs_bindex_t bindex; ++}; ++ ++static int test_empty_cb(struct dir_context *ctx, const char *__name, ++ int namelen, loff_t offset __maybe_unused, u64 ino, ++ unsigned int d_type) ++{ ++ struct test_empty_arg *arg = container_of(ctx, struct test_empty_arg, ++ ctx); ++ char *name = (void *)__name; ++ ++ arg->err = 0; ++ au_fset_testempty(arg->flags, CALLED); ++ /* smp_mb(); */ ++ if (name[0] == '.' ++ && (namelen == 1 || (name[1] == '.' && namelen == 2))) ++ goto out; /* success */ ++ ++ if (namelen <= AUFS_WH_PFX_LEN ++ || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { ++ if (au_ftest_testempty(arg->flags, WHONLY) ++ && !au_nhash_test_known_wh(arg->whlist, name, namelen)) ++ arg->err = -ENOTEMPTY; ++ goto out; ++ } ++ ++ name += AUFS_WH_PFX_LEN; ++ namelen -= AUFS_WH_PFX_LEN; ++ if (!au_nhash_test_known_wh(arg->whlist, name, namelen)) ++ arg->err = au_nhash_append_wh ++ (arg->whlist, name, namelen, ino, d_type, arg->bindex, ++ au_ftest_testempty(arg->flags, SHWH)); ++ ++out: ++ /* smp_mb(); */ ++ AuTraceErr(arg->err); ++ return arg->err; ++} ++ ++static int do_test_empty(struct dentry *dentry, struct test_empty_arg *arg) ++{ ++ int err; ++ struct file *h_file; ++ ++ h_file = au_h_open(dentry, arg->bindex, ++ O_RDONLY | O_NONBLOCK | O_DIRECTORY | O_LARGEFILE, ++ /*file*/NULL, /*force_wr*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ err = 0; ++ if (!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE) ++ && !file_inode(h_file)->i_nlink) ++ goto out_put; ++ ++ do { ++ arg->err = 0; ++ au_fclr_testempty(arg->flags, CALLED); ++ /* smp_mb(); */ ++ err = vfsub_iterate_dir(h_file, &arg->ctx); ++ if (err >= 0) ++ err = arg->err; ++ } while (!err && au_ftest_testempty(arg->flags, CALLED)); ++ ++out_put: ++ fput(h_file); ++ au_sbr_put(dentry->d_sb, arg->bindex); ++out: ++ return err; ++} ++ ++struct do_test_empty_args { ++ int *errp; ++ struct dentry *dentry; ++ struct test_empty_arg *arg; ++}; ++ ++static void call_do_test_empty(void *args) ++{ ++ struct do_test_empty_args *a = args; ++ *a->errp = do_test_empty(a->dentry, a->arg); ++} ++ ++static int sio_test_empty(struct dentry *dentry, struct test_empty_arg *arg) ++{ ++ int err, wkq_err; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ ++ h_dentry = au_h_dptr(dentry, arg->bindex); ++ h_inode = d_inode(h_dentry); ++ /* todo: i_mode changes anytime? */ ++ vfsub_inode_lock_shared_nested(h_inode, AuLsc_I_CHILD); ++ err = au_test_h_perm_sio(h_inode, MAY_EXEC | MAY_READ); ++ inode_unlock_shared(h_inode); ++ if (!err) ++ err = do_test_empty(dentry, arg); ++ else { ++ struct do_test_empty_args args = { ++ .errp = &err, ++ .dentry = dentry, ++ .arg = arg ++ }; ++ unsigned int flags = arg->flags; ++ ++ wkq_err = au_wkq_wait(call_do_test_empty, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ arg->flags = flags; ++ } ++ ++ return err; ++} ++ ++int au_test_empty_lower(struct dentry *dentry) ++{ ++ int err; ++ unsigned int rdhash; ++ aufs_bindex_t bindex, btop, btail; ++ struct au_nhash whlist; ++ struct test_empty_arg arg = { ++ .ctx = { ++ .actor = test_empty_cb ++ } ++ }; ++ int (*test_empty)(struct dentry *dentry, struct test_empty_arg *arg); ++ ++ SiMustAnyLock(dentry->d_sb); ++ ++ rdhash = au_sbi(dentry->d_sb)->si_rdhash; ++ if (!rdhash) ++ rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, dentry)); ++ err = au_nhash_alloc(&whlist, rdhash, GFP_NOFS); ++ if (unlikely(err)) ++ goto out; ++ ++ arg.flags = 0; ++ arg.whlist = &whlist; ++ btop = au_dbtop(dentry); ++ if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)) ++ au_fset_testempty(arg.flags, SHWH); ++ test_empty = do_test_empty; ++ if (au_opt_test(au_mntflags(dentry->d_sb), DIRPERM1)) ++ test_empty = sio_test_empty; ++ arg.bindex = btop; ++ err = test_empty(dentry, &arg); ++ if (unlikely(err)) ++ goto out_whlist; ++ ++ au_fset_testempty(arg.flags, WHONLY); ++ btail = au_dbtaildir(dentry); ++ for (bindex = btop + 1; !err && bindex <= btail; bindex++) { ++ struct dentry *h_dentry; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry && d_is_positive(h_dentry)) { ++ arg.bindex = bindex; ++ err = test_empty(dentry, &arg); ++ } ++ } ++ ++out_whlist: ++ au_nhash_wh_free(&whlist); ++out: ++ return err; ++} ++ ++int au_test_empty(struct dentry *dentry, struct au_nhash *whlist) ++{ ++ int err; ++ struct test_empty_arg arg = { ++ .ctx = { ++ .actor = test_empty_cb ++ } ++ }; ++ aufs_bindex_t bindex, btail; ++ ++ err = 0; ++ arg.whlist = whlist; ++ arg.flags = AuTestEmpty_WHONLY; ++ if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)) ++ au_fset_testempty(arg.flags, SHWH); ++ btail = au_dbtaildir(dentry); ++ for (bindex = au_dbtop(dentry); !err && bindex <= btail; bindex++) { ++ struct dentry *h_dentry; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry && d_is_positive(h_dentry)) { ++ arg.bindex = bindex; ++ err = sio_test_empty(dentry, &arg); ++ } ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++const struct file_operations aufs_dir_fop = { ++ .owner = THIS_MODULE, ++ .llseek = default_llseek, ++ .read = generic_read_dir, ++ .iterate_shared = aufs_iterate_shared, ++ .unlocked_ioctl = aufs_ioctl_dir, ++#ifdef CONFIG_COMPAT ++ .compat_ioctl = aufs_compat_ioctl_dir, ++#endif ++ .open = aufs_open_dir, ++ .release = aufs_release_dir, ++ .flush = aufs_flush_dir, ++ .fsync = aufs_fsync_dir ++}; +diff --git a/fs/aufs/dir.h b/fs/aufs/dir.h +new file mode 100644 +index 00000000..ece11af4 +--- /dev/null ++++ b/fs/aufs/dir.h +@@ -0,0 +1,131 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * directory operations ++ */ ++ ++#ifndef __AUFS_DIR_H__ ++#define __AUFS_DIR_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* need to be faster and smaller */ ++ ++struct au_nhash { ++ unsigned int nh_num; ++ struct hlist_head *nh_head; ++}; ++ ++struct au_vdir_destr { ++ unsigned char len; ++ unsigned char name[0]; ++} __packed; ++ ++struct au_vdir_dehstr { ++ struct hlist_node hash; ++ struct au_vdir_destr *str; ++} ____cacheline_aligned_in_smp; ++ ++struct au_vdir_de { ++ ino_t de_ino; ++ unsigned char de_type; ++ /* caution: packed */ ++ struct au_vdir_destr de_str; ++} __packed; ++ ++struct au_vdir_wh { ++ struct hlist_node wh_hash; ++#ifdef CONFIG_AUFS_SHWH ++ ino_t wh_ino; ++ aufs_bindex_t wh_bindex; ++ unsigned char wh_type; ++#else ++ aufs_bindex_t wh_bindex; ++#endif ++ /* caution: packed */ ++ struct au_vdir_destr wh_str; ++} __packed; ++ ++union au_vdir_deblk_p { ++ unsigned char *deblk; ++ struct au_vdir_de *de; ++}; ++ ++struct au_vdir { ++ unsigned char **vd_deblk; ++ unsigned long vd_nblk; ++ struct { ++ unsigned long ul; ++ union au_vdir_deblk_p p; ++ } vd_last; ++ ++ unsigned long vd_version; ++ unsigned int vd_deblk_sz; ++ unsigned long vd_jiffy; ++} ____cacheline_aligned_in_smp; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* dir.c */ ++extern const struct file_operations aufs_dir_fop; ++void au_add_nlink(struct inode *dir, struct inode *h_dir); ++void au_sub_nlink(struct inode *dir, struct inode *h_dir); ++loff_t au_dir_size(struct file *file, struct dentry *dentry); ++void au_dir_ts(struct inode *dir, aufs_bindex_t bsrc); ++int au_test_empty_lower(struct dentry *dentry); ++int au_test_empty(struct dentry *dentry, struct au_nhash *whlist); ++ ++/* vdir.c */ ++unsigned int au_rdhash_est(loff_t sz); ++int au_nhash_alloc(struct au_nhash *nhash, unsigned int num_hash, gfp_t gfp); ++void au_nhash_wh_free(struct au_nhash *whlist); ++int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt, ++ int limit); ++int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int nlen); ++int au_nhash_append_wh(struct au_nhash *whlist, char *name, int nlen, ino_t ino, ++ unsigned int d_type, aufs_bindex_t bindex, ++ unsigned char shwh); ++void au_vdir_free(struct au_vdir *vdir); ++int au_vdir_init(struct file *file); ++int au_vdir_fill_de(struct file *file, struct dir_context *ctx); ++ ++/* ioctl.c */ ++long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg); ++ ++#ifdef CONFIG_AUFS_RDU ++/* rdu.c */ ++long au_rdu_ioctl(struct file *file, unsigned int cmd, unsigned long arg); ++#ifdef CONFIG_COMPAT ++long au_rdu_compat_ioctl(struct file *file, unsigned int cmd, ++ unsigned long arg); ++#endif ++#else ++AuStub(long, au_rdu_ioctl, return -EINVAL, struct file *file, ++ unsigned int cmd, unsigned long arg) ++#ifdef CONFIG_COMPAT ++AuStub(long, au_rdu_compat_ioctl, return -EINVAL, struct file *file, ++ unsigned int cmd, unsigned long arg) ++#endif ++#endif ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DIR_H__ */ +diff --git a/fs/aufs/dirren.c b/fs/aufs/dirren.c +new file mode 100644 +index 00000000..cf5b2033 +--- /dev/null ++++ b/fs/aufs/dirren.c +@@ -0,0 +1,1314 @@ ++/* ++ * Copyright (C) 2017-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * special handling in renaming a directoy ++ * in order to support looking-up the before-renamed name on the lower readonly ++ * branches ++ */ ++ ++#include ++#include "aufs.h" ++ ++static void au_dr_hino_del(struct au_dr_br *dr, struct au_dr_hino *ent) ++{ ++ int idx; ++ ++ idx = au_dr_ihash(ent->dr_h_ino); ++ au_hbl_del(&ent->dr_hnode, dr->dr_h_ino + idx); ++} ++ ++static int au_dr_hino_test_empty(struct au_dr_br *dr) ++{ ++ int ret, i; ++ struct hlist_bl_head *hbl; ++ ++ ret = 1; ++ for (i = 0; ret && i < AuDirren_NHASH; i++) { ++ hbl = dr->dr_h_ino + i; ++ hlist_bl_lock(hbl); ++ ret &= hlist_bl_empty(hbl); ++ hlist_bl_unlock(hbl); ++ } ++ ++ return ret; ++} ++ ++static struct au_dr_hino *au_dr_hino_find(struct au_dr_br *dr, ino_t ino) ++{ ++ struct au_dr_hino *found, *ent; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos; ++ int idx; ++ ++ found = NULL; ++ idx = au_dr_ihash(ino); ++ hbl = dr->dr_h_ino + idx; ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(ent, pos, hbl, dr_hnode) ++ if (ent->dr_h_ino == ino) { ++ found = ent; ++ break; ++ } ++ hlist_bl_unlock(hbl); ++ ++ return found; ++} ++ ++int au_dr_hino_test_add(struct au_dr_br *dr, ino_t ino, ++ struct au_dr_hino *add_ent) ++{ ++ int found, idx; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos; ++ struct au_dr_hino *ent; ++ ++ found = 0; ++ idx = au_dr_ihash(ino); ++ hbl = dr->dr_h_ino + idx; ++#if 0 ++ { ++ struct hlist_bl_node *tmp; ++ ++ hlist_bl_for_each_entry_safe(ent, pos, tmp, hbl, dr_hnode) ++ AuDbg("hi%llu\n", (unsigned long long)ent->dr_h_ino); ++ } ++#endif ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(ent, pos, hbl, dr_hnode) ++ if (ent->dr_h_ino == ino) { ++ found = 1; ++ break; ++ } ++ if (!found && add_ent) ++ hlist_bl_add_head(&add_ent->dr_hnode, hbl); ++ hlist_bl_unlock(hbl); ++ ++ if (!found && add_ent) ++ AuDbg("i%llu added\n", (unsigned long long)add_ent->dr_h_ino); ++ ++ return found; ++} ++ ++void au_dr_hino_free(struct au_dr_br *dr) ++{ ++ int i; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos, *tmp; ++ struct au_dr_hino *ent; ++ ++ /* SiMustWriteLock(sb); */ ++ ++ for (i = 0; i < AuDirren_NHASH; i++) { ++ hbl = dr->dr_h_ino + i; ++ /* no spinlock since sbinfo must be write-locked */ ++ hlist_bl_for_each_entry_safe(ent, pos, tmp, hbl, dr_hnode) ++ kfree(ent); ++ INIT_HLIST_BL_HEAD(hbl); ++ } ++} ++ ++/* returns the number of inodes or an error */ ++static int au_dr_hino_store(struct super_block *sb, struct au_branch *br, ++ struct file *hinofile) ++{ ++ int err, i; ++ ssize_t ssz; ++ loff_t pos, oldsize; ++ uint64_t u64; ++ struct inode *hinoinode; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *n1, *n2; ++ struct au_dr_hino *ent; ++ ++ SiMustWriteLock(sb); ++ AuDebugOn(!au_br_writable(br->br_perm)); ++ ++ hinoinode = file_inode(hinofile); ++ oldsize = i_size_read(hinoinode); ++ ++ err = 0; ++ pos = 0; ++ hbl = br->br_dirren.dr_h_ino; ++ for (i = 0; !err && i < AuDirren_NHASH; i++, hbl++) { ++ /* no bit-lock since sbinfo must be write-locked */ ++ hlist_bl_for_each_entry_safe(ent, n1, n2, hbl, dr_hnode) { ++ AuDbg("hi%llu, %pD2\n", ++ (unsigned long long)ent->dr_h_ino, hinofile); ++ u64 = cpu_to_be64(ent->dr_h_ino); ++ ssz = vfsub_write_k(hinofile, &u64, sizeof(u64), &pos); ++ if (ssz == sizeof(u64)) ++ continue; ++ ++ /* write error */ ++ pr_err("ssz %zd, %pD2\n", ssz, hinofile); ++ err = -ENOSPC; ++ if (ssz < 0) ++ err = ssz; ++ break; ++ } ++ } ++ /* regardless the error */ ++ if (pos < oldsize) { ++ err = vfsub_trunc(&hinofile->f_path, pos, /*attr*/0, hinofile); ++ AuTraceErr(err); ++ } ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++static int au_dr_hino_load(struct au_dr_br *dr, struct file *hinofile) ++{ ++ int err, hidx; ++ ssize_t ssz; ++ size_t sz, n; ++ loff_t pos; ++ uint64_t u64; ++ struct au_dr_hino *ent; ++ struct inode *hinoinode; ++ struct hlist_bl_head *hbl; ++ ++ err = 0; ++ pos = 0; ++ hbl = dr->dr_h_ino; ++ hinoinode = file_inode(hinofile); ++ sz = i_size_read(hinoinode); ++ AuDebugOn(sz % sizeof(u64)); ++ n = sz / sizeof(u64); ++ while (n--) { ++ ssz = vfsub_read_k(hinofile, &u64, sizeof(u64), &pos); ++ if (unlikely(ssz != sizeof(u64))) { ++ pr_err("ssz %zd, %pD2\n", ssz, hinofile); ++ err = -EINVAL; ++ if (ssz < 0) ++ err = ssz; ++ goto out_free; ++ } ++ ++ ent = kmalloc(sizeof(*ent), GFP_NOFS); ++ if (!ent) { ++ err = -ENOMEM; ++ AuTraceErr(err); ++ goto out_free; ++ } ++ ent->dr_h_ino = be64_to_cpu(u64); ++ AuDbg("hi%llu, %pD2\n", ++ (unsigned long long)ent->dr_h_ino, hinofile); ++ hidx = au_dr_ihash(ent->dr_h_ino); ++ au_hbl_add(&ent->dr_hnode, hbl + hidx); ++ } ++ goto out; /* success */ ++ ++out_free: ++ au_dr_hino_free(dr); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ++ * @bindex/@br is a switch to distinguish whether suspending hnotify or not. ++ * @path is a switch to distinguish load and store. ++ */ ++static int au_dr_hino(struct super_block *sb, aufs_bindex_t bindex, ++ struct au_branch *br, const struct path *path) ++{ ++ int err, flags; ++ unsigned char load, suspend; ++ struct file *hinofile; ++ struct au_hinode *hdir; ++ struct inode *dir, *delegated; ++ struct path hinopath; ++ struct qstr hinoname = QSTR_INIT(AUFS_WH_DR_BRHINO, ++ sizeof(AUFS_WH_DR_BRHINO) - 1); ++ ++ AuDebugOn(bindex < 0 && !br); ++ AuDebugOn(bindex >= 0 && br); ++ ++ err = -EINVAL; ++ suspend = !br; ++ if (suspend) ++ br = au_sbr(sb, bindex); ++ load = !!path; ++ if (!load) { ++ path = &br->br_path; ++ AuDebugOn(!au_br_writable(br->br_perm)); ++ if (unlikely(!au_br_writable(br->br_perm))) ++ goto out; ++ } ++ ++ hdir = NULL; ++ if (suspend) { ++ dir = d_inode(sb->s_root); ++ hdir = au_hinode(au_ii(dir), bindex); ++ dir = hdir->hi_inode; ++ au_hn_inode_lock_nested(hdir, AuLsc_I_CHILD); ++ } else { ++ dir = d_inode(path->dentry); ++ inode_lock_nested(dir, AuLsc_I_CHILD); ++ } ++ hinopath.dentry = vfsub_lkup_one(&hinoname, path->dentry); ++ err = PTR_ERR(hinopath.dentry); ++ if (IS_ERR(hinopath.dentry)) ++ goto out_unlock; ++ ++ err = 0; ++ flags = O_RDONLY; ++ if (load) { ++ if (d_is_negative(hinopath.dentry)) ++ goto out_dput; /* success */ ++ } else { ++ if (au_dr_hino_test_empty(&br->br_dirren)) { ++ if (d_is_positive(hinopath.dentry)) { ++ delegated = NULL; ++ err = vfsub_unlink(dir, &hinopath, &delegated, ++ /*force*/0); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ pr_err("ignored err %d, %pd2\n", ++ err, hinopath.dentry); ++ if (unlikely(err == -EWOULDBLOCK)) ++ iput(delegated); ++ err = 0; ++ } ++ goto out_dput; ++ } else if (!d_is_positive(hinopath.dentry)) { ++ err = vfsub_create(dir, &hinopath, 0600, ++ /*want_excl*/false); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ goto out_dput; ++ } ++ flags = O_WRONLY; ++ } ++ hinopath.mnt = path->mnt; ++ hinofile = vfsub_dentry_open(&hinopath, flags); ++ if (suspend) ++ au_hn_inode_unlock(hdir); ++ else ++ inode_unlock(dir); ++ dput(hinopath.dentry); ++ AuTraceErrPtr(hinofile); ++ if (IS_ERR(hinofile)) { ++ err = PTR_ERR(hinofile); ++ goto out; ++ } ++ ++ if (load) ++ err = au_dr_hino_load(&br->br_dirren, hinofile); ++ else ++ err = au_dr_hino_store(sb, br, hinofile); ++ fput(hinofile); ++ goto out; ++ ++out_dput: ++ dput(hinopath.dentry); ++out_unlock: ++ if (suspend) ++ au_hn_inode_unlock(hdir); ++ else ++ inode_unlock(dir); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_dr_brid_init(struct au_dr_brid *brid, const struct path *path) ++{ ++ int err; ++ struct kstatfs kstfs; ++ dev_t dev; ++ struct dentry *dentry; ++ struct super_block *sb; ++ ++ err = vfs_statfs((void *)path, &kstfs); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ goto out; ++ ++ /* todo: support for UUID */ ++ ++ if (kstfs.f_fsid.val[0] || kstfs.f_fsid.val[1]) { ++ brid->type = AuBrid_FSID; ++ brid->fsid = kstfs.f_fsid; ++ } else { ++ dentry = path->dentry; ++ sb = dentry->d_sb; ++ dev = sb->s_dev; ++ if (dev) { ++ brid->type = AuBrid_DEV; ++ brid->dev = dev; ++ } ++ } ++ ++out: ++ return err; ++} ++ ++int au_dr_br_init(struct super_block *sb, struct au_branch *br, ++ const struct path *path) ++{ ++ int err, i; ++ struct au_dr_br *dr; ++ struct hlist_bl_head *hbl; ++ ++ dr = &br->br_dirren; ++ hbl = dr->dr_h_ino; ++ for (i = 0; i < AuDirren_NHASH; i++, hbl++) ++ INIT_HLIST_BL_HEAD(hbl); ++ ++ err = au_dr_brid_init(&dr->dr_brid, path); ++ if (unlikely(err)) ++ goto out; ++ ++ if (au_opt_test(au_mntflags(sb), DIRREN)) ++ err = au_dr_hino(sb, /*bindex*/-1, br, path); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++int au_dr_br_fin(struct super_block *sb, struct au_branch *br) ++{ ++ int err; ++ ++ err = 0; ++ if (au_br_writable(br->br_perm)) ++ err = au_dr_hino(sb, /*bindex*/-1, br, /*path*/NULL); ++ if (!err) ++ au_dr_hino_free(&br->br_dirren); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_brid_str(struct au_dr_brid *brid, struct inode *h_inode, ++ char *buf, size_t sz) ++{ ++ int err; ++ unsigned int major, minor; ++ char *p; ++ ++ p = buf; ++ err = snprintf(p, sz, "%d_", brid->type); ++ AuDebugOn(err > sz); ++ p += err; ++ sz -= err; ++ switch (brid->type) { ++ case AuBrid_Unset: ++ return -EINVAL; ++ case AuBrid_UUID: ++ err = snprintf(p, sz, "%pU", brid->uuid.__u_bits); ++ break; ++ case AuBrid_FSID: ++ err = snprintf(p, sz, "%08x-%08x", ++ brid->fsid.val[0], brid->fsid.val[1]); ++ break; ++ case AuBrid_DEV: ++ major = MAJOR(brid->dev); ++ minor = MINOR(brid->dev); ++ if (major <= 0xff && minor <= 0xff) ++ err = snprintf(p, sz, "%02x%02x", major, minor); ++ else ++ err = snprintf(p, sz, "%03x:%05x", major, minor); ++ break; ++ } ++ AuDebugOn(err > sz); ++ p += err; ++ sz -= err; ++ err = snprintf(p, sz, "_%llu", (unsigned long long)h_inode->i_ino); ++ AuDebugOn(err > sz); ++ p += err; ++ sz -= err; ++ ++ return p - buf; ++} ++ ++static int au_drinfo_name(struct au_branch *br, char *name, int len) ++{ ++ int rlen; ++ struct dentry *br_dentry; ++ struct inode *br_inode; ++ ++ br_dentry = au_br_dentry(br); ++ br_inode = d_inode(br_dentry); ++ rlen = au_brid_str(&br->br_dirren.dr_brid, br_inode, name, len); ++ AuDebugOn(rlen >= AUFS_DIRREN_ENV_VAL_SZ); ++ AuDebugOn(rlen > len); ++ ++ return rlen; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * from the given @h_dentry, construct drinfo at @*fdata. ++ * when the size of @*fdata is not enough, reallocate and return new @fdata and ++ * @allocated. ++ */ ++static int au_drinfo_construct(struct au_drinfo_fdata **fdata, ++ struct dentry *h_dentry, ++ unsigned char *allocated) ++{ ++ int err, v; ++ struct au_drinfo_fdata *f, *p; ++ struct au_drinfo *drinfo; ++ struct inode *h_inode; ++ struct qstr *qname; ++ ++ err = 0; ++ f = *fdata; ++ h_inode = d_inode(h_dentry); ++ qname = &h_dentry->d_name; ++ drinfo = &f->drinfo; ++ drinfo->ino = cpu_to_be64(h_inode->i_ino); ++ drinfo->oldnamelen = qname->len; ++ if (*allocated < sizeof(*f) + qname->len) { ++ v = roundup_pow_of_two(*allocated + qname->len); ++ p = au_krealloc(f, v, GFP_NOFS, /*may_shrink*/0); ++ if (unlikely(!p)) { ++ err = -ENOMEM; ++ AuTraceErr(err); ++ goto out; ++ } ++ f = p; ++ *fdata = f; ++ *allocated = v; ++ drinfo = &f->drinfo; ++ } ++ memcpy(drinfo->oldname, qname->name, qname->len); ++ AuDbg("i%llu, %.*s\n", ++ be64_to_cpu(drinfo->ino), drinfo->oldnamelen, drinfo->oldname); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* callers have to free the return value */ ++static struct au_drinfo *au_drinfo_read_k(struct file *file, ino_t h_ino) ++{ ++ struct au_drinfo *ret, *drinfo; ++ struct au_drinfo_fdata fdata; ++ int len; ++ loff_t pos; ++ ssize_t ssz; ++ ++ ret = ERR_PTR(-EIO); ++ pos = 0; ++ ssz = vfsub_read_k(file, &fdata, sizeof(fdata), &pos); ++ if (unlikely(ssz != sizeof(fdata))) { ++ AuIOErr("ssz %zd, %u, %pD2\n", ++ ssz, (unsigned int)sizeof(fdata), file); ++ goto out; ++ } ++ ++ fdata.magic = ntohl(fdata.magic); ++ switch (fdata.magic) { ++ case AUFS_DRINFO_MAGIC_V1: ++ break; ++ default: ++ AuIOErr("magic-num 0x%x, 0x%x, %pD2\n", ++ fdata.magic, AUFS_DRINFO_MAGIC_V1, file); ++ goto out; ++ } ++ ++ drinfo = &fdata.drinfo; ++ len = drinfo->oldnamelen; ++ if (!len) { ++ AuIOErr("broken drinfo %pD2\n", file); ++ goto out; ++ } ++ ++ ret = NULL; ++ drinfo->ino = be64_to_cpu(drinfo->ino); ++ if (unlikely(h_ino && drinfo->ino != h_ino)) { ++ AuDbg("ignored i%llu, i%llu, %pD2\n", ++ (unsigned long long)drinfo->ino, ++ (unsigned long long)h_ino, file); ++ goto out; /* success */ ++ } ++ ++ ret = kmalloc(sizeof(*ret) + len, GFP_NOFS); ++ if (unlikely(!ret)) { ++ ret = ERR_PTR(-ENOMEM); ++ AuTraceErrPtr(ret); ++ goto out; ++ } ++ ++ *ret = *drinfo; ++ ssz = vfsub_read_k(file, (void *)ret->oldname, len, &pos); ++ if (unlikely(ssz != len)) { ++ kfree(ret); ++ ret = ERR_PTR(-EIO); ++ AuIOErr("ssz %zd, %u, %pD2\n", ssz, len, file); ++ goto out; ++ } ++ ++ AuDbg("oldname %.*s\n", ret->oldnamelen, ret->oldname); ++ ++out: ++ return ret; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* in order to be revertible */ ++struct au_drinfo_rev_elm { ++ int created; ++ struct dentry *info_dentry; ++ struct au_drinfo *info_last; ++}; ++ ++struct au_drinfo_rev { ++ unsigned char already; ++ aufs_bindex_t nelm; ++ struct au_drinfo_rev_elm elm[0]; ++}; ++ ++/* todo: isn't it too large? */ ++struct au_drinfo_store { ++ struct path h_ppath; ++ struct dentry *h_dentry; ++ struct au_drinfo_fdata *fdata; ++ char *infoname; /* inside of whname, just after PFX */ ++ char whname[sizeof(AUFS_WH_DR_INFO_PFX) + AUFS_DIRREN_ENV_VAL_SZ]; ++ aufs_bindex_t btgt, btail; ++ unsigned char no_sio, ++ allocated, /* current size of *fdata */ ++ infonamelen, /* room size for p */ ++ whnamelen, /* length of the genarated name */ ++ renameback; /* renamed back */ ++}; ++ ++/* on rename(2) error, the caller should revert it using @elm */ ++static int au_drinfo_do_store(struct au_drinfo_store *w, ++ struct au_drinfo_rev_elm *elm) ++{ ++ int err, len; ++ ssize_t ssz; ++ loff_t pos; ++ struct path infopath = { ++ .mnt = w->h_ppath.mnt ++ }; ++ struct inode *h_dir, *h_inode, *delegated; ++ struct file *infofile; ++ struct qstr *qname; ++ ++ AuDebugOn(elm ++ && memcmp(elm, page_address(ZERO_PAGE(0)), sizeof(*elm))); ++ ++ infopath.dentry = vfsub_lookup_one_len(w->whname, w->h_ppath.dentry, ++ w->whnamelen); ++ AuTraceErrPtr(infopath.dentry); ++ if (IS_ERR(infopath.dentry)) { ++ err = PTR_ERR(infopath.dentry); ++ goto out; ++ } ++ ++ err = 0; ++ h_dir = d_inode(w->h_ppath.dentry); ++ if (elm && d_is_negative(infopath.dentry)) { ++ err = vfsub_create(h_dir, &infopath, 0600, /*want_excl*/true); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ goto out_dput; ++ elm->created = 1; ++ elm->info_dentry = dget(infopath.dentry); ++ } ++ ++ infofile = vfsub_dentry_open(&infopath, O_RDWR); ++ AuTraceErrPtr(infofile); ++ if (IS_ERR(infofile)) { ++ err = PTR_ERR(infofile); ++ goto out_dput; ++ } ++ ++ h_inode = d_inode(infopath.dentry); ++ if (elm && i_size_read(h_inode)) { ++ h_inode = d_inode(w->h_dentry); ++ elm->info_last = au_drinfo_read_k(infofile, h_inode->i_ino); ++ AuTraceErrPtr(elm->info_last); ++ if (IS_ERR(elm->info_last)) { ++ err = PTR_ERR(elm->info_last); ++ elm->info_last = NULL; ++ AuDebugOn(elm->info_dentry); ++ goto out_fput; ++ } ++ } ++ ++ if (elm && w->renameback) { ++ delegated = NULL; ++ err = vfsub_unlink(h_dir, &infopath, &delegated, /*force*/0); ++ AuTraceErr(err); ++ if (unlikely(err == -EWOULDBLOCK)) ++ iput(delegated); ++ goto out_fput; ++ } ++ ++ pos = 0; ++ qname = &w->h_dentry->d_name; ++ len = sizeof(*w->fdata) + qname->len; ++ if (!elm) ++ len = sizeof(*w->fdata) + w->fdata->drinfo.oldnamelen; ++ ssz = vfsub_write_k(infofile, w->fdata, len, &pos); ++ if (ssz == len) { ++ AuDbg("hi%llu, %.*s\n", w->fdata->drinfo.ino, ++ w->fdata->drinfo.oldnamelen, w->fdata->drinfo.oldname); ++ goto out_fput; /* success */ ++ } else { ++ err = -EIO; ++ if (ssz < 0) ++ err = ssz; ++ /* the caller should revert it using @elm */ ++ } ++ ++out_fput: ++ fput(infofile); ++out_dput: ++ dput(infopath.dentry); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++struct au_call_drinfo_do_store_args { ++ int *errp; ++ struct au_drinfo_store *w; ++ struct au_drinfo_rev_elm *elm; ++}; ++ ++static void au_call_drinfo_do_store(void *args) ++{ ++ struct au_call_drinfo_do_store_args *a = args; ++ ++ *a->errp = au_drinfo_do_store(a->w, a->elm); ++} ++ ++static int au_drinfo_store_sio(struct au_drinfo_store *w, ++ struct au_drinfo_rev_elm *elm) ++{ ++ int err, wkq_err; ++ ++ if (w->no_sio) ++ err = au_drinfo_do_store(w, elm); ++ else { ++ struct au_call_drinfo_do_store_args a = { ++ .errp = &err, ++ .w = w, ++ .elm = elm ++ }; ++ wkq_err = au_wkq_wait(au_call_drinfo_do_store, &a); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ AuTraceErr(err); ++ ++ return err; ++} ++ ++static int au_drinfo_store_work_init(struct au_drinfo_store *w, ++ aufs_bindex_t btgt) ++{ ++ int err; ++ ++ memset(w, 0, sizeof(*w)); ++ w->allocated = roundup_pow_of_two(sizeof(*w->fdata) + 40); ++ strcpy(w->whname, AUFS_WH_DR_INFO_PFX); ++ w->infoname = w->whname + sizeof(AUFS_WH_DR_INFO_PFX) - 1; ++ w->infonamelen = sizeof(w->whname) - sizeof(AUFS_WH_DR_INFO_PFX); ++ w->btgt = btgt; ++ w->no_sio = !!uid_eq(current_fsuid(), GLOBAL_ROOT_UID); ++ ++ err = -ENOMEM; ++ w->fdata = kcalloc(1, w->allocated, GFP_NOFS); ++ if (unlikely(!w->fdata)) { ++ AuTraceErr(err); ++ goto out; ++ } ++ w->fdata->magic = htonl(AUFS_DRINFO_MAGIC_V1); ++ err = 0; ++ ++out: ++ return err; ++} ++ ++static void au_drinfo_store_work_fin(struct au_drinfo_store *w) ++{ ++ kfree(w->fdata); ++} ++ ++static void au_drinfo_store_rev(struct au_drinfo_rev *rev, ++ struct au_drinfo_store *w) ++{ ++ struct au_drinfo_rev_elm *elm; ++ struct inode *h_dir, *delegated; ++ int err, nelm; ++ struct path infopath = { ++ .mnt = w->h_ppath.mnt ++ }; ++ ++ h_dir = d_inode(w->h_ppath.dentry); ++ IMustLock(h_dir); ++ ++ err = 0; ++ elm = rev->elm; ++ for (nelm = rev->nelm; nelm > 0; nelm--, elm++) { ++ AuDebugOn(elm->created && elm->info_last); ++ if (elm->created) { ++ AuDbg("here\n"); ++ delegated = NULL; ++ infopath.dentry = elm->info_dentry; ++ err = vfsub_unlink(h_dir, &infopath, &delegated, ++ !w->no_sio); ++ AuTraceErr(err); ++ if (unlikely(err == -EWOULDBLOCK)) ++ iput(delegated); ++ dput(elm->info_dentry); ++ } else if (elm->info_last) { ++ AuDbg("here\n"); ++ w->fdata->drinfo = *elm->info_last; ++ memcpy(w->fdata->drinfo.oldname, ++ elm->info_last->oldname, ++ elm->info_last->oldnamelen); ++ err = au_drinfo_store_sio(w, /*elm*/NULL); ++ kfree(elm->info_last); ++ } ++ if (unlikely(err)) ++ AuIOErr("%d, %s\n", err, w->whname); ++ /* go on even if err */ ++ } ++} ++ ++/* caller has to call au_dr_rename_fin() later */ ++static int au_drinfo_store(struct dentry *dentry, aufs_bindex_t btgt, ++ struct qstr *dst_name, void *_rev) ++{ ++ int err, sz, nelm; ++ aufs_bindex_t bindex, btail; ++ struct au_drinfo_store work; ++ struct au_drinfo_rev *rev, **p; ++ struct au_drinfo_rev_elm *elm; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct au_hinode *hdir; ++ ++ err = au_drinfo_store_work_init(&work, btgt); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ goto out; ++ ++ err = -ENOMEM; ++ btail = au_dbtaildir(dentry); ++ nelm = btail - btgt; ++ sz = sizeof(*rev) + sizeof(*elm) * nelm; ++ rev = kcalloc(1, sz, GFP_NOFS); ++ if (unlikely(!rev)) { ++ AuTraceErr(err); ++ goto out_args; ++ } ++ rev->nelm = nelm; ++ elm = rev->elm; ++ p = _rev; ++ *p = rev; ++ ++ err = 0; ++ sb = dentry->d_sb; ++ work.h_ppath.dentry = au_h_dptr(dentry, btgt); ++ work.h_ppath.mnt = au_sbr_mnt(sb, btgt); ++ hdir = au_hi(d_inode(dentry), btgt); ++ au_hn_inode_lock_nested(hdir, AuLsc_I_CHILD); ++ for (bindex = btgt + 1; bindex <= btail; bindex++, elm++) { ++ work.h_dentry = au_h_dptr(dentry, bindex); ++ if (!work.h_dentry) ++ continue; ++ ++ err = au_drinfo_construct(&work.fdata, work.h_dentry, ++ &work.allocated); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ break; ++ ++ work.renameback = au_qstreq(&work.h_dentry->d_name, dst_name); ++ br = au_sbr(sb, bindex); ++ work.whnamelen = sizeof(AUFS_WH_DR_INFO_PFX) - 1; ++ work.whnamelen += au_drinfo_name(br, work.infoname, ++ work.infonamelen); ++ AuDbg("whname %.*s, i%llu, %.*s\n", ++ work.whnamelen, work.whname, ++ be64_to_cpu(work.fdata->drinfo.ino), ++ work.fdata->drinfo.oldnamelen, ++ work.fdata->drinfo.oldname); ++ ++ err = au_drinfo_store_sio(&work, elm); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ break; ++ } ++ if (unlikely(err)) { ++ /* revert all drinfo */ ++ au_drinfo_store_rev(rev, &work); ++ kfree(rev); ++ *p = NULL; ++ } ++ au_hn_inode_unlock(hdir); ++ ++out_args: ++ au_drinfo_store_work_fin(&work); ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_dr_rename(struct dentry *src, aufs_bindex_t bindex, ++ struct qstr *dst_name, void *_rev) ++{ ++ int err, already; ++ ino_t ino; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct au_dr_br *dr; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ struct au_dr_hino *ent; ++ struct au_drinfo_rev *rev, **p; ++ ++ AuDbg("bindex %d\n", bindex); ++ ++ err = -ENOMEM; ++ ent = kmalloc(sizeof(*ent), GFP_NOFS); ++ if (unlikely(!ent)) ++ goto out; ++ ++ sb = src->d_sb; ++ br = au_sbr(sb, bindex); ++ dr = &br->br_dirren; ++ h_dentry = au_h_dptr(src, bindex); ++ h_inode = d_inode(h_dentry); ++ ino = h_inode->i_ino; ++ ent->dr_h_ino = ino; ++ already = au_dr_hino_test_add(dr, ino, ent); ++ AuDbg("b%d, hi%llu, already %d\n", ++ bindex, (unsigned long long)ino, already); ++ ++ err = au_drinfo_store(src, bindex, dst_name, _rev); ++ AuTraceErr(err); ++ if (!err) { ++ p = _rev; ++ rev = *p; ++ rev->already = already; ++ goto out; /* success */ ++ } ++ ++ /* revert */ ++ if (!already) ++ au_dr_hino_del(dr, ent); ++ kfree(ent); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *_rev) ++{ ++ struct au_drinfo_rev *rev; ++ struct au_drinfo_rev_elm *elm; ++ int nelm; ++ ++ rev = _rev; ++ elm = rev->elm; ++ for (nelm = rev->nelm; nelm > 0; nelm--, elm++) { ++ dput(elm->info_dentry); ++ kfree(elm->info_last); ++ } ++ kfree(rev); ++} ++ ++void au_dr_rename_rev(struct dentry *src, aufs_bindex_t btgt, void *_rev) ++{ ++ int err; ++ struct au_drinfo_store work; ++ struct au_drinfo_rev *rev = _rev; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct inode *h_inode; ++ struct au_dr_br *dr; ++ struct au_dr_hino *ent; ++ ++ err = au_drinfo_store_work_init(&work, btgt); ++ if (unlikely(err)) ++ goto out; ++ ++ sb = src->d_sb; ++ br = au_sbr(sb, btgt); ++ work.h_ppath.dentry = au_h_dptr(src, btgt); ++ work.h_ppath.mnt = au_br_mnt(br); ++ au_drinfo_store_rev(rev, &work); ++ au_drinfo_store_work_fin(&work); ++ if (rev->already) ++ goto out; ++ ++ dr = &br->br_dirren; ++ h_inode = d_inode(work.h_ppath.dentry); ++ ent = au_dr_hino_find(dr, h_inode->i_ino); ++ BUG_ON(!ent); ++ au_dr_hino_del(dr, ent); ++ kfree(ent); ++ ++out: ++ kfree(rev); ++ if (unlikely(err)) ++ pr_err("failed to remove dirren info\n"); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct au_drinfo *au_drinfo_do_load(struct path *h_ppath, ++ char *whname, int whnamelen, ++ struct dentry **info_dentry) ++{ ++ struct au_drinfo *drinfo; ++ struct file *f; ++ struct inode *h_dir; ++ struct path infopath; ++ int unlocked; ++ ++ AuDbg("%pd/%.*s\n", h_ppath->dentry, whnamelen, whname); ++ ++ *info_dentry = NULL; ++ drinfo = NULL; ++ unlocked = 0; ++ h_dir = d_inode(h_ppath->dentry); ++ vfsub_inode_lock_shared_nested(h_dir, AuLsc_I_PARENT); ++ infopath.dentry = vfsub_lookup_one_len(whname, h_ppath->dentry, ++ whnamelen); ++ if (IS_ERR(infopath.dentry)) { ++ drinfo = (void *)infopath.dentry; ++ goto out; ++ } ++ ++ if (d_is_negative(infopath.dentry)) ++ goto out_dput; /* success */ ++ ++ infopath.mnt = h_ppath->mnt; ++ f = vfsub_dentry_open(&infopath, O_RDONLY); ++ inode_unlock_shared(h_dir); ++ unlocked = 1; ++ if (IS_ERR(f)) { ++ drinfo = (void *)f; ++ goto out_dput; ++ } ++ ++ drinfo = au_drinfo_read_k(f, /*h_ino*/0); ++ if (IS_ERR_OR_NULL(drinfo)) ++ goto out_fput; ++ ++ AuDbg("oldname %.*s\n", drinfo->oldnamelen, drinfo->oldname); ++ *info_dentry = dget(infopath.dentry); /* keep it alive */ ++ ++out_fput: ++ fput(f); ++out_dput: ++ dput(infopath.dentry); ++out: ++ if (!unlocked) ++ inode_unlock_shared(h_dir); ++ AuTraceErrPtr(drinfo); ++ return drinfo; ++} ++ ++struct au_drinfo_do_load_args { ++ struct au_drinfo **drinfop; ++ struct path *h_ppath; ++ char *whname; ++ int whnamelen; ++ struct dentry **info_dentry; ++}; ++ ++static void au_call_drinfo_do_load(void *args) ++{ ++ struct au_drinfo_do_load_args *a = args; ++ ++ *a->drinfop = au_drinfo_do_load(a->h_ppath, a->whname, a->whnamelen, ++ a->info_dentry); ++} ++ ++struct au_drinfo_load { ++ struct path h_ppath; ++ struct qstr *qname; ++ unsigned char no_sio; ++ ++ aufs_bindex_t ninfo; ++ struct au_drinfo **drinfo; ++}; ++ ++static int au_drinfo_load(struct au_drinfo_load *w, aufs_bindex_t bindex, ++ struct au_branch *br) ++{ ++ int err, wkq_err, whnamelen, e; ++ char whname[sizeof(AUFS_WH_DR_INFO_PFX) + AUFS_DIRREN_ENV_VAL_SZ] ++ = AUFS_WH_DR_INFO_PFX; ++ struct au_drinfo *drinfo; ++ struct qstr oldname; ++ struct inode *h_dir, *delegated; ++ struct dentry *info_dentry; ++ struct path infopath; ++ ++ whnamelen = sizeof(AUFS_WH_DR_INFO_PFX) - 1; ++ whnamelen += au_drinfo_name(br, whname + whnamelen, ++ sizeof(whname) - whnamelen); ++ if (w->no_sio) ++ drinfo = au_drinfo_do_load(&w->h_ppath, whname, whnamelen, ++ &info_dentry); ++ else { ++ struct au_drinfo_do_load_args args = { ++ .drinfop = &drinfo, ++ .h_ppath = &w->h_ppath, ++ .whname = whname, ++ .whnamelen = whnamelen, ++ .info_dentry = &info_dentry ++ }; ++ wkq_err = au_wkq_wait(au_call_drinfo_do_load, &args); ++ if (unlikely(wkq_err)) ++ drinfo = ERR_PTR(wkq_err); ++ } ++ err = PTR_ERR(drinfo); ++ if (IS_ERR_OR_NULL(drinfo)) ++ goto out; ++ ++ err = 0; ++ oldname.len = drinfo->oldnamelen; ++ oldname.name = drinfo->oldname; ++ if (au_qstreq(w->qname, &oldname)) { ++ /* the name is renamed back */ ++ kfree(drinfo); ++ drinfo = NULL; ++ ++ infopath.dentry = info_dentry; ++ infopath.mnt = w->h_ppath.mnt; ++ h_dir = d_inode(w->h_ppath.dentry); ++ delegated = NULL; ++ inode_lock_nested(h_dir, AuLsc_I_PARENT); ++ e = vfsub_unlink(h_dir, &infopath, &delegated, !w->no_sio); ++ inode_unlock(h_dir); ++ if (unlikely(e)) ++ AuIOErr("ignored %d, %pd2\n", e, &infopath.dentry); ++ if (unlikely(e == -EWOULDBLOCK)) ++ iput(delegated); ++ } ++ kfree(w->drinfo[bindex]); ++ w->drinfo[bindex] = drinfo; ++ dput(info_dentry); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void au_dr_lkup_free(struct au_drinfo **drinfo, int n) ++{ ++ struct au_drinfo **p = drinfo; ++ ++ while (n-- > 0) ++ kfree(*drinfo++); ++ kfree(p); ++} ++ ++int au_dr_lkup(struct au_do_lookup_args *lkup, struct dentry *dentry, ++ aufs_bindex_t btgt) ++{ ++ int err, ninfo; ++ struct au_drinfo_load w; ++ aufs_bindex_t bindex, bbot; ++ struct au_branch *br; ++ struct inode *h_dir; ++ struct au_dr_hino *ent; ++ struct super_block *sb; ++ ++ AuDbg("%.*s, name %.*s, whname %.*s, b%d\n", ++ AuLNPair(&dentry->d_name), AuLNPair(&lkup->dirren.dr_name), ++ AuLNPair(&lkup->whname), btgt); ++ ++ sb = dentry->d_sb; ++ bbot = au_sbbot(sb); ++ w.ninfo = bbot + 1; ++ if (!lkup->dirren.drinfo) { ++ lkup->dirren.drinfo = kcalloc(w.ninfo, ++ sizeof(*lkup->dirren.drinfo), ++ GFP_NOFS); ++ if (unlikely(!lkup->dirren.drinfo)) { ++ err = -ENOMEM; ++ goto out; ++ } ++ lkup->dirren.ninfo = w.ninfo; ++ } ++ w.drinfo = lkup->dirren.drinfo; ++ w.no_sio = !!uid_eq(current_fsuid(), GLOBAL_ROOT_UID); ++ w.h_ppath.dentry = au_h_dptr(dentry, btgt); ++ AuDebugOn(!w.h_ppath.dentry); ++ w.h_ppath.mnt = au_sbr_mnt(sb, btgt); ++ w.qname = &dentry->d_name; ++ ++ ninfo = 0; ++ for (bindex = btgt + 1; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ err = au_drinfo_load(&w, bindex, br); ++ if (unlikely(err)) ++ goto out_free; ++ if (w.drinfo[bindex]) ++ ninfo++; ++ } ++ if (!ninfo) { ++ br = au_sbr(sb, btgt); ++ h_dir = d_inode(w.h_ppath.dentry); ++ ent = au_dr_hino_find(&br->br_dirren, h_dir->i_ino); ++ AuDebugOn(!ent); ++ au_dr_hino_del(&br->br_dirren, ent); ++ kfree(ent); ++ } ++ goto out; /* success */ ++ ++out_free: ++ au_dr_lkup_free(lkup->dirren.drinfo, lkup->dirren.ninfo); ++ lkup->dirren.ninfo = 0; ++ lkup->dirren.drinfo = NULL; ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++void au_dr_lkup_fin(struct au_do_lookup_args *lkup) ++{ ++ au_dr_lkup_free(lkup->dirren.drinfo, lkup->dirren.ninfo); ++} ++ ++int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt) ++{ ++ int err; ++ struct au_drinfo *drinfo; ++ ++ err = 0; ++ if (!lkup->dirren.drinfo) ++ goto out; ++ AuDebugOn(lkup->dirren.ninfo < btgt + 1); ++ drinfo = lkup->dirren.drinfo[btgt + 1]; ++ if (!drinfo) ++ goto out; ++ ++ kfree(lkup->whname.name); ++ lkup->whname.name = NULL; ++ lkup->dirren.dr_name.len = drinfo->oldnamelen; ++ lkup->dirren.dr_name.name = drinfo->oldname; ++ lkup->name = &lkup->dirren.dr_name; ++ err = au_wh_name_alloc(&lkup->whname, lkup->name); ++ if (!err) ++ AuDbg("name %.*s, whname %.*s, b%d\n", ++ AuLNPair(lkup->name), AuLNPair(&lkup->whname), ++ btgt); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex, ++ ino_t h_ino) ++{ ++ int match; ++ struct au_drinfo *drinfo; ++ ++ match = 1; ++ if (!lkup->dirren.drinfo) ++ goto out; ++ AuDebugOn(lkup->dirren.ninfo < bindex + 1); ++ drinfo = lkup->dirren.drinfo[bindex + 1]; ++ if (!drinfo) ++ goto out; ++ ++ match = (drinfo->ino == h_ino); ++ AuDbg("match %d\n", match); ++ ++out: ++ return match; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_dr_opt_set(struct super_block *sb) ++{ ++ int err; ++ aufs_bindex_t bindex, bbot; ++ struct au_branch *br; ++ ++ err = 0; ++ bbot = au_sbbot(sb); ++ for (bindex = 0; !err && bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ err = au_dr_hino(sb, bindex, /*br*/NULL, &br->br_path); ++ } ++ ++ return err; ++} ++ ++int au_dr_opt_flush(struct super_block *sb) ++{ ++ int err; ++ aufs_bindex_t bindex, bbot; ++ struct au_branch *br; ++ ++ err = 0; ++ bbot = au_sbbot(sb); ++ for (bindex = 0; !err && bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (au_br_writable(br->br_perm)) ++ err = au_dr_hino(sb, bindex, /*br*/NULL, /*path*/NULL); ++ } ++ ++ return err; ++} ++ ++int au_dr_opt_clr(struct super_block *sb, int no_flush) ++{ ++ int err; ++ aufs_bindex_t bindex, bbot; ++ struct au_branch *br; ++ ++ err = 0; ++ if (!no_flush) { ++ err = au_dr_opt_flush(sb); ++ if (unlikely(err)) ++ goto out; ++ } ++ ++ bbot = au_sbbot(sb); ++ for (bindex = 0; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ au_dr_hino_free(&br->br_dirren); ++ } ++ ++out: ++ return err; ++} +diff --git a/fs/aufs/dirren.h b/fs/aufs/dirren.h +new file mode 100644 +index 00000000..55efe85b +--- /dev/null ++++ b/fs/aufs/dirren.h +@@ -0,0 +1,145 @@ ++/* ++ * Copyright (C) 2017-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * renamed dir info ++ */ ++ ++#ifndef __AUFS_DIRREN_H__ ++#define __AUFS_DIRREN_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include ++#include "hbl.h" ++ ++#define AuDirren_NHASH 100 ++ ++#ifdef CONFIG_AUFS_DIRREN ++/* copied from linux/fs/xfs/uuid.h */ ++typedef struct { ++ unsigned char __u_bits[16]; ++} uuid_t; ++ ++#define __UUID_TMPLT "01234567-0123-4567-0123-456701234567" ++ ++enum au_brid_type { ++ AuBrid_Unset, ++ AuBrid_UUID, ++ AuBrid_FSID, ++ AuBrid_DEV ++}; ++ ++struct au_dr_brid { ++ enum au_brid_type type; ++ union { ++ uuid_t uuid; /* unimplemented yet */ ++ fsid_t fsid; ++ dev_t dev; ++ }; ++}; ++ ++/* 20 is the max digits length of ulong 64 */ ++/* brid-type "_" uuid "_" inum */ ++#define AUFS_DIRREN_FNAME_SZ (1 + 1 + sizeof(__UUID_TMPLT) + 20) ++#define AUFS_DIRREN_ENV_VAL_SZ (AUFS_DIRREN_FNAME_SZ + 1 + 20) ++ ++struct au_dr_hino { ++ struct hlist_bl_node dr_hnode; ++ ino_t dr_h_ino; ++}; ++ ++struct au_dr_br { ++ struct hlist_bl_head dr_h_ino[AuDirren_NHASH]; ++ struct au_dr_brid dr_brid; ++}; ++ ++struct au_dr_lookup { ++ /* dr_name is pointed by struct au_do_lookup_args.name */ ++ struct qstr dr_name; /* subset of dr_info */ ++ aufs_bindex_t ninfo; ++ struct au_drinfo **drinfo; ++}; ++#else ++struct au_dr_hino; ++/* empty */ ++struct au_dr_br { }; ++struct au_dr_lookup { }; ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_branch; ++struct au_do_lookup_args; ++struct au_hinode; ++#ifdef CONFIG_AUFS_DIRREN ++int au_dr_hino_test_add(struct au_dr_br *dr, ino_t h_ino, ++ struct au_dr_hino *add_ent); ++void au_dr_hino_free(struct au_dr_br *dr); ++int au_dr_br_init(struct super_block *sb, struct au_branch *br, ++ const struct path *path); ++int au_dr_br_fin(struct super_block *sb, struct au_branch *br); ++int au_dr_rename(struct dentry *src, aufs_bindex_t bindex, ++ struct qstr *dst_name, void *_rev); ++void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *rev); ++void au_dr_rename_rev(struct dentry *src, aufs_bindex_t bindex, void *rev); ++int au_dr_lkup(struct au_do_lookup_args *lkup, struct dentry *dentry, ++ aufs_bindex_t bindex); ++int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt); ++int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex, ++ ino_t h_ino); ++void au_dr_lkup_fin(struct au_do_lookup_args *lkup); ++int au_dr_opt_set(struct super_block *sb); ++int au_dr_opt_flush(struct super_block *sb); ++int au_dr_opt_clr(struct super_block *sb, int no_flush); ++#else ++AuStubInt0(au_dr_hino_test_add, struct au_dr_br *dr, ino_t h_ino, ++ struct au_dr_hino *add_ent); ++AuStubVoid(au_dr_hino_free, struct au_dr_br *dr); ++AuStubInt0(au_dr_br_init, struct super_block *sb, struct au_branch *br, ++ const struct path *path); ++AuStubInt0(au_dr_br_fin, struct super_block *sb, struct au_branch *br); ++AuStubInt0(au_dr_rename, struct dentry *src, aufs_bindex_t bindex, ++ struct qstr *dst_name, void *_rev); ++AuStubVoid(au_dr_rename_fin, struct dentry *src, aufs_bindex_t btgt, void *rev); ++AuStubVoid(au_dr_rename_rev, struct dentry *src, aufs_bindex_t bindex, ++ void *rev); ++AuStubInt0(au_dr_lkup, struct au_do_lookup_args *lkup, struct dentry *dentry, ++ aufs_bindex_t bindex); ++AuStubInt0(au_dr_lkup_name, struct au_do_lookup_args *lkup, aufs_bindex_t btgt); ++AuStubInt0(au_dr_lkup_h_ino, struct au_do_lookup_args *lkup, ++ aufs_bindex_t bindex, ino_t h_ino); ++AuStubVoid(au_dr_lkup_fin, struct au_do_lookup_args *lkup); ++AuStubInt0(au_dr_opt_set, struct super_block *sb); ++AuStubInt0(au_dr_opt_flush, struct super_block *sb); ++AuStubInt0(au_dr_opt_clr, struct super_block *sb, int no_flush); ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_DIRREN ++static inline int au_dr_ihash(ino_t h_ino) ++{ ++ return h_ino % AuDirren_NHASH; ++} ++#else ++AuStubInt0(au_dr_ihash, ino_t h_ino); ++#endif ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DIRREN_H__ */ +diff --git a/fs/aufs/dynop.c b/fs/aufs/dynop.c +new file mode 100644 +index 00000000..d38dd77a +--- /dev/null ++++ b/fs/aufs/dynop.c +@@ -0,0 +1,369 @@ ++/* ++ * Copyright (C) 2010-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * dynamically customizable operations for regular files ++ */ ++ ++#include "aufs.h" ++ ++#define DyPrSym(key) AuDbgSym(key->dk_op.dy_hop) ++ ++/* ++ * How large will these lists be? ++ * Usually just a few elements, 20-30 at most for each, I guess. ++ */ ++static struct hlist_bl_head dynop[AuDyLast]; ++ ++static struct au_dykey *dy_gfind_get(struct hlist_bl_head *hbl, ++ const void *h_op) ++{ ++ struct au_dykey *key, *tmp; ++ struct hlist_bl_node *pos; ++ ++ key = NULL; ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode) ++ if (tmp->dk_op.dy_hop == h_op) { ++ key = tmp; ++ kref_get(&key->dk_kref); ++ break; ++ } ++ hlist_bl_unlock(hbl); ++ ++ return key; ++} ++ ++static struct au_dykey *dy_bradd(struct au_branch *br, struct au_dykey *key) ++{ ++ struct au_dykey **k, *found; ++ const void *h_op = key->dk_op.dy_hop; ++ int i; ++ ++ found = NULL; ++ k = br->br_dykey; ++ for (i = 0; i < AuBrDynOp; i++) ++ if (k[i]) { ++ if (k[i]->dk_op.dy_hop == h_op) { ++ found = k[i]; ++ break; ++ } ++ } else ++ break; ++ if (!found) { ++ spin_lock(&br->br_dykey_lock); ++ for (; i < AuBrDynOp; i++) ++ if (k[i]) { ++ if (k[i]->dk_op.dy_hop == h_op) { ++ found = k[i]; ++ break; ++ } ++ } else { ++ k[i] = key; ++ break; ++ } ++ spin_unlock(&br->br_dykey_lock); ++ BUG_ON(i == AuBrDynOp); /* expand the array */ ++ } ++ ++ return found; ++} ++ ++/* kref_get() if @key is already added */ ++static struct au_dykey *dy_gadd(struct hlist_bl_head *hbl, struct au_dykey *key) ++{ ++ struct au_dykey *tmp, *found; ++ struct hlist_bl_node *pos; ++ const void *h_op = key->dk_op.dy_hop; ++ ++ found = NULL; ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode) ++ if (tmp->dk_op.dy_hop == h_op) { ++ kref_get(&tmp->dk_kref); ++ found = tmp; ++ break; ++ } ++ if (!found) ++ hlist_bl_add_head(&key->dk_hnode, hbl); ++ hlist_bl_unlock(hbl); ++ ++ if (!found) ++ DyPrSym(key); ++ return found; ++} ++ ++static void dy_free_rcu(struct rcu_head *rcu) ++{ ++ struct au_dykey *key; ++ ++ key = container_of(rcu, struct au_dykey, dk_rcu); ++ DyPrSym(key); ++ kfree(key); ++} ++ ++static void dy_free(struct kref *kref) ++{ ++ struct au_dykey *key; ++ struct hlist_bl_head *hbl; ++ ++ key = container_of(kref, struct au_dykey, dk_kref); ++ hbl = dynop + key->dk_op.dy_type; ++ au_hbl_del(&key->dk_hnode, hbl); ++ call_rcu(&key->dk_rcu, dy_free_rcu); ++} ++ ++void au_dy_put(struct au_dykey *key) ++{ ++ kref_put(&key->dk_kref, dy_free); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#define DyDbgSize(cnt, op) AuDebugOn(cnt != sizeof(op)/sizeof(void *)) ++ ++#ifdef CONFIG_AUFS_DEBUG ++#define DyDbgDeclare(cnt) unsigned int cnt = 0 ++#define DyDbgInc(cnt) do { cnt++; } while (0) ++#else ++#define DyDbgDeclare(cnt) do {} while (0) ++#define DyDbgInc(cnt) do {} while (0) ++#endif ++ ++#define DySet(func, dst, src, h_op, h_sb) do { \ ++ DyDbgInc(cnt); \ ++ if (h_op->func) { \ ++ if (src.func) \ ++ dst.func = src.func; \ ++ else \ ++ AuDbg("%s %s\n", au_sbtype(h_sb), #func); \ ++ } \ ++} while (0) ++ ++#define DySetForce(func, dst, src) do { \ ++ AuDebugOn(!src.func); \ ++ DyDbgInc(cnt); \ ++ dst.func = src.func; \ ++} while (0) ++ ++#define DySetAop(func) \ ++ DySet(func, dyaop->da_op, aufs_aop, h_aop, h_sb) ++#define DySetAopForce(func) \ ++ DySetForce(func, dyaop->da_op, aufs_aop) ++ ++static void dy_aop(struct au_dykey *key, const void *h_op, ++ struct super_block *h_sb __maybe_unused) ++{ ++ struct au_dyaop *dyaop = (void *)key; ++ const struct address_space_operations *h_aop = h_op; ++ DyDbgDeclare(cnt); ++ ++ AuDbg("%s\n", au_sbtype(h_sb)); ++ ++ DySetAop(writepage); ++ DySetAopForce(readpage); /* force */ ++ DySetAop(writepages); ++ DySetAop(set_page_dirty); ++ DySetAop(readpages); ++ DySetAop(write_begin); ++ DySetAop(write_end); ++ DySetAop(bmap); ++ DySetAop(invalidatepage); ++ DySetAop(releasepage); ++ DySetAop(freepage); ++ /* this one will be changed according to an aufs mount option */ ++ DySetAop(direct_IO); ++ DySetAop(migratepage); ++ DySetAop(isolate_page); ++ DySetAop(putback_page); ++ DySetAop(launder_page); ++ DySetAop(is_partially_uptodate); ++ DySetAop(is_dirty_writeback); ++ DySetAop(error_remove_page); ++ DySetAop(swap_activate); ++ DySetAop(swap_deactivate); ++ ++ DyDbgSize(cnt, *h_aop); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void dy_bug(struct kref *kref) ++{ ++ BUG(); ++} ++ ++static struct au_dykey *dy_get(struct au_dynop *op, struct au_branch *br) ++{ ++ struct au_dykey *key, *old; ++ struct hlist_bl_head *hbl; ++ struct op { ++ unsigned int sz; ++ void (*set)(struct au_dykey *key, const void *h_op, ++ struct super_block *h_sb __maybe_unused); ++ }; ++ static const struct op a[] = { ++ [AuDy_AOP] = { ++ .sz = sizeof(struct au_dyaop), ++ .set = dy_aop ++ } ++ }; ++ const struct op *p; ++ ++ hbl = dynop + op->dy_type; ++ key = dy_gfind_get(hbl, op->dy_hop); ++ if (key) ++ goto out_add; /* success */ ++ ++ p = a + op->dy_type; ++ key = kzalloc(p->sz, GFP_NOFS); ++ if (unlikely(!key)) { ++ key = ERR_PTR(-ENOMEM); ++ goto out; ++ } ++ ++ key->dk_op.dy_hop = op->dy_hop; ++ kref_init(&key->dk_kref); ++ p->set(key, op->dy_hop, au_br_sb(br)); ++ old = dy_gadd(hbl, key); ++ if (old) { ++ kfree(key); ++ key = old; ++ } ++ ++out_add: ++ old = dy_bradd(br, key); ++ if (old) ++ /* its ref-count should never be zero here */ ++ kref_put(&key->dk_kref, dy_bug); ++out: ++ return key; ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* ++ * Aufs prohibits O_DIRECT by defaut even if the branch supports it. ++ * This behaviour is necessary to return an error from open(O_DIRECT) instead ++ * of the succeeding I/O. The dio mount option enables O_DIRECT and makes ++ * open(O_DIRECT) always succeed, but the succeeding I/O may return an error. ++ * See the aufs manual in detail. ++ */ ++static void dy_adx(struct au_dyaop *dyaop, int do_dx) ++{ ++ if (!do_dx) ++ dyaop->da_op.direct_IO = NULL; ++ else ++ dyaop->da_op.direct_IO = aufs_aop.direct_IO; ++} ++ ++static struct au_dyaop *dy_aget(struct au_branch *br, ++ const struct address_space_operations *h_aop, ++ int do_dx) ++{ ++ struct au_dyaop *dyaop; ++ struct au_dynop op; ++ ++ op.dy_type = AuDy_AOP; ++ op.dy_haop = h_aop; ++ dyaop = (void *)dy_get(&op, br); ++ if (IS_ERR(dyaop)) ++ goto out; ++ dy_adx(dyaop, do_dx); ++ ++out: ++ return dyaop; ++} ++ ++int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex, ++ struct inode *h_inode) ++{ ++ int err, do_dx; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct au_dyaop *dyaop; ++ ++ AuDebugOn(!S_ISREG(h_inode->i_mode)); ++ IiMustWriteLock(inode); ++ ++ sb = inode->i_sb; ++ br = au_sbr(sb, bindex); ++ do_dx = !!au_opt_test(au_mntflags(sb), DIO); ++ dyaop = dy_aget(br, h_inode->i_mapping->a_ops, do_dx); ++ err = PTR_ERR(dyaop); ++ if (IS_ERR(dyaop)) ++ /* unnecessary to call dy_fput() */ ++ goto out; ++ ++ err = 0; ++ inode->i_mapping->a_ops = &dyaop->da_op; ++ ++out: ++ return err; ++} ++ ++/* ++ * Is it safe to replace a_ops during the inode/file is in operation? ++ * Yes, I hope so. ++ */ ++int au_dy_irefresh(struct inode *inode) ++{ ++ int err; ++ aufs_bindex_t btop; ++ struct inode *h_inode; ++ ++ err = 0; ++ if (S_ISREG(inode->i_mode)) { ++ btop = au_ibtop(inode); ++ h_inode = au_h_iptr(inode, btop); ++ err = au_dy_iaop(inode, btop, h_inode); ++ } ++ return err; ++} ++ ++void au_dy_arefresh(int do_dx) ++{ ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos; ++ struct au_dykey *key; ++ ++ hbl = dynop + AuDy_AOP; ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(key, pos, hbl, dk_hnode) ++ dy_adx((void *)key, do_dx); ++ hlist_bl_unlock(hbl); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void __init au_dy_init(void) ++{ ++ int i; ++ ++ /* make sure that 'struct au_dykey *' can be any type */ ++ BUILD_BUG_ON(offsetof(struct au_dyaop, da_key)); ++ ++ for (i = 0; i < AuDyLast; i++) ++ INIT_HLIST_BL_HEAD(dynop + i); ++} ++ ++void au_dy_fin(void) ++{ ++ int i; ++ ++ for (i = 0; i < AuDyLast; i++) ++ WARN_ON(!hlist_bl_empty(dynop + i)); ++} +diff --git a/fs/aufs/dynop.h b/fs/aufs/dynop.h +new file mode 100644 +index 00000000..81a77050 +--- /dev/null ++++ b/fs/aufs/dynop.h +@@ -0,0 +1,74 @@ ++/* ++ * Copyright (C) 2010-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * dynamically customizable operations (for regular files only) ++ */ ++ ++#ifndef __AUFS_DYNOP_H__ ++#define __AUFS_DYNOP_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include ++ ++enum {AuDy_AOP, AuDyLast}; ++ ++struct au_dynop { ++ int dy_type; ++ union { ++ const void *dy_hop; ++ const struct address_space_operations *dy_haop; ++ }; ++}; ++ ++struct au_dykey { ++ union { ++ struct hlist_bl_node dk_hnode; ++ struct rcu_head dk_rcu; ++ }; ++ struct au_dynop dk_op; ++ ++ /* ++ * during I am in the branch local array, kref is gotten. when the ++ * branch is removed, kref is put. ++ */ ++ struct kref dk_kref; ++}; ++ ++/* stop unioning since their sizes are very different from each other */ ++struct au_dyaop { ++ struct au_dykey da_key; ++ struct address_space_operations da_op; /* not const */ ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* dynop.c */ ++struct au_branch; ++void au_dy_put(struct au_dykey *key); ++int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex, ++ struct inode *h_inode); ++int au_dy_irefresh(struct inode *inode); ++void au_dy_arefresh(int do_dio); ++ ++void __init au_dy_init(void); ++void au_dy_fin(void); ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DYNOP_H__ */ +diff --git a/fs/aufs/export.c b/fs/aufs/export.c +new file mode 100644 +index 00000000..4cf60fce +--- /dev/null ++++ b/fs/aufs/export.c +@@ -0,0 +1,837 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * export via nfs ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include "aufs.h" ++ ++union conv { ++#ifdef CONFIG_AUFS_INO_T_64 ++ __u32 a[2]; ++#else ++ __u32 a[1]; ++#endif ++ ino_t ino; ++}; ++ ++static ino_t decode_ino(__u32 *a) ++{ ++ union conv u; ++ ++ BUILD_BUG_ON(sizeof(u.ino) != sizeof(u.a)); ++ u.a[0] = a[0]; ++#ifdef CONFIG_AUFS_INO_T_64 ++ u.a[1] = a[1]; ++#endif ++ return u.ino; ++} ++ ++static void encode_ino(__u32 *a, ino_t ino) ++{ ++ union conv u; ++ ++ u.ino = ino; ++ a[0] = u.a[0]; ++#ifdef CONFIG_AUFS_INO_T_64 ++ a[1] = u.a[1]; ++#endif ++} ++ ++/* NFS file handle */ ++enum { ++ Fh_br_id, ++ Fh_sigen, ++#ifdef CONFIG_AUFS_INO_T_64 ++ /* support 64bit inode number */ ++ Fh_ino1, ++ Fh_ino2, ++ Fh_dir_ino1, ++ Fh_dir_ino2, ++#else ++ Fh_ino1, ++ Fh_dir_ino1, ++#endif ++ Fh_igen, ++ Fh_h_type, ++ Fh_tail, ++ ++ Fh_ino = Fh_ino1, ++ Fh_dir_ino = Fh_dir_ino1 ++}; ++ ++static int au_test_anon(struct dentry *dentry) ++{ ++ /* note: read d_flags without d_lock */ ++ return !!(dentry->d_flags & DCACHE_DISCONNECTED); ++} ++ ++int au_test_nfsd(void) ++{ ++ int ret; ++ struct task_struct *tsk = current; ++ char comm[sizeof(tsk->comm)]; ++ ++ ret = 0; ++ if (tsk->flags & PF_KTHREAD) { ++ get_task_comm(comm, tsk); ++ ret = !strcmp(comm, "nfsd"); ++ } ++ ++ return ret; ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* inode generation external table */ ++ ++void au_xigen_inc(struct inode *inode) ++{ ++ loff_t pos; ++ ssize_t sz; ++ __u32 igen; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ ++ sb = inode->i_sb; ++ AuDebugOn(!au_opt_test(au_mntflags(sb), XINO)); ++ ++ sbinfo = au_sbi(sb); ++ pos = inode->i_ino; ++ pos *= sizeof(igen); ++ igen = inode->i_generation + 1; ++ sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xigen, &igen, ++ sizeof(igen), &pos); ++ if (sz == sizeof(igen)) ++ return; /* success */ ++ ++ if (unlikely(sz >= 0)) ++ AuIOErr("xigen error (%zd)\n", sz); ++} ++ ++int au_xigen_new(struct inode *inode) ++{ ++ int err; ++ loff_t pos; ++ ssize_t sz; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ struct file *file; ++ ++ err = 0; ++ /* todo: dirty, at mount time */ ++ if (inode->i_ino == AUFS_ROOT_INO) ++ goto out; ++ sb = inode->i_sb; ++ SiMustAnyLock(sb); ++ if (unlikely(!au_opt_test(au_mntflags(sb), XINO))) ++ goto out; ++ ++ err = -EFBIG; ++ pos = inode->i_ino; ++ if (unlikely(au_loff_max / sizeof(inode->i_generation) - 1 < pos)) { ++ AuIOErr1("too large i%lld\n", pos); ++ goto out; ++ } ++ pos *= sizeof(inode->i_generation); ++ ++ err = 0; ++ sbinfo = au_sbi(sb); ++ file = sbinfo->si_xigen; ++ BUG_ON(!file); ++ ++ if (vfsub_f_size_read(file) ++ < pos + sizeof(inode->i_generation)) { ++ inode->i_generation = atomic_inc_return(&sbinfo->si_xigen_next); ++ sz = xino_fwrite(sbinfo->si_xwrite, file, &inode->i_generation, ++ sizeof(inode->i_generation), &pos); ++ } else ++ sz = xino_fread(sbinfo->si_xread, file, &inode->i_generation, ++ sizeof(inode->i_generation), &pos); ++ if (sz == sizeof(inode->i_generation)) ++ goto out; /* success */ ++ ++ err = sz; ++ if (unlikely(sz >= 0)) { ++ err = -EIO; ++ AuIOErr("xigen error (%zd)\n", sz); ++ } ++ ++out: ++ return err; ++} ++ ++int au_xigen_set(struct super_block *sb, struct path *path) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ struct file *file; ++ ++ SiMustWriteLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ file = au_xino_create2(sb, path, sbinfo->si_xigen); ++ err = PTR_ERR(file); ++ if (IS_ERR(file)) ++ goto out; ++ err = 0; ++ if (sbinfo->si_xigen) ++ fput(sbinfo->si_xigen); ++ sbinfo->si_xigen = file; ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++void au_xigen_clr(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ ++ SiMustWriteLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ if (sbinfo->si_xigen) { ++ fput(sbinfo->si_xigen); ++ sbinfo->si_xigen = NULL; ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct dentry *decode_by_ino(struct super_block *sb, ino_t ino, ++ ino_t dir_ino) ++{ ++ struct dentry *dentry, *d; ++ struct inode *inode; ++ unsigned int sigen; ++ ++ dentry = NULL; ++ inode = ilookup(sb, ino); ++ if (!inode) ++ goto out; ++ ++ dentry = ERR_PTR(-ESTALE); ++ sigen = au_sigen(sb); ++ if (unlikely(au_is_bad_inode(inode) ++ || IS_DEADDIR(inode) ++ || sigen != au_iigen(inode, NULL))) ++ goto out_iput; ++ ++ dentry = NULL; ++ if (!dir_ino || S_ISDIR(inode->i_mode)) ++ dentry = d_find_alias(inode); ++ else { ++ spin_lock(&inode->i_lock); ++ hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) { ++ spin_lock(&d->d_lock); ++ if (!au_test_anon(d) ++ && d_inode(d->d_parent)->i_ino == dir_ino) { ++ dentry = dget_dlock(d); ++ spin_unlock(&d->d_lock); ++ break; ++ } ++ spin_unlock(&d->d_lock); ++ } ++ spin_unlock(&inode->i_lock); ++ } ++ if (unlikely(dentry && au_digen_test(dentry, sigen))) { ++ /* need to refresh */ ++ dput(dentry); ++ dentry = NULL; ++ } ++ ++out_iput: ++ iput(inode); ++out: ++ AuTraceErrPtr(dentry); ++ return dentry; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* todo: dirty? */ ++/* if exportfs_decode_fh() passed vfsmount*, we could be happy */ ++ ++struct au_compare_mnt_args { ++ /* input */ ++ struct super_block *sb; ++ ++ /* output */ ++ struct vfsmount *mnt; ++}; ++ ++static int au_compare_mnt(struct vfsmount *mnt, void *arg) ++{ ++ struct au_compare_mnt_args *a = arg; ++ ++ if (mnt->mnt_sb != a->sb) ++ return 0; ++ a->mnt = mntget(mnt); ++ return 1; ++} ++ ++static struct vfsmount *au_mnt_get(struct super_block *sb) ++{ ++ int err; ++ struct path root; ++ struct au_compare_mnt_args args = { ++ .sb = sb ++ }; ++ ++ get_fs_root(current->fs, &root); ++ rcu_read_lock(); ++ err = iterate_mounts(au_compare_mnt, &args, root.mnt); ++ rcu_read_unlock(); ++ path_put(&root); ++ AuDebugOn(!err); ++ AuDebugOn(!args.mnt); ++ return args.mnt; ++} ++ ++struct au_nfsd_si_lock { ++ unsigned int sigen; ++ aufs_bindex_t bindex, br_id; ++ unsigned char force_lock; ++}; ++ ++static int si_nfsd_read_lock(struct super_block *sb, ++ struct au_nfsd_si_lock *nsi_lock) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ ++ si_read_lock(sb, AuLock_FLUSH); ++ ++ /* branch id may be wrapped around */ ++ err = 0; ++ bindex = au_br_index(sb, nsi_lock->br_id); ++ if (bindex >= 0 && nsi_lock->sigen + AUFS_BRANCH_MAX > au_sigen(sb)) ++ goto out; /* success */ ++ ++ err = -ESTALE; ++ bindex = -1; ++ if (!nsi_lock->force_lock) ++ si_read_unlock(sb); ++ ++out: ++ nsi_lock->bindex = bindex; ++ return err; ++} ++ ++struct find_name_by_ino { ++ struct dir_context ctx; ++ int called, found; ++ ino_t ino; ++ char *name; ++ int namelen; ++}; ++ ++static int ++find_name_by_ino(struct dir_context *ctx, const char *name, int namelen, ++ loff_t offset, u64 ino, unsigned int d_type) ++{ ++ struct find_name_by_ino *a = container_of(ctx, struct find_name_by_ino, ++ ctx); ++ ++ a->called++; ++ if (a->ino != ino) ++ return 0; ++ ++ memcpy(a->name, name, namelen); ++ a->namelen = namelen; ++ a->found = 1; ++ return 1; ++} ++ ++static struct dentry *au_lkup_by_ino(struct path *path, ino_t ino, ++ struct au_nfsd_si_lock *nsi_lock) ++{ ++ struct dentry *dentry, *parent; ++ struct file *file; ++ struct inode *dir; ++ struct find_name_by_ino arg = { ++ .ctx = { ++ .actor = find_name_by_ino ++ } ++ }; ++ int err; ++ ++ parent = path->dentry; ++ if (nsi_lock) ++ si_read_unlock(parent->d_sb); ++ file = vfsub_dentry_open(path, au_dir_roflags); ++ dentry = (void *)file; ++ if (IS_ERR(file)) ++ goto out; ++ ++ dentry = ERR_PTR(-ENOMEM); ++ arg.name = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!arg.name)) ++ goto out_file; ++ arg.ino = ino; ++ arg.found = 0; ++ do { ++ arg.called = 0; ++ /* smp_mb(); */ ++ err = vfsub_iterate_dir(file, &arg.ctx); ++ } while (!err && !arg.found && arg.called); ++ dentry = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out_name; ++ /* instead of ENOENT */ ++ dentry = ERR_PTR(-ESTALE); ++ if (!arg.found) ++ goto out_name; ++ ++ /* do not call vfsub_lkup_one() */ ++ dir = d_inode(parent); ++ dentry = vfsub_lookup_one_len_unlocked(arg.name, parent, arg.namelen); ++ AuTraceErrPtr(dentry); ++ if (IS_ERR(dentry)) ++ goto out_name; ++ AuDebugOn(au_test_anon(dentry)); ++ if (unlikely(d_really_is_negative(dentry))) { ++ dput(dentry); ++ dentry = ERR_PTR(-ENOENT); ++ } ++ ++out_name: ++ free_page((unsigned long)arg.name); ++out_file: ++ fput(file); ++out: ++ if (unlikely(nsi_lock ++ && si_nfsd_read_lock(parent->d_sb, nsi_lock) < 0)) ++ if (!IS_ERR(dentry)) { ++ dput(dentry); ++ dentry = ERR_PTR(-ESTALE); ++ } ++ AuTraceErrPtr(dentry); ++ return dentry; ++} ++ ++static struct dentry *decode_by_dir_ino(struct super_block *sb, ino_t ino, ++ ino_t dir_ino, ++ struct au_nfsd_si_lock *nsi_lock) ++{ ++ struct dentry *dentry; ++ struct path path; ++ ++ if (dir_ino != AUFS_ROOT_INO) { ++ path.dentry = decode_by_ino(sb, dir_ino, 0); ++ dentry = path.dentry; ++ if (!path.dentry || IS_ERR(path.dentry)) ++ goto out; ++ AuDebugOn(au_test_anon(path.dentry)); ++ } else ++ path.dentry = dget(sb->s_root); ++ ++ path.mnt = au_mnt_get(sb); ++ dentry = au_lkup_by_ino(&path, ino, nsi_lock); ++ path_put(&path); ++ ++out: ++ AuTraceErrPtr(dentry); ++ return dentry; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int h_acceptable(void *expv, struct dentry *dentry) ++{ ++ return 1; ++} ++ ++static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath, ++ char *buf, int len, struct super_block *sb) ++{ ++ char *p; ++ int n; ++ struct path path; ++ ++ p = d_path(h_rootpath, buf, len); ++ if (IS_ERR(p)) ++ goto out; ++ n = strlen(p); ++ ++ path.mnt = h_rootpath->mnt; ++ path.dentry = h_parent; ++ p = d_path(&path, buf, len); ++ if (IS_ERR(p)) ++ goto out; ++ if (n != 1) ++ p += n; ++ ++ path.mnt = au_mnt_get(sb); ++ path.dentry = sb->s_root; ++ p = d_path(&path, buf, len - strlen(p)); ++ mntput(path.mnt); ++ if (IS_ERR(p)) ++ goto out; ++ if (n != 1) ++ p[strlen(p)] = '/'; ++ ++out: ++ AuTraceErrPtr(p); ++ return p; ++} ++ ++static ++struct dentry *decode_by_path(struct super_block *sb, ino_t ino, __u32 *fh, ++ int fh_len, struct au_nfsd_si_lock *nsi_lock) ++{ ++ struct dentry *dentry, *h_parent, *root; ++ struct super_block *h_sb; ++ char *pathname, *p; ++ struct vfsmount *h_mnt; ++ struct au_branch *br; ++ int err; ++ struct path path; ++ ++ br = au_sbr(sb, nsi_lock->bindex); ++ h_mnt = au_br_mnt(br); ++ h_sb = h_mnt->mnt_sb; ++ /* todo: call lower fh_to_dentry()? fh_to_parent()? */ ++ lockdep_off(); ++ h_parent = exportfs_decode_fh(h_mnt, (void *)(fh + Fh_tail), ++ fh_len - Fh_tail, fh[Fh_h_type], ++ h_acceptable, /*context*/NULL); ++ lockdep_on(); ++ dentry = h_parent; ++ if (unlikely(!h_parent || IS_ERR(h_parent))) { ++ AuWarn1("%s decode_fh failed, %ld\n", ++ au_sbtype(h_sb), PTR_ERR(h_parent)); ++ goto out; ++ } ++ dentry = NULL; ++ if (unlikely(au_test_anon(h_parent))) { ++ AuWarn1("%s decode_fh returned a disconnected dentry\n", ++ au_sbtype(h_sb)); ++ goto out_h_parent; ++ } ++ ++ dentry = ERR_PTR(-ENOMEM); ++ pathname = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!pathname)) ++ goto out_h_parent; ++ ++ root = sb->s_root; ++ path.mnt = h_mnt; ++ di_read_lock_parent(root, !AuLock_IR); ++ path.dentry = au_h_dptr(root, nsi_lock->bindex); ++ di_read_unlock(root, !AuLock_IR); ++ p = au_build_path(h_parent, &path, pathname, PAGE_SIZE, sb); ++ dentry = (void *)p; ++ if (IS_ERR(p)) ++ goto out_pathname; ++ ++ si_read_unlock(sb); ++ err = vfsub_kern_path(p, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); ++ dentry = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out_relock; ++ ++ dentry = ERR_PTR(-ENOENT); ++ AuDebugOn(au_test_anon(path.dentry)); ++ if (unlikely(d_really_is_negative(path.dentry))) ++ goto out_path; ++ ++ if (ino != d_inode(path.dentry)->i_ino) ++ dentry = au_lkup_by_ino(&path, ino, /*nsi_lock*/NULL); ++ else ++ dentry = dget(path.dentry); ++ ++out_path: ++ path_put(&path); ++out_relock: ++ if (unlikely(si_nfsd_read_lock(sb, nsi_lock) < 0)) ++ if (!IS_ERR(dentry)) { ++ dput(dentry); ++ dentry = ERR_PTR(-ESTALE); ++ } ++out_pathname: ++ free_page((unsigned long)pathname); ++out_h_parent: ++ dput(h_parent); ++out: ++ AuTraceErrPtr(dentry); ++ return dentry; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct dentry * ++aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, ++ int fh_type) ++{ ++ struct dentry *dentry; ++ __u32 *fh = fid->raw; ++ struct au_branch *br; ++ ino_t ino, dir_ino; ++ struct au_nfsd_si_lock nsi_lock = { ++ .force_lock = 0 ++ }; ++ ++ dentry = ERR_PTR(-ESTALE); ++ /* it should never happen, but the file handle is unreliable */ ++ if (unlikely(fh_len < Fh_tail)) ++ goto out; ++ nsi_lock.sigen = fh[Fh_sigen]; ++ nsi_lock.br_id = fh[Fh_br_id]; ++ ++ /* branch id may be wrapped around */ ++ br = NULL; ++ if (unlikely(si_nfsd_read_lock(sb, &nsi_lock))) ++ goto out; ++ nsi_lock.force_lock = 1; ++ ++ /* is this inode still cached? */ ++ ino = decode_ino(fh + Fh_ino); ++ /* it should never happen */ ++ if (unlikely(ino == AUFS_ROOT_INO)) ++ goto out_unlock; ++ ++ dir_ino = decode_ino(fh + Fh_dir_ino); ++ dentry = decode_by_ino(sb, ino, dir_ino); ++ if (IS_ERR(dentry)) ++ goto out_unlock; ++ if (dentry) ++ goto accept; ++ ++ /* is the parent dir cached? */ ++ br = au_sbr(sb, nsi_lock.bindex); ++ au_br_get(br); ++ dentry = decode_by_dir_ino(sb, ino, dir_ino, &nsi_lock); ++ if (IS_ERR(dentry)) ++ goto out_unlock; ++ if (dentry) ++ goto accept; ++ ++ /* lookup path */ ++ dentry = decode_by_path(sb, ino, fh, fh_len, &nsi_lock); ++ if (IS_ERR(dentry)) ++ goto out_unlock; ++ if (unlikely(!dentry)) ++ /* todo?: make it ESTALE */ ++ goto out_unlock; ++ ++accept: ++ if (!au_digen_test(dentry, au_sigen(sb)) ++ && d_inode(dentry)->i_generation == fh[Fh_igen]) ++ goto out_unlock; /* success */ ++ ++ dput(dentry); ++ dentry = ERR_PTR(-ESTALE); ++out_unlock: ++ if (br) ++ au_br_put(br); ++ si_read_unlock(sb); ++out: ++ AuTraceErrPtr(dentry); ++ return dentry; ++} ++ ++#if 0 /* reserved for future use */ ++/* support subtreecheck option */ ++static struct dentry *aufs_fh_to_parent(struct super_block *sb, struct fid *fid, ++ int fh_len, int fh_type) ++{ ++ struct dentry *parent; ++ __u32 *fh = fid->raw; ++ ino_t dir_ino; ++ ++ dir_ino = decode_ino(fh + Fh_dir_ino); ++ parent = decode_by_ino(sb, dir_ino, 0); ++ if (IS_ERR(parent)) ++ goto out; ++ if (!parent) ++ parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]), ++ dir_ino, fh, fh_len); ++ ++out: ++ AuTraceErrPtr(parent); ++ return parent; ++} ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int aufs_encode_fh(struct inode *inode, __u32 *fh, int *max_len, ++ struct inode *dir) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ struct super_block *sb, *h_sb; ++ struct dentry *dentry, *parent, *h_parent; ++ struct inode *h_dir; ++ struct au_branch *br; ++ ++ err = -ENOSPC; ++ if (unlikely(*max_len <= Fh_tail)) { ++ AuWarn1("NFSv2 client (max_len %d)?\n", *max_len); ++ goto out; ++ } ++ ++ err = FILEID_ROOT; ++ if (inode->i_ino == AUFS_ROOT_INO) { ++ AuDebugOn(inode->i_ino != AUFS_ROOT_INO); ++ goto out; ++ } ++ ++ h_parent = NULL; ++ sb = inode->i_sb; ++ err = si_read_lock(sb, AuLock_FLUSH); ++ if (unlikely(err)) ++ goto out; ++ ++#ifdef CONFIG_AUFS_DEBUG ++ if (unlikely(!au_opt_test(au_mntflags(sb), XINO))) ++ AuWarn1("NFS-exporting requires xino\n"); ++#endif ++ err = -EIO; ++ parent = NULL; ++ ii_read_lock_child(inode); ++ bindex = au_ibtop(inode); ++ if (!dir) { ++ dentry = d_find_any_alias(inode); ++ if (unlikely(!dentry)) ++ goto out_unlock; ++ AuDebugOn(au_test_anon(dentry)); ++ parent = dget_parent(dentry); ++ dput(dentry); ++ if (unlikely(!parent)) ++ goto out_unlock; ++ if (d_really_is_positive(parent)) ++ dir = d_inode(parent); ++ } ++ ++ ii_read_lock_parent(dir); ++ h_dir = au_h_iptr(dir, bindex); ++ ii_read_unlock(dir); ++ if (unlikely(!h_dir)) ++ goto out_parent; ++ h_parent = d_find_any_alias(h_dir); ++ if (unlikely(!h_parent)) ++ goto out_hparent; ++ ++ err = -EPERM; ++ br = au_sbr(sb, bindex); ++ h_sb = au_br_sb(br); ++ if (unlikely(!h_sb->s_export_op)) { ++ AuErr1("%s branch is not exportable\n", au_sbtype(h_sb)); ++ goto out_hparent; ++ } ++ ++ fh[Fh_br_id] = br->br_id; ++ fh[Fh_sigen] = au_sigen(sb); ++ encode_ino(fh + Fh_ino, inode->i_ino); ++ encode_ino(fh + Fh_dir_ino, dir->i_ino); ++ fh[Fh_igen] = inode->i_generation; ++ ++ *max_len -= Fh_tail; ++ fh[Fh_h_type] = exportfs_encode_fh(h_parent, (void *)(fh + Fh_tail), ++ max_len, ++ /*connectable or subtreecheck*/0); ++ err = fh[Fh_h_type]; ++ *max_len += Fh_tail; ++ /* todo: macros? */ ++ if (err != FILEID_INVALID) ++ err = 99; ++ else ++ AuWarn1("%s encode_fh failed\n", au_sbtype(h_sb)); ++ ++out_hparent: ++ dput(h_parent); ++out_parent: ++ dput(parent); ++out_unlock: ++ ii_read_unlock(inode); ++ si_read_unlock(sb); ++out: ++ if (unlikely(err < 0)) ++ err = FILEID_INVALID; ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int aufs_commit_metadata(struct inode *inode) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ struct super_block *sb; ++ struct inode *h_inode; ++ int (*f)(struct inode *inode); ++ ++ sb = inode->i_sb; ++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); ++ ii_write_lock_child(inode); ++ bindex = au_ibtop(inode); ++ AuDebugOn(bindex < 0); ++ h_inode = au_h_iptr(inode, bindex); ++ ++ f = h_inode->i_sb->s_export_op->commit_metadata; ++ if (f) ++ err = f(h_inode); ++ else { ++ struct writeback_control wbc = { ++ .sync_mode = WB_SYNC_ALL, ++ .nr_to_write = 0 /* metadata only */ ++ }; ++ ++ err = sync_inode(h_inode, &wbc); ++ } ++ ++ au_cpup_attr_timesizes(inode); ++ ii_write_unlock(inode); ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct export_operations aufs_export_op = { ++ .fh_to_dentry = aufs_fh_to_dentry, ++ /* .fh_to_parent = aufs_fh_to_parent, */ ++ .encode_fh = aufs_encode_fh, ++ .commit_metadata = aufs_commit_metadata ++}; ++ ++void au_export_init(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ __u32 u; ++ ++ BUILD_BUG_ON_MSG(IS_BUILTIN(CONFIG_AUFS_FS) ++ && IS_MODULE(CONFIG_EXPORTFS), ++ AUFS_NAME ": unsupported configuration " ++ "CONFIG_EXPORTFS=m and CONFIG_AUFS_FS=y"); ++ ++ sb->s_export_op = &aufs_export_op; ++ sbinfo = au_sbi(sb); ++ sbinfo->si_xigen = NULL; ++ get_random_bytes(&u, sizeof(u)); ++ BUILD_BUG_ON(sizeof(u) != sizeof(int)); ++ atomic_set(&sbinfo->si_xigen_next, u); ++} +diff --git a/fs/aufs/f_op.c b/fs/aufs/f_op.c +new file mode 100644 +index 00000000..e1ed7dac +--- /dev/null ++++ b/fs/aufs/f_op.c +@@ -0,0 +1,817 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * file and vm operations ++ */ ++ ++#include ++#include ++#include ++#include ++#include "aufs.h" ++ ++int au_do_open_nondir(struct file *file, int flags, struct file *h_file) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ struct dentry *dentry, *h_dentry; ++ struct au_finfo *finfo; ++ struct inode *h_inode; ++ ++ FiMustWriteLock(file); ++ ++ err = 0; ++ dentry = file->f_path.dentry; ++ AuDebugOn(IS_ERR_OR_NULL(dentry)); ++ finfo = au_fi(file); ++ memset(&finfo->fi_htop, 0, sizeof(finfo->fi_htop)); ++ atomic_set(&finfo->fi_mmapped, 0); ++ bindex = au_dbtop(dentry); ++ if (!h_file) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb); ++ if (unlikely(err)) ++ goto out; ++ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); ++ } else { ++ h_dentry = h_file->f_path.dentry; ++ err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb); ++ if (unlikely(err)) ++ goto out; ++ get_file(h_file); ++ } ++ if (IS_ERR(h_file)) ++ err = PTR_ERR(h_file); ++ else { ++ if ((flags & __O_TMPFILE) ++ && !(flags & O_EXCL)) { ++ h_inode = file_inode(h_file); ++ spin_lock(&h_inode->i_lock); ++ h_inode->i_state |= I_LINKABLE; ++ spin_unlock(&h_inode->i_lock); ++ } ++ au_set_fbtop(file, bindex); ++ au_set_h_fptr(file, bindex, h_file); ++ au_update_figen(file); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ } ++ ++out: ++ return err; ++} ++ ++static int aufs_open_nondir(struct inode *inode __maybe_unused, ++ struct file *file) ++{ ++ int err; ++ struct super_block *sb; ++ struct au_do_open_args args = { ++ .open = au_do_open_nondir ++ }; ++ ++ AuDbg("%pD, f_flags 0x%x, f_mode 0x%x\n", ++ file, vfsub_file_flags(file), file->f_mode); ++ ++ sb = file->f_path.dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ err = au_do_open(file, &args); ++ si_read_unlock(sb); ++ return err; ++} ++ ++int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file) ++{ ++ struct au_finfo *finfo; ++ aufs_bindex_t bindex; ++ ++ finfo = au_fi(file); ++ au_hbl_del(&finfo->fi_hlist, ++ &au_sbi(file->f_path.dentry->d_sb)->si_files); ++ bindex = finfo->fi_btop; ++ if (bindex >= 0) ++ au_set_h_fptr(file, bindex, NULL); ++ ++ au_finfo_fin(file); ++ return 0; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_do_flush_nondir(struct file *file, fl_owner_t id) ++{ ++ int err; ++ struct file *h_file; ++ ++ err = 0; ++ h_file = au_hf_top(file); ++ if (h_file) ++ err = vfsub_flush(h_file, id); ++ return err; ++} ++ ++static int aufs_flush_nondir(struct file *file, fl_owner_t id) ++{ ++ return au_do_flush(file, id, au_do_flush_nondir); ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* ++ * read and write functions acquire [fdi]_rwsem once, but release before ++ * mmap_sem. This is because to stop a race condition between mmap(2). ++ * Releasing these aufs-rwsem should be safe, no branch-mamagement (by keeping ++ * si_rwsem), no harmful copy-up should happen. Actually copy-up may happen in ++ * read functions after [fdi]_rwsem are released, but it should be harmless. ++ */ ++ ++/* Callers should call au_read_post() or fput() in the end */ ++struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc) ++{ ++ struct file *h_file; ++ int err; ++ ++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0, lsc); ++ if (!err) { ++ di_read_unlock(file->f_path.dentry, AuLock_IR); ++ h_file = au_hf_top(file); ++ get_file(h_file); ++ if (!keep_fi) ++ fi_read_unlock(file); ++ } else ++ h_file = ERR_PTR(err); ++ ++ return h_file; ++} ++ ++static void au_read_post(struct inode *inode, struct file *h_file) ++{ ++ /* update without lock, I don't think it a problem */ ++ fsstack_copy_attr_atime(inode, file_inode(h_file)); ++ fput(h_file); ++} ++ ++struct au_write_pre { ++ /* input */ ++ unsigned int lsc; ++ ++ /* output */ ++ blkcnt_t blks; ++ aufs_bindex_t btop; ++}; ++ ++/* ++ * return with iinfo is write-locked ++ * callers should call au_write_post() or iinfo_write_unlock() + fput() in the ++ * end ++ */ ++static struct file *au_write_pre(struct file *file, int do_ready, ++ struct au_write_pre *wpre) ++{ ++ struct file *h_file; ++ struct dentry *dentry; ++ int err; ++ unsigned int lsc; ++ struct au_pin pin; ++ ++ lsc = 0; ++ if (wpre) ++ lsc = wpre->lsc; ++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1, lsc); ++ h_file = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out; ++ ++ dentry = file->f_path.dentry; ++ if (do_ready) { ++ err = au_ready_to_write(file, -1, &pin); ++ if (unlikely(err)) { ++ h_file = ERR_PTR(err); ++ di_write_unlock(dentry); ++ goto out_fi; ++ } ++ } ++ ++ di_downgrade_lock(dentry, /*flags*/0); ++ if (wpre) ++ wpre->btop = au_fbtop(file); ++ h_file = au_hf_top(file); ++ get_file(h_file); ++ if (wpre) ++ wpre->blks = file_inode(h_file)->i_blocks; ++ if (do_ready) ++ au_unpin(&pin); ++ di_read_unlock(dentry, /*flags*/0); ++ ++out_fi: ++ fi_write_unlock(file); ++out: ++ return h_file; ++} ++ ++static void au_write_post(struct inode *inode, struct file *h_file, ++ struct au_write_pre *wpre, ssize_t written) ++{ ++ struct inode *h_inode; ++ ++ au_cpup_attr_timesizes(inode); ++ AuDebugOn(au_ibtop(inode) != wpre->btop); ++ h_inode = file_inode(h_file); ++ inode->i_mode = h_inode->i_mode; ++ ii_write_unlock(inode); ++ /* AuDbg("blks %llu, %llu\n", (u64)blks, (u64)h_inode->i_blocks); */ ++ if (written > 0) ++ au_fhsm_wrote(inode->i_sb, wpre->btop, ++ /*force*/h_inode->i_blocks > wpre->blks); ++ fput(h_file); ++} ++ ++static ssize_t aufs_read(struct file *file, char __user *buf, size_t count, ++ loff_t *ppos) ++{ ++ ssize_t err; ++ struct inode *inode; ++ struct file *h_file; ++ struct super_block *sb; ++ ++ inode = file_inode(file); ++ sb = inode->i_sb; ++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); ++ ++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ /* filedata may be obsoleted by concurrent copyup, but no problem */ ++ err = vfsub_read_u(h_file, buf, count, ppos); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ au_read_post(inode, h_file); ++ ++out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ++ * todo: very ugly ++ * it locks both of i_mutex and si_rwsem for read in safe. ++ * if the plink maintenance mode continues forever (that is the problem), ++ * may loop forever. ++ */ ++static void au_mtx_and_read_lock(struct inode *inode) ++{ ++ int err; ++ struct super_block *sb = inode->i_sb; ++ ++ while (1) { ++ inode_lock(inode); ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (!err) ++ break; ++ inode_unlock(inode); ++ si_read_lock(sb, AuLock_NOPLMW); ++ si_read_unlock(sb); ++ } ++} ++ ++static ssize_t aufs_write(struct file *file, const char __user *ubuf, ++ size_t count, loff_t *ppos) ++{ ++ ssize_t err; ++ struct au_write_pre wpre; ++ struct inode *inode; ++ struct file *h_file; ++ char __user *buf = (char __user *)ubuf; ++ ++ inode = file_inode(file); ++ au_mtx_and_read_lock(inode); ++ ++ wpre.lsc = 0; ++ h_file = au_write_pre(file, /*do_ready*/1, &wpre); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ err = vfsub_write_u(h_file, buf, count, ppos); ++ au_write_post(inode, h_file, &wpre, err); ++ ++out: ++ si_read_unlock(inode->i_sb); ++ inode_unlock(inode); ++ return err; ++} ++ ++static ssize_t au_do_iter(struct file *h_file, int rw, struct kiocb *kio, ++ struct iov_iter *iov_iter) ++{ ++ ssize_t err; ++ struct file *file; ++ ssize_t (*iter)(struct kiocb *, struct iov_iter *); ++ ++ err = security_file_permission(h_file, rw); ++ if (unlikely(err)) ++ goto out; ++ ++ err = -ENOSYS; ++ iter = NULL; ++ if (rw == MAY_READ) ++ iter = h_file->f_op->read_iter; ++ else if (rw == MAY_WRITE) ++ iter = h_file->f_op->write_iter; ++ ++ file = kio->ki_filp; ++ kio->ki_filp = h_file; ++ if (iter) { ++ lockdep_off(); ++ err = iter(kio, iov_iter); ++ lockdep_on(); ++ } else ++ /* currently there is no such fs */ ++ WARN_ON_ONCE(1); ++ kio->ki_filp = file; ++ ++out: ++ return err; ++} ++ ++static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter) ++{ ++ ssize_t err; ++ struct file *file, *h_file; ++ struct inode *inode; ++ struct super_block *sb; ++ ++ file = kio->ki_filp; ++ inode = file_inode(file); ++ sb = inode->i_sb; ++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); ++ ++ h_file = au_read_pre(file, /*keep_fi*/1, /*lsc*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ if (au_test_loopback_kthread()) { ++ au_warn_loopback(h_file->f_path.dentry->d_sb); ++ if (file->f_mapping != h_file->f_mapping) { ++ file->f_mapping = h_file->f_mapping; ++ smp_mb(); /* unnecessary? */ ++ } ++ } ++ fi_read_unlock(file); ++ ++ err = au_do_iter(h_file, MAY_READ, kio, iov_iter); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ au_read_post(inode, h_file); ++ ++out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter) ++{ ++ ssize_t err; ++ struct au_write_pre wpre; ++ struct inode *inode; ++ struct file *file, *h_file; ++ ++ file = kio->ki_filp; ++ inode = file_inode(file); ++ au_mtx_and_read_lock(inode); ++ ++ wpre.lsc = 0; ++ h_file = au_write_pre(file, /*do_ready*/1, &wpre); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ err = au_do_iter(h_file, MAY_WRITE, kio, iov_iter); ++ au_write_post(inode, h_file, &wpre, err); ++ ++out: ++ si_read_unlock(inode->i_sb); ++ inode_unlock(inode); ++ return err; ++} ++ ++static ssize_t aufs_splice_read(struct file *file, loff_t *ppos, ++ struct pipe_inode_info *pipe, size_t len, ++ unsigned int flags) ++{ ++ ssize_t err; ++ struct file *h_file; ++ struct inode *inode; ++ struct super_block *sb; ++ ++ inode = file_inode(file); ++ sb = inode->i_sb; ++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); ++ ++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ err = vfsub_splice_to(h_file, ppos, pipe, len, flags); ++ /* todo: necessasry? */ ++ /* file->f_ra = h_file->f_ra; */ ++ au_read_post(inode, h_file); ++ ++out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++static ssize_t ++aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos, ++ size_t len, unsigned int flags) ++{ ++ ssize_t err; ++ struct au_write_pre wpre; ++ struct inode *inode; ++ struct file *h_file; ++ ++ inode = file_inode(file); ++ au_mtx_and_read_lock(inode); ++ ++ wpre.lsc = 0; ++ h_file = au_write_pre(file, /*do_ready*/1, &wpre); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ err = vfsub_splice_from(pipe, h_file, ppos, len, flags); ++ au_write_post(inode, h_file, &wpre, err); ++ ++out: ++ si_read_unlock(inode->i_sb); ++ inode_unlock(inode); ++ return err; ++} ++ ++static long aufs_fallocate(struct file *file, int mode, loff_t offset, ++ loff_t len) ++{ ++ long err; ++ struct au_write_pre wpre; ++ struct inode *inode; ++ struct file *h_file; ++ ++ inode = file_inode(file); ++ au_mtx_and_read_lock(inode); ++ ++ wpre.lsc = 0; ++ h_file = au_write_pre(file, /*do_ready*/1, &wpre); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ lockdep_off(); ++ err = vfs_fallocate(h_file, mode, offset, len); ++ lockdep_on(); ++ au_write_post(inode, h_file, &wpre, /*written*/1); ++ ++out: ++ si_read_unlock(inode->i_sb); ++ inode_unlock(inode); ++ return err; ++} ++ ++static ssize_t aufs_copy_file_range(struct file *src, loff_t src_pos, ++ struct file *dst, loff_t dst_pos, ++ size_t len, unsigned int flags) ++{ ++ ssize_t err; ++ struct au_write_pre wpre; ++ enum { SRC, DST }; ++ struct { ++ struct inode *inode; ++ struct file *h_file; ++ struct super_block *h_sb; ++ } a[2]; ++#define a_src a[SRC] ++#define a_dst a[DST] ++ ++ err = -EINVAL; ++ a_src.inode = file_inode(src); ++ if (unlikely(!S_ISREG(a_src.inode->i_mode))) ++ goto out; ++ a_dst.inode = file_inode(dst); ++ if (unlikely(!S_ISREG(a_dst.inode->i_mode))) ++ goto out; ++ ++ au_mtx_and_read_lock(a_dst.inode); ++ /* ++ * in order to match the order in di_write_lock2_{child,parent}(), ++ * use f_path.dentry for this comparision. ++ */ ++ if (src->f_path.dentry < dst->f_path.dentry) { ++ a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_1); ++ err = PTR_ERR(a_src.h_file); ++ if (IS_ERR(a_src.h_file)) ++ goto out_si; ++ ++ wpre.lsc = AuLsc_FI_2; ++ a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre); ++ err = PTR_ERR(a_dst.h_file); ++ if (IS_ERR(a_dst.h_file)) { ++ au_read_post(a_src.inode, a_src.h_file); ++ goto out_si; ++ } ++ } else { ++ wpre.lsc = AuLsc_FI_1; ++ a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre); ++ err = PTR_ERR(a_dst.h_file); ++ if (IS_ERR(a_dst.h_file)) ++ goto out_si; ++ ++ a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_2); ++ err = PTR_ERR(a_src.h_file); ++ if (IS_ERR(a_src.h_file)) { ++ au_write_post(a_dst.inode, a_dst.h_file, &wpre, ++ /*written*/0); ++ goto out_si; ++ } ++ } ++ ++ err = -EXDEV; ++ a_src.h_sb = file_inode(a_src.h_file)->i_sb; ++ a_dst.h_sb = file_inode(a_dst.h_file)->i_sb; ++ if (unlikely(a_src.h_sb != a_dst.h_sb)) { ++ AuDbgFile(src); ++ AuDbgFile(dst); ++ goto out_file; ++ } ++ ++ err = vfsub_copy_file_range(a_src.h_file, src_pos, a_dst.h_file, ++ dst_pos, len, flags); ++ ++out_file: ++ au_write_post(a_dst.inode, a_dst.h_file, &wpre, err); ++ fi_read_unlock(src); ++ au_read_post(a_src.inode, a_src.h_file); ++out_si: ++ si_read_unlock(a_dst.inode->i_sb); ++ inode_unlock(a_dst.inode); ++out: ++ return err; ++#undef a_src ++#undef a_dst ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * The locking order around current->mmap_sem. ++ * - in most and regular cases ++ * file I/O syscall -- aufs_read() or something ++ * -- si_rwsem for read -- mmap_sem ++ * (Note that [fdi]i_rwsem are released before mmap_sem). ++ * - in mmap case ++ * mmap(2) -- mmap_sem -- aufs_mmap() -- si_rwsem for read -- [fdi]i_rwsem ++ * This AB-BA order is definitly bad, but is not a problem since "si_rwsem for ++ * read" allows muliple processes to acquire it and [fdi]i_rwsem are not held in ++ * file I/O. Aufs needs to stop lockdep in aufs_mmap() though. ++ * It means that when aufs acquires si_rwsem for write, the process should never ++ * acquire mmap_sem. ++ * ++ * Actually aufs_iterate() holds [fdi]i_rwsem before mmap_sem, but this is not a ++ * problem either since any directory is not able to be mmap-ed. ++ * The similar scenario is applied to aufs_readlink() too. ++ */ ++ ++#if 0 /* stop calling security_file_mmap() */ ++/* cf. linux/include/linux/mman.h: calc_vm_prot_bits() */ ++#define AuConv_VM_PROT(f, b) _calc_vm_trans(f, VM_##b, PROT_##b) ++ ++static unsigned long au_arch_prot_conv(unsigned long flags) ++{ ++ /* currently ppc64 only */ ++#ifdef CONFIG_PPC64 ++ /* cf. linux/arch/powerpc/include/asm/mman.h */ ++ AuDebugOn(arch_calc_vm_prot_bits(-1) != VM_SAO); ++ return AuConv_VM_PROT(flags, SAO); ++#else ++ AuDebugOn(arch_calc_vm_prot_bits(-1)); ++ return 0; ++#endif ++} ++ ++static unsigned long au_prot_conv(unsigned long flags) ++{ ++ return AuConv_VM_PROT(flags, READ) ++ | AuConv_VM_PROT(flags, WRITE) ++ | AuConv_VM_PROT(flags, EXEC) ++ | au_arch_prot_conv(flags); ++} ++ ++/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */ ++#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b) ++ ++static unsigned long au_flag_conv(unsigned long flags) ++{ ++ return AuConv_VM_MAP(flags, GROWSDOWN) ++ | AuConv_VM_MAP(flags, DENYWRITE) ++ | AuConv_VM_MAP(flags, LOCKED); ++} ++#endif ++ ++static int aufs_mmap(struct file *file, struct vm_area_struct *vma) ++{ ++ int err; ++ const unsigned char wlock ++ = (file->f_mode & FMODE_WRITE) && (vma->vm_flags & VM_SHARED); ++ struct super_block *sb; ++ struct file *h_file; ++ struct inode *inode; ++ ++ AuDbgVmRegion(file, vma); ++ ++ inode = file_inode(file); ++ sb = inode->i_sb; ++ lockdep_off(); ++ si_read_lock(sb, AuLock_NOPLMW); ++ ++ h_file = au_write_pre(file, wlock, /*wpre*/NULL); ++ lockdep_on(); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ err = 0; ++ au_set_mmapped(file); ++ au_vm_file_reset(vma, h_file); ++ /* ++ * we cannot call security_mmap_file() here since it may acquire ++ * mmap_sem or i_mutex. ++ * ++ * err = security_mmap_file(h_file, au_prot_conv(vma->vm_flags), ++ * au_flag_conv(vma->vm_flags)); ++ */ ++ if (!err) ++ err = h_file->f_op->mmap(h_file, vma); ++ if (!err) { ++ au_vm_prfile_set(vma, file); ++ fsstack_copy_attr_atime(inode, file_inode(h_file)); ++ goto out_fput; /* success */ ++ } ++ au_unset_mmapped(file); ++ au_vm_file_reset(vma, file); ++ ++out_fput: ++ lockdep_off(); ++ ii_write_unlock(inode); ++ lockdep_on(); ++ fput(h_file); ++out: ++ lockdep_off(); ++ si_read_unlock(sb); ++ lockdep_on(); ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end, ++ int datasync) ++{ ++ int err; ++ struct au_write_pre wpre; ++ struct inode *inode; ++ struct file *h_file; ++ ++ err = 0; /* -EBADF; */ /* posix? */ ++ if (unlikely(!(file->f_mode & FMODE_WRITE))) ++ goto out; ++ ++ inode = file_inode(file); ++ au_mtx_and_read_lock(inode); ++ ++ wpre.lsc = 0; ++ h_file = au_write_pre(file, /*do_ready*/1, &wpre); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out_unlock; ++ ++ err = vfsub_fsync(h_file, &h_file->f_path, datasync); ++ au_write_post(inode, h_file, &wpre, /*written*/0); ++ ++out_unlock: ++ si_read_unlock(inode->i_sb); ++ inode_unlock(inode); ++out: ++ return err; ++} ++ ++static int aufs_fasync(int fd, struct file *file, int flag) ++{ ++ int err; ++ struct file *h_file; ++ struct super_block *sb; ++ ++ sb = file->f_path.dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); ++ ++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ if (h_file->f_op->fasync) ++ err = h_file->f_op->fasync(fd, h_file, flag); ++ fput(h_file); /* instead of au_read_post() */ ++ ++out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++static int aufs_setfl(struct file *file, unsigned long arg) ++{ ++ int err; ++ struct file *h_file; ++ struct super_block *sb; ++ ++ sb = file->f_path.dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); ++ ++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ /* stop calling h_file->fasync */ ++ arg |= vfsub_file_flags(file) & FASYNC; ++ err = setfl(/*unused fd*/-1, h_file, arg); ++ fput(h_file); /* instead of au_read_post() */ ++ ++out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* no one supports this operation, currently */ ++#if 0 ++static ssize_t aufs_sendpage(struct file *file, struct page *page, int offset, ++ size_t len, loff_t *pos, int more) ++{ ++} ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++const struct file_operations aufs_file_fop = { ++ .owner = THIS_MODULE, ++ ++ .llseek = default_llseek, ++ ++ .read = aufs_read, ++ .write = aufs_write, ++ .read_iter = aufs_read_iter, ++ .write_iter = aufs_write_iter, ++ ++#ifdef CONFIG_AUFS_POLL ++ .poll = aufs_poll, ++#endif ++ .unlocked_ioctl = aufs_ioctl_nondir, ++#ifdef CONFIG_COMPAT ++ .compat_ioctl = aufs_compat_ioctl_nondir, ++#endif ++ .mmap = aufs_mmap, ++ .open = aufs_open_nondir, ++ .flush = aufs_flush_nondir, ++ .release = aufs_release_nondir, ++ .fsync = aufs_fsync_nondir, ++ .fasync = aufs_fasync, ++ /* .sendpage = aufs_sendpage, */ ++ .setfl = aufs_setfl, ++ .splice_write = aufs_splice_write, ++ .splice_read = aufs_splice_read, ++#if 0 ++ .aio_splice_write = aufs_aio_splice_write, ++ .aio_splice_read = aufs_aio_splice_read, ++#endif ++ .fallocate = aufs_fallocate, ++ .copy_file_range = aufs_copy_file_range ++}; +diff --git a/fs/aufs/fhsm.c b/fs/aufs/fhsm.c +new file mode 100644 +index 00000000..cf0503ba +--- /dev/null ++++ b/fs/aufs/fhsm.c +@@ -0,0 +1,427 @@ ++/* ++ * Copyright (C) 2011-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program; if not, write to the Free Software ++ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA ++ */ ++ ++/* ++ * File-based Hierarchy Storage Management ++ */ ++ ++#include ++#include ++#include ++#include ++#include "aufs.h" ++ ++static aufs_bindex_t au_fhsm_bottom(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ struct au_fhsm *fhsm; ++ ++ SiMustAnyLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ fhsm = &sbinfo->si_fhsm; ++ AuDebugOn(!fhsm); ++ return fhsm->fhsm_bottom; ++} ++ ++void au_fhsm_set_bottom(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ struct au_sbinfo *sbinfo; ++ struct au_fhsm *fhsm; ++ ++ SiMustWriteLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ fhsm = &sbinfo->si_fhsm; ++ AuDebugOn(!fhsm); ++ fhsm->fhsm_bottom = bindex; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_fhsm_test_jiffy(struct au_sbinfo *sbinfo, struct au_branch *br) ++{ ++ struct au_br_fhsm *bf; ++ ++ bf = br->br_fhsm; ++ MtxMustLock(&bf->bf_lock); ++ ++ return !bf->bf_readable ++ || time_after(jiffies, ++ bf->bf_jiffy + sbinfo->si_fhsm.fhsm_expire); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void au_fhsm_notify(struct super_block *sb, int val) ++{ ++ struct au_sbinfo *sbinfo; ++ struct au_fhsm *fhsm; ++ ++ SiMustAnyLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ fhsm = &sbinfo->si_fhsm; ++ if (au_fhsm_pid(fhsm) ++ && atomic_read(&fhsm->fhsm_readable) != -1) { ++ atomic_set(&fhsm->fhsm_readable, val); ++ if (val) ++ wake_up(&fhsm->fhsm_wqh); ++ } ++} ++ ++static int au_fhsm_stfs(struct super_block *sb, aufs_bindex_t bindex, ++ struct aufs_stfs *rstfs, int do_lock, int do_notify) ++{ ++ int err; ++ struct au_branch *br; ++ struct au_br_fhsm *bf; ++ ++ br = au_sbr(sb, bindex); ++ AuDebugOn(au_br_rdonly(br)); ++ bf = br->br_fhsm; ++ AuDebugOn(!bf); ++ ++ if (do_lock) ++ mutex_lock(&bf->bf_lock); ++ else ++ MtxMustLock(&bf->bf_lock); ++ ++ /* sb->s_root for NFS is unreliable */ ++ err = au_br_stfs(br, &bf->bf_stfs); ++ if (unlikely(err)) { ++ AuErr1("FHSM failed (%d), b%d, ignored.\n", bindex, err); ++ goto out; ++ } ++ ++ bf->bf_jiffy = jiffies; ++ bf->bf_readable = 1; ++ if (do_notify) ++ au_fhsm_notify(sb, /*val*/1); ++ if (rstfs) ++ *rstfs = bf->bf_stfs; ++ ++out: ++ if (do_lock) ++ mutex_unlock(&bf->bf_lock); ++ au_fhsm_notify(sb, /*val*/1); ++ ++ return err; ++} ++ ++void au_fhsm_wrote(struct super_block *sb, aufs_bindex_t bindex, int force) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ struct au_fhsm *fhsm; ++ struct au_branch *br; ++ struct au_br_fhsm *bf; ++ ++ AuDbg("b%d, force %d\n", bindex, force); ++ SiMustAnyLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ fhsm = &sbinfo->si_fhsm; ++ if (!au_ftest_si(sbinfo, FHSM) ++ || fhsm->fhsm_bottom == bindex) ++ return; ++ ++ br = au_sbr(sb, bindex); ++ bf = br->br_fhsm; ++ AuDebugOn(!bf); ++ mutex_lock(&bf->bf_lock); ++ if (force ++ || au_fhsm_pid(fhsm) ++ || au_fhsm_test_jiffy(sbinfo, br)) ++ err = au_fhsm_stfs(sb, bindex, /*rstfs*/NULL, /*do_lock*/0, ++ /*do_notify*/1); ++ mutex_unlock(&bf->bf_lock); ++} ++ ++void au_fhsm_wrote_all(struct super_block *sb, int force) ++{ ++ aufs_bindex_t bindex, bbot; ++ struct au_branch *br; ++ ++ /* exclude the bottom */ ++ bbot = au_fhsm_bottom(sb); ++ for (bindex = 0; bindex < bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (au_br_fhsm(br->br_perm)) ++ au_fhsm_wrote(sb, bindex, force); ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static unsigned int au_fhsm_poll(struct file *file, ++ struct poll_table_struct *wait) ++{ ++ unsigned int mask; ++ struct au_sbinfo *sbinfo; ++ struct au_fhsm *fhsm; ++ ++ mask = 0; ++ sbinfo = file->private_data; ++ fhsm = &sbinfo->si_fhsm; ++ poll_wait(file, &fhsm->fhsm_wqh, wait); ++ if (atomic_read(&fhsm->fhsm_readable)) ++ mask = POLLIN /* | POLLRDNORM */; ++ ++ if (!mask) ++ AuDbg("mask 0x%x\n", mask); ++ return mask; ++} ++ ++static int au_fhsm_do_read_one(struct aufs_stbr __user *stbr, ++ struct aufs_stfs *stfs, __s16 brid) ++{ ++ int err; ++ ++ err = copy_to_user(&stbr->stfs, stfs, sizeof(*stfs)); ++ if (!err) ++ err = __put_user(brid, &stbr->brid); ++ if (unlikely(err)) ++ err = -EFAULT; ++ ++ return err; ++} ++ ++static ssize_t au_fhsm_do_read(struct super_block *sb, ++ struct aufs_stbr __user *stbr, size_t count) ++{ ++ ssize_t err; ++ int nstbr; ++ aufs_bindex_t bindex, bbot; ++ struct au_branch *br; ++ struct au_br_fhsm *bf; ++ ++ /* except the bottom branch */ ++ err = 0; ++ nstbr = 0; ++ bbot = au_fhsm_bottom(sb); ++ for (bindex = 0; !err && bindex < bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (!au_br_fhsm(br->br_perm)) ++ continue; ++ ++ bf = br->br_fhsm; ++ mutex_lock(&bf->bf_lock); ++ if (bf->bf_readable) { ++ err = -EFAULT; ++ if (count >= sizeof(*stbr)) ++ err = au_fhsm_do_read_one(stbr++, &bf->bf_stfs, ++ br->br_id); ++ if (!err) { ++ bf->bf_readable = 0; ++ count -= sizeof(*stbr); ++ nstbr++; ++ } ++ } ++ mutex_unlock(&bf->bf_lock); ++ } ++ if (!err) ++ err = sizeof(*stbr) * nstbr; ++ ++ return err; ++} ++ ++static ssize_t au_fhsm_read(struct file *file, char __user *buf, size_t count, ++ loff_t *pos) ++{ ++ ssize_t err; ++ int readable; ++ aufs_bindex_t nfhsm, bindex, bbot; ++ struct au_sbinfo *sbinfo; ++ struct au_fhsm *fhsm; ++ struct au_branch *br; ++ struct super_block *sb; ++ ++ err = 0; ++ sbinfo = file->private_data; ++ fhsm = &sbinfo->si_fhsm; ++need_data: ++ spin_lock_irq(&fhsm->fhsm_wqh.lock); ++ if (!atomic_read(&fhsm->fhsm_readable)) { ++ if (vfsub_file_flags(file) & O_NONBLOCK) ++ err = -EAGAIN; ++ else ++ err = wait_event_interruptible_locked_irq ++ (fhsm->fhsm_wqh, ++ atomic_read(&fhsm->fhsm_readable)); ++ } ++ spin_unlock_irq(&fhsm->fhsm_wqh.lock); ++ if (unlikely(err)) ++ goto out; ++ ++ /* sb may already be dead */ ++ au_rw_read_lock(&sbinfo->si_rwsem); ++ readable = atomic_read(&fhsm->fhsm_readable); ++ if (readable > 0) { ++ sb = sbinfo->si_sb; ++ AuDebugOn(!sb); ++ /* exclude the bottom branch */ ++ nfhsm = 0; ++ bbot = au_fhsm_bottom(sb); ++ for (bindex = 0; bindex < bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (au_br_fhsm(br->br_perm)) ++ nfhsm++; ++ } ++ err = -EMSGSIZE; ++ if (nfhsm * sizeof(struct aufs_stbr) <= count) { ++ atomic_set(&fhsm->fhsm_readable, 0); ++ err = au_fhsm_do_read(sbinfo->si_sb, (void __user *)buf, ++ count); ++ } ++ } ++ au_rw_read_unlock(&sbinfo->si_rwsem); ++ if (!readable) ++ goto need_data; ++ ++out: ++ return err; ++} ++ ++static int au_fhsm_release(struct inode *inode, struct file *file) ++{ ++ struct au_sbinfo *sbinfo; ++ struct au_fhsm *fhsm; ++ ++ /* sb may already be dead */ ++ sbinfo = file->private_data; ++ fhsm = &sbinfo->si_fhsm; ++ spin_lock(&fhsm->fhsm_spin); ++ fhsm->fhsm_pid = 0; ++ spin_unlock(&fhsm->fhsm_spin); ++ kobject_put(&sbinfo->si_kobj); ++ ++ return 0; ++} ++ ++static const struct file_operations au_fhsm_fops = { ++ .owner = THIS_MODULE, ++ .llseek = noop_llseek, ++ .read = au_fhsm_read, ++ .poll = au_fhsm_poll, ++ .release = au_fhsm_release ++}; ++ ++int au_fhsm_fd(struct super_block *sb, int oflags) ++{ ++ int err, fd; ++ struct au_sbinfo *sbinfo; ++ struct au_fhsm *fhsm; ++ ++ err = -EPERM; ++ if (unlikely(!capable(CAP_SYS_ADMIN))) ++ goto out; ++ ++ err = -EINVAL; ++ if (unlikely(oflags & ~(O_CLOEXEC | O_NONBLOCK))) ++ goto out; ++ ++ err = 0; ++ sbinfo = au_sbi(sb); ++ fhsm = &sbinfo->si_fhsm; ++ spin_lock(&fhsm->fhsm_spin); ++ if (!fhsm->fhsm_pid) ++ fhsm->fhsm_pid = current->pid; ++ else ++ err = -EBUSY; ++ spin_unlock(&fhsm->fhsm_spin); ++ if (unlikely(err)) ++ goto out; ++ ++ oflags |= O_RDONLY; ++ /* oflags |= FMODE_NONOTIFY; */ ++ fd = anon_inode_getfd("[aufs_fhsm]", &au_fhsm_fops, sbinfo, oflags); ++ err = fd; ++ if (unlikely(fd < 0)) ++ goto out_pid; ++ ++ /* succeed reglardless 'fhsm' status */ ++ kobject_get(&sbinfo->si_kobj); ++ si_noflush_read_lock(sb); ++ if (au_ftest_si(sbinfo, FHSM)) ++ au_fhsm_wrote_all(sb, /*force*/0); ++ si_read_unlock(sb); ++ goto out; /* success */ ++ ++out_pid: ++ spin_lock(&fhsm->fhsm_spin); ++ fhsm->fhsm_pid = 0; ++ spin_unlock(&fhsm->fhsm_spin); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_fhsm_br_alloc(struct au_branch *br) ++{ ++ int err; ++ ++ err = 0; ++ br->br_fhsm = kmalloc(sizeof(*br->br_fhsm), GFP_NOFS); ++ if (br->br_fhsm) ++ au_br_fhsm_init(br->br_fhsm); ++ else ++ err = -ENOMEM; ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_fhsm_fin(struct super_block *sb) ++{ ++ au_fhsm_notify(sb, /*val*/-1); ++} ++ ++void au_fhsm_init(struct au_sbinfo *sbinfo) ++{ ++ struct au_fhsm *fhsm; ++ ++ fhsm = &sbinfo->si_fhsm; ++ spin_lock_init(&fhsm->fhsm_spin); ++ init_waitqueue_head(&fhsm->fhsm_wqh); ++ atomic_set(&fhsm->fhsm_readable, 0); ++ fhsm->fhsm_expire ++ = msecs_to_jiffies(AUFS_FHSM_CACHE_DEF_SEC * MSEC_PER_SEC); ++ fhsm->fhsm_bottom = -1; ++} ++ ++void au_fhsm_set(struct au_sbinfo *sbinfo, unsigned int sec) ++{ ++ sbinfo->si_fhsm.fhsm_expire ++ = msecs_to_jiffies(sec * MSEC_PER_SEC); ++} ++ ++void au_fhsm_show(struct seq_file *seq, struct au_sbinfo *sbinfo) ++{ ++ unsigned int u; ++ ++ if (!au_ftest_si(sbinfo, FHSM)) ++ return; ++ ++ u = jiffies_to_msecs(sbinfo->si_fhsm.fhsm_expire) / MSEC_PER_SEC; ++ if (u != AUFS_FHSM_CACHE_DEF_SEC) ++ seq_printf(seq, ",fhsm_sec=%u", u); ++} +diff --git a/fs/aufs/file.c b/fs/aufs/file.c +new file mode 100644 +index 00000000..3a133973 +--- /dev/null ++++ b/fs/aufs/file.c +@@ -0,0 +1,848 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * handling file/dir, and address_space operation ++ */ ++ ++#ifdef CONFIG_AUFS_DEBUG ++#include ++#endif ++#include ++#include "aufs.h" ++ ++/* drop flags for writing */ ++unsigned int au_file_roflags(unsigned int flags) ++{ ++ flags &= ~(O_WRONLY | O_RDWR | O_APPEND | O_CREAT | O_TRUNC); ++ flags |= O_RDONLY | O_NOATIME; ++ return flags; ++} ++ ++/* common functions to regular file and dir */ ++struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags, ++ struct file *file, int force_wr) ++{ ++ struct file *h_file; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct path h_path; ++ int err; ++ ++ /* a race condition can happen between open and unlink/rmdir */ ++ h_file = ERR_PTR(-ENOENT); ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (au_test_nfsd() && (!h_dentry || d_is_negative(h_dentry))) ++ goto out; ++ h_inode = d_inode(h_dentry); ++ spin_lock(&h_dentry->d_lock); ++ err = (!d_unhashed(dentry) && d_unlinked(h_dentry)) ++ /* || !d_inode(dentry)->i_nlink */ ++ ; ++ spin_unlock(&h_dentry->d_lock); ++ if (unlikely(err)) ++ goto out; ++ ++ sb = dentry->d_sb; ++ br = au_sbr(sb, bindex); ++ err = au_br_test_oflag(flags, br); ++ h_file = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out; ++ ++ /* drop flags for writing */ ++ if (au_test_ro(sb, bindex, d_inode(dentry))) { ++ if (force_wr && !(flags & O_WRONLY)) ++ force_wr = 0; ++ flags = au_file_roflags(flags); ++ if (force_wr) { ++ h_file = ERR_PTR(-EROFS); ++ flags = au_file_roflags(flags); ++ if (unlikely(vfsub_native_ro(h_inode) ++ || IS_APPEND(h_inode))) ++ goto out; ++ flags &= ~O_ACCMODE; ++ flags |= O_WRONLY; ++ } ++ } ++ flags &= ~O_CREAT; ++ au_br_get(br); ++ h_path.dentry = h_dentry; ++ h_path.mnt = au_br_mnt(br); ++ h_file = vfsub_dentry_open(&h_path, flags); ++ if (IS_ERR(h_file)) ++ goto out_br; ++ ++ if (flags & __FMODE_EXEC) { ++ err = deny_write_access(h_file); ++ if (unlikely(err)) { ++ fput(h_file); ++ h_file = ERR_PTR(err); ++ goto out_br; ++ } ++ } ++ fsnotify_open(h_file); ++ goto out; /* success */ ++ ++out_br: ++ au_br_put(br); ++out: ++ return h_file; ++} ++ ++static int au_cmoo(struct dentry *dentry) ++{ ++ int err, cmoo, matched; ++ unsigned int udba; ++ struct path h_path; ++ struct au_pin pin; ++ struct au_cp_generic cpg = { ++ .dentry = dentry, ++ .bdst = -1, ++ .bsrc = -1, ++ .len = -1, ++ .pin = &pin, ++ .flags = AuCpup_DTIME | AuCpup_HOPEN ++ }; ++ struct inode *delegated; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ struct au_fhsm *fhsm; ++ pid_t pid; ++ struct au_branch *br; ++ struct dentry *parent; ++ struct au_hinode *hdir; ++ ++ DiMustWriteLock(dentry); ++ IiMustWriteLock(d_inode(dentry)); ++ ++ err = 0; ++ if (IS_ROOT(dentry)) ++ goto out; ++ cpg.bsrc = au_dbtop(dentry); ++ if (!cpg.bsrc) ++ goto out; ++ ++ sb = dentry->d_sb; ++ sbinfo = au_sbi(sb); ++ fhsm = &sbinfo->si_fhsm; ++ pid = au_fhsm_pid(fhsm); ++ rcu_read_lock(); ++ matched = (pid ++ && (current->pid == pid ++ || rcu_dereference(current->real_parent)->pid == pid)); ++ rcu_read_unlock(); ++ if (matched) ++ goto out; ++ ++ br = au_sbr(sb, cpg.bsrc); ++ cmoo = au_br_cmoo(br->br_perm); ++ if (!cmoo) ++ goto out; ++ if (!d_is_reg(dentry)) ++ cmoo &= AuBrAttr_COO_ALL; ++ if (!cmoo) ++ goto out; ++ ++ parent = dget_parent(dentry); ++ di_write_lock_parent(parent); ++ err = au_wbr_do_copyup_bu(dentry, cpg.bsrc - 1); ++ cpg.bdst = err; ++ if (unlikely(err < 0)) { ++ err = 0; /* there is no upper writable branch */ ++ goto out_dgrade; ++ } ++ AuDbg("bsrc %d, bdst %d\n", cpg.bsrc, cpg.bdst); ++ ++ /* do not respect the coo attrib for the target branch */ ++ err = au_cpup_dirs(dentry, cpg.bdst); ++ if (unlikely(err)) ++ goto out_dgrade; ++ ++ di_downgrade_lock(parent, AuLock_IR); ++ udba = au_opt_udba(sb); ++ err = au_pin(&pin, dentry, cpg.bdst, udba, ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ if (unlikely(err)) ++ goto out_parent; ++ ++ err = au_sio_cpup_simple(&cpg); ++ au_unpin(&pin); ++ if (unlikely(err)) ++ goto out_parent; ++ if (!(cmoo & AuBrWAttr_MOO)) ++ goto out_parent; /* success */ ++ ++ err = au_pin(&pin, dentry, cpg.bsrc, udba, ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ if (unlikely(err)) ++ goto out_parent; ++ ++ h_path.mnt = au_br_mnt(br); ++ h_path.dentry = au_h_dptr(dentry, cpg.bsrc); ++ hdir = au_hi(d_inode(parent), cpg.bsrc); ++ delegated = NULL; ++ err = vfsub_unlink(hdir->hi_inode, &h_path, &delegated, /*force*/1); ++ au_unpin(&pin); ++ /* todo: keep h_dentry or not? */ ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal unlink\n"); ++ iput(delegated); ++ } ++ if (unlikely(err)) { ++ pr_err("unlink %pd after coo failed (%d), ignored\n", ++ dentry, err); ++ err = 0; ++ } ++ goto out_parent; /* success */ ++ ++out_dgrade: ++ di_downgrade_lock(parent, AuLock_IR); ++out_parent: ++ di_read_unlock(parent, AuLock_IR); ++ dput(parent); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++int au_do_open(struct file *file, struct au_do_open_args *args) ++{ ++ int err, aopen = args->aopen; ++ struct dentry *dentry; ++ struct au_finfo *finfo; ++ ++ if (!aopen) ++ err = au_finfo_init(file, args->fidir); ++ else { ++ lockdep_off(); ++ err = au_finfo_init(file, args->fidir); ++ lockdep_on(); ++ } ++ if (unlikely(err)) ++ goto out; ++ ++ dentry = file->f_path.dentry; ++ AuDebugOn(IS_ERR_OR_NULL(dentry)); ++ di_write_lock_child(dentry); ++ err = au_cmoo(dentry); ++ di_downgrade_lock(dentry, AuLock_IR); ++ if (!err) ++ err = args->open(file, vfsub_file_flags(file), NULL); ++ di_read_unlock(dentry, AuLock_IR); ++ ++ finfo = au_fi(file); ++ if (!err) { ++ finfo->fi_file = file; ++ au_hbl_add(&finfo->fi_hlist, ++ &au_sbi(file->f_path.dentry->d_sb)->si_files); ++ } ++ if (!aopen) ++ fi_write_unlock(file); ++ else { ++ lockdep_off(); ++ fi_write_unlock(file); ++ lockdep_on(); ++ } ++ if (unlikely(err)) { ++ finfo->fi_hdir = NULL; ++ au_finfo_fin(file); ++ } ++ ++out: ++ return err; ++} ++ ++int au_reopen_nondir(struct file *file) ++{ ++ int err; ++ aufs_bindex_t btop; ++ struct dentry *dentry; ++ struct file *h_file, *h_file_tmp; ++ ++ dentry = file->f_path.dentry; ++ btop = au_dbtop(dentry); ++ h_file_tmp = NULL; ++ if (au_fbtop(file) == btop) { ++ h_file = au_hf_top(file); ++ if (file->f_mode == h_file->f_mode) ++ return 0; /* success */ ++ h_file_tmp = h_file; ++ get_file(h_file_tmp); ++ au_set_h_fptr(file, btop, NULL); ++ } ++ AuDebugOn(au_fi(file)->fi_hdir); ++ /* ++ * it can happen ++ * file exists on both of rw and ro ++ * open --> dbtop and fbtop are both 0 ++ * prepend a branch as rw, "rw" become ro ++ * remove rw/file ++ * delete the top branch, "rw" becomes rw again ++ * --> dbtop is 1, fbtop is still 0 ++ * write --> fbtop is 0 but dbtop is 1 ++ */ ++ /* AuDebugOn(au_fbtop(file) < btop); */ ++ ++ h_file = au_h_open(dentry, btop, vfsub_file_flags(file) & ~O_TRUNC, ++ file, /*force_wr*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) { ++ if (h_file_tmp) { ++ au_sbr_get(dentry->d_sb, btop); ++ au_set_h_fptr(file, btop, h_file_tmp); ++ h_file_tmp = NULL; ++ } ++ goto out; /* todo: close all? */ ++ } ++ ++ err = 0; ++ au_set_fbtop(file, btop); ++ au_set_h_fptr(file, btop, h_file); ++ au_update_figen(file); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ ++out: ++ if (h_file_tmp) ++ fput(h_file_tmp); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_reopen_wh(struct file *file, aufs_bindex_t btgt, ++ struct dentry *hi_wh) ++{ ++ int err; ++ aufs_bindex_t btop; ++ struct au_dinfo *dinfo; ++ struct dentry *h_dentry; ++ struct au_hdentry *hdp; ++ ++ dinfo = au_di(file->f_path.dentry); ++ AuRwMustWriteLock(&dinfo->di_rwsem); ++ ++ btop = dinfo->di_btop; ++ dinfo->di_btop = btgt; ++ hdp = au_hdentry(dinfo, btgt); ++ h_dentry = hdp->hd_dentry; ++ hdp->hd_dentry = hi_wh; ++ err = au_reopen_nondir(file); ++ hdp->hd_dentry = h_dentry; ++ dinfo->di_btop = btop; ++ ++ return err; ++} ++ ++static int au_ready_to_write_wh(struct file *file, loff_t len, ++ aufs_bindex_t bcpup, struct au_pin *pin) ++{ ++ int err; ++ struct inode *inode, *h_inode; ++ struct dentry *h_dentry, *hi_wh; ++ struct au_cp_generic cpg = { ++ .dentry = file->f_path.dentry, ++ .bdst = bcpup, ++ .bsrc = -1, ++ .len = len, ++ .pin = pin ++ }; ++ ++ au_update_dbtop(cpg.dentry); ++ inode = d_inode(cpg.dentry); ++ h_inode = NULL; ++ if (au_dbtop(cpg.dentry) <= bcpup ++ && au_dbbot(cpg.dentry) >= bcpup) { ++ h_dentry = au_h_dptr(cpg.dentry, bcpup); ++ if (h_dentry && d_is_positive(h_dentry)) ++ h_inode = d_inode(h_dentry); ++ } ++ hi_wh = au_hi_wh(inode, bcpup); ++ if (!hi_wh && !h_inode) ++ err = au_sio_cpup_wh(&cpg, file); ++ else ++ /* already copied-up after unlink */ ++ err = au_reopen_wh(file, bcpup, hi_wh); ++ ++ if (!err ++ && (inode->i_nlink > 1 ++ || (inode->i_state & I_LINKABLE)) ++ && au_opt_test(au_mntflags(cpg.dentry->d_sb), PLINK)) ++ au_plink_append(inode, bcpup, au_h_dptr(cpg.dentry, bcpup)); ++ ++ return err; ++} ++ ++/* ++ * prepare the @file for writing. ++ */ ++int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin) ++{ ++ int err; ++ aufs_bindex_t dbtop; ++ struct dentry *parent; ++ struct inode *inode; ++ struct super_block *sb; ++ struct file *h_file; ++ struct au_cp_generic cpg = { ++ .dentry = file->f_path.dentry, ++ .bdst = -1, ++ .bsrc = -1, ++ .len = len, ++ .pin = pin, ++ .flags = AuCpup_DTIME ++ }; ++ ++ sb = cpg.dentry->d_sb; ++ inode = d_inode(cpg.dentry); ++ cpg.bsrc = au_fbtop(file); ++ err = au_test_ro(sb, cpg.bsrc, inode); ++ if (!err && (au_hf_top(file)->f_mode & FMODE_WRITE)) { ++ err = au_pin(pin, cpg.dentry, cpg.bsrc, AuOpt_UDBA_NONE, ++ /*flags*/0); ++ goto out; ++ } ++ ++ /* need to cpup or reopen */ ++ parent = dget_parent(cpg.dentry); ++ di_write_lock_parent(parent); ++ err = AuWbrCopyup(au_sbi(sb), cpg.dentry); ++ cpg.bdst = err; ++ if (unlikely(err < 0)) ++ goto out_dgrade; ++ err = 0; ++ ++ if (!d_unhashed(cpg.dentry) && !au_h_dptr(parent, cpg.bdst)) { ++ err = au_cpup_dirs(cpg.dentry, cpg.bdst); ++ if (unlikely(err)) ++ goto out_dgrade; ++ } ++ ++ err = au_pin(pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE, ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ if (unlikely(err)) ++ goto out_dgrade; ++ ++ dbtop = au_dbtop(cpg.dentry); ++ if (dbtop <= cpg.bdst) ++ cpg.bsrc = cpg.bdst; ++ ++ if (dbtop <= cpg.bdst /* just reopen */ ++ || !d_unhashed(cpg.dentry) /* copyup and reopen */ ++ ) { ++ h_file = au_h_open_pre(cpg.dentry, cpg.bsrc, /*force_wr*/0); ++ if (IS_ERR(h_file)) ++ err = PTR_ERR(h_file); ++ else { ++ di_downgrade_lock(parent, AuLock_IR); ++ if (dbtop > cpg.bdst) ++ err = au_sio_cpup_simple(&cpg); ++ if (!err) ++ err = au_reopen_nondir(file); ++ au_h_open_post(cpg.dentry, cpg.bsrc, h_file); ++ } ++ } else { /* copyup as wh and reopen */ ++ /* ++ * since writable hfsplus branch is not supported, ++ * h_open_pre/post() are unnecessary. ++ */ ++ err = au_ready_to_write_wh(file, len, cpg.bdst, pin); ++ di_downgrade_lock(parent, AuLock_IR); ++ } ++ ++ if (!err) { ++ au_pin_set_parent_lflag(pin, /*lflag*/0); ++ goto out_dput; /* success */ ++ } ++ au_unpin(pin); ++ goto out_unlock; ++ ++out_dgrade: ++ di_downgrade_lock(parent, AuLock_IR); ++out_unlock: ++ di_read_unlock(parent, AuLock_IR); ++out_dput: ++ dput(parent); ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_do_flush(struct file *file, fl_owner_t id, ++ int (*flush)(struct file *file, fl_owner_t id)) ++{ ++ int err; ++ struct super_block *sb; ++ struct inode *inode; ++ ++ inode = file_inode(file); ++ sb = inode->i_sb; ++ si_noflush_read_lock(sb); ++ fi_read_lock(file); ++ ii_read_lock_child(inode); ++ ++ err = flush(file, id); ++ au_cpup_attr_timesizes(inode); ++ ++ ii_read_unlock(inode); ++ fi_read_unlock(file); ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_file_refresh_by_inode(struct file *file, int *need_reopen) ++{ ++ int err; ++ struct au_pin pin; ++ struct au_finfo *finfo; ++ struct dentry *parent, *hi_wh; ++ struct inode *inode; ++ struct super_block *sb; ++ struct au_cp_generic cpg = { ++ .dentry = file->f_path.dentry, ++ .bdst = -1, ++ .bsrc = -1, ++ .len = -1, ++ .pin = &pin, ++ .flags = AuCpup_DTIME ++ }; ++ ++ FiMustWriteLock(file); ++ ++ err = 0; ++ finfo = au_fi(file); ++ sb = cpg.dentry->d_sb; ++ inode = d_inode(cpg.dentry); ++ cpg.bdst = au_ibtop(inode); ++ if (cpg.bdst == finfo->fi_btop || IS_ROOT(cpg.dentry)) ++ goto out; ++ ++ parent = dget_parent(cpg.dentry); ++ if (au_test_ro(sb, cpg.bdst, inode)) { ++ di_read_lock_parent(parent, !AuLock_IR); ++ err = AuWbrCopyup(au_sbi(sb), cpg.dentry); ++ cpg.bdst = err; ++ di_read_unlock(parent, !AuLock_IR); ++ if (unlikely(err < 0)) ++ goto out_parent; ++ err = 0; ++ } ++ ++ di_read_lock_parent(parent, AuLock_IR); ++ hi_wh = au_hi_wh(inode, cpg.bdst); ++ if (!S_ISDIR(inode->i_mode) ++ && au_opt_test(au_mntflags(sb), PLINK) ++ && au_plink_test(inode) ++ && !d_unhashed(cpg.dentry) ++ && cpg.bdst < au_dbtop(cpg.dentry)) { ++ err = au_test_and_cpup_dirs(cpg.dentry, cpg.bdst); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ /* always superio. */ ++ err = au_pin(&pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE, ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ if (!err) { ++ err = au_sio_cpup_simple(&cpg); ++ au_unpin(&pin); ++ } ++ } else if (hi_wh) { ++ /* already copied-up after unlink */ ++ err = au_reopen_wh(file, cpg.bdst, hi_wh); ++ *need_reopen = 0; ++ } ++ ++out_unlock: ++ di_read_unlock(parent, AuLock_IR); ++out_parent: ++ dput(parent); ++out: ++ return err; ++} ++ ++static void au_do_refresh_dir(struct file *file) ++{ ++ aufs_bindex_t bindex, bbot, new_bindex, brid; ++ struct au_hfile *p, tmp, *q; ++ struct au_finfo *finfo; ++ struct super_block *sb; ++ struct au_fidir *fidir; ++ ++ FiMustWriteLock(file); ++ ++ sb = file->f_path.dentry->d_sb; ++ finfo = au_fi(file); ++ fidir = finfo->fi_hdir; ++ AuDebugOn(!fidir); ++ p = fidir->fd_hfile + finfo->fi_btop; ++ brid = p->hf_br->br_id; ++ bbot = fidir->fd_bbot; ++ for (bindex = finfo->fi_btop; bindex <= bbot; bindex++, p++) { ++ if (!p->hf_file) ++ continue; ++ ++ new_bindex = au_br_index(sb, p->hf_br->br_id); ++ if (new_bindex == bindex) ++ continue; ++ if (new_bindex < 0) { ++ au_set_h_fptr(file, bindex, NULL); ++ continue; ++ } ++ ++ /* swap two lower inode, and loop again */ ++ q = fidir->fd_hfile + new_bindex; ++ tmp = *q; ++ *q = *p; ++ *p = tmp; ++ if (tmp.hf_file) { ++ bindex--; ++ p--; ++ } ++ } ++ ++ p = fidir->fd_hfile; ++ if (!au_test_mmapped(file) && !d_unlinked(file->f_path.dentry)) { ++ bbot = au_sbbot(sb); ++ for (finfo->fi_btop = 0; finfo->fi_btop <= bbot; ++ finfo->fi_btop++, p++) ++ if (p->hf_file) { ++ if (file_inode(p->hf_file)) ++ break; ++ au_hfput(p, /*execed*/0); ++ } ++ } else { ++ bbot = au_br_index(sb, brid); ++ for (finfo->fi_btop = 0; finfo->fi_btop < bbot; ++ finfo->fi_btop++, p++) ++ if (p->hf_file) ++ au_hfput(p, /*execed*/0); ++ bbot = au_sbbot(sb); ++ } ++ ++ p = fidir->fd_hfile + bbot; ++ for (fidir->fd_bbot = bbot; fidir->fd_bbot >= finfo->fi_btop; ++ fidir->fd_bbot--, p--) ++ if (p->hf_file) { ++ if (file_inode(p->hf_file)) ++ break; ++ au_hfput(p, /*execed*/0); ++ } ++ AuDebugOn(fidir->fd_bbot < finfo->fi_btop); ++} ++ ++/* ++ * after branch manipulating, refresh the file. ++ */ ++static int refresh_file(struct file *file, int (*reopen)(struct file *file)) ++{ ++ int err, need_reopen, nbr; ++ aufs_bindex_t bbot, bindex; ++ struct dentry *dentry; ++ struct super_block *sb; ++ struct au_finfo *finfo; ++ struct au_hfile *hfile; ++ ++ dentry = file->f_path.dentry; ++ sb = dentry->d_sb; ++ nbr = au_sbbot(sb) + 1; ++ finfo = au_fi(file); ++ if (!finfo->fi_hdir) { ++ hfile = &finfo->fi_htop; ++ AuDebugOn(!hfile->hf_file); ++ bindex = au_br_index(sb, hfile->hf_br->br_id); ++ AuDebugOn(bindex < 0); ++ if (bindex != finfo->fi_btop) ++ au_set_fbtop(file, bindex); ++ } else { ++ err = au_fidir_realloc(finfo, nbr, /*may_shrink*/0); ++ if (unlikely(err)) ++ goto out; ++ au_do_refresh_dir(file); ++ } ++ ++ err = 0; ++ need_reopen = 1; ++ if (!au_test_mmapped(file)) ++ err = au_file_refresh_by_inode(file, &need_reopen); ++ if (finfo->fi_hdir) ++ /* harmless if err */ ++ au_fidir_realloc(finfo, nbr, /*may_shrink*/1); ++ if (!err && need_reopen && !d_unlinked(dentry)) ++ err = reopen(file); ++ if (!err) { ++ au_update_figen(file); ++ goto out; /* success */ ++ } ++ ++ /* error, close all lower files */ ++ if (finfo->fi_hdir) { ++ bbot = au_fbbot_dir(file); ++ for (bindex = au_fbtop(file); bindex <= bbot; bindex++) ++ au_set_h_fptr(file, bindex, NULL); ++ } ++ ++out: ++ return err; ++} ++ ++/* common function to regular file and dir */ ++int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file), ++ int wlock, unsigned int fi_lsc) ++{ ++ int err; ++ unsigned int sigen, figen; ++ aufs_bindex_t btop; ++ unsigned char pseudo_link; ++ struct dentry *dentry; ++ struct inode *inode; ++ ++ err = 0; ++ dentry = file->f_path.dentry; ++ inode = d_inode(dentry); ++ sigen = au_sigen(dentry->d_sb); ++ fi_write_lock_nested(file, fi_lsc); ++ figen = au_figen(file); ++ if (!fi_lsc) ++ di_write_lock_child(dentry); ++ else ++ di_write_lock_child2(dentry); ++ btop = au_dbtop(dentry); ++ pseudo_link = (btop != au_ibtop(inode)); ++ if (sigen == figen && !pseudo_link && au_fbtop(file) == btop) { ++ if (!wlock) { ++ di_downgrade_lock(dentry, AuLock_IR); ++ fi_downgrade_lock(file); ++ } ++ goto out; /* success */ ++ } ++ ++ AuDbg("sigen %d, figen %d\n", sigen, figen); ++ if (au_digen_test(dentry, sigen)) { ++ err = au_reval_dpath(dentry, sigen); ++ AuDebugOn(!err && au_digen_test(dentry, sigen)); ++ } ++ ++ if (!err) ++ err = refresh_file(file, reopen); ++ if (!err) { ++ if (!wlock) { ++ di_downgrade_lock(dentry, AuLock_IR); ++ fi_downgrade_lock(file); ++ } ++ } else { ++ di_write_unlock(dentry); ++ fi_write_unlock(file); ++ } ++ ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* cf. aufs_nopage() */ ++/* for madvise(2) */ ++static int aufs_readpage(struct file *file __maybe_unused, struct page *page) ++{ ++ unlock_page(page); ++ return 0; ++} ++ ++/* it will never be called, but necessary to support O_DIRECT */ ++static ssize_t aufs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) ++{ BUG(); return 0; } ++ ++/* they will never be called. */ ++#ifdef CONFIG_AUFS_DEBUG ++static int aufs_write_begin(struct file *file, struct address_space *mapping, ++ loff_t pos, unsigned len, unsigned flags, ++ struct page **pagep, void **fsdata) ++{ AuUnsupport(); return 0; } ++static int aufs_write_end(struct file *file, struct address_space *mapping, ++ loff_t pos, unsigned len, unsigned copied, ++ struct page *page, void *fsdata) ++{ AuUnsupport(); return 0; } ++static int aufs_writepage(struct page *page, struct writeback_control *wbc) ++{ AuUnsupport(); return 0; } ++ ++static int aufs_set_page_dirty(struct page *page) ++{ AuUnsupport(); return 0; } ++static void aufs_invalidatepage(struct page *page, unsigned int offset, ++ unsigned int length) ++{ AuUnsupport(); } ++static int aufs_releasepage(struct page *page, gfp_t gfp) ++{ AuUnsupport(); return 0; } ++#if 0 /* called by memory compaction regardless file */ ++static int aufs_migratepage(struct address_space *mapping, struct page *newpage, ++ struct page *page, enum migrate_mode mode) ++{ AuUnsupport(); return 0; } ++#endif ++static bool aufs_isolate_page(struct page *page, isolate_mode_t mode) ++{ AuUnsupport(); return true; } ++static void aufs_putback_page(struct page *page) ++{ AuUnsupport(); } ++static int aufs_launder_page(struct page *page) ++{ AuUnsupport(); return 0; } ++static int aufs_is_partially_uptodate(struct page *page, ++ unsigned long from, ++ unsigned long count) ++{ AuUnsupport(); return 0; } ++static void aufs_is_dirty_writeback(struct page *page, bool *dirty, ++ bool *writeback) ++{ AuUnsupport(); } ++static int aufs_error_remove_page(struct address_space *mapping, ++ struct page *page) ++{ AuUnsupport(); return 0; } ++static int aufs_swap_activate(struct swap_info_struct *sis, struct file *file, ++ sector_t *span) ++{ AuUnsupport(); return 0; } ++static void aufs_swap_deactivate(struct file *file) ++{ AuUnsupport(); } ++#endif /* CONFIG_AUFS_DEBUG */ ++ ++const struct address_space_operations aufs_aop = { ++ .readpage = aufs_readpage, ++ .direct_IO = aufs_direct_IO, ++#ifdef CONFIG_AUFS_DEBUG ++ .writepage = aufs_writepage, ++ /* no writepages, because of writepage */ ++ .set_page_dirty = aufs_set_page_dirty, ++ /* no readpages, because of readpage */ ++ .write_begin = aufs_write_begin, ++ .write_end = aufs_write_end, ++ /* no bmap, no block device */ ++ .invalidatepage = aufs_invalidatepage, ++ .releasepage = aufs_releasepage, ++ /* is fallback_migrate_page ok? */ ++ /* .migratepage = aufs_migratepage, */ ++ .isolate_page = aufs_isolate_page, ++ .putback_page = aufs_putback_page, ++ .launder_page = aufs_launder_page, ++ .is_partially_uptodate = aufs_is_partially_uptodate, ++ .is_dirty_writeback = aufs_is_dirty_writeback, ++ .error_remove_page = aufs_error_remove_page, ++ .swap_activate = aufs_swap_activate, ++ .swap_deactivate = aufs_swap_deactivate ++#endif /* CONFIG_AUFS_DEBUG */ ++}; +diff --git a/fs/aufs/file.h b/fs/aufs/file.h +new file mode 100644 +index 00000000..66e45f31 +--- /dev/null ++++ b/fs/aufs/file.h +@@ -0,0 +1,330 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * file operations ++ */ ++ ++#ifndef __AUFS_FILE_H__ ++#define __AUFS_FILE_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include ++#include ++#include "rwsem.h" ++ ++struct au_branch; ++struct au_hfile { ++ struct file *hf_file; ++ struct au_branch *hf_br; ++}; ++ ++struct au_vdir; ++struct au_fidir { ++ aufs_bindex_t fd_bbot; ++ aufs_bindex_t fd_nent; ++ struct au_vdir *fd_vdir_cache; ++ struct au_hfile fd_hfile[]; ++}; ++ ++static inline int au_fidir_sz(int nent) ++{ ++ AuDebugOn(nent < 0); ++ return sizeof(struct au_fidir) + sizeof(struct au_hfile) * nent; ++} ++ ++struct au_finfo { ++ atomic_t fi_generation; ++ ++ struct au_rwsem fi_rwsem; ++ aufs_bindex_t fi_btop; ++ ++ /* do not union them */ ++ struct { /* for non-dir */ ++ struct au_hfile fi_htop; ++ atomic_t fi_mmapped; ++ }; ++ struct au_fidir *fi_hdir; /* for dir only */ ++ ++ struct hlist_bl_node fi_hlist; ++ struct file *fi_file; /* very ugly */ ++} ____cacheline_aligned_in_smp; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* file.c */ ++extern const struct address_space_operations aufs_aop; ++unsigned int au_file_roflags(unsigned int flags); ++struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags, ++ struct file *file, int force_wr); ++struct au_do_open_args { ++ int aopen; ++ int (*open)(struct file *file, int flags, ++ struct file *h_file); ++ struct au_fidir *fidir; ++ struct file *h_file; ++}; ++int au_do_open(struct file *file, struct au_do_open_args *args); ++int au_reopen_nondir(struct file *file); ++struct au_pin; ++int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin); ++int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file), ++ int wlock, unsigned int fi_lsc); ++int au_do_flush(struct file *file, fl_owner_t id, ++ int (*flush)(struct file *file, fl_owner_t id)); ++ ++/* poll.c */ ++#ifdef CONFIG_AUFS_POLL ++unsigned int aufs_poll(struct file *file, poll_table *wait); ++#endif ++ ++#ifdef CONFIG_AUFS_BR_HFSPLUS ++/* hfsplus.c */ ++struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex, ++ int force_wr); ++void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex, ++ struct file *h_file); ++#else ++AuStub(struct file *, au_h_open_pre, return NULL, struct dentry *dentry, ++ aufs_bindex_t bindex, int force_wr) ++AuStubVoid(au_h_open_post, struct dentry *dentry, aufs_bindex_t bindex, ++ struct file *h_file); ++#endif ++ ++/* f_op.c */ ++extern const struct file_operations aufs_file_fop; ++int au_do_open_nondir(struct file *file, int flags, struct file *h_file); ++int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file); ++struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc); ++ ++/* finfo.c */ ++void au_hfput(struct au_hfile *hf, int execed); ++void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, ++ struct file *h_file); ++ ++void au_update_figen(struct file *file); ++struct au_fidir *au_fidir_alloc(struct super_block *sb); ++int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink); ++ ++void au_fi_init_once(void *_fi); ++void au_finfo_fin(struct file *file); ++int au_finfo_init(struct file *file, struct au_fidir *fidir); ++ ++/* ioctl.c */ ++long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg); ++#ifdef CONFIG_COMPAT ++long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd, ++ unsigned long arg); ++long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd, ++ unsigned long arg); ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct au_finfo *au_fi(struct file *file) ++{ ++ return file->private_data; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * fi_read_lock, fi_write_lock, ++ * fi_read_unlock, fi_write_unlock, fi_downgrade_lock ++ */ ++AuSimpleRwsemFuncs(fi, struct file *f, &au_fi(f)->fi_rwsem); ++ ++/* lock subclass for finfo */ ++enum { ++ AuLsc_FI_1, ++ AuLsc_FI_2 ++}; ++ ++static inline void fi_read_lock_nested(struct file *f, unsigned int lsc) ++{ ++ au_rw_read_lock_nested(&au_fi(f)->fi_rwsem, lsc); ++} ++ ++static inline void fi_write_lock_nested(struct file *f, unsigned int lsc) ++{ ++ au_rw_write_lock_nested(&au_fi(f)->fi_rwsem, lsc); ++} ++ ++/* ++ * fi_read_lock_1, fi_write_lock_1, ++ * fi_read_lock_2, fi_write_lock_2 ++ */ ++#define AuReadLockFunc(name) \ ++static inline void fi_read_lock_##name(struct file *f) \ ++{ fi_read_lock_nested(f, AuLsc_FI_##name); } ++ ++#define AuWriteLockFunc(name) \ ++static inline void fi_write_lock_##name(struct file *f) \ ++{ fi_write_lock_nested(f, AuLsc_FI_##name); } ++ ++#define AuRWLockFuncs(name) \ ++ AuReadLockFunc(name) \ ++ AuWriteLockFunc(name) ++ ++AuRWLockFuncs(1); ++AuRWLockFuncs(2); ++ ++#undef AuReadLockFunc ++#undef AuWriteLockFunc ++#undef AuRWLockFuncs ++ ++#define FiMustNoWaiters(f) AuRwMustNoWaiters(&au_fi(f)->fi_rwsem) ++#define FiMustAnyLock(f) AuRwMustAnyLock(&au_fi(f)->fi_rwsem) ++#define FiMustWriteLock(f) AuRwMustWriteLock(&au_fi(f)->fi_rwsem) ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* todo: hard/soft set? */ ++static inline aufs_bindex_t au_fbtop(struct file *file) ++{ ++ FiMustAnyLock(file); ++ return au_fi(file)->fi_btop; ++} ++ ++static inline aufs_bindex_t au_fbbot_dir(struct file *file) ++{ ++ FiMustAnyLock(file); ++ AuDebugOn(!au_fi(file)->fi_hdir); ++ return au_fi(file)->fi_hdir->fd_bbot; ++} ++ ++static inline struct au_vdir *au_fvdir_cache(struct file *file) ++{ ++ FiMustAnyLock(file); ++ AuDebugOn(!au_fi(file)->fi_hdir); ++ return au_fi(file)->fi_hdir->fd_vdir_cache; ++} ++ ++static inline void au_set_fbtop(struct file *file, aufs_bindex_t bindex) ++{ ++ FiMustWriteLock(file); ++ au_fi(file)->fi_btop = bindex; ++} ++ ++static inline void au_set_fbbot_dir(struct file *file, aufs_bindex_t bindex) ++{ ++ FiMustWriteLock(file); ++ AuDebugOn(!au_fi(file)->fi_hdir); ++ au_fi(file)->fi_hdir->fd_bbot = bindex; ++} ++ ++static inline void au_set_fvdir_cache(struct file *file, ++ struct au_vdir *vdir_cache) ++{ ++ FiMustWriteLock(file); ++ AuDebugOn(!au_fi(file)->fi_hdir); ++ au_fi(file)->fi_hdir->fd_vdir_cache = vdir_cache; ++} ++ ++static inline struct file *au_hf_top(struct file *file) ++{ ++ FiMustAnyLock(file); ++ AuDebugOn(au_fi(file)->fi_hdir); ++ return au_fi(file)->fi_htop.hf_file; ++} ++ ++static inline struct file *au_hf_dir(struct file *file, aufs_bindex_t bindex) ++{ ++ FiMustAnyLock(file); ++ AuDebugOn(!au_fi(file)->fi_hdir); ++ return au_fi(file)->fi_hdir->fd_hfile[0 + bindex].hf_file; ++} ++ ++/* todo: memory barrier? */ ++static inline unsigned int au_figen(struct file *f) ++{ ++ return atomic_read(&au_fi(f)->fi_generation); ++} ++ ++static inline void au_set_mmapped(struct file *f) ++{ ++ if (atomic_inc_return(&au_fi(f)->fi_mmapped)) ++ return; ++ pr_warn("fi_mmapped wrapped around\n"); ++ while (!atomic_inc_return(&au_fi(f)->fi_mmapped)) ++ ; ++} ++ ++static inline void au_unset_mmapped(struct file *f) ++{ ++ atomic_dec(&au_fi(f)->fi_mmapped); ++} ++ ++static inline int au_test_mmapped(struct file *f) ++{ ++ return atomic_read(&au_fi(f)->fi_mmapped); ++} ++ ++/* customize vma->vm_file */ ++ ++static inline void au_do_vm_file_reset(struct vm_area_struct *vma, ++ struct file *file) ++{ ++ struct file *f; ++ ++ f = vma->vm_file; ++ get_file(file); ++ vma->vm_file = file; ++ fput(f); ++} ++ ++#ifdef CONFIG_MMU ++#define AuDbgVmRegion(file, vma) do {} while (0) ++ ++static inline void au_vm_file_reset(struct vm_area_struct *vma, ++ struct file *file) ++{ ++ au_do_vm_file_reset(vma, file); ++} ++#else ++#define AuDbgVmRegion(file, vma) \ ++ AuDebugOn((vma)->vm_region && (vma)->vm_region->vm_file != (file)) ++ ++static inline void au_vm_file_reset(struct vm_area_struct *vma, ++ struct file *file) ++{ ++ struct file *f; ++ ++ au_do_vm_file_reset(vma, file); ++ f = vma->vm_region->vm_file; ++ get_file(file); ++ vma->vm_region->vm_file = file; ++ fput(f); ++} ++#endif /* CONFIG_MMU */ ++ ++/* handle vma->vm_prfile */ ++static inline void au_vm_prfile_set(struct vm_area_struct *vma, ++ struct file *file) ++{ ++ get_file(file); ++ vma->vm_prfile = file; ++#ifndef CONFIG_MMU ++ get_file(file); ++ vma->vm_region->vm_prfile = file; ++#endif ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_FILE_H__ */ +diff --git a/fs/aufs/finfo.c b/fs/aufs/finfo.c +new file mode 100644 +index 00000000..3144f462 +--- /dev/null ++++ b/fs/aufs/finfo.c +@@ -0,0 +1,148 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * file private data ++ */ ++ ++#include "aufs.h" ++ ++void au_hfput(struct au_hfile *hf, int execed) ++{ ++ if (execed) ++ allow_write_access(hf->hf_file); ++ fput(hf->hf_file); ++ hf->hf_file = NULL; ++ au_br_put(hf->hf_br); ++ hf->hf_br = NULL; ++} ++ ++void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, struct file *val) ++{ ++ struct au_finfo *finfo = au_fi(file); ++ struct au_hfile *hf; ++ struct au_fidir *fidir; ++ ++ fidir = finfo->fi_hdir; ++ if (!fidir) { ++ AuDebugOn(finfo->fi_btop != bindex); ++ hf = &finfo->fi_htop; ++ } else ++ hf = fidir->fd_hfile + bindex; ++ ++ if (hf && hf->hf_file) ++ au_hfput(hf, vfsub_file_execed(file)); ++ if (val) { ++ FiMustWriteLock(file); ++ AuDebugOn(IS_ERR_OR_NULL(file->f_path.dentry)); ++ hf->hf_file = val; ++ hf->hf_br = au_sbr(file->f_path.dentry->d_sb, bindex); ++ } ++} ++ ++void au_update_figen(struct file *file) ++{ ++ atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_path.dentry)); ++ /* smp_mb(); */ /* atomic_set */ ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_fidir *au_fidir_alloc(struct super_block *sb) ++{ ++ struct au_fidir *fidir; ++ int nbr; ++ ++ nbr = au_sbbot(sb) + 1; ++ if (nbr < 2) ++ nbr = 2; /* initial allocate for 2 branches */ ++ fidir = kzalloc(au_fidir_sz(nbr), GFP_NOFS); ++ if (fidir) { ++ fidir->fd_bbot = -1; ++ fidir->fd_nent = nbr; ++ } ++ ++ return fidir; ++} ++ ++int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink) ++{ ++ int err; ++ struct au_fidir *fidir, *p; ++ ++ AuRwMustWriteLock(&finfo->fi_rwsem); ++ fidir = finfo->fi_hdir; ++ AuDebugOn(!fidir); ++ ++ err = -ENOMEM; ++ p = au_kzrealloc(fidir, au_fidir_sz(fidir->fd_nent), au_fidir_sz(nbr), ++ GFP_NOFS, may_shrink); ++ if (p) { ++ p->fd_nent = nbr; ++ finfo->fi_hdir = p; ++ err = 0; ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_finfo_fin(struct file *file) ++{ ++ struct au_finfo *finfo; ++ ++ au_nfiles_dec(file->f_path.dentry->d_sb); ++ ++ finfo = au_fi(file); ++ AuDebugOn(finfo->fi_hdir); ++ AuRwDestroy(&finfo->fi_rwsem); ++ au_cache_free_finfo(finfo); ++} ++ ++void au_fi_init_once(void *_finfo) ++{ ++ struct au_finfo *finfo = _finfo; ++ ++ au_rw_init(&finfo->fi_rwsem); ++} ++ ++int au_finfo_init(struct file *file, struct au_fidir *fidir) ++{ ++ int err; ++ struct au_finfo *finfo; ++ struct dentry *dentry; ++ ++ err = -ENOMEM; ++ dentry = file->f_path.dentry; ++ finfo = au_cache_alloc_finfo(); ++ if (unlikely(!finfo)) ++ goto out; ++ ++ err = 0; ++ au_nfiles_inc(dentry->d_sb); ++ au_rw_write_lock(&finfo->fi_rwsem); ++ finfo->fi_btop = -1; ++ finfo->fi_hdir = fidir; ++ atomic_set(&finfo->fi_generation, au_digen(dentry)); ++ /* smp_mb(); */ /* atomic_set */ ++ ++ file->private_data = finfo; ++ ++out: ++ return err; ++} +diff --git a/fs/aufs/fstype.h b/fs/aufs/fstype.h +new file mode 100644 +index 00000000..5dd8e5e7 +--- /dev/null ++++ b/fs/aufs/fstype.h +@@ -0,0 +1,400 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * judging filesystem type ++ */ ++ ++#ifndef __AUFS_FSTYPE_H__ ++#define __AUFS_FSTYPE_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include ++#include ++#include ++ ++static inline int au_test_aufs(struct super_block *sb) ++{ ++ return sb->s_magic == AUFS_SUPER_MAGIC; ++} ++ ++static inline const char *au_sbtype(struct super_block *sb) ++{ ++ return sb->s_type->name; ++} ++ ++static inline int au_test_iso9660(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_ISO9660_FS) ++ return sb->s_magic == ISOFS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_romfs(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_ROMFS_FS) ++ return sb->s_magic == ROMFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_cramfs(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_CRAMFS) ++ return sb->s_magic == CRAMFS_MAGIC; ++#endif ++ return 0; ++} ++ ++static inline int au_test_nfs(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_NFS_FS) ++ return sb->s_magic == NFS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_fuse(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_FUSE_FS) ++ return sb->s_magic == FUSE_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_xfs(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_XFS_FS) ++ return sb->s_magic == XFS_SB_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_tmpfs(struct super_block *sb __maybe_unused) ++{ ++#ifdef CONFIG_TMPFS ++ return sb->s_magic == TMPFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_ecryptfs(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_ECRYPT_FS) ++ return !strcmp(au_sbtype(sb), "ecryptfs"); ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_ramfs(struct super_block *sb) ++{ ++ return sb->s_magic == RAMFS_MAGIC; ++} ++ ++static inline int au_test_ubifs(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_UBIFS_FS) ++ return sb->s_magic == UBIFS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_procfs(struct super_block *sb __maybe_unused) ++{ ++#ifdef CONFIG_PROC_FS ++ return sb->s_magic == PROC_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_sysfs(struct super_block *sb __maybe_unused) ++{ ++#ifdef CONFIG_SYSFS ++ return sb->s_magic == SYSFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_configfs(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_CONFIGFS_FS) ++ return sb->s_magic == CONFIGFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_minix(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_MINIX_FS) ++ return sb->s_magic == MINIX3_SUPER_MAGIC ++ || sb->s_magic == MINIX2_SUPER_MAGIC ++ || sb->s_magic == MINIX2_SUPER_MAGIC2 ++ || sb->s_magic == MINIX_SUPER_MAGIC ++ || sb->s_magic == MINIX_SUPER_MAGIC2; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_fat(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_FAT_FS) ++ return sb->s_magic == MSDOS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_msdos(struct super_block *sb) ++{ ++ return au_test_fat(sb); ++} ++ ++static inline int au_test_vfat(struct super_block *sb) ++{ ++ return au_test_fat(sb); ++} ++ ++static inline int au_test_securityfs(struct super_block *sb __maybe_unused) ++{ ++#ifdef CONFIG_SECURITYFS ++ return sb->s_magic == SECURITYFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_squashfs(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_SQUASHFS) ++ return sb->s_magic == SQUASHFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_btrfs(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_BTRFS_FS) ++ return sb->s_magic == BTRFS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_xenfs(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_XENFS) ++ return sb->s_magic == XENFS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_debugfs(struct super_block *sb __maybe_unused) ++{ ++#ifdef CONFIG_DEBUG_FS ++ return sb->s_magic == DEBUGFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_nilfs(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_NILFS) ++ return sb->s_magic == NILFS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_hfsplus(struct super_block *sb __maybe_unused) ++{ ++#if IS_ENABLED(CONFIG_HFSPLUS_FS) ++ return sb->s_magic == HFSPLUS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* ++ * they can't be an aufs branch. ++ */ ++static inline int au_test_fs_unsuppoted(struct super_block *sb) ++{ ++ return ++#ifndef CONFIG_AUFS_BR_RAMFS ++ au_test_ramfs(sb) || ++#endif ++ au_test_procfs(sb) ++ || au_test_sysfs(sb) ++ || au_test_configfs(sb) ++ || au_test_debugfs(sb) ++ || au_test_securityfs(sb) ++ || au_test_xenfs(sb) ++ || au_test_ecryptfs(sb) ++ /* || !strcmp(au_sbtype(sb), "unionfs") */ ++ || au_test_aufs(sb); /* will be supported in next version */ ++} ++ ++static inline int au_test_fs_remote(struct super_block *sb) ++{ ++ return !au_test_tmpfs(sb) ++#ifdef CONFIG_AUFS_BR_RAMFS ++ && !au_test_ramfs(sb) ++#endif ++ && !(sb->s_type->fs_flags & FS_REQUIRES_DEV); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * Note: these functions (below) are created after reading ->getattr() in all ++ * filesystems under linux/fs. it means we have to do so in every update... ++ */ ++ ++/* ++ * some filesystems require getattr to refresh the inode attributes before ++ * referencing. ++ * in most cases, we can rely on the inode attribute in NFS (or every remote fs) ++ * and leave the work for d_revalidate() ++ */ ++static inline int au_test_fs_refresh_iattr(struct super_block *sb) ++{ ++ return au_test_nfs(sb) ++ || au_test_fuse(sb) ++ /* || au_test_btrfs(sb) */ /* untested */ ++ ; ++} ++ ++/* ++ * filesystems which don't maintain i_size or i_blocks. ++ */ ++static inline int au_test_fs_bad_iattr_size(struct super_block *sb) ++{ ++ return au_test_xfs(sb) ++ || au_test_btrfs(sb) ++ || au_test_ubifs(sb) ++ || au_test_hfsplus(sb) /* maintained, but incorrect */ ++ /* || au_test_minix(sb) */ /* untested */ ++ ; ++} ++ ++/* ++ * filesystems which don't store the correct value in some of their inode ++ * attributes. ++ */ ++static inline int au_test_fs_bad_iattr(struct super_block *sb) ++{ ++ return au_test_fs_bad_iattr_size(sb) ++ || au_test_fat(sb) ++ || au_test_msdos(sb) ++ || au_test_vfat(sb); ++} ++ ++/* they don't check i_nlink in link(2) */ ++static inline int au_test_fs_no_limit_nlink(struct super_block *sb) ++{ ++ return au_test_tmpfs(sb) ++#ifdef CONFIG_AUFS_BR_RAMFS ++ || au_test_ramfs(sb) ++#endif ++ || au_test_ubifs(sb) ++ || au_test_hfsplus(sb); ++} ++ ++/* ++ * filesystems which sets S_NOATIME and S_NOCMTIME. ++ */ ++static inline int au_test_fs_notime(struct super_block *sb) ++{ ++ return au_test_nfs(sb) ++ || au_test_fuse(sb) ++ || au_test_ubifs(sb) ++ ; ++} ++ ++/* temporary support for i#1 in cramfs */ ++static inline int au_test_fs_unique_ino(struct inode *inode) ++{ ++ if (au_test_cramfs(inode->i_sb)) ++ return inode->i_ino != 1; ++ return 1; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * the filesystem where the xino files placed must support i/o after unlink and ++ * maintain i_size and i_blocks. ++ */ ++static inline int au_test_fs_bad_xino(struct super_block *sb) ++{ ++ return au_test_fs_remote(sb) ++ || au_test_fs_bad_iattr_size(sb) ++ /* don't want unnecessary work for xino */ ++ || au_test_aufs(sb) ++ || au_test_ecryptfs(sb) ++ || au_test_nilfs(sb); ++} ++ ++static inline int au_test_fs_trunc_xino(struct super_block *sb) ++{ ++ return au_test_tmpfs(sb) ++ || au_test_ramfs(sb); ++} ++ ++/* ++ * test if the @sb is real-readonly. ++ */ ++static inline int au_test_fs_rr(struct super_block *sb) ++{ ++ return au_test_squashfs(sb) ++ || au_test_iso9660(sb) ++ || au_test_cramfs(sb) ++ || au_test_romfs(sb); ++} ++ ++/* ++ * test if the @inode is nfs with 'noacl' option ++ * NFS always sets MS_POSIXACL regardless its mount option 'noacl.' ++ */ ++static inline int au_test_nfs_noacl(struct inode *inode) ++{ ++ return au_test_nfs(inode->i_sb) ++ /* && IS_POSIXACL(inode) */ ++ && !nfs_server_capable(inode, NFS_CAP_ACLS); ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_FSTYPE_H__ */ +diff --git a/fs/aufs/hbl.h b/fs/aufs/hbl.h +new file mode 100644 +index 00000000..328586e3 +--- /dev/null ++++ b/fs/aufs/hbl.h +@@ -0,0 +1,64 @@ ++/* ++ * Copyright (C) 2017-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * helpers for hlist_bl.h ++ */ ++ ++#ifndef __AUFS_HBL_H__ ++#define __AUFS_HBL_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++ ++static inline void au_hbl_add(struct hlist_bl_node *node, ++ struct hlist_bl_head *hbl) ++{ ++ hlist_bl_lock(hbl); ++ hlist_bl_add_head(node, hbl); ++ hlist_bl_unlock(hbl); ++} ++ ++static inline void au_hbl_del(struct hlist_bl_node *node, ++ struct hlist_bl_head *hbl) ++{ ++ hlist_bl_lock(hbl); ++ hlist_bl_del(node); ++ hlist_bl_unlock(hbl); ++} ++ ++#define au_hbl_for_each(pos, head) \ ++ for (pos = hlist_bl_first(head); \ ++ pos; \ ++ pos = pos->next) ++ ++static inline unsigned long au_hbl_count(struct hlist_bl_head *hbl) ++{ ++ unsigned long cnt; ++ struct hlist_bl_node *pos; ++ ++ cnt = 0; ++ hlist_bl_lock(hbl); ++ au_hbl_for_each(pos, hbl) ++ cnt++; ++ hlist_bl_unlock(hbl); ++ return cnt; ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_HBL_H__ */ +diff --git a/fs/aufs/hfsnotify.c b/fs/aufs/hfsnotify.c +new file mode 100644 +index 00000000..091eab1b +--- /dev/null ++++ b/fs/aufs/hfsnotify.c +@@ -0,0 +1,287 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * fsnotify for the lower directories ++ */ ++ ++#include "aufs.h" ++ ++/* FS_IN_IGNORED is unnecessary */ ++static const __u32 AuHfsnMask = (FS_MOVED_TO | FS_MOVED_FROM | FS_DELETE ++ | FS_CREATE | FS_EVENT_ON_CHILD); ++static DECLARE_WAIT_QUEUE_HEAD(au_hfsn_wq); ++static __cacheline_aligned_in_smp atomic64_t au_hfsn_ifree = ATOMIC64_INIT(0); ++ ++static void au_hfsn_free_mark(struct fsnotify_mark *mark) ++{ ++ struct au_hnotify *hn = container_of(mark, struct au_hnotify, ++ hn_mark); ++ /* AuDbg("here\n"); */ ++ au_cache_free_hnotify(hn); ++ smp_mb__before_atomic(); /* for atomic64_dec */ ++ if (atomic64_dec_and_test(&au_hfsn_ifree)) ++ wake_up(&au_hfsn_wq); ++} ++ ++static int au_hfsn_alloc(struct au_hinode *hinode) ++{ ++ int err; ++ struct au_hnotify *hn; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct fsnotify_mark *mark; ++ aufs_bindex_t bindex; ++ ++ hn = hinode->hi_notify; ++ sb = hn->hn_aufs_inode->i_sb; ++ bindex = au_br_index(sb, hinode->hi_id); ++ br = au_sbr(sb, bindex); ++ AuDebugOn(!br->br_hfsn); ++ ++ mark = &hn->hn_mark; ++ fsnotify_init_mark(mark, au_hfsn_free_mark); ++ mark->mask = AuHfsnMask; ++ /* ++ * by udba rename or rmdir, aufs assign a new inode to the known ++ * h_inode, so specify 1 to allow dups. ++ */ ++ lockdep_off(); ++ err = fsnotify_add_mark(mark, br->br_hfsn->hfsn_group, hinode->hi_inode, ++ /*mnt*/NULL, /*allow_dups*/1); ++ lockdep_on(); ++ ++ return err; ++} ++ ++static int au_hfsn_free(struct au_hinode *hinode, struct au_hnotify *hn) ++{ ++ struct fsnotify_mark *mark; ++ unsigned long long ull; ++ struct fsnotify_group *group; ++ ++ ull = atomic64_inc_return(&au_hfsn_ifree); ++ BUG_ON(!ull); ++ ++ mark = &hn->hn_mark; ++ spin_lock(&mark->lock); ++ group = mark->group; ++ fsnotify_get_group(group); ++ spin_unlock(&mark->lock); ++ lockdep_off(); ++ fsnotify_destroy_mark(mark, group); ++ fsnotify_put_mark(mark); ++ fsnotify_put_group(group); ++ lockdep_on(); ++ ++ /* free hn by myself */ ++ return 0; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void au_hfsn_ctl(struct au_hinode *hinode, int do_set) ++{ ++ struct fsnotify_mark *mark; ++ ++ mark = &hinode->hi_notify->hn_mark; ++ spin_lock(&mark->lock); ++ if (do_set) { ++ AuDebugOn(mark->mask & AuHfsnMask); ++ mark->mask |= AuHfsnMask; ++ } else { ++ AuDebugOn(!(mark->mask & AuHfsnMask)); ++ mark->mask &= ~AuHfsnMask; ++ } ++ spin_unlock(&mark->lock); ++ /* fsnotify_recalc_inode_mask(hinode->hi_inode); */ ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* #define AuDbgHnotify */ ++#ifdef AuDbgHnotify ++static char *au_hfsn_name(u32 mask) ++{ ++#ifdef CONFIG_AUFS_DEBUG ++#define test_ret(flag) \ ++ do { \ ++ if (mask & flag) \ ++ return #flag; \ ++ } while (0) ++ test_ret(FS_ACCESS); ++ test_ret(FS_MODIFY); ++ test_ret(FS_ATTRIB); ++ test_ret(FS_CLOSE_WRITE); ++ test_ret(FS_CLOSE_NOWRITE); ++ test_ret(FS_OPEN); ++ test_ret(FS_MOVED_FROM); ++ test_ret(FS_MOVED_TO); ++ test_ret(FS_CREATE); ++ test_ret(FS_DELETE); ++ test_ret(FS_DELETE_SELF); ++ test_ret(FS_MOVE_SELF); ++ test_ret(FS_UNMOUNT); ++ test_ret(FS_Q_OVERFLOW); ++ test_ret(FS_IN_IGNORED); ++ test_ret(FS_ISDIR); ++ test_ret(FS_IN_ONESHOT); ++ test_ret(FS_EVENT_ON_CHILD); ++ return ""; ++#undef test_ret ++#else ++ return "??"; ++#endif ++} ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void au_hfsn_free_group(struct fsnotify_group *group) ++{ ++ struct au_br_hfsnotify *hfsn = group->private; ++ ++ /* AuDbg("here\n"); */ ++ kfree(hfsn); ++} ++ ++static int au_hfsn_handle_event(struct fsnotify_group *group, ++ struct inode *inode, ++ struct fsnotify_mark *inode_mark, ++ struct fsnotify_mark *vfsmount_mark, ++ u32 mask, void *data, int data_type, ++ const unsigned char *file_name, u32 cookie) ++{ ++ int err; ++ struct au_hnotify *hnotify; ++ struct inode *h_dir, *h_inode; ++ struct qstr h_child_qstr = QSTR_INIT(file_name, strlen(file_name)); ++ ++ AuDebugOn(data_type != FSNOTIFY_EVENT_INODE); ++ ++ err = 0; ++ /* if FS_UNMOUNT happens, there must be another bug */ ++ AuDebugOn(mask & FS_UNMOUNT); ++ if (mask & (FS_IN_IGNORED | FS_UNMOUNT)) ++ goto out; ++ ++ h_dir = inode; ++ h_inode = NULL; ++#ifdef AuDbgHnotify ++ au_debug_on(); ++ if (1 || h_child_qstr.len != sizeof(AUFS_XINO_FNAME) - 1 ++ || strncmp(h_child_qstr.name, AUFS_XINO_FNAME, h_child_qstr.len)) { ++ AuDbg("i%lu, mask 0x%x %s, hcname %.*s, hi%lu\n", ++ h_dir->i_ino, mask, au_hfsn_name(mask), ++ AuLNPair(&h_child_qstr), h_inode ? h_inode->i_ino : 0); ++ /* WARN_ON(1); */ ++ } ++ au_debug_off(); ++#endif ++ ++ AuDebugOn(!inode_mark); ++ hnotify = container_of(inode_mark, struct au_hnotify, hn_mark); ++ err = au_hnotify(h_dir, hnotify, mask, &h_child_qstr, h_inode); ++ ++out: ++ return err; ++} ++ ++static struct fsnotify_ops au_hfsn_ops = { ++ .handle_event = au_hfsn_handle_event, ++ .free_group_priv = au_hfsn_free_group ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void au_hfsn_fin_br(struct au_branch *br) ++{ ++ struct au_br_hfsnotify *hfsn; ++ ++ hfsn = br->br_hfsn; ++ if (hfsn) { ++ lockdep_off(); ++ fsnotify_put_group(hfsn->hfsn_group); ++ lockdep_on(); ++ } ++} ++ ++static int au_hfsn_init_br(struct au_branch *br, int perm) ++{ ++ int err; ++ struct fsnotify_group *group; ++ struct au_br_hfsnotify *hfsn; ++ ++ err = 0; ++ br->br_hfsn = NULL; ++ if (!au_br_hnotifyable(perm)) ++ goto out; ++ ++ err = -ENOMEM; ++ hfsn = kmalloc(sizeof(*hfsn), GFP_NOFS); ++ if (unlikely(!hfsn)) ++ goto out; ++ ++ err = 0; ++ group = fsnotify_alloc_group(&au_hfsn_ops); ++ if (IS_ERR(group)) { ++ err = PTR_ERR(group); ++ pr_err("fsnotify_alloc_group() failed, %d\n", err); ++ goto out_hfsn; ++ } ++ ++ group->private = hfsn; ++ hfsn->hfsn_group = group; ++ br->br_hfsn = hfsn; ++ goto out; /* success */ ++ ++out_hfsn: ++ kfree(hfsn); ++out: ++ return err; ++} ++ ++static int au_hfsn_reset_br(unsigned int udba, struct au_branch *br, int perm) ++{ ++ int err; ++ ++ err = 0; ++ if (!br->br_hfsn) ++ err = au_hfsn_init_br(br, perm); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void au_hfsn_fin(void) ++{ ++ AuDbg("au_hfsn_ifree %lld\n", (long long)atomic64_read(&au_hfsn_ifree)); ++ wait_event(au_hfsn_wq, !atomic64_read(&au_hfsn_ifree)); ++} ++ ++const struct au_hnotify_op au_hnotify_op = { ++ .ctl = au_hfsn_ctl, ++ .alloc = au_hfsn_alloc, ++ .free = au_hfsn_free, ++ ++ .fin = au_hfsn_fin, ++ ++ .reset_br = au_hfsn_reset_br, ++ .fin_br = au_hfsn_fin_br, ++ .init_br = au_hfsn_init_br ++}; +diff --git a/fs/aufs/hfsplus.c b/fs/aufs/hfsplus.c +new file mode 100644 +index 00000000..f4ed5167 +--- /dev/null ++++ b/fs/aufs/hfsplus.c +@@ -0,0 +1,56 @@ ++/* ++ * Copyright (C) 2010-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * special support for filesystems which aqucires an inode mutex ++ * at final closing a file, eg, hfsplus. ++ * ++ * This trick is very simple and stupid, just to open the file before really ++ * neceeary open to tell hfsplus that this is not the final closing. ++ * The caller should call au_h_open_pre() after acquiring the inode mutex, ++ * and au_h_open_post() after releasing it. ++ */ ++ ++#include "aufs.h" ++ ++struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex, ++ int force_wr) ++{ ++ struct file *h_file; ++ struct dentry *h_dentry; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ AuDebugOn(!h_dentry); ++ AuDebugOn(d_is_negative(h_dentry)); ++ ++ h_file = NULL; ++ if (au_test_hfsplus(h_dentry->d_sb) ++ && d_is_reg(h_dentry)) ++ h_file = au_h_open(dentry, bindex, ++ O_RDONLY | O_NOATIME | O_LARGEFILE, ++ /*file*/NULL, force_wr); ++ return h_file; ++} ++ ++void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex, ++ struct file *h_file) ++{ ++ if (h_file) { ++ fput(h_file); ++ au_sbr_put(dentry->d_sb, bindex); ++ } ++} +diff --git a/fs/aufs/hnotify.c b/fs/aufs/hnotify.c +new file mode 100644 +index 00000000..7dd64918 +--- /dev/null ++++ b/fs/aufs/hnotify.c +@@ -0,0 +1,719 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * abstraction to notify the direct changes on lower directories ++ */ ++ ++#include "aufs.h" ++ ++int au_hn_alloc(struct au_hinode *hinode, struct inode *inode) ++{ ++ int err; ++ struct au_hnotify *hn; ++ ++ err = -ENOMEM; ++ hn = au_cache_alloc_hnotify(); ++ if (hn) { ++ hn->hn_aufs_inode = inode; ++ hinode->hi_notify = hn; ++ err = au_hnotify_op.alloc(hinode); ++ AuTraceErr(err); ++ if (unlikely(err)) { ++ hinode->hi_notify = NULL; ++ au_cache_free_hnotify(hn); ++ /* ++ * The upper dir was removed by udba, but the same named ++ * dir left. In this case, aufs assignes a new inode ++ * number and set the monitor again. ++ * For the lower dir, the old monitnor is still left. ++ */ ++ if (err == -EEXIST) ++ err = 0; ++ } ++ } ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++void au_hn_free(struct au_hinode *hinode) ++{ ++ struct au_hnotify *hn; ++ ++ hn = hinode->hi_notify; ++ if (hn) { ++ hinode->hi_notify = NULL; ++ if (au_hnotify_op.free(hinode, hn)) ++ au_cache_free_hnotify(hn); ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_hn_ctl(struct au_hinode *hinode, int do_set) ++{ ++ if (hinode->hi_notify) ++ au_hnotify_op.ctl(hinode, do_set); ++} ++ ++void au_hn_reset(struct inode *inode, unsigned int flags) ++{ ++ aufs_bindex_t bindex, bbot; ++ struct inode *hi; ++ struct dentry *iwhdentry; ++ ++ bbot = au_ibbot(inode); ++ for (bindex = au_ibtop(inode); bindex <= bbot; bindex++) { ++ hi = au_h_iptr(inode, bindex); ++ if (!hi) ++ continue; ++ ++ /* inode_lock_nested(hi, AuLsc_I_CHILD); */ ++ iwhdentry = au_hi_wh(inode, bindex); ++ if (iwhdentry) ++ dget(iwhdentry); ++ au_igrab(hi); ++ au_set_h_iptr(inode, bindex, NULL, 0); ++ au_set_h_iptr(inode, bindex, au_igrab(hi), ++ flags & ~AuHi_XINO); ++ iput(hi); ++ dput(iwhdentry); ++ /* inode_unlock(hi); */ ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int hn_xino(struct inode *inode, struct inode *h_inode) ++{ ++ int err; ++ aufs_bindex_t bindex, bbot, bfound, btop; ++ struct inode *h_i; ++ ++ err = 0; ++ if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { ++ pr_warn("branch root dir was changed\n"); ++ goto out; ++ } ++ ++ bfound = -1; ++ bbot = au_ibbot(inode); ++ btop = au_ibtop(inode); ++#if 0 /* reserved for future use */ ++ if (bindex == bbot) { ++ /* keep this ino in rename case */ ++ goto out; ++ } ++#endif ++ for (bindex = btop; bindex <= bbot; bindex++) ++ if (au_h_iptr(inode, bindex) == h_inode) { ++ bfound = bindex; ++ break; ++ } ++ if (bfound < 0) ++ goto out; ++ ++ for (bindex = btop; bindex <= bbot; bindex++) { ++ h_i = au_h_iptr(inode, bindex); ++ if (!h_i) ++ continue; ++ ++ err = au_xino_write(inode->i_sb, bindex, h_i->i_ino, /*ino*/0); ++ /* ignore this error */ ++ /* bad action? */ ++ } ++ ++ /* children inode number will be broken */ ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++static int hn_gen_tree(struct dentry *dentry) ++{ ++ int err, i, j, ndentry; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry **dentries; ++ ++ err = au_dpages_init(&dpages, GFP_NOFS); ++ if (unlikely(err)) ++ goto out; ++ err = au_dcsub_pages(&dpages, dentry, NULL, NULL); ++ if (unlikely(err)) ++ goto out_dpages; ++ ++ for (i = 0; i < dpages.ndpage; i++) { ++ dpage = dpages.dpages + i; ++ dentries = dpage->dentries; ++ ndentry = dpage->ndentry; ++ for (j = 0; j < ndentry; j++) { ++ struct dentry *d; ++ ++ d = dentries[j]; ++ if (IS_ROOT(d)) ++ continue; ++ ++ au_digen_dec(d); ++ if (d_really_is_positive(d)) ++ /* todo: reset children xino? ++ cached children only? */ ++ au_iigen_dec(d_inode(d)); ++ } ++ } ++ ++out_dpages: ++ au_dpages_free(&dpages); ++ ++#if 0 ++ /* discard children */ ++ dentry_unhash(dentry); ++ dput(dentry); ++#endif ++out: ++ return err; ++} ++ ++/* ++ * return 0 if processed. ++ */ ++static int hn_gen_by_inode(char *name, unsigned int nlen, struct inode *inode, ++ const unsigned int isdir) ++{ ++ int err; ++ struct dentry *d; ++ struct qstr *dname; ++ ++ err = 1; ++ if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { ++ pr_warn("branch root dir was changed\n"); ++ err = 0; ++ goto out; ++ } ++ ++ if (!isdir) { ++ AuDebugOn(!name); ++ au_iigen_dec(inode); ++ spin_lock(&inode->i_lock); ++ hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) { ++ spin_lock(&d->d_lock); ++ dname = &d->d_name; ++ if (dname->len != nlen ++ && memcmp(dname->name, name, nlen)) { ++ spin_unlock(&d->d_lock); ++ continue; ++ } ++ err = 0; ++ au_digen_dec(d); ++ spin_unlock(&d->d_lock); ++ break; ++ } ++ spin_unlock(&inode->i_lock); ++ } else { ++ au_fset_si(au_sbi(inode->i_sb), FAILED_REFRESH_DIR); ++ d = d_find_any_alias(inode); ++ if (!d) { ++ au_iigen_dec(inode); ++ goto out; ++ } ++ ++ spin_lock(&d->d_lock); ++ dname = &d->d_name; ++ if (dname->len == nlen && !memcmp(dname->name, name, nlen)) { ++ spin_unlock(&d->d_lock); ++ err = hn_gen_tree(d); ++ spin_lock(&d->d_lock); ++ } ++ spin_unlock(&d->d_lock); ++ dput(d); ++ } ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++static int hn_gen_by_name(struct dentry *dentry, const unsigned int isdir) ++{ ++ int err; ++ ++ if (IS_ROOT(dentry)) { ++ pr_warn("branch root dir was changed\n"); ++ return 0; ++ } ++ ++ err = 0; ++ if (!isdir) { ++ au_digen_dec(dentry); ++ if (d_really_is_positive(dentry)) ++ au_iigen_dec(d_inode(dentry)); ++ } else { ++ au_fset_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR); ++ if (d_really_is_positive(dentry)) ++ err = hn_gen_tree(dentry); ++ } ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* hnotify job flags */ ++#define AuHnJob_XINO0 1 ++#define AuHnJob_GEN (1 << 1) ++#define AuHnJob_DIRENT (1 << 2) ++#define AuHnJob_ISDIR (1 << 3) ++#define AuHnJob_TRYXINO0 (1 << 4) ++#define AuHnJob_MNTPNT (1 << 5) ++#define au_ftest_hnjob(flags, name) ((flags) & AuHnJob_##name) ++#define au_fset_hnjob(flags, name) \ ++ do { (flags) |= AuHnJob_##name; } while (0) ++#define au_fclr_hnjob(flags, name) \ ++ do { (flags) &= ~AuHnJob_##name; } while (0) ++ ++enum { ++ AuHn_CHILD, ++ AuHn_PARENT, ++ AuHnLast ++}; ++ ++struct au_hnotify_args { ++ struct inode *h_dir, *dir, *h_child_inode; ++ u32 mask; ++ unsigned int flags[AuHnLast]; ++ unsigned int h_child_nlen; ++ char h_child_name[]; ++}; ++ ++struct hn_job_args { ++ unsigned int flags; ++ struct inode *inode, *h_inode, *dir, *h_dir; ++ struct dentry *dentry; ++ char *h_name; ++ int h_nlen; ++}; ++ ++static int hn_job(struct hn_job_args *a) ++{ ++ const unsigned int isdir = au_ftest_hnjob(a->flags, ISDIR); ++ int e; ++ ++ /* reset xino */ ++ if (au_ftest_hnjob(a->flags, XINO0) && a->inode) ++ hn_xino(a->inode, a->h_inode); /* ignore this error */ ++ ++ if (au_ftest_hnjob(a->flags, TRYXINO0) ++ && a->inode ++ && a->h_inode) { ++ vfsub_inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD); ++ if (!a->h_inode->i_nlink ++ && !(a->h_inode->i_state & I_LINKABLE)) ++ hn_xino(a->inode, a->h_inode); /* ignore this error */ ++ inode_unlock_shared(a->h_inode); ++ } ++ ++ /* make the generation obsolete */ ++ if (au_ftest_hnjob(a->flags, GEN)) { ++ e = -1; ++ if (a->inode) ++ e = hn_gen_by_inode(a->h_name, a->h_nlen, a->inode, ++ isdir); ++ if (e && a->dentry) ++ hn_gen_by_name(a->dentry, isdir); ++ /* ignore this error */ ++ } ++ ++ /* make dir entries obsolete */ ++ if (au_ftest_hnjob(a->flags, DIRENT) && a->inode) { ++ struct au_vdir *vdir; ++ ++ vdir = au_ivdir(a->inode); ++ if (vdir) ++ vdir->vd_jiffy = 0; ++ /* IMustLock(a->inode); */ ++ /* a->inode->i_version++; */ ++ } ++ ++ /* can do nothing but warn */ ++ if (au_ftest_hnjob(a->flags, MNTPNT) ++ && a->dentry ++ && d_mountpoint(a->dentry)) ++ pr_warn("mount-point %pd is removed or renamed\n", a->dentry); ++ ++ return 0; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct dentry *lookup_wlock_by_name(char *name, unsigned int nlen, ++ struct inode *dir) ++{ ++ struct dentry *dentry, *d, *parent; ++ struct qstr *dname; ++ ++ parent = d_find_any_alias(dir); ++ if (!parent) ++ return NULL; ++ ++ dentry = NULL; ++ spin_lock(&parent->d_lock); ++ list_for_each_entry(d, &parent->d_subdirs, d_child) { ++ /* AuDbg("%pd\n", d); */ ++ spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); ++ dname = &d->d_name; ++ if (dname->len != nlen || memcmp(dname->name, name, nlen)) ++ goto cont_unlock; ++ if (au_di(d)) ++ au_digen_dec(d); ++ else ++ goto cont_unlock; ++ if (au_dcount(d) > 0) { ++ dentry = dget_dlock(d); ++ spin_unlock(&d->d_lock); ++ break; ++ } ++ ++cont_unlock: ++ spin_unlock(&d->d_lock); ++ } ++ spin_unlock(&parent->d_lock); ++ dput(parent); ++ ++ if (dentry) ++ di_write_lock_child(dentry); ++ ++ return dentry; ++} ++ ++static struct inode *lookup_wlock_by_ino(struct super_block *sb, ++ aufs_bindex_t bindex, ino_t h_ino) ++{ ++ struct inode *inode; ++ ino_t ino; ++ int err; ++ ++ inode = NULL; ++ err = au_xino_read(sb, bindex, h_ino, &ino); ++ if (!err && ino) ++ inode = ilookup(sb, ino); ++ if (!inode) ++ goto out; ++ ++ if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { ++ pr_warn("wrong root branch\n"); ++ iput(inode); ++ inode = NULL; ++ goto out; ++ } ++ ++ ii_write_lock_child(inode); ++ ++out: ++ return inode; ++} ++ ++static void au_hn_bh(void *_args) ++{ ++ struct au_hnotify_args *a = _args; ++ struct super_block *sb; ++ aufs_bindex_t bindex, bbot, bfound; ++ unsigned char xino, try_iput; ++ int err; ++ struct inode *inode; ++ ino_t h_ino; ++ struct hn_job_args args; ++ struct dentry *dentry; ++ struct au_sbinfo *sbinfo; ++ ++ AuDebugOn(!_args); ++ AuDebugOn(!a->h_dir); ++ AuDebugOn(!a->dir); ++ AuDebugOn(!a->mask); ++ AuDbg("mask 0x%x, i%lu, hi%lu, hci%lu\n", ++ a->mask, a->dir->i_ino, a->h_dir->i_ino, ++ a->h_child_inode ? a->h_child_inode->i_ino : 0); ++ ++ inode = NULL; ++ dentry = NULL; ++ /* ++ * do not lock a->dir->i_mutex here ++ * because of d_revalidate() may cause a deadlock. ++ */ ++ sb = a->dir->i_sb; ++ AuDebugOn(!sb); ++ sbinfo = au_sbi(sb); ++ AuDebugOn(!sbinfo); ++ si_write_lock(sb, AuLock_NOPLMW); ++ ++ if (au_opt_test(sbinfo->si_mntflags, DIRREN)) ++ switch (a->mask & FS_EVENTS_POSS_ON_CHILD) { ++ case FS_MOVED_FROM: ++ case FS_MOVED_TO: ++ AuWarn1("DIRREN with UDBA may not work correctly " ++ "for the direct rename(2)\n"); ++ } ++ ++ ii_read_lock_parent(a->dir); ++ bfound = -1; ++ bbot = au_ibbot(a->dir); ++ for (bindex = au_ibtop(a->dir); bindex <= bbot; bindex++) ++ if (au_h_iptr(a->dir, bindex) == a->h_dir) { ++ bfound = bindex; ++ break; ++ } ++ ii_read_unlock(a->dir); ++ if (unlikely(bfound < 0)) ++ goto out; ++ ++ xino = !!au_opt_test(au_mntflags(sb), XINO); ++ h_ino = 0; ++ if (a->h_child_inode) ++ h_ino = a->h_child_inode->i_ino; ++ ++ if (a->h_child_nlen ++ && (au_ftest_hnjob(a->flags[AuHn_CHILD], GEN) ++ || au_ftest_hnjob(a->flags[AuHn_CHILD], MNTPNT))) ++ dentry = lookup_wlock_by_name(a->h_child_name, a->h_child_nlen, ++ a->dir); ++ try_iput = 0; ++ if (dentry && d_really_is_positive(dentry)) ++ inode = d_inode(dentry); ++ if (xino && !inode && h_ino ++ && (au_ftest_hnjob(a->flags[AuHn_CHILD], XINO0) ++ || au_ftest_hnjob(a->flags[AuHn_CHILD], TRYXINO0) ++ || au_ftest_hnjob(a->flags[AuHn_CHILD], GEN))) { ++ inode = lookup_wlock_by_ino(sb, bfound, h_ino); ++ try_iput = 1; ++ } ++ ++ args.flags = a->flags[AuHn_CHILD]; ++ args.dentry = dentry; ++ args.inode = inode; ++ args.h_inode = a->h_child_inode; ++ args.dir = a->dir; ++ args.h_dir = a->h_dir; ++ args.h_name = a->h_child_name; ++ args.h_nlen = a->h_child_nlen; ++ err = hn_job(&args); ++ if (dentry) { ++ if (au_di(dentry)) ++ di_write_unlock(dentry); ++ dput(dentry); ++ } ++ if (inode && try_iput) { ++ ii_write_unlock(inode); ++ iput(inode); ++ } ++ ++ ii_write_lock_parent(a->dir); ++ args.flags = a->flags[AuHn_PARENT]; ++ args.dentry = NULL; ++ args.inode = a->dir; ++ args.h_inode = a->h_dir; ++ args.dir = NULL; ++ args.h_dir = NULL; ++ args.h_name = NULL; ++ args.h_nlen = 0; ++ err = hn_job(&args); ++ ii_write_unlock(a->dir); ++ ++out: ++ iput(a->h_child_inode); ++ iput(a->h_dir); ++ iput(a->dir); ++ si_write_unlock(sb); ++ au_nwt_done(&sbinfo->si_nowait); ++ kfree(a); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_hnotify(struct inode *h_dir, struct au_hnotify *hnotify, u32 mask, ++ struct qstr *h_child_qstr, struct inode *h_child_inode) ++{ ++ int err, len; ++ unsigned int flags[AuHnLast], f; ++ unsigned char isdir, isroot, wh; ++ struct inode *dir; ++ struct au_hnotify_args *args; ++ char *p, *h_child_name; ++ ++ err = 0; ++ AuDebugOn(!hnotify || !hnotify->hn_aufs_inode); ++ dir = igrab(hnotify->hn_aufs_inode); ++ if (!dir) ++ goto out; ++ ++ isroot = (dir->i_ino == AUFS_ROOT_INO); ++ wh = 0; ++ h_child_name = (void *)h_child_qstr->name; ++ len = h_child_qstr->len; ++ if (h_child_name) { ++ if (len > AUFS_WH_PFX_LEN ++ && !memcmp(h_child_name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { ++ h_child_name += AUFS_WH_PFX_LEN; ++ len -= AUFS_WH_PFX_LEN; ++ wh = 1; ++ } ++ } ++ ++ isdir = 0; ++ if (h_child_inode) ++ isdir = !!S_ISDIR(h_child_inode->i_mode); ++ flags[AuHn_PARENT] = AuHnJob_ISDIR; ++ flags[AuHn_CHILD] = 0; ++ if (isdir) ++ flags[AuHn_CHILD] = AuHnJob_ISDIR; ++ au_fset_hnjob(flags[AuHn_PARENT], DIRENT); ++ au_fset_hnjob(flags[AuHn_CHILD], GEN); ++ switch (mask & FS_EVENTS_POSS_ON_CHILD) { ++ case FS_MOVED_FROM: ++ case FS_MOVED_TO: ++ au_fset_hnjob(flags[AuHn_CHILD], XINO0); ++ au_fset_hnjob(flags[AuHn_CHILD], MNTPNT); ++ /*FALLTHROUGH*/ ++ case FS_CREATE: ++ AuDebugOn(!h_child_name); ++ break; ++ ++ case FS_DELETE: ++ /* ++ * aufs never be able to get this child inode. ++ * revalidation should be in d_revalidate() ++ * by checking i_nlink, i_generation or d_unhashed(). ++ */ ++ AuDebugOn(!h_child_name); ++ au_fset_hnjob(flags[AuHn_CHILD], TRYXINO0); ++ au_fset_hnjob(flags[AuHn_CHILD], MNTPNT); ++ break; ++ ++ default: ++ AuDebugOn(1); ++ } ++ ++ if (wh) ++ h_child_inode = NULL; ++ ++ err = -ENOMEM; ++ /* iput() and kfree() will be called in au_hnotify() */ ++ args = kmalloc(sizeof(*args) + len + 1, GFP_NOFS); ++ if (unlikely(!args)) { ++ AuErr1("no memory\n"); ++ iput(dir); ++ goto out; ++ } ++ args->flags[AuHn_PARENT] = flags[AuHn_PARENT]; ++ args->flags[AuHn_CHILD] = flags[AuHn_CHILD]; ++ args->mask = mask; ++ args->dir = dir; ++ args->h_dir = igrab(h_dir); ++ if (h_child_inode) ++ h_child_inode = igrab(h_child_inode); /* can be NULL */ ++ args->h_child_inode = h_child_inode; ++ args->h_child_nlen = len; ++ if (len) { ++ p = (void *)args; ++ p += sizeof(*args); ++ memcpy(p, h_child_name, len); ++ p[len] = 0; ++ } ++ ++ /* NFS fires the event for silly-renamed one from kworker */ ++ f = 0; ++ if (!dir->i_nlink ++ || (au_test_nfs(h_dir->i_sb) && (mask & FS_DELETE))) ++ f = AuWkq_NEST; ++ err = au_wkq_nowait(au_hn_bh, args, dir->i_sb, f); ++ if (unlikely(err)) { ++ pr_err("wkq %d\n", err); ++ iput(args->h_child_inode); ++ iput(args->h_dir); ++ iput(args->dir); ++ kfree(args); ++ } ++ ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm) ++{ ++ int err; ++ ++ AuDebugOn(!(udba & AuOptMask_UDBA)); ++ ++ err = 0; ++ if (au_hnotify_op.reset_br) ++ err = au_hnotify_op.reset_br(udba, br, perm); ++ ++ return err; ++} ++ ++int au_hnotify_init_br(struct au_branch *br, int perm) ++{ ++ int err; ++ ++ err = 0; ++ if (au_hnotify_op.init_br) ++ err = au_hnotify_op.init_br(br, perm); ++ ++ return err; ++} ++ ++void au_hnotify_fin_br(struct au_branch *br) ++{ ++ if (au_hnotify_op.fin_br) ++ au_hnotify_op.fin_br(br); ++} ++ ++static void au_hn_destroy_cache(void) ++{ ++ kmem_cache_destroy(au_cache[AuCache_HNOTIFY]); ++ au_cache[AuCache_HNOTIFY] = NULL; ++} ++ ++int __init au_hnotify_init(void) ++{ ++ int err; ++ ++ err = -ENOMEM; ++ au_cache[AuCache_HNOTIFY] = AuCache(au_hnotify); ++ if (au_cache[AuCache_HNOTIFY]) { ++ err = 0; ++ if (au_hnotify_op.init) ++ err = au_hnotify_op.init(); ++ if (unlikely(err)) ++ au_hn_destroy_cache(); ++ } ++ AuTraceErr(err); ++ return err; ++} ++ ++void au_hnotify_fin(void) ++{ ++ if (au_hnotify_op.fin) ++ au_hnotify_op.fin(); ++ ++ /* cf. au_cache_fin() */ ++ if (au_cache[AuCache_HNOTIFY]) ++ au_hn_destroy_cache(); ++} +diff --git a/fs/aufs/i_op.c b/fs/aufs/i_op.c +new file mode 100644 +index 00000000..7de89636 +--- /dev/null ++++ b/fs/aufs/i_op.c +@@ -0,0 +1,1459 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * inode operations (except add/del/rename) ++ */ ++ ++#include ++#include ++#include ++#include ++#include "aufs.h" ++ ++static int h_permission(struct inode *h_inode, int mask, ++ struct path *h_path, int brperm) ++{ ++ int err; ++ const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); ++ ++ err = -EPERM; ++ if (write_mask && IS_IMMUTABLE(h_inode)) ++ goto out; ++ ++ err = -EACCES; ++ if (((mask & MAY_EXEC) ++ && S_ISREG(h_inode->i_mode) ++ && (path_noexec(h_path) ++ || !(h_inode->i_mode & 0111)))) ++ goto out; ++ ++ /* ++ * - skip the lower fs test in the case of write to ro branch. ++ * - nfs dir permission write check is optimized, but a policy for ++ * link/rename requires a real check. ++ * - nfs always sets MS_POSIXACL regardless its mount option 'noacl.' ++ * in this case, generic_permission() returns -EOPNOTSUPP. ++ */ ++ if ((write_mask && !au_br_writable(brperm)) ++ || (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode) ++ && write_mask && !(mask & MAY_READ)) ++ || !h_inode->i_op->permission) { ++ /* AuLabel(generic_permission); */ ++ /* AuDbg("get_acl %pf\n", h_inode->i_op->get_acl); */ ++ err = generic_permission(h_inode, mask); ++ if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode)) ++ err = h_inode->i_op->permission(h_inode, mask); ++ AuTraceErr(err); ++ } else { ++ /* AuLabel(h_inode->permission); */ ++ err = h_inode->i_op->permission(h_inode, mask); ++ AuTraceErr(err); ++ } ++ ++ if (!err) ++ err = devcgroup_inode_permission(h_inode, mask); ++ if (!err) ++ err = security_inode_permission(h_inode, mask); ++ ++#if 0 ++ if (!err) { ++ /* todo: do we need to call ima_path_check()? */ ++ struct path h_path = { ++ .dentry = ++ .mnt = h_mnt ++ }; ++ err = ima_path_check(&h_path, ++ mask & (MAY_READ | MAY_WRITE | MAY_EXEC), ++ IMA_COUNT_LEAVE); ++ } ++#endif ++ ++out: ++ return err; ++} ++ ++static int aufs_permission(struct inode *inode, int mask) ++{ ++ int err; ++ aufs_bindex_t bindex, bbot; ++ const unsigned char isdir = !!S_ISDIR(inode->i_mode), ++ write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); ++ struct inode *h_inode; ++ struct super_block *sb; ++ struct au_branch *br; ++ ++ /* todo: support rcu-walk? */ ++ if (mask & MAY_NOT_BLOCK) ++ return -ECHILD; ++ ++ sb = inode->i_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ ii_read_lock_child(inode); ++#if 0 ++ err = au_iigen_test(inode, au_sigen(sb)); ++ if (unlikely(err)) ++ goto out; ++#endif ++ ++ if (!isdir ++ || write_mask ++ || au_opt_test(au_mntflags(sb), DIRPERM1)) { ++ err = au_busy_or_stale(); ++ h_inode = au_h_iptr(inode, au_ibtop(inode)); ++ if (unlikely(!h_inode ++ || (h_inode->i_mode & S_IFMT) ++ != (inode->i_mode & S_IFMT))) ++ goto out; ++ ++ err = 0; ++ bindex = au_ibtop(inode); ++ br = au_sbr(sb, bindex); ++ err = h_permission(h_inode, mask, &br->br_path, br->br_perm); ++ if (write_mask ++ && !err ++ && !special_file(h_inode->i_mode)) { ++ /* test whether the upper writable branch exists */ ++ err = -EROFS; ++ for (; bindex >= 0; bindex--) ++ if (!au_br_rdonly(au_sbr(sb, bindex))) { ++ err = 0; ++ break; ++ } ++ } ++ goto out; ++ } ++ ++ /* non-write to dir */ ++ err = 0; ++ bbot = au_ibbot(inode); ++ for (bindex = au_ibtop(inode); !err && bindex <= bbot; bindex++) { ++ h_inode = au_h_iptr(inode, bindex); ++ if (h_inode) { ++ err = au_busy_or_stale(); ++ if (unlikely(!S_ISDIR(h_inode->i_mode))) ++ break; ++ ++ br = au_sbr(sb, bindex); ++ err = h_permission(h_inode, mask, &br->br_path, ++ br->br_perm); ++ } ++ } ++ ++out: ++ ii_read_unlock(inode); ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry, ++ unsigned int flags) ++{ ++ struct dentry *ret, *parent; ++ struct inode *inode; ++ struct super_block *sb; ++ int err, npositive; ++ ++ IMustLock(dir); ++ ++ /* todo: support rcu-walk? */ ++ ret = ERR_PTR(-ECHILD); ++ if (flags & LOOKUP_RCU) ++ goto out; ++ ++ ret = ERR_PTR(-ENAMETOOLONG); ++ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) ++ goto out; ++ ++ sb = dir->i_sb; ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ ret = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out; ++ ++ err = au_di_init(dentry); ++ ret = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out_si; ++ ++ inode = NULL; ++ npositive = 0; /* suppress a warning */ ++ parent = dentry->d_parent; /* dir inode is locked */ ++ di_read_lock_parent(parent, AuLock_IR); ++ err = au_alive_dir(parent); ++ if (!err) ++ err = au_digen_test(parent, au_sigen(sb)); ++ if (!err) { ++ /* regardless LOOKUP_CREATE, always ALLOW_NEG */ ++ npositive = au_lkup_dentry(dentry, au_dbtop(parent), ++ AuLkup_ALLOW_NEG); ++ err = npositive; ++ } ++ di_read_unlock(parent, AuLock_IR); ++ ret = ERR_PTR(err); ++ if (unlikely(err < 0)) ++ goto out_unlock; ++ ++ if (npositive) { ++ inode = au_new_inode(dentry, /*must_new*/0); ++ if (IS_ERR(inode)) { ++ ret = (void *)inode; ++ inode = NULL; ++ goto out_unlock; ++ } ++ } ++ ++ if (inode) ++ atomic_inc(&inode->i_count); ++ ret = d_splice_alias(inode, dentry); ++#if 0 ++ if (unlikely(d_need_lookup(dentry))) { ++ spin_lock(&dentry->d_lock); ++ dentry->d_flags &= ~DCACHE_NEED_LOOKUP; ++ spin_unlock(&dentry->d_lock); ++ } else ++#endif ++ if (inode) { ++ if (!IS_ERR(ret)) { ++ iput(inode); ++ if (ret && ret != dentry) ++ ii_write_unlock(inode); ++ } else { ++ ii_write_unlock(inode); ++ iput(inode); ++ inode = NULL; ++ } ++ } ++ ++out_unlock: ++ di_write_unlock(dentry); ++out_si: ++ si_read_unlock(sb); ++out: ++ return ret; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct aopen_node { ++ struct hlist_bl_node hblist; ++ struct file *file, *h_file; ++}; ++ ++static int au_do_aopen(struct inode *inode, struct file *file) ++{ ++ struct hlist_bl_head *aopen; ++ struct hlist_bl_node *pos; ++ struct aopen_node *node; ++ struct au_do_open_args args = { ++ .aopen = 1, ++ .open = au_do_open_nondir ++ }; ++ ++ aopen = &au_sbi(inode->i_sb)->si_aopen; ++ hlist_bl_lock(aopen); ++ hlist_bl_for_each_entry(node, pos, aopen, hblist) ++ if (node->file == file) { ++ args.h_file = node->h_file; ++ break; ++ } ++ hlist_bl_unlock(aopen); ++ /* AuDebugOn(!args.h_file); */ ++ ++ return au_do_open(file, &args); ++} ++ ++static int aufs_atomic_open(struct inode *dir, struct dentry *dentry, ++ struct file *file, unsigned int open_flag, ++ umode_t create_mode, int *opened) ++{ ++ int err, unlocked, h_opened = *opened; ++ unsigned int lkup_flags; ++ struct dentry *parent, *d; ++ struct hlist_bl_head *aopen; ++ struct vfsub_aopen_args args = { ++ .open_flag = open_flag, ++ .create_mode = create_mode, ++ .opened = &h_opened ++ }; ++ struct aopen_node aopen_node = { ++ .file = file ++ }; ++ ++ IMustLock(dir); ++ AuDbg("open_flag 0%o\n", open_flag); ++ AuDbgDentry(dentry); ++ ++ err = 0; ++ if (!au_di(dentry)) { ++ lkup_flags = LOOKUP_OPEN; ++ if (open_flag & O_CREAT) ++ lkup_flags |= LOOKUP_CREATE; ++ d = aufs_lookup(dir, dentry, lkup_flags); ++ if (IS_ERR(d)) { ++ err = PTR_ERR(d); ++ AuTraceErr(err); ++ goto out; ++ } else if (d) { ++ /* ++ * obsoleted dentry found. ++ * another error will be returned later. ++ */ ++ d_drop(d); ++ AuDbgDentry(d); ++ dput(d); ++ } ++ AuDbgDentry(dentry); ++ } ++ ++ if (d_is_positive(dentry) ++ || d_unhashed(dentry) ++ || d_unlinked(dentry) ++ || !(open_flag & O_CREAT)) ++ goto out_no_open; ++ ++ unlocked = 0; ++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN); ++ if (unlikely(err)) ++ goto out; ++ ++ parent = dentry->d_parent; /* dir is locked */ ++ di_write_lock_parent(parent); ++ err = au_lkup_dentry(dentry, /*btop*/0, AuLkup_ALLOW_NEG); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ AuDbgDentry(dentry); ++ if (d_is_positive(dentry)) ++ goto out_unlock; ++ ++ args.file = get_empty_filp(); ++ err = PTR_ERR(args.file); ++ if (IS_ERR(args.file)) ++ goto out_unlock; ++ ++ args.file->f_flags = file->f_flags; ++ err = au_aopen_or_create(dir, dentry, &args); ++ AuTraceErr(err); ++ AuDbgFile(args.file); ++ if (unlikely(err < 0)) { ++ if (h_opened & FILE_OPENED) ++ fput(args.file); ++ else ++ put_filp(args.file); ++ goto out_unlock; ++ } ++ di_write_unlock(parent); ++ di_write_unlock(dentry); ++ unlocked = 1; ++ ++ /* some filesystems don't set FILE_CREATED while succeeded? */ ++ *opened |= FILE_CREATED; ++ if (h_opened & FILE_OPENED) ++ aopen_node.h_file = args.file; ++ else { ++ put_filp(args.file); ++ args.file = NULL; ++ } ++ aopen = &au_sbi(dir->i_sb)->si_aopen; ++ au_hbl_add(&aopen_node.hblist, aopen); ++ err = finish_open(file, dentry, au_do_aopen, opened); ++ au_hbl_del(&aopen_node.hblist, aopen); ++ AuTraceErr(err); ++ AuDbgFile(file); ++ if (aopen_node.h_file) ++ fput(aopen_node.h_file); ++ ++out_unlock: ++ if (unlocked) ++ si_read_unlock(dentry->d_sb); ++ else { ++ di_write_unlock(parent); ++ aufs_read_unlock(dentry, AuLock_DW); ++ } ++ AuDbgDentry(dentry); ++ if (unlikely(err < 0)) ++ goto out; ++out_no_open: ++ if (err >= 0 && !(*opened & FILE_CREATED)) { ++ AuLabel(out_no_open); ++ dget(dentry); ++ err = finish_no_open(file, dentry); ++ } ++out: ++ AuDbg("%pd%s%s\n", dentry, ++ (*opened & FILE_CREATED) ? " created" : "", ++ (*opened & FILE_OPENED) ? " opened" : ""); ++ AuTraceErr(err); ++ return err; ++} ++ ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_wr_dir_cpup(struct dentry *dentry, struct dentry *parent, ++ const unsigned char add_entry, aufs_bindex_t bcpup, ++ aufs_bindex_t btop) ++{ ++ int err; ++ struct dentry *h_parent; ++ struct inode *h_dir; ++ ++ if (add_entry) ++ IMustLock(d_inode(parent)); ++ else ++ di_write_lock_parent(parent); ++ ++ err = 0; ++ if (!au_h_dptr(parent, bcpup)) { ++ if (btop > bcpup) ++ err = au_cpup_dirs(dentry, bcpup); ++ else if (btop < bcpup) ++ err = au_cpdown_dirs(dentry, bcpup); ++ else ++ BUG(); ++ } ++ if (!err && add_entry && !au_ftest_wrdir(add_entry, TMPFILE)) { ++ h_parent = au_h_dptr(parent, bcpup); ++ h_dir = d_inode(h_parent); ++ vfsub_inode_lock_shared_nested(h_dir, AuLsc_I_PARENT); ++ err = au_lkup_neg(dentry, bcpup, /*wh*/0); ++ /* todo: no unlock here */ ++ inode_unlock_shared(h_dir); ++ ++ AuDbg("bcpup %d\n", bcpup); ++ if (!err) { ++ if (d_really_is_negative(dentry)) ++ au_set_h_dptr(dentry, btop, NULL); ++ au_update_dbrange(dentry, /*do_put_zero*/0); ++ } ++ } ++ ++ if (!add_entry) ++ di_write_unlock(parent); ++ if (!err) ++ err = bcpup; /* success */ ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ++ * decide the branch and the parent dir where we will create a new entry. ++ * returns new bindex or an error. ++ * copyup the parent dir if needed. ++ */ ++int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry, ++ struct au_wr_dir_args *args) ++{ ++ int err; ++ unsigned int flags; ++ aufs_bindex_t bcpup, btop, src_btop; ++ const unsigned char add_entry ++ = au_ftest_wrdir(args->flags, ADD_ENTRY) ++ | au_ftest_wrdir(args->flags, TMPFILE); ++ struct super_block *sb; ++ struct dentry *parent; ++ struct au_sbinfo *sbinfo; ++ ++ sb = dentry->d_sb; ++ sbinfo = au_sbi(sb); ++ parent = dget_parent(dentry); ++ btop = au_dbtop(dentry); ++ bcpup = btop; ++ if (args->force_btgt < 0) { ++ if (src_dentry) { ++ src_btop = au_dbtop(src_dentry); ++ if (src_btop < btop) ++ bcpup = src_btop; ++ } else if (add_entry) { ++ flags = 0; ++ if (au_ftest_wrdir(args->flags, ISDIR)) ++ au_fset_wbr(flags, DIR); ++ err = AuWbrCreate(sbinfo, dentry, flags); ++ bcpup = err; ++ } ++ ++ if (bcpup < 0 || au_test_ro(sb, bcpup, d_inode(dentry))) { ++ if (add_entry) ++ err = AuWbrCopyup(sbinfo, dentry); ++ else { ++ if (!IS_ROOT(dentry)) { ++ di_read_lock_parent(parent, !AuLock_IR); ++ err = AuWbrCopyup(sbinfo, dentry); ++ di_read_unlock(parent, !AuLock_IR); ++ } else ++ err = AuWbrCopyup(sbinfo, dentry); ++ } ++ bcpup = err; ++ if (unlikely(err < 0)) ++ goto out; ++ } ++ } else { ++ bcpup = args->force_btgt; ++ AuDebugOn(au_test_ro(sb, bcpup, d_inode(dentry))); ++ } ++ ++ AuDbg("btop %d, bcpup %d\n", btop, bcpup); ++ err = bcpup; ++ if (bcpup == btop) ++ goto out; /* success */ ++ ++ /* copyup the new parent into the branch we process */ ++ err = au_wr_dir_cpup(dentry, parent, add_entry, bcpup, btop); ++ if (err >= 0) { ++ if (d_really_is_negative(dentry)) { ++ au_set_h_dptr(dentry, btop, NULL); ++ au_set_dbtop(dentry, bcpup); ++ au_set_dbbot(dentry, bcpup); ++ } ++ AuDebugOn(add_entry ++ && !au_ftest_wrdir(args->flags, TMPFILE) ++ && !au_h_dptr(dentry, bcpup)); ++ } ++ ++out: ++ dput(parent); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_pin_hdir_unlock(struct au_pin *p) ++{ ++ if (p->hdir) ++ au_hn_inode_unlock(p->hdir); ++} ++ ++int au_pin_hdir_lock(struct au_pin *p) ++{ ++ int err; ++ ++ err = 0; ++ if (!p->hdir) ++ goto out; ++ ++ /* even if an error happens later, keep this lock */ ++ au_hn_inode_lock_nested(p->hdir, p->lsc_hi); ++ ++ err = -EBUSY; ++ if (unlikely(p->hdir->hi_inode != d_inode(p->h_parent))) ++ goto out; ++ ++ err = 0; ++ if (p->h_dentry) ++ err = au_h_verify(p->h_dentry, p->udba, p->hdir->hi_inode, ++ p->h_parent, p->br); ++ ++out: ++ return err; ++} ++ ++int au_pin_hdir_relock(struct au_pin *p) ++{ ++ int err, i; ++ struct inode *h_i; ++ struct dentry *h_d[] = { ++ p->h_dentry, ++ p->h_parent ++ }; ++ ++ err = au_pin_hdir_lock(p); ++ if (unlikely(err)) ++ goto out; ++ ++ for (i = 0; !err && i < sizeof(h_d)/sizeof(*h_d); i++) { ++ if (!h_d[i]) ++ continue; ++ if (d_is_positive(h_d[i])) { ++ h_i = d_inode(h_d[i]); ++ err = !h_i->i_nlink; ++ } ++ } ++ ++out: ++ return err; ++} ++ ++static void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task) ++{ ++#if !defined(CONFIG_RWSEM_GENERIC_SPINLOCK) && defined(CONFIG_RWSEM_SPIN_ON_OWNER) ++ p->hdir->hi_inode->i_rwsem.owner = task; ++#endif ++} ++ ++void au_pin_hdir_acquire_nest(struct au_pin *p) ++{ ++ if (p->hdir) { ++ rwsem_acquire_nest(&p->hdir->hi_inode->i_rwsem.dep_map, ++ p->lsc_hi, 0, NULL, _RET_IP_); ++ au_pin_hdir_set_owner(p, current); ++ } ++} ++ ++void au_pin_hdir_release(struct au_pin *p) ++{ ++ if (p->hdir) { ++ au_pin_hdir_set_owner(p, p->task); ++ rwsem_release(&p->hdir->hi_inode->i_rwsem.dep_map, 1, _RET_IP_); ++ } ++} ++ ++struct dentry *au_pinned_h_parent(struct au_pin *pin) ++{ ++ if (pin && pin->parent) ++ return au_h_dptr(pin->parent, pin->bindex); ++ return NULL; ++} ++ ++void au_unpin(struct au_pin *p) ++{ ++ if (p->hdir) ++ au_pin_hdir_unlock(p); ++ if (p->h_mnt && au_ftest_pin(p->flags, MNT_WRITE)) ++ vfsub_mnt_drop_write(p->h_mnt); ++ if (!p->hdir) ++ return; ++ ++ if (!au_ftest_pin(p->flags, DI_LOCKED)) ++ di_read_unlock(p->parent, AuLock_IR); ++ iput(p->hdir->hi_inode); ++ dput(p->parent); ++ p->parent = NULL; ++ p->hdir = NULL; ++ p->h_mnt = NULL; ++ /* do not clear p->task */ ++} ++ ++int au_do_pin(struct au_pin *p) ++{ ++ int err; ++ struct super_block *sb; ++ struct inode *h_dir; ++ ++ err = 0; ++ sb = p->dentry->d_sb; ++ p->br = au_sbr(sb, p->bindex); ++ if (IS_ROOT(p->dentry)) { ++ if (au_ftest_pin(p->flags, MNT_WRITE)) { ++ p->h_mnt = au_br_mnt(p->br); ++ err = vfsub_mnt_want_write(p->h_mnt); ++ if (unlikely(err)) { ++ au_fclr_pin(p->flags, MNT_WRITE); ++ goto out_err; ++ } ++ } ++ goto out; ++ } ++ ++ p->h_dentry = NULL; ++ if (p->bindex <= au_dbbot(p->dentry)) ++ p->h_dentry = au_h_dptr(p->dentry, p->bindex); ++ ++ p->parent = dget_parent(p->dentry); ++ if (!au_ftest_pin(p->flags, DI_LOCKED)) ++ di_read_lock(p->parent, AuLock_IR, p->lsc_di); ++ ++ h_dir = NULL; ++ p->h_parent = au_h_dptr(p->parent, p->bindex); ++ p->hdir = au_hi(d_inode(p->parent), p->bindex); ++ if (p->hdir) ++ h_dir = p->hdir->hi_inode; ++ ++ /* ++ * udba case, or ++ * if DI_LOCKED is not set, then p->parent may be different ++ * and h_parent can be NULL. ++ */ ++ if (unlikely(!p->hdir || !h_dir || !p->h_parent)) { ++ err = -EBUSY; ++ if (!au_ftest_pin(p->flags, DI_LOCKED)) ++ di_read_unlock(p->parent, AuLock_IR); ++ dput(p->parent); ++ p->parent = NULL; ++ goto out_err; ++ } ++ ++ if (au_ftest_pin(p->flags, MNT_WRITE)) { ++ p->h_mnt = au_br_mnt(p->br); ++ err = vfsub_mnt_want_write(p->h_mnt); ++ if (unlikely(err)) { ++ au_fclr_pin(p->flags, MNT_WRITE); ++ if (!au_ftest_pin(p->flags, DI_LOCKED)) ++ di_read_unlock(p->parent, AuLock_IR); ++ dput(p->parent); ++ p->parent = NULL; ++ goto out_err; ++ } ++ } ++ ++ au_igrab(h_dir); ++ err = au_pin_hdir_lock(p); ++ if (!err) ++ goto out; /* success */ ++ ++ au_unpin(p); ++ ++out_err: ++ pr_err("err %d\n", err); ++ err = au_busy_or_stale(); ++out: ++ return err; ++} ++ ++void au_pin_init(struct au_pin *p, struct dentry *dentry, ++ aufs_bindex_t bindex, int lsc_di, int lsc_hi, ++ unsigned int udba, unsigned char flags) ++{ ++ p->dentry = dentry; ++ p->udba = udba; ++ p->lsc_di = lsc_di; ++ p->lsc_hi = lsc_hi; ++ p->flags = flags; ++ p->bindex = bindex; ++ ++ p->parent = NULL; ++ p->hdir = NULL; ++ p->h_mnt = NULL; ++ ++ p->h_dentry = NULL; ++ p->h_parent = NULL; ++ p->br = NULL; ++ p->task = current; ++} ++ ++int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex, ++ unsigned int udba, unsigned char flags) ++{ ++ au_pin_init(pin, dentry, bindex, AuLsc_DI_PARENT, AuLsc_I_PARENT2, ++ udba, flags); ++ return au_do_pin(pin); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * ->setattr() and ->getattr() are called in various cases. ++ * chmod, stat: dentry is revalidated. ++ * fchmod, fstat: file and dentry are not revalidated, additionally they may be ++ * unhashed. ++ * for ->setattr(), ia->ia_file is passed from ftruncate only. ++ */ ++/* todo: consolidate with do_refresh() and simple_reval_dpath() */ ++int au_reval_for_attr(struct dentry *dentry, unsigned int sigen) ++{ ++ int err; ++ struct dentry *parent; ++ ++ err = 0; ++ if (au_digen_test(dentry, sigen)) { ++ parent = dget_parent(dentry); ++ di_read_lock_parent(parent, AuLock_IR); ++ err = au_refresh_dentry(dentry, parent); ++ di_read_unlock(parent, AuLock_IR); ++ dput(parent); ++ } ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia, ++ struct au_icpup_args *a) ++{ ++ int err; ++ loff_t sz; ++ aufs_bindex_t btop, ibtop; ++ struct dentry *hi_wh, *parent; ++ struct inode *inode; ++ struct au_wr_dir_args wr_dir_args = { ++ .force_btgt = -1, ++ .flags = 0 ++ }; ++ ++ if (d_is_dir(dentry)) ++ au_fset_wrdir(wr_dir_args.flags, ISDIR); ++ /* plink or hi_wh() case */ ++ btop = au_dbtop(dentry); ++ inode = d_inode(dentry); ++ ibtop = au_ibtop(inode); ++ if (btop != ibtop && !au_test_ro(inode->i_sb, ibtop, inode)) ++ wr_dir_args.force_btgt = ibtop; ++ err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args); ++ if (unlikely(err < 0)) ++ goto out; ++ a->btgt = err; ++ if (err != btop) ++ au_fset_icpup(a->flags, DID_CPUP); ++ ++ err = 0; ++ a->pin_flags = AuPin_MNT_WRITE; ++ parent = NULL; ++ if (!IS_ROOT(dentry)) { ++ au_fset_pin(a->pin_flags, DI_LOCKED); ++ parent = dget_parent(dentry); ++ di_write_lock_parent(parent); ++ } ++ ++ err = au_pin(&a->pin, dentry, a->btgt, a->udba, a->pin_flags); ++ if (unlikely(err)) ++ goto out_parent; ++ ++ sz = -1; ++ a->h_path.dentry = au_h_dptr(dentry, btop); ++ a->h_inode = d_inode(a->h_path.dentry); ++ if (ia && (ia->ia_valid & ATTR_SIZE)) { ++ vfsub_inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD); ++ if (ia->ia_size < i_size_read(a->h_inode)) ++ sz = ia->ia_size; ++ inode_unlock_shared(a->h_inode); ++ } ++ ++ hi_wh = NULL; ++ if (au_ftest_icpup(a->flags, DID_CPUP) && d_unlinked(dentry)) { ++ hi_wh = au_hi_wh(inode, a->btgt); ++ if (!hi_wh) { ++ struct au_cp_generic cpg = { ++ .dentry = dentry, ++ .bdst = a->btgt, ++ .bsrc = -1, ++ .len = sz, ++ .pin = &a->pin ++ }; ++ err = au_sio_cpup_wh(&cpg, /*file*/NULL); ++ if (unlikely(err)) ++ goto out_unlock; ++ hi_wh = au_hi_wh(inode, a->btgt); ++ /* todo: revalidate hi_wh? */ ++ } ++ } ++ ++ if (parent) { ++ au_pin_set_parent_lflag(&a->pin, /*lflag*/0); ++ di_downgrade_lock(parent, AuLock_IR); ++ dput(parent); ++ parent = NULL; ++ } ++ if (!au_ftest_icpup(a->flags, DID_CPUP)) ++ goto out; /* success */ ++ ++ if (!d_unhashed(dentry)) { ++ struct au_cp_generic cpg = { ++ .dentry = dentry, ++ .bdst = a->btgt, ++ .bsrc = btop, ++ .len = sz, ++ .pin = &a->pin, ++ .flags = AuCpup_DTIME | AuCpup_HOPEN ++ }; ++ err = au_sio_cpup_simple(&cpg); ++ if (!err) ++ a->h_path.dentry = au_h_dptr(dentry, a->btgt); ++ } else if (!hi_wh) ++ a->h_path.dentry = au_h_dptr(dentry, a->btgt); ++ else ++ a->h_path.dentry = hi_wh; /* do not dget here */ ++ ++out_unlock: ++ a->h_inode = d_inode(a->h_path.dentry); ++ if (!err) ++ goto out; /* success */ ++ au_unpin(&a->pin); ++out_parent: ++ if (parent) { ++ di_write_unlock(parent); ++ dput(parent); ++ } ++out: ++ if (!err) ++ inode_lock_nested(a->h_inode, AuLsc_I_CHILD); ++ return err; ++} ++ ++static int aufs_setattr(struct dentry *dentry, struct iattr *ia) ++{ ++ int err; ++ struct inode *inode, *delegated; ++ struct super_block *sb; ++ struct file *file; ++ struct au_icpup_args *a; ++ ++ inode = d_inode(dentry); ++ IMustLock(inode); ++ ++ err = setattr_prepare(dentry, ia); ++ if (unlikely(err)) ++ goto out; ++ ++ err = -ENOMEM; ++ a = kzalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) ++ ia->ia_valid &= ~ATTR_MODE; ++ ++ file = NULL; ++ sb = dentry->d_sb; ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (unlikely(err)) ++ goto out_kfree; ++ ++ if (ia->ia_valid & ATTR_FILE) { ++ /* currently ftruncate(2) only */ ++ AuDebugOn(!d_is_reg(dentry)); ++ file = ia->ia_file; ++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1, ++ /*fi_lsc*/0); ++ if (unlikely(err)) ++ goto out_si; ++ ia->ia_file = au_hf_top(file); ++ a->udba = AuOpt_UDBA_NONE; ++ } else { ++ /* fchmod() doesn't pass ia_file */ ++ a->udba = au_opt_udba(sb); ++ di_write_lock_child(dentry); ++ /* no d_unlinked(), to set UDBA_NONE for root */ ++ if (d_unhashed(dentry)) ++ a->udba = AuOpt_UDBA_NONE; ++ if (a->udba != AuOpt_UDBA_NONE) { ++ AuDebugOn(IS_ROOT(dentry)); ++ err = au_reval_for_attr(dentry, au_sigen(sb)); ++ if (unlikely(err)) ++ goto out_dentry; ++ } ++ } ++ ++ err = au_pin_and_icpup(dentry, ia, a); ++ if (unlikely(err < 0)) ++ goto out_dentry; ++ if (au_ftest_icpup(a->flags, DID_CPUP)) { ++ ia->ia_file = NULL; ++ ia->ia_valid &= ~ATTR_FILE; ++ } ++ ++ a->h_path.mnt = au_sbr_mnt(sb, a->btgt); ++ if ((ia->ia_valid & (ATTR_MODE | ATTR_CTIME)) ++ == (ATTR_MODE | ATTR_CTIME)) { ++ err = security_path_chmod(&a->h_path, ia->ia_mode); ++ if (unlikely(err)) ++ goto out_unlock; ++ } else if ((ia->ia_valid & (ATTR_UID | ATTR_GID)) ++ && (ia->ia_valid & ATTR_CTIME)) { ++ err = security_path_chown(&a->h_path, ia->ia_uid, ia->ia_gid); ++ if (unlikely(err)) ++ goto out_unlock; ++ } ++ ++ if (ia->ia_valid & ATTR_SIZE) { ++ struct file *f; ++ ++ if (ia->ia_size < i_size_read(inode)) ++ /* unmap only */ ++ truncate_setsize(inode, ia->ia_size); ++ ++ f = NULL; ++ if (ia->ia_valid & ATTR_FILE) ++ f = ia->ia_file; ++ inode_unlock(a->h_inode); ++ err = vfsub_trunc(&a->h_path, ia->ia_size, ia->ia_valid, f); ++ inode_lock_nested(a->h_inode, AuLsc_I_CHILD); ++ } else { ++ delegated = NULL; ++ while (1) { ++ err = vfsub_notify_change(&a->h_path, ia, &delegated); ++ if (delegated) { ++ err = break_deleg_wait(&delegated); ++ if (!err) ++ continue; ++ } ++ break; ++ } ++ } ++ /* ++ * regardless aufs 'acl' option setting. ++ * why don't all acl-aware fs call this func from their ->setattr()? ++ */ ++ if (!err && (ia->ia_valid & ATTR_MODE)) ++ err = vfsub_acl_chmod(a->h_inode, ia->ia_mode); ++ if (!err) ++ au_cpup_attr_changeable(inode); ++ ++out_unlock: ++ inode_unlock(a->h_inode); ++ au_unpin(&a->pin); ++ if (unlikely(err)) ++ au_update_dbtop(dentry); ++out_dentry: ++ di_write_unlock(dentry); ++ if (file) { ++ fi_write_unlock(file); ++ ia->ia_file = file; ++ ia->ia_valid |= ATTR_FILE; ++ } ++out_si: ++ si_read_unlock(sb); ++out_kfree: ++ kfree(a); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL) ++static int au_h_path_to_set_attr(struct dentry *dentry, ++ struct au_icpup_args *a, struct path *h_path) ++{ ++ int err; ++ struct super_block *sb; ++ ++ sb = dentry->d_sb; ++ a->udba = au_opt_udba(sb); ++ /* no d_unlinked(), to set UDBA_NONE for root */ ++ if (d_unhashed(dentry)) ++ a->udba = AuOpt_UDBA_NONE; ++ if (a->udba != AuOpt_UDBA_NONE) { ++ AuDebugOn(IS_ROOT(dentry)); ++ err = au_reval_for_attr(dentry, au_sigen(sb)); ++ if (unlikely(err)) ++ goto out; ++ } ++ err = au_pin_and_icpup(dentry, /*ia*/NULL, a); ++ if (unlikely(err < 0)) ++ goto out; ++ ++ h_path->dentry = a->h_path.dentry; ++ h_path->mnt = au_sbr_mnt(sb, a->btgt); ++ ++out: ++ return err; ++} ++ ++ssize_t au_sxattr(struct dentry *dentry, struct inode *inode, ++ struct au_sxattr *arg) ++{ ++ int err; ++ struct path h_path; ++ struct super_block *sb; ++ struct au_icpup_args *a; ++ struct inode *h_inode; ++ ++ IMustLock(inode); ++ ++ err = -ENOMEM; ++ a = kzalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ sb = dentry->d_sb; ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (unlikely(err)) ++ goto out_kfree; ++ ++ h_path.dentry = NULL; /* silence gcc */ ++ di_write_lock_child(dentry); ++ err = au_h_path_to_set_attr(dentry, a, &h_path); ++ if (unlikely(err)) ++ goto out_di; ++ ++ inode_unlock(a->h_inode); ++ switch (arg->type) { ++ case AU_XATTR_SET: ++ AuDebugOn(d_is_negative(h_path.dentry)); ++ err = vfsub_setxattr(h_path.dentry, ++ arg->u.set.name, arg->u.set.value, ++ arg->u.set.size, arg->u.set.flags); ++ break; ++ case AU_ACL_SET: ++ err = -EOPNOTSUPP; ++ h_inode = d_inode(h_path.dentry); ++ if (h_inode->i_op->set_acl) ++ /* this will call posix_acl_update_mode */ ++ err = h_inode->i_op->set_acl(h_inode, ++ arg->u.acl_set.acl, ++ arg->u.acl_set.type); ++ break; ++ } ++ if (!err) ++ au_cpup_attr_timesizes(inode); ++ ++ au_unpin(&a->pin); ++ if (unlikely(err)) ++ au_update_dbtop(dentry); ++ ++out_di: ++ di_write_unlock(dentry); ++ si_read_unlock(sb); ++out_kfree: ++ kfree(a); ++out: ++ AuTraceErr(err); ++ return err; ++} ++#endif ++ ++static void au_refresh_iattr(struct inode *inode, struct kstat *st, ++ unsigned int nlink) ++{ ++ unsigned int n; ++ ++ inode->i_mode = st->mode; ++ /* don't i_[ug]id_write() here */ ++ inode->i_uid = st->uid; ++ inode->i_gid = st->gid; ++ inode->i_atime = st->atime; ++ inode->i_mtime = st->mtime; ++ inode->i_ctime = st->ctime; ++ ++ au_cpup_attr_nlink(inode, /*force*/0); ++ if (S_ISDIR(inode->i_mode)) { ++ n = inode->i_nlink; ++ n -= nlink; ++ n += st->nlink; ++ smp_mb(); /* for i_nlink */ ++ /* 0 can happen */ ++ set_nlink(inode, n); ++ } ++ ++ spin_lock(&inode->i_lock); ++ inode->i_blocks = st->blocks; ++ i_size_write(inode, st->size); ++ spin_unlock(&inode->i_lock); ++} ++ ++/* ++ * common routine for aufs_getattr() and au_getxattr(). ++ * returns zero or negative (an error). ++ * @dentry will be read-locked in success. ++ */ ++int au_h_path_getattr(struct dentry *dentry, int force, struct path *h_path, ++ int locked) ++{ ++ int err; ++ unsigned int mnt_flags, sigen; ++ unsigned char udba_none; ++ aufs_bindex_t bindex; ++ struct super_block *sb, *h_sb; ++ struct inode *inode; ++ ++ h_path->mnt = NULL; ++ h_path->dentry = NULL; ++ ++ err = 0; ++ sb = dentry->d_sb; ++ mnt_flags = au_mntflags(sb); ++ udba_none = !!au_opt_test(mnt_flags, UDBA_NONE); ++ ++ if (unlikely(locked)) ++ goto body; /* skip locking dinfo */ ++ ++ /* support fstat(2) */ ++ if (!d_unlinked(dentry) && !udba_none) { ++ sigen = au_sigen(sb); ++ err = au_digen_test(dentry, sigen); ++ if (!err) { ++ di_read_lock_child(dentry, AuLock_IR); ++ err = au_dbrange_test(dentry); ++ if (unlikely(err)) { ++ di_read_unlock(dentry, AuLock_IR); ++ goto out; ++ } ++ } else { ++ AuDebugOn(IS_ROOT(dentry)); ++ di_write_lock_child(dentry); ++ err = au_dbrange_test(dentry); ++ if (!err) ++ err = au_reval_for_attr(dentry, sigen); ++ if (!err) ++ di_downgrade_lock(dentry, AuLock_IR); ++ else { ++ di_write_unlock(dentry); ++ goto out; ++ } ++ } ++ } else ++ di_read_lock_child(dentry, AuLock_IR); ++ ++body: ++ inode = d_inode(dentry); ++ bindex = au_ibtop(inode); ++ h_path->mnt = au_sbr_mnt(sb, bindex); ++ h_sb = h_path->mnt->mnt_sb; ++ if (!force ++ && !au_test_fs_bad_iattr(h_sb) ++ && udba_none) ++ goto out; /* success */ ++ ++ if (au_dbtop(dentry) == bindex) ++ h_path->dentry = au_h_dptr(dentry, bindex); ++ else if (au_opt_test(mnt_flags, PLINK) && au_plink_test(inode)) { ++ h_path->dentry = au_plink_lkup(inode, bindex); ++ if (IS_ERR(h_path->dentry)) ++ /* pretending success */ ++ h_path->dentry = NULL; ++ else ++ dput(h_path->dentry); ++ } ++ ++out: ++ return err; ++} ++ ++static int aufs_getattr(struct vfsmount *mnt __maybe_unused, ++ struct dentry *dentry, struct kstat *st) ++{ ++ int err; ++ unsigned char positive; ++ struct path h_path; ++ struct inode *inode; ++ struct super_block *sb; ++ ++ inode = d_inode(dentry); ++ sb = dentry->d_sb; ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (unlikely(err)) ++ goto out; ++ err = au_h_path_getattr(dentry, /*force*/0, &h_path, /*locked*/0); ++ if (unlikely(err)) ++ goto out_si; ++ if (unlikely(!h_path.dentry)) ++ /* illegally overlapped or something */ ++ goto out_fill; /* pretending success */ ++ ++ positive = d_is_positive(h_path.dentry); ++ if (positive) ++ err = vfs_getattr(&h_path, st); ++ if (!err) { ++ if (positive) ++ au_refresh_iattr(inode, st, ++ d_inode(h_path.dentry)->i_nlink); ++ goto out_fill; /* success */ ++ } ++ AuTraceErr(err); ++ goto out_di; ++ ++out_fill: ++ generic_fillattr(inode, st); ++out_di: ++ di_read_unlock(dentry, AuLock_IR); ++out_si: ++ si_read_unlock(sb); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static const char *aufs_get_link(struct dentry *dentry, struct inode *inode, ++ struct delayed_call *done) ++{ ++ const char *ret; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ int err; ++ aufs_bindex_t bindex; ++ ++ ret = NULL; /* suppress a warning */ ++ err = -ECHILD; ++ if (!dentry) ++ goto out; ++ ++ err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN); ++ if (unlikely(err)) ++ goto out; ++ ++ err = au_d_hashed_positive(dentry); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ err = -EINVAL; ++ inode = d_inode(dentry); ++ bindex = au_ibtop(inode); ++ h_inode = au_h_iptr(inode, bindex); ++ if (unlikely(!h_inode->i_op->get_link)) ++ goto out_unlock; ++ ++ err = -EBUSY; ++ h_dentry = NULL; ++ if (au_dbtop(dentry) <= bindex) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry) ++ dget(h_dentry); ++ } ++ if (!h_dentry) { ++ h_dentry = d_find_any_alias(h_inode); ++ if (IS_ERR(h_dentry)) { ++ err = PTR_ERR(h_dentry); ++ goto out_unlock; ++ } ++ } ++ if (unlikely(!h_dentry)) ++ goto out_unlock; ++ ++ err = 0; ++ AuDbg("%pf\n", h_inode->i_op->get_link); ++ AuDbgDentry(h_dentry); ++ ret = vfs_get_link(h_dentry, done); ++ dput(h_dentry); ++ if (IS_ERR(ret)) ++ err = PTR_ERR(ret); ++ ++out_unlock: ++ aufs_read_unlock(dentry, AuLock_IR); ++out: ++ if (unlikely(err)) ++ ret = ERR_PTR(err); ++ AuTraceErrPtr(ret); ++ return ret; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_is_special(struct inode *inode) ++{ ++ return (inode->i_mode & (S_IFBLK | S_IFCHR | S_IFIFO | S_IFSOCK)); ++} ++ ++static int aufs_update_time(struct inode *inode, struct timespec *ts, int flags) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ struct super_block *sb; ++ struct inode *h_inode; ++ struct vfsmount *h_mnt; ++ ++ sb = inode->i_sb; ++ WARN_ONCE((flags & S_ATIME) && !IS_NOATIME(inode), ++ "unexpected s_flags 0x%lx", sb->s_flags); ++ ++ /* mmap_sem might be acquired already, cf. aufs_mmap() */ ++ lockdep_off(); ++ si_read_lock(sb, AuLock_FLUSH); ++ ii_write_lock_child(inode); ++ lockdep_on(); ++ ++ err = 0; ++ bindex = au_ibtop(inode); ++ h_inode = au_h_iptr(inode, bindex); ++ if (!au_test_ro(sb, bindex, inode)) { ++ h_mnt = au_sbr_mnt(sb, bindex); ++ err = vfsub_mnt_want_write(h_mnt); ++ if (!err) { ++ err = vfsub_update_time(h_inode, ts, flags); ++ vfsub_mnt_drop_write(h_mnt); ++ } ++ } else if (au_is_special(h_inode)) { ++ /* ++ * Never copy-up here. ++ * These special files may already be opened and used for ++ * communicating. If we copied it up, then the communication ++ * would be corrupted. ++ */ ++ AuWarn1("timestamps for i%lu are ignored " ++ "since it is on readonly branch (hi%lu).\n", ++ inode->i_ino, h_inode->i_ino); ++ } else if (flags & ~S_ATIME) { ++ err = -EIO; ++ AuIOErr1("unexpected flags 0x%x\n", flags); ++ AuDebugOn(1); ++ } ++ ++ lockdep_off(); ++ if (!err) ++ au_cpup_attr_timesizes(inode); ++ ii_write_unlock(inode); ++ si_read_unlock(sb); ++ lockdep_on(); ++ ++ if (!err && (flags & S_VERSION)) ++ inode_inc_iversion(inode); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* no getattr version will be set by module.c:aufs_init() */ ++struct inode_operations aufs_iop_nogetattr[AuIop_Last], ++ aufs_iop[] = { ++ [AuIop_SYMLINK] = { ++ .permission = aufs_permission, ++#ifdef CONFIG_FS_POSIX_ACL ++ .get_acl = aufs_get_acl, ++ .set_acl = aufs_set_acl, /* unsupport for symlink? */ ++#endif ++ ++ .setattr = aufs_setattr, ++ .getattr = aufs_getattr, ++ ++#ifdef CONFIG_AUFS_XATTR ++ .listxattr = aufs_listxattr, ++#endif ++ ++ .readlink = generic_readlink, ++ .get_link = aufs_get_link, ++ ++ /* .update_time = aufs_update_time */ ++ }, ++ [AuIop_DIR] = { ++ .create = aufs_create, ++ .lookup = aufs_lookup, ++ .link = aufs_link, ++ .unlink = aufs_unlink, ++ .symlink = aufs_symlink, ++ .mkdir = aufs_mkdir, ++ .rmdir = aufs_rmdir, ++ .mknod = aufs_mknod, ++ .rename = aufs_rename, ++ ++ .permission = aufs_permission, ++#ifdef CONFIG_FS_POSIX_ACL ++ .get_acl = aufs_get_acl, ++ .set_acl = aufs_set_acl, ++#endif ++ ++ .setattr = aufs_setattr, ++ .getattr = aufs_getattr, ++ ++#ifdef CONFIG_AUFS_XATTR ++ .listxattr = aufs_listxattr, ++#endif ++ ++ .update_time = aufs_update_time, ++ .atomic_open = aufs_atomic_open, ++ .tmpfile = aufs_tmpfile ++ }, ++ [AuIop_OTHER] = { ++ .permission = aufs_permission, ++#ifdef CONFIG_FS_POSIX_ACL ++ .get_acl = aufs_get_acl, ++ .set_acl = aufs_set_acl, ++#endif ++ ++ .setattr = aufs_setattr, ++ .getattr = aufs_getattr, ++ ++#ifdef CONFIG_AUFS_XATTR ++ .listxattr = aufs_listxattr, ++#endif ++ ++ .update_time = aufs_update_time ++ } ++}; +diff --git a/fs/aufs/i_op_add.c b/fs/aufs/i_op_add.c +new file mode 100644 +index 00000000..0fc4f7cf +--- /dev/null ++++ b/fs/aufs/i_op_add.c +@@ -0,0 +1,928 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * inode operations (add entry) ++ */ ++ ++#include "aufs.h" ++ ++/* ++ * final procedure of adding a new entry, except link(2). ++ * remove whiteout, instantiate, copyup the parent dir's times and size ++ * and update version. ++ * if it failed, re-create the removed whiteout. ++ */ ++static int epilog(struct inode *dir, aufs_bindex_t bindex, ++ struct dentry *wh_dentry, struct dentry *dentry) ++{ ++ int err, rerr; ++ aufs_bindex_t bwh; ++ struct path h_path; ++ struct super_block *sb; ++ struct inode *inode, *h_dir; ++ struct dentry *wh; ++ ++ bwh = -1; ++ sb = dir->i_sb; ++ if (wh_dentry) { ++ h_dir = d_inode(wh_dentry->d_parent); /* dir inode is locked */ ++ IMustLock(h_dir); ++ AuDebugOn(au_h_iptr(dir, bindex) != h_dir); ++ bwh = au_dbwh(dentry); ++ h_path.dentry = wh_dentry; ++ h_path.mnt = au_sbr_mnt(sb, bindex); ++ err = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, ++ dentry); ++ if (unlikely(err)) ++ goto out; ++ } ++ ++ inode = au_new_inode(dentry, /*must_new*/1); ++ if (!IS_ERR(inode)) { ++ d_instantiate(dentry, inode); ++ dir = d_inode(dentry->d_parent); /* dir inode is locked */ ++ IMustLock(dir); ++ au_dir_ts(dir, bindex); ++ dir->i_version++; ++ au_fhsm_wrote(sb, bindex, /*force*/0); ++ return 0; /* success */ ++ } ++ ++ err = PTR_ERR(inode); ++ if (!wh_dentry) ++ goto out; ++ ++ /* revert */ ++ /* dir inode is locked */ ++ wh = au_wh_create(dentry, bwh, wh_dentry->d_parent); ++ rerr = PTR_ERR(wh); ++ if (IS_ERR(wh)) { ++ AuIOErr("%pd reverting whiteout failed(%d, %d)\n", ++ dentry, err, rerr); ++ err = -EIO; ++ } else ++ dput(wh); ++ ++out: ++ return err; ++} ++ ++static int au_d_may_add(struct dentry *dentry) ++{ ++ int err; ++ ++ err = 0; ++ if (unlikely(d_unhashed(dentry))) ++ err = -ENOENT; ++ if (unlikely(d_really_is_positive(dentry))) ++ err = -EEXIST; ++ return err; ++} ++ ++/* ++ * simple tests for the adding inode operations. ++ * following the checks in vfs, plus the parent-child relationship. ++ */ ++int au_may_add(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_parent, int isdir) ++{ ++ int err; ++ umode_t h_mode; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ ++ err = -ENAMETOOLONG; ++ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) ++ goto out; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (d_really_is_negative(dentry)) { ++ err = -EEXIST; ++ if (unlikely(d_is_positive(h_dentry))) ++ goto out; ++ } else { ++ /* rename(2) case */ ++ err = -EIO; ++ if (unlikely(d_is_negative(h_dentry))) ++ goto out; ++ h_inode = d_inode(h_dentry); ++ if (unlikely(!h_inode->i_nlink)) ++ goto out; ++ ++ h_mode = h_inode->i_mode; ++ if (!isdir) { ++ err = -EISDIR; ++ if (unlikely(S_ISDIR(h_mode))) ++ goto out; ++ } else if (unlikely(!S_ISDIR(h_mode))) { ++ err = -ENOTDIR; ++ goto out; ++ } ++ } ++ ++ err = 0; ++ /* expected parent dir is locked */ ++ if (unlikely(h_parent != h_dentry->d_parent)) ++ err = -EIO; ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ++ * initial procedure of adding a new entry. ++ * prepare writable branch and the parent dir, lock it, ++ * and lookup whiteout for the new entry. ++ */ ++static struct dentry* ++lock_hdir_lkup_wh(struct dentry *dentry, struct au_dtime *dt, ++ struct dentry *src_dentry, struct au_pin *pin, ++ struct au_wr_dir_args *wr_dir_args) ++{ ++ struct dentry *wh_dentry, *h_parent; ++ struct super_block *sb; ++ struct au_branch *br; ++ int err; ++ unsigned int udba; ++ aufs_bindex_t bcpup; ++ ++ AuDbg("%pd\n", dentry); ++ ++ err = au_wr_dir(dentry, src_dentry, wr_dir_args); ++ bcpup = err; ++ wh_dentry = ERR_PTR(err); ++ if (unlikely(err < 0)) ++ goto out; ++ ++ sb = dentry->d_sb; ++ udba = au_opt_udba(sb); ++ err = au_pin(pin, dentry, bcpup, udba, ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ wh_dentry = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out; ++ ++ h_parent = au_pinned_h_parent(pin); ++ if (udba != AuOpt_UDBA_NONE ++ && au_dbtop(dentry) == bcpup) ++ err = au_may_add(dentry, bcpup, h_parent, ++ au_ftest_wrdir(wr_dir_args->flags, ISDIR)); ++ else if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) ++ err = -ENAMETOOLONG; ++ wh_dentry = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out_unpin; ++ ++ br = au_sbr(sb, bcpup); ++ if (dt) { ++ struct path tmp = { ++ .dentry = h_parent, ++ .mnt = au_br_mnt(br) ++ }; ++ au_dtime_store(dt, au_pinned_parent(pin), &tmp); ++ } ++ ++ wh_dentry = NULL; ++ if (bcpup != au_dbwh(dentry)) ++ goto out; /* success */ ++ ++ /* ++ * ENAMETOOLONG here means that if we allowed create such name, then it ++ * would not be able to removed in the future. So we don't allow such ++ * name here and we don't handle ENAMETOOLONG differently here. ++ */ ++ wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, br); ++ ++out_unpin: ++ if (IS_ERR(wh_dentry)) ++ au_unpin(pin); ++out: ++ return wh_dentry; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++enum { Mknod, Symlink, Creat }; ++struct simple_arg { ++ int type; ++ union { ++ struct { ++ umode_t mode; ++ bool want_excl; ++ bool try_aopen; ++ struct vfsub_aopen_args *aopen; ++ } c; ++ struct { ++ const char *symname; ++ } s; ++ struct { ++ umode_t mode; ++ dev_t dev; ++ } m; ++ } u; ++}; ++ ++static int add_simple(struct inode *dir, struct dentry *dentry, ++ struct simple_arg *arg) ++{ ++ int err, rerr; ++ aufs_bindex_t btop; ++ unsigned char created; ++ const unsigned char try_aopen ++ = (arg->type == Creat && arg->u.c.try_aopen); ++ struct dentry *wh_dentry, *parent; ++ struct inode *h_dir; ++ struct super_block *sb; ++ struct au_branch *br; ++ /* to reuduce stack size */ ++ struct { ++ struct au_dtime dt; ++ struct au_pin pin; ++ struct path h_path; ++ struct au_wr_dir_args wr_dir_args; ++ } *a; ++ ++ AuDbg("%pd\n", dentry); ++ IMustLock(dir); ++ ++ err = -ENOMEM; ++ a = kmalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ a->wr_dir_args.force_btgt = -1; ++ a->wr_dir_args.flags = AuWrDir_ADD_ENTRY; ++ ++ parent = dentry->d_parent; /* dir inode is locked */ ++ if (!try_aopen) { ++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); ++ if (unlikely(err)) ++ goto out_free; ++ } ++ err = au_d_may_add(dentry); ++ if (unlikely(err)) ++ goto out_unlock; ++ if (!try_aopen) ++ di_write_lock_parent(parent); ++ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL, ++ &a->pin, &a->wr_dir_args); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out_parent; ++ ++ btop = au_dbtop(dentry); ++ sb = dentry->d_sb; ++ br = au_sbr(sb, btop); ++ a->h_path.dentry = au_h_dptr(dentry, btop); ++ a->h_path.mnt = au_br_mnt(br); ++ h_dir = au_pinned_h_dir(&a->pin); ++ switch (arg->type) { ++ case Creat: ++ err = 0; ++ if (!try_aopen || !h_dir->i_op->atomic_open) ++ err = vfsub_create(h_dir, &a->h_path, arg->u.c.mode, ++ arg->u.c.want_excl); ++ else ++ err = vfsub_atomic_open(h_dir, a->h_path.dentry, ++ arg->u.c.aopen, br); ++ break; ++ case Symlink: ++ err = vfsub_symlink(h_dir, &a->h_path, arg->u.s.symname); ++ break; ++ case Mknod: ++ err = vfsub_mknod(h_dir, &a->h_path, arg->u.m.mode, ++ arg->u.m.dev); ++ break; ++ default: ++ BUG(); ++ } ++ created = !err; ++ if (!err) ++ err = epilog(dir, btop, wh_dentry, dentry); ++ ++ /* revert */ ++ if (unlikely(created && err && d_is_positive(a->h_path.dentry))) { ++ /* no delegation since it is just created */ ++ rerr = vfsub_unlink(h_dir, &a->h_path, /*delegated*/NULL, ++ /*force*/0); ++ if (rerr) { ++ AuIOErr("%pd revert failure(%d, %d)\n", ++ dentry, err, rerr); ++ err = -EIO; ++ } ++ au_dtime_revert(&a->dt); ++ } ++ ++ if (!err && try_aopen && !h_dir->i_op->atomic_open) ++ *arg->u.c.aopen->opened |= FILE_CREATED; ++ ++ au_unpin(&a->pin); ++ dput(wh_dentry); ++ ++out_parent: ++ if (!try_aopen) ++ di_write_unlock(parent); ++out_unlock: ++ if (unlikely(err)) { ++ au_update_dbtop(dentry); ++ d_drop(dentry); ++ } ++ if (!try_aopen) ++ aufs_read_unlock(dentry, AuLock_DW); ++out_free: ++ kfree(a); ++out: ++ return err; ++} ++ ++int aufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, ++ dev_t dev) ++{ ++ struct simple_arg arg = { ++ .type = Mknod, ++ .u.m = { ++ .mode = mode, ++ .dev = dev ++ } ++ }; ++ return add_simple(dir, dentry, &arg); ++} ++ ++int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) ++{ ++ struct simple_arg arg = { ++ .type = Symlink, ++ .u.s.symname = symname ++ }; ++ return add_simple(dir, dentry, &arg); ++} ++ ++int aufs_create(struct inode *dir, struct dentry *dentry, umode_t mode, ++ bool want_excl) ++{ ++ struct simple_arg arg = { ++ .type = Creat, ++ .u.c = { ++ .mode = mode, ++ .want_excl = want_excl ++ } ++ }; ++ return add_simple(dir, dentry, &arg); ++} ++ ++int au_aopen_or_create(struct inode *dir, struct dentry *dentry, ++ struct vfsub_aopen_args *aopen_args) ++{ ++ struct simple_arg arg = { ++ .type = Creat, ++ .u.c = { ++ .mode = aopen_args->create_mode, ++ .want_excl = aopen_args->open_flag & O_EXCL, ++ .try_aopen = true, ++ .aopen = aopen_args ++ } ++ }; ++ return add_simple(dir, dentry, &arg); ++} ++ ++int aufs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ struct super_block *sb; ++ struct dentry *parent, *h_parent, *h_dentry; ++ struct inode *h_dir, *inode; ++ struct vfsmount *h_mnt; ++ struct au_wr_dir_args wr_dir_args = { ++ .force_btgt = -1, ++ .flags = AuWrDir_TMPFILE ++ }; ++ ++ /* copy-up may happen */ ++ inode_lock(dir); ++ ++ sb = dir->i_sb; ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (unlikely(err)) ++ goto out; ++ ++ err = au_di_init(dentry); ++ if (unlikely(err)) ++ goto out_si; ++ ++ err = -EBUSY; ++ parent = d_find_any_alias(dir); ++ AuDebugOn(!parent); ++ di_write_lock_parent(parent); ++ if (unlikely(d_inode(parent) != dir)) ++ goto out_parent; ++ ++ err = au_digen_test(parent, au_sigen(sb)); ++ if (unlikely(err)) ++ goto out_parent; ++ ++ bindex = au_dbtop(parent); ++ au_set_dbtop(dentry, bindex); ++ au_set_dbbot(dentry, bindex); ++ err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args); ++ bindex = err; ++ if (unlikely(err < 0)) ++ goto out_parent; ++ ++ err = -EOPNOTSUPP; ++ h_dir = au_h_iptr(dir, bindex); ++ if (unlikely(!h_dir->i_op->tmpfile)) ++ goto out_parent; ++ ++ h_mnt = au_sbr_mnt(sb, bindex); ++ err = vfsub_mnt_want_write(h_mnt); ++ if (unlikely(err)) ++ goto out_parent; ++ ++ h_parent = au_h_dptr(parent, bindex); ++ err = inode_permission(d_inode(h_parent), MAY_WRITE | MAY_EXEC); ++ if (unlikely(err)) ++ goto out_mnt; ++ ++ err = -ENOMEM; ++ h_dentry = d_alloc(h_parent, &dentry->d_name); ++ if (unlikely(!h_dentry)) ++ goto out_mnt; ++ ++ err = h_dir->i_op->tmpfile(h_dir, h_dentry, mode); ++ if (unlikely(err)) ++ goto out_dentry; ++ ++ au_set_dbtop(dentry, bindex); ++ au_set_dbbot(dentry, bindex); ++ au_set_h_dptr(dentry, bindex, dget(h_dentry)); ++ inode = au_new_inode(dentry, /*must_new*/1); ++ if (IS_ERR(inode)) { ++ err = PTR_ERR(inode); ++ au_set_h_dptr(dentry, bindex, NULL); ++ au_set_dbtop(dentry, -1); ++ au_set_dbbot(dentry, -1); ++ } else { ++ if (!inode->i_nlink) ++ set_nlink(inode, 1); ++ d_tmpfile(dentry, inode); ++ au_di(dentry)->di_tmpfile = 1; ++ ++ /* update without i_mutex */ ++ if (au_ibtop(dir) == au_dbtop(dentry)) ++ au_cpup_attr_timesizes(dir); ++ } ++ ++out_dentry: ++ dput(h_dentry); ++out_mnt: ++ vfsub_mnt_drop_write(h_mnt); ++out_parent: ++ di_write_unlock(parent); ++ dput(parent); ++ di_write_unlock(dentry); ++ if (unlikely(err)) { ++ au_di_fin(dentry); ++ dentry->d_fsdata = NULL; ++ } ++out_si: ++ si_read_unlock(sb); ++out: ++ inode_unlock(dir); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_link_args { ++ aufs_bindex_t bdst, bsrc; ++ struct au_pin pin; ++ struct path h_path; ++ struct dentry *src_parent, *parent; ++}; ++ ++static int au_cpup_before_link(struct dentry *src_dentry, ++ struct au_link_args *a) ++{ ++ int err; ++ struct dentry *h_src_dentry; ++ struct au_cp_generic cpg = { ++ .dentry = src_dentry, ++ .bdst = a->bdst, ++ .bsrc = a->bsrc, ++ .len = -1, ++ .pin = &a->pin, ++ .flags = AuCpup_DTIME | AuCpup_HOPEN /* | AuCpup_KEEPLINO */ ++ }; ++ ++ di_read_lock_parent(a->src_parent, AuLock_IR); ++ err = au_test_and_cpup_dirs(src_dentry, a->bdst); ++ if (unlikely(err)) ++ goto out; ++ ++ h_src_dentry = au_h_dptr(src_dentry, a->bsrc); ++ err = au_pin(&a->pin, src_dentry, a->bdst, ++ au_opt_udba(src_dentry->d_sb), ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ if (unlikely(err)) ++ goto out; ++ ++ err = au_sio_cpup_simple(&cpg); ++ au_unpin(&a->pin); ++ ++out: ++ di_read_unlock(a->src_parent, AuLock_IR); ++ return err; ++} ++ ++static int au_cpup_or_link(struct dentry *src_dentry, struct dentry *dentry, ++ struct au_link_args *a) ++{ ++ int err; ++ unsigned char plink; ++ aufs_bindex_t bbot; ++ struct dentry *h_src_dentry; ++ struct inode *h_inode, *inode, *delegated; ++ struct super_block *sb; ++ struct file *h_file; ++ ++ plink = 0; ++ h_inode = NULL; ++ sb = src_dentry->d_sb; ++ inode = d_inode(src_dentry); ++ if (au_ibtop(inode) <= a->bdst) ++ h_inode = au_h_iptr(inode, a->bdst); ++ if (!h_inode || !h_inode->i_nlink) { ++ /* copyup src_dentry as the name of dentry. */ ++ bbot = au_dbbot(dentry); ++ if (bbot < a->bsrc) ++ au_set_dbbot(dentry, a->bsrc); ++ au_set_h_dptr(dentry, a->bsrc, ++ dget(au_h_dptr(src_dentry, a->bsrc))); ++ dget(a->h_path.dentry); ++ au_set_h_dptr(dentry, a->bdst, NULL); ++ AuDbg("temporary d_inode...\n"); ++ spin_lock(&dentry->d_lock); ++ dentry->d_inode = d_inode(src_dentry); /* tmp */ ++ spin_unlock(&dentry->d_lock); ++ h_file = au_h_open_pre(dentry, a->bsrc, /*force_wr*/0); ++ if (IS_ERR(h_file)) ++ err = PTR_ERR(h_file); ++ else { ++ struct au_cp_generic cpg = { ++ .dentry = dentry, ++ .bdst = a->bdst, ++ .bsrc = -1, ++ .len = -1, ++ .pin = &a->pin, ++ .flags = AuCpup_KEEPLINO ++ }; ++ err = au_sio_cpup_simple(&cpg); ++ au_h_open_post(dentry, a->bsrc, h_file); ++ if (!err) { ++ dput(a->h_path.dentry); ++ a->h_path.dentry = au_h_dptr(dentry, a->bdst); ++ } else ++ au_set_h_dptr(dentry, a->bdst, ++ a->h_path.dentry); ++ } ++ spin_lock(&dentry->d_lock); ++ dentry->d_inode = NULL; /* restore */ ++ spin_unlock(&dentry->d_lock); ++ AuDbg("temporary d_inode...done\n"); ++ au_set_h_dptr(dentry, a->bsrc, NULL); ++ au_set_dbbot(dentry, bbot); ++ } else { ++ /* the inode of src_dentry already exists on a.bdst branch */ ++ h_src_dentry = d_find_alias(h_inode); ++ if (!h_src_dentry && au_plink_test(inode)) { ++ plink = 1; ++ h_src_dentry = au_plink_lkup(inode, a->bdst); ++ err = PTR_ERR(h_src_dentry); ++ if (IS_ERR(h_src_dentry)) ++ goto out; ++ ++ if (unlikely(d_is_negative(h_src_dentry))) { ++ dput(h_src_dentry); ++ h_src_dentry = NULL; ++ } ++ ++ } ++ if (h_src_dentry) { ++ delegated = NULL; ++ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), ++ &a->h_path, &delegated); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal link\n"); ++ iput(delegated); ++ } ++ dput(h_src_dentry); ++ } else { ++ AuIOErr("no dentry found for hi%lu on b%d\n", ++ h_inode->i_ino, a->bdst); ++ err = -EIO; ++ } ++ } ++ ++ if (!err && !plink) ++ au_plink_append(inode, a->bdst, a->h_path.dentry); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++int aufs_link(struct dentry *src_dentry, struct inode *dir, ++ struct dentry *dentry) ++{ ++ int err, rerr; ++ struct au_dtime dt; ++ struct au_link_args *a; ++ struct dentry *wh_dentry, *h_src_dentry; ++ struct inode *inode, *delegated; ++ struct super_block *sb; ++ struct au_wr_dir_args wr_dir_args = { ++ /* .force_btgt = -1, */ ++ .flags = AuWrDir_ADD_ENTRY ++ }; ++ ++ IMustLock(dir); ++ inode = d_inode(src_dentry); ++ IMustLock(inode); ++ ++ err = -ENOMEM; ++ a = kzalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ a->parent = dentry->d_parent; /* dir inode is locked */ ++ err = aufs_read_and_write_lock2(dentry, src_dentry, ++ AuLock_NOPLM | AuLock_GEN); ++ if (unlikely(err)) ++ goto out_kfree; ++ err = au_d_linkable(src_dentry); ++ if (unlikely(err)) ++ goto out_unlock; ++ err = au_d_may_add(dentry); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ a->src_parent = dget_parent(src_dentry); ++ wr_dir_args.force_btgt = au_ibtop(inode); ++ ++ di_write_lock_parent(a->parent); ++ wr_dir_args.force_btgt = au_wbr(dentry, wr_dir_args.force_btgt); ++ wh_dentry = lock_hdir_lkup_wh(dentry, &dt, src_dentry, &a->pin, ++ &wr_dir_args); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out_parent; ++ ++ err = 0; ++ sb = dentry->d_sb; ++ a->bdst = au_dbtop(dentry); ++ a->h_path.dentry = au_h_dptr(dentry, a->bdst); ++ a->h_path.mnt = au_sbr_mnt(sb, a->bdst); ++ a->bsrc = au_ibtop(inode); ++ h_src_dentry = au_h_d_alias(src_dentry, a->bsrc); ++ if (!h_src_dentry && au_di(src_dentry)->di_tmpfile) ++ h_src_dentry = dget(au_hi_wh(inode, a->bsrc)); ++ if (!h_src_dentry) { ++ a->bsrc = au_dbtop(src_dentry); ++ h_src_dentry = au_h_d_alias(src_dentry, a->bsrc); ++ AuDebugOn(!h_src_dentry); ++ } else if (IS_ERR(h_src_dentry)) { ++ err = PTR_ERR(h_src_dentry); ++ goto out_parent; ++ } ++ ++ /* ++ * aufs doesn't touch the credential so ++ * security_dentry_create_files_as() is unnecrssary. ++ */ ++ if (au_opt_test(au_mntflags(sb), PLINK)) { ++ if (a->bdst < a->bsrc ++ /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) ++ err = au_cpup_or_link(src_dentry, dentry, a); ++ else { ++ delegated = NULL; ++ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), ++ &a->h_path, &delegated); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal link\n"); ++ iput(delegated); ++ } ++ } ++ dput(h_src_dentry); ++ } else { ++ /* ++ * copyup src_dentry to the branch we process, ++ * and then link(2) to it. ++ */ ++ dput(h_src_dentry); ++ if (a->bdst < a->bsrc ++ /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) { ++ au_unpin(&a->pin); ++ di_write_unlock(a->parent); ++ err = au_cpup_before_link(src_dentry, a); ++ di_write_lock_parent(a->parent); ++ if (!err) ++ err = au_pin(&a->pin, dentry, a->bdst, ++ au_opt_udba(sb), ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ if (unlikely(err)) ++ goto out_wh; ++ } ++ if (!err) { ++ h_src_dentry = au_h_dptr(src_dentry, a->bdst); ++ err = -ENOENT; ++ if (h_src_dentry && d_is_positive(h_src_dentry)) { ++ delegated = NULL; ++ err = vfsub_link(h_src_dentry, ++ au_pinned_h_dir(&a->pin), ++ &a->h_path, &delegated); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry" ++ " for NFSv4 delegation" ++ " for an internal link\n"); ++ iput(delegated); ++ } ++ } ++ } ++ } ++ if (unlikely(err)) ++ goto out_unpin; ++ ++ if (wh_dentry) { ++ a->h_path.dentry = wh_dentry; ++ err = au_wh_unlink_dentry(au_pinned_h_dir(&a->pin), &a->h_path, ++ dentry); ++ if (unlikely(err)) ++ goto out_revert; ++ } ++ ++ au_dir_ts(dir, a->bdst); ++ dir->i_version++; ++ inc_nlink(inode); ++ inode->i_ctime = dir->i_ctime; ++ d_instantiate(dentry, au_igrab(inode)); ++ if (d_unhashed(a->h_path.dentry)) ++ /* some filesystem calls d_drop() */ ++ d_drop(dentry); ++ /* some filesystems consume an inode even hardlink */ ++ au_fhsm_wrote(sb, a->bdst, /*force*/0); ++ goto out_unpin; /* success */ ++ ++out_revert: ++ /* no delegation since it is just created */ ++ rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path, ++ /*delegated*/NULL, /*force*/0); ++ if (unlikely(rerr)) { ++ AuIOErr("%pd reverting failed(%d, %d)\n", dentry, err, rerr); ++ err = -EIO; ++ } ++ au_dtime_revert(&dt); ++out_unpin: ++ au_unpin(&a->pin); ++out_wh: ++ dput(wh_dentry); ++out_parent: ++ di_write_unlock(a->parent); ++ dput(a->src_parent); ++out_unlock: ++ if (unlikely(err)) { ++ au_update_dbtop(dentry); ++ d_drop(dentry); ++ } ++ aufs_read_and_write_unlock2(dentry, src_dentry); ++out_kfree: ++ kfree(a); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) ++{ ++ int err, rerr; ++ aufs_bindex_t bindex; ++ unsigned char diropq; ++ struct path h_path; ++ struct dentry *wh_dentry, *parent, *opq_dentry; ++ struct inode *h_inode; ++ struct super_block *sb; ++ struct { ++ struct au_pin pin; ++ struct au_dtime dt; ++ } *a; /* reduce the stack usage */ ++ struct au_wr_dir_args wr_dir_args = { ++ .force_btgt = -1, ++ .flags = AuWrDir_ADD_ENTRY | AuWrDir_ISDIR ++ }; ++ ++ IMustLock(dir); ++ ++ err = -ENOMEM; ++ a = kmalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); ++ if (unlikely(err)) ++ goto out_free; ++ err = au_d_may_add(dentry); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ parent = dentry->d_parent; /* dir inode is locked */ ++ di_write_lock_parent(parent); ++ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL, ++ &a->pin, &wr_dir_args); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out_parent; ++ ++ sb = dentry->d_sb; ++ bindex = au_dbtop(dentry); ++ h_path.dentry = au_h_dptr(dentry, bindex); ++ h_path.mnt = au_sbr_mnt(sb, bindex); ++ err = vfsub_mkdir(au_pinned_h_dir(&a->pin), &h_path, mode); ++ if (unlikely(err)) ++ goto out_unpin; ++ ++ /* make the dir opaque */ ++ diropq = 0; ++ h_inode = d_inode(h_path.dentry); ++ if (wh_dentry ++ || au_opt_test(au_mntflags(sb), ALWAYS_DIROPQ)) { ++ inode_lock_nested(h_inode, AuLsc_I_CHILD); ++ opq_dentry = au_diropq_create(dentry, bindex); ++ inode_unlock(h_inode); ++ err = PTR_ERR(opq_dentry); ++ if (IS_ERR(opq_dentry)) ++ goto out_dir; ++ dput(opq_dentry); ++ diropq = 1; ++ } ++ ++ err = epilog(dir, bindex, wh_dentry, dentry); ++ if (!err) { ++ inc_nlink(dir); ++ goto out_unpin; /* success */ ++ } ++ ++ /* revert */ ++ if (diropq) { ++ AuLabel(revert opq); ++ inode_lock_nested(h_inode, AuLsc_I_CHILD); ++ rerr = au_diropq_remove(dentry, bindex); ++ inode_unlock(h_inode); ++ if (rerr) { ++ AuIOErr("%pd reverting diropq failed(%d, %d)\n", ++ dentry, err, rerr); ++ err = -EIO; ++ } ++ } ++ ++out_dir: ++ AuLabel(revert dir); ++ rerr = vfsub_rmdir(au_pinned_h_dir(&a->pin), &h_path); ++ if (rerr) { ++ AuIOErr("%pd reverting dir failed(%d, %d)\n", ++ dentry, err, rerr); ++ err = -EIO; ++ } ++ au_dtime_revert(&a->dt); ++out_unpin: ++ au_unpin(&a->pin); ++ dput(wh_dentry); ++out_parent: ++ di_write_unlock(parent); ++out_unlock: ++ if (unlikely(err)) { ++ au_update_dbtop(dentry); ++ d_drop(dentry); ++ } ++ aufs_read_unlock(dentry, AuLock_DW); ++out_free: ++ kfree(a); ++out: ++ return err; ++} +diff --git a/fs/aufs/i_op_del.c b/fs/aufs/i_op_del.c +new file mode 100644 +index 00000000..1e9162a2 +--- /dev/null ++++ b/fs/aufs/i_op_del.c +@@ -0,0 +1,511 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * inode operations (del entry) ++ */ ++ ++#include "aufs.h" ++ ++/* ++ * decide if a new whiteout for @dentry is necessary or not. ++ * when it is necessary, prepare the parent dir for the upper branch whose ++ * branch index is @bcpup for creation. the actual creation of the whiteout will ++ * be done by caller. ++ * return value: ++ * 0: wh is unnecessary ++ * plus: wh is necessary ++ * minus: error ++ */ ++int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup) ++{ ++ int need_wh, err; ++ aufs_bindex_t btop; ++ struct super_block *sb; ++ ++ sb = dentry->d_sb; ++ btop = au_dbtop(dentry); ++ if (*bcpup < 0) { ++ *bcpup = btop; ++ if (au_test_ro(sb, btop, d_inode(dentry))) { ++ err = AuWbrCopyup(au_sbi(sb), dentry); ++ *bcpup = err; ++ if (unlikely(err < 0)) ++ goto out; ++ } ++ } else ++ AuDebugOn(btop < *bcpup ++ || au_test_ro(sb, *bcpup, d_inode(dentry))); ++ AuDbg("bcpup %d, btop %d\n", *bcpup, btop); ++ ++ if (*bcpup != btop) { ++ err = au_cpup_dirs(dentry, *bcpup); ++ if (unlikely(err)) ++ goto out; ++ need_wh = 1; ++ } else { ++ struct au_dinfo *dinfo, *tmp; ++ ++ need_wh = -ENOMEM; ++ dinfo = au_di(dentry); ++ tmp = au_di_alloc(sb, AuLsc_DI_TMP); ++ if (tmp) { ++ au_di_cp(tmp, dinfo); ++ au_di_swap(tmp, dinfo); ++ /* returns the number of positive dentries */ ++ need_wh = au_lkup_dentry(dentry, btop + 1, ++ /* AuLkup_IGNORE_PERM */ 0); ++ au_di_swap(tmp, dinfo); ++ au_rw_write_unlock(&tmp->di_rwsem); ++ au_di_free(tmp); ++ } ++ } ++ AuDbg("need_wh %d\n", need_wh); ++ err = need_wh; ++ ++out: ++ return err; ++} ++ ++/* ++ * simple tests for the del-entry operations. ++ * following the checks in vfs, plus the parent-child relationship. ++ */ ++int au_may_del(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_parent, int isdir) ++{ ++ int err; ++ umode_t h_mode; ++ struct dentry *h_dentry, *h_latest; ++ struct inode *h_inode; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (d_really_is_positive(dentry)) { ++ err = -ENOENT; ++ if (unlikely(d_is_negative(h_dentry))) ++ goto out; ++ h_inode = d_inode(h_dentry); ++ if (unlikely(!h_inode->i_nlink)) ++ goto out; ++ ++ h_mode = h_inode->i_mode; ++ if (!isdir) { ++ err = -EISDIR; ++ if (unlikely(S_ISDIR(h_mode))) ++ goto out; ++ } else if (unlikely(!S_ISDIR(h_mode))) { ++ err = -ENOTDIR; ++ goto out; ++ } ++ } else { ++ /* rename(2) case */ ++ err = -EIO; ++ if (unlikely(d_is_positive(h_dentry))) ++ goto out; ++ } ++ ++ err = -ENOENT; ++ /* expected parent dir is locked */ ++ if (unlikely(h_parent != h_dentry->d_parent)) ++ goto out; ++ err = 0; ++ ++ /* ++ * rmdir a dir may break the consistency on some filesystem. ++ * let's try heavy test. ++ */ ++ err = -EACCES; ++ if (unlikely(!au_opt_test(au_mntflags(dentry->d_sb), DIRPERM1) ++ && au_test_h_perm(d_inode(h_parent), ++ MAY_EXEC | MAY_WRITE))) ++ goto out; ++ ++ h_latest = au_sio_lkup_one(&dentry->d_name, h_parent); ++ err = -EIO; ++ if (IS_ERR(h_latest)) ++ goto out; ++ if (h_latest == h_dentry) ++ err = 0; ++ dput(h_latest); ++ ++out: ++ return err; ++} ++ ++/* ++ * decide the branch where we operate for @dentry. the branch index will be set ++ * @rbcpup. after diciding it, 'pin' it and store the timestamps of the parent ++ * dir for reverting. ++ * when a new whiteout is necessary, create it. ++ */ ++static struct dentry* ++lock_hdir_create_wh(struct dentry *dentry, int isdir, aufs_bindex_t *rbcpup, ++ struct au_dtime *dt, struct au_pin *pin) ++{ ++ struct dentry *wh_dentry; ++ struct super_block *sb; ++ struct path h_path; ++ int err, need_wh; ++ unsigned int udba; ++ aufs_bindex_t bcpup; ++ ++ need_wh = au_wr_dir_need_wh(dentry, isdir, rbcpup); ++ wh_dentry = ERR_PTR(need_wh); ++ if (unlikely(need_wh < 0)) ++ goto out; ++ ++ sb = dentry->d_sb; ++ udba = au_opt_udba(sb); ++ bcpup = *rbcpup; ++ err = au_pin(pin, dentry, bcpup, udba, ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ wh_dentry = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out; ++ ++ h_path.dentry = au_pinned_h_parent(pin); ++ if (udba != AuOpt_UDBA_NONE ++ && au_dbtop(dentry) == bcpup) { ++ err = au_may_del(dentry, bcpup, h_path.dentry, isdir); ++ wh_dentry = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out_unpin; ++ } ++ ++ h_path.mnt = au_sbr_mnt(sb, bcpup); ++ au_dtime_store(dt, au_pinned_parent(pin), &h_path); ++ wh_dentry = NULL; ++ if (!need_wh) ++ goto out; /* success, no need to create whiteout */ ++ ++ wh_dentry = au_wh_create(dentry, bcpup, h_path.dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out_unpin; ++ ++ /* returns with the parent is locked and wh_dentry is dget-ed */ ++ goto out; /* success */ ++ ++out_unpin: ++ au_unpin(pin); ++out: ++ return wh_dentry; ++} ++ ++/* ++ * when removing a dir, rename it to a unique temporary whiteout-ed name first ++ * in order to be revertible and save time for removing many child whiteouts ++ * under the dir. ++ * returns 1 when there are too many child whiteout and caller should remove ++ * them asynchronously. returns 0 when the number of children is enough small to ++ * remove now or the branch fs is a remote fs. ++ * otherwise return an error. ++ */ ++static int renwh_and_rmdir(struct dentry *dentry, aufs_bindex_t bindex, ++ struct au_nhash *whlist, struct inode *dir) ++{ ++ int rmdir_later, err, dirwh; ++ struct dentry *h_dentry; ++ struct super_block *sb; ++ struct inode *inode; ++ ++ sb = dentry->d_sb; ++ SiMustAnyLock(sb); ++ h_dentry = au_h_dptr(dentry, bindex); ++ err = au_whtmp_ren(h_dentry, au_sbr(sb, bindex)); ++ if (unlikely(err)) ++ goto out; ++ ++ /* stop monitoring */ ++ inode = d_inode(dentry); ++ au_hn_free(au_hi(inode, bindex)); ++ ++ if (!au_test_fs_remote(h_dentry->d_sb)) { ++ dirwh = au_sbi(sb)->si_dirwh; ++ rmdir_later = (dirwh <= 1); ++ if (!rmdir_later) ++ rmdir_later = au_nhash_test_longer_wh(whlist, bindex, ++ dirwh); ++ if (rmdir_later) ++ return rmdir_later; ++ } ++ ++ err = au_whtmp_rmdir(dir, bindex, h_dentry, whlist); ++ if (unlikely(err)) { ++ AuIOErr("rmdir %pd, b%d failed, %d. ignored\n", ++ h_dentry, bindex, err); ++ err = 0; ++ } ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ++ * final procedure for deleting a entry. ++ * maintain dentry and iattr. ++ */ ++static void epilog(struct inode *dir, struct dentry *dentry, ++ aufs_bindex_t bindex) ++{ ++ struct inode *inode; ++ ++ inode = d_inode(dentry); ++ d_drop(dentry); ++ inode->i_ctime = dir->i_ctime; ++ ++ au_dir_ts(dir, bindex); ++ dir->i_version++; ++} ++ ++/* ++ * when an error happened, remove the created whiteout and revert everything. ++ */ ++static int do_revert(int err, struct inode *dir, aufs_bindex_t bindex, ++ aufs_bindex_t bwh, struct dentry *wh_dentry, ++ struct dentry *dentry, struct au_dtime *dt) ++{ ++ int rerr; ++ struct path h_path = { ++ .dentry = wh_dentry, ++ .mnt = au_sbr_mnt(dir->i_sb, bindex) ++ }; ++ ++ rerr = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, dentry); ++ if (!rerr) { ++ au_set_dbwh(dentry, bwh); ++ au_dtime_revert(dt); ++ return 0; ++ } ++ ++ AuIOErr("%pd reverting whiteout failed(%d, %d)\n", dentry, err, rerr); ++ return -EIO; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int aufs_unlink(struct inode *dir, struct dentry *dentry) ++{ ++ int err; ++ aufs_bindex_t bwh, bindex, btop; ++ struct inode *inode, *h_dir, *delegated; ++ struct dentry *parent, *wh_dentry; ++ /* to reuduce stack size */ ++ struct { ++ struct au_dtime dt; ++ struct au_pin pin; ++ struct path h_path; ++ } *a; ++ ++ IMustLock(dir); ++ ++ err = -ENOMEM; ++ a = kmalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); ++ if (unlikely(err)) ++ goto out_free; ++ err = au_d_hashed_positive(dentry); ++ if (unlikely(err)) ++ goto out_unlock; ++ inode = d_inode(dentry); ++ IMustLock(inode); ++ err = -EISDIR; ++ if (unlikely(d_is_dir(dentry))) ++ goto out_unlock; /* possible? */ ++ ++ btop = au_dbtop(dentry); ++ bwh = au_dbwh(dentry); ++ bindex = -1; ++ parent = dentry->d_parent; /* dir inode is locked */ ++ di_write_lock_parent(parent); ++ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &a->dt, ++ &a->pin); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out_parent; ++ ++ a->h_path.mnt = au_sbr_mnt(dentry->d_sb, btop); ++ a->h_path.dentry = au_h_dptr(dentry, btop); ++ dget(a->h_path.dentry); ++ if (bindex == btop) { ++ h_dir = au_pinned_h_dir(&a->pin); ++ delegated = NULL; ++ err = vfsub_unlink(h_dir, &a->h_path, &delegated, /*force*/0); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal unlink\n"); ++ iput(delegated); ++ } ++ } else { ++ /* dir inode is locked */ ++ h_dir = d_inode(wh_dentry->d_parent); ++ IMustLock(h_dir); ++ err = 0; ++ } ++ ++ if (!err) { ++ vfsub_drop_nlink(inode); ++ epilog(dir, dentry, bindex); ++ ++ /* update target timestamps */ ++ if (bindex == btop) { ++ vfsub_update_h_iattr(&a->h_path, /*did*/NULL); ++ /*ignore*/ ++ inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime; ++ } else ++ /* todo: this timestamp may be reverted later */ ++ inode->i_ctime = h_dir->i_ctime; ++ goto out_unpin; /* success */ ++ } ++ ++ /* revert */ ++ if (wh_dentry) { ++ int rerr; ++ ++ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, ++ &a->dt); ++ if (rerr) ++ err = rerr; ++ } ++ ++out_unpin: ++ au_unpin(&a->pin); ++ dput(wh_dentry); ++ dput(a->h_path.dentry); ++out_parent: ++ di_write_unlock(parent); ++out_unlock: ++ aufs_read_unlock(dentry, AuLock_DW); ++out_free: ++ kfree(a); ++out: ++ return err; ++} ++ ++int aufs_rmdir(struct inode *dir, struct dentry *dentry) ++{ ++ int err, rmdir_later; ++ aufs_bindex_t bwh, bindex, btop; ++ struct inode *inode; ++ struct dentry *parent, *wh_dentry, *h_dentry; ++ struct au_whtmp_rmdir *args; ++ /* to reuduce stack size */ ++ struct { ++ struct au_dtime dt; ++ struct au_pin pin; ++ } *a; ++ ++ IMustLock(dir); ++ ++ err = -ENOMEM; ++ a = kmalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN); ++ if (unlikely(err)) ++ goto out_free; ++ err = au_alive_dir(dentry); ++ if (unlikely(err)) ++ goto out_unlock; ++ inode = d_inode(dentry); ++ IMustLock(inode); ++ err = -ENOTDIR; ++ if (unlikely(!d_is_dir(dentry))) ++ goto out_unlock; /* possible? */ ++ ++ err = -ENOMEM; ++ args = au_whtmp_rmdir_alloc(dir->i_sb, GFP_NOFS); ++ if (unlikely(!args)) ++ goto out_unlock; ++ ++ parent = dentry->d_parent; /* dir inode is locked */ ++ di_write_lock_parent(parent); ++ err = au_test_empty(dentry, &args->whlist); ++ if (unlikely(err)) ++ goto out_parent; ++ ++ btop = au_dbtop(dentry); ++ bwh = au_dbwh(dentry); ++ bindex = -1; ++ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &a->dt, ++ &a->pin); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out_parent; ++ ++ h_dentry = au_h_dptr(dentry, btop); ++ dget(h_dentry); ++ rmdir_later = 0; ++ if (bindex == btop) { ++ err = renwh_and_rmdir(dentry, btop, &args->whlist, dir); ++ if (err > 0) { ++ rmdir_later = err; ++ err = 0; ++ } ++ } else { ++ /* stop monitoring */ ++ au_hn_free(au_hi(inode, btop)); ++ ++ /* dir inode is locked */ ++ IMustLock(d_inode(wh_dentry->d_parent)); ++ err = 0; ++ } ++ ++ if (!err) { ++ vfsub_dead_dir(inode); ++ au_set_dbdiropq(dentry, -1); ++ epilog(dir, dentry, bindex); ++ ++ if (rmdir_later) { ++ au_whtmp_kick_rmdir(dir, btop, h_dentry, args); ++ args = NULL; ++ } ++ ++ goto out_unpin; /* success */ ++ } ++ ++ /* revert */ ++ AuLabel(revert); ++ if (wh_dentry) { ++ int rerr; ++ ++ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, ++ &a->dt); ++ if (rerr) ++ err = rerr; ++ } ++ ++out_unpin: ++ au_unpin(&a->pin); ++ dput(wh_dentry); ++ dput(h_dentry); ++out_parent: ++ di_write_unlock(parent); ++ if (args) ++ au_whtmp_rmdir_free(args); ++out_unlock: ++ aufs_read_unlock(dentry, AuLock_DW); ++out_free: ++ kfree(a); ++out: ++ AuTraceErr(err); ++ return err; ++} +diff --git a/fs/aufs/i_op_ren.c b/fs/aufs/i_op_ren.c +new file mode 100644 +index 00000000..9cf1d7e4 +--- /dev/null ++++ b/fs/aufs/i_op_ren.c +@@ -0,0 +1,1246 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * inode operation (rename entry) ++ * todo: this is crazy monster ++ */ ++ ++#include "aufs.h" ++ ++enum { AuSRC, AuDST, AuSrcDst }; ++enum { AuPARENT, AuCHILD, AuParentChild }; ++ ++#define AuRen_ISDIR_SRC 1 ++#define AuRen_ISDIR_DST (1 << 1) ++#define AuRen_ISSAMEDIR (1 << 2) ++#define AuRen_WHSRC (1 << 3) ++#define AuRen_WHDST (1 << 4) ++#define AuRen_MNT_WRITE (1 << 5) ++#define AuRen_DT_DSTDIR (1 << 6) ++#define AuRen_DIROPQ_SRC (1 << 7) ++#define AuRen_DIROPQ_DST (1 << 8) ++#define AuRen_DIRREN (1 << 9) ++#define AuRen_DROPPED_SRC (1 << 10) ++#define AuRen_DROPPED_DST (1 << 11) ++#define au_ftest_ren(flags, name) ((flags) & AuRen_##name) ++#define au_fset_ren(flags, name) \ ++ do { (flags) |= AuRen_##name; } while (0) ++#define au_fclr_ren(flags, name) \ ++ do { (flags) &= ~AuRen_##name; } while (0) ++ ++#ifndef CONFIG_AUFS_DIRREN ++#undef AuRen_DIRREN ++#define AuRen_DIRREN 0 ++#endif ++ ++struct au_ren_args { ++ struct { ++ struct dentry *dentry, *h_dentry, *parent, *h_parent, ++ *wh_dentry; ++ struct inode *dir, *inode; ++ struct au_hinode *hdir, *hinode; ++ struct au_dtime dt[AuParentChild]; ++ aufs_bindex_t btop, bdiropq; ++ } sd[AuSrcDst]; ++ ++#define src_dentry sd[AuSRC].dentry ++#define src_dir sd[AuSRC].dir ++#define src_inode sd[AuSRC].inode ++#define src_h_dentry sd[AuSRC].h_dentry ++#define src_parent sd[AuSRC].parent ++#define src_h_parent sd[AuSRC].h_parent ++#define src_wh_dentry sd[AuSRC].wh_dentry ++#define src_hdir sd[AuSRC].hdir ++#define src_hinode sd[AuSRC].hinode ++#define src_h_dir sd[AuSRC].hdir->hi_inode ++#define src_dt sd[AuSRC].dt ++#define src_btop sd[AuSRC].btop ++#define src_bdiropq sd[AuSRC].bdiropq ++ ++#define dst_dentry sd[AuDST].dentry ++#define dst_dir sd[AuDST].dir ++#define dst_inode sd[AuDST].inode ++#define dst_h_dentry sd[AuDST].h_dentry ++#define dst_parent sd[AuDST].parent ++#define dst_h_parent sd[AuDST].h_parent ++#define dst_wh_dentry sd[AuDST].wh_dentry ++#define dst_hdir sd[AuDST].hdir ++#define dst_hinode sd[AuDST].hinode ++#define dst_h_dir sd[AuDST].hdir->hi_inode ++#define dst_dt sd[AuDST].dt ++#define dst_btop sd[AuDST].btop ++#define dst_bdiropq sd[AuDST].bdiropq ++ ++ struct dentry *h_trap; ++ struct au_branch *br; ++ struct path h_path; ++ struct au_nhash whlist; ++ aufs_bindex_t btgt, src_bwh; ++ ++ struct { ++ unsigned short auren_flags; ++ unsigned char flags; /* syscall parameter */ ++ unsigned char exchange; ++ } __packed; ++ ++ struct au_whtmp_rmdir *thargs; ++ struct dentry *h_dst; ++ struct au_hinode *h_root; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * functions for reverting. ++ * when an error happened in a single rename systemcall, we should revert ++ * everything as if nothing happened. ++ * we don't need to revert the copied-up/down the parent dir since they are ++ * harmless. ++ */ ++ ++#define RevertFailure(fmt, ...) do { \ ++ AuIOErr("revert failure: " fmt " (%d, %d)\n", \ ++ ##__VA_ARGS__, err, rerr); \ ++ err = -EIO; \ ++} while (0) ++ ++static void au_ren_do_rev_diropq(int err, struct au_ren_args *a, int idx) ++{ ++ int rerr; ++ struct dentry *d; ++#define src_or_dst(member) a->sd[idx].member ++ ++ d = src_or_dst(dentry); /* {src,dst}_dentry */ ++ au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD); ++ rerr = au_diropq_remove(d, a->btgt); ++ au_hn_inode_unlock(src_or_dst(hinode)); ++ au_set_dbdiropq(d, src_or_dst(bdiropq)); ++ if (rerr) ++ RevertFailure("remove diropq %pd", d); ++ ++#undef src_or_dst_ ++} ++ ++static void au_ren_rev_diropq(int err, struct au_ren_args *a) ++{ ++ if (au_ftest_ren(a->auren_flags, DIROPQ_SRC)) ++ au_ren_do_rev_diropq(err, a, AuSRC); ++ if (au_ftest_ren(a->auren_flags, DIROPQ_DST)) ++ au_ren_do_rev_diropq(err, a, AuDST); ++} ++ ++static void au_ren_rev_rename(int err, struct au_ren_args *a) ++{ ++ int rerr; ++ struct inode *delegated; ++ ++ a->h_path.dentry = vfsub_lkup_one(&a->src_dentry->d_name, ++ a->src_h_parent); ++ rerr = PTR_ERR(a->h_path.dentry); ++ if (IS_ERR(a->h_path.dentry)) { ++ RevertFailure("lkup one %pd", a->src_dentry); ++ return; ++ } ++ ++ delegated = NULL; ++ rerr = vfsub_rename(a->dst_h_dir, ++ au_h_dptr(a->src_dentry, a->btgt), ++ a->src_h_dir, &a->h_path, &delegated, a->flags); ++ if (unlikely(rerr == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal rename\n"); ++ iput(delegated); ++ } ++ d_drop(a->h_path.dentry); ++ dput(a->h_path.dentry); ++ /* au_set_h_dptr(a->src_dentry, a->btgt, NULL); */ ++ if (rerr) ++ RevertFailure("rename %pd", a->src_dentry); ++} ++ ++static void au_ren_rev_whtmp(int err, struct au_ren_args *a) ++{ ++ int rerr; ++ struct inode *delegated; ++ ++ a->h_path.dentry = vfsub_lkup_one(&a->dst_dentry->d_name, ++ a->dst_h_parent); ++ rerr = PTR_ERR(a->h_path.dentry); ++ if (IS_ERR(a->h_path.dentry)) { ++ RevertFailure("lkup one %pd", a->dst_dentry); ++ return; ++ } ++ if (d_is_positive(a->h_path.dentry)) { ++ d_drop(a->h_path.dentry); ++ dput(a->h_path.dentry); ++ return; ++ } ++ ++ delegated = NULL; ++ rerr = vfsub_rename(a->dst_h_dir, a->h_dst, a->dst_h_dir, &a->h_path, ++ &delegated, a->flags); ++ if (unlikely(rerr == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal rename\n"); ++ iput(delegated); ++ } ++ d_drop(a->h_path.dentry); ++ dput(a->h_path.dentry); ++ if (!rerr) ++ au_set_h_dptr(a->dst_dentry, a->btgt, dget(a->h_dst)); ++ else ++ RevertFailure("rename %pd", a->h_dst); ++} ++ ++static void au_ren_rev_whsrc(int err, struct au_ren_args *a) ++{ ++ int rerr; ++ ++ a->h_path.dentry = a->src_wh_dentry; ++ rerr = au_wh_unlink_dentry(a->src_h_dir, &a->h_path, a->src_dentry); ++ au_set_dbwh(a->src_dentry, a->src_bwh); ++ if (rerr) ++ RevertFailure("unlink %pd", a->src_wh_dentry); ++} ++#undef RevertFailure ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * when we have to copyup the renaming entry, do it with the rename-target name ++ * in order to minimize the cost (the later actual rename is unnecessary). ++ * otherwise rename it on the target branch. ++ */ ++static int au_ren_or_cpup(struct au_ren_args *a) ++{ ++ int err; ++ struct dentry *d; ++ struct inode *delegated; ++ ++ d = a->src_dentry; ++ if (au_dbtop(d) == a->btgt) { ++ a->h_path.dentry = a->dst_h_dentry; ++ AuDebugOn(au_dbtop(d) != a->btgt); ++ delegated = NULL; ++ err = vfsub_rename(a->src_h_dir, au_h_dptr(d, a->btgt), ++ a->dst_h_dir, &a->h_path, &delegated, ++ a->flags); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal rename\n"); ++ iput(delegated); ++ } ++ } else ++ BUG(); ++ ++ if (!err && a->h_dst) ++ /* it will be set to dinfo later */ ++ dget(a->h_dst); ++ ++ return err; ++} ++ ++/* cf. aufs_rmdir() */ ++static int au_ren_del_whtmp(struct au_ren_args *a) ++{ ++ int err; ++ struct inode *dir; ++ ++ dir = a->dst_dir; ++ SiMustAnyLock(dir->i_sb); ++ if (!au_nhash_test_longer_wh(&a->whlist, a->btgt, ++ au_sbi(dir->i_sb)->si_dirwh) ++ || au_test_fs_remote(a->h_dst->d_sb)) { ++ err = au_whtmp_rmdir(dir, a->btgt, a->h_dst, &a->whlist); ++ if (unlikely(err)) ++ pr_warn("failed removing whtmp dir %pd (%d), " ++ "ignored.\n", a->h_dst, err); ++ } else { ++ au_nhash_wh_free(&a->thargs->whlist); ++ a->thargs->whlist = a->whlist; ++ a->whlist.nh_num = 0; ++ au_whtmp_kick_rmdir(dir, a->btgt, a->h_dst, a->thargs); ++ dput(a->h_dst); ++ a->thargs = NULL; ++ } ++ ++ return 0; ++} ++ ++/* make it 'opaque' dir. */ ++static int au_ren_do_diropq(struct au_ren_args *a, int idx) ++{ ++ int err; ++ struct dentry *d, *diropq; ++#define src_or_dst(member) a->sd[idx].member ++ ++ err = 0; ++ d = src_or_dst(dentry); /* {src,dst}_dentry */ ++ src_or_dst(bdiropq) = au_dbdiropq(d); ++ src_or_dst(hinode) = au_hi(src_or_dst(inode), a->btgt); ++ au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD); ++ diropq = au_diropq_create(d, a->btgt); ++ au_hn_inode_unlock(src_or_dst(hinode)); ++ if (IS_ERR(diropq)) ++ err = PTR_ERR(diropq); ++ else ++ dput(diropq); ++ ++#undef src_or_dst_ ++ return err; ++} ++ ++static int au_ren_diropq(struct au_ren_args *a) ++{ ++ int err; ++ unsigned char always; ++ struct dentry *d; ++ ++ err = 0; ++ d = a->dst_dentry; /* already renamed on the branch */ ++ always = !!au_opt_test(au_mntflags(d->d_sb), ALWAYS_DIROPQ); ++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC) ++ && !au_ftest_ren(a->auren_flags, DIRREN) ++ && a->btgt != au_dbdiropq(a->src_dentry) ++ && (a->dst_wh_dentry ++ || a->btgt <= au_dbdiropq(d) ++ /* hide the lower to keep xino */ ++ /* the lowers may not be a dir, but we hide them anyway */ ++ || a->btgt < au_dbbot(d) ++ || always)) { ++ AuDbg("here\n"); ++ err = au_ren_do_diropq(a, AuSRC); ++ if (unlikely(err)) ++ goto out; ++ au_fset_ren(a->auren_flags, DIROPQ_SRC); ++ } ++ if (!a->exchange) ++ goto out; /* success */ ++ ++ d = a->src_dentry; /* already renamed on the branch */ ++ if (au_ftest_ren(a->auren_flags, ISDIR_DST) ++ && a->btgt != au_dbdiropq(a->dst_dentry) ++ && (a->btgt < au_dbdiropq(d) ++ || a->btgt < au_dbbot(d) ++ || always)) { ++ AuDbgDentry(a->src_dentry); ++ AuDbgDentry(a->dst_dentry); ++ err = au_ren_do_diropq(a, AuDST); ++ if (unlikely(err)) ++ goto out_rev_src; ++ au_fset_ren(a->auren_flags, DIROPQ_DST); ++ } ++ goto out; /* success */ ++ ++out_rev_src: ++ AuDbg("err %d, reverting src\n", err); ++ au_ren_rev_diropq(err, a); ++out: ++ return err; ++} ++ ++static int do_rename(struct au_ren_args *a) ++{ ++ int err; ++ struct dentry *d, *h_d; ++ ++ if (!a->exchange) { ++ /* prepare workqueue args for asynchronous rmdir */ ++ h_d = a->dst_h_dentry; ++ if (au_ftest_ren(a->auren_flags, ISDIR_DST) ++ /* && !au_ftest_ren(a->auren_flags, DIRREN) */ ++ && d_is_positive(h_d)) { ++ err = -ENOMEM; ++ a->thargs = au_whtmp_rmdir_alloc(a->src_dentry->d_sb, ++ GFP_NOFS); ++ if (unlikely(!a->thargs)) ++ goto out; ++ a->h_dst = dget(h_d); ++ } ++ ++ /* create whiteout for src_dentry */ ++ if (au_ftest_ren(a->auren_flags, WHSRC)) { ++ a->src_bwh = au_dbwh(a->src_dentry); ++ AuDebugOn(a->src_bwh >= 0); ++ a->src_wh_dentry = au_wh_create(a->src_dentry, a->btgt, ++ a->src_h_parent); ++ err = PTR_ERR(a->src_wh_dentry); ++ if (IS_ERR(a->src_wh_dentry)) ++ goto out_thargs; ++ } ++ ++ /* lookup whiteout for dentry */ ++ if (au_ftest_ren(a->auren_flags, WHDST)) { ++ h_d = au_wh_lkup(a->dst_h_parent, ++ &a->dst_dentry->d_name, a->br); ++ err = PTR_ERR(h_d); ++ if (IS_ERR(h_d)) ++ goto out_whsrc; ++ if (d_is_negative(h_d)) ++ dput(h_d); ++ else ++ a->dst_wh_dentry = h_d; ++ } ++ ++ /* rename dentry to tmpwh */ ++ if (a->thargs) { ++ err = au_whtmp_ren(a->dst_h_dentry, a->br); ++ if (unlikely(err)) ++ goto out_whdst; ++ ++ d = a->dst_dentry; ++ au_set_h_dptr(d, a->btgt, NULL); ++ err = au_lkup_neg(d, a->btgt, /*wh*/0); ++ if (unlikely(err)) ++ goto out_whtmp; ++ a->dst_h_dentry = au_h_dptr(d, a->btgt); ++ } ++ } ++ ++ BUG_ON(d_is_positive(a->dst_h_dentry) && a->src_btop != a->btgt); ++#if 0 ++ BUG_ON(!au_ftest_ren(a->auren_flags, DIRREN) ++ && d_is_positive(a->dst_h_dentry) ++ && a->src_btop != a->btgt); ++#endif ++ ++ /* rename by vfs_rename or cpup */ ++ err = au_ren_or_cpup(a); ++ if (unlikely(err)) ++ /* leave the copied-up one */ ++ goto out_whtmp; ++ ++ /* make dir opaque */ ++ err = au_ren_diropq(a); ++ if (unlikely(err)) ++ goto out_rename; ++ ++ /* update target timestamps */ ++ if (a->exchange) { ++ AuDebugOn(au_dbtop(a->dst_dentry) != a->btgt); ++ a->h_path.dentry = au_h_dptr(a->dst_dentry, a->btgt); ++ vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/ ++ a->dst_inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime; ++ } ++ AuDebugOn(au_dbtop(a->src_dentry) != a->btgt); ++ a->h_path.dentry = au_h_dptr(a->src_dentry, a->btgt); ++ vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/ ++ a->src_inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime; ++ ++ if (!a->exchange) { ++ /* remove whiteout for dentry */ ++ if (a->dst_wh_dentry) { ++ a->h_path.dentry = a->dst_wh_dentry; ++ err = au_wh_unlink_dentry(a->dst_h_dir, &a->h_path, ++ a->dst_dentry); ++ if (unlikely(err)) ++ goto out_diropq; ++ } ++ ++ /* remove whtmp */ ++ if (a->thargs) ++ au_ren_del_whtmp(a); /* ignore this error */ ++ ++ au_fhsm_wrote(a->src_dentry->d_sb, a->btgt, /*force*/0); ++ } ++ err = 0; ++ goto out_success; ++ ++out_diropq: ++ au_ren_rev_diropq(err, a); ++out_rename: ++ au_ren_rev_rename(err, a); ++ dput(a->h_dst); ++out_whtmp: ++ if (a->thargs) ++ au_ren_rev_whtmp(err, a); ++out_whdst: ++ dput(a->dst_wh_dentry); ++ a->dst_wh_dentry = NULL; ++out_whsrc: ++ if (a->src_wh_dentry) ++ au_ren_rev_whsrc(err, a); ++out_success: ++ dput(a->src_wh_dentry); ++ dput(a->dst_wh_dentry); ++out_thargs: ++ if (a->thargs) { ++ dput(a->h_dst); ++ au_whtmp_rmdir_free(a->thargs); ++ a->thargs = NULL; ++ } ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * test if @dentry dir can be rename destination or not. ++ * success means, it is a logically empty dir. ++ */ ++static int may_rename_dstdir(struct dentry *dentry, struct au_nhash *whlist) ++{ ++ return au_test_empty(dentry, whlist); ++} ++ ++/* ++ * test if @a->src_dentry dir can be rename source or not. ++ * if it can, return 0. ++ * success means, ++ * - it is a logically empty dir. ++ * - or, it exists on writable branch and has no children including whiteouts ++ * on the lower branch unless DIRREN is on. ++ */ ++static int may_rename_srcdir(struct au_ren_args *a) ++{ ++ int err; ++ unsigned int rdhash; ++ aufs_bindex_t btop, btgt; ++ struct dentry *dentry; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ ++ dentry = a->src_dentry; ++ sb = dentry->d_sb; ++ sbinfo = au_sbi(sb); ++ if (au_opt_test(sbinfo->si_mntflags, DIRREN)) ++ au_fset_ren(a->auren_flags, DIRREN); ++ ++ btgt = a->btgt; ++ btop = au_dbtop(dentry); ++ if (btop != btgt) { ++ struct au_nhash whlist; ++ ++ SiMustAnyLock(sb); ++ rdhash = sbinfo->si_rdhash; ++ if (!rdhash) ++ rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, ++ dentry)); ++ err = au_nhash_alloc(&whlist, rdhash, GFP_NOFS); ++ if (unlikely(err)) ++ goto out; ++ err = au_test_empty(dentry, &whlist); ++ au_nhash_wh_free(&whlist); ++ goto out; ++ } ++ ++ if (btop == au_dbtaildir(dentry)) ++ return 0; /* success */ ++ ++ err = au_test_empty_lower(dentry); ++ ++out: ++ if (err == -ENOTEMPTY) { ++ if (au_ftest_ren(a->auren_flags, DIRREN)) { ++ err = 0; ++ } else { ++ AuWarn1("renaming dir who has child(ren) on multiple " ++ "branches, is not supported\n"); ++ err = -EXDEV; ++ } ++ } ++ return err; ++} ++ ++/* side effect: sets whlist and h_dentry */ ++static int au_ren_may_dir(struct au_ren_args *a) ++{ ++ int err; ++ unsigned int rdhash; ++ struct dentry *d; ++ ++ d = a->dst_dentry; ++ SiMustAnyLock(d->d_sb); ++ ++ err = 0; ++ if (au_ftest_ren(a->auren_flags, ISDIR_DST) && a->dst_inode) { ++ rdhash = au_sbi(d->d_sb)->si_rdhash; ++ if (!rdhash) ++ rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, d)); ++ err = au_nhash_alloc(&a->whlist, rdhash, GFP_NOFS); ++ if (unlikely(err)) ++ goto out; ++ ++ if (!a->exchange) { ++ au_set_dbtop(d, a->dst_btop); ++ err = may_rename_dstdir(d, &a->whlist); ++ au_set_dbtop(d, a->btgt); ++ } else ++ err = may_rename_srcdir(a); ++ } ++ a->dst_h_dentry = au_h_dptr(d, au_dbtop(d)); ++ if (unlikely(err)) ++ goto out; ++ ++ d = a->src_dentry; ++ a->src_h_dentry = au_h_dptr(d, au_dbtop(d)); ++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) { ++ err = may_rename_srcdir(a); ++ if (unlikely(err)) { ++ au_nhash_wh_free(&a->whlist); ++ a->whlist.nh_num = 0; ++ } ++ } ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * simple tests for rename. ++ * following the checks in vfs, plus the parent-child relationship. ++ */ ++static int au_may_ren(struct au_ren_args *a) ++{ ++ int err, isdir; ++ struct inode *h_inode; ++ ++ if (a->src_btop == a->btgt) { ++ err = au_may_del(a->src_dentry, a->btgt, a->src_h_parent, ++ au_ftest_ren(a->auren_flags, ISDIR_SRC)); ++ if (unlikely(err)) ++ goto out; ++ err = -EINVAL; ++ if (unlikely(a->src_h_dentry == a->h_trap)) ++ goto out; ++ } ++ ++ err = 0; ++ if (a->dst_btop != a->btgt) ++ goto out; ++ ++ err = -ENOTEMPTY; ++ if (unlikely(a->dst_h_dentry == a->h_trap)) ++ goto out; ++ ++ err = -EIO; ++ isdir = !!au_ftest_ren(a->auren_flags, ISDIR_DST); ++ if (d_really_is_negative(a->dst_dentry)) { ++ if (d_is_negative(a->dst_h_dentry)) ++ err = au_may_add(a->dst_dentry, a->btgt, ++ a->dst_h_parent, isdir); ++ } else { ++ if (unlikely(d_is_negative(a->dst_h_dentry))) ++ goto out; ++ h_inode = d_inode(a->dst_h_dentry); ++ if (h_inode->i_nlink) ++ err = au_may_del(a->dst_dentry, a->btgt, ++ a->dst_h_parent, isdir); ++ } ++ ++out: ++ if (unlikely(err == -ENOENT || err == -EEXIST)) ++ err = -EIO; ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * locking order ++ * (VFS) ++ * - src_dir and dir by lock_rename() ++ * - inode if exitsts ++ * (aufs) ++ * - lock all ++ * + src_dentry and dentry by aufs_read_and_write_lock2() which calls, ++ * + si_read_lock ++ * + di_write_lock2_child() ++ * + di_write_lock_child() ++ * + ii_write_lock_child() ++ * + di_write_lock_child2() ++ * + ii_write_lock_child2() ++ * + src_parent and parent ++ * + di_write_lock_parent() ++ * + ii_write_lock_parent() ++ * + di_write_lock_parent2() ++ * + ii_write_lock_parent2() ++ * + lower src_dir and dir by vfsub_lock_rename() ++ * + verify the every relationships between child and parent. if any ++ * of them failed, unlock all and return -EBUSY. ++ */ ++static void au_ren_unlock(struct au_ren_args *a) ++{ ++ vfsub_unlock_rename(a->src_h_parent, a->src_hdir, ++ a->dst_h_parent, a->dst_hdir); ++ if (au_ftest_ren(a->auren_flags, DIRREN) ++ && a->h_root) ++ au_hn_inode_unlock(a->h_root); ++ if (au_ftest_ren(a->auren_flags, MNT_WRITE)) ++ vfsub_mnt_drop_write(au_br_mnt(a->br)); ++} ++ ++static int au_ren_lock(struct au_ren_args *a) ++{ ++ int err; ++ unsigned int udba; ++ ++ err = 0; ++ a->src_h_parent = au_h_dptr(a->src_parent, a->btgt); ++ a->src_hdir = au_hi(a->src_dir, a->btgt); ++ a->dst_h_parent = au_h_dptr(a->dst_parent, a->btgt); ++ a->dst_hdir = au_hi(a->dst_dir, a->btgt); ++ ++ err = vfsub_mnt_want_write(au_br_mnt(a->br)); ++ if (unlikely(err)) ++ goto out; ++ au_fset_ren(a->auren_flags, MNT_WRITE); ++ if (au_ftest_ren(a->auren_flags, DIRREN)) { ++ struct dentry *root; ++ struct inode *dir; ++ ++ /* ++ * sbinfo is already locked, so this ii_read_lock is ++ * unnecessary. but our debugging feature checks it. ++ */ ++ root = a->src_inode->i_sb->s_root; ++ if (root != a->src_parent && root != a->dst_parent) { ++ dir = d_inode(root); ++ ii_read_lock_parent3(dir); ++ a->h_root = au_hi(dir, a->btgt); ++ ii_read_unlock(dir); ++ au_hn_inode_lock_nested(a->h_root, AuLsc_I_PARENT3); ++ } ++ } ++ a->h_trap = vfsub_lock_rename(a->src_h_parent, a->src_hdir, ++ a->dst_h_parent, a->dst_hdir); ++ udba = au_opt_udba(a->src_dentry->d_sb); ++ if (unlikely(a->src_hdir->hi_inode != d_inode(a->src_h_parent) ++ || a->dst_hdir->hi_inode != d_inode(a->dst_h_parent))) ++ err = au_busy_or_stale(); ++ if (!err && au_dbtop(a->src_dentry) == a->btgt) ++ err = au_h_verify(a->src_h_dentry, udba, ++ d_inode(a->src_h_parent), a->src_h_parent, ++ a->br); ++ if (!err && au_dbtop(a->dst_dentry) == a->btgt) ++ err = au_h_verify(a->dst_h_dentry, udba, ++ d_inode(a->dst_h_parent), a->dst_h_parent, ++ a->br); ++ if (!err) ++ goto out; /* success */ ++ ++ err = au_busy_or_stale(); ++ au_ren_unlock(a); ++ ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void au_ren_refresh_dir(struct au_ren_args *a) ++{ ++ struct inode *dir; ++ ++ dir = a->dst_dir; ++ dir->i_version++; ++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) { ++ /* is this updating defined in POSIX? */ ++ au_cpup_attr_timesizes(a->src_inode); ++ au_cpup_attr_nlink(dir, /*force*/1); ++ } ++ au_dir_ts(dir, a->btgt); ++ ++ if (a->exchange) { ++ dir = a->src_dir; ++ dir->i_version++; ++ if (au_ftest_ren(a->auren_flags, ISDIR_DST)) { ++ /* is this updating defined in POSIX? */ ++ au_cpup_attr_timesizes(a->dst_inode); ++ au_cpup_attr_nlink(dir, /*force*/1); ++ } ++ au_dir_ts(dir, a->btgt); ++ } ++ ++ if (au_ftest_ren(a->auren_flags, ISSAMEDIR)) ++ return; ++ ++ dir = a->src_dir; ++ dir->i_version++; ++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) ++ au_cpup_attr_nlink(dir, /*force*/1); ++ au_dir_ts(dir, a->btgt); ++} ++ ++static void au_ren_refresh(struct au_ren_args *a) ++{ ++ aufs_bindex_t bbot, bindex; ++ struct dentry *d, *h_d; ++ struct inode *i, *h_i; ++ struct super_block *sb; ++ ++ d = a->dst_dentry; ++ d_drop(d); ++ if (a->h_dst) ++ /* already dget-ed by au_ren_or_cpup() */ ++ au_set_h_dptr(d, a->btgt, a->h_dst); ++ ++ i = a->dst_inode; ++ if (i) { ++ if (!a->exchange) { ++ if (!au_ftest_ren(a->auren_flags, ISDIR_DST)) ++ vfsub_drop_nlink(i); ++ else { ++ vfsub_dead_dir(i); ++ au_cpup_attr_timesizes(i); ++ } ++ au_update_dbrange(d, /*do_put_zero*/1); ++ } else ++ au_cpup_attr_nlink(i, /*force*/1); ++ } else { ++ bbot = a->btgt; ++ for (bindex = au_dbtop(d); bindex < bbot; bindex++) ++ au_set_h_dptr(d, bindex, NULL); ++ bbot = au_dbbot(d); ++ for (bindex = a->btgt + 1; bindex <= bbot; bindex++) ++ au_set_h_dptr(d, bindex, NULL); ++ au_update_dbrange(d, /*do_put_zero*/0); ++ } ++ ++ if (a->exchange ++ || au_ftest_ren(a->auren_flags, DIRREN)) { ++ d_drop(a->src_dentry); ++ if (au_ftest_ren(a->auren_flags, DIRREN)) ++ au_set_dbwh(a->src_dentry, -1); ++ return; ++ } ++ ++ d = a->src_dentry; ++ au_set_dbwh(d, -1); ++ bbot = au_dbbot(d); ++ for (bindex = a->btgt + 1; bindex <= bbot; bindex++) { ++ h_d = au_h_dptr(d, bindex); ++ if (h_d) ++ au_set_h_dptr(d, bindex, NULL); ++ } ++ au_set_dbbot(d, a->btgt); ++ ++ sb = d->d_sb; ++ i = a->src_inode; ++ if (au_opt_test(au_mntflags(sb), PLINK) && au_plink_test(i)) ++ return; /* success */ ++ ++ bbot = au_ibbot(i); ++ for (bindex = a->btgt + 1; bindex <= bbot; bindex++) { ++ h_i = au_h_iptr(i, bindex); ++ if (h_i) { ++ au_xino_write(sb, bindex, h_i->i_ino, /*ino*/0); ++ /* ignore this error */ ++ au_set_h_iptr(i, bindex, NULL, 0); ++ } ++ } ++ au_set_ibbot(i, a->btgt); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* mainly for link(2) and rename(2) */ ++int au_wbr(struct dentry *dentry, aufs_bindex_t btgt) ++{ ++ aufs_bindex_t bdiropq, bwh; ++ struct dentry *parent; ++ struct au_branch *br; ++ ++ parent = dentry->d_parent; ++ IMustLock(d_inode(parent)); /* dir is locked */ ++ ++ bdiropq = au_dbdiropq(parent); ++ bwh = au_dbwh(dentry); ++ br = au_sbr(dentry->d_sb, btgt); ++ if (au_br_rdonly(br) ++ || (0 <= bdiropq && bdiropq < btgt) ++ || (0 <= bwh && bwh < btgt)) ++ btgt = -1; ++ ++ AuDbg("btgt %d\n", btgt); ++ return btgt; ++} ++ ++/* sets src_btop, dst_btop and btgt */ ++static int au_ren_wbr(struct au_ren_args *a) ++{ ++ int err; ++ struct au_wr_dir_args wr_dir_args = { ++ /* .force_btgt = -1, */ ++ .flags = AuWrDir_ADD_ENTRY ++ }; ++ ++ a->src_btop = au_dbtop(a->src_dentry); ++ a->dst_btop = au_dbtop(a->dst_dentry); ++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC) ++ || au_ftest_ren(a->auren_flags, ISDIR_DST)) ++ au_fset_wrdir(wr_dir_args.flags, ISDIR); ++ wr_dir_args.force_btgt = a->src_btop; ++ if (a->dst_inode && a->dst_btop < a->src_btop) ++ wr_dir_args.force_btgt = a->dst_btop; ++ wr_dir_args.force_btgt = au_wbr(a->dst_dentry, wr_dir_args.force_btgt); ++ err = au_wr_dir(a->dst_dentry, a->src_dentry, &wr_dir_args); ++ a->btgt = err; ++ if (a->exchange) ++ au_update_dbtop(a->dst_dentry); ++ ++ return err; ++} ++ ++static void au_ren_dt(struct au_ren_args *a) ++{ ++ a->h_path.dentry = a->src_h_parent; ++ au_dtime_store(a->src_dt + AuPARENT, a->src_parent, &a->h_path); ++ if (!au_ftest_ren(a->auren_flags, ISSAMEDIR)) { ++ a->h_path.dentry = a->dst_h_parent; ++ au_dtime_store(a->dst_dt + AuPARENT, a->dst_parent, &a->h_path); ++ } ++ ++ au_fclr_ren(a->auren_flags, DT_DSTDIR); ++ if (!au_ftest_ren(a->auren_flags, ISDIR_SRC) ++ && !a->exchange) ++ return; ++ ++ a->h_path.dentry = a->src_h_dentry; ++ au_dtime_store(a->src_dt + AuCHILD, a->src_dentry, &a->h_path); ++ if (d_is_positive(a->dst_h_dentry)) { ++ au_fset_ren(a->auren_flags, DT_DSTDIR); ++ a->h_path.dentry = a->dst_h_dentry; ++ au_dtime_store(a->dst_dt + AuCHILD, a->dst_dentry, &a->h_path); ++ } ++} ++ ++static void au_ren_rev_dt(int err, struct au_ren_args *a) ++{ ++ struct dentry *h_d; ++ struct inode *h_inode; ++ ++ au_dtime_revert(a->src_dt + AuPARENT); ++ if (!au_ftest_ren(a->auren_flags, ISSAMEDIR)) ++ au_dtime_revert(a->dst_dt + AuPARENT); ++ ++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC) && err != -EIO) { ++ h_d = a->src_dt[AuCHILD].dt_h_path.dentry; ++ h_inode = d_inode(h_d); ++ inode_lock_nested(h_inode, AuLsc_I_CHILD); ++ au_dtime_revert(a->src_dt + AuCHILD); ++ inode_unlock(h_inode); ++ ++ if (au_ftest_ren(a->auren_flags, DT_DSTDIR)) { ++ h_d = a->dst_dt[AuCHILD].dt_h_path.dentry; ++ h_inode = d_inode(h_d); ++ inode_lock_nested(h_inode, AuLsc_I_CHILD); ++ au_dtime_revert(a->dst_dt + AuCHILD); ++ inode_unlock(h_inode); ++ } ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int aufs_rename(struct inode *_src_dir, struct dentry *_src_dentry, ++ struct inode *_dst_dir, struct dentry *_dst_dentry, ++ unsigned int _flags) ++{ ++ int err, lock_flags; ++ void *rev; ++ /* reduce stack space */ ++ struct au_ren_args *a; ++ struct au_pin pin; ++ ++ AuDbg("%pd, %pd, 0x%x\n", _src_dentry, _dst_dentry, _flags); ++ IMustLock(_src_dir); ++ IMustLock(_dst_dir); ++ ++ err = -EINVAL; ++ if (unlikely(_flags & RENAME_WHITEOUT)) ++ goto out; ++ ++ err = -ENOMEM; ++ BUILD_BUG_ON(sizeof(*a) > PAGE_SIZE); ++ a = kzalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ a->flags = _flags; ++ a->exchange = _flags & RENAME_EXCHANGE; ++ a->src_dir = _src_dir; ++ a->src_dentry = _src_dentry; ++ a->src_inode = NULL; ++ if (d_really_is_positive(a->src_dentry)) ++ a->src_inode = d_inode(a->src_dentry); ++ a->src_parent = a->src_dentry->d_parent; /* dir inode is locked */ ++ a->dst_dir = _dst_dir; ++ a->dst_dentry = _dst_dentry; ++ a->dst_inode = NULL; ++ if (d_really_is_positive(a->dst_dentry)) ++ a->dst_inode = d_inode(a->dst_dentry); ++ a->dst_parent = a->dst_dentry->d_parent; /* dir inode is locked */ ++ if (a->dst_inode) { ++ /* ++ * if EXCHANGE && src is non-dir && dst is dir, ++ * dst is not locked. ++ */ ++ /* IMustLock(a->dst_inode); */ ++ au_igrab(a->dst_inode); ++ } ++ ++ err = -ENOTDIR; ++ lock_flags = AuLock_FLUSH | AuLock_NOPLM | AuLock_GEN; ++ if (d_is_dir(a->src_dentry)) { ++ au_fset_ren(a->auren_flags, ISDIR_SRC); ++ if (unlikely(!a->exchange ++ && d_really_is_positive(a->dst_dentry) ++ && !d_is_dir(a->dst_dentry))) ++ goto out_free; ++ lock_flags |= AuLock_DIRS; ++ } ++ if (a->dst_inode && d_is_dir(a->dst_dentry)) { ++ au_fset_ren(a->auren_flags, ISDIR_DST); ++ if (unlikely(!a->exchange ++ && d_really_is_positive(a->src_dentry) ++ && !d_is_dir(a->src_dentry))) ++ goto out_free; ++ lock_flags |= AuLock_DIRS; ++ } ++ err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry, ++ lock_flags); ++ if (unlikely(err)) ++ goto out_free; ++ ++ err = au_d_hashed_positive(a->src_dentry); ++ if (unlikely(err)) ++ goto out_unlock; ++ err = -ENOENT; ++ if (a->dst_inode) { ++ /* ++ * If it is a dir, VFS unhash it before this ++ * function. It means we cannot rely upon d_unhashed(). ++ */ ++ if (unlikely(!a->dst_inode->i_nlink)) ++ goto out_unlock; ++ if (!au_ftest_ren(a->auren_flags, ISDIR_DST)) { ++ err = au_d_hashed_positive(a->dst_dentry); ++ if (unlikely(err && !a->exchange)) ++ goto out_unlock; ++ } else if (unlikely(IS_DEADDIR(a->dst_inode))) ++ goto out_unlock; ++ } else if (unlikely(d_unhashed(a->dst_dentry))) ++ goto out_unlock; ++ ++ /* ++ * is it possible? ++ * yes, it happened (in linux-3.3-rcN) but I don't know why. ++ * there may exist a problem somewhere else. ++ */ ++ err = -EINVAL; ++ if (unlikely(d_inode(a->dst_parent) == d_inode(a->src_dentry))) ++ goto out_unlock; ++ ++ au_fset_ren(a->auren_flags, ISSAMEDIR); /* temporary */ ++ di_write_lock_parent(a->dst_parent); ++ ++ /* which branch we process */ ++ err = au_ren_wbr(a); ++ if (unlikely(err < 0)) ++ goto out_parent; ++ a->br = au_sbr(a->dst_dentry->d_sb, a->btgt); ++ a->h_path.mnt = au_br_mnt(a->br); ++ ++ /* are they available to be renamed */ ++ err = au_ren_may_dir(a); ++ if (unlikely(err)) ++ goto out_children; ++ ++ /* prepare the writable parent dir on the same branch */ ++ if (a->dst_btop == a->btgt) { ++ au_fset_ren(a->auren_flags, WHDST); ++ } else { ++ err = au_cpup_dirs(a->dst_dentry, a->btgt); ++ if (unlikely(err)) ++ goto out_children; ++ } ++ ++ err = 0; ++ if (!a->exchange) { ++ if (a->src_dir != a->dst_dir) { ++ /* ++ * this temporary unlock is safe, ++ * because both dir->i_mutex are locked. ++ */ ++ di_write_unlock(a->dst_parent); ++ di_write_lock_parent(a->src_parent); ++ err = au_wr_dir_need_wh(a->src_dentry, ++ au_ftest_ren(a->auren_flags, ++ ISDIR_SRC), ++ &a->btgt); ++ di_write_unlock(a->src_parent); ++ di_write_lock2_parent(a->src_parent, a->dst_parent, ++ /*isdir*/1); ++ au_fclr_ren(a->auren_flags, ISSAMEDIR); ++ } else ++ err = au_wr_dir_need_wh(a->src_dentry, ++ au_ftest_ren(a->auren_flags, ++ ISDIR_SRC), ++ &a->btgt); ++ } ++ if (unlikely(err < 0)) ++ goto out_children; ++ if (err) ++ au_fset_ren(a->auren_flags, WHSRC); ++ ++ /* cpup src */ ++ if (a->src_btop != a->btgt) { ++ err = au_pin(&pin, a->src_dentry, a->btgt, ++ au_opt_udba(a->src_dentry->d_sb), ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ if (!err) { ++ struct au_cp_generic cpg = { ++ .dentry = a->src_dentry, ++ .bdst = a->btgt, ++ .bsrc = a->src_btop, ++ .len = -1, ++ .pin = &pin, ++ .flags = AuCpup_DTIME | AuCpup_HOPEN ++ }; ++ AuDebugOn(au_dbtop(a->src_dentry) != a->src_btop); ++ err = au_sio_cpup_simple(&cpg); ++ au_unpin(&pin); ++ } ++ if (unlikely(err)) ++ goto out_children; ++ a->src_btop = a->btgt; ++ a->src_h_dentry = au_h_dptr(a->src_dentry, a->btgt); ++ if (!a->exchange) ++ au_fset_ren(a->auren_flags, WHSRC); ++ } ++ ++ /* cpup dst */ ++ if (a->exchange && a->dst_inode ++ && a->dst_btop != a->btgt) { ++ err = au_pin(&pin, a->dst_dentry, a->btgt, ++ au_opt_udba(a->dst_dentry->d_sb), ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ if (!err) { ++ struct au_cp_generic cpg = { ++ .dentry = a->dst_dentry, ++ .bdst = a->btgt, ++ .bsrc = a->dst_btop, ++ .len = -1, ++ .pin = &pin, ++ .flags = AuCpup_DTIME | AuCpup_HOPEN ++ }; ++ err = au_sio_cpup_simple(&cpg); ++ au_unpin(&pin); ++ } ++ if (unlikely(err)) ++ goto out_children; ++ a->dst_btop = a->btgt; ++ a->dst_h_dentry = au_h_dptr(a->dst_dentry, a->btgt); ++ } ++ ++ /* lock them all */ ++ err = au_ren_lock(a); ++ if (unlikely(err)) ++ /* leave the copied-up one */ ++ goto out_children; ++ ++ if (!a->exchange) { ++ if (!au_opt_test(au_mntflags(a->dst_dir->i_sb), UDBA_NONE)) ++ err = au_may_ren(a); ++ else if (unlikely(a->dst_dentry->d_name.len > AUFS_MAX_NAMELEN)) ++ err = -ENAMETOOLONG; ++ if (unlikely(err)) ++ goto out_hdir; ++ } ++ ++ /* store timestamps to be revertible */ ++ au_ren_dt(a); ++ ++ /* store dirren info */ ++ if (au_ftest_ren(a->auren_flags, DIRREN)) { ++ err = au_dr_rename(a->src_dentry, a->btgt, ++ &a->dst_dentry->d_name, &rev); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ goto out_dt; ++ } ++ ++ /* here we go */ ++ err = do_rename(a); ++ if (unlikely(err)) ++ goto out_dirren; ++ ++ if (au_ftest_ren(a->auren_flags, DIRREN)) ++ au_dr_rename_fin(a->src_dentry, a->btgt, rev); ++ ++ /* update dir attributes */ ++ au_ren_refresh_dir(a); ++ ++ /* dput/iput all lower dentries */ ++ au_ren_refresh(a); ++ ++ goto out_hdir; /* success */ ++ ++out_dirren: ++ if (au_ftest_ren(a->auren_flags, DIRREN)) ++ au_dr_rename_rev(a->src_dentry, a->btgt, rev); ++out_dt: ++ au_ren_rev_dt(err, a); ++out_hdir: ++ au_ren_unlock(a); ++out_children: ++ au_nhash_wh_free(&a->whlist); ++ if (err && a->dst_inode && a->dst_btop != a->btgt) { ++ AuDbg("btop %d, btgt %d\n", a->dst_btop, a->btgt); ++ au_set_h_dptr(a->dst_dentry, a->btgt, NULL); ++ au_set_dbtop(a->dst_dentry, a->dst_btop); ++ } ++out_parent: ++ if (!err) { ++ if (d_unhashed(a->src_dentry)) ++ au_fset_ren(a->auren_flags, DROPPED_SRC); ++ if (d_unhashed(a->dst_dentry)) ++ au_fset_ren(a->auren_flags, DROPPED_DST); ++ if (!a->exchange) ++ d_move(a->src_dentry, a->dst_dentry); ++ else { ++ d_exchange(a->src_dentry, a->dst_dentry); ++ if (au_ftest_ren(a->auren_flags, DROPPED_DST)) ++ d_drop(a->dst_dentry); ++ } ++ if (au_ftest_ren(a->auren_flags, DROPPED_SRC)) ++ d_drop(a->src_dentry); ++ } else { ++ au_update_dbtop(a->dst_dentry); ++ if (!a->dst_inode) ++ d_drop(a->dst_dentry); ++ } ++ if (au_ftest_ren(a->auren_flags, ISSAMEDIR)) ++ di_write_unlock(a->dst_parent); ++ else ++ di_write_unlock2(a->src_parent, a->dst_parent); ++out_unlock: ++ aufs_read_and_write_unlock2(a->dst_dentry, a->src_dentry); ++out_free: ++ iput(a->dst_inode); ++ if (a->thargs) ++ au_whtmp_rmdir_free(a->thargs); ++ kfree(a); ++out: ++ AuTraceErr(err); ++ return err; ++} +diff --git a/fs/aufs/iinfo.c b/fs/aufs/iinfo.c +new file mode 100644 +index 00000000..d5cba3b9 +--- /dev/null ++++ b/fs/aufs/iinfo.c +@@ -0,0 +1,285 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * inode private data ++ */ ++ ++#include "aufs.h" ++ ++struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex) ++{ ++ struct inode *h_inode; ++ struct au_hinode *hinode; ++ ++ IiMustAnyLock(inode); ++ ++ hinode = au_hinode(au_ii(inode), bindex); ++ h_inode = hinode->hi_inode; ++ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0); ++ return h_inode; ++} ++ ++/* todo: hard/soft set? */ ++void au_hiput(struct au_hinode *hinode) ++{ ++ au_hn_free(hinode); ++ dput(hinode->hi_whdentry); ++ iput(hinode->hi_inode); ++} ++ ++unsigned int au_hi_flags(struct inode *inode, int isdir) ++{ ++ unsigned int flags; ++ const unsigned int mnt_flags = au_mntflags(inode->i_sb); ++ ++ flags = 0; ++ if (au_opt_test(mnt_flags, XINO)) ++ au_fset_hi(flags, XINO); ++ if (isdir && au_opt_test(mnt_flags, UDBA_HNOTIFY)) ++ au_fset_hi(flags, HNOTIFY); ++ return flags; ++} ++ ++void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex, ++ struct inode *h_inode, unsigned int flags) ++{ ++ struct au_hinode *hinode; ++ struct inode *hi; ++ struct au_iinfo *iinfo = au_ii(inode); ++ ++ IiMustWriteLock(inode); ++ ++ hinode = au_hinode(iinfo, bindex); ++ hi = hinode->hi_inode; ++ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0); ++ ++ if (hi) ++ au_hiput(hinode); ++ hinode->hi_inode = h_inode; ++ if (h_inode) { ++ int err; ++ struct super_block *sb = inode->i_sb; ++ struct au_branch *br; ++ ++ AuDebugOn(inode->i_mode ++ && (h_inode->i_mode & S_IFMT) ++ != (inode->i_mode & S_IFMT)); ++ if (bindex == iinfo->ii_btop) ++ au_cpup_igen(inode, h_inode); ++ br = au_sbr(sb, bindex); ++ hinode->hi_id = br->br_id; ++ if (au_ftest_hi(flags, XINO)) { ++ err = au_xino_write(sb, bindex, h_inode->i_ino, ++ inode->i_ino); ++ if (unlikely(err)) ++ AuIOErr1("failed au_xino_write() %d\n", err); ++ } ++ ++ if (au_ftest_hi(flags, HNOTIFY) ++ && au_br_hnotifyable(br->br_perm)) { ++ err = au_hn_alloc(hinode, inode); ++ if (unlikely(err)) ++ AuIOErr1("au_hn_alloc() %d\n", err); ++ } ++ } ++} ++ ++void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex, ++ struct dentry *h_wh) ++{ ++ struct au_hinode *hinode; ++ ++ IiMustWriteLock(inode); ++ ++ hinode = au_hinode(au_ii(inode), bindex); ++ AuDebugOn(hinode->hi_whdentry); ++ hinode->hi_whdentry = h_wh; ++} ++ ++void au_update_iigen(struct inode *inode, int half) ++{ ++ struct au_iinfo *iinfo; ++ struct au_iigen *iigen; ++ unsigned int sigen; ++ ++ sigen = au_sigen(inode->i_sb); ++ iinfo = au_ii(inode); ++ iigen = &iinfo->ii_generation; ++ spin_lock(&iigen->ig_spin); ++ iigen->ig_generation = sigen; ++ if (half) ++ au_ig_fset(iigen->ig_flags, HALF_REFRESHED); ++ else ++ au_ig_fclr(iigen->ig_flags, HALF_REFRESHED); ++ spin_unlock(&iigen->ig_spin); ++} ++ ++/* it may be called at remount time, too */ ++void au_update_ibrange(struct inode *inode, int do_put_zero) ++{ ++ struct au_iinfo *iinfo; ++ aufs_bindex_t bindex, bbot; ++ ++ AuDebugOn(au_is_bad_inode(inode)); ++ IiMustWriteLock(inode); ++ ++ iinfo = au_ii(inode); ++ if (do_put_zero && iinfo->ii_btop >= 0) { ++ for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot; ++ bindex++) { ++ struct inode *h_i; ++ ++ h_i = au_hinode(iinfo, bindex)->hi_inode; ++ if (h_i ++ && !h_i->i_nlink ++ && !(h_i->i_state & I_LINKABLE)) ++ au_set_h_iptr(inode, bindex, NULL, 0); ++ } ++ } ++ ++ iinfo->ii_btop = -1; ++ iinfo->ii_bbot = -1; ++ bbot = au_sbbot(inode->i_sb); ++ for (bindex = 0; bindex <= bbot; bindex++) ++ if (au_hinode(iinfo, bindex)->hi_inode) { ++ iinfo->ii_btop = bindex; ++ break; ++ } ++ if (iinfo->ii_btop >= 0) ++ for (bindex = bbot; bindex >= iinfo->ii_btop; bindex--) ++ if (au_hinode(iinfo, bindex)->hi_inode) { ++ iinfo->ii_bbot = bindex; ++ break; ++ } ++ AuDebugOn(iinfo->ii_btop > iinfo->ii_bbot); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_icntnr_init_once(void *_c) ++{ ++ struct au_icntnr *c = _c; ++ struct au_iinfo *iinfo = &c->iinfo; ++ ++ spin_lock_init(&iinfo->ii_generation.ig_spin); ++ au_rw_init(&iinfo->ii_rwsem); ++ inode_init_once(&c->vfs_inode); ++} ++ ++void au_hinode_init(struct au_hinode *hinode) ++{ ++ hinode->hi_inode = NULL; ++ hinode->hi_id = -1; ++ au_hn_init(hinode); ++ hinode->hi_whdentry = NULL; ++} ++ ++int au_iinfo_init(struct inode *inode) ++{ ++ struct au_iinfo *iinfo; ++ struct super_block *sb; ++ struct au_hinode *hi; ++ int nbr, i; ++ ++ sb = inode->i_sb; ++ iinfo = &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo); ++ nbr = au_sbbot(sb) + 1; ++ if (unlikely(nbr <= 0)) ++ nbr = 1; ++ hi = kmalloc_array(nbr, sizeof(*iinfo->ii_hinode), GFP_NOFS); ++ if (hi) { ++ au_ninodes_inc(sb); ++ ++ iinfo->ii_hinode = hi; ++ for (i = 0; i < nbr; i++, hi++) ++ au_hinode_init(hi); ++ ++ iinfo->ii_generation.ig_generation = au_sigen(sb); ++ iinfo->ii_btop = -1; ++ iinfo->ii_bbot = -1; ++ iinfo->ii_vdir = NULL; ++ return 0; ++ } ++ return -ENOMEM; ++} ++ ++int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink) ++{ ++ int err, i; ++ struct au_hinode *hip; ++ ++ AuRwMustWriteLock(&iinfo->ii_rwsem); ++ ++ err = -ENOMEM; ++ hip = au_krealloc(iinfo->ii_hinode, sizeof(*hip) * nbr, GFP_NOFS, ++ may_shrink); ++ if (hip) { ++ iinfo->ii_hinode = hip; ++ i = iinfo->ii_bbot + 1; ++ hip += i; ++ for (; i < nbr; i++, hip++) ++ au_hinode_init(hip); ++ err = 0; ++ } ++ ++ return err; ++} ++ ++void au_iinfo_fin(struct inode *inode) ++{ ++ struct au_iinfo *iinfo; ++ struct au_hinode *hi; ++ struct super_block *sb; ++ aufs_bindex_t bindex, bbot; ++ const unsigned char unlinked = !inode->i_nlink; ++ ++ AuDebugOn(au_is_bad_inode(inode)); ++ ++ sb = inode->i_sb; ++ au_ninodes_dec(sb); ++ if (si_pid_test(sb)) ++ au_xino_delete_inode(inode, unlinked); ++ else { ++ /* ++ * it is safe to hide the dependency between sbinfo and ++ * sb->s_umount. ++ */ ++ lockdep_off(); ++ si_noflush_read_lock(sb); ++ au_xino_delete_inode(inode, unlinked); ++ si_read_unlock(sb); ++ lockdep_on(); ++ } ++ ++ iinfo = au_ii(inode); ++ if (iinfo->ii_vdir) ++ au_vdir_free(iinfo->ii_vdir); ++ ++ bindex = iinfo->ii_btop; ++ if (bindex >= 0) { ++ hi = au_hinode(iinfo, bindex); ++ bbot = iinfo->ii_bbot; ++ while (bindex++ <= bbot) { ++ if (hi->hi_inode) ++ au_hiput(hi); ++ hi++; ++ } ++ } ++ kfree(iinfo->ii_hinode); ++ AuRwDestroy(&iinfo->ii_rwsem); ++} +diff --git a/fs/aufs/inode.c b/fs/aufs/inode.c +new file mode 100644 +index 00000000..79803c4e +--- /dev/null ++++ b/fs/aufs/inode.c +@@ -0,0 +1,527 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * inode functions ++ */ ++ ++#include "aufs.h" ++ ++struct inode *au_igrab(struct inode *inode) ++{ ++ if (inode) { ++ AuDebugOn(!atomic_read(&inode->i_count)); ++ ihold(inode); ++ } ++ return inode; ++} ++ ++static void au_refresh_hinode_attr(struct inode *inode, int do_version) ++{ ++ au_cpup_attr_all(inode, /*force*/0); ++ au_update_iigen(inode, /*half*/1); ++ if (do_version) ++ inode->i_version++; ++} ++ ++static int au_ii_refresh(struct inode *inode, int *update) ++{ ++ int err, e, nbr; ++ umode_t type; ++ aufs_bindex_t bindex, new_bindex; ++ struct super_block *sb; ++ struct au_iinfo *iinfo; ++ struct au_hinode *p, *q, tmp; ++ ++ AuDebugOn(au_is_bad_inode(inode)); ++ IiMustWriteLock(inode); ++ ++ *update = 0; ++ sb = inode->i_sb; ++ nbr = au_sbbot(sb) + 1; ++ type = inode->i_mode & S_IFMT; ++ iinfo = au_ii(inode); ++ err = au_hinode_realloc(iinfo, nbr, /*may_shrink*/0); ++ if (unlikely(err)) ++ goto out; ++ ++ AuDebugOn(iinfo->ii_btop < 0); ++ p = au_hinode(iinfo, iinfo->ii_btop); ++ for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot; ++ bindex++, p++) { ++ if (!p->hi_inode) ++ continue; ++ ++ AuDebugOn(type != (p->hi_inode->i_mode & S_IFMT)); ++ new_bindex = au_br_index(sb, p->hi_id); ++ if (new_bindex == bindex) ++ continue; ++ ++ if (new_bindex < 0) { ++ *update = 1; ++ au_hiput(p); ++ p->hi_inode = NULL; ++ continue; ++ } ++ ++ if (new_bindex < iinfo->ii_btop) ++ iinfo->ii_btop = new_bindex; ++ if (iinfo->ii_bbot < new_bindex) ++ iinfo->ii_bbot = new_bindex; ++ /* swap two lower inode, and loop again */ ++ q = au_hinode(iinfo, new_bindex); ++ tmp = *q; ++ *q = *p; ++ *p = tmp; ++ if (tmp.hi_inode) { ++ bindex--; ++ p--; ++ } ++ } ++ au_update_ibrange(inode, /*do_put_zero*/0); ++ au_hinode_realloc(iinfo, nbr, /*may_shrink*/1); /* harmless if err */ ++ e = au_dy_irefresh(inode); ++ if (unlikely(e && !err)) ++ err = e; ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++void au_refresh_iop(struct inode *inode, int force_getattr) ++{ ++ int type; ++ struct au_sbinfo *sbi = au_sbi(inode->i_sb); ++ const struct inode_operations *iop ++ = force_getattr ? aufs_iop : sbi->si_iop_array; ++ ++ if (inode->i_op == iop) ++ return; ++ ++ switch (inode->i_mode & S_IFMT) { ++ case S_IFDIR: ++ type = AuIop_DIR; ++ break; ++ case S_IFLNK: ++ type = AuIop_SYMLINK; ++ break; ++ default: ++ type = AuIop_OTHER; ++ break; ++ } ++ ++ inode->i_op = iop + type; ++ /* unnecessary smp_wmb() */ ++} ++ ++int au_refresh_hinode_self(struct inode *inode) ++{ ++ int err, update; ++ ++ err = au_ii_refresh(inode, &update); ++ if (!err) ++ au_refresh_hinode_attr(inode, update && S_ISDIR(inode->i_mode)); ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++int au_refresh_hinode(struct inode *inode, struct dentry *dentry) ++{ ++ int err, e, update; ++ unsigned int flags; ++ umode_t mode; ++ aufs_bindex_t bindex, bbot; ++ unsigned char isdir; ++ struct au_hinode *p; ++ struct au_iinfo *iinfo; ++ ++ err = au_ii_refresh(inode, &update); ++ if (unlikely(err)) ++ goto out; ++ ++ update = 0; ++ iinfo = au_ii(inode); ++ p = au_hinode(iinfo, iinfo->ii_btop); ++ mode = (inode->i_mode & S_IFMT); ++ isdir = S_ISDIR(mode); ++ flags = au_hi_flags(inode, isdir); ++ bbot = au_dbbot(dentry); ++ for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) { ++ struct inode *h_i, *h_inode; ++ struct dentry *h_d; ++ ++ h_d = au_h_dptr(dentry, bindex); ++ if (!h_d || d_is_negative(h_d)) ++ continue; ++ ++ h_inode = d_inode(h_d); ++ AuDebugOn(mode != (h_inode->i_mode & S_IFMT)); ++ if (iinfo->ii_btop <= bindex && bindex <= iinfo->ii_bbot) { ++ h_i = au_h_iptr(inode, bindex); ++ if (h_i) { ++ if (h_i == h_inode) ++ continue; ++ err = -EIO; ++ break; ++ } ++ } ++ if (bindex < iinfo->ii_btop) ++ iinfo->ii_btop = bindex; ++ if (iinfo->ii_bbot < bindex) ++ iinfo->ii_bbot = bindex; ++ au_set_h_iptr(inode, bindex, au_igrab(h_inode), flags); ++ update = 1; ++ } ++ au_update_ibrange(inode, /*do_put_zero*/0); ++ e = au_dy_irefresh(inode); ++ if (unlikely(e && !err)) ++ err = e; ++ if (!err) ++ au_refresh_hinode_attr(inode, update && isdir); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++static int set_inode(struct inode *inode, struct dentry *dentry) ++{ ++ int err; ++ unsigned int flags; ++ umode_t mode; ++ aufs_bindex_t bindex, btop, btail; ++ unsigned char isdir; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ struct au_iinfo *iinfo; ++ struct inode_operations *iop; ++ ++ IiMustWriteLock(inode); ++ ++ err = 0; ++ isdir = 0; ++ iop = au_sbi(inode->i_sb)->si_iop_array; ++ btop = au_dbtop(dentry); ++ h_dentry = au_h_dptr(dentry, btop); ++ h_inode = d_inode(h_dentry); ++ mode = h_inode->i_mode; ++ switch (mode & S_IFMT) { ++ case S_IFREG: ++ btail = au_dbtail(dentry); ++ inode->i_op = iop + AuIop_OTHER; ++ inode->i_fop = &aufs_file_fop; ++ err = au_dy_iaop(inode, btop, h_inode); ++ if (unlikely(err)) ++ goto out; ++ break; ++ case S_IFDIR: ++ isdir = 1; ++ btail = au_dbtaildir(dentry); ++ inode->i_op = iop + AuIop_DIR; ++ inode->i_fop = &aufs_dir_fop; ++ break; ++ case S_IFLNK: ++ btail = au_dbtail(dentry); ++ inode->i_op = iop + AuIop_SYMLINK; ++ break; ++ case S_IFBLK: ++ case S_IFCHR: ++ case S_IFIFO: ++ case S_IFSOCK: ++ btail = au_dbtail(dentry); ++ inode->i_op = iop + AuIop_OTHER; ++ init_special_inode(inode, mode, h_inode->i_rdev); ++ break; ++ default: ++ AuIOErr("Unknown file type 0%o\n", mode); ++ err = -EIO; ++ goto out; ++ } ++ ++ /* do not set hnotify for whiteouted dirs (SHWH mode) */ ++ flags = au_hi_flags(inode, isdir); ++ if (au_opt_test(au_mntflags(dentry->d_sb), SHWH) ++ && au_ftest_hi(flags, HNOTIFY) ++ && dentry->d_name.len > AUFS_WH_PFX_LEN ++ && !memcmp(dentry->d_name.name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) ++ au_fclr_hi(flags, HNOTIFY); ++ iinfo = au_ii(inode); ++ iinfo->ii_btop = btop; ++ iinfo->ii_bbot = btail; ++ for (bindex = btop; bindex <= btail; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry) ++ au_set_h_iptr(inode, bindex, ++ au_igrab(d_inode(h_dentry)), flags); ++ } ++ au_cpup_attr_all(inode, /*force*/1); ++ /* ++ * to force calling aufs_get_acl() every time, ++ * do not call cache_no_acl() for aufs inode. ++ */ ++ ++out: ++ return err; ++} ++ ++/* ++ * successful returns with iinfo write_locked ++ * minus: errno ++ * zero: success, matched ++ * plus: no error, but unmatched ++ */ ++static int reval_inode(struct inode *inode, struct dentry *dentry) ++{ ++ int err; ++ unsigned int gen, igflags; ++ aufs_bindex_t bindex, bbot; ++ struct inode *h_inode, *h_dinode; ++ struct dentry *h_dentry; ++ ++ /* ++ * before this function, if aufs got any iinfo lock, it must be only ++ * one, the parent dir. ++ * it can happen by UDBA and the obsoleted inode number. ++ */ ++ err = -EIO; ++ if (unlikely(inode->i_ino == parent_ino(dentry))) ++ goto out; ++ ++ err = 1; ++ ii_write_lock_new_child(inode); ++ h_dentry = au_h_dptr(dentry, au_dbtop(dentry)); ++ h_dinode = d_inode(h_dentry); ++ bbot = au_ibbot(inode); ++ for (bindex = au_ibtop(inode); bindex <= bbot; bindex++) { ++ h_inode = au_h_iptr(inode, bindex); ++ if (!h_inode || h_inode != h_dinode) ++ continue; ++ ++ err = 0; ++ gen = au_iigen(inode, &igflags); ++ if (gen == au_digen(dentry) ++ && !au_ig_ftest(igflags, HALF_REFRESHED)) ++ break; ++ ++ /* fully refresh inode using dentry */ ++ err = au_refresh_hinode(inode, dentry); ++ if (!err) ++ au_update_iigen(inode, /*half*/0); ++ break; ++ } ++ ++ if (unlikely(err)) ++ ii_write_unlock(inode); ++out: ++ return err; ++} ++ ++int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ unsigned int d_type, ino_t *ino) ++{ ++ int err, idx; ++ const int isnondir = d_type != DT_DIR; ++ ++ /* prevent hardlinked inode number from race condition */ ++ if (isnondir) { ++ err = au_xinondir_enter(sb, bindex, h_ino, &idx); ++ if (unlikely(err)) ++ goto out; ++ } ++ ++ err = au_xino_read(sb, bindex, h_ino, ino); ++ if (unlikely(err)) ++ goto out_xinondir; ++ ++ if (!*ino) { ++ err = -EIO; ++ *ino = au_xino_new_ino(sb); ++ if (unlikely(!*ino)) ++ goto out_xinondir; ++ err = au_xino_write(sb, bindex, h_ino, *ino); ++ if (unlikely(err)) ++ goto out_xinondir; ++ } ++ ++out_xinondir: ++ if (isnondir && idx >= 0) ++ au_xinondir_leave(sb, bindex, h_ino, idx); ++out: ++ return err; ++} ++ ++/* successful returns with iinfo write_locked */ ++/* todo: return with unlocked? */ ++struct inode *au_new_inode(struct dentry *dentry, int must_new) ++{ ++ struct inode *inode, *h_inode; ++ struct dentry *h_dentry; ++ struct super_block *sb; ++ ino_t h_ino, ino; ++ int err, idx, hlinked; ++ aufs_bindex_t btop; ++ ++ sb = dentry->d_sb; ++ btop = au_dbtop(dentry); ++ h_dentry = au_h_dptr(dentry, btop); ++ h_inode = d_inode(h_dentry); ++ h_ino = h_inode->i_ino; ++ hlinked = !d_is_dir(h_dentry) && h_inode->i_nlink > 1; ++ ++new_ino: ++ /* ++ * stop 'race'-ing between hardlinks under different ++ * parents. ++ */ ++ if (hlinked) { ++ err = au_xinondir_enter(sb, btop, h_ino, &idx); ++ inode = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out; ++ } ++ ++ err = au_xino_read(sb, btop, h_ino, &ino); ++ inode = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out_xinondir; ++ ++ if (!ino) { ++ ino = au_xino_new_ino(sb); ++ if (unlikely(!ino)) { ++ inode = ERR_PTR(-EIO); ++ goto out_xinondir; ++ } ++ } ++ ++ AuDbg("i%lu\n", (unsigned long)ino); ++ inode = au_iget_locked(sb, ino); ++ err = PTR_ERR(inode); ++ if (IS_ERR(inode)) ++ goto out_xinondir; ++ ++ AuDbg("%lx, new %d\n", inode->i_state, !!(inode->i_state & I_NEW)); ++ if (inode->i_state & I_NEW) { ++ ii_write_lock_new_child(inode); ++ err = set_inode(inode, dentry); ++ if (!err) { ++ unlock_new_inode(inode); ++ goto out_xinondir; /* success */ ++ } ++ ++ /* ++ * iget_failed() calls iput(), but we need to call ++ * ii_write_unlock() after iget_failed(). so dirty hack for ++ * i_count. ++ */ ++ atomic_inc(&inode->i_count); ++ iget_failed(inode); ++ ii_write_unlock(inode); ++ au_xino_write(sb, btop, h_ino, /*ino*/0); ++ /* ignore this error */ ++ goto out_iput; ++ } else if (!must_new && !IS_DEADDIR(inode) && inode->i_nlink) { ++ /* ++ * horrible race condition between lookup, readdir and copyup ++ * (or something). ++ */ ++ if (hlinked && idx >= 0) ++ au_xinondir_leave(sb, btop, h_ino, idx); ++ err = reval_inode(inode, dentry); ++ if (unlikely(err < 0)) { ++ hlinked = 0; ++ goto out_iput; ++ } ++ if (!err) ++ goto out; /* success */ ++ else if (hlinked && idx >= 0) { ++ err = au_xinondir_enter(sb, btop, h_ino, &idx); ++ if (unlikely(err)) { ++ iput(inode); ++ inode = ERR_PTR(err); ++ goto out; ++ } ++ } ++ } ++ ++ if (unlikely(au_test_fs_unique_ino(h_inode))) ++ AuWarn1("Warning: Un-notified UDBA or repeatedly renamed dir," ++ " b%d, %s, %pd, hi%lu, i%lu.\n", ++ btop, au_sbtype(h_dentry->d_sb), dentry, ++ (unsigned long)h_ino, (unsigned long)ino); ++ ino = 0; ++ err = au_xino_write(sb, btop, h_ino, /*ino*/0); ++ if (!err) { ++ iput(inode); ++ if (hlinked && idx >= 0) ++ au_xinondir_leave(sb, btop, h_ino, idx); ++ goto new_ino; ++ } ++ ++out_iput: ++ iput(inode); ++ inode = ERR_PTR(err); ++out_xinondir: ++ if (hlinked && idx >= 0) ++ au_xinondir_leave(sb, btop, h_ino, idx); ++out: ++ return inode; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_test_ro(struct super_block *sb, aufs_bindex_t bindex, ++ struct inode *inode) ++{ ++ int err; ++ struct inode *hi; ++ ++ err = au_br_rdonly(au_sbr(sb, bindex)); ++ ++ /* pseudo-link after flushed may happen out of bounds */ ++ if (!err ++ && inode ++ && au_ibtop(inode) <= bindex ++ && bindex <= au_ibbot(inode)) { ++ /* ++ * permission check is unnecessary since vfsub routine ++ * will be called later ++ */ ++ hi = au_h_iptr(inode, bindex); ++ if (hi) ++ err = IS_IMMUTABLE(hi) ? -EROFS : 0; ++ } ++ ++ return err; ++} ++ ++int au_test_h_perm(struct inode *h_inode, int mask) ++{ ++ if (uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) ++ return 0; ++ return inode_permission(h_inode, mask); ++} ++ ++int au_test_h_perm_sio(struct inode *h_inode, int mask) ++{ ++ if (au_test_nfs(h_inode->i_sb) ++ && (mask & MAY_WRITE) ++ && S_ISDIR(h_inode->i_mode)) ++ mask |= MAY_READ; /* force permission check */ ++ return au_test_h_perm(h_inode, mask); ++} +diff --git a/fs/aufs/inode.h b/fs/aufs/inode.h +new file mode 100644 +index 00000000..1f5c9e75 +--- /dev/null ++++ b/fs/aufs/inode.h +@@ -0,0 +1,696 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * inode operations ++ */ ++ ++#ifndef __AUFS_INODE_H__ ++#define __AUFS_INODE_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include "rwsem.h" ++ ++struct vfsmount; ++ ++struct au_hnotify { ++#ifdef CONFIG_AUFS_HNOTIFY ++#ifdef CONFIG_AUFS_HFSNOTIFY ++ /* never use fsnotify_add_vfsmount_mark() */ ++ struct fsnotify_mark hn_mark; ++#endif ++ struct inode *hn_aufs_inode; /* no get/put */ ++#endif ++} ____cacheline_aligned_in_smp; ++ ++struct au_hinode { ++ struct inode *hi_inode; ++ aufs_bindex_t hi_id; ++#ifdef CONFIG_AUFS_HNOTIFY ++ struct au_hnotify *hi_notify; ++#endif ++ ++ /* reference to the copied-up whiteout with get/put */ ++ struct dentry *hi_whdentry; ++}; ++ ++/* ig_flags */ ++#define AuIG_HALF_REFRESHED 1 ++#define au_ig_ftest(flags, name) ((flags) & AuIG_##name) ++#define au_ig_fset(flags, name) \ ++ do { (flags) |= AuIG_##name; } while (0) ++#define au_ig_fclr(flags, name) \ ++ do { (flags) &= ~AuIG_##name; } while (0) ++ ++struct au_iigen { ++ spinlock_t ig_spin; ++ __u32 ig_generation, ig_flags; ++}; ++ ++struct au_vdir; ++struct au_iinfo { ++ struct au_iigen ii_generation; ++ struct super_block *ii_hsb1; /* no get/put */ ++ ++ struct au_rwsem ii_rwsem; ++ aufs_bindex_t ii_btop, ii_bbot; ++ __u32 ii_higen; ++ struct au_hinode *ii_hinode; ++ struct au_vdir *ii_vdir; ++}; ++ ++struct au_icntnr { ++ struct au_iinfo iinfo; ++ struct inode vfs_inode; ++ struct hlist_bl_node plink; ++} ____cacheline_aligned_in_smp; ++ ++/* au_pin flags */ ++#define AuPin_DI_LOCKED 1 ++#define AuPin_MNT_WRITE (1 << 1) ++#define au_ftest_pin(flags, name) ((flags) & AuPin_##name) ++#define au_fset_pin(flags, name) \ ++ do { (flags) |= AuPin_##name; } while (0) ++#define au_fclr_pin(flags, name) \ ++ do { (flags) &= ~AuPin_##name; } while (0) ++ ++struct au_pin { ++ /* input */ ++ struct dentry *dentry; ++ unsigned int udba; ++ unsigned char lsc_di, lsc_hi, flags; ++ aufs_bindex_t bindex; ++ ++ /* output */ ++ struct dentry *parent; ++ struct au_hinode *hdir; ++ struct vfsmount *h_mnt; ++ ++ /* temporary unlock/relock for copyup */ ++ struct dentry *h_dentry, *h_parent; ++ struct au_branch *br; ++ struct task_struct *task; ++}; ++ ++void au_pin_hdir_unlock(struct au_pin *p); ++int au_pin_hdir_lock(struct au_pin *p); ++int au_pin_hdir_relock(struct au_pin *p); ++void au_pin_hdir_acquire_nest(struct au_pin *p); ++void au_pin_hdir_release(struct au_pin *p); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct au_iinfo *au_ii(struct inode *inode) ++{ ++ BUG_ON(is_bad_inode(inode)); ++ return &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* inode.c */ ++struct inode *au_igrab(struct inode *inode); ++void au_refresh_iop(struct inode *inode, int force_getattr); ++int au_refresh_hinode_self(struct inode *inode); ++int au_refresh_hinode(struct inode *inode, struct dentry *dentry); ++int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ unsigned int d_type, ino_t *ino); ++struct inode *au_new_inode(struct dentry *dentry, int must_new); ++int au_test_ro(struct super_block *sb, aufs_bindex_t bindex, ++ struct inode *inode); ++int au_test_h_perm(struct inode *h_inode, int mask); ++int au_test_h_perm_sio(struct inode *h_inode, int mask); ++ ++static inline int au_wh_ino(struct super_block *sb, aufs_bindex_t bindex, ++ ino_t h_ino, unsigned int d_type, ino_t *ino) ++{ ++#ifdef CONFIG_AUFS_SHWH ++ return au_ino(sb, bindex, h_ino, d_type, ino); ++#else ++ return 0; ++#endif ++} ++ ++/* i_op.c */ ++enum { ++ AuIop_SYMLINK, ++ AuIop_DIR, ++ AuIop_OTHER, ++ AuIop_Last ++}; ++extern struct inode_operations aufs_iop[AuIop_Last], ++ aufs_iop_nogetattr[AuIop_Last]; ++ ++/* au_wr_dir flags */ ++#define AuWrDir_ADD_ENTRY 1 ++#define AuWrDir_ISDIR (1 << 1) ++#define AuWrDir_TMPFILE (1 << 2) ++#define au_ftest_wrdir(flags, name) ((flags) & AuWrDir_##name) ++#define au_fset_wrdir(flags, name) \ ++ do { (flags) |= AuWrDir_##name; } while (0) ++#define au_fclr_wrdir(flags, name) \ ++ do { (flags) &= ~AuWrDir_##name; } while (0) ++ ++struct au_wr_dir_args { ++ aufs_bindex_t force_btgt; ++ unsigned char flags; ++}; ++int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry, ++ struct au_wr_dir_args *args); ++ ++struct dentry *au_pinned_h_parent(struct au_pin *pin); ++void au_pin_init(struct au_pin *pin, struct dentry *dentry, ++ aufs_bindex_t bindex, int lsc_di, int lsc_hi, ++ unsigned int udba, unsigned char flags); ++int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex, ++ unsigned int udba, unsigned char flags) __must_check; ++int au_do_pin(struct au_pin *pin) __must_check; ++void au_unpin(struct au_pin *pin); ++int au_reval_for_attr(struct dentry *dentry, unsigned int sigen); ++ ++#define AuIcpup_DID_CPUP 1 ++#define au_ftest_icpup(flags, name) ((flags) & AuIcpup_##name) ++#define au_fset_icpup(flags, name) \ ++ do { (flags) |= AuIcpup_##name; } while (0) ++#define au_fclr_icpup(flags, name) \ ++ do { (flags) &= ~AuIcpup_##name; } while (0) ++ ++struct au_icpup_args { ++ unsigned char flags; ++ unsigned char pin_flags; ++ aufs_bindex_t btgt; ++ unsigned int udba; ++ struct au_pin pin; ++ struct path h_path; ++ struct inode *h_inode; ++}; ++ ++int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia, ++ struct au_icpup_args *a); ++ ++int au_h_path_getattr(struct dentry *dentry, int force, struct path *h_path, ++ int locked); ++ ++/* i_op_add.c */ ++int au_may_add(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_parent, int isdir); ++int aufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, ++ dev_t dev); ++int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname); ++int aufs_create(struct inode *dir, struct dentry *dentry, umode_t mode, ++ bool want_excl); ++struct vfsub_aopen_args; ++int au_aopen_or_create(struct inode *dir, struct dentry *dentry, ++ struct vfsub_aopen_args *args); ++int aufs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode); ++int aufs_link(struct dentry *src_dentry, struct inode *dir, ++ struct dentry *dentry); ++int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); ++ ++/* i_op_del.c */ ++int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup); ++int au_may_del(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_parent, int isdir); ++int aufs_unlink(struct inode *dir, struct dentry *dentry); ++int aufs_rmdir(struct inode *dir, struct dentry *dentry); ++ ++/* i_op_ren.c */ ++int au_wbr(struct dentry *dentry, aufs_bindex_t btgt); ++int aufs_rename(struct inode *src_dir, struct dentry *src_dentry, ++ struct inode *dir, struct dentry *dentry, ++ unsigned int flags); ++ ++/* iinfo.c */ ++struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex); ++void au_hiput(struct au_hinode *hinode); ++void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex, ++ struct dentry *h_wh); ++unsigned int au_hi_flags(struct inode *inode, int isdir); ++ ++/* hinode flags */ ++#define AuHi_XINO 1 ++#define AuHi_HNOTIFY (1 << 1) ++#define au_ftest_hi(flags, name) ((flags) & AuHi_##name) ++#define au_fset_hi(flags, name) \ ++ do { (flags) |= AuHi_##name; } while (0) ++#define au_fclr_hi(flags, name) \ ++ do { (flags) &= ~AuHi_##name; } while (0) ++ ++#ifndef CONFIG_AUFS_HNOTIFY ++#undef AuHi_HNOTIFY ++#define AuHi_HNOTIFY 0 ++#endif ++ ++void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex, ++ struct inode *h_inode, unsigned int flags); ++ ++void au_update_iigen(struct inode *inode, int half); ++void au_update_ibrange(struct inode *inode, int do_put_zero); ++ ++void au_icntnr_init_once(void *_c); ++void au_hinode_init(struct au_hinode *hinode); ++int au_iinfo_init(struct inode *inode); ++void au_iinfo_fin(struct inode *inode); ++int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink); ++ ++#ifdef CONFIG_PROC_FS ++/* plink.c */ ++int au_plink_maint(struct super_block *sb, int flags); ++struct au_sbinfo; ++void au_plink_maint_leave(struct au_sbinfo *sbinfo); ++int au_plink_maint_enter(struct super_block *sb); ++#ifdef CONFIG_AUFS_DEBUG ++void au_plink_list(struct super_block *sb); ++#else ++AuStubVoid(au_plink_list, struct super_block *sb) ++#endif ++int au_plink_test(struct inode *inode); ++struct dentry *au_plink_lkup(struct inode *inode, aufs_bindex_t bindex); ++void au_plink_append(struct inode *inode, aufs_bindex_t bindex, ++ struct dentry *h_dentry); ++void au_plink_put(struct super_block *sb, int verbose); ++void au_plink_clean(struct super_block *sb, int verbose); ++void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id); ++#else ++AuStubInt0(au_plink_maint, struct super_block *sb, int flags); ++AuStubVoid(au_plink_maint_leave, struct au_sbinfo *sbinfo); ++AuStubInt0(au_plink_maint_enter, struct super_block *sb); ++AuStubVoid(au_plink_list, struct super_block *sb); ++AuStubInt0(au_plink_test, struct inode *inode); ++AuStub(struct dentry *, au_plink_lkup, return NULL, ++ struct inode *inode, aufs_bindex_t bindex); ++AuStubVoid(au_plink_append, struct inode *inode, aufs_bindex_t bindex, ++ struct dentry *h_dentry); ++AuStubVoid(au_plink_put, struct super_block *sb, int verbose); ++AuStubVoid(au_plink_clean, struct super_block *sb, int verbose); ++AuStubVoid(au_plink_half_refresh, struct super_block *sb, aufs_bindex_t br_id); ++#endif /* CONFIG_PROC_FS */ ++ ++#ifdef CONFIG_AUFS_XATTR ++/* xattr.c */ ++int au_cpup_xattr(struct dentry *h_dst, struct dentry *h_src, int ignore_flags, ++ unsigned int verbose); ++ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size); ++void au_xattr_init(struct super_block *sb); ++#else ++AuStubInt0(au_cpup_xattr, struct dentry *h_dst, struct dentry *h_src, ++ int ignore_flags, unsigned int verbose); ++AuStubVoid(au_xattr_init, struct super_block *sb); ++#endif ++ ++#ifdef CONFIG_FS_POSIX_ACL ++struct posix_acl *aufs_get_acl(struct inode *inode, int type); ++int aufs_set_acl(struct inode *inode, struct posix_acl *acl, int type); ++#endif ++ ++#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL) ++enum { ++ AU_XATTR_SET, ++ AU_ACL_SET ++}; ++ ++struct au_sxattr { ++ int type; ++ union { ++ struct { ++ const char *name; ++ const void *value; ++ size_t size; ++ int flags; ++ } set; ++ struct { ++ struct posix_acl *acl; ++ int type; ++ } acl_set; ++ } u; ++}; ++ssize_t au_sxattr(struct dentry *dentry, struct inode *inode, ++ struct au_sxattr *arg); ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* lock subclass for iinfo */ ++enum { ++ AuLsc_II_CHILD, /* child first */ ++ AuLsc_II_CHILD2, /* rename(2), link(2), and cpup at hnotify */ ++ AuLsc_II_CHILD3, /* copyup dirs */ ++ AuLsc_II_PARENT, /* see AuLsc_I_PARENT in vfsub.h */ ++ AuLsc_II_PARENT2, ++ AuLsc_II_PARENT3, /* copyup dirs */ ++ AuLsc_II_NEW_CHILD ++}; ++ ++/* ++ * ii_read_lock_child, ii_write_lock_child, ++ * ii_read_lock_child2, ii_write_lock_child2, ++ * ii_read_lock_child3, ii_write_lock_child3, ++ * ii_read_lock_parent, ii_write_lock_parent, ++ * ii_read_lock_parent2, ii_write_lock_parent2, ++ * ii_read_lock_parent3, ii_write_lock_parent3, ++ * ii_read_lock_new_child, ii_write_lock_new_child, ++ */ ++#define AuReadLockFunc(name, lsc) \ ++static inline void ii_read_lock_##name(struct inode *i) \ ++{ \ ++ au_rw_read_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \ ++} ++ ++#define AuWriteLockFunc(name, lsc) \ ++static inline void ii_write_lock_##name(struct inode *i) \ ++{ \ ++ au_rw_write_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \ ++} ++ ++#define AuRWLockFuncs(name, lsc) \ ++ AuReadLockFunc(name, lsc) \ ++ AuWriteLockFunc(name, lsc) ++ ++AuRWLockFuncs(child, CHILD); ++AuRWLockFuncs(child2, CHILD2); ++AuRWLockFuncs(child3, CHILD3); ++AuRWLockFuncs(parent, PARENT); ++AuRWLockFuncs(parent2, PARENT2); ++AuRWLockFuncs(parent3, PARENT3); ++AuRWLockFuncs(new_child, NEW_CHILD); ++ ++#undef AuReadLockFunc ++#undef AuWriteLockFunc ++#undef AuRWLockFuncs ++ ++/* ++ * ii_read_unlock, ii_write_unlock, ii_downgrade_lock ++ */ ++AuSimpleUnlockRwsemFuncs(ii, struct inode *i, &au_ii(i)->ii_rwsem); ++ ++#define IiMustNoWaiters(i) AuRwMustNoWaiters(&au_ii(i)->ii_rwsem) ++#define IiMustAnyLock(i) AuRwMustAnyLock(&au_ii(i)->ii_rwsem) ++#define IiMustWriteLock(i) AuRwMustWriteLock(&au_ii(i)->ii_rwsem) ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline void au_icntnr_init(struct au_icntnr *c) ++{ ++#ifdef CONFIG_AUFS_DEBUG ++ c->vfs_inode.i_mode = 0; ++#endif ++} ++ ++static inline unsigned int au_iigen(struct inode *inode, unsigned int *igflags) ++{ ++ unsigned int gen; ++ struct au_iinfo *iinfo; ++ struct au_iigen *iigen; ++ ++ iinfo = au_ii(inode); ++ iigen = &iinfo->ii_generation; ++ spin_lock(&iigen->ig_spin); ++ if (igflags) ++ *igflags = iigen->ig_flags; ++ gen = iigen->ig_generation; ++ spin_unlock(&iigen->ig_spin); ++ ++ return gen; ++} ++ ++/* tiny test for inode number */ ++/* tmpfs generation is too rough */ ++static inline int au_test_higen(struct inode *inode, struct inode *h_inode) ++{ ++ struct au_iinfo *iinfo; ++ ++ iinfo = au_ii(inode); ++ AuRwMustAnyLock(&iinfo->ii_rwsem); ++ return !(iinfo->ii_hsb1 == h_inode->i_sb ++ && iinfo->ii_higen == h_inode->i_generation); ++} ++ ++static inline void au_iigen_dec(struct inode *inode) ++{ ++ struct au_iinfo *iinfo; ++ struct au_iigen *iigen; ++ ++ iinfo = au_ii(inode); ++ iigen = &iinfo->ii_generation; ++ spin_lock(&iigen->ig_spin); ++ iigen->ig_generation--; ++ spin_unlock(&iigen->ig_spin); ++} ++ ++static inline int au_iigen_test(struct inode *inode, unsigned int sigen) ++{ ++ int err; ++ ++ err = 0; ++ if (unlikely(inode && au_iigen(inode, NULL) != sigen)) ++ err = -EIO; ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct au_hinode *au_hinode(struct au_iinfo *iinfo, ++ aufs_bindex_t bindex) ++{ ++ return iinfo->ii_hinode + bindex; ++} ++ ++static inline int au_is_bad_inode(struct inode *inode) ++{ ++ return !!(is_bad_inode(inode) || !au_hinode(au_ii(inode), 0)); ++} ++ ++static inline aufs_bindex_t au_ii_br_id(struct inode *inode, ++ aufs_bindex_t bindex) ++{ ++ IiMustAnyLock(inode); ++ return au_hinode(au_ii(inode), bindex)->hi_id; ++} ++ ++static inline aufs_bindex_t au_ibtop(struct inode *inode) ++{ ++ IiMustAnyLock(inode); ++ return au_ii(inode)->ii_btop; ++} ++ ++static inline aufs_bindex_t au_ibbot(struct inode *inode) ++{ ++ IiMustAnyLock(inode); ++ return au_ii(inode)->ii_bbot; ++} ++ ++static inline struct au_vdir *au_ivdir(struct inode *inode) ++{ ++ IiMustAnyLock(inode); ++ return au_ii(inode)->ii_vdir; ++} ++ ++static inline struct dentry *au_hi_wh(struct inode *inode, aufs_bindex_t bindex) ++{ ++ IiMustAnyLock(inode); ++ return au_hinode(au_ii(inode), bindex)->hi_whdentry; ++} ++ ++static inline void au_set_ibtop(struct inode *inode, aufs_bindex_t bindex) ++{ ++ IiMustWriteLock(inode); ++ au_ii(inode)->ii_btop = bindex; ++} ++ ++static inline void au_set_ibbot(struct inode *inode, aufs_bindex_t bindex) ++{ ++ IiMustWriteLock(inode); ++ au_ii(inode)->ii_bbot = bindex; ++} ++ ++static inline void au_set_ivdir(struct inode *inode, struct au_vdir *vdir) ++{ ++ IiMustWriteLock(inode); ++ au_ii(inode)->ii_vdir = vdir; ++} ++ ++static inline struct au_hinode *au_hi(struct inode *inode, aufs_bindex_t bindex) ++{ ++ IiMustAnyLock(inode); ++ return au_hinode(au_ii(inode), bindex); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct dentry *au_pinned_parent(struct au_pin *pin) ++{ ++ if (pin) ++ return pin->parent; ++ return NULL; ++} ++ ++static inline struct inode *au_pinned_h_dir(struct au_pin *pin) ++{ ++ if (pin && pin->hdir) ++ return pin->hdir->hi_inode; ++ return NULL; ++} ++ ++static inline struct au_hinode *au_pinned_hdir(struct au_pin *pin) ++{ ++ if (pin) ++ return pin->hdir; ++ return NULL; ++} ++ ++static inline void au_pin_set_dentry(struct au_pin *pin, struct dentry *dentry) ++{ ++ if (pin) ++ pin->dentry = dentry; ++} ++ ++static inline void au_pin_set_parent_lflag(struct au_pin *pin, ++ unsigned char lflag) ++{ ++ if (pin) { ++ if (lflag) ++ au_fset_pin(pin->flags, DI_LOCKED); ++ else ++ au_fclr_pin(pin->flags, DI_LOCKED); ++ } ++} ++ ++#if 0 /* reserved */ ++static inline void au_pin_set_parent(struct au_pin *pin, struct dentry *parent) ++{ ++ if (pin) { ++ dput(pin->parent); ++ pin->parent = dget(parent); ++ } ++} ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_branch; ++#ifdef CONFIG_AUFS_HNOTIFY ++struct au_hnotify_op { ++ void (*ctl)(struct au_hinode *hinode, int do_set); ++ int (*alloc)(struct au_hinode *hinode); ++ ++ /* ++ * if it returns true, the the caller should free hinode->hi_notify, ++ * otherwise ->free() frees it. ++ */ ++ int (*free)(struct au_hinode *hinode, ++ struct au_hnotify *hn) __must_check; ++ ++ void (*fin)(void); ++ int (*init)(void); ++ ++ int (*reset_br)(unsigned int udba, struct au_branch *br, int perm); ++ void (*fin_br)(struct au_branch *br); ++ int (*init_br)(struct au_branch *br, int perm); ++}; ++ ++/* hnotify.c */ ++int au_hn_alloc(struct au_hinode *hinode, struct inode *inode); ++void au_hn_free(struct au_hinode *hinode); ++void au_hn_ctl(struct au_hinode *hinode, int do_set); ++void au_hn_reset(struct inode *inode, unsigned int flags); ++int au_hnotify(struct inode *h_dir, struct au_hnotify *hnotify, u32 mask, ++ struct qstr *h_child_qstr, struct inode *h_child_inode); ++int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm); ++int au_hnotify_init_br(struct au_branch *br, int perm); ++void au_hnotify_fin_br(struct au_branch *br); ++int __init au_hnotify_init(void); ++void au_hnotify_fin(void); ++ ++/* hfsnotify.c */ ++extern const struct au_hnotify_op au_hnotify_op; ++ ++static inline ++void au_hn_init(struct au_hinode *hinode) ++{ ++ hinode->hi_notify = NULL; ++} ++ ++static inline struct au_hnotify *au_hn(struct au_hinode *hinode) ++{ ++ return hinode->hi_notify; ++} ++ ++#else ++AuStub(int, au_hn_alloc, return -EOPNOTSUPP, ++ struct au_hinode *hinode __maybe_unused, ++ struct inode *inode __maybe_unused) ++AuStub(struct au_hnotify *, au_hn, return NULL, struct au_hinode *hinode) ++AuStubVoid(au_hn_free, struct au_hinode *hinode __maybe_unused) ++AuStubVoid(au_hn_ctl, struct au_hinode *hinode __maybe_unused, ++ int do_set __maybe_unused) ++AuStubVoid(au_hn_reset, struct inode *inode __maybe_unused, ++ unsigned int flags __maybe_unused) ++AuStubInt0(au_hnotify_reset_br, unsigned int udba __maybe_unused, ++ struct au_branch *br __maybe_unused, ++ int perm __maybe_unused) ++AuStubInt0(au_hnotify_init_br, struct au_branch *br __maybe_unused, ++ int perm __maybe_unused) ++AuStubVoid(au_hnotify_fin_br, struct au_branch *br __maybe_unused) ++AuStubInt0(__init au_hnotify_init, void) ++AuStubVoid(au_hnotify_fin, void) ++AuStubVoid(au_hn_init, struct au_hinode *hinode __maybe_unused) ++#endif /* CONFIG_AUFS_HNOTIFY */ ++ ++static inline void au_hn_suspend(struct au_hinode *hdir) ++{ ++ au_hn_ctl(hdir, /*do_set*/0); ++} ++ ++static inline void au_hn_resume(struct au_hinode *hdir) ++{ ++ au_hn_ctl(hdir, /*do_set*/1); ++} ++ ++static inline void au_hn_inode_lock(struct au_hinode *hdir) ++{ ++ inode_lock(hdir->hi_inode); ++ au_hn_suspend(hdir); ++} ++ ++static inline void au_hn_inode_lock_nested(struct au_hinode *hdir, ++ unsigned int sc __maybe_unused) ++{ ++ inode_lock_nested(hdir->hi_inode, sc); ++ au_hn_suspend(hdir); ++} ++ ++#if 0 /* unused */ ++#include "vfsub.h" ++static inline void au_hn_inode_lock_shared_nested(struct au_hinode *hdir, ++ unsigned int sc) ++{ ++ vfsub_inode_lock_shared_nested(hdir->hi_inode, sc); ++ au_hn_suspend(hdir); ++} ++#endif ++ ++static inline void au_hn_inode_unlock(struct au_hinode *hdir) ++{ ++ au_hn_resume(hdir); ++ inode_unlock(hdir->hi_inode); ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_INODE_H__ */ +diff --git a/fs/aufs/ioctl.c b/fs/aufs/ioctl.c +new file mode 100644 +index 00000000..de188adb +--- /dev/null ++++ b/fs/aufs/ioctl.c +@@ -0,0 +1,219 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * ioctl ++ * plink-management and readdir in userspace. ++ * assist the pathconf(3) wrapper library. ++ * move-down ++ * File-based Hierarchical Storage Management. ++ */ ++ ++#include ++#include ++#include "aufs.h" ++ ++static int au_wbr_fd(struct path *path, struct aufs_wbr_fd __user *arg) ++{ ++ int err, fd; ++ aufs_bindex_t wbi, bindex, bbot; ++ struct file *h_file; ++ struct super_block *sb; ++ struct dentry *root; ++ struct au_branch *br; ++ struct aufs_wbr_fd wbrfd = { ++ .oflags = au_dir_roflags, ++ .brid = -1 ++ }; ++ const int valid = O_RDONLY | O_NONBLOCK | O_LARGEFILE | O_DIRECTORY ++ | O_NOATIME | O_CLOEXEC; ++ ++ AuDebugOn(wbrfd.oflags & ~valid); ++ ++ if (arg) { ++ err = copy_from_user(&wbrfd, arg, sizeof(wbrfd)); ++ if (unlikely(err)) { ++ err = -EFAULT; ++ goto out; ++ } ++ ++ err = -EINVAL; ++ AuDbg("wbrfd{0%o, %d}\n", wbrfd.oflags, wbrfd.brid); ++ wbrfd.oflags |= au_dir_roflags; ++ AuDbg("0%o\n", wbrfd.oflags); ++ if (unlikely(wbrfd.oflags & ~valid)) ++ goto out; ++ } ++ ++ fd = get_unused_fd_flags(0); ++ err = fd; ++ if (unlikely(fd < 0)) ++ goto out; ++ ++ h_file = ERR_PTR(-EINVAL); ++ wbi = 0; ++ br = NULL; ++ sb = path->dentry->d_sb; ++ root = sb->s_root; ++ aufs_read_lock(root, AuLock_IR); ++ bbot = au_sbbot(sb); ++ if (wbrfd.brid >= 0) { ++ wbi = au_br_index(sb, wbrfd.brid); ++ if (unlikely(wbi < 0 || wbi > bbot)) ++ goto out_unlock; ++ } ++ ++ h_file = ERR_PTR(-ENOENT); ++ br = au_sbr(sb, wbi); ++ if (!au_br_writable(br->br_perm)) { ++ if (arg) ++ goto out_unlock; ++ ++ bindex = wbi + 1; ++ wbi = -1; ++ for (; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (au_br_writable(br->br_perm)) { ++ wbi = bindex; ++ br = au_sbr(sb, wbi); ++ break; ++ } ++ } ++ } ++ AuDbg("wbi %d\n", wbi); ++ if (wbi >= 0) ++ h_file = au_h_open(root, wbi, wbrfd.oflags, NULL, ++ /*force_wr*/0); ++ ++out_unlock: ++ aufs_read_unlock(root, AuLock_IR); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out_fd; ++ ++ au_br_put(br); /* cf. au_h_open() */ ++ fd_install(fd, h_file); ++ err = fd; ++ goto out; /* success */ ++ ++out_fd: ++ put_unused_fd(fd); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg) ++{ ++ long err; ++ struct dentry *dentry; ++ ++ switch (cmd) { ++ case AUFS_CTL_RDU: ++ case AUFS_CTL_RDU_INO: ++ err = au_rdu_ioctl(file, cmd, arg); ++ break; ++ ++ case AUFS_CTL_WBR_FD: ++ err = au_wbr_fd(&file->f_path, (void __user *)arg); ++ break; ++ ++ case AUFS_CTL_IBUSY: ++ err = au_ibusy_ioctl(file, arg); ++ break; ++ ++ case AUFS_CTL_BRINFO: ++ err = au_brinfo_ioctl(file, arg); ++ break; ++ ++ case AUFS_CTL_FHSM_FD: ++ dentry = file->f_path.dentry; ++ if (IS_ROOT(dentry)) ++ err = au_fhsm_fd(dentry->d_sb, arg); ++ else ++ err = -ENOTTY; ++ break; ++ ++ default: ++ /* do not call the lower */ ++ AuDbg("0x%x\n", cmd); ++ err = -ENOTTY; ++ } ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg) ++{ ++ long err; ++ ++ switch (cmd) { ++ case AUFS_CTL_MVDOWN: ++ err = au_mvdown(file->f_path.dentry, (void __user *)arg); ++ break; ++ ++ case AUFS_CTL_WBR_FD: ++ err = au_wbr_fd(&file->f_path, (void __user *)arg); ++ break; ++ ++ default: ++ /* do not call the lower */ ++ AuDbg("0x%x\n", cmd); ++ err = -ENOTTY; ++ } ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++#ifdef CONFIG_COMPAT ++long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd, ++ unsigned long arg) ++{ ++ long err; ++ ++ switch (cmd) { ++ case AUFS_CTL_RDU: ++ case AUFS_CTL_RDU_INO: ++ err = au_rdu_compat_ioctl(file, cmd, arg); ++ break; ++ ++ case AUFS_CTL_IBUSY: ++ err = au_ibusy_compat_ioctl(file, arg); ++ break; ++ ++ case AUFS_CTL_BRINFO: ++ err = au_brinfo_compat_ioctl(file, arg); ++ break; ++ ++ default: ++ err = aufs_ioctl_dir(file, cmd, arg); ++ } ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd, ++ unsigned long arg) ++{ ++ return aufs_ioctl_nondir(file, cmd, (unsigned long)compat_ptr(arg)); ++} ++#endif +diff --git a/fs/aufs/loop.c b/fs/aufs/loop.c +new file mode 100644 +index 00000000..983ef987 +--- /dev/null ++++ b/fs/aufs/loop.c +@@ -0,0 +1,147 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * support for loopback block device as a branch ++ */ ++ ++#include "aufs.h" ++ ++/* added into drivers/block/loop.c */ ++static struct file *(*backing_file_func)(struct super_block *sb); ++ ++/* ++ * test if two lower dentries have overlapping branches. ++ */ ++int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_adding) ++{ ++ struct super_block *h_sb; ++ struct file *backing_file; ++ ++ if (unlikely(!backing_file_func)) { ++ /* don't load "loop" module here */ ++ backing_file_func = symbol_get(loop_backing_file); ++ if (unlikely(!backing_file_func)) ++ /* "loop" module is not loaded */ ++ return 0; ++ } ++ ++ h_sb = h_adding->d_sb; ++ backing_file = backing_file_func(h_sb); ++ if (!backing_file) ++ return 0; ++ ++ h_adding = backing_file->f_path.dentry; ++ /* ++ * h_adding can be local NFS. ++ * in this case aufs cannot detect the loop. ++ */ ++ if (unlikely(h_adding->d_sb == sb)) ++ return 1; ++ return !!au_test_subdir(h_adding, sb->s_root); ++} ++ ++/* true if a kernel thread named 'loop[0-9].*' accesses a file */ ++int au_test_loopback_kthread(void) ++{ ++ int ret; ++ struct task_struct *tsk = current; ++ char c, comm[sizeof(tsk->comm)]; ++ ++ ret = 0; ++ if (tsk->flags & PF_KTHREAD) { ++ get_task_comm(comm, tsk); ++ c = comm[4]; ++ ret = ('0' <= c && c <= '9' ++ && !strncmp(comm, "loop", 4)); ++ } ++ ++ return ret; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#define au_warn_loopback_step 16 ++static int au_warn_loopback_nelem = au_warn_loopback_step; ++static unsigned long *au_warn_loopback_array; ++ ++void au_warn_loopback(struct super_block *h_sb) ++{ ++ int i, new_nelem; ++ unsigned long *a, magic; ++ static DEFINE_SPINLOCK(spin); ++ ++ magic = h_sb->s_magic; ++ spin_lock(&spin); ++ a = au_warn_loopback_array; ++ for (i = 0; i < au_warn_loopback_nelem && *a; i++) ++ if (a[i] == magic) { ++ spin_unlock(&spin); ++ return; ++ } ++ ++ /* h_sb is new to us, print it */ ++ if (i < au_warn_loopback_nelem) { ++ a[i] = magic; ++ goto pr; ++ } ++ ++ /* expand the array */ ++ new_nelem = au_warn_loopback_nelem + au_warn_loopback_step; ++ a = au_kzrealloc(au_warn_loopback_array, ++ au_warn_loopback_nelem * sizeof(unsigned long), ++ new_nelem * sizeof(unsigned long), GFP_ATOMIC, ++ /*may_shrink*/0); ++ if (a) { ++ au_warn_loopback_nelem = new_nelem; ++ au_warn_loopback_array = a; ++ a[i] = magic; ++ goto pr; ++ } ++ ++ spin_unlock(&spin); ++ AuWarn1("realloc failed, ignored\n"); ++ return; ++ ++pr: ++ spin_unlock(&spin); ++ pr_warn("you may want to try another patch for loopback file " ++ "on %s(0x%lx) branch\n", au_sbtype(h_sb), magic); ++} ++ ++int au_loopback_init(void) ++{ ++ int err; ++ struct super_block *sb __maybe_unused; ++ ++ BUILD_BUG_ON(sizeof(sb->s_magic) != sizeof(unsigned long)); ++ ++ err = 0; ++ au_warn_loopback_array = kcalloc(au_warn_loopback_step, ++ sizeof(unsigned long), GFP_NOFS); ++ if (unlikely(!au_warn_loopback_array)) ++ err = -ENOMEM; ++ ++ return err; ++} ++ ++void au_loopback_fin(void) ++{ ++ if (backing_file_func) ++ symbol_put(loop_backing_file); ++ kfree(au_warn_loopback_array); ++} +diff --git a/fs/aufs/loop.h b/fs/aufs/loop.h +new file mode 100644 +index 00000000..e6b76609 +--- /dev/null ++++ b/fs/aufs/loop.h +@@ -0,0 +1,52 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * support for loopback mount as a branch ++ */ ++ ++#ifndef __AUFS_LOOP_H__ ++#define __AUFS_LOOP_H__ ++ ++#ifdef __KERNEL__ ++ ++struct dentry; ++struct super_block; ++ ++#ifdef CONFIG_AUFS_BDEV_LOOP ++/* drivers/block/loop.c */ ++struct file *loop_backing_file(struct super_block *sb); ++ ++/* loop.c */ ++int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_adding); ++int au_test_loopback_kthread(void); ++void au_warn_loopback(struct super_block *h_sb); ++ ++int au_loopback_init(void); ++void au_loopback_fin(void); ++#else ++AuStubInt0(au_test_loopback_overlap, struct super_block *sb, ++ struct dentry *h_adding) ++AuStubInt0(au_test_loopback_kthread, void) ++AuStubVoid(au_warn_loopback, struct super_block *h_sb) ++ ++AuStubInt0(au_loopback_init, void) ++AuStubVoid(au_loopback_fin, void) ++#endif /* BLK_DEV_LOOP */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_LOOP_H__ */ +diff --git a/fs/aufs/magic.mk b/fs/aufs/magic.mk +new file mode 100644 +index 00000000..4f83bdf1 +--- /dev/null ++++ b/fs/aufs/magic.mk +@@ -0,0 +1,30 @@ ++ ++# defined in ${srctree}/fs/fuse/inode.c ++# tristate ++ifdef CONFIG_FUSE_FS ++ccflags-y += -DFUSE_SUPER_MAGIC=0x65735546 ++endif ++ ++# defined in ${srctree}/fs/xfs/xfs_sb.h ++# tristate ++ifdef CONFIG_XFS_FS ++ccflags-y += -DXFS_SB_MAGIC=0x58465342 ++endif ++ ++# defined in ${srctree}/fs/configfs/mount.c ++# tristate ++ifdef CONFIG_CONFIGFS_FS ++ccflags-y += -DCONFIGFS_MAGIC=0x62656570 ++endif ++ ++# defined in ${srctree}/fs/ubifs/ubifs.h ++# tristate ++ifdef CONFIG_UBIFS_FS ++ccflags-y += -DUBIFS_SUPER_MAGIC=0x24051905 ++endif ++ ++# defined in ${srctree}/fs/hfsplus/hfsplus_raw.h ++# tristate ++ifdef CONFIG_HFSPLUS_FS ++ccflags-y += -DHFSPLUS_SUPER_MAGIC=0x482b ++endif +diff --git a/fs/aufs/module.c b/fs/aufs/module.c +new file mode 100644 +index 00000000..75e0a38e +--- /dev/null ++++ b/fs/aufs/module.c +@@ -0,0 +1,272 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * module global variables and operations ++ */ ++ ++#include ++#include ++#include "aufs.h" ++ ++/* shrinkable realloc */ ++void *au_krealloc(void *p, unsigned int new_sz, gfp_t gfp, int may_shrink) ++{ ++ size_t sz; ++ int diff; ++ ++ sz = 0; ++ diff = -1; ++ if (p) { ++#if 0 /* unused */ ++ if (!new_sz) { ++ kfree(p); ++ p = NULL; ++ goto out; ++ } ++#else ++ AuDebugOn(!new_sz); ++#endif ++ sz = ksize(p); ++ diff = au_kmidx_sub(sz, new_sz); ++ } ++ if (sz && !diff) ++ goto out; ++ ++ if (sz < new_sz) ++ /* expand or SLOB */ ++ p = krealloc(p, new_sz, gfp); ++ else if (new_sz < sz && may_shrink) { ++ /* shrink */ ++ void *q; ++ ++ q = kmalloc(new_sz, gfp); ++ if (q) { ++ if (p) { ++ memcpy(q, p, new_sz); ++ kfree(p); ++ } ++ p = q; ++ } else ++ p = NULL; ++ } ++ ++out: ++ return p; ++} ++ ++void *au_kzrealloc(void *p, unsigned int nused, unsigned int new_sz, gfp_t gfp, ++ int may_shrink) ++{ ++ p = au_krealloc(p, new_sz, gfp, may_shrink); ++ if (p && new_sz > nused) ++ memset(p + nused, 0, new_sz - nused); ++ return p; ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* ++ * aufs caches ++ */ ++struct kmem_cache *au_cache[AuCache_Last]; ++ ++static void au_cache_fin(void) ++{ ++ int i; ++ ++ /* ++ * Make sure all delayed rcu free inodes are flushed before we ++ * destroy cache. ++ */ ++ rcu_barrier(); ++ ++ /* excluding AuCache_HNOTIFY */ ++ BUILD_BUG_ON(AuCache_HNOTIFY + 1 != AuCache_Last); ++ for (i = 0; i < AuCache_HNOTIFY; i++) { ++ kmem_cache_destroy(au_cache[i]); ++ au_cache[i] = NULL; ++ } ++} ++ ++static int __init au_cache_init(void) ++{ ++ au_cache[AuCache_DINFO] = AuCacheCtor(au_dinfo, au_di_init_once); ++ if (au_cache[AuCache_DINFO]) ++ /* SLAB_DESTROY_BY_RCU */ ++ au_cache[AuCache_ICNTNR] = AuCacheCtor(au_icntnr, ++ au_icntnr_init_once); ++ if (au_cache[AuCache_ICNTNR]) ++ au_cache[AuCache_FINFO] = AuCacheCtor(au_finfo, ++ au_fi_init_once); ++ if (au_cache[AuCache_FINFO]) ++ au_cache[AuCache_VDIR] = AuCache(au_vdir); ++ if (au_cache[AuCache_VDIR]) ++ au_cache[AuCache_DEHSTR] = AuCache(au_vdir_dehstr); ++ if (au_cache[AuCache_DEHSTR]) ++ return 0; ++ ++ au_cache_fin(); ++ return -ENOMEM; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_dir_roflags; ++ ++#ifdef CONFIG_AUFS_SBILIST ++/* ++ * iterate_supers_type() doesn't protect us from ++ * remounting (branch management) ++ */ ++struct hlist_bl_head au_sbilist; ++#endif ++ ++/* ++ * functions for module interface. ++ */ ++MODULE_LICENSE("GPL"); ++/* MODULE_LICENSE("GPL v2"); */ ++MODULE_AUTHOR("Junjiro R. Okajima "); ++MODULE_DESCRIPTION(AUFS_NAME ++ " -- Advanced multi layered unification filesystem"); ++MODULE_VERSION(AUFS_VERSION); ++MODULE_ALIAS_FS(AUFS_NAME); ++ ++/* this module parameter has no meaning when SYSFS is disabled */ ++int sysaufs_brs = 1; ++MODULE_PARM_DESC(brs, "use /fs/aufs/si_*/brN"); ++module_param_named(brs, sysaufs_brs, int, 0444); ++ ++/* this module parameter has no meaning when USER_NS is disabled */ ++bool au_userns; ++MODULE_PARM_DESC(allow_userns, "allow unprivileged to mount under userns"); ++module_param_named(allow_userns, au_userns, bool, 0444); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static char au_esc_chars[0x20 + 3]; /* 0x01-0x20, backslash, del, and NULL */ ++ ++int au_seq_path(struct seq_file *seq, struct path *path) ++{ ++ int err; ++ ++ err = seq_path(seq, path, au_esc_chars); ++ if (err >= 0) ++ err = 0; ++ else ++ err = -ENOMEM; ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int __init aufs_init(void) ++{ ++ int err, i; ++ char *p; ++ ++ p = au_esc_chars; ++ for (i = 1; i <= ' '; i++) ++ *p++ = i; ++ *p++ = '\\'; ++ *p++ = '\x7f'; ++ *p = 0; ++ ++ au_dir_roflags = au_file_roflags(O_DIRECTORY | O_LARGEFILE); ++ ++ memcpy(aufs_iop_nogetattr, aufs_iop, sizeof(aufs_iop)); ++ for (i = 0; i < AuIop_Last; i++) ++ aufs_iop_nogetattr[i].getattr = NULL; ++ ++ memset(au_cache, 0, sizeof(au_cache)); /* including hnotify */ ++ ++ au_sbilist_init(); ++ sysaufs_brs_init(); ++ au_debug_init(); ++ au_dy_init(); ++ err = sysaufs_init(); ++ if (unlikely(err)) ++ goto out; ++ err = dbgaufs_init(); ++ if (unlikely(err)) ++ goto out_sysaufs; ++ err = au_procfs_init(); ++ if (unlikely(err)) ++ goto out_dbgaufs; ++ err = au_wkq_init(); ++ if (unlikely(err)) ++ goto out_procfs; ++ err = au_loopback_init(); ++ if (unlikely(err)) ++ goto out_wkq; ++ err = au_hnotify_init(); ++ if (unlikely(err)) ++ goto out_loopback; ++ err = au_sysrq_init(); ++ if (unlikely(err)) ++ goto out_hin; ++ err = au_cache_init(); ++ if (unlikely(err)) ++ goto out_sysrq; ++ ++ aufs_fs_type.fs_flags |= au_userns ? FS_USERNS_MOUNT : 0; ++ err = register_filesystem(&aufs_fs_type); ++ if (unlikely(err)) ++ goto out_cache; ++ ++ /* since we define pr_fmt, call printk directly */ ++ printk(KERN_INFO AUFS_NAME " " AUFS_VERSION "\n"); ++ goto out; /* success */ ++ ++out_cache: ++ au_cache_fin(); ++out_sysrq: ++ au_sysrq_fin(); ++out_hin: ++ au_hnotify_fin(); ++out_loopback: ++ au_loopback_fin(); ++out_wkq: ++ au_wkq_fin(); ++out_procfs: ++ au_procfs_fin(); ++out_dbgaufs: ++ dbgaufs_fin(); ++out_sysaufs: ++ sysaufs_fin(); ++ au_dy_fin(); ++out: ++ return err; ++} ++ ++static void __exit aufs_exit(void) ++{ ++ unregister_filesystem(&aufs_fs_type); ++ au_cache_fin(); ++ au_sysrq_fin(); ++ au_hnotify_fin(); ++ au_loopback_fin(); ++ au_wkq_fin(); ++ au_procfs_fin(); ++ dbgaufs_fin(); ++ sysaufs_fin(); ++ au_dy_fin(); ++} ++ ++module_init(aufs_init); ++module_exit(aufs_exit); +diff --git a/fs/aufs/module.h b/fs/aufs/module.h +new file mode 100644 +index 00000000..6d222d1c +--- /dev/null ++++ b/fs/aufs/module.h +@@ -0,0 +1,101 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * module initialization and module-global ++ */ ++ ++#ifndef __AUFS_MODULE_H__ ++#define __AUFS_MODULE_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++ ++struct path; ++struct seq_file; ++ ++/* module parameters */ ++extern int sysaufs_brs; ++extern bool au_userns; ++ ++/* ---------------------------------------------------------------------- */ ++ ++extern int au_dir_roflags; ++ ++void *au_krealloc(void *p, unsigned int new_sz, gfp_t gfp, int may_shrink); ++void *au_kzrealloc(void *p, unsigned int nused, unsigned int new_sz, gfp_t gfp, ++ int may_shrink); ++ ++static inline int au_kmidx_sub(size_t sz, size_t new_sz) ++{ ++#ifndef CONFIG_SLOB ++ return kmalloc_index(sz) - kmalloc_index(new_sz); ++#else ++ return -1; /* SLOB is untested */ ++#endif ++} ++ ++int au_seq_path(struct seq_file *seq, struct path *path); ++ ++#ifdef CONFIG_PROC_FS ++/* procfs.c */ ++int __init au_procfs_init(void); ++void au_procfs_fin(void); ++#else ++AuStubInt0(au_procfs_init, void); ++AuStubVoid(au_procfs_fin, void); ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* kmem cache */ ++enum { ++ AuCache_DINFO, ++ AuCache_ICNTNR, ++ AuCache_FINFO, ++ AuCache_VDIR, ++ AuCache_DEHSTR, ++ AuCache_HNOTIFY, /* must be last */ ++ AuCache_Last ++}; ++ ++extern struct kmem_cache *au_cache[AuCache_Last]; ++ ++#define AuCacheFlags (SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD) ++#define AuCache(type) KMEM_CACHE(type, AuCacheFlags) ++#define AuCacheCtor(type, ctor) \ ++ kmem_cache_create(#type, sizeof(struct type), \ ++ __alignof__(struct type), AuCacheFlags, ctor) ++ ++#define AuCacheFuncs(name, index) \ ++static inline struct au_##name *au_cache_alloc_##name(void) \ ++{ return kmem_cache_alloc(au_cache[AuCache_##index], GFP_NOFS); } \ ++static inline void au_cache_free_##name(struct au_##name *p) \ ++{ kmem_cache_free(au_cache[AuCache_##index], p); } ++ ++AuCacheFuncs(dinfo, DINFO); ++AuCacheFuncs(icntnr, ICNTNR); ++AuCacheFuncs(finfo, FINFO); ++AuCacheFuncs(vdir, VDIR); ++AuCacheFuncs(vdir_dehstr, DEHSTR); ++#ifdef CONFIG_AUFS_HNOTIFY ++AuCacheFuncs(hnotify, HNOTIFY); ++#endif ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_MODULE_H__ */ +diff --git a/fs/aufs/mvdown.c b/fs/aufs/mvdown.c +new file mode 100644 +index 00000000..caebd648 +--- /dev/null ++++ b/fs/aufs/mvdown.c +@@ -0,0 +1,704 @@ ++/* ++ * Copyright (C) 2011-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * move-down, opposite of copy-up ++ */ ++ ++#include "aufs.h" ++ ++struct au_mvd_args { ++ struct { ++ struct super_block *h_sb; ++ struct dentry *h_parent; ++ struct au_hinode *hdir; ++ struct inode *h_dir, *h_inode; ++ struct au_pin pin; ++ } info[AUFS_MVDOWN_NARRAY]; ++ ++ struct aufs_mvdown mvdown; ++ struct dentry *dentry, *parent; ++ struct inode *inode, *dir; ++ struct super_block *sb; ++ aufs_bindex_t bopq, bwh, bfound; ++ unsigned char rename_lock; ++}; ++ ++#define mvd_errno mvdown.au_errno ++#define mvd_bsrc mvdown.stbr[AUFS_MVDOWN_UPPER].bindex ++#define mvd_src_brid mvdown.stbr[AUFS_MVDOWN_UPPER].brid ++#define mvd_bdst mvdown.stbr[AUFS_MVDOWN_LOWER].bindex ++#define mvd_dst_brid mvdown.stbr[AUFS_MVDOWN_LOWER].brid ++ ++#define mvd_h_src_sb info[AUFS_MVDOWN_UPPER].h_sb ++#define mvd_h_src_parent info[AUFS_MVDOWN_UPPER].h_parent ++#define mvd_hdir_src info[AUFS_MVDOWN_UPPER].hdir ++#define mvd_h_src_dir info[AUFS_MVDOWN_UPPER].h_dir ++#define mvd_h_src_inode info[AUFS_MVDOWN_UPPER].h_inode ++#define mvd_pin_src info[AUFS_MVDOWN_UPPER].pin ++ ++#define mvd_h_dst_sb info[AUFS_MVDOWN_LOWER].h_sb ++#define mvd_h_dst_parent info[AUFS_MVDOWN_LOWER].h_parent ++#define mvd_hdir_dst info[AUFS_MVDOWN_LOWER].hdir ++#define mvd_h_dst_dir info[AUFS_MVDOWN_LOWER].h_dir ++#define mvd_h_dst_inode info[AUFS_MVDOWN_LOWER].h_inode ++#define mvd_pin_dst info[AUFS_MVDOWN_LOWER].pin ++ ++#define AU_MVD_PR(flag, ...) do { \ ++ if (flag) \ ++ pr_err(__VA_ARGS__); \ ++ } while (0) ++ ++static int find_lower_writable(struct au_mvd_args *a) ++{ ++ struct super_block *sb; ++ aufs_bindex_t bindex, bbot; ++ struct au_branch *br; ++ ++ sb = a->sb; ++ bindex = a->mvd_bsrc; ++ bbot = au_sbbot(sb); ++ if (a->mvdown.flags & AUFS_MVDOWN_FHSM_LOWER) ++ for (bindex++; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (au_br_fhsm(br->br_perm) ++ && (!(au_br_sb(br)->s_flags & MS_RDONLY))) ++ return bindex; ++ } ++ else if (!(a->mvdown.flags & AUFS_MVDOWN_ROLOWER)) ++ for (bindex++; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (!au_br_rdonly(br)) ++ return bindex; ++ } ++ else ++ for (bindex++; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (!(au_br_sb(br)->s_flags & MS_RDONLY)) { ++ if (au_br_rdonly(br)) ++ a->mvdown.flags ++ |= AUFS_MVDOWN_ROLOWER_R; ++ return bindex; ++ } ++ } ++ ++ return -1; ++} ++ ++/* make the parent dir on bdst */ ++static int au_do_mkdir(const unsigned char dmsg, struct au_mvd_args *a) ++{ ++ int err; ++ ++ err = 0; ++ a->mvd_hdir_src = au_hi(a->dir, a->mvd_bsrc); ++ a->mvd_hdir_dst = au_hi(a->dir, a->mvd_bdst); ++ a->mvd_h_src_parent = au_h_dptr(a->parent, a->mvd_bsrc); ++ a->mvd_h_dst_parent = NULL; ++ if (au_dbbot(a->parent) >= a->mvd_bdst) ++ a->mvd_h_dst_parent = au_h_dptr(a->parent, a->mvd_bdst); ++ if (!a->mvd_h_dst_parent) { ++ err = au_cpdown_dirs(a->dentry, a->mvd_bdst); ++ if (unlikely(err)) { ++ AU_MVD_PR(dmsg, "cpdown_dirs failed\n"); ++ goto out; ++ } ++ a->mvd_h_dst_parent = au_h_dptr(a->parent, a->mvd_bdst); ++ } ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* lock them all */ ++static int au_do_lock(const unsigned char dmsg, struct au_mvd_args *a) ++{ ++ int err; ++ struct dentry *h_trap; ++ ++ a->mvd_h_src_sb = au_sbr_sb(a->sb, a->mvd_bsrc); ++ a->mvd_h_dst_sb = au_sbr_sb(a->sb, a->mvd_bdst); ++ err = au_pin(&a->mvd_pin_dst, a->dentry, a->mvd_bdst, ++ au_opt_udba(a->sb), ++ AuPin_MNT_WRITE | AuPin_DI_LOCKED); ++ AuTraceErr(err); ++ if (unlikely(err)) { ++ AU_MVD_PR(dmsg, "pin_dst failed\n"); ++ goto out; ++ } ++ ++ if (a->mvd_h_src_sb != a->mvd_h_dst_sb) { ++ a->rename_lock = 0; ++ au_pin_init(&a->mvd_pin_src, a->dentry, a->mvd_bsrc, ++ AuLsc_DI_PARENT, AuLsc_I_PARENT3, ++ au_opt_udba(a->sb), ++ AuPin_MNT_WRITE | AuPin_DI_LOCKED); ++ err = au_do_pin(&a->mvd_pin_src); ++ AuTraceErr(err); ++ a->mvd_h_src_dir = d_inode(a->mvd_h_src_parent); ++ if (unlikely(err)) { ++ AU_MVD_PR(dmsg, "pin_src failed\n"); ++ goto out_dst; ++ } ++ goto out; /* success */ ++ } ++ ++ a->rename_lock = 1; ++ au_pin_hdir_unlock(&a->mvd_pin_dst); ++ err = au_pin(&a->mvd_pin_src, a->dentry, a->mvd_bsrc, ++ au_opt_udba(a->sb), ++ AuPin_MNT_WRITE | AuPin_DI_LOCKED); ++ AuTraceErr(err); ++ a->mvd_h_src_dir = d_inode(a->mvd_h_src_parent); ++ if (unlikely(err)) { ++ AU_MVD_PR(dmsg, "pin_src failed\n"); ++ au_pin_hdir_lock(&a->mvd_pin_dst); ++ goto out_dst; ++ } ++ au_pin_hdir_unlock(&a->mvd_pin_src); ++ h_trap = vfsub_lock_rename(a->mvd_h_src_parent, a->mvd_hdir_src, ++ a->mvd_h_dst_parent, a->mvd_hdir_dst); ++ if (h_trap) { ++ err = (h_trap != a->mvd_h_src_parent); ++ if (err) ++ err = (h_trap != a->mvd_h_dst_parent); ++ } ++ BUG_ON(err); /* it should never happen */ ++ if (unlikely(a->mvd_h_src_dir != au_pinned_h_dir(&a->mvd_pin_src))) { ++ err = -EBUSY; ++ AuTraceErr(err); ++ vfsub_unlock_rename(a->mvd_h_src_parent, a->mvd_hdir_src, ++ a->mvd_h_dst_parent, a->mvd_hdir_dst); ++ au_pin_hdir_lock(&a->mvd_pin_src); ++ au_unpin(&a->mvd_pin_src); ++ au_pin_hdir_lock(&a->mvd_pin_dst); ++ goto out_dst; ++ } ++ goto out; /* success */ ++ ++out_dst: ++ au_unpin(&a->mvd_pin_dst); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++static void au_do_unlock(const unsigned char dmsg, struct au_mvd_args *a) ++{ ++ if (!a->rename_lock) ++ au_unpin(&a->mvd_pin_src); ++ else { ++ vfsub_unlock_rename(a->mvd_h_src_parent, a->mvd_hdir_src, ++ a->mvd_h_dst_parent, a->mvd_hdir_dst); ++ au_pin_hdir_lock(&a->mvd_pin_src); ++ au_unpin(&a->mvd_pin_src); ++ au_pin_hdir_lock(&a->mvd_pin_dst); ++ } ++ au_unpin(&a->mvd_pin_dst); ++} ++ ++/* copy-down the file */ ++static int au_do_cpdown(const unsigned char dmsg, struct au_mvd_args *a) ++{ ++ int err; ++ struct au_cp_generic cpg = { ++ .dentry = a->dentry, ++ .bdst = a->mvd_bdst, ++ .bsrc = a->mvd_bsrc, ++ .len = -1, ++ .pin = &a->mvd_pin_dst, ++ .flags = AuCpup_DTIME | AuCpup_HOPEN ++ }; ++ ++ AuDbg("b%d, b%d\n", cpg.bsrc, cpg.bdst); ++ if (a->mvdown.flags & AUFS_MVDOWN_OWLOWER) ++ au_fset_cpup(cpg.flags, OVERWRITE); ++ if (a->mvdown.flags & AUFS_MVDOWN_ROLOWER) ++ au_fset_cpup(cpg.flags, RWDST); ++ err = au_sio_cpdown_simple(&cpg); ++ if (unlikely(err)) ++ AU_MVD_PR(dmsg, "cpdown failed\n"); ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ++ * unlink the whiteout on bdst if exist which may be created by UDBA while we ++ * were sleeping ++ */ ++static int au_do_unlink_wh(const unsigned char dmsg, struct au_mvd_args *a) ++{ ++ int err; ++ struct path h_path; ++ struct au_branch *br; ++ struct inode *delegated; ++ ++ br = au_sbr(a->sb, a->mvd_bdst); ++ h_path.dentry = au_wh_lkup(a->mvd_h_dst_parent, &a->dentry->d_name, br); ++ err = PTR_ERR(h_path.dentry); ++ if (IS_ERR(h_path.dentry)) { ++ AU_MVD_PR(dmsg, "wh_lkup failed\n"); ++ goto out; ++ } ++ ++ err = 0; ++ if (d_is_positive(h_path.dentry)) { ++ h_path.mnt = au_br_mnt(br); ++ delegated = NULL; ++ err = vfsub_unlink(d_inode(a->mvd_h_dst_parent), &h_path, ++ &delegated, /*force*/0); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal unlink\n"); ++ iput(delegated); ++ } ++ if (unlikely(err)) ++ AU_MVD_PR(dmsg, "wh_unlink failed\n"); ++ } ++ dput(h_path.dentry); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ++ * unlink the topmost h_dentry ++ */ ++static int au_do_unlink(const unsigned char dmsg, struct au_mvd_args *a) ++{ ++ int err; ++ struct path h_path; ++ struct inode *delegated; ++ ++ h_path.mnt = au_sbr_mnt(a->sb, a->mvd_bsrc); ++ h_path.dentry = au_h_dptr(a->dentry, a->mvd_bsrc); ++ delegated = NULL; ++ err = vfsub_unlink(a->mvd_h_src_dir, &h_path, &delegated, /*force*/0); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal unlink\n"); ++ iput(delegated); ++ } ++ if (unlikely(err)) ++ AU_MVD_PR(dmsg, "unlink failed\n"); ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++/* Since mvdown succeeded, we ignore an error of this function */ ++static void au_do_stfs(const unsigned char dmsg, struct au_mvd_args *a) ++{ ++ int err; ++ struct au_branch *br; ++ ++ a->mvdown.flags |= AUFS_MVDOWN_STFS_FAILED; ++ br = au_sbr(a->sb, a->mvd_bsrc); ++ err = au_br_stfs(br, &a->mvdown.stbr[AUFS_MVDOWN_UPPER].stfs); ++ if (!err) { ++ br = au_sbr(a->sb, a->mvd_bdst); ++ a->mvdown.stbr[AUFS_MVDOWN_LOWER].brid = br->br_id; ++ err = au_br_stfs(br, &a->mvdown.stbr[AUFS_MVDOWN_LOWER].stfs); ++ } ++ if (!err) ++ a->mvdown.flags &= ~AUFS_MVDOWN_STFS_FAILED; ++ else ++ AU_MVD_PR(dmsg, "statfs failed (%d), ignored\n", err); ++} ++ ++/* ++ * copy-down the file and unlink the bsrc file. ++ * - unlink the bdst whout if exist ++ * - copy-down the file (with whtmp name and rename) ++ * - unlink the bsrc file ++ */ ++static int au_do_mvdown(const unsigned char dmsg, struct au_mvd_args *a) ++{ ++ int err; ++ ++ err = au_do_mkdir(dmsg, a); ++ if (!err) ++ err = au_do_lock(dmsg, a); ++ if (unlikely(err)) ++ goto out; ++ ++ /* ++ * do not revert the activities we made on bdst since they should be ++ * harmless in aufs. ++ */ ++ ++ err = au_do_cpdown(dmsg, a); ++ if (!err) ++ err = au_do_unlink_wh(dmsg, a); ++ if (!err && !(a->mvdown.flags & AUFS_MVDOWN_KUPPER)) ++ err = au_do_unlink(dmsg, a); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ AuDbg("%pd2, 0x%x, %d --> %d\n", ++ a->dentry, a->mvdown.flags, a->mvd_bsrc, a->mvd_bdst); ++ if (find_lower_writable(a) < 0) ++ a->mvdown.flags |= AUFS_MVDOWN_BOTTOM; ++ ++ if (a->mvdown.flags & AUFS_MVDOWN_STFS) ++ au_do_stfs(dmsg, a); ++ ++ /* maintain internal array */ ++ if (!(a->mvdown.flags & AUFS_MVDOWN_KUPPER)) { ++ au_set_h_dptr(a->dentry, a->mvd_bsrc, NULL); ++ au_set_dbtop(a->dentry, a->mvd_bdst); ++ au_set_h_iptr(a->inode, a->mvd_bsrc, NULL, /*flags*/0); ++ au_set_ibtop(a->inode, a->mvd_bdst); ++ } else { ++ /* hide the lower */ ++ au_set_h_dptr(a->dentry, a->mvd_bdst, NULL); ++ au_set_dbbot(a->dentry, a->mvd_bsrc); ++ au_set_h_iptr(a->inode, a->mvd_bdst, NULL, /*flags*/0); ++ au_set_ibbot(a->inode, a->mvd_bsrc); ++ } ++ if (au_dbbot(a->dentry) < a->mvd_bdst) ++ au_set_dbbot(a->dentry, a->mvd_bdst); ++ if (au_ibbot(a->inode) < a->mvd_bdst) ++ au_set_ibbot(a->inode, a->mvd_bdst); ++ ++out_unlock: ++ au_do_unlock(dmsg, a); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* make sure the file is idle */ ++static int au_mvd_args_busy(const unsigned char dmsg, struct au_mvd_args *a) ++{ ++ int err, plinked; ++ ++ err = 0; ++ plinked = !!au_opt_test(au_mntflags(a->sb), PLINK); ++ if (au_dbtop(a->dentry) == a->mvd_bsrc ++ && au_dcount(a->dentry) == 1 ++ && atomic_read(&a->inode->i_count) == 1 ++ /* && a->mvd_h_src_inode->i_nlink == 1 */ ++ && (!plinked || !au_plink_test(a->inode)) ++ && a->inode->i_nlink == 1) ++ goto out; ++ ++ err = -EBUSY; ++ AU_MVD_PR(dmsg, ++ "b%d, d{b%d, c%d?}, i{c%d?, l%u}, hi{l%u}, p{%d, %d}\n", ++ a->mvd_bsrc, au_dbtop(a->dentry), au_dcount(a->dentry), ++ atomic_read(&a->inode->i_count), a->inode->i_nlink, ++ a->mvd_h_src_inode->i_nlink, ++ plinked, plinked ? au_plink_test(a->inode) : 0); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* make sure the parent dir is fine */ ++static int au_mvd_args_parent(const unsigned char dmsg, ++ struct au_mvd_args *a) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ ++ err = 0; ++ if (unlikely(au_alive_dir(a->parent))) { ++ err = -ENOENT; ++ AU_MVD_PR(dmsg, "parent dir is dead\n"); ++ goto out; ++ } ++ ++ a->bopq = au_dbdiropq(a->parent); ++ bindex = au_wbr_nonopq(a->dentry, a->mvd_bdst); ++ AuDbg("b%d\n", bindex); ++ if (unlikely((bindex >= 0 && bindex < a->mvd_bdst) ++ || (a->bopq != -1 && a->bopq < a->mvd_bdst))) { ++ err = -EINVAL; ++ a->mvd_errno = EAU_MVDOWN_OPAQUE; ++ AU_MVD_PR(dmsg, "ancestor is opaque b%d, b%d\n", ++ a->bopq, a->mvd_bdst); ++ } ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++static int au_mvd_args_intermediate(const unsigned char dmsg, ++ struct au_mvd_args *a) ++{ ++ int err; ++ struct au_dinfo *dinfo, *tmp; ++ ++ /* lookup the next lower positive entry */ ++ err = -ENOMEM; ++ tmp = au_di_alloc(a->sb, AuLsc_DI_TMP); ++ if (unlikely(!tmp)) ++ goto out; ++ ++ a->bfound = -1; ++ a->bwh = -1; ++ dinfo = au_di(a->dentry); ++ au_di_cp(tmp, dinfo); ++ au_di_swap(tmp, dinfo); ++ ++ /* returns the number of positive dentries */ ++ err = au_lkup_dentry(a->dentry, a->mvd_bsrc + 1, ++ /* AuLkup_IGNORE_PERM */ 0); ++ if (!err) ++ a->bwh = au_dbwh(a->dentry); ++ else if (err > 0) ++ a->bfound = au_dbtop(a->dentry); ++ ++ au_di_swap(tmp, dinfo); ++ au_rw_write_unlock(&tmp->di_rwsem); ++ au_di_free(tmp); ++ if (unlikely(err < 0)) ++ AU_MVD_PR(dmsg, "failed look-up lower\n"); ++ ++ /* ++ * here, we have these cases. ++ * bfound == -1 ++ * no positive dentry under bsrc. there are more sub-cases. ++ * bwh < 0 ++ * there no whiteout, we can safely move-down. ++ * bwh <= bsrc ++ * impossible ++ * bsrc < bwh && bwh < bdst ++ * there is a whiteout on RO branch. cannot proceed. ++ * bwh == bdst ++ * there is a whiteout on the RW target branch. it should ++ * be removed. ++ * bdst < bwh ++ * there is a whiteout somewhere unrelated branch. ++ * -1 < bfound && bfound <= bsrc ++ * impossible. ++ * bfound < bdst ++ * found, but it is on RO branch between bsrc and bdst. cannot ++ * proceed. ++ * bfound == bdst ++ * found, replace it if AUFS_MVDOWN_FORCE is set. otherwise return ++ * error. ++ * bdst < bfound ++ * found, after we create the file on bdst, it will be hidden. ++ */ ++ ++ AuDebugOn(a->bfound == -1 ++ && a->bwh != -1 ++ && a->bwh <= a->mvd_bsrc); ++ AuDebugOn(-1 < a->bfound ++ && a->bfound <= a->mvd_bsrc); ++ ++ err = -EINVAL; ++ if (a->bfound == -1 ++ && a->mvd_bsrc < a->bwh ++ && a->bwh != -1 ++ && a->bwh < a->mvd_bdst) { ++ a->mvd_errno = EAU_MVDOWN_WHITEOUT; ++ AU_MVD_PR(dmsg, "bsrc %d, bdst %d, bfound %d, bwh %d\n", ++ a->mvd_bsrc, a->mvd_bdst, a->bfound, a->bwh); ++ goto out; ++ } else if (a->bfound != -1 && a->bfound < a->mvd_bdst) { ++ a->mvd_errno = EAU_MVDOWN_UPPER; ++ AU_MVD_PR(dmsg, "bdst %d, bfound %d\n", ++ a->mvd_bdst, a->bfound); ++ goto out; ++ } ++ ++ err = 0; /* success */ ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++static int au_mvd_args_exist(const unsigned char dmsg, struct au_mvd_args *a) ++{ ++ int err; ++ ++ err = 0; ++ if (!(a->mvdown.flags & AUFS_MVDOWN_OWLOWER) ++ && a->bfound == a->mvd_bdst) ++ err = -EEXIST; ++ AuTraceErr(err); ++ return err; ++} ++ ++static int au_mvd_args(const unsigned char dmsg, struct au_mvd_args *a) ++{ ++ int err; ++ struct au_branch *br; ++ ++ err = -EISDIR; ++ if (unlikely(S_ISDIR(a->inode->i_mode))) ++ goto out; ++ ++ err = -EINVAL; ++ if (!(a->mvdown.flags & AUFS_MVDOWN_BRID_UPPER)) ++ a->mvd_bsrc = au_ibtop(a->inode); ++ else { ++ a->mvd_bsrc = au_br_index(a->sb, a->mvd_src_brid); ++ if (unlikely(a->mvd_bsrc < 0 ++ || (a->mvd_bsrc < au_dbtop(a->dentry) ++ || au_dbbot(a->dentry) < a->mvd_bsrc ++ || !au_h_dptr(a->dentry, a->mvd_bsrc)) ++ || (a->mvd_bsrc < au_ibtop(a->inode) ++ || au_ibbot(a->inode) < a->mvd_bsrc ++ || !au_h_iptr(a->inode, a->mvd_bsrc)))) { ++ a->mvd_errno = EAU_MVDOWN_NOUPPER; ++ AU_MVD_PR(dmsg, "no upper\n"); ++ goto out; ++ } ++ } ++ if (unlikely(a->mvd_bsrc == au_sbbot(a->sb))) { ++ a->mvd_errno = EAU_MVDOWN_BOTTOM; ++ AU_MVD_PR(dmsg, "on the bottom\n"); ++ goto out; ++ } ++ a->mvd_h_src_inode = au_h_iptr(a->inode, a->mvd_bsrc); ++ br = au_sbr(a->sb, a->mvd_bsrc); ++ err = au_br_rdonly(br); ++ if (!(a->mvdown.flags & AUFS_MVDOWN_ROUPPER)) { ++ if (unlikely(err)) ++ goto out; ++ } else if (!(vfsub_native_ro(a->mvd_h_src_inode) ++ || IS_APPEND(a->mvd_h_src_inode))) { ++ if (err) ++ a->mvdown.flags |= AUFS_MVDOWN_ROUPPER_R; ++ /* go on */ ++ } else ++ goto out; ++ ++ err = -EINVAL; ++ if (!(a->mvdown.flags & AUFS_MVDOWN_BRID_LOWER)) { ++ a->mvd_bdst = find_lower_writable(a); ++ if (unlikely(a->mvd_bdst < 0)) { ++ a->mvd_errno = EAU_MVDOWN_BOTTOM; ++ AU_MVD_PR(dmsg, "no writable lower branch\n"); ++ goto out; ++ } ++ } else { ++ a->mvd_bdst = au_br_index(a->sb, a->mvd_dst_brid); ++ if (unlikely(a->mvd_bdst < 0 ++ || au_sbbot(a->sb) < a->mvd_bdst)) { ++ a->mvd_errno = EAU_MVDOWN_NOLOWERBR; ++ AU_MVD_PR(dmsg, "no lower brid\n"); ++ goto out; ++ } ++ } ++ ++ err = au_mvd_args_busy(dmsg, a); ++ if (!err) ++ err = au_mvd_args_parent(dmsg, a); ++ if (!err) ++ err = au_mvd_args_intermediate(dmsg, a); ++ if (!err) ++ err = au_mvd_args_exist(dmsg, a); ++ if (!err) ++ AuDbg("b%d, b%d\n", a->mvd_bsrc, a->mvd_bdst); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++int au_mvdown(struct dentry *dentry, struct aufs_mvdown __user *uarg) ++{ ++ int err, e; ++ unsigned char dmsg; ++ struct au_mvd_args *args; ++ struct inode *inode; ++ ++ inode = d_inode(dentry); ++ err = -EPERM; ++ if (unlikely(!capable(CAP_SYS_ADMIN))) ++ goto out; ++ ++ err = -ENOMEM; ++ args = kmalloc(sizeof(*args), GFP_NOFS); ++ if (unlikely(!args)) ++ goto out; ++ ++ err = copy_from_user(&args->mvdown, uarg, sizeof(args->mvdown)); ++ if (!err) ++ err = !access_ok(VERIFY_WRITE, uarg, sizeof(*uarg)); ++ if (unlikely(err)) { ++ err = -EFAULT; ++ AuTraceErr(err); ++ goto out_free; ++ } ++ AuDbg("flags 0x%x\n", args->mvdown.flags); ++ args->mvdown.flags &= ~(AUFS_MVDOWN_ROLOWER_R | AUFS_MVDOWN_ROUPPER_R); ++ args->mvdown.au_errno = 0; ++ args->dentry = dentry; ++ args->inode = inode; ++ args->sb = dentry->d_sb; ++ ++ err = -ENOENT; ++ dmsg = !!(args->mvdown.flags & AUFS_MVDOWN_DMSG); ++ args->parent = dget_parent(dentry); ++ args->dir = d_inode(args->parent); ++ inode_lock_nested(args->dir, I_MUTEX_PARENT); ++ dput(args->parent); ++ if (unlikely(args->parent != dentry->d_parent)) { ++ AU_MVD_PR(dmsg, "parent dir is moved\n"); ++ goto out_dir; ++ } ++ ++ inode_lock_nested(inode, I_MUTEX_CHILD); ++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_NOPLMW); ++ if (unlikely(err)) ++ goto out_inode; ++ ++ di_write_lock_parent(args->parent); ++ err = au_mvd_args(dmsg, args); ++ if (unlikely(err)) ++ goto out_parent; ++ ++ err = au_do_mvdown(dmsg, args); ++ if (unlikely(err)) ++ goto out_parent; ++ ++ au_cpup_attr_timesizes(args->dir); ++ au_cpup_attr_timesizes(inode); ++ if (!(args->mvdown.flags & AUFS_MVDOWN_KUPPER)) ++ au_cpup_igen(inode, au_h_iptr(inode, args->mvd_bdst)); ++ /* au_digen_dec(dentry); */ ++ ++out_parent: ++ di_write_unlock(args->parent); ++ aufs_read_unlock(dentry, AuLock_DW); ++out_inode: ++ inode_unlock(inode); ++out_dir: ++ inode_unlock(args->dir); ++out_free: ++ e = copy_to_user(uarg, &args->mvdown, sizeof(args->mvdown)); ++ if (unlikely(e)) ++ err = -EFAULT; ++ kfree(args); ++out: ++ AuTraceErr(err); ++ return err; ++} +diff --git a/fs/aufs/opts.c b/fs/aufs/opts.c +new file mode 100644 +index 00000000..9626153b +--- /dev/null ++++ b/fs/aufs/opts.c +@@ -0,0 +1,1912 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * mount options/flags ++ */ ++ ++#include ++#include /* a distribution requires */ ++#include ++#include "aufs.h" ++ ++/* ---------------------------------------------------------------------- */ ++ ++enum { ++ Opt_br, ++ Opt_add, Opt_del, Opt_mod, Opt_append, Opt_prepend, ++ Opt_idel, Opt_imod, ++ Opt_dirwh, Opt_rdcache, Opt_rdblk, Opt_rdhash, ++ Opt_rdblk_def, Opt_rdhash_def, ++ Opt_xino, Opt_noxino, ++ Opt_trunc_xino, Opt_trunc_xino_v, Opt_notrunc_xino, ++ Opt_trunc_xino_path, Opt_itrunc_xino, ++ Opt_trunc_xib, Opt_notrunc_xib, ++ Opt_shwh, Opt_noshwh, ++ Opt_plink, Opt_noplink, Opt_list_plink, ++ Opt_udba, ++ Opt_dio, Opt_nodio, ++ Opt_diropq_a, Opt_diropq_w, ++ Opt_warn_perm, Opt_nowarn_perm, ++ Opt_wbr_copyup, Opt_wbr_create, ++ Opt_fhsm_sec, ++ Opt_verbose, Opt_noverbose, ++ Opt_sum, Opt_nosum, Opt_wsum, ++ Opt_dirperm1, Opt_nodirperm1, ++ Opt_dirren, Opt_nodirren, ++ Opt_acl, Opt_noacl, ++ Opt_tail, Opt_ignore, Opt_ignore_silent, Opt_err ++}; ++ ++static match_table_t options = { ++ {Opt_br, "br=%s"}, ++ {Opt_br, "br:%s"}, ++ ++ {Opt_add, "add=%d:%s"}, ++ {Opt_add, "add:%d:%s"}, ++ {Opt_add, "ins=%d:%s"}, ++ {Opt_add, "ins:%d:%s"}, ++ {Opt_append, "append=%s"}, ++ {Opt_append, "append:%s"}, ++ {Opt_prepend, "prepend=%s"}, ++ {Opt_prepend, "prepend:%s"}, ++ ++ {Opt_del, "del=%s"}, ++ {Opt_del, "del:%s"}, ++ /* {Opt_idel, "idel:%d"}, */ ++ {Opt_mod, "mod=%s"}, ++ {Opt_mod, "mod:%s"}, ++ /* {Opt_imod, "imod:%d:%s"}, */ ++ ++ {Opt_dirwh, "dirwh=%d"}, ++ ++ {Opt_xino, "xino=%s"}, ++ {Opt_noxino, "noxino"}, ++ {Opt_trunc_xino, "trunc_xino"}, ++ {Opt_trunc_xino_v, "trunc_xino_v=%d:%d"}, ++ {Opt_notrunc_xino, "notrunc_xino"}, ++ {Opt_trunc_xino_path, "trunc_xino=%s"}, ++ {Opt_itrunc_xino, "itrunc_xino=%d"}, ++ /* {Opt_zxino, "zxino=%s"}, */ ++ {Opt_trunc_xib, "trunc_xib"}, ++ {Opt_notrunc_xib, "notrunc_xib"}, ++ ++#ifdef CONFIG_PROC_FS ++ {Opt_plink, "plink"}, ++#else ++ {Opt_ignore_silent, "plink"}, ++#endif ++ ++ {Opt_noplink, "noplink"}, ++ ++#ifdef CONFIG_AUFS_DEBUG ++ {Opt_list_plink, "list_plink"}, ++#endif ++ ++ {Opt_udba, "udba=%s"}, ++ ++ {Opt_dio, "dio"}, ++ {Opt_nodio, "nodio"}, ++ ++#ifdef CONFIG_AUFS_DIRREN ++ {Opt_dirren, "dirren"}, ++ {Opt_nodirren, "nodirren"}, ++#else ++ {Opt_ignore, "dirren"}, ++ {Opt_ignore_silent, "nodirren"}, ++#endif ++ ++#ifdef CONFIG_AUFS_FHSM ++ {Opt_fhsm_sec, "fhsm_sec=%d"}, ++#else ++ {Opt_ignore, "fhsm_sec=%d"}, ++#endif ++ ++ {Opt_diropq_a, "diropq=always"}, ++ {Opt_diropq_a, "diropq=a"}, ++ {Opt_diropq_w, "diropq=whiteouted"}, ++ {Opt_diropq_w, "diropq=w"}, ++ ++ {Opt_warn_perm, "warn_perm"}, ++ {Opt_nowarn_perm, "nowarn_perm"}, ++ ++ /* keep them temporary */ ++ {Opt_ignore_silent, "nodlgt"}, ++ {Opt_ignore, "clean_plink"}, ++ ++#ifdef CONFIG_AUFS_SHWH ++ {Opt_shwh, "shwh"}, ++#endif ++ {Opt_noshwh, "noshwh"}, ++ ++ {Opt_dirperm1, "dirperm1"}, ++ {Opt_nodirperm1, "nodirperm1"}, ++ ++ {Opt_verbose, "verbose"}, ++ {Opt_verbose, "v"}, ++ {Opt_noverbose, "noverbose"}, ++ {Opt_noverbose, "quiet"}, ++ {Opt_noverbose, "q"}, ++ {Opt_noverbose, "silent"}, ++ ++ {Opt_sum, "sum"}, ++ {Opt_nosum, "nosum"}, ++ {Opt_wsum, "wsum"}, ++ ++ {Opt_rdcache, "rdcache=%d"}, ++ {Opt_rdblk, "rdblk=%d"}, ++ {Opt_rdblk_def, "rdblk=def"}, ++ {Opt_rdhash, "rdhash=%d"}, ++ {Opt_rdhash_def, "rdhash=def"}, ++ ++ {Opt_wbr_create, "create=%s"}, ++ {Opt_wbr_create, "create_policy=%s"}, ++ {Opt_wbr_copyup, "cpup=%s"}, ++ {Opt_wbr_copyup, "copyup=%s"}, ++ {Opt_wbr_copyup, "copyup_policy=%s"}, ++ ++ /* generic VFS flag */ ++#ifdef CONFIG_FS_POSIX_ACL ++ {Opt_acl, "acl"}, ++ {Opt_noacl, "noacl"}, ++#else ++ {Opt_ignore, "acl"}, ++ {Opt_ignore_silent, "noacl"}, ++#endif ++ ++ /* internal use for the scripts */ ++ {Opt_ignore_silent, "si=%s"}, ++ ++ {Opt_br, "dirs=%s"}, ++ {Opt_ignore, "debug=%d"}, ++ {Opt_ignore, "delete=whiteout"}, ++ {Opt_ignore, "delete=all"}, ++ {Opt_ignore, "imap=%s"}, ++ ++ /* temporary workaround, due to old mount(8)? */ ++ {Opt_ignore_silent, "relatime"}, ++ ++ {Opt_err, NULL} ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static const char *au_parser_pattern(int val, match_table_t tbl) ++{ ++ struct match_token *p; ++ ++ p = tbl; ++ while (p->pattern) { ++ if (p->token == val) ++ return p->pattern; ++ p++; ++ } ++ BUG(); ++ return "??"; ++} ++ ++static const char *au_optstr(int *val, match_table_t tbl) ++{ ++ struct match_token *p; ++ int v; ++ ++ v = *val; ++ if (!v) ++ goto out; ++ p = tbl; ++ while (p->pattern) { ++ if (p->token ++ && (v & p->token) == p->token) { ++ *val &= ~p->token; ++ return p->pattern; ++ } ++ p++; ++ } ++ ++out: ++ return NULL; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static match_table_t brperm = { ++ {AuBrPerm_RO, AUFS_BRPERM_RO}, ++ {AuBrPerm_RR, AUFS_BRPERM_RR}, ++ {AuBrPerm_RW, AUFS_BRPERM_RW}, ++ {0, NULL} ++}; ++ ++static match_table_t brattr = { ++ /* general */ ++ {AuBrAttr_COO_REG, AUFS_BRATTR_COO_REG}, ++ {AuBrAttr_COO_ALL, AUFS_BRATTR_COO_ALL}, ++ /* 'unpin' attrib is meaningless since linux-3.18-rc1 */ ++ {AuBrAttr_UNPIN, AUFS_BRATTR_UNPIN}, ++#ifdef CONFIG_AUFS_FHSM ++ {AuBrAttr_FHSM, AUFS_BRATTR_FHSM}, ++#endif ++#ifdef CONFIG_AUFS_XATTR ++ {AuBrAttr_ICEX, AUFS_BRATTR_ICEX}, ++ {AuBrAttr_ICEX_SEC, AUFS_BRATTR_ICEX_SEC}, ++ {AuBrAttr_ICEX_SYS, AUFS_BRATTR_ICEX_SYS}, ++ {AuBrAttr_ICEX_TR, AUFS_BRATTR_ICEX_TR}, ++ {AuBrAttr_ICEX_USR, AUFS_BRATTR_ICEX_USR}, ++ {AuBrAttr_ICEX_OTH, AUFS_BRATTR_ICEX_OTH}, ++#endif ++ ++ /* ro/rr branch */ ++ {AuBrRAttr_WH, AUFS_BRRATTR_WH}, ++ ++ /* rw branch */ ++ {AuBrWAttr_MOO, AUFS_BRWATTR_MOO}, ++ {AuBrWAttr_NoLinkWH, AUFS_BRWATTR_NLWH}, ++ ++ {0, NULL} ++}; ++ ++static int br_attr_val(char *str, match_table_t table, substring_t args[]) ++{ ++ int attr, v; ++ char *p; ++ ++ attr = 0; ++ do { ++ p = strchr(str, '+'); ++ if (p) ++ *p = 0; ++ v = match_token(str, table, args); ++ if (v) { ++ if (v & AuBrAttr_CMOO_Mask) ++ attr &= ~AuBrAttr_CMOO_Mask; ++ attr |= v; ++ } else { ++ if (p) ++ *p = '+'; ++ pr_warn("ignored branch attribute %s\n", str); ++ break; ++ } ++ if (p) ++ str = p + 1; ++ } while (p); ++ ++ return attr; ++} ++ ++static int au_do_optstr_br_attr(au_br_perm_str_t *str, int perm) ++{ ++ int sz; ++ const char *p; ++ char *q; ++ ++ q = str->a; ++ *q = 0; ++ p = au_optstr(&perm, brattr); ++ if (p) { ++ sz = strlen(p); ++ memcpy(q, p, sz + 1); ++ q += sz; ++ } else ++ goto out; ++ ++ do { ++ p = au_optstr(&perm, brattr); ++ if (p) { ++ *q++ = '+'; ++ sz = strlen(p); ++ memcpy(q, p, sz + 1); ++ q += sz; ++ } ++ } while (p); ++ ++out: ++ return q - str->a; ++} ++ ++static int noinline_for_stack br_perm_val(char *perm) ++{ ++ int val, bad, sz; ++ char *p; ++ substring_t args[MAX_OPT_ARGS]; ++ au_br_perm_str_t attr; ++ ++ p = strchr(perm, '+'); ++ if (p) ++ *p = 0; ++ val = match_token(perm, brperm, args); ++ if (!val) { ++ if (p) ++ *p = '+'; ++ pr_warn("ignored branch permission %s\n", perm); ++ val = AuBrPerm_RO; ++ goto out; ++ } ++ if (!p) ++ goto out; ++ ++ val |= br_attr_val(p + 1, brattr, args); ++ ++ bad = 0; ++ switch (val & AuBrPerm_Mask) { ++ case AuBrPerm_RO: ++ case AuBrPerm_RR: ++ bad = val & AuBrWAttr_Mask; ++ val &= ~AuBrWAttr_Mask; ++ break; ++ case AuBrPerm_RW: ++ bad = val & AuBrRAttr_Mask; ++ val &= ~AuBrRAttr_Mask; ++ break; ++ } ++ ++ /* ++ * 'unpin' attrib becomes meaningless since linux-3.18-rc1, but aufs ++ * does not treat it as an error, just warning. ++ * this is a tiny guard for the user operation. ++ */ ++ if (val & AuBrAttr_UNPIN) { ++ bad |= AuBrAttr_UNPIN; ++ val &= ~AuBrAttr_UNPIN; ++ } ++ ++ if (unlikely(bad)) { ++ sz = au_do_optstr_br_attr(&attr, bad); ++ AuDebugOn(!sz); ++ pr_warn("ignored branch attribute %s\n", attr.a); ++ } ++ ++out: ++ return val; ++} ++ ++void au_optstr_br_perm(au_br_perm_str_t *str, int perm) ++{ ++ au_br_perm_str_t attr; ++ const char *p; ++ char *q; ++ int sz; ++ ++ q = str->a; ++ p = au_optstr(&perm, brperm); ++ AuDebugOn(!p || !*p); ++ sz = strlen(p); ++ memcpy(q, p, sz + 1); ++ q += sz; ++ ++ sz = au_do_optstr_br_attr(&attr, perm); ++ if (sz) { ++ *q++ = '+'; ++ memcpy(q, attr.a, sz + 1); ++ } ++ ++ AuDebugOn(strlen(str->a) >= sizeof(str->a)); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static match_table_t udbalevel = { ++ {AuOpt_UDBA_REVAL, "reval"}, ++ {AuOpt_UDBA_NONE, "none"}, ++#ifdef CONFIG_AUFS_HNOTIFY ++ {AuOpt_UDBA_HNOTIFY, "notify"}, /* abstraction */ ++#ifdef CONFIG_AUFS_HFSNOTIFY ++ {AuOpt_UDBA_HNOTIFY, "fsnotify"}, ++#endif ++#endif ++ {-1, NULL} ++}; ++ ++static int noinline_for_stack udba_val(char *str) ++{ ++ substring_t args[MAX_OPT_ARGS]; ++ ++ return match_token(str, udbalevel, args); ++} ++ ++const char *au_optstr_udba(int udba) ++{ ++ return au_parser_pattern(udba, udbalevel); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static match_table_t au_wbr_create_policy = { ++ {AuWbrCreate_TDP, "tdp"}, ++ {AuWbrCreate_TDP, "top-down-parent"}, ++ {AuWbrCreate_RR, "rr"}, ++ {AuWbrCreate_RR, "round-robin"}, ++ {AuWbrCreate_MFS, "mfs"}, ++ {AuWbrCreate_MFS, "most-free-space"}, ++ {AuWbrCreate_MFSV, "mfs:%d"}, ++ {AuWbrCreate_MFSV, "most-free-space:%d"}, ++ ++ /* top-down regardless the parent, and then mfs */ ++ {AuWbrCreate_TDMFS, "tdmfs:%d"}, ++ {AuWbrCreate_TDMFSV, "tdmfs:%d:%d"}, ++ ++ {AuWbrCreate_MFSRR, "mfsrr:%d"}, ++ {AuWbrCreate_MFSRRV, "mfsrr:%d:%d"}, ++ {AuWbrCreate_PMFS, "pmfs"}, ++ {AuWbrCreate_PMFSV, "pmfs:%d"}, ++ {AuWbrCreate_PMFSRR, "pmfsrr:%d"}, ++ {AuWbrCreate_PMFSRRV, "pmfsrr:%d:%d"}, ++ ++ {-1, NULL} ++}; ++ ++/* ++ * cf. linux/lib/parser.c and cmdline.c ++ * gave up calling memparse() since it uses simple_strtoull() instead of ++ * kstrto...(). ++ */ ++static int noinline_for_stack ++au_match_ull(substring_t *s, unsigned long long *result) ++{ ++ int err; ++ unsigned int len; ++ char a[32]; ++ ++ err = -ERANGE; ++ len = s->to - s->from; ++ if (len + 1 <= sizeof(a)) { ++ memcpy(a, s->from, len); ++ a[len] = '\0'; ++ err = kstrtoull(a, 0, result); ++ } ++ return err; ++} ++ ++static int au_wbr_mfs_wmark(substring_t *arg, char *str, ++ struct au_opt_wbr_create *create) ++{ ++ int err; ++ unsigned long long ull; ++ ++ err = 0; ++ if (!au_match_ull(arg, &ull)) ++ create->mfsrr_watermark = ull; ++ else { ++ pr_err("bad integer in %s\n", str); ++ err = -EINVAL; ++ } ++ ++ return err; ++} ++ ++static int au_wbr_mfs_sec(substring_t *arg, char *str, ++ struct au_opt_wbr_create *create) ++{ ++ int n, err; ++ ++ err = 0; ++ if (!match_int(arg, &n) && 0 <= n && n <= AUFS_MFS_MAX_SEC) ++ create->mfs_second = n; ++ else { ++ pr_err("bad integer in %s\n", str); ++ err = -EINVAL; ++ } ++ ++ return err; ++} ++ ++static int noinline_for_stack ++au_wbr_create_val(char *str, struct au_opt_wbr_create *create) ++{ ++ int err, e; ++ substring_t args[MAX_OPT_ARGS]; ++ ++ err = match_token(str, au_wbr_create_policy, args); ++ create->wbr_create = err; ++ switch (err) { ++ case AuWbrCreate_MFSRRV: ++ case AuWbrCreate_TDMFSV: ++ case AuWbrCreate_PMFSRRV: ++ e = au_wbr_mfs_wmark(&args[0], str, create); ++ if (!e) ++ e = au_wbr_mfs_sec(&args[1], str, create); ++ if (unlikely(e)) ++ err = e; ++ break; ++ case AuWbrCreate_MFSRR: ++ case AuWbrCreate_TDMFS: ++ case AuWbrCreate_PMFSRR: ++ e = au_wbr_mfs_wmark(&args[0], str, create); ++ if (unlikely(e)) { ++ err = e; ++ break; ++ } ++ /*FALLTHROUGH*/ ++ case AuWbrCreate_MFS: ++ case AuWbrCreate_PMFS: ++ create->mfs_second = AUFS_MFS_DEF_SEC; ++ break; ++ case AuWbrCreate_MFSV: ++ case AuWbrCreate_PMFSV: ++ e = au_wbr_mfs_sec(&args[0], str, create); ++ if (unlikely(e)) ++ err = e; ++ break; ++ } ++ ++ return err; ++} ++ ++const char *au_optstr_wbr_create(int wbr_create) ++{ ++ return au_parser_pattern(wbr_create, au_wbr_create_policy); ++} ++ ++static match_table_t au_wbr_copyup_policy = { ++ {AuWbrCopyup_TDP, "tdp"}, ++ {AuWbrCopyup_TDP, "top-down-parent"}, ++ {AuWbrCopyup_BUP, "bup"}, ++ {AuWbrCopyup_BUP, "bottom-up-parent"}, ++ {AuWbrCopyup_BU, "bu"}, ++ {AuWbrCopyup_BU, "bottom-up"}, ++ {-1, NULL} ++}; ++ ++static int noinline_for_stack au_wbr_copyup_val(char *str) ++{ ++ substring_t args[MAX_OPT_ARGS]; ++ ++ return match_token(str, au_wbr_copyup_policy, args); ++} ++ ++const char *au_optstr_wbr_copyup(int wbr_copyup) ++{ ++ return au_parser_pattern(wbr_copyup, au_wbr_copyup_policy); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static const int lkup_dirflags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; ++ ++static void dump_opts(struct au_opts *opts) ++{ ++#ifdef CONFIG_AUFS_DEBUG ++ /* reduce stack space */ ++ union { ++ struct au_opt_add *add; ++ struct au_opt_del *del; ++ struct au_opt_mod *mod; ++ struct au_opt_xino *xino; ++ struct au_opt_xino_itrunc *xino_itrunc; ++ struct au_opt_wbr_create *create; ++ } u; ++ struct au_opt *opt; ++ ++ opt = opts->opt; ++ while (opt->type != Opt_tail) { ++ switch (opt->type) { ++ case Opt_add: ++ u.add = &opt->add; ++ AuDbg("add {b%d, %s, 0x%x, %p}\n", ++ u.add->bindex, u.add->pathname, u.add->perm, ++ u.add->path.dentry); ++ break; ++ case Opt_del: ++ case Opt_idel: ++ u.del = &opt->del; ++ AuDbg("del {%s, %p}\n", ++ u.del->pathname, u.del->h_path.dentry); ++ break; ++ case Opt_mod: ++ case Opt_imod: ++ u.mod = &opt->mod; ++ AuDbg("mod {%s, 0x%x, %p}\n", ++ u.mod->path, u.mod->perm, u.mod->h_root); ++ break; ++ case Opt_append: ++ u.add = &opt->add; ++ AuDbg("append {b%d, %s, 0x%x, %p}\n", ++ u.add->bindex, u.add->pathname, u.add->perm, ++ u.add->path.dentry); ++ break; ++ case Opt_prepend: ++ u.add = &opt->add; ++ AuDbg("prepend {b%d, %s, 0x%x, %p}\n", ++ u.add->bindex, u.add->pathname, u.add->perm, ++ u.add->path.dentry); ++ break; ++ case Opt_dirwh: ++ AuDbg("dirwh %d\n", opt->dirwh); ++ break; ++ case Opt_rdcache: ++ AuDbg("rdcache %d\n", opt->rdcache); ++ break; ++ case Opt_rdblk: ++ AuDbg("rdblk %u\n", opt->rdblk); ++ break; ++ case Opt_rdblk_def: ++ AuDbg("rdblk_def\n"); ++ break; ++ case Opt_rdhash: ++ AuDbg("rdhash %u\n", opt->rdhash); ++ break; ++ case Opt_rdhash_def: ++ AuDbg("rdhash_def\n"); ++ break; ++ case Opt_xino: ++ u.xino = &opt->xino; ++ AuDbg("xino {%s %pD}\n", u.xino->path, u.xino->file); ++ break; ++ case Opt_trunc_xino: ++ AuLabel(trunc_xino); ++ break; ++ case Opt_notrunc_xino: ++ AuLabel(notrunc_xino); ++ break; ++ case Opt_trunc_xino_path: ++ case Opt_itrunc_xino: ++ u.xino_itrunc = &opt->xino_itrunc; ++ AuDbg("trunc_xino %d\n", u.xino_itrunc->bindex); ++ break; ++ case Opt_noxino: ++ AuLabel(noxino); ++ break; ++ case Opt_trunc_xib: ++ AuLabel(trunc_xib); ++ break; ++ case Opt_notrunc_xib: ++ AuLabel(notrunc_xib); ++ break; ++ case Opt_shwh: ++ AuLabel(shwh); ++ break; ++ case Opt_noshwh: ++ AuLabel(noshwh); ++ break; ++ case Opt_dirperm1: ++ AuLabel(dirperm1); ++ break; ++ case Opt_nodirperm1: ++ AuLabel(nodirperm1); ++ break; ++ case Opt_plink: ++ AuLabel(plink); ++ break; ++ case Opt_noplink: ++ AuLabel(noplink); ++ break; ++ case Opt_list_plink: ++ AuLabel(list_plink); ++ break; ++ case Opt_udba: ++ AuDbg("udba %d, %s\n", ++ opt->udba, au_optstr_udba(opt->udba)); ++ break; ++ case Opt_dio: ++ AuLabel(dio); ++ break; ++ case Opt_nodio: ++ AuLabel(nodio); ++ break; ++ case Opt_diropq_a: ++ AuLabel(diropq_a); ++ break; ++ case Opt_diropq_w: ++ AuLabel(diropq_w); ++ break; ++ case Opt_warn_perm: ++ AuLabel(warn_perm); ++ break; ++ case Opt_nowarn_perm: ++ AuLabel(nowarn_perm); ++ break; ++ case Opt_verbose: ++ AuLabel(verbose); ++ break; ++ case Opt_noverbose: ++ AuLabel(noverbose); ++ break; ++ case Opt_sum: ++ AuLabel(sum); ++ break; ++ case Opt_nosum: ++ AuLabel(nosum); ++ break; ++ case Opt_wsum: ++ AuLabel(wsum); ++ break; ++ case Opt_wbr_create: ++ u.create = &opt->wbr_create; ++ AuDbg("create %d, %s\n", u.create->wbr_create, ++ au_optstr_wbr_create(u.create->wbr_create)); ++ switch (u.create->wbr_create) { ++ case AuWbrCreate_MFSV: ++ case AuWbrCreate_PMFSV: ++ AuDbg("%d sec\n", u.create->mfs_second); ++ break; ++ case AuWbrCreate_MFSRR: ++ case AuWbrCreate_TDMFS: ++ AuDbg("%llu watermark\n", ++ u.create->mfsrr_watermark); ++ break; ++ case AuWbrCreate_MFSRRV: ++ case AuWbrCreate_TDMFSV: ++ case AuWbrCreate_PMFSRRV: ++ AuDbg("%llu watermark, %d sec\n", ++ u.create->mfsrr_watermark, ++ u.create->mfs_second); ++ break; ++ } ++ break; ++ case Opt_wbr_copyup: ++ AuDbg("copyup %d, %s\n", opt->wbr_copyup, ++ au_optstr_wbr_copyup(opt->wbr_copyup)); ++ break; ++ case Opt_fhsm_sec: ++ AuDbg("fhsm_sec %u\n", opt->fhsm_second); ++ break; ++ case Opt_dirren: ++ AuLabel(dirren); ++ break; ++ case Opt_nodirren: ++ AuLabel(nodirren); ++ break; ++ case Opt_acl: ++ AuLabel(acl); ++ break; ++ case Opt_noacl: ++ AuLabel(noacl); ++ break; ++ default: ++ BUG(); ++ } ++ opt++; ++ } ++#endif ++} ++ ++void au_opts_free(struct au_opts *opts) ++{ ++ struct au_opt *opt; ++ ++ opt = opts->opt; ++ while (opt->type != Opt_tail) { ++ switch (opt->type) { ++ case Opt_add: ++ case Opt_append: ++ case Opt_prepend: ++ path_put(&opt->add.path); ++ break; ++ case Opt_del: ++ case Opt_idel: ++ path_put(&opt->del.h_path); ++ break; ++ case Opt_mod: ++ case Opt_imod: ++ dput(opt->mod.h_root); ++ break; ++ case Opt_xino: ++ fput(opt->xino.file); ++ break; ++ } ++ opt++; ++ } ++} ++ ++static int opt_add(struct au_opt *opt, char *opt_str, unsigned long sb_flags, ++ aufs_bindex_t bindex) ++{ ++ int err; ++ struct au_opt_add *add = &opt->add; ++ char *p; ++ ++ add->bindex = bindex; ++ add->perm = AuBrPerm_RO; ++ add->pathname = opt_str; ++ p = strchr(opt_str, '='); ++ if (p) { ++ *p++ = 0; ++ if (*p) ++ add->perm = br_perm_val(p); ++ } ++ ++ err = vfsub_kern_path(add->pathname, lkup_dirflags, &add->path); ++ if (!err) { ++ if (!p) { ++ add->perm = AuBrPerm_RO; ++ if (au_test_fs_rr(add->path.dentry->d_sb)) ++ add->perm = AuBrPerm_RR; ++ else if (!bindex && !(sb_flags & MS_RDONLY)) ++ add->perm = AuBrPerm_RW; ++ } ++ opt->type = Opt_add; ++ goto out; ++ } ++ pr_err("lookup failed %s (%d)\n", add->pathname, err); ++ err = -EINVAL; ++ ++out: ++ return err; ++} ++ ++static int au_opts_parse_del(struct au_opt_del *del, substring_t args[]) ++{ ++ int err; ++ ++ del->pathname = args[0].from; ++ AuDbg("del path %s\n", del->pathname); ++ ++ err = vfsub_kern_path(del->pathname, lkup_dirflags, &del->h_path); ++ if (unlikely(err)) ++ pr_err("lookup failed %s (%d)\n", del->pathname, err); ++ ++ return err; ++} ++ ++#if 0 /* reserved for future use */ ++static int au_opts_parse_idel(struct super_block *sb, aufs_bindex_t bindex, ++ struct au_opt_del *del, substring_t args[]) ++{ ++ int err; ++ struct dentry *root; ++ ++ err = -EINVAL; ++ root = sb->s_root; ++ aufs_read_lock(root, AuLock_FLUSH); ++ if (bindex < 0 || au_sbbot(sb) < bindex) { ++ pr_err("out of bounds, %d\n", bindex); ++ goto out; ++ } ++ ++ err = 0; ++ del->h_path.dentry = dget(au_h_dptr(root, bindex)); ++ del->h_path.mnt = mntget(au_sbr_mnt(sb, bindex)); ++ ++out: ++ aufs_read_unlock(root, !AuLock_IR); ++ return err; ++} ++#endif ++ ++static int noinline_for_stack ++au_opts_parse_mod(struct au_opt_mod *mod, substring_t args[]) ++{ ++ int err; ++ struct path path; ++ char *p; ++ ++ err = -EINVAL; ++ mod->path = args[0].from; ++ p = strchr(mod->path, '='); ++ if (unlikely(!p)) { ++ pr_err("no permssion %s\n", args[0].from); ++ goto out; ++ } ++ ++ *p++ = 0; ++ err = vfsub_kern_path(mod->path, lkup_dirflags, &path); ++ if (unlikely(err)) { ++ pr_err("lookup failed %s (%d)\n", mod->path, err); ++ goto out; ++ } ++ ++ mod->perm = br_perm_val(p); ++ AuDbg("mod path %s, perm 0x%x, %s\n", mod->path, mod->perm, p); ++ mod->h_root = dget(path.dentry); ++ path_put(&path); ++ ++out: ++ return err; ++} ++ ++#if 0 /* reserved for future use */ ++static int au_opts_parse_imod(struct super_block *sb, aufs_bindex_t bindex, ++ struct au_opt_mod *mod, substring_t args[]) ++{ ++ int err; ++ struct dentry *root; ++ ++ err = -EINVAL; ++ root = sb->s_root; ++ aufs_read_lock(root, AuLock_FLUSH); ++ if (bindex < 0 || au_sbbot(sb) < bindex) { ++ pr_err("out of bounds, %d\n", bindex); ++ goto out; ++ } ++ ++ err = 0; ++ mod->perm = br_perm_val(args[1].from); ++ AuDbg("mod path %s, perm 0x%x, %s\n", ++ mod->path, mod->perm, args[1].from); ++ mod->h_root = dget(au_h_dptr(root, bindex)); ++ ++out: ++ aufs_read_unlock(root, !AuLock_IR); ++ return err; ++} ++#endif ++ ++static int au_opts_parse_xino(struct super_block *sb, struct au_opt_xino *xino, ++ substring_t args[]) ++{ ++ int err; ++ struct file *file; ++ ++ file = au_xino_create(sb, args[0].from, /*silent*/0); ++ err = PTR_ERR(file); ++ if (IS_ERR(file)) ++ goto out; ++ ++ err = -EINVAL; ++ if (unlikely(file->f_path.dentry->d_sb == sb)) { ++ fput(file); ++ pr_err("%s must be outside\n", args[0].from); ++ goto out; ++ } ++ ++ err = 0; ++ xino->file = file; ++ xino->path = args[0].from; ++ ++out: ++ return err; ++} ++ ++static int noinline_for_stack ++au_opts_parse_xino_itrunc_path(struct super_block *sb, ++ struct au_opt_xino_itrunc *xino_itrunc, ++ substring_t args[]) ++{ ++ int err; ++ aufs_bindex_t bbot, bindex; ++ struct path path; ++ struct dentry *root; ++ ++ err = vfsub_kern_path(args[0].from, lkup_dirflags, &path); ++ if (unlikely(err)) { ++ pr_err("lookup failed %s (%d)\n", args[0].from, err); ++ goto out; ++ } ++ ++ xino_itrunc->bindex = -1; ++ root = sb->s_root; ++ aufs_read_lock(root, AuLock_FLUSH); ++ bbot = au_sbbot(sb); ++ for (bindex = 0; bindex <= bbot; bindex++) { ++ if (au_h_dptr(root, bindex) == path.dentry) { ++ xino_itrunc->bindex = bindex; ++ break; ++ } ++ } ++ aufs_read_unlock(root, !AuLock_IR); ++ path_put(&path); ++ ++ if (unlikely(xino_itrunc->bindex < 0)) { ++ pr_err("no such branch %s\n", args[0].from); ++ err = -EINVAL; ++ } ++ ++out: ++ return err; ++} ++ ++/* called without aufs lock */ ++int au_opts_parse(struct super_block *sb, char *str, struct au_opts *opts) ++{ ++ int err, n, token; ++ aufs_bindex_t bindex; ++ unsigned char skipped; ++ struct dentry *root; ++ struct au_opt *opt, *opt_tail; ++ char *opt_str; ++ /* reduce the stack space */ ++ union { ++ struct au_opt_xino_itrunc *xino_itrunc; ++ struct au_opt_wbr_create *create; ++ } u; ++ struct { ++ substring_t args[MAX_OPT_ARGS]; ++ } *a; ++ ++ err = -ENOMEM; ++ a = kmalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ root = sb->s_root; ++ err = 0; ++ bindex = 0; ++ opt = opts->opt; ++ opt_tail = opt + opts->max_opt - 1; ++ opt->type = Opt_tail; ++ while (!err && (opt_str = strsep(&str, ",")) && *opt_str) { ++ err = -EINVAL; ++ skipped = 0; ++ token = match_token(opt_str, options, a->args); ++ switch (token) { ++ case Opt_br: ++ err = 0; ++ while (!err && (opt_str = strsep(&a->args[0].from, ":")) ++ && *opt_str) { ++ err = opt_add(opt, opt_str, opts->sb_flags, ++ bindex++); ++ if (unlikely(!err && ++opt > opt_tail)) { ++ err = -E2BIG; ++ break; ++ } ++ opt->type = Opt_tail; ++ skipped = 1; ++ } ++ break; ++ case Opt_add: ++ if (unlikely(match_int(&a->args[0], &n))) { ++ pr_err("bad integer in %s\n", opt_str); ++ break; ++ } ++ bindex = n; ++ err = opt_add(opt, a->args[1].from, opts->sb_flags, ++ bindex); ++ if (!err) ++ opt->type = token; ++ break; ++ case Opt_append: ++ err = opt_add(opt, a->args[0].from, opts->sb_flags, ++ /*dummy bindex*/1); ++ if (!err) ++ opt->type = token; ++ break; ++ case Opt_prepend: ++ err = opt_add(opt, a->args[0].from, opts->sb_flags, ++ /*bindex*/0); ++ if (!err) ++ opt->type = token; ++ break; ++ case Opt_del: ++ err = au_opts_parse_del(&opt->del, a->args); ++ if (!err) ++ opt->type = token; ++ break; ++#if 0 /* reserved for future use */ ++ case Opt_idel: ++ del->pathname = "(indexed)"; ++ if (unlikely(match_int(&args[0], &n))) { ++ pr_err("bad integer in %s\n", opt_str); ++ break; ++ } ++ err = au_opts_parse_idel(sb, n, &opt->del, a->args); ++ if (!err) ++ opt->type = token; ++ break; ++#endif ++ case Opt_mod: ++ err = au_opts_parse_mod(&opt->mod, a->args); ++ if (!err) ++ opt->type = token; ++ break; ++#ifdef IMOD /* reserved for future use */ ++ case Opt_imod: ++ u.mod->path = "(indexed)"; ++ if (unlikely(match_int(&a->args[0], &n))) { ++ pr_err("bad integer in %s\n", opt_str); ++ break; ++ } ++ err = au_opts_parse_imod(sb, n, &opt->mod, a->args); ++ if (!err) ++ opt->type = token; ++ break; ++#endif ++ case Opt_xino: ++ err = au_opts_parse_xino(sb, &opt->xino, a->args); ++ if (!err) ++ opt->type = token; ++ break; ++ ++ case Opt_trunc_xino_path: ++ err = au_opts_parse_xino_itrunc_path ++ (sb, &opt->xino_itrunc, a->args); ++ if (!err) ++ opt->type = token; ++ break; ++ ++ case Opt_itrunc_xino: ++ u.xino_itrunc = &opt->xino_itrunc; ++ if (unlikely(match_int(&a->args[0], &n))) { ++ pr_err("bad integer in %s\n", opt_str); ++ break; ++ } ++ u.xino_itrunc->bindex = n; ++ aufs_read_lock(root, AuLock_FLUSH); ++ if (n < 0 || au_sbbot(sb) < n) { ++ pr_err("out of bounds, %d\n", n); ++ aufs_read_unlock(root, !AuLock_IR); ++ break; ++ } ++ aufs_read_unlock(root, !AuLock_IR); ++ err = 0; ++ opt->type = token; ++ break; ++ ++ case Opt_dirwh: ++ if (unlikely(match_int(&a->args[0], &opt->dirwh))) ++ break; ++ err = 0; ++ opt->type = token; ++ break; ++ ++ case Opt_rdcache: ++ if (unlikely(match_int(&a->args[0], &n))) { ++ pr_err("bad integer in %s\n", opt_str); ++ break; ++ } ++ if (unlikely(n > AUFS_RDCACHE_MAX)) { ++ pr_err("rdcache must be smaller than %d\n", ++ AUFS_RDCACHE_MAX); ++ break; ++ } ++ opt->rdcache = n; ++ err = 0; ++ opt->type = token; ++ break; ++ case Opt_rdblk: ++ if (unlikely(match_int(&a->args[0], &n) ++ || n < 0 ++ || n > KMALLOC_MAX_SIZE)) { ++ pr_err("bad integer in %s\n", opt_str); ++ break; ++ } ++ if (unlikely(n && n < NAME_MAX)) { ++ pr_err("rdblk must be larger than %d\n", ++ NAME_MAX); ++ break; ++ } ++ opt->rdblk = n; ++ err = 0; ++ opt->type = token; ++ break; ++ case Opt_rdhash: ++ if (unlikely(match_int(&a->args[0], &n) ++ || n < 0 ++ || n * sizeof(struct hlist_head) ++ > KMALLOC_MAX_SIZE)) { ++ pr_err("bad integer in %s\n", opt_str); ++ break; ++ } ++ opt->rdhash = n; ++ err = 0; ++ opt->type = token; ++ break; ++ ++ case Opt_trunc_xino: ++ case Opt_notrunc_xino: ++ case Opt_noxino: ++ case Opt_trunc_xib: ++ case Opt_notrunc_xib: ++ case Opt_shwh: ++ case Opt_noshwh: ++ case Opt_dirperm1: ++ case Opt_nodirperm1: ++ case Opt_plink: ++ case Opt_noplink: ++ case Opt_list_plink: ++ case Opt_dio: ++ case Opt_nodio: ++ case Opt_diropq_a: ++ case Opt_diropq_w: ++ case Opt_warn_perm: ++ case Opt_nowarn_perm: ++ case Opt_verbose: ++ case Opt_noverbose: ++ case Opt_sum: ++ case Opt_nosum: ++ case Opt_wsum: ++ case Opt_rdblk_def: ++ case Opt_rdhash_def: ++ case Opt_dirren: ++ case Opt_nodirren: ++ case Opt_acl: ++ case Opt_noacl: ++ err = 0; ++ opt->type = token; ++ break; ++ ++ case Opt_udba: ++ opt->udba = udba_val(a->args[0].from); ++ if (opt->udba >= 0) { ++ err = 0; ++ opt->type = token; ++ } else ++ pr_err("wrong value, %s\n", opt_str); ++ break; ++ ++ case Opt_wbr_create: ++ u.create = &opt->wbr_create; ++ u.create->wbr_create ++ = au_wbr_create_val(a->args[0].from, u.create); ++ if (u.create->wbr_create >= 0) { ++ err = 0; ++ opt->type = token; ++ } else ++ pr_err("wrong value, %s\n", opt_str); ++ break; ++ case Opt_wbr_copyup: ++ opt->wbr_copyup = au_wbr_copyup_val(a->args[0].from); ++ if (opt->wbr_copyup >= 0) { ++ err = 0; ++ opt->type = token; ++ } else ++ pr_err("wrong value, %s\n", opt_str); ++ break; ++ ++ case Opt_fhsm_sec: ++ if (unlikely(match_int(&a->args[0], &n) ++ || n < 0)) { ++ pr_err("bad integer in %s\n", opt_str); ++ break; ++ } ++ if (sysaufs_brs) { ++ opt->fhsm_second = n; ++ opt->type = token; ++ } else ++ pr_warn("ignored %s\n", opt_str); ++ err = 0; ++ break; ++ ++ case Opt_ignore: ++ pr_warn("ignored %s\n", opt_str); ++ /*FALLTHROUGH*/ ++ case Opt_ignore_silent: ++ skipped = 1; ++ err = 0; ++ break; ++ case Opt_err: ++ pr_err("unknown option %s\n", opt_str); ++ break; ++ } ++ ++ if (!err && !skipped) { ++ if (unlikely(++opt > opt_tail)) { ++ err = -E2BIG; ++ opt--; ++ opt->type = Opt_tail; ++ break; ++ } ++ opt->type = Opt_tail; ++ } ++ } ++ ++ kfree(a); ++ dump_opts(opts); ++ if (unlikely(err)) ++ au_opts_free(opts); ++ ++out: ++ return err; ++} ++ ++static int au_opt_wbr_create(struct super_block *sb, ++ struct au_opt_wbr_create *create) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ ++ SiMustWriteLock(sb); ++ ++ err = 1; /* handled */ ++ sbinfo = au_sbi(sb); ++ if (sbinfo->si_wbr_create_ops->fin) { ++ err = sbinfo->si_wbr_create_ops->fin(sb); ++ if (!err) ++ err = 1; ++ } ++ ++ sbinfo->si_wbr_create = create->wbr_create; ++ sbinfo->si_wbr_create_ops = au_wbr_create_ops + create->wbr_create; ++ switch (create->wbr_create) { ++ case AuWbrCreate_MFSRRV: ++ case AuWbrCreate_MFSRR: ++ case AuWbrCreate_TDMFS: ++ case AuWbrCreate_TDMFSV: ++ case AuWbrCreate_PMFSRR: ++ case AuWbrCreate_PMFSRRV: ++ sbinfo->si_wbr_mfs.mfsrr_watermark = create->mfsrr_watermark; ++ /*FALLTHROUGH*/ ++ case AuWbrCreate_MFS: ++ case AuWbrCreate_MFSV: ++ case AuWbrCreate_PMFS: ++ case AuWbrCreate_PMFSV: ++ sbinfo->si_wbr_mfs.mfs_expire ++ = msecs_to_jiffies(create->mfs_second * MSEC_PER_SEC); ++ break; ++ } ++ ++ if (sbinfo->si_wbr_create_ops->init) ++ sbinfo->si_wbr_create_ops->init(sb); /* ignore */ ++ ++ return err; ++} ++ ++/* ++ * returns, ++ * plus: processed without an error ++ * zero: unprocessed ++ */ ++static int au_opt_simple(struct super_block *sb, struct au_opt *opt, ++ struct au_opts *opts) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ ++ SiMustWriteLock(sb); ++ ++ err = 1; /* handled */ ++ sbinfo = au_sbi(sb); ++ switch (opt->type) { ++ case Opt_udba: ++ sbinfo->si_mntflags &= ~AuOptMask_UDBA; ++ sbinfo->si_mntflags |= opt->udba; ++ opts->given_udba |= opt->udba; ++ break; ++ ++ case Opt_plink: ++ au_opt_set(sbinfo->si_mntflags, PLINK); ++ break; ++ case Opt_noplink: ++ if (au_opt_test(sbinfo->si_mntflags, PLINK)) ++ au_plink_put(sb, /*verbose*/1); ++ au_opt_clr(sbinfo->si_mntflags, PLINK); ++ break; ++ case Opt_list_plink: ++ if (au_opt_test(sbinfo->si_mntflags, PLINK)) ++ au_plink_list(sb); ++ break; ++ ++ case Opt_dio: ++ au_opt_set(sbinfo->si_mntflags, DIO); ++ au_fset_opts(opts->flags, REFRESH_DYAOP); ++ break; ++ case Opt_nodio: ++ au_opt_clr(sbinfo->si_mntflags, DIO); ++ au_fset_opts(opts->flags, REFRESH_DYAOP); ++ break; ++ ++ case Opt_fhsm_sec: ++ au_fhsm_set(sbinfo, opt->fhsm_second); ++ break; ++ ++ case Opt_diropq_a: ++ au_opt_set(sbinfo->si_mntflags, ALWAYS_DIROPQ); ++ break; ++ case Opt_diropq_w: ++ au_opt_clr(sbinfo->si_mntflags, ALWAYS_DIROPQ); ++ break; ++ ++ case Opt_warn_perm: ++ au_opt_set(sbinfo->si_mntflags, WARN_PERM); ++ break; ++ case Opt_nowarn_perm: ++ au_opt_clr(sbinfo->si_mntflags, WARN_PERM); ++ break; ++ ++ case Opt_verbose: ++ au_opt_set(sbinfo->si_mntflags, VERBOSE); ++ break; ++ case Opt_noverbose: ++ au_opt_clr(sbinfo->si_mntflags, VERBOSE); ++ break; ++ ++ case Opt_sum: ++ au_opt_set(sbinfo->si_mntflags, SUM); ++ break; ++ case Opt_wsum: ++ au_opt_clr(sbinfo->si_mntflags, SUM); ++ au_opt_set(sbinfo->si_mntflags, SUM_W); ++ case Opt_nosum: ++ au_opt_clr(sbinfo->si_mntflags, SUM); ++ au_opt_clr(sbinfo->si_mntflags, SUM_W); ++ break; ++ ++ case Opt_wbr_create: ++ err = au_opt_wbr_create(sb, &opt->wbr_create); ++ break; ++ case Opt_wbr_copyup: ++ sbinfo->si_wbr_copyup = opt->wbr_copyup; ++ sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + opt->wbr_copyup; ++ break; ++ ++ case Opt_dirwh: ++ sbinfo->si_dirwh = opt->dirwh; ++ break; ++ ++ case Opt_rdcache: ++ sbinfo->si_rdcache ++ = msecs_to_jiffies(opt->rdcache * MSEC_PER_SEC); ++ break; ++ case Opt_rdblk: ++ sbinfo->si_rdblk = opt->rdblk; ++ break; ++ case Opt_rdblk_def: ++ sbinfo->si_rdblk = AUFS_RDBLK_DEF; ++ break; ++ case Opt_rdhash: ++ sbinfo->si_rdhash = opt->rdhash; ++ break; ++ case Opt_rdhash_def: ++ sbinfo->si_rdhash = AUFS_RDHASH_DEF; ++ break; ++ ++ case Opt_shwh: ++ au_opt_set(sbinfo->si_mntflags, SHWH); ++ break; ++ case Opt_noshwh: ++ au_opt_clr(sbinfo->si_mntflags, SHWH); ++ break; ++ ++ case Opt_dirperm1: ++ au_opt_set(sbinfo->si_mntflags, DIRPERM1); ++ break; ++ case Opt_nodirperm1: ++ au_opt_clr(sbinfo->si_mntflags, DIRPERM1); ++ break; ++ ++ case Opt_trunc_xino: ++ au_opt_set(sbinfo->si_mntflags, TRUNC_XINO); ++ break; ++ case Opt_notrunc_xino: ++ au_opt_clr(sbinfo->si_mntflags, TRUNC_XINO); ++ break; ++ ++ case Opt_trunc_xino_path: ++ case Opt_itrunc_xino: ++ err = au_xino_trunc(sb, opt->xino_itrunc.bindex); ++ if (!err) ++ err = 1; ++ break; ++ ++ case Opt_trunc_xib: ++ au_fset_opts(opts->flags, TRUNC_XIB); ++ break; ++ case Opt_notrunc_xib: ++ au_fclr_opts(opts->flags, TRUNC_XIB); ++ break; ++ ++ case Opt_dirren: ++ err = 1; ++ if (!au_opt_test(sbinfo->si_mntflags, DIRREN)) { ++ err = au_dr_opt_set(sb); ++ if (!err) ++ err = 1; ++ } ++ if (err == 1) ++ au_opt_set(sbinfo->si_mntflags, DIRREN); ++ break; ++ case Opt_nodirren: ++ err = 1; ++ if (au_opt_test(sbinfo->si_mntflags, DIRREN)) { ++ err = au_dr_opt_clr(sb, au_ftest_opts(opts->flags, ++ DR_FLUSHED)); ++ if (!err) ++ err = 1; ++ } ++ if (err == 1) ++ au_opt_clr(sbinfo->si_mntflags, DIRREN); ++ break; ++ ++ case Opt_acl: ++ sb->s_flags |= MS_POSIXACL; ++ break; ++ case Opt_noacl: ++ sb->s_flags &= ~MS_POSIXACL; ++ break; ++ ++ default: ++ err = 0; ++ break; ++ } ++ ++ return err; ++} ++ ++/* ++ * returns tri-state. ++ * plus: processed without an error ++ * zero: unprocessed ++ * minus: error ++ */ ++static int au_opt_br(struct super_block *sb, struct au_opt *opt, ++ struct au_opts *opts) ++{ ++ int err, do_refresh; ++ ++ err = 0; ++ switch (opt->type) { ++ case Opt_append: ++ opt->add.bindex = au_sbbot(sb) + 1; ++ if (opt->add.bindex < 0) ++ opt->add.bindex = 0; ++ goto add; ++ case Opt_prepend: ++ opt->add.bindex = 0; ++ add: /* indented label */ ++ case Opt_add: ++ err = au_br_add(sb, &opt->add, ++ au_ftest_opts(opts->flags, REMOUNT)); ++ if (!err) { ++ err = 1; ++ au_fset_opts(opts->flags, REFRESH); ++ } ++ break; ++ ++ case Opt_del: ++ case Opt_idel: ++ err = au_br_del(sb, &opt->del, ++ au_ftest_opts(opts->flags, REMOUNT)); ++ if (!err) { ++ err = 1; ++ au_fset_opts(opts->flags, TRUNC_XIB); ++ au_fset_opts(opts->flags, REFRESH); ++ } ++ break; ++ ++ case Opt_mod: ++ case Opt_imod: ++ err = au_br_mod(sb, &opt->mod, ++ au_ftest_opts(opts->flags, REMOUNT), ++ &do_refresh); ++ if (!err) { ++ err = 1; ++ if (do_refresh) ++ au_fset_opts(opts->flags, REFRESH); ++ } ++ break; ++ } ++ return err; ++} ++ ++static int au_opt_xino(struct super_block *sb, struct au_opt *opt, ++ struct au_opt_xino **opt_xino, ++ struct au_opts *opts) ++{ ++ int err; ++ aufs_bindex_t bbot, bindex; ++ struct dentry *root, *parent, *h_root; ++ ++ err = 0; ++ switch (opt->type) { ++ case Opt_xino: ++ au_xino_brid_set(sb, -1); ++ /* safe d_parent access */ ++ parent = opt->xino.file->f_path.dentry->d_parent; ++ root = sb->s_root; ++ bbot = au_sbbot(sb); ++ for (bindex = 0; bindex <= bbot; bindex++) { ++ h_root = au_h_dptr(root, bindex); ++ if (h_root == parent) { ++ au_xino_brid_set(sb, au_sbr_id(sb, bindex)); ++ break; ++ } ++ } ++ ++ err = au_xino_set(sb, &opt->xino, ++ !!au_ftest_opts(opts->flags, REMOUNT)); ++ if (unlikely(err)) ++ break; ++ ++ *opt_xino = &opt->xino; ++ break; ++ ++ case Opt_noxino: ++ au_xino_clr(sb); ++ *opt_xino = (void *)-1; ++ break; ++ } ++ ++ return err; ++} ++ ++int au_opts_verify(struct super_block *sb, unsigned long sb_flags, ++ unsigned int pending) ++{ ++ int err, fhsm; ++ aufs_bindex_t bindex, bbot; ++ unsigned char do_plink, skip, do_free, can_no_dreval; ++ struct au_branch *br; ++ struct au_wbr *wbr; ++ struct dentry *root, *dentry; ++ struct inode *dir, *h_dir; ++ struct au_sbinfo *sbinfo; ++ struct au_hinode *hdir; ++ ++ SiMustAnyLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ AuDebugOn(!(sbinfo->si_mntflags & AuOptMask_UDBA)); ++ ++ if (!(sb_flags & MS_RDONLY)) { ++ if (unlikely(!au_br_writable(au_sbr_perm(sb, 0)))) ++ pr_warn("first branch should be rw\n"); ++ if (unlikely(au_opt_test(sbinfo->si_mntflags, SHWH))) ++ pr_warn_once("shwh should be used with ro\n"); ++ } ++ ++ if (au_opt_test((sbinfo->si_mntflags | pending), UDBA_HNOTIFY) ++ && !au_opt_test(sbinfo->si_mntflags, XINO)) ++ pr_warn_once("udba=*notify requires xino\n"); ++ ++ if (au_opt_test(sbinfo->si_mntflags, DIRPERM1)) ++ pr_warn_once("dirperm1 breaks the protection" ++ " by the permission bits on the lower branch\n"); ++ ++ err = 0; ++ fhsm = 0; ++ root = sb->s_root; ++ dir = d_inode(root); ++ do_plink = !!au_opt_test(sbinfo->si_mntflags, PLINK); ++ can_no_dreval = !!au_opt_test((sbinfo->si_mntflags | pending), ++ UDBA_NONE); ++ bbot = au_sbbot(sb); ++ for (bindex = 0; !err && bindex <= bbot; bindex++) { ++ skip = 0; ++ h_dir = au_h_iptr(dir, bindex); ++ br = au_sbr(sb, bindex); ++ ++ if ((br->br_perm & AuBrAttr_ICEX) ++ && !h_dir->i_op->listxattr) ++ br->br_perm &= ~AuBrAttr_ICEX; ++#if 0 ++ if ((br->br_perm & AuBrAttr_ICEX_SEC) ++ && (au_br_sb(br)->s_flags & MS_NOSEC)) ++ br->br_perm &= ~AuBrAttr_ICEX_SEC; ++#endif ++ ++ do_free = 0; ++ wbr = br->br_wbr; ++ if (wbr) ++ wbr_wh_read_lock(wbr); ++ ++ if (!au_br_writable(br->br_perm)) { ++ do_free = !!wbr; ++ skip = (!wbr ++ || (!wbr->wbr_whbase ++ && !wbr->wbr_plink ++ && !wbr->wbr_orph)); ++ } else if (!au_br_wh_linkable(br->br_perm)) { ++ /* skip = (!br->br_whbase && !br->br_orph); */ ++ skip = (!wbr || !wbr->wbr_whbase); ++ if (skip && wbr) { ++ if (do_plink) ++ skip = !!wbr->wbr_plink; ++ else ++ skip = !wbr->wbr_plink; ++ } ++ } else { ++ /* skip = (br->br_whbase && br->br_ohph); */ ++ skip = (wbr && wbr->wbr_whbase); ++ if (skip) { ++ if (do_plink) ++ skip = !!wbr->wbr_plink; ++ else ++ skip = !wbr->wbr_plink; ++ } ++ } ++ if (wbr) ++ wbr_wh_read_unlock(wbr); ++ ++ if (can_no_dreval) { ++ dentry = br->br_path.dentry; ++ spin_lock(&dentry->d_lock); ++ if (dentry->d_flags & ++ (DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE)) ++ can_no_dreval = 0; ++ spin_unlock(&dentry->d_lock); ++ } ++ ++ if (au_br_fhsm(br->br_perm)) { ++ fhsm++; ++ AuDebugOn(!br->br_fhsm); ++ } ++ ++ if (skip) ++ continue; ++ ++ hdir = au_hi(dir, bindex); ++ au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); ++ if (wbr) ++ wbr_wh_write_lock(wbr); ++ err = au_wh_init(br, sb); ++ if (wbr) ++ wbr_wh_write_unlock(wbr); ++ au_hn_inode_unlock(hdir); ++ ++ if (!err && do_free) { ++ kfree(wbr); ++ br->br_wbr = NULL; ++ } ++ } ++ ++ if (can_no_dreval) ++ au_fset_si(sbinfo, NO_DREVAL); ++ else ++ au_fclr_si(sbinfo, NO_DREVAL); ++ ++ if (fhsm >= 2) { ++ au_fset_si(sbinfo, FHSM); ++ for (bindex = bbot; bindex >= 0; bindex--) { ++ br = au_sbr(sb, bindex); ++ if (au_br_fhsm(br->br_perm)) { ++ au_fhsm_set_bottom(sb, bindex); ++ break; ++ } ++ } ++ } else { ++ au_fclr_si(sbinfo, FHSM); ++ au_fhsm_set_bottom(sb, -1); ++ } ++ ++ return err; ++} ++ ++int au_opts_mount(struct super_block *sb, struct au_opts *opts) ++{ ++ int err; ++ unsigned int tmp; ++ aufs_bindex_t bindex, bbot; ++ struct au_opt *opt; ++ struct au_opt_xino *opt_xino, xino; ++ struct au_sbinfo *sbinfo; ++ struct au_branch *br; ++ struct inode *dir; ++ ++ SiMustWriteLock(sb); ++ ++ err = 0; ++ opt_xino = NULL; ++ opt = opts->opt; ++ while (err >= 0 && opt->type != Opt_tail) ++ err = au_opt_simple(sb, opt++, opts); ++ if (err > 0) ++ err = 0; ++ else if (unlikely(err < 0)) ++ goto out; ++ ++ /* disable xino and udba temporary */ ++ sbinfo = au_sbi(sb); ++ tmp = sbinfo->si_mntflags; ++ au_opt_clr(sbinfo->si_mntflags, XINO); ++ au_opt_set_udba(sbinfo->si_mntflags, UDBA_REVAL); ++ ++ opt = opts->opt; ++ while (err >= 0 && opt->type != Opt_tail) ++ err = au_opt_br(sb, opt++, opts); ++ if (err > 0) ++ err = 0; ++ else if (unlikely(err < 0)) ++ goto out; ++ ++ bbot = au_sbbot(sb); ++ if (unlikely(bbot < 0)) { ++ err = -EINVAL; ++ pr_err("no branches\n"); ++ goto out; ++ } ++ ++ if (au_opt_test(tmp, XINO)) ++ au_opt_set(sbinfo->si_mntflags, XINO); ++ opt = opts->opt; ++ while (!err && opt->type != Opt_tail) ++ err = au_opt_xino(sb, opt++, &opt_xino, opts); ++ if (unlikely(err)) ++ goto out; ++ ++ err = au_opts_verify(sb, sb->s_flags, tmp); ++ if (unlikely(err)) ++ goto out; ++ ++ /* restore xino */ ++ if (au_opt_test(tmp, XINO) && !opt_xino) { ++ xino.file = au_xino_def(sb); ++ err = PTR_ERR(xino.file); ++ if (IS_ERR(xino.file)) ++ goto out; ++ ++ err = au_xino_set(sb, &xino, /*remount*/0); ++ fput(xino.file); ++ if (unlikely(err)) ++ goto out; ++ } ++ ++ /* restore udba */ ++ tmp &= AuOptMask_UDBA; ++ sbinfo->si_mntflags &= ~AuOptMask_UDBA; ++ sbinfo->si_mntflags |= tmp; ++ bbot = au_sbbot(sb); ++ for (bindex = 0; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ err = au_hnotify_reset_br(tmp, br, br->br_perm); ++ if (unlikely(err)) ++ AuIOErr("hnotify failed on br %d, %d, ignored\n", ++ bindex, err); ++ /* go on even if err */ ++ } ++ if (au_opt_test(tmp, UDBA_HNOTIFY)) { ++ dir = d_inode(sb->s_root); ++ au_hn_reset(dir, au_hi_flags(dir, /*isdir*/1) & ~AuHi_XINO); ++ } ++ ++out: ++ return err; ++} ++ ++int au_opts_remount(struct super_block *sb, struct au_opts *opts) ++{ ++ int err, rerr; ++ unsigned char no_dreval; ++ struct inode *dir; ++ struct au_opt_xino *opt_xino; ++ struct au_opt *opt; ++ struct au_sbinfo *sbinfo; ++ ++ SiMustWriteLock(sb); ++ ++ err = au_dr_opt_flush(sb); ++ if (unlikely(err)) ++ goto out; ++ au_fset_opts(opts->flags, DR_FLUSHED); ++ ++ dir = d_inode(sb->s_root); ++ sbinfo = au_sbi(sb); ++ opt_xino = NULL; ++ opt = opts->opt; ++ while (err >= 0 && opt->type != Opt_tail) { ++ err = au_opt_simple(sb, opt, opts); ++ if (!err) ++ err = au_opt_br(sb, opt, opts); ++ if (!err) ++ err = au_opt_xino(sb, opt, &opt_xino, opts); ++ opt++; ++ } ++ if (err > 0) ++ err = 0; ++ AuTraceErr(err); ++ /* go on even err */ ++ ++ no_dreval = !!au_ftest_si(sbinfo, NO_DREVAL); ++ rerr = au_opts_verify(sb, opts->sb_flags, /*pending*/0); ++ if (unlikely(rerr && !err)) ++ err = rerr; ++ ++ if (no_dreval != !!au_ftest_si(sbinfo, NO_DREVAL)) ++ au_fset_opts(opts->flags, REFRESH_IDOP); ++ ++ if (au_ftest_opts(opts->flags, TRUNC_XIB)) { ++ rerr = au_xib_trunc(sb); ++ if (unlikely(rerr && !err)) ++ err = rerr; ++ } ++ ++ /* will be handled by the caller */ ++ if (!au_ftest_opts(opts->flags, REFRESH) ++ && (opts->given_udba ++ || au_opt_test(sbinfo->si_mntflags, XINO) ++ || au_ftest_opts(opts->flags, REFRESH_IDOP) ++ )) ++ au_fset_opts(opts->flags, REFRESH); ++ ++ AuDbg("status 0x%x\n", opts->flags); ++ ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++unsigned int au_opt_udba(struct super_block *sb) ++{ ++ return au_mntflags(sb) & AuOptMask_UDBA; ++} +diff --git a/fs/aufs/opts.h b/fs/aufs/opts.h +new file mode 100644 +index 00000000..30bda60f +--- /dev/null ++++ b/fs/aufs/opts.h +@@ -0,0 +1,224 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * mount options/flags ++ */ ++ ++#ifndef __AUFS_OPTS_H__ ++#define __AUFS_OPTS_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++ ++struct file; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* mount flags */ ++#define AuOpt_XINO 1 /* external inode number bitmap ++ and translation table */ ++#define AuOpt_TRUNC_XINO (1 << 1) /* truncate xino files */ ++#define AuOpt_UDBA_NONE (1 << 2) /* users direct branch access */ ++#define AuOpt_UDBA_REVAL (1 << 3) ++#define AuOpt_UDBA_HNOTIFY (1 << 4) ++#define AuOpt_SHWH (1 << 5) /* show whiteout */ ++#define AuOpt_PLINK (1 << 6) /* pseudo-link */ ++#define AuOpt_DIRPERM1 (1 << 7) /* ignore the lower dir's perm ++ bits */ ++#define AuOpt_ALWAYS_DIROPQ (1 << 9) /* policy to creating diropq */ ++#define AuOpt_SUM (1 << 10) /* summation for statfs(2) */ ++#define AuOpt_SUM_W (1 << 11) /* unimplemented */ ++#define AuOpt_WARN_PERM (1 << 12) /* warn when add-branch */ ++#define AuOpt_VERBOSE (1 << 13) /* busy inode when del-branch */ ++#define AuOpt_DIO (1 << 14) /* direct io */ ++#define AuOpt_DIRREN (1 << 15) /* directory rename */ ++ ++#ifndef CONFIG_AUFS_HNOTIFY ++#undef AuOpt_UDBA_HNOTIFY ++#define AuOpt_UDBA_HNOTIFY 0 ++#endif ++#ifndef CONFIG_AUFS_DIRREN ++#undef AuOpt_DIRREN ++#define AuOpt_DIRREN 0 ++#endif ++#ifndef CONFIG_AUFS_SHWH ++#undef AuOpt_SHWH ++#define AuOpt_SHWH 0 ++#endif ++ ++#define AuOpt_Def (AuOpt_XINO \ ++ | AuOpt_UDBA_REVAL \ ++ | AuOpt_PLINK \ ++ /* | AuOpt_DIRPERM1 */ \ ++ | AuOpt_WARN_PERM) ++#define AuOptMask_UDBA (AuOpt_UDBA_NONE \ ++ | AuOpt_UDBA_REVAL \ ++ | AuOpt_UDBA_HNOTIFY) ++ ++#define au_opt_test(flags, name) (flags & AuOpt_##name) ++#define au_opt_set(flags, name) do { \ ++ BUILD_BUG_ON(AuOpt_##name & AuOptMask_UDBA); \ ++ ((flags) |= AuOpt_##name); \ ++} while (0) ++#define au_opt_set_udba(flags, name) do { \ ++ (flags) &= ~AuOptMask_UDBA; \ ++ ((flags) |= AuOpt_##name); \ ++} while (0) ++#define au_opt_clr(flags, name) do { \ ++ ((flags) &= ~AuOpt_##name); \ ++} while (0) ++ ++static inline unsigned int au_opts_plink(unsigned int mntflags) ++{ ++#ifdef CONFIG_PROC_FS ++ return mntflags; ++#else ++ return mntflags & ~AuOpt_PLINK; ++#endif ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* policies to select one among multiple writable branches */ ++enum { ++ AuWbrCreate_TDP, /* top down parent */ ++ AuWbrCreate_RR, /* round robin */ ++ AuWbrCreate_MFS, /* most free space */ ++ AuWbrCreate_MFSV, /* mfs with seconds */ ++ AuWbrCreate_MFSRR, /* mfs then rr */ ++ AuWbrCreate_MFSRRV, /* mfs then rr with seconds */ ++ AuWbrCreate_TDMFS, /* top down regardless parent and mfs */ ++ AuWbrCreate_TDMFSV, /* top down regardless parent and mfs */ ++ AuWbrCreate_PMFS, /* parent and mfs */ ++ AuWbrCreate_PMFSV, /* parent and mfs with seconds */ ++ AuWbrCreate_PMFSRR, /* parent, mfs and round-robin */ ++ AuWbrCreate_PMFSRRV, /* plus seconds */ ++ ++ AuWbrCreate_Def = AuWbrCreate_TDP ++}; ++ ++enum { ++ AuWbrCopyup_TDP, /* top down parent */ ++ AuWbrCopyup_BUP, /* bottom up parent */ ++ AuWbrCopyup_BU, /* bottom up */ ++ ++ AuWbrCopyup_Def = AuWbrCopyup_TDP ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_opt_add { ++ aufs_bindex_t bindex; ++ char *pathname; ++ int perm; ++ struct path path; ++}; ++ ++struct au_opt_del { ++ char *pathname; ++ struct path h_path; ++}; ++ ++struct au_opt_mod { ++ char *path; ++ int perm; ++ struct dentry *h_root; ++}; ++ ++struct au_opt_xino { ++ char *path; ++ struct file *file; ++}; ++ ++struct au_opt_xino_itrunc { ++ aufs_bindex_t bindex; ++}; ++ ++struct au_opt_wbr_create { ++ int wbr_create; ++ int mfs_second; ++ unsigned long long mfsrr_watermark; ++}; ++ ++struct au_opt { ++ int type; ++ union { ++ struct au_opt_xino xino; ++ struct au_opt_xino_itrunc xino_itrunc; ++ struct au_opt_add add; ++ struct au_opt_del del; ++ struct au_opt_mod mod; ++ int dirwh; ++ int rdcache; ++ unsigned int rdblk; ++ unsigned int rdhash; ++ int udba; ++ struct au_opt_wbr_create wbr_create; ++ int wbr_copyup; ++ unsigned int fhsm_second; ++ }; ++}; ++ ++/* opts flags */ ++#define AuOpts_REMOUNT 1 ++#define AuOpts_REFRESH (1 << 1) ++#define AuOpts_TRUNC_XIB (1 << 2) ++#define AuOpts_REFRESH_DYAOP (1 << 3) ++#define AuOpts_REFRESH_IDOP (1 << 4) ++#define AuOpts_DR_FLUSHED (1 << 5) ++#define au_ftest_opts(flags, name) ((flags) & AuOpts_##name) ++#define au_fset_opts(flags, name) \ ++ do { (flags) |= AuOpts_##name; } while (0) ++#define au_fclr_opts(flags, name) \ ++ do { (flags) &= ~AuOpts_##name; } while (0) ++ ++#ifndef CONFIG_AUFS_DIRREN ++#undef AuOpts_DR_FLUSHED ++#define AuOpts_DR_FLUSHED 0 ++#endif ++ ++struct au_opts { ++ struct au_opt *opt; ++ int max_opt; ++ ++ unsigned int given_udba; ++ unsigned int flags; ++ unsigned long sb_flags; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* opts.c */ ++void au_optstr_br_perm(au_br_perm_str_t *str, int perm); ++const char *au_optstr_udba(int udba); ++const char *au_optstr_wbr_copyup(int wbr_copyup); ++const char *au_optstr_wbr_create(int wbr_create); ++ ++void au_opts_free(struct au_opts *opts); ++struct super_block; ++int au_opts_parse(struct super_block *sb, char *str, struct au_opts *opts); ++int au_opts_verify(struct super_block *sb, unsigned long sb_flags, ++ unsigned int pending); ++int au_opts_mount(struct super_block *sb, struct au_opts *opts); ++int au_opts_remount(struct super_block *sb, struct au_opts *opts); ++ ++unsigned int au_opt_udba(struct super_block *sb); ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_OPTS_H__ */ +diff --git a/fs/aufs/plink.c b/fs/aufs/plink.c +new file mode 100644 +index 00000000..9ad02300 +--- /dev/null ++++ b/fs/aufs/plink.c +@@ -0,0 +1,515 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * pseudo-link ++ */ ++ ++#include "aufs.h" ++ ++/* ++ * the pseudo-link maintenance mode. ++ * during a user process maintains the pseudo-links, ++ * prohibit adding a new plink and branch manipulation. ++ * ++ * Flags ++ * NOPLM: ++ * For entry functions which will handle plink, and i_mutex is already held ++ * in VFS. ++ * They cannot wait and should return an error at once. ++ * Callers has to check the error. ++ * NOPLMW: ++ * For entry functions which will handle plink, but i_mutex is not held ++ * in VFS. ++ * They can wait the plink maintenance mode to finish. ++ * ++ * They behave like F_SETLK and F_SETLKW. ++ * If the caller never handle plink, then both flags are unnecessary. ++ */ ++ ++int au_plink_maint(struct super_block *sb, int flags) ++{ ++ int err; ++ pid_t pid, ppid; ++ struct task_struct *parent, *prev; ++ struct au_sbinfo *sbi; ++ ++ SiMustAnyLock(sb); ++ ++ err = 0; ++ if (!au_opt_test(au_mntflags(sb), PLINK)) ++ goto out; ++ ++ sbi = au_sbi(sb); ++ pid = sbi->si_plink_maint_pid; ++ if (!pid || pid == current->pid) ++ goto out; ++ ++ /* todo: it highly depends upon /sbin/mount.aufs */ ++ prev = NULL; ++ parent = current; ++ ppid = 0; ++ rcu_read_lock(); ++ while (1) { ++ parent = rcu_dereference(parent->real_parent); ++ if (parent == prev) ++ break; ++ ppid = task_pid_vnr(parent); ++ if (pid == ppid) { ++ rcu_read_unlock(); ++ goto out; ++ } ++ prev = parent; ++ } ++ rcu_read_unlock(); ++ ++ if (au_ftest_lock(flags, NOPLMW)) { ++ /* if there is no i_mutex lock in VFS, we don't need to wait */ ++ /* AuDebugOn(!lockdep_depth(current)); */ ++ while (sbi->si_plink_maint_pid) { ++ si_read_unlock(sb); ++ /* gave up wake_up_bit() */ ++ wait_event(sbi->si_plink_wq, !sbi->si_plink_maint_pid); ++ ++ if (au_ftest_lock(flags, FLUSH)) ++ au_nwt_flush(&sbi->si_nowait); ++ si_noflush_read_lock(sb); ++ } ++ } else if (au_ftest_lock(flags, NOPLM)) { ++ AuDbg("ppid %d, pid %d\n", ppid, pid); ++ err = -EAGAIN; ++ } ++ ++out: ++ return err; ++} ++ ++void au_plink_maint_leave(struct au_sbinfo *sbinfo) ++{ ++ spin_lock(&sbinfo->si_plink_maint_lock); ++ sbinfo->si_plink_maint_pid = 0; ++ spin_unlock(&sbinfo->si_plink_maint_lock); ++ wake_up_all(&sbinfo->si_plink_wq); ++} ++ ++int au_plink_maint_enter(struct super_block *sb) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ ++ err = 0; ++ sbinfo = au_sbi(sb); ++ /* make sure i am the only one in this fs */ ++ si_write_lock(sb, AuLock_FLUSH); ++ if (au_opt_test(au_mntflags(sb), PLINK)) { ++ spin_lock(&sbinfo->si_plink_maint_lock); ++ if (!sbinfo->si_plink_maint_pid) ++ sbinfo->si_plink_maint_pid = current->pid; ++ else ++ err = -EBUSY; ++ spin_unlock(&sbinfo->si_plink_maint_lock); ++ } ++ si_write_unlock(sb); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_DEBUG ++void au_plink_list(struct super_block *sb) ++{ ++ int i; ++ struct au_sbinfo *sbinfo; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos; ++ struct au_icntnr *icntnr; ++ ++ SiMustAnyLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); ++ AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); ++ ++ for (i = 0; i < AuPlink_NHASH; i++) { ++ hbl = sbinfo->si_plink + i; ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(icntnr, pos, hbl, plink) ++ AuDbg("%lu\n", icntnr->vfs_inode.i_ino); ++ hlist_bl_unlock(hbl); ++ } ++} ++#endif ++ ++/* is the inode pseudo-linked? */ ++int au_plink_test(struct inode *inode) ++{ ++ int found, i; ++ struct au_sbinfo *sbinfo; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos; ++ struct au_icntnr *icntnr; ++ ++ sbinfo = au_sbi(inode->i_sb); ++ AuRwMustAnyLock(&sbinfo->si_rwsem); ++ AuDebugOn(!au_opt_test(au_mntflags(inode->i_sb), PLINK)); ++ AuDebugOn(au_plink_maint(inode->i_sb, AuLock_NOPLM)); ++ ++ found = 0; ++ i = au_plink_hash(inode->i_ino); ++ hbl = sbinfo->si_plink + i; ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(icntnr, pos, hbl, plink) ++ if (&icntnr->vfs_inode == inode) { ++ found = 1; ++ break; ++ } ++ hlist_bl_unlock(hbl); ++ return found; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * generate a name for plink. ++ * the file will be stored under AUFS_WH_PLINKDIR. ++ */ ++/* 20 is max digits length of ulong 64 */ ++#define PLINK_NAME_LEN ((20 + 1) * 2) ++ ++static int plink_name(char *name, int len, struct inode *inode, ++ aufs_bindex_t bindex) ++{ ++ int rlen; ++ struct inode *h_inode; ++ ++ h_inode = au_h_iptr(inode, bindex); ++ rlen = snprintf(name, len, "%lu.%lu", inode->i_ino, h_inode->i_ino); ++ return rlen; ++} ++ ++struct au_do_plink_lkup_args { ++ struct dentry **errp; ++ struct qstr *tgtname; ++ struct dentry *h_parent; ++ struct au_branch *br; ++}; ++ ++static struct dentry *au_do_plink_lkup(struct qstr *tgtname, ++ struct dentry *h_parent, ++ struct au_branch *br) ++{ ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ ++ h_inode = d_inode(h_parent); ++ vfsub_inode_lock_shared_nested(h_inode, AuLsc_I_CHILD2); ++ h_dentry = vfsub_lkup_one(tgtname, h_parent); ++ inode_unlock_shared(h_inode); ++ return h_dentry; ++} ++ ++static void au_call_do_plink_lkup(void *args) ++{ ++ struct au_do_plink_lkup_args *a = args; ++ *a->errp = au_do_plink_lkup(a->tgtname, a->h_parent, a->br); ++} ++ ++/* lookup the plink-ed @inode under the branch at @bindex */ ++struct dentry *au_plink_lkup(struct inode *inode, aufs_bindex_t bindex) ++{ ++ struct dentry *h_dentry, *h_parent; ++ struct au_branch *br; ++ int wkq_err; ++ char a[PLINK_NAME_LEN]; ++ struct qstr tgtname = QSTR_INIT(a, 0); ++ ++ AuDebugOn(au_plink_maint(inode->i_sb, AuLock_NOPLM)); ++ ++ br = au_sbr(inode->i_sb, bindex); ++ h_parent = br->br_wbr->wbr_plink; ++ tgtname.len = plink_name(a, sizeof(a), inode, bindex); ++ ++ if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) { ++ struct au_do_plink_lkup_args args = { ++ .errp = &h_dentry, ++ .tgtname = &tgtname, ++ .h_parent = h_parent, ++ .br = br ++ }; ++ ++ wkq_err = au_wkq_wait(au_call_do_plink_lkup, &args); ++ if (unlikely(wkq_err)) ++ h_dentry = ERR_PTR(wkq_err); ++ } else ++ h_dentry = au_do_plink_lkup(&tgtname, h_parent, br); ++ ++ return h_dentry; ++} ++ ++/* create a pseudo-link */ ++static int do_whplink(struct qstr *tgt, struct dentry *h_parent, ++ struct dentry *h_dentry, struct au_branch *br) ++{ ++ int err; ++ struct path h_path = { ++ .mnt = au_br_mnt(br) ++ }; ++ struct inode *h_dir, *delegated; ++ ++ h_dir = d_inode(h_parent); ++ inode_lock_nested(h_dir, AuLsc_I_CHILD2); ++again: ++ h_path.dentry = vfsub_lkup_one(tgt, h_parent); ++ err = PTR_ERR(h_path.dentry); ++ if (IS_ERR(h_path.dentry)) ++ goto out; ++ ++ err = 0; ++ /* wh.plink dir is not monitored */ ++ /* todo: is it really safe? */ ++ if (d_is_positive(h_path.dentry) ++ && d_inode(h_path.dentry) != d_inode(h_dentry)) { ++ delegated = NULL; ++ err = vfsub_unlink(h_dir, &h_path, &delegated, /*force*/0); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal unlink\n"); ++ iput(delegated); ++ } ++ dput(h_path.dentry); ++ h_path.dentry = NULL; ++ if (!err) ++ goto again; ++ } ++ if (!err && d_is_negative(h_path.dentry)) { ++ delegated = NULL; ++ err = vfsub_link(h_dentry, h_dir, &h_path, &delegated); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal link\n"); ++ iput(delegated); ++ } ++ } ++ dput(h_path.dentry); ++ ++out: ++ inode_unlock(h_dir); ++ return err; ++} ++ ++struct do_whplink_args { ++ int *errp; ++ struct qstr *tgt; ++ struct dentry *h_parent; ++ struct dentry *h_dentry; ++ struct au_branch *br; ++}; ++ ++static void call_do_whplink(void *args) ++{ ++ struct do_whplink_args *a = args; ++ *a->errp = do_whplink(a->tgt, a->h_parent, a->h_dentry, a->br); ++} ++ ++static int whplink(struct dentry *h_dentry, struct inode *inode, ++ aufs_bindex_t bindex, struct au_branch *br) ++{ ++ int err, wkq_err; ++ struct au_wbr *wbr; ++ struct dentry *h_parent; ++ char a[PLINK_NAME_LEN]; ++ struct qstr tgtname = QSTR_INIT(a, 0); ++ ++ wbr = au_sbr(inode->i_sb, bindex)->br_wbr; ++ h_parent = wbr->wbr_plink; ++ tgtname.len = plink_name(a, sizeof(a), inode, bindex); ++ ++ /* always superio. */ ++ if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) { ++ struct do_whplink_args args = { ++ .errp = &err, ++ .tgt = &tgtname, ++ .h_parent = h_parent, ++ .h_dentry = h_dentry, ++ .br = br ++ }; ++ wkq_err = au_wkq_wait(call_do_whplink, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } else ++ err = do_whplink(&tgtname, h_parent, h_dentry, br); ++ ++ return err; ++} ++ ++/* ++ * create a new pseudo-link for @h_dentry on @bindex. ++ * the linked inode is held in aufs @inode. ++ */ ++void au_plink_append(struct inode *inode, aufs_bindex_t bindex, ++ struct dentry *h_dentry) ++{ ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos; ++ struct au_icntnr *icntnr; ++ int found, err, cnt, i; ++ ++ sb = inode->i_sb; ++ sbinfo = au_sbi(sb); ++ AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); ++ AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); ++ ++ found = au_plink_test(inode); ++ if (found) ++ return; ++ ++ i = au_plink_hash(inode->i_ino); ++ hbl = sbinfo->si_plink + i; ++ au_igrab(inode); ++ ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(icntnr, pos, hbl, plink) { ++ if (&icntnr->vfs_inode == inode) { ++ found = 1; ++ break; ++ } ++ } ++ if (!found) { ++ icntnr = container_of(inode, struct au_icntnr, vfs_inode); ++ hlist_bl_add_head(&icntnr->plink, hbl); ++ } ++ hlist_bl_unlock(hbl); ++ if (!found) { ++ cnt = au_hbl_count(hbl); ++#define msg "unexpectedly unblanced or too many pseudo-links" ++ if (cnt > AUFS_PLINK_WARN) ++ AuWarn1(msg ", %d\n", cnt); ++#undef msg ++ err = whplink(h_dentry, inode, bindex, au_sbr(sb, bindex)); ++ if (unlikely(err)) { ++ pr_warn("err %d, damaged pseudo link.\n", err); ++ au_hbl_del(&icntnr->plink, hbl); ++ iput(&icntnr->vfs_inode); ++ } ++ } else ++ iput(&icntnr->vfs_inode); ++} ++ ++/* free all plinks */ ++void au_plink_put(struct super_block *sb, int verbose) ++{ ++ int i, warned; ++ struct au_sbinfo *sbinfo; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos, *tmp; ++ struct au_icntnr *icntnr; ++ ++ SiMustWriteLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); ++ AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); ++ ++ /* no spin_lock since sbinfo is write-locked */ ++ warned = 0; ++ for (i = 0; i < AuPlink_NHASH; i++) { ++ hbl = sbinfo->si_plink + i; ++ if (!warned && verbose && !hlist_bl_empty(hbl)) { ++ pr_warn("pseudo-link is not flushed"); ++ warned = 1; ++ } ++ hlist_bl_for_each_entry_safe(icntnr, pos, tmp, hbl, plink) ++ iput(&icntnr->vfs_inode); ++ INIT_HLIST_BL_HEAD(hbl); ++ } ++} ++ ++void au_plink_clean(struct super_block *sb, int verbose) ++{ ++ struct dentry *root; ++ ++ root = sb->s_root; ++ aufs_write_lock(root); ++ if (au_opt_test(au_mntflags(sb), PLINK)) ++ au_plink_put(sb, verbose); ++ aufs_write_unlock(root); ++} ++ ++static int au_plink_do_half_refresh(struct inode *inode, aufs_bindex_t br_id) ++{ ++ int do_put; ++ aufs_bindex_t btop, bbot, bindex; ++ ++ do_put = 0; ++ btop = au_ibtop(inode); ++ bbot = au_ibbot(inode); ++ if (btop >= 0) { ++ for (bindex = btop; bindex <= bbot; bindex++) { ++ if (!au_h_iptr(inode, bindex) ++ || au_ii_br_id(inode, bindex) != br_id) ++ continue; ++ au_set_h_iptr(inode, bindex, NULL, 0); ++ do_put = 1; ++ break; ++ } ++ if (do_put) ++ for (bindex = btop; bindex <= bbot; bindex++) ++ if (au_h_iptr(inode, bindex)) { ++ do_put = 0; ++ break; ++ } ++ } else ++ do_put = 1; ++ ++ return do_put; ++} ++ ++/* free the plinks on a branch specified by @br_id */ ++void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id) ++{ ++ struct au_sbinfo *sbinfo; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos, *tmp; ++ struct au_icntnr *icntnr; ++ struct inode *inode; ++ int i, do_put; ++ ++ SiMustWriteLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); ++ AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); ++ ++ /* no bit_lock since sbinfo is write-locked */ ++ for (i = 0; i < AuPlink_NHASH; i++) { ++ hbl = sbinfo->si_plink + i; ++ hlist_bl_for_each_entry_safe(icntnr, pos, tmp, hbl, plink) { ++ inode = au_igrab(&icntnr->vfs_inode); ++ ii_write_lock_child(inode); ++ do_put = au_plink_do_half_refresh(inode, br_id); ++ if (do_put) { ++ hlist_bl_del(&icntnr->plink); ++ iput(inode); ++ } ++ ii_write_unlock(inode); ++ iput(inode); ++ } ++ } ++} +diff --git a/fs/aufs/poll.c b/fs/aufs/poll.c +new file mode 100644 +index 00000000..de790b16 +--- /dev/null ++++ b/fs/aufs/poll.c +@@ -0,0 +1,53 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * poll operation ++ * There is only one filesystem which implements ->poll operation, currently. ++ */ ++ ++#include "aufs.h" ++ ++unsigned int aufs_poll(struct file *file, poll_table *wait) ++{ ++ unsigned int mask; ++ struct file *h_file; ++ struct super_block *sb; ++ ++ /* We should pretend an error happened. */ ++ mask = POLLERR /* | POLLIN | POLLOUT */; ++ sb = file->f_path.dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); ++ ++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); ++ if (IS_ERR(h_file)) { ++ AuDbg("h_file %ld\n", PTR_ERR(h_file)); ++ goto out; ++ } ++ ++ /* it is not an error if h_file has no operation */ ++ mask = DEFAULT_POLLMASK; ++ if (h_file->f_op->poll) ++ mask = h_file->f_op->poll(h_file, wait); ++ fput(h_file); /* instead of au_read_post() */ ++ ++out: ++ si_read_unlock(sb); ++ if (mask & POLLERR) ++ AuDbg("mask 0x%x\n", mask); ++ return mask; ++} +diff --git a/fs/aufs/posix_acl.c b/fs/aufs/posix_acl.c +new file mode 100644 +index 00000000..4a820126 +--- /dev/null ++++ b/fs/aufs/posix_acl.c +@@ -0,0 +1,102 @@ ++/* ++ * Copyright (C) 2014-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * posix acl operations ++ */ ++ ++#include ++#include "aufs.h" ++ ++struct posix_acl *aufs_get_acl(struct inode *inode, int type) ++{ ++ struct posix_acl *acl; ++ int err; ++ aufs_bindex_t bindex; ++ struct inode *h_inode; ++ struct super_block *sb; ++ ++ acl = NULL; ++ sb = inode->i_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ ii_read_lock_child(inode); ++ if (!(sb->s_flags & MS_POSIXACL)) ++ goto out; ++ ++ bindex = au_ibtop(inode); ++ h_inode = au_h_iptr(inode, bindex); ++ if (unlikely(!h_inode ++ || ((h_inode->i_mode & S_IFMT) ++ != (inode->i_mode & S_IFMT)))) { ++ err = au_busy_or_stale(); ++ acl = ERR_PTR(err); ++ goto out; ++ } ++ ++ /* always topmost only */ ++ acl = get_acl(h_inode, type); ++ if (!IS_ERR_OR_NULL(acl)) ++ set_cached_acl(inode, type, acl); ++ ++out: ++ ii_read_unlock(inode); ++ si_read_unlock(sb); ++ ++ AuTraceErrPtr(acl); ++ return acl; ++} ++ ++int aufs_set_acl(struct inode *inode, struct posix_acl *acl, int type) ++{ ++ int err; ++ ssize_t ssz; ++ struct dentry *dentry; ++ struct au_sxattr arg = { ++ .type = AU_ACL_SET, ++ .u.acl_set = { ++ .acl = acl, ++ .type = type ++ }, ++ }; ++ ++ IMustLock(inode); ++ ++ if (inode->i_ino == AUFS_ROOT_INO) ++ dentry = dget(inode->i_sb->s_root); ++ else { ++ dentry = d_find_alias(inode); ++ if (!dentry) ++ dentry = d_find_any_alias(inode); ++ if (!dentry) { ++ pr_warn("cannot handle this inode, " ++ "please report to aufs-users ML\n"); ++ err = -ENOENT; ++ goto out; ++ } ++ } ++ ++ ssz = au_sxattr(dentry, inode, &arg); ++ dput(dentry); ++ err = ssz; ++ if (ssz >= 0) { ++ err = 0; ++ set_cached_acl(inode, type, acl); ++ } ++ ++out: ++ return err; ++} +diff --git a/fs/aufs/procfs.c b/fs/aufs/procfs.c +new file mode 100644 +index 00000000..1301b8f4 +--- /dev/null ++++ b/fs/aufs/procfs.c +@@ -0,0 +1,170 @@ ++/* ++ * Copyright (C) 2010-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * procfs interfaces ++ */ ++ ++#include ++#include "aufs.h" ++ ++static int au_procfs_plm_release(struct inode *inode, struct file *file) ++{ ++ struct au_sbinfo *sbinfo; ++ ++ sbinfo = file->private_data; ++ if (sbinfo) { ++ au_plink_maint_leave(sbinfo); ++ kobject_put(&sbinfo->si_kobj); ++ } ++ ++ return 0; ++} ++ ++static void au_procfs_plm_write_clean(struct file *file) ++{ ++ struct au_sbinfo *sbinfo; ++ ++ sbinfo = file->private_data; ++ if (sbinfo) ++ au_plink_clean(sbinfo->si_sb, /*verbose*/0); ++} ++ ++static int au_procfs_plm_write_si(struct file *file, unsigned long id) ++{ ++ int err; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ struct hlist_bl_node *pos; ++ ++ err = -EBUSY; ++ if (unlikely(file->private_data)) ++ goto out; ++ ++ sb = NULL; ++ /* don't use au_sbilist_lock() here */ ++ hlist_bl_lock(&au_sbilist); ++ hlist_bl_for_each_entry(sbinfo, pos, &au_sbilist, si_list) ++ if (id == sysaufs_si_id(sbinfo)) { ++ kobject_get(&sbinfo->si_kobj); ++ sb = sbinfo->si_sb; ++ break; ++ } ++ hlist_bl_unlock(&au_sbilist); ++ ++ err = -EINVAL; ++ if (unlikely(!sb)) ++ goto out; ++ ++ err = au_plink_maint_enter(sb); ++ if (!err) ++ /* keep kobject_get() */ ++ file->private_data = sbinfo; ++ else ++ kobject_put(&sbinfo->si_kobj); ++out: ++ return err; ++} ++ ++/* ++ * Accept a valid "si=xxxx" only. ++ * Once it is accepted successfully, accept "clean" too. ++ */ ++static ssize_t au_procfs_plm_write(struct file *file, const char __user *ubuf, ++ size_t count, loff_t *ppos) ++{ ++ ssize_t err; ++ unsigned long id; ++ /* last newline is allowed */ ++ char buf[3 + sizeof(unsigned long) * 2 + 1]; ++ ++ err = -EACCES; ++ if (unlikely(!capable(CAP_SYS_ADMIN))) ++ goto out; ++ ++ err = -EINVAL; ++ if (unlikely(count > sizeof(buf))) ++ goto out; ++ ++ err = copy_from_user(buf, ubuf, count); ++ if (unlikely(err)) { ++ err = -EFAULT; ++ goto out; ++ } ++ buf[count] = 0; ++ ++ err = -EINVAL; ++ if (!strcmp("clean", buf)) { ++ au_procfs_plm_write_clean(file); ++ goto out_success; ++ } else if (unlikely(strncmp("si=", buf, 3))) ++ goto out; ++ ++ err = kstrtoul(buf + 3, 16, &id); ++ if (unlikely(err)) ++ goto out; ++ ++ err = au_procfs_plm_write_si(file, id); ++ if (unlikely(err)) ++ goto out; ++ ++out_success: ++ err = count; /* success */ ++out: ++ return err; ++} ++ ++static const struct file_operations au_procfs_plm_fop = { ++ .write = au_procfs_plm_write, ++ .release = au_procfs_plm_release, ++ .owner = THIS_MODULE ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct proc_dir_entry *au_procfs_dir; ++ ++void au_procfs_fin(void) ++{ ++ remove_proc_entry(AUFS_PLINK_MAINT_NAME, au_procfs_dir); ++ remove_proc_entry(AUFS_PLINK_MAINT_DIR, NULL); ++} ++ ++int __init au_procfs_init(void) ++{ ++ int err; ++ struct proc_dir_entry *entry; ++ ++ err = -ENOMEM; ++ au_procfs_dir = proc_mkdir(AUFS_PLINK_MAINT_DIR, NULL); ++ if (unlikely(!au_procfs_dir)) ++ goto out; ++ ++ entry = proc_create(AUFS_PLINK_MAINT_NAME, S_IFREG | 0200, ++ au_procfs_dir, &au_procfs_plm_fop); ++ if (unlikely(!entry)) ++ goto out_dir; ++ ++ err = 0; ++ goto out; /* success */ ++ ++ ++out_dir: ++ remove_proc_entry(AUFS_PLINK_MAINT_DIR, NULL); ++out: ++ return err; ++} +diff --git a/fs/aufs/rdu.c b/fs/aufs/rdu.c +new file mode 100644 +index 00000000..f6a10f55 +--- /dev/null ++++ b/fs/aufs/rdu.c +@@ -0,0 +1,381 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * readdir in userspace. ++ */ ++ ++#include ++#include ++#include ++#include "aufs.h" ++ ++/* bits for struct aufs_rdu.flags */ ++#define AuRdu_CALLED 1 ++#define AuRdu_CONT (1 << 1) ++#define AuRdu_FULL (1 << 2) ++#define au_ftest_rdu(flags, name) ((flags) & AuRdu_##name) ++#define au_fset_rdu(flags, name) \ ++ do { (flags) |= AuRdu_##name; } while (0) ++#define au_fclr_rdu(flags, name) \ ++ do { (flags) &= ~AuRdu_##name; } while (0) ++ ++struct au_rdu_arg { ++ struct dir_context ctx; ++ struct aufs_rdu *rdu; ++ union au_rdu_ent_ul ent; ++ unsigned long end; ++ ++ struct super_block *sb; ++ int err; ++}; ++ ++static int au_rdu_fill(struct dir_context *ctx, const char *name, int nlen, ++ loff_t offset, u64 h_ino, unsigned int d_type) ++{ ++ int err, len; ++ struct au_rdu_arg *arg = container_of(ctx, struct au_rdu_arg, ctx); ++ struct aufs_rdu *rdu = arg->rdu; ++ struct au_rdu_ent ent; ++ ++ err = 0; ++ arg->err = 0; ++ au_fset_rdu(rdu->cookie.flags, CALLED); ++ len = au_rdu_len(nlen); ++ if (arg->ent.ul + len < arg->end) { ++ ent.ino = h_ino; ++ ent.bindex = rdu->cookie.bindex; ++ ent.type = d_type; ++ ent.nlen = nlen; ++ if (unlikely(nlen > AUFS_MAX_NAMELEN)) ++ ent.type = DT_UNKNOWN; ++ ++ /* unnecessary to support mmap_sem since this is a dir */ ++ err = -EFAULT; ++ if (copy_to_user(arg->ent.e, &ent, sizeof(ent))) ++ goto out; ++ if (copy_to_user(arg->ent.e->name, name, nlen)) ++ goto out; ++ /* the terminating NULL */ ++ if (__put_user(0, arg->ent.e->name + nlen)) ++ goto out; ++ err = 0; ++ /* AuDbg("%p, %.*s\n", arg->ent.p, nlen, name); */ ++ arg->ent.ul += len; ++ rdu->rent++; ++ } else { ++ err = -EFAULT; ++ au_fset_rdu(rdu->cookie.flags, FULL); ++ rdu->full = 1; ++ rdu->tail = arg->ent; ++ } ++ ++out: ++ /* AuTraceErr(err); */ ++ return err; ++} ++ ++static int au_rdu_do(struct file *h_file, struct au_rdu_arg *arg) ++{ ++ int err; ++ loff_t offset; ++ struct au_rdu_cookie *cookie = &arg->rdu->cookie; ++ ++ /* we don't have to care (FMODE_32BITHASH | FMODE_64BITHASH) for ext4 */ ++ offset = vfsub_llseek(h_file, cookie->h_pos, SEEK_SET); ++ err = offset; ++ if (unlikely(offset != cookie->h_pos)) ++ goto out; ++ ++ err = 0; ++ do { ++ arg->err = 0; ++ au_fclr_rdu(cookie->flags, CALLED); ++ /* smp_mb(); */ ++ err = vfsub_iterate_dir(h_file, &arg->ctx); ++ if (err >= 0) ++ err = arg->err; ++ } while (!err ++ && au_ftest_rdu(cookie->flags, CALLED) ++ && !au_ftest_rdu(cookie->flags, FULL)); ++ cookie->h_pos = h_file->f_pos; ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++static int au_rdu(struct file *file, struct aufs_rdu *rdu) ++{ ++ int err; ++ aufs_bindex_t bbot; ++ struct au_rdu_arg arg = { ++ .ctx = { ++ .actor = au_rdu_fill ++ } ++ }; ++ struct dentry *dentry; ++ struct inode *inode; ++ struct file *h_file; ++ struct au_rdu_cookie *cookie = &rdu->cookie; ++ ++ err = !access_ok(VERIFY_WRITE, rdu->ent.e, rdu->sz); ++ if (unlikely(err)) { ++ err = -EFAULT; ++ AuTraceErr(err); ++ goto out; ++ } ++ rdu->rent = 0; ++ rdu->tail = rdu->ent; ++ rdu->full = 0; ++ arg.rdu = rdu; ++ arg.ent = rdu->ent; ++ arg.end = arg.ent.ul; ++ arg.end += rdu->sz; ++ ++ err = -ENOTDIR; ++ if (unlikely(!file->f_op->iterate && !file->f_op->iterate_shared)) ++ goto out; ++ ++ err = security_file_permission(file, MAY_READ); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ goto out; ++ ++ dentry = file->f_path.dentry; ++ inode = d_inode(dentry); ++ inode_lock_shared(inode); ++ ++ arg.sb = inode->i_sb; ++ err = si_read_lock(arg.sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (unlikely(err)) ++ goto out_mtx; ++ err = au_alive_dir(dentry); ++ if (unlikely(err)) ++ goto out_si; ++ /* todo: reval? */ ++ fi_read_lock(file); ++ ++ err = -EAGAIN; ++ if (unlikely(au_ftest_rdu(cookie->flags, CONT) ++ && cookie->generation != au_figen(file))) ++ goto out_unlock; ++ ++ err = 0; ++ if (!rdu->blk) { ++ rdu->blk = au_sbi(arg.sb)->si_rdblk; ++ if (!rdu->blk) ++ rdu->blk = au_dir_size(file, /*dentry*/NULL); ++ } ++ bbot = au_fbtop(file); ++ if (cookie->bindex < bbot) ++ cookie->bindex = bbot; ++ bbot = au_fbbot_dir(file); ++ /* AuDbg("b%d, b%d\n", cookie->bindex, bbot); */ ++ for (; !err && cookie->bindex <= bbot; ++ cookie->bindex++, cookie->h_pos = 0) { ++ h_file = au_hf_dir(file, cookie->bindex); ++ if (!h_file) ++ continue; ++ ++ au_fclr_rdu(cookie->flags, FULL); ++ err = au_rdu_do(h_file, &arg); ++ AuTraceErr(err); ++ if (unlikely(au_ftest_rdu(cookie->flags, FULL) || err)) ++ break; ++ } ++ AuDbg("rent %llu\n", rdu->rent); ++ ++ if (!err && !au_ftest_rdu(cookie->flags, CONT)) { ++ rdu->shwh = !!au_opt_test(au_sbi(arg.sb)->si_mntflags, SHWH); ++ au_fset_rdu(cookie->flags, CONT); ++ cookie->generation = au_figen(file); ++ } ++ ++ ii_read_lock_child(inode); ++ fsstack_copy_attr_atime(inode, au_h_iptr(inode, au_ibtop(inode))); ++ ii_read_unlock(inode); ++ ++out_unlock: ++ fi_read_unlock(file); ++out_si: ++ si_read_unlock(arg.sb); ++out_mtx: ++ inode_unlock_shared(inode); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++static int au_rdu_ino(struct file *file, struct aufs_rdu *rdu) ++{ ++ int err; ++ ino_t ino; ++ unsigned long long nent; ++ union au_rdu_ent_ul *u; ++ struct au_rdu_ent ent; ++ struct super_block *sb; ++ ++ err = 0; ++ nent = rdu->nent; ++ u = &rdu->ent; ++ sb = file->f_path.dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ while (nent-- > 0) { ++ /* unnecessary to support mmap_sem since this is a dir */ ++ err = copy_from_user(&ent, u->e, sizeof(ent)); ++ if (!err) ++ err = !access_ok(VERIFY_WRITE, &u->e->ino, sizeof(ino)); ++ if (unlikely(err)) { ++ err = -EFAULT; ++ AuTraceErr(err); ++ break; ++ } ++ ++ /* AuDbg("b%d, i%llu\n", ent.bindex, ent.ino); */ ++ if (!ent.wh) ++ err = au_ino(sb, ent.bindex, ent.ino, ent.type, &ino); ++ else ++ err = au_wh_ino(sb, ent.bindex, ent.ino, ent.type, ++ &ino); ++ if (unlikely(err)) { ++ AuTraceErr(err); ++ break; ++ } ++ ++ err = __put_user(ino, &u->e->ino); ++ if (unlikely(err)) { ++ err = -EFAULT; ++ AuTraceErr(err); ++ break; ++ } ++ u->ul += au_rdu_len(ent.nlen); ++ } ++ si_read_unlock(sb); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_rdu_verify(struct aufs_rdu *rdu) ++{ ++ AuDbg("rdu{%llu, %p, %u | %u | %llu, %u, %u | " ++ "%llu, b%d, 0x%x, g%u}\n", ++ rdu->sz, rdu->ent.e, rdu->verify[AufsCtlRduV_SZ], ++ rdu->blk, ++ rdu->rent, rdu->shwh, rdu->full, ++ rdu->cookie.h_pos, rdu->cookie.bindex, rdu->cookie.flags, ++ rdu->cookie.generation); ++ ++ if (rdu->verify[AufsCtlRduV_SZ] == sizeof(*rdu)) ++ return 0; ++ ++ AuDbg("%u:%u\n", ++ rdu->verify[AufsCtlRduV_SZ], (unsigned int)sizeof(*rdu)); ++ return -EINVAL; ++} ++ ++long au_rdu_ioctl(struct file *file, unsigned int cmd, unsigned long arg) ++{ ++ long err, e; ++ struct aufs_rdu rdu; ++ void __user *p = (void __user *)arg; ++ ++ err = copy_from_user(&rdu, p, sizeof(rdu)); ++ if (unlikely(err)) { ++ err = -EFAULT; ++ AuTraceErr(err); ++ goto out; ++ } ++ err = au_rdu_verify(&rdu); ++ if (unlikely(err)) ++ goto out; ++ ++ switch (cmd) { ++ case AUFS_CTL_RDU: ++ err = au_rdu(file, &rdu); ++ if (unlikely(err)) ++ break; ++ ++ e = copy_to_user(p, &rdu, sizeof(rdu)); ++ if (unlikely(e)) { ++ err = -EFAULT; ++ AuTraceErr(err); ++ } ++ break; ++ case AUFS_CTL_RDU_INO: ++ err = au_rdu_ino(file, &rdu); ++ break; ++ ++ default: ++ /* err = -ENOTTY; */ ++ err = -EINVAL; ++ } ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++#ifdef CONFIG_COMPAT ++long au_rdu_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) ++{ ++ long err, e; ++ struct aufs_rdu rdu; ++ void __user *p = compat_ptr(arg); ++ ++ /* todo: get_user()? */ ++ err = copy_from_user(&rdu, p, sizeof(rdu)); ++ if (unlikely(err)) { ++ err = -EFAULT; ++ AuTraceErr(err); ++ goto out; ++ } ++ rdu.ent.e = compat_ptr(rdu.ent.ul); ++ err = au_rdu_verify(&rdu); ++ if (unlikely(err)) ++ goto out; ++ ++ switch (cmd) { ++ case AUFS_CTL_RDU: ++ err = au_rdu(file, &rdu); ++ if (unlikely(err)) ++ break; ++ ++ rdu.ent.ul = ptr_to_compat(rdu.ent.e); ++ rdu.tail.ul = ptr_to_compat(rdu.tail.e); ++ e = copy_to_user(p, &rdu, sizeof(rdu)); ++ if (unlikely(e)) { ++ err = -EFAULT; ++ AuTraceErr(err); ++ } ++ break; ++ case AUFS_CTL_RDU_INO: ++ err = au_rdu_ino(file, &rdu); ++ break; ++ ++ default: ++ /* err = -ENOTTY; */ ++ err = -EINVAL; ++ } ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++#endif +diff --git a/fs/aufs/rwsem.h b/fs/aufs/rwsem.h +new file mode 100644 +index 00000000..c2d33dc8 +--- /dev/null ++++ b/fs/aufs/rwsem.h +@@ -0,0 +1,198 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * simple read-write semaphore wrappers ++ */ ++ ++#ifndef __AUFS_RWSEM_H__ ++#define __AUFS_RWSEM_H__ ++ ++#ifdef __KERNEL__ ++ ++#include "debug.h" ++ ++struct au_rwsem { ++ struct rw_semaphore rwsem; ++#ifdef CONFIG_AUFS_DEBUG ++ /* just for debugging, not almighty counter */ ++ atomic_t rcnt, wcnt; ++#endif ++}; ++ ++#ifdef CONFIG_LOCKDEP ++#define au_lockdep_set_name(rw) \ ++ lockdep_set_class_and_name(&(rw)->rwsem, \ ++ /*original key*/(rw)->rwsem.dep_map.key, \ ++ /*name*/#rw) ++#else ++#define au_lockdep_set_name(rw) do {} while (0) ++#endif ++ ++#ifdef CONFIG_AUFS_DEBUG ++#define AuDbgCntInit(rw) do { \ ++ atomic_set(&(rw)->rcnt, 0); \ ++ atomic_set(&(rw)->wcnt, 0); \ ++ smp_mb(); /* atomic set */ \ ++} while (0) ++ ++#define AuDbgCnt(rw, cnt) atomic_read(&(rw)->cnt) ++#define AuDbgCntInc(rw, cnt) atomic_inc(&(rw)->cnt) ++#define AuDbgCntDec(rw, cnt) WARN_ON(atomic_dec_return(&(rw)->cnt) < 0) ++#define AuDbgRcntInc(rw) AuDbgCntInc(rw, rcnt) ++#define AuDbgRcntDec(rw) AuDbgCntDec(rw, rcnt) ++#define AuDbgWcntInc(rw) AuDbgCntInc(rw, wcnt) ++#define AuDbgWcntDec(rw) AuDbgCntDec(rw, wcnt) ++#else ++#define AuDbgCnt(rw, cnt) 0 ++#define AuDbgCntInit(rw) do {} while (0) ++#define AuDbgRcntInc(rw) do {} while (0) ++#define AuDbgRcntDec(rw) do {} while (0) ++#define AuDbgWcntInc(rw) do {} while (0) ++#define AuDbgWcntDec(rw) do {} while (0) ++#endif /* CONFIG_AUFS_DEBUG */ ++ ++/* to debug easier, do not make them inlined functions */ ++#define AuRwMustNoWaiters(rw) AuDebugOn(rwsem_is_contended(&(rw)->rwsem)) ++/* rwsem_is_locked() is unusable */ ++#define AuRwMustReadLock(rw) AuDebugOn(AuDbgCnt(rw, rcnt) <= 0) ++#define AuRwMustWriteLock(rw) AuDebugOn(AuDbgCnt(rw, wcnt) <= 0) ++#define AuRwMustAnyLock(rw) AuDebugOn(AuDbgCnt(rw, rcnt) <= 0 \ ++ && AuDbgCnt(rw, wcnt) <= 0) ++#define AuRwDestroy(rw) AuDebugOn(AuDbgCnt(rw, rcnt) \ ++ || AuDbgCnt(rw, wcnt)) ++ ++#define au_rw_init(rw) do { \ ++ AuDbgCntInit(rw); \ ++ init_rwsem(&(rw)->rwsem); \ ++ au_lockdep_set_name(rw); \ ++ } while (0) ++ ++#define au_rw_init_wlock(rw) do { \ ++ au_rw_init(rw); \ ++ down_write(&(rw)->rwsem); \ ++ AuDbgWcntInc(rw); \ ++ } while (0) ++ ++#define au_rw_init_wlock_nested(rw, lsc) do { \ ++ au_rw_init(rw); \ ++ down_write_nested(&(rw)->rwsem, lsc); \ ++ AuDbgWcntInc(rw); \ ++ } while (0) ++ ++static inline void au_rw_read_lock(struct au_rwsem *rw) ++{ ++ down_read(&rw->rwsem); ++ AuDbgRcntInc(rw); ++} ++ ++static inline void au_rw_read_lock_nested(struct au_rwsem *rw, unsigned int lsc) ++{ ++ down_read_nested(&rw->rwsem, lsc); ++ AuDbgRcntInc(rw); ++} ++ ++static inline void au_rw_read_unlock(struct au_rwsem *rw) ++{ ++ AuRwMustReadLock(rw); ++ AuDbgRcntDec(rw); ++ up_read(&rw->rwsem); ++} ++ ++static inline void au_rw_dgrade_lock(struct au_rwsem *rw) ++{ ++ AuRwMustWriteLock(rw); ++ AuDbgRcntInc(rw); ++ AuDbgWcntDec(rw); ++ downgrade_write(&rw->rwsem); ++} ++ ++static inline void au_rw_write_lock(struct au_rwsem *rw) ++{ ++ down_write(&rw->rwsem); ++ AuDbgWcntInc(rw); ++} ++ ++static inline void au_rw_write_lock_nested(struct au_rwsem *rw, ++ unsigned int lsc) ++{ ++ down_write_nested(&rw->rwsem, lsc); ++ AuDbgWcntInc(rw); ++} ++ ++static inline void au_rw_write_unlock(struct au_rwsem *rw) ++{ ++ AuRwMustWriteLock(rw); ++ AuDbgWcntDec(rw); ++ up_write(&rw->rwsem); ++} ++ ++/* why is not _nested version defined */ ++static inline int au_rw_read_trylock(struct au_rwsem *rw) ++{ ++ int ret; ++ ++ ret = down_read_trylock(&rw->rwsem); ++ if (ret) ++ AuDbgRcntInc(rw); ++ return ret; ++} ++ ++static inline int au_rw_write_trylock(struct au_rwsem *rw) ++{ ++ int ret; ++ ++ ret = down_write_trylock(&rw->rwsem); ++ if (ret) ++ AuDbgWcntInc(rw); ++ return ret; ++} ++ ++#undef AuDbgCntDec ++#undef AuDbgRcntInc ++#undef AuDbgRcntDec ++#undef AuDbgWcntDec ++ ++#define AuSimpleLockRwsemFuncs(prefix, param, rwsem) \ ++static inline void prefix##_read_lock(param) \ ++{ au_rw_read_lock(rwsem); } \ ++static inline void prefix##_write_lock(param) \ ++{ au_rw_write_lock(rwsem); } \ ++static inline int prefix##_read_trylock(param) \ ++{ return au_rw_read_trylock(rwsem); } \ ++static inline int prefix##_write_trylock(param) \ ++{ return au_rw_write_trylock(rwsem); } ++/* why is not _nested version defined */ ++/* static inline void prefix##_read_trylock_nested(param, lsc) ++{ au_rw_read_trylock_nested(rwsem, lsc)); } ++static inline void prefix##_write_trylock_nestd(param, lsc) ++{ au_rw_write_trylock_nested(rwsem, lsc); } */ ++ ++#define AuSimpleUnlockRwsemFuncs(prefix, param, rwsem) \ ++static inline void prefix##_read_unlock(param) \ ++{ au_rw_read_unlock(rwsem); } \ ++static inline void prefix##_write_unlock(param) \ ++{ au_rw_write_unlock(rwsem); } \ ++static inline void prefix##_downgrade_lock(param) \ ++{ au_rw_dgrade_lock(rwsem); } ++ ++#define AuSimpleRwsemFuncs(prefix, param, rwsem) \ ++ AuSimpleLockRwsemFuncs(prefix, param, rwsem) \ ++ AuSimpleUnlockRwsemFuncs(prefix, param, rwsem) ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_RWSEM_H__ */ +diff --git a/fs/aufs/sbinfo.c b/fs/aufs/sbinfo.c +new file mode 100644 +index 00000000..63f11119 +--- /dev/null ++++ b/fs/aufs/sbinfo.c +@@ -0,0 +1,311 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * superblock private data ++ */ ++ ++#include "aufs.h" ++ ++/* ++ * they are necessary regardless sysfs is disabled. ++ */ ++void au_si_free(struct kobject *kobj) ++{ ++ int i; ++ struct au_sbinfo *sbinfo; ++ char *locked __maybe_unused; /* debug only */ ++ ++ sbinfo = container_of(kobj, struct au_sbinfo, si_kobj); ++ for (i = 0; i < AuPlink_NHASH; i++) ++ AuDebugOn(!hlist_bl_empty(sbinfo->si_plink + i)); ++ AuDebugOn(atomic_read(&sbinfo->si_nowait.nw_len)); ++ ++ AuDebugOn(percpu_counter_sum(&sbinfo->si_ninodes)); ++ percpu_counter_destroy(&sbinfo->si_ninodes); ++ AuDebugOn(percpu_counter_sum(&sbinfo->si_nfiles)); ++ percpu_counter_destroy(&sbinfo->si_nfiles); ++ ++ dbgaufs_si_fin(sbinfo); ++ au_rw_write_lock(&sbinfo->si_rwsem); ++ au_br_free(sbinfo); ++ au_rw_write_unlock(&sbinfo->si_rwsem); ++ ++ kfree(sbinfo->si_branch); ++ mutex_destroy(&sbinfo->si_xib_mtx); ++ AuRwDestroy(&sbinfo->si_rwsem); ++ ++ kfree(sbinfo); ++} ++ ++int au_si_alloc(struct super_block *sb) ++{ ++ int err, i; ++ struct au_sbinfo *sbinfo; ++ ++ err = -ENOMEM; ++ sbinfo = kzalloc(sizeof(*sbinfo), GFP_NOFS); ++ if (unlikely(!sbinfo)) ++ goto out; ++ ++ /* will be reallocated separately */ ++ sbinfo->si_branch = kzalloc(sizeof(*sbinfo->si_branch), GFP_NOFS); ++ if (unlikely(!sbinfo->si_branch)) ++ goto out_sbinfo; ++ ++ err = sysaufs_si_init(sbinfo); ++ if (!err) { ++ dbgaufs_si_null(sbinfo); ++ err = dbgaufs_si_init(sbinfo); ++ if (unlikely(err)) ++ kobject_put(&sbinfo->si_kobj); ++ } ++ if (unlikely(err)) ++ goto out_br; ++ ++ au_nwt_init(&sbinfo->si_nowait); ++ au_rw_init_wlock(&sbinfo->si_rwsem); ++ ++ percpu_counter_init(&sbinfo->si_ninodes, 0, GFP_NOFS); ++ percpu_counter_init(&sbinfo->si_nfiles, 0, GFP_NOFS); ++ ++ sbinfo->si_bbot = -1; ++ sbinfo->si_last_br_id = AUFS_BRANCH_MAX / 2; ++ ++ sbinfo->si_wbr_copyup = AuWbrCopyup_Def; ++ sbinfo->si_wbr_create = AuWbrCreate_Def; ++ sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + sbinfo->si_wbr_copyup; ++ sbinfo->si_wbr_create_ops = au_wbr_create_ops + sbinfo->si_wbr_create; ++ ++ au_fhsm_init(sbinfo); ++ ++ sbinfo->si_mntflags = au_opts_plink(AuOpt_Def); ++ ++ sbinfo->si_xino_jiffy = jiffies; ++ sbinfo->si_xino_expire ++ = msecs_to_jiffies(AUFS_XINO_DEF_SEC * MSEC_PER_SEC); ++ mutex_init(&sbinfo->si_xib_mtx); ++ sbinfo->si_xino_brid = -1; ++ /* leave si_xib_last_pindex and si_xib_next_bit */ ++ ++ INIT_HLIST_BL_HEAD(&sbinfo->si_aopen); ++ ++ sbinfo->si_rdcache = msecs_to_jiffies(AUFS_RDCACHE_DEF * MSEC_PER_SEC); ++ sbinfo->si_rdblk = AUFS_RDBLK_DEF; ++ sbinfo->si_rdhash = AUFS_RDHASH_DEF; ++ sbinfo->si_dirwh = AUFS_DIRWH_DEF; ++ ++ for (i = 0; i < AuPlink_NHASH; i++) ++ INIT_HLIST_BL_HEAD(sbinfo->si_plink + i); ++ init_waitqueue_head(&sbinfo->si_plink_wq); ++ spin_lock_init(&sbinfo->si_plink_maint_lock); ++ ++ INIT_HLIST_BL_HEAD(&sbinfo->si_files); ++ ++ /* with getattr by default */ ++ sbinfo->si_iop_array = aufs_iop; ++ ++ /* leave other members for sysaufs and si_mnt. */ ++ sbinfo->si_sb = sb; ++ sb->s_fs_info = sbinfo; ++ si_pid_set(sb); ++ return 0; /* success */ ++ ++out_br: ++ kfree(sbinfo->si_branch); ++out_sbinfo: ++ kfree(sbinfo); ++out: ++ return err; ++} ++ ++int au_sbr_realloc(struct au_sbinfo *sbinfo, int nbr, int may_shrink) ++{ ++ int err, sz; ++ struct au_branch **brp; ++ ++ AuRwMustWriteLock(&sbinfo->si_rwsem); ++ ++ err = -ENOMEM; ++ sz = sizeof(*brp) * (sbinfo->si_bbot + 1); ++ if (unlikely(!sz)) ++ sz = sizeof(*brp); ++ brp = au_kzrealloc(sbinfo->si_branch, sz, sizeof(*brp) * nbr, GFP_NOFS, ++ may_shrink); ++ if (brp) { ++ sbinfo->si_branch = brp; ++ err = 0; ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++unsigned int au_sigen_inc(struct super_block *sb) ++{ ++ unsigned int gen; ++ struct inode *inode; ++ ++ SiMustWriteLock(sb); ++ ++ gen = ++au_sbi(sb)->si_generation; ++ au_update_digen(sb->s_root); ++ inode = d_inode(sb->s_root); ++ au_update_iigen(inode, /*half*/0); ++ inode->i_version++; ++ return gen; ++} ++ ++aufs_bindex_t au_new_br_id(struct super_block *sb) ++{ ++ aufs_bindex_t br_id; ++ int i; ++ struct au_sbinfo *sbinfo; ++ ++ SiMustWriteLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ for (i = 0; i <= AUFS_BRANCH_MAX; i++) { ++ br_id = ++sbinfo->si_last_br_id; ++ AuDebugOn(br_id < 0); ++ if (br_id && au_br_index(sb, br_id) < 0) ++ return br_id; ++ } ++ ++ return -1; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* it is ok that new 'nwt' tasks are appended while we are sleeping */ ++int si_read_lock(struct super_block *sb, int flags) ++{ ++ int err; ++ ++ err = 0; ++ if (au_ftest_lock(flags, FLUSH)) ++ au_nwt_flush(&au_sbi(sb)->si_nowait); ++ ++ si_noflush_read_lock(sb); ++ err = au_plink_maint(sb, flags); ++ if (unlikely(err)) ++ si_read_unlock(sb); ++ ++ return err; ++} ++ ++int si_write_lock(struct super_block *sb, int flags) ++{ ++ int err; ++ ++ if (au_ftest_lock(flags, FLUSH)) ++ au_nwt_flush(&au_sbi(sb)->si_nowait); ++ ++ si_noflush_write_lock(sb); ++ err = au_plink_maint(sb, flags); ++ if (unlikely(err)) ++ si_write_unlock(sb); ++ ++ return err; ++} ++ ++/* dentry and super_block lock. call at entry point */ ++int aufs_read_lock(struct dentry *dentry, int flags) ++{ ++ int err; ++ struct super_block *sb; ++ ++ sb = dentry->d_sb; ++ err = si_read_lock(sb, flags); ++ if (unlikely(err)) ++ goto out; ++ ++ if (au_ftest_lock(flags, DW)) ++ di_write_lock_child(dentry); ++ else ++ di_read_lock_child(dentry, flags); ++ ++ if (au_ftest_lock(flags, GEN)) { ++ err = au_digen_test(dentry, au_sigen(sb)); ++ if (!au_opt_test(au_mntflags(sb), UDBA_NONE)) ++ AuDebugOn(!err && au_dbrange_test(dentry)); ++ else if (!err) ++ err = au_dbrange_test(dentry); ++ if (unlikely(err)) ++ aufs_read_unlock(dentry, flags); ++ } ++ ++out: ++ return err; ++} ++ ++void aufs_read_unlock(struct dentry *dentry, int flags) ++{ ++ if (au_ftest_lock(flags, DW)) ++ di_write_unlock(dentry); ++ else ++ di_read_unlock(dentry, flags); ++ si_read_unlock(dentry->d_sb); ++} ++ ++void aufs_write_lock(struct dentry *dentry) ++{ ++ si_write_lock(dentry->d_sb, AuLock_FLUSH | AuLock_NOPLMW); ++ di_write_lock_child(dentry); ++} ++ ++void aufs_write_unlock(struct dentry *dentry) ++{ ++ di_write_unlock(dentry); ++ si_write_unlock(dentry->d_sb); ++} ++ ++int aufs_read_and_write_lock2(struct dentry *d1, struct dentry *d2, int flags) ++{ ++ int err; ++ unsigned int sigen; ++ struct super_block *sb; ++ ++ sb = d1->d_sb; ++ err = si_read_lock(sb, flags); ++ if (unlikely(err)) ++ goto out; ++ ++ di_write_lock2_child(d1, d2, au_ftest_lock(flags, DIRS)); ++ ++ if (au_ftest_lock(flags, GEN)) { ++ sigen = au_sigen(sb); ++ err = au_digen_test(d1, sigen); ++ AuDebugOn(!err && au_dbrange_test(d1)); ++ if (!err) { ++ err = au_digen_test(d2, sigen); ++ AuDebugOn(!err && au_dbrange_test(d2)); ++ } ++ if (unlikely(err)) ++ aufs_read_and_write_unlock2(d1, d2); ++ } ++ ++out: ++ return err; ++} ++ ++void aufs_read_and_write_unlock2(struct dentry *d1, struct dentry *d2) ++{ ++ di_write_unlock2(d1, d2); ++ si_read_unlock(d1->d_sb); ++} +diff --git a/fs/aufs/super.c b/fs/aufs/super.c +new file mode 100644 +index 00000000..0cf6c27c +--- /dev/null ++++ b/fs/aufs/super.c +@@ -0,0 +1,1037 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * mount and super_block operations ++ */ ++ ++#include ++#include ++#include ++#include ++#include "aufs.h" ++ ++/* ++ * super_operations ++ */ ++static struct inode *aufs_alloc_inode(struct super_block *sb __maybe_unused) ++{ ++ struct au_icntnr *c; ++ ++ c = au_cache_alloc_icntnr(); ++ if (c) { ++ au_icntnr_init(c); ++ c->vfs_inode.i_version = 1; /* sigen(sb); */ ++ c->iinfo.ii_hinode = NULL; ++ return &c->vfs_inode; ++ } ++ return NULL; ++} ++ ++static void aufs_destroy_inode_cb(struct rcu_head *head) ++{ ++ struct inode *inode = container_of(head, struct inode, i_rcu); ++ ++ au_cache_free_icntnr(container_of(inode, struct au_icntnr, vfs_inode)); ++} ++ ++static void aufs_destroy_inode(struct inode *inode) ++{ ++ if (!au_is_bad_inode(inode)) ++ au_iinfo_fin(inode); ++ call_rcu(&inode->i_rcu, aufs_destroy_inode_cb); ++} ++ ++struct inode *au_iget_locked(struct super_block *sb, ino_t ino) ++{ ++ struct inode *inode; ++ int err; ++ ++ inode = iget_locked(sb, ino); ++ if (unlikely(!inode)) { ++ inode = ERR_PTR(-ENOMEM); ++ goto out; ++ } ++ if (!(inode->i_state & I_NEW)) ++ goto out; ++ ++ err = au_xigen_new(inode); ++ if (!err) ++ err = au_iinfo_init(inode); ++ if (!err) ++ inode->i_version++; ++ else { ++ iget_failed(inode); ++ inode = ERR_PTR(err); ++ } ++ ++out: ++ /* never return NULL */ ++ AuDebugOn(!inode); ++ AuTraceErrPtr(inode); ++ return inode; ++} ++ ++/* lock free root dinfo */ ++static int au_show_brs(struct seq_file *seq, struct super_block *sb) ++{ ++ int err; ++ aufs_bindex_t bindex, bbot; ++ struct path path; ++ struct au_hdentry *hdp; ++ struct au_branch *br; ++ au_br_perm_str_t perm; ++ ++ err = 0; ++ bbot = au_sbbot(sb); ++ bindex = 0; ++ hdp = au_hdentry(au_di(sb->s_root), bindex); ++ for (; !err && bindex <= bbot; bindex++, hdp++) { ++ br = au_sbr(sb, bindex); ++ path.mnt = au_br_mnt(br); ++ path.dentry = hdp->hd_dentry; ++ err = au_seq_path(seq, &path); ++ if (!err) { ++ au_optstr_br_perm(&perm, br->br_perm); ++ seq_printf(seq, "=%s", perm.a); ++ if (bindex != bbot) ++ seq_putc(seq, ':'); ++ } ++ } ++ if (unlikely(err || seq_has_overflowed(seq))) ++ err = -E2BIG; ++ ++ return err; ++} ++ ++static void au_gen_fmt(char *fmt, int len __maybe_unused, const char *pat, ++ const char *append) ++{ ++ char *p; ++ ++ p = fmt; ++ while (*pat != ':') ++ *p++ = *pat++; ++ *p++ = *pat++; ++ strcpy(p, append); ++ AuDebugOn(strlen(fmt) >= len); ++} ++ ++static void au_show_wbr_create(struct seq_file *m, int v, ++ struct au_sbinfo *sbinfo) ++{ ++ const char *pat; ++ char fmt[32]; ++ struct au_wbr_mfs *mfs; ++ ++ AuRwMustAnyLock(&sbinfo->si_rwsem); ++ ++ seq_puts(m, ",create="); ++ pat = au_optstr_wbr_create(v); ++ mfs = &sbinfo->si_wbr_mfs; ++ switch (v) { ++ case AuWbrCreate_TDP: ++ case AuWbrCreate_RR: ++ case AuWbrCreate_MFS: ++ case AuWbrCreate_PMFS: ++ seq_puts(m, pat); ++ break; ++ case AuWbrCreate_MFSRR: ++ case AuWbrCreate_TDMFS: ++ case AuWbrCreate_PMFSRR: ++ au_gen_fmt(fmt, sizeof(fmt), pat, "%llu"); ++ seq_printf(m, fmt, mfs->mfsrr_watermark); ++ break; ++ case AuWbrCreate_MFSV: ++ case AuWbrCreate_PMFSV: ++ au_gen_fmt(fmt, sizeof(fmt), pat, "%lu"); ++ seq_printf(m, fmt, ++ jiffies_to_msecs(mfs->mfs_expire) ++ / MSEC_PER_SEC); ++ break; ++ case AuWbrCreate_MFSRRV: ++ case AuWbrCreate_TDMFSV: ++ case AuWbrCreate_PMFSRRV: ++ au_gen_fmt(fmt, sizeof(fmt), pat, "%llu:%lu"); ++ seq_printf(m, fmt, mfs->mfsrr_watermark, ++ jiffies_to_msecs(mfs->mfs_expire) / MSEC_PER_SEC); ++ break; ++ default: ++ BUG(); ++ } ++} ++ ++static int au_show_xino(struct seq_file *seq, struct super_block *sb) ++{ ++#ifdef CONFIG_SYSFS ++ return 0; ++#else ++ int err; ++ const int len = sizeof(AUFS_XINO_FNAME) - 1; ++ aufs_bindex_t bindex, brid; ++ struct qstr *name; ++ struct file *f; ++ struct dentry *d, *h_root; ++ ++ AuRwMustAnyLock(&sbinfo->si_rwsem); ++ ++ err = 0; ++ f = au_sbi(sb)->si_xib; ++ if (!f) ++ goto out; ++ ++ /* stop printing the default xino path on the first writable branch */ ++ h_root = NULL; ++ brid = au_xino_brid(sb); ++ if (brid >= 0) { ++ bindex = au_br_index(sb, brid); ++ h_root = au_hdentry(au_di(sb->s_root), bindex)->hd_dentry; ++ } ++ d = f->f_path.dentry; ++ name = &d->d_name; ++ /* safe ->d_parent because the file is unlinked */ ++ if (d->d_parent == h_root ++ && name->len == len ++ && !memcmp(name->name, AUFS_XINO_FNAME, len)) ++ goto out; ++ ++ seq_puts(seq, ",xino="); ++ err = au_xino_path(seq, f); ++ ++out: ++ return err; ++#endif ++} ++ ++/* seq_file will re-call me in case of too long string */ ++static int aufs_show_options(struct seq_file *m, struct dentry *dentry) ++{ ++ int err; ++ unsigned int mnt_flags, v; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ ++#define AuBool(name, str) do { \ ++ v = au_opt_test(mnt_flags, name); \ ++ if (v != au_opt_test(AuOpt_Def, name)) \ ++ seq_printf(m, ",%s" #str, v ? "" : "no"); \ ++} while (0) ++ ++#define AuStr(name, str) do { \ ++ v = mnt_flags & AuOptMask_##name; \ ++ if (v != (AuOpt_Def & AuOptMask_##name)) \ ++ seq_printf(m, "," #str "=%s", au_optstr_##str(v)); \ ++} while (0) ++ ++#define AuUInt(name, str, val) do { \ ++ if (val != AUFS_##name##_DEF) \ ++ seq_printf(m, "," #str "=%u", val); \ ++} while (0) ++ ++ sb = dentry->d_sb; ++ if (sb->s_flags & MS_POSIXACL) ++ seq_puts(m, ",acl"); ++ ++ /* lock free root dinfo */ ++ si_noflush_read_lock(sb); ++ sbinfo = au_sbi(sb); ++ seq_printf(m, ",si=%lx", sysaufs_si_id(sbinfo)); ++ ++ mnt_flags = au_mntflags(sb); ++ if (au_opt_test(mnt_flags, XINO)) { ++ err = au_show_xino(m, sb); ++ if (unlikely(err)) ++ goto out; ++ } else ++ seq_puts(m, ",noxino"); ++ ++ AuBool(TRUNC_XINO, trunc_xino); ++ AuStr(UDBA, udba); ++ AuBool(SHWH, shwh); ++ AuBool(PLINK, plink); ++ AuBool(DIO, dio); ++ AuBool(DIRPERM1, dirperm1); ++ ++ v = sbinfo->si_wbr_create; ++ if (v != AuWbrCreate_Def) ++ au_show_wbr_create(m, v, sbinfo); ++ ++ v = sbinfo->si_wbr_copyup; ++ if (v != AuWbrCopyup_Def) ++ seq_printf(m, ",cpup=%s", au_optstr_wbr_copyup(v)); ++ ++ v = au_opt_test(mnt_flags, ALWAYS_DIROPQ); ++ if (v != au_opt_test(AuOpt_Def, ALWAYS_DIROPQ)) ++ seq_printf(m, ",diropq=%c", v ? 'a' : 'w'); ++ ++ AuUInt(DIRWH, dirwh, sbinfo->si_dirwh); ++ ++ v = jiffies_to_msecs(sbinfo->si_rdcache) / MSEC_PER_SEC; ++ AuUInt(RDCACHE, rdcache, v); ++ ++ AuUInt(RDBLK, rdblk, sbinfo->si_rdblk); ++ AuUInt(RDHASH, rdhash, sbinfo->si_rdhash); ++ ++ au_fhsm_show(m, sbinfo); ++ ++ AuBool(DIRREN, dirren); ++ AuBool(SUM, sum); ++ /* AuBool(SUM_W, wsum); */ ++ AuBool(WARN_PERM, warn_perm); ++ AuBool(VERBOSE, verbose); ++ ++out: ++ /* be sure to print "br:" last */ ++ if (!sysaufs_brs) { ++ seq_puts(m, ",br:"); ++ au_show_brs(m, sb); ++ } ++ si_read_unlock(sb); ++ return 0; ++ ++#undef AuBool ++#undef AuStr ++#undef AuUInt ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* sum mode which returns the summation for statfs(2) */ ++ ++static u64 au_add_till_max(u64 a, u64 b) ++{ ++ u64 old; ++ ++ old = a; ++ a += b; ++ if (old <= a) ++ return a; ++ return ULLONG_MAX; ++} ++ ++static u64 au_mul_till_max(u64 a, long mul) ++{ ++ u64 old; ++ ++ old = a; ++ a *= mul; ++ if (old <= a) ++ return a; ++ return ULLONG_MAX; ++} ++ ++static int au_statfs_sum(struct super_block *sb, struct kstatfs *buf) ++{ ++ int err; ++ long bsize, factor; ++ u64 blocks, bfree, bavail, files, ffree; ++ aufs_bindex_t bbot, bindex, i; ++ unsigned char shared; ++ struct path h_path; ++ struct super_block *h_sb; ++ ++ err = 0; ++ bsize = LONG_MAX; ++ files = 0; ++ ffree = 0; ++ blocks = 0; ++ bfree = 0; ++ bavail = 0; ++ bbot = au_sbbot(sb); ++ for (bindex = 0; bindex <= bbot; bindex++) { ++ h_path.mnt = au_sbr_mnt(sb, bindex); ++ h_sb = h_path.mnt->mnt_sb; ++ shared = 0; ++ for (i = 0; !shared && i < bindex; i++) ++ shared = (au_sbr_sb(sb, i) == h_sb); ++ if (shared) ++ continue; ++ ++ /* sb->s_root for NFS is unreliable */ ++ h_path.dentry = h_path.mnt->mnt_root; ++ err = vfs_statfs(&h_path, buf); ++ if (unlikely(err)) ++ goto out; ++ ++ if (bsize > buf->f_bsize) { ++ /* ++ * we will reduce bsize, so we have to expand blocks ++ * etc. to match them again ++ */ ++ factor = (bsize / buf->f_bsize); ++ blocks = au_mul_till_max(blocks, factor); ++ bfree = au_mul_till_max(bfree, factor); ++ bavail = au_mul_till_max(bavail, factor); ++ bsize = buf->f_bsize; ++ } ++ ++ factor = (buf->f_bsize / bsize); ++ blocks = au_add_till_max(blocks, ++ au_mul_till_max(buf->f_blocks, factor)); ++ bfree = au_add_till_max(bfree, ++ au_mul_till_max(buf->f_bfree, factor)); ++ bavail = au_add_till_max(bavail, ++ au_mul_till_max(buf->f_bavail, factor)); ++ files = au_add_till_max(files, buf->f_files); ++ ffree = au_add_till_max(ffree, buf->f_ffree); ++ } ++ ++ buf->f_bsize = bsize; ++ buf->f_blocks = blocks; ++ buf->f_bfree = bfree; ++ buf->f_bavail = bavail; ++ buf->f_files = files; ++ buf->f_ffree = ffree; ++ buf->f_frsize = 0; ++ ++out: ++ return err; ++} ++ ++static int aufs_statfs(struct dentry *dentry, struct kstatfs *buf) ++{ ++ int err; ++ struct path h_path; ++ struct super_block *sb; ++ ++ /* lock free root dinfo */ ++ sb = dentry->d_sb; ++ si_noflush_read_lock(sb); ++ if (!au_opt_test(au_mntflags(sb), SUM)) { ++ /* sb->s_root for NFS is unreliable */ ++ h_path.mnt = au_sbr_mnt(sb, 0); ++ h_path.dentry = h_path.mnt->mnt_root; ++ err = vfs_statfs(&h_path, buf); ++ } else ++ err = au_statfs_sum(sb, buf); ++ si_read_unlock(sb); ++ ++ if (!err) { ++ buf->f_type = AUFS_SUPER_MAGIC; ++ buf->f_namelen = AUFS_MAX_NAMELEN; ++ memset(&buf->f_fsid, 0, sizeof(buf->f_fsid)); ++ } ++ /* buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1; */ ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int aufs_sync_fs(struct super_block *sb, int wait) ++{ ++ int err, e; ++ aufs_bindex_t bbot, bindex; ++ struct au_branch *br; ++ struct super_block *h_sb; ++ ++ err = 0; ++ si_noflush_read_lock(sb); ++ bbot = au_sbbot(sb); ++ for (bindex = 0; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (!au_br_writable(br->br_perm)) ++ continue; ++ ++ h_sb = au_sbr_sb(sb, bindex); ++ e = vfsub_sync_filesystem(h_sb, wait); ++ if (unlikely(e && !err)) ++ err = e; ++ /* go on even if an error happens */ ++ } ++ si_read_unlock(sb); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* final actions when unmounting a file system */ ++static void aufs_put_super(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ ++ sbinfo = au_sbi(sb); ++ if (sbinfo) ++ kobject_put(&sbinfo->si_kobj); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void *au_array_alloc(unsigned long long *hint, au_arraycb_t cb, ++ struct super_block *sb, void *arg) ++{ ++ void *array; ++ unsigned long long n, sz; ++ ++ array = NULL; ++ n = 0; ++ if (!*hint) ++ goto out; ++ ++ if (*hint > ULLONG_MAX / sizeof(array)) { ++ array = ERR_PTR(-EMFILE); ++ pr_err("hint %llu\n", *hint); ++ goto out; ++ } ++ ++ sz = sizeof(array) * *hint; ++ array = kzalloc(sz, GFP_NOFS); ++ if (unlikely(!array)) ++ array = vzalloc(sz); ++ if (unlikely(!array)) { ++ array = ERR_PTR(-ENOMEM); ++ goto out; ++ } ++ ++ n = cb(sb, array, *hint, arg); ++ AuDebugOn(n > *hint); ++ ++out: ++ *hint = n; ++ return array; ++} ++ ++static unsigned long long au_iarray_cb(struct super_block *sb, void *a, ++ unsigned long long max __maybe_unused, ++ void *arg) ++{ ++ unsigned long long n; ++ struct inode **p, *inode; ++ struct list_head *head; ++ ++ n = 0; ++ p = a; ++ head = arg; ++ spin_lock(&sb->s_inode_list_lock); ++ list_for_each_entry(inode, head, i_sb_list) { ++ if (!au_is_bad_inode(inode) ++ && au_ii(inode)->ii_btop >= 0) { ++ spin_lock(&inode->i_lock); ++ if (atomic_read(&inode->i_count)) { ++ au_igrab(inode); ++ *p++ = inode; ++ n++; ++ AuDebugOn(n > max); ++ } ++ spin_unlock(&inode->i_lock); ++ } ++ } ++ spin_unlock(&sb->s_inode_list_lock); ++ ++ return n; ++} ++ ++struct inode **au_iarray_alloc(struct super_block *sb, unsigned long long *max) ++{ ++ *max = au_ninodes(sb); ++ return au_array_alloc(max, au_iarray_cb, sb, &sb->s_inodes); ++} ++ ++void au_iarray_free(struct inode **a, unsigned long long max) ++{ ++ unsigned long long ull; ++ ++ for (ull = 0; ull < max; ull++) ++ iput(a[ull]); ++ kvfree(a); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * refresh dentry and inode at remount time. ++ */ ++/* todo: consolidate with simple_reval_dpath() and au_reval_for_attr() */ ++static int au_do_refresh(struct dentry *dentry, unsigned int dir_flags, ++ struct dentry *parent) ++{ ++ int err; ++ ++ di_write_lock_child(dentry); ++ di_read_lock_parent(parent, AuLock_IR); ++ err = au_refresh_dentry(dentry, parent); ++ if (!err && dir_flags) ++ au_hn_reset(d_inode(dentry), dir_flags); ++ di_read_unlock(parent, AuLock_IR); ++ di_write_unlock(dentry); ++ ++ return err; ++} ++ ++static int au_do_refresh_d(struct dentry *dentry, unsigned int sigen, ++ struct au_sbinfo *sbinfo, ++ const unsigned int dir_flags, unsigned int do_idop) ++{ ++ int err; ++ struct dentry *parent; ++ ++ err = 0; ++ parent = dget_parent(dentry); ++ if (!au_digen_test(parent, sigen) && au_digen_test(dentry, sigen)) { ++ if (d_really_is_positive(dentry)) { ++ if (!d_is_dir(dentry)) ++ err = au_do_refresh(dentry, /*dir_flags*/0, ++ parent); ++ else { ++ err = au_do_refresh(dentry, dir_flags, parent); ++ if (unlikely(err)) ++ au_fset_si(sbinfo, FAILED_REFRESH_DIR); ++ } ++ } else ++ err = au_do_refresh(dentry, /*dir_flags*/0, parent); ++ AuDbgDentry(dentry); ++ } ++ dput(parent); ++ ++ if (!err) { ++ if (do_idop) ++ au_refresh_dop(dentry, /*force_reval*/0); ++ } else ++ au_refresh_dop(dentry, /*force_reval*/1); ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++static int au_refresh_d(struct super_block *sb, unsigned int do_idop) ++{ ++ int err, i, j, ndentry, e; ++ unsigned int sigen; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry **dentries, *d; ++ struct au_sbinfo *sbinfo; ++ struct dentry *root = sb->s_root; ++ const unsigned int dir_flags = au_hi_flags(d_inode(root), /*isdir*/1); ++ ++ if (do_idop) ++ au_refresh_dop(root, /*force_reval*/0); ++ ++ err = au_dpages_init(&dpages, GFP_NOFS); ++ if (unlikely(err)) ++ goto out; ++ err = au_dcsub_pages(&dpages, root, NULL, NULL); ++ if (unlikely(err)) ++ goto out_dpages; ++ ++ sigen = au_sigen(sb); ++ sbinfo = au_sbi(sb); ++ for (i = 0; i < dpages.ndpage; i++) { ++ dpage = dpages.dpages + i; ++ dentries = dpage->dentries; ++ ndentry = dpage->ndentry; ++ for (j = 0; j < ndentry; j++) { ++ d = dentries[j]; ++ e = au_do_refresh_d(d, sigen, sbinfo, dir_flags, ++ do_idop); ++ if (unlikely(e && !err)) ++ err = e; ++ /* go on even err */ ++ } ++ } ++ ++out_dpages: ++ au_dpages_free(&dpages); ++out: ++ return err; ++} ++ ++static int au_refresh_i(struct super_block *sb, unsigned int do_idop) ++{ ++ int err, e; ++ unsigned int sigen; ++ unsigned long long max, ull; ++ struct inode *inode, **array; ++ ++ array = au_iarray_alloc(sb, &max); ++ err = PTR_ERR(array); ++ if (IS_ERR(array)) ++ goto out; ++ ++ err = 0; ++ sigen = au_sigen(sb); ++ for (ull = 0; ull < max; ull++) { ++ inode = array[ull]; ++ if (unlikely(!inode)) ++ break; ++ ++ e = 0; ++ ii_write_lock_child(inode); ++ if (au_iigen(inode, NULL) != sigen) { ++ e = au_refresh_hinode_self(inode); ++ if (unlikely(e)) { ++ au_refresh_iop(inode, /*force_getattr*/1); ++ pr_err("error %d, i%lu\n", e, inode->i_ino); ++ if (!err) ++ err = e; ++ /* go on even if err */ ++ } ++ } ++ if (!e && do_idop) ++ au_refresh_iop(inode, /*force_getattr*/0); ++ ii_write_unlock(inode); ++ } ++ ++ au_iarray_free(array, max); ++ ++out: ++ return err; ++} ++ ++static void au_remount_refresh(struct super_block *sb, unsigned int do_idop) ++{ ++ int err, e; ++ unsigned int udba; ++ aufs_bindex_t bindex, bbot; ++ struct dentry *root; ++ struct inode *inode; ++ struct au_branch *br; ++ struct au_sbinfo *sbi; ++ ++ au_sigen_inc(sb); ++ sbi = au_sbi(sb); ++ au_fclr_si(sbi, FAILED_REFRESH_DIR); ++ ++ root = sb->s_root; ++ DiMustNoWaiters(root); ++ inode = d_inode(root); ++ IiMustNoWaiters(inode); ++ ++ udba = au_opt_udba(sb); ++ bbot = au_sbbot(sb); ++ for (bindex = 0; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ err = au_hnotify_reset_br(udba, br, br->br_perm); ++ if (unlikely(err)) ++ AuIOErr("hnotify failed on br %d, %d, ignored\n", ++ bindex, err); ++ /* go on even if err */ ++ } ++ au_hn_reset(inode, au_hi_flags(inode, /*isdir*/1)); ++ ++ if (do_idop) { ++ if (au_ftest_si(sbi, NO_DREVAL)) { ++ AuDebugOn(sb->s_d_op == &aufs_dop_noreval); ++ sb->s_d_op = &aufs_dop_noreval; ++ AuDebugOn(sbi->si_iop_array == aufs_iop_nogetattr); ++ sbi->si_iop_array = aufs_iop_nogetattr; ++ } else { ++ AuDebugOn(sb->s_d_op == &aufs_dop); ++ sb->s_d_op = &aufs_dop; ++ AuDebugOn(sbi->si_iop_array == aufs_iop); ++ sbi->si_iop_array = aufs_iop; ++ } ++ pr_info("reset to %pf and %pf\n", ++ sb->s_d_op, sbi->si_iop_array); ++ } ++ ++ di_write_unlock(root); ++ err = au_refresh_d(sb, do_idop); ++ e = au_refresh_i(sb, do_idop); ++ if (unlikely(e && !err)) ++ err = e; ++ /* aufs_write_lock() calls ..._child() */ ++ di_write_lock_child(root); ++ ++ au_cpup_attr_all(inode, /*force*/1); ++ ++ if (unlikely(err)) ++ AuIOErr("refresh failed, ignored, %d\n", err); ++} ++ ++/* stop extra interpretation of errno in mount(8), and strange error messages */ ++static int cvt_err(int err) ++{ ++ AuTraceErr(err); ++ ++ switch (err) { ++ case -ENOENT: ++ case -ENOTDIR: ++ case -EEXIST: ++ case -EIO: ++ err = -EINVAL; ++ } ++ return err; ++} ++ ++static int aufs_remount_fs(struct super_block *sb, int *flags, char *data) ++{ ++ int err, do_dx; ++ unsigned int mntflags; ++ struct au_opts opts = { ++ .opt = NULL ++ }; ++ struct dentry *root; ++ struct inode *inode; ++ struct au_sbinfo *sbinfo; ++ ++ err = 0; ++ root = sb->s_root; ++ if (!data || !*data) { ++ err = si_write_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (!err) { ++ di_write_lock_child(root); ++ err = au_opts_verify(sb, *flags, /*pending*/0); ++ aufs_write_unlock(root); ++ } ++ goto out; ++ } ++ ++ err = -ENOMEM; ++ opts.opt = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!opts.opt)) ++ goto out; ++ opts.max_opt = PAGE_SIZE / sizeof(*opts.opt); ++ opts.flags = AuOpts_REMOUNT; ++ opts.sb_flags = *flags; ++ ++ /* parse it before aufs lock */ ++ err = au_opts_parse(sb, data, &opts); ++ if (unlikely(err)) ++ goto out_opts; ++ ++ sbinfo = au_sbi(sb); ++ inode = d_inode(root); ++ inode_lock(inode); ++ err = si_write_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (unlikely(err)) ++ goto out_mtx; ++ di_write_lock_child(root); ++ ++ /* au_opts_remount() may return an error */ ++ err = au_opts_remount(sb, &opts); ++ au_opts_free(&opts); ++ ++ if (au_ftest_opts(opts.flags, REFRESH)) ++ au_remount_refresh(sb, au_ftest_opts(opts.flags, REFRESH_IDOP)); ++ ++ if (au_ftest_opts(opts.flags, REFRESH_DYAOP)) { ++ mntflags = au_mntflags(sb); ++ do_dx = !!au_opt_test(mntflags, DIO); ++ au_dy_arefresh(do_dx); ++ } ++ ++ au_fhsm_wrote_all(sb, /*force*/1); /* ?? */ ++ aufs_write_unlock(root); ++ ++out_mtx: ++ inode_unlock(inode); ++out_opts: ++ free_page((unsigned long)opts.opt); ++out: ++ err = cvt_err(err); ++ AuTraceErr(err); ++ return err; ++} ++ ++static const struct super_operations aufs_sop = { ++ .alloc_inode = aufs_alloc_inode, ++ .destroy_inode = aufs_destroy_inode, ++ /* always deleting, no clearing */ ++ .drop_inode = generic_delete_inode, ++ .show_options = aufs_show_options, ++ .statfs = aufs_statfs, ++ .put_super = aufs_put_super, ++ .sync_fs = aufs_sync_fs, ++ .remount_fs = aufs_remount_fs ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int alloc_root(struct super_block *sb) ++{ ++ int err; ++ struct inode *inode; ++ struct dentry *root; ++ ++ err = -ENOMEM; ++ inode = au_iget_locked(sb, AUFS_ROOT_INO); ++ err = PTR_ERR(inode); ++ if (IS_ERR(inode)) ++ goto out; ++ ++ inode->i_op = aufs_iop + AuIop_DIR; /* with getattr by default */ ++ inode->i_fop = &aufs_dir_fop; ++ inode->i_mode = S_IFDIR; ++ set_nlink(inode, 2); ++ unlock_new_inode(inode); ++ ++ root = d_make_root(inode); ++ if (unlikely(!root)) ++ goto out; ++ err = PTR_ERR(root); ++ if (IS_ERR(root)) ++ goto out; ++ ++ err = au_di_init(root); ++ if (!err) { ++ sb->s_root = root; ++ return 0; /* success */ ++ } ++ dput(root); ++ ++out: ++ return err; ++} ++ ++static int aufs_fill_super(struct super_block *sb, void *raw_data, ++ int silent __maybe_unused) ++{ ++ int err; ++ struct au_opts opts = { ++ .opt = NULL ++ }; ++ struct au_sbinfo *sbinfo; ++ struct dentry *root; ++ struct inode *inode; ++ char *arg = raw_data; ++ ++ if (unlikely(!arg || !*arg)) { ++ err = -EINVAL; ++ pr_err("no arg\n"); ++ goto out; ++ } ++ ++ err = -ENOMEM; ++ opts.opt = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!opts.opt)) ++ goto out; ++ opts.max_opt = PAGE_SIZE / sizeof(*opts.opt); ++ opts.sb_flags = sb->s_flags; ++ ++ err = au_si_alloc(sb); ++ if (unlikely(err)) ++ goto out_opts; ++ sbinfo = au_sbi(sb); ++ ++ /* all timestamps always follow the ones on the branch */ ++ sb->s_flags |= MS_NOATIME | MS_NODIRATIME; ++ sb->s_op = &aufs_sop; ++ sb->s_d_op = &aufs_dop; ++ sb->s_magic = AUFS_SUPER_MAGIC; ++ sb->s_maxbytes = 0; ++ sb->s_stack_depth = 1; ++ au_export_init(sb); ++ au_xattr_init(sb); ++ ++ err = alloc_root(sb); ++ if (unlikely(err)) { ++ si_write_unlock(sb); ++ goto out_info; ++ } ++ root = sb->s_root; ++ inode = d_inode(root); ++ ++ /* ++ * actually we can parse options regardless aufs lock here. ++ * but at remount time, parsing must be done before aufs lock. ++ * so we follow the same rule. ++ */ ++ ii_write_lock_parent(inode); ++ aufs_write_unlock(root); ++ err = au_opts_parse(sb, arg, &opts); ++ if (unlikely(err)) ++ goto out_root; ++ ++ /* lock vfs_inode first, then aufs. */ ++ inode_lock(inode); ++ aufs_write_lock(root); ++ err = au_opts_mount(sb, &opts); ++ au_opts_free(&opts); ++ if (!err && au_ftest_si(sbinfo, NO_DREVAL)) { ++ sb->s_d_op = &aufs_dop_noreval; ++ pr_info("%pf\n", sb->s_d_op); ++ au_refresh_dop(root, /*force_reval*/0); ++ sbinfo->si_iop_array = aufs_iop_nogetattr; ++ au_refresh_iop(inode, /*force_getattr*/0); ++ } ++ aufs_write_unlock(root); ++ inode_unlock(inode); ++ if (!err) ++ goto out_opts; /* success */ ++ ++out_root: ++ dput(root); ++ sb->s_root = NULL; ++out_info: ++ kobject_put(&sbinfo->si_kobj); ++ sb->s_fs_info = NULL; ++out_opts: ++ free_page((unsigned long)opts.opt); ++out: ++ AuTraceErr(err); ++ err = cvt_err(err); ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct dentry *aufs_mount(struct file_system_type *fs_type, int flags, ++ const char *dev_name __maybe_unused, ++ void *raw_data) ++{ ++ struct dentry *root; ++ ++ /* all timestamps always follow the ones on the branch */ ++ /* mnt->mnt_flags |= MNT_NOATIME | MNT_NODIRATIME; */ ++ root = mount_nodev(fs_type, flags, raw_data, aufs_fill_super); ++ if (IS_ERR(root)) ++ goto out; ++ ++ au_sbilist_add(root->d_sb); ++ ++out: ++ return root; ++} ++ ++static void aufs_kill_sb(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ ++ sbinfo = au_sbi(sb); ++ if (sbinfo) { ++ au_sbilist_del(sb); ++ aufs_write_lock(sb->s_root); ++ au_fhsm_fin(sb); ++ if (sbinfo->si_wbr_create_ops->fin) ++ sbinfo->si_wbr_create_ops->fin(sb); ++ if (au_opt_test(sbinfo->si_mntflags, UDBA_HNOTIFY)) { ++ au_opt_set_udba(sbinfo->si_mntflags, UDBA_NONE); ++ au_remount_refresh(sb, /*do_idop*/0); ++ } ++ if (au_opt_test(sbinfo->si_mntflags, PLINK)) ++ au_plink_put(sb, /*verbose*/1); ++ au_xino_clr(sb); ++ au_dr_opt_flush(sb); ++ sbinfo->si_sb = NULL; ++ aufs_write_unlock(sb->s_root); ++ au_nwt_flush(&sbinfo->si_nowait); ++ } ++ kill_anon_super(sb); ++} ++ ++struct file_system_type aufs_fs_type = { ++ .name = AUFS_FSTYPE, ++ /* a race between rename and others */ ++ .fs_flags = FS_RENAME_DOES_D_MOVE, ++ .mount = aufs_mount, ++ .kill_sb = aufs_kill_sb, ++ /* no need to __module_get() and module_put(). */ ++ .owner = THIS_MODULE, ++}; +diff --git a/fs/aufs/super.h b/fs/aufs/super.h +new file mode 100644 +index 00000000..49ece660 +--- /dev/null ++++ b/fs/aufs/super.h +@@ -0,0 +1,617 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * super_block operations ++ */ ++ ++#ifndef __AUFS_SUPER_H__ ++#define __AUFS_SUPER_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include ++#include "hbl.h" ++#include "rwsem.h" ++#include "wkq.h" ++ ++/* policies to select one among multiple writable branches */ ++struct au_wbr_copyup_operations { ++ int (*copyup)(struct dentry *dentry); ++}; ++ ++#define AuWbr_DIR 1 /* target is a dir */ ++#define AuWbr_PARENT (1 << 1) /* always require a parent */ ++ ++#define au_ftest_wbr(flags, name) ((flags) & AuWbr_##name) ++#define au_fset_wbr(flags, name) { (flags) |= AuWbr_##name; } ++#define au_fclr_wbr(flags, name) { (flags) &= ~AuWbr_##name; } ++ ++struct au_wbr_create_operations { ++ int (*create)(struct dentry *dentry, unsigned int flags); ++ int (*init)(struct super_block *sb); ++ int (*fin)(struct super_block *sb); ++}; ++ ++struct au_wbr_mfs { ++ struct mutex mfs_lock; /* protect this structure */ ++ unsigned long mfs_jiffy; ++ unsigned long mfs_expire; ++ aufs_bindex_t mfs_bindex; ++ ++ unsigned long long mfsrr_bytes; ++ unsigned long long mfsrr_watermark; ++}; ++ ++#define AuPlink_NHASH 100 ++static inline int au_plink_hash(ino_t ino) ++{ ++ return ino % AuPlink_NHASH; ++} ++ ++/* File-based Hierarchical Storage Management */ ++struct au_fhsm { ++#ifdef CONFIG_AUFS_FHSM ++ /* allow only one process who can receive the notification */ ++ spinlock_t fhsm_spin; ++ pid_t fhsm_pid; ++ wait_queue_head_t fhsm_wqh; ++ atomic_t fhsm_readable; ++ ++ /* these are protected by si_rwsem */ ++ unsigned long fhsm_expire; ++ aufs_bindex_t fhsm_bottom; ++#endif ++}; ++ ++struct au_branch; ++struct au_sbinfo { ++ /* nowait tasks in the system-wide workqueue */ ++ struct au_nowait_tasks si_nowait; ++ ++ /* ++ * tried sb->s_umount, but failed due to the dependecy between i_mutex. ++ * rwsem for au_sbinfo is necessary. ++ */ ++ struct au_rwsem si_rwsem; ++ ++ /* ++ * dirty approach to protect sb->sb_inodes and ->s_files (gone) from ++ * remount. ++ */ ++ struct percpu_counter si_ninodes, si_nfiles; ++ ++ /* branch management */ ++ unsigned int si_generation; ++ ++ /* see AuSi_ flags */ ++ unsigned char au_si_status; ++ ++ aufs_bindex_t si_bbot; ++ ++ /* dirty trick to keep br_id plus */ ++ unsigned int si_last_br_id : ++ sizeof(aufs_bindex_t) * BITS_PER_BYTE - 1; ++ struct au_branch **si_branch; ++ ++ /* policy to select a writable branch */ ++ unsigned char si_wbr_copyup; ++ unsigned char si_wbr_create; ++ struct au_wbr_copyup_operations *si_wbr_copyup_ops; ++ struct au_wbr_create_operations *si_wbr_create_ops; ++ ++ /* round robin */ ++ atomic_t si_wbr_rr_next; ++ ++ /* most free space */ ++ struct au_wbr_mfs si_wbr_mfs; ++ ++ /* File-based Hierarchical Storage Management */ ++ struct au_fhsm si_fhsm; ++ ++ /* mount flags */ ++ /* include/asm-ia64/siginfo.h defines a macro named si_flags */ ++ unsigned int si_mntflags; ++ ++ /* external inode number (bitmap and translation table) */ ++ vfs_readf_t si_xread; ++ vfs_writef_t si_xwrite; ++ struct file *si_xib; ++ struct mutex si_xib_mtx; /* protect xib members */ ++ unsigned long *si_xib_buf; ++ unsigned long si_xib_last_pindex; ++ int si_xib_next_bit; ++ aufs_bindex_t si_xino_brid; ++ unsigned long si_xino_jiffy; ++ unsigned long si_xino_expire; ++ /* reserved for future use */ ++ /* unsigned long long si_xib_limit; */ /* Max xib file size */ ++ ++#ifdef CONFIG_AUFS_EXPORT ++ /* i_generation */ ++ struct file *si_xigen; ++ atomic_t si_xigen_next; ++#endif ++ ++ /* dirty trick to suppoer atomic_open */ ++ struct hlist_bl_head si_aopen; ++ ++ /* vdir parameters */ ++ unsigned long si_rdcache; /* max cache time in jiffies */ ++ unsigned int si_rdblk; /* deblk size */ ++ unsigned int si_rdhash; /* hash size */ ++ ++ /* ++ * If the number of whiteouts are larger than si_dirwh, leave all of ++ * them after au_whtmp_ren to reduce the cost of rmdir(2). ++ * future fsck.aufs or kernel thread will remove them later. ++ * Otherwise, remove all whiteouts and the dir in rmdir(2). ++ */ ++ unsigned int si_dirwh; ++ ++ /* pseudo_link list */ ++ struct hlist_bl_head si_plink[AuPlink_NHASH]; ++ wait_queue_head_t si_plink_wq; ++ spinlock_t si_plink_maint_lock; ++ pid_t si_plink_maint_pid; ++ ++ /* file list */ ++ struct hlist_bl_head si_files; ++ ++ /* with/without getattr, brother of sb->s_d_op */ ++ struct inode_operations *si_iop_array; ++ ++ /* ++ * sysfs and lifetime management. ++ * this is not a small structure and it may be a waste of memory in case ++ * of sysfs is disabled, particulary when many aufs-es are mounted. ++ * but using sysfs is majority. ++ */ ++ struct kobject si_kobj; ++#ifdef CONFIG_DEBUG_FS ++ struct dentry *si_dbgaufs; ++ struct dentry *si_dbgaufs_plink; ++ struct dentry *si_dbgaufs_xib; ++#ifdef CONFIG_AUFS_EXPORT ++ struct dentry *si_dbgaufs_xigen; ++#endif ++#endif ++ ++#ifdef CONFIG_AUFS_SBILIST ++ struct hlist_bl_node si_list; ++#endif ++ ++ /* dirty, necessary for unmounting, sysfs and sysrq */ ++ struct super_block *si_sb; ++}; ++ ++/* sbinfo status flags */ ++/* ++ * set true when refresh_dirs() failed at remount time. ++ * then try refreshing dirs at access time again. ++ * if it is false, refreshing dirs at access time is unnecessary ++ */ ++#define AuSi_FAILED_REFRESH_DIR 1 ++#define AuSi_FHSM (1 << 1) /* fhsm is active now */ ++#define AuSi_NO_DREVAL (1 << 2) /* disable all d_revalidate */ ++ ++#ifndef CONFIG_AUFS_FHSM ++#undef AuSi_FHSM ++#define AuSi_FHSM 0 ++#endif ++ ++static inline unsigned char au_do_ftest_si(struct au_sbinfo *sbi, ++ unsigned int flag) ++{ ++ AuRwMustAnyLock(&sbi->si_rwsem); ++ return sbi->au_si_status & flag; ++} ++#define au_ftest_si(sbinfo, name) au_do_ftest_si(sbinfo, AuSi_##name) ++#define au_fset_si(sbinfo, name) do { \ ++ AuRwMustWriteLock(&(sbinfo)->si_rwsem); \ ++ (sbinfo)->au_si_status |= AuSi_##name; \ ++} while (0) ++#define au_fclr_si(sbinfo, name) do { \ ++ AuRwMustWriteLock(&(sbinfo)->si_rwsem); \ ++ (sbinfo)->au_si_status &= ~AuSi_##name; \ ++} while (0) ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* policy to select one among writable branches */ ++#define AuWbrCopyup(sbinfo, ...) \ ++ ((sbinfo)->si_wbr_copyup_ops->copyup(__VA_ARGS__)) ++#define AuWbrCreate(sbinfo, ...) \ ++ ((sbinfo)->si_wbr_create_ops->create(__VA_ARGS__)) ++ ++/* flags for si_read_lock()/aufs_read_lock()/di_read_lock() */ ++#define AuLock_DW 1 /* write-lock dentry */ ++#define AuLock_IR (1 << 1) /* read-lock inode */ ++#define AuLock_IW (1 << 2) /* write-lock inode */ ++#define AuLock_FLUSH (1 << 3) /* wait for 'nowait' tasks */ ++#define AuLock_DIRS (1 << 4) /* target is a pair of dirs */ ++ /* except RENAME_EXCHANGE */ ++#define AuLock_NOPLM (1 << 5) /* return err in plm mode */ ++#define AuLock_NOPLMW (1 << 6) /* wait for plm mode ends */ ++#define AuLock_GEN (1 << 7) /* test digen/iigen */ ++#define au_ftest_lock(flags, name) ((flags) & AuLock_##name) ++#define au_fset_lock(flags, name) \ ++ do { (flags) |= AuLock_##name; } while (0) ++#define au_fclr_lock(flags, name) \ ++ do { (flags) &= ~AuLock_##name; } while (0) ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* super.c */ ++extern struct file_system_type aufs_fs_type; ++struct inode *au_iget_locked(struct super_block *sb, ino_t ino); ++typedef unsigned long long (*au_arraycb_t)(struct super_block *sb, void *array, ++ unsigned long long max, void *arg); ++void *au_array_alloc(unsigned long long *hint, au_arraycb_t cb, ++ struct super_block *sb, void *arg); ++struct inode **au_iarray_alloc(struct super_block *sb, unsigned long long *max); ++void au_iarray_free(struct inode **a, unsigned long long max); ++ ++/* sbinfo.c */ ++void au_si_free(struct kobject *kobj); ++int au_si_alloc(struct super_block *sb); ++int au_sbr_realloc(struct au_sbinfo *sbinfo, int nbr, int may_shrink); ++ ++unsigned int au_sigen_inc(struct super_block *sb); ++aufs_bindex_t au_new_br_id(struct super_block *sb); ++ ++int si_read_lock(struct super_block *sb, int flags); ++int si_write_lock(struct super_block *sb, int flags); ++int aufs_read_lock(struct dentry *dentry, int flags); ++void aufs_read_unlock(struct dentry *dentry, int flags); ++void aufs_write_lock(struct dentry *dentry); ++void aufs_write_unlock(struct dentry *dentry); ++int aufs_read_and_write_lock2(struct dentry *d1, struct dentry *d2, int flags); ++void aufs_read_and_write_unlock2(struct dentry *d1, struct dentry *d2); ++ ++/* wbr_policy.c */ ++extern struct au_wbr_copyup_operations au_wbr_copyup_ops[]; ++extern struct au_wbr_create_operations au_wbr_create_ops[]; ++int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst); ++int au_wbr_nonopq(struct dentry *dentry, aufs_bindex_t bindex); ++int au_wbr_do_copyup_bu(struct dentry *dentry, aufs_bindex_t btop); ++ ++/* mvdown.c */ ++int au_mvdown(struct dentry *dentry, struct aufs_mvdown __user *arg); ++ ++#ifdef CONFIG_AUFS_FHSM ++/* fhsm.c */ ++ ++static inline pid_t au_fhsm_pid(struct au_fhsm *fhsm) ++{ ++ pid_t pid; ++ ++ spin_lock(&fhsm->fhsm_spin); ++ pid = fhsm->fhsm_pid; ++ spin_unlock(&fhsm->fhsm_spin); ++ ++ return pid; ++} ++ ++void au_fhsm_wrote(struct super_block *sb, aufs_bindex_t bindex, int force); ++void au_fhsm_wrote_all(struct super_block *sb, int force); ++int au_fhsm_fd(struct super_block *sb, int oflags); ++int au_fhsm_br_alloc(struct au_branch *br); ++void au_fhsm_set_bottom(struct super_block *sb, aufs_bindex_t bindex); ++void au_fhsm_fin(struct super_block *sb); ++void au_fhsm_init(struct au_sbinfo *sbinfo); ++void au_fhsm_set(struct au_sbinfo *sbinfo, unsigned int sec); ++void au_fhsm_show(struct seq_file *seq, struct au_sbinfo *sbinfo); ++#else ++AuStubVoid(au_fhsm_wrote, struct super_block *sb, aufs_bindex_t bindex, ++ int force) ++AuStubVoid(au_fhsm_wrote_all, struct super_block *sb, int force) ++AuStub(int, au_fhsm_fd, return -EOPNOTSUPP, struct super_block *sb, int oflags) ++AuStub(pid_t, au_fhsm_pid, return 0, struct au_fhsm *fhsm) ++AuStubInt0(au_fhsm_br_alloc, struct au_branch *br) ++AuStubVoid(au_fhsm_set_bottom, struct super_block *sb, aufs_bindex_t bindex) ++AuStubVoid(au_fhsm_fin, struct super_block *sb) ++AuStubVoid(au_fhsm_init, struct au_sbinfo *sbinfo) ++AuStubVoid(au_fhsm_set, struct au_sbinfo *sbinfo, unsigned int sec) ++AuStubVoid(au_fhsm_show, struct seq_file *seq, struct au_sbinfo *sbinfo) ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct au_sbinfo *au_sbi(struct super_block *sb) ++{ ++ return sb->s_fs_info; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_EXPORT ++int au_test_nfsd(void); ++void au_export_init(struct super_block *sb); ++void au_xigen_inc(struct inode *inode); ++int au_xigen_new(struct inode *inode); ++int au_xigen_set(struct super_block *sb, struct path *path); ++void au_xigen_clr(struct super_block *sb); ++ ++static inline int au_busy_or_stale(void) ++{ ++ if (!au_test_nfsd()) ++ return -EBUSY; ++ return -ESTALE; ++} ++#else ++AuStubInt0(au_test_nfsd, void) ++AuStubVoid(au_export_init, struct super_block *sb) ++AuStubVoid(au_xigen_inc, struct inode *inode) ++AuStubInt0(au_xigen_new, struct inode *inode) ++AuStubInt0(au_xigen_set, struct super_block *sb, struct path *path) ++AuStubVoid(au_xigen_clr, struct super_block *sb) ++AuStub(int, au_busy_or_stale, return -EBUSY, void) ++#endif /* CONFIG_AUFS_EXPORT */ ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_SBILIST ++/* module.c */ ++extern struct hlist_bl_head au_sbilist; ++ ++static inline void au_sbilist_init(void) ++{ ++ INIT_HLIST_BL_HEAD(&au_sbilist); ++} ++ ++static inline void au_sbilist_add(struct super_block *sb) ++{ ++ au_hbl_add(&au_sbi(sb)->si_list, &au_sbilist); ++} ++ ++static inline void au_sbilist_del(struct super_block *sb) ++{ ++ au_hbl_del(&au_sbi(sb)->si_list, &au_sbilist); ++} ++ ++#ifdef CONFIG_AUFS_MAGIC_SYSRQ ++static inline void au_sbilist_lock(void) ++{ ++ hlist_bl_lock(&au_sbilist); ++} ++ ++static inline void au_sbilist_unlock(void) ++{ ++ hlist_bl_unlock(&au_sbilist); ++} ++#define AuGFP_SBILIST GFP_ATOMIC ++#else ++AuStubVoid(au_sbilist_lock, void) ++AuStubVoid(au_sbilist_unlock, void) ++#define AuGFP_SBILIST GFP_NOFS ++#endif /* CONFIG_AUFS_MAGIC_SYSRQ */ ++#else ++AuStubVoid(au_sbilist_init, void) ++AuStubVoid(au_sbilist_add, struct super_block *sb) ++AuStubVoid(au_sbilist_del, struct super_block *sb) ++AuStubVoid(au_sbilist_lock, void) ++AuStubVoid(au_sbilist_unlock, void) ++#define AuGFP_SBILIST GFP_NOFS ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline void dbgaufs_si_null(struct au_sbinfo *sbinfo) ++{ ++ /* ++ * This function is a dynamic '__init' function actually, ++ * so the tiny check for si_rwsem is unnecessary. ++ */ ++ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ ++#ifdef CONFIG_DEBUG_FS ++ sbinfo->si_dbgaufs = NULL; ++ sbinfo->si_dbgaufs_plink = NULL; ++ sbinfo->si_dbgaufs_xib = NULL; ++#ifdef CONFIG_AUFS_EXPORT ++ sbinfo->si_dbgaufs_xigen = NULL; ++#endif ++#endif ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* current->atomic_flags */ ++/* this value should never corrupt the ones defined in linux/sched.h */ ++#define PFA_AUFS 7 ++ ++TASK_PFA_TEST(AUFS, test_aufs) /* task_test_aufs */ ++TASK_PFA_SET(AUFS, aufs) /* task_set_aufs */ ++TASK_PFA_CLEAR(AUFS, aufs) /* task_clear_aufs */ ++ ++static inline int si_pid_test(struct super_block *sb) ++{ ++ return !!task_test_aufs(current); ++} ++ ++static inline void si_pid_clr(struct super_block *sb) ++{ ++ AuDebugOn(!task_test_aufs(current)); ++ task_clear_aufs(current); ++} ++ ++static inline void si_pid_set(struct super_block *sb) ++{ ++ AuDebugOn(task_test_aufs(current)); ++ task_set_aufs(current); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* lock superblock. mainly for entry point functions */ ++/* ++ * __si_read_lock, __si_write_lock, ++ * __si_read_unlock, __si_write_unlock, __si_downgrade_lock ++ */ ++AuSimpleRwsemFuncs(__si, struct super_block *sb, &au_sbi(sb)->si_rwsem); ++ ++#define SiMustNoWaiters(sb) AuRwMustNoWaiters(&au_sbi(sb)->si_rwsem) ++#define SiMustAnyLock(sb) AuRwMustAnyLock(&au_sbi(sb)->si_rwsem) ++#define SiMustWriteLock(sb) AuRwMustWriteLock(&au_sbi(sb)->si_rwsem) ++ ++static inline void si_noflush_read_lock(struct super_block *sb) ++{ ++ __si_read_lock(sb); ++ si_pid_set(sb); ++} ++ ++static inline int si_noflush_read_trylock(struct super_block *sb) ++{ ++ int locked; ++ ++ locked = __si_read_trylock(sb); ++ if (locked) ++ si_pid_set(sb); ++ return locked; ++} ++ ++static inline void si_noflush_write_lock(struct super_block *sb) ++{ ++ __si_write_lock(sb); ++ si_pid_set(sb); ++} ++ ++static inline int si_noflush_write_trylock(struct super_block *sb) ++{ ++ int locked; ++ ++ locked = __si_write_trylock(sb); ++ if (locked) ++ si_pid_set(sb); ++ return locked; ++} ++ ++#if 0 /* reserved */ ++static inline int si_read_trylock(struct super_block *sb, int flags) ++{ ++ if (au_ftest_lock(flags, FLUSH)) ++ au_nwt_flush(&au_sbi(sb)->si_nowait); ++ return si_noflush_read_trylock(sb); ++} ++#endif ++ ++static inline void si_read_unlock(struct super_block *sb) ++{ ++ si_pid_clr(sb); ++ __si_read_unlock(sb); ++} ++ ++#if 0 /* reserved */ ++static inline int si_write_trylock(struct super_block *sb, int flags) ++{ ++ if (au_ftest_lock(flags, FLUSH)) ++ au_nwt_flush(&au_sbi(sb)->si_nowait); ++ return si_noflush_write_trylock(sb); ++} ++#endif ++ ++static inline void si_write_unlock(struct super_block *sb) ++{ ++ si_pid_clr(sb); ++ __si_write_unlock(sb); ++} ++ ++#if 0 /* reserved */ ++static inline void si_downgrade_lock(struct super_block *sb) ++{ ++ __si_downgrade_lock(sb); ++} ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline aufs_bindex_t au_sbbot(struct super_block *sb) ++{ ++ SiMustAnyLock(sb); ++ return au_sbi(sb)->si_bbot; ++} ++ ++static inline unsigned int au_mntflags(struct super_block *sb) ++{ ++ SiMustAnyLock(sb); ++ return au_sbi(sb)->si_mntflags; ++} ++ ++static inline unsigned int au_sigen(struct super_block *sb) ++{ ++ SiMustAnyLock(sb); ++ return au_sbi(sb)->si_generation; ++} ++ ++static inline unsigned long long au_ninodes(struct super_block *sb) ++{ ++ s64 n = percpu_counter_sum(&au_sbi(sb)->si_ninodes); ++ ++ BUG_ON(n < 0); ++ return n; ++} ++ ++static inline void au_ninodes_inc(struct super_block *sb) ++{ ++ percpu_counter_inc(&au_sbi(sb)->si_ninodes); ++} ++ ++static inline void au_ninodes_dec(struct super_block *sb) ++{ ++ percpu_counter_dec(&au_sbi(sb)->si_ninodes); ++} ++ ++static inline unsigned long long au_nfiles(struct super_block *sb) ++{ ++ s64 n = percpu_counter_sum(&au_sbi(sb)->si_nfiles); ++ ++ BUG_ON(n < 0); ++ return n; ++} ++ ++static inline void au_nfiles_inc(struct super_block *sb) ++{ ++ percpu_counter_inc(&au_sbi(sb)->si_nfiles); ++} ++ ++static inline void au_nfiles_dec(struct super_block *sb) ++{ ++ percpu_counter_dec(&au_sbi(sb)->si_nfiles); ++} ++ ++static inline struct au_branch *au_sbr(struct super_block *sb, ++ aufs_bindex_t bindex) ++{ ++ SiMustAnyLock(sb); ++ return au_sbi(sb)->si_branch[0 + bindex]; ++} ++ ++static inline void au_xino_brid_set(struct super_block *sb, aufs_bindex_t brid) ++{ ++ SiMustWriteLock(sb); ++ au_sbi(sb)->si_xino_brid = brid; ++} ++ ++static inline aufs_bindex_t au_xino_brid(struct super_block *sb) ++{ ++ SiMustAnyLock(sb); ++ return au_sbi(sb)->si_xino_brid; ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_SUPER_H__ */ +diff --git a/fs/aufs/sysaufs.c b/fs/aufs/sysaufs.c +new file mode 100644 +index 00000000..798645ba +--- /dev/null ++++ b/fs/aufs/sysaufs.c +@@ -0,0 +1,92 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * sysfs interface and lifetime management ++ * they are necessary regardless sysfs is disabled. ++ */ ++ ++#include ++#include "aufs.h" ++ ++unsigned long sysaufs_si_mask; ++struct kset *sysaufs_kset; ++ ++#define AuSiAttr(_name) { \ ++ .attr = { .name = __stringify(_name), .mode = 0444 }, \ ++ .show = sysaufs_si_##_name, \ ++} ++ ++static struct sysaufs_si_attr sysaufs_si_attr_xi_path = AuSiAttr(xi_path); ++struct attribute *sysaufs_si_attrs[] = { ++ &sysaufs_si_attr_xi_path.attr, ++ NULL, ++}; ++ ++static const struct sysfs_ops au_sbi_ops = { ++ .show = sysaufs_si_show ++}; ++ ++static struct kobj_type au_sbi_ktype = { ++ .release = au_si_free, ++ .sysfs_ops = &au_sbi_ops, ++ .default_attrs = sysaufs_si_attrs ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++int sysaufs_si_init(struct au_sbinfo *sbinfo) ++{ ++ int err; ++ ++ sbinfo->si_kobj.kset = sysaufs_kset; ++ /* cf. sysaufs_name() */ ++ err = kobject_init_and_add ++ (&sbinfo->si_kobj, &au_sbi_ktype, /*&sysaufs_kset->kobj*/NULL, ++ SysaufsSiNamePrefix "%lx", sysaufs_si_id(sbinfo)); ++ ++ return err; ++} ++ ++void sysaufs_fin(void) ++{ ++ sysfs_remove_group(&sysaufs_kset->kobj, sysaufs_attr_group); ++ kset_unregister(sysaufs_kset); ++} ++ ++int __init sysaufs_init(void) ++{ ++ int err; ++ ++ do { ++ get_random_bytes(&sysaufs_si_mask, sizeof(sysaufs_si_mask)); ++ } while (!sysaufs_si_mask); ++ ++ err = -EINVAL; ++ sysaufs_kset = kset_create_and_add(AUFS_NAME, NULL, fs_kobj); ++ if (unlikely(!sysaufs_kset)) ++ goto out; ++ err = PTR_ERR(sysaufs_kset); ++ if (IS_ERR(sysaufs_kset)) ++ goto out; ++ err = sysfs_create_group(&sysaufs_kset->kobj, sysaufs_attr_group); ++ if (unlikely(err)) ++ kset_unregister(sysaufs_kset); ++ ++out: ++ return err; ++} +diff --git a/fs/aufs/sysaufs.h b/fs/aufs/sysaufs.h +new file mode 100644 +index 00000000..50aca1dc +--- /dev/null ++++ b/fs/aufs/sysaufs.h +@@ -0,0 +1,101 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * sysfs interface and mount lifetime management ++ */ ++ ++#ifndef __SYSAUFS_H__ ++#define __SYSAUFS_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include "module.h" ++ ++struct super_block; ++struct au_sbinfo; ++ ++struct sysaufs_si_attr { ++ struct attribute attr; ++ int (*show)(struct seq_file *seq, struct super_block *sb); ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* sysaufs.c */ ++extern unsigned long sysaufs_si_mask; ++extern struct kset *sysaufs_kset; ++extern struct attribute *sysaufs_si_attrs[]; ++int sysaufs_si_init(struct au_sbinfo *sbinfo); ++int __init sysaufs_init(void); ++void sysaufs_fin(void); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* some people doesn't like to show a pointer in kernel */ ++static inline unsigned long sysaufs_si_id(struct au_sbinfo *sbinfo) ++{ ++ return sysaufs_si_mask ^ (unsigned long)sbinfo; ++} ++ ++#define SysaufsSiNamePrefix "si_" ++#define SysaufsSiNameLen (sizeof(SysaufsSiNamePrefix) + 16) ++static inline void sysaufs_name(struct au_sbinfo *sbinfo, char *name) ++{ ++ snprintf(name, SysaufsSiNameLen, SysaufsSiNamePrefix "%lx", ++ sysaufs_si_id(sbinfo)); ++} ++ ++struct au_branch; ++#ifdef CONFIG_SYSFS ++/* sysfs.c */ ++extern struct attribute_group *sysaufs_attr_group; ++ ++int sysaufs_si_xi_path(struct seq_file *seq, struct super_block *sb); ++ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr, ++ char *buf); ++long au_brinfo_ioctl(struct file *file, unsigned long arg); ++#ifdef CONFIG_COMPAT ++long au_brinfo_compat_ioctl(struct file *file, unsigned long arg); ++#endif ++ ++void sysaufs_br_init(struct au_branch *br); ++void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex); ++void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex); ++ ++#define sysaufs_brs_init() do {} while (0) ++ ++#else ++#define sysaufs_attr_group NULL ++ ++AuStubInt0(sysaufs_si_xi_path, struct seq_file *seq, struct super_block *sb) ++AuStub(ssize_t, sysaufs_si_show, return 0, struct kobject *kobj, ++ struct attribute *attr, char *buf) ++AuStubVoid(sysaufs_br_init, struct au_branch *br) ++AuStubVoid(sysaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex) ++AuStubVoid(sysaufs_brs_del, struct super_block *sb, aufs_bindex_t bindex) ++ ++static inline void sysaufs_brs_init(void) ++{ ++ sysaufs_brs = 0; ++} ++ ++#endif /* CONFIG_SYSFS */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __SYSAUFS_H__ */ +diff --git a/fs/aufs/sysfs.c b/fs/aufs/sysfs.c +new file mode 100644 +index 00000000..18a465bd +--- /dev/null ++++ b/fs/aufs/sysfs.c +@@ -0,0 +1,372 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * sysfs interface ++ */ ++ ++#include ++#include ++#include "aufs.h" ++ ++#ifdef CONFIG_AUFS_FS_MODULE ++/* this entry violates the "one line per file" policy of sysfs */ ++static ssize_t config_show(struct kobject *kobj, struct kobj_attribute *attr, ++ char *buf) ++{ ++ ssize_t err; ++ static char *conf = ++/* this file is generated at compiling */ ++#include "conf.str" ++ ; ++ ++ err = snprintf(buf, PAGE_SIZE, conf); ++ if (unlikely(err >= PAGE_SIZE)) ++ err = -EFBIG; ++ return err; ++} ++ ++static struct kobj_attribute au_config_attr = __ATTR_RO(config); ++#endif ++ ++static struct attribute *au_attr[] = { ++#ifdef CONFIG_AUFS_FS_MODULE ++ &au_config_attr.attr, ++#endif ++ NULL, /* need to NULL terminate the list of attributes */ ++}; ++ ++static struct attribute_group sysaufs_attr_group_body = { ++ .attrs = au_attr ++}; ++ ++struct attribute_group *sysaufs_attr_group = &sysaufs_attr_group_body; ++ ++/* ---------------------------------------------------------------------- */ ++ ++int sysaufs_si_xi_path(struct seq_file *seq, struct super_block *sb) ++{ ++ int err; ++ ++ SiMustAnyLock(sb); ++ ++ err = 0; ++ if (au_opt_test(au_mntflags(sb), XINO)) { ++ err = au_xino_path(seq, au_sbi(sb)->si_xib); ++ seq_putc(seq, '\n'); ++ } ++ return err; ++} ++ ++/* ++ * the lifetime of branch is independent from the entry under sysfs. ++ * sysfs handles the lifetime of the entry, and never call ->show() after it is ++ * unlinked. ++ */ ++static int sysaufs_si_br(struct seq_file *seq, struct super_block *sb, ++ aufs_bindex_t bindex, int idx) ++{ ++ int err; ++ struct path path; ++ struct dentry *root; ++ struct au_branch *br; ++ au_br_perm_str_t perm; ++ ++ AuDbg("b%d\n", bindex); ++ ++ err = 0; ++ root = sb->s_root; ++ di_read_lock_parent(root, !AuLock_IR); ++ br = au_sbr(sb, bindex); ++ ++ switch (idx) { ++ case AuBrSysfs_BR: ++ path.mnt = au_br_mnt(br); ++ path.dentry = au_h_dptr(root, bindex); ++ err = au_seq_path(seq, &path); ++ if (!err) { ++ au_optstr_br_perm(&perm, br->br_perm); ++ seq_printf(seq, "=%s\n", perm.a); ++ } ++ break; ++ case AuBrSysfs_BRID: ++ seq_printf(seq, "%d\n", br->br_id); ++ break; ++ } ++ di_read_unlock(root, !AuLock_IR); ++ if (unlikely(err || seq_has_overflowed(seq))) ++ err = -E2BIG; ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct seq_file *au_seq(char *p, ssize_t len) ++{ ++ struct seq_file *seq; ++ ++ seq = kzalloc(sizeof(*seq), GFP_NOFS); ++ if (seq) { ++ /* mutex_init(&seq.lock); */ ++ seq->buf = p; ++ seq->size = len; ++ return seq; /* success */ ++ } ++ ++ seq = ERR_PTR(-ENOMEM); ++ return seq; ++} ++ ++#define SysaufsBr_PREFIX "br" ++#define SysaufsBrid_PREFIX "brid" ++ ++/* todo: file size may exceed PAGE_SIZE */ ++ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr, ++ char *buf) ++{ ++ ssize_t err; ++ int idx; ++ long l; ++ aufs_bindex_t bbot; ++ struct au_sbinfo *sbinfo; ++ struct super_block *sb; ++ struct seq_file *seq; ++ char *name; ++ struct attribute **cattr; ++ ++ sbinfo = container_of(kobj, struct au_sbinfo, si_kobj); ++ sb = sbinfo->si_sb; ++ ++ /* ++ * prevent a race condition between sysfs and aufs. ++ * for instance, sysfs_file_read() calls sysfs_get_active_two() which ++ * prohibits maintaining the sysfs entries. ++ * hew we acquire read lock after sysfs_get_active_two(). ++ * on the other hand, the remount process may maintain the sysfs/aufs ++ * entries after acquiring write lock. ++ * it can cause a deadlock. ++ * simply we gave up processing read here. ++ */ ++ err = -EBUSY; ++ if (unlikely(!si_noflush_read_trylock(sb))) ++ goto out; ++ ++ seq = au_seq(buf, PAGE_SIZE); ++ err = PTR_ERR(seq); ++ if (IS_ERR(seq)) ++ goto out_unlock; ++ ++ name = (void *)attr->name; ++ cattr = sysaufs_si_attrs; ++ while (*cattr) { ++ if (!strcmp(name, (*cattr)->name)) { ++ err = container_of(*cattr, struct sysaufs_si_attr, attr) ++ ->show(seq, sb); ++ goto out_seq; ++ } ++ cattr++; ++ } ++ ++ if (!strncmp(name, SysaufsBrid_PREFIX, ++ sizeof(SysaufsBrid_PREFIX) - 1)) { ++ idx = AuBrSysfs_BRID; ++ name += sizeof(SysaufsBrid_PREFIX) - 1; ++ } else if (!strncmp(name, SysaufsBr_PREFIX, ++ sizeof(SysaufsBr_PREFIX) - 1)) { ++ idx = AuBrSysfs_BR; ++ name += sizeof(SysaufsBr_PREFIX) - 1; ++ } else ++ BUG(); ++ ++ err = kstrtol(name, 10, &l); ++ if (!err) { ++ bbot = au_sbbot(sb); ++ if (l <= bbot) ++ err = sysaufs_si_br(seq, sb, (aufs_bindex_t)l, idx); ++ else ++ err = -ENOENT; ++ } ++ ++out_seq: ++ if (!err) { ++ err = seq->count; ++ /* sysfs limit */ ++ if (unlikely(err == PAGE_SIZE)) ++ err = -EFBIG; ++ } ++ kfree(seq); ++out_unlock: ++ si_read_unlock(sb); ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_brinfo(struct super_block *sb, union aufs_brinfo __user *arg) ++{ ++ int err; ++ int16_t brid; ++ aufs_bindex_t bindex, bbot; ++ size_t sz; ++ char *buf; ++ struct seq_file *seq; ++ struct au_branch *br; ++ ++ si_read_lock(sb, AuLock_FLUSH); ++ bbot = au_sbbot(sb); ++ err = bbot + 1; ++ if (!arg) ++ goto out; ++ ++ err = -ENOMEM; ++ buf = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!buf)) ++ goto out; ++ ++ seq = au_seq(buf, PAGE_SIZE); ++ err = PTR_ERR(seq); ++ if (IS_ERR(seq)) ++ goto out_buf; ++ ++ sz = sizeof(*arg) - offsetof(union aufs_brinfo, path); ++ for (bindex = 0; bindex <= bbot; bindex++, arg++) { ++ err = !access_ok(VERIFY_WRITE, arg, sizeof(*arg)); ++ if (unlikely(err)) ++ break; ++ ++ br = au_sbr(sb, bindex); ++ brid = br->br_id; ++ BUILD_BUG_ON(sizeof(brid) != sizeof(arg->id)); ++ err = __put_user(brid, &arg->id); ++ if (unlikely(err)) ++ break; ++ ++ BUILD_BUG_ON(sizeof(br->br_perm) != sizeof(arg->perm)); ++ err = __put_user(br->br_perm, &arg->perm); ++ if (unlikely(err)) ++ break; ++ ++ err = au_seq_path(seq, &br->br_path); ++ if (unlikely(err)) ++ break; ++ seq_putc(seq, '\0'); ++ if (!seq_has_overflowed(seq)) { ++ err = copy_to_user(arg->path, seq->buf, seq->count); ++ seq->count = 0; ++ if (unlikely(err)) ++ break; ++ } else { ++ err = -E2BIG; ++ goto out_seq; ++ } ++ } ++ if (unlikely(err)) ++ err = -EFAULT; ++ ++out_seq: ++ kfree(seq); ++out_buf: ++ free_page((unsigned long)buf); ++out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++long au_brinfo_ioctl(struct file *file, unsigned long arg) ++{ ++ return au_brinfo(file->f_path.dentry->d_sb, (void __user *)arg); ++} ++ ++#ifdef CONFIG_COMPAT ++long au_brinfo_compat_ioctl(struct file *file, unsigned long arg) ++{ ++ return au_brinfo(file->f_path.dentry->d_sb, compat_ptr(arg)); ++} ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++void sysaufs_br_init(struct au_branch *br) ++{ ++ int i; ++ struct au_brsysfs *br_sysfs; ++ struct attribute *attr; ++ ++ br_sysfs = br->br_sysfs; ++ for (i = 0; i < ARRAY_SIZE(br->br_sysfs); i++) { ++ attr = &br_sysfs->attr; ++ sysfs_attr_init(attr); ++ attr->name = br_sysfs->name; ++ attr->mode = 0444; ++ br_sysfs++; ++ } ++} ++ ++void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ struct au_branch *br; ++ struct kobject *kobj; ++ struct au_brsysfs *br_sysfs; ++ int i; ++ aufs_bindex_t bbot; ++ ++ if (!sysaufs_brs) ++ return; ++ ++ kobj = &au_sbi(sb)->si_kobj; ++ bbot = au_sbbot(sb); ++ for (; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ br_sysfs = br->br_sysfs; ++ for (i = 0; i < ARRAY_SIZE(br->br_sysfs); i++) { ++ sysfs_remove_file(kobj, &br_sysfs->attr); ++ br_sysfs++; ++ } ++ } ++} ++ ++void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ int err, i; ++ aufs_bindex_t bbot; ++ struct kobject *kobj; ++ struct au_branch *br; ++ struct au_brsysfs *br_sysfs; ++ ++ if (!sysaufs_brs) ++ return; ++ ++ kobj = &au_sbi(sb)->si_kobj; ++ bbot = au_sbbot(sb); ++ for (; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ br_sysfs = br->br_sysfs; ++ snprintf(br_sysfs[AuBrSysfs_BR].name, sizeof(br_sysfs->name), ++ SysaufsBr_PREFIX "%d", bindex); ++ snprintf(br_sysfs[AuBrSysfs_BRID].name, sizeof(br_sysfs->name), ++ SysaufsBrid_PREFIX "%d", bindex); ++ for (i = 0; i < ARRAY_SIZE(br->br_sysfs); i++) { ++ err = sysfs_create_file(kobj, &br_sysfs->attr); ++ if (unlikely(err)) ++ pr_warn("failed %s under sysfs(%d)\n", ++ br_sysfs->name, err); ++ br_sysfs++; ++ } ++ } ++} +diff --git a/fs/aufs/sysrq.c b/fs/aufs/sysrq.c +new file mode 100644 +index 00000000..69b1c83d +--- /dev/null ++++ b/fs/aufs/sysrq.c +@@ -0,0 +1,159 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * magic sysrq hanlder ++ */ ++ ++/* #include */ ++#include ++#include "aufs.h" ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void sysrq_sb(struct super_block *sb) ++{ ++ char *plevel; ++ struct au_sbinfo *sbinfo; ++ struct file *file; ++ struct hlist_bl_head *files; ++ struct hlist_bl_node *pos; ++ struct au_finfo *finfo; ++ ++ plevel = au_plevel; ++ au_plevel = KERN_WARNING; ++ ++ /* since we define pr_fmt, call printk directly */ ++#define pr(str) printk(KERN_WARNING AUFS_NAME ": " str) ++ ++ sbinfo = au_sbi(sb); ++ printk(KERN_WARNING "si=%lx\n", sysaufs_si_id(sbinfo)); ++ pr("superblock\n"); ++ au_dpri_sb(sb); ++ ++#if 0 ++ pr("root dentry\n"); ++ au_dpri_dentry(sb->s_root); ++ pr("root inode\n"); ++ au_dpri_inode(d_inode(sb->s_root)); ++#endif ++ ++#if 0 ++ do { ++ int err, i, j, ndentry; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ ++ err = au_dpages_init(&dpages, GFP_ATOMIC); ++ if (unlikely(err)) ++ break; ++ err = au_dcsub_pages(&dpages, sb->s_root, NULL, NULL); ++ if (!err) ++ for (i = 0; i < dpages.ndpage; i++) { ++ dpage = dpages.dpages + i; ++ ndentry = dpage->ndentry; ++ for (j = 0; j < ndentry; j++) ++ au_dpri_dentry(dpage->dentries[j]); ++ } ++ au_dpages_free(&dpages); ++ } while (0); ++#endif ++ ++#if 1 ++ { ++ struct inode *i; ++ ++ pr("isolated inode\n"); ++ spin_lock(&sb->s_inode_list_lock); ++ list_for_each_entry(i, &sb->s_inodes, i_sb_list) { ++ spin_lock(&i->i_lock); ++ if (1 || hlist_empty(&i->i_dentry)) ++ au_dpri_inode(i); ++ spin_unlock(&i->i_lock); ++ } ++ spin_unlock(&sb->s_inode_list_lock); ++ } ++#endif ++ pr("files\n"); ++ files = &au_sbi(sb)->si_files; ++ hlist_bl_lock(files); ++ hlist_bl_for_each_entry(finfo, pos, files, fi_hlist) { ++ umode_t mode; ++ ++ file = finfo->fi_file; ++ mode = file_inode(file)->i_mode; ++ if (!special_file(mode)) ++ au_dpri_file(file); ++ } ++ hlist_bl_unlock(files); ++ pr("done\n"); ++ ++#undef pr ++ au_plevel = plevel; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* module parameter */ ++static char *aufs_sysrq_key = "a"; ++module_param_named(sysrq, aufs_sysrq_key, charp, 0444); ++MODULE_PARM_DESC(sysrq, "MagicSysRq key for " AUFS_NAME); ++ ++static void au_sysrq(int key __maybe_unused) ++{ ++ struct au_sbinfo *sbinfo; ++ struct hlist_bl_node *pos; ++ ++ lockdep_off(); ++ au_sbilist_lock(); ++ hlist_bl_for_each_entry(sbinfo, pos, &au_sbilist, si_list) ++ sysrq_sb(sbinfo->si_sb); ++ au_sbilist_unlock(); ++ lockdep_on(); ++} ++ ++static struct sysrq_key_op au_sysrq_op = { ++ .handler = au_sysrq, ++ .help_msg = "Aufs", ++ .action_msg = "Aufs", ++ .enable_mask = SYSRQ_ENABLE_DUMP ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++int __init au_sysrq_init(void) ++{ ++ int err; ++ char key; ++ ++ err = -1; ++ key = *aufs_sysrq_key; ++ if ('a' <= key && key <= 'z') ++ err = register_sysrq_key(key, &au_sysrq_op); ++ if (unlikely(err)) ++ pr_err("err %d, sysrq=%c\n", err, key); ++ return err; ++} ++ ++void au_sysrq_fin(void) ++{ ++ int err; ++ ++ err = unregister_sysrq_key(*aufs_sysrq_key, &au_sysrq_op); ++ if (unlikely(err)) ++ pr_err("err %d (ignored)\n", err); ++} +diff --git a/fs/aufs/vdir.c b/fs/aufs/vdir.c +new file mode 100644 +index 00000000..6db51723 +--- /dev/null ++++ b/fs/aufs/vdir.c +@@ -0,0 +1,893 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * virtual or vertical directory ++ */ ++ ++#include "aufs.h" ++ ++static unsigned int calc_size(int nlen) ++{ ++ return ALIGN(sizeof(struct au_vdir_de) + nlen, sizeof(ino_t)); ++} ++ ++static int set_deblk_end(union au_vdir_deblk_p *p, ++ union au_vdir_deblk_p *deblk_end) ++{ ++ if (calc_size(0) <= deblk_end->deblk - p->deblk) { ++ p->de->de_str.len = 0; ++ /* smp_mb(); */ ++ return 0; ++ } ++ return -1; /* error */ ++} ++ ++/* returns true or false */ ++static int is_deblk_end(union au_vdir_deblk_p *p, ++ union au_vdir_deblk_p *deblk_end) ++{ ++ if (calc_size(0) <= deblk_end->deblk - p->deblk) ++ return !p->de->de_str.len; ++ return 1; ++} ++ ++static unsigned char *last_deblk(struct au_vdir *vdir) ++{ ++ return vdir->vd_deblk[vdir->vd_nblk - 1]; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* estimate the appropriate size for name hash table */ ++unsigned int au_rdhash_est(loff_t sz) ++{ ++ unsigned int n; ++ ++ n = UINT_MAX; ++ sz >>= 10; ++ if (sz < n) ++ n = sz; ++ if (sz < AUFS_RDHASH_DEF) ++ n = AUFS_RDHASH_DEF; ++ /* pr_info("n %u\n", n); */ ++ return n; ++} ++ ++/* ++ * the allocated memory has to be freed by ++ * au_nhash_wh_free() or au_nhash_de_free(). ++ */ ++int au_nhash_alloc(struct au_nhash *nhash, unsigned int num_hash, gfp_t gfp) ++{ ++ struct hlist_head *head; ++ unsigned int u; ++ size_t sz; ++ ++ sz = sizeof(*nhash->nh_head) * num_hash; ++ head = kmalloc(sz, gfp); ++ if (head) { ++ nhash->nh_num = num_hash; ++ nhash->nh_head = head; ++ for (u = 0; u < num_hash; u++) ++ INIT_HLIST_HEAD(head++); ++ return 0; /* success */ ++ } ++ ++ return -ENOMEM; ++} ++ ++static void nhash_count(struct hlist_head *head) ++{ ++#if 0 ++ unsigned long n; ++ struct hlist_node *pos; ++ ++ n = 0; ++ hlist_for_each(pos, head) ++ n++; ++ pr_info("%lu\n", n); ++#endif ++} ++ ++static void au_nhash_wh_do_free(struct hlist_head *head) ++{ ++ struct au_vdir_wh *pos; ++ struct hlist_node *node; ++ ++ hlist_for_each_entry_safe(pos, node, head, wh_hash) ++ kfree(pos); ++} ++ ++static void au_nhash_de_do_free(struct hlist_head *head) ++{ ++ struct au_vdir_dehstr *pos; ++ struct hlist_node *node; ++ ++ hlist_for_each_entry_safe(pos, node, head, hash) ++ au_cache_free_vdir_dehstr(pos); ++} ++ ++static void au_nhash_do_free(struct au_nhash *nhash, ++ void (*free)(struct hlist_head *head)) ++{ ++ unsigned int n; ++ struct hlist_head *head; ++ ++ n = nhash->nh_num; ++ if (!n) ++ return; ++ ++ head = nhash->nh_head; ++ while (n-- > 0) { ++ nhash_count(head); ++ free(head++); ++ } ++ kfree(nhash->nh_head); ++} ++ ++void au_nhash_wh_free(struct au_nhash *whlist) ++{ ++ au_nhash_do_free(whlist, au_nhash_wh_do_free); ++} ++ ++static void au_nhash_de_free(struct au_nhash *delist) ++{ ++ au_nhash_do_free(delist, au_nhash_de_do_free); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt, ++ int limit) ++{ ++ int num; ++ unsigned int u, n; ++ struct hlist_head *head; ++ struct au_vdir_wh *pos; ++ ++ num = 0; ++ n = whlist->nh_num; ++ head = whlist->nh_head; ++ for (u = 0; u < n; u++, head++) ++ hlist_for_each_entry(pos, head, wh_hash) ++ if (pos->wh_bindex == btgt && ++num > limit) ++ return 1; ++ return 0; ++} ++ ++static struct hlist_head *au_name_hash(struct au_nhash *nhash, ++ unsigned char *name, ++ unsigned int len) ++{ ++ unsigned int v; ++ /* const unsigned int magic_bit = 12; */ ++ ++ AuDebugOn(!nhash->nh_num || !nhash->nh_head); ++ ++ v = 0; ++ if (len > 8) ++ len = 8; ++ while (len--) ++ v += *name++; ++ /* v = hash_long(v, magic_bit); */ ++ v %= nhash->nh_num; ++ return nhash->nh_head + v; ++} ++ ++static int au_nhash_test_name(struct au_vdir_destr *str, const char *name, ++ int nlen) ++{ ++ return str->len == nlen && !memcmp(str->name, name, nlen); ++} ++ ++/* returns found or not */ ++int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int nlen) ++{ ++ struct hlist_head *head; ++ struct au_vdir_wh *pos; ++ struct au_vdir_destr *str; ++ ++ head = au_name_hash(whlist, name, nlen); ++ hlist_for_each_entry(pos, head, wh_hash) { ++ str = &pos->wh_str; ++ AuDbg("%.*s\n", str->len, str->name); ++ if (au_nhash_test_name(str, name, nlen)) ++ return 1; ++ } ++ return 0; ++} ++ ++/* returns found(true) or not */ ++static int test_known(struct au_nhash *delist, char *name, int nlen) ++{ ++ struct hlist_head *head; ++ struct au_vdir_dehstr *pos; ++ struct au_vdir_destr *str; ++ ++ head = au_name_hash(delist, name, nlen); ++ hlist_for_each_entry(pos, head, hash) { ++ str = pos->str; ++ AuDbg("%.*s\n", str->len, str->name); ++ if (au_nhash_test_name(str, name, nlen)) ++ return 1; ++ } ++ return 0; ++} ++ ++static void au_shwh_init_wh(struct au_vdir_wh *wh, ino_t ino, ++ unsigned char d_type) ++{ ++#ifdef CONFIG_AUFS_SHWH ++ wh->wh_ino = ino; ++ wh->wh_type = d_type; ++#endif ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_nhash_append_wh(struct au_nhash *whlist, char *name, int nlen, ino_t ino, ++ unsigned int d_type, aufs_bindex_t bindex, ++ unsigned char shwh) ++{ ++ int err; ++ struct au_vdir_destr *str; ++ struct au_vdir_wh *wh; ++ ++ AuDbg("%.*s\n", nlen, name); ++ AuDebugOn(!whlist->nh_num || !whlist->nh_head); ++ ++ err = -ENOMEM; ++ wh = kmalloc(sizeof(*wh) + nlen, GFP_NOFS); ++ if (unlikely(!wh)) ++ goto out; ++ ++ err = 0; ++ wh->wh_bindex = bindex; ++ if (shwh) ++ au_shwh_init_wh(wh, ino, d_type); ++ str = &wh->wh_str; ++ str->len = nlen; ++ memcpy(str->name, name, nlen); ++ hlist_add_head(&wh->wh_hash, au_name_hash(whlist, name, nlen)); ++ /* smp_mb(); */ ++ ++out: ++ return err; ++} ++ ++static int append_deblk(struct au_vdir *vdir) ++{ ++ int err; ++ unsigned long ul; ++ const unsigned int deblk_sz = vdir->vd_deblk_sz; ++ union au_vdir_deblk_p p, deblk_end; ++ unsigned char **o; ++ ++ err = -ENOMEM; ++ o = au_krealloc(vdir->vd_deblk, sizeof(*o) * (vdir->vd_nblk + 1), ++ GFP_NOFS, /*may_shrink*/0); ++ if (unlikely(!o)) ++ goto out; ++ ++ vdir->vd_deblk = o; ++ p.deblk = kmalloc(deblk_sz, GFP_NOFS); ++ if (p.deblk) { ++ ul = vdir->vd_nblk++; ++ vdir->vd_deblk[ul] = p.deblk; ++ vdir->vd_last.ul = ul; ++ vdir->vd_last.p.deblk = p.deblk; ++ deblk_end.deblk = p.deblk + deblk_sz; ++ err = set_deblk_end(&p, &deblk_end); ++ } ++ ++out: ++ return err; ++} ++ ++static int append_de(struct au_vdir *vdir, char *name, int nlen, ino_t ino, ++ unsigned int d_type, struct au_nhash *delist) ++{ ++ int err; ++ unsigned int sz; ++ const unsigned int deblk_sz = vdir->vd_deblk_sz; ++ union au_vdir_deblk_p p, *room, deblk_end; ++ struct au_vdir_dehstr *dehstr; ++ ++ p.deblk = last_deblk(vdir); ++ deblk_end.deblk = p.deblk + deblk_sz; ++ room = &vdir->vd_last.p; ++ AuDebugOn(room->deblk < p.deblk || deblk_end.deblk <= room->deblk ++ || !is_deblk_end(room, &deblk_end)); ++ ++ sz = calc_size(nlen); ++ if (unlikely(sz > deblk_end.deblk - room->deblk)) { ++ err = append_deblk(vdir); ++ if (unlikely(err)) ++ goto out; ++ ++ p.deblk = last_deblk(vdir); ++ deblk_end.deblk = p.deblk + deblk_sz; ++ /* smp_mb(); */ ++ AuDebugOn(room->deblk != p.deblk); ++ } ++ ++ err = -ENOMEM; ++ dehstr = au_cache_alloc_vdir_dehstr(); ++ if (unlikely(!dehstr)) ++ goto out; ++ ++ dehstr->str = &room->de->de_str; ++ hlist_add_head(&dehstr->hash, au_name_hash(delist, name, nlen)); ++ room->de->de_ino = ino; ++ room->de->de_type = d_type; ++ room->de->de_str.len = nlen; ++ memcpy(room->de->de_str.name, name, nlen); ++ ++ err = 0; ++ room->deblk += sz; ++ if (unlikely(set_deblk_end(room, &deblk_end))) ++ err = append_deblk(vdir); ++ /* smp_mb(); */ ++ ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_vdir_free(struct au_vdir *vdir) ++{ ++ unsigned char **deblk; ++ ++ deblk = vdir->vd_deblk; ++ while (vdir->vd_nblk--) ++ kfree(*deblk++); ++ kfree(vdir->vd_deblk); ++ au_cache_free_vdir(vdir); ++} ++ ++static struct au_vdir *alloc_vdir(struct file *file) ++{ ++ struct au_vdir *vdir; ++ struct super_block *sb; ++ int err; ++ ++ sb = file->f_path.dentry->d_sb; ++ SiMustAnyLock(sb); ++ ++ err = -ENOMEM; ++ vdir = au_cache_alloc_vdir(); ++ if (unlikely(!vdir)) ++ goto out; ++ ++ vdir->vd_deblk = kzalloc(sizeof(*vdir->vd_deblk), GFP_NOFS); ++ if (unlikely(!vdir->vd_deblk)) ++ goto out_free; ++ ++ vdir->vd_deblk_sz = au_sbi(sb)->si_rdblk; ++ if (!vdir->vd_deblk_sz) { ++ /* estimate the appropriate size for deblk */ ++ vdir->vd_deblk_sz = au_dir_size(file, /*dentry*/NULL); ++ /* pr_info("vd_deblk_sz %u\n", vdir->vd_deblk_sz); */ ++ } ++ vdir->vd_nblk = 0; ++ vdir->vd_version = 0; ++ vdir->vd_jiffy = 0; ++ err = append_deblk(vdir); ++ if (!err) ++ return vdir; /* success */ ++ ++ kfree(vdir->vd_deblk); ++ ++out_free: ++ au_cache_free_vdir(vdir); ++out: ++ vdir = ERR_PTR(err); ++ return vdir; ++} ++ ++static int reinit_vdir(struct au_vdir *vdir) ++{ ++ int err; ++ union au_vdir_deblk_p p, deblk_end; ++ ++ while (vdir->vd_nblk > 1) { ++ kfree(vdir->vd_deblk[vdir->vd_nblk - 1]); ++ /* vdir->vd_deblk[vdir->vd_nblk - 1] = NULL; */ ++ vdir->vd_nblk--; ++ } ++ p.deblk = vdir->vd_deblk[0]; ++ deblk_end.deblk = p.deblk + vdir->vd_deblk_sz; ++ err = set_deblk_end(&p, &deblk_end); ++ /* keep vd_dblk_sz */ ++ vdir->vd_last.ul = 0; ++ vdir->vd_last.p.deblk = vdir->vd_deblk[0]; ++ vdir->vd_version = 0; ++ vdir->vd_jiffy = 0; ++ /* smp_mb(); */ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#define AuFillVdir_CALLED 1 ++#define AuFillVdir_WHABLE (1 << 1) ++#define AuFillVdir_SHWH (1 << 2) ++#define au_ftest_fillvdir(flags, name) ((flags) & AuFillVdir_##name) ++#define au_fset_fillvdir(flags, name) \ ++ do { (flags) |= AuFillVdir_##name; } while (0) ++#define au_fclr_fillvdir(flags, name) \ ++ do { (flags) &= ~AuFillVdir_##name; } while (0) ++ ++#ifndef CONFIG_AUFS_SHWH ++#undef AuFillVdir_SHWH ++#define AuFillVdir_SHWH 0 ++#endif ++ ++struct fillvdir_arg { ++ struct dir_context ctx; ++ struct file *file; ++ struct au_vdir *vdir; ++ struct au_nhash delist; ++ struct au_nhash whlist; ++ aufs_bindex_t bindex; ++ unsigned int flags; ++ int err; ++}; ++ ++static int fillvdir(struct dir_context *ctx, const char *__name, int nlen, ++ loff_t offset __maybe_unused, u64 h_ino, ++ unsigned int d_type) ++{ ++ struct fillvdir_arg *arg = container_of(ctx, struct fillvdir_arg, ctx); ++ char *name = (void *)__name; ++ struct super_block *sb; ++ ino_t ino; ++ const unsigned char shwh = !!au_ftest_fillvdir(arg->flags, SHWH); ++ ++ arg->err = 0; ++ sb = arg->file->f_path.dentry->d_sb; ++ au_fset_fillvdir(arg->flags, CALLED); ++ /* smp_mb(); */ ++ if (nlen <= AUFS_WH_PFX_LEN ++ || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { ++ if (test_known(&arg->delist, name, nlen) ++ || au_nhash_test_known_wh(&arg->whlist, name, nlen)) ++ goto out; /* already exists or whiteouted */ ++ ++ arg->err = au_ino(sb, arg->bindex, h_ino, d_type, &ino); ++ if (!arg->err) { ++ if (unlikely(nlen > AUFS_MAX_NAMELEN)) ++ d_type = DT_UNKNOWN; ++ arg->err = append_de(arg->vdir, name, nlen, ino, ++ d_type, &arg->delist); ++ } ++ } else if (au_ftest_fillvdir(arg->flags, WHABLE)) { ++ name += AUFS_WH_PFX_LEN; ++ nlen -= AUFS_WH_PFX_LEN; ++ if (au_nhash_test_known_wh(&arg->whlist, name, nlen)) ++ goto out; /* already whiteouted */ ++ ++ if (shwh) ++ arg->err = au_wh_ino(sb, arg->bindex, h_ino, d_type, ++ &ino); ++ if (!arg->err) { ++ if (nlen <= AUFS_MAX_NAMELEN + AUFS_WH_PFX_LEN) ++ d_type = DT_UNKNOWN; ++ arg->err = au_nhash_append_wh ++ (&arg->whlist, name, nlen, ino, d_type, ++ arg->bindex, shwh); ++ } ++ } ++ ++out: ++ if (!arg->err) ++ arg->vdir->vd_jiffy = jiffies; ++ /* smp_mb(); */ ++ AuTraceErr(arg->err); ++ return arg->err; ++} ++ ++static int au_handle_shwh(struct super_block *sb, struct au_vdir *vdir, ++ struct au_nhash *whlist, struct au_nhash *delist) ++{ ++#ifdef CONFIG_AUFS_SHWH ++ int err; ++ unsigned int nh, u; ++ struct hlist_head *head; ++ struct au_vdir_wh *pos; ++ struct hlist_node *n; ++ char *p, *o; ++ struct au_vdir_destr *destr; ++ ++ AuDebugOn(!au_opt_test(au_mntflags(sb), SHWH)); ++ ++ err = -ENOMEM; ++ o = p = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!p)) ++ goto out; ++ ++ err = 0; ++ nh = whlist->nh_num; ++ memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN); ++ p += AUFS_WH_PFX_LEN; ++ for (u = 0; u < nh; u++) { ++ head = whlist->nh_head + u; ++ hlist_for_each_entry_safe(pos, n, head, wh_hash) { ++ destr = &pos->wh_str; ++ memcpy(p, destr->name, destr->len); ++ err = append_de(vdir, o, destr->len + AUFS_WH_PFX_LEN, ++ pos->wh_ino, pos->wh_type, delist); ++ if (unlikely(err)) ++ break; ++ } ++ } ++ ++ free_page((unsigned long)o); ++ ++out: ++ AuTraceErr(err); ++ return err; ++#else ++ return 0; ++#endif ++} ++ ++static int au_do_read_vdir(struct fillvdir_arg *arg) ++{ ++ int err; ++ unsigned int rdhash; ++ loff_t offset; ++ aufs_bindex_t bbot, bindex, btop; ++ unsigned char shwh; ++ struct file *hf, *file; ++ struct super_block *sb; ++ ++ file = arg->file; ++ sb = file->f_path.dentry->d_sb; ++ SiMustAnyLock(sb); ++ ++ rdhash = au_sbi(sb)->si_rdhash; ++ if (!rdhash) ++ rdhash = au_rdhash_est(au_dir_size(file, /*dentry*/NULL)); ++ err = au_nhash_alloc(&arg->delist, rdhash, GFP_NOFS); ++ if (unlikely(err)) ++ goto out; ++ err = au_nhash_alloc(&arg->whlist, rdhash, GFP_NOFS); ++ if (unlikely(err)) ++ goto out_delist; ++ ++ err = 0; ++ arg->flags = 0; ++ shwh = 0; ++ if (au_opt_test(au_mntflags(sb), SHWH)) { ++ shwh = 1; ++ au_fset_fillvdir(arg->flags, SHWH); ++ } ++ btop = au_fbtop(file); ++ bbot = au_fbbot_dir(file); ++ for (bindex = btop; !err && bindex <= bbot; bindex++) { ++ hf = au_hf_dir(file, bindex); ++ if (!hf) ++ continue; ++ ++ offset = vfsub_llseek(hf, 0, SEEK_SET); ++ err = offset; ++ if (unlikely(offset)) ++ break; ++ ++ arg->bindex = bindex; ++ au_fclr_fillvdir(arg->flags, WHABLE); ++ if (shwh ++ || (bindex != bbot ++ && au_br_whable(au_sbr_perm(sb, bindex)))) ++ au_fset_fillvdir(arg->flags, WHABLE); ++ do { ++ arg->err = 0; ++ au_fclr_fillvdir(arg->flags, CALLED); ++ /* smp_mb(); */ ++ err = vfsub_iterate_dir(hf, &arg->ctx); ++ if (err >= 0) ++ err = arg->err; ++ } while (!err && au_ftest_fillvdir(arg->flags, CALLED)); ++ ++ /* ++ * dir_relax() may be good for concurrency, but aufs should not ++ * use it since it will cause a lockdep problem. ++ */ ++ } ++ ++ if (!err && shwh) ++ err = au_handle_shwh(sb, arg->vdir, &arg->whlist, &arg->delist); ++ ++ au_nhash_wh_free(&arg->whlist); ++ ++out_delist: ++ au_nhash_de_free(&arg->delist); ++out: ++ return err; ++} ++ ++static int read_vdir(struct file *file, int may_read) ++{ ++ int err; ++ unsigned long expire; ++ unsigned char do_read; ++ struct fillvdir_arg arg = { ++ .ctx = { ++ .actor = fillvdir ++ } ++ }; ++ struct inode *inode; ++ struct au_vdir *vdir, *allocated; ++ ++ err = 0; ++ inode = file_inode(file); ++ IMustLock(inode); ++ IiMustWriteLock(inode); ++ SiMustAnyLock(inode->i_sb); ++ ++ allocated = NULL; ++ do_read = 0; ++ expire = au_sbi(inode->i_sb)->si_rdcache; ++ vdir = au_ivdir(inode); ++ if (!vdir) { ++ do_read = 1; ++ vdir = alloc_vdir(file); ++ err = PTR_ERR(vdir); ++ if (IS_ERR(vdir)) ++ goto out; ++ err = 0; ++ allocated = vdir; ++ } else if (may_read ++ && (inode->i_version != vdir->vd_version ++ || time_after(jiffies, vdir->vd_jiffy + expire))) { ++ do_read = 1; ++ err = reinit_vdir(vdir); ++ if (unlikely(err)) ++ goto out; ++ } ++ ++ if (!do_read) ++ return 0; /* success */ ++ ++ arg.file = file; ++ arg.vdir = vdir; ++ err = au_do_read_vdir(&arg); ++ if (!err) { ++ /* file->f_pos = 0; */ /* todo: ctx->pos? */ ++ vdir->vd_version = inode->i_version; ++ vdir->vd_last.ul = 0; ++ vdir->vd_last.p.deblk = vdir->vd_deblk[0]; ++ if (allocated) ++ au_set_ivdir(inode, allocated); ++ } else if (allocated) ++ au_vdir_free(allocated); ++ ++out: ++ return err; ++} ++ ++static int copy_vdir(struct au_vdir *tgt, struct au_vdir *src) ++{ ++ int err, rerr; ++ unsigned long ul, n; ++ const unsigned int deblk_sz = src->vd_deblk_sz; ++ ++ AuDebugOn(tgt->vd_nblk != 1); ++ ++ err = -ENOMEM; ++ if (tgt->vd_nblk < src->vd_nblk) { ++ unsigned char **p; ++ ++ p = au_krealloc(tgt->vd_deblk, sizeof(*p) * src->vd_nblk, ++ GFP_NOFS, /*may_shrink*/0); ++ if (unlikely(!p)) ++ goto out; ++ tgt->vd_deblk = p; ++ } ++ ++ if (tgt->vd_deblk_sz != deblk_sz) { ++ unsigned char *p; ++ ++ tgt->vd_deblk_sz = deblk_sz; ++ p = au_krealloc(tgt->vd_deblk[0], deblk_sz, GFP_NOFS, ++ /*may_shrink*/1); ++ if (unlikely(!p)) ++ goto out; ++ tgt->vd_deblk[0] = p; ++ } ++ memcpy(tgt->vd_deblk[0], src->vd_deblk[0], deblk_sz); ++ tgt->vd_version = src->vd_version; ++ tgt->vd_jiffy = src->vd_jiffy; ++ ++ n = src->vd_nblk; ++ for (ul = 1; ul < n; ul++) { ++ tgt->vd_deblk[ul] = kmemdup(src->vd_deblk[ul], deblk_sz, ++ GFP_NOFS); ++ if (unlikely(!tgt->vd_deblk[ul])) ++ goto out; ++ tgt->vd_nblk++; ++ } ++ tgt->vd_nblk = n; ++ tgt->vd_last.ul = tgt->vd_last.ul; ++ tgt->vd_last.p.deblk = tgt->vd_deblk[tgt->vd_last.ul]; ++ tgt->vd_last.p.deblk += src->vd_last.p.deblk ++ - src->vd_deblk[src->vd_last.ul]; ++ /* smp_mb(); */ ++ return 0; /* success */ ++ ++out: ++ rerr = reinit_vdir(tgt); ++ BUG_ON(rerr); ++ return err; ++} ++ ++int au_vdir_init(struct file *file) ++{ ++ int err; ++ struct inode *inode; ++ struct au_vdir *vdir_cache, *allocated; ++ ++ /* test file->f_pos here instead of ctx->pos */ ++ err = read_vdir(file, !file->f_pos); ++ if (unlikely(err)) ++ goto out; ++ ++ allocated = NULL; ++ vdir_cache = au_fvdir_cache(file); ++ if (!vdir_cache) { ++ vdir_cache = alloc_vdir(file); ++ err = PTR_ERR(vdir_cache); ++ if (IS_ERR(vdir_cache)) ++ goto out; ++ allocated = vdir_cache; ++ } else if (!file->f_pos && vdir_cache->vd_version != file->f_version) { ++ /* test file->f_pos here instead of ctx->pos */ ++ err = reinit_vdir(vdir_cache); ++ if (unlikely(err)) ++ goto out; ++ } else ++ return 0; /* success */ ++ ++ inode = file_inode(file); ++ err = copy_vdir(vdir_cache, au_ivdir(inode)); ++ if (!err) { ++ file->f_version = inode->i_version; ++ if (allocated) ++ au_set_fvdir_cache(file, allocated); ++ } else if (allocated) ++ au_vdir_free(allocated); ++ ++out: ++ return err; ++} ++ ++static loff_t calc_offset(struct au_vdir *vdir) ++{ ++ loff_t offset; ++ union au_vdir_deblk_p p; ++ ++ p.deblk = vdir->vd_deblk[vdir->vd_last.ul]; ++ offset = vdir->vd_last.p.deblk - p.deblk; ++ offset += vdir->vd_deblk_sz * vdir->vd_last.ul; ++ return offset; ++} ++ ++/* returns true or false */ ++static int seek_vdir(struct file *file, struct dir_context *ctx) ++{ ++ int valid; ++ unsigned int deblk_sz; ++ unsigned long ul, n; ++ loff_t offset; ++ union au_vdir_deblk_p p, deblk_end; ++ struct au_vdir *vdir_cache; ++ ++ valid = 1; ++ vdir_cache = au_fvdir_cache(file); ++ offset = calc_offset(vdir_cache); ++ AuDbg("offset %lld\n", offset); ++ if (ctx->pos == offset) ++ goto out; ++ ++ vdir_cache->vd_last.ul = 0; ++ vdir_cache->vd_last.p.deblk = vdir_cache->vd_deblk[0]; ++ if (!ctx->pos) ++ goto out; ++ ++ valid = 0; ++ deblk_sz = vdir_cache->vd_deblk_sz; ++ ul = div64_u64(ctx->pos, deblk_sz); ++ AuDbg("ul %lu\n", ul); ++ if (ul >= vdir_cache->vd_nblk) ++ goto out; ++ ++ n = vdir_cache->vd_nblk; ++ for (; ul < n; ul++) { ++ p.deblk = vdir_cache->vd_deblk[ul]; ++ deblk_end.deblk = p.deblk + deblk_sz; ++ offset = ul; ++ offset *= deblk_sz; ++ while (!is_deblk_end(&p, &deblk_end) && offset < ctx->pos) { ++ unsigned int l; ++ ++ l = calc_size(p.de->de_str.len); ++ offset += l; ++ p.deblk += l; ++ } ++ if (!is_deblk_end(&p, &deblk_end)) { ++ valid = 1; ++ vdir_cache->vd_last.ul = ul; ++ vdir_cache->vd_last.p = p; ++ break; ++ } ++ } ++ ++out: ++ /* smp_mb(); */ ++ if (!valid) ++ AuDbg("valid %d\n", !valid); ++ return valid; ++} ++ ++int au_vdir_fill_de(struct file *file, struct dir_context *ctx) ++{ ++ unsigned int l, deblk_sz; ++ union au_vdir_deblk_p deblk_end; ++ struct au_vdir *vdir_cache; ++ struct au_vdir_de *de; ++ ++ vdir_cache = au_fvdir_cache(file); ++ if (!seek_vdir(file, ctx)) ++ return 0; ++ ++ deblk_sz = vdir_cache->vd_deblk_sz; ++ while (1) { ++ deblk_end.deblk = vdir_cache->vd_deblk[vdir_cache->vd_last.ul]; ++ deblk_end.deblk += deblk_sz; ++ while (!is_deblk_end(&vdir_cache->vd_last.p, &deblk_end)) { ++ de = vdir_cache->vd_last.p.de; ++ AuDbg("%.*s, off%lld, i%lu, dt%d\n", ++ de->de_str.len, de->de_str.name, ctx->pos, ++ (unsigned long)de->de_ino, de->de_type); ++ if (unlikely(!dir_emit(ctx, de->de_str.name, ++ de->de_str.len, de->de_ino, ++ de->de_type))) { ++ /* todo: ignore the error caused by udba? */ ++ /* return err; */ ++ return 0; ++ } ++ ++ l = calc_size(de->de_str.len); ++ vdir_cache->vd_last.p.deblk += l; ++ ctx->pos += l; ++ } ++ if (vdir_cache->vd_last.ul < vdir_cache->vd_nblk - 1) { ++ vdir_cache->vd_last.ul++; ++ vdir_cache->vd_last.p.deblk ++ = vdir_cache->vd_deblk[vdir_cache->vd_last.ul]; ++ ctx->pos = deblk_sz * vdir_cache->vd_last.ul; ++ continue; ++ } ++ break; ++ } ++ ++ /* smp_mb(); */ ++ return 0; ++} +diff --git a/fs/aufs/vfsub.c b/fs/aufs/vfsub.c +new file mode 100644 +index 00000000..5786b4a4 +--- /dev/null ++++ b/fs/aufs/vfsub.c +@@ -0,0 +1,894 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * sub-routines for VFS ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include "aufs.h" ++ ++#ifdef CONFIG_AUFS_BR_FUSE ++int vfsub_test_mntns(struct vfsmount *mnt, struct super_block *h_sb) ++{ ++ if (!au_test_fuse(h_sb) || !au_userns) ++ return 0; ++ ++ return is_current_mnt_ns(mnt) ? 0 : -EACCES; ++} ++#endif ++ ++int vfsub_sync_filesystem(struct super_block *h_sb, int wait) ++{ ++ int err; ++ ++ lockdep_off(); ++ down_read(&h_sb->s_umount); ++ err = __sync_filesystem(h_sb, wait); ++ up_read(&h_sb->s_umount); ++ lockdep_on(); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int vfsub_update_h_iattr(struct path *h_path, int *did) ++{ ++ int err; ++ struct kstat st; ++ struct super_block *h_sb; ++ ++ /* for remote fs, leave work for its getattr or d_revalidate */ ++ /* for bad i_attr fs, handle them in aufs_getattr() */ ++ /* still some fs may acquire i_mutex. we need to skip them */ ++ err = 0; ++ if (!did) ++ did = &err; ++ h_sb = h_path->dentry->d_sb; ++ *did = (!au_test_fs_remote(h_sb) && au_test_fs_refresh_iattr(h_sb)); ++ if (*did) ++ err = vfs_getattr(h_path, &st); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct file *vfsub_dentry_open(struct path *path, int flags) ++{ ++ struct file *file; ++ ++ file = dentry_open(path, flags /* | __FMODE_NONOTIFY */, ++ current_cred()); ++ if (!IS_ERR_OR_NULL(file) ++ && (file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) ++ i_readcount_inc(d_inode(path->dentry)); ++ ++ return file; ++} ++ ++struct file *vfsub_filp_open(const char *path, int oflags, int mode) ++{ ++ struct file *file; ++ ++ lockdep_off(); ++ file = filp_open(path, ++ oflags /* | __FMODE_NONOTIFY */, ++ mode); ++ lockdep_on(); ++ if (IS_ERR(file)) ++ goto out; ++ vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ ++ ++out: ++ return file; ++} ++ ++/* ++ * Ideally this function should call VFS:do_last() in order to keep all its ++ * checkings. But it is very hard for aufs to regenerate several VFS internal ++ * structure such as nameidata. This is a second (or third) best approach. ++ * cf. linux/fs/namei.c:do_last(), lookup_open() and atomic_open(). ++ */ ++int vfsub_atomic_open(struct inode *dir, struct dentry *dentry, ++ struct vfsub_aopen_args *args, struct au_branch *br) ++{ ++ int err; ++ struct file *file = args->file; ++ /* copied from linux/fs/namei.c:atomic_open() */ ++ struct dentry *const DENTRY_NOT_SET = (void *)-1UL; ++ ++ IMustLock(dir); ++ AuDebugOn(!dir->i_op->atomic_open); ++ ++ err = au_br_test_oflag(args->open_flag, br); ++ if (unlikely(err)) ++ goto out; ++ ++ args->file->f_path.dentry = DENTRY_NOT_SET; ++ args->file->f_path.mnt = au_br_mnt(br); ++ err = dir->i_op->atomic_open(dir, dentry, file, args->open_flag, ++ args->create_mode, args->opened); ++ if (err >= 0) { ++ /* some filesystems don't set FILE_CREATED while succeeded? */ ++ if (*args->opened & FILE_CREATED) ++ fsnotify_create(dir, dentry); ++ } else ++ goto out; ++ ++ ++ if (!err) { ++ /* todo: call VFS:may_open() here */ ++ err = open_check_o_direct(file); ++ /* todo: ima_file_check() too? */ ++ if (!err && (args->open_flag & __FMODE_EXEC)) ++ err = deny_write_access(file); ++ if (unlikely(err)) ++ /* note that the file is created and still opened */ ++ goto out; ++ } ++ ++ au_br_get(br); ++ fsnotify_open(file); ++ ++out: ++ return err; ++} ++ ++int vfsub_kern_path(const char *name, unsigned int flags, struct path *path) ++{ ++ int err; ++ ++ err = kern_path(name, flags, path); ++ if (!err && d_is_positive(path->dentry)) ++ vfsub_update_h_iattr(path, /*did*/NULL); /*ignore*/ ++ return err; ++} ++ ++struct dentry *vfsub_lookup_one_len_unlocked(const char *name, ++ struct dentry *parent, int len) ++{ ++ struct path path = { ++ .mnt = NULL ++ }; ++ ++ path.dentry = lookup_one_len_unlocked(name, parent, len); ++ if (IS_ERR(path.dentry)) ++ goto out; ++ if (d_is_positive(path.dentry)) ++ vfsub_update_h_iattr(&path, /*did*/NULL); /*ignore*/ ++ ++out: ++ AuTraceErrPtr(path.dentry); ++ return path.dentry; ++} ++ ++struct dentry *vfsub_lookup_one_len(const char *name, struct dentry *parent, ++ int len) ++{ ++ struct path path = { ++ .mnt = NULL ++ }; ++ ++ /* VFS checks it too, but by WARN_ON_ONCE() */ ++ IMustLock(d_inode(parent)); ++ ++ path.dentry = lookup_one_len(name, parent, len); ++ if (IS_ERR(path.dentry)) ++ goto out; ++ if (d_is_positive(path.dentry)) ++ vfsub_update_h_iattr(&path, /*did*/NULL); /*ignore*/ ++ ++out: ++ AuTraceErrPtr(path.dentry); ++ return path.dentry; ++} ++ ++void vfsub_call_lkup_one(void *args) ++{ ++ struct vfsub_lkup_one_args *a = args; ++ *a->errp = vfsub_lkup_one(a->name, a->parent); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct dentry *vfsub_lock_rename(struct dentry *d1, struct au_hinode *hdir1, ++ struct dentry *d2, struct au_hinode *hdir2) ++{ ++ struct dentry *d; ++ ++ lockdep_off(); ++ d = lock_rename(d1, d2); ++ lockdep_on(); ++ au_hn_suspend(hdir1); ++ if (hdir1 != hdir2) ++ au_hn_suspend(hdir2); ++ ++ return d; ++} ++ ++void vfsub_unlock_rename(struct dentry *d1, struct au_hinode *hdir1, ++ struct dentry *d2, struct au_hinode *hdir2) ++{ ++ au_hn_resume(hdir1); ++ if (hdir1 != hdir2) ++ au_hn_resume(hdir2); ++ lockdep_off(); ++ unlock_rename(d1, d2); ++ lockdep_on(); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int vfsub_create(struct inode *dir, struct path *path, int mode, bool want_excl) ++{ ++ int err; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ err = security_path_mknod(path, d, mode, 0); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ lockdep_off(); ++ err = vfs_create(dir, path->dentry, mode, want_excl); ++ lockdep_on(); ++ if (!err) { ++ struct path tmp = *path; ++ int did; ++ ++ vfsub_update_h_iattr(&tmp, &did); ++ if (did) { ++ tmp.dentry = path->dentry->d_parent; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ } ++ /*ignore*/ ++ } ++ ++out: ++ return err; ++} ++ ++int vfsub_symlink(struct inode *dir, struct path *path, const char *symname) ++{ ++ int err; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ err = security_path_symlink(path, d, symname); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ lockdep_off(); ++ err = vfs_symlink(dir, path->dentry, symname); ++ lockdep_on(); ++ if (!err) { ++ struct path tmp = *path; ++ int did; ++ ++ vfsub_update_h_iattr(&tmp, &did); ++ if (did) { ++ tmp.dentry = path->dentry->d_parent; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ } ++ /*ignore*/ ++ } ++ ++out: ++ return err; ++} ++ ++int vfsub_mknod(struct inode *dir, struct path *path, int mode, dev_t dev) ++{ ++ int err; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ err = security_path_mknod(path, d, mode, new_encode_dev(dev)); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ lockdep_off(); ++ err = vfs_mknod(dir, path->dentry, mode, dev); ++ lockdep_on(); ++ if (!err) { ++ struct path tmp = *path; ++ int did; ++ ++ vfsub_update_h_iattr(&tmp, &did); ++ if (did) { ++ tmp.dentry = path->dentry->d_parent; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ } ++ /*ignore*/ ++ } ++ ++out: ++ return err; ++} ++ ++static int au_test_nlink(struct inode *inode) ++{ ++ const unsigned int link_max = UINT_MAX >> 1; /* rough margin */ ++ ++ if (!au_test_fs_no_limit_nlink(inode->i_sb) ++ || inode->i_nlink < link_max) ++ return 0; ++ return -EMLINK; ++} ++ ++int vfsub_link(struct dentry *src_dentry, struct inode *dir, struct path *path, ++ struct inode **delegated_inode) ++{ ++ int err; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ ++ err = au_test_nlink(d_inode(src_dentry)); ++ if (unlikely(err)) ++ return err; ++ ++ /* we don't call may_linkat() */ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ err = security_path_link(src_dentry, path, d); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ lockdep_off(); ++ err = vfs_link(src_dentry, dir, path->dentry, delegated_inode); ++ lockdep_on(); ++ if (!err) { ++ struct path tmp = *path; ++ int did; ++ ++ /* fuse has different memory inode for the same inumber */ ++ vfsub_update_h_iattr(&tmp, &did); ++ if (did) { ++ tmp.dentry = path->dentry->d_parent; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ tmp.dentry = src_dentry; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ } ++ /*ignore*/ ++ } ++ ++out: ++ return err; ++} ++ ++int vfsub_rename(struct inode *src_dir, struct dentry *src_dentry, ++ struct inode *dir, struct path *path, ++ struct inode **delegated_inode, unsigned int flags) ++{ ++ int err; ++ struct path tmp = { ++ .mnt = path->mnt ++ }; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ IMustLock(src_dir); ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ tmp.dentry = src_dentry->d_parent; ++ err = security_path_rename(&tmp, src_dentry, path, d, /*flags*/0); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ lockdep_off(); ++ err = vfs_rename(src_dir, src_dentry, dir, path->dentry, ++ delegated_inode, flags); ++ lockdep_on(); ++ if (!err) { ++ int did; ++ ++ tmp.dentry = d->d_parent; ++ vfsub_update_h_iattr(&tmp, &did); ++ if (did) { ++ tmp.dentry = src_dentry; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ tmp.dentry = src_dentry->d_parent; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ } ++ /*ignore*/ ++ } ++ ++out: ++ return err; ++} ++ ++int vfsub_mkdir(struct inode *dir, struct path *path, int mode) ++{ ++ int err; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ err = security_path_mkdir(path, d, mode); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ lockdep_off(); ++ err = vfs_mkdir(dir, path->dentry, mode); ++ lockdep_on(); ++ if (!err) { ++ struct path tmp = *path; ++ int did; ++ ++ vfsub_update_h_iattr(&tmp, &did); ++ if (did) { ++ tmp.dentry = path->dentry->d_parent; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ } ++ /*ignore*/ ++ } ++ ++out: ++ return err; ++} ++ ++int vfsub_rmdir(struct inode *dir, struct path *path) ++{ ++ int err; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ err = security_path_rmdir(path, d); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ lockdep_off(); ++ err = vfs_rmdir(dir, path->dentry); ++ lockdep_on(); ++ if (!err) { ++ struct path tmp = { ++ .dentry = path->dentry->d_parent, ++ .mnt = path->mnt ++ }; ++ ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); /*ignore*/ ++ } ++ ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* todo: support mmap_sem? */ ++ssize_t vfsub_read_u(struct file *file, char __user *ubuf, size_t count, ++ loff_t *ppos) ++{ ++ ssize_t err; ++ ++ lockdep_off(); ++ err = vfs_read(file, ubuf, count, ppos); ++ lockdep_on(); ++ if (err >= 0) ++ vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ ++ return err; ++} ++ ++/* todo: kernel_read()? */ ++ssize_t vfsub_read_k(struct file *file, void *kbuf, size_t count, ++ loff_t *ppos) ++{ ++ ssize_t err; ++ mm_segment_t oldfs; ++ union { ++ void *k; ++ char __user *u; ++ } buf; ++ ++ buf.k = kbuf; ++ oldfs = get_fs(); ++ set_fs(KERNEL_DS); ++ err = vfsub_read_u(file, buf.u, count, ppos); ++ set_fs(oldfs); ++ return err; ++} ++ ++ssize_t vfsub_write_u(struct file *file, const char __user *ubuf, size_t count, ++ loff_t *ppos) ++{ ++ ssize_t err; ++ ++ lockdep_off(); ++ err = vfs_write(file, ubuf, count, ppos); ++ lockdep_on(); ++ if (err >= 0) ++ vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ ++ return err; ++} ++ ++ssize_t vfsub_write_k(struct file *file, void *kbuf, size_t count, loff_t *ppos) ++{ ++ ssize_t err; ++ mm_segment_t oldfs; ++ union { ++ void *k; ++ const char __user *u; ++ } buf; ++ ++ buf.k = kbuf; ++ oldfs = get_fs(); ++ set_fs(KERNEL_DS); ++ err = vfsub_write_u(file, buf.u, count, ppos); ++ set_fs(oldfs); ++ return err; ++} ++ ++int vfsub_flush(struct file *file, fl_owner_t id) ++{ ++ int err; ++ ++ err = 0; ++ if (file->f_op->flush) { ++ if (!au_test_nfs(file->f_path.dentry->d_sb)) ++ err = file->f_op->flush(file, id); ++ else { ++ lockdep_off(); ++ err = file->f_op->flush(file, id); ++ lockdep_on(); ++ } ++ if (!err) ++ vfsub_update_h_iattr(&file->f_path, /*did*/NULL); ++ /*ignore*/ ++ } ++ return err; ++} ++ ++int vfsub_iterate_dir(struct file *file, struct dir_context *ctx) ++{ ++ int err; ++ ++ AuDbg("%pD, ctx{%pf, %llu}\n", file, ctx->actor, ctx->pos); ++ ++ lockdep_off(); ++ err = iterate_dir(file, ctx); ++ lockdep_on(); ++ if (err >= 0) ++ vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ ++ ++ return err; ++} ++ ++long vfsub_splice_to(struct file *in, loff_t *ppos, ++ struct pipe_inode_info *pipe, size_t len, ++ unsigned int flags) ++{ ++ long err; ++ ++ lockdep_off(); ++ err = do_splice_to(in, ppos, pipe, len, flags); ++ lockdep_on(); ++ file_accessed(in); ++ if (err >= 0) ++ vfsub_update_h_iattr(&in->f_path, /*did*/NULL); /*ignore*/ ++ return err; ++} ++ ++long vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out, ++ loff_t *ppos, size_t len, unsigned int flags) ++{ ++ long err; ++ ++ lockdep_off(); ++ err = do_splice_from(pipe, out, ppos, len, flags); ++ lockdep_on(); ++ if (err >= 0) ++ vfsub_update_h_iattr(&out->f_path, /*did*/NULL); /*ignore*/ ++ return err; ++} ++ ++int vfsub_fsync(struct file *file, struct path *path, int datasync) ++{ ++ int err; ++ ++ /* file can be NULL */ ++ lockdep_off(); ++ err = vfs_fsync(file, datasync); ++ lockdep_on(); ++ if (!err) { ++ if (!path) { ++ AuDebugOn(!file); ++ path = &file->f_path; ++ } ++ vfsub_update_h_iattr(path, /*did*/NULL); /*ignore*/ ++ } ++ return err; ++} ++ ++/* cf. open.c:do_sys_truncate() and do_sys_ftruncate() */ ++int vfsub_trunc(struct path *h_path, loff_t length, unsigned int attr, ++ struct file *h_file) ++{ ++ int err; ++ struct inode *h_inode; ++ struct super_block *h_sb; ++ ++ if (!h_file) { ++ err = vfsub_truncate(h_path, length); ++ goto out; ++ } ++ ++ h_inode = d_inode(h_path->dentry); ++ h_sb = h_inode->i_sb; ++ lockdep_off(); ++ sb_start_write(h_sb); ++ lockdep_on(); ++ err = locks_verify_truncate(h_inode, h_file, length); ++ if (!err) ++ err = security_path_truncate(h_path); ++ if (!err) { ++ lockdep_off(); ++ err = do_truncate(h_path->dentry, length, attr, h_file); ++ lockdep_on(); ++ } ++ lockdep_off(); ++ sb_end_write(h_sb); ++ lockdep_on(); ++ ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_vfsub_mkdir_args { ++ int *errp; ++ struct inode *dir; ++ struct path *path; ++ int mode; ++}; ++ ++static void au_call_vfsub_mkdir(void *args) ++{ ++ struct au_vfsub_mkdir_args *a = args; ++ *a->errp = vfsub_mkdir(a->dir, a->path, a->mode); ++} ++ ++int vfsub_sio_mkdir(struct inode *dir, struct path *path, int mode) ++{ ++ int err, do_sio, wkq_err; ++ ++ do_sio = au_test_h_perm_sio(dir, MAY_EXEC | MAY_WRITE); ++ if (!do_sio) { ++ lockdep_off(); ++ err = vfsub_mkdir(dir, path, mode); ++ lockdep_on(); ++ } else { ++ struct au_vfsub_mkdir_args args = { ++ .errp = &err, ++ .dir = dir, ++ .path = path, ++ .mode = mode ++ }; ++ wkq_err = au_wkq_wait(au_call_vfsub_mkdir, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ return err; ++} ++ ++struct au_vfsub_rmdir_args { ++ int *errp; ++ struct inode *dir; ++ struct path *path; ++}; ++ ++static void au_call_vfsub_rmdir(void *args) ++{ ++ struct au_vfsub_rmdir_args *a = args; ++ *a->errp = vfsub_rmdir(a->dir, a->path); ++} ++ ++int vfsub_sio_rmdir(struct inode *dir, struct path *path) ++{ ++ int err, do_sio, wkq_err; ++ ++ do_sio = au_test_h_perm_sio(dir, MAY_EXEC | MAY_WRITE); ++ if (!do_sio) { ++ lockdep_off(); ++ err = vfsub_rmdir(dir, path); ++ lockdep_on(); ++ } else { ++ struct au_vfsub_rmdir_args args = { ++ .errp = &err, ++ .dir = dir, ++ .path = path ++ }; ++ wkq_err = au_wkq_wait(au_call_vfsub_rmdir, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct notify_change_args { ++ int *errp; ++ struct path *path; ++ struct iattr *ia; ++ struct inode **delegated_inode; ++}; ++ ++static void call_notify_change(void *args) ++{ ++ struct notify_change_args *a = args; ++ struct inode *h_inode; ++ ++ h_inode = d_inode(a->path->dentry); ++ IMustLock(h_inode); ++ ++ *a->errp = -EPERM; ++ if (!IS_IMMUTABLE(h_inode) && !IS_APPEND(h_inode)) { ++ lockdep_off(); ++ *a->errp = notify_change(a->path->dentry, a->ia, ++ a->delegated_inode); ++ lockdep_on(); ++ if (!*a->errp) ++ vfsub_update_h_iattr(a->path, /*did*/NULL); /*ignore*/ ++ } ++ AuTraceErr(*a->errp); ++} ++ ++int vfsub_notify_change(struct path *path, struct iattr *ia, ++ struct inode **delegated_inode) ++{ ++ int err; ++ struct notify_change_args args = { ++ .errp = &err, ++ .path = path, ++ .ia = ia, ++ .delegated_inode = delegated_inode ++ }; ++ ++ call_notify_change(&args); ++ ++ return err; ++} ++ ++int vfsub_sio_notify_change(struct path *path, struct iattr *ia, ++ struct inode **delegated_inode) ++{ ++ int err, wkq_err; ++ struct notify_change_args args = { ++ .errp = &err, ++ .path = path, ++ .ia = ia, ++ .delegated_inode = delegated_inode ++ }; ++ ++ wkq_err = au_wkq_wait(call_notify_change, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct unlink_args { ++ int *errp; ++ struct inode *dir; ++ struct path *path; ++ struct inode **delegated_inode; ++}; ++ ++static void call_unlink(void *args) ++{ ++ struct unlink_args *a = args; ++ struct dentry *d = a->path->dentry; ++ struct inode *h_inode; ++ const int stop_sillyrename = (au_test_nfs(d->d_sb) ++ && au_dcount(d) == 1); ++ ++ IMustLock(a->dir); ++ ++ a->path->dentry = d->d_parent; ++ *a->errp = security_path_unlink(a->path, d); ++ a->path->dentry = d; ++ if (unlikely(*a->errp)) ++ return; ++ ++ if (!stop_sillyrename) ++ dget(d); ++ h_inode = NULL; ++ if (d_is_positive(d)) { ++ h_inode = d_inode(d); ++ ihold(h_inode); ++ } ++ ++ lockdep_off(); ++ *a->errp = vfs_unlink(a->dir, d, a->delegated_inode); ++ lockdep_on(); ++ if (!*a->errp) { ++ struct path tmp = { ++ .dentry = d->d_parent, ++ .mnt = a->path->mnt ++ }; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); /*ignore*/ ++ } ++ ++ if (!stop_sillyrename) ++ dput(d); ++ if (h_inode) ++ iput(h_inode); ++ ++ AuTraceErr(*a->errp); ++} ++ ++/* ++ * @dir: must be locked. ++ * @dentry: target dentry. ++ */ ++int vfsub_unlink(struct inode *dir, struct path *path, ++ struct inode **delegated_inode, int force) ++{ ++ int err; ++ struct unlink_args args = { ++ .errp = &err, ++ .dir = dir, ++ .path = path, ++ .delegated_inode = delegated_inode ++ }; ++ ++ if (!force) ++ call_unlink(&args); ++ else { ++ int wkq_err; ++ ++ wkq_err = au_wkq_wait(call_unlink, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ return err; ++} +diff --git a/fs/aufs/vfsub.h b/fs/aufs/vfsub.h +new file mode 100644 +index 00000000..2c598af2 +--- /dev/null ++++ b/fs/aufs/vfsub.h +@@ -0,0 +1,355 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * sub-routines for VFS ++ */ ++ ++#ifndef __AUFS_VFSUB_H__ ++#define __AUFS_VFSUB_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include ++#include ++#include ++#include "debug.h" ++ ++/* copied from linux/fs/internal.h */ ++/* todo: BAD approach!! */ ++extern void __mnt_drop_write(struct vfsmount *); ++extern int open_check_o_direct(struct file *f); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* lock subclass for lower inode */ ++/* default MAX_LOCKDEP_SUBCLASSES(8) is not enough */ ++/* reduce? gave up. */ ++enum { ++ AuLsc_I_Begin = I_MUTEX_PARENT2, /* 5 */ ++ AuLsc_I_PARENT, /* lower inode, parent first */ ++ AuLsc_I_PARENT2, /* copyup dirs */ ++ AuLsc_I_PARENT3, /* copyup wh */ ++ AuLsc_I_CHILD, ++ AuLsc_I_CHILD2, ++ AuLsc_I_End ++}; ++ ++/* to debug easier, do not make them inlined functions */ ++#define MtxMustLock(mtx) AuDebugOn(!mutex_is_locked(mtx)) ++#define IMustLock(i) AuDebugOn(!inode_is_locked(i)) ++ ++/* why VFS doesn't define it? */ ++static inline ++void vfsub_inode_lock_shared_nested(struct inode *inode, unsigned int sc) ++{ ++ down_read_nested(&inode->i_rwsem, sc); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline void vfsub_drop_nlink(struct inode *inode) ++{ ++ AuDebugOn(!inode->i_nlink); ++ drop_nlink(inode); ++} ++ ++static inline void vfsub_dead_dir(struct inode *inode) ++{ ++ AuDebugOn(!S_ISDIR(inode->i_mode)); ++ inode->i_flags |= S_DEAD; ++ clear_nlink(inode); ++} ++ ++static inline int vfsub_native_ro(struct inode *inode) ++{ ++ return (inode->i_sb->s_flags & MS_RDONLY) ++ || IS_RDONLY(inode) ++ /* || IS_APPEND(inode) */ ++ || IS_IMMUTABLE(inode); ++} ++ ++#ifdef CONFIG_AUFS_BR_FUSE ++int vfsub_test_mntns(struct vfsmount *mnt, struct super_block *h_sb); ++#else ++AuStubInt0(vfsub_test_mntns, struct vfsmount *mnt, struct super_block *h_sb); ++#endif ++ ++int vfsub_sync_filesystem(struct super_block *h_sb, int wait); ++ ++/* ---------------------------------------------------------------------- */ ++ ++int vfsub_update_h_iattr(struct path *h_path, int *did); ++struct file *vfsub_dentry_open(struct path *path, int flags); ++struct file *vfsub_filp_open(const char *path, int oflags, int mode); ++struct vfsub_aopen_args { ++ struct file *file; ++ unsigned int open_flag; ++ umode_t create_mode; ++ int *opened; ++}; ++struct au_branch; ++int vfsub_atomic_open(struct inode *dir, struct dentry *dentry, ++ struct vfsub_aopen_args *args, struct au_branch *br); ++int vfsub_kern_path(const char *name, unsigned int flags, struct path *path); ++ ++struct dentry *vfsub_lookup_one_len_unlocked(const char *name, ++ struct dentry *parent, int len); ++struct dentry *vfsub_lookup_one_len(const char *name, struct dentry *parent, ++ int len); ++ ++struct vfsub_lkup_one_args { ++ struct dentry **errp; ++ struct qstr *name; ++ struct dentry *parent; ++}; ++ ++static inline struct dentry *vfsub_lkup_one(struct qstr *name, ++ struct dentry *parent) ++{ ++ return vfsub_lookup_one_len(name->name, parent, name->len); ++} ++ ++void vfsub_call_lkup_one(void *args); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline int vfsub_mnt_want_write(struct vfsmount *mnt) ++{ ++ int err; ++ ++ lockdep_off(); ++ err = mnt_want_write(mnt); ++ lockdep_on(); ++ return err; ++} ++ ++static inline void vfsub_mnt_drop_write(struct vfsmount *mnt) ++{ ++ lockdep_off(); ++ mnt_drop_write(mnt); ++ lockdep_on(); ++} ++ ++#if 0 /* reserved */ ++static inline void vfsub_mnt_drop_write_file(struct file *file) ++{ ++ lockdep_off(); ++ mnt_drop_write_file(file); ++ lockdep_on(); ++} ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_hinode; ++struct dentry *vfsub_lock_rename(struct dentry *d1, struct au_hinode *hdir1, ++ struct dentry *d2, struct au_hinode *hdir2); ++void vfsub_unlock_rename(struct dentry *d1, struct au_hinode *hdir1, ++ struct dentry *d2, struct au_hinode *hdir2); ++ ++int vfsub_create(struct inode *dir, struct path *path, int mode, ++ bool want_excl); ++int vfsub_symlink(struct inode *dir, struct path *path, ++ const char *symname); ++int vfsub_mknod(struct inode *dir, struct path *path, int mode, dev_t dev); ++int vfsub_link(struct dentry *src_dentry, struct inode *dir, ++ struct path *path, struct inode **delegated_inode); ++int vfsub_rename(struct inode *src_hdir, struct dentry *src_dentry, ++ struct inode *hdir, struct path *path, ++ struct inode **delegated_inode, unsigned int flags); ++int vfsub_mkdir(struct inode *dir, struct path *path, int mode); ++int vfsub_rmdir(struct inode *dir, struct path *path); ++ ++/* ---------------------------------------------------------------------- */ ++ ++ssize_t vfsub_read_u(struct file *file, char __user *ubuf, size_t count, ++ loff_t *ppos); ++ssize_t vfsub_read_k(struct file *file, void *kbuf, size_t count, ++ loff_t *ppos); ++ssize_t vfsub_write_u(struct file *file, const char __user *ubuf, size_t count, ++ loff_t *ppos); ++ssize_t vfsub_write_k(struct file *file, void *kbuf, size_t count, ++ loff_t *ppos); ++int vfsub_flush(struct file *file, fl_owner_t id); ++int vfsub_iterate_dir(struct file *file, struct dir_context *ctx); ++ ++static inline loff_t vfsub_f_size_read(struct file *file) ++{ ++ return i_size_read(file_inode(file)); ++} ++ ++static inline unsigned int vfsub_file_flags(struct file *file) ++{ ++ unsigned int flags; ++ ++ spin_lock(&file->f_lock); ++ flags = file->f_flags; ++ spin_unlock(&file->f_lock); ++ ++ return flags; ++} ++ ++static inline int vfsub_file_execed(struct file *file) ++{ ++ /* todo: direct access f_flags */ ++ return !!(vfsub_file_flags(file) & __FMODE_EXEC); ++} ++ ++#if 0 /* reserved */ ++static inline void vfsub_file_accessed(struct file *h_file) ++{ ++ file_accessed(h_file); ++ vfsub_update_h_iattr(&h_file->f_path, /*did*/NULL); /*ignore*/ ++} ++#endif ++ ++#if 0 /* reserved */ ++static inline void vfsub_touch_atime(struct vfsmount *h_mnt, ++ struct dentry *h_dentry) ++{ ++ struct path h_path = { ++ .dentry = h_dentry, ++ .mnt = h_mnt ++ }; ++ touch_atime(&h_path); ++ vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/ ++} ++#endif ++ ++static inline int vfsub_update_time(struct inode *h_inode, struct timespec *ts, ++ int flags) ++{ ++ return update_time(h_inode, ts, flags); ++ /* no vfsub_update_h_iattr() since we don't have struct path */ ++} ++ ++#ifdef CONFIG_FS_POSIX_ACL ++static inline int vfsub_acl_chmod(struct inode *h_inode, umode_t h_mode) ++{ ++ int err; ++ ++ err = posix_acl_chmod(h_inode, h_mode); ++ if (err == -EOPNOTSUPP) ++ err = 0; ++ return err; ++} ++#else ++AuStubInt0(vfsub_acl_chmod, struct inode *h_inode, umode_t h_mode); ++#endif ++ ++long vfsub_splice_to(struct file *in, loff_t *ppos, ++ struct pipe_inode_info *pipe, size_t len, ++ unsigned int flags); ++long vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out, ++ loff_t *ppos, size_t len, unsigned int flags); ++ ++static inline long vfsub_truncate(struct path *path, loff_t length) ++{ ++ long err; ++ ++ lockdep_off(); ++ err = vfs_truncate(path, length); ++ lockdep_on(); ++ return err; ++} ++ ++int vfsub_trunc(struct path *h_path, loff_t length, unsigned int attr, ++ struct file *h_file); ++int vfsub_fsync(struct file *file, struct path *path, int datasync); ++ ++/* ++ * re-use branch fs's ioctl(FICLONE) while aufs itself doesn't support such ++ * ioctl. ++ */ ++static inline int vfsub_clone_file_range(struct file *src, struct file *dst, ++ u64 len) ++{ ++ int err; ++ ++ lockdep_off(); ++ err = vfs_clone_file_range(src, 0, dst, 0, len); ++ lockdep_on(); ++ ++ return err; ++} ++ ++/* copy_file_range(2) is a systemcall */ ++static inline ssize_t vfsub_copy_file_range(struct file *src, loff_t src_pos, ++ struct file *dst, loff_t dst_pos, ++ size_t len, unsigned int flags) ++{ ++ ssize_t ssz; ++ ++ lockdep_off(); ++ ssz = vfs_copy_file_range(src, src_pos, dst, dst_pos, len, flags); ++ lockdep_on(); ++ ++ return ssz; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline loff_t vfsub_llseek(struct file *file, loff_t offset, int origin) ++{ ++ loff_t err; ++ ++ lockdep_off(); ++ err = vfs_llseek(file, offset, origin); ++ lockdep_on(); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int vfsub_sio_mkdir(struct inode *dir, struct path *path, int mode); ++int vfsub_sio_rmdir(struct inode *dir, struct path *path); ++int vfsub_sio_notify_change(struct path *path, struct iattr *ia, ++ struct inode **delegated_inode); ++int vfsub_notify_change(struct path *path, struct iattr *ia, ++ struct inode **delegated_inode); ++int vfsub_unlink(struct inode *dir, struct path *path, ++ struct inode **delegated_inode, int force); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline int vfsub_setxattr(struct dentry *dentry, const char *name, ++ const void *value, size_t size, int flags) ++{ ++ int err; ++ ++ lockdep_off(); ++ err = vfs_setxattr(dentry, name, value, size, flags); ++ lockdep_on(); ++ ++ return err; ++} ++ ++static inline int vfsub_removexattr(struct dentry *dentry, const char *name) ++{ ++ int err; ++ ++ lockdep_off(); ++ err = vfs_removexattr(dentry, name); ++ lockdep_on(); ++ ++ return err; ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_VFSUB_H__ */ +diff --git a/fs/aufs/wbr_policy.c b/fs/aufs/wbr_policy.c +new file mode 100644 +index 00000000..d94e8983 +--- /dev/null ++++ b/fs/aufs/wbr_policy.c +@@ -0,0 +1,829 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * policies for selecting one among multiple writable branches ++ */ ++ ++#include ++#include "aufs.h" ++ ++/* subset of cpup_attr() */ ++static noinline_for_stack ++int au_cpdown_attr(struct path *h_path, struct dentry *h_src) ++{ ++ int err, sbits; ++ struct iattr ia; ++ struct inode *h_isrc; ++ ++ h_isrc = d_inode(h_src); ++ ia.ia_valid = ATTR_FORCE | ATTR_MODE | ATTR_UID | ATTR_GID; ++ ia.ia_mode = h_isrc->i_mode; ++ ia.ia_uid = h_isrc->i_uid; ++ ia.ia_gid = h_isrc->i_gid; ++ sbits = !!(ia.ia_mode & (S_ISUID | S_ISGID)); ++ au_cpup_attr_flags(d_inode(h_path->dentry), h_isrc->i_flags); ++ /* no delegation since it is just created */ ++ err = vfsub_sio_notify_change(h_path, &ia, /*delegated*/NULL); ++ ++ /* is this nfs only? */ ++ if (!err && sbits && au_test_nfs(h_path->dentry->d_sb)) { ++ ia.ia_valid = ATTR_FORCE | ATTR_MODE; ++ ia.ia_mode = h_isrc->i_mode; ++ err = vfsub_sio_notify_change(h_path, &ia, /*delegated*/NULL); ++ } ++ ++ return err; ++} ++ ++#define AuCpdown_PARENT_OPQ 1 ++#define AuCpdown_WHED (1 << 1) ++#define AuCpdown_MADE_DIR (1 << 2) ++#define AuCpdown_DIROPQ (1 << 3) ++#define au_ftest_cpdown(flags, name) ((flags) & AuCpdown_##name) ++#define au_fset_cpdown(flags, name) \ ++ do { (flags) |= AuCpdown_##name; } while (0) ++#define au_fclr_cpdown(flags, name) \ ++ do { (flags) &= ~AuCpdown_##name; } while (0) ++ ++static int au_cpdown_dir_opq(struct dentry *dentry, aufs_bindex_t bdst, ++ unsigned int *flags) ++{ ++ int err; ++ struct dentry *opq_dentry; ++ ++ opq_dentry = au_diropq_create(dentry, bdst); ++ err = PTR_ERR(opq_dentry); ++ if (IS_ERR(opq_dentry)) ++ goto out; ++ dput(opq_dentry); ++ au_fset_cpdown(*flags, DIROPQ); ++ ++out: ++ return err; ++} ++ ++static int au_cpdown_dir_wh(struct dentry *dentry, struct dentry *h_parent, ++ struct inode *dir, aufs_bindex_t bdst) ++{ ++ int err; ++ struct path h_path; ++ struct au_branch *br; ++ ++ br = au_sbr(dentry->d_sb, bdst); ++ h_path.dentry = au_wh_lkup(h_parent, &dentry->d_name, br); ++ err = PTR_ERR(h_path.dentry); ++ if (IS_ERR(h_path.dentry)) ++ goto out; ++ ++ err = 0; ++ if (d_is_positive(h_path.dentry)) { ++ h_path.mnt = au_br_mnt(br); ++ err = au_wh_unlink_dentry(au_h_iptr(dir, bdst), &h_path, ++ dentry); ++ } ++ dput(h_path.dentry); ++ ++out: ++ return err; ++} ++ ++static int au_cpdown_dir(struct dentry *dentry, aufs_bindex_t bdst, ++ struct au_pin *pin, ++ struct dentry *h_parent, void *arg) ++{ ++ int err, rerr; ++ aufs_bindex_t bopq, btop; ++ struct path h_path; ++ struct dentry *parent; ++ struct inode *h_dir, *h_inode, *inode, *dir; ++ unsigned int *flags = arg; ++ ++ btop = au_dbtop(dentry); ++ /* dentry is di-locked */ ++ parent = dget_parent(dentry); ++ dir = d_inode(parent); ++ h_dir = d_inode(h_parent); ++ AuDebugOn(h_dir != au_h_iptr(dir, bdst)); ++ IMustLock(h_dir); ++ ++ err = au_lkup_neg(dentry, bdst, /*wh*/0); ++ if (unlikely(err < 0)) ++ goto out; ++ h_path.dentry = au_h_dptr(dentry, bdst); ++ h_path.mnt = au_sbr_mnt(dentry->d_sb, bdst); ++ err = vfsub_sio_mkdir(au_h_iptr(dir, bdst), &h_path, 0755); ++ if (unlikely(err)) ++ goto out_put; ++ au_fset_cpdown(*flags, MADE_DIR); ++ ++ bopq = au_dbdiropq(dentry); ++ au_fclr_cpdown(*flags, WHED); ++ au_fclr_cpdown(*flags, DIROPQ); ++ if (au_dbwh(dentry) == bdst) ++ au_fset_cpdown(*flags, WHED); ++ if (!au_ftest_cpdown(*flags, PARENT_OPQ) && bopq <= bdst) ++ au_fset_cpdown(*flags, PARENT_OPQ); ++ h_inode = d_inode(h_path.dentry); ++ inode_lock_nested(h_inode, AuLsc_I_CHILD); ++ if (au_ftest_cpdown(*flags, WHED)) { ++ err = au_cpdown_dir_opq(dentry, bdst, flags); ++ if (unlikely(err)) { ++ inode_unlock(h_inode); ++ goto out_dir; ++ } ++ } ++ ++ err = au_cpdown_attr(&h_path, au_h_dptr(dentry, btop)); ++ inode_unlock(h_inode); ++ if (unlikely(err)) ++ goto out_opq; ++ ++ if (au_ftest_cpdown(*flags, WHED)) { ++ err = au_cpdown_dir_wh(dentry, h_parent, dir, bdst); ++ if (unlikely(err)) ++ goto out_opq; ++ } ++ ++ inode = d_inode(dentry); ++ if (au_ibbot(inode) < bdst) ++ au_set_ibbot(inode, bdst); ++ au_set_h_iptr(inode, bdst, au_igrab(h_inode), ++ au_hi_flags(inode, /*isdir*/1)); ++ au_fhsm_wrote(dentry->d_sb, bdst, /*force*/0); ++ goto out; /* success */ ++ ++ /* revert */ ++out_opq: ++ if (au_ftest_cpdown(*flags, DIROPQ)) { ++ inode_lock_nested(h_inode, AuLsc_I_CHILD); ++ rerr = au_diropq_remove(dentry, bdst); ++ inode_unlock(h_inode); ++ if (unlikely(rerr)) { ++ AuIOErr("failed removing diropq for %pd b%d (%d)\n", ++ dentry, bdst, rerr); ++ err = -EIO; ++ goto out; ++ } ++ } ++out_dir: ++ if (au_ftest_cpdown(*flags, MADE_DIR)) { ++ rerr = vfsub_sio_rmdir(au_h_iptr(dir, bdst), &h_path); ++ if (unlikely(rerr)) { ++ AuIOErr("failed removing %pd b%d (%d)\n", ++ dentry, bdst, rerr); ++ err = -EIO; ++ } ++ } ++out_put: ++ au_set_h_dptr(dentry, bdst, NULL); ++ if (au_dbbot(dentry) == bdst) ++ au_update_dbbot(dentry); ++out: ++ dput(parent); ++ return err; ++} ++ ++int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst) ++{ ++ int err; ++ unsigned int flags; ++ ++ flags = 0; ++ err = au_cp_dirs(dentry, bdst, au_cpdown_dir, &flags); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* policies for create */ ++ ++int au_wbr_nonopq(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ int err, i, j, ndentry; ++ aufs_bindex_t bopq; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry **dentries, *parent, *d; ++ ++ err = au_dpages_init(&dpages, GFP_NOFS); ++ if (unlikely(err)) ++ goto out; ++ parent = dget_parent(dentry); ++ err = au_dcsub_pages_rev_aufs(&dpages, parent, /*do_include*/0); ++ if (unlikely(err)) ++ goto out_free; ++ ++ err = bindex; ++ for (i = 0; i < dpages.ndpage; i++) { ++ dpage = dpages.dpages + i; ++ dentries = dpage->dentries; ++ ndentry = dpage->ndentry; ++ for (j = 0; j < ndentry; j++) { ++ d = dentries[j]; ++ di_read_lock_parent2(d, !AuLock_IR); ++ bopq = au_dbdiropq(d); ++ di_read_unlock(d, !AuLock_IR); ++ if (bopq >= 0 && bopq < err) ++ err = bopq; ++ } ++ } ++ ++out_free: ++ dput(parent); ++ au_dpages_free(&dpages); ++out: ++ return err; ++} ++ ++static int au_wbr_bu(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ for (; bindex >= 0; bindex--) ++ if (!au_br_rdonly(au_sbr(sb, bindex))) ++ return bindex; ++ return -EROFS; ++} ++ ++/* top down parent */ ++static int au_wbr_create_tdp(struct dentry *dentry, ++ unsigned int flags __maybe_unused) ++{ ++ int err; ++ aufs_bindex_t btop, bindex; ++ struct super_block *sb; ++ struct dentry *parent, *h_parent; ++ ++ sb = dentry->d_sb; ++ btop = au_dbtop(dentry); ++ err = btop; ++ if (!au_br_rdonly(au_sbr(sb, btop))) ++ goto out; ++ ++ err = -EROFS; ++ parent = dget_parent(dentry); ++ for (bindex = au_dbtop(parent); bindex < btop; bindex++) { ++ h_parent = au_h_dptr(parent, bindex); ++ if (!h_parent || d_is_negative(h_parent)) ++ continue; ++ ++ if (!au_br_rdonly(au_sbr(sb, bindex))) { ++ err = bindex; ++ break; ++ } ++ } ++ dput(parent); ++ ++ /* bottom up here */ ++ if (unlikely(err < 0)) { ++ err = au_wbr_bu(sb, btop - 1); ++ if (err >= 0) ++ err = au_wbr_nonopq(dentry, err); ++ } ++ ++out: ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* an exception for the policy other than tdp */ ++static int au_wbr_create_exp(struct dentry *dentry) ++{ ++ int err; ++ aufs_bindex_t bwh, bdiropq; ++ struct dentry *parent; ++ ++ err = -1; ++ bwh = au_dbwh(dentry); ++ parent = dget_parent(dentry); ++ bdiropq = au_dbdiropq(parent); ++ if (bwh >= 0) { ++ if (bdiropq >= 0) ++ err = min(bdiropq, bwh); ++ else ++ err = bwh; ++ AuDbg("%d\n", err); ++ } else if (bdiropq >= 0) { ++ err = bdiropq; ++ AuDbg("%d\n", err); ++ } ++ dput(parent); ++ ++ if (err >= 0) ++ err = au_wbr_nonopq(dentry, err); ++ ++ if (err >= 0 && au_br_rdonly(au_sbr(dentry->d_sb, err))) ++ err = -1; ++ ++ AuDbg("%d\n", err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* round robin */ ++static int au_wbr_create_init_rr(struct super_block *sb) ++{ ++ int err; ++ ++ err = au_wbr_bu(sb, au_sbbot(sb)); ++ atomic_set(&au_sbi(sb)->si_wbr_rr_next, -err); /* less important */ ++ /* smp_mb(); */ ++ ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++static int au_wbr_create_rr(struct dentry *dentry, unsigned int flags) ++{ ++ int err, nbr; ++ unsigned int u; ++ aufs_bindex_t bindex, bbot; ++ struct super_block *sb; ++ atomic_t *next; ++ ++ err = au_wbr_create_exp(dentry); ++ if (err >= 0) ++ goto out; ++ ++ sb = dentry->d_sb; ++ next = &au_sbi(sb)->si_wbr_rr_next; ++ bbot = au_sbbot(sb); ++ nbr = bbot + 1; ++ for (bindex = 0; bindex <= bbot; bindex++) { ++ if (!au_ftest_wbr(flags, DIR)) { ++ err = atomic_dec_return(next) + 1; ++ /* modulo for 0 is meaningless */ ++ if (unlikely(!err)) ++ err = atomic_dec_return(next) + 1; ++ } else ++ err = atomic_read(next); ++ AuDbg("%d\n", err); ++ u = err; ++ err = u % nbr; ++ AuDbg("%d\n", err); ++ if (!au_br_rdonly(au_sbr(sb, err))) ++ break; ++ err = -EROFS; ++ } ++ ++ if (err >= 0) ++ err = au_wbr_nonopq(dentry, err); ++ ++out: ++ AuDbg("%d\n", err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* most free space */ ++static void au_mfs(struct dentry *dentry, struct dentry *parent) ++{ ++ struct super_block *sb; ++ struct au_branch *br; ++ struct au_wbr_mfs *mfs; ++ struct dentry *h_parent; ++ aufs_bindex_t bindex, bbot; ++ int err; ++ unsigned long long b, bavail; ++ struct path h_path; ++ /* reduce the stack usage */ ++ struct kstatfs *st; ++ ++ st = kmalloc(sizeof(*st), GFP_NOFS); ++ if (unlikely(!st)) { ++ AuWarn1("failed updating mfs(%d), ignored\n", -ENOMEM); ++ return; ++ } ++ ++ bavail = 0; ++ sb = dentry->d_sb; ++ mfs = &au_sbi(sb)->si_wbr_mfs; ++ MtxMustLock(&mfs->mfs_lock); ++ mfs->mfs_bindex = -EROFS; ++ mfs->mfsrr_bytes = 0; ++ if (!parent) { ++ bindex = 0; ++ bbot = au_sbbot(sb); ++ } else { ++ bindex = au_dbtop(parent); ++ bbot = au_dbtaildir(parent); ++ } ++ ++ for (; bindex <= bbot; bindex++) { ++ if (parent) { ++ h_parent = au_h_dptr(parent, bindex); ++ if (!h_parent || d_is_negative(h_parent)) ++ continue; ++ } ++ br = au_sbr(sb, bindex); ++ if (au_br_rdonly(br)) ++ continue; ++ ++ /* sb->s_root for NFS is unreliable */ ++ h_path.mnt = au_br_mnt(br); ++ h_path.dentry = h_path.mnt->mnt_root; ++ err = vfs_statfs(&h_path, st); ++ if (unlikely(err)) { ++ AuWarn1("failed statfs, b%d, %d\n", bindex, err); ++ continue; ++ } ++ ++ /* when the available size is equal, select the lower one */ ++ BUILD_BUG_ON(sizeof(b) < sizeof(st->f_bavail) ++ || sizeof(b) < sizeof(st->f_bsize)); ++ b = st->f_bavail * st->f_bsize; ++ br->br_wbr->wbr_bytes = b; ++ if (b >= bavail) { ++ bavail = b; ++ mfs->mfs_bindex = bindex; ++ mfs->mfs_jiffy = jiffies; ++ } ++ } ++ ++ mfs->mfsrr_bytes = bavail; ++ AuDbg("b%d\n", mfs->mfs_bindex); ++ kfree(st); ++} ++ ++static int au_wbr_create_mfs(struct dentry *dentry, unsigned int flags) ++{ ++ int err; ++ struct dentry *parent; ++ struct super_block *sb; ++ struct au_wbr_mfs *mfs; ++ ++ err = au_wbr_create_exp(dentry); ++ if (err >= 0) ++ goto out; ++ ++ sb = dentry->d_sb; ++ parent = NULL; ++ if (au_ftest_wbr(flags, PARENT)) ++ parent = dget_parent(dentry); ++ mfs = &au_sbi(sb)->si_wbr_mfs; ++ mutex_lock(&mfs->mfs_lock); ++ if (time_after(jiffies, mfs->mfs_jiffy + mfs->mfs_expire) ++ || mfs->mfs_bindex < 0 ++ || au_br_rdonly(au_sbr(sb, mfs->mfs_bindex))) ++ au_mfs(dentry, parent); ++ mutex_unlock(&mfs->mfs_lock); ++ err = mfs->mfs_bindex; ++ dput(parent); ++ ++ if (err >= 0) ++ err = au_wbr_nonopq(dentry, err); ++ ++out: ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++static int au_wbr_create_init_mfs(struct super_block *sb) ++{ ++ struct au_wbr_mfs *mfs; ++ ++ mfs = &au_sbi(sb)->si_wbr_mfs; ++ mutex_init(&mfs->mfs_lock); ++ mfs->mfs_jiffy = 0; ++ mfs->mfs_bindex = -EROFS; ++ ++ return 0; ++} ++ ++static int au_wbr_create_fin_mfs(struct super_block *sb __maybe_unused) ++{ ++ mutex_destroy(&au_sbi(sb)->si_wbr_mfs.mfs_lock); ++ return 0; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* top down regardless parent, and then mfs */ ++static int au_wbr_create_tdmfs(struct dentry *dentry, ++ unsigned int flags __maybe_unused) ++{ ++ int err; ++ aufs_bindex_t bwh, btail, bindex, bfound, bmfs; ++ unsigned long long watermark; ++ struct super_block *sb; ++ struct au_wbr_mfs *mfs; ++ struct au_branch *br; ++ struct dentry *parent; ++ ++ sb = dentry->d_sb; ++ mfs = &au_sbi(sb)->si_wbr_mfs; ++ mutex_lock(&mfs->mfs_lock); ++ if (time_after(jiffies, mfs->mfs_jiffy + mfs->mfs_expire) ++ || mfs->mfs_bindex < 0) ++ au_mfs(dentry, /*parent*/NULL); ++ watermark = mfs->mfsrr_watermark; ++ bmfs = mfs->mfs_bindex; ++ mutex_unlock(&mfs->mfs_lock); ++ ++ /* another style of au_wbr_create_exp() */ ++ bwh = au_dbwh(dentry); ++ parent = dget_parent(dentry); ++ btail = au_dbtaildir(parent); ++ if (bwh >= 0 && bwh < btail) ++ btail = bwh; ++ ++ err = au_wbr_nonopq(dentry, btail); ++ if (unlikely(err < 0)) ++ goto out; ++ btail = err; ++ bfound = -1; ++ for (bindex = 0; bindex <= btail; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (au_br_rdonly(br)) ++ continue; ++ if (br->br_wbr->wbr_bytes > watermark) { ++ bfound = bindex; ++ break; ++ } ++ } ++ err = bfound; ++ if (err < 0) ++ err = bmfs; ++ ++out: ++ dput(parent); ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* most free space and then round robin */ ++static int au_wbr_create_mfsrr(struct dentry *dentry, unsigned int flags) ++{ ++ int err; ++ struct au_wbr_mfs *mfs; ++ ++ err = au_wbr_create_mfs(dentry, flags); ++ if (err >= 0) { ++ mfs = &au_sbi(dentry->d_sb)->si_wbr_mfs; ++ mutex_lock(&mfs->mfs_lock); ++ if (mfs->mfsrr_bytes < mfs->mfsrr_watermark) ++ err = au_wbr_create_rr(dentry, flags); ++ mutex_unlock(&mfs->mfs_lock); ++ } ++ ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++static int au_wbr_create_init_mfsrr(struct super_block *sb) ++{ ++ int err; ++ ++ au_wbr_create_init_mfs(sb); /* ignore */ ++ err = au_wbr_create_init_rr(sb); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* top down parent and most free space */ ++static int au_wbr_create_pmfs(struct dentry *dentry, unsigned int flags) ++{ ++ int err, e2; ++ unsigned long long b; ++ aufs_bindex_t bindex, btop, bbot; ++ struct super_block *sb; ++ struct dentry *parent, *h_parent; ++ struct au_branch *br; ++ ++ err = au_wbr_create_tdp(dentry, flags); ++ if (unlikely(err < 0)) ++ goto out; ++ parent = dget_parent(dentry); ++ btop = au_dbtop(parent); ++ bbot = au_dbtaildir(parent); ++ if (btop == bbot) ++ goto out_parent; /* success */ ++ ++ e2 = au_wbr_create_mfs(dentry, flags); ++ if (e2 < 0) ++ goto out_parent; /* success */ ++ ++ /* when the available size is equal, select upper one */ ++ sb = dentry->d_sb; ++ br = au_sbr(sb, err); ++ b = br->br_wbr->wbr_bytes; ++ AuDbg("b%d, %llu\n", err, b); ++ ++ for (bindex = btop; bindex <= bbot; bindex++) { ++ h_parent = au_h_dptr(parent, bindex); ++ if (!h_parent || d_is_negative(h_parent)) ++ continue; ++ ++ br = au_sbr(sb, bindex); ++ if (!au_br_rdonly(br) && br->br_wbr->wbr_bytes > b) { ++ b = br->br_wbr->wbr_bytes; ++ err = bindex; ++ AuDbg("b%d, %llu\n", err, b); ++ } ++ } ++ ++ if (err >= 0) ++ err = au_wbr_nonopq(dentry, err); ++ ++out_parent: ++ dput(parent); ++out: ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * - top down parent ++ * - most free space with parent ++ * - most free space round-robin regardless parent ++ */ ++static int au_wbr_create_pmfsrr(struct dentry *dentry, unsigned int flags) ++{ ++ int err; ++ unsigned long long watermark; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct au_wbr_mfs *mfs; ++ ++ err = au_wbr_create_pmfs(dentry, flags | AuWbr_PARENT); ++ if (unlikely(err < 0)) ++ goto out; ++ ++ sb = dentry->d_sb; ++ br = au_sbr(sb, err); ++ mfs = &au_sbi(sb)->si_wbr_mfs; ++ mutex_lock(&mfs->mfs_lock); ++ watermark = mfs->mfsrr_watermark; ++ mutex_unlock(&mfs->mfs_lock); ++ if (br->br_wbr->wbr_bytes < watermark) ++ /* regardless the parent dir */ ++ err = au_wbr_create_mfsrr(dentry, flags); ++ ++out: ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* policies for copyup */ ++ ++/* top down parent */ ++static int au_wbr_copyup_tdp(struct dentry *dentry) ++{ ++ return au_wbr_create_tdp(dentry, /*flags, anything is ok*/0); ++} ++ ++/* bottom up parent */ ++static int au_wbr_copyup_bup(struct dentry *dentry) ++{ ++ int err; ++ aufs_bindex_t bindex, btop; ++ struct dentry *parent, *h_parent; ++ struct super_block *sb; ++ ++ err = -EROFS; ++ sb = dentry->d_sb; ++ parent = dget_parent(dentry); ++ btop = au_dbtop(parent); ++ for (bindex = au_dbtop(dentry); bindex >= btop; bindex--) { ++ h_parent = au_h_dptr(parent, bindex); ++ if (!h_parent || d_is_negative(h_parent)) ++ continue; ++ ++ if (!au_br_rdonly(au_sbr(sb, bindex))) { ++ err = bindex; ++ break; ++ } ++ } ++ dput(parent); ++ ++ /* bottom up here */ ++ if (unlikely(err < 0)) ++ err = au_wbr_bu(sb, btop - 1); ++ ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++/* bottom up */ ++int au_wbr_do_copyup_bu(struct dentry *dentry, aufs_bindex_t btop) ++{ ++ int err; ++ ++ err = au_wbr_bu(dentry->d_sb, btop); ++ AuDbg("b%d\n", err); ++ if (err > btop) ++ err = au_wbr_nonopq(dentry, err); ++ ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++static int au_wbr_copyup_bu(struct dentry *dentry) ++{ ++ int err; ++ aufs_bindex_t btop; ++ ++ btop = au_dbtop(dentry); ++ err = au_wbr_do_copyup_bu(dentry, btop); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_wbr_copyup_operations au_wbr_copyup_ops[] = { ++ [AuWbrCopyup_TDP] = { ++ .copyup = au_wbr_copyup_tdp ++ }, ++ [AuWbrCopyup_BUP] = { ++ .copyup = au_wbr_copyup_bup ++ }, ++ [AuWbrCopyup_BU] = { ++ .copyup = au_wbr_copyup_bu ++ } ++}; ++ ++struct au_wbr_create_operations au_wbr_create_ops[] = { ++ [AuWbrCreate_TDP] = { ++ .create = au_wbr_create_tdp ++ }, ++ [AuWbrCreate_RR] = { ++ .create = au_wbr_create_rr, ++ .init = au_wbr_create_init_rr ++ }, ++ [AuWbrCreate_MFS] = { ++ .create = au_wbr_create_mfs, ++ .init = au_wbr_create_init_mfs, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_MFSV] = { ++ .create = au_wbr_create_mfs, ++ .init = au_wbr_create_init_mfs, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_MFSRR] = { ++ .create = au_wbr_create_mfsrr, ++ .init = au_wbr_create_init_mfsrr, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_MFSRRV] = { ++ .create = au_wbr_create_mfsrr, ++ .init = au_wbr_create_init_mfsrr, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_TDMFS] = { ++ .create = au_wbr_create_tdmfs, ++ .init = au_wbr_create_init_mfs, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_TDMFSV] = { ++ .create = au_wbr_create_tdmfs, ++ .init = au_wbr_create_init_mfs, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_PMFS] = { ++ .create = au_wbr_create_pmfs, ++ .init = au_wbr_create_init_mfs, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_PMFSV] = { ++ .create = au_wbr_create_pmfs, ++ .init = au_wbr_create_init_mfs, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_PMFSRR] = { ++ .create = au_wbr_create_pmfsrr, ++ .init = au_wbr_create_init_mfsrr, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_PMFSRRV] = { ++ .create = au_wbr_create_pmfsrr, ++ .init = au_wbr_create_init_mfsrr, ++ .fin = au_wbr_create_fin_mfs ++ } ++}; +diff --git a/fs/aufs/whout.c b/fs/aufs/whout.c +new file mode 100644 +index 00000000..2d5e8d6b +--- /dev/null ++++ b/fs/aufs/whout.c +@@ -0,0 +1,1061 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * whiteout for logical deletion and opaque directory ++ */ ++ ++#include "aufs.h" ++ ++#define WH_MASK 0444 ++ ++/* ++ * If a directory contains this file, then it is opaque. We start with the ++ * .wh. flag so that it is blocked by lookup. ++ */ ++static struct qstr diropq_name = QSTR_INIT(AUFS_WH_DIROPQ, ++ sizeof(AUFS_WH_DIROPQ) - 1); ++ ++/* ++ * generate whiteout name, which is NOT terminated by NULL. ++ * @name: original d_name.name ++ * @len: original d_name.len ++ * @wh: whiteout qstr ++ * returns zero when succeeds, otherwise error. ++ * succeeded value as wh->name should be freed by kfree(). ++ */ ++int au_wh_name_alloc(struct qstr *wh, const struct qstr *name) ++{ ++ char *p; ++ ++ if (unlikely(name->len > PATH_MAX - AUFS_WH_PFX_LEN)) ++ return -ENAMETOOLONG; ++ ++ wh->len = name->len + AUFS_WH_PFX_LEN; ++ p = kmalloc(wh->len, GFP_NOFS); ++ wh->name = p; ++ if (p) { ++ memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN); ++ memcpy(p + AUFS_WH_PFX_LEN, name->name, name->len); ++ /* smp_mb(); */ ++ return 0; ++ } ++ return -ENOMEM; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * test if the @wh_name exists under @h_parent. ++ * @try_sio specifies the necessary of super-io. ++ */ ++int au_wh_test(struct dentry *h_parent, struct qstr *wh_name, int try_sio) ++{ ++ int err; ++ struct dentry *wh_dentry; ++ ++ if (!try_sio) ++ wh_dentry = vfsub_lkup_one(wh_name, h_parent); ++ else ++ wh_dentry = au_sio_lkup_one(wh_name, h_parent); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) { ++ if (err == -ENAMETOOLONG) ++ err = 0; ++ goto out; ++ } ++ ++ err = 0; ++ if (d_is_negative(wh_dentry)) ++ goto out_wh; /* success */ ++ ++ err = 1; ++ if (d_is_reg(wh_dentry)) ++ goto out_wh; /* success */ ++ ++ err = -EIO; ++ AuIOErr("%pd Invalid whiteout entry type 0%o.\n", ++ wh_dentry, d_inode(wh_dentry)->i_mode); ++ ++out_wh: ++ dput(wh_dentry); ++out: ++ return err; ++} ++ ++/* ++ * test if the @h_dentry sets opaque or not. ++ */ ++int au_diropq_test(struct dentry *h_dentry) ++{ ++ int err; ++ struct inode *h_dir; ++ ++ h_dir = d_inode(h_dentry); ++ err = au_wh_test(h_dentry, &diropq_name, ++ au_test_h_perm_sio(h_dir, MAY_EXEC)); ++ return err; ++} ++ ++/* ++ * returns a negative dentry whose name is unique and temporary. ++ */ ++struct dentry *au_whtmp_lkup(struct dentry *h_parent, struct au_branch *br, ++ struct qstr *prefix) ++{ ++ struct dentry *dentry; ++ int i; ++ char defname[NAME_MAX - AUFS_MAX_NAMELEN + DNAME_INLINE_LEN + 1], ++ *name, *p; ++ /* strict atomic_t is unnecessary here */ ++ static unsigned short cnt; ++ struct qstr qs; ++ ++ BUILD_BUG_ON(sizeof(cnt) * 2 > AUFS_WH_TMP_LEN); ++ ++ name = defname; ++ qs.len = sizeof(defname) - DNAME_INLINE_LEN + prefix->len - 1; ++ if (unlikely(prefix->len > DNAME_INLINE_LEN)) { ++ dentry = ERR_PTR(-ENAMETOOLONG); ++ if (unlikely(qs.len > NAME_MAX)) ++ goto out; ++ dentry = ERR_PTR(-ENOMEM); ++ name = kmalloc(qs.len + 1, GFP_NOFS); ++ if (unlikely(!name)) ++ goto out; ++ } ++ ++ /* doubly whiteout-ed */ ++ memcpy(name, AUFS_WH_PFX AUFS_WH_PFX, AUFS_WH_PFX_LEN * 2); ++ p = name + AUFS_WH_PFX_LEN * 2; ++ memcpy(p, prefix->name, prefix->len); ++ p += prefix->len; ++ *p++ = '.'; ++ AuDebugOn(name + qs.len + 1 - p <= AUFS_WH_TMP_LEN); ++ ++ qs.name = name; ++ for (i = 0; i < 3; i++) { ++ sprintf(p, "%.*x", AUFS_WH_TMP_LEN, cnt++); ++ dentry = au_sio_lkup_one(&qs, h_parent); ++ if (IS_ERR(dentry) || d_is_negative(dentry)) ++ goto out_name; ++ dput(dentry); ++ } ++ /* pr_warn("could not get random name\n"); */ ++ dentry = ERR_PTR(-EEXIST); ++ AuDbg("%.*s\n", AuLNPair(&qs)); ++ BUG(); ++ ++out_name: ++ if (name != defname) ++ kfree(name); ++out: ++ AuTraceErrPtr(dentry); ++ return dentry; ++} ++ ++/* ++ * rename the @h_dentry on @br to the whiteouted temporary name. ++ */ ++int au_whtmp_ren(struct dentry *h_dentry, struct au_branch *br) ++{ ++ int err; ++ struct path h_path = { ++ .mnt = au_br_mnt(br) ++ }; ++ struct inode *h_dir, *delegated; ++ struct dentry *h_parent; ++ ++ h_parent = h_dentry->d_parent; /* dir inode is locked */ ++ h_dir = d_inode(h_parent); ++ IMustLock(h_dir); ++ ++ h_path.dentry = au_whtmp_lkup(h_parent, br, &h_dentry->d_name); ++ err = PTR_ERR(h_path.dentry); ++ if (IS_ERR(h_path.dentry)) ++ goto out; ++ ++ /* under the same dir, no need to lock_rename() */ ++ delegated = NULL; ++ err = vfsub_rename(h_dir, h_dentry, h_dir, &h_path, &delegated, ++ /*flags*/0); ++ AuTraceErr(err); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal rename\n"); ++ iput(delegated); ++ } ++ dput(h_path.dentry); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* ++ * functions for removing a whiteout ++ */ ++ ++static int do_unlink_wh(struct inode *h_dir, struct path *h_path) ++{ ++ int err, force; ++ struct inode *delegated; ++ ++ /* ++ * forces superio when the dir has a sticky bit. ++ * this may be a violation of unix fs semantics. ++ */ ++ force = (h_dir->i_mode & S_ISVTX) ++ && !uid_eq(current_fsuid(), d_inode(h_path->dentry)->i_uid); ++ delegated = NULL; ++ err = vfsub_unlink(h_dir, h_path, &delegated, force); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal unlink\n"); ++ iput(delegated); ++ } ++ return err; ++} ++ ++int au_wh_unlink_dentry(struct inode *h_dir, struct path *h_path, ++ struct dentry *dentry) ++{ ++ int err; ++ ++ err = do_unlink_wh(h_dir, h_path); ++ if (!err && dentry) ++ au_set_dbwh(dentry, -1); ++ ++ return err; ++} ++ ++static int unlink_wh_name(struct dentry *h_parent, struct qstr *wh, ++ struct au_branch *br) ++{ ++ int err; ++ struct path h_path = { ++ .mnt = au_br_mnt(br) ++ }; ++ ++ err = 0; ++ h_path.dentry = vfsub_lkup_one(wh, h_parent); ++ if (IS_ERR(h_path.dentry)) ++ err = PTR_ERR(h_path.dentry); ++ else { ++ if (d_is_reg(h_path.dentry)) ++ err = do_unlink_wh(d_inode(h_parent), &h_path); ++ dput(h_path.dentry); ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* ++ * initialize/clean whiteout for a branch ++ */ ++ ++static void au_wh_clean(struct inode *h_dir, struct path *whpath, ++ const int isdir) ++{ ++ int err; ++ struct inode *delegated; ++ ++ if (d_is_negative(whpath->dentry)) ++ return; ++ ++ if (isdir) ++ err = vfsub_rmdir(h_dir, whpath); ++ else { ++ delegated = NULL; ++ err = vfsub_unlink(h_dir, whpath, &delegated, /*force*/0); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal unlink\n"); ++ iput(delegated); ++ } ++ } ++ if (unlikely(err)) ++ pr_warn("failed removing %pd (%d), ignored.\n", ++ whpath->dentry, err); ++} ++ ++static int test_linkable(struct dentry *h_root) ++{ ++ struct inode *h_dir = d_inode(h_root); ++ ++ if (h_dir->i_op->link) ++ return 0; ++ ++ pr_err("%pd (%s) doesn't support link(2), use noplink and rw+nolwh\n", ++ h_root, au_sbtype(h_root->d_sb)); ++ return -ENOSYS; ++} ++ ++/* todo: should this mkdir be done in /sbin/mount.aufs helper? */ ++static int au_whdir(struct inode *h_dir, struct path *path) ++{ ++ int err; ++ ++ err = -EEXIST; ++ if (d_is_negative(path->dentry)) { ++ int mode = 0700; ++ ++ if (au_test_nfs(path->dentry->d_sb)) ++ mode |= 0111; ++ err = vfsub_mkdir(h_dir, path, mode); ++ } else if (d_is_dir(path->dentry)) ++ err = 0; ++ else ++ pr_err("unknown %pd exists\n", path->dentry); ++ ++ return err; ++} ++ ++struct au_wh_base { ++ const struct qstr *name; ++ struct dentry *dentry; ++}; ++ ++static void au_wh_init_ro(struct inode *h_dir, struct au_wh_base base[], ++ struct path *h_path) ++{ ++ h_path->dentry = base[AuBrWh_BASE].dentry; ++ au_wh_clean(h_dir, h_path, /*isdir*/0); ++ h_path->dentry = base[AuBrWh_PLINK].dentry; ++ au_wh_clean(h_dir, h_path, /*isdir*/1); ++ h_path->dentry = base[AuBrWh_ORPH].dentry; ++ au_wh_clean(h_dir, h_path, /*isdir*/1); ++} ++ ++/* ++ * returns tri-state, ++ * minus: error, caller should print the message ++ * zero: succuess ++ * plus: error, caller should NOT print the message ++ */ ++static int au_wh_init_rw_nolink(struct dentry *h_root, struct au_wbr *wbr, ++ int do_plink, struct au_wh_base base[], ++ struct path *h_path) ++{ ++ int err; ++ struct inode *h_dir; ++ ++ h_dir = d_inode(h_root); ++ h_path->dentry = base[AuBrWh_BASE].dentry; ++ au_wh_clean(h_dir, h_path, /*isdir*/0); ++ h_path->dentry = base[AuBrWh_PLINK].dentry; ++ if (do_plink) { ++ err = test_linkable(h_root); ++ if (unlikely(err)) { ++ err = 1; ++ goto out; ++ } ++ ++ err = au_whdir(h_dir, h_path); ++ if (unlikely(err)) ++ goto out; ++ wbr->wbr_plink = dget(base[AuBrWh_PLINK].dentry); ++ } else ++ au_wh_clean(h_dir, h_path, /*isdir*/1); ++ h_path->dentry = base[AuBrWh_ORPH].dentry; ++ err = au_whdir(h_dir, h_path); ++ if (unlikely(err)) ++ goto out; ++ wbr->wbr_orph = dget(base[AuBrWh_ORPH].dentry); ++ ++out: ++ return err; ++} ++ ++/* ++ * for the moment, aufs supports the branch filesystem which does not support ++ * link(2). testing on FAT which does not support i_op->setattr() fully either, ++ * copyup failed. finally, such filesystem will not be used as the writable ++ * branch. ++ * ++ * returns tri-state, see above. ++ */ ++static int au_wh_init_rw(struct dentry *h_root, struct au_wbr *wbr, ++ int do_plink, struct au_wh_base base[], ++ struct path *h_path) ++{ ++ int err; ++ struct inode *h_dir; ++ ++ WbrWhMustWriteLock(wbr); ++ ++ err = test_linkable(h_root); ++ if (unlikely(err)) { ++ err = 1; ++ goto out; ++ } ++ ++ /* ++ * todo: should this create be done in /sbin/mount.aufs helper? ++ */ ++ err = -EEXIST; ++ h_dir = d_inode(h_root); ++ if (d_is_negative(base[AuBrWh_BASE].dentry)) { ++ h_path->dentry = base[AuBrWh_BASE].dentry; ++ err = vfsub_create(h_dir, h_path, WH_MASK, /*want_excl*/true); ++ } else if (d_is_reg(base[AuBrWh_BASE].dentry)) ++ err = 0; ++ else ++ pr_err("unknown %pd2 exists\n", base[AuBrWh_BASE].dentry); ++ if (unlikely(err)) ++ goto out; ++ ++ h_path->dentry = base[AuBrWh_PLINK].dentry; ++ if (do_plink) { ++ err = au_whdir(h_dir, h_path); ++ if (unlikely(err)) ++ goto out; ++ wbr->wbr_plink = dget(base[AuBrWh_PLINK].dentry); ++ } else ++ au_wh_clean(h_dir, h_path, /*isdir*/1); ++ wbr->wbr_whbase = dget(base[AuBrWh_BASE].dentry); ++ ++ h_path->dentry = base[AuBrWh_ORPH].dentry; ++ err = au_whdir(h_dir, h_path); ++ if (unlikely(err)) ++ goto out; ++ wbr->wbr_orph = dget(base[AuBrWh_ORPH].dentry); ++ ++out: ++ return err; ++} ++ ++/* ++ * initialize the whiteout base file/dir for @br. ++ */ ++int au_wh_init(struct au_branch *br, struct super_block *sb) ++{ ++ int err, i; ++ const unsigned char do_plink ++ = !!au_opt_test(au_mntflags(sb), PLINK); ++ struct inode *h_dir; ++ struct path path = br->br_path; ++ struct dentry *h_root = path.dentry; ++ struct au_wbr *wbr = br->br_wbr; ++ static const struct qstr base_name[] = { ++ [AuBrWh_BASE] = QSTR_INIT(AUFS_BASE_NAME, ++ sizeof(AUFS_BASE_NAME) - 1), ++ [AuBrWh_PLINK] = QSTR_INIT(AUFS_PLINKDIR_NAME, ++ sizeof(AUFS_PLINKDIR_NAME) - 1), ++ [AuBrWh_ORPH] = QSTR_INIT(AUFS_ORPHDIR_NAME, ++ sizeof(AUFS_ORPHDIR_NAME) - 1) ++ }; ++ struct au_wh_base base[] = { ++ [AuBrWh_BASE] = { ++ .name = base_name + AuBrWh_BASE, ++ .dentry = NULL ++ }, ++ [AuBrWh_PLINK] = { ++ .name = base_name + AuBrWh_PLINK, ++ .dentry = NULL ++ }, ++ [AuBrWh_ORPH] = { ++ .name = base_name + AuBrWh_ORPH, ++ .dentry = NULL ++ } ++ }; ++ ++ if (wbr) ++ WbrWhMustWriteLock(wbr); ++ ++ for (i = 0; i < AuBrWh_Last; i++) { ++ /* doubly whiteouted */ ++ struct dentry *d; ++ ++ d = au_wh_lkup(h_root, (void *)base[i].name, br); ++ err = PTR_ERR(d); ++ if (IS_ERR(d)) ++ goto out; ++ ++ base[i].dentry = d; ++ AuDebugOn(wbr ++ && wbr->wbr_wh[i] ++ && wbr->wbr_wh[i] != base[i].dentry); ++ } ++ ++ if (wbr) ++ for (i = 0; i < AuBrWh_Last; i++) { ++ dput(wbr->wbr_wh[i]); ++ wbr->wbr_wh[i] = NULL; ++ } ++ ++ err = 0; ++ if (!au_br_writable(br->br_perm)) { ++ h_dir = d_inode(h_root); ++ au_wh_init_ro(h_dir, base, &path); ++ } else if (!au_br_wh_linkable(br->br_perm)) { ++ err = au_wh_init_rw_nolink(h_root, wbr, do_plink, base, &path); ++ if (err > 0) ++ goto out; ++ else if (err) ++ goto out_err; ++ } else { ++ err = au_wh_init_rw(h_root, wbr, do_plink, base, &path); ++ if (err > 0) ++ goto out; ++ else if (err) ++ goto out_err; ++ } ++ goto out; /* success */ ++ ++out_err: ++ pr_err("an error(%d) on the writable branch %pd(%s)\n", ++ err, h_root, au_sbtype(h_root->d_sb)); ++out: ++ for (i = 0; i < AuBrWh_Last; i++) ++ dput(base[i].dentry); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* ++ * whiteouts are all hard-linked usually. ++ * when its link count reaches a ceiling, we create a new whiteout base ++ * asynchronously. ++ */ ++ ++struct reinit_br_wh { ++ struct super_block *sb; ++ struct au_branch *br; ++}; ++ ++static void reinit_br_wh(void *arg) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ struct path h_path; ++ struct reinit_br_wh *a = arg; ++ struct au_wbr *wbr; ++ struct inode *dir, *delegated; ++ struct dentry *h_root; ++ struct au_hinode *hdir; ++ ++ err = 0; ++ wbr = a->br->br_wbr; ++ /* big aufs lock */ ++ si_noflush_write_lock(a->sb); ++ if (!au_br_writable(a->br->br_perm)) ++ goto out; ++ bindex = au_br_index(a->sb, a->br->br_id); ++ if (unlikely(bindex < 0)) ++ goto out; ++ ++ di_read_lock_parent(a->sb->s_root, AuLock_IR); ++ dir = d_inode(a->sb->s_root); ++ hdir = au_hi(dir, bindex); ++ h_root = au_h_dptr(a->sb->s_root, bindex); ++ AuDebugOn(h_root != au_br_dentry(a->br)); ++ ++ au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); ++ wbr_wh_write_lock(wbr); ++ err = au_h_verify(wbr->wbr_whbase, au_opt_udba(a->sb), hdir->hi_inode, ++ h_root, a->br); ++ if (!err) { ++ h_path.dentry = wbr->wbr_whbase; ++ h_path.mnt = au_br_mnt(a->br); ++ delegated = NULL; ++ err = vfsub_unlink(hdir->hi_inode, &h_path, &delegated, ++ /*force*/0); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal unlink\n"); ++ iput(delegated); ++ } ++ } else { ++ pr_warn("%pd is moved, ignored\n", wbr->wbr_whbase); ++ err = 0; ++ } ++ dput(wbr->wbr_whbase); ++ wbr->wbr_whbase = NULL; ++ if (!err) ++ err = au_wh_init(a->br, a->sb); ++ wbr_wh_write_unlock(wbr); ++ au_hn_inode_unlock(hdir); ++ di_read_unlock(a->sb->s_root, AuLock_IR); ++ if (!err) ++ au_fhsm_wrote(a->sb, bindex, /*force*/0); ++ ++out: ++ if (wbr) ++ atomic_dec(&wbr->wbr_wh_running); ++ au_br_put(a->br); ++ si_write_unlock(a->sb); ++ au_nwt_done(&au_sbi(a->sb)->si_nowait); ++ kfree(arg); ++ if (unlikely(err)) ++ AuIOErr("err %d\n", err); ++} ++ ++static void kick_reinit_br_wh(struct super_block *sb, struct au_branch *br) ++{ ++ int do_dec, wkq_err; ++ struct reinit_br_wh *arg; ++ ++ do_dec = 1; ++ if (atomic_inc_return(&br->br_wbr->wbr_wh_running) != 1) ++ goto out; ++ ++ /* ignore ENOMEM */ ++ arg = kmalloc(sizeof(*arg), GFP_NOFS); ++ if (arg) { ++ /* ++ * dec(wh_running), kfree(arg) and dec(br_count) ++ * in reinit function ++ */ ++ arg->sb = sb; ++ arg->br = br; ++ au_br_get(br); ++ wkq_err = au_wkq_nowait(reinit_br_wh, arg, sb, /*flags*/0); ++ if (unlikely(wkq_err)) { ++ atomic_dec(&br->br_wbr->wbr_wh_running); ++ au_br_put(br); ++ kfree(arg); ++ } ++ do_dec = 0; ++ } ++ ++out: ++ if (do_dec) ++ atomic_dec(&br->br_wbr->wbr_wh_running); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * create the whiteout @wh. ++ */ ++static int link_or_create_wh(struct super_block *sb, aufs_bindex_t bindex, ++ struct dentry *wh) ++{ ++ int err; ++ struct path h_path = { ++ .dentry = wh ++ }; ++ struct au_branch *br; ++ struct au_wbr *wbr; ++ struct dentry *h_parent; ++ struct inode *h_dir, *delegated; ++ ++ h_parent = wh->d_parent; /* dir inode is locked */ ++ h_dir = d_inode(h_parent); ++ IMustLock(h_dir); ++ ++ br = au_sbr(sb, bindex); ++ h_path.mnt = au_br_mnt(br); ++ wbr = br->br_wbr; ++ wbr_wh_read_lock(wbr); ++ if (wbr->wbr_whbase) { ++ delegated = NULL; ++ err = vfsub_link(wbr->wbr_whbase, h_dir, &h_path, &delegated); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal link\n"); ++ iput(delegated); ++ } ++ if (!err || err != -EMLINK) ++ goto out; ++ ++ /* link count full. re-initialize br_whbase. */ ++ kick_reinit_br_wh(sb, br); ++ } ++ ++ /* return this error in this context */ ++ err = vfsub_create(h_dir, &h_path, WH_MASK, /*want_excl*/true); ++ if (!err) ++ au_fhsm_wrote(sb, bindex, /*force*/0); ++ ++out: ++ wbr_wh_read_unlock(wbr); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * create or remove the diropq. ++ */ ++static struct dentry *do_diropq(struct dentry *dentry, aufs_bindex_t bindex, ++ unsigned int flags) ++{ ++ struct dentry *opq_dentry, *h_dentry; ++ struct super_block *sb; ++ struct au_branch *br; ++ int err; ++ ++ sb = dentry->d_sb; ++ br = au_sbr(sb, bindex); ++ h_dentry = au_h_dptr(dentry, bindex); ++ opq_dentry = vfsub_lkup_one(&diropq_name, h_dentry); ++ if (IS_ERR(opq_dentry)) ++ goto out; ++ ++ if (au_ftest_diropq(flags, CREATE)) { ++ err = link_or_create_wh(sb, bindex, opq_dentry); ++ if (!err) { ++ au_set_dbdiropq(dentry, bindex); ++ goto out; /* success */ ++ } ++ } else { ++ struct path tmp = { ++ .dentry = opq_dentry, ++ .mnt = au_br_mnt(br) ++ }; ++ err = do_unlink_wh(au_h_iptr(d_inode(dentry), bindex), &tmp); ++ if (!err) ++ au_set_dbdiropq(dentry, -1); ++ } ++ dput(opq_dentry); ++ opq_dentry = ERR_PTR(err); ++ ++out: ++ return opq_dentry; ++} ++ ++struct do_diropq_args { ++ struct dentry **errp; ++ struct dentry *dentry; ++ aufs_bindex_t bindex; ++ unsigned int flags; ++}; ++ ++static void call_do_diropq(void *args) ++{ ++ struct do_diropq_args *a = args; ++ *a->errp = do_diropq(a->dentry, a->bindex, a->flags); ++} ++ ++struct dentry *au_diropq_sio(struct dentry *dentry, aufs_bindex_t bindex, ++ unsigned int flags) ++{ ++ struct dentry *diropq, *h_dentry; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!au_test_h_perm_sio(d_inode(h_dentry), MAY_EXEC | MAY_WRITE)) ++ diropq = do_diropq(dentry, bindex, flags); ++ else { ++ int wkq_err; ++ struct do_diropq_args args = { ++ .errp = &diropq, ++ .dentry = dentry, ++ .bindex = bindex, ++ .flags = flags ++ }; ++ ++ wkq_err = au_wkq_wait(call_do_diropq, &args); ++ if (unlikely(wkq_err)) ++ diropq = ERR_PTR(wkq_err); ++ } ++ ++ return diropq; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * lookup whiteout dentry. ++ * @h_parent: lower parent dentry which must exist and be locked ++ * @base_name: name of dentry which will be whiteouted ++ * returns dentry for whiteout. ++ */ ++struct dentry *au_wh_lkup(struct dentry *h_parent, struct qstr *base_name, ++ struct au_branch *br) ++{ ++ int err; ++ struct qstr wh_name; ++ struct dentry *wh_dentry; ++ ++ err = au_wh_name_alloc(&wh_name, base_name); ++ wh_dentry = ERR_PTR(err); ++ if (!err) { ++ wh_dentry = vfsub_lkup_one(&wh_name, h_parent); ++ kfree(wh_name.name); ++ } ++ return wh_dentry; ++} ++ ++/* ++ * link/create a whiteout for @dentry on @bindex. ++ */ ++struct dentry *au_wh_create(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_parent) ++{ ++ struct dentry *wh_dentry; ++ struct super_block *sb; ++ int err; ++ ++ sb = dentry->d_sb; ++ wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, au_sbr(sb, bindex)); ++ if (!IS_ERR(wh_dentry) && d_is_negative(wh_dentry)) { ++ err = link_or_create_wh(sb, bindex, wh_dentry); ++ if (!err) { ++ au_set_dbwh(dentry, bindex); ++ au_fhsm_wrote(sb, bindex, /*force*/0); ++ } else { ++ dput(wh_dentry); ++ wh_dentry = ERR_PTR(err); ++ } ++ } ++ ++ return wh_dentry; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* Delete all whiteouts in this directory on branch bindex. */ ++static int del_wh_children(struct dentry *h_dentry, struct au_nhash *whlist, ++ aufs_bindex_t bindex, struct au_branch *br) ++{ ++ int err; ++ unsigned long ul, n; ++ struct qstr wh_name; ++ char *p; ++ struct hlist_head *head; ++ struct au_vdir_wh *pos; ++ struct au_vdir_destr *str; ++ ++ err = -ENOMEM; ++ p = (void *)__get_free_page(GFP_NOFS); ++ wh_name.name = p; ++ if (unlikely(!wh_name.name)) ++ goto out; ++ ++ err = 0; ++ memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN); ++ p += AUFS_WH_PFX_LEN; ++ n = whlist->nh_num; ++ head = whlist->nh_head; ++ for (ul = 0; !err && ul < n; ul++, head++) { ++ hlist_for_each_entry(pos, head, wh_hash) { ++ if (pos->wh_bindex != bindex) ++ continue; ++ ++ str = &pos->wh_str; ++ if (str->len + AUFS_WH_PFX_LEN <= PATH_MAX) { ++ memcpy(p, str->name, str->len); ++ wh_name.len = AUFS_WH_PFX_LEN + str->len; ++ err = unlink_wh_name(h_dentry, &wh_name, br); ++ if (!err) ++ continue; ++ break; ++ } ++ AuIOErr("whiteout name too long %.*s\n", ++ str->len, str->name); ++ err = -EIO; ++ break; ++ } ++ } ++ free_page((unsigned long)wh_name.name); ++ ++out: ++ return err; ++} ++ ++struct del_wh_children_args { ++ int *errp; ++ struct dentry *h_dentry; ++ struct au_nhash *whlist; ++ aufs_bindex_t bindex; ++ struct au_branch *br; ++}; ++ ++static void call_del_wh_children(void *args) ++{ ++ struct del_wh_children_args *a = args; ++ *a->errp = del_wh_children(a->h_dentry, a->whlist, a->bindex, a->br); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_whtmp_rmdir *au_whtmp_rmdir_alloc(struct super_block *sb, gfp_t gfp) ++{ ++ struct au_whtmp_rmdir *whtmp; ++ int err; ++ unsigned int rdhash; ++ ++ SiMustAnyLock(sb); ++ ++ whtmp = kzalloc(sizeof(*whtmp), gfp); ++ if (unlikely(!whtmp)) { ++ whtmp = ERR_PTR(-ENOMEM); ++ goto out; ++ } ++ ++ /* no estimation for dir size */ ++ rdhash = au_sbi(sb)->si_rdhash; ++ if (!rdhash) ++ rdhash = AUFS_RDHASH_DEF; ++ err = au_nhash_alloc(&whtmp->whlist, rdhash, gfp); ++ if (unlikely(err)) { ++ kfree(whtmp); ++ whtmp = ERR_PTR(err); ++ } ++ ++out: ++ return whtmp; ++} ++ ++void au_whtmp_rmdir_free(struct au_whtmp_rmdir *whtmp) ++{ ++ if (whtmp->br) ++ au_br_put(whtmp->br); ++ dput(whtmp->wh_dentry); ++ iput(whtmp->dir); ++ au_nhash_wh_free(&whtmp->whlist); ++ kfree(whtmp); ++} ++ ++/* ++ * rmdir the whiteouted temporary named dir @h_dentry. ++ * @whlist: whiteouted children. ++ */ ++int au_whtmp_rmdir(struct inode *dir, aufs_bindex_t bindex, ++ struct dentry *wh_dentry, struct au_nhash *whlist) ++{ ++ int err; ++ unsigned int h_nlink; ++ struct path h_tmp; ++ struct inode *wh_inode, *h_dir; ++ struct au_branch *br; ++ ++ h_dir = d_inode(wh_dentry->d_parent); /* dir inode is locked */ ++ IMustLock(h_dir); ++ ++ br = au_sbr(dir->i_sb, bindex); ++ wh_inode = d_inode(wh_dentry); ++ inode_lock_nested(wh_inode, AuLsc_I_CHILD); ++ ++ /* ++ * someone else might change some whiteouts while we were sleeping. ++ * it means this whlist may have an obsoleted entry. ++ */ ++ if (!au_test_h_perm_sio(wh_inode, MAY_EXEC | MAY_WRITE)) ++ err = del_wh_children(wh_dentry, whlist, bindex, br); ++ else { ++ int wkq_err; ++ struct del_wh_children_args args = { ++ .errp = &err, ++ .h_dentry = wh_dentry, ++ .whlist = whlist, ++ .bindex = bindex, ++ .br = br ++ }; ++ ++ wkq_err = au_wkq_wait(call_del_wh_children, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ inode_unlock(wh_inode); ++ ++ if (!err) { ++ h_tmp.dentry = wh_dentry; ++ h_tmp.mnt = au_br_mnt(br); ++ h_nlink = h_dir->i_nlink; ++ err = vfsub_rmdir(h_dir, &h_tmp); ++ /* some fs doesn't change the parent nlink in some cases */ ++ h_nlink -= h_dir->i_nlink; ++ } ++ ++ if (!err) { ++ if (au_ibtop(dir) == bindex) { ++ /* todo: dir->i_mutex is necessary */ ++ au_cpup_attr_timesizes(dir); ++ if (h_nlink) ++ vfsub_drop_nlink(dir); ++ } ++ return 0; /* success */ ++ } ++ ++ pr_warn("failed removing %pd(%d), ignored\n", wh_dentry, err); ++ return err; ++} ++ ++static void call_rmdir_whtmp(void *args) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ struct au_whtmp_rmdir *a = args; ++ struct super_block *sb; ++ struct dentry *h_parent; ++ struct inode *h_dir; ++ struct au_hinode *hdir; ++ ++ /* rmdir by nfsd may cause deadlock with this i_mutex */ ++ /* inode_lock(a->dir); */ ++ err = -EROFS; ++ sb = a->dir->i_sb; ++ si_read_lock(sb, !AuLock_FLUSH); ++ if (!au_br_writable(a->br->br_perm)) ++ goto out; ++ bindex = au_br_index(sb, a->br->br_id); ++ if (unlikely(bindex < 0)) ++ goto out; ++ ++ err = -EIO; ++ ii_write_lock_parent(a->dir); ++ h_parent = dget_parent(a->wh_dentry); ++ h_dir = d_inode(h_parent); ++ hdir = au_hi(a->dir, bindex); ++ err = vfsub_mnt_want_write(au_br_mnt(a->br)); ++ if (unlikely(err)) ++ goto out_mnt; ++ au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); ++ err = au_h_verify(a->wh_dentry, au_opt_udba(sb), h_dir, h_parent, ++ a->br); ++ if (!err) ++ err = au_whtmp_rmdir(a->dir, bindex, a->wh_dentry, &a->whlist); ++ au_hn_inode_unlock(hdir); ++ vfsub_mnt_drop_write(au_br_mnt(a->br)); ++ ++out_mnt: ++ dput(h_parent); ++ ii_write_unlock(a->dir); ++out: ++ /* inode_unlock(a->dir); */ ++ au_whtmp_rmdir_free(a); ++ si_read_unlock(sb); ++ au_nwt_done(&au_sbi(sb)->si_nowait); ++ if (unlikely(err)) ++ AuIOErr("err %d\n", err); ++} ++ ++void au_whtmp_kick_rmdir(struct inode *dir, aufs_bindex_t bindex, ++ struct dentry *wh_dentry, struct au_whtmp_rmdir *args) ++{ ++ int wkq_err; ++ struct super_block *sb; ++ ++ IMustLock(dir); ++ ++ /* all post-process will be done in do_rmdir_whtmp(). */ ++ sb = dir->i_sb; ++ args->dir = au_igrab(dir); ++ args->br = au_sbr(sb, bindex); ++ au_br_get(args->br); ++ args->wh_dentry = dget(wh_dentry); ++ wkq_err = au_wkq_nowait(call_rmdir_whtmp, args, sb, /*flags*/0); ++ if (unlikely(wkq_err)) { ++ pr_warn("rmdir error %pd (%d), ignored\n", wh_dentry, wkq_err); ++ au_whtmp_rmdir_free(args); ++ } ++} +diff --git a/fs/aufs/whout.h b/fs/aufs/whout.h +new file mode 100644 +index 00000000..766a1d93 +--- /dev/null ++++ b/fs/aufs/whout.h +@@ -0,0 +1,85 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * whiteout for logical deletion and opaque directory ++ */ ++ ++#ifndef __AUFS_WHOUT_H__ ++#define __AUFS_WHOUT_H__ ++ ++#ifdef __KERNEL__ ++ ++#include "dir.h" ++ ++/* whout.c */ ++int au_wh_name_alloc(struct qstr *wh, const struct qstr *name); ++int au_wh_test(struct dentry *h_parent, struct qstr *wh_name, int try_sio); ++int au_diropq_test(struct dentry *h_dentry); ++struct au_branch; ++struct dentry *au_whtmp_lkup(struct dentry *h_parent, struct au_branch *br, ++ struct qstr *prefix); ++int au_whtmp_ren(struct dentry *h_dentry, struct au_branch *br); ++int au_wh_unlink_dentry(struct inode *h_dir, struct path *h_path, ++ struct dentry *dentry); ++int au_wh_init(struct au_branch *br, struct super_block *sb); ++ ++/* diropq flags */ ++#define AuDiropq_CREATE 1 ++#define au_ftest_diropq(flags, name) ((flags) & AuDiropq_##name) ++#define au_fset_diropq(flags, name) \ ++ do { (flags) |= AuDiropq_##name; } while (0) ++#define au_fclr_diropq(flags, name) \ ++ do { (flags) &= ~AuDiropq_##name; } while (0) ++ ++struct dentry *au_diropq_sio(struct dentry *dentry, aufs_bindex_t bindex, ++ unsigned int flags); ++struct dentry *au_wh_lkup(struct dentry *h_parent, struct qstr *base_name, ++ struct au_branch *br); ++struct dentry *au_wh_create(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_parent); ++ ++/* real rmdir for the whiteout-ed dir */ ++struct au_whtmp_rmdir { ++ struct inode *dir; ++ struct au_branch *br; ++ struct dentry *wh_dentry; ++ struct au_nhash whlist; ++}; ++ ++struct au_whtmp_rmdir *au_whtmp_rmdir_alloc(struct super_block *sb, gfp_t gfp); ++void au_whtmp_rmdir_free(struct au_whtmp_rmdir *whtmp); ++int au_whtmp_rmdir(struct inode *dir, aufs_bindex_t bindex, ++ struct dentry *wh_dentry, struct au_nhash *whlist); ++void au_whtmp_kick_rmdir(struct inode *dir, aufs_bindex_t bindex, ++ struct dentry *wh_dentry, struct au_whtmp_rmdir *args); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct dentry *au_diropq_create(struct dentry *dentry, ++ aufs_bindex_t bindex) ++{ ++ return au_diropq_sio(dentry, bindex, AuDiropq_CREATE); ++} ++ ++static inline int au_diropq_remove(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ return PTR_ERR(au_diropq_sio(dentry, bindex, !AuDiropq_CREATE)); ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_WHOUT_H__ */ +diff --git a/fs/aufs/wkq.c b/fs/aufs/wkq.c +new file mode 100644 +index 00000000..0b252453 +--- /dev/null ++++ b/fs/aufs/wkq.c +@@ -0,0 +1,212 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * workqueue for asynchronous/super-io operations ++ * todo: try new dredential scheme ++ */ ++ ++#include ++#include "aufs.h" ++ ++/* internal workqueue named AUFS_WKQ_NAME */ ++ ++static struct workqueue_struct *au_wkq; ++ ++struct au_wkinfo { ++ struct work_struct wk; ++ struct kobject *kobj; ++ ++ unsigned int flags; /* see wkq.h */ ++ ++ au_wkq_func_t func; ++ void *args; ++ ++ struct completion *comp; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void wkq_func(struct work_struct *wk) ++{ ++ struct au_wkinfo *wkinfo = container_of(wk, struct au_wkinfo, wk); ++ ++ AuDebugOn(!uid_eq(current_fsuid(), GLOBAL_ROOT_UID)); ++ AuDebugOn(rlimit(RLIMIT_FSIZE) != RLIM_INFINITY); ++ ++ wkinfo->func(wkinfo->args); ++ if (au_ftest_wkq(wkinfo->flags, WAIT)) ++ complete(wkinfo->comp); ++ else { ++ kobject_put(wkinfo->kobj); ++ module_put(THIS_MODULE); /* todo: ?? */ ++ kfree(wkinfo); ++ } ++} ++ ++/* ++ * Since struct completion is large, try allocating it dynamically. ++ */ ++#if 1 /* defined(CONFIG_4KSTACKS) || defined(AuTest4KSTACKS) */ ++#define AuWkqCompDeclare(name) struct completion *comp = NULL ++ ++static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp) ++{ ++ *comp = kmalloc(sizeof(**comp), GFP_NOFS); ++ if (*comp) { ++ init_completion(*comp); ++ wkinfo->comp = *comp; ++ return 0; ++ } ++ return -ENOMEM; ++} ++ ++static void au_wkq_comp_free(struct completion *comp) ++{ ++ kfree(comp); ++} ++ ++#else ++ ++/* no braces */ ++#define AuWkqCompDeclare(name) \ ++ DECLARE_COMPLETION_ONSTACK(_ ## name); \ ++ struct completion *comp = &_ ## name ++ ++static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp) ++{ ++ wkinfo->comp = *comp; ++ return 0; ++} ++ ++static void au_wkq_comp_free(struct completion *comp __maybe_unused) ++{ ++ /* empty */ ++} ++#endif /* 4KSTACKS */ ++ ++static void au_wkq_run(struct au_wkinfo *wkinfo) ++{ ++ if (au_ftest_wkq(wkinfo->flags, NEST)) { ++ if (au_wkq_test()) { ++ AuWarn1("wkq from wkq, unless silly-rename on NFS," ++ " due to a dead dir by UDBA?\n"); ++ AuDebugOn(au_ftest_wkq(wkinfo->flags, WAIT)); ++ } ++ } else ++ au_dbg_verify_kthread(); ++ ++ if (au_ftest_wkq(wkinfo->flags, WAIT)) { ++ INIT_WORK_ONSTACK(&wkinfo->wk, wkq_func); ++ queue_work(au_wkq, &wkinfo->wk); ++ } else { ++ INIT_WORK(&wkinfo->wk, wkq_func); ++ schedule_work(&wkinfo->wk); ++ } ++} ++ ++/* ++ * Be careful. It is easy to make deadlock happen. ++ * processA: lock, wkq and wait ++ * processB: wkq and wait, lock in wkq ++ * --> deadlock ++ */ ++int au_wkq_do_wait(unsigned int flags, au_wkq_func_t func, void *args) ++{ ++ int err; ++ AuWkqCompDeclare(comp); ++ struct au_wkinfo wkinfo = { ++ .flags = flags, ++ .func = func, ++ .args = args ++ }; ++ ++ err = au_wkq_comp_alloc(&wkinfo, &comp); ++ if (!err) { ++ au_wkq_run(&wkinfo); ++ /* no timeout, no interrupt */ ++ wait_for_completion(wkinfo.comp); ++ au_wkq_comp_free(comp); ++ } ++ ++ destroy_work_on_stack(&wkinfo.wk); ++ return err; ++} ++ ++/* ++ * Note: dget/dput() in func for aufs dentries are not supported. It will be a ++ * problem in a concurrent umounting. ++ */ ++int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb, ++ unsigned int flags) ++{ ++ int err; ++ struct au_wkinfo *wkinfo; ++ ++ atomic_inc(&au_sbi(sb)->si_nowait.nw_len); ++ ++ /* ++ * wkq_func() must free this wkinfo. ++ * it highly depends upon the implementation of workqueue. ++ */ ++ err = 0; ++ wkinfo = kmalloc(sizeof(*wkinfo), GFP_NOFS); ++ if (wkinfo) { ++ wkinfo->kobj = &au_sbi(sb)->si_kobj; ++ wkinfo->flags = flags & ~AuWkq_WAIT; ++ wkinfo->func = func; ++ wkinfo->args = args; ++ wkinfo->comp = NULL; ++ kobject_get(wkinfo->kobj); ++ __module_get(THIS_MODULE); /* todo: ?? */ ++ ++ au_wkq_run(wkinfo); ++ } else { ++ err = -ENOMEM; ++ au_nwt_done(&au_sbi(sb)->si_nowait); ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_nwt_init(struct au_nowait_tasks *nwt) ++{ ++ atomic_set(&nwt->nw_len, 0); ++ /* smp_mb(); */ /* atomic_set */ ++ init_waitqueue_head(&nwt->nw_wq); ++} ++ ++void au_wkq_fin(void) ++{ ++ destroy_workqueue(au_wkq); ++} ++ ++int __init au_wkq_init(void) ++{ ++ int err; ++ ++ err = 0; ++ au_wkq = alloc_workqueue(AUFS_WKQ_NAME, 0, WQ_DFL_ACTIVE); ++ if (IS_ERR(au_wkq)) ++ err = PTR_ERR(au_wkq); ++ else if (!au_wkq) ++ err = -ENOMEM; ++ ++ return err; ++} +diff --git a/fs/aufs/wkq.h b/fs/aufs/wkq.h +new file mode 100644 +index 00000000..9fc86c11 +--- /dev/null ++++ b/fs/aufs/wkq.h +@@ -0,0 +1,93 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * workqueue for asynchronous/super-io operations ++ * todo: try new credentials management scheme ++ */ ++ ++#ifndef __AUFS_WKQ_H__ ++#define __AUFS_WKQ_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++ ++struct super_block; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * in the next operation, wait for the 'nowait' tasks in system-wide workqueue ++ */ ++struct au_nowait_tasks { ++ atomic_t nw_len; ++ wait_queue_head_t nw_wq; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++typedef void (*au_wkq_func_t)(void *args); ++ ++/* wkq flags */ ++#define AuWkq_WAIT 1 ++#define AuWkq_NEST (1 << 1) ++#define au_ftest_wkq(flags, name) ((flags) & AuWkq_##name) ++#define au_fset_wkq(flags, name) \ ++ do { (flags) |= AuWkq_##name; } while (0) ++#define au_fclr_wkq(flags, name) \ ++ do { (flags) &= ~AuWkq_##name; } while (0) ++ ++#ifndef CONFIG_AUFS_HNOTIFY ++#undef AuWkq_NEST ++#define AuWkq_NEST 0 ++#endif ++ ++/* wkq.c */ ++int au_wkq_do_wait(unsigned int flags, au_wkq_func_t func, void *args); ++int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb, ++ unsigned int flags); ++void au_nwt_init(struct au_nowait_tasks *nwt); ++int __init au_wkq_init(void); ++void au_wkq_fin(void); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline int au_wkq_test(void) ++{ ++ return current->flags & PF_WQ_WORKER; ++} ++ ++static inline int au_wkq_wait(au_wkq_func_t func, void *args) ++{ ++ return au_wkq_do_wait(AuWkq_WAIT, func, args); ++} ++ ++static inline void au_nwt_done(struct au_nowait_tasks *nwt) ++{ ++ if (atomic_dec_and_test(&nwt->nw_len)) ++ wake_up_all(&nwt->nw_wq); ++} ++ ++static inline int au_nwt_flush(struct au_nowait_tasks *nwt) ++{ ++ wait_event(nwt->nw_wq, !atomic_read(&nwt->nw_len)); ++ return 0; ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_WKQ_H__ */ +diff --git a/fs/aufs/xattr.c b/fs/aufs/xattr.c +new file mode 100644 +index 00000000..7c647bbb +--- /dev/null ++++ b/fs/aufs/xattr.c +@@ -0,0 +1,355 @@ ++/* ++ * Copyright (C) 2014-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * handling xattr functions ++ */ ++ ++#include ++#include ++#include ++#include "aufs.h" ++ ++static int au_xattr_ignore(int err, char *name, unsigned int ignore_flags) ++{ ++ if (!ignore_flags) ++ goto out; ++ switch (err) { ++ case -ENOMEM: ++ case -EDQUOT: ++ goto out; ++ } ++ ++ if ((ignore_flags & AuBrAttr_ICEX) == AuBrAttr_ICEX) { ++ err = 0; ++ goto out; ++ } ++ ++#define cmp(brattr, prefix) do { \ ++ if (!strncmp(name, XATTR_##prefix##_PREFIX, \ ++ XATTR_##prefix##_PREFIX_LEN)) { \ ++ if (ignore_flags & AuBrAttr_ICEX_##brattr) \ ++ err = 0; \ ++ goto out; \ ++ } \ ++ } while (0) ++ ++ cmp(SEC, SECURITY); ++ cmp(SYS, SYSTEM); ++ cmp(TR, TRUSTED); ++ cmp(USR, USER); ++#undef cmp ++ ++ if (ignore_flags & AuBrAttr_ICEX_OTH) ++ err = 0; ++ ++out: ++ return err; ++} ++ ++static const int au_xattr_out_of_list = AuBrAttr_ICEX_OTH << 1; ++ ++static int au_do_cpup_xattr(struct dentry *h_dst, struct dentry *h_src, ++ char *name, char **buf, unsigned int ignore_flags, ++ unsigned int verbose) ++{ ++ int err; ++ ssize_t ssz; ++ struct inode *h_idst; ++ ++ ssz = vfs_getxattr_alloc(h_src, name, buf, 0, GFP_NOFS); ++ err = ssz; ++ if (unlikely(err <= 0)) { ++ if (err == -ENODATA ++ || (err == -EOPNOTSUPP ++ && ((ignore_flags & au_xattr_out_of_list) ++ || (au_test_nfs_noacl(d_inode(h_src)) ++ && (!strcmp(name, XATTR_NAME_POSIX_ACL_ACCESS) ++ || !strcmp(name, ++ XATTR_NAME_POSIX_ACL_DEFAULT)))) ++ )) ++ err = 0; ++ if (err && (verbose || au_debug_test())) ++ pr_err("%s, err %d\n", name, err); ++ goto out; ++ } ++ ++ /* unlock it temporary */ ++ h_idst = d_inode(h_dst); ++ inode_unlock(h_idst); ++ err = vfsub_setxattr(h_dst, name, *buf, ssz, /*flags*/0); ++ inode_lock_nested(h_idst, AuLsc_I_CHILD2); ++ if (unlikely(err)) { ++ if (verbose || au_debug_test()) ++ pr_err("%s, err %d\n", name, err); ++ err = au_xattr_ignore(err, name, ignore_flags); ++ } ++ ++out: ++ return err; ++} ++ ++int au_cpup_xattr(struct dentry *h_dst, struct dentry *h_src, int ignore_flags, ++ unsigned int verbose) ++{ ++ int err, unlocked, acl_access, acl_default; ++ ssize_t ssz; ++ struct inode *h_isrc, *h_idst; ++ char *value, *p, *o, *e; ++ ++ /* try stopping to update the source inode while we are referencing */ ++ /* there should not be the parent-child relationship between them */ ++ h_isrc = d_inode(h_src); ++ h_idst = d_inode(h_dst); ++ inode_unlock(h_idst); ++ vfsub_inode_lock_shared_nested(h_isrc, AuLsc_I_CHILD); ++ inode_lock_nested(h_idst, AuLsc_I_CHILD2); ++ unlocked = 0; ++ ++ /* some filesystems don't list POSIX ACL, for example tmpfs */ ++ ssz = vfs_listxattr(h_src, NULL, 0); ++ err = ssz; ++ if (unlikely(err < 0)) { ++ AuTraceErr(err); ++ if (err == -ENODATA ++ || err == -EOPNOTSUPP) ++ err = 0; /* ignore */ ++ goto out; ++ } ++ ++ err = 0; ++ p = NULL; ++ o = NULL; ++ if (ssz) { ++ err = -ENOMEM; ++ p = kmalloc(ssz, GFP_NOFS); ++ o = p; ++ if (unlikely(!p)) ++ goto out; ++ err = vfs_listxattr(h_src, p, ssz); ++ } ++ inode_unlock_shared(h_isrc); ++ unlocked = 1; ++ AuDbg("err %d, ssz %zd\n", err, ssz); ++ if (unlikely(err < 0)) ++ goto out_free; ++ ++ err = 0; ++ e = p + ssz; ++ value = NULL; ++ acl_access = 0; ++ acl_default = 0; ++ while (!err && p < e) { ++ acl_access |= !strncmp(p, XATTR_NAME_POSIX_ACL_ACCESS, ++ sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1); ++ acl_default |= !strncmp(p, XATTR_NAME_POSIX_ACL_DEFAULT, ++ sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) ++ - 1); ++ err = au_do_cpup_xattr(h_dst, h_src, p, &value, ignore_flags, ++ verbose); ++ p += strlen(p) + 1; ++ } ++ AuTraceErr(err); ++ ignore_flags |= au_xattr_out_of_list; ++ if (!err && !acl_access) { ++ err = au_do_cpup_xattr(h_dst, h_src, ++ XATTR_NAME_POSIX_ACL_ACCESS, &value, ++ ignore_flags, verbose); ++ AuTraceErr(err); ++ } ++ if (!err && !acl_default) { ++ err = au_do_cpup_xattr(h_dst, h_src, ++ XATTR_NAME_POSIX_ACL_DEFAULT, &value, ++ ignore_flags, verbose); ++ AuTraceErr(err); ++ } ++ ++ kfree(value); ++ ++out_free: ++ kfree(o); ++out: ++ if (!unlocked) ++ inode_unlock_shared(h_isrc); ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_smack_reentering(struct super_block *sb) ++{ ++#if IS_ENABLED(CONFIG_SECURITY_SMACK) ++ /* ++ * as a part of lookup, smack_d_instantiate() is called, and it calls ++ * i_op->getxattr(). ouch. ++ */ ++ return si_pid_test(sb); ++#else ++ return 0; ++#endif ++} ++ ++enum { ++ AU_XATTR_LIST, ++ AU_XATTR_GET ++}; ++ ++struct au_lgxattr { ++ int type; ++ union { ++ struct { ++ char *list; ++ size_t size; ++ } list; ++ struct { ++ const char *name; ++ void *value; ++ size_t size; ++ } get; ++ } u; ++}; ++ ++static ssize_t au_lgxattr(struct dentry *dentry, struct au_lgxattr *arg) ++{ ++ ssize_t err; ++ int reenter; ++ struct path h_path; ++ struct super_block *sb; ++ ++ sb = dentry->d_sb; ++ reenter = au_smack_reentering(sb); ++ if (!reenter) { ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (unlikely(err)) ++ goto out; ++ } ++ err = au_h_path_getattr(dentry, /*force*/1, &h_path, reenter); ++ if (unlikely(err)) ++ goto out_si; ++ if (unlikely(!h_path.dentry)) ++ /* illegally overlapped or something */ ++ goto out_di; /* pretending success */ ++ ++ /* always topmost entry only */ ++ switch (arg->type) { ++ case AU_XATTR_LIST: ++ err = vfs_listxattr(h_path.dentry, ++ arg->u.list.list, arg->u.list.size); ++ break; ++ case AU_XATTR_GET: ++ AuDebugOn(d_is_negative(h_path.dentry)); ++ err = vfs_getxattr(h_path.dentry, ++ arg->u.get.name, arg->u.get.value, ++ arg->u.get.size); ++ break; ++ } ++ ++out_di: ++ if (!reenter) ++ di_read_unlock(dentry, AuLock_IR); ++out_si: ++ if (!reenter) ++ si_read_unlock(sb); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size) ++{ ++ struct au_lgxattr arg = { ++ .type = AU_XATTR_LIST, ++ .u.list = { ++ .list = list, ++ .size = size ++ }, ++ }; ++ ++ return au_lgxattr(dentry, &arg); ++} ++ ++static ssize_t au_getxattr(struct dentry *dentry, ++ struct inode *inode __maybe_unused, ++ const char *name, void *value, size_t size) ++{ ++ struct au_lgxattr arg = { ++ .type = AU_XATTR_GET, ++ .u.get = { ++ .name = name, ++ .value = value, ++ .size = size ++ }, ++ }; ++ ++ return au_lgxattr(dentry, &arg); ++} ++ ++static int au_setxattr(struct dentry *dentry, struct inode *inode, ++ const char *name, const void *value, size_t size, ++ int flags) ++{ ++ struct au_sxattr arg = { ++ .type = AU_XATTR_SET, ++ .u.set = { ++ .name = name, ++ .value = value, ++ .size = size, ++ .flags = flags ++ }, ++ }; ++ ++ return au_sxattr(dentry, inode, &arg); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_xattr_get(const struct xattr_handler *handler, ++ struct dentry *dentry, struct inode *inode, ++ const char *name, void *buffer, size_t size) ++{ ++ return au_getxattr(dentry, inode, name, buffer, size); ++} ++ ++static int au_xattr_set(const struct xattr_handler *handler, ++ struct dentry *dentry, struct inode *inode, ++ const char *name, const void *value, size_t size, ++ int flags) ++{ ++ return au_setxattr(dentry, inode, name, value, size, flags); ++} ++ ++static const struct xattr_handler au_xattr_handler = { ++ .name = "", ++ .prefix = "", ++ .get = au_xattr_get, ++ .set = au_xattr_set ++}; ++ ++static const struct xattr_handler *au_xattr_handlers[] = { ++#ifdef CONFIG_FS_POSIX_ACL ++ &posix_acl_access_xattr_handler, ++ &posix_acl_default_xattr_handler, ++#endif ++ &au_xattr_handler, /* must be last */ ++ NULL ++}; ++ ++void au_xattr_init(struct super_block *sb) ++{ ++ sb->s_xattr = au_xattr_handlers; ++} +diff --git a/fs/aufs/xino.c b/fs/aufs/xino.c +new file mode 100644 +index 00000000..aa44c0d2 +--- /dev/null ++++ b/fs/aufs/xino.c +@@ -0,0 +1,1589 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * external inode number translation table and bitmap ++ * ++ * things to consider ++ * - the lifetime ++ * + au_xino object ++ * + XINO files (xino, xib, xigen) ++ * + dynamic debugfs entries (xiN) ++ * + static debugfs entries (xib, xigen) ++ * + static sysfs entry (xi_path) ++ * - several entry points to handle them. ++ * + mount(2) without xino option (default) ++ * + mount(2) with xino option ++ * + mount(2) with noxino option ++ * + umount(2) ++ * + remount with add/del branches ++ * + remount with xino/noxino options ++ */ ++ ++#include ++#include ++#include "aufs.h" ++ ++static aufs_bindex_t sbr_find_shared(struct super_block *sb, aufs_bindex_t btop, ++ aufs_bindex_t bbot, ++ struct super_block *h_sb) ++{ ++ /* todo: try binary-search if the branches are many */ ++ for (; btop <= bbot; btop++) ++ if (h_sb == au_sbr_sb(sb, btop)) ++ return btop; ++ return -1; ++} ++ ++/* ++ * find another branch who is on the same filesystem of the specified ++ * branch{@btgt}. search until @bbot. ++ */ ++static aufs_bindex_t is_sb_shared(struct super_block *sb, aufs_bindex_t btgt, ++ aufs_bindex_t bbot) ++{ ++ aufs_bindex_t bindex; ++ struct super_block *tgt_sb; ++ ++ tgt_sb = au_sbr_sb(sb, btgt); ++ bindex = sbr_find_shared(sb, /*btop*/0, btgt - 1, tgt_sb); ++ if (bindex < 0) ++ bindex = sbr_find_shared(sb, btgt + 1, bbot, tgt_sb); ++ ++ return bindex; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * stop unnecessary notify events at creating xino files ++ */ ++struct au_xino_lock_dir { ++ struct au_hinode *hdir; ++ struct dentry *parent; ++ struct inode *dir; ++}; ++ ++static struct dentry *au_dget_parent_lock(struct dentry *dentry, ++ unsigned int lsc) ++{ ++ struct dentry *parent; ++ struct inode *dir; ++ ++ parent = dget_parent(dentry); ++ dir = d_inode(parent); ++ inode_lock_nested(dir, lsc); ++#if 0 /* it should not happen */ ++ spin_lock(&dentry->d_lock); ++ if (unlikely(dentry->d_parent != parent)) { ++ spin_unlock(&dentry->d_lock); ++ inode_unlock(dir); ++ dput(parent); ++ parent = NULL; ++ goto out; ++ } ++ spin_unlock(&dentry->d_lock); ++ ++out: ++#endif ++ return parent; ++} ++ ++static void au_xino_lock_dir(struct super_block *sb, struct path *xipath, ++ struct au_xino_lock_dir *ldir) ++{ ++ aufs_bindex_t brid, bindex; ++ ++ ldir->hdir = NULL; ++ bindex = -1; ++ brid = au_xino_brid(sb); ++ if (brid >= 0) ++ bindex = au_br_index(sb, brid); ++ if (bindex >= 0) { ++ /* rw branch root */ ++ ldir->hdir = au_hi(d_inode(sb->s_root), bindex); ++ au_hn_inode_lock_nested(ldir->hdir, AuLsc_I_PARENT); ++ } else { ++ /* other */ ++ ldir->parent = au_dget_parent_lock(xipath->dentry, ++ AuLsc_I_PARENT); ++ ldir->dir = d_inode(ldir->parent); ++ } ++} ++ ++static void au_xino_unlock_dir(struct au_xino_lock_dir *ldir) ++{ ++ if (ldir->hdir) ++ au_hn_inode_unlock(ldir->hdir); ++ else { ++ inode_unlock(ldir->dir); ++ dput(ldir->parent); ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * create and set a new xino file ++ */ ++struct file *au_xino_create(struct super_block *sb, char *fpath, int silent) ++{ ++ struct file *file; ++ struct dentry *h_parent, *d; ++ struct inode *h_dir, *inode; ++ int err; ++ ++ /* ++ * at mount-time, and the xino file is the default path, ++ * hnotify is disabled so we have no notify events to ignore. ++ * when a user specified the xino, we cannot get au_hdir to be ignored. ++ */ ++ file = vfsub_filp_open(fpath, O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE ++ /* | __FMODE_NONOTIFY */, ++ 0666); ++ if (IS_ERR(file)) { ++ if (!silent) ++ pr_err("open %s(%ld)\n", fpath, PTR_ERR(file)); ++ return file; ++ } ++ ++ /* keep file count */ ++ err = 0; ++ d = file->f_path.dentry; ++ h_parent = au_dget_parent_lock(d, AuLsc_I_PARENT); ++ /* mnt_want_write() is unnecessary here */ ++ h_dir = d_inode(h_parent); ++ inode = file_inode(file); ++ /* no delegation since it is just created */ ++ if (inode->i_nlink) ++ err = vfsub_unlink(h_dir, &file->f_path, /*delegated*/NULL, ++ /*force*/0); ++ inode_unlock(h_dir); ++ dput(h_parent); ++ if (unlikely(err)) { ++ if (!silent) ++ pr_err("unlink %s(%d)\n", fpath, err); ++ goto out; ++ } ++ ++ err = -EINVAL; ++ if (unlikely(sb == d->d_sb)) { ++ if (!silent) ++ pr_err("%s must be outside\n", fpath); ++ goto out; ++ } ++ if (unlikely(au_test_fs_bad_xino(d->d_sb))) { ++ if (!silent) ++ pr_err("xino doesn't support %s(%s)\n", ++ fpath, au_sbtype(d->d_sb)); ++ goto out; ++ } ++ return file; /* success */ ++ ++out: ++ fput(file); ++ file = ERR_PTR(err); ++ return file; ++} ++ ++/* ++ * create a new xinofile at the same place/path as @base. ++ */ ++struct file *au_xino_create2(struct super_block *sb, struct path *base, ++ struct file *copy_src) ++{ ++ struct file *file; ++ struct dentry *dentry, *parent; ++ struct inode *dir, *delegated; ++ struct qstr *name; ++ struct path path; ++ int err, do_unlock; ++ struct au_xino_lock_dir ldir; ++ ++ do_unlock = 1; ++ au_xino_lock_dir(sb, base, &ldir); ++ dentry = base->dentry; ++ parent = dentry->d_parent; /* dir inode is locked */ ++ dir = d_inode(parent); ++ IMustLock(dir); ++ ++ name = &dentry->d_name; ++ path.dentry = vfsub_lookup_one_len(name->name, parent, name->len); ++ if (IS_ERR(path.dentry)) { ++ file = (void *)path.dentry; ++ pr_err("%pd lookup err %ld\n", dentry, PTR_ERR(path.dentry)); ++ goto out; ++ } ++ ++ /* no need to mnt_want_write() since we call dentry_open() later */ ++ err = vfs_create(dir, path.dentry, 0666, NULL); ++ if (unlikely(err)) { ++ file = ERR_PTR(err); ++ pr_err("%pd create err %d\n", dentry, err); ++ goto out_dput; ++ } ++ ++ path.mnt = base->mnt; ++ file = vfsub_dentry_open(&path, ++ O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE ++ /* | __FMODE_NONOTIFY */); ++ if (IS_ERR(file)) { ++ pr_err("%pd open err %ld\n", dentry, PTR_ERR(file)); ++ goto out_dput; ++ } ++ ++ delegated = NULL; ++ err = vfsub_unlink(dir, &file->f_path, &delegated, /*force*/0); ++ au_xino_unlock_dir(&ldir); ++ do_unlock = 0; ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal unlink\n"); ++ iput(delegated); ++ } ++ if (unlikely(err)) { ++ pr_err("%pd unlink err %d\n", dentry, err); ++ goto out_fput; ++ } ++ ++ if (copy_src) { ++ /* no one can touch copy_src xino */ ++ err = au_copy_file(file, copy_src, vfsub_f_size_read(copy_src)); ++ if (unlikely(err)) { ++ pr_err("%pd copy err %d\n", dentry, err); ++ goto out_fput; ++ } ++ } ++ goto out_dput; /* success */ ++ ++out_fput: ++ fput(file); ++ file = ERR_PTR(err); ++out_dput: ++ dput(path.dentry); ++out: ++ if (do_unlock) ++ au_xino_unlock_dir(&ldir); ++ return file; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * truncate xino files ++ */ ++int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ int err; ++ unsigned long jiffy; ++ blkcnt_t blocks; ++ aufs_bindex_t bbot; ++ struct kstatfs *st; ++ struct au_branch *br; ++ struct file *new_xino, *file; ++ struct path *path; ++ ++ err = -ENOMEM; ++ st = kmalloc(sizeof(*st), GFP_NOFS); ++ if (unlikely(!st)) ++ goto out; ++ ++ err = -EINVAL; ++ bbot = au_sbbot(sb); ++ if (unlikely(bindex < 0 || bbot < bindex)) ++ goto out_st; ++ br = au_sbr(sb, bindex); ++ file = au_xino_file(br); ++ if (!file) ++ goto out_st; ++ ++ path = &file->f_path; ++ err = vfs_statfs(path, st); ++ if (unlikely(err)) ++ AuErr1("statfs err %d, ignored\n", err); ++ jiffy = jiffies; ++ blocks = file_inode(file)->i_blocks; ++ pr_info("begin truncating xino(b%d), ib%llu, %llu/%llu free blks\n", ++ bindex, (u64)blocks, st->f_bfree, st->f_blocks); ++ ++ new_xino = au_xino_create2(sb, path, file); ++ err = PTR_ERR(new_xino); ++ if (IS_ERR(new_xino)) { ++ pr_err("err %d, ignored\n", err); ++ goto out_st; ++ } ++ err = 0; ++ au_xino_file_set(br, new_xino); ++ ++ err = vfs_statfs(&new_xino->f_path, st); ++ if (!err) { ++ pr_info("end truncating xino(b%d), ib%llu, %llu/%llu free blks\n", ++ bindex, (u64)file_inode(new_xino)->i_blocks, ++ st->f_bfree, st->f_blocks); ++ if (file_inode(new_xino)->i_blocks < blocks) ++ au_sbi(sb)->si_xino_jiffy = jiffy; ++ } else ++ AuErr1("statfs err %d, ignored\n", err); ++ fput(new_xino); ++ ++out_st: ++ kfree(st); ++out: ++ return err; ++} ++ ++struct xino_do_trunc_args { ++ struct super_block *sb; ++ struct au_branch *br; ++}; ++ ++static void xino_do_trunc(void *_args) ++{ ++ struct xino_do_trunc_args *args = _args; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct inode *dir; ++ int err; ++ aufs_bindex_t bindex; ++ ++ err = 0; ++ sb = args->sb; ++ dir = d_inode(sb->s_root); ++ br = args->br; ++ ++ si_noflush_write_lock(sb); ++ ii_read_lock_parent(dir); ++ bindex = au_br_index(sb, br->br_id); ++ err = au_xino_trunc(sb, bindex); ++ ii_read_unlock(dir); ++ if (unlikely(err)) ++ pr_warn("err b%d, (%d)\n", bindex, err); ++ atomic_dec(&br->br_xino->xi_truncating); ++ au_br_put(br); ++ si_write_unlock(sb); ++ au_nwt_done(&au_sbi(sb)->si_nowait); ++ kfree(args); ++} ++ ++static int xino_trunc_test(struct super_block *sb, struct au_branch *br) ++{ ++ int err; ++ struct kstatfs st; ++ struct au_sbinfo *sbinfo; ++ struct file *file; ++ ++ /* todo: si_xino_expire and the ratio should be customizable */ ++ sbinfo = au_sbi(sb); ++ if (time_before(jiffies, ++ sbinfo->si_xino_jiffy + sbinfo->si_xino_expire)) ++ return 0; ++ ++ /* truncation border */ ++ file = au_xino_file(br); ++ AuDebugOn(!file); ++ err = vfs_statfs(&file->f_path, &st); ++ if (unlikely(err)) { ++ AuErr1("statfs err %d, ignored\n", err); ++ return 0; ++ } ++ if (div64_u64(st.f_bfree * 100, st.f_blocks) >= AUFS_XINO_DEF_TRUNC) ++ return 0; ++ ++ return 1; ++} ++ ++static void xino_try_trunc(struct super_block *sb, struct au_branch *br) ++{ ++ struct xino_do_trunc_args *args; ++ int wkq_err; ++ ++ if (!xino_trunc_test(sb, br)) ++ return; ++ ++ if (atomic_inc_return(&br->br_xino->xi_truncating) > 1) ++ goto out; ++ ++ /* lock and kfree() will be called in trunc_xino() */ ++ args = kmalloc(sizeof(*args), GFP_NOFS); ++ if (unlikely(!args)) { ++ AuErr1("no memory\n"); ++ goto out; ++ } ++ ++ au_br_get(br); ++ args->sb = sb; ++ args->br = br; ++ wkq_err = au_wkq_nowait(xino_do_trunc, args, sb, /*flags*/0); ++ if (!wkq_err) ++ return; /* success */ ++ ++ pr_err("wkq %d\n", wkq_err); ++ au_br_put(br); ++ kfree(args); ++ ++out: ++ atomic_dec(&br->br_xino->xi_truncating); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * read @ino from xinofile for the specified branch{@sb, @bindex} ++ * at the position of @h_ino. ++ */ ++int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ ino_t *ino) ++{ ++ int err; ++ ssize_t sz; ++ loff_t pos; ++ struct au_branch *br; ++ struct file *file; ++ struct au_sbinfo *sbinfo; ++ ++ *ino = 0; ++ if (!au_opt_test(au_mntflags(sb), XINO)) ++ return 0; /* no xino */ ++ ++ err = 0; ++ sbinfo = au_sbi(sb); ++ pos = h_ino; ++ if (unlikely(au_loff_max / sizeof(*ino) - 1 < pos)) { ++ AuIOErr1("too large hi%lu\n", (unsigned long)h_ino); ++ return -EFBIG; ++ } ++ pos *= sizeof(*ino); ++ ++ br = au_sbr(sb, bindex); ++ file = au_xino_file(br); ++ if (vfsub_f_size_read(file) < pos + sizeof(*ino)) ++ return 0; /* no ino */ ++ ++ sz = xino_fread(sbinfo->si_xread, file, ino, sizeof(*ino), &pos); ++ if (sz == sizeof(*ino)) ++ return 0; /* success */ ++ ++ err = sz; ++ if (unlikely(sz >= 0)) { ++ err = -EIO; ++ AuIOErr("xino read error (%zd)\n", sz); ++ } ++ ++ return err; ++} ++ ++static int au_xino_do_write(vfs_writef_t write, struct file *file, ++ ino_t h_ino, ino_t ino) ++{ ++ loff_t pos; ++ ssize_t sz; ++ ++ pos = h_ino; ++ if (unlikely(au_loff_max / sizeof(ino) - 1 < pos)) { ++ AuIOErr1("too large hi%lu\n", (unsigned long)h_ino); ++ return -EFBIG; ++ } ++ pos *= sizeof(ino); ++ sz = xino_fwrite(write, file, &ino, sizeof(ino), &pos); ++ if (sz == sizeof(ino)) ++ return 0; /* success */ ++ ++ AuIOErr("write failed (%zd)\n", sz); ++ return -EIO; ++} ++ ++/* ++ * write @ino to the xinofile for the specified branch{@sb, @bindex} ++ * at the position of @h_ino. ++ * even if @ino is zero, it is written to the xinofile and means no entry. ++ * if the size of the xino file on a specific filesystem exceeds the watermark, ++ * try truncating it. ++ */ ++int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ ino_t ino) ++{ ++ int err; ++ unsigned int mnt_flags; ++ struct au_branch *br; ++ ++ BUILD_BUG_ON(sizeof(long long) != sizeof(au_loff_max) ++ || ((loff_t)-1) > 0); ++ SiMustAnyLock(sb); ++ ++ mnt_flags = au_mntflags(sb); ++ if (!au_opt_test(mnt_flags, XINO)) ++ return 0; ++ ++ br = au_sbr(sb, bindex); ++ err = au_xino_do_write(au_sbi(sb)->si_xwrite, au_xino_file(br), h_ino, ++ ino); ++ if (!err) { ++ if (au_opt_test(mnt_flags, TRUNC_XINO) ++ && au_test_fs_trunc_xino(au_br_sb(br))) ++ xino_try_trunc(sb, br); ++ return 0; /* success */ ++ } ++ ++ AuIOErr("write failed (%d)\n", err); ++ return -EIO; ++} ++ ++static ssize_t xino_fread_wkq(vfs_readf_t func, struct file *file, void *buf, ++ size_t size, loff_t *pos); ++ ++/* todo: unnecessary to support mmap_sem since kernel-space? */ ++ssize_t xino_fread(vfs_readf_t func, struct file *file, void *kbuf, size_t size, ++ loff_t *pos) ++{ ++ ssize_t err; ++ mm_segment_t oldfs; ++ union { ++ void *k; ++ char __user *u; ++ } buf; ++ int i; ++ const int prevent_endless = 10; ++ ++ i = 0; ++ buf.k = kbuf; ++ oldfs = get_fs(); ++ set_fs(KERNEL_DS); ++ do { ++ err = func(file, buf.u, size, pos); ++ if (err == -EINTR ++ && !au_wkq_test() ++ && fatal_signal_pending(current)) { ++ set_fs(oldfs); ++ err = xino_fread_wkq(func, file, kbuf, size, pos); ++ BUG_ON(err == -EINTR); ++ oldfs = get_fs(); ++ set_fs(KERNEL_DS); ++ } ++ } while (i++ < prevent_endless ++ && (err == -EAGAIN || err == -EINTR)); ++ set_fs(oldfs); ++ ++#if 0 /* reserved for future use */ ++ if (err > 0) ++ fsnotify_access(file->f_path.dentry); ++#endif ++ ++ return err; ++} ++ ++struct xino_fread_args { ++ ssize_t *errp; ++ vfs_readf_t func; ++ struct file *file; ++ void *buf; ++ size_t size; ++ loff_t *pos; ++}; ++ ++static void call_xino_fread(void *args) ++{ ++ struct xino_fread_args *a = args; ++ *a->errp = xino_fread(a->func, a->file, a->buf, a->size, a->pos); ++} ++ ++static ssize_t xino_fread_wkq(vfs_readf_t func, struct file *file, void *buf, ++ size_t size, loff_t *pos) ++{ ++ ssize_t err; ++ int wkq_err; ++ struct xino_fread_args args = { ++ .errp = &err, ++ .func = func, ++ .file = file, ++ .buf = buf, ++ .size = size, ++ .pos = pos ++ }; ++ ++ wkq_err = au_wkq_wait(call_xino_fread, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ ++ return err; ++} ++ ++static ssize_t xino_fwrite_wkq(vfs_writef_t func, struct file *file, void *buf, ++ size_t size, loff_t *pos); ++ ++static ssize_t do_xino_fwrite(vfs_writef_t func, struct file *file, void *kbuf, ++ size_t size, loff_t *pos) ++{ ++ ssize_t err; ++ mm_segment_t oldfs; ++ union { ++ void *k; ++ const char __user *u; ++ } buf; ++ int i; ++ const int prevent_endless = 10; ++ ++ i = 0; ++ buf.k = kbuf; ++ oldfs = get_fs(); ++ set_fs(KERNEL_DS); ++ do { ++ err = func(file, buf.u, size, pos); ++ if (err == -EINTR ++ && !au_wkq_test() ++ && fatal_signal_pending(current)) { ++ set_fs(oldfs); ++ err = xino_fwrite_wkq(func, file, kbuf, size, pos); ++ BUG_ON(err == -EINTR); ++ oldfs = get_fs(); ++ set_fs(KERNEL_DS); ++ } ++ } while (i++ < prevent_endless ++ && (err == -EAGAIN || err == -EINTR)); ++ set_fs(oldfs); ++ ++#if 0 /* reserved for future use */ ++ if (err > 0) ++ fsnotify_modify(file->f_path.dentry); ++#endif ++ ++ return err; ++} ++ ++struct do_xino_fwrite_args { ++ ssize_t *errp; ++ vfs_writef_t func; ++ struct file *file; ++ void *buf; ++ size_t size; ++ loff_t *pos; ++}; ++ ++static void call_do_xino_fwrite(void *args) ++{ ++ struct do_xino_fwrite_args *a = args; ++ *a->errp = do_xino_fwrite(a->func, a->file, a->buf, a->size, a->pos); ++} ++ ++static ssize_t xino_fwrite_wkq(vfs_writef_t func, struct file *file, void *buf, ++ size_t size, loff_t *pos) ++{ ++ ssize_t err; ++ int wkq_err; ++ struct do_xino_fwrite_args args = { ++ .errp = &err, ++ .func = func, ++ .file = file, ++ .buf = buf, ++ .size = size, ++ .pos = pos ++ }; ++ ++ /* ++ * it breaks RLIMIT_FSIZE and normal user's limit, ++ * users should care about quota and real 'filesystem full.' ++ */ ++ wkq_err = au_wkq_wait(call_do_xino_fwrite, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ ++ return err; ++} ++ ++ssize_t xino_fwrite(vfs_writef_t func, struct file *file, void *buf, ++ size_t size, loff_t *pos) ++{ ++ ssize_t err; ++ ++ if (rlimit(RLIMIT_FSIZE) == RLIM_INFINITY) { ++ lockdep_off(); ++ err = do_xino_fwrite(func, file, buf, size, pos); ++ lockdep_on(); ++ } else ++ err = xino_fwrite_wkq(func, file, buf, size, pos); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * inode number bitmap ++ */ ++static const int page_bits = (int)PAGE_SIZE * BITS_PER_BYTE; ++static ino_t xib_calc_ino(unsigned long pindex, int bit) ++{ ++ ino_t ino; ++ ++ AuDebugOn(bit < 0 || page_bits <= bit); ++ ino = AUFS_FIRST_INO + pindex * page_bits + bit; ++ return ino; ++} ++ ++static void xib_calc_bit(ino_t ino, unsigned long *pindex, int *bit) ++{ ++ AuDebugOn(ino < AUFS_FIRST_INO); ++ ino -= AUFS_FIRST_INO; ++ *pindex = ino / page_bits; ++ *bit = ino % page_bits; ++} ++ ++static int xib_pindex(struct super_block *sb, unsigned long pindex) ++{ ++ int err; ++ loff_t pos; ++ ssize_t sz; ++ struct au_sbinfo *sbinfo; ++ struct file *xib; ++ unsigned long *p; ++ ++ sbinfo = au_sbi(sb); ++ MtxMustLock(&sbinfo->si_xib_mtx); ++ AuDebugOn(pindex > ULONG_MAX / PAGE_SIZE ++ || !au_opt_test(sbinfo->si_mntflags, XINO)); ++ ++ if (pindex == sbinfo->si_xib_last_pindex) ++ return 0; ++ ++ xib = sbinfo->si_xib; ++ p = sbinfo->si_xib_buf; ++ pos = sbinfo->si_xib_last_pindex; ++ pos *= PAGE_SIZE; ++ sz = xino_fwrite(sbinfo->si_xwrite, xib, p, PAGE_SIZE, &pos); ++ if (unlikely(sz != PAGE_SIZE)) ++ goto out; ++ ++ pos = pindex; ++ pos *= PAGE_SIZE; ++ if (vfsub_f_size_read(xib) >= pos + PAGE_SIZE) ++ sz = xino_fread(sbinfo->si_xread, xib, p, PAGE_SIZE, &pos); ++ else { ++ memset(p, 0, PAGE_SIZE); ++ sz = xino_fwrite(sbinfo->si_xwrite, xib, p, PAGE_SIZE, &pos); ++ } ++ if (sz == PAGE_SIZE) { ++ sbinfo->si_xib_last_pindex = pindex; ++ return 0; /* success */ ++ } ++ ++out: ++ AuIOErr1("write failed (%zd)\n", sz); ++ err = sz; ++ if (sz >= 0) ++ err = -EIO; ++ return err; ++} ++ ++static void au_xib_clear_bit(struct inode *inode) ++{ ++ int err, bit; ++ unsigned long pindex; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ ++ AuDebugOn(inode->i_nlink); ++ ++ sb = inode->i_sb; ++ xib_calc_bit(inode->i_ino, &pindex, &bit); ++ AuDebugOn(page_bits <= bit); ++ sbinfo = au_sbi(sb); ++ mutex_lock(&sbinfo->si_xib_mtx); ++ err = xib_pindex(sb, pindex); ++ if (!err) { ++ clear_bit(bit, sbinfo->si_xib_buf); ++ sbinfo->si_xib_next_bit = bit; ++ } ++ mutex_unlock(&sbinfo->si_xib_mtx); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * truncate a xino bitmap file ++ */ ++ ++/* todo: slow */ ++static int do_xib_restore(struct super_block *sb, struct file *file, void *page) ++{ ++ int err, bit; ++ ssize_t sz; ++ unsigned long pindex; ++ loff_t pos, pend; ++ struct au_sbinfo *sbinfo; ++ vfs_readf_t func; ++ ino_t *ino; ++ unsigned long *p; ++ ++ err = 0; ++ sbinfo = au_sbi(sb); ++ MtxMustLock(&sbinfo->si_xib_mtx); ++ p = sbinfo->si_xib_buf; ++ func = sbinfo->si_xread; ++ pend = vfsub_f_size_read(file); ++ pos = 0; ++ while (pos < pend) { ++ sz = xino_fread(func, file, page, PAGE_SIZE, &pos); ++ err = sz; ++ if (unlikely(sz <= 0)) ++ goto out; ++ ++ err = 0; ++ for (ino = page; sz > 0; ino++, sz -= sizeof(ino)) { ++ if (unlikely(*ino < AUFS_FIRST_INO)) ++ continue; ++ ++ xib_calc_bit(*ino, &pindex, &bit); ++ AuDebugOn(page_bits <= bit); ++ err = xib_pindex(sb, pindex); ++ if (!err) ++ set_bit(bit, p); ++ else ++ goto out; ++ } ++ } ++ ++out: ++ return err; ++} ++ ++static int xib_restore(struct super_block *sb) ++{ ++ int err; ++ aufs_bindex_t bindex, bbot; ++ void *page; ++ struct au_branch *br; ++ ++ err = -ENOMEM; ++ page = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!page)) ++ goto out; ++ ++ err = 0; ++ bbot = au_sbbot(sb); ++ for (bindex = 0; !err && bindex <= bbot; bindex++) ++ if (!bindex || is_sb_shared(sb, bindex, bindex - 1) < 0) { ++ br = au_sbr(sb, bindex); ++ err = do_xib_restore(sb, au_xino_file(br), page); ++ } else ++ AuDbg("skip shared b%d\n", bindex); ++ free_page((unsigned long)page); ++ ++out: ++ return err; ++} ++ ++int au_xib_trunc(struct super_block *sb) ++{ ++ int err; ++ ssize_t sz; ++ loff_t pos; ++ struct au_sbinfo *sbinfo; ++ unsigned long *p; ++ struct file *file; ++ ++ SiMustWriteLock(sb); ++ ++ err = 0; ++ sbinfo = au_sbi(sb); ++ if (!au_opt_test(sbinfo->si_mntflags, XINO)) ++ goto out; ++ ++ file = sbinfo->si_xib; ++ if (vfsub_f_size_read(file) <= PAGE_SIZE) ++ goto out; ++ ++ file = au_xino_create2(sb, &sbinfo->si_xib->f_path, NULL); ++ err = PTR_ERR(file); ++ if (IS_ERR(file)) ++ goto out; ++ fput(sbinfo->si_xib); ++ sbinfo->si_xib = file; ++ ++ p = sbinfo->si_xib_buf; ++ memset(p, 0, PAGE_SIZE); ++ pos = 0; ++ sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xib, p, PAGE_SIZE, &pos); ++ if (unlikely(sz != PAGE_SIZE)) { ++ err = sz; ++ AuIOErr("err %d\n", err); ++ if (sz >= 0) ++ err = -EIO; ++ goto out; ++ } ++ ++ mutex_lock(&sbinfo->si_xib_mtx); ++ /* mnt_want_write() is unnecessary here */ ++ err = xib_restore(sb); ++ mutex_unlock(&sbinfo->si_xib_mtx); ++ ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_xino *au_xino_alloc(void) ++{ ++ struct au_xino *xi; ++ ++ xi = kzalloc(sizeof(*xi), GFP_NOFS); ++ if (unlikely(!xi)) ++ goto out; ++ ++ xi->xi_nondir.total = 8; /* initial size */ ++ xi->xi_nondir.array = kcalloc(xi->xi_nondir.total, sizeof(ino_t), ++ GFP_NOFS); ++ if (unlikely(!xi->xi_nondir.array)) ++ goto out_free; ++ ++ spin_lock_init(&xi->xi_nondir.spin); ++ init_waitqueue_head(&xi->xi_nondir.wqh); ++ atomic_set(&xi->xi_truncating, 0); ++ kref_init(&xi->xi_kref); ++ goto out; /* success */ ++ ++out_free: ++ kfree(xi); ++ xi = NULL; ++out: ++ return xi; ++} ++ ++static int au_xino_init(struct au_branch *br, struct file *file) ++{ ++ int err; ++ struct au_xino *xi; ++ ++ err = 0; ++ xi = au_xino_alloc(); ++ if (unlikely(!xi)) { ++ err = -ENOMEM; ++ goto out; ++ } ++ ++ get_file(file); ++ xi->xi_file = file; ++ AuDebugOn(br->br_xino); ++ br->br_xino = xi; ++ ++out: ++ return err; ++} ++ ++static void au_xino_release(struct kref *kref) ++{ ++ struct au_xino *xi; ++ int i; ++ ++ xi = container_of(kref, struct au_xino, xi_kref); ++ if (xi->xi_file) ++ fput(xi->xi_file); ++ for (i = xi->xi_nondir.total - 1; i >= 0; i--) ++ AuDebugOn(xi->xi_nondir.array[i]); ++ kfree(xi->xi_nondir.array); ++ kfree(xi); ++} ++ ++int au_xino_put(struct au_branch *br) ++{ ++ int ret; ++ struct au_xino *xi; ++ ++ ret = 0; ++ xi = br->br_xino; ++ if (xi) { ++ br->br_xino = NULL; ++ ret = kref_put(&xi->xi_kref, au_xino_release); ++ } ++ ++ return ret; ++} ++ ++void au_xino_file_set(struct au_branch *br, struct file *file) ++{ ++ struct au_xino *xi; ++ struct file *f; ++ ++ if (file) ++ get_file(file); ++ xi = br->br_xino; ++ AuDebugOn(!xi); ++ f = xi->xi_file; ++ if (f) ++ fput(f); ++ xi->xi_file = file; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * xino mount option handlers ++ */ ++ ++/* xino bitmap */ ++static void xino_clear_xib(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ ++ SiMustWriteLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ /* unnecessary to clear sbinfo->si_xread and ->si_xwrite */ ++ if (sbinfo->si_xib) ++ fput(sbinfo->si_xib); ++ sbinfo->si_xib = NULL; ++ if (sbinfo->si_xib_buf) ++ free_page((unsigned long)sbinfo->si_xib_buf); ++ sbinfo->si_xib_buf = NULL; ++} ++ ++static int au_xino_set_xib(struct super_block *sb, struct path *path) ++{ ++ int err; ++ loff_t pos; ++ struct au_sbinfo *sbinfo; ++ struct file *file; ++ ++ SiMustWriteLock(sb); ++ ++ sbinfo = au_sbi(sb); ++ file = au_xino_create2(sb, path, sbinfo->si_xib); ++ err = PTR_ERR(file); ++ if (IS_ERR(file)) ++ goto out; ++ if (sbinfo->si_xib) ++ fput(sbinfo->si_xib); ++ sbinfo->si_xib = file; ++ sbinfo->si_xread = vfs_readf(file); ++ sbinfo->si_xwrite = vfs_writef(file); ++ ++ err = -ENOMEM; ++ if (!sbinfo->si_xib_buf) ++ sbinfo->si_xib_buf = (void *)get_zeroed_page(GFP_NOFS); ++ if (unlikely(!sbinfo->si_xib_buf)) ++ goto out_unset; ++ ++ sbinfo->si_xib_last_pindex = 0; ++ sbinfo->si_xib_next_bit = 0; ++ if (vfsub_f_size_read(file) < PAGE_SIZE) { ++ pos = 0; ++ err = xino_fwrite(sbinfo->si_xwrite, file, sbinfo->si_xib_buf, ++ PAGE_SIZE, &pos); ++ if (unlikely(err != PAGE_SIZE)) ++ goto out_free; ++ } ++ err = 0; ++ goto out; /* success */ ++ ++out_free: ++ if (sbinfo->si_xib_buf) ++ free_page((unsigned long)sbinfo->si_xib_buf); ++ sbinfo->si_xib_buf = NULL; ++ if (err >= 0) ++ err = -EIO; ++out_unset: ++ fput(sbinfo->si_xib); ++ sbinfo->si_xib = NULL; ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* xino for each branch */ ++static void xino_clear_br(struct super_block *sb) ++{ ++ aufs_bindex_t bindex, bbot; ++ struct au_branch *br; ++ ++ bbot = au_sbbot(sb); ++ for (bindex = 0; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ AuDebugOn(!br); ++ au_xino_put(br); ++ } ++} ++ ++static void au_xino_set_br_shared(struct super_block *sb, struct au_branch *br, ++ aufs_bindex_t bshared) ++{ ++ struct au_branch *brshared; ++ ++ brshared = au_sbr(sb, bshared); ++ AuDebugOn(!brshared->br_xino); ++ AuDebugOn(!brshared->br_xino->xi_file); ++ if (br->br_xino != brshared->br_xino) { ++ au_xino_get(brshared); ++ au_xino_put(br); ++ br->br_xino = brshared->br_xino; ++ } ++} ++ ++struct au_xino_do_set_br { ++ vfs_writef_t writef; ++ struct au_branch *br; ++ ino_t h_ino; ++ aufs_bindex_t bshared; ++}; ++ ++static int au_xino_do_set_br(struct super_block *sb, struct path *path, ++ struct au_xino_do_set_br *args) ++{ ++ int err; ++ struct file *file; ++ ++ if (args->bshared >= 0) { ++ /* shared xino */ ++ au_xino_set_br_shared(sb, args->br, args->bshared); ++ file = au_xino_file(args->br); ++ goto out_ino; /* success */ ++ } ++ ++ /* new xino */ ++ file = au_xino_create2(sb, path, au_xino_file(args->br)); ++ err = PTR_ERR(file); ++ if (IS_ERR(file)) ++ goto out; ++ if (!args->br->br_xino) { ++ err = au_xino_init(args->br, file); ++ fput(file); ++ if (unlikely(err)) ++ goto out; ++ } else { ++ au_xino_file_set(args->br, file); ++ fput(file); ++ } ++ ++out_ino: ++ err = au_xino_do_write(args->writef, file, args->h_ino, AUFS_ROOT_INO); ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++static int au_xino_set_br(struct super_block *sb, struct path *path) ++{ ++ int err; ++ aufs_bindex_t bindex, bbot; ++ struct au_xino_do_set_br args; ++ struct inode *inode; ++ ++ SiMustWriteLock(sb); ++ ++ bbot = au_sbbot(sb); ++ inode = d_inode(sb->s_root); ++ args.writef = au_sbi(sb)->si_xwrite; ++ for (bindex = 0; bindex <= bbot; bindex++) { ++ args.h_ino = au_h_iptr(inode, bindex)->i_ino; ++ args.br = au_sbr(sb, bindex); ++ args.bshared = is_sb_shared(sb, bindex, bindex - 1); ++ err = au_xino_do_set_br(sb, path, &args); ++ if (unlikely(err)) ++ break; ++ } ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++void au_xino_clr(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ ++ au_xigen_clr(sb); ++ xino_clear_xib(sb); ++ xino_clear_br(sb); ++ dbgaufs_brs_del(sb, 0); ++ au_xino_brid_set(sb, -1); ++ sbinfo = au_sbi(sb); ++ /* lvalue, do not call au_mntflags() */ ++ au_opt_clr(sbinfo->si_mntflags, XINO); ++} ++ ++int au_xino_set(struct super_block *sb, struct au_opt_xino *xiopt, int remount) ++{ ++ int err, skip; ++ struct dentry *dentry, *parent, *cur_dentry, *cur_parent; ++ struct qstr *dname, *cur_name; ++ struct file *cur_xino; ++ struct au_sbinfo *sbinfo; ++ struct path *path, *cur_path; ++ ++ SiMustWriteLock(sb); ++ ++ err = 0; ++ sbinfo = au_sbi(sb); ++ path = &xiopt->file->f_path; ++ dentry = path->dentry; ++ parent = dget_parent(dentry); ++ if (remount) { ++ skip = 0; ++ cur_xino = sbinfo->si_xib; ++ if (cur_xino) { ++ cur_path = &cur_xino->f_path; ++ cur_dentry = cur_path->dentry; ++ cur_parent = dget_parent(cur_dentry); ++ cur_name = &cur_dentry->d_name; ++ dname = &dentry->d_name; ++ skip = (cur_parent == parent ++ && au_qstreq(dname, cur_name)); ++ dput(cur_parent); ++ } ++ if (skip) ++ goto out; ++ } ++ ++ au_opt_set(sbinfo->si_mntflags, XINO); ++ err = au_xino_set_xib(sb, path); ++ /* si_x{read,write} are set */ ++ if (!err) ++ err = au_xigen_set(sb, path); ++ if (!err) ++ err = au_xino_set_br(sb, path); ++ if (!err) { ++ dbgaufs_brs_add(sb, 0, /*topdown*/1); ++ goto out; /* success */ ++ } ++ ++ /* reset all */ ++ AuIOErr("failed setting xino(%d).\n", err); ++ au_xino_clr(sb); ++ ++out: ++ dput(parent); ++ return err; ++} ++ ++/* ++ * create a xinofile at the default place/path. ++ */ ++struct file *au_xino_def(struct super_block *sb) ++{ ++ struct file *file; ++ char *page, *p; ++ struct au_branch *br; ++ struct super_block *h_sb; ++ struct path path; ++ aufs_bindex_t bbot, bindex, bwr; ++ ++ br = NULL; ++ bbot = au_sbbot(sb); ++ bwr = -1; ++ for (bindex = 0; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (au_br_writable(br->br_perm) ++ && !au_test_fs_bad_xino(au_br_sb(br))) { ++ bwr = bindex; ++ break; ++ } ++ } ++ ++ if (bwr >= 0) { ++ file = ERR_PTR(-ENOMEM); ++ page = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!page)) ++ goto out; ++ path.mnt = au_br_mnt(br); ++ path.dentry = au_h_dptr(sb->s_root, bwr); ++ p = d_path(&path, page, PATH_MAX - sizeof(AUFS_XINO_FNAME)); ++ file = (void *)p; ++ if (!IS_ERR(p)) { ++ strcat(p, "/" AUFS_XINO_FNAME); ++ AuDbg("%s\n", p); ++ file = au_xino_create(sb, p, /*silent*/0); ++ if (!IS_ERR(file)) ++ au_xino_brid_set(sb, br->br_id); ++ } ++ free_page((unsigned long)page); ++ } else { ++ file = au_xino_create(sb, AUFS_XINO_DEFPATH, /*silent*/0); ++ if (IS_ERR(file)) ++ goto out; ++ h_sb = file->f_path.dentry->d_sb; ++ if (unlikely(au_test_fs_bad_xino(h_sb))) { ++ pr_err("xino doesn't support %s(%s)\n", ++ AUFS_XINO_DEFPATH, au_sbtype(h_sb)); ++ fput(file); ++ file = ERR_PTR(-EINVAL); ++ } ++ if (!IS_ERR(file)) ++ au_xino_brid_set(sb, -1); ++ } ++ ++out: ++ return file; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * initialize the xinofile for the specified branch @br ++ * at the place/path where @base_file indicates. ++ * test whether another branch is on the same filesystem or not, ++ * if found then share the xinofile with another branch. ++ */ ++int au_xino_init_br(struct super_block *sb, struct au_branch *br, ino_t h_ino, ++ struct path *base) ++{ ++ int err; ++ struct au_xino_do_set_br args = { ++ .h_ino = h_ino, ++ .br = br ++ }; ++ ++ args.writef = au_sbi(sb)->si_xwrite; ++ args.bshared = sbr_find_shared(sb, /*btop*/0, au_sbbot(sb), ++ au_br_sb(br)); ++ err = au_xino_do_set_br(sb, base, &args); ++ if (unlikely(err)) ++ au_xino_put(br); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * get an unused inode number from bitmap ++ */ ++ino_t au_xino_new_ino(struct super_block *sb) ++{ ++ ino_t ino; ++ unsigned long *p, pindex, ul, pend; ++ struct au_sbinfo *sbinfo; ++ struct file *file; ++ int free_bit, err; ++ ++ if (!au_opt_test(au_mntflags(sb), XINO)) ++ return iunique(sb, AUFS_FIRST_INO); ++ ++ sbinfo = au_sbi(sb); ++ mutex_lock(&sbinfo->si_xib_mtx); ++ p = sbinfo->si_xib_buf; ++ free_bit = sbinfo->si_xib_next_bit; ++ if (free_bit < page_bits && !test_bit(free_bit, p)) ++ goto out; /* success */ ++ free_bit = find_first_zero_bit(p, page_bits); ++ if (free_bit < page_bits) ++ goto out; /* success */ ++ ++ pindex = sbinfo->si_xib_last_pindex; ++ for (ul = pindex - 1; ul < ULONG_MAX; ul--) { ++ err = xib_pindex(sb, ul); ++ if (unlikely(err)) ++ goto out_err; ++ free_bit = find_first_zero_bit(p, page_bits); ++ if (free_bit < page_bits) ++ goto out; /* success */ ++ } ++ ++ file = sbinfo->si_xib; ++ pend = vfsub_f_size_read(file) / PAGE_SIZE; ++ for (ul = pindex + 1; ul <= pend; ul++) { ++ err = xib_pindex(sb, ul); ++ if (unlikely(err)) ++ goto out_err; ++ free_bit = find_first_zero_bit(p, page_bits); ++ if (free_bit < page_bits) ++ goto out; /* success */ ++ } ++ BUG(); ++ ++out: ++ set_bit(free_bit, p); ++ sbinfo->si_xib_next_bit = free_bit + 1; ++ pindex = sbinfo->si_xib_last_pindex; ++ mutex_unlock(&sbinfo->si_xib_mtx); ++ ino = xib_calc_ino(pindex, free_bit); ++ AuDbg("i%lu\n", (unsigned long)ino); ++ return ino; ++out_err: ++ mutex_unlock(&sbinfo->si_xib_mtx); ++ AuDbg("i0\n"); ++ return 0; ++} ++ ++/* for s_op->delete_inode() */ ++void au_xino_delete_inode(struct inode *inode, const int unlinked) ++{ ++ int err; ++ unsigned int mnt_flags; ++ aufs_bindex_t bindex, bbot, bi; ++ unsigned char try_trunc; ++ struct au_iinfo *iinfo; ++ struct super_block *sb; ++ struct au_hinode *hi; ++ struct inode *h_inode; ++ struct au_branch *br; ++ vfs_writef_t xwrite; ++ ++ AuDebugOn(au_is_bad_inode(inode)); ++ ++ sb = inode->i_sb; ++ mnt_flags = au_mntflags(sb); ++ if (!au_opt_test(mnt_flags, XINO) ++ || inode->i_ino == AUFS_ROOT_INO) ++ return; ++ ++ if (unlinked) { ++ au_xigen_inc(inode); ++ au_xib_clear_bit(inode); ++ } ++ ++ iinfo = au_ii(inode); ++ bindex = iinfo->ii_btop; ++ if (bindex < 0) ++ return; ++ ++ xwrite = au_sbi(sb)->si_xwrite; ++ try_trunc = !!au_opt_test(mnt_flags, TRUNC_XINO); ++ hi = au_hinode(iinfo, bindex); ++ bbot = iinfo->ii_bbot; ++ for (; bindex <= bbot; bindex++, hi++) { ++ h_inode = hi->hi_inode; ++ if (!h_inode ++ || (!unlinked && h_inode->i_nlink)) ++ continue; ++ ++ /* inode may not be revalidated */ ++ bi = au_br_index(sb, hi->hi_id); ++ if (bi < 0) ++ continue; ++ ++ br = au_sbr(sb, bi); ++ err = au_xino_do_write(xwrite, au_xino_file(br), ++ h_inode->i_ino, /*ino*/0); ++ if (!err && try_trunc ++ && au_test_fs_trunc_xino(au_br_sb(br))) ++ xino_try_trunc(sb, br); ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_xinondir_find(struct au_xino *xi, ino_t h_ino) ++{ ++ int found, total, i; ++ ++ found = -1; ++ total = xi->xi_nondir.total; ++ for (i = 0; i < total; i++) { ++ if (xi->xi_nondir.array[i] != h_ino) ++ continue; ++ found = i; ++ break; ++ } ++ ++ return found; ++} ++ ++static int au_xinondir_expand(struct au_xino *xi) ++{ ++ int err, sz; ++ ino_t *p; ++ ++ BUILD_BUG_ON(KMALLOC_MAX_SIZE > INT_MAX); ++ ++ err = -ENOMEM; ++ sz = xi->xi_nondir.total * sizeof(ino_t); ++ if (unlikely(sz > KMALLOC_MAX_SIZE / 2)) ++ goto out; ++ p = au_kzrealloc(xi->xi_nondir.array, sz, sz << 1, GFP_ATOMIC, ++ /*may_shrink*/0); ++ if (p) { ++ xi->xi_nondir.array = p; ++ xi->xi_nondir.total <<= 1; ++ AuDbg("xi_nondir.total %d\n", xi->xi_nondir.total); ++ err = 0; ++ } ++ ++out: ++ return err; ++} ++ ++void au_xinondir_leave(struct super_block *sb, aufs_bindex_t bindex, ++ ino_t h_ino, int idx) ++{ ++ struct au_xino *xi; ++ ++ AuDebugOn(!au_opt_test(au_mntflags(sb), XINO)); ++ xi = au_sbr(sb, bindex)->br_xino; ++ AuDebugOn(idx < 0 || xi->xi_nondir.total <= idx); ++ ++ spin_lock(&xi->xi_nondir.spin); ++ AuDebugOn(xi->xi_nondir.array[idx] != h_ino); ++ xi->xi_nondir.array[idx] = 0; ++ spin_unlock(&xi->xi_nondir.spin); ++ wake_up_all(&xi->xi_nondir.wqh); ++} ++ ++int au_xinondir_enter(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ int *idx) ++{ ++ int err, found, empty; ++ struct au_xino *xi; ++ ++ err = 0; ++ *idx = -1; ++ if (!au_opt_test(au_mntflags(sb), XINO)) ++ goto out; /* no xino */ ++ ++ xi = au_sbr(sb, bindex)->br_xino; ++ ++again: ++ spin_lock(&xi->xi_nondir.spin); ++ found = au_xinondir_find(xi, h_ino); ++ if (found == -1) { ++ empty = au_xinondir_find(xi, /*h_ino*/0); ++ if (empty == -1) { ++ empty = xi->xi_nondir.total; ++ err = au_xinondir_expand(xi); ++ if (unlikely(err)) ++ goto out_unlock; ++ } ++ xi->xi_nondir.array[empty] = h_ino; ++ *idx = empty; ++ } else { ++ spin_unlock(&xi->xi_nondir.spin); ++ wait_event(xi->xi_nondir.wqh, ++ xi->xi_nondir.array[found] != h_ino); ++ goto again; ++ } ++ ++out_unlock: ++ spin_unlock(&xi->xi_nondir.spin); ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_xino_path(struct seq_file *seq, struct file *file) ++{ ++ int err; ++ ++ err = au_seq_path(seq, &file->f_path); ++ if (unlikely(err)) ++ goto out; ++ ++#define Deleted "\\040(deleted)" ++ seq->count -= sizeof(Deleted) - 1; ++ AuDebugOn(memcmp(seq->buf + seq->count, Deleted, ++ sizeof(Deleted) - 1)); ++#undef Deleted ++ ++out: ++ return err; ++} +diff --git a/fs/dcache.c b/fs/dcache.c +index 426fe9bb..69f944d2 100644 +--- a/fs/dcache.c ++++ b/fs/dcache.c +@@ -1198,7 +1198,7 @@ enum d_walk_ret { + * + * The @enter() and @finish() callbacks are called with d_lock held. + */ +-static void d_walk(struct dentry *parent, void *data, ++void d_walk(struct dentry *parent, void *data, + enum d_walk_ret (*enter)(void *, struct dentry *), + void (*finish)(void *)) + { +@@ -1306,6 +1306,7 @@ static void d_walk(struct dentry *parent, void *data, + seq = 1; + goto again; + } ++EXPORT_SYMBOL_GPL(d_walk); + + /* + * Search for at least 1 mount point in the dentry's subdirs. +@@ -2922,6 +2923,7 @@ void d_exchange(struct dentry *dentry1, struct dentry *dentry2) + + write_sequnlock(&rename_lock); + } ++EXPORT_SYMBOL_GPL(d_exchange); + + /** + * d_ancestor - search for an ancestor +diff --git a/fs/exec.c b/fs/exec.c +index b9fdb838..e744e66f 100644 +--- a/fs/exec.c ++++ b/fs/exec.c +@@ -104,6 +104,7 @@ bool path_noexec(const struct path *path) + return (path->mnt->mnt_flags & MNT_NOEXEC) || + (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC); + } ++EXPORT_SYMBOL_GPL(path_noexec); + + #ifdef CONFIG_USELIB + /* +diff --git a/fs/fcntl.c b/fs/fcntl.c +index ec03cf62..33d48e0c 100644 +--- a/fs/fcntl.c ++++ b/fs/fcntl.c +@@ -29,7 +29,7 @@ + + #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) + +-static int setfl(int fd, struct file * filp, unsigned long arg) ++int setfl(int fd, struct file * filp, unsigned long arg) + { + struct inode * inode = file_inode(filp); + int error = 0; +@@ -60,6 +60,8 @@ static int setfl(int fd, struct file * filp, unsigned long arg) + + if (filp->f_op->check_flags) + error = filp->f_op->check_flags(arg); ++ if (!error && filp->f_op->setfl) ++ error = filp->f_op->setfl(filp, arg); + if (error) + return error; + +@@ -80,6 +82,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg) + out: + return error; + } ++EXPORT_SYMBOL_GPL(setfl); + + static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, + int force) +diff --git a/fs/file_table.c b/fs/file_table.c +index ad17e05e..ae9f2676 100644 +--- a/fs/file_table.c ++++ b/fs/file_table.c +@@ -147,6 +147,7 @@ struct file *get_empty_filp(void) + } + return ERR_PTR(-ENFILE); + } ++EXPORT_SYMBOL_GPL(get_empty_filp); + + /** + * alloc_file - allocate and initialize a 'struct file' +@@ -258,6 +259,7 @@ void flush_delayed_fput(void) + { + delayed_fput(NULL); + } ++EXPORT_SYMBOL_GPL(flush_delayed_fput); + + static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); + +@@ -300,6 +302,7 @@ void __fput_sync(struct file *file) + } + + EXPORT_SYMBOL(fput); ++EXPORT_SYMBOL_GPL(__fput_sync); + + void put_filp(struct file *file) + { +@@ -308,6 +311,7 @@ void put_filp(struct file *file) + file_free(file); + } + } ++EXPORT_SYMBOL_GPL(put_filp); + + void __init files_init(void) + { +diff --git a/fs/inode.c b/fs/inode.c +index 3844c312..c7f6962c 100644 +--- a/fs/inode.c ++++ b/fs/inode.c +@@ -1643,7 +1643,7 @@ EXPORT_SYMBOL(generic_update_time); + * This does the actual work of updating an inodes time or version. Must have + * had called mnt_want_write() before calling this. + */ +-static int update_time(struct inode *inode, struct timespec *time, int flags) ++int update_time(struct inode *inode, struct timespec *time, int flags) + { + int (*update_time)(struct inode *, struct timespec *, int); + +@@ -1652,6 +1652,7 @@ static int update_time(struct inode *inode, struct timespec *time, int flags) + + return update_time(inode, time, flags); + } ++EXPORT_SYMBOL_GPL(update_time); + + /** + * touch_atime - update the access time +diff --git a/fs/namespace.c b/fs/namespace.c +index 77b46bf4..d808acb6 100644 +--- a/fs/namespace.c ++++ b/fs/namespace.c +@@ -468,6 +468,7 @@ void __mnt_drop_write(struct vfsmount *mnt) + mnt_dec_writers(real_mount(mnt)); + preempt_enable(); + } ++EXPORT_SYMBOL_GPL(__mnt_drop_write); + + /** + * mnt_drop_write - give up write access to a mount +@@ -801,6 +802,13 @@ static inline int check_mnt(struct mount *mnt) + return mnt->mnt_ns == current->nsproxy->mnt_ns; + } + ++/* for aufs, CONFIG_AUFS_BR_FUSE */ ++int is_current_mnt_ns(struct vfsmount *mnt) ++{ ++ return check_mnt(real_mount(mnt)); ++} ++EXPORT_SYMBOL_GPL(is_current_mnt_ns); ++ + /* + * vfsmount lock must be held for write + */ +@@ -1912,6 +1920,7 @@ int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, + } + return 0; + } ++EXPORT_SYMBOL_GPL(iterate_mounts); + + static void cleanup_group_ids(struct mount *mnt, struct mount *end) + { +diff --git a/fs/notify/group.c b/fs/notify/group.c +index fbe3cbeb..bdfc61e6 100644 +--- a/fs/notify/group.c ++++ b/fs/notify/group.c +@@ -22,6 +22,7 @@ + #include + #include + #include ++#include + + #include + #include "fsnotify.h" +@@ -100,6 +101,7 @@ void fsnotify_get_group(struct fsnotify_group *group) + { + atomic_inc(&group->refcnt); + } ++EXPORT_SYMBOL_GPL(fsnotify_get_group); + + /* + * Drop a reference to a group. Free it if it's through. +@@ -109,6 +111,7 @@ void fsnotify_put_group(struct fsnotify_group *group) + if (atomic_dec_and_test(&group->refcnt)) + fsnotify_final_destroy_group(group); + } ++EXPORT_SYMBOL_GPL(fsnotify_put_group); + + /* + * Create a new fsnotify_group and hold a reference for the group returned. +@@ -137,6 +140,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) + + return group; + } ++EXPORT_SYMBOL_GPL(fsnotify_alloc_group); + + int fsnotify_fasync(int fd, struct file *file, int on) + { +diff --git a/fs/notify/mark.c b/fs/notify/mark.c +index d3fea0bd..4b928ad3 100644 +--- a/fs/notify/mark.c ++++ b/fs/notify/mark.c +@@ -113,6 +113,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) + mark->free_mark(mark); + } + } ++EXPORT_SYMBOL_GPL(fsnotify_put_mark); + + /* Calculate mask of events for a list of marks */ + u32 fsnotify_recalc_mask(struct hlist_head *head) +@@ -230,6 +231,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark, + mutex_unlock(&group->mark_mutex); + fsnotify_free_mark(mark); + } ++EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); + + void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock) + { +@@ -425,6 +427,7 @@ int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group, + mutex_unlock(&group->mark_mutex); + return ret; + } ++EXPORT_SYMBOL_GPL(fsnotify_add_mark); + + /* + * Given a list of marks, find the mark associated with given group. If found +@@ -533,6 +536,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, + atomic_set(&mark->refcnt, 1); + mark->free_mark = free_mark; + } ++EXPORT_SYMBOL_GPL(fsnotify_init_mark); + + /* + * Destroy all marks in destroy_list, waits for SRCU period to finish before +diff --git a/fs/open.c b/fs/open.c +index e8818eaa..9341484b 100644 +--- a/fs/open.c ++++ b/fs/open.c +@@ -69,6 +69,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, + { + return do_truncate2(NULL, dentry, length, time_attrs, filp); + } ++EXPORT_SYMBOL_GPL(do_truncate); + + long vfs_truncate(const struct path *path, loff_t length) + { +@@ -708,6 +709,7 @@ int open_check_o_direct(struct file *f) + } + return 0; + } ++EXPORT_SYMBOL_GPL(open_check_o_direct); + + static int do_dentry_open(struct file *f, + struct inode *inode, +diff --git a/fs/proc/base.c b/fs/proc/base.c +index 1649be69..0b5a771a 100644 +--- a/fs/proc/base.c ++++ b/fs/proc/base.c +@@ -1991,7 +1991,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path) + down_read(&mm->mmap_sem); + vma = find_exact_vma(mm, vm_start, vm_end); + if (vma && vma->vm_file) { +- *path = vma->vm_file->f_path; ++ *path = vma_pr_or_file(vma)->f_path; + path_get(path); + rc = 0; + } +diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c +index f8595e8b..cb8eda06 100644 +--- a/fs/proc/nommu.c ++++ b/fs/proc/nommu.c +@@ -45,7 +45,10 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region) + file = region->vm_file; + + if (file) { +- struct inode *inode = file_inode(region->vm_file); ++ struct inode *inode; ++ ++ file = vmr_pr_or_file(region); ++ inode = file_inode(file); + dev = inode->i_sb->s_dev; + ino = inode->i_ino; + } +diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c +index 9182f84e..2324c307 100644 +--- a/fs/proc/task_mmu.c ++++ b/fs/proc/task_mmu.c +@@ -341,7 +341,10 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) + const char *name = NULL; + + if (file) { +- struct inode *inode = file_inode(vma->vm_file); ++ struct inode *inode; ++ ++ file = vma_pr_or_file(vma); ++ inode = file_inode(file); + dev = inode->i_sb->s_dev; + ino = inode->i_ino; + pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT; +@@ -1693,7 +1696,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) + struct proc_maps_private *proc_priv = &numa_priv->proc_maps; + struct vm_area_struct *vma = v; + struct numa_maps *md = &numa_priv->md; +- struct file *file = vma->vm_file; ++ struct file *file = vma_pr_or_file(vma); + struct mm_struct *mm = vma->vm_mm; + struct mm_walk walk = { + .hugetlb_entry = gather_hugetlb_stats, +diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c +index 37175621..6a328f1a 100644 +--- a/fs/proc/task_nommu.c ++++ b/fs/proc/task_nommu.c +@@ -155,7 +155,10 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma, + file = vma->vm_file; + + if (file) { +- struct inode *inode = file_inode(vma->vm_file); ++ struct inode *inode; ++ ++ file = vma_pr_or_file(vma); ++ inode = file_inode(file); + dev = inode->i_sb->s_dev; + ino = inode->i_ino; + pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT; +diff --git a/fs/read_write.c b/fs/read_write.c +index ce77e76a..954d2417 100644 +--- a/fs/read_write.c ++++ b/fs/read_write.c +@@ -514,6 +514,30 @@ ssize_t __vfs_write(struct file *file, const char __user *p, size_t count, + } + EXPORT_SYMBOL(__vfs_write); + ++vfs_readf_t vfs_readf(struct file *file) ++{ ++ const struct file_operations *fop = file->f_op; ++ ++ if (fop->read) ++ return fop->read; ++ if (fop->read_iter) ++ return new_sync_read; ++ return ERR_PTR(-ENOSYS); ++} ++EXPORT_SYMBOL_GPL(vfs_readf); ++ ++vfs_writef_t vfs_writef(struct file *file) ++{ ++ const struct file_operations *fop = file->f_op; ++ ++ if (fop->write) ++ return fop->write; ++ if (fop->write_iter) ++ return new_sync_write; ++ return ERR_PTR(-ENOSYS); ++} ++EXPORT_SYMBOL_GPL(vfs_writef); ++ + ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos) + { + mm_segment_t old_fs; +diff --git a/fs/splice.c b/fs/splice.c +index 01983bea..700db604 100644 +--- a/fs/splice.c ++++ b/fs/splice.c +@@ -856,8 +856,8 @@ EXPORT_SYMBOL(generic_splice_sendpage); + /* + * Attempt to initiate a splice from pipe to file. + */ +-static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, +- loff_t *ppos, size_t len, unsigned int flags) ++long do_splice_from(struct pipe_inode_info *pipe, struct file *out, ++ loff_t *ppos, size_t len, unsigned int flags) + { + ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, + loff_t *, size_t, unsigned int); +@@ -869,13 +869,14 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, + + return splice_write(pipe, out, ppos, len, flags); + } ++EXPORT_SYMBOL_GPL(do_splice_from); + + /* + * Attempt to initiate a splice from a file to a pipe. + */ +-static long do_splice_to(struct file *in, loff_t *ppos, +- struct pipe_inode_info *pipe, size_t len, +- unsigned int flags) ++long do_splice_to(struct file *in, loff_t *ppos, ++ struct pipe_inode_info *pipe, size_t len, ++ unsigned int flags) + { + ssize_t (*splice_read)(struct file *, loff_t *, + struct pipe_inode_info *, size_t, unsigned int); +@@ -898,6 +899,7 @@ static long do_splice_to(struct file *in, loff_t *ppos, + + return splice_read(in, ppos, pipe, len, flags); + } ++EXPORT_SYMBOL_GPL(do_splice_to); + + /** + * splice_direct_to_actor - splices data directly between two non-pipes +diff --git a/fs/sync.c b/fs/sync.c +index 5c2420c3..4ca74d5d 100644 +--- a/fs/sync.c ++++ b/fs/sync.c +@@ -27,7 +27,7 @@ + * wait == 1 case since in that case write_inode() functions do + * sync_dirty_buffer() and thus effectively write one block at a time. + */ +-static int __sync_filesystem(struct super_block *sb, int wait) ++int __sync_filesystem(struct super_block *sb, int wait) + { + if (wait) + sync_inodes_sb(sb); +@@ -38,6 +38,7 @@ static int __sync_filesystem(struct super_block *sb, int wait) + sb->s_op->sync_fs(sb, wait); + return __sync_blockdev(sb->s_bdev, wait); + } ++EXPORT_SYMBOL_GPL(__sync_filesystem); + + /* + * Write out and wait upon all dirty data associated with this +diff --git a/fs/xattr.c b/fs/xattr.c +index 1c91835a..ed13bcf5 100644 +--- a/fs/xattr.c ++++ b/fs/xattr.c +@@ -296,6 +296,7 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, + *xattr_value = value; + return error; + } ++EXPORT_SYMBOL_GPL(vfs_getxattr_alloc); + + ssize_t + __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name, +diff --git a/include/linux/file.h b/include/linux/file.h +index 7444f5fe..bdac0be2 100644 +--- a/include/linux/file.h ++++ b/include/linux/file.h +@@ -19,6 +19,7 @@ struct dentry; + struct path; + extern struct file *alloc_file(struct path *, fmode_t mode, + const struct file_operations *fop); ++extern struct file *get_empty_filp(void); + + static inline void fput_light(struct file *file, int fput_needed) + { +diff --git a/include/linux/fs.h b/include/linux/fs.h +index 8719c0c2..3deca014 100644 +--- a/include/linux/fs.h ++++ b/include/linux/fs.h +@@ -1316,6 +1316,7 @@ extern void fasync_free(struct fasync_struct *); + /* can be called from interrupts */ + extern void kill_fasync(struct fasync_struct **, int, int); + ++extern int setfl(int fd, struct file * filp, unsigned long arg); + extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); + extern void f_setown(struct file *filp, unsigned long arg, int force); + extern void f_delown(struct file *filp); +@@ -1749,6 +1750,7 @@ struct file_operations { + ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); + unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); + int (*check_flags)(int); ++ int (*setfl)(struct file *, unsigned long); + int (*flock) (struct file *, int, struct file_lock *); + ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); + ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); +@@ -1804,6 +1806,12 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, + struct iovec *fast_pointer, + struct iovec **ret_pointer); + ++typedef ssize_t (*vfs_readf_t)(struct file *, char __user *, size_t, loff_t *); ++typedef ssize_t (*vfs_writef_t)(struct file *, const char __user *, size_t, ++ loff_t *); ++vfs_readf_t vfs_readf(struct file *file); ++vfs_writef_t vfs_writef(struct file *file); ++ + extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *); + extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *); + extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); +@@ -2185,6 +2193,7 @@ extern int current_umask(void); + extern void ihold(struct inode * inode); + extern void iput(struct inode *); + extern int generic_update_time(struct inode *, struct timespec *, int); ++extern int update_time(struct inode *, struct timespec *, int); + + /* /sys/fs */ + extern struct kobject *fs_kobj; +@@ -2466,6 +2475,7 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb) + return false; + } + #endif ++extern int __sync_filesystem(struct super_block *, int); + extern int sync_filesystem(struct super_block *); + extern const struct file_operations def_blk_fops; + extern const struct file_operations def_chr_fops; +diff --git a/include/linux/mm.h b/include/linux/mm.h +index f4677779..9ec827a1 100644 +--- a/include/linux/mm.h ++++ b/include/linux/mm.h +@@ -1285,6 +1285,28 @@ static inline int fixup_user_fault(struct task_struct *tsk, + } + #endif + ++extern void vma_do_file_update_time(struct vm_area_struct *, const char[], int); ++extern struct file *vma_do_pr_or_file(struct vm_area_struct *, const char[], ++ int); ++extern void vma_do_get_file(struct vm_area_struct *, const char[], int); ++extern void vma_do_fput(struct vm_area_struct *, const char[], int); ++ ++#define vma_file_update_time(vma) vma_do_file_update_time(vma, __func__, \ ++ __LINE__) ++#define vma_pr_or_file(vma) vma_do_pr_or_file(vma, __func__, \ ++ __LINE__) ++#define vma_get_file(vma) vma_do_get_file(vma, __func__, __LINE__) ++#define vma_fput(vma) vma_do_fput(vma, __func__, __LINE__) ++ ++#ifndef CONFIG_MMU ++extern struct file *vmr_do_pr_or_file(struct vm_region *, const char[], int); ++extern void vmr_do_fput(struct vm_region *, const char[], int); ++ ++#define vmr_pr_or_file(region) vmr_do_pr_or_file(region, __func__, \ ++ __LINE__) ++#define vmr_fput(region) vmr_do_fput(region, __func__, __LINE__) ++#endif /* !CONFIG_MMU */ ++ + extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, + unsigned int gup_flags); + extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, +diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h +index d02ad26a..1ce6b70b 100644 +--- a/include/linux/mm_types.h ++++ b/include/linux/mm_types.h +@@ -285,6 +285,7 @@ struct vm_region { + unsigned long vm_top; /* region allocated to here */ + unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ + struct file *vm_file; /* the backing file or NULL */ ++ struct file *vm_prfile; /* the virtual backing file or NULL */ + + int vm_usage; /* region usage count (access under nommu_region_sem) */ + bool vm_icache_flushed : 1; /* true if the icache has been flushed for +@@ -366,6 +367,7 @@ struct vm_area_struct { + unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE + units */ + struct file * vm_file; /* File we map to (can be NULL). */ ++ struct file *vm_prfile; /* shadow of vm_file */ + void * vm_private_data; /* was vm_pte (shared mem) */ + + #ifndef CONFIG_MMU +diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h +index 12b2ab51..8b810d1f 100644 +--- a/include/linux/mnt_namespace.h ++++ b/include/linux/mnt_namespace.h +@@ -5,11 +5,14 @@ + struct mnt_namespace; + struct fs_struct; + struct user_namespace; ++struct vfsmount; + + extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, + struct user_namespace *, struct fs_struct *); + extern void put_mnt_ns(struct mnt_namespace *ns); + ++extern int is_current_mnt_ns(struct vfsmount *mnt); ++ + extern const struct file_operations proc_mounts_operations; + extern const struct file_operations proc_mountinfo_operations; + extern const struct file_operations proc_mountstats_operations; +diff --git a/include/linux/splice.h b/include/linux/splice.h +index 00a21166..1f0a4a2b 100644 +--- a/include/linux/splice.h ++++ b/include/linux/splice.h +@@ -86,4 +86,10 @@ extern void spd_release_page(struct splice_pipe_desc *, unsigned int); + + extern const struct pipe_buf_operations page_cache_pipe_buf_ops; + extern const struct pipe_buf_operations default_pipe_buf_ops; ++ ++extern long do_splice_from(struct pipe_inode_info *pipe, struct file *out, ++ loff_t *ppos, size_t len, unsigned int flags); ++extern long do_splice_to(struct file *in, loff_t *ppos, ++ struct pipe_inode_info *pipe, size_t len, ++ unsigned int flags); + #endif +diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild +index cd2be1c8..78f3c682 100644 +--- a/include/uapi/linux/Kbuild ++++ b/include/uapi/linux/Kbuild +@@ -59,6 +59,7 @@ header-y += atmsvc.h + header-y += atm_tcp.h + header-y += atm_zatm.h + header-y += audit.h ++header-y += aufs_type.h + header-y += auto_fs4.h + header-y += auto_fs.h + header-y += auxvec.h +diff --git a/include/uapi/linux/aufs_type.h b/include/uapi/linux/aufs_type.h +new file mode 100644 +index 00000000..d53ad109 +--- /dev/null ++++ b/include/uapi/linux/aufs_type.h +@@ -0,0 +1,447 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++#ifndef __AUFS_TYPE_H__ ++#define __AUFS_TYPE_H__ ++ ++#define AUFS_NAME "aufs" ++ ++#ifdef __KERNEL__ ++/* ++ * define it before including all other headers. ++ * sched.h may use pr_* macros before defining "current", so define the ++ * no-current version first, and re-define later. ++ */ ++#define pr_fmt(fmt) AUFS_NAME " %s:%d: " fmt, __func__, __LINE__ ++#include ++#undef pr_fmt ++#define pr_fmt(fmt) \ ++ AUFS_NAME " %s:%d:%.*s[%d]: " fmt, __func__, __LINE__, \ ++ (int)sizeof(current->comm), current->comm, current->pid ++#else ++#include ++#include ++#endif /* __KERNEL__ */ ++ ++#include ++ ++#define AUFS_VERSION "4.9.94+-20180730" ++ ++/* todo? move this to linux-2.6.19/include/magic.h */ ++#define AUFS_SUPER_MAGIC ('a' << 24 | 'u' << 16 | 'f' << 8 | 's') ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_BRANCH_MAX_127 ++typedef int8_t aufs_bindex_t; ++#define AUFS_BRANCH_MAX 127 ++#else ++typedef int16_t aufs_bindex_t; ++#ifdef CONFIG_AUFS_BRANCH_MAX_511 ++#define AUFS_BRANCH_MAX 511 ++#elif defined(CONFIG_AUFS_BRANCH_MAX_1023) ++#define AUFS_BRANCH_MAX 1023 ++#elif defined(CONFIG_AUFS_BRANCH_MAX_32767) ++#define AUFS_BRANCH_MAX 32767 ++#endif ++#endif ++ ++#ifdef __KERNEL__ ++#ifndef AUFS_BRANCH_MAX ++#error unknown CONFIG_AUFS_BRANCH_MAX value ++#endif ++#endif /* __KERNEL__ */ ++ ++/* ---------------------------------------------------------------------- */ ++ ++#define AUFS_FSTYPE AUFS_NAME ++ ++#define AUFS_ROOT_INO 2 ++#define AUFS_FIRST_INO 11 ++ ++#define AUFS_WH_PFX ".wh." ++#define AUFS_WH_PFX_LEN ((int)sizeof(AUFS_WH_PFX) - 1) ++#define AUFS_WH_TMP_LEN 4 ++/* a limit for rmdir/rename a dir and copyup */ ++#define AUFS_MAX_NAMELEN (NAME_MAX \ ++ - AUFS_WH_PFX_LEN * 2 /* doubly whiteouted */\ ++ - 1 /* dot */\ ++ - AUFS_WH_TMP_LEN) /* hex */ ++#define AUFS_XINO_FNAME "." AUFS_NAME ".xino" ++#define AUFS_XINO_DEFPATH "/tmp/" AUFS_XINO_FNAME ++#define AUFS_XINO_DEF_SEC 30 /* seconds */ ++#define AUFS_XINO_DEF_TRUNC 45 /* percentage */ ++#define AUFS_DIRWH_DEF 3 ++#define AUFS_RDCACHE_DEF 10 /* seconds */ ++#define AUFS_RDCACHE_MAX 3600 /* seconds */ ++#define AUFS_RDBLK_DEF 512 /* bytes */ ++#define AUFS_RDHASH_DEF 32 ++#define AUFS_WKQ_NAME AUFS_NAME "d" ++#define AUFS_MFS_DEF_SEC 30 /* seconds */ ++#define AUFS_MFS_MAX_SEC 3600 /* seconds */ ++#define AUFS_FHSM_CACHE_DEF_SEC 30 /* seconds */ ++#define AUFS_PLINK_WARN 50 /* number of plinks in a single bucket */ ++ ++/* pseudo-link maintenace under /proc */ ++#define AUFS_PLINK_MAINT_NAME "plink_maint" ++#define AUFS_PLINK_MAINT_DIR "fs/" AUFS_NAME ++#define AUFS_PLINK_MAINT_PATH AUFS_PLINK_MAINT_DIR "/" AUFS_PLINK_MAINT_NAME ++ ++/* dirren, renamed dir */ ++#define AUFS_DR_INFO_PFX AUFS_WH_PFX ".dr." ++#define AUFS_DR_BRHINO_NAME AUFS_WH_PFX "hino" ++/* whiteouted doubly */ ++#define AUFS_WH_DR_INFO_PFX AUFS_WH_PFX AUFS_DR_INFO_PFX ++#define AUFS_WH_DR_BRHINO AUFS_WH_PFX AUFS_DR_BRHINO_NAME ++ ++#define AUFS_DIROPQ_NAME AUFS_WH_PFX ".opq" /* whiteouted doubly */ ++#define AUFS_WH_DIROPQ AUFS_WH_PFX AUFS_DIROPQ_NAME ++ ++#define AUFS_BASE_NAME AUFS_WH_PFX AUFS_NAME ++#define AUFS_PLINKDIR_NAME AUFS_WH_PFX "plnk" ++#define AUFS_ORPHDIR_NAME AUFS_WH_PFX "orph" ++ ++/* doubly whiteouted */ ++#define AUFS_WH_BASE AUFS_WH_PFX AUFS_BASE_NAME ++#define AUFS_WH_PLINKDIR AUFS_WH_PFX AUFS_PLINKDIR_NAME ++#define AUFS_WH_ORPHDIR AUFS_WH_PFX AUFS_ORPHDIR_NAME ++ ++/* branch permissions and attributes */ ++#define AUFS_BRPERM_RW "rw" ++#define AUFS_BRPERM_RO "ro" ++#define AUFS_BRPERM_RR "rr" ++#define AUFS_BRATTR_COO_REG "coo_reg" ++#define AUFS_BRATTR_COO_ALL "coo_all" ++#define AUFS_BRATTR_FHSM "fhsm" ++#define AUFS_BRATTR_UNPIN "unpin" ++#define AUFS_BRATTR_ICEX "icex" ++#define AUFS_BRATTR_ICEX_SEC "icexsec" ++#define AUFS_BRATTR_ICEX_SYS "icexsys" ++#define AUFS_BRATTR_ICEX_TR "icextr" ++#define AUFS_BRATTR_ICEX_USR "icexusr" ++#define AUFS_BRATTR_ICEX_OTH "icexoth" ++#define AUFS_BRRATTR_WH "wh" ++#define AUFS_BRWATTR_NLWH "nolwh" ++#define AUFS_BRWATTR_MOO "moo" ++ ++#define AuBrPerm_RW 1 /* writable, hardlinkable wh */ ++#define AuBrPerm_RO (1 << 1) /* readonly */ ++#define AuBrPerm_RR (1 << 2) /* natively readonly */ ++#define AuBrPerm_Mask (AuBrPerm_RW | AuBrPerm_RO | AuBrPerm_RR) ++ ++#define AuBrAttr_COO_REG (1 << 3) /* copy-up on open */ ++#define AuBrAttr_COO_ALL (1 << 4) ++#define AuBrAttr_COO_Mask (AuBrAttr_COO_REG | AuBrAttr_COO_ALL) ++ ++#define AuBrAttr_FHSM (1 << 5) /* file-based hsm */ ++#define AuBrAttr_UNPIN (1 << 6) /* rename-able top dir of ++ branch. meaningless since ++ linux-3.18-rc1 */ ++ ++/* ignore error in copying XATTR */ ++#define AuBrAttr_ICEX_SEC (1 << 7) ++#define AuBrAttr_ICEX_SYS (1 << 8) ++#define AuBrAttr_ICEX_TR (1 << 9) ++#define AuBrAttr_ICEX_USR (1 << 10) ++#define AuBrAttr_ICEX_OTH (1 << 11) ++#define AuBrAttr_ICEX (AuBrAttr_ICEX_SEC \ ++ | AuBrAttr_ICEX_SYS \ ++ | AuBrAttr_ICEX_TR \ ++ | AuBrAttr_ICEX_USR \ ++ | AuBrAttr_ICEX_OTH) ++ ++#define AuBrRAttr_WH (1 << 12) /* whiteout-able */ ++#define AuBrRAttr_Mask AuBrRAttr_WH ++ ++#define AuBrWAttr_NoLinkWH (1 << 13) /* un-hardlinkable whiteouts */ ++#define AuBrWAttr_MOO (1 << 14) /* move-up on open */ ++#define AuBrWAttr_Mask (AuBrWAttr_NoLinkWH | AuBrWAttr_MOO) ++ ++#define AuBrAttr_CMOO_Mask (AuBrAttr_COO_Mask | AuBrWAttr_MOO) ++ ++/* #warning test userspace */ ++#ifdef __KERNEL__ ++#ifndef CONFIG_AUFS_FHSM ++#undef AuBrAttr_FHSM ++#define AuBrAttr_FHSM 0 ++#endif ++#ifndef CONFIG_AUFS_XATTR ++#undef AuBrAttr_ICEX ++#define AuBrAttr_ICEX 0 ++#undef AuBrAttr_ICEX_SEC ++#define AuBrAttr_ICEX_SEC 0 ++#undef AuBrAttr_ICEX_SYS ++#define AuBrAttr_ICEX_SYS 0 ++#undef AuBrAttr_ICEX_TR ++#define AuBrAttr_ICEX_TR 0 ++#undef AuBrAttr_ICEX_USR ++#define AuBrAttr_ICEX_USR 0 ++#undef AuBrAttr_ICEX_OTH ++#define AuBrAttr_ICEX_OTH 0 ++#endif ++#endif ++ ++/* the longest combination */ ++/* AUFS_BRATTR_ICEX and AUFS_BRATTR_ICEX_TR don't affect here */ ++#define AuBrPermStrSz sizeof(AUFS_BRPERM_RW \ ++ "+" AUFS_BRATTR_COO_REG \ ++ "+" AUFS_BRATTR_FHSM \ ++ "+" AUFS_BRATTR_UNPIN \ ++ "+" AUFS_BRATTR_ICEX_SEC \ ++ "+" AUFS_BRATTR_ICEX_SYS \ ++ "+" AUFS_BRATTR_ICEX_USR \ ++ "+" AUFS_BRATTR_ICEX_OTH \ ++ "+" AUFS_BRWATTR_NLWH) ++ ++typedef struct { ++ char a[AuBrPermStrSz]; ++} au_br_perm_str_t; ++ ++static inline int au_br_writable(int brperm) ++{ ++ return brperm & AuBrPerm_RW; ++} ++ ++static inline int au_br_whable(int brperm) ++{ ++ return brperm & (AuBrPerm_RW | AuBrRAttr_WH); ++} ++ ++static inline int au_br_wh_linkable(int brperm) ++{ ++ return !(brperm & AuBrWAttr_NoLinkWH); ++} ++ ++static inline int au_br_cmoo(int brperm) ++{ ++ return brperm & AuBrAttr_CMOO_Mask; ++} ++ ++static inline int au_br_fhsm(int brperm) ++{ ++ return brperm & AuBrAttr_FHSM; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ioctl */ ++enum { ++ /* readdir in userspace */ ++ AuCtl_RDU, ++ AuCtl_RDU_INO, ++ ++ AuCtl_WBR_FD, /* pathconf wrapper */ ++ AuCtl_IBUSY, /* busy inode */ ++ AuCtl_MVDOWN, /* move-down */ ++ AuCtl_BR, /* info about branches */ ++ AuCtl_FHSM_FD /* connection for fhsm */ ++}; ++ ++/* borrowed from linux/include/linux/kernel.h */ ++#ifndef ALIGN ++#define ALIGN(x, a) __ALIGN_MASK(x, (typeof(x))(a)-1) ++#define __ALIGN_MASK(x, mask) (((x)+(mask))&~(mask)) ++#endif ++ ++/* borrowed from linux/include/linux/compiler-gcc3.h */ ++#ifndef __aligned ++#define __aligned(x) __attribute__((aligned(x))) ++#endif ++ ++#ifdef __KERNEL__ ++#ifndef __packed ++#define __packed __attribute__((packed)) ++#endif ++#endif ++ ++struct au_rdu_cookie { ++ uint64_t h_pos; ++ int16_t bindex; ++ uint8_t flags; ++ uint8_t pad; ++ uint32_t generation; ++} __aligned(8); ++ ++struct au_rdu_ent { ++ uint64_t ino; ++ int16_t bindex; ++ uint8_t type; ++ uint8_t nlen; ++ uint8_t wh; ++ char name[0]; ++} __aligned(8); ++ ++static inline int au_rdu_len(int nlen) ++{ ++ /* include the terminating NULL */ ++ return ALIGN(sizeof(struct au_rdu_ent) + nlen + 1, ++ sizeof(uint64_t)); ++} ++ ++union au_rdu_ent_ul { ++ struct au_rdu_ent __user *e; ++ uint64_t ul; ++}; ++ ++enum { ++ AufsCtlRduV_SZ, ++ AufsCtlRduV_End ++}; ++ ++struct aufs_rdu { ++ /* input */ ++ union { ++ uint64_t sz; /* AuCtl_RDU */ ++ uint64_t nent; /* AuCtl_RDU_INO */ ++ }; ++ union au_rdu_ent_ul ent; ++ uint16_t verify[AufsCtlRduV_End]; ++ ++ /* input/output */ ++ uint32_t blk; ++ ++ /* output */ ++ union au_rdu_ent_ul tail; ++ /* number of entries which were added in a single call */ ++ uint64_t rent; ++ uint8_t full; ++ uint8_t shwh; ++ ++ struct au_rdu_cookie cookie; ++} __aligned(8); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* dirren. the branch is identified by the filename who contains this */ ++struct au_drinfo { ++ uint64_t ino; ++ union { ++ uint8_t oldnamelen; ++ uint64_t _padding; ++ }; ++ uint8_t oldname[0]; ++} __aligned(8); ++ ++struct au_drinfo_fdata { ++ uint32_t magic; ++ struct au_drinfo drinfo; ++} __aligned(8); ++ ++#define AUFS_DRINFO_MAGIC_V1 ('a' << 24 | 'd' << 16 | 'r' << 8 | 0x01) ++/* future */ ++#define AUFS_DRINFO_MAGIC_V2 ('a' << 24 | 'd' << 16 | 'r' << 8 | 0x02) ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct aufs_wbr_fd { ++ uint32_t oflags; ++ int16_t brid; ++} __aligned(8); ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct aufs_ibusy { ++ uint64_t ino, h_ino; ++ int16_t bindex; ++} __aligned(8); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* error code for move-down */ ++/* the actual message strings are implemented in aufs-util.git */ ++enum { ++ EAU_MVDOWN_OPAQUE = 1, ++ EAU_MVDOWN_WHITEOUT, ++ EAU_MVDOWN_UPPER, ++ EAU_MVDOWN_BOTTOM, ++ EAU_MVDOWN_NOUPPER, ++ EAU_MVDOWN_NOLOWERBR, ++ EAU_Last ++}; ++ ++/* flags for move-down */ ++#define AUFS_MVDOWN_DMSG 1 ++#define AUFS_MVDOWN_OWLOWER (1 << 1) /* overwrite lower */ ++#define AUFS_MVDOWN_KUPPER (1 << 2) /* keep upper */ ++#define AUFS_MVDOWN_ROLOWER (1 << 3) /* do even if lower is RO */ ++#define AUFS_MVDOWN_ROLOWER_R (1 << 4) /* did on lower RO */ ++#define AUFS_MVDOWN_ROUPPER (1 << 5) /* do even if upper is RO */ ++#define AUFS_MVDOWN_ROUPPER_R (1 << 6) /* did on upper RO */ ++#define AUFS_MVDOWN_BRID_UPPER (1 << 7) /* upper brid */ ++#define AUFS_MVDOWN_BRID_LOWER (1 << 8) /* lower brid */ ++#define AUFS_MVDOWN_FHSM_LOWER (1 << 9) /* find fhsm attr for lower */ ++#define AUFS_MVDOWN_STFS (1 << 10) /* req. stfs */ ++#define AUFS_MVDOWN_STFS_FAILED (1 << 11) /* output: stfs is unusable */ ++#define AUFS_MVDOWN_BOTTOM (1 << 12) /* output: no more lowers */ ++ ++/* index for move-down */ ++enum { ++ AUFS_MVDOWN_UPPER, ++ AUFS_MVDOWN_LOWER, ++ AUFS_MVDOWN_NARRAY ++}; ++ ++/* ++ * additional info of move-down ++ * number of free blocks and inodes. ++ * subset of struct kstatfs, but smaller and always 64bit. ++ */ ++struct aufs_stfs { ++ uint64_t f_blocks; ++ uint64_t f_bavail; ++ uint64_t f_files; ++ uint64_t f_ffree; ++}; ++ ++struct aufs_stbr { ++ int16_t brid; /* optional input */ ++ int16_t bindex; /* output */ ++ struct aufs_stfs stfs; /* output when AUFS_MVDOWN_STFS set */ ++} __aligned(8); ++ ++struct aufs_mvdown { ++ uint32_t flags; /* input/output */ ++ struct aufs_stbr stbr[AUFS_MVDOWN_NARRAY]; /* input/output */ ++ int8_t au_errno; /* output */ ++} __aligned(8); ++ ++/* ---------------------------------------------------------------------- */ ++ ++union aufs_brinfo { ++ /* PATH_MAX may differ between kernel-space and user-space */ ++ char _spacer[4096]; ++ struct { ++ int16_t id; ++ int perm; ++ char path[0]; ++ }; ++} __aligned(8); ++ ++/* ---------------------------------------------------------------------- */ ++ ++#define AuCtlType 'A' ++#define AUFS_CTL_RDU _IOWR(AuCtlType, AuCtl_RDU, struct aufs_rdu) ++#define AUFS_CTL_RDU_INO _IOWR(AuCtlType, AuCtl_RDU_INO, struct aufs_rdu) ++#define AUFS_CTL_WBR_FD _IOW(AuCtlType, AuCtl_WBR_FD, \ ++ struct aufs_wbr_fd) ++#define AUFS_CTL_IBUSY _IOWR(AuCtlType, AuCtl_IBUSY, struct aufs_ibusy) ++#define AUFS_CTL_MVDOWN _IOWR(AuCtlType, AuCtl_MVDOWN, \ ++ struct aufs_mvdown) ++#define AUFS_CTL_BRINFO _IOW(AuCtlType, AuCtl_BR, union aufs_brinfo) ++#define AUFS_CTL_FHSM_FD _IOW(AuCtlType, AuCtl_FHSM_FD, int) ++ ++#endif /* __AUFS_TYPE_H__ */ +diff --git a/kernel/fork.c b/kernel/fork.c +index 91063407..7db7d10d 100644 +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -663,7 +663,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, + struct inode *inode = file_inode(file); + struct address_space *mapping = file->f_mapping; + +- get_file(file); ++ vma_get_file(tmp); + if (tmp->vm_flags & VM_DENYWRITE) + atomic_dec(&inode->i_writecount); + i_mmap_lock_write(mapping); +diff --git a/kernel/task_work.c b/kernel/task_work.c +index d513051f..e056d542 100644 +--- a/kernel/task_work.c ++++ b/kernel/task_work.c +@@ -119,3 +119,4 @@ void task_work_run(void) + } while (work); + } + } ++EXPORT_SYMBOL_GPL(task_work_run); +diff --git a/mm/Makefile b/mm/Makefile +index 295bd7a9..14fa1c83 100644 +--- a/mm/Makefile ++++ b/mm/Makefile +@@ -37,7 +37,7 @@ obj-y := filemap.o mempool.o oom_kill.o \ + mm_init.o mmu_context.o percpu.o slab_common.o \ + compaction.o vmacache.o \ + interval_tree.o list_lru.o workingset.o \ +- debug.o $(mmu-y) ++ prfile.o debug.o $(mmu-y) + + obj-y += init-mm.o + +diff --git a/mm/filemap.c b/mm/filemap.c +index c82b3072..3fe8019f 100644 +--- a/mm/filemap.c ++++ b/mm/filemap.c +@@ -2311,7 +2311,7 @@ int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) + int ret = VM_FAULT_LOCKED; + + sb_start_pagefault(inode->i_sb); +- file_update_time(vma->vm_file); ++ vma_file_update_time(vma); + lock_page(page); + if (page->mapping != inode->i_mapping) { + unlock_page(page); +diff --git a/mm/memory.c b/mm/memory.c +index 47248dc0..d0bac427 100644 +--- a/mm/memory.c ++++ b/mm/memory.c +@@ -2124,7 +2124,7 @@ static inline int wp_page_reuse(struct fault_env *fe, pte_t orig_pte, + } + + if (!page_mkwrite) +- file_update_time(vma->vm_file); ++ vma_file_update_time(vma); + } + + return VM_FAULT_WRITE; +diff --git a/mm/mmap.c b/mm/mmap.c +index 6441ef82..c26f9675 100644 +--- a/mm/mmap.c ++++ b/mm/mmap.c +@@ -170,7 +170,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); + if (vma->vm_file) +- fput(vma->vm_file); ++ vma_fput(vma); + mpol_put(vma_policy(vma)); + kmem_cache_free(vm_area_cachep, vma); + return next; +@@ -893,7 +893,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, + if (remove_next) { + if (file) { + uprobe_munmap(next, next->vm_start, next->vm_end); +- fput(file); ++ vma_fput(vma); + } + if (next->anon_vma) + anon_vma_merge(vma, next); +@@ -1782,8 +1782,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, + return addr; + + unmap_and_free_vma: ++ vma_fput(vma); + vma->vm_file = NULL; +- fput(file); + + /* Undo any partial mapping done by a device driver. */ + unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); +@@ -2611,7 +2611,7 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, + goto out_free_mpol; + + if (new->vm_file) +- get_file(new->vm_file); ++ vma_get_file(new); + + if (new->vm_ops && new->vm_ops->open) + new->vm_ops->open(new); +@@ -2630,7 +2630,7 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, + if (new->vm_ops && new->vm_ops->close) + new->vm_ops->close(new); + if (new->vm_file) +- fput(new->vm_file); ++ vma_fput(new); + unlink_anon_vmas(new); + out_free_mpol: + mpol_put(vma_policy(new)); +@@ -2782,7 +2782,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, + struct vm_area_struct *vma; + unsigned long populate = 0; + unsigned long ret = -EINVAL; +- struct file *file; ++ struct file *file, *prfile; + + pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.txt.\n", + current->comm, current->pid); +@@ -2857,10 +2857,27 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, + } + } + +- file = get_file(vma->vm_file); ++ vma_get_file(vma); ++ file = vma->vm_file; ++ prfile = vma->vm_prfile; + ret = do_mmap_pgoff(vma->vm_file, start, size, + prot, flags, pgoff, &populate); ++ if (!IS_ERR_VALUE(ret) && file && prfile) { ++ struct vm_area_struct *new_vma; ++ ++ new_vma = find_vma(mm, ret); ++ if (!new_vma->vm_prfile) ++ new_vma->vm_prfile = prfile; ++ if (new_vma != vma) ++ get_file(prfile); ++ } ++ /* ++ * two fput()s instead of vma_fput(vma), ++ * coz vma may not be available anymore. ++ */ + fput(file); ++ if (prfile) ++ fput(prfile); + out: + up_write(&mm->mmap_sem); + if (populate) +@@ -3136,7 +3153,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, + if (anon_vma_clone(new_vma, vma)) + goto out_free_mempol; + if (new_vma->vm_file) +- get_file(new_vma->vm_file); ++ vma_get_file(new_vma); + if (new_vma->vm_ops && new_vma->vm_ops->open) + new_vma->vm_ops->open(new_vma); + vma_link(mm, new_vma, prev, rb_link, rb_parent); +diff --git a/mm/nommu.c b/mm/nommu.c +index 44265e00..781c61e3 100644 +--- a/mm/nommu.c ++++ b/mm/nommu.c +@@ -636,7 +636,7 @@ static void __put_nommu_region(struct vm_region *region) + up_write(&nommu_region_sem); + + if (region->vm_file) +- fput(region->vm_file); ++ vmr_fput(region); + + /* IO memory and memory shared directly out of the pagecache + * from ramfs/tmpfs mustn't be released here */ +@@ -794,7 +794,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); + if (vma->vm_file) +- fput(vma->vm_file); ++ vma_fput(vma); + put_nommu_region(vma->vm_region); + kmem_cache_free(vm_area_cachep, vma); + } +@@ -1320,7 +1320,7 @@ unsigned long do_mmap(struct file *file, + goto error_just_free; + } + } +- fput(region->vm_file); ++ vmr_fput(region); + kmem_cache_free(vm_region_jar, region); + region = pregion; + result = start; +@@ -1395,10 +1395,10 @@ unsigned long do_mmap(struct file *file, + up_write(&nommu_region_sem); + error: + if (region->vm_file) +- fput(region->vm_file); ++ vmr_fput(region); + kmem_cache_free(vm_region_jar, region); + if (vma->vm_file) +- fput(vma->vm_file); ++ vma_fput(vma); + kmem_cache_free(vm_area_cachep, vma); + return ret; + +diff --git a/mm/prfile.c b/mm/prfile.c +new file mode 100644 +index 00000000..86e01bdb +--- /dev/null ++++ b/mm/prfile.c +@@ -0,0 +1,85 @@ ++/* ++ * Mainly for aufs which mmap(2) different file and wants to print different ++ * path in /proc/PID/maps. ++ * Call these functions via macros defined in linux/mm.h. ++ * ++ * See Documentation/filesystems/aufs/design/06mmap.txt ++ * ++ * Copyright (c) 2014-2018 Junjro R. Okajima ++ * Copyright (c) 2014 Ian Campbell ++ */ ++ ++#include ++#include ++#include ++ ++/* #define PRFILE_TRACE */ ++static inline void prfile_trace(struct file *f, struct file *pr, ++ const char func[], int line, const char func2[]) ++{ ++#ifdef PRFILE_TRACE ++ if (pr) ++ pr_info("%s:%d: %s, %pD2\n", func, line, func2, f); ++#endif ++} ++ ++void vma_do_file_update_time(struct vm_area_struct *vma, const char func[], ++ int line) ++{ ++ struct file *f = vma->vm_file, *pr = vma->vm_prfile; ++ ++ prfile_trace(f, pr, func, line, __func__); ++ file_update_time(f); ++ if (f && pr) ++ file_update_time(pr); ++} ++ ++struct file *vma_do_pr_or_file(struct vm_area_struct *vma, const char func[], ++ int line) ++{ ++ struct file *f = vma->vm_file, *pr = vma->vm_prfile; ++ ++ prfile_trace(f, pr, func, line, __func__); ++ return (f && pr) ? pr : f; ++} ++ ++void vma_do_get_file(struct vm_area_struct *vma, const char func[], int line) ++{ ++ struct file *f = vma->vm_file, *pr = vma->vm_prfile; ++ ++ prfile_trace(f, pr, func, line, __func__); ++ get_file(f); ++ if (f && pr) ++ get_file(pr); ++} ++ ++void vma_do_fput(struct vm_area_struct *vma, const char func[], int line) ++{ ++ struct file *f = vma->vm_file, *pr = vma->vm_prfile; ++ ++ prfile_trace(f, pr, func, line, __func__); ++ fput(f); ++ if (f && pr) ++ fput(pr); ++} ++ ++#ifndef CONFIG_MMU ++struct file *vmr_do_pr_or_file(struct vm_region *region, const char func[], ++ int line) ++{ ++ struct file *f = region->vm_file, *pr = region->vm_prfile; ++ ++ prfile_trace(f, pr, func, line, __func__); ++ return (f && pr) ? pr : f; ++} ++ ++void vmr_do_fput(struct vm_region *region, const char func[], int line) ++{ ++ struct file *f = region->vm_file, *pr = region->vm_prfile; ++ ++ prfile_trace(f, pr, func, line, __func__); ++ fput(f); ++ if (f && pr) ++ fput(pr); ++} ++#endif /* !CONFIG_MMU */ +diff --git a/security/commoncap.c b/security/commoncap.c +index 1076608f..2e402d4f 100644 +--- a/security/commoncap.c ++++ b/security/commoncap.c +@@ -1086,12 +1086,14 @@ int cap_mmap_addr(unsigned long addr) + } + return ret; + } ++EXPORT_SYMBOL_GPL(cap_mmap_addr); + + int cap_mmap_file(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags) + { + return 0; + } ++EXPORT_SYMBOL_GPL(cap_mmap_file); + + #ifdef CONFIG_SECURITY + +diff --git a/security/device_cgroup.c b/security/device_cgroup.c +index db3bdc91..348a2295 100644 +--- a/security/device_cgroup.c ++++ b/security/device_cgroup.c +@@ -7,6 +7,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -849,6 +850,7 @@ int __devcgroup_inode_permission(struct inode *inode, int mask) + return __devcgroup_check_permission(type, imajor(inode), iminor(inode), + access); + } ++EXPORT_SYMBOL_GPL(__devcgroup_inode_permission); + + int devcgroup_inode_mknod(int mode, dev_t dev) + { +diff --git a/security/security.c b/security/security.c +index de6ebf85..e4b786b5 100644 +--- a/security/security.c ++++ b/security/security.c +@@ -444,6 +444,7 @@ int security_path_rmdir(const struct path *dir, struct dentry *dentry) + return 0; + return call_int_hook(path_rmdir, 0, dir, dentry); + } ++EXPORT_SYMBOL_GPL(security_path_rmdir); + + int security_path_unlink(const struct path *dir, struct dentry *dentry) + { +@@ -460,6 +461,7 @@ int security_path_symlink(const struct path *dir, struct dentry *dentry, + return 0; + return call_int_hook(path_symlink, 0, dir, dentry, old_name); + } ++EXPORT_SYMBOL_GPL(security_path_symlink); + + int security_path_link(struct dentry *old_dentry, const struct path *new_dir, + struct dentry *new_dentry) +@@ -468,6 +470,7 @@ int security_path_link(struct dentry *old_dentry, const struct path *new_dir, + return 0; + return call_int_hook(path_link, 0, old_dentry, new_dir, new_dentry); + } ++EXPORT_SYMBOL_GPL(security_path_link); + + int security_path_rename(const struct path *old_dir, struct dentry *old_dentry, + const struct path *new_dir, struct dentry *new_dentry, +@@ -495,6 +498,7 @@ int security_path_truncate(const struct path *path) + return 0; + return call_int_hook(path_truncate, 0, path); + } ++EXPORT_SYMBOL_GPL(security_path_truncate); + + int security_path_chmod(const struct path *path, umode_t mode) + { +@@ -502,6 +506,7 @@ int security_path_chmod(const struct path *path, umode_t mode) + return 0; + return call_int_hook(path_chmod, 0, path, mode); + } ++EXPORT_SYMBOL_GPL(security_path_chmod); + + int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid) + { +@@ -532,6 +537,7 @@ int security_inode_link(struct dentry *old_dentry, struct inode *dir, + return 0; + return call_int_hook(inode_link, 0, old_dentry, dir, new_dentry); + } ++EXPORT_SYMBOL_GPL(security_path_chown); + + int security_inode_unlink(struct inode *dir, struct dentry *dentry) + { +@@ -595,6 +601,7 @@ int security_inode_readlink(struct dentry *dentry) + return 0; + return call_int_hook(inode_readlink, 0, dentry); + } ++EXPORT_SYMBOL_GPL(security_inode_readlink); + + int security_inode_follow_link(struct dentry *dentry, struct inode *inode, + bool rcu) +@@ -610,6 +617,7 @@ int security_inode_permission(struct inode *inode, int mask) + return 0; + return call_int_hook(inode_permission, 0, inode, mask); + } ++EXPORT_SYMBOL_GPL(security_inode_permission); + + int security_inode_setattr(struct dentry *dentry, struct iattr *attr) + { +@@ -781,6 +789,7 @@ int security_file_permission(struct file *file, int mask) + + return fsnotify_perm(file, mask); + } ++EXPORT_SYMBOL_GPL(security_file_permission); + + int security_file_alloc(struct file *file) + { +@@ -840,6 +849,7 @@ int security_mmap_file(struct file *file, unsigned long prot, + return ret; + return ima_file_mmap(file, prot); + } ++EXPORT_SYMBOL_GPL(security_mmap_file); + + int security_mmap_addr(unsigned long addr) + { diff --git a/patch/kernel/odroidn2-default/patch-4.9.170-171.patch b/patch/kernel/odroidn2-default/patch-4.9.170-171.patch deleted file mode 100644 index bd31f7acaa..0000000000 --- a/patch/kernel/odroidn2-default/patch-4.9.170-171.patch +++ /dev/null @@ -1,1956 +0,0 @@ -diff --git a/Makefile b/Makefile -index 966069dab768..dbdef749e1c8 100644 ---- a/Makefile -+++ b/Makefile -@@ -1,6 +1,6 @@ - VERSION = 4 - PATCHLEVEL = 9 --SUBLEVEL = 170 -+SUBLEVEL = 171 - EXTRAVERSION = - NAME = Roaring Lionus - -@@ -655,8 +655,7 @@ KBUILD_CFLAGS += $(call cc-option,-fdata-sections,) - endif - - ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE --KBUILD_CFLAGS += $(call cc-option,-Oz,-Os) --KBUILD_CFLAGS += $(call cc-disable-warning,maybe-uninitialized,) -+KBUILD_CFLAGS += -Os $(call cc-disable-warning,maybe-uninitialized,) - else - ifdef CONFIG_PROFILE_ALL_BRANCHES - KBUILD_CFLAGS += -O2 $(call cc-disable-warning,maybe-uninitialized,) -diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h -index d7116f5935fb..86a43450f014 100644 ---- a/arch/arm64/include/asm/futex.h -+++ b/arch/arm64/include/asm/futex.h -@@ -53,7 +53,7 @@ - static inline int - arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) - { -- int oldval, ret, tmp; -+ int oldval = 0, ret, tmp; - - pagefault_disable(); - -diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S -index eff2f414e22b..ec234c43b3f4 100644 ---- a/arch/x86/crypto/poly1305-avx2-x86_64.S -+++ b/arch/x86/crypto/poly1305-avx2-x86_64.S -@@ -321,6 +321,12 @@ ENTRY(poly1305_4block_avx2) - vpaddq t2,t1,t1 - vmovq t1x,d4 - -+ # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> -+ # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small -+ # amount. Careful: we must not assume the carry bits 'd0 >> 26', -+ # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit -+ # integers. It's true in a single-block implementation, but not here. -+ - # d1 += d0 >> 26 - mov d0,%rax - shr $26,%rax -@@ -359,16 +365,16 @@ ENTRY(poly1305_4block_avx2) - # h0 += (d4 >> 26) * 5 - mov d4,%rax - shr $26,%rax -- lea (%eax,%eax,4),%eax -- add %eax,%ebx -+ lea (%rax,%rax,4),%rax -+ add %rax,%rbx - # h4 = d4 & 0x3ffffff - mov d4,%rax - and $0x3ffffff,%eax - mov %eax,h4 - - # h1 += h0 >> 26 -- mov %ebx,%eax -- shr $26,%eax -+ mov %rbx,%rax -+ shr $26,%rax - add %eax,h1 - # h0 = h0 & 0x3ffffff - andl $0x3ffffff,%ebx -diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S -index 338c748054ed..639d9760b089 100644 ---- a/arch/x86/crypto/poly1305-sse2-x86_64.S -+++ b/arch/x86/crypto/poly1305-sse2-x86_64.S -@@ -251,16 +251,16 @@ ENTRY(poly1305_block_sse2) - # h0 += (d4 >> 26) * 5 - mov d4,%rax - shr $26,%rax -- lea (%eax,%eax,4),%eax -- add %eax,%ebx -+ lea (%rax,%rax,4),%rax -+ add %rax,%rbx - # h4 = d4 & 0x3ffffff - mov d4,%rax - and $0x3ffffff,%eax - mov %eax,h4 - - # h1 += h0 >> 26 -- mov %ebx,%eax -- shr $26,%eax -+ mov %rbx,%rax -+ shr $26,%rax - add %eax,h1 - # h0 = h0 & 0x3ffffff - andl $0x3ffffff,%ebx -@@ -518,6 +518,12 @@ ENTRY(poly1305_2block_sse2) - paddq t2,t1 - movq t1,d4 - -+ # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> -+ # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small -+ # amount. Careful: we must not assume the carry bits 'd0 >> 26', -+ # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit -+ # integers. It's true in a single-block implementation, but not here. -+ - # d1 += d0 >> 26 - mov d0,%rax - shr $26,%rax -@@ -556,16 +562,16 @@ ENTRY(poly1305_2block_sse2) - # h0 += (d4 >> 26) * 5 - mov d4,%rax - shr $26,%rax -- lea (%eax,%eax,4),%eax -- add %eax,%ebx -+ lea (%rax,%rax,4),%rax -+ add %rax,%rbx - # h4 = d4 & 0x3ffffff - mov d4,%rax - and $0x3ffffff,%eax - mov %eax,h4 - - # h1 += h0 >> 26 -- mov %ebx,%eax -- shr $26,%eax -+ mov %rbx,%rax -+ shr $26,%rax - add %eax,h1 - # h0 = h0 & 0x3ffffff - andl $0x3ffffff,%ebx -diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c -index afb222b63cae..de050d5a4506 100644 ---- a/arch/x86/events/amd/core.c -+++ b/arch/x86/events/amd/core.c -@@ -113,22 +113,39 @@ static __initconst const u64 amd_hw_cache_event_ids - }; - - /* -- * AMD Performance Monitor K7 and later. -+ * AMD Performance Monitor K7 and later, up to and including Family 16h: - */ - static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = - { -- [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, -- [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, -- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, -- [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, -- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, -- [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, -- [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ -- [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */ -+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, -+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, -+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, -+ [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, -+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, -+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, -+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ -+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */ -+}; -+ -+/* -+ * AMD Performance Monitor Family 17h and later: -+ */ -+static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = -+{ -+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, -+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, -+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, -+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, -+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, -+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287, -+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187, - }; - - static u64 amd_pmu_event_map(int hw_event) - { -+ if (boot_cpu_data.x86 >= 0x17) -+ return amd_f17h_perfmon_event_map[hw_event]; -+ - return amd_perfmon_event_map[hw_event]; - } - -diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c -index 64a70b2e2285..3f3cfeca1083 100644 ---- a/arch/x86/kernel/kprobes/core.c -+++ b/arch/x86/kernel/kprobes/core.c -@@ -545,6 +545,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) - unsigned long *sara = stack_addr(regs); - - ri->ret_addr = (kprobe_opcode_t *) *sara; -+ ri->fp = sara; - - /* Replace the return addr with trampoline addr */ - *sara = (unsigned long) &kretprobe_trampoline; -@@ -746,15 +747,21 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) - unsigned long flags, orig_ret_address = 0; - unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; - kprobe_opcode_t *correct_ret_addr = NULL; -+ void *frame_pointer; -+ bool skipped = false; - - INIT_HLIST_HEAD(&empty_rp); - kretprobe_hash_lock(current, &head, &flags); - /* fixup registers */ - #ifdef CONFIG_X86_64 - regs->cs = __KERNEL_CS; -+ /* On x86-64, we use pt_regs->sp for return address holder. */ -+ frame_pointer = ®s->sp; - #else - regs->cs = __KERNEL_CS | get_kernel_rpl(); - regs->gs = 0; -+ /* On x86-32, we use pt_regs->flags for return address holder. */ -+ frame_pointer = ®s->flags; - #endif - regs->ip = trampoline_address; - regs->orig_ax = ~0UL; -@@ -776,8 +783,25 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) - if (ri->task != current) - /* another task is sharing our hash bucket */ - continue; -+ /* -+ * Return probes must be pushed on this hash list correct -+ * order (same as return order) so that it can be poped -+ * correctly. However, if we find it is pushed it incorrect -+ * order, this means we find a function which should not be -+ * probed, because the wrong order entry is pushed on the -+ * path of processing other kretprobe itself. -+ */ -+ if (ri->fp != frame_pointer) { -+ if (!skipped) -+ pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n"); -+ skipped = true; -+ continue; -+ } - - orig_ret_address = (unsigned long)ri->ret_addr; -+ if (skipped) -+ pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n", -+ ri->rp->kp.addr); - - if (orig_ret_address != trampoline_address) - /* -@@ -795,6 +819,8 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) - if (ri->task != current) - /* another task is sharing our hash bucket */ - continue; -+ if (ri->fp != frame_pointer) -+ continue; - - orig_ret_address = (unsigned long)ri->ret_addr; - if (ri->rp && ri->rp->handler) { -diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c -index 510cfc06701a..b636a1e849fd 100644 ---- a/arch/x86/kvm/emulate.c -+++ b/arch/x86/kvm/emulate.c -@@ -2579,15 +2579,13 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) - * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU - * supports long mode. - */ -- cr4 = ctxt->ops->get_cr(ctxt, 4); - if (emulator_has_longmode(ctxt)) { - struct desc_struct cs_desc; - - /* Zero CR4.PCIDE before CR0.PG. */ -- if (cr4 & X86_CR4_PCIDE) { -+ cr4 = ctxt->ops->get_cr(ctxt, 4); -+ if (cr4 & X86_CR4_PCIDE) - ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); -- cr4 &= ~X86_CR4_PCIDE; -- } - - /* A 32-bit code segment is required to clear EFER.LMA. */ - memset(&cs_desc, 0, sizeof(cs_desc)); -@@ -2601,13 +2599,16 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) - if (cr0 & X86_CR0_PE) - ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); - -- /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */ -- if (cr4 & X86_CR4_PAE) -- ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); -+ if (emulator_has_longmode(ctxt)) { -+ /* Clear CR4.PAE before clearing EFER.LME. */ -+ cr4 = ctxt->ops->get_cr(ctxt, 4); -+ if (cr4 & X86_CR4_PAE) -+ ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); - -- /* And finally go back to 32-bit mode. */ -- efer = 0; -- ctxt->ops->set_msr(ctxt, MSR_EFER, efer); -+ /* And finally go back to 32-bit mode. */ -+ efer = 0; -+ ctxt->ops->set_msr(ctxt, MSR_EFER, efer); -+ } - - smbase = ctxt->ops->get_smbase(ctxt); - if (emulator_has_longmode(ctxt)) -diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c -index 01eb0451b96d..9a6d258c3c16 100644 ---- a/arch/x86/kvm/svm.c -+++ b/arch/x86/kvm/svm.c -@@ -3940,14 +3940,25 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm) - kvm_lapic_reg_write(apic, APIC_ICR, icrl); - break; - case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: { -+ int i; -+ struct kvm_vcpu *vcpu; -+ struct kvm *kvm = svm->vcpu.kvm; - struct kvm_lapic *apic = svm->vcpu.arch.apic; - - /* -- * Update ICR high and low, then emulate sending IPI, -- * which is handled when writing APIC_ICR. -+ * At this point, we expect that the AVIC HW has already -+ * set the appropriate IRR bits on the valid target -+ * vcpus. So, we just need to kick the appropriate vcpu. - */ -- kvm_lapic_reg_write(apic, APIC_ICR2, icrh); -- kvm_lapic_reg_write(apic, APIC_ICR, icrl); -+ kvm_for_each_vcpu(i, vcpu, kvm) { -+ bool m = kvm_apic_match_dest(vcpu, apic, -+ icrl & KVM_APIC_SHORT_MASK, -+ GET_APIC_DEST_FIELD(icrh), -+ icrl & KVM_APIC_DEST_MASK); -+ -+ if (m && !avic_vcpu_is_running(vcpu)) -+ kvm_vcpu_wake_up(vcpu); -+ } - break; - } - case AVIC_IPI_FAILURE_INVALID_TARGET: -diff --git a/crypto/testmgr.h b/crypto/testmgr.h -index 9033088ca231..ebff33765ac3 100644 ---- a/crypto/testmgr.h -+++ b/crypto/testmgr.h -@@ -4527,7 +4527,49 @@ static struct hash_testvec poly1305_tv_template[] = { - .psize = 80, - .digest = "\x13\x00\x00\x00\x00\x00\x00\x00" - "\x00\x00\x00\x00\x00\x00\x00\x00", -- }, -+ }, { /* Regression test for overflow in AVX2 implementation */ -+ .plaintext = "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff\xff\xff\xff\xff" -+ "\xff\xff\xff\xff", -+ .psize = 300, -+ .digest = "\xfb\x5e\x96\xd8\x61\xd5\xc7\xc8" -+ "\x78\xe5\x87\xcc\x2d\x5a\x22\xe1", -+ } - }; - - /* -diff --git a/drivers/char/tpm/tpm_i2c_atmel.c b/drivers/char/tpm/tpm_i2c_atmel.c -index 95ce2e9ccdc6..cc4e642d3180 100644 ---- a/drivers/char/tpm/tpm_i2c_atmel.c -+++ b/drivers/char/tpm/tpm_i2c_atmel.c -@@ -65,7 +65,15 @@ static int i2c_atmel_send(struct tpm_chip *chip, u8 *buf, size_t len) - dev_dbg(&chip->dev, - "%s(buf=%*ph len=%0zx) -> sts=%d\n", __func__, - (int)min_t(size_t, 64, len), buf, len, status); -- return status; -+ -+ if (status < 0) -+ return status; -+ -+ /* The upper layer does not support incomplete sends. */ -+ if (status != len) -+ return -E2BIG; -+ -+ return 0; - } - - static int i2c_atmel_recv(struct tpm_chip *chip, u8 *buf, size_t count) -diff --git a/drivers/crypto/amcc/crypto4xx_alg.c b/drivers/crypto/amcc/crypto4xx_alg.c -index 4afca3968773..e3b8bebfdd30 100644 ---- a/drivers/crypto/amcc/crypto4xx_alg.c -+++ b/drivers/crypto/amcc/crypto4xx_alg.c -@@ -138,7 +138,8 @@ static int crypto4xx_setkey_aes(struct crypto_ablkcipher *cipher, - sa = (struct dynamic_sa_ctl *) ctx->sa_in; - ctx->hash_final = 0; - -- set_dynamic_sa_command_0(sa, SA_NOT_SAVE_HASH, SA_NOT_SAVE_IV, -+ set_dynamic_sa_command_0(sa, SA_NOT_SAVE_HASH, (cm == CRYPTO_MODE_CBC ? -+ SA_SAVE_IV : SA_NOT_SAVE_IV), - SA_LOAD_HASH_FROM_SA, SA_LOAD_IV_FROM_STATE, - SA_NO_HEADER_PROC, SA_HASH_ALG_NULL, - SA_CIPHER_ALG_AES, SA_PAD_TYPE_ZERO, -diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c -index c7524bbbaf98..7d066fa9f2ad 100644 ---- a/drivers/crypto/amcc/crypto4xx_core.c -+++ b/drivers/crypto/amcc/crypto4xx_core.c -@@ -646,6 +646,15 @@ static u32 crypto4xx_ablkcipher_done(struct crypto4xx_device *dev, - addr = dma_map_page(dev->core_dev->device, sg_page(dst), - dst->offset, dst->length, DMA_FROM_DEVICE); - } -+ -+ if (pd_uinfo->sa_va->sa_command_0.bf.save_iv == SA_SAVE_IV) { -+ struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); -+ -+ crypto4xx_memcpy_from_le32((u32 *)req->iv, -+ pd_uinfo->sr_va->save_iv, -+ crypto_skcipher_ivsize(skcipher)); -+ } -+ - crypto4xx_ret_sg_desc(dev, pd_uinfo); - if (ablk_req->base.complete != NULL) - ablk_req->base.complete(&ablk_req->base, 0); -diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c -index 1d645c9ab417..cac262a912c1 100644 ---- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c -+++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c -@@ -337,7 +337,8 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "FlexBook edge11 - M-FBE11"), - }, - .driver_data = (void *)&sipodev_desc -- } -+ }, -+ { } /* Terminate list */ - }; - - -diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c -index 784636800361..780f886ccbfe 100644 ---- a/drivers/iio/accel/kxcjk-1013.c -+++ b/drivers/iio/accel/kxcjk-1013.c -@@ -1340,6 +1340,8 @@ static int kxcjk1013_resume(struct device *dev) - - mutex_lock(&data->mutex); - ret = kxcjk1013_set_mode(data, OPERATION); -+ if (ret == 0) -+ ret = kxcjk1013_set_range(data, data->range); - mutex_unlock(&data->mutex); - - return ret; -diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c -index 22c4c17cd996..a1d072ecb717 100644 ---- a/drivers/iio/adc/ad_sigma_delta.c -+++ b/drivers/iio/adc/ad_sigma_delta.c -@@ -121,6 +121,7 @@ static int ad_sd_read_reg_raw(struct ad_sigma_delta *sigma_delta, - if (sigma_delta->info->has_registers) { - data[0] = reg << sigma_delta->info->addr_shift; - data[0] |= sigma_delta->info->read_mask; -+ data[0] |= sigma_delta->comm; - spi_message_add_tail(&t[0], &m); - } - spi_message_add_tail(&t[1], &m); -diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c -index e3e2155b0386..dd9f2280927b 100644 ---- a/drivers/iio/adc/at91_adc.c -+++ b/drivers/iio/adc/at91_adc.c -@@ -704,23 +704,29 @@ static int at91_adc_read_raw(struct iio_dev *idev, - ret = wait_event_interruptible_timeout(st->wq_data_avail, - st->done, - msecs_to_jiffies(1000)); -- if (ret == 0) -- ret = -ETIMEDOUT; -- if (ret < 0) { -- mutex_unlock(&st->lock); -- return ret; -- } -- -- *val = st->last_value; - -+ /* Disable interrupts, regardless if adc conversion was -+ * successful or not -+ */ - at91_adc_writel(st, AT91_ADC_CHDR, - AT91_ADC_CH(chan->channel)); - at91_adc_writel(st, AT91_ADC_IDR, BIT(chan->channel)); - -- st->last_value = 0; -- st->done = false; -+ if (ret > 0) { -+ /* a valid conversion took place */ -+ *val = st->last_value; -+ st->last_value = 0; -+ st->done = false; -+ ret = IIO_VAL_INT; -+ } else if (ret == 0) { -+ /* conversion timeout */ -+ dev_err(&idev->dev, "ADC Channel %d timeout.\n", -+ chan->channel); -+ ret = -ETIMEDOUT; -+ } -+ - mutex_unlock(&st->lock); -- return IIO_VAL_INT; -+ return ret; - - case IIO_CHAN_INFO_SCALE: - *val = st->vref_mv; -diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c -index 821919dd245b..b5a5517e3ce1 100644 ---- a/drivers/iio/gyro/bmg160_core.c -+++ b/drivers/iio/gyro/bmg160_core.c -@@ -583,11 +583,10 @@ static int bmg160_read_raw(struct iio_dev *indio_dev, - case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY: - return bmg160_get_filter(data, val); - case IIO_CHAN_INFO_SCALE: -- *val = 0; - switch (chan->type) { - case IIO_TEMP: -- *val2 = 500000; -- return IIO_VAL_INT_PLUS_MICRO; -+ *val = 500; -+ return IIO_VAL_INT; - case IIO_ANGL_VEL: - { - int i; -@@ -595,6 +594,7 @@ static int bmg160_read_raw(struct iio_dev *indio_dev, - for (i = 0; i < ARRAY_SIZE(bmg160_scale_table); ++i) { - if (bmg160_scale_table[i].dps_range == - data->dps_range) { -+ *val = 0; - *val2 = bmg160_scale_table[i].scale; - return IIO_VAL_INT_PLUS_MICRO; - } -diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c -index 6bf58d27b6fc..df306caba296 100644 ---- a/drivers/mmc/host/sdhci.c -+++ b/drivers/mmc/host/sdhci.c -@@ -944,8 +944,7 @@ static bool sdhci_needs_reset(struct sdhci_host *host, struct mmc_request *mrq) - return (!(host->flags & SDHCI_DEVICE_DEAD) && - ((mrq->cmd && mrq->cmd->error) || - (mrq->sbc && mrq->sbc->error) || -- (mrq->data && ((mrq->data->error && !mrq->data->stop) || -- (mrq->data->stop && mrq->data->stop->error))) || -+ (mrq->data && mrq->data->stop && mrq->data->stop->error) || - (host->quirks & SDHCI_QUIRK_RESET_AFTER_REQUEST))); - } - -@@ -997,6 +996,16 @@ static void sdhci_finish_data(struct sdhci_host *host) - host->data = NULL; - host->data_cmd = NULL; - -+ /* -+ * The controller needs a reset of internal state machines upon error -+ * conditions. -+ */ -+ if (data->error) { -+ if (!host->cmd || host->cmd == data_cmd) -+ sdhci_do_reset(host, SDHCI_RESET_CMD); -+ sdhci_do_reset(host, SDHCI_RESET_DATA); -+ } -+ - if ((host->flags & (SDHCI_REQ_USE_DMA | SDHCI_USE_ADMA)) == - (SDHCI_REQ_USE_DMA | SDHCI_USE_ADMA)) - sdhci_adma_table_post(host, data); -@@ -1021,17 +1030,6 @@ static void sdhci_finish_data(struct sdhci_host *host) - if (data->stop && - (data->error || - !data->mrq->sbc)) { -- -- /* -- * The controller needs a reset of internal state machines -- * upon error conditions. -- */ -- if (data->error) { -- if (!host->cmd || host->cmd == data_cmd) -- sdhci_do_reset(host, SDHCI_RESET_CMD); -- sdhci_do_reset(host, SDHCI_RESET_DATA); -- } -- - /* - * 'cap_cmd_during_tfr' request must not use the command line - * after mmc_command_done() has been called. It is upper layer's -@@ -2457,7 +2455,7 @@ static void sdhci_timeout_data_timer(unsigned long data) - * * - \*****************************************************************************/ - --static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask) -+static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *intmask_p) - { - if (!host->cmd) { - /* -@@ -2480,20 +2478,12 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask) - else - host->cmd->error = -EILSEQ; - -- /* -- * If this command initiates a data phase and a response -- * CRC error is signalled, the card can start transferring -- * data - the card may have received the command without -- * error. We must not terminate the mmc_request early. -- * -- * If the card did not receive the command or returned an -- * error which prevented it sending data, the data phase -- * will time out. -- */ -+ /* Treat data command CRC error the same as data CRC error */ - if (host->cmd->data && - (intmask & (SDHCI_INT_CRC | SDHCI_INT_TIMEOUT)) == - SDHCI_INT_CRC) { - host->cmd = NULL; -+ *intmask_p |= SDHCI_INT_DATA_CRC; - return; - } - -@@ -2722,7 +2712,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id) - } - - if (intmask & SDHCI_INT_CMD_MASK) -- sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK); -+ sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK, &intmask); - - if (intmask & SDHCI_INT_DATA_MASK) - sdhci_data_irq(host, intmask & SDHCI_INT_DATA_MASK); -diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c -index 24a3433f3944..93169729dfc9 100644 ---- a/drivers/net/bonding/bond_main.c -+++ b/drivers/net/bonding/bond_main.c -@@ -3134,8 +3134,12 @@ static int bond_netdev_event(struct notifier_block *this, - return NOTIFY_DONE; - - if (event_dev->flags & IFF_MASTER) { -+ int ret; -+ - netdev_dbg(event_dev, "IFF_MASTER\n"); -- return bond_master_netdev_event(event, event_dev); -+ ret = bond_master_netdev_event(event, event_dev); -+ if (ret != NOTIFY_DONE) -+ return ret; - } - - if (event_dev->flags & IFF_SLAVE) { -diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c -index 375b6810bf46..b8874faaa813 100644 ---- a/drivers/net/team/team.c -+++ b/drivers/net/team/team.c -@@ -1251,6 +1251,23 @@ static int team_port_add(struct team *team, struct net_device *port_dev) - goto err_option_port_add; - } - -+ /* set promiscuity level to new slave */ -+ if (dev->flags & IFF_PROMISC) { -+ err = dev_set_promiscuity(port_dev, 1); -+ if (err) -+ goto err_set_slave_promisc; -+ } -+ -+ /* set allmulti level to new slave */ -+ if (dev->flags & IFF_ALLMULTI) { -+ err = dev_set_allmulti(port_dev, 1); -+ if (err) { -+ if (dev->flags & IFF_PROMISC) -+ dev_set_promiscuity(port_dev, -1); -+ goto err_set_slave_promisc; -+ } -+ } -+ - netif_addr_lock_bh(dev); - dev_uc_sync_multiple(port_dev, dev); - dev_mc_sync_multiple(port_dev, dev); -@@ -1267,6 +1284,9 @@ static int team_port_add(struct team *team, struct net_device *port_dev) - - return 0; - -+err_set_slave_promisc: -+ __team_option_inst_del_port(team, port); -+ - err_option_port_add: - team_upper_dev_unlink(team, port); - -@@ -1312,6 +1332,12 @@ static int team_port_del(struct team *team, struct net_device *port_dev) - - team_port_disable(team, port); - list_del_rcu(&port->list); -+ -+ if (dev->flags & IFF_PROMISC) -+ dev_set_promiscuity(port_dev, -1); -+ if (dev->flags & IFF_ALLMULTI) -+ dev_set_allmulti(port_dev, -1); -+ - team_upper_dev_unlink(team, port); - netdev_rx_handler_unregister(port_dev); - team_port_disable_netpoll(port); -diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h -index f68d492129c6..822833a52dd3 100644 ---- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h -+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h -@@ -669,7 +669,6 @@ enum rt2x00_state_flags { - CONFIG_CHANNEL_HT40, - CONFIG_POWERSAVING, - CONFIG_HT_DISABLED, -- CONFIG_QOS_DISABLED, - CONFIG_MONITORING, - - /* -diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c -index 987c7c4f43cd..55036ce5465c 100644 ---- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c -+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c -@@ -666,18 +666,8 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw, - rt2x00dev->intf_associated--; - - rt2x00leds_led_assoc(rt2x00dev, !!rt2x00dev->intf_associated); -- -- clear_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags); - } - -- /* -- * Check for access point which do not support 802.11e . We have to -- * generate data frames sequence number in S/W for such AP, because -- * of H/W bug. -- */ -- if (changes & BSS_CHANGED_QOS && !bss_conf->qos) -- set_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags); -- - /* - * When the erp information has changed, we should perform - * additional configuration steps. For all other changes we are done. -diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c -index 68b620b2462f..9a15a69b96a6 100644 ---- a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c -+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c -@@ -201,15 +201,18 @@ static void rt2x00queue_create_tx_descriptor_seq(struct rt2x00_dev *rt2x00dev, - if (!rt2x00_has_cap_flag(rt2x00dev, REQUIRE_SW_SEQNO)) { - /* - * rt2800 has a H/W (or F/W) bug, device incorrectly increase -- * seqno on retransmited data (non-QOS) frames. To workaround -- * the problem let's generate seqno in software if QOS is -- * disabled. -+ * seqno on retransmitted data (non-QOS) and management frames. -+ * To workaround the problem let's generate seqno in software. -+ * Except for beacons which are transmitted periodically by H/W -+ * hence hardware has to assign seqno for them. - */ -- if (test_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags)) -- __clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags); -- else -+ if (ieee80211_is_beacon(hdr->frame_control)) { -+ __set_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags); - /* H/W will generate sequence number */ - return; -+ } -+ -+ __clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags); - } - - /* -diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c -index e3ffd244603e..97aeaddd600d 100644 ---- a/drivers/scsi/libfc/fc_rport.c -+++ b/drivers/scsi/libfc/fc_rport.c -@@ -1935,7 +1935,6 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp) - FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n", - fc_rport_state(rdata)); - -- rdata->flags &= ~FC_RP_STARTED; - fc_rport_enter_delete(rdata, RPORT_EV_STOP); - mutex_unlock(&rdata->rp_mutex); - kref_put(&rdata->kref, rdata->local_port->tt.rport_destroy); -diff --git a/drivers/staging/comedi/drivers/ni_usb6501.c b/drivers/staging/comedi/drivers/ni_usb6501.c -index 5036eebb9162..2f174a34d9e9 100644 ---- a/drivers/staging/comedi/drivers/ni_usb6501.c -+++ b/drivers/staging/comedi/drivers/ni_usb6501.c -@@ -472,10 +472,8 @@ static int ni6501_alloc_usb_buffers(struct comedi_device *dev) - - size = usb_endpoint_maxp(devpriv->ep_tx); - devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL); -- if (!devpriv->usb_tx_buf) { -- kfree(devpriv->usb_rx_buf); -+ if (!devpriv->usb_tx_buf) - return -ENOMEM; -- } - - return 0; - } -@@ -527,6 +525,9 @@ static int ni6501_auto_attach(struct comedi_device *dev, - if (!devpriv) - return -ENOMEM; - -+ mutex_init(&devpriv->mut); -+ usb_set_intfdata(intf, devpriv); -+ - ret = ni6501_find_endpoints(dev); - if (ret) - return ret; -@@ -535,9 +536,6 @@ static int ni6501_auto_attach(struct comedi_device *dev, - if (ret) - return ret; - -- mutex_init(&devpriv->mut); -- usb_set_intfdata(intf, devpriv); -- - ret = comedi_alloc_subdevices(dev, 2); - if (ret) - return ret; -diff --git a/drivers/staging/comedi/drivers/vmk80xx.c b/drivers/staging/comedi/drivers/vmk80xx.c -index a004aed0147a..1800eb3ae017 100644 ---- a/drivers/staging/comedi/drivers/vmk80xx.c -+++ b/drivers/staging/comedi/drivers/vmk80xx.c -@@ -691,10 +691,8 @@ static int vmk80xx_alloc_usb_buffers(struct comedi_device *dev) - - size = usb_endpoint_maxp(devpriv->ep_tx); - devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL); -- if (!devpriv->usb_tx_buf) { -- kfree(devpriv->usb_rx_buf); -+ if (!devpriv->usb_tx_buf) - return -ENOMEM; -- } - - return 0; - } -@@ -809,6 +807,8 @@ static int vmk80xx_auto_attach(struct comedi_device *dev, - - devpriv->model = board->model; - -+ sema_init(&devpriv->limit_sem, 8); -+ - ret = vmk80xx_find_usb_endpoints(dev); - if (ret) - return ret; -@@ -817,8 +817,6 @@ static int vmk80xx_auto_attach(struct comedi_device *dev, - if (ret) - return ret; - -- sema_init(&devpriv->limit_sem, 8); -- - usb_set_intfdata(intf, devpriv); - - if (devpriv->model == VMK8055_MODEL) -diff --git a/drivers/staging/iio/adc/ad7192.c b/drivers/staging/iio/adc/ad7192.c -index 4dc9ca3a11b4..b82a4ab77860 100644 ---- a/drivers/staging/iio/adc/ad7192.c -+++ b/drivers/staging/iio/adc/ad7192.c -@@ -109,10 +109,10 @@ - #define AD7192_CH_AIN3 BIT(6) /* AIN3 - AINCOM */ - #define AD7192_CH_AIN4 BIT(7) /* AIN4 - AINCOM */ - --#define AD7193_CH_AIN1P_AIN2M 0x000 /* AIN1(+) - AIN2(-) */ --#define AD7193_CH_AIN3P_AIN4M 0x001 /* AIN3(+) - AIN4(-) */ --#define AD7193_CH_AIN5P_AIN6M 0x002 /* AIN5(+) - AIN6(-) */ --#define AD7193_CH_AIN7P_AIN8M 0x004 /* AIN7(+) - AIN8(-) */ -+#define AD7193_CH_AIN1P_AIN2M 0x001 /* AIN1(+) - AIN2(-) */ -+#define AD7193_CH_AIN3P_AIN4M 0x002 /* AIN3(+) - AIN4(-) */ -+#define AD7193_CH_AIN5P_AIN6M 0x004 /* AIN5(+) - AIN6(-) */ -+#define AD7193_CH_AIN7P_AIN8M 0x008 /* AIN7(+) - AIN8(-) */ - #define AD7193_CH_TEMP 0x100 /* Temp senseor */ - #define AD7193_CH_AIN2P_AIN2M 0x200 /* AIN2(+) - AIN2(-) */ - #define AD7193_CH_AIN1 0x401 /* AIN1 - AINCOM */ -diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c -index 2383caf88b67..a54dbfe664cd 100644 ---- a/drivers/vhost/vhost.c -+++ b/drivers/vhost/vhost.c -@@ -863,8 +863,12 @@ static int vhost_new_umem_range(struct vhost_umem *umem, - u64 start, u64 size, u64 end, - u64 userspace_addr, int perm) - { -- struct vhost_umem_node *tmp, *node = kmalloc(sizeof(*node), GFP_ATOMIC); -+ struct vhost_umem_node *tmp, *node; - -+ if (!size) -+ return -EFAULT; -+ -+ node = kmalloc(sizeof(*node), GFP_ATOMIC); - if (!node) - return -ENOMEM; - -diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h -index 4ed4736b5bc6..5367b684c1f7 100644 ---- a/fs/cifs/cifsglob.h -+++ b/fs/cifs/cifsglob.h -@@ -1157,6 +1157,7 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file) - } - - struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); -+void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr); - void cifsFileInfo_put(struct cifsFileInfo *cifs_file); - - #define CIFS_CACHE_READ_FLG 1 -@@ -1651,6 +1652,7 @@ GLOBAL_EXTERN spinlock_t gidsidlock; - #endif /* CONFIG_CIFS_ACL */ - - void cifs_oplock_break(struct work_struct *work); -+void cifs_queue_oplock_break(struct cifsFileInfo *cfile); - - extern const struct slow_work_ops cifs_oplock_break_ops; - extern struct workqueue_struct *cifsiod_wq; -diff --git a/fs/cifs/file.c b/fs/cifs/file.c -index 7d295bf283ca..e7f1773b25d6 100644 ---- a/fs/cifs/file.c -+++ b/fs/cifs/file.c -@@ -358,12 +358,30 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file) - return cifs_file; - } - --/* -- * Release a reference on the file private data. This may involve closing -- * the filehandle out on the server. Must be called without holding -- * tcon->open_file_lock and cifs_file->file_info_lock. -+/** -+ * cifsFileInfo_put - release a reference of file priv data -+ * -+ * Always potentially wait for oplock handler. See _cifsFileInfo_put(). - */ - void cifsFileInfo_put(struct cifsFileInfo *cifs_file) -+{ -+ _cifsFileInfo_put(cifs_file, true); -+} -+ -+/** -+ * _cifsFileInfo_put - release a reference of file priv data -+ * -+ * This may involve closing the filehandle @cifs_file out on the -+ * server. Must be called without holding tcon->open_file_lock and -+ * cifs_file->file_info_lock. -+ * -+ * If @wait_for_oplock_handler is true and we are releasing the last -+ * reference, wait for any running oplock break handler of the file -+ * and cancel any pending one. If calling this function from the -+ * oplock break handler, you need to pass false. -+ * -+ */ -+void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) - { - struct inode *inode = d_inode(cifs_file->dentry); - struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); -@@ -411,7 +429,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) - - spin_unlock(&tcon->open_file_lock); - -- oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); -+ oplock_break_cancelled = wait_oplock_handler ? -+ cancel_work_sync(&cifs_file->oplock_break) : false; - - if (!tcon->need_reconnect && !cifs_file->invalidHandle) { - struct TCP_Server_Info *server = tcon->ses->server; -@@ -3913,6 +3932,7 @@ void cifs_oplock_break(struct work_struct *work) - cinode); - cifs_dbg(FYI, "Oplock release rc = %d\n", rc); - } -+ _cifsFileInfo_put(cfile, false /* do not wait for ourself */); - cifs_done_oplock_break(cinode); - } - -diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c -index 50559a80acf8..5e75df69062d 100644 ---- a/fs/cifs/misc.c -+++ b/fs/cifs/misc.c -@@ -494,8 +494,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &pCifsInode->flags); - -- queue_work(cifsoplockd_wq, -- &netfile->oplock_break); -+ cifs_queue_oplock_break(netfile); - netfile->oplock_break_cancelled = false; - - spin_unlock(&tcon->open_file_lock); -@@ -592,6 +591,28 @@ void cifs_put_writer(struct cifsInodeInfo *cinode) - spin_unlock(&cinode->writers_lock); - } - -+/** -+ * cifs_queue_oplock_break - queue the oplock break handler for cfile -+ * -+ * This function is called from the demultiplex thread when it -+ * receives an oplock break for @cfile. -+ * -+ * Assumes the tcon->open_file_lock is held. -+ * Assumes cfile->file_info_lock is NOT held. -+ */ -+void cifs_queue_oplock_break(struct cifsFileInfo *cfile) -+{ -+ /* -+ * Bump the handle refcount now while we hold the -+ * open_file_lock to enforce the validity of it for the oplock -+ * break handler. The matching put is done at the end of the -+ * handler. -+ */ -+ cifsFileInfo_get(cfile); -+ -+ queue_work(cifsoplockd_wq, &cfile->oplock_break); -+} -+ - void cifs_done_oplock_break(struct cifsInodeInfo *cinode) - { - clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); -diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c -index 244d27bb8fba..9994d15a32fc 100644 ---- a/fs/cifs/smb2misc.c -+++ b/fs/cifs/smb2misc.c -@@ -512,7 +512,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, - clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); - -- queue_work(cifsoplockd_wq, &cfile->oplock_break); -+ cifs_queue_oplock_break(cfile); - kfree(lw); - return true; - } -@@ -656,8 +656,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); - spin_unlock(&cfile->file_info_lock); -- queue_work(cifsoplockd_wq, -- &cfile->oplock_break); -+ -+ cifs_queue_oplock_break(cfile); - - spin_unlock(&tcon->open_file_lock); - spin_unlock(&cifs_tcp_ses_lock); -diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h -index e23392517db9..cb527c78de9f 100644 ---- a/include/linux/kprobes.h -+++ b/include/linux/kprobes.h -@@ -197,6 +197,7 @@ struct kretprobe_instance { - struct kretprobe *rp; - kprobe_opcode_t *ret_addr; - struct task_struct *task; -+ void *fp; - char data[0]; - }; - -diff --git a/kernel/kprobes.c b/kernel/kprobes.c -index f580352cc6e5..e2845dd53b30 100644 ---- a/kernel/kprobes.c -+++ b/kernel/kprobes.c -@@ -668,7 +668,6 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) - static int reuse_unused_kprobe(struct kprobe *ap) - { - struct optimized_kprobe *op; -- int ret; - - BUG_ON(!kprobe_unused(ap)); - /* -@@ -682,9 +681,8 @@ static int reuse_unused_kprobe(struct kprobe *ap) - /* Enable the probe again */ - ap->flags &= ~KPROBE_FLAG_DISABLED; - /* Optimize it again (remove from op->list) */ -- ret = kprobe_optready(ap); -- if (ret) -- return ret; -+ if (!kprobe_optready(ap)) -+ return -EINVAL; - - optimize_kprobe(ap); - return 0; -diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c -index d5b779d7e79f..26fc428476b9 100644 ---- a/kernel/locking/lockdep.c -+++ b/kernel/locking/lockdep.c -@@ -3446,9 +3446,6 @@ __lock_set_class(struct lockdep_map *lock, const char *name, - unsigned int depth; - int i; - -- if (unlikely(!debug_locks)) -- return 0; -- - depth = curr->lockdep_depth; - /* - * This function is about (re)setting the class of a held lock, -diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c -index 1c630d94f86b..4b1e0669740c 100644 ---- a/kernel/sched/fair.c -+++ b/kernel/sched/fair.c -@@ -4347,12 +4347,15 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) - return HRTIMER_NORESTART; - } - -+extern const u64 max_cfs_quota_period; -+ - static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) - { - struct cfs_bandwidth *cfs_b = - container_of(timer, struct cfs_bandwidth, period_timer); - int overrun; - int idle = 0; -+ int count = 0; - - raw_spin_lock(&cfs_b->lock); - for (;;) { -@@ -4360,6 +4363,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) - if (!overrun) - break; - -+ if (++count > 3) { -+ u64 new, old = ktime_to_ns(cfs_b->period); -+ -+ new = (old * 147) / 128; /* ~115% */ -+ new = min(new, max_cfs_quota_period); -+ -+ cfs_b->period = ns_to_ktime(new); -+ -+ /* since max is 1s, this is limited to 1e9^2, which fits in u64 */ -+ cfs_b->quota *= new; -+ cfs_b->quota = div64_u64(cfs_b->quota, old); -+ -+ pr_warn_ratelimited( -+ "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n", -+ smp_processor_id(), -+ div_u64(new, NSEC_PER_USEC), -+ div_u64(cfs_b->quota, NSEC_PER_USEC)); -+ -+ /* reset count so we don't come right back in here */ -+ count = 0; -+ } -+ - idle = do_sched_cfs_period_timer(cfs_b, overrun); - } - if (idle) -diff --git a/kernel/sysctl.c b/kernel/sysctl.c -index 5515d578095b..cf0aeaae567e 100644 ---- a/kernel/sysctl.c -+++ b/kernel/sysctl.c -@@ -124,6 +124,7 @@ static int zero; - static int __maybe_unused one = 1; - static int __maybe_unused two = 2; - static int __maybe_unused four = 4; -+static unsigned long zero_ul; - static unsigned long one_ul = 1; - static unsigned long long_max = LONG_MAX; - static int one_hundred = 100; -@@ -1683,7 +1684,7 @@ static struct ctl_table fs_table[] = { - .maxlen = sizeof(files_stat.max_files), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, -- .extra1 = &zero, -+ .extra1 = &zero_ul, - .extra2 = &long_max, - }, - { -diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c -index 8f4227d4cd39..0043aef0ed8d 100644 ---- a/kernel/trace/ftrace.c -+++ b/kernel/trace/ftrace.c -@@ -32,6 +32,7 @@ - #include - #include - #include -+#include - - #include - -@@ -5246,7 +5247,7 @@ void ftrace_reset_array_ops(struct trace_array *tr) - tr->ops->func = ftrace_stub; - } - --static inline void -+static nokprobe_inline void - __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ignored, struct pt_regs *regs) - { -@@ -5311,12 +5311,14 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, - { - __ftrace_ops_list_func(ip, parent_ip, NULL, regs); - } -+NOKPROBE_SYMBOL(ftrace_ops_list_func); - #else - static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *regs) - { - __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); - } -+NOKPROBE_SYMBOL(ftrace_ops_no_ops); - #endif - - /* -@@ -5343,6 +5346,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, - preempt_enable_notrace(); - trace_clear_recursion(bit); - } -+NOKPROBE_SYMBOL(ftrace_ops_assist_func); - - /** - * ftrace_ops_get_func - get the function a trampoline should call -diff --git a/mm/percpu.c b/mm/percpu.c -index 3794cfc88689..0462a2a00f05 100644 ---- a/mm/percpu.c -+++ b/mm/percpu.c -@@ -2048,8 +2048,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, - ai->groups[group].base_offset = areas[group] - base; - } - -- pr_info("Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n", -- PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size, -+ pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", -+ PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, - ai->dyn_size, ai->unit_size); - - rc = pcpu_setup_first_chunk(ai, base); -@@ -2162,8 +2162,8 @@ int __init pcpu_page_first_chunk(size_t reserved_size, - } - - /* we're ready, commit */ -- pr_info("%d %s pages/cpu @%p s%zu r%zu d%zu\n", -- unit_pages, psize_str, vm.addr, ai->static_size, -+ pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", -+ unit_pages, psize_str, ai->static_size, - ai->reserved_size, ai->dyn_size); - - rc = pcpu_setup_first_chunk(ai, vm.addr); -diff --git a/mm/vmstat.c b/mm/vmstat.c -index 5e6a4d76659d..9af8d369e112 100644 ---- a/mm/vmstat.c -+++ b/mm/vmstat.c -@@ -1075,13 +1075,8 @@ const char * const vmstat_text[] = { - #endif - #endif /* CONFIG_MEMORY_BALLOON */ - #ifdef CONFIG_DEBUG_TLBFLUSH --#ifdef CONFIG_SMP - "nr_tlb_remote_flush", - "nr_tlb_remote_flush_received", --#else -- "", /* nr_tlb_remote_flush */ -- "", /* nr_tlb_remote_flush_received */ --#endif /* CONFIG_SMP */ - "nr_tlb_local_flush_all", - "nr_tlb_local_flush_one", - #endif /* CONFIG_DEBUG_TLBFLUSH */ -diff --git a/net/atm/lec.c b/net/atm/lec.c -index 1e84c5226c84..704892d79bf1 100644 ---- a/net/atm/lec.c -+++ b/net/atm/lec.c -@@ -721,7 +721,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) - - static int lec_mcast_attach(struct atm_vcc *vcc, int arg) - { -- if (arg < 0 || arg >= MAX_LEC_ITF || !dev_lec[arg]) -+ if (arg < 0 || arg >= MAX_LEC_ITF) -+ return -EINVAL; -+ arg = array_index_nospec(arg, MAX_LEC_ITF); -+ if (!dev_lec[arg]) - return -EINVAL; - vcc->proto_data = dev_lec[arg]; - return lec_mcast_make(netdev_priv(dev_lec[arg]), vcc); -@@ -739,6 +742,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg) - i = arg; - if (arg >= MAX_LEC_ITF) - return -EINVAL; -+ i = array_index_nospec(arg, MAX_LEC_ITF); - if (!dev_lec[i]) { - int size; - -diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c -index 267b46af407f..c615dff40ab4 100644 ---- a/net/bridge/br_input.c -+++ b/net/bridge/br_input.c -@@ -231,13 +231,10 @@ static void __br_handle_local_finish(struct sk_buff *skb) - /* note: already called with rcu_read_lock */ - static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb) - { -- struct net_bridge_port *p = br_port_get_rcu(skb->dev); -- - __br_handle_local_finish(skb); - -- BR_INPUT_SKB_CB(skb)->brdev = p->br->dev; -- br_pass_frame_up(skb); -- return 0; -+ /* return 1 to signal the okfn() was called so it's ok to use the skb */ -+ return 1; - } - - /* -@@ -308,10 +305,18 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) - goto forward; - } - -- /* Deliver packet to local host only */ -- NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev), -- NULL, skb, skb->dev, NULL, br_handle_local_finish); -- return RX_HANDLER_CONSUMED; -+ /* The else clause should be hit when nf_hook(): -+ * - returns < 0 (drop/error) -+ * - returns = 0 (stolen/nf_queue) -+ * Thus return 1 from the okfn() to signal the skb is ok to pass -+ */ -+ if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, -+ dev_net(skb->dev), NULL, skb, skb->dev, NULL, -+ br_handle_local_finish) == 1) { -+ return RX_HANDLER_PASS; -+ } else { -+ return RX_HANDLER_CONSUMED; -+ } - } - - forward: -diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c -index 2136e45f5277..964ffff90432 100644 ---- a/net/bridge/br_multicast.c -+++ b/net/bridge/br_multicast.c -@@ -1983,7 +1983,8 @@ static void br_multicast_start_querier(struct net_bridge *br, - - __br_multicast_open(br, query); - -- list_for_each_entry(port, &br->port_list, list) { -+ rcu_read_lock(); -+ list_for_each_entry_rcu(port, &br->port_list, list) { - if (port->state == BR_STATE_DISABLED || - port->state == BR_STATE_BLOCKING) - continue; -@@ -1995,6 +1996,7 @@ static void br_multicast_start_querier(struct net_bridge *br, - br_multicast_enable(&port->ip6_own_query); - #endif - } -+ rcu_read_unlock(); - } - - int br_multicast_toggle(struct net_bridge *br, unsigned long val) -diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c -index 030d1531e897..17acc89f9dec 100644 ---- a/net/ipv4/fou.c -+++ b/net/ipv4/fou.c -@@ -119,6 +119,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) - struct guehdr *guehdr; - void *data; - u16 doffset = 0; -+ u8 proto_ctype; - - if (!fou) - return 1; -@@ -210,13 +211,14 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) - if (unlikely(guehdr->control)) - return gue_control_message(skb, guehdr); - -+ proto_ctype = guehdr->proto_ctype; - __skb_pull(skb, sizeof(struct udphdr) + hdrlen); - skb_reset_transport_header(skb); - - if (iptunnel_pull_offloads(skb)) - goto drop; - -- return -guehdr->proto_ctype; -+ return -proto_ctype; - - drop: - kfree_skb(skb); -diff --git a/net/ipv4/route.c b/net/ipv4/route.c -index c42fb2330b45..0e2cf9634541 100644 ---- a/net/ipv4/route.c -+++ b/net/ipv4/route.c -@@ -1170,9 +1170,23 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) - - static void ipv4_link_failure(struct sk_buff *skb) - { -+ struct ip_options opt; - struct rtable *rt; -+ int res; -+ -+ /* Recompile ip options since IPCB may not be valid anymore. -+ */ -+ memset(&opt, 0, sizeof(opt)); -+ opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); -+ -+ rcu_read_lock(); -+ res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); -+ rcu_read_unlock(); -+ -+ if (res) -+ return; - -- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); -+ __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); - - rt = skb_rtable(skb); - if (rt) -diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c -index cd4f13dda49e..e238539c3497 100644 ---- a/net/ipv4/tcp_input.c -+++ b/net/ipv4/tcp_input.c -@@ -389,11 +389,12 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb) - static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) - { - struct tcp_sock *tp = tcp_sk(sk); -+ int room; -+ -+ room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh; - - /* Check #1 */ -- if (tp->rcv_ssthresh < tp->window_clamp && -- (int)tp->rcv_ssthresh < tcp_space(sk) && -- !tcp_under_memory_pressure(sk)) { -+ if (room > 0 && !tcp_under_memory_pressure(sk)) { - int incr; - - /* Check #2. Increase window, if skb with such overhead -@@ -406,8 +407,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) - - if (incr) { - incr = max_t(int, incr, 2 * skb->len); -- tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr, -- tp->window_clamp); -+ tp->rcv_ssthresh += min(room, incr); - inet_csk(sk)->icsk_ack.quick |= 1; - } - } -diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h -index 49c8a9c9b91f..1a169de60192 100644 ---- a/net/mac80211/driver-ops.h -+++ b/net/mac80211/driver-ops.h -@@ -1163,6 +1163,9 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, - { - struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif); - -+ if (local->in_reconfig) -+ return; -+ - if (!check_sdata_in_driver(sdata)) - return; - -diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c -index 29d6699d5a06..55b4c0dc2b93 100644 ---- a/scripts/mod/file2alias.c -+++ b/scripts/mod/file2alias.c -@@ -47,49 +47,9 @@ typedef struct { - struct devtable { - const char *device_id; /* name of table, __mod___*_device_table. */ - unsigned long id_size; -- void *function; -+ int (*do_entry)(const char *filename, void *symval, char *alias); - }; - --#define ___cat(a,b) a ## b --#define __cat(a,b) ___cat(a,b) -- --/* we need some special handling for this host tool running eventually on -- * Darwin. The Mach-O section handling is a bit different than ELF section -- * handling. The differnces in detail are: -- * a) we have segments which have sections -- * b) we need a API call to get the respective section symbols */ --#if defined(__MACH__) --#include -- --#define INIT_SECTION(name) do { \ -- unsigned long name ## _len; \ -- char *__cat(pstart_,name) = getsectdata("__TEXT", \ -- #name, &__cat(name,_len)); \ -- char *__cat(pstop_,name) = __cat(pstart_,name) + \ -- __cat(name, _len); \ -- __cat(__start_,name) = (void *)__cat(pstart_,name); \ -- __cat(__stop_,name) = (void *)__cat(pstop_,name); \ -- } while (0) --#define SECTION(name) __attribute__((section("__TEXT, " #name))) -- --struct devtable **__start___devtable, **__stop___devtable; --#else --#define INIT_SECTION(name) /* no-op for ELF */ --#define SECTION(name) __attribute__((section(#name))) -- --/* We construct a table of pointers in an ELF section (pointers generally -- * go unpadded by gcc). ld creates boundary syms for us. */ --extern struct devtable *__start___devtable[], *__stop___devtable[]; --#endif /* __MACH__ */ -- --#if !defined(__used) --# if __GNUC__ == 3 && __GNUC_MINOR__ < 3 --# define __used __attribute__((__unused__)) --# else --# define __used __attribute__((__used__)) --# endif --#endif -- - /* Define a variable f that holds the value of field f of struct devid - * based at address m. - */ -@@ -102,16 +62,6 @@ extern struct devtable *__start___devtable[], *__stop___devtable[]; - #define DEF_FIELD_ADDR(m, devid, f) \ - typeof(((struct devid *)0)->f) *f = ((m) + OFF_##devid##_##f) - --/* Add a table entry. We test function type matches while we're here. */ --#define ADD_TO_DEVTABLE(device_id, type, function) \ -- static struct devtable __cat(devtable,__LINE__) = { \ -- device_id + 0*sizeof((function)((const char *)NULL, \ -- (void *)NULL, \ -- (char *)NULL)), \ -- SIZE_##type, (function) }; \ -- static struct devtable *SECTION(__devtable) __used \ -- __cat(devtable_ptr,__LINE__) = &__cat(devtable,__LINE__) -- - #define ADD(str, sep, cond, field) \ - do { \ - strcat(str, sep); \ -@@ -431,7 +381,6 @@ static int do_hid_entry(const char *filename, - - return 1; - } --ADD_TO_DEVTABLE("hid", hid_device_id, do_hid_entry); - - /* Looks like: ieee1394:venNmoNspNverN */ - static int do_ieee1394_entry(const char *filename, -@@ -456,7 +405,6 @@ static int do_ieee1394_entry(const char *filename, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("ieee1394", ieee1394_device_id, do_ieee1394_entry); - - /* Looks like: pci:vNdNsvNsdNbcNscNiN. */ - static int do_pci_entry(const char *filename, -@@ -500,7 +448,6 @@ static int do_pci_entry(const char *filename, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("pci", pci_device_id, do_pci_entry); - - /* looks like: "ccw:tNmNdtNdmN" */ - static int do_ccw_entry(const char *filename, -@@ -524,7 +471,6 @@ static int do_ccw_entry(const char *filename, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("ccw", ccw_device_id, do_ccw_entry); - - /* looks like: "ap:tN" */ - static int do_ap_entry(const char *filename, -@@ -535,7 +481,6 @@ static int do_ap_entry(const char *filename, - sprintf(alias, "ap:t%02X*", dev_type); - return 1; - } --ADD_TO_DEVTABLE("ap", ap_device_id, do_ap_entry); - - /* looks like: "css:tN" */ - static int do_css_entry(const char *filename, -@@ -546,7 +491,6 @@ static int do_css_entry(const char *filename, - sprintf(alias, "css:t%01X", type); - return 1; - } --ADD_TO_DEVTABLE("css", css_device_id, do_css_entry); - - /* Looks like: "serio:tyNprNidNexN" */ - static int do_serio_entry(const char *filename, -@@ -566,7 +510,6 @@ static int do_serio_entry(const char *filename, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("serio", serio_device_id, do_serio_entry); - - /* looks like: "acpi:ACPI0003" or "acpi:PNP0C0B" or "acpi:LNXVIDEO" or - * "acpi:bbsspp" (bb=base-class, ss=sub-class, pp=prog-if) -@@ -604,7 +547,6 @@ static int do_acpi_entry(const char *filename, - } - return 1; - } --ADD_TO_DEVTABLE("acpi", acpi_device_id, do_acpi_entry); - - /* looks like: "pnp:dD" */ - static void do_pnp_device_entry(void *symval, unsigned long size, -@@ -725,7 +667,6 @@ static int do_pcmcia_entry(const char *filename, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("pcmcia", pcmcia_device_id, do_pcmcia_entry); - - static int do_vio_entry(const char *filename, void *symval, - char *alias) -@@ -745,7 +686,6 @@ static int do_vio_entry(const char *filename, void *symval, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("vio", vio_device_id, do_vio_entry); - - #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) - -@@ -818,7 +758,6 @@ static int do_input_entry(const char *filename, void *symval, - do_input(alias, *swbit, 0, INPUT_DEVICE_ID_SW_MAX); - return 1; - } --ADD_TO_DEVTABLE("input", input_device_id, do_input_entry); - - static int do_eisa_entry(const char *filename, void *symval, - char *alias) -@@ -830,7 +769,6 @@ static int do_eisa_entry(const char *filename, void *symval, - strcat(alias, "*"); - return 1; - } --ADD_TO_DEVTABLE("eisa", eisa_device_id, do_eisa_entry); - - /* Looks like: parisc:tNhvNrevNsvN */ - static int do_parisc_entry(const char *filename, void *symval, -@@ -850,7 +788,6 @@ static int do_parisc_entry(const char *filename, void *symval, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("parisc", parisc_device_id, do_parisc_entry); - - /* Looks like: sdio:cNvNdN. */ - static int do_sdio_entry(const char *filename, -@@ -867,7 +804,6 @@ static int do_sdio_entry(const char *filename, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("sdio", sdio_device_id, do_sdio_entry); - - /* Looks like: ssb:vNidNrevN. */ - static int do_ssb_entry(const char *filename, -@@ -884,7 +820,6 @@ static int do_ssb_entry(const char *filename, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("ssb", ssb_device_id, do_ssb_entry); - - /* Looks like: bcma:mNidNrevNclN. */ - static int do_bcma_entry(const char *filename, -@@ -903,7 +838,6 @@ static int do_bcma_entry(const char *filename, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("bcma", bcma_device_id, do_bcma_entry); - - /* Looks like: virtio:dNvN */ - static int do_virtio_entry(const char *filename, void *symval, -@@ -919,7 +853,6 @@ static int do_virtio_entry(const char *filename, void *symval, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("virtio", virtio_device_id, do_virtio_entry); - - /* - * Looks like: vmbus:guid -@@ -942,7 +875,6 @@ static int do_vmbus_entry(const char *filename, void *symval, - - return 1; - } --ADD_TO_DEVTABLE("vmbus", hv_vmbus_device_id, do_vmbus_entry); - - /* Looks like: i2c:S */ - static int do_i2c_entry(const char *filename, void *symval, -@@ -953,7 +885,6 @@ static int do_i2c_entry(const char *filename, void *symval, - - return 1; - } --ADD_TO_DEVTABLE("i2c", i2c_device_id, do_i2c_entry); - - /* Looks like: spi:S */ - static int do_spi_entry(const char *filename, void *symval, -@@ -964,7 +895,6 @@ static int do_spi_entry(const char *filename, void *symval, - - return 1; - } --ADD_TO_DEVTABLE("spi", spi_device_id, do_spi_entry); - - static const struct dmifield { - const char *prefix; -@@ -1019,7 +949,6 @@ static int do_dmi_entry(const char *filename, void *symval, - strcat(alias, ":"); - return 1; - } --ADD_TO_DEVTABLE("dmi", dmi_system_id, do_dmi_entry); - - static int do_platform_entry(const char *filename, - void *symval, char *alias) -@@ -1028,7 +957,6 @@ static int do_platform_entry(const char *filename, - sprintf(alias, PLATFORM_MODULE_PREFIX "%s", *name); - return 1; - } --ADD_TO_DEVTABLE("platform", platform_device_id, do_platform_entry); - - static int do_mdio_entry(const char *filename, - void *symval, char *alias) -@@ -1053,7 +981,6 @@ static int do_mdio_entry(const char *filename, - - return 1; - } --ADD_TO_DEVTABLE("mdio", mdio_device_id, do_mdio_entry); - - /* Looks like: zorro:iN. */ - static int do_zorro_entry(const char *filename, void *symval, -@@ -1064,7 +991,6 @@ static int do_zorro_entry(const char *filename, void *symval, - ADD(alias, "i", id != ZORRO_WILDCARD, id); - return 1; - } --ADD_TO_DEVTABLE("zorro", zorro_device_id, do_zorro_entry); - - /* looks like: "pnp:dD" */ - static int do_isapnp_entry(const char *filename, -@@ -1080,7 +1006,6 @@ static int do_isapnp_entry(const char *filename, - (function >> 12) & 0x0f, (function >> 8) & 0x0f); - return 1; - } --ADD_TO_DEVTABLE("isapnp", isapnp_device_id, do_isapnp_entry); - - /* Looks like: "ipack:fNvNdN". */ - static int do_ipack_entry(const char *filename, -@@ -1096,7 +1021,6 @@ static int do_ipack_entry(const char *filename, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("ipack", ipack_device_id, do_ipack_entry); - - /* - * Append a match expression for a single masked hex digit. -@@ -1167,7 +1091,6 @@ static int do_amba_entry(const char *filename, - - return 1; - } --ADD_TO_DEVTABLE("amba", amba_id, do_amba_entry); - - /* - * looks like: "mipscdmm:tN" -@@ -1183,7 +1106,6 @@ static int do_mips_cdmm_entry(const char *filename, - sprintf(alias, "mipscdmm:t%02X*", type); - return 1; - } --ADD_TO_DEVTABLE("mipscdmm", mips_cdmm_device_id, do_mips_cdmm_entry); - - /* LOOKS like cpu:type:x86,venVVVVfamFFFFmodMMMM:feature:*,FEAT,* - * All fields are numbers. It would be nicer to use strings for vendor -@@ -1208,7 +1130,6 @@ static int do_x86cpu_entry(const char *filename, void *symval, - sprintf(alias + strlen(alias), "%04X*", feature); - return 1; - } --ADD_TO_DEVTABLE("x86cpu", x86_cpu_id, do_x86cpu_entry); - - /* LOOKS like cpu:type:*:feature:*FEAT* */ - static int do_cpu_entry(const char *filename, void *symval, char *alias) -@@ -1218,7 +1139,6 @@ static int do_cpu_entry(const char *filename, void *symval, char *alias) - sprintf(alias, "cpu:type:*:feature:*%04X*", feature); - return 1; - } --ADD_TO_DEVTABLE("cpu", cpu_feature, do_cpu_entry); - - /* Looks like: mei:S:uuid:N:* */ - static int do_mei_entry(const char *filename, void *symval, -@@ -1237,7 +1157,6 @@ static int do_mei_entry(const char *filename, void *symval, - - return 1; - } --ADD_TO_DEVTABLE("mei", mei_cl_device_id, do_mei_entry); - - /* Looks like: rapidio:vNdNavNadN */ - static int do_rio_entry(const char *filename, -@@ -1257,7 +1176,6 @@ static int do_rio_entry(const char *filename, - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("rapidio", rio_device_id, do_rio_entry); - - /* Looks like: ulpi:vNpN */ - static int do_ulpi_entry(const char *filename, void *symval, -@@ -1270,7 +1188,6 @@ static int do_ulpi_entry(const char *filename, void *symval, - - return 1; - } --ADD_TO_DEVTABLE("ulpi", ulpi_device_id, do_ulpi_entry); - - /* Looks like: hdaudio:vNrNaN */ - static int do_hda_entry(const char *filename, void *symval, char *alias) -@@ -1287,7 +1204,6 @@ static int do_hda_entry(const char *filename, void *symval, char *alias) - add_wildcard(alias); - return 1; - } --ADD_TO_DEVTABLE("hdaudio", hda_device_id, do_hda_entry); - - /* Looks like: fsl-mc:vNdN */ - static int do_fsl_mc_entry(const char *filename, void *symval, -@@ -1299,7 +1215,6 @@ static int do_fsl_mc_entry(const char *filename, void *symval, - sprintf(alias, "fsl-mc:v%08Xd%s", vendor, *obj_type); - return 1; - } --ADD_TO_DEVTABLE("fslmc", fsl_mc_device_id, do_fsl_mc_entry); - - /* Does namelen bytes of name exactly match the symbol? */ - static bool sym_is(const char *name, unsigned namelen, const char *symbol) -@@ -1313,12 +1228,11 @@ static bool sym_is(const char *name, unsigned namelen, const char *symbol) - static void do_table(void *symval, unsigned long size, - unsigned long id_size, - const char *device_id, -- void *function, -+ int (*do_entry)(const char *filename, void *symval, char *alias), - struct module *mod) - { - unsigned int i; - char alias[500]; -- int (*do_entry)(const char *, void *entry, char *alias) = function; - - device_id_check(mod->name, device_id, size, id_size, symval); - /* Leave last one: it's the terminator. */ -@@ -1332,6 +1246,44 @@ static void do_table(void *symval, unsigned long size, - } - } - -+static const struct devtable devtable[] = { -+ {"hid", SIZE_hid_device_id, do_hid_entry}, -+ {"ieee1394", SIZE_ieee1394_device_id, do_ieee1394_entry}, -+ {"pci", SIZE_pci_device_id, do_pci_entry}, -+ {"ccw", SIZE_ccw_device_id, do_ccw_entry}, -+ {"ap", SIZE_ap_device_id, do_ap_entry}, -+ {"css", SIZE_css_device_id, do_css_entry}, -+ {"serio", SIZE_serio_device_id, do_serio_entry}, -+ {"acpi", SIZE_acpi_device_id, do_acpi_entry}, -+ {"pcmcia", SIZE_pcmcia_device_id, do_pcmcia_entry}, -+ {"vio", SIZE_vio_device_id, do_vio_entry}, -+ {"input", SIZE_input_device_id, do_input_entry}, -+ {"eisa", SIZE_eisa_device_id, do_eisa_entry}, -+ {"parisc", SIZE_parisc_device_id, do_parisc_entry}, -+ {"sdio", SIZE_sdio_device_id, do_sdio_entry}, -+ {"ssb", SIZE_ssb_device_id, do_ssb_entry}, -+ {"bcma", SIZE_bcma_device_id, do_bcma_entry}, -+ {"virtio", SIZE_virtio_device_id, do_virtio_entry}, -+ {"vmbus", SIZE_hv_vmbus_device_id, do_vmbus_entry}, -+ {"i2c", SIZE_i2c_device_id, do_i2c_entry}, -+ {"spi", SIZE_spi_device_id, do_spi_entry}, -+ {"dmi", SIZE_dmi_system_id, do_dmi_entry}, -+ {"platform", SIZE_platform_device_id, do_platform_entry}, -+ {"mdio", SIZE_mdio_device_id, do_mdio_entry}, -+ {"zorro", SIZE_zorro_device_id, do_zorro_entry}, -+ {"isapnp", SIZE_isapnp_device_id, do_isapnp_entry}, -+ {"ipack", SIZE_ipack_device_id, do_ipack_entry}, -+ {"amba", SIZE_amba_id, do_amba_entry}, -+ {"mipscdmm", SIZE_mips_cdmm_device_id, do_mips_cdmm_entry}, -+ {"x86cpu", SIZE_x86_cpu_id, do_x86cpu_entry}, -+ {"cpu", SIZE_cpu_feature, do_cpu_entry}, -+ {"mei", SIZE_mei_cl_device_id, do_mei_entry}, -+ {"rapidio", SIZE_rio_device_id, do_rio_entry}, -+ {"ulpi", SIZE_ulpi_device_id, do_ulpi_entry}, -+ {"hdaudio", SIZE_hda_device_id, do_hda_entry}, -+ {"fslmc", SIZE_fsl_mc_device_id, do_fsl_mc_entry}, -+}; -+ - /* Create MODULE_ALIAS() statements. - * At this time, we cannot write the actual output C source yet, - * so we write into the mod->dev_table_buf buffer. */ -@@ -1386,13 +1338,14 @@ void handle_moddevtable(struct module *mod, struct elf_info *info, - else if (sym_is(name, namelen, "pnp_card")) - do_pnp_card_entries(symval, sym->st_size, mod); - else { -- struct devtable **p; -- INIT_SECTION(__devtable); -+ int i; -+ -+ for (i = 0; i < ARRAY_SIZE(devtable); i++) { -+ const struct devtable *p = &devtable[i]; - -- for (p = __start___devtable; p < __stop___devtable; p++) { -- if (sym_is(name, namelen, (*p)->device_id)) { -- do_table(symval, sym->st_size, (*p)->id_size, -- (*p)->device_id, (*p)->function, mod); -+ if (sym_is(name, namelen, p->device_id)) { -+ do_table(symval, sym->st_size, p->id_size, -+ p->device_id, p->do_entry, mod); - break; - } - } -diff --git a/security/device_cgroup.c b/security/device_cgroup.c -index 03c1652c9a1f..db3bdc91c520 100644 ---- a/security/device_cgroup.c -+++ b/security/device_cgroup.c -@@ -568,7 +568,7 @@ static int propagate_exception(struct dev_cgroup *devcg_root, - devcg->behavior == DEVCG_DEFAULT_ALLOW) { - rc = dev_exception_add(devcg, ex); - if (rc) -- break; -+ return rc; - } else { - /* - * in the other possible cases: -diff --git a/sound/core/info.c b/sound/core/info.c -index 8ab72e0f5932..358a6947342d 100644 ---- a/sound/core/info.c -+++ b/sound/core/info.c -@@ -724,8 +724,11 @@ snd_info_create_entry(const char *name, struct snd_info_entry *parent) - INIT_LIST_HEAD(&entry->children); - INIT_LIST_HEAD(&entry->list); - entry->parent = parent; -- if (parent) -+ if (parent) { -+ mutex_lock(&parent->access); - list_add_tail(&entry->list, &parent->children); -+ mutex_unlock(&parent->access); -+ } - return entry; - } - -@@ -809,7 +812,12 @@ void snd_info_free_entry(struct snd_info_entry * entry) - list_for_each_entry_safe(p, n, &entry->children, list) - snd_info_free_entry(p); - -- list_del(&entry->list); -+ p = entry->parent; -+ if (p) { -+ mutex_lock(&p->access); -+ list_del(&entry->list); -+ mutex_unlock(&p->access); -+ } - kfree(entry->name); - if (entry->private_free) - entry->private_free(entry); -diff --git a/sound/core/init.c b/sound/core/init.c -index 6bda8436d765..02e96c580cb7 100644 ---- a/sound/core/init.c -+++ b/sound/core/init.c -@@ -408,14 +408,7 @@ int snd_card_disconnect(struct snd_card *card) - card->shutdown = 1; - spin_unlock(&card->files_lock); - -- /* phase 1: disable fops (user space) operations for ALSA API */ -- mutex_lock(&snd_card_mutex); -- snd_cards[card->number] = NULL; -- clear_bit(card->number, snd_cards_lock); -- mutex_unlock(&snd_card_mutex); -- -- /* phase 2: replace file->f_op with special dummy operations */ -- -+ /* replace file->f_op with special dummy operations */ - spin_lock(&card->files_lock); - list_for_each_entry(mfile, &card->files_list, list) { - /* it's critical part, use endless loop */ -@@ -431,7 +424,7 @@ int snd_card_disconnect(struct snd_card *card) - } - spin_unlock(&card->files_lock); - -- /* phase 3: notify all connected devices about disconnection */ -+ /* notify all connected devices about disconnection */ - /* at this point, they cannot respond to any calls except release() */ - - #if IS_ENABLED(CONFIG_SND_MIXER_OSS) -@@ -447,6 +440,13 @@ int snd_card_disconnect(struct snd_card *card) - device_del(&card->card_dev); - card->registered = false; - } -+ -+ /* disable fops (user space) operations for ALSA API */ -+ mutex_lock(&snd_card_mutex); -+ snd_cards[card->number] = NULL; -+ clear_bit(card->number, snd_cards_lock); -+ mutex_unlock(&snd_card_mutex); -+ - #ifdef CONFIG_PM - wake_up(&card->power_sleep); - #endif diff --git a/patch/kernel/odroidn2-default/patch-4.9.171-172.patch b/patch/kernel/odroidn2-default/patch-4.9.171-172.patch deleted file mode 100644 index 709313d71d..0000000000 --- a/patch/kernel/odroidn2-default/patch-4.9.171-172.patch +++ /dev/null @@ -1,3013 +0,0 @@ -diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt -index c708a50b060e..a1472b48ee22 100644 ---- a/Documentation/kernel-parameters.txt -+++ b/Documentation/kernel-parameters.txt -@@ -2758,6 +2758,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. - - nohugeiomap [KNL,x86] Disable kernel huge I/O mappings. - -+ nospectre_v1 [PPC] Disable mitigations for Spectre Variant 1 (bounds -+ check bypass). With this option data leaks are possible -+ in the system. -+ - nosmt [KNL,S390] Disable symmetric multithreading (SMT). - Equivalent to smt=1. - -@@ -2765,7 +2769,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. - nosmt=force: Force disable SMT, cannot be undone - via the sysfs control file. - -- nospectre_v2 [X86] Disable all mitigations for the Spectre variant 2 -+ nospectre_v2 [X86,PPC_FSL_BOOK3E] Disable all mitigations for the Spectre variant 2 - (indirect branch prediction) vulnerability. System may - allow data leaks with this option, which is equivalent - to spectre_v2=off. -diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt -index dbdc4130e149..0335285f3918 100644 ---- a/Documentation/networking/ip-sysctl.txt -+++ b/Documentation/networking/ip-sysctl.txt -@@ -405,6 +405,7 @@ tcp_min_rtt_wlen - INTEGER - minimum RTT when it is moved to a longer path (e.g., due to traffic - engineering). A longer window makes the filter more resistant to RTT - inflations such as transient congestion. The unit is seconds. -+ Possible values: 0 - 86400 (1 day) - Default: 300 - - tcp_moderate_rcvbuf - BOOLEAN -diff --git a/Makefile b/Makefile -index dbdef749e1c8..75cba5fbdb46 100644 ---- a/Makefile -+++ b/Makefile -@@ -1,6 +1,6 @@ - VERSION = 4 - PATCHLEVEL = 9 --SUBLEVEL = 171 -+SUBLEVEL = 172 - EXTRAVERSION = - NAME = Roaring Lionus - -diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S -index 2d7f2bb0d66a..a67ed746b0e3 100644 ---- a/arch/arm/boot/compressed/head.S -+++ b/arch/arm/boot/compressed/head.S -@@ -1383,7 +1383,21 @@ ENTRY(efi_stub_entry) - - @ Preserve return value of efi_entry() in r4 - mov r4, r0 -- bl cache_clean_flush -+ -+ @ our cache maintenance code relies on CP15 barrier instructions -+ @ but since we arrived here with the MMU and caches configured -+ @ by UEFI, we must check that the CP15BEN bit is set in SCTLR. -+ @ Note that this bit is RAO/WI on v6 and earlier, so the ISB in -+ @ the enable path will be executed on v7+ only. -+ mrc p15, 0, r1, c1, c0, 0 @ read SCTLR -+ tst r1, #(1 << 5) @ CP15BEN bit set? -+ bne 0f -+ orr r1, r1, #(1 << 5) @ CP15 barrier instructions -+ mcr p15, 0, r1, c1, c0, 0 @ write SCTLR -+ ARM( .inst 0xf57ff06f @ v7+ isb ) -+ THUMB( isb ) -+ -+0: bl cache_clean_flush - bl cache_off - - @ Set parameters for booting zImage according to boot protocol -diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S -index 7913a5cf6806..b9c788790c0f 100644 ---- a/arch/mips/kernel/scall64-o32.S -+++ b/arch/mips/kernel/scall64-o32.S -@@ -125,7 +125,7 @@ trace_a_syscall: - subu t1, v0, __NR_O32_Linux - move a1, v0 - bnez t1, 1f /* __NR_syscall at offset 0 */ -- lw a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ -+ ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ - .set pop - - 1: jal syscall_trace_enter -diff --git a/drivers/block/loop.c b/drivers/block/loop.c -index 28ce17405aab..9f840d9fdfcb 100644 ---- a/drivers/block/loop.c -+++ b/drivers/block/loop.c -@@ -82,7 +82,6 @@ - - static DEFINE_IDR(loop_index_idr); - static DEFINE_MUTEX(loop_index_mutex); --static DEFINE_MUTEX(loop_ctl_mutex); - - static int max_part; - static int part_shift; -@@ -1034,7 +1033,7 @@ static int loop_clr_fd(struct loop_device *lo) - */ - if (atomic_read(&lo->lo_refcnt) > 1) { - lo->lo_flags |= LO_FLAGS_AUTOCLEAR; -- mutex_unlock(&loop_ctl_mutex); -+ mutex_unlock(&lo->lo_ctl_mutex); - return 0; - } - -@@ -1083,12 +1082,12 @@ static int loop_clr_fd(struct loop_device *lo) - if (!part_shift) - lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; - loop_unprepare_queue(lo); -- mutex_unlock(&loop_ctl_mutex); -+ mutex_unlock(&lo->lo_ctl_mutex); - /* -- * Need not hold loop_ctl_mutex to fput backing file. -- * Calling fput holding loop_ctl_mutex triggers a circular -+ * Need not hold lo_ctl_mutex to fput backing file. -+ * Calling fput holding lo_ctl_mutex triggers a circular - * lock dependency possibility warning as fput can take -- * bd_mutex which is usually taken before loop_ctl_mutex. -+ * bd_mutex which is usually taken before lo_ctl_mutex. - */ - fput(filp); - return 0; -@@ -1351,7 +1350,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, - struct loop_device *lo = bdev->bd_disk->private_data; - int err; - -- mutex_lock_nested(&loop_ctl_mutex, 1); -+ mutex_lock_nested(&lo->lo_ctl_mutex, 1); - switch (cmd) { - case LOOP_SET_FD: - err = loop_set_fd(lo, mode, bdev, arg); -@@ -1360,7 +1359,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, - err = loop_change_fd(lo, bdev, arg); - break; - case LOOP_CLR_FD: -- /* loop_clr_fd would have unlocked loop_ctl_mutex on success */ -+ /* loop_clr_fd would have unlocked lo_ctl_mutex on success */ - err = loop_clr_fd(lo); - if (!err) - goto out_unlocked; -@@ -1396,7 +1395,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, - default: - err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; - } -- mutex_unlock(&loop_ctl_mutex); -+ mutex_unlock(&lo->lo_ctl_mutex); - - out_unlocked: - return err; -@@ -1529,16 +1528,16 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, - - switch(cmd) { - case LOOP_SET_STATUS: -- mutex_lock(&loop_ctl_mutex); -+ mutex_lock(&lo->lo_ctl_mutex); - err = loop_set_status_compat( - lo, (const struct compat_loop_info __user *) arg); -- mutex_unlock(&loop_ctl_mutex); -+ mutex_unlock(&lo->lo_ctl_mutex); - break; - case LOOP_GET_STATUS: -- mutex_lock(&loop_ctl_mutex); -+ mutex_lock(&lo->lo_ctl_mutex); - err = loop_get_status_compat( - lo, (struct compat_loop_info __user *) arg); -- mutex_unlock(&loop_ctl_mutex); -+ mutex_unlock(&lo->lo_ctl_mutex); - break; - case LOOP_SET_CAPACITY: - case LOOP_CLR_FD: -@@ -1582,7 +1581,7 @@ static void __lo_release(struct loop_device *lo) - if (atomic_dec_return(&lo->lo_refcnt)) - return; - -- mutex_lock(&loop_ctl_mutex); -+ mutex_lock(&lo->lo_ctl_mutex); - if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { - /* - * In autoclear mode, stop the loop thread -@@ -1599,7 +1598,7 @@ static void __lo_release(struct loop_device *lo) - loop_flush(lo); - } - -- mutex_unlock(&loop_ctl_mutex); -+ mutex_unlock(&lo->lo_ctl_mutex); - } - - static void lo_release(struct gendisk *disk, fmode_t mode) -@@ -1645,10 +1644,10 @@ static int unregister_transfer_cb(int id, void *ptr, void *data) - struct loop_device *lo = ptr; - struct loop_func_table *xfer = data; - -- mutex_lock(&loop_ctl_mutex); -+ mutex_lock(&lo->lo_ctl_mutex); - if (lo->lo_encryption == xfer) - loop_release_xfer(lo); -- mutex_unlock(&loop_ctl_mutex); -+ mutex_unlock(&lo->lo_ctl_mutex); - return 0; - } - -@@ -1814,6 +1813,7 @@ static int loop_add(struct loop_device **l, int i) - if (!part_shift) - disk->flags |= GENHD_FL_NO_PART_SCAN; - disk->flags |= GENHD_FL_EXT_DEVT; -+ mutex_init(&lo->lo_ctl_mutex); - atomic_set(&lo->lo_refcnt, 0); - lo->lo_number = i; - spin_lock_init(&lo->lo_lock); -@@ -1926,19 +1926,19 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd, - ret = loop_lookup(&lo, parm); - if (ret < 0) - break; -- mutex_lock(&loop_ctl_mutex); -+ mutex_lock(&lo->lo_ctl_mutex); - if (lo->lo_state != Lo_unbound) { - ret = -EBUSY; -- mutex_unlock(&loop_ctl_mutex); -+ mutex_unlock(&lo->lo_ctl_mutex); - break; - } - if (atomic_read(&lo->lo_refcnt) > 0) { - ret = -EBUSY; -- mutex_unlock(&loop_ctl_mutex); -+ mutex_unlock(&lo->lo_ctl_mutex); - break; - } - lo->lo_disk->private_data = NULL; -- mutex_unlock(&loop_ctl_mutex); -+ mutex_unlock(&lo->lo_ctl_mutex); - idr_remove(&loop_index_idr, lo->lo_number); - loop_remove(lo); - break; -diff --git a/drivers/block/loop.h b/drivers/block/loop.h -index a923e74495ce..60f0fd2c0c65 100644 ---- a/drivers/block/loop.h -+++ b/drivers/block/loop.h -@@ -55,6 +55,7 @@ struct loop_device { - - spinlock_t lo_lock; - int lo_state; -+ struct mutex lo_ctl_mutex; - struct kthread_worker worker; - struct task_struct *worker_task; - bool use_dio; -diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c -index d032032337e7..f37a6ef4f544 100644 ---- a/drivers/dma/sh/rcar-dmac.c -+++ b/drivers/dma/sh/rcar-dmac.c -@@ -1311,6 +1311,7 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan, - enum dma_status status; - unsigned long flags; - unsigned int residue; -+ bool cyclic; - - status = dma_cookie_status(chan, cookie, txstate); - if (status == DMA_COMPLETE || !txstate) -@@ -1318,10 +1319,11 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan, - - spin_lock_irqsave(&rchan->lock, flags); - residue = rcar_dmac_chan_get_residue(rchan, cookie); -+ cyclic = rchan->desc.running ? rchan->desc.running->cyclic : false; - spin_unlock_irqrestore(&rchan->lock, flags); - - /* if there's no residue, the cookie is complete */ -- if (!residue) -+ if (!residue && !cyclic) - return DMA_COMPLETE; - - dma_set_residue(txstate, residue); -diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c -index c7e6c9839c9a..51d34e7275ab 100644 ---- a/drivers/gpu/drm/vc4/vc4_crtc.c -+++ b/drivers/gpu/drm/vc4/vc4_crtc.c -@@ -846,7 +846,7 @@ static void - vc4_crtc_reset(struct drm_crtc *crtc) - { - if (crtc->state) -- __drm_atomic_helper_crtc_destroy_state(crtc->state); -+ vc4_crtc_destroy_state(crtc, crtc->state); - - crtc->state = kzalloc(sizeof(struct vc4_crtc_state), GFP_KERNEL); - if (crtc->state) -diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c -index b0502e2782c1..98a4cb5d4993 100644 ---- a/drivers/hwtracing/intel_th/gth.c -+++ b/drivers/hwtracing/intel_th/gth.c -@@ -605,7 +605,7 @@ static void intel_th_gth_unassign(struct intel_th_device *thdev, - othdev->output.port = -1; - othdev->output.active = false; - gth->output[port].output = NULL; -- for (master = 0; master < TH_CONFIGURABLE_MASTERS; master++) -+ for (master = 0; master <= TH_CONFIGURABLE_MASTERS; master++) - if (gth->master[master] == port) - gth->master[master] = -1; - spin_unlock(>h->gth_lock); -diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c -index 46b64970058e..49d55a0322f6 100644 ---- a/drivers/infiniband/sw/rdmavt/mr.c -+++ b/drivers/infiniband/sw/rdmavt/mr.c -@@ -497,11 +497,6 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr) - if (unlikely(mapped_segs == mr->mr.max_segs)) - return -ENOMEM; - -- if (mr->mr.length == 0) { -- mr->mr.user_base = addr; -- mr->mr.iova = addr; -- } -- - m = mapped_segs / RVT_SEGSZ; - n = mapped_segs % RVT_SEGSZ; - mr->mr.map[m]->segs[n].vaddr = (void *)addr; -@@ -518,17 +513,24 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr) - * @sg_nents: number of entries in sg - * @sg_offset: offset in bytes into sg - * -+ * Overwrite rvt_mr length with mr length calculated by ib_sg_to_pages. -+ * - * Return: number of sg elements mapped to the memory region - */ - int rvt_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, - int sg_nents, unsigned int *sg_offset) - { - struct rvt_mr *mr = to_imr(ibmr); -+ int ret; - - mr->mr.length = 0; - mr->mr.page_shift = PAGE_SHIFT; -- return ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, -- rvt_set_page); -+ ret = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, rvt_set_page); -+ mr->mr.user_base = ibmr->iova; -+ mr->mr.iova = ibmr->iova; -+ mr->mr.offset = ibmr->iova - (u64)mr->mr.map[0]->segs[0].vaddr; -+ mr->mr.length = (size_t)ibmr->length; -+ return ret; - } - - /** -@@ -559,6 +561,7 @@ int rvt_fast_reg_mr(struct rvt_qp *qp, struct ib_mr *ibmr, u32 key, - ibmr->rkey = key; - mr->mr.lkey = key; - mr->mr.access_flags = access; -+ mr->mr.iova = ibmr->iova; - atomic_set(&mr->mr.lkey_invalid, 0); - - return 0; -diff --git a/drivers/input/rmi4/rmi_f11.c b/drivers/input/rmi4/rmi_f11.c -index f798f427a46f..275f957604f7 100644 ---- a/drivers/input/rmi4/rmi_f11.c -+++ b/drivers/input/rmi4/rmi_f11.c -@@ -1198,7 +1198,7 @@ static int rmi_f11_initialize(struct rmi_function *fn) - ctrl->ctrl0_11[11] = ctrl->ctrl0_11[11] & ~BIT(0); - - rc = f11_write_control_regs(fn, &f11->sens_query, -- &f11->dev_controls, fn->fd.query_base_addr); -+ &f11->dev_controls, fn->fd.control_base_addr); - if (rc) - dev_warn(&fn->dev, "Failed to write control registers\n"); - -diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c -index 2aae6f88dca0..a52663745051 100644 ---- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c -+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c -@@ -58,6 +58,8 @@ static int __init fm10k_init_module(void) - /* create driver workqueue */ - fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, - fm10k_driver_name); -+ if (!fm10k_workqueue) -+ return -ENOMEM; - - fm10k_dbg_init(); - -diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c -index d5e8ac86c195..54872f8f2f7d 100644 ---- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c -+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c -@@ -1365,7 +1365,7 @@ static int mlx5e_get_module_info(struct net_device *netdev, - break; - case MLX5_MODULE_ID_SFP: - modinfo->type = ETH_MODULE_SFF_8472; -- modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; -+ modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH; - break; - default: - netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n", -diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c -index 43d7c8378fb4..0bad09d06206 100644 ---- a/drivers/net/ethernet/mellanox/mlx5/core/port.c -+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c -@@ -368,10 +368,6 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, - size -= offset + size - MLX5_EEPROM_PAGE_LENGTH; - - i2c_addr = MLX5_I2C_ADDR_LOW; -- if (offset >= MLX5_EEPROM_PAGE_LENGTH) { -- i2c_addr = MLX5_I2C_ADDR_HIGH; -- offset -= MLX5_EEPROM_PAGE_LENGTH; -- } - - MLX5_SET(mcia_reg, in, l, 0); - MLX5_SET(mcia_reg, in, module, module_num); -diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c -index cc847e0cac2d..e3ed70a24029 100644 ---- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c -+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c -@@ -2059,11 +2059,11 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev, - if (err) - return err; - -+ mlxsw_sp_port->link.autoneg = autoneg; -+ - if (!netif_running(dev)) - return 0; - -- mlxsw_sp_port->link.autoneg = autoneg; -- - mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); - mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true); - -diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c -index b46b56ad7517..2c04a0739fd6 100644 ---- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c -+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c -@@ -1796,8 +1796,6 @@ static int stmmac_open(struct net_device *dev) - struct stmmac_priv *priv = netdev_priv(dev); - int ret; - -- stmmac_check_ether_addr(priv); -- - if (priv->hw->pcs != STMMAC_PCS_RGMII && - priv->hw->pcs != STMMAC_PCS_TBI && - priv->hw->pcs != STMMAC_PCS_RTBI) { -@@ -3355,6 +3353,8 @@ int stmmac_dvr_probe(struct device *device, - if (ret) - goto error_hw_init; - -+ stmmac_check_ether_addr(priv); -+ - ndev->netdev_ops = &stmmac_netdev_ops; - - ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | -diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c -index cfd81eb1b532..ddceed3c5a4a 100644 ---- a/drivers/net/slip/slhc.c -+++ b/drivers/net/slip/slhc.c -@@ -153,7 +153,7 @@ out_fail: - void - slhc_free(struct slcompress *comp) - { -- if ( comp == NULLSLCOMPR ) -+ if ( IS_ERR_OR_NULL(comp) ) - return; - - if ( comp->tstate != NULLSLSTATE ) -diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c -index b8874faaa813..3eb6d48c3148 100644 ---- a/drivers/net/team/team.c -+++ b/drivers/net/team/team.c -@@ -1163,6 +1163,12 @@ static int team_port_add(struct team *team, struct net_device *port_dev) - return -EINVAL; - } - -+ if (netdev_has_upper_dev(dev, port_dev)) { -+ netdev_err(dev, "Device %s is already an upper device of the team interface\n", -+ portname); -+ return -EBUSY; -+ } -+ - if (port_dev->features & NETIF_F_VLAN_CHALLENGED && - vlan_uses_dev(dev)) { - netdev_err(dev, "Device %s is VLAN challenged and team device has VLAN set up\n", -diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c -index e9d6cf146fcc..c17b254e4f64 100644 ---- a/drivers/usb/core/driver.c -+++ b/drivers/usb/core/driver.c -@@ -1888,14 +1888,11 @@ int usb_runtime_idle(struct device *dev) - return -EBUSY; - } - --int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable) -+static int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable) - { - struct usb_hcd *hcd = bus_to_hcd(udev->bus); - int ret = -EPERM; - -- if (enable && !udev->usb2_hw_lpm_allowed) -- return 0; -- - if (hcd->driver->set_usb2_hw_lpm) { - ret = hcd->driver->set_usb2_hw_lpm(hcd, udev, enable); - if (!ret) -@@ -1905,6 +1902,24 @@ int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable) - return ret; - } - -+int usb_enable_usb2_hardware_lpm(struct usb_device *udev) -+{ -+ if (!udev->usb2_hw_lpm_capable || -+ !udev->usb2_hw_lpm_allowed || -+ udev->usb2_hw_lpm_enabled) -+ return 0; -+ -+ return usb_set_usb2_hardware_lpm(udev, 1); -+} -+ -+int usb_disable_usb2_hardware_lpm(struct usb_device *udev) -+{ -+ if (!udev->usb2_hw_lpm_enabled) -+ return 0; -+ -+ return usb_set_usb2_hardware_lpm(udev, 0); -+} -+ - #endif /* CONFIG_PM */ - - struct bus_type usb_bus_type = { -diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c -index 7b6919086539..8fddb94f1874 100644 ---- a/drivers/usb/core/hub.c -+++ b/drivers/usb/core/hub.c -@@ -3168,8 +3168,7 @@ int usb_port_suspend(struct usb_device *udev, pm_message_t msg) - } - - /* disable USB2 hardware LPM */ -- if (udev->usb2_hw_lpm_enabled == 1) -- usb_set_usb2_hardware_lpm(udev, 0); -+ usb_disable_usb2_hardware_lpm(udev); - - if (usb_disable_ltm(udev)) { - dev_err(&udev->dev, "Failed to disable LTM before suspend\n."); -@@ -3215,8 +3214,7 @@ int usb_port_suspend(struct usb_device *udev, pm_message_t msg) - usb_enable_ltm(udev); - err_ltm: - /* Try to enable USB2 hardware LPM again */ -- if (udev->usb2_hw_lpm_capable == 1) -- usb_set_usb2_hardware_lpm(udev, 1); -+ usb_enable_usb2_hardware_lpm(udev); - - if (udev->do_remote_wakeup) - (void) usb_disable_remote_wakeup(udev); -@@ -3499,8 +3497,7 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg) - hub_port_logical_disconnect(hub, port1); - } else { - /* Try to enable USB2 hardware LPM */ -- if (udev->usb2_hw_lpm_capable == 1) -- usb_set_usb2_hardware_lpm(udev, 1); -+ usb_enable_usb2_hardware_lpm(udev); - - /* Try to enable USB3 LTM and LPM */ - usb_enable_ltm(udev); -@@ -4337,7 +4334,7 @@ static void hub_set_initial_usb2_lpm_policy(struct usb_device *udev) - if ((udev->bos->ext_cap->bmAttributes & cpu_to_le32(USB_BESL_SUPPORT)) || - connect_type == USB_PORT_CONNECT_TYPE_HARD_WIRED) { - udev->usb2_hw_lpm_allowed = 1; -- usb_set_usb2_hardware_lpm(udev, 1); -+ usb_enable_usb2_hardware_lpm(udev); - } - } - -@@ -5481,8 +5478,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev) - /* Disable USB2 hardware LPM. - * It will be re-enabled by the enumeration process. - */ -- if (udev->usb2_hw_lpm_enabled == 1) -- usb_set_usb2_hardware_lpm(udev, 0); -+ usb_disable_usb2_hardware_lpm(udev); - - /* Disable LPM and LTM while we reset the device and reinstall the alt - * settings. Device-initiated LPM settings, and system exit latency -@@ -5592,7 +5588,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev) - - done: - /* Now that the alt settings are re-installed, enable LTM and LPM. */ -- usb_set_usb2_hardware_lpm(udev, 1); -+ usb_enable_usb2_hardware_lpm(udev); - usb_unlocked_enable_lpm(udev); - usb_enable_ltm(udev); - usb_release_bos_descriptor(udev); -diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c -index c0c5d5b3ec40..0e6ab0a17c08 100644 ---- a/drivers/usb/core/message.c -+++ b/drivers/usb/core/message.c -@@ -1181,8 +1181,7 @@ void usb_disable_device(struct usb_device *dev, int skip_ep0) - dev->actconfig->interface[i] = NULL; - } - -- if (dev->usb2_hw_lpm_enabled == 1) -- usb_set_usb2_hardware_lpm(dev, 0); -+ usb_disable_usb2_hardware_lpm(dev); - usb_unlocked_disable_lpm(dev); - usb_disable_ltm(dev); - -diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c -index c953a0f1c695..1a232b4ffe71 100644 ---- a/drivers/usb/core/sysfs.c -+++ b/drivers/usb/core/sysfs.c -@@ -494,7 +494,10 @@ static ssize_t usb2_hardware_lpm_store(struct device *dev, - - if (!ret) { - udev->usb2_hw_lpm_allowed = value; -- ret = usb_set_usb2_hardware_lpm(udev, value); -+ if (value) -+ ret = usb_enable_usb2_hardware_lpm(udev); -+ else -+ ret = usb_disable_usb2_hardware_lpm(udev); - } - - usb_unlock_device(udev); -diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h -index 53318126ed91..6b2f11544283 100644 ---- a/drivers/usb/core/usb.h -+++ b/drivers/usb/core/usb.h -@@ -84,7 +84,8 @@ extern int usb_remote_wakeup(struct usb_device *dev); - extern int usb_runtime_suspend(struct device *dev); - extern int usb_runtime_resume(struct device *dev); - extern int usb_runtime_idle(struct device *dev); --extern int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable); -+extern int usb_enable_usb2_hardware_lpm(struct usb_device *udev); -+extern int usb_disable_usb2_hardware_lpm(struct usb_device *udev); - - #else - -@@ -104,7 +105,12 @@ static inline int usb_autoresume_device(struct usb_device *udev) - return 0; - } - --static inline int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable) -+static inline int usb_enable_usb2_hardware_lpm(struct usb_device *udev) -+{ -+ return 0; -+} -+ -+static inline int usb_disable_usb2_hardware_lpm(struct usb_device *udev) - { - return 0; - } -diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c -index cec25691cbae..2ffc7fe8da52 100644 ---- a/fs/ceph/dir.c -+++ b/fs/ceph/dir.c -@@ -1471,6 +1471,7 @@ void ceph_dentry_lru_del(struct dentry *dn) - unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) - { - struct ceph_inode_info *dci = ceph_inode(dir); -+ unsigned hash; - - switch (dci->i_dir_layout.dl_dir_hash) { - case 0: /* for backward compat */ -@@ -1478,8 +1479,11 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) - return dn->d_name.hash; - - default: -- return ceph_str_hash(dci->i_dir_layout.dl_dir_hash, -+ spin_lock(&dn->d_lock); -+ hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash, - dn->d_name.name, dn->d_name.len); -+ spin_unlock(&dn->d_lock); -+ return hash; - } - } - -diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c -index 6cbd0d805c9d..67cb9d078bfa 100644 ---- a/fs/ceph/mds_client.c -+++ b/fs/ceph/mds_client.c -@@ -1187,6 +1187,15 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, - list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove); - ci->i_prealloc_cap_flush = NULL; - } -+ -+ if (drop && -+ ci->i_wrbuffer_ref_head == 0 && -+ ci->i_wr_ref == 0 && -+ ci->i_dirty_caps == 0 && -+ ci->i_flushing_caps == 0) { -+ ceph_put_snap_context(ci->i_head_snapc); -+ ci->i_head_snapc = NULL; -+ } - } - spin_unlock(&ci->i_ceph_lock); - while (!list_empty(&to_remove)) { -diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c -index 411e9df0d40e..3a76ae001360 100644 ---- a/fs/ceph/snap.c -+++ b/fs/ceph/snap.c -@@ -563,7 +563,12 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci) - old_snapc = NULL; - - update_snapc: -- if (ci->i_head_snapc) { -+ if (ci->i_wrbuffer_ref_head == 0 && -+ ci->i_wr_ref == 0 && -+ ci->i_dirty_caps == 0 && -+ ci->i_flushing_caps == 0) { -+ ci->i_head_snapc = NULL; -+ } else { - ci->i_head_snapc = ceph_get_snap_context(new_snapc); - dout(" new snapc is %p\n", new_snapc); - } -diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c -index a8a2fc9ae056..786f67bee43a 100644 ---- a/fs/cifs/inode.c -+++ b/fs/cifs/inode.c -@@ -1722,6 +1722,10 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, - if (rc == 0 || rc != -EBUSY) - goto do_rename_exit; - -+ /* Don't fall back to using SMB on SMB 2+ mount */ -+ if (server->vals->protocol_id != 0) -+ goto do_rename_exit; -+ - /* open-file renames don't work across directories */ - if (to_dentry->d_parent != from_dentry->d_parent) - goto do_rename_exit; -diff --git a/fs/nfs/super.c b/fs/nfs/super.c -index 659ad12e33ba..42c31587a936 100644 ---- a/fs/nfs/super.c -+++ b/fs/nfs/super.c -@@ -2047,7 +2047,8 @@ static int nfs23_validate_mount_data(void *options, - memcpy(sap, &data->addr, sizeof(data->addr)); - args->nfs_server.addrlen = sizeof(data->addr); - args->nfs_server.port = ntohs(data->addr.sin_port); -- if (!nfs_verify_server_address(sap)) -+ if (sap->sa_family != AF_INET || -+ !nfs_verify_server_address(sap)) - goto out_no_address; - - if (!(data->flags & NFS_MOUNT_TCP)) -diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c -index 3069cd46ea66..8d842282111b 100644 ---- a/fs/nfsd/nfs4callback.c -+++ b/fs/nfsd/nfs4callback.c -@@ -934,8 +934,9 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) - cb->cb_seq_status = 1; - cb->cb_status = 0; - if (minorversion) { -- if (!nfsd41_cb_get_slot(clp, task)) -+ if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task)) - return; -+ cb->cb_holds_slot = true; - } - rpc_call_start(task); - } -@@ -962,6 +963,9 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback - return true; - } - -+ if (!cb->cb_holds_slot) -+ goto need_restart; -+ - switch (cb->cb_seq_status) { - case 0: - /* -@@ -999,6 +1003,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback - cb->cb_seq_status); - } - -+ cb->cb_holds_slot = false; - clear_bit(0, &clp->cl_cb_slot_busy); - rpc_wake_up_next(&clp->cl_cb_waitq); - dprintk("%s: freed slot, new seqid=%d\n", __func__, -@@ -1206,6 +1211,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, - cb->cb_seq_status = 1; - cb->cb_status = 0; - cb->cb_need_restart = false; -+ cb->cb_holds_slot = false; - } - - void nfsd4_run_cb(struct nfsd4_callback *cb) -diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h -index 86aa92d200e1..133d8bf62a5c 100644 ---- a/fs/nfsd/state.h -+++ b/fs/nfsd/state.h -@@ -69,6 +69,7 @@ struct nfsd4_callback { - int cb_seq_status; - int cb_status; - bool cb_need_restart; -+ bool cb_holds_slot; - }; - - struct nfsd4_callback_ops { -diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c -index 6f30cf8ef7a1..5b32c054df71 100644 ---- a/fs/proc/proc_sysctl.c -+++ b/fs/proc/proc_sysctl.c -@@ -1604,9 +1604,11 @@ static void drop_sysctl_table(struct ctl_table_header *header) - if (--header->nreg) - return; - -- if (parent) -+ if (parent) { - put_links(header); -- start_unregistering(header); -+ start_unregistering(header); -+ } -+ - if (!--header->count) - kfree_rcu(header, rcu); - -diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h -index a3812e9c8fee..c2c724abde57 100644 ---- a/include/net/inet_frag.h -+++ b/include/net/inet_frag.h -@@ -76,8 +76,8 @@ struct inet_frag_queue { - struct timer_list timer; - spinlock_t lock; - atomic_t refcnt; -- struct sk_buff *fragments; /* Used in IPv6. */ -- struct rb_root rb_fragments; /* Used in IPv4. */ -+ struct sk_buff *fragments; /* used in 6lopwpan IPv6. */ -+ struct rb_root rb_fragments; /* Used in IPv4/IPv6. */ - struct sk_buff *fragments_tail; - struct sk_buff *last_run_head; - ktime_t stamp; -@@ -152,4 +152,16 @@ static inline void add_frag_mem_limit(struct netns_frags *nf, long val) - - extern const u8 ip_frag_ecn_table[16]; - -+/* Return values of inet_frag_queue_insert() */ -+#define IPFRAG_OK 0 -+#define IPFRAG_DUP 1 -+#define IPFRAG_OVERLAP 2 -+int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, -+ int offset, int end); -+void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, -+ struct sk_buff *parent); -+void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, -+ void *reasm_data); -+struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q); -+ - #endif -diff --git a/include/net/ipv6.h b/include/net/ipv6.h -index 7cb100d25bb5..168009eef5e4 100644 ---- a/include/net/ipv6.h -+++ b/include/net/ipv6.h -@@ -511,35 +511,6 @@ static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, - } - #endif - --struct inet_frag_queue; -- --enum ip6_defrag_users { -- IP6_DEFRAG_LOCAL_DELIVER, -- IP6_DEFRAG_CONNTRACK_IN, -- __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX, -- IP6_DEFRAG_CONNTRACK_OUT, -- __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX, -- IP6_DEFRAG_CONNTRACK_BRIDGE_IN, -- __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, --}; -- --void ip6_frag_init(struct inet_frag_queue *q, const void *a); --extern const struct rhashtable_params ip6_rhash_params; -- --/* -- * Equivalent of ipv4 struct ip -- */ --struct frag_queue { -- struct inet_frag_queue q; -- -- int iif; -- unsigned int csum; -- __u16 nhoffset; -- u8 ecn; --}; -- --void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq); -- - static inline bool ipv6_addr_any(const struct in6_addr *a) - { - #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 -diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h -new file mode 100644 -index 000000000000..28aa9b30aece ---- /dev/null -+++ b/include/net/ipv6_frag.h -@@ -0,0 +1,111 @@ -+/* SPDX-License-Identifier: GPL-2.0 */ -+#ifndef _IPV6_FRAG_H -+#define _IPV6_FRAG_H -+#include -+#include -+#include -+#include -+ -+enum ip6_defrag_users { -+ IP6_DEFRAG_LOCAL_DELIVER, -+ IP6_DEFRAG_CONNTRACK_IN, -+ __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX, -+ IP6_DEFRAG_CONNTRACK_OUT, -+ __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX, -+ IP6_DEFRAG_CONNTRACK_BRIDGE_IN, -+ __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, -+}; -+ -+/* -+ * Equivalent of ipv4 struct ip -+ */ -+struct frag_queue { -+ struct inet_frag_queue q; -+ -+ int iif; -+ __u16 nhoffset; -+ u8 ecn; -+}; -+ -+#if IS_ENABLED(CONFIG_IPV6) -+static inline void ip6frag_init(struct inet_frag_queue *q, const void *a) -+{ -+ struct frag_queue *fq = container_of(q, struct frag_queue, q); -+ const struct frag_v6_compare_key *key = a; -+ -+ q->key.v6 = *key; -+ fq->ecn = 0; -+} -+ -+static inline u32 ip6frag_key_hashfn(const void *data, u32 len, u32 seed) -+{ -+ return jhash2(data, -+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); -+} -+ -+static inline u32 ip6frag_obj_hashfn(const void *data, u32 len, u32 seed) -+{ -+ const struct inet_frag_queue *fq = data; -+ -+ return jhash2((const u32 *)&fq->key.v6, -+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); -+} -+ -+static inline int -+ip6frag_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) -+{ -+ const struct frag_v6_compare_key *key = arg->key; -+ const struct inet_frag_queue *fq = ptr; -+ -+ return !!memcmp(&fq->key, key, sizeof(*key)); -+} -+ -+static inline void -+ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) -+{ -+ struct net_device *dev = NULL; -+ struct sk_buff *head; -+ -+ rcu_read_lock(); -+ spin_lock(&fq->q.lock); -+ -+ if (fq->q.flags & INET_FRAG_COMPLETE) -+ goto out; -+ -+ inet_frag_kill(&fq->q); -+ -+ dev = dev_get_by_index_rcu(net, fq->iif); -+ if (!dev) -+ goto out; -+ -+ __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); -+ __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); -+ -+ /* Don't send error if the first segment did not arrive. */ -+ if (!(fq->q.flags & INET_FRAG_FIRST_IN)) -+ goto out; -+ -+ /* sk_buff::dev and sk_buff::rbnode are unionized. So we -+ * pull the head out of the tree in order to be able to -+ * deal with head->dev. -+ */ -+ head = inet_frag_pull_head(&fq->q); -+ if (!head) -+ goto out; -+ -+ head->dev = dev; -+ skb_get(head); -+ spin_unlock(&fq->q.lock); -+ -+ icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); -+ kfree_skb(head); -+ goto out_rcu_unlock; -+ -+out: -+ spin_unlock(&fq->q.lock); -+out_rcu_unlock: -+ rcu_read_unlock(); -+ inet_frag_put(&fq->q); -+} -+#endif -+#endif -diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c -index 4b1e0669740c..f0c9b6925687 100644 ---- a/kernel/sched/fair.c -+++ b/kernel/sched/fair.c -@@ -1925,6 +1925,10 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) - if (p->last_task_numa_placement) { - delta = runtime - p->last_sum_exec_runtime; - *period = now - p->last_task_numa_placement; -+ -+ /* Avoid time going backwards, prevent potential divide error: */ -+ if (unlikely((s64)*period < 0)) -+ *period = 0; - } else { - delta = p->se.avg.load_sum / p->se.load.weight; - *period = LOAD_AVG_MAX; -diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c -index 5473dcaaca8d..2cfe11e1190b 100644 ---- a/kernel/trace/ring_buffer.c -+++ b/kernel/trace/ring_buffer.c -@@ -701,7 +701,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu) - - preempt_disable_notrace(); - time = rb_time_stamp(buffer); -- preempt_enable_no_resched_notrace(); -+ preempt_enable_notrace(); - - return time; - } -diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c -index d4773939c054..a2d8bd68c16e 100644 ---- a/kernel/trace/trace.c -+++ b/kernel/trace/trace.c -@@ -500,8 +500,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, - * not modified. - */ - pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL); -- if (!pid_list) -+ if (!pid_list) { -+ trace_parser_put(&parser); - return -ENOMEM; -+ } - - pid_list->pid_max = READ_ONCE(pid_max); - -@@ -511,6 +513,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, - - pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3); - if (!pid_list->pids) { -+ trace_parser_put(&parser); - kfree(pid_list); - return -ENOMEM; - } -diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c -index c7e5aaf2eeb8..142ccaae9c7b 100644 ---- a/net/bridge/netfilter/ebtables.c -+++ b/net/bridge/netfilter/ebtables.c -@@ -2056,7 +2056,8 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, - if (match_kern) - match_kern->match_size = ret; - -- if (WARN_ON(type == EBT_COMPAT_TARGET && size_left)) -+ /* rule should have no remaining data after target */ -+ if (type == EBT_COMPAT_TARGET && size_left) - return -EINVAL; - - match32 = (struct compat_ebt_entry_mwt *) buf; -diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c -index aab1e2dfdfca..c01df341b5f6 100644 ---- a/net/ieee802154/6lowpan/reassembly.c -+++ b/net/ieee802154/6lowpan/reassembly.c -@@ -25,7 +25,7 @@ - - #include - #include --#include -+#include - #include - - #include "6lowpan_i.h" -diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c -index 0fb49dedc9fb..2325cd3454a6 100644 ---- a/net/ipv4/inet_fragment.c -+++ b/net/ipv4/inet_fragment.c -@@ -24,6 +24,62 @@ - #include - #include - #include -+#include -+#include -+ -+/* Use skb->cb to track consecutive/adjacent fragments coming at -+ * the end of the queue. Nodes in the rb-tree queue will -+ * contain "runs" of one or more adjacent fragments. -+ * -+ * Invariants: -+ * - next_frag is NULL at the tail of a "run"; -+ * - the head of a "run" has the sum of all fragment lengths in frag_run_len. -+ */ -+struct ipfrag_skb_cb { -+ union { -+ struct inet_skb_parm h4; -+ struct inet6_skb_parm h6; -+ }; -+ struct sk_buff *next_frag; -+ int frag_run_len; -+}; -+ -+#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) -+ -+static void fragcb_clear(struct sk_buff *skb) -+{ -+ RB_CLEAR_NODE(&skb->rbnode); -+ FRAG_CB(skb)->next_frag = NULL; -+ FRAG_CB(skb)->frag_run_len = skb->len; -+} -+ -+/* Append skb to the last "run". */ -+static void fragrun_append_to_last(struct inet_frag_queue *q, -+ struct sk_buff *skb) -+{ -+ fragcb_clear(skb); -+ -+ FRAG_CB(q->last_run_head)->frag_run_len += skb->len; -+ FRAG_CB(q->fragments_tail)->next_frag = skb; -+ q->fragments_tail = skb; -+} -+ -+/* Create a new "run" with the skb. */ -+static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb) -+{ -+ BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); -+ fragcb_clear(skb); -+ -+ if (q->last_run_head) -+ rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, -+ &q->last_run_head->rbnode.rb_right); -+ else -+ rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); -+ rb_insert_color(&skb->rbnode, &q->rb_fragments); -+ -+ q->fragments_tail = skb; -+ q->last_run_head = skb; -+} - - /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements - * Value : 0xff if frame should be dropped. -@@ -122,6 +178,28 @@ static void inet_frag_destroy_rcu(struct rcu_head *head) - kmem_cache_free(f->frags_cachep, q); - } - -+unsigned int inet_frag_rbtree_purge(struct rb_root *root) -+{ -+ struct rb_node *p = rb_first(root); -+ unsigned int sum = 0; -+ -+ while (p) { -+ struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); -+ -+ p = rb_next(p); -+ rb_erase(&skb->rbnode, root); -+ while (skb) { -+ struct sk_buff *next = FRAG_CB(skb)->next_frag; -+ -+ sum += skb->truesize; -+ kfree_skb(skb); -+ skb = next; -+ } -+ } -+ return sum; -+} -+EXPORT_SYMBOL(inet_frag_rbtree_purge); -+ - void inet_frag_destroy(struct inet_frag_queue *q) - { - struct sk_buff *fp; -@@ -223,3 +301,218 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) - return fq; - } - EXPORT_SYMBOL(inet_frag_find); -+ -+int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, -+ int offset, int end) -+{ -+ struct sk_buff *last = q->fragments_tail; -+ -+ /* RFC5722, Section 4, amended by Errata ID : 3089 -+ * When reassembling an IPv6 datagram, if -+ * one or more its constituent fragments is determined to be an -+ * overlapping fragment, the entire datagram (and any constituent -+ * fragments) MUST be silently discarded. -+ * -+ * Duplicates, however, should be ignored (i.e. skb dropped, but the -+ * queue/fragments kept for later reassembly). -+ */ -+ if (!last) -+ fragrun_create(q, skb); /* First fragment. */ -+ else if (last->ip_defrag_offset + last->len < end) { -+ /* This is the common case: skb goes to the end. */ -+ /* Detect and discard overlaps. */ -+ if (offset < last->ip_defrag_offset + last->len) -+ return IPFRAG_OVERLAP; -+ if (offset == last->ip_defrag_offset + last->len) -+ fragrun_append_to_last(q, skb); -+ else -+ fragrun_create(q, skb); -+ } else { -+ /* Binary search. Note that skb can become the first fragment, -+ * but not the last (covered above). -+ */ -+ struct rb_node **rbn, *parent; -+ -+ rbn = &q->rb_fragments.rb_node; -+ do { -+ struct sk_buff *curr; -+ int curr_run_end; -+ -+ parent = *rbn; -+ curr = rb_to_skb(parent); -+ curr_run_end = curr->ip_defrag_offset + -+ FRAG_CB(curr)->frag_run_len; -+ if (end <= curr->ip_defrag_offset) -+ rbn = &parent->rb_left; -+ else if (offset >= curr_run_end) -+ rbn = &parent->rb_right; -+ else if (offset >= curr->ip_defrag_offset && -+ end <= curr_run_end) -+ return IPFRAG_DUP; -+ else -+ return IPFRAG_OVERLAP; -+ } while (*rbn); -+ /* Here we have parent properly set, and rbn pointing to -+ * one of its NULL left/right children. Insert skb. -+ */ -+ fragcb_clear(skb); -+ rb_link_node(&skb->rbnode, parent, rbn); -+ rb_insert_color(&skb->rbnode, &q->rb_fragments); -+ } -+ -+ skb->ip_defrag_offset = offset; -+ -+ return IPFRAG_OK; -+} -+EXPORT_SYMBOL(inet_frag_queue_insert); -+ -+void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, -+ struct sk_buff *parent) -+{ -+ struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); -+ struct sk_buff **nextp; -+ int delta; -+ -+ if (head != skb) { -+ fp = skb_clone(skb, GFP_ATOMIC); -+ if (!fp) -+ return NULL; -+ FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; -+ if (RB_EMPTY_NODE(&skb->rbnode)) -+ FRAG_CB(parent)->next_frag = fp; -+ else -+ rb_replace_node(&skb->rbnode, &fp->rbnode, -+ &q->rb_fragments); -+ if (q->fragments_tail == skb) -+ q->fragments_tail = fp; -+ skb_morph(skb, head); -+ FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; -+ rb_replace_node(&head->rbnode, &skb->rbnode, -+ &q->rb_fragments); -+ consume_skb(head); -+ head = skb; -+ } -+ WARN_ON(head->ip_defrag_offset != 0); -+ -+ delta = -head->truesize; -+ -+ /* Head of list must not be cloned. */ -+ if (skb_unclone(head, GFP_ATOMIC)) -+ return NULL; -+ -+ delta += head->truesize; -+ if (delta) -+ add_frag_mem_limit(q->net, delta); -+ -+ /* If the first fragment is fragmented itself, we split -+ * it to two chunks: the first with data and paged part -+ * and the second, holding only fragments. -+ */ -+ if (skb_has_frag_list(head)) { -+ struct sk_buff *clone; -+ int i, plen = 0; -+ -+ clone = alloc_skb(0, GFP_ATOMIC); -+ if (!clone) -+ return NULL; -+ skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; -+ skb_frag_list_init(head); -+ for (i = 0; i < skb_shinfo(head)->nr_frags; i++) -+ plen += skb_frag_size(&skb_shinfo(head)->frags[i]); -+ clone->data_len = head->data_len - plen; -+ clone->len = clone->data_len; -+ head->truesize += clone->truesize; -+ clone->csum = 0; -+ clone->ip_summed = head->ip_summed; -+ add_frag_mem_limit(q->net, clone->truesize); -+ skb_shinfo(head)->frag_list = clone; -+ nextp = &clone->next; -+ } else { -+ nextp = &skb_shinfo(head)->frag_list; -+ } -+ -+ return nextp; -+} -+EXPORT_SYMBOL(inet_frag_reasm_prepare); -+ -+void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, -+ void *reasm_data) -+{ -+ struct sk_buff **nextp = (struct sk_buff **)reasm_data; -+ struct rb_node *rbn; -+ struct sk_buff *fp; -+ -+ skb_push(head, head->data - skb_network_header(head)); -+ -+ /* Traverse the tree in order, to build frag_list. */ -+ fp = FRAG_CB(head)->next_frag; -+ rbn = rb_next(&head->rbnode); -+ rb_erase(&head->rbnode, &q->rb_fragments); -+ while (rbn || fp) { -+ /* fp points to the next sk_buff in the current run; -+ * rbn points to the next run. -+ */ -+ /* Go through the current run. */ -+ while (fp) { -+ *nextp = fp; -+ nextp = &fp->next; -+ fp->prev = NULL; -+ memset(&fp->rbnode, 0, sizeof(fp->rbnode)); -+ fp->sk = NULL; -+ head->data_len += fp->len; -+ head->len += fp->len; -+ if (head->ip_summed != fp->ip_summed) -+ head->ip_summed = CHECKSUM_NONE; -+ else if (head->ip_summed == CHECKSUM_COMPLETE) -+ head->csum = csum_add(head->csum, fp->csum); -+ head->truesize += fp->truesize; -+ fp = FRAG_CB(fp)->next_frag; -+ } -+ /* Move to the next run. */ -+ if (rbn) { -+ struct rb_node *rbnext = rb_next(rbn); -+ -+ fp = rb_to_skb(rbn); -+ rb_erase(rbn, &q->rb_fragments); -+ rbn = rbnext; -+ } -+ } -+ sub_frag_mem_limit(q->net, head->truesize); -+ -+ *nextp = NULL; -+ head->next = NULL; -+ head->prev = NULL; -+ head->tstamp = q->stamp; -+} -+EXPORT_SYMBOL(inet_frag_reasm_finish); -+ -+struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q) -+{ -+ struct sk_buff *head; -+ -+ if (q->fragments) { -+ head = q->fragments; -+ q->fragments = head->next; -+ } else { -+ struct sk_buff *skb; -+ -+ head = skb_rb_first(&q->rb_fragments); -+ if (!head) -+ return NULL; -+ skb = FRAG_CB(head)->next_frag; -+ if (skb) -+ rb_replace_node(&head->rbnode, &skb->rbnode, -+ &q->rb_fragments); -+ else -+ rb_erase(&head->rbnode, &q->rb_fragments); -+ memset(&head->rbnode, 0, sizeof(head->rbnode)); -+ barrier(); -+ } -+ if (head == q->fragments_tail) -+ q->fragments_tail = NULL; -+ -+ sub_frag_mem_limit(q->net, head->truesize); -+ -+ return head; -+} -+EXPORT_SYMBOL(inet_frag_pull_head); -diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c -index c7334d1e392a..6e9ba9dfb5b2 100644 ---- a/net/ipv4/ip_fragment.c -+++ b/net/ipv4/ip_fragment.c -@@ -56,57 +56,6 @@ - */ - static const char ip_frag_cache_name[] = "ip4-frags"; - --/* Use skb->cb to track consecutive/adjacent fragments coming at -- * the end of the queue. Nodes in the rb-tree queue will -- * contain "runs" of one or more adjacent fragments. -- * -- * Invariants: -- * - next_frag is NULL at the tail of a "run"; -- * - the head of a "run" has the sum of all fragment lengths in frag_run_len. -- */ --struct ipfrag_skb_cb { -- struct inet_skb_parm h; -- struct sk_buff *next_frag; -- int frag_run_len; --}; -- --#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) -- --static void ip4_frag_init_run(struct sk_buff *skb) --{ -- BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); -- -- FRAG_CB(skb)->next_frag = NULL; -- FRAG_CB(skb)->frag_run_len = skb->len; --} -- --/* Append skb to the last "run". */ --static void ip4_frag_append_to_last_run(struct inet_frag_queue *q, -- struct sk_buff *skb) --{ -- RB_CLEAR_NODE(&skb->rbnode); -- FRAG_CB(skb)->next_frag = NULL; -- -- FRAG_CB(q->last_run_head)->frag_run_len += skb->len; -- FRAG_CB(q->fragments_tail)->next_frag = skb; -- q->fragments_tail = skb; --} -- --/* Create a new "run" with the skb. */ --static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb) --{ -- if (q->last_run_head) -- rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, -- &q->last_run_head->rbnode.rb_right); -- else -- rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); -- rb_insert_color(&skb->rbnode, &q->rb_fragments); -- -- ip4_frag_init_run(skb); -- q->fragments_tail = skb; -- q->last_run_head = skb; --} -- - /* Describe an entry in the "incomplete datagrams" queue. */ - struct ipq { - struct inet_frag_queue q; -@@ -210,27 +159,9 @@ static void ip_expire(unsigned long arg) - * pull the head out of the tree in order to be able to - * deal with head->dev. - */ -- if (qp->q.fragments) { -- head = qp->q.fragments; -- qp->q.fragments = head->next; -- } else { -- head = skb_rb_first(&qp->q.rb_fragments); -- if (!head) -- goto out; -- if (FRAG_CB(head)->next_frag) -- rb_replace_node(&head->rbnode, -- &FRAG_CB(head)->next_frag->rbnode, -- &qp->q.rb_fragments); -- else -- rb_erase(&head->rbnode, &qp->q.rb_fragments); -- memset(&head->rbnode, 0, sizeof(head->rbnode)); -- barrier(); -- } -- if (head == qp->q.fragments_tail) -- qp->q.fragments_tail = NULL; -- -- sub_frag_mem_limit(qp->q.net, head->truesize); -- -+ head = inet_frag_pull_head(&qp->q); -+ if (!head) -+ goto out; - head->dev = dev_get_by_index_rcu(net, qp->iif); - if (!head->dev) - goto out; -@@ -343,12 +274,10 @@ static int ip_frag_reinit(struct ipq *qp) - static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) - { - struct net *net = container_of(qp->q.net, struct net, ipv4.frags); -- struct rb_node **rbn, *parent; -- struct sk_buff *skb1, *prev_tail; -- int ihl, end, skb1_run_end; -+ int ihl, end, flags, offset; -+ struct sk_buff *prev_tail; - struct net_device *dev; - unsigned int fragsize; -- int flags, offset; - int err = -ENOENT; - u8 ecn; - -@@ -380,7 +309,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) - */ - if (end < qp->q.len || - ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len)) -- goto err; -+ goto discard_qp; - qp->q.flags |= INET_FRAG_LAST_IN; - qp->q.len = end; - } else { -@@ -392,82 +321,33 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) - if (end > qp->q.len) { - /* Some bits beyond end -> corruption. */ - if (qp->q.flags & INET_FRAG_LAST_IN) -- goto err; -+ goto discard_qp; - qp->q.len = end; - } - } - if (end == offset) -- goto err; -+ goto discard_qp; - - err = -ENOMEM; - if (!pskb_pull(skb, skb_network_offset(skb) + ihl)) -- goto err; -+ goto discard_qp; - - err = pskb_trim_rcsum(skb, end - offset); - if (err) -- goto err; -+ goto discard_qp; - - /* Note : skb->rbnode and skb->dev share the same location. */ - dev = skb->dev; - /* Makes sure compiler wont do silly aliasing games */ - barrier(); - -- /* RFC5722, Section 4, amended by Errata ID : 3089 -- * When reassembling an IPv6 datagram, if -- * one or more its constituent fragments is determined to be an -- * overlapping fragment, the entire datagram (and any constituent -- * fragments) MUST be silently discarded. -- * -- * We do the same here for IPv4 (and increment an snmp counter) but -- * we do not want to drop the whole queue in response to a duplicate -- * fragment. -- */ -- -- err = -EINVAL; -- /* Find out where to put this fragment. */ - prev_tail = qp->q.fragments_tail; -- if (!prev_tail) -- ip4_frag_create_run(&qp->q, skb); /* First fragment. */ -- else if (prev_tail->ip_defrag_offset + prev_tail->len < end) { -- /* This is the common case: skb goes to the end. */ -- /* Detect and discard overlaps. */ -- if (offset < prev_tail->ip_defrag_offset + prev_tail->len) -- goto discard_qp; -- if (offset == prev_tail->ip_defrag_offset + prev_tail->len) -- ip4_frag_append_to_last_run(&qp->q, skb); -- else -- ip4_frag_create_run(&qp->q, skb); -- } else { -- /* Binary search. Note that skb can become the first fragment, -- * but not the last (covered above). -- */ -- rbn = &qp->q.rb_fragments.rb_node; -- do { -- parent = *rbn; -- skb1 = rb_to_skb(parent); -- skb1_run_end = skb1->ip_defrag_offset + -- FRAG_CB(skb1)->frag_run_len; -- if (end <= skb1->ip_defrag_offset) -- rbn = &parent->rb_left; -- else if (offset >= skb1_run_end) -- rbn = &parent->rb_right; -- else if (offset >= skb1->ip_defrag_offset && -- end <= skb1_run_end) -- goto err; /* No new data, potential duplicate */ -- else -- goto discard_qp; /* Found an overlap */ -- } while (*rbn); -- /* Here we have parent properly set, and rbn pointing to -- * one of its NULL left/right children. Insert skb. -- */ -- ip4_frag_init_run(skb); -- rb_link_node(&skb->rbnode, parent, rbn); -- rb_insert_color(&skb->rbnode, &qp->q.rb_fragments); -- } -+ err = inet_frag_queue_insert(&qp->q, skb, offset, end); -+ if (err) -+ goto insert_error; - - if (dev) - qp->iif = dev->ifindex; -- skb->ip_defrag_offset = offset; - - qp->q.stamp = skb->tstamp; - qp->q.meat += skb->len; -@@ -492,15 +372,24 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) - skb->_skb_refdst = 0UL; - err = ip_frag_reasm(qp, skb, prev_tail, dev); - skb->_skb_refdst = orefdst; -+ if (err) -+ inet_frag_kill(&qp->q); - return err; - } - - skb_dst_drop(skb); - return -EINPROGRESS; - -+insert_error: -+ if (err == IPFRAG_DUP) { -+ kfree_skb(skb); -+ return -EINVAL; -+ } -+ err = -EINVAL; -+ __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); - discard_qp: - inet_frag_kill(&qp->q); -- __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); -+ __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); - err: - kfree_skb(skb); - return err; -@@ -512,12 +401,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, - { - struct net *net = container_of(qp->q.net, struct net, ipv4.frags); - struct iphdr *iph; -- struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments); -- struct sk_buff **nextp; /* To build frag_list. */ -- struct rb_node *rbn; -- int len; -- int ihlen; -- int err; -+ void *reasm_data; -+ int len, err; - u8 ecn; - - ipq_kill(qp); -@@ -527,111 +412,23 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, - err = -EINVAL; - goto out_fail; - } -- /* Make the one we just received the head. */ -- if (head != skb) { -- fp = skb_clone(skb, GFP_ATOMIC); -- if (!fp) -- goto out_nomem; -- FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; -- if (RB_EMPTY_NODE(&skb->rbnode)) -- FRAG_CB(prev_tail)->next_frag = fp; -- else -- rb_replace_node(&skb->rbnode, &fp->rbnode, -- &qp->q.rb_fragments); -- if (qp->q.fragments_tail == skb) -- qp->q.fragments_tail = fp; -- skb_morph(skb, head); -- FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; -- rb_replace_node(&head->rbnode, &skb->rbnode, -- &qp->q.rb_fragments); -- consume_skb(head); -- head = skb; -- } -- -- WARN_ON(head->ip_defrag_offset != 0); - -- /* Allocate a new buffer for the datagram. */ -- ihlen = ip_hdrlen(head); -- len = ihlen + qp->q.len; -+ /* Make the one we just received the head. */ -+ reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail); -+ if (!reasm_data) -+ goto out_nomem; - -+ len = ip_hdrlen(skb) + qp->q.len; - err = -E2BIG; - if (len > 65535) - goto out_oversize; - -- /* Head of list must not be cloned. */ -- if (skb_unclone(head, GFP_ATOMIC)) -- goto out_nomem; -- -- /* If the first fragment is fragmented itself, we split -- * it to two chunks: the first with data and paged part -- * and the second, holding only fragments. */ -- if (skb_has_frag_list(head)) { -- struct sk_buff *clone; -- int i, plen = 0; -- -- clone = alloc_skb(0, GFP_ATOMIC); -- if (!clone) -- goto out_nomem; -- skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; -- skb_frag_list_init(head); -- for (i = 0; i < skb_shinfo(head)->nr_frags; i++) -- plen += skb_frag_size(&skb_shinfo(head)->frags[i]); -- clone->len = clone->data_len = head->data_len - plen; -- head->truesize += clone->truesize; -- clone->csum = 0; -- clone->ip_summed = head->ip_summed; -- add_frag_mem_limit(qp->q.net, clone->truesize); -- skb_shinfo(head)->frag_list = clone; -- nextp = &clone->next; -- } else { -- nextp = &skb_shinfo(head)->frag_list; -- } -+ inet_frag_reasm_finish(&qp->q, skb, reasm_data); - -- skb_push(head, head->data - skb_network_header(head)); -+ skb->dev = dev; -+ IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size); - -- /* Traverse the tree in order, to build frag_list. */ -- fp = FRAG_CB(head)->next_frag; -- rbn = rb_next(&head->rbnode); -- rb_erase(&head->rbnode, &qp->q.rb_fragments); -- while (rbn || fp) { -- /* fp points to the next sk_buff in the current run; -- * rbn points to the next run. -- */ -- /* Go through the current run. */ -- while (fp) { -- *nextp = fp; -- nextp = &fp->next; -- fp->prev = NULL; -- memset(&fp->rbnode, 0, sizeof(fp->rbnode)); -- fp->sk = NULL; -- head->data_len += fp->len; -- head->len += fp->len; -- if (head->ip_summed != fp->ip_summed) -- head->ip_summed = CHECKSUM_NONE; -- else if (head->ip_summed == CHECKSUM_COMPLETE) -- head->csum = csum_add(head->csum, fp->csum); -- head->truesize += fp->truesize; -- fp = FRAG_CB(fp)->next_frag; -- } -- /* Move to the next run. */ -- if (rbn) { -- struct rb_node *rbnext = rb_next(rbn); -- -- fp = rb_to_skb(rbn); -- rb_erase(rbn, &qp->q.rb_fragments); -- rbn = rbnext; -- } -- } -- sub_frag_mem_limit(qp->q.net, head->truesize); -- -- *nextp = NULL; -- head->next = NULL; -- head->prev = NULL; -- head->dev = dev; -- head->tstamp = qp->q.stamp; -- IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size); -- -- iph = ip_hdr(head); -+ iph = ip_hdr(skb); - iph->tot_len = htons(len); - iph->tos |= ecn; - -@@ -644,7 +441,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, - * from one very small df-fragment and one large non-df frag. - */ - if (qp->max_df_size == qp->q.max_size) { -- IPCB(head)->flags |= IPSKB_FRAG_PMTU; -+ IPCB(skb)->flags |= IPSKB_FRAG_PMTU; - iph->frag_off = htons(IP_DF); - } else { - iph->frag_off = 0; -@@ -742,28 +539,6 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) - } - EXPORT_SYMBOL(ip_check_defrag); - --unsigned int inet_frag_rbtree_purge(struct rb_root *root) --{ -- struct rb_node *p = rb_first(root); -- unsigned int sum = 0; -- -- while (p) { -- struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); -- -- p = rb_next(p); -- rb_erase(&skb->rbnode, root); -- while (skb) { -- struct sk_buff *next = FRAG_CB(skb)->next_frag; -- -- sum += skb->truesize; -- kfree_skb(skb); -- skb = next; -- } -- } -- return sum; --} --EXPORT_SYMBOL(inet_frag_rbtree_purge); -- - #ifdef CONFIG_SYSCTL - static int dist_min; - -diff --git a/net/ipv4/route.c b/net/ipv4/route.c -index 0e2cf9634541..02c49857b5a7 100644 ---- a/net/ipv4/route.c -+++ b/net/ipv4/route.c -@@ -1168,25 +1168,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) - return dst; - } - --static void ipv4_link_failure(struct sk_buff *skb) -+static void ipv4_send_dest_unreach(struct sk_buff *skb) - { - struct ip_options opt; -- struct rtable *rt; - int res; - - /* Recompile ip options since IPCB may not be valid anymore. -+ * Also check we have a reasonable ipv4 header. - */ -- memset(&opt, 0, sizeof(opt)); -- opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); -+ if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || -+ ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) -+ return; - -- rcu_read_lock(); -- res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); -- rcu_read_unlock(); -+ memset(&opt, 0, sizeof(opt)); -+ if (ip_hdr(skb)->ihl > 5) { -+ if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) -+ return; -+ opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); - -- if (res) -- return; -+ rcu_read_lock(); -+ res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); -+ rcu_read_unlock(); - -+ if (res) -+ return; -+ } - __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); -+} -+ -+static void ipv4_link_failure(struct sk_buff *skb) -+{ -+ struct rtable *rt; -+ -+ ipv4_send_dest_unreach(skb); - - rt = skb_rtable(skb); - if (rt) -diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c -index 024ab833557d..85713adf2770 100644 ---- a/net/ipv4/sysctl_net_ipv4.c -+++ b/net/ipv4/sysctl_net_ipv4.c -@@ -41,6 +41,7 @@ static int tcp_syn_retries_min = 1; - static int tcp_syn_retries_max = MAX_TCP_SYNCNT; - static int ip_ping_group_range_min[] = { 0, 0 }; - static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; -+static int one_day_secs = 24 * 3600; - - /* Update system visible IP port range */ - static void set_local_port_range(struct net *net, int range[2]) -@@ -460,7 +461,9 @@ static struct ctl_table ipv4_table[] = { - .data = &sysctl_tcp_min_rtt_wlen, - .maxlen = sizeof(int), - .mode = 0644, -- .proc_handler = proc_dointvec -+ .proc_handler = proc_dointvec_minmax, -+ .extra1 = &zero, -+ .extra2 = &one_day_secs - }, - { - .procname = "tcp_low_latency", -diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c -index e46185377981..1e1fa99b3243 100644 ---- a/net/ipv6/netfilter/nf_conntrack_reasm.c -+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c -@@ -33,9 +33,8 @@ - - #include - #include --#include -+#include - --#include - #include - #include - #include -@@ -52,14 +51,6 @@ - - static const char nf_frags_cache_name[] = "nf-frags"; - --struct nf_ct_frag6_skb_cb --{ -- struct inet6_skb_parm h; -- int offset; --}; -- --#define NFCT_FRAG6_CB(skb) ((struct nf_ct_frag6_skb_cb *)((skb)->cb)) -- - static struct inet_frags nf_frags; - - #ifdef CONFIG_SYSCTL -@@ -145,6 +136,9 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) - } - #endif - -+static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, -+ struct sk_buff *prev_tail, struct net_device *dev); -+ - static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) - { - return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); -@@ -158,7 +152,7 @@ static void nf_ct_frag6_expire(unsigned long data) - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); - net = container_of(fq->q.net, struct net, nf_frag.frags); - -- ip6_expire_frag_queue(net, fq); -+ ip6frag_expire_frag_queue(net, fq); - } - - /* Creation primitives. */ -@@ -185,9 +179,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, - static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, - const struct frag_hdr *fhdr, int nhoff) - { -- struct sk_buff *prev, *next; - unsigned int payload_len; -- int offset, end; -+ struct net_device *dev; -+ struct sk_buff *prev; -+ int offset, end, err; - u8 ecn; - - if (fq->q.flags & INET_FRAG_COMPLETE) { -@@ -262,55 +257,19 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, - goto err; - } - -- /* Find out which fragments are in front and at the back of us -- * in the chain of fragments so far. We must know where to put -- * this fragment, right? -- */ -+ /* Note : skb->rbnode and skb->dev share the same location. */ -+ dev = skb->dev; -+ /* Makes sure compiler wont do silly aliasing games */ -+ barrier(); -+ - prev = fq->q.fragments_tail; -- if (!prev || NFCT_FRAG6_CB(prev)->offset < offset) { -- next = NULL; -- goto found; -- } -- prev = NULL; -- for (next = fq->q.fragments; next != NULL; next = next->next) { -- if (NFCT_FRAG6_CB(next)->offset >= offset) -- break; /* bingo! */ -- prev = next; -- } -+ err = inet_frag_queue_insert(&fq->q, skb, offset, end); -+ if (err) -+ goto insert_error; - --found: -- /* RFC5722, Section 4: -- * When reassembling an IPv6 datagram, if -- * one or more its constituent fragments is determined to be an -- * overlapping fragment, the entire datagram (and any constituent -- * fragments, including those not yet received) MUST be silently -- * discarded. -- */ -+ if (dev) -+ fq->iif = dev->ifindex; - -- /* Check for overlap with preceding fragment. */ -- if (prev && -- (NFCT_FRAG6_CB(prev)->offset + prev->len) > offset) -- goto discard_fq; -- -- /* Look for overlap with succeeding segment. */ -- if (next && NFCT_FRAG6_CB(next)->offset < end) -- goto discard_fq; -- -- NFCT_FRAG6_CB(skb)->offset = offset; -- -- /* Insert this fragment in the chain of fragments. */ -- skb->next = next; -- if (!next) -- fq->q.fragments_tail = skb; -- if (prev) -- prev->next = skb; -- else -- fq->q.fragments = skb; -- -- if (skb->dev) { -- fq->iif = skb->dev->ifindex; -- skb->dev = NULL; -- } - fq->q.stamp = skb->tstamp; - fq->q.meat += skb->len; - fq->ecn |= ecn; -@@ -326,11 +285,25 @@ found: - fq->q.flags |= INET_FRAG_FIRST_IN; - } - -- return 0; -+ if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && -+ fq->q.meat == fq->q.len) { -+ unsigned long orefdst = skb->_skb_refdst; - --discard_fq: -+ skb->_skb_refdst = 0UL; -+ err = nf_ct_frag6_reasm(fq, skb, prev, dev); -+ skb->_skb_refdst = orefdst; -+ return err; -+ } -+ -+ skb_dst_drop(skb); -+ return -EINPROGRESS; -+ -+insert_error: -+ if (err == IPFRAG_DUP) -+ goto err; - inet_frag_kill(&fq->q); - err: -+ skb_dst_drop(skb); - return -EINVAL; - } - -@@ -340,141 +313,67 @@ err: - * It is called with locked fq, and caller must check that - * queue is eligible for reassembly i.e. it is not COMPLETE, - * the last and the first frames arrived and all the bits are here. -- * -- * returns true if *prev skb has been transformed into the reassembled -- * skb, false otherwise. - */ --static bool --nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev) -+static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, -+ struct sk_buff *prev_tail, struct net_device *dev) - { -- struct sk_buff *fp, *head = fq->q.fragments; -- int payload_len; -+ void *reasm_data; -+ int payload_len; - u8 ecn; - - inet_frag_kill(&fq->q); - -- WARN_ON(head == NULL); -- WARN_ON(NFCT_FRAG6_CB(head)->offset != 0); -- - ecn = ip_frag_ecn_table[fq->ecn]; - if (unlikely(ecn == 0xff)) -- return false; -+ goto err; - -- /* Unfragmented part is taken from the first segment. */ -- payload_len = ((head->data - skb_network_header(head)) - -+ reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); -+ if (!reasm_data) -+ goto err; -+ -+ payload_len = ((skb->data - skb_network_header(skb)) - - sizeof(struct ipv6hdr) + fq->q.len - - sizeof(struct frag_hdr)); - if (payload_len > IPV6_MAXPLEN) { - net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", - payload_len); -- return false; -- } -- -- /* Head of list must not be cloned. */ -- if (skb_unclone(head, GFP_ATOMIC)) -- return false; -- -- /* If the first fragment is fragmented itself, we split -- * it to two chunks: the first with data and paged part -- * and the second, holding only fragments. */ -- if (skb_has_frag_list(head)) { -- struct sk_buff *clone; -- int i, plen = 0; -- -- clone = alloc_skb(0, GFP_ATOMIC); -- if (clone == NULL) -- return false; -- -- clone->next = head->next; -- head->next = clone; -- skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; -- skb_frag_list_init(head); -- for (i = 0; i < skb_shinfo(head)->nr_frags; i++) -- plen += skb_frag_size(&skb_shinfo(head)->frags[i]); -- clone->len = clone->data_len = head->data_len - plen; -- head->data_len -= clone->len; -- head->len -= clone->len; -- clone->csum = 0; -- clone->ip_summed = head->ip_summed; -- -- add_frag_mem_limit(fq->q.net, clone->truesize); -- } -- -- /* morph head into last received skb: prev. -- * -- * This allows callers of ipv6 conntrack defrag to continue -- * to use the last skb(frag) passed into the reasm engine. -- * The last skb frag 'silently' turns into the full reassembled skb. -- * -- * Since prev is also part of q->fragments we have to clone it first. -- */ -- if (head != prev) { -- struct sk_buff *iter; -- -- fp = skb_clone(prev, GFP_ATOMIC); -- if (!fp) -- return false; -- -- fp->next = prev->next; -- -- iter = head; -- while (iter) { -- if (iter->next == prev) { -- iter->next = fp; -- break; -- } -- iter = iter->next; -- } -- -- skb_morph(prev, head); -- prev->next = head->next; -- consume_skb(head); -- head = prev; -+ goto err; - } - - /* We have to remove fragment header from datagram and to relocate - * header in order to calculate ICV correctly. */ -- skb_network_header(head)[fq->nhoffset] = skb_transport_header(head)[0]; -- memmove(head->head + sizeof(struct frag_hdr), head->head, -- (head->data - head->head) - sizeof(struct frag_hdr)); -- head->mac_header += sizeof(struct frag_hdr); -- head->network_header += sizeof(struct frag_hdr); -- -- skb_shinfo(head)->frag_list = head->next; -- skb_reset_transport_header(head); -- skb_push(head, head->data - skb_network_header(head)); -- -- for (fp = head->next; fp; fp = fp->next) { -- head->data_len += fp->len; -- head->len += fp->len; -- if (head->ip_summed != fp->ip_summed) -- head->ip_summed = CHECKSUM_NONE; -- else if (head->ip_summed == CHECKSUM_COMPLETE) -- head->csum = csum_add(head->csum, fp->csum); -- head->truesize += fp->truesize; -- fp->sk = NULL; -- } -- sub_frag_mem_limit(fq->q.net, head->truesize); -+ skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0]; -+ memmove(skb->head + sizeof(struct frag_hdr), skb->head, -+ (skb->data - skb->head) - sizeof(struct frag_hdr)); -+ skb->mac_header += sizeof(struct frag_hdr); -+ skb->network_header += sizeof(struct frag_hdr); -+ -+ skb_reset_transport_header(skb); - -- head->ignore_df = 1; -- head->next = NULL; -- head->dev = dev; -- head->tstamp = fq->q.stamp; -- ipv6_hdr(head)->payload_len = htons(payload_len); -- ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); -- IP6CB(head)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; -+ inet_frag_reasm_finish(&fq->q, skb, reasm_data); -+ -+ skb->ignore_df = 1; -+ skb->dev = dev; -+ ipv6_hdr(skb)->payload_len = htons(payload_len); -+ ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); -+ IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; - - /* Yes, and fold redundant checksum back. 8) */ -- if (head->ip_summed == CHECKSUM_COMPLETE) -- head->csum = csum_partial(skb_network_header(head), -- skb_network_header_len(head), -- head->csum); -+ if (skb->ip_summed == CHECKSUM_COMPLETE) -+ skb->csum = csum_partial(skb_network_header(skb), -+ skb_network_header_len(skb), -+ skb->csum); - - fq->q.fragments = NULL; - fq->q.rb_fragments = RB_ROOT; - fq->q.fragments_tail = NULL; -+ fq->q.last_run_head = NULL; -+ -+ return 0; - -- return true; -+err: -+ inet_frag_kill(&fq->q); -+ return -EINVAL; - } - - /* -@@ -543,7 +442,6 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) - int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) - { - u16 savethdr = skb->transport_header; -- struct net_device *dev = skb->dev; - int fhoff, nhoff, ret; - struct frag_hdr *fhdr; - struct frag_queue *fq; -@@ -566,10 +464,6 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) - hdr = ipv6_hdr(skb); - fhdr = (struct frag_hdr *)skb_transport_header(skb); - -- if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU && -- fhdr->frag_off & htons(IP6_MF)) -- return -EINVAL; -- - skb_orphan(skb); - fq = fq_find(net, fhdr->identification, user, hdr, - skb->dev ? skb->dev->ifindex : 0); -@@ -581,24 +475,17 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) - spin_lock_bh(&fq->q.lock); - - ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff); -- if (ret < 0) { -- if (ret == -EPROTO) { -- skb->transport_header = savethdr; -- ret = 0; -- } -- goto out_unlock; -+ if (ret == -EPROTO) { -+ skb->transport_header = savethdr; -+ ret = 0; - } - - /* after queue has assumed skb ownership, only 0 or -EINPROGRESS - * must be returned. - */ -- ret = -EINPROGRESS; -- if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && -- fq->q.meat == fq->q.len && -- nf_ct_frag6_reasm(fq, skb, dev)) -- ret = 0; -+ if (ret) -+ ret = -EINPROGRESS; - --out_unlock: - spin_unlock_bh(&fq->q.lock); - inet_frag_put(&fq->q); - return ret; -@@ -634,16 +521,24 @@ static struct pernet_operations nf_ct_net_ops = { - .exit = nf_ct_net_exit, - }; - -+static const struct rhashtable_params nfct_rhash_params = { -+ .head_offset = offsetof(struct inet_frag_queue, node), -+ .hashfn = ip6frag_key_hashfn, -+ .obj_hashfn = ip6frag_obj_hashfn, -+ .obj_cmpfn = ip6frag_obj_cmpfn, -+ .automatic_shrinking = true, -+}; -+ - int nf_ct_frag6_init(void) - { - int ret = 0; - -- nf_frags.constructor = ip6_frag_init; -+ nf_frags.constructor = ip6frag_init; - nf_frags.destructor = NULL; - nf_frags.qsize = sizeof(struct frag_queue); - nf_frags.frag_expire = nf_ct_frag6_expire; - nf_frags.frags_cache_name = nf_frags_cache_name; -- nf_frags.rhash_params = ip6_rhash_params; -+ nf_frags.rhash_params = nfct_rhash_params; - ret = inet_frags_init(&nf_frags); - if (ret) - goto out; -diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c -index f06b0471f39f..c4070e9c4260 100644 ---- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c -+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c -@@ -14,8 +14,7 @@ - #include - #include - #include --#include --#include -+#include - - #include - #include -diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c -index 74ffbcb306a6..4aed9c45a91a 100644 ---- a/net/ipv6/reassembly.c -+++ b/net/ipv6/reassembly.c -@@ -57,18 +57,11 @@ - #include - #include - #include --#include -+#include - #include - - static const char ip6_frag_cache_name[] = "ip6-frags"; - --struct ip6frag_skb_cb { -- struct inet6_skb_parm h; -- int offset; --}; -- --#define FRAG6_CB(skb) ((struct ip6frag_skb_cb *)((skb)->cb)) -- - static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) - { - return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); -@@ -76,63 +69,8 @@ static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) - - static struct inet_frags ip6_frags; - --static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, -- struct net_device *dev); -- --void ip6_frag_init(struct inet_frag_queue *q, const void *a) --{ -- struct frag_queue *fq = container_of(q, struct frag_queue, q); -- const struct frag_v6_compare_key *key = a; -- -- q->key.v6 = *key; -- fq->ecn = 0; --} --EXPORT_SYMBOL(ip6_frag_init); -- --void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq) --{ -- struct net_device *dev = NULL; -- struct sk_buff *head; -- -- rcu_read_lock(); -- spin_lock(&fq->q.lock); -- -- if (fq->q.flags & INET_FRAG_COMPLETE) -- goto out; -- -- inet_frag_kill(&fq->q); -- -- dev = dev_get_by_index_rcu(net, fq->iif); -- if (!dev) -- goto out; -- -- __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); -- __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); -- -- /* Don't send error if the first segment did not arrive. */ -- head = fq->q.fragments; -- if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head) -- goto out; -- -- /* But use as source device on which LAST ARRIVED -- * segment was received. And do not use fq->dev -- * pointer directly, device might already disappeared. -- */ -- head->dev = dev; -- skb_get(head); -- spin_unlock(&fq->q.lock); -- -- icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); -- kfree_skb(head); -- goto out_rcu_unlock; -- --out: -- spin_unlock(&fq->q.lock); --out_rcu_unlock: -- rcu_read_unlock(); -- inet_frag_put(&fq->q); --} --EXPORT_SYMBOL(ip6_expire_frag_queue); -+static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, -+ struct sk_buff *prev_tail, struct net_device *dev); - - static void ip6_frag_expire(unsigned long data) - { -@@ -142,7 +80,7 @@ static void ip6_frag_expire(unsigned long data) - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); - net = container_of(fq->q.net, struct net, ipv6.frags); - -- ip6_expire_frag_queue(net, fq); -+ ip6frag_expire_frag_queue(net, fq); - } - - static struct frag_queue * -@@ -169,27 +107,29 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif) - } - - static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, -- struct frag_hdr *fhdr, int nhoff) -+ struct frag_hdr *fhdr, int nhoff, -+ u32 *prob_offset) - { -- struct sk_buff *prev, *next; -- struct net_device *dev; -- int offset, end; - struct net *net = dev_net(skb_dst(skb)->dev); -+ int offset, end, fragsize; -+ struct sk_buff *prev_tail; -+ struct net_device *dev; -+ int err = -ENOENT; - u8 ecn; - - if (fq->q.flags & INET_FRAG_COMPLETE) - goto err; - -+ err = -EINVAL; - offset = ntohs(fhdr->frag_off) & ~0x7; - end = offset + (ntohs(ipv6_hdr(skb)->payload_len) - - ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); - - if ((unsigned int)end > IPV6_MAXPLEN) { -- __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), -- IPSTATS_MIB_INHDRERRORS); -- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, -- ((u8 *)&fhdr->frag_off - -- skb_network_header(skb))); -+ *prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb); -+ /* note that if prob_offset is set, the skb is freed elsewhere, -+ * we do not free it here. -+ */ - return -1; - } - -@@ -209,7 +149,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, - */ - if (end < fq->q.len || - ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) -- goto err; -+ goto discard_fq; - fq->q.flags |= INET_FRAG_LAST_IN; - fq->q.len = end; - } else { -@@ -220,84 +160,51 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, - /* RFC2460 says always send parameter problem in - * this case. -DaveM - */ -- __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), -- IPSTATS_MIB_INHDRERRORS); -- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, -- offsetof(struct ipv6hdr, payload_len)); -+ *prob_offset = offsetof(struct ipv6hdr, payload_len); - return -1; - } - if (end > fq->q.len) { - /* Some bits beyond end -> corruption. */ - if (fq->q.flags & INET_FRAG_LAST_IN) -- goto err; -+ goto discard_fq; - fq->q.len = end; - } - } - - if (end == offset) -- goto err; -+ goto discard_fq; - -+ err = -ENOMEM; - /* Point into the IP datagram 'data' part. */ - if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) -- goto err; -- -- if (pskb_trim_rcsum(skb, end - offset)) -- goto err; -- -- /* Find out which fragments are in front and at the back of us -- * in the chain of fragments so far. We must know where to put -- * this fragment, right? -- */ -- prev = fq->q.fragments_tail; -- if (!prev || FRAG6_CB(prev)->offset < offset) { -- next = NULL; -- goto found; -- } -- prev = NULL; -- for (next = fq->q.fragments; next != NULL; next = next->next) { -- if (FRAG6_CB(next)->offset >= offset) -- break; /* bingo! */ -- prev = next; -- } -- --found: -- /* RFC5722, Section 4, amended by Errata ID : 3089 -- * When reassembling an IPv6 datagram, if -- * one or more its constituent fragments is determined to be an -- * overlapping fragment, the entire datagram (and any constituent -- * fragments) MUST be silently discarded. -- */ -- -- /* Check for overlap with preceding fragment. */ -- if (prev && -- (FRAG6_CB(prev)->offset + prev->len) > offset) - goto discard_fq; - -- /* Look for overlap with succeeding segment. */ -- if (next && FRAG6_CB(next)->offset < end) -+ err = pskb_trim_rcsum(skb, end - offset); -+ if (err) - goto discard_fq; - -- FRAG6_CB(skb)->offset = offset; -+ /* Note : skb->rbnode and skb->dev share the same location. */ -+ dev = skb->dev; -+ /* Makes sure compiler wont do silly aliasing games */ -+ barrier(); - -- /* Insert this fragment in the chain of fragments. */ -- skb->next = next; -- if (!next) -- fq->q.fragments_tail = skb; -- if (prev) -- prev->next = skb; -- else -- fq->q.fragments = skb; -+ prev_tail = fq->q.fragments_tail; -+ err = inet_frag_queue_insert(&fq->q, skb, offset, end); -+ if (err) -+ goto insert_error; - -- dev = skb->dev; -- if (dev) { -+ if (dev) - fq->iif = dev->ifindex; -- skb->dev = NULL; -- } -+ - fq->q.stamp = skb->tstamp; - fq->q.meat += skb->len; - fq->ecn |= ecn; - add_frag_mem_limit(fq->q.net, skb->truesize); - -+ fragsize = -skb_network_offset(skb) + skb->len; -+ if (fragsize > fq->q.max_size) -+ fq->q.max_size = fragsize; -+ - /* The first fragment. - * nhoffset is obtained from the first fragment, of course. - */ -@@ -308,44 +215,48 @@ found: - - if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len) { -- int res; - unsigned long orefdst = skb->_skb_refdst; - - skb->_skb_refdst = 0UL; -- res = ip6_frag_reasm(fq, prev, dev); -+ err = ip6_frag_reasm(fq, skb, prev_tail, dev); - skb->_skb_refdst = orefdst; -- return res; -+ return err; - } - - skb_dst_drop(skb); -- return -1; -+ return -EINPROGRESS; - -+insert_error: -+ if (err == IPFRAG_DUP) { -+ kfree_skb(skb); -+ return -EINVAL; -+ } -+ err = -EINVAL; -+ __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), -+ IPSTATS_MIB_REASM_OVERLAPS); - discard_fq: - inet_frag_kill(&fq->q); --err: - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_REASMFAILS); -+err: - kfree_skb(skb); -- return -1; -+ return err; - } - - /* - * Check if this packet is complete. -- * Returns NULL on failure by any reason, and pointer -- * to current nexthdr field in reassembled frame. - * - * It is called with locked fq, and caller must check that - * queue is eligible for reassembly i.e. it is not COMPLETE, - * the last and the first frames arrived and all the bits are here. - */ --static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, -- struct net_device *dev) -+static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, -+ struct sk_buff *prev_tail, struct net_device *dev) - { - struct net *net = container_of(fq->q.net, struct net, ipv6.frags); -- struct sk_buff *fp, *head = fq->q.fragments; -- int payload_len; - unsigned int nhoff; -- int sum_truesize; -+ void *reasm_data; -+ int payload_len; - u8 ecn; - - inet_frag_kill(&fq->q); -@@ -354,113 +265,40 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, - if (unlikely(ecn == 0xff)) - goto out_fail; - -- /* Make the one we just received the head. */ -- if (prev) { -- head = prev->next; -- fp = skb_clone(head, GFP_ATOMIC); -- -- if (!fp) -- goto out_oom; -- -- fp->next = head->next; -- if (!fp->next) -- fq->q.fragments_tail = fp; -- prev->next = fp; -- -- skb_morph(head, fq->q.fragments); -- head->next = fq->q.fragments->next; -- -- consume_skb(fq->q.fragments); -- fq->q.fragments = head; -- } -- -- WARN_ON(head == NULL); -- WARN_ON(FRAG6_CB(head)->offset != 0); -+ reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); -+ if (!reasm_data) -+ goto out_oom; - -- /* Unfragmented part is taken from the first segment. */ -- payload_len = ((head->data - skb_network_header(head)) - -+ payload_len = ((skb->data - skb_network_header(skb)) - - sizeof(struct ipv6hdr) + fq->q.len - - sizeof(struct frag_hdr)); - if (payload_len > IPV6_MAXPLEN) - goto out_oversize; - -- /* Head of list must not be cloned. */ -- if (skb_unclone(head, GFP_ATOMIC)) -- goto out_oom; -- -- /* If the first fragment is fragmented itself, we split -- * it to two chunks: the first with data and paged part -- * and the second, holding only fragments. */ -- if (skb_has_frag_list(head)) { -- struct sk_buff *clone; -- int i, plen = 0; -- -- clone = alloc_skb(0, GFP_ATOMIC); -- if (!clone) -- goto out_oom; -- clone->next = head->next; -- head->next = clone; -- skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; -- skb_frag_list_init(head); -- for (i = 0; i < skb_shinfo(head)->nr_frags; i++) -- plen += skb_frag_size(&skb_shinfo(head)->frags[i]); -- clone->len = clone->data_len = head->data_len - plen; -- head->data_len -= clone->len; -- head->len -= clone->len; -- clone->csum = 0; -- clone->ip_summed = head->ip_summed; -- add_frag_mem_limit(fq->q.net, clone->truesize); -- } -- - /* We have to remove fragment header from datagram and to relocate - * header in order to calculate ICV correctly. */ - nhoff = fq->nhoffset; -- skb_network_header(head)[nhoff] = skb_transport_header(head)[0]; -- memmove(head->head + sizeof(struct frag_hdr), head->head, -- (head->data - head->head) - sizeof(struct frag_hdr)); -- if (skb_mac_header_was_set(head)) -- head->mac_header += sizeof(struct frag_hdr); -- head->network_header += sizeof(struct frag_hdr); -- -- skb_reset_transport_header(head); -- skb_push(head, head->data - skb_network_header(head)); -- -- sum_truesize = head->truesize; -- for (fp = head->next; fp;) { -- bool headstolen; -- int delta; -- struct sk_buff *next = fp->next; -- -- sum_truesize += fp->truesize; -- if (head->ip_summed != fp->ip_summed) -- head->ip_summed = CHECKSUM_NONE; -- else if (head->ip_summed == CHECKSUM_COMPLETE) -- head->csum = csum_add(head->csum, fp->csum); -- -- if (skb_try_coalesce(head, fp, &headstolen, &delta)) { -- kfree_skb_partial(fp, headstolen); -- } else { -- if (!skb_shinfo(head)->frag_list) -- skb_shinfo(head)->frag_list = fp; -- head->data_len += fp->len; -- head->len += fp->len; -- head->truesize += fp->truesize; -- } -- fp = next; -- } -- sub_frag_mem_limit(fq->q.net, sum_truesize); -+ skb_network_header(skb)[nhoff] = skb_transport_header(skb)[0]; -+ memmove(skb->head + sizeof(struct frag_hdr), skb->head, -+ (skb->data - skb->head) - sizeof(struct frag_hdr)); -+ if (skb_mac_header_was_set(skb)) -+ skb->mac_header += sizeof(struct frag_hdr); -+ skb->network_header += sizeof(struct frag_hdr); - -- head->next = NULL; -- head->dev = dev; -- head->tstamp = fq->q.stamp; -- ipv6_hdr(head)->payload_len = htons(payload_len); -- ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); -- IP6CB(head)->nhoff = nhoff; -- IP6CB(head)->flags |= IP6SKB_FRAGMENTED; -+ skb_reset_transport_header(skb); -+ -+ inet_frag_reasm_finish(&fq->q, skb, reasm_data); -+ -+ skb->dev = dev; -+ ipv6_hdr(skb)->payload_len = htons(payload_len); -+ ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); -+ IP6CB(skb)->nhoff = nhoff; -+ IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; -+ IP6CB(skb)->frag_max_size = fq->q.max_size; - - /* Yes, and fold redundant checksum back. 8) */ -- skb_postpush_rcsum(head, skb_network_header(head), -- skb_network_header_len(head)); -+ skb_postpush_rcsum(skb, skb_network_header(skb), -+ skb_network_header_len(skb)); - - rcu_read_lock(); - __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); -@@ -468,6 +306,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, - fq->q.fragments = NULL; - fq->q.rb_fragments = RB_ROOT; - fq->q.fragments_tail = NULL; -+ fq->q.last_run_head = NULL; - return 1; - - out_oversize: -@@ -479,6 +318,7 @@ out_fail: - rcu_read_lock(); - __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); - rcu_read_unlock(); -+ inet_frag_kill(&fq->q); - return -1; - } - -@@ -517,22 +357,26 @@ static int ipv6_frag_rcv(struct sk_buff *skb) - return 1; - } - -- if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU && -- fhdr->frag_off & htons(IP6_MF)) -- goto fail_hdr; -- - iif = skb->dev ? skb->dev->ifindex : 0; - fq = fq_find(net, fhdr->identification, hdr, iif); - if (fq) { -+ u32 prob_offset = 0; - int ret; - - spin_lock(&fq->q.lock); - - fq->iif = iif; -- ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff); -+ ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff, -+ &prob_offset); - - spin_unlock(&fq->q.lock); - inet_frag_put(&fq->q); -+ if (prob_offset) { -+ __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), -+ IPSTATS_MIB_INHDRERRORS); -+ /* icmpv6_param_prob() calls kfree_skb(skb) */ -+ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset); -+ } - return ret; - } - -@@ -700,42 +544,19 @@ static struct pernet_operations ip6_frags_ops = { - .exit = ipv6_frags_exit_net, - }; - --static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed) --{ -- return jhash2(data, -- sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); --} -- --static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed) --{ -- const struct inet_frag_queue *fq = data; -- -- return jhash2((const u32 *)&fq->key.v6, -- sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); --} -- --static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) --{ -- const struct frag_v6_compare_key *key = arg->key; -- const struct inet_frag_queue *fq = ptr; -- -- return !!memcmp(&fq->key, key, sizeof(*key)); --} -- --const struct rhashtable_params ip6_rhash_params = { -+static const struct rhashtable_params ip6_rhash_params = { - .head_offset = offsetof(struct inet_frag_queue, node), -- .hashfn = ip6_key_hashfn, -- .obj_hashfn = ip6_obj_hashfn, -- .obj_cmpfn = ip6_obj_cmpfn, -+ .hashfn = ip6frag_key_hashfn, -+ .obj_hashfn = ip6frag_obj_hashfn, -+ .obj_cmpfn = ip6frag_obj_cmpfn, - .automatic_shrinking = true, - }; --EXPORT_SYMBOL(ip6_rhash_params); - - int __init ipv6_frag_init(void) - { - int ret; - -- ip6_frags.constructor = ip6_frag_init; -+ ip6_frags.constructor = ip6frag_init; - ip6_frags.destructor = NULL; - ip6_frags.qsize = sizeof(struct frag_queue); - ip6_frags.frag_expire = ip6_frag_expire; -diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c -index f135814c34ad..02d6f38f7869 100644 ---- a/net/openvswitch/conntrack.c -+++ b/net/openvswitch/conntrack.c -@@ -23,6 +23,7 @@ - #include - #include - #include -+#include - - #ifdef CONFIG_NF_NAT_NEEDED - #include -diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c -index 4fe8f4fec4ee..da84d6b2f72c 100644 ---- a/net/rds/ib_fmr.c -+++ b/net/rds/ib_fmr.c -@@ -44,6 +44,17 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages) - else - pool = rds_ibdev->mr_1m_pool; - -+ if (atomic_read(&pool->dirty_count) >= pool->max_items / 10) -+ queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); -+ -+ /* Switch pools if one of the pool is reaching upper limit */ -+ if (atomic_read(&pool->dirty_count) >= pool->max_items * 9 / 10) { -+ if (pool->pool_type == RDS_IB_MR_8K_POOL) -+ pool = rds_ibdev->mr_1m_pool; -+ else -+ pool = rds_ibdev->mr_8k_pool; -+ } -+ - ibmr = rds_ib_try_reuse_ibmr(pool); - if (ibmr) - return ibmr; -diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c -index 977f69886c00..91b53d462fc0 100644 ---- a/net/rds/ib_rdma.c -+++ b/net/rds/ib_rdma.c -@@ -442,9 +442,6 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool) - struct rds_ib_mr *ibmr = NULL; - int iter = 0; - -- if (atomic_read(&pool->dirty_count) >= pool->max_items_soft / 10) -- queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); -- - while (1) { - ibmr = rds_ib_reuse_mr(pool); - if (ibmr) -diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c -index cab50ece6f3d..cdcc0fea9f5a 100644 ---- a/net/sunrpc/cache.c -+++ b/net/sunrpc/cache.c -@@ -54,6 +54,7 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail) - h->last_refresh = now; - } - -+static inline int cache_is_valid(struct cache_head *h); - static void cache_fresh_locked(struct cache_head *head, time_t expiry, - struct cache_detail *detail); - static void cache_fresh_unlocked(struct cache_head *head, -@@ -100,6 +101,8 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, - if (cache_is_expired(detail, tmp)) { - hlist_del_init(&tmp->cache_list); - detail->entries --; -+ if (cache_is_valid(tmp) == -EAGAIN) -+ set_bit(CACHE_NEGATIVE, &tmp->flags); - cache_fresh_locked(tmp, 0, detail); - freeme = tmp; - break; -diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c -index d947b8210399..0cf9403b4c44 100644 ---- a/net/tipc/netlink_compat.c -+++ b/net/tipc/netlink_compat.c -@@ -262,8 +262,14 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, - if (msg->rep_type) - tipc_tlv_init(msg->rep, msg->rep_type); - -- if (cmd->header) -- (*cmd->header)(msg); -+ if (cmd->header) { -+ err = (*cmd->header)(msg); -+ if (err) { -+ kfree_skb(msg->rep); -+ msg->rep = NULL; -+ return err; -+ } -+ } - - arg = nlmsg_new(0, GFP_KERNEL); - if (!arg) { -@@ -388,7 +394,12 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, - if (!bearer) - return -EMSGSIZE; - -- len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME); -+ len = TLV_GET_DATA_LEN(msg->req); -+ len -= offsetof(struct tipc_bearer_config, name); -+ if (len <= 0) -+ return -EINVAL; -+ -+ len = min_t(int, len, TIPC_MAX_BEARER_NAME); - if (!string_is_valid(b->name, len)) - return -EINVAL; - -@@ -757,7 +768,12 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd, - - lc = (struct tipc_link_config *)TLV_DATA(msg->req); - -- len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); -+ len = TLV_GET_DATA_LEN(msg->req); -+ len -= offsetof(struct tipc_link_config, name); -+ if (len <= 0) -+ return -EINVAL; -+ -+ len = min_t(int, len, TIPC_MAX_LINK_NAME); - if (!string_is_valid(lc->name, len)) - return -EINVAL; - -diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c -index 9c07c76c504d..cc4b4abb2759 100644 ---- a/net/vmw_vsock/virtio_transport_common.c -+++ b/net/vmw_vsock/virtio_transport_common.c -@@ -601,6 +601,8 @@ static int virtio_transport_reset(struct vsock_sock *vsk, - */ - static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) - { -+ const struct virtio_transport *t; -+ struct virtio_vsock_pkt *reply; - struct virtio_vsock_pkt_info info = { - .op = VIRTIO_VSOCK_OP_RST, - .type = le16_to_cpu(pkt->hdr.type), -@@ -611,15 +613,21 @@ static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) - if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) - return 0; - -- pkt = virtio_transport_alloc_pkt(&info, 0, -- le64_to_cpu(pkt->hdr.dst_cid), -- le32_to_cpu(pkt->hdr.dst_port), -- le64_to_cpu(pkt->hdr.src_cid), -- le32_to_cpu(pkt->hdr.src_port)); -- if (!pkt) -+ reply = virtio_transport_alloc_pkt(&info, 0, -+ le64_to_cpu(pkt->hdr.dst_cid), -+ le32_to_cpu(pkt->hdr.dst_port), -+ le64_to_cpu(pkt->hdr.src_cid), -+ le32_to_cpu(pkt->hdr.src_port)); -+ if (!reply) - return -ENOMEM; - -- return virtio_transport_get_ops()->send_pkt(pkt); -+ t = virtio_transport_get_ops(); -+ if (!t) { -+ virtio_transport_free_pkt(reply); -+ return -ENOTCONN; -+ } -+ -+ return t->send_pkt(reply); - } - - static void virtio_transport_wait_close(struct sock *sk, long timeout) -diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include -index 7f430778f418..558dea61db11 100644 ---- a/scripts/Kbuild.include -+++ b/scripts/Kbuild.include -@@ -166,9 +166,7 @@ cc-ldoption = $(call try-run,\ - - # ld-option - # Usage: LDFLAGS += $(call ld-option, -X) --ld-option = $(call try-run,\ -- $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -x c /dev/null -c -o "$$TMPO"; \ -- $(LD) $(LDFLAGS) $(1) "$$TMPO" -o "$$TMP",$(1),$(2)) -+ld-option = $(call try-run, $(LD) $(LDFLAGS) $(1) -v,$(1),$(2)) - - # ar-option - # Usage: KBUILD_ARFLAGS := $(call ar-option,D) diff --git a/patch/kernel/odroidn2-default/patch-4.9.172-173.patch b/patch/kernel/odroidn2-default/patch-4.9.172-173.patch deleted file mode 100644 index 14ca386a93..0000000000 --- a/patch/kernel/odroidn2-default/patch-4.9.172-173.patch +++ /dev/null @@ -1,881 +0,0 @@ -diff --git a/Makefile b/Makefile -index 75cba5fbdb46..a4e35453f9e4 100644 ---- a/Makefile -+++ b/Makefile -@@ -1,6 +1,6 @@ - VERSION = 4 - PATCHLEVEL = 9 --SUBLEVEL = 172 -+SUBLEVEL = 173 - EXTRAVERSION = - NAME = Roaring Lionus - -diff --git a/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts b/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts -index 84df85ea6296..7efde03daadd 100644 ---- a/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts -+++ b/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts -@@ -26,5 +26,5 @@ - }; - - &hdmi { -- hpd-gpios = <&gpio 46 GPIO_ACTIVE_LOW>; -+ hpd-gpios = <&gpio 46 GPIO_ACTIVE_HIGH>; - }; -diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi -index e0280cac2484..fed72a5f3ffa 100644 ---- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi -+++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi -@@ -90,6 +90,7 @@ - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; -+ phy-reset-duration = <10>; /* in msecs */ - phy-reset-gpios = <&gpio3 23 GPIO_ACTIVE_LOW>; - phy-supply = <&vdd_eth_io_reg>; - status = "disabled"; -diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h -index 8d665f1b29f8..f0fe566a9910 100644 ---- a/arch/s390/include/asm/elf.h -+++ b/arch/s390/include/asm/elf.h -@@ -215,11 +215,14 @@ do { \ - - /* - * Cache aliasing on the latest machines calls for a mapping granularity -- * of 512KB. For 64-bit processes use a 512KB alignment and a randomization -- * of up to 1GB. For 31-bit processes the virtual address space is limited, -- * use no alignment and limit the randomization to 8MB. -+ * of 512KB for the anonymous mapping base. For 64-bit processes use a -+ * 512KB alignment and a randomization of up to 1GB. For 31-bit processes -+ * the virtual address space is limited, use no alignment and limit the -+ * randomization to 8MB. -+ * For the additional randomization of the program break use 32MB for -+ * 64-bit and 8MB for 31-bit. - */ --#define BRK_RND_MASK (is_compat_task() ? 0x7ffUL : 0x3ffffUL) -+#define BRK_RND_MASK (is_compat_task() ? 0x7ffUL : 0x1fffUL) - #define MMAP_RND_MASK (is_compat_task() ? 0x7ffUL : 0x3ff80UL) - #define MMAP_ALIGN_MASK (is_compat_task() ? 0 : 0x7fUL) - #define STACK_RND_MASK MMAP_RND_MASK -diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c -index 0ad96c647541..7017a81d53cf 100644 ---- a/drivers/ata/libata-zpodd.c -+++ b/drivers/ata/libata-zpodd.c -@@ -51,38 +51,52 @@ static int eject_tray(struct ata_device *dev) - /* Per the spec, only slot type and drawer type ODD can be supported */ - static enum odd_mech_type zpodd_get_mech_type(struct ata_device *dev) - { -- char buf[16]; -+ char *buf; - unsigned int ret; -- struct rm_feature_desc *desc = (void *)(buf + 8); -+ struct rm_feature_desc *desc; - struct ata_taskfile tf; - static const char cdb[] = { GPCMD_GET_CONFIGURATION, - 2, /* only 1 feature descriptor requested */ - 0, 3, /* 3, removable medium feature */ - 0, 0, 0,/* reserved */ -- 0, sizeof(buf), -+ 0, 16, - 0, 0, 0, - }; - -+ buf = kzalloc(16, GFP_KERNEL); -+ if (!buf) -+ return ODD_MECH_TYPE_UNSUPPORTED; -+ desc = (void *)(buf + 8); -+ - ata_tf_init(dev, &tf); - tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; - tf.command = ATA_CMD_PACKET; - tf.protocol = ATAPI_PROT_PIO; -- tf.lbam = sizeof(buf); -+ tf.lbam = 16; - - ret = ata_exec_internal(dev, &tf, cdb, DMA_FROM_DEVICE, -- buf, sizeof(buf), 0); -- if (ret) -+ buf, 16, 0); -+ if (ret) { -+ kfree(buf); - return ODD_MECH_TYPE_UNSUPPORTED; -+ } - -- if (be16_to_cpu(desc->feature_code) != 3) -+ if (be16_to_cpu(desc->feature_code) != 3) { -+ kfree(buf); - return ODD_MECH_TYPE_UNSUPPORTED; -+ } - -- if (desc->mech_type == 0 && desc->load == 0 && desc->eject == 1) -+ if (desc->mech_type == 0 && desc->load == 0 && desc->eject == 1) { -+ kfree(buf); - return ODD_MECH_TYPE_SLOT; -- else if (desc->mech_type == 1 && desc->load == 0 && desc->eject == 1) -+ } else if (desc->mech_type == 1 && desc->load == 0 && -+ desc->eject == 1) { -+ kfree(buf); - return ODD_MECH_TYPE_DRAWER; -- else -+ } else { -+ kfree(buf); - return ODD_MECH_TYPE_UNSUPPORTED; -+ } - } - - /* Test if ODD is zero power ready by sense code */ -diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c -index aac84329c759..b863386be911 100644 ---- a/drivers/gpio/gpiolib-of.c -+++ b/drivers/gpio/gpiolib-of.c -@@ -531,7 +531,13 @@ int of_gpiochip_add(struct gpio_chip *chip) - - of_node_get(chip->of_node); - -- return of_gpiochip_scan_gpios(chip); -+ status = of_gpiochip_scan_gpios(chip); -+ if (status) { -+ of_node_put(chip->of_node); -+ gpiochip_remove_pin_ranges(chip); -+ } -+ -+ return status; - } - - void of_gpiochip_remove(struct gpio_chip *chip) -diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c -index 09a7cffbc46f..896b38f6f9c0 100644 ---- a/drivers/leds/leds-pca9532.c -+++ b/drivers/leds/leds-pca9532.c -@@ -488,6 +488,7 @@ static int pca9532_probe(struct i2c_client *client, - const struct i2c_device_id *id) - { - int devid; -+ const struct of_device_id *of_id; - struct pca9532_data *data = i2c_get_clientdata(client); - struct pca9532_platform_data *pca9532_pdata = - dev_get_platdata(&client->dev); -@@ -503,8 +504,11 @@ static int pca9532_probe(struct i2c_client *client, - dev_err(&client->dev, "no platform data\n"); - return -EINVAL; - } -- devid = (int)(uintptr_t)of_match_device( -- of_pca9532_leds_match, &client->dev)->data; -+ of_id = of_match_device(of_pca9532_leds_match, -+ &client->dev); -+ if (unlikely(!of_id)) -+ return -EINVAL; -+ devid = (int)(uintptr_t) of_id->data; - } else { - devid = id->driver_data; - } -diff --git a/drivers/media/platform/vivid/vivid-vid-common.c b/drivers/media/platform/vivid/vivid-vid-common.c -index f9a810e3f521..5f052189a6c4 100644 ---- a/drivers/media/platform/vivid/vivid-vid-common.c -+++ b/drivers/media/platform/vivid/vivid-vid-common.c -@@ -841,6 +841,7 @@ int vidioc_g_edid(struct file *file, void *_fh, - if (edid->start_block + edid->blocks > dev->edid_blocks) - edid->blocks = dev->edid_blocks - edid->start_block; - memcpy(edid->edid, dev->edid, edid->blocks * 128); -- cec_set_edid_phys_addr(edid->edid, edid->blocks * 128, adap->phys_addr); -+ if (adap) -+ cec_set_edid_phys_addr(edid->edid, edid->blocks * 128, adap->phys_addr); - return 0; - } -diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c -index bd719e25dd76..2dd17e01e3a7 100644 ---- a/drivers/net/ethernet/ibm/ehea/ehea_main.c -+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c -@@ -3184,6 +3184,7 @@ static ssize_t ehea_probe_port(struct device *dev, - - if (ehea_add_adapter_mr(adapter)) { - pr_err("creating MR failed\n"); -+ of_node_put(eth_dn); - return -EIO; - } - -diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c -index 1edc973df4c4..7377dca6eb57 100644 ---- a/drivers/net/ethernet/micrel/ks8851.c -+++ b/drivers/net/ethernet/micrel/ks8851.c -@@ -547,9 +547,8 @@ static void ks8851_rx_pkts(struct ks8851_net *ks) - /* set dma read address */ - ks8851_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI | 0x00); - -- /* start the packet dma process, and set auto-dequeue rx */ -- ks8851_wrreg16(ks, KS_RXQCR, -- ks->rc_rxqcr | RXQCR_SDA | RXQCR_ADRFE); -+ /* start DMA access */ -+ ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); - - if (rxlen > 4) { - unsigned int rxalign; -@@ -580,7 +579,8 @@ static void ks8851_rx_pkts(struct ks8851_net *ks) - } - } - -- ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr); -+ /* end DMA access and dequeue packet */ -+ ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_RRXEF); - } - } - -@@ -797,6 +797,15 @@ static void ks8851_tx_work(struct work_struct *work) - static int ks8851_net_open(struct net_device *dev) - { - struct ks8851_net *ks = netdev_priv(dev); -+ int ret; -+ -+ ret = request_threaded_irq(dev->irq, NULL, ks8851_irq, -+ IRQF_TRIGGER_LOW | IRQF_ONESHOT, -+ dev->name, ks); -+ if (ret < 0) { -+ netdev_err(dev, "failed to get irq\n"); -+ return ret; -+ } - - /* lock the card, even if we may not actually be doing anything - * else at the moment */ -@@ -861,6 +870,7 @@ static int ks8851_net_open(struct net_device *dev) - netif_dbg(ks, ifup, ks->netdev, "network device up\n"); - - mutex_unlock(&ks->lock); -+ mii_check_link(&ks->mii); - return 0; - } - -@@ -911,6 +921,8 @@ static int ks8851_net_stop(struct net_device *dev) - dev_kfree_skb(txb); - } - -+ free_irq(dev->irq, ks); -+ - return 0; - } - -@@ -1516,6 +1528,7 @@ static int ks8851_probe(struct spi_device *spi) - - spi_set_drvdata(spi, ks); - -+ netif_carrier_off(ks->netdev); - ndev->if_port = IF_PORT_100BASET; - ndev->netdev_ops = &ks8851_netdev_ops; - ndev->irq = spi->irq; -@@ -1542,14 +1555,6 @@ static int ks8851_probe(struct spi_device *spi) - ks8851_read_selftest(ks); - ks8851_init_mac(ks); - -- ret = request_threaded_irq(spi->irq, NULL, ks8851_irq, -- IRQF_TRIGGER_LOW | IRQF_ONESHOT, -- ndev->name, ks); -- if (ret < 0) { -- dev_err(&spi->dev, "failed to get irq\n"); -- goto err_irq; -- } -- - ret = register_netdev(ndev); - if (ret) { - dev_err(&spi->dev, "failed to register network device\n"); -@@ -1562,14 +1567,10 @@ static int ks8851_probe(struct spi_device *spi) - - return 0; - -- - err_netdev: -- free_irq(ndev->irq, ks); -- --err_irq: -+err_id: - if (gpio_is_valid(gpio)) - gpio_set_value(gpio, 0); --err_id: - regulator_disable(ks->vdd_reg); - err_reg: - regulator_disable(ks->vdd_io); -@@ -1587,7 +1588,6 @@ static int ks8851_remove(struct spi_device *spi) - dev_info(&spi->dev, "remove\n"); - - unregister_netdev(priv->netdev); -- free_irq(spi->irq, priv); - if (gpio_is_valid(priv->gpio)) - gpio_set_value(priv->gpio, 0); - regulator_disable(priv->vdd_reg); -diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c -index 0a2318cad34d..63ebc491057b 100644 ---- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c -+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c -@@ -1038,6 +1038,8 @@ int qlcnic_do_lb_test(struct qlcnic_adapter *adapter, u8 mode) - - for (i = 0; i < QLCNIC_NUM_ILB_PKT; i++) { - skb = netdev_alloc_skb(adapter->netdev, QLCNIC_ILB_PKT_SIZE); -+ if (!skb) -+ break; - qlcnic_create_loopback_buff(skb->data, adapter->mac_addr); - skb_put(skb, QLCNIC_ILB_PKT_SIZE); - adapter->ahw->diag_cnt = 0; -diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c -index d543298d6750..ff24524e7f46 100644 ---- a/drivers/net/ethernet/ti/netcp_ethss.c -+++ b/drivers/net/ethernet/ti/netcp_ethss.c -@@ -3122,12 +3122,16 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, - - ret = netcp_txpipe_init(&gbe_dev->tx_pipe, netcp_device, - gbe_dev->dma_chan_name, gbe_dev->tx_queue_id); -- if (ret) -+ if (ret) { -+ of_node_put(interfaces); - return ret; -+ } - - ret = netcp_txpipe_open(&gbe_dev->tx_pipe); -- if (ret) -+ if (ret) { -+ of_node_put(interfaces); - return ret; -+ } - - /* Create network interfaces */ - INIT_LIST_HEAD(&gbe_dev->gbe_intf_head); -diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c -index c688d68c39aa..a8afc92cbfca 100644 ---- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c -+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c -@@ -1548,12 +1548,14 @@ static int axienet_probe(struct platform_device *pdev) - ret = of_address_to_resource(np, 0, &dmares); - if (ret) { - dev_err(&pdev->dev, "unable to get DMA resource\n"); -+ of_node_put(np); - goto free_netdev; - } - lp->dma_regs = devm_ioremap_resource(&pdev->dev, &dmares); - if (IS_ERR(lp->dma_regs)) { - dev_err(&pdev->dev, "could not map DMA regs\n"); - ret = PTR_ERR(lp->dma_regs); -+ of_node_put(np); - goto free_netdev; - } - lp->rx_irq = irq_of_parse_and_map(np, 1); -diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c -index f1f8227e7342..01f95d192d25 100644 ---- a/drivers/net/usb/ipheth.c -+++ b/drivers/net/usb/ipheth.c -@@ -148,6 +148,7 @@ struct ipheth_device { - u8 bulk_in; - u8 bulk_out; - struct delayed_work carrier_work; -+ bool confirmed_pairing; - }; - - static int ipheth_rx_submit(struct ipheth_device *dev, gfp_t mem_flags); -@@ -259,7 +260,7 @@ static void ipheth_rcvbulk_callback(struct urb *urb) - - dev->net->stats.rx_packets++; - dev->net->stats.rx_bytes += len; -- -+ dev->confirmed_pairing = true; - netif_rx(skb); - ipheth_rx_submit(dev, GFP_ATOMIC); - } -@@ -280,14 +281,24 @@ static void ipheth_sndbulk_callback(struct urb *urb) - dev_err(&dev->intf->dev, "%s: urb status: %d\n", - __func__, status); - -- netif_wake_queue(dev->net); -+ if (status == 0) -+ netif_wake_queue(dev->net); -+ else -+ // on URB error, trigger immediate poll -+ schedule_delayed_work(&dev->carrier_work, 0); - } - - static int ipheth_carrier_set(struct ipheth_device *dev) - { -- struct usb_device *udev = dev->udev; -+ struct usb_device *udev; - int retval; - -+ if (!dev) -+ return 0; -+ if (!dev->confirmed_pairing) -+ return 0; -+ -+ udev = dev->udev; - retval = usb_control_msg(udev, - usb_rcvctrlpipe(udev, IPHETH_CTRL_ENDP), - IPHETH_CMD_CARRIER_CHECK, /* request */ -@@ -302,11 +313,14 @@ static int ipheth_carrier_set(struct ipheth_device *dev) - return retval; - } - -- if (dev->ctrl_buf[0] == IPHETH_CARRIER_ON) -+ if (dev->ctrl_buf[0] == IPHETH_CARRIER_ON) { - netif_carrier_on(dev->net); -- else -+ if (dev->tx_urb->status != -EINPROGRESS) -+ netif_wake_queue(dev->net); -+ } else { - netif_carrier_off(dev->net); -- -+ netif_stop_queue(dev->net); -+ } - return 0; - } - -@@ -386,7 +400,6 @@ static int ipheth_open(struct net_device *net) - return retval; - - schedule_delayed_work(&dev->carrier_work, IPHETH_CARRIER_CHECK_TIMEOUT); -- netif_start_queue(net); - return retval; - } - -@@ -489,7 +502,7 @@ static int ipheth_probe(struct usb_interface *intf, - dev->udev = udev; - dev->net = netdev; - dev->intf = intf; -- -+ dev->confirmed_pairing = false; - /* Set up endpoints */ - hintf = usb_altnum_to_altsetting(intf, IPHETH_ALT_INTFNUM); - if (hintf == NULL) { -@@ -540,7 +553,9 @@ static int ipheth_probe(struct usb_interface *intf, - retval = -EIO; - goto err_register_netdev; - } -- -+ // carrier down and transmit queues stopped until packet from device -+ netif_carrier_off(netdev); -+ netif_tx_stop_all_queues(netdev); - dev_info(&intf->dev, "Apple iPhone USB Ethernet device attached\n"); - return 0; - -diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c -index 237688af179b..f7630cf581cd 100644 ---- a/drivers/s390/scsi/zfcp_fc.c -+++ b/drivers/s390/scsi/zfcp_fc.c -@@ -238,10 +238,6 @@ static void _zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req, u32 range, - list_for_each_entry(port, &adapter->port_list, list) { - if ((port->d_id & range) == (ntoh24(page->rscn_fid) & range)) - zfcp_fc_test_link(port); -- if (!port->d_id) -- zfcp_erp_port_reopen(port, -- ZFCP_STATUS_COMMON_ERP_FAILED, -- "fcrscn1"); - } - read_unlock_irqrestore(&adapter->port_list_lock, flags); - } -@@ -249,6 +245,7 @@ static void _zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req, u32 range, - static void zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req) - { - struct fsf_status_read_buffer *status_buffer = (void *)fsf_req->data; -+ struct zfcp_adapter *adapter = fsf_req->adapter; - struct fc_els_rscn *head; - struct fc_els_rscn_page *page; - u16 i; -@@ -261,6 +258,22 @@ static void zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req) - /* see FC-FS */ - no_entries = head->rscn_plen / sizeof(struct fc_els_rscn_page); - -+ if (no_entries > 1) { -+ /* handle failed ports */ -+ unsigned long flags; -+ struct zfcp_port *port; -+ -+ read_lock_irqsave(&adapter->port_list_lock, flags); -+ list_for_each_entry(port, &adapter->port_list, list) { -+ if (port->d_id) -+ continue; -+ zfcp_erp_port_reopen(port, -+ ZFCP_STATUS_COMMON_ERP_FAILED, -+ "fcrscn1"); -+ } -+ read_unlock_irqrestore(&adapter->port_list_lock, flags); -+ } -+ - for (i = 1; i < no_entries; i++) { - /* skip head and start with 1st element */ - page++; -diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c -index f9f899ec9427..c158967b59d7 100644 ---- a/drivers/scsi/qla4xxx/ql4_os.c -+++ b/drivers/scsi/qla4xxx/ql4_os.c -@@ -3207,6 +3207,8 @@ static int qla4xxx_conn_bind(struct iscsi_cls_session *cls_session, - if (iscsi_conn_bind(cls_session, cls_conn, is_leading)) - return -EINVAL; - ep = iscsi_lookup_endpoint(transport_fd); -+ if (!ep) -+ return -EINVAL; - conn = cls_conn->dd_data; - qla_conn = conn->dd_data; - qla_conn->qla_ep = ep->dd_data; -diff --git a/drivers/staging/rtl8712/rtl8712_cmd.c b/drivers/staging/rtl8712/rtl8712_cmd.c -index 9f61583af150..41b667c8385c 100644 ---- a/drivers/staging/rtl8712/rtl8712_cmd.c -+++ b/drivers/staging/rtl8712/rtl8712_cmd.c -@@ -158,17 +158,9 @@ static u8 write_macreg_hdl(struct _adapter *padapter, u8 *pbuf) - - static u8 read_bbreg_hdl(struct _adapter *padapter, u8 *pbuf) - { -- u32 val; -- void (*pcmd_callback)(struct _adapter *dev, struct cmd_obj *pcmd); - struct cmd_obj *pcmd = (struct cmd_obj *)pbuf; - -- if (pcmd->rsp && pcmd->rspsz > 0) -- memcpy(pcmd->rsp, (u8 *)&val, pcmd->rspsz); -- pcmd_callback = cmd_callback[pcmd->cmdcode].callback; -- if (!pcmd_callback) -- r8712_free_cmd_obj(pcmd); -- else -- pcmd_callback(padapter, pcmd); -+ r8712_free_cmd_obj(pcmd); - return H2C_SUCCESS; - } - -diff --git a/drivers/staging/rtl8712/rtl8712_cmd.h b/drivers/staging/rtl8712/rtl8712_cmd.h -index 67e9e910aef9..d10a59d4a550 100644 ---- a/drivers/staging/rtl8712/rtl8712_cmd.h -+++ b/drivers/staging/rtl8712/rtl8712_cmd.h -@@ -152,7 +152,7 @@ enum rtl8712_h2c_cmd { - static struct _cmd_callback cmd_callback[] = { - {GEN_CMD_CODE(_Read_MACREG), NULL}, /*0*/ - {GEN_CMD_CODE(_Write_MACREG), NULL}, -- {GEN_CMD_CODE(_Read_BBREG), &r8712_getbbrfreg_cmdrsp_callback}, -+ {GEN_CMD_CODE(_Read_BBREG), NULL}, - {GEN_CMD_CODE(_Write_BBREG), NULL}, - {GEN_CMD_CODE(_Read_RFREG), &r8712_getbbrfreg_cmdrsp_callback}, - {GEN_CMD_CODE(_Write_RFREG), NULL}, /*5*/ -diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c -index 73137f4aac20..d4462512605b 100644 ---- a/drivers/tty/serial/ar933x_uart.c -+++ b/drivers/tty/serial/ar933x_uart.c -@@ -52,11 +52,6 @@ struct ar933x_uart_port { - struct clk *clk; - }; - --static inline bool ar933x_uart_console_enabled(void) --{ -- return IS_ENABLED(CONFIG_SERIAL_AR933X_CONSOLE); --} -- - static inline unsigned int ar933x_uart_read(struct ar933x_uart_port *up, - int offset) - { -@@ -511,6 +506,7 @@ static struct uart_ops ar933x_uart_ops = { - .verify_port = ar933x_uart_verify_port, - }; - -+#ifdef CONFIG_SERIAL_AR933X_CONSOLE - static struct ar933x_uart_port * - ar933x_console_ports[CONFIG_SERIAL_AR933X_NR_UARTS]; - -@@ -607,14 +603,7 @@ static struct console ar933x_uart_console = { - .index = -1, - .data = &ar933x_uart_driver, - }; -- --static void ar933x_uart_add_console_port(struct ar933x_uart_port *up) --{ -- if (!ar933x_uart_console_enabled()) -- return; -- -- ar933x_console_ports[up->port.line] = up; --} -+#endif /* CONFIG_SERIAL_AR933X_CONSOLE */ - - static struct uart_driver ar933x_uart_driver = { - .owner = THIS_MODULE, -@@ -703,7 +692,9 @@ static int ar933x_uart_probe(struct platform_device *pdev) - baud = ar933x_uart_get_baud(port->uartclk, 0, AR933X_UART_MAX_STEP); - up->max_baud = min_t(unsigned int, baud, AR933X_UART_MAX_BAUD); - -- ar933x_uart_add_console_port(up); -+#ifdef CONFIG_SERIAL_AR933X_CONSOLE -+ ar933x_console_ports[up->port.line] = up; -+#endif - - ret = uart_add_one_port(&ar933x_uart_driver, &up->port); - if (ret) -@@ -752,8 +743,9 @@ static int __init ar933x_uart_init(void) - { - int ret; - -- if (ar933x_uart_console_enabled()) -- ar933x_uart_driver.cons = &ar933x_uart_console; -+#ifdef CONFIG_SERIAL_AR933X_CONSOLE -+ ar933x_uart_driver.cons = &ar933x_uart_console; -+#endif - - ret = uart_register_driver(&ar933x_uart_driver); - if (ret) -diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c -index ea6b62cece88..82451bb6622b 100644 ---- a/drivers/tty/serial/sc16is7xx.c -+++ b/drivers/tty/serial/sc16is7xx.c -@@ -1482,7 +1482,7 @@ static int __init sc16is7xx_init(void) - ret = i2c_add_driver(&sc16is7xx_i2c_uart_driver); - if (ret < 0) { - pr_err("failed to init sc16is7xx i2c --> %d\n", ret); -- return ret; -+ goto err_i2c; - } - #endif - -@@ -1490,10 +1490,18 @@ static int __init sc16is7xx_init(void) - ret = spi_register_driver(&sc16is7xx_spi_uart_driver); - if (ret < 0) { - pr_err("failed to init sc16is7xx spi --> %d\n", ret); -- return ret; -+ goto err_spi; - } - #endif - return ret; -+ -+err_spi: -+#ifdef CONFIG_SERIAL_SC16IS7XX_I2C -+ i2c_del_driver(&sc16is7xx_i2c_uart_driver); -+#endif -+err_i2c: -+ uart_unregister_driver(&sc16is7xx_uart); -+ return ret; - } - module_init(sc16is7xx_init); - -diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c -index 40396a265a3f..f57d293a1791 100644 ---- a/drivers/usb/gadget/udc/net2272.c -+++ b/drivers/usb/gadget/udc/net2272.c -@@ -958,6 +958,7 @@ net2272_dequeue(struct usb_ep *_ep, struct usb_request *_req) - break; - } - if (&req->req != _req) { -+ ep->stopped = stopped; - spin_unlock_irqrestore(&ep->dev->lock, flags); - return -EINVAL; - } -diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c -index 7a8c36642293..dfaed8e8cc52 100644 ---- a/drivers/usb/gadget/udc/net2280.c -+++ b/drivers/usb/gadget/udc/net2280.c -@@ -870,9 +870,6 @@ static void start_queue(struct net2280_ep *ep, u32 dmactl, u32 td_dma) - (void) readl(&ep->dev->pci->pcimstctl); - - writel(BIT(DMA_START), &dma->dmastat); -- -- if (!ep->is_in) -- stop_out_naking(ep); - } - - static void start_dma(struct net2280_ep *ep, struct net2280_request *req) -@@ -911,6 +908,7 @@ static void start_dma(struct net2280_ep *ep, struct net2280_request *req) - writel(BIT(DMA_START), &dma->dmastat); - return; - } -+ stop_out_naking(ep); - } - - tmp = dmactl_default; -@@ -1279,9 +1277,9 @@ static int net2280_dequeue(struct usb_ep *_ep, struct usb_request *_req) - break; - } - if (&req->req != _req) { -+ ep->stopped = stopped; - spin_unlock_irqrestore(&ep->dev->lock, flags); -- dev_err(&ep->dev->pdev->dev, "%s: Request mismatch\n", -- __func__); -+ ep_dbg(ep->dev, "%s: Request mismatch\n", __func__); - return -EINVAL; - } - -diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c -index 43618976d68a..3efb7b0e8269 100644 ---- a/drivers/usb/host/u132-hcd.c -+++ b/drivers/usb/host/u132-hcd.c -@@ -3208,6 +3208,9 @@ static int __init u132_hcd_init(void) - printk(KERN_INFO "driver %s\n", hcd_name); - workqueue = create_singlethread_workqueue("u132"); - retval = platform_driver_register(&u132_platform_driver); -+ if (retval) -+ destroy_workqueue(workqueue); -+ - return retval; - } - -diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c -index 1d48e62f4f52..0d5b667c0e65 100644 ---- a/drivers/vfio/vfio_iommu_type1.c -+++ b/drivers/vfio/vfio_iommu_type1.c -@@ -53,10 +53,16 @@ module_param_named(disable_hugepages, - MODULE_PARM_DESC(disable_hugepages, - "Disable VFIO IOMMU support for IOMMU hugepages."); - -+static unsigned int dma_entry_limit __read_mostly = U16_MAX; -+module_param_named(dma_entry_limit, dma_entry_limit, uint, 0644); -+MODULE_PARM_DESC(dma_entry_limit, -+ "Maximum number of user DMA mappings per container (65535)."); -+ - struct vfio_iommu { - struct list_head domain_list; - struct mutex lock; - struct rb_root dma_list; -+ unsigned int dma_avail; - bool v2; - bool nesting; - }; -@@ -384,6 +390,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma) - vfio_unmap_unpin(iommu, dma); - vfio_unlink_dma(iommu, dma); - kfree(dma); -+ iommu->dma_avail++; - } - - static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu) -@@ -584,12 +591,18 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu, - return -EEXIST; - } - -+ if (!iommu->dma_avail) { -+ mutex_unlock(&iommu->lock); -+ return -ENOSPC; -+ } -+ - dma = kzalloc(sizeof(*dma), GFP_KERNEL); - if (!dma) { - mutex_unlock(&iommu->lock); - return -ENOMEM; - } - -+ iommu->dma_avail--; - dma->iova = iova; - dma->vaddr = vaddr; - dma->prot = prot; -@@ -905,6 +918,7 @@ static void *vfio_iommu_type1_open(unsigned long arg) - - INIT_LIST_HEAD(&iommu->domain_list); - iommu->dma_list = RB_ROOT; -+ iommu->dma_avail = dma_entry_limit; - mutex_init(&iommu->lock); - - return iommu; -diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c -index 30d9d9e7057d..7a4052501866 100644 ---- a/fs/ceph/inode.c -+++ b/fs/ceph/inode.c -@@ -523,6 +523,7 @@ static void ceph_i_callback(struct rcu_head *head) - struct inode *inode = container_of(head, struct inode, i_rcu); - struct ceph_inode_info *ci = ceph_inode(inode); - -+ kfree(ci->i_symlink); - kmem_cache_free(ceph_inode_cachep, ci); - } - -@@ -554,7 +555,6 @@ void ceph_destroy_inode(struct inode *inode) - ceph_put_snap_realm(mdsc, realm); - } - -- kfree(ci->i_symlink); - while ((n = rb_first(&ci->i_fragtree)) != NULL) { - frag = rb_entry(n, struct ceph_inode_frag, node); - rb_erase(n, &ci->i_fragtree); -diff --git a/fs/nfs/client.c b/fs/nfs/client.c -index ebecfb8fba06..28d8a57a9908 100644 ---- a/fs/nfs/client.c -+++ b/fs/nfs/client.c -@@ -440,7 +440,7 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto, - case XPRT_TRANSPORT_RDMA: - if (retrans == NFS_UNSPEC_RETRANS) - to->to_retries = NFS_DEF_TCP_RETRANS; -- if (timeo == NFS_UNSPEC_TIMEO || to->to_retries == 0) -+ if (timeo == NFS_UNSPEC_TIMEO || to->to_initval == 0) - to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10; - if (to->to_initval > NFS_MAX_TCP_TIMEOUT) - to->to_initval = NFS_MAX_TCP_TIMEOUT; -diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c -index 38865deab3ac..0c96773d1829 100644 ---- a/net/bridge/br_netfilter_hooks.c -+++ b/net/bridge/br_netfilter_hooks.c -@@ -512,6 +512,7 @@ static unsigned int br_nf_pre_routing(void *priv, - nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr; - - skb->protocol = htons(ETH_P_IP); -+ skb->transport_header = skb->network_header + ip_hdr(skb)->ihl * 4; - - NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->net, state->sk, skb, - skb->dev, NULL, -diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c -index a1b57cb07f1e..8c08dd07419f 100644 ---- a/net/bridge/br_netfilter_ipv6.c -+++ b/net/bridge/br_netfilter_ipv6.c -@@ -235,6 +235,8 @@ unsigned int br_nf_pre_routing_ipv6(void *priv, - nf_bridge->ipv6_daddr = ipv6_hdr(skb)->daddr; - - skb->protocol = htons(ETH_P_IPV6); -+ skb->transport_header = skb->network_header + sizeof(struct ipv6hdr); -+ - NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->net, state->sk, skb, - skb->dev, NULL, - br_nf_pre_routing_finish_ipv6); -diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c -index 93820e0d8814..4ee8acded0a4 100644 ---- a/net/netfilter/nft_set_rbtree.c -+++ b/net/netfilter/nft_set_rbtree.c -@@ -191,10 +191,6 @@ static void *nft_rbtree_deactivate(const struct net *net, - else if (d > 0) - parent = parent->rb_right; - else { -- if (!nft_set_elem_active(&rbe->ext, genmask)) { -- parent = parent->rb_left; -- continue; -- } - if (nft_rbtree_interval_end(rbe) && - !nft_rbtree_interval_end(this)) { - parent = parent->rb_left; -@@ -203,6 +199,9 @@ static void *nft_rbtree_deactivate(const struct net *net, - nft_rbtree_interval_end(this)) { - parent = parent->rb_right; - continue; -+ } else if (!nft_set_elem_active(&rbe->ext, genmask)) { -+ parent = parent->rb_left; -+ continue; - } - nft_set_elem_change_active(net, set, &rbe->ext); - return rbe; -diff --git a/scripts/kconfig/lxdialog/inputbox.c b/scripts/kconfig/lxdialog/inputbox.c -index d58de1dc5360..510049a7bd1d 100644 ---- a/scripts/kconfig/lxdialog/inputbox.c -+++ b/scripts/kconfig/lxdialog/inputbox.c -@@ -126,7 +126,8 @@ do_resize: - case KEY_DOWN: - break; - case KEY_BACKSPACE: -- case 127: -+ case 8: /* ^H */ -+ case 127: /* ^? */ - if (pos) { - wattrset(dialog, dlg.inputbox.atr); - if (input_x == 0) { -diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c -index d42d534a66cd..f7049e288e93 100644 ---- a/scripts/kconfig/nconf.c -+++ b/scripts/kconfig/nconf.c -@@ -1046,7 +1046,7 @@ static int do_match(int key, struct match_state *state, int *ans) - state->match_direction = FIND_NEXT_MATCH_UP; - *ans = get_mext_match(state->pattern, - state->match_direction); -- } else if (key == KEY_BACKSPACE || key == 127) { -+ } else if (key == KEY_BACKSPACE || key == 8 || key == 127) { - state->pattern[strlen(state->pattern)-1] = '\0'; - adj_match_dir(&state->match_direction); - } else -diff --git a/scripts/kconfig/nconf.gui.c b/scripts/kconfig/nconf.gui.c -index 4b2f44c20caf..9a65035cf787 100644 ---- a/scripts/kconfig/nconf.gui.c -+++ b/scripts/kconfig/nconf.gui.c -@@ -439,7 +439,8 @@ int dialog_inputbox(WINDOW *main_window, - case KEY_F(F_EXIT): - case KEY_F(F_BACK): - break; -- case 127: -+ case 8: /* ^H */ -+ case 127: /* ^? */ - case KEY_BACKSPACE: - if (cursor_position > 0) { - memmove(&result[cursor_position-1], diff --git a/patch/kernel/odroidn2-default/patch-4.9.173-174.patch.disabled b/patch/kernel/odroidn2-default/patch-4.9.173-174.patch.disabled deleted file mode 100644 index 076ee1a773..0000000000 --- a/patch/kernel/odroidn2-default/patch-4.9.173-174.patch.disabled +++ /dev/null @@ -1,2517 +0,0 @@ -diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt -index 0a94ffe17ab6..b13e031beaa6 100644 ---- a/Documentation/usb/power-management.txt -+++ b/Documentation/usb/power-management.txt -@@ -365,11 +365,15 @@ autosuspend the interface's device. When the usage counter is = 0 - then the interface is considered to be idle, and the kernel may - autosuspend the device. - --Drivers need not be concerned about balancing changes to the usage --counter; the USB core will undo any remaining "get"s when a driver --is unbound from its interface. As a corollary, drivers must not call --any of the usb_autopm_* functions after their disconnect() routine has --returned. -+Drivers must be careful to balance their overall changes to the usage -+counter. Unbalanced "get"s will remain in effect when a driver is -+unbound from its interface, preventing the device from going into -+runtime suspend should the interface be bound to a driver again. On -+the other hand, drivers are allowed to achieve this balance by calling -+the ``usb_autopm_*`` functions even after their ``disconnect`` routine -+has returned -- say from within a work-queue routine -- provided they -+retain an active reference to the interface (via ``usb_get_intf`` and -+``usb_put_intf``). - - Drivers using the async routines are responsible for their own - synchronization and mutual exclusion. -diff --git a/Makefile b/Makefile -index a4e35453f9e4..f5836837df15 100644 ---- a/Makefile -+++ b/Makefile -@@ -1,6 +1,6 @@ - VERSION = 4 - PATCHLEVEL = 9 --SUBLEVEL = 173 -+SUBLEVEL = 174 - EXTRAVERSION = - NAME = Roaring Lionus - -diff --git a/arch/arm/mach-iop13xx/setup.c b/arch/arm/mach-iop13xx/setup.c -index 53c316f7301e..fe4932fda01d 100644 ---- a/arch/arm/mach-iop13xx/setup.c -+++ b/arch/arm/mach-iop13xx/setup.c -@@ -300,7 +300,7 @@ static struct resource iop13xx_adma_2_resources[] = { - } - }; - --static u64 iop13xx_adma_dmamask = DMA_BIT_MASK(64); -+static u64 iop13xx_adma_dmamask = DMA_BIT_MASK(32); - static struct iop_adma_platform_data iop13xx_adma_0_data = { - .hw_id = 0, - .pool_size = PAGE_SIZE, -@@ -324,7 +324,7 @@ static struct platform_device iop13xx_adma_0_channel = { - .resource = iop13xx_adma_0_resources, - .dev = { - .dma_mask = &iop13xx_adma_dmamask, -- .coherent_dma_mask = DMA_BIT_MASK(64), -+ .coherent_dma_mask = DMA_BIT_MASK(32), - .platform_data = (void *) &iop13xx_adma_0_data, - }, - }; -@@ -336,7 +336,7 @@ static struct platform_device iop13xx_adma_1_channel = { - .resource = iop13xx_adma_1_resources, - .dev = { - .dma_mask = &iop13xx_adma_dmamask, -- .coherent_dma_mask = DMA_BIT_MASK(64), -+ .coherent_dma_mask = DMA_BIT_MASK(32), - .platform_data = (void *) &iop13xx_adma_1_data, - }, - }; -@@ -348,7 +348,7 @@ static struct platform_device iop13xx_adma_2_channel = { - .resource = iop13xx_adma_2_resources, - .dev = { - .dma_mask = &iop13xx_adma_dmamask, -- .coherent_dma_mask = DMA_BIT_MASK(64), -+ .coherent_dma_mask = DMA_BIT_MASK(32), - .platform_data = (void *) &iop13xx_adma_2_data, - }, - }; -diff --git a/arch/arm/mach-iop13xx/tpmi.c b/arch/arm/mach-iop13xx/tpmi.c -index db511ec2b1df..116feb6b261e 100644 ---- a/arch/arm/mach-iop13xx/tpmi.c -+++ b/arch/arm/mach-iop13xx/tpmi.c -@@ -152,7 +152,7 @@ static struct resource iop13xx_tpmi_3_resources[] = { - } - }; - --u64 iop13xx_tpmi_mask = DMA_BIT_MASK(64); -+u64 iop13xx_tpmi_mask = DMA_BIT_MASK(32); - static struct platform_device iop13xx_tpmi_0_device = { - .name = "iop-tpmi", - .id = 0, -@@ -160,7 +160,7 @@ static struct platform_device iop13xx_tpmi_0_device = { - .resource = iop13xx_tpmi_0_resources, - .dev = { - .dma_mask = &iop13xx_tpmi_mask, -- .coherent_dma_mask = DMA_BIT_MASK(64), -+ .coherent_dma_mask = DMA_BIT_MASK(32), - }, - }; - -@@ -171,7 +171,7 @@ static struct platform_device iop13xx_tpmi_1_device = { - .resource = iop13xx_tpmi_1_resources, - .dev = { - .dma_mask = &iop13xx_tpmi_mask, -- .coherent_dma_mask = DMA_BIT_MASK(64), -+ .coherent_dma_mask = DMA_BIT_MASK(32), - }, - }; - -@@ -182,7 +182,7 @@ static struct platform_device iop13xx_tpmi_2_device = { - .resource = iop13xx_tpmi_2_resources, - .dev = { - .dma_mask = &iop13xx_tpmi_mask, -- .coherent_dma_mask = DMA_BIT_MASK(64), -+ .coherent_dma_mask = DMA_BIT_MASK(32), - }, - }; - -@@ -193,7 +193,7 @@ static struct platform_device iop13xx_tpmi_3_device = { - .resource = iop13xx_tpmi_3_resources, - .dev = { - .dma_mask = &iop13xx_tpmi_mask, -- .coherent_dma_mask = DMA_BIT_MASK(64), -+ .coherent_dma_mask = DMA_BIT_MASK(32), - }, - }; - -diff --git a/arch/arm/plat-iop/adma.c b/arch/arm/plat-iop/adma.c -index a4d1f8de3b5b..d9612221e484 100644 ---- a/arch/arm/plat-iop/adma.c -+++ b/arch/arm/plat-iop/adma.c -@@ -143,7 +143,7 @@ struct platform_device iop3xx_dma_0_channel = { - .resource = iop3xx_dma_0_resources, - .dev = { - .dma_mask = &iop3xx_adma_dmamask, -- .coherent_dma_mask = DMA_BIT_MASK(64), -+ .coherent_dma_mask = DMA_BIT_MASK(32), - .platform_data = (void *) &iop3xx_dma_0_data, - }, - }; -@@ -155,7 +155,7 @@ struct platform_device iop3xx_dma_1_channel = { - .resource = iop3xx_dma_1_resources, - .dev = { - .dma_mask = &iop3xx_adma_dmamask, -- .coherent_dma_mask = DMA_BIT_MASK(64), -+ .coherent_dma_mask = DMA_BIT_MASK(32), - .platform_data = (void *) &iop3xx_dma_1_data, - }, - }; -@@ -167,7 +167,7 @@ struct platform_device iop3xx_aau_channel = { - .resource = iop3xx_aau_resources, - .dev = { - .dma_mask = &iop3xx_adma_dmamask, -- .coherent_dma_mask = DMA_BIT_MASK(64), -+ .coherent_dma_mask = DMA_BIT_MASK(32), - .platform_data = (void *) &iop3xx_aau_data, - }, - }; -diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c -index 272f49b2c68f..bb29e6ebdc0d 100644 ---- a/arch/arm/plat-orion/common.c -+++ b/arch/arm/plat-orion/common.c -@@ -605,7 +605,7 @@ static struct platform_device orion_xor0_shared = { - .resource = orion_xor0_shared_resources, - .dev = { - .dma_mask = &orion_xor_dmamask, -- .coherent_dma_mask = DMA_BIT_MASK(64), -+ .coherent_dma_mask = DMA_BIT_MASK(32), - .platform_data = &orion_xor0_pdata, - }, - }; -@@ -666,7 +666,7 @@ static struct platform_device orion_xor1_shared = { - .resource = orion_xor1_shared_resources, - .dev = { - .dma_mask = &orion_xor_dmamask, -- .coherent_dma_mask = DMA_BIT_MASK(64), -+ .coherent_dma_mask = DMA_BIT_MASK(32), - .platform_data = &orion_xor1_pdata, - }, - }; -diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h -index bc812435bc76..d0beefeb6d25 100644 ---- a/arch/arm64/include/asm/system_misc.h -+++ b/arch/arm64/include/asm/system_misc.h -@@ -40,7 +40,7 @@ void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned int, - int sig, int code, const char *name); - - struct mm_struct; --extern void show_pte(struct mm_struct *mm, unsigned long addr); -+extern void show_pte(unsigned long addr); - extern void __show_regs(struct pt_regs *); - - extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd); -diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c -index 051b32084776..575c11a6f9b6 100644 ---- a/arch/arm64/mm/fault.c -+++ b/arch/arm64/mm/fault.c -@@ -79,18 +79,33 @@ static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr) - #endif - - /* -- * Dump out the page tables associated with 'addr' in mm 'mm'. -+ * Dump out the page tables associated with 'addr' in the currently active mm. - */ --void show_pte(struct mm_struct *mm, unsigned long addr) -+void show_pte(unsigned long addr) - { -+ struct mm_struct *mm; - pgd_t *pgd; - -- if (!mm) -+ if (addr < TASK_SIZE) { -+ /* TTBR0 */ -+ mm = current->active_mm; -+ if (mm == &init_mm) { -+ pr_alert("[%016lx] user address but active_mm is swapper\n", -+ addr); -+ return; -+ } -+ } else if (addr >= VA_START) { -+ /* TTBR1 */ - mm = &init_mm; -+ } else { -+ pr_alert("[%016lx] address between user and kernel address ranges\n", -+ addr); -+ return; -+ } - - pr_alert("pgd = %p\n", mm->pgd); - pgd = pgd_offset(mm, addr); -- pr_alert("[%08lx] *pgd=%016llx", addr, pgd_val(*pgd)); -+ pr_alert("[%016lx] *pgd=%016llx", addr, pgd_val(*pgd)); - - do { - pud_t *pud; -@@ -176,8 +191,8 @@ static bool is_el1_instruction_abort(unsigned int esr) - /* - * The kernel tried to access some page that wasn't present. - */ --static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr, -- unsigned int esr, struct pt_regs *regs) -+static void __do_kernel_fault(unsigned long addr, unsigned int esr, -+ struct pt_regs *regs) - { - /* - * Are we prepared to handle this kernel fault? -@@ -194,7 +209,7 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr, - (addr < PAGE_SIZE) ? "NULL pointer dereference" : - "paging request", addr); - -- show_pte(mm, addr); -+ show_pte(addr); - die("Oops", regs, esr); - bust_spinlocks(0); - do_exit(SIGKILL); -@@ -216,7 +231,6 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr, - pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n", - tsk->comm, task_pid_nr(tsk), inf->name, sig, - addr, esr); -- show_pte(tsk->mm, addr); - show_regs(regs); - } - -@@ -232,7 +246,6 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr, - static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs) - { - struct task_struct *tsk = current; -- struct mm_struct *mm = tsk->active_mm; - const struct fault_info *inf; - - /* -@@ -243,7 +256,7 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re - inf = esr_to_fault_info(esr); - __do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs); - } else -- __do_kernel_fault(mm, addr, esr, regs); -+ __do_kernel_fault(addr, esr, regs); - } - - #define VM_FAULT_BADMAP 0x010000 -@@ -454,7 +467,7 @@ retry: - return 0; - - no_context: -- __do_kernel_fault(mm, addr, esr, regs); -+ __do_kernel_fault(addr, esr, regs); - return 0; - } - -diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c -index 757009daa9ed..ff43da269fe8 100644 ---- a/arch/arm64/mm/kasan_init.c -+++ b/arch/arm64/mm/kasan_init.c -@@ -153,7 +153,7 @@ void __init kasan_init(void) - clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); - - vmemmap_populate(kimg_shadow_start, kimg_shadow_end, -- pfn_to_nid(virt_to_pfn(_text))); -+ pfn_to_nid(virt_to_pfn(lm_alias(_text)))); - - /* - * vmemmap_populate() has populated the shadow region that covers the -diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S -index 18d96d349a8b..f5fde8d389c9 100644 ---- a/arch/arm64/mm/proc.S -+++ b/arch/arm64/mm/proc.S -@@ -181,7 +181,8 @@ ENDPROC(idmap_cpu_replace_ttbr1) - dc cvac, cur_\()\type\()p // Ensure any existing dirty - dmb sy // lines are written back before - ldr \type, [cur_\()\type\()p] // loading the entry -- tbz \type, #0, next_\()\type // Skip invalid entries -+ tbz \type, #0, skip_\()\type // Skip invalid and -+ tbnz \type, #11, skip_\()\type // non-global entries - .endm - - .macro __idmap_kpti_put_pgtable_ent_ng, type -@@ -241,8 +242,9 @@ ENTRY(idmap_kpti_install_ng_mappings) - add end_pgdp, cur_pgdp, #(PTRS_PER_PGD * 8) - do_pgd: __idmap_kpti_get_pgtable_ent pgd - tbnz pgd, #1, walk_puds -- __idmap_kpti_put_pgtable_ent_ng pgd - next_pgd: -+ __idmap_kpti_put_pgtable_ent_ng pgd -+skip_pgd: - add cur_pgdp, cur_pgdp, #8 - cmp cur_pgdp, end_pgdp - b.ne do_pgd -@@ -270,8 +272,9 @@ walk_puds: - add end_pudp, cur_pudp, #(PTRS_PER_PUD * 8) - do_pud: __idmap_kpti_get_pgtable_ent pud - tbnz pud, #1, walk_pmds -- __idmap_kpti_put_pgtable_ent_ng pud - next_pud: -+ __idmap_kpti_put_pgtable_ent_ng pud -+skip_pud: - add cur_pudp, cur_pudp, 8 - cmp cur_pudp, end_pudp - b.ne do_pud -@@ -290,8 +293,9 @@ walk_pmds: - add end_pmdp, cur_pmdp, #(PTRS_PER_PMD * 8) - do_pmd: __idmap_kpti_get_pgtable_ent pmd - tbnz pmd, #1, walk_ptes -- __idmap_kpti_put_pgtable_ent_ng pmd - next_pmd: -+ __idmap_kpti_put_pgtable_ent_ng pmd -+skip_pmd: - add cur_pmdp, cur_pmdp, #8 - cmp cur_pmdp, end_pmdp - b.ne do_pmd -@@ -309,7 +313,7 @@ walk_ptes: - add end_ptep, cur_ptep, #(PTRS_PER_PTE * 8) - do_pte: __idmap_kpti_get_pgtable_ent pte - __idmap_kpti_put_pgtable_ent_ng pte --next_pte: -+skip_pte: - add cur_ptep, cur_ptep, #8 - cmp cur_ptep, end_ptep - b.ne do_pte -diff --git a/arch/sh/boards/of-generic.c b/arch/sh/boards/of-generic.c -index 1fb6d5714bae..fd00566677c9 100644 ---- a/arch/sh/boards/of-generic.c -+++ b/arch/sh/boards/of-generic.c -@@ -180,10 +180,10 @@ static struct sh_machine_vector __initmv sh_of_generic_mv = { - - struct sh_clk_ops; - --void __init arch_init_clk_ops(struct sh_clk_ops **ops, int idx) -+void __init __weak arch_init_clk_ops(struct sh_clk_ops **ops, int idx) - { - } - --void __init plat_irq_setup(void) -+void __init __weak plat_irq_setup(void) - { - } -diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c -index de050d5a4506..00b56cc69d37 100644 ---- a/arch/x86/events/amd/core.c -+++ b/arch/x86/events/amd/core.c -@@ -112,6 +112,110 @@ static __initconst const u64 amd_hw_cache_event_ids - }, - }; - -+static __initconst const u64 amd_hw_cache_event_ids_f17h -+ [PERF_COUNT_HW_CACHE_MAX] -+ [PERF_COUNT_HW_CACHE_OP_MAX] -+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = { -+[C(L1D)] = { -+ [C(OP_READ)] = { -+ [C(RESULT_ACCESS)] = 0x0040, /* Data Cache Accesses */ -+ [C(RESULT_MISS)] = 0xc860, /* L2$ access from DC Miss */ -+ }, -+ [C(OP_WRITE)] = { -+ [C(RESULT_ACCESS)] = 0, -+ [C(RESULT_MISS)] = 0, -+ }, -+ [C(OP_PREFETCH)] = { -+ [C(RESULT_ACCESS)] = 0xff5a, /* h/w prefetch DC Fills */ -+ [C(RESULT_MISS)] = 0, -+ }, -+}, -+[C(L1I)] = { -+ [C(OP_READ)] = { -+ [C(RESULT_ACCESS)] = 0x0080, /* Instruction cache fetches */ -+ [C(RESULT_MISS)] = 0x0081, /* Instruction cache misses */ -+ }, -+ [C(OP_WRITE)] = { -+ [C(RESULT_ACCESS)] = -1, -+ [C(RESULT_MISS)] = -1, -+ }, -+ [C(OP_PREFETCH)] = { -+ [C(RESULT_ACCESS)] = 0, -+ [C(RESULT_MISS)] = 0, -+ }, -+}, -+[C(LL)] = { -+ [C(OP_READ)] = { -+ [C(RESULT_ACCESS)] = 0, -+ [C(RESULT_MISS)] = 0, -+ }, -+ [C(OP_WRITE)] = { -+ [C(RESULT_ACCESS)] = 0, -+ [C(RESULT_MISS)] = 0, -+ }, -+ [C(OP_PREFETCH)] = { -+ [C(RESULT_ACCESS)] = 0, -+ [C(RESULT_MISS)] = 0, -+ }, -+}, -+[C(DTLB)] = { -+ [C(OP_READ)] = { -+ [C(RESULT_ACCESS)] = 0xff45, /* All L2 DTLB accesses */ -+ [C(RESULT_MISS)] = 0xf045, /* L2 DTLB misses (PT walks) */ -+ }, -+ [C(OP_WRITE)] = { -+ [C(RESULT_ACCESS)] = 0, -+ [C(RESULT_MISS)] = 0, -+ }, -+ [C(OP_PREFETCH)] = { -+ [C(RESULT_ACCESS)] = 0, -+ [C(RESULT_MISS)] = 0, -+ }, -+}, -+[C(ITLB)] = { -+ [C(OP_READ)] = { -+ [C(RESULT_ACCESS)] = 0x0084, /* L1 ITLB misses, L2 ITLB hits */ -+ [C(RESULT_MISS)] = 0xff85, /* L1 ITLB misses, L2 misses */ -+ }, -+ [C(OP_WRITE)] = { -+ [C(RESULT_ACCESS)] = -1, -+ [C(RESULT_MISS)] = -1, -+ }, -+ [C(OP_PREFETCH)] = { -+ [C(RESULT_ACCESS)] = -1, -+ [C(RESULT_MISS)] = -1, -+ }, -+}, -+[C(BPU)] = { -+ [C(OP_READ)] = { -+ [C(RESULT_ACCESS)] = 0x00c2, /* Retired Branch Instr. */ -+ [C(RESULT_MISS)] = 0x00c3, /* Retired Mispredicted BI */ -+ }, -+ [C(OP_WRITE)] = { -+ [C(RESULT_ACCESS)] = -1, -+ [C(RESULT_MISS)] = -1, -+ }, -+ [C(OP_PREFETCH)] = { -+ [C(RESULT_ACCESS)] = -1, -+ [C(RESULT_MISS)] = -1, -+ }, -+}, -+[C(NODE)] = { -+ [C(OP_READ)] = { -+ [C(RESULT_ACCESS)] = 0, -+ [C(RESULT_MISS)] = 0, -+ }, -+ [C(OP_WRITE)] = { -+ [C(RESULT_ACCESS)] = -1, -+ [C(RESULT_MISS)] = -1, -+ }, -+ [C(OP_PREFETCH)] = { -+ [C(RESULT_ACCESS)] = -1, -+ [C(RESULT_MISS)] = -1, -+ }, -+}, -+}; -+ - /* - * AMD Performance Monitor K7 and later, up to and including Family 16h: - */ -@@ -731,9 +835,10 @@ __init int amd_pmu_init(void) - x86_pmu.amd_nb_constraints = 0; - } - -- /* Events are common for all AMDs */ -- memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, -- sizeof(hw_cache_event_ids)); -+ if (boot_cpu_data.x86 >= 0x17) -+ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids_f17h, sizeof(hw_cache_event_ids)); -+ else -+ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - - return 0; - } -diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h -index 37f2e0b377ad..4141ead86879 100644 ---- a/arch/x86/include/asm/stacktrace.h -+++ b/arch/x86/include/asm/stacktrace.h -@@ -55,13 +55,16 @@ extern int kstack_depth_to_print; - static inline unsigned long * - get_frame_pointer(struct task_struct *task, struct pt_regs *regs) - { -+ struct inactive_task_frame *frame; -+ - if (regs) - return (unsigned long *)regs->bp; - - if (task == current) - return __builtin_frame_address(0); - -- return (unsigned long *)((struct inactive_task_frame *)task->thread.sp)->bp; -+ frame = (struct inactive_task_frame *)task->thread.sp; -+ return (unsigned long *)READ_ONCE_NOCHECK(frame->bp); - } - #else - static inline unsigned long * -diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S -index 169963f471bb..50b8ed0317a3 100644 ---- a/arch/x86/kernel/acpi/wakeup_64.S -+++ b/arch/x86/kernel/acpi/wakeup_64.S -@@ -109,6 +109,15 @@ ENTRY(do_suspend_lowlevel) - movq pt_regs_r14(%rax), %r14 - movq pt_regs_r15(%rax), %r15 - -+#ifdef CONFIG_KASAN -+ /* -+ * The suspend path may have poisoned some areas deeper in the stack, -+ * which we now need to unpoison. -+ */ -+ movq %rsp, %rdi -+ call kasan_unpoison_task_stack_below -+#endif -+ - xorl %eax, %eax - addq $8, %rsp - FRAME_END -diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c -index 3e0199ee5a2f..0372913e0134 100644 ---- a/arch/x86/kernel/cpu/mcheck/mce-severity.c -+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c -@@ -148,6 +148,11 @@ static struct severity { - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), - KERNEL - ), -+ MCESEV( -+ PANIC, "Instruction fetch error in kernel", -+ SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), -+ KERNEL -+ ), - #endif - MCESEV( - PANIC, "Action required: unknown MCACOD", -diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c -index a2456d4d286a..9b8b3cb2e934 100644 ---- a/arch/x86/kernel/unwind_frame.c -+++ b/arch/x86/kernel/unwind_frame.c -@@ -6,6 +6,21 @@ - - #define FRAME_HEADER_SIZE (sizeof(long) * 2) - -+/* -+ * This disables KASAN checking when reading a value from another task's stack, -+ * since the other task could be running on another CPU and could have poisoned -+ * the stack in the meantime. -+ */ -+#define READ_ONCE_TASK_STACK(task, x) \ -+({ \ -+ unsigned long val; \ -+ if (task == current) \ -+ val = READ_ONCE(x); \ -+ else \ -+ val = READ_ONCE_NOCHECK(x); \ -+ val; \ -+}) -+ - unsigned long unwind_get_return_address(struct unwind_state *state) - { - unsigned long addr; -@@ -14,7 +29,8 @@ unsigned long unwind_get_return_address(struct unwind_state *state) - if (unwind_done(state)) - return 0; - -- addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p, -+ addr = READ_ONCE_TASK_STACK(state->task, *addr_p); -+ addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr, - addr_p); - - return __kernel_text_address(addr) ? addr : 0; -@@ -48,7 +64,7 @@ bool unwind_next_frame(struct unwind_state *state) - if (unwind_done(state)) - return false; - -- next_bp = (unsigned long *)*state->bp; -+ next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task,*state->bp); - - /* make sure the next frame's data is accessible */ - if (!update_stack_state(state, next_bp, FRAME_HEADER_SIZE)) -diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c -index c4328d9d9981..f838119d12b2 100644 ---- a/drivers/block/xsysace.c -+++ b/drivers/block/xsysace.c -@@ -1062,6 +1062,8 @@ static int ace_setup(struct ace_device *ace) - return 0; - - err_read: -+ /* prevent double queue cleanup */ -+ ace->gd->queue = NULL; - put_disk(ace->gd); - err_alloc_disk: - blk_cleanup_queue(ace->queue); -diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c -index d7179dd3c9ef..3cafa1d28fed 100644 ---- a/drivers/hid/hid-debug.c -+++ b/drivers/hid/hid-debug.c -@@ -1058,10 +1058,15 @@ static int hid_debug_rdesc_show(struct seq_file *f, void *p) - seq_printf(f, "\n\n"); - - /* dump parsed data and input mappings */ -+ if (down_interruptible(&hdev->driver_input_lock)) -+ return 0; -+ - hid_dump_device(hdev, f); - seq_printf(f, "\n"); - hid_dump_input_mapping(hdev, f); - -+ up(&hdev->driver_input_lock); -+ - return 0; - } - -diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c -index 2e2515a4c070..3198faf5cff4 100644 ---- a/drivers/hid/hid-logitech-hidpp.c -+++ b/drivers/hid/hid-logitech-hidpp.c -@@ -1282,6 +1282,13 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index) - kfree(data); - return -ENOMEM; - } -+ data->wq = create_singlethread_workqueue("hidpp-ff-sendqueue"); -+ if (!data->wq) { -+ kfree(data->effect_ids); -+ kfree(data); -+ return -ENOMEM; -+ } -+ - data->hidpp = hidpp; - data->feature_index = feature_index; - data->version = version; -@@ -1326,7 +1333,6 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index) - /* ignore boost value at response.fap.params[2] */ - - /* init the hardware command queue */ -- data->wq = create_singlethread_workqueue("hidpp-ff-sendqueue"); - atomic_set(&data->workqueue_size, 0); - - /* initialize with zero autocenter to get wheel in usable state */ -diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c -index 2a44a2c3e859..6914cc18b4a1 100644 ---- a/drivers/infiniband/ulp/srpt/ib_srpt.c -+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c -@@ -2368,8 +2368,19 @@ static void srpt_queue_tm_rsp(struct se_cmd *cmd) - srpt_queue_response(cmd); - } - -+/* -+ * This function is called for aborted commands if no response is sent to the -+ * initiator. Make sure that the credits freed by aborting a command are -+ * returned to the initiator the next time a response is sent by incrementing -+ * ch->req_lim_delta. -+ */ - static void srpt_aborted_task(struct se_cmd *cmd) - { -+ struct srpt_send_ioctx *ioctx = container_of(cmd, -+ struct srpt_send_ioctx, cmd); -+ struct srpt_rdma_ch *ch = ioctx->ch; -+ -+ atomic_inc(&ch->req_lim_delta); - } - - static int srpt_queue_status(struct se_cmd *cmd) -diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c -index 7544888c4749..b8dbde746b4e 100644 ---- a/drivers/input/keyboard/snvs_pwrkey.c -+++ b/drivers/input/keyboard/snvs_pwrkey.c -@@ -156,6 +156,9 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev) - return error; - } - -+ pdata->input = input; -+ platform_set_drvdata(pdev, pdata); -+ - error = devm_request_irq(&pdev->dev, pdata->irq, - imx_snvs_pwrkey_interrupt, - 0, pdev->name, pdev); -@@ -171,9 +174,6 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev) - return error; - } - -- pdata->input = input; -- platform_set_drvdata(pdev, pdata); -- - device_init_wakeup(&pdev->dev, pdata->wakeup); - - return 0; -diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c -index 56cfb5ca9c95..0a72228734ae 100644 ---- a/drivers/media/i2c/ov7670.c -+++ b/drivers/media/i2c/ov7670.c -@@ -155,10 +155,10 @@ MODULE_PARM_DESC(debug, "Debug level (0-1)"); - #define REG_GFIX 0x69 /* Fix gain control */ - - #define REG_DBLV 0x6b /* PLL control an debugging */ --#define DBLV_BYPASS 0x00 /* Bypass PLL */ --#define DBLV_X4 0x01 /* clock x4 */ --#define DBLV_X6 0x10 /* clock x6 */ --#define DBLV_X8 0x11 /* clock x8 */ -+#define DBLV_BYPASS 0x0a /* Bypass PLL */ -+#define DBLV_X4 0x4a /* clock x4 */ -+#define DBLV_X6 0x8a /* clock x6 */ -+#define DBLV_X8 0xca /* clock x8 */ - - #define REG_REG76 0x76 /* OV's name */ - #define R76_BLKPCOR 0x80 /* Black pixel correction enable */ -@@ -833,7 +833,7 @@ static int ov7675_set_framerate(struct v4l2_subdev *sd, - if (ret < 0) - return ret; - -- return ov7670_write(sd, REG_DBLV, DBLV_X4); -+ return 0; - } - - static void ov7670_get_framerate_legacy(struct v4l2_subdev *sd, -@@ -1578,11 +1578,7 @@ static int ov7670_probe(struct i2c_client *client, - if (config->clock_speed) - info->clock_speed = config->clock_speed; - -- /* -- * It should be allowed for ov7670 too when it is migrated to -- * the new frame rate formula. -- */ -- if (config->pll_bypass && id->driver_data != MODEL_OV7670) -+ if (config->pll_bypass) - info->pll_bypass = true; - - if (config->pclk_hb_disable) -diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c -index 7d16c51e6913..641a532b67cb 100644 ---- a/drivers/net/bonding/bond_sysfs_slave.c -+++ b/drivers/net/bonding/bond_sysfs_slave.c -@@ -55,7 +55,9 @@ static SLAVE_ATTR_RO(link_failure_count); - - static ssize_t perm_hwaddr_show(struct slave *slave, char *buf) - { -- return sprintf(buf, "%pM\n", slave->perm_hwaddr); -+ return sprintf(buf, "%*phC\n", -+ slave->dev->addr_len, -+ slave->perm_hwaddr); - } - static SLAVE_ATTR_RO(perm_hwaddr); - -diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c -index 45ea2718c65d..620a470eb4c8 100644 ---- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c -+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c -@@ -5954,8 +5954,15 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp) - - skip_uc: - rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0); -+ if (rc && vnic->mc_list_count) { -+ netdev_info(bp->dev, "Failed setting MC filters rc: %d, turning on ALL_MCAST mode\n", -+ rc); -+ vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST; -+ vnic->mc_list_count = 0; -+ rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0); -+ } - if (rc) -- netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n", -+ netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %d\n", - rc); - - return rc; -diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c -index 06bc8638501e..66e7a5fd4249 100644 ---- a/drivers/net/ethernet/hisilicon/hns/hnae.c -+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c -@@ -146,7 +146,6 @@ out_buffer_fail: - /* free desc along with its attached buffer */ - static void hnae_free_desc(struct hnae_ring *ring) - { -- hnae_free_buffers(ring); - dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr, - ring->desc_num * sizeof(ring->desc[0]), - ring_to_dma_dir(ring)); -@@ -179,6 +178,9 @@ static int hnae_alloc_desc(struct hnae_ring *ring) - /* fini ring, also free the buffer for the ring */ - static void hnae_fini_ring(struct hnae_ring *ring) - { -+ if (is_rx_ring(ring)) -+ hnae_free_buffers(ring); -+ - hnae_free_desc(ring); - kfree(ring->desc_cb); - ring->desc_cb = NULL; -diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c -index ad8681cf5ef0..24a815997ec5 100644 ---- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c -+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c -@@ -28,9 +28,6 @@ - - #define SERVICE_TIMER_HZ (1 * HZ) - --#define NIC_TX_CLEAN_MAX_NUM 256 --#define NIC_RX_CLEAN_MAX_NUM 64 -- - #define RCB_IRQ_NOT_INITED 0 - #define RCB_IRQ_INITED 1 - #define HNS_BUFFER_SIZE_2048 2048 -@@ -375,8 +372,6 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, - wmb(); /* commit all data before submit */ - assert(skb->queue_mapping < priv->ae_handle->q_num); - hnae_queue_xmit(priv->ae_handle->qs[skb->queue_mapping], buf_num); -- ring->stats.tx_pkts++; -- ring->stats.tx_bytes += skb->len; - - return NETDEV_TX_OK; - -@@ -916,6 +911,9 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, - /* issue prefetch for next Tx descriptor */ - prefetch(&ring->desc_cb[ring->next_to_clean]); - } -+ /* update tx ring statistics. */ -+ ring->stats.tx_pkts += pkts; -+ ring->stats.tx_bytes += bytes; - - NETIF_TX_UNLOCK(ndev); - -@@ -1821,7 +1819,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv) - hns_nic_tx_fini_pro_v2; - - netif_napi_add(priv->netdev, &rd->napi, -- hns_nic_common_poll, NIC_TX_CLEAN_MAX_NUM); -+ hns_nic_common_poll, NAPI_POLL_WEIGHT); - rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED; - } - for (i = h->q_num; i < h->q_num * 2; i++) { -@@ -1834,7 +1832,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv) - hns_nic_rx_fini_pro_v2; - - netif_napi_add(priv->netdev, &rd->napi, -- hns_nic_common_poll, NIC_RX_CLEAN_MAX_NUM); -+ hns_nic_common_poll, NAPI_POLL_WEIGHT); - rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED; - } - -diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h -index 2688180a7acd..f948eec7b35f 100644 ---- a/drivers/net/ethernet/intel/igb/e1000_defines.h -+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h -@@ -193,6 +193,8 @@ - /* enable link status from external LINK_0 and LINK_1 pins */ - #define E1000_CTRL_SWDPIN0 0x00040000 /* SWDPIN 0 value */ - #define E1000_CTRL_SWDPIN1 0x00080000 /* SWDPIN 1 value */ -+#define E1000_CTRL_ADVD3WUC 0x00100000 /* D3 WUC */ -+#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000 /* PHY PM enable */ - #define E1000_CTRL_SDP0_DIR 0x00400000 /* SDP0 Data direction */ - #define E1000_CTRL_SDP1_DIR 0x00800000 /* SDP1 Data direction */ - #define E1000_CTRL_RST 0x04000000 /* Global reset */ -diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c -index 82e48e355fb9..7956176c2c73 100644 ---- a/drivers/net/ethernet/intel/igb/igb_main.c -+++ b/drivers/net/ethernet/intel/igb/igb_main.c -@@ -7548,9 +7548,7 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, - struct e1000_hw *hw = &adapter->hw; - u32 ctrl, rctl, status; - u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol; --#ifdef CONFIG_PM -- int retval = 0; --#endif -+ bool wake; - - rtnl_lock(); - netif_device_detach(netdev); -@@ -7563,14 +7561,6 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, - igb_clear_interrupt_scheme(adapter); - rtnl_unlock(); - --#ifdef CONFIG_PM -- if (!runtime) { -- retval = pci_save_state(pdev); -- if (retval) -- return retval; -- } --#endif -- - status = rd32(E1000_STATUS); - if (status & E1000_STATUS_LU) - wufc &= ~E1000_WUFC_LNKC; -@@ -7587,10 +7577,6 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, - } - - ctrl = rd32(E1000_CTRL); -- /* advertise wake from D3Cold */ -- #define E1000_CTRL_ADVD3WUC 0x00100000 -- /* phy power management enable */ -- #define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000 - ctrl |= E1000_CTRL_ADVD3WUC; - wr32(E1000_CTRL, ctrl); - -@@ -7604,12 +7590,15 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, - wr32(E1000_WUFC, 0); - } - -- *enable_wake = wufc || adapter->en_mng_pt; -- if (!*enable_wake) -+ wake = wufc || adapter->en_mng_pt; -+ if (!wake) - igb_power_down_link(adapter); - else - igb_power_up_link(adapter); - -+ if (enable_wake) -+ *enable_wake = wake; -+ - /* Release control of h/w to f/w. If f/w is AMT enabled, this - * would have already happened in close and is redundant. - */ -@@ -7624,22 +7613,7 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, - #ifdef CONFIG_PM_SLEEP - static int igb_suspend(struct device *dev) - { -- int retval; -- bool wake; -- struct pci_dev *pdev = to_pci_dev(dev); -- -- retval = __igb_shutdown(pdev, &wake, 0); -- if (retval) -- return retval; -- -- if (wake) { -- pci_prepare_to_sleep(pdev); -- } else { -- pci_wake_from_d3(pdev, false); -- pci_set_power_state(pdev, PCI_D3hot); -- } -- -- return 0; -+ return __igb_shutdown(to_pci_dev(dev), NULL, 0); - } - #endif /* CONFIG_PM_SLEEP */ - -@@ -7707,22 +7681,7 @@ static int igb_runtime_idle(struct device *dev) - - static int igb_runtime_suspend(struct device *dev) - { -- struct pci_dev *pdev = to_pci_dev(dev); -- int retval; -- bool wake; -- -- retval = __igb_shutdown(pdev, &wake, 1); -- if (retval) -- return retval; -- -- if (wake) { -- pci_prepare_to_sleep(pdev); -- } else { -- pci_wake_from_d3(pdev, false); -- pci_set_power_state(pdev, PCI_D3hot); -- } -- -- return 0; -+ return __igb_shutdown(to_pci_dev(dev), NULL, 1); - } - - static int igb_runtime_resume(struct device *dev) -diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c -index da9246f6c31e..d1a3a35ba87b 100644 ---- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c -+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c -@@ -92,8 +92,7 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport, - opcode, MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT); - MLX5_SET(modify_nic_vport_context_in, in, field_select.change_event, 1); - MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport); -- if (vport) -- MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1); -+ MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1); - nic_vport_ctx = MLX5_ADDR_OF(modify_nic_vport_context_in, - in, nic_vport_context); - -@@ -121,8 +120,7 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport, - MLX5_SET(modify_esw_vport_context_in, in, opcode, - MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT); - MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport); -- if (vport) -- MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1); -+ MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1); - return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); - } - -diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c -index ce97e522566a..77dc5842bd0b 100644 ---- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c -+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c -@@ -205,6 +205,11 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x, - if (unlikely(rdes0 & RDES0_OWN)) - return dma_own; - -+ if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) { -+ stats->rx_length_errors++; -+ return discard_frame; -+ } -+ - if (unlikely(rdes0 & RDES0_ERROR_SUMMARY)) { - if (unlikely(rdes0 & RDES0_DESCRIPTOR_ERROR)) { - x->rx_desc++; -@@ -235,9 +240,10 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x, - * It doesn't match with the information reported into the databook. - * At any rate, we need to understand if the CSUM hw computation is ok - * and report this info to the upper layers. */ -- ret = enh_desc_coe_rdes0(!!(rdes0 & RDES0_IPC_CSUM_ERROR), -- !!(rdes0 & RDES0_FRAME_TYPE), -- !!(rdes0 & ERDES0_RX_MAC_ADDR)); -+ if (likely(ret == good_frame)) -+ ret = enh_desc_coe_rdes0(!!(rdes0 & RDES0_IPC_CSUM_ERROR), -+ !!(rdes0 & RDES0_FRAME_TYPE), -+ !!(rdes0 & ERDES0_RX_MAC_ADDR)); - - if (unlikely(rdes0 & RDES0_DRIBBLING)) - x->dribbling_bit++; -diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c -index fd78406e2e9a..01f8f2e94c0f 100644 ---- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c -+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c -@@ -95,8 +95,6 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x, - return dma_own; - - if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) { -- pr_warn("%s: Oversized frame spanned multiple buffers\n", -- __func__); - stats->rx_length_errors++; - return discard_frame; - } -diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c -index 520352327104..77357b07f6c9 100644 ---- a/drivers/net/phy/marvell.c -+++ b/drivers/net/phy/marvell.c -@@ -1429,9 +1429,10 @@ static int marvell_get_sset_count(struct phy_device *phydev) - - static void marvell_get_strings(struct phy_device *phydev, u8 *data) - { -+ int count = marvell_get_sset_count(phydev); - int i; - -- for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) { -+ for (i = 0; i < count; i++) { - memcpy(data + i * ETH_GSTRING_LEN, - marvell_hw_stats[i].string, ETH_GSTRING_LEN); - } -@@ -1470,9 +1471,10 @@ static u64 marvell_get_stat(struct phy_device *phydev, int i) - static void marvell_get_stats(struct phy_device *phydev, - struct ethtool_stats *stats, u64 *data) - { -+ int count = marvell_get_sset_count(phydev); - int i; - -- for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) -+ for (i = 0; i < count; i++) - data[i] = marvell_get_stat(phydev, i); - } - -diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c -index f12753eb3216..96ea6c76be6e 100644 ---- a/drivers/nvme/target/core.c -+++ b/drivers/nvme/target/core.c -@@ -709,6 +709,15 @@ bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys, - return __nvmet_host_allowed(subsys, hostnqn); - } - -+static void nvmet_fatal_error_handler(struct work_struct *work) -+{ -+ struct nvmet_ctrl *ctrl = -+ container_of(work, struct nvmet_ctrl, fatal_err_work); -+ -+ pr_err("ctrl %d fatal error occurred!\n", ctrl->cntlid); -+ ctrl->ops->delete_ctrl(ctrl); -+} -+ - u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, - struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp) - { -@@ -747,6 +756,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, - - INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work); - INIT_LIST_HEAD(&ctrl->async_events); -+ INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler); - - memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE); - memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE); -@@ -849,21 +859,11 @@ void nvmet_ctrl_put(struct nvmet_ctrl *ctrl) - kref_put(&ctrl->ref, nvmet_ctrl_free); - } - --static void nvmet_fatal_error_handler(struct work_struct *work) --{ -- struct nvmet_ctrl *ctrl = -- container_of(work, struct nvmet_ctrl, fatal_err_work); -- -- pr_err("ctrl %d fatal error occurred!\n", ctrl->cntlid); -- ctrl->ops->delete_ctrl(ctrl); --} -- - void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl) - { - mutex_lock(&ctrl->lock); - if (!(ctrl->csts & NVME_CSTS_CFS)) { - ctrl->csts |= NVME_CSTS_CFS; -- INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler); - schedule_work(&ctrl->fatal_err_work); - } - mutex_unlock(&ctrl->lock); -diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c -index f85cae240f12..7e92e491c2e7 100644 ---- a/drivers/rtc/rtc-da9063.c -+++ b/drivers/rtc/rtc-da9063.c -@@ -480,6 +480,13 @@ static int da9063_rtc_probe(struct platform_device *pdev) - da9063_data_to_tm(data, &rtc->alarm_time, rtc); - rtc->rtc_sync = false; - -+ /* -+ * TODO: some models have alarms on a minute boundary but still support -+ * real hardware interrupts. Add this once the core supports it. -+ */ -+ if (config->rtc_data_start != RTC_SEC) -+ rtc->rtc_dev->uie_unsupported = 1; -+ - irq_alarm = platform_get_irq_byname(pdev, "ALARM"); - ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL, - da9063_alarm_event, -diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c -index 17b6235d67a5..600fb7f93939 100644 ---- a/drivers/rtc/rtc-sh.c -+++ b/drivers/rtc/rtc-sh.c -@@ -454,7 +454,7 @@ static int sh_rtc_set_time(struct device *dev, struct rtc_time *tm) - static inline int sh_rtc_read_alarm_value(struct sh_rtc *rtc, int reg_off) - { - unsigned int byte; -- int value = 0xff; /* return 0xff for ignored values */ -+ int value = -1; /* return -1 for ignored values */ - - byte = readb(rtc->regbase + reg_off); - if (byte & AR_ENB) { -diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c -index 282ea00d0f87..9d555b63d2e2 100644 ---- a/drivers/scsi/scsi_devinfo.c -+++ b/drivers/scsi/scsi_devinfo.c -@@ -249,6 +249,7 @@ static struct { - {"NETAPP", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, - {"LSI", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, - {"ENGENIO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, -+ {"LENOVO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, - {"SMSC", "USB 2 HS-CF", NULL, BLIST_SPARSELUN | BLIST_INQUIRY_36}, - {"SONY", "CD-ROM CDU-8001", NULL, BLIST_BORKEN}, - {"SONY", "TSL", NULL, BLIST_FORCELUN}, /* DDS3 & DDS4 autoloaders */ -diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c -index 375cede0c534..c9bc6f058424 100644 ---- a/drivers/scsi/scsi_dh.c -+++ b/drivers/scsi/scsi_dh.c -@@ -75,6 +75,7 @@ static const struct scsi_dh_blist scsi_dh_blist[] = { - {"NETAPP", "INF-01-00", "rdac", }, - {"LSI", "INF-01-00", "rdac", }, - {"ENGENIO", "INF-01-00", "rdac", }, -+ {"LENOVO", "DE_Series", "rdac", }, - {NULL, NULL, NULL }, - }; - -diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c -index d92b2808d191..6df34d68737f 100644 ---- a/drivers/scsi/storvsc_drv.c -+++ b/drivers/scsi/storvsc_drv.c -@@ -641,13 +641,22 @@ static void handle_sc_creation(struct vmbus_channel *new_sc) - static void handle_multichannel_storage(struct hv_device *device, int max_chns) - { - struct storvsc_device *stor_device; -- int num_cpus = num_online_cpus(); - int num_sc; - struct storvsc_cmd_request *request; - struct vstor_packet *vstor_packet; - int ret, t; - -- num_sc = ((max_chns > num_cpus) ? num_cpus : max_chns); -+ /* -+ * If the number of CPUs is artificially restricted, such as -+ * with maxcpus=1 on the kernel boot line, Hyper-V could offer -+ * sub-channels >= the number of CPUs. These sub-channels -+ * should not be created. The primary channel is already created -+ * and assigned to one CPU, so check against # CPUs - 1. -+ */ -+ num_sc = min((int)(num_online_cpus() - 1), max_chns); -+ if (!num_sc) -+ return; -+ - stor_device = get_out_stor_device(device); - if (!stor_device) - return; -diff --git a/drivers/staging/iio/addac/adt7316.c b/drivers/staging/iio/addac/adt7316.c -index 3faffe59c933..95f5be1cd498 100644 ---- a/drivers/staging/iio/addac/adt7316.c -+++ b/drivers/staging/iio/addac/adt7316.c -@@ -47,6 +47,8 @@ - #define ADT7516_MSB_AIN3 0xA - #define ADT7516_MSB_AIN4 0xB - #define ADT7316_DA_DATA_BASE 0x10 -+#define ADT7316_DA_10_BIT_LSB_SHIFT 6 -+#define ADT7316_DA_12_BIT_LSB_SHIFT 4 - #define ADT7316_DA_MSB_DATA_REGS 4 - #define ADT7316_LSB_DAC_A 0x10 - #define ADT7316_MSB_DAC_A 0x11 -@@ -1089,7 +1091,7 @@ static ssize_t adt7316_store_DAC_internal_Vref(struct device *dev, - ldac_config = chip->ldac_config & (~ADT7516_DAC_IN_VREF_MASK); - if (data & 0x1) - ldac_config |= ADT7516_DAC_AB_IN_VREF; -- else if (data & 0x2) -+ if (data & 0x2) - ldac_config |= ADT7516_DAC_CD_IN_VREF; - } else { - ret = kstrtou8(buf, 16, &data); -@@ -1411,7 +1413,7 @@ static IIO_DEVICE_ATTR(ex_analog_temp_offset, S_IRUGO | S_IWUSR, - static ssize_t adt7316_show_DAC(struct adt7316_chip_info *chip, - int channel, char *buf) - { -- u16 data; -+ u16 data = 0; - u8 msb, lsb, offset; - int ret; - -@@ -1436,7 +1438,11 @@ static ssize_t adt7316_show_DAC(struct adt7316_chip_info *chip, - if (ret) - return -EIO; - -- data = (msb << offset) + (lsb & ((1 << offset) - 1)); -+ if (chip->dac_bits == 12) -+ data = lsb >> ADT7316_DA_12_BIT_LSB_SHIFT; -+ else if (chip->dac_bits == 10) -+ data = lsb >> ADT7316_DA_10_BIT_LSB_SHIFT; -+ data |= msb << offset; - - return sprintf(buf, "%d\n", data); - } -@@ -1444,7 +1450,7 @@ static ssize_t adt7316_show_DAC(struct adt7316_chip_info *chip, - static ssize_t adt7316_store_DAC(struct adt7316_chip_info *chip, - int channel, const char *buf, size_t len) - { -- u8 msb, lsb, offset; -+ u8 msb, lsb, lsb_reg, offset; - u16 data; - int ret; - -@@ -1462,9 +1468,13 @@ static ssize_t adt7316_store_DAC(struct adt7316_chip_info *chip, - return -EINVAL; - - if (chip->dac_bits > 8) { -- lsb = data & (1 << offset); -+ lsb = data & ((1 << offset) - 1); -+ if (chip->dac_bits == 12) -+ lsb_reg = lsb << ADT7316_DA_12_BIT_LSB_SHIFT; -+ else -+ lsb_reg = lsb << ADT7316_DA_10_BIT_LSB_SHIFT; - ret = chip->bus.write(chip->bus.client, -- ADT7316_DA_DATA_BASE + channel * 2, lsb); -+ ADT7316_DA_DATA_BASE + channel * 2, lsb_reg); - if (ret) - return -EIO; - } -diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c -index c17b254e4f64..654199c6a36c 100644 ---- a/drivers/usb/core/driver.c -+++ b/drivers/usb/core/driver.c -@@ -470,11 +470,6 @@ static int usb_unbind_interface(struct device *dev) - pm_runtime_disable(dev); - pm_runtime_set_suspended(dev); - -- /* Undo any residual pm_autopm_get_interface_* calls */ -- for (r = atomic_read(&intf->pm_usage_cnt); r > 0; --r) -- usb_autopm_put_interface_no_suspend(intf); -- atomic_set(&intf->pm_usage_cnt, 0); -- - if (!error) - usb_autosuspend_device(udev); - -@@ -1625,7 +1620,6 @@ void usb_autopm_put_interface(struct usb_interface *intf) - int status; - - usb_mark_last_busy(udev); -- atomic_dec(&intf->pm_usage_cnt); - status = pm_runtime_put_sync(&intf->dev); - dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", - __func__, atomic_read(&intf->dev.power.usage_count), -@@ -1654,7 +1648,6 @@ void usb_autopm_put_interface_async(struct usb_interface *intf) - int status; - - usb_mark_last_busy(udev); -- atomic_dec(&intf->pm_usage_cnt); - status = pm_runtime_put(&intf->dev); - dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", - __func__, atomic_read(&intf->dev.power.usage_count), -@@ -1676,7 +1669,6 @@ void usb_autopm_put_interface_no_suspend(struct usb_interface *intf) - struct usb_device *udev = interface_to_usbdev(intf); - - usb_mark_last_busy(udev); -- atomic_dec(&intf->pm_usage_cnt); - pm_runtime_put_noidle(&intf->dev); - } - EXPORT_SYMBOL_GPL(usb_autopm_put_interface_no_suspend); -@@ -1707,8 +1699,6 @@ int usb_autopm_get_interface(struct usb_interface *intf) - status = pm_runtime_get_sync(&intf->dev); - if (status < 0) - pm_runtime_put_sync(&intf->dev); -- else -- atomic_inc(&intf->pm_usage_cnt); - dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", - __func__, atomic_read(&intf->dev.power.usage_count), - status); -@@ -1742,8 +1732,6 @@ int usb_autopm_get_interface_async(struct usb_interface *intf) - status = pm_runtime_get(&intf->dev); - if (status < 0 && status != -EINPROGRESS) - pm_runtime_put_noidle(&intf->dev); -- else -- atomic_inc(&intf->pm_usage_cnt); - dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", - __func__, atomic_read(&intf->dev.power.usage_count), - status); -@@ -1767,7 +1755,6 @@ void usb_autopm_get_interface_no_resume(struct usb_interface *intf) - struct usb_device *udev = interface_to_usbdev(intf); - - usb_mark_last_busy(udev); -- atomic_inc(&intf->pm_usage_cnt); - pm_runtime_get_noresume(&intf->dev); - } - EXPORT_SYMBOL_GPL(usb_autopm_get_interface_no_resume); -diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c -index 0e6ab0a17c08..955cd6552e95 100644 ---- a/drivers/usb/core/message.c -+++ b/drivers/usb/core/message.c -@@ -817,9 +817,11 @@ int usb_string(struct usb_device *dev, int index, char *buf, size_t size) - - if (dev->state == USB_STATE_SUSPENDED) - return -EHOSTUNREACH; -- if (size <= 0 || !buf || !index) -+ if (size <= 0 || !buf) - return -EINVAL; - buf[0] = 0; -+ if (index <= 0 || index >= 256) -+ return -EINVAL; - tbuf = kmalloc(256, GFP_NOIO); - if (!tbuf) - return -ENOMEM; -diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c -index 1e672343bcd6..efa3c86bd262 100644 ---- a/drivers/usb/misc/yurex.c -+++ b/drivers/usb/misc/yurex.c -@@ -324,6 +324,7 @@ static void yurex_disconnect(struct usb_interface *interface) - usb_deregister_dev(interface, &yurex_class); - - /* prevent more I/O from starting */ -+ usb_poison_urb(dev->urb); - mutex_lock(&dev->io_mutex); - dev->interface = NULL; - mutex_unlock(&dev->io_mutex); -diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c -index 4176d1af9bf2..fac3447021b2 100644 ---- a/drivers/usb/storage/realtek_cr.c -+++ b/drivers/usb/storage/realtek_cr.c -@@ -776,18 +776,16 @@ static void rts51x_suspend_timer_fn(unsigned long data) - break; - case RTS51X_STAT_IDLE: - case RTS51X_STAT_SS: -- usb_stor_dbg(us, "RTS51X_STAT_SS, intf->pm_usage_cnt:%d, power.usage:%d\n", -- atomic_read(&us->pusb_intf->pm_usage_cnt), -+ usb_stor_dbg(us, "RTS51X_STAT_SS, power.usage:%d\n", - atomic_read(&us->pusb_intf->dev.power.usage_count)); - -- if (atomic_read(&us->pusb_intf->pm_usage_cnt) > 0) { -+ if (atomic_read(&us->pusb_intf->dev.power.usage_count) > 0) { - usb_stor_dbg(us, "Ready to enter SS state\n"); - rts51x_set_stat(chip, RTS51X_STAT_SS); - /* ignore mass storage interface's children */ - pm_suspend_ignore_children(&us->pusb_intf->dev, true); - usb_autopm_put_interface_async(us->pusb_intf); -- usb_stor_dbg(us, "RTS51X_STAT_SS 01, intf->pm_usage_cnt:%d, power.usage:%d\n", -- atomic_read(&us->pusb_intf->pm_usage_cnt), -+ usb_stor_dbg(us, "RTS51X_STAT_SS 01, power.usage:%d\n", - atomic_read(&us->pusb_intf->dev.power.usage_count)); - } - break; -@@ -820,11 +818,10 @@ static void rts51x_invoke_transport(struct scsi_cmnd *srb, struct us_data *us) - int ret; - - if (working_scsi(srb)) { -- usb_stor_dbg(us, "working scsi, intf->pm_usage_cnt:%d, power.usage:%d\n", -- atomic_read(&us->pusb_intf->pm_usage_cnt), -+ usb_stor_dbg(us, "working scsi, power.usage:%d\n", - atomic_read(&us->pusb_intf->dev.power.usage_count)); - -- if (atomic_read(&us->pusb_intf->pm_usage_cnt) <= 0) { -+ if (atomic_read(&us->pusb_intf->dev.power.usage_count) <= 0) { - ret = usb_autopm_get_interface(us->pusb_intf); - usb_stor_dbg(us, "working scsi, ret=%d\n", ret); - } -diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c -index 5b807185f79e..777a4058c407 100644 ---- a/drivers/usb/usbip/stub_rx.c -+++ b/drivers/usb/usbip/stub_rx.c -@@ -383,16 +383,10 @@ static int get_pipe(struct stub_device *sdev, struct usbip_header *pdu) - } - - if (usb_endpoint_xfer_isoc(epd)) { -- /* validate packet size and number of packets */ -- unsigned int maxp, packets, bytes; -- -- maxp = usb_endpoint_maxp(epd); -- maxp *= usb_endpoint_maxp_mult(epd); -- bytes = pdu->u.cmd_submit.transfer_buffer_length; -- packets = DIV_ROUND_UP(bytes, maxp); -- -+ /* validate number of packets */ - if (pdu->u.cmd_submit.number_of_packets < 0 || -- pdu->u.cmd_submit.number_of_packets > packets) { -+ pdu->u.cmd_submit.number_of_packets > -+ USBIP_MAX_ISO_PACKETS) { - dev_err(&sdev->udev->dev, - "CMD_SUBMIT: isoc invalid num packets %d\n", - pdu->u.cmd_submit.number_of_packets); -diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h -index 109e65ba01a0..0b199a2664c0 100644 ---- a/drivers/usb/usbip/usbip_common.h -+++ b/drivers/usb/usbip/usbip_common.h -@@ -136,6 +136,13 @@ extern struct device_attribute dev_attr_usbip_debug; - #define USBIP_DIR_OUT 0x00 - #define USBIP_DIR_IN 0x01 - -+/* -+ * Arbitrary limit for the maximum number of isochronous packets in an URB, -+ * compare for example the uhci_submit_isochronous function in -+ * drivers/usb/host/uhci-q.c -+ */ -+#define USBIP_MAX_ISO_PACKETS 1024 -+ - /** - * struct usbip_header_basic - data pertinent to every request - * @command: the usbip request type -diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c -index 7338e43faa17..f9a75df2d22d 100644 ---- a/drivers/vfio/pci/vfio_pci.c -+++ b/drivers/vfio/pci/vfio_pci.c -@@ -1467,11 +1467,11 @@ static void __init vfio_pci_fill_ids(void) - rc = pci_add_dynid(&vfio_pci_driver, vendor, device, - subvendor, subdevice, class, class_mask, 0); - if (rc) -- pr_warn("failed to add dynamic id [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x (%d)\n", -+ pr_warn("failed to add dynamic id [%04x:%04x[%04x:%04x]] class %#08x/%08x (%d)\n", - vendor, device, subvendor, subdevice, - class, class_mask, rc); - else -- pr_info("add [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x\n", -+ pr_info("add [%04x:%04x[%04x:%04x]] class %#08x/%08x\n", - vendor, device, subvendor, subdevice, - class, class_mask); - } -diff --git a/drivers/w1/masters/ds2490.c b/drivers/w1/masters/ds2490.c -index 59d74d1b47a8..2287e1be0e55 100644 ---- a/drivers/w1/masters/ds2490.c -+++ b/drivers/w1/masters/ds2490.c -@@ -1039,15 +1039,15 @@ static int ds_probe(struct usb_interface *intf, - /* alternative 3, 1ms interrupt (greatly speeds search), 64 byte bulk */ - alt = 3; - err = usb_set_interface(dev->udev, -- intf->altsetting[alt].desc.bInterfaceNumber, alt); -+ intf->cur_altsetting->desc.bInterfaceNumber, alt); - if (err) { - dev_err(&dev->udev->dev, "Failed to set alternative setting %d " - "for %d interface: err=%d.\n", alt, -- intf->altsetting[alt].desc.bInterfaceNumber, err); -+ intf->cur_altsetting->desc.bInterfaceNumber, err); - goto err_out_clear; - } - -- iface_desc = &intf->altsetting[alt]; -+ iface_desc = intf->cur_altsetting; - if (iface_desc->desc.bNumEndpoints != NUM_EP-1) { - pr_info("Num endpoints=%d. It is not DS9490R.\n", - iface_desc->desc.bNumEndpoints); -diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c -index 77e9cd7a0137..20ee612017bf 100644 ---- a/fs/debugfs/inode.c -+++ b/fs/debugfs/inode.c -@@ -170,19 +170,24 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root) - return 0; - } - --static void debugfs_evict_inode(struct inode *inode) -+static void debugfs_i_callback(struct rcu_head *head) - { -- truncate_inode_pages_final(&inode->i_data); -- clear_inode(inode); -+ struct inode *inode = container_of(head, struct inode, i_rcu); - if (S_ISLNK(inode->i_mode)) - kfree(inode->i_link); -+ free_inode_nonrcu(inode); -+} -+ -+static void debugfs_destroy_inode(struct inode *inode) -+{ -+ call_rcu(&inode->i_rcu, debugfs_i_callback); - } - - 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, -+ .destroy_inode = debugfs_destroy_inode, - }; - - static struct vfsmount *debugfs_automount(struct path *path) -diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c -index 001487b230b5..4acc677ac8fb 100644 ---- a/fs/hugetlbfs/inode.c -+++ b/fs/hugetlbfs/inode.c -@@ -746,11 +746,17 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, - umode_t mode, dev_t dev) - { - struct inode *inode; -- struct resv_map *resv_map; -+ struct resv_map *resv_map = NULL; - -- resv_map = resv_map_alloc(); -- if (!resv_map) -- return NULL; -+ /* -+ * Reserve maps are only needed for inodes that can have associated -+ * page allocations. -+ */ -+ if (S_ISREG(mode) || S_ISLNK(mode)) { -+ resv_map = resv_map_alloc(); -+ if (!resv_map) -+ return NULL; -+ } - - inode = new_inode(sb); - if (inode) { -@@ -782,8 +788,10 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, - break; - } - lockdep_annotate_inode_mutex_key(inode); -- } else -- kref_put(&resv_map->refs, resv_map_release); -+ } else { -+ if (resv_map) -+ kref_put(&resv_map->refs, resv_map_release); -+ } - - return inode; - } -diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c -index 06a71dbd4833..2f236cca6095 100644 ---- a/fs/jffs2/readinode.c -+++ b/fs/jffs2/readinode.c -@@ -1414,11 +1414,6 @@ void jffs2_do_clear_inode(struct jffs2_sb_info *c, struct jffs2_inode_info *f) - - jffs2_kill_fragtree(&f->fragtree, deleted?c:NULL); - -- if (f->target) { -- kfree(f->target); -- f->target = NULL; -- } -- - fds = f->dents; - while(fds) { - fd = fds; -diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c -index 226640563df3..76aedbc97773 100644 ---- a/fs/jffs2/super.c -+++ b/fs/jffs2/super.c -@@ -47,7 +47,10 @@ static struct inode *jffs2_alloc_inode(struct super_block *sb) - static void jffs2_i_callback(struct rcu_head *head) - { - struct inode *inode = container_of(head, struct inode, i_rcu); -- kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode)); -+ struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); -+ -+ kfree(f->target); -+ kmem_cache_free(jffs2_inode_cachep, f); - } - - static void jffs2_destroy_inode(struct inode *inode) -diff --git a/include/linux/kasan.h b/include/linux/kasan.h -index 820c0ad54a01..c9df9e180610 100644 ---- a/include/linux/kasan.h -+++ b/include/linux/kasan.h -@@ -7,6 +7,7 @@ - struct kmem_cache; - struct page; - struct vm_struct; -+struct task_struct; - - #ifdef CONFIG_KASAN - -diff --git a/include/linux/usb.h b/include/linux/usb.h -index 346665a0c49d..9b5ca59271d9 100644 ---- a/include/linux/usb.h -+++ b/include/linux/usb.h -@@ -129,7 +129,6 @@ enum usb_interface_condition { - * @dev: driver model's view of this device - * @usb_dev: if an interface is bound to the USB major, this will point - * to the sysfs representation for that device. -- * @pm_usage_cnt: PM usage counter for this interface - * @reset_ws: Used for scheduling resets from atomic context. - * @resetting_device: USB core reset the device, so use alt setting 0 as - * current; needs bandwidth alloc after reset. -@@ -186,7 +185,6 @@ struct usb_interface { - - struct device dev; /* interface specific device info */ - struct device *usb_dev; -- atomic_t pm_usage_cnt; /* usage counter for autosuspend */ - struct work_struct reset_ws; /* for resets in atomic context */ - }; - #define to_usb_interface(d) container_of(d, struct usb_interface, dev) -diff --git a/include/net/caif/cfpkt.h b/include/net/caif/cfpkt.h -index fe328c52c46b..801489bb14c3 100644 ---- a/include/net/caif/cfpkt.h -+++ b/include/net/caif/cfpkt.h -@@ -32,6 +32,33 @@ void cfpkt_destroy(struct cfpkt *pkt); - */ - int cfpkt_extr_head(struct cfpkt *pkt, void *data, u16 len); - -+static inline u8 cfpkt_extr_head_u8(struct cfpkt *pkt) -+{ -+ u8 tmp; -+ -+ cfpkt_extr_head(pkt, &tmp, 1); -+ -+ return tmp; -+} -+ -+static inline u16 cfpkt_extr_head_u16(struct cfpkt *pkt) -+{ -+ __le16 tmp; -+ -+ cfpkt_extr_head(pkt, &tmp, 2); -+ -+ return le16_to_cpu(tmp); -+} -+ -+static inline u32 cfpkt_extr_head_u32(struct cfpkt *pkt) -+{ -+ __le32 tmp; -+ -+ cfpkt_extr_head(pkt, &tmp, 4); -+ -+ return le32_to_cpu(tmp); -+} -+ - /* - * Peek header from packet. - * Reads data from packet without changing packet. -diff --git a/lib/Makefile b/lib/Makefile -index 50144a3aeebd..2447a218fff8 100644 ---- a/lib/Makefile -+++ b/lib/Makefile -@@ -46,6 +46,7 @@ obj-$(CONFIG_TEST_BPF) += test_bpf.o - obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o - obj-$(CONFIG_TEST_HASH) += test_hash.o - obj-$(CONFIG_TEST_KASAN) += test_kasan.o -+CFLAGS_test_kasan.o += -fno-builtin - obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o - obj-$(CONFIG_TEST_LKM) += test_module.o - obj-$(CONFIG_TEST_RHASHTABLE) += test_rhashtable.o -diff --git a/lib/test_kasan.c b/lib/test_kasan.c -index fbdf87920093..4ba4cbe169a8 100644 ---- a/lib/test_kasan.c -+++ b/lib/test_kasan.c -@@ -355,7 +355,7 @@ static noinline void __init kasan_stack_oob(void) - static noinline void __init ksize_unpoisons_memory(void) - { - char *ptr; -- size_t size = 123, real_size = size; -+ size_t size = 123, real_size; - - pr_info("ksize() unpoisons the whole allocated chunk\n"); - ptr = kmalloc(size, GFP_KERNEL); -diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c -index 4ce386c44cf1..1169c1fe941f 100644 ---- a/mm/kasan/kasan.c -+++ b/mm/kasan/kasan.c -@@ -80,7 +80,14 @@ void kasan_unpoison_task_stack(struct task_struct *task) - /* Unpoison the stack for the current task beyond a watermark sp value. */ - asmlinkage void kasan_unpoison_task_stack_below(const void *watermark) - { -- __kasan_unpoison_stack(current, watermark); -+ /* -+ * Calculate the task stack base address. Avoid using 'current' -+ * because this function is called by early resume code which hasn't -+ * yet set up the percpu register (%gs). -+ */ -+ void *base = (void *)((unsigned long)watermark & ~(THREAD_SIZE - 1)); -+ -+ kasan_unpoison_shadow(base, watermark - base); - } - - /* -diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c -index 3f9a41cf0ac6..31238dad85fb 100644 ---- a/mm/kasan/kasan_init.c -+++ b/mm/kasan/kasan_init.c -@@ -15,6 +15,7 @@ - #include - #include - #include -+#include - #include - - #include -@@ -49,7 +50,7 @@ static void __init zero_pte_populate(pmd_t *pmd, unsigned long addr, - pte_t *pte = pte_offset_kernel(pmd, addr); - pte_t zero_pte; - -- zero_pte = pfn_pte(PFN_DOWN(__pa(kasan_zero_page)), PAGE_KERNEL); -+ zero_pte = pfn_pte(PFN_DOWN(__pa_symbol(kasan_zero_page)), PAGE_KERNEL); - zero_pte = pte_wrprotect(zero_pte); - - while (addr + PAGE_SIZE <= end) { -@@ -69,7 +70,7 @@ static void __init zero_pmd_populate(pud_t *pud, unsigned long addr, - next = pmd_addr_end(addr, end); - - if (IS_ALIGNED(addr, PMD_SIZE) && end - addr >= PMD_SIZE) { -- pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte); -+ pmd_populate_kernel(&init_mm, pmd, lm_alias(kasan_zero_pte)); - continue; - } - -@@ -92,9 +93,9 @@ static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr, - if (IS_ALIGNED(addr, PUD_SIZE) && end - addr >= PUD_SIZE) { - pmd_t *pmd; - -- pud_populate(&init_mm, pud, kasan_zero_pmd); -+ pud_populate(&init_mm, pud, lm_alias(kasan_zero_pmd)); - pmd = pmd_offset(pud, addr); -- pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte); -+ pmd_populate_kernel(&init_mm, pmd, lm_alias(kasan_zero_pte)); - continue; - } - -@@ -135,11 +136,11 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, - * puds,pmds, so pgd_populate(), pud_populate() - * is noops. - */ -- pgd_populate(&init_mm, pgd, kasan_zero_pud); -+ pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_pud)); - pud = pud_offset(pgd, addr); -- pud_populate(&init_mm, pud, kasan_zero_pmd); -+ pud_populate(&init_mm, pud, lm_alias(kasan_zero_pmd)); - pmd = pmd_offset(pud, addr); -- pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte); -+ pmd_populate_kernel(&init_mm, pmd, lm_alias(kasan_zero_pte)); - continue; - } - -diff --git a/mm/kasan/report.c b/mm/kasan/report.c -index 8ca412aebcf1..c505ac5b2d46 100644 ---- a/mm/kasan/report.c -+++ b/mm/kasan/report.c -@@ -302,6 +302,7 @@ void kasan_report(unsigned long addr, size_t size, - disable_trace_on_warning(); - - info.access_addr = (void *)addr; -+ info.first_bad_addr = (void *)addr; - info.access_size = size; - info.is_write = is_write; - info.ip = ip; -diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c -index 8b6f654bc85d..00123064eb26 100644 ---- a/net/batman-adv/bridge_loop_avoidance.c -+++ b/net/batman-adv/bridge_loop_avoidance.c -@@ -802,6 +802,8 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, - const u8 *mac, const unsigned short vid) - { - struct batadv_bla_claim search_claim, *claim; -+ struct batadv_bla_claim *claim_removed_entry; -+ struct hlist_node *claim_removed_node; - - ether_addr_copy(search_claim.addr, mac); - search_claim.vid = vid; -@@ -812,10 +814,18 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, - batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_del_claim(): %pM, vid %d\n", - mac, BATADV_PRINT_VID(vid)); - -- batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim, -- batadv_choose_claim, claim); -- batadv_claim_put(claim); /* reference from the hash is gone */ -+ claim_removed_node = batadv_hash_remove(bat_priv->bla.claim_hash, -+ batadv_compare_claim, -+ batadv_choose_claim, claim); -+ if (!claim_removed_node) -+ goto free_claim; - -+ /* reference from the hash is gone */ -+ claim_removed_entry = hlist_entry(claim_removed_node, -+ struct batadv_bla_claim, hash_entry); -+ batadv_claim_put(claim_removed_entry); -+ -+free_claim: - /* don't need the reference from hash_find() anymore */ - batadv_claim_put(claim); - } -diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c -index b9f9a310eb78..af4a02ad8503 100644 ---- a/net/batman-adv/translation-table.c -+++ b/net/batman-adv/translation-table.c -@@ -615,14 +615,26 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv, - struct batadv_tt_global_entry *tt_global, - const char *message) - { -+ struct batadv_tt_global_entry *tt_removed_entry; -+ struct hlist_node *tt_removed_node; -+ - batadv_dbg(BATADV_DBG_TT, bat_priv, - "Deleting global tt entry %pM (vid: %d): %s\n", - tt_global->common.addr, - BATADV_PRINT_VID(tt_global->common.vid), message); - -- batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt, -- batadv_choose_tt, &tt_global->common); -- batadv_tt_global_entry_put(tt_global); -+ tt_removed_node = batadv_hash_remove(bat_priv->tt.global_hash, -+ batadv_compare_tt, -+ batadv_choose_tt, -+ &tt_global->common); -+ if (!tt_removed_node) -+ return; -+ -+ /* drop reference of remove hash entry */ -+ tt_removed_entry = hlist_entry(tt_removed_node, -+ struct batadv_tt_global_entry, -+ common.hash_entry); -+ batadv_tt_global_entry_put(tt_removed_entry); - } - - /** -@@ -1308,9 +1320,10 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, - unsigned short vid, const char *message, - bool roaming) - { -+ struct batadv_tt_local_entry *tt_removed_entry; - struct batadv_tt_local_entry *tt_local_entry; - u16 flags, curr_flags = BATADV_NO_FLAGS; -- void *tt_entry_exists; -+ struct hlist_node *tt_removed_node; - - tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid); - if (!tt_local_entry) -@@ -1339,15 +1352,18 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, - */ - batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL); - -- tt_entry_exists = batadv_hash_remove(bat_priv->tt.local_hash, -+ tt_removed_node = batadv_hash_remove(bat_priv->tt.local_hash, - batadv_compare_tt, - batadv_choose_tt, - &tt_local_entry->common); -- if (!tt_entry_exists) -+ if (!tt_removed_node) - goto out; - -- /* extra call to free the local tt entry */ -- batadv_tt_local_entry_put(tt_local_entry); -+ /* drop reference of remove hash entry */ -+ tt_removed_entry = hlist_entry(tt_removed_node, -+ struct batadv_tt_local_entry, -+ common.hash_entry); -+ batadv_tt_local_entry_put(tt_removed_entry); - - out: - if (tt_local_entry) -diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c -index f5afda1abc76..4dc82e9a855d 100644 ---- a/net/caif/cfctrl.c -+++ b/net/caif/cfctrl.c -@@ -352,15 +352,14 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) - u8 cmdrsp; - u8 cmd; - int ret = -1; -- u16 tmp16; - u8 len; - u8 param[255]; -- u8 linkid; -+ u8 linkid = 0; - struct cfctrl *cfctrl = container_obj(layer); - struct cfctrl_request_info rsp, *req; - - -- cfpkt_extr_head(pkt, &cmdrsp, 1); -+ cmdrsp = cfpkt_extr_head_u8(pkt); - cmd = cmdrsp & CFCTRL_CMD_MASK; - if (cmd != CFCTRL_CMD_LINK_ERR - && CFCTRL_RSP_BIT != (CFCTRL_RSP_BIT & cmdrsp) -@@ -378,13 +377,12 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) - u8 physlinkid; - u8 prio; - u8 tmp; -- u32 tmp32; - u8 *cp; - int i; - struct cfctrl_link_param linkparam; - memset(&linkparam, 0, sizeof(linkparam)); - -- cfpkt_extr_head(pkt, &tmp, 1); -+ tmp = cfpkt_extr_head_u8(pkt); - - serv = tmp & CFCTRL_SRV_MASK; - linkparam.linktype = serv; -@@ -392,13 +390,13 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) - servtype = tmp >> 4; - linkparam.chtype = servtype; - -- cfpkt_extr_head(pkt, &tmp, 1); -+ tmp = cfpkt_extr_head_u8(pkt); - physlinkid = tmp & 0x07; - prio = tmp >> 3; - - linkparam.priority = prio; - linkparam.phyid = physlinkid; -- cfpkt_extr_head(pkt, &endpoint, 1); -+ endpoint = cfpkt_extr_head_u8(pkt); - linkparam.endpoint = endpoint & 0x03; - - switch (serv) { -@@ -407,45 +405,43 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) - if (CFCTRL_ERR_BIT & cmdrsp) - break; - /* Link ID */ -- cfpkt_extr_head(pkt, &linkid, 1); -+ linkid = cfpkt_extr_head_u8(pkt); - break; - case CFCTRL_SRV_VIDEO: -- cfpkt_extr_head(pkt, &tmp, 1); -+ tmp = cfpkt_extr_head_u8(pkt); - linkparam.u.video.connid = tmp; - if (CFCTRL_ERR_BIT & cmdrsp) - break; - /* Link ID */ -- cfpkt_extr_head(pkt, &linkid, 1); -+ linkid = cfpkt_extr_head_u8(pkt); - break; - - case CFCTRL_SRV_DATAGRAM: -- cfpkt_extr_head(pkt, &tmp32, 4); - linkparam.u.datagram.connid = -- le32_to_cpu(tmp32); -+ cfpkt_extr_head_u32(pkt); - if (CFCTRL_ERR_BIT & cmdrsp) - break; - /* Link ID */ -- cfpkt_extr_head(pkt, &linkid, 1); -+ linkid = cfpkt_extr_head_u8(pkt); - break; - case CFCTRL_SRV_RFM: - /* Construct a frame, convert - * DatagramConnectionID - * to network format long and copy it out... - */ -- cfpkt_extr_head(pkt, &tmp32, 4); - linkparam.u.rfm.connid = -- le32_to_cpu(tmp32); -+ cfpkt_extr_head_u32(pkt); - cp = (u8 *) linkparam.u.rfm.volume; -- for (cfpkt_extr_head(pkt, &tmp, 1); -+ for (tmp = cfpkt_extr_head_u8(pkt); - cfpkt_more(pkt) && tmp != '\0'; -- cfpkt_extr_head(pkt, &tmp, 1)) -+ tmp = cfpkt_extr_head_u8(pkt)) - *cp++ = tmp; - *cp = '\0'; - - if (CFCTRL_ERR_BIT & cmdrsp) - break; - /* Link ID */ -- cfpkt_extr_head(pkt, &linkid, 1); -+ linkid = cfpkt_extr_head_u8(pkt); - - break; - case CFCTRL_SRV_UTIL: -@@ -454,13 +450,11 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) - * to network format long and copy it out... - */ - /* Fifosize KB */ -- cfpkt_extr_head(pkt, &tmp16, 2); - linkparam.u.utility.fifosize_kb = -- le16_to_cpu(tmp16); -+ cfpkt_extr_head_u16(pkt); - /* Fifosize bufs */ -- cfpkt_extr_head(pkt, &tmp16, 2); - linkparam.u.utility.fifosize_bufs = -- le16_to_cpu(tmp16); -+ cfpkt_extr_head_u16(pkt); - /* name */ - cp = (u8 *) linkparam.u.utility.name; - caif_assert(sizeof(linkparam.u.utility.name) -@@ -468,24 +462,24 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) - for (i = 0; - i < UTILITY_NAME_LENGTH - && cfpkt_more(pkt); i++) { -- cfpkt_extr_head(pkt, &tmp, 1); -+ tmp = cfpkt_extr_head_u8(pkt); - *cp++ = tmp; - } - /* Length */ -- cfpkt_extr_head(pkt, &len, 1); -+ len = cfpkt_extr_head_u8(pkt); - linkparam.u.utility.paramlen = len; - /* Param Data */ - cp = linkparam.u.utility.params; - while (cfpkt_more(pkt) && len--) { -- cfpkt_extr_head(pkt, &tmp, 1); -+ tmp = cfpkt_extr_head_u8(pkt); - *cp++ = tmp; - } - if (CFCTRL_ERR_BIT & cmdrsp) - break; - /* Link ID */ -- cfpkt_extr_head(pkt, &linkid, 1); -+ linkid = cfpkt_extr_head_u8(pkt); - /* Length */ -- cfpkt_extr_head(pkt, &len, 1); -+ len = cfpkt_extr_head_u8(pkt); - /* Param Data */ - cfpkt_extr_head(pkt, ¶m, len); - break; -@@ -522,7 +516,7 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) - } - break; - case CFCTRL_CMD_LINK_DESTROY: -- cfpkt_extr_head(pkt, &linkid, 1); -+ linkid = cfpkt_extr_head_u8(pkt); - cfctrl->res.linkdestroy_rsp(cfctrl->serv.layer.up, linkid); - break; - case CFCTRL_CMD_LINK_ERR: -diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c -index 100c86f1f547..7f1a85c6a614 100644 ---- a/net/ipv4/ip_output.c -+++ b/net/ipv4/ip_output.c -@@ -492,6 +492,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) - to->pkt_type = from->pkt_type; - to->priority = from->priority; - to->protocol = from->protocol; -+ to->skb_iif = from->skb_iif; - skb_dst_drop(to); - skb_dst_copy(to, from); - to->dev = from->dev; -diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c -index b82e439804d1..8c2f9aedc2af 100644 ---- a/net/ipv6/ip6_flowlabel.c -+++ b/net/ipv6/ip6_flowlabel.c -@@ -94,15 +94,21 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label) - return fl; - } - -+static void fl_free_rcu(struct rcu_head *head) -+{ -+ struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu); -+ -+ if (fl->share == IPV6_FL_S_PROCESS) -+ put_pid(fl->owner.pid); -+ kfree(fl->opt); -+ kfree(fl); -+} -+ - - static void fl_free(struct ip6_flowlabel *fl) - { -- if (fl) { -- if (fl->share == IPV6_FL_S_PROCESS) -- put_pid(fl->owner.pid); -- kfree(fl->opt); -- kfree_rcu(fl, rcu); -- } -+ if (fl) -+ call_rcu(&fl->rcu, fl_free_rcu); - } - - static void fl_release(struct ip6_flowlabel *fl) -@@ -634,9 +640,9 @@ recheck: - if (fl1->share == IPV6_FL_S_EXCL || - fl1->share != fl->share || - ((fl1->share == IPV6_FL_S_PROCESS) && -- (fl1->owner.pid == fl->owner.pid)) || -+ (fl1->owner.pid != fl->owner.pid)) || - ((fl1->share == IPV6_FL_S_USER) && -- uid_eq(fl1->owner.uid, fl->owner.uid))) -+ !uid_eq(fl1->owner.uid, fl->owner.uid))) - goto release; - - err = -ENOMEM; -diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c -index 522d4ca715c9..ea37160d5ae2 100644 ---- a/net/packet/af_packet.c -+++ b/net/packet/af_packet.c -@@ -2638,8 +2638,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) - void *ph; - DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); - bool need_wait = !(msg->msg_flags & MSG_DONTWAIT); -+ unsigned char *addr = NULL; - int tp_len, size_max; -- unsigned char *addr; - void *data; - int len_sum = 0; - int status = TP_STATUS_AVAILABLE; -@@ -2650,7 +2650,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) - if (likely(saddr == NULL)) { - dev = packet_cached_dev_get(po); - proto = po->num; -- addr = NULL; - } else { - err = -EINVAL; - if (msg->msg_namelen < sizeof(struct sockaddr_ll)) -@@ -2660,10 +2659,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) - sll_addr))) - goto out; - proto = saddr->sll_protocol; -- addr = saddr->sll_halen ? saddr->sll_addr : NULL; - dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); -- if (addr && dev && saddr->sll_halen < dev->addr_len) -- goto out_put; -+ if (po->sk.sk_socket->type == SOCK_DGRAM) { -+ if (dev && msg->msg_namelen < dev->addr_len + -+ offsetof(struct sockaddr_ll, sll_addr)) -+ goto out_put; -+ addr = saddr->sll_addr; -+ } - } - - err = -ENXIO; -@@ -2834,7 +2836,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) - struct sk_buff *skb; - struct net_device *dev; - __be16 proto; -- unsigned char *addr; -+ unsigned char *addr = NULL; - int err, reserve = 0; - struct sockcm_cookie sockc; - struct virtio_net_hdr vnet_hdr = { 0 }; -@@ -2851,7 +2853,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) - if (likely(saddr == NULL)) { - dev = packet_cached_dev_get(po); - proto = po->num; -- addr = NULL; - } else { - err = -EINVAL; - if (msg->msg_namelen < sizeof(struct sockaddr_ll)) -@@ -2859,10 +2860,13 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) - if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) - goto out; - proto = saddr->sll_protocol; -- addr = saddr->sll_halen ? saddr->sll_addr : NULL; - dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); -- if (addr && dev && saddr->sll_halen < dev->addr_len) -- goto out_unlock; -+ if (sock->type == SOCK_DGRAM) { -+ if (dev && msg->msg_namelen < dev->addr_len + -+ offsetof(struct sockaddr_ll, sll_addr)) -+ goto out_unlock; -+ addr = saddr->sll_addr; -+ } - } - - err = -ENXIO; -diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c -index 9bd6f97ccd21..772df402c495 100644 ---- a/security/selinux/hooks.c -+++ b/security/selinux/hooks.c -@@ -467,21 +467,43 @@ static int may_context_mount_inode_relabel(u32 sid, - return rc; - } - --static int selinux_is_sblabel_mnt(struct super_block *sb) -+static int selinux_is_genfs_special_handling(struct super_block *sb) - { -- struct superblock_security_struct *sbsec = sb->s_security; -- -- return sbsec->behavior == SECURITY_FS_USE_XATTR || -- sbsec->behavior == SECURITY_FS_USE_TRANS || -- sbsec->behavior == SECURITY_FS_USE_TASK || -- sbsec->behavior == SECURITY_FS_USE_NATIVE || -- /* Special handling. Genfs but also in-core setxattr handler */ -- !strcmp(sb->s_type->name, "sysfs") || -+ /* Special handling. Genfs but also in-core setxattr handler */ -+ return !strcmp(sb->s_type->name, "sysfs") || - !strcmp(sb->s_type->name, "pstore") || - !strcmp(sb->s_type->name, "debugfs") || - !strcmp(sb->s_type->name, "rootfs"); - } - -+static int selinux_is_sblabel_mnt(struct super_block *sb) -+{ -+ struct superblock_security_struct *sbsec = sb->s_security; -+ -+ /* -+ * IMPORTANT: Double-check logic in this function when adding a new -+ * SECURITY_FS_USE_* definition! -+ */ -+ BUILD_BUG_ON(SECURITY_FS_USE_MAX != 7); -+ -+ switch (sbsec->behavior) { -+ case SECURITY_FS_USE_XATTR: -+ case SECURITY_FS_USE_TRANS: -+ case SECURITY_FS_USE_TASK: -+ case SECURITY_FS_USE_NATIVE: -+ return 1; -+ -+ case SECURITY_FS_USE_GENFS: -+ return selinux_is_genfs_special_handling(sb); -+ -+ /* Never allow relabeling on context mounts */ -+ case SECURITY_FS_USE_MNTPOINT: -+ case SECURITY_FS_USE_NONE: -+ default: -+ return 0; -+ } -+} -+ - static int sb_finish_set_opts(struct super_block *sb) - { - struct superblock_security_struct *sbsec = sb->s_security; -diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c -index 58d624938a9f..09189249d0d1 100644 ---- a/sound/usb/line6/driver.c -+++ b/sound/usb/line6/driver.c -@@ -337,12 +337,16 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data, - { - struct usb_device *usbdev = line6->usbdev; - int ret; -- unsigned char len; -+ unsigned char *len; - unsigned count; - - if (address > 0xffff || datalen > 0xff) - return -EINVAL; - -+ len = kmalloc(sizeof(*len), GFP_KERNEL); -+ if (!len) -+ return -ENOMEM; -+ - /* query the serial number: */ - ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), 0x67, - USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT, -@@ -351,7 +355,7 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data, - - if (ret < 0) { - dev_err(line6->ifcdev, "read request failed (error %d)\n", ret); -- return ret; -+ goto exit; - } - - /* Wait for data length. We'll get 0xff until length arrives. */ -@@ -361,28 +365,29 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data, - ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0), 0x67, - USB_TYPE_VENDOR | USB_RECIP_DEVICE | - USB_DIR_IN, -- 0x0012, 0x0000, &len, 1, -+ 0x0012, 0x0000, len, 1, - LINE6_TIMEOUT * HZ); - if (ret < 0) { - dev_err(line6->ifcdev, - "receive length failed (error %d)\n", ret); -- return ret; -+ goto exit; - } - -- if (len != 0xff) -+ if (*len != 0xff) - break; - } - -- if (len == 0xff) { -+ ret = -EIO; -+ if (*len == 0xff) { - dev_err(line6->ifcdev, "read failed after %d retries\n", - count); -- return -EIO; -- } else if (len != datalen) { -+ goto exit; -+ } else if (*len != datalen) { - /* should be equal or something went wrong */ - dev_err(line6->ifcdev, - "length mismatch (expected %d, got %d)\n", -- (int)datalen, (int)len); -- return -EIO; -+ (int)datalen, (int)*len); -+ goto exit; - } - - /* receive the result: */ -@@ -391,12 +396,12 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data, - 0x0013, 0x0000, data, datalen, - LINE6_TIMEOUT * HZ); - -- if (ret < 0) { -+ if (ret < 0) - dev_err(line6->ifcdev, "read failed (error %d)\n", ret); -- return ret; -- } - -- return 0; -+exit: -+ kfree(len); -+ return ret; - } - EXPORT_SYMBOL_GPL(line6_read_data); - -@@ -408,12 +413,16 @@ int line6_write_data(struct usb_line6 *line6, unsigned address, void *data, - { - struct usb_device *usbdev = line6->usbdev; - int ret; -- unsigned char status; -+ unsigned char *status; - int count; - - if (address > 0xffff || datalen > 0xffff) - return -EINVAL; - -+ status = kmalloc(sizeof(*status), GFP_KERNEL); -+ if (!status) -+ return -ENOMEM; -+ - ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), 0x67, - USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT, - 0x0022, address, data, datalen, -@@ -422,7 +431,7 @@ int line6_write_data(struct usb_line6 *line6, unsigned address, void *data, - if (ret < 0) { - dev_err(line6->ifcdev, - "write request failed (error %d)\n", ret); -- return ret; -+ goto exit; - } - - for (count = 0; count < LINE6_READ_WRITE_MAX_RETRIES; count++) { -@@ -433,28 +442,29 @@ int line6_write_data(struct usb_line6 *line6, unsigned address, void *data, - USB_TYPE_VENDOR | USB_RECIP_DEVICE | - USB_DIR_IN, - 0x0012, 0x0000, -- &status, 1, LINE6_TIMEOUT * HZ); -+ status, 1, LINE6_TIMEOUT * HZ); - - if (ret < 0) { - dev_err(line6->ifcdev, - "receiving status failed (error %d)\n", ret); -- return ret; -+ goto exit; - } - -- if (status != 0xff) -+ if (*status != 0xff) - break; - } - -- if (status == 0xff) { -+ if (*status == 0xff) { - dev_err(line6->ifcdev, "write failed after %d retries\n", - count); -- return -EIO; -- } else if (status != 0) { -+ ret = -EIO; -+ } else if (*status != 0) { - dev_err(line6->ifcdev, "write failed (error %d)\n", ret); -- return -EIO; -+ ret = -EIO; - } -- -- return 0; -+exit: -+ kfree(status); -+ return ret; - } - EXPORT_SYMBOL_GPL(line6_write_data); - -diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c -index 5ab9e0c89211..c0b6733c0623 100644 ---- a/sound/usb/line6/podhd.c -+++ b/sound/usb/line6/podhd.c -@@ -221,28 +221,32 @@ static void podhd_startup_start_workqueue(unsigned long data) - static int podhd_dev_start(struct usb_line6_podhd *pod) - { - int ret; -- u8 init_bytes[8]; -+ u8 *init_bytes; - int i; - struct usb_device *usbdev = pod->line6.usbdev; - -+ init_bytes = kmalloc(8, GFP_KERNEL); -+ if (!init_bytes) -+ return -ENOMEM; -+ - ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), - 0x67, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT, - 0x11, 0, - NULL, 0, LINE6_TIMEOUT * HZ); - if (ret < 0) { - dev_err(pod->line6.ifcdev, "read request failed (error %d)\n", ret); -- return ret; -+ goto exit; - } - - /* NOTE: looks like some kind of ping message */ - ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0), 0x67, - USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN, - 0x11, 0x0, -- &init_bytes, 3, LINE6_TIMEOUT * HZ); -+ init_bytes, 3, LINE6_TIMEOUT * HZ); - if (ret < 0) { - dev_err(pod->line6.ifcdev, - "receive length failed (error %d)\n", ret); -- return ret; -+ goto exit; - } - - pod->firmware_version = -@@ -251,7 +255,7 @@ static int podhd_dev_start(struct usb_line6_podhd *pod) - for (i = 0; i <= 16; i++) { - ret = line6_read_data(&pod->line6, 0xf000 + 0x08 * i, init_bytes, 8); - if (ret < 0) -- return ret; -+ goto exit; - } - - ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), -@@ -259,10 +263,9 @@ static int podhd_dev_start(struct usb_line6_podhd *pod) - USB_TYPE_STANDARD | USB_RECIP_DEVICE | USB_DIR_OUT, - 1, 0, - NULL, 0, LINE6_TIMEOUT * HZ); -- if (ret < 0) -- return ret; -- -- return 0; -+exit: -+ kfree(init_bytes); -+ return ret; - } - - static void podhd_startup_workqueue(struct work_struct *work) -diff --git a/sound/usb/line6/toneport.c b/sound/usb/line6/toneport.c -index 8e22f430d700..d3871d99ade4 100644 ---- a/sound/usb/line6/toneport.c -+++ b/sound/usb/line6/toneport.c -@@ -365,15 +365,20 @@ static bool toneport_has_source_select(struct usb_line6_toneport *toneport) - /* - Setup Toneport device. - */ --static void toneport_setup(struct usb_line6_toneport *toneport) -+static int toneport_setup(struct usb_line6_toneport *toneport) - { -- int ticks; -+ int *ticks; - struct usb_line6 *line6 = &toneport->line6; - struct usb_device *usbdev = line6->usbdev; - -+ ticks = kmalloc(sizeof(*ticks), GFP_KERNEL); -+ if (!ticks) -+ return -ENOMEM; -+ - /* sync time on device with host: */ -- ticks = (int)get_seconds(); -- line6_write_data(line6, 0x80c6, &ticks, 4); -+ *ticks = (int)get_seconds(); -+ line6_write_data(line6, 0x80c6, ticks, 4); -+ kfree(ticks); - - /* enable device: */ - toneport_send_cmd(usbdev, 0x0301, 0x0000); -@@ -388,6 +393,7 @@ static void toneport_setup(struct usb_line6_toneport *toneport) - toneport_update_led(toneport); - - mod_timer(&toneport->timer, jiffies + TONEPORT_PCM_DELAY * HZ); -+ return 0; - } - - /* -@@ -451,7 +457,9 @@ static int toneport_init(struct usb_line6 *line6, - return err; - } - -- toneport_setup(toneport); -+ err = toneport_setup(toneport); -+ if (err) -+ return err; - - /* register audio system: */ - return snd_card_register(line6->card); -@@ -463,7 +471,11 @@ static int toneport_init(struct usb_line6 *line6, - */ - static int toneport_reset_resume(struct usb_interface *interface) - { -- toneport_setup(usb_get_intfdata(interface)); -+ int err; -+ -+ err = toneport_setup(usb_get_intfdata(interface)); -+ if (err) -+ return err; - return line6_resume(interface); - } - #endif diff --git a/patch/kernel/odroidn2-dev/general-packaging-4.20-dev.patch b/patch/kernel/odroidn2-dev/general-packaging-4.20-dev.patch new file mode 100644 index 0000000000..12222b81e7 --- /dev/null +++ b/patch/kernel/odroidn2-dev/general-packaging-4.20-dev.patch @@ -0,0 +1,221 @@ +diff --git a/scripts/package/builddeb b/scripts/package/builddeb +index 90c9a8a..3c79b90 100755 +--- a/scripts/package/builddeb ++++ b/scripts/package/builddeb +@@ -29,6 +29,27 @@ create_package() { + # in case we are in a restrictive umask environment like 0077 + chmod -R a+rX "$pdir" + ++ # Create preinstall and post install script to remove dtb ++ if [[ "$1" == *dtb* ]]; then ++ echo "if [ -d /boot/dtb-$version ]; then mv /boot/dtb-$version /boot/dtb-$version.old; fi" >> $pdir/DEBIAN/preinst ++ echo "if [ -d /boot/dtb.old ]; then rm -rf /boot/dtb.old; fi" >> $pdir/DEBIAN/preinst ++ echo "if [ -d /boot/dtb ]; then mv /boot/dtb /boot/dtb.old; fi" >> $pdir/DEBIAN/preinst ++ echo "exit 0" >> $pdir/DEBIAN/preinst ++ chmod 775 $pdir/DEBIAN/preinst ++ ++ echo "if [ -d /boot/dtb-$version.old ]; then rm -rf /boot/dtb-$version.old; fi" >> $pdir/DEBIAN/postinst ++ echo "ln -sf dtb-$version /boot/dtb > /dev/null 2>&1 || mv /boot/dtb-$version /boot/dtb" >> $pdir/DEBIAN/postinst ++ echo "exit 0" >> $pdir/DEBIAN/postinst ++ chmod 775 $pdir/DEBIAN/postinst ++ fi ++ ++ # Create postinstall script for headers ++ if [[ "$1" == *headers* ]]; then ++ echo "cd /usr/src/linux-headers-$version; echo \"Compiling headers - please wait ...\"; find -type f -exec touch {} +;make -s scripts >/dev/null 2>&1" >> $pdir/DEBIAN/postinst ++ echo "exit 0" >> $pdir/DEBIAN/postinst ++ chmod 775 $pdir/DEBIAN/postinst ++ fi ++ + # Create the package + dpkg-gencontrol -p$pname -P"$pdir" + dpkg --build "$pdir" .. +@@ -39,9 +60,11 @@ tmpdir="$objtree/debian/tmp" + kernel_headers_dir="$objtree/debian/hdrtmp" + libc_headers_dir="$objtree/debian/headertmp" + dbg_dir="$objtree/debian/dbgtmp" +-packagename=linux-image-$version +-kernel_headers_packagename=linux-headers-$version +-libc_headers_packagename=linux-libc-dev ++dtb_dir="$objtree/debian/dtbtmp" ++packagename=linux-image-dev"$LOCALVERSION" ++kernel_headers_packagename=linux-headers-dev"$LOCALVERSION" ++dtb_packagename=linux-dtb-dev"$LOCALVERSION" ++libc_headers_packagename=linux-libc-dev-dev"$LOCALVERSION" + dbg_packagename=$packagename-dbg + + if [ "$ARCH" = "um" ] ; then +@@ -52,6 +75,15 @@ fi + # XXX: have each arch Makefile export a variable of the canonical image install + # path instead + case $ARCH in ++aarch64|arm64) ++ image_name=Image ++ installed_image_path="boot/vmlinuz-$version" ++ ++ ;; ++arm*) ++ image_name=zImage ++ installed_image_path="boot/vmlinuz-$version" ++ ;; + um) + installed_image_path="usr/bin/linux-$version" + ;; +@@ -65,7 +97,9 @@ esac + BUILD_DEBUG="$(grep -s '^CONFIG_DEBUG_INFO=y' $KCONFIG_CONFIG || true)" + + # Setup the directory structure +-rm -rf "$tmpdir" "$kernel_headers_dir" "$libc_headers_dir" "$dbg_dir" $objtree/debian/files ++rm -rf "$tmpdir" "$kernel_headers_dir" "$libc_headers_dir" "$dbg_dir" "$dtb_dir" $objtree/debian/files ++mkdir -m 755 -p "$dtb_dir/DEBIAN" ++mkdir -p "$dtb_dir/boot/dtb-$version" "$dtb_dir/usr/share/doc/$dtb_packagename" + mkdir -m 755 -p "$tmpdir/DEBIAN" + mkdir -p "$tmpdir/lib" "$tmpdir/boot" + mkdir -p "$kernel_headers_dir/lib/modules/$version/" +@@ -118,6 +152,11 @@ if grep -q '^CONFIG_MODULES=y' $KCONFIG_CONFIG ; then + fi + fi + ++if grep -q '^CONFIG_OF=y' $KCONFIG_CONFIG ; then ++ #mkdir -p "$tmpdir/boot/dtb" ++ INSTALL_DTBS_PATH="$dtb_dir/boot/dtb-$version" $MAKE KBUILD_SRC= dtbs_install ++fi ++ + if [ "$ARCH" != "um" ]; then + $MAKE headers_check KBUILD_SRC= + $MAKE headers_install KBUILD_SRC= INSTALL_HDR_PATH="$libc_headers_dir/usr" +@@ -137,7 +176,7 @@ fi + for script in postinst postrm preinst prerm ; do + mkdir -p "$tmpdir$debhookdir/$script.d" + cat < "$tmpdir/DEBIAN/$script" +-#!/bin/sh ++#!/bin/bash + + set -e + +@@ -153,9 +192,60 @@ EOF + chmod 755 "$tmpdir/DEBIAN/$script" + done + ++## ++## Create sym link to kernel image ++## ++sed -e "s/set -e//g" -i $tmpdir/DEBIAN/postinst ++sed -e "s/exit 0//g" -i $tmpdir/DEBIAN/postinst ++cat >> $tmpdir/DEBIAN/postinst < /dev/null 2>&1 ++ cp /boot/uImage /tmp/uImage ++ sync ++ mountpoint -q /boot || mount /boot ++ cp /tmp/uImage /boot/uImage ++ rm -f /$installed_image_path ++else ++ ln -sf $(basename $installed_image_path) /boot/$image_name || mv /$installed_image_path /boot/$image_name ++fi ++touch /boot/.next ++exit 0 ++EOT ++ ++## ++## FAT install workaround ++## ++sed -e "s/set -e//g" -i $tmpdir/DEBIAN/preinst ++sed -e "s/exit 0//g" -i $tmpdir/DEBIAN/preinst ++cat >> $tmpdir/DEBIAN/preinst <> $tmpdir/DEBIAN/preinst ++ + # Build kernel header package + (cd $srctree; find . -name Makefile\* -o -name Kconfig\* -o -name \*.pl) > "$objtree/debian/hdrsrcfiles" + (cd $srctree; find arch/*/include include scripts -type f -o -type l) >> "$objtree/debian/hdrsrcfiles" ++(cd $srctree; find security/*/include -type f) >> "$objtree/debian/hdrsrcfiles" + (cd $srctree; find arch/$SRCARCH -name module.lds -o -name Kbuild.platforms -o -name Platform) >> "$objtree/debian/hdrsrcfiles" + (cd $srctree; find $(find arch/$SRCARCH -name include -o -name scripts -type d) -type f) >> "$objtree/debian/hdrsrcfiles" + if grep -q '^CONFIG_STACK_VALIDATION=y' $KCONFIG_CONFIG ; then +@@ -167,15 +257,19 @@ if grep -q '^CONFIG_GCC_PLUGINS=y' $KCONFIG_CONFIG ; then + fi + destdir=$kernel_headers_dir/usr/src/linux-headers-$version + mkdir -p "$destdir" ++(cd $destdir; patch -p1 < /tmp/headers-debian-byteshift.patch) + (cd $srctree; tar -c -f - -T -) < "$objtree/debian/hdrsrcfiles" | (cd $destdir; tar -xf -) + (cd $objtree; tar -c -f - -T -) < "$objtree/debian/hdrobjfiles" | (cd $destdir; tar -xf -) + (cd $objtree; cp $KCONFIG_CONFIG $destdir/.config) # copy .config manually to be where it's expected to be + ln -sf "/usr/src/linux-headers-$version" "$kernel_headers_dir/lib/modules/$version/build" + rm -f "$objtree/debian/hdrsrcfiles" "$objtree/debian/hdrobjfiles" + ++(cd $destdir; make M=scripts clean) ++ + if [ "$ARCH" != "um" ]; then + create_package "$kernel_headers_packagename" "$kernel_headers_dir" +- create_package "$libc_headers_packagename" "$libc_headers_dir" ++ # create_package "$libc_headers_packagename" "$libc_headers_dir" ++ create_package "$dtb_packagename" "$dtb_dir" + fi + + create_package "$packagename" "$tmpdir" +diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian +index 6adb3a1..00e12eb 100755 +--- a/scripts/package/mkdebian ++++ b/scripts/package/mkdebian +@@ -61,10 +61,12 @@ else + packageversion=$version-$revision + fi + sourcename=$KDEB_SOURCENAME +-packagename=linux-image-$version +-kernel_headers_packagename=linux-headers-$version ++packagename=linux-image-dev$LOCALVERSION ++kernel_headers_packagename=linux-headers-dev$LOCALVERSION ++dtb_packagename=linux-dtb-dev$LOCALVERSION + dbg_packagename=$packagename-dbg + debarch= ++image_name= + set_debarch + + if [ "$ARCH" = "um" ] ; then +@@ -168,6 +170,11 @@ Architecture: $debarch + Description: Linux kernel debugging symbols for $version + This package will come in handy if you need to debug the kernel. It provides + all the necessary debug symbols for the kernel and its modules. ++ ++Package: $dtb_packagename ++Architecture: $debarch ++Description: Linux DTB, version $version ++ This package contains device blobs from the Linux kernel, version $version + EOF + + cat < debian/rules +diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile +index f839ecd9..cd276162 100644 +--- a/arch/arm64/Makefile ++++ b/arch/arm64/Makefile +@@ -103,7 +103,7 @@ core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a + + # Default target when executing plain make + boot := arch/arm64/boot +-KBUILD_IMAGE := $(boot)/Image.gz ++KBUILD_IMAGE := $(boot)/Image + + all: Image.gz $(KBUILD_DTBS) + diff --git a/patch/kernel/odroidn2-next/general-packaging-4.20-dev.patch b/patch/kernel/odroidn2-next/general-packaging-4.20-dev.patch new file mode 100644 index 0000000000..0cd36cc73f --- /dev/null +++ b/patch/kernel/odroidn2-next/general-packaging-4.20-dev.patch @@ -0,0 +1,221 @@ +diff --git a/scripts/package/builddeb b/scripts/package/builddeb +index 90c9a8a..3c79b90 100755 +--- a/scripts/package/builddeb ++++ b/scripts/package/builddeb +@@ -29,6 +29,27 @@ create_package() { + # in case we are in a restrictive umask environment like 0077 + chmod -R a+rX "$pdir" + ++ # Create preinstall and post install script to remove dtb ++ if [[ "$1" == *dtb* ]]; then ++ echo "if [ -d /boot/dtb-$version ]; then mv /boot/dtb-$version /boot/dtb-$version.old; fi" >> $pdir/DEBIAN/preinst ++ echo "if [ -d /boot/dtb.old ]; then rm -rf /boot/dtb.old; fi" >> $pdir/DEBIAN/preinst ++ echo "if [ -d /boot/dtb ]; then mv /boot/dtb /boot/dtb.old; fi" >> $pdir/DEBIAN/preinst ++ echo "exit 0" >> $pdir/DEBIAN/preinst ++ chmod 775 $pdir/DEBIAN/preinst ++ ++ echo "if [ -d /boot/dtb-$version.old ]; then rm -rf /boot/dtb-$version.old; fi" >> $pdir/DEBIAN/postinst ++ echo "ln -sf dtb-$version /boot/dtb > /dev/null 2>&1 || mv /boot/dtb-$version /boot/dtb" >> $pdir/DEBIAN/postinst ++ echo "exit 0" >> $pdir/DEBIAN/postinst ++ chmod 775 $pdir/DEBIAN/postinst ++ fi ++ ++ # Create postinstall script for headers ++ if [[ "$1" == *headers* ]]; then ++ echo "cd /usr/src/linux-headers-$version; echo \"Compiling headers - please wait ...\"; find -type f -exec touch {} +;make -s scripts >/dev/null 2>&1" >> $pdir/DEBIAN/postinst ++ echo "exit 0" >> $pdir/DEBIAN/postinst ++ chmod 775 $pdir/DEBIAN/postinst ++ fi ++ + # Create the package + dpkg-gencontrol -p$pname -P"$pdir" + dpkg --build "$pdir" .. +@@ -39,9 +60,11 @@ tmpdir="$objtree/debian/tmp" + kernel_headers_dir="$objtree/debian/hdrtmp" + libc_headers_dir="$objtree/debian/headertmp" + dbg_dir="$objtree/debian/dbgtmp" +-packagename=linux-image-$version +-kernel_headers_packagename=linux-headers-$version +-libc_headers_packagename=linux-libc-dev ++dtb_dir="$objtree/debian/dtbtmp" ++packagename=linux-image-next"$LOCALVERSION" ++kernel_headers_packagename=linux-headers-next"$LOCALVERSION" ++dtb_packagename=linux-dtb-next"$LOCALVERSION" ++libc_headers_packagename=linux-libc-dev-next"$LOCALVERSION" + dbg_packagename=$packagename-dbg + + if [ "$ARCH" = "um" ] ; then +@@ -52,6 +75,15 @@ fi + # XXX: have each arch Makefile export a variable of the canonical image install + # path instead + case $ARCH in ++aarch64|arm64) ++ image_name=Image ++ installed_image_path="boot/vmlinuz-$version" ++ ++ ;; ++arm*) ++ image_name=zImage ++ installed_image_path="boot/vmlinuz-$version" ++ ;; + um) + installed_image_path="usr/bin/linux-$version" + ;; +@@ -65,7 +97,9 @@ esac + BUILD_DEBUG="$(grep -s '^CONFIG_DEBUG_INFO=y' $KCONFIG_CONFIG || true)" + + # Setup the directory structure +-rm -rf "$tmpdir" "$kernel_headers_dir" "$libc_headers_dir" "$dbg_dir" $objtree/debian/files ++rm -rf "$tmpdir" "$kernel_headers_dir" "$libc_headers_dir" "$dbg_dir" "$dtb_dir" $objtree/debian/files ++mkdir -m 755 -p "$dtb_dir/DEBIAN" ++mkdir -p "$dtb_dir/boot/dtb-$version" "$dtb_dir/usr/share/doc/$dtb_packagename" + mkdir -m 755 -p "$tmpdir/DEBIAN" + mkdir -p "$tmpdir/lib" "$tmpdir/boot" + mkdir -p "$kernel_headers_dir/lib/modules/$version/" +@@ -118,6 +152,11 @@ if grep -q '^CONFIG_MODULES=y' $KCONFIG_CONFIG ; then + fi + fi + ++if grep -q '^CONFIG_OF=y' $KCONFIG_CONFIG ; then ++ #mkdir -p "$tmpdir/boot/dtb" ++ INSTALL_DTBS_PATH="$dtb_dir/boot/dtb-$version" $MAKE KBUILD_SRC= dtbs_install ++fi ++ + if [ "$ARCH" != "um" ]; then + $MAKE headers_check KBUILD_SRC= + $MAKE headers_install KBUILD_SRC= INSTALL_HDR_PATH="$libc_headers_dir/usr" +@@ -137,7 +176,7 @@ fi + for script in postinst postrm preinst prerm ; do + mkdir -p "$tmpdir$debhookdir/$script.d" + cat < "$tmpdir/DEBIAN/$script" +-#!/bin/sh ++#!/bin/bash + + set -e + +@@ -153,9 +192,60 @@ EOF + chmod 755 "$tmpdir/DEBIAN/$script" + done + ++## ++## Create sym link to kernel image ++## ++sed -e "s/set -e//g" -i $tmpdir/DEBIAN/postinst ++sed -e "s/exit 0//g" -i $tmpdir/DEBIAN/postinst ++cat >> $tmpdir/DEBIAN/postinst < /dev/null 2>&1 ++ cp /boot/uImage /tmp/uImage ++ sync ++ mountpoint -q /boot || mount /boot ++ cp /tmp/uImage /boot/uImage ++ rm -f /$installed_image_path ++else ++ ln -sf $(basename $installed_image_path) /boot/$image_name || mv /$installed_image_path /boot/$image_name ++fi ++touch /boot/.next ++exit 0 ++EOT ++ ++## ++## FAT install workaround ++## ++sed -e "s/set -e//g" -i $tmpdir/DEBIAN/preinst ++sed -e "s/exit 0//g" -i $tmpdir/DEBIAN/preinst ++cat >> $tmpdir/DEBIAN/preinst <> $tmpdir/DEBIAN/preinst ++ + # Build kernel header package + (cd $srctree; find . -name Makefile\* -o -name Kconfig\* -o -name \*.pl) > "$objtree/debian/hdrsrcfiles" + (cd $srctree; find arch/*/include include scripts -type f -o -type l) >> "$objtree/debian/hdrsrcfiles" ++(cd $srctree; find security/*/include -type f) >> "$objtree/debian/hdrsrcfiles" + (cd $srctree; find arch/$SRCARCH -name module.lds -o -name Kbuild.platforms -o -name Platform) >> "$objtree/debian/hdrsrcfiles" + (cd $srctree; find $(find arch/$SRCARCH -name include -o -name scripts -type d) -type f) >> "$objtree/debian/hdrsrcfiles" + if grep -q '^CONFIG_STACK_VALIDATION=y' $KCONFIG_CONFIG ; then +@@ -167,15 +257,19 @@ if grep -q '^CONFIG_GCC_PLUGINS=y' $KCONFIG_CONFIG ; then + fi + destdir=$kernel_headers_dir/usr/src/linux-headers-$version + mkdir -p "$destdir" ++(cd $destdir; patch -p1 < /tmp/headers-debian-byteshift.patch) + (cd $srctree; tar -c -f - -T -) < "$objtree/debian/hdrsrcfiles" | (cd $destdir; tar -xf -) + (cd $objtree; tar -c -f - -T -) < "$objtree/debian/hdrobjfiles" | (cd $destdir; tar -xf -) + (cd $objtree; cp $KCONFIG_CONFIG $destdir/.config) # copy .config manually to be where it's expected to be + ln -sf "/usr/src/linux-headers-$version" "$kernel_headers_dir/lib/modules/$version/build" + rm -f "$objtree/debian/hdrsrcfiles" "$objtree/debian/hdrobjfiles" + ++(cd $destdir; make M=scripts clean) ++ + if [ "$ARCH" != "um" ]; then + create_package "$kernel_headers_packagename" "$kernel_headers_dir" +- create_package "$libc_headers_packagename" "$libc_headers_dir" ++ # create_package "$libc_headers_packagename" "$libc_headers_dir" ++ create_package "$dtb_packagename" "$dtb_dir" + fi + + create_package "$packagename" "$tmpdir" +diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian +index 6adb3a1..00e12eb 100755 +--- a/scripts/package/mkdebian ++++ b/scripts/package/mkdebian +@@ -61,10 +61,12 @@ else + packageversion=$version-$revision + fi + sourcename=$KDEB_SOURCENAME +-packagename=linux-image-$version +-kernel_headers_packagename=linux-headers-$version ++packagename=linux-image-next$LOCALVERSION ++kernel_headers_packagename=linux-headers-next$LOCALVERSION ++dtb_packagename=linux-dtb-next$LOCALVERSION + dbg_packagename=$packagename-dbg + debarch= ++image_name= + set_debarch + + if [ "$ARCH" = "um" ] ; then +@@ -168,6 +170,11 @@ Architecture: $debarch + Description: Linux kernel debugging symbols for $version + This package will come in handy if you need to debug the kernel. It provides + all the necessary debug symbols for the kernel and its modules. ++ ++Package: $dtb_packagename ++Architecture: $debarch ++Description: Linux DTB, version $version ++ This package contains device blobs from the Linux kernel, version $version + EOF + + cat < debian/rules +diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile +index f839ecd9..cd276162 100644 +--- a/arch/arm64/Makefile ++++ b/arch/arm64/Makefile +@@ -103,7 +103,7 @@ core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a + + # Default target when executing plain make + boot := arch/arm64/boot +-KBUILD_IMAGE := $(boot)/Image.gz ++KBUILD_IMAGE := $(boot)/Image + + all: Image.gz $(KBUILD_DTBS) +