From b1c387cec595ab956c38fc4c75f0f3b4a2d15cb7 Mon Sep 17 00:00:00 2001 From: Igor Pecovnik Date: Tue, 23 Aug 2016 14:12:46 +0200 Subject: [PATCH] RT patch (disabled) with some fixes by ChrisK http://forum.armbian.com/index.php/topic/1885-rt-patches-for-sun8i-kernel/ --- ...ng-genhd-include-in-firmware_class.c.patch | 11 + .../30001-rt143-full.patch.disabled | 24451 ++++++++++++++++ ...002-disable-sunxi-ss-when-no-highmem.patch | 10 + .../sun8i-default/30003-fix-timerfd.patch | 11 + .../sun8i-default/30004-add-irqpriority.patch | 200 + ...-irq-set-affinity-hint-work-properly.patch | 12 + 6 files changed, 24695 insertions(+) create mode 100644 patch/kernel/sun8i-default/30000-fix-missing-genhd-include-in-firmware_class.c.patch create mode 100644 patch/kernel/sun8i-default/30001-rt143-full.patch.disabled create mode 100644 patch/kernel/sun8i-default/30002-disable-sunxi-ss-when-no-highmem.patch create mode 100644 patch/kernel/sun8i-default/30003-fix-timerfd.patch create mode 100644 patch/kernel/sun8i-default/30004-add-irqpriority.patch create mode 100644 patch/kernel/sun8i-default/30005-make-irq-set-affinity-hint-work-properly.patch diff --git a/patch/kernel/sun8i-default/30000-fix-missing-genhd-include-in-firmware_class.c.patch b/patch/kernel/sun8i-default/30000-fix-missing-genhd-include-in-firmware_class.c.patch new file mode 100644 index 0000000000..0089df8702 --- /dev/null +++ b/patch/kernel/sun8i-default/30000-fix-missing-genhd-include-in-firmware_class.c.patch @@ -0,0 +1,11 @@ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/base/firmware_class.c sun8i-rt/drivers/base/firmware_class.c +--- sun8i/drivers/base/firmware_class.c 2016-08-22 14:14:41.000000000 +0200 ++++ sun8i-rt/drivers/base/firmware_class.c 2016-08-22 18:58:39.756320362 +0200 +@@ -27,6 +27,7 @@ + #include + #include + #include ++#include + + #include + diff --git a/patch/kernel/sun8i-default/30001-rt143-full.patch.disabled b/patch/kernel/sun8i-default/30001-rt143-full.patch.disabled new file mode 100644 index 0000000000..bdd785b5dc --- /dev/null +++ b/patch/kernel/sun8i-default/30001-rt143-full.patch.disabled @@ -0,0 +1,24451 @@ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/alpha/mm/fault.c sun8i-rt/arch/alpha/mm/fault.c +--- sun8i/arch/alpha/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/alpha/mm/fault.c 2016-08-22 16:13:41.848206568 +0200 +@@ -106,7 +106,7 @@ do_page_fault(unsigned long address, uns + + /* If we're in an interrupt context, or have no user context, + we must not take the fault. */ +- if (!mm || in_atomic()) ++ if (!mm || pagefault_disabled()) + goto no_context; + + #ifdef CONFIG_ALPHA_LARGE_VMALLOC +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/include/asm/cmpxchg.h sun8i-rt/arch/arm/include/asm/cmpxchg.h +--- sun8i/arch/arm/include/asm/cmpxchg.h 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/include/asm/cmpxchg.h 2016-08-22 18:24:25.668296747 +0200 +@@ -127,6 +127,8 @@ static inline unsigned long __xchg(unsig + + #else /* min ARCH >= ARMv6 */ + ++#define __HAVE_ARCH_CMPXCHG 1 ++ + extern void __bad_cmpxchg(volatile void *ptr, int size); + + /* +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/include/asm/futex.h sun8i-rt/arch/arm/include/asm/futex.h +--- sun8i/arch/arm/include/asm/futex.h 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/include/asm/futex.h 2016-08-22 18:24:14.204296615 +0200 +@@ -94,6 +94,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + return -EFAULT; + ++ preempt_disable_rt(); ++ + __asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n" + "1: " TUSER(ldr) " %1, [%4]\n" + " teq %1, %2\n" +@@ -105,6 +107,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, + : "cc", "memory"); + + *uval = val; ++ ++ preempt_enable_rt(); + return ret; + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/Kconfig sun8i-rt/arch/arm/Kconfig +--- sun8i/arch/arm/Kconfig 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/arch/arm/Kconfig 2016-08-22 17:46:55.508270877 +0200 +@@ -32,6 +32,7 @@ config ARM + select HAVE_C_RECORDMCOUNT + select HAVE_GENERIC_HARDIRQS + select GENERIC_IRQ_SHOW ++ select IRQ_FORCED_THREADING + select CPU_PM if (SUSPEND || CPU_IDLE) + select GENERIC_PCI_IOMAP + select HAVE_BPF_JIT if NET +@@ -1942,7 +1943,7 @@ config HAVE_ARCH_PFN_VALID + + config HIGHMEM + bool "High Memory Support" +- depends on MMU ++ depends on MMU && !PREEMPT_RT_FULL + help + The address space of ARM processors is only 4 Gigabytes large + and it has to accommodate user address space, kernel address +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/kernel/early_printk.c sun8i-rt/arch/arm/kernel/early_printk.c +--- sun8i/arch/arm/kernel/early_printk.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/kernel/early_printk.c 2016-08-22 16:29:00.332217128 +0200 +@@ -40,28 +40,17 @@ static void early_console_write(struct c + early_write(s, n); + } + +-static struct console early_console = { ++static struct console early_console_dev = { + .name = "earlycon", + .write = early_console_write, + .flags = CON_PRINTBUFFER | CON_BOOT, + .index = -1, + }; + +-asmlinkage void early_printk(const char *fmt, ...) +-{ +- char buf[512]; +- int n; +- va_list ap; +- +- va_start(ap, fmt); +- n = vscnprintf(buf, sizeof(buf), fmt, ap); +- early_write(buf, n); +- va_end(ap); +-} +- + static int __init setup_early_printk(char *buf) + { +- register_console(&early_console); ++ early_console = &early_console_dev; ++ register_console(&early_console_dev); + return 0; + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/kernel/perf_event.c sun8i-rt/arch/arm/kernel/perf_event.c +--- sun8i/arch/arm/kernel/perf_event.c 2016-08-22 14:14:35.000000000 +0200 ++++ sun8i-rt/arch/arm/kernel/perf_event.c 2016-08-22 15:59:34.192196823 +0200 +@@ -454,7 +454,7 @@ armpmu_reserve_hardware(struct arm_pmu * + } + + err = request_irq(irq, handle_irq, +- IRQF_DISABLED | IRQF_NOBALANCING, ++ IRQF_NOBALANCING | IRQF_NO_THREAD, + "arm-pmu", armpmu); + if (err) { + pr_err("unable to request IRQ%d for ARM PMU counters\n", +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/kernel/process.c sun8i-rt/arch/arm/kernel/process.c +--- sun8i/arch/arm/kernel/process.c 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/arch/arm/kernel/process.c 2016-08-22 17:06:22.220242902 +0200 +@@ -654,6 +654,31 @@ unsigned long arch_randomize_brk(struct + } + + #ifdef CONFIG_MMU ++ ++/* ++ * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock. If the lock is not ++ * initialized by pgtable_page_ctor() then a coredump of the vector page will ++ * fail. ++ */ ++static int __init vectors_user_mapping_init_page(void) ++{ ++ struct page *page; ++ unsigned long addr = 0xffff0000; ++ pgd_t *pgd; ++ pud_t *pud; ++ pmd_t *pmd; ++ ++ pgd = pgd_offset_k(addr); ++ pud = pud_offset(pgd, addr); ++ pmd = pmd_offset(pud, addr); ++ page = pmd_page(*(pmd)); ++ ++ pgtable_page_ctor(page); ++ ++ return 0; ++} ++late_initcall(vectors_user_mapping_init_page); ++ + /* + * The vectors page is always readable from user space for the + * atomic helpers and the signal restart code. Insert it into the +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/kernel/signal.c sun8i-rt/arch/arm/kernel/signal.c +--- sun8i/arch/arm/kernel/signal.c 2016-08-22 14:14:41.000000000 +0200 ++++ sun8i-rt/arch/arm/kernel/signal.c 2016-08-22 15:57:37.356195480 +0200 +@@ -628,6 +628,9 @@ static void do_signal(struct pt_regs *re + if (!user_mode(regs)) + return; + ++ local_irq_enable(); ++ preempt_check_resched(); ++ + /* + * If we were from a system call, check for system call restarting... + */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/kernel/unwind.c sun8i-rt/arch/arm/kernel/unwind.c +--- sun8i/arch/arm/kernel/unwind.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/kernel/unwind.c 2016-08-22 18:17:41.260292098 +0200 +@@ -87,7 +87,7 @@ extern const struct unwind_idx __start_u + static const struct unwind_idx *__origin_unwind_idx; + extern const struct unwind_idx __stop_unwind_idx[]; + +-static DEFINE_SPINLOCK(unwind_lock); ++static DEFINE_RAW_SPINLOCK(unwind_lock); + static LIST_HEAD(unwind_tables); + + /* Convert a prel31 symbol to an absolute address */ +@@ -195,7 +195,7 @@ static const struct unwind_idx *unwind_f + /* module unwind tables */ + struct unwind_table *table; + +- spin_lock_irqsave(&unwind_lock, flags); ++ raw_spin_lock_irqsave(&unwind_lock, flags); + list_for_each_entry(table, &unwind_tables, list) { + if (addr >= table->begin_addr && + addr < table->end_addr) { +@@ -207,7 +207,7 @@ static const struct unwind_idx *unwind_f + break; + } + } +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + } + + pr_debug("%s: idx = %p\n", __func__, idx); +@@ -469,9 +469,9 @@ struct unwind_table *unwind_table_add(un + tab->begin_addr = text_addr; + tab->end_addr = text_addr + text_size; + +- spin_lock_irqsave(&unwind_lock, flags); ++ raw_spin_lock_irqsave(&unwind_lock, flags); + list_add_tail(&tab->list, &unwind_tables); +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + + return tab; + } +@@ -483,9 +483,9 @@ void unwind_table_del(struct unwind_tabl + if (!tab) + return; + +- spin_lock_irqsave(&unwind_lock, flags); ++ raw_spin_lock_irqsave(&unwind_lock, flags); + list_del(&tab->list); +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + + kfree(tab); + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/mach-at91/at91rm9200_time.c sun8i-rt/arch/arm/mach-at91/at91rm9200_time.c +--- sun8i/arch/arm/mach-at91/at91rm9200_time.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/mach-at91/at91rm9200_time.c 2016-08-22 16:03:18.096199397 +0200 +@@ -130,6 +130,7 @@ clkevt32k_mode(enum clock_event_mode mod + break; + case CLOCK_EVT_MODE_SHUTDOWN: + case CLOCK_EVT_MODE_UNUSED: ++ remove_irq(AT91_ID_SYS, &at91rm9200_timer_irq); + case CLOCK_EVT_MODE_RESUME: + irqmask = 0; + break; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/mach-at91/at91sam926x_time.c sun8i-rt/arch/arm/mach-at91/at91sam926x_time.c +--- sun8i/arch/arm/mach-at91/at91sam926x_time.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/mach-at91/at91sam926x_time.c 2016-08-22 16:03:18.096199397 +0200 +@@ -67,7 +67,7 @@ static struct clocksource pit_clk = { + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + }; + +- ++static struct irqaction at91sam926x_pit_irq; + /* + * Clockevent device: interrupts every 1/HZ (== pit_cycles * MCK/16) + */ +@@ -76,6 +76,8 @@ pit_clkevt_mode(enum clock_event_mode mo + { + switch (mode) { + case CLOCK_EVT_MODE_PERIODIC: ++ /* Set up irq handler */ ++ setup_irq(AT91_ID_SYS, &at91sam926x_pit_irq); + /* update clocksource counter */ + pit_cnt += pit_cycle * PIT_PICNT(pit_read(AT91_PIT_PIVR)); + pit_write(AT91_PIT_MR, (pit_cycle - 1) | AT91_PIT_PITEN +@@ -88,6 +90,7 @@ pit_clkevt_mode(enum clock_event_mode mo + case CLOCK_EVT_MODE_UNUSED: + /* disable irq, leaving the clocksource active */ + pit_write(AT91_PIT_MR, (pit_cycle - 1) | AT91_PIT_PITEN); ++ remove_irq(AT91_ID_SYS, &at91sam926x_pit_irq); + break; + case CLOCK_EVT_MODE_RESUME: + break; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/mach-exynos/platsmp.c sun8i-rt/arch/arm/mach-exynos/platsmp.c +--- sun8i/arch/arm/mach-exynos/platsmp.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/mach-exynos/platsmp.c 2016-08-22 16:00:11.624197253 +0200 +@@ -55,7 +55,7 @@ static void __iomem *scu_base_addr(void) + return (void __iomem *)(S5P_VA_SCU); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void __cpuinit platform_secondary_init(unsigned int cpu) + { +@@ -75,8 +75,8 @@ void __cpuinit platform_secondary_init(u + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -87,7 +87,7 @@ int __cpuinit boot_secondary(unsigned in + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -116,7 +116,7 @@ int __cpuinit boot_secondary(unsigned in + + if (timeout == 0) { + printk(KERN_ERR "cpu1 power enable failed"); +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + return -ETIMEDOUT; + } + } +@@ -144,7 +144,7 @@ int __cpuinit boot_secondary(unsigned in + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/mach-msm/platsmp.c sun8i-rt/arch/arm/mach-msm/platsmp.c +--- sun8i/arch/arm/mach-msm/platsmp.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/mach-msm/platsmp.c 2016-08-22 16:00:11.624197253 +0200 +@@ -35,7 +35,7 @@ + + extern void msm_secondary_startup(void); + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static inline int get_core_count(void) + { +@@ -65,8 +65,8 @@ void __cpuinit platform_secondary_init(u + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static __cpuinit void prepare_cold_cpu(unsigned int cpu) +@@ -103,7 +103,7 @@ int __cpuinit boot_secondary(unsigned in + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -137,7 +137,7 @@ int __cpuinit boot_secondary(unsigned in + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/mach-omap2/omap-smp.c sun8i-rt/arch/arm/mach-omap2/omap-smp.c +--- sun8i/arch/arm/mach-omap2/omap-smp.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/mach-omap2/omap-smp.c 2016-08-22 16:00:11.624197253 +0200 +@@ -34,7 +34,7 @@ + /* SCU base address */ + static void __iomem *scu_base; + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void __iomem *omap4_get_scu_base(void) + { +@@ -65,8 +65,8 @@ void __cpuinit platform_secondary_init(u + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -77,7 +77,7 @@ int __cpuinit boot_secondary(unsigned in + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * Update the AuxCoreBoot0 with boot state for secondary core. +@@ -117,7 +117,7 @@ int __cpuinit boot_secondary(unsigned in + * Now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return 0; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/mach-omap2/omap-wakeupgen.c sun8i-rt/arch/arm/mach-omap2/omap-wakeupgen.c +--- sun8i/arch/arm/mach-omap2/omap-wakeupgen.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/mach-omap2/omap-wakeupgen.c 2016-08-22 16:01:21.272198054 +0200 +@@ -43,7 +43,7 @@ + + static void __iomem *wakeupgen_base; + static void __iomem *sar_base; +-static DEFINE_SPINLOCK(wakeupgen_lock); ++static DEFINE_RAW_SPINLOCK(wakeupgen_lock); + static unsigned int irq_target_cpu[NR_IRQS]; + + /* +@@ -128,9 +128,9 @@ static void wakeupgen_mask(struct irq_da + { + unsigned long flags; + +- spin_lock_irqsave(&wakeupgen_lock, flags); ++ raw_spin_lock_irqsave(&wakeupgen_lock, flags); + _wakeupgen_clear(d->irq, irq_target_cpu[d->irq]); +- spin_unlock_irqrestore(&wakeupgen_lock, flags); ++ raw_spin_unlock_irqrestore(&wakeupgen_lock, flags); + } + + /* +@@ -140,9 +140,9 @@ static void wakeupgen_unmask(struct irq_ + { + unsigned long flags; + +- spin_lock_irqsave(&wakeupgen_lock, flags); ++ raw_spin_lock_irqsave(&wakeupgen_lock, flags); + _wakeupgen_set(d->irq, irq_target_cpu[d->irq]); +- spin_unlock_irqrestore(&wakeupgen_lock, flags); ++ raw_spin_unlock_irqrestore(&wakeupgen_lock, flags); + } + + #ifdef CONFIG_HOTPLUG_CPU +@@ -183,7 +183,7 @@ static void wakeupgen_irqmask_all(unsign + { + unsigned long flags; + +- spin_lock_irqsave(&wakeupgen_lock, flags); ++ raw_spin_lock_irqsave(&wakeupgen_lock, flags); + if (set) { + _wakeupgen_save_masks(cpu); + _wakeupgen_set_all(cpu, WKG_MASK_ALL); +@@ -191,7 +191,7 @@ static void wakeupgen_irqmask_all(unsign + _wakeupgen_set_all(cpu, WKG_UNMASK_ALL); + _wakeupgen_restore_masks(cpu); + } +- spin_unlock_irqrestore(&wakeupgen_lock, flags); ++ raw_spin_unlock_irqrestore(&wakeupgen_lock, flags); + } + #endif + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/mach-ux500/platsmp.c sun8i-rt/arch/arm/mach-ux500/platsmp.c +--- sun8i/arch/arm/mach-ux500/platsmp.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/mach-ux500/platsmp.c 2016-08-22 16:00:11.624197253 +0200 +@@ -52,7 +52,7 @@ static void __iomem *scu_base_addr(void) + return NULL; + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void __cpuinit platform_secondary_init(unsigned int cpu) + { +@@ -72,8 +72,8 @@ void __cpuinit platform_secondary_init(u + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -84,7 +84,7 @@ int __cpuinit boot_secondary(unsigned in + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -105,7 +105,7 @@ int __cpuinit boot_secondary(unsigned in + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/mm/fault.c sun8i-rt/arch/arm/mm/fault.c +--- sun8i/arch/arm/mm/fault.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/mm/fault.c 2016-08-22 18:23:59.088296441 +0200 +@@ -279,7 +279,7 @@ do_page_fault(unsigned long addr, unsign + * If we're in an interrupt, or have no irqs, or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || irqs_disabled() || !mm) ++ if (irqs_disabled() || !mm || pagefault_disabled()) + goto no_context; + + /* +@@ -427,6 +427,9 @@ do_translation_fault(unsigned long addr, + if (addr < TASK_SIZE) + return do_page_fault(addr, fsr, regs); + ++ if (interrupts_enabled(regs)) ++ local_irq_enable(); ++ + if (user_mode(regs)) + goto bad_area; + +@@ -505,6 +508,9 @@ do_translation_fault(unsigned long addr, + static int + do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) + { ++ if (interrupts_enabled(regs)) ++ local_irq_enable(); ++ + do_bad_area(addr, fsr, regs); + return 0; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/arm/plat-versatile/platsmp.c sun8i-rt/arch/arm/plat-versatile/platsmp.c +--- sun8i/arch/arm/plat-versatile/platsmp.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/arm/plat-versatile/platsmp.c 2016-08-22 16:00:11.624197253 +0200 +@@ -32,7 +32,7 @@ static void __cpuinit write_pen_release( + outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1)); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void __cpuinit platform_secondary_init(unsigned int cpu) + { +@@ -52,8 +52,8 @@ void __cpuinit platform_secondary_init(u + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -64,7 +64,7 @@ int __cpuinit boot_secondary(unsigned in + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * This is really belt and braces; we hold unintended secondary +@@ -94,7 +94,7 @@ int __cpuinit boot_secondary(unsigned in + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/avr32/mm/fault.c sun8i-rt/arch/avr32/mm/fault.c +--- sun8i/arch/avr32/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/avr32/mm/fault.c 2016-08-22 16:13:41.864206569 +0200 +@@ -81,7 +81,7 @@ asmlinkage void do_page_fault(unsigned l + * If we're in an interrupt or have no user context, we must + * not take the fault... + */ +- if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM)) ++ if (!mm || regs->sr & SYSREG_BIT(GM) || pagefault_disabled()) + goto no_context; + + local_irq_enable(); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/blackfin/kernel/early_printk.c sun8i-rt/arch/blackfin/kernel/early_printk.c +--- sun8i/arch/blackfin/kernel/early_printk.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/blackfin/kernel/early_printk.c 2016-08-22 16:29:00.332217128 +0200 +@@ -25,8 +25,6 @@ extern struct console *bfin_earlyserial_ + extern struct console *bfin_jc_early_init(void); + #endif + +-static struct console *early_console; +- + /* Default console */ + #define DEFAULT_PORT 0 + #define DEFAULT_CFLAG CS8|B57600 +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/cris/mm/fault.c sun8i-rt/arch/cris/mm/fault.c +--- sun8i/arch/cris/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/cris/mm/fault.c 2016-08-22 16:13:41.864206569 +0200 +@@ -112,7 +112,7 @@ do_page_fault(unsigned long address, str + * user context, we must not take the fault. + */ + +- if (in_atomic() || !mm) ++ if (!mm || pagefault_disabled()) + goto no_context; + + down_read(&mm->mmap_sem); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/frv/mm/fault.c sun8i-rt/arch/frv/mm/fault.c +--- sun8i/arch/frv/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/frv/mm/fault.c 2016-08-22 16:13:41.864206569 +0200 +@@ -78,7 +78,7 @@ asmlinkage void do_page_fault(int datamm + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (!mm || pagefault_disabled()) + goto no_context; + + down_read(&mm->mmap_sem); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/ia64/mm/fault.c sun8i-rt/arch/ia64/mm/fault.c +--- sun8i/arch/ia64/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/ia64/mm/fault.c 2016-08-22 16:13:41.864206569 +0200 +@@ -88,7 +88,7 @@ ia64_do_page_fault (unsigned long addres + /* + * If we're in an interrupt or have no user context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (!mm || pagefault_disabled()) + goto no_context; + + #ifdef CONFIG_VIRTUAL_MEM_MAP +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/Kconfig sun8i-rt/arch/Kconfig +--- sun8i/arch/Kconfig 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/Kconfig 2016-08-22 18:27:45.848299048 +0200 +@@ -6,6 +6,7 @@ config OPROFILE + tristate "OProfile system profiling" + depends on PROFILING + depends on HAVE_OPROFILE ++ depends on !PREEMPT_RT_FULL + select RING_BUFFER + select RING_BUFFER_ALLOW_SWAP + help +@@ -49,6 +50,7 @@ config KPROBES + config JUMP_LABEL + bool "Optimize very unlikely/likely branches" + depends on HAVE_ARCH_JUMP_LABEL ++ depends on (!INTERRUPT_OFF_HIST && !PREEMPT_OFF_HIST && !WAKEUP_LATENCY_HIST && !MISSED_TIMER_OFFSETS_HIST) + help + This option enables a transparent branch optimization that + makes certain almost-always-true or almost-always-false branch +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/m32r/mm/fault.c sun8i-rt/arch/m32r/mm/fault.c +--- sun8i/arch/m32r/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/m32r/mm/fault.c 2016-08-22 16:13:41.864206569 +0200 +@@ -114,7 +114,7 @@ asmlinkage void do_page_fault(struct pt_ + * If we're in an interrupt or have no user context or are running in an + * atomic region then we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (!mm || pagefault_disabled()) + goto bad_area_nosemaphore; + + /* When running in the kernel we expect faults to occur only to +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/m68k/mm/fault.c sun8i-rt/arch/m68k/mm/fault.c +--- sun8i/arch/m68k/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/m68k/mm/fault.c 2016-08-22 16:13:41.864206569 +0200 +@@ -84,7 +84,7 @@ int do_page_fault(struct pt_regs *regs, + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (!mm || pagefault_disabled()) + goto no_context; + + down_read(&mm->mmap_sem); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/microblaze/kernel/early_printk.c sun8i-rt/arch/microblaze/kernel/early_printk.c +--- sun8i/arch/microblaze/kernel/early_printk.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/microblaze/kernel/early_printk.c 2016-08-22 16:29:00.332217128 +0200 +@@ -21,7 +21,6 @@ + #include + #include + +-static u32 early_console_initialized; + static u32 base_addr; + + #ifdef CONFIG_SERIAL_UARTLITE_CONSOLE +@@ -109,27 +108,11 @@ static struct console early_serial_uart1 + }; + #endif /* CONFIG_SERIAL_8250_CONSOLE */ + +-static struct console *early_console; +- +-void early_printk(const char *fmt, ...) +-{ +- char buf[512]; +- int n; +- va_list ap; +- +- if (early_console_initialized) { +- va_start(ap, fmt); +- n = vscnprintf(buf, 512, fmt, ap); +- early_console->write(early_console, buf, n); +- va_end(ap); +- } +-} +- + int __init setup_early_printk(char *opt) + { + int version = 0; + +- if (early_console_initialized) ++ if (early_console) + return 1; + + base_addr = of_early_console(&version); +@@ -159,7 +142,6 @@ int __init setup_early_printk(char *opt) + } + + register_console(early_console); +- early_console_initialized = 1; + return 0; + } + return 1; +@@ -169,7 +151,7 @@ int __init setup_early_printk(char *opt) + * only for early console because of performance degression */ + void __init remap_early_printk(void) + { +- if (!early_console_initialized || !early_console) ++ if (!early_console) + return; + printk(KERN_INFO "early_printk_console remapping from 0x%x to ", + base_addr); +@@ -195,9 +177,9 @@ void __init remap_early_printk(void) + + void __init disable_early_printk(void) + { +- if (!early_console_initialized || !early_console) ++ if (!early_console) + return; + printk(KERN_WARNING "disabling early console\n"); + unregister_console(early_console); +- early_console_initialized = 0; ++ early_console = NULL; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/microblaze/mm/fault.c sun8i-rt/arch/microblaze/mm/fault.c +--- sun8i/arch/microblaze/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/microblaze/mm/fault.c 2016-08-22 16:13:41.868206569 +0200 +@@ -106,7 +106,7 @@ void do_page_fault(struct pt_regs *regs, + if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11) + is_write = 0; + +- if (unlikely(in_atomic() || !mm)) { ++ if (unlikely(!mm || pagefault_disabled())) { + if (kernel_mode(regs)) + goto bad_area_nosemaphore; + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/mips/cavium-octeon/smp.c sun8i-rt/arch/mips/cavium-octeon/smp.c +--- sun8i/arch/mips/cavium-octeon/smp.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/mips/cavium-octeon/smp.c 2016-08-22 17:53:30.764275422 +0200 +@@ -257,8 +257,6 @@ DEFINE_PER_CPU(int, cpu_state); + + extern void fixup_irqs(void); + +-static DEFINE_SPINLOCK(smp_reserve_lock); +- + static int octeon_cpu_disable(void) + { + unsigned int cpu = smp_processor_id(); +@@ -266,8 +264,6 @@ static int octeon_cpu_disable(void) + if (cpu == 0) + return -EBUSY; + +- spin_lock(&smp_reserve_lock); +- + set_cpu_online(cpu, false); + cpu_clear(cpu, cpu_callin_map); + local_irq_disable(); +@@ -277,8 +273,6 @@ static int octeon_cpu_disable(void) + flush_cache_all(); + local_flush_tlb_all(); + +- spin_unlock(&smp_reserve_lock); +- + return 0; + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/mips/Kconfig sun8i-rt/arch/mips/Kconfig +--- sun8i/arch/mips/Kconfig 2016-08-22 14:14:35.000000000 +0200 ++++ sun8i-rt/arch/mips/Kconfig 2016-08-22 17:47:25.256271219 +0200 +@@ -2082,7 +2082,7 @@ config CPU_R4400_WORKAROUNDS + # + config HIGHMEM + bool "High Memory Support" +- depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM ++ depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !PREEMPT_RT_FULL + + config CPU_SUPPORTS_HIGHMEM + bool +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/mips/kernel/early_printk.c sun8i-rt/arch/mips/kernel/early_printk.c +--- sun8i/arch/mips/kernel/early_printk.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/mips/kernel/early_printk.c 2016-08-22 16:29:00.332217128 +0200 +@@ -25,20 +25,18 @@ early_console_write(struct console *con, + } + } + +-static struct console early_console __initdata = { ++static struct console early_console_prom = { + .name = "early", + .write = early_console_write, + .flags = CON_PRINTBUFFER | CON_BOOT, + .index = -1 + }; + +-static int early_console_initialized __initdata; +- + void __init setup_early_printk(void) + { +- if (early_console_initialized) ++ if (early_console) + return; +- early_console_initialized = 1; ++ early_console = &early_console_prom; + +- register_console(&early_console); ++ register_console(&early_console_prom); + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/mips/kernel/signal.c sun8i-rt/arch/mips/kernel/signal.c +--- sun8i/arch/mips/kernel/signal.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/mips/kernel/signal.c 2016-08-22 15:57:20.772195289 +0200 +@@ -588,6 +588,9 @@ static void do_signal(struct pt_regs *re + if (!user_mode(regs)) + return; + ++ local_irq_enable(); ++ preempt_check_resched(); ++ + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + oldset = ¤t->saved_sigmask; + else +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/mips/mm/fault.c sun8i-rt/arch/mips/mm/fault.c +--- sun8i/arch/mips/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/mips/mm/fault.c 2016-08-22 16:13:41.868206569 +0200 +@@ -89,7 +89,7 @@ asmlinkage void __kprobes do_page_fault( + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (!mm || pagefault_disabled()) + goto bad_area_nosemaphore; + + retry: +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/mn10300/mm/fault.c sun8i-rt/arch/mn10300/mm/fault.c +--- sun8i/arch/mn10300/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/mn10300/mm/fault.c 2016-08-22 16:13:41.868206569 +0200 +@@ -167,7 +167,7 @@ asmlinkage void do_page_fault(struct pt_ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (!mm || pagefault_disabled()) + goto no_context; + + down_read(&mm->mmap_sem); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/parisc/mm/fault.c sun8i-rt/arch/parisc/mm/fault.c +--- sun8i/arch/parisc/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/parisc/mm/fault.c 2016-08-22 16:13:41.868206569 +0200 +@@ -176,7 +176,7 @@ void do_page_fault(struct pt_regs *regs, + unsigned long acc_type; + int fault; + +- if (in_atomic() || !mm) ++ if (!mm || pagefault_disabled()) + goto no_context; + + down_read(&mm->mmap_sem); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/powerpc/Kconfig sun8i-rt/arch/powerpc/Kconfig +--- sun8i/arch/powerpc/Kconfig 2016-08-22 14:14:35.000000000 +0200 ++++ sun8i-rt/arch/powerpc/Kconfig 2016-08-22 17:46:39.064270688 +0200 +@@ -69,10 +69,11 @@ config LOCKDEP_SUPPORT + + config RWSEM_GENERIC_SPINLOCK + bool ++ default y if PREEMPT_RT_FULL + + config RWSEM_XCHGADD_ALGORITHM + bool +- default y ++ default y if !PREEMPT_RT_FULL + + config GENERIC_LOCKBREAK + bool +@@ -282,7 +283,7 @@ menu "Kernel options" + + config HIGHMEM + bool "High memory support" +- depends on PPC32 ++ depends on PPC32 && !PREEMPT_RT_FULL + + source kernel/time/Kconfig + source kernel/Kconfig.hz +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/powerpc/kernel/irq.c sun8i-rt/arch/powerpc/kernel/irq.c +--- sun8i/arch/powerpc/kernel/irq.c 2016-08-22 14:14:35.000000000 +0200 ++++ sun8i-rt/arch/powerpc/kernel/irq.c 2016-08-22 17:23:13.544254529 +0200 +@@ -584,6 +584,7 @@ void irq_ctx_init(void) + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + static inline void do_softirq_onstack(void) + { + struct thread_info *curtp, *irqtp; +@@ -620,6 +621,7 @@ void do_softirq(void) + + local_irq_restore(flags); + } ++#endif + + irq_hw_number_t virq_to_hw(unsigned int virq) + { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/powerpc/kernel/misc_32.S sun8i-rt/arch/powerpc/kernel/misc_32.S +--- sun8i/arch/powerpc/kernel/misc_32.S 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/powerpc/kernel/misc_32.S 2016-08-22 17:23:13.544254529 +0200 +@@ -36,6 +36,7 @@ + + .text + ++#ifndef CONFIG_PREEMPT_RT_FULL + _GLOBAL(call_do_softirq) + mflr r0 + stw r0,4(r1) +@@ -46,6 +47,7 @@ _GLOBAL(call_do_softirq) + lwz r0,4(r1) + mtlr r0 + blr ++#endif + + _GLOBAL(call_handle_irq) + mflr r0 +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/powerpc/kernel/misc_64.S sun8i-rt/arch/powerpc/kernel/misc_64.S +--- sun8i/arch/powerpc/kernel/misc_64.S 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/powerpc/kernel/misc_64.S 2016-08-22 17:23:13.544254529 +0200 +@@ -29,6 +29,7 @@ + + .text + ++#ifndef CONFIG_PREEMPT_RT_FULL + _GLOBAL(call_do_softirq) + mflr r0 + std r0,16(r1) +@@ -39,6 +40,7 @@ _GLOBAL(call_do_softirq) + ld r0,16(r1) + mtlr r0 + blr ++#endif + + _GLOBAL(call_handle_irq) + ld r8,0(r6) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/powerpc/kernel/udbg.c sun8i-rt/arch/powerpc/kernel/udbg.c +--- sun8i/arch/powerpc/kernel/udbg.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/powerpc/kernel/udbg.c 2016-08-22 16:29:00.332217128 +0200 +@@ -179,15 +179,13 @@ static struct console udbg_console = { + .index = 0, + }; + +-static int early_console_initialized; +- + /* + * Called by setup_system after ppc_md->probe and ppc_md->early_init. + * Call it again after setting udbg_putc in ppc_md->setup_arch. + */ + void __init register_early_udbg_console(void) + { +- if (early_console_initialized) ++ if (early_console) + return; + + if (!udbg_putc) +@@ -197,7 +195,7 @@ void __init register_early_udbg_console( + printk(KERN_INFO "early console immortal !\n"); + udbg_console.flags &= ~CON_BOOT; + } +- early_console_initialized = 1; ++ early_console = &udbg_console; + register_console(&udbg_console); + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/powerpc/mm/fault.c sun8i-rt/arch/powerpc/mm/fault.c +--- sun8i/arch/powerpc/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/powerpc/mm/fault.c 2016-08-22 16:13:41.868206569 +0200 +@@ -261,7 +261,7 @@ int __kprobes do_page_fault(struct pt_re + if (!arch_irq_disabled_regs(regs)) + local_irq_enable(); + +- if (in_atomic() || mm == NULL) { ++ if (!mm || pagefault_disabled()) { + if (!user_mode(regs)) + return SIGSEGV; + /* in_atomic() in user mode is really bad, +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/powerpc/platforms/8xx/m8xx_setup.c sun8i-rt/arch/powerpc/platforms/8xx/m8xx_setup.c +--- sun8i/arch/powerpc/platforms/8xx/m8xx_setup.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/powerpc/platforms/8xx/m8xx_setup.c 2016-08-22 17:59:15.056279380 +0200 +@@ -43,6 +43,7 @@ static irqreturn_t timebase_interrupt(in + + static struct irqaction tbint_irqaction = { + .handler = timebase_interrupt, ++ .flags = IRQF_NO_THREAD, + .name = "tbint", + }; + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/powerpc/sysdev/cpm1.c sun8i-rt/arch/powerpc/sysdev/cpm1.c +--- sun8i/arch/powerpc/sysdev/cpm1.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/powerpc/sysdev/cpm1.c 2016-08-22 17:59:15.056279380 +0200 +@@ -120,6 +120,7 @@ static irqreturn_t cpm_error_interrupt(i + + static struct irqaction cpm_error_irqaction = { + .handler = cpm_error_interrupt, ++ .flags = IRQF_NO_THREAD, + .name = "error", + }; + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/s390/mm/fault.c sun8i-rt/arch/s390/mm/fault.c +--- sun8i/arch/s390/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/s390/mm/fault.c 2016-08-22 16:13:41.868206569 +0200 +@@ -289,7 +289,8 @@ static inline int do_exception(struct pt + * user context. + */ + fault = VM_FAULT_BADCONTEXT; +- if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm)) ++ if (unlikely(!user_space_fault(trans_exc_code) || ++ !mm || pagefault_disabled())) + goto out; + + address = trans_exc_code & __FAIL_ADDR_MASK; +@@ -421,7 +422,8 @@ void __kprobes do_asce_exception(struct + unsigned long trans_exc_code; + + trans_exc_code = regs->int_parm_long; +- if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm)) ++ if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm || ++ pagefault_disabled())) + goto no_context; + + down_read(&mm->mmap_sem); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/score/mm/fault.c sun8i-rt/arch/score/mm/fault.c +--- sun8i/arch/score/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/score/mm/fault.c 2016-08-22 16:13:41.868206569 +0200 +@@ -72,7 +72,7 @@ asmlinkage void do_page_fault(struct pt_ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (!mm || pagefault_disabled()) + goto bad_area_nosemaphore; + + down_read(&mm->mmap_sem); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/sh/kernel/irq.c sun8i-rt/arch/sh/kernel/irq.c +--- sun8i/arch/sh/kernel/irq.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/sh/kernel/irq.c 2016-08-22 17:23:13.544254529 +0200 +@@ -149,6 +149,7 @@ void irq_ctx_exit(int cpu) + hardirq_ctx[cpu] = NULL; + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + asmlinkage void do_softirq(void) + { + unsigned long flags; +@@ -191,6 +192,7 @@ asmlinkage void do_softirq(void) + + local_irq_restore(flags); + } ++#endif + #else + static inline void handle_one_irq(unsigned int irq) + { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/sh/kernel/sh_bios.c sun8i-rt/arch/sh/kernel/sh_bios.c +--- sun8i/arch/sh/kernel/sh_bios.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/sh/kernel/sh_bios.c 2016-08-22 16:29:00.332217128 +0200 +@@ -144,8 +144,6 @@ static struct console bios_console = { + .index = -1, + }; + +-static struct console *early_console; +- + static int __init setup_early_printk(char *buf) + { + int keep_early = 0; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/sh/mm/fault_32.c sun8i-rt/arch/sh/mm/fault_32.c +--- sun8i/arch/sh/mm/fault_32.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/sh/mm/fault_32.c 2016-08-22 16:13:41.868206569 +0200 +@@ -166,7 +166,7 @@ asmlinkage void __kprobes do_page_fault( + * If we're in an interrupt, have no user context or are running + * in an atomic region then we must not take the fault: + */ +- if (in_atomic() || !mm) ++ if (!mm || pagefault_disabled()) + goto no_context; + + down_read(&mm->mmap_sem); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/sparc/kernel/irq_64.c sun8i-rt/arch/sparc/kernel/irq_64.c +--- sun8i/arch/sparc/kernel/irq_64.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/sparc/kernel/irq_64.c 2016-08-22 17:23:13.544254529 +0200 +@@ -698,6 +698,7 @@ void __irq_entry handler_irq(int pil, st + set_irq_regs(old_regs); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq(void) + { + unsigned long flags; +@@ -723,6 +724,7 @@ void do_softirq(void) + + local_irq_restore(flags); + } ++#endif + + #ifdef CONFIG_HOTPLUG_CPU + void fixup_irqs(void) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/sparc/kernel/prom_common.c sun8i-rt/arch/sparc/kernel/prom_common.c +--- sun8i/arch/sparc/kernel/prom_common.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/sparc/kernel/prom_common.c 2016-08-22 16:18:11.100209664 +0200 +@@ -65,7 +65,7 @@ int of_set_property(struct device_node * + err = -ENODEV; + + mutex_lock(&of_set_property_mutex); +- write_lock(&devtree_lock); ++ raw_spin_lock(&devtree_lock); + prevp = &dp->properties; + while (*prevp) { + struct property *prop = *prevp; +@@ -92,7 +92,7 @@ int of_set_property(struct device_node * + } + prevp = &(*prevp)->next; + } +- write_unlock(&devtree_lock); ++ raw_spin_unlock(&devtree_lock); + mutex_unlock(&of_set_property_mutex); + + /* XXX Upate procfs if necessary... */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/sparc/kernel/setup_32.c sun8i-rt/arch/sparc/kernel/setup_32.c +--- sun8i/arch/sparc/kernel/setup_32.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/sparc/kernel/setup_32.c 2016-08-22 16:29:00.332217128 +0200 +@@ -221,6 +221,7 @@ void __init setup_arch(char **cmdline_p) + + boot_flags_init(*cmdline_p); + ++ early_console = &prom_early_console; + register_console(&prom_early_console); + + /* Set sparc_cpu_model */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/sparc/kernel/setup_64.c sun8i-rt/arch/sparc/kernel/setup_64.c +--- sun8i/arch/sparc/kernel/setup_64.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/sparc/kernel/setup_64.c 2016-08-22 16:29:00.332217128 +0200 +@@ -487,6 +487,12 @@ static void __init init_sparc64_elf_hwca + popc_patch(); + } + ++static inline void register_prom_console(void) ++{ ++ early_console = &prom_early_console; ++ register_console(&prom_early_console); ++} ++ + void __init setup_arch(char **cmdline_p) + { + /* Initialize PROM console and command line. */ +@@ -498,7 +504,7 @@ void __init setup_arch(char **cmdline_p) + #ifdef CONFIG_EARLYFB + if (btext_find_display()) + #endif +- register_console(&prom_early_console); ++ register_prom_console(); + + if (tlb_type == hypervisor) + printk("ARCH: SUN4V\n"); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/sparc/mm/fault_32.c sun8i-rt/arch/sparc/mm/fault_32.c +--- sun8i/arch/sparc/mm/fault_32.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/sparc/mm/fault_32.c 2016-08-22 16:13:41.868206569 +0200 +@@ -248,8 +248,8 @@ asmlinkage void do_sparc_fault(struct pt + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) +- goto no_context; ++ if (!mm || pagefault_disabled()) ++ goto no_context; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/sparc/mm/fault_64.c sun8i-rt/arch/sparc/mm/fault_64.c +--- sun8i/arch/sparc/mm/fault_64.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/sparc/mm/fault_64.c 2016-08-22 16:13:41.868206569 +0200 +@@ -331,7 +331,7 @@ asmlinkage void __kprobes do_sparc64_fau + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (!mm || pagefault_disabled()) + goto intr_or_no_mm; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/tile/kernel/early_printk.c sun8i-rt/arch/tile/kernel/early_printk.c +--- sun8i/arch/tile/kernel/early_printk.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/tile/kernel/early_printk.c 2016-08-22 16:29:00.332217128 +0200 +@@ -33,25 +33,8 @@ static struct console early_hv_console = + }; + + /* Direct interface for emergencies */ +-static struct console *early_console = &early_hv_console; +-static int early_console_initialized; + static int early_console_complete; + +-static void early_vprintk(const char *fmt, va_list ap) +-{ +- char buf[512]; +- int n = vscnprintf(buf, sizeof(buf), fmt, ap); +- early_console->write(early_console, buf, n); +-} +- +-void early_printk(const char *fmt, ...) +-{ +- va_list ap; +- va_start(ap, fmt); +- early_vprintk(fmt, ap); +- va_end(ap); +-} +- + void early_panic(const char *fmt, ...) + { + va_list ap; +@@ -69,14 +52,13 @@ static int __initdata keep_early; + + static int __init setup_early_printk(char *str) + { +- if (early_console_initialized) ++ if (early_console) + return 1; + + if (str != NULL && strncmp(str, "keep", 4) == 0) + keep_early = 1; + + early_console = &early_hv_console; +- early_console_initialized = 1; + register_console(early_console); + + return 0; +@@ -85,12 +67,12 @@ static int __init setup_early_printk(cha + void __init disable_early_printk(void) + { + early_console_complete = 1; +- if (!early_console_initialized || !early_console) ++ if (!early_console) + return; + if (!keep_early) { + early_printk("disabling early console\n"); + unregister_console(early_console); +- early_console_initialized = 0; ++ early_console = NULL; + } else { + early_printk("keeping early console\n"); + } +@@ -98,7 +80,7 @@ void __init disable_early_printk(void) + + void warn_early_printk(void) + { +- if (early_console_complete || early_console_initialized) ++ if (early_console_complete || early_console) + return; + early_printk("\ + Machine shutting down before console output is fully initialized.\n\ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/tile/mm/fault.c sun8i-rt/arch/tile/mm/fault.c +--- sun8i/arch/tile/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/tile/mm/fault.c 2016-08-22 16:13:41.868206569 +0200 +@@ -355,7 +355,7 @@ static int handle_page_fault(struct pt_r + * If we're in an interrupt, have no user context or are running in an + * atomic region then we must not take the fault. + */ +- if (in_atomic() || !mm) { ++ if (!mm || pagefault_disabled()) { + vma = NULL; /* happy compiler */ + goto bad_area_nosemaphore; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/um/kernel/early_printk.c sun8i-rt/arch/um/kernel/early_printk.c +--- sun8i/arch/um/kernel/early_printk.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/um/kernel/early_printk.c 2016-08-22 16:29:00.332217128 +0200 +@@ -16,7 +16,7 @@ static void early_console_write(struct c + um_early_printk(s, n); + } + +-static struct console early_console = { ++static struct console early_console_dev = { + .name = "earlycon", + .write = early_console_write, + .flags = CON_BOOT, +@@ -25,8 +25,10 @@ static struct console early_console = { + + static int __init setup_early_printk(char *buf) + { +- register_console(&early_console); +- ++ if (!early_console) { ++ early_console = &early_console_dev; ++ register_console(&early_console_dev); ++ } + return 0; + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/um/kernel/trap.c sun8i-rt/arch/um/kernel/trap.c +--- sun8i/arch/um/kernel/trap.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/um/kernel/trap.c 2016-08-22 16:13:41.868206569 +0200 +@@ -37,7 +37,7 @@ int handle_page_fault(unsigned long addr + * If the fault was during atomic operation, don't take the fault, just + * fail. + */ +- if (in_atomic()) ++ if (!mm || pagefault_disabled()) + goto out_nosemaphore; + + down_read(&mm->mmap_sem); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/unicore32/kernel/early_printk.c sun8i-rt/arch/unicore32/kernel/early_printk.c +--- sun8i/arch/unicore32/kernel/early_printk.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/unicore32/kernel/early_printk.c 2016-08-22 16:29:00.332217128 +0200 +@@ -33,21 +33,17 @@ static struct console early_ocd_console + .index = -1, + }; + +-/* Direct interface for emergencies */ +-static struct console *early_console = &early_ocd_console; +- +-static int __initdata keep_early; +- + static int __init setup_early_printk(char *buf) + { +- if (!buf) ++ int keep_early; ++ ++ if (!buf || early_console) + return 0; + + if (strstr(buf, "keep")) + keep_early = 1; + +- if (!strncmp(buf, "ocd", 3)) +- early_console = &early_ocd_console; ++ early_console = &early_ocd_console; + + if (keep_early) + early_console->flags &= ~CON_BOOT; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/crypto/aesni-intel_glue.c sun8i-rt/arch/x86/crypto/aesni-intel_glue.c +--- sun8i/arch/x86/crypto/aesni-intel_glue.c 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/arch/x86/crypto/aesni-intel_glue.c 2016-08-22 17:49:36.152272724 +0200 +@@ -290,14 +290,14 @@ static int ecb_encrypt(struct blkcipher_ + err = blkcipher_walk_virt(desc, &walk); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, +- nbytes & AES_BLOCK_MASK); ++ nbytes & AES_BLOCK_MASK); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -314,14 +314,14 @@ static int ecb_decrypt(struct blkcipher_ + err = blkcipher_walk_virt(desc, &walk); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -360,14 +360,14 @@ static int cbc_encrypt(struct blkcipher_ + err = blkcipher_walk_virt(desc, &walk); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -384,14 +384,14 @@ static int cbc_decrypt(struct blkcipher_ + err = blkcipher_walk_virt(desc, &walk); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -446,18 +446,20 @@ static int ctr_crypt(struct blkcipher_de + err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { ++ kernel_fpu_begin(); + aesni_ctr_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + if (walk.nbytes) { ++ kernel_fpu_begin(); + ctr_crypt_final(ctx, &walk); ++ kernel_fpu_end(); + err = blkcipher_walk_done(desc, &walk, 0); + } +- kernel_fpu_end(); + + return err; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/include/asm/acpi.h sun8i-rt/arch/x86/include/asm/acpi.h +--- sun8i/arch/x86/include/asm/acpi.h 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/include/asm/acpi.h 2016-08-22 16:31:59.428219187 +0200 +@@ -51,8 +51,8 @@ + + #define ACPI_ASM_MACROS + #define BREAKPOINT3 +-#define ACPI_DISABLE_IRQS() local_irq_disable() +-#define ACPI_ENABLE_IRQS() local_irq_enable() ++#define ACPI_DISABLE_IRQS() local_irq_disable_nort() ++#define ACPI_ENABLE_IRQS() local_irq_enable_nort() + #define ACPI_FLUSH_CPU_CACHE() wbinvd() + + int __acpi_acquire_global_lock(unsigned int *lock); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/include/asm/signal.h sun8i-rt/arch/x86/include/asm/signal.h +--- sun8i/arch/x86/include/asm/signal.h 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/include/asm/signal.h 2016-08-22 16:02:35.808198911 +0200 +@@ -31,6 +31,19 @@ typedef struct { + unsigned long sig[_NSIG_WORDS]; + } sigset_t; + ++/* ++ * Because some traps use the IST stack, we must keep ++ * preemption disabled while calling do_trap(), but do_trap() ++ * may call force_sig_info() which will grab the signal spin_locks ++ * for the task, which in PREEMPT_RT_FULL are mutexes. ++ * By defining ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will ++ * set TIF_NOTIFY_RESUME and set up the signal to be sent on exit ++ * of the trap. ++ */ ++#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_X86_64) ++#define ARCH_RT_DELAYS_SIGNAL_SEND ++#endif ++ + #else + /* Here we must cater to libcs that poke about in kernel headers. */ + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/include/asm/stackprotector.h sun8i-rt/arch/x86/include/asm/stackprotector.h +--- sun8i/arch/x86/include/asm/stackprotector.h 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/include/asm/stackprotector.h 2016-08-22 17:39:42.200265896 +0200 +@@ -57,7 +57,7 @@ + */ + static __always_inline void boot_init_stack_canary(void) + { +- u64 canary; ++ u64 uninitialized_var(canary); + u64 tsc; + + #ifdef CONFIG_X86_64 +@@ -68,8 +68,16 @@ static __always_inline void boot_init_st + * of randomness. The TSC only matters for very early init, + * there it already has some randomness on most systems. Later + * on during the bootup the random pool has true entropy too. ++ * ++ * For preempt-rt we need to weaken the randomness a bit, as ++ * we can't call into the random generator from atomic context ++ * due to locking constraints. We just leave canary ++ * uninitialized and use the TSC based randomness on top of ++ * it. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + get_random_bytes(&canary, sizeof(canary)); ++#endif + tsc = __native_read_tsc(); + canary += tsc + (tsc << 32UL); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/include/asm/uv/uv_bau.h sun8i-rt/arch/x86/include/asm/uv/uv_bau.h +--- sun8i/arch/x86/include/asm/uv/uv_bau.h 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/include/asm/uv/uv_bau.h 2016-08-22 18:23:44.708296276 +0200 +@@ -602,8 +602,8 @@ struct bau_control { + unsigned short uvhub_quiesce; + short socket_acknowledge_count[DEST_Q_SIZE]; + cycles_t send_message; +- spinlock_t uvhub_lock; +- spinlock_t queue_lock; ++ raw_spinlock_t uvhub_lock; ++ raw_spinlock_t queue_lock; + /* tunables */ + int max_concurr; + int max_concurr_const; +@@ -760,15 +760,15 @@ static inline int atom_asr(short i, stru + * to be lowered below the current 'v'. atomic_add_unless can only stop + * on equal. + */ +-static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u) ++static inline int atomic_inc_unless_ge(raw_spinlock_t *lock, atomic_t *v, int u) + { +- spin_lock(lock); ++ raw_spin_lock(lock); + if (atomic_read(v) >= u) { +- spin_unlock(lock); ++ raw_spin_unlock(lock); + return 0; + } + atomic_inc(v); +- spin_unlock(lock); ++ raw_spin_unlock(lock); + return 1; + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/include/asm/uv/uv_hub.h sun8i-rt/arch/x86/include/asm/uv/uv_hub.h +--- sun8i/arch/x86/include/asm/uv/uv_hub.h 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/include/asm/uv/uv_hub.h 2016-08-22 18:23:44.708296276 +0200 +@@ -475,7 +475,7 @@ struct uv_blade_info { + unsigned short nr_online_cpus; + unsigned short pnode; + short memory_nid; +- spinlock_t nmi_lock; ++ raw_spinlock_t nmi_lock; + unsigned long nmi_count; + }; + extern struct uv_blade_info *uv_blade_info; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/Kconfig sun8i-rt/arch/x86/Kconfig +--- sun8i/arch/x86/Kconfig 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/arch/x86/Kconfig 2016-08-22 17:50:02.648273029 +0200 +@@ -156,10 +156,10 @@ config ARCH_MAY_HAVE_PC_FDC + def_bool ISA_DMA_API + + config RWSEM_GENERIC_SPINLOCK +- def_bool !X86_XADD ++ def_bool !X86_XADD || PREEMPT_RT_FULL + + config RWSEM_XCHGADD_ALGORITHM +- def_bool X86_XADD ++ def_bool X86_XADD && !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL + + config ARCH_HAS_CPU_IDLE_WAIT + def_bool y +@@ -751,7 +751,7 @@ config IOMMU_HELPER + config MAXSMP + bool "Enable Maximum number of SMP Processors and NUMA Nodes" + depends on X86_64 && SMP && DEBUG_KERNEL && EXPERIMENTAL +- select CPUMASK_OFFSTACK ++ select CPUMASK_OFFSTACK if !PREEMPT_RT_FULL + ---help--- + Enable maximum number of CPUS and NUMA Nodes for this architecture. + If unsure, say N. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/apic/io_apic.c sun8i-rt/arch/x86/kernel/apic/io_apic.c +--- sun8i/arch/x86/kernel/apic/io_apic.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/apic/io_apic.c 2016-08-22 16:22:27.972212617 +0200 +@@ -2555,7 +2555,8 @@ atomic_t irq_mis_count; + static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) + { + /* If we are moving the irq we need to mask it */ +- if (unlikely(irqd_is_setaffinity_pending(data))) { ++ if (unlikely(irqd_is_setaffinity_pending(data) && ++ !irqd_irq_inprogress(data))) { + mask_ioapic(cfg); + return true; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/apic/x2apic_uv_x.c sun8i-rt/arch/x86/kernel/apic/x2apic_uv_x.c +--- sun8i/arch/x86/kernel/apic/x2apic_uv_x.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/apic/x2apic_uv_x.c 2016-08-22 18:23:44.708296276 +0200 +@@ -56,7 +56,7 @@ int uv_min_hub_revision_id; + EXPORT_SYMBOL_GPL(uv_min_hub_revision_id); + unsigned int uv_apicid_hibits; + EXPORT_SYMBOL_GPL(uv_apicid_hibits); +-static DEFINE_SPINLOCK(uv_nmi_lock); ++static DEFINE_RAW_SPINLOCK(uv_nmi_lock); + + static struct apic apic_x2apic_uv_x; + +@@ -695,13 +695,13 @@ int uv_handle_nmi(unsigned int reason, s + real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK); + + if (unlikely(real_uv_nmi)) { +- spin_lock(&uv_blade_info[bid].nmi_lock); ++ raw_spin_lock(&uv_blade_info[bid].nmi_lock); + real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK); + if (real_uv_nmi) { + uv_blade_info[bid].nmi_count++; + uv_write_local_mmr(UVH_NMI_MMR_CLEAR, UV_NMI_PENDING_MASK); + } +- spin_unlock(&uv_blade_info[bid].nmi_lock); ++ raw_spin_unlock(&uv_blade_info[bid].nmi_lock); + } + + if (likely(__get_cpu_var(cpu_last_nmi_count) == uv_blade_info[bid].nmi_count)) +@@ -713,10 +713,10 @@ int uv_handle_nmi(unsigned int reason, s + * Use a lock so only one cpu prints at a time. + * This prevents intermixed output. + */ +- spin_lock(&uv_nmi_lock); ++ raw_spin_lock(&uv_nmi_lock); + pr_info("UV NMI stack dump cpu %u:\n", smp_processor_id()); + dump_stack(); +- spin_unlock(&uv_nmi_lock); ++ raw_spin_unlock(&uv_nmi_lock); + + return NMI_HANDLED; + } +@@ -811,7 +811,7 @@ void __init uv_system_init(void) + uv_blade_info[blade].pnode = pnode; + uv_blade_info[blade].nr_possible_cpus = 0; + uv_blade_info[blade].nr_online_cpus = 0; +- spin_lock_init(&uv_blade_info[blade].nmi_lock); ++ raw_spin_lock_init(&uv_blade_info[blade].nmi_lock); + max_pnode = max(pnode, max_pnode); + blade++; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/cpu/mcheck/mce.c sun8i-rt/arch/x86/kernel/cpu/mcheck/mce.c +--- sun8i/arch/x86/kernel/cpu/mcheck/mce.c 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/cpu/mcheck/mce.c 2016-08-22 18:29:30.132300247 +0200 +@@ -15,6 +15,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -38,6 +39,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -1250,17 +1252,14 @@ void mce_log_therm_throt_event(__u64 sta + * poller finds an MCE, poll 2x faster. When the poller finds no more + * errors, poll 2x slower (up to check_interval seconds). + */ +-static int check_interval = 5 * 60; /* 5 minutes */ ++static unsigned long check_interval = 5 * 60; /* 5 minutes */ + +-static DEFINE_PER_CPU(int, mce_next_interval); /* in jiffies */ +-static DEFINE_PER_CPU(struct timer_list, mce_timer); ++static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ ++static DEFINE_PER_CPU(struct hrtimer, mce_timer); + +-static void mce_start_timer(unsigned long data) ++static enum hrtimer_restart mce_start_timer(struct hrtimer *timer) + { +- struct timer_list *t = &per_cpu(mce_timer, data); +- int *n; +- +- WARN_ON(smp_processor_id() != data); ++ unsigned long *n; + + if (mce_available(__this_cpu_ptr(&cpu_info))) { + machine_check_poll(MCP_TIMESTAMP, +@@ -1273,21 +1272,22 @@ static void mce_start_timer(unsigned lon + */ + n = &__get_cpu_var(mce_next_interval); + if (mce_notify_irq()) +- *n = max(*n/2, HZ/100); ++ *n = max(*n/2, HZ/100UL); + else +- *n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ)); ++ *n = min(*n*2, round_jiffies_relative(check_interval*HZ)); + +- t->expires = jiffies + *n; +- add_timer_on(t, smp_processor_id()); ++ hrtimer_forward(timer, timer->base->get_time(), ++ ns_to_ktime(jiffies_to_usecs(*n) * 1000ULL)); ++ return HRTIMER_RESTART; + } + +-/* Must not be called in IRQ context where del_timer_sync() can deadlock */ ++/* Must not be called in IRQ context where hrtimer_cancel() can deadlock */ + static void mce_timer_delete_all(void) + { + int cpu; + + for_each_online_cpu(cpu) +- del_timer_sync(&per_cpu(mce_timer, cpu)); ++ hrtimer_cancel(&per_cpu(mce_timer, cpu)); + } + + static void mce_do_trigger(struct work_struct *work) +@@ -1297,6 +1297,64 @@ static void mce_do_trigger(struct work_s + + static DECLARE_WORK(mce_trigger_work, mce_do_trigger); + ++static void __mce_notify_work(void) ++{ ++ /* Not more than two messages every minute */ ++ static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); ++ ++ /* wake processes polling /dev/mcelog */ ++ wake_up_interruptible(&mce_chrdev_wait); ++ ++ /* ++ * There is no risk of missing notifications because ++ * work_pending is always cleared before the function is ++ * executed. ++ */ ++ if (mce_helper[0] && !work_pending(&mce_trigger_work)) ++ schedule_work(&mce_trigger_work); ++ ++ if (__ratelimit(&ratelimit)) ++ pr_info(HW_ERR "Machine check events logged\n"); ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++struct task_struct *mce_notify_helper; ++ ++static int mce_notify_helper_thread(void *unused) ++{ ++ while (1) { ++ set_current_state(TASK_INTERRUPTIBLE); ++ schedule(); ++ if (kthread_should_stop()) ++ break; ++ __mce_notify_work(); ++ } ++ return 0; ++} ++ ++static int mce_notify_work_init(void) ++{ ++ mce_notify_helper = kthread_run(mce_notify_helper_thread, NULL, ++ "mce-notify"); ++ if (!mce_notify_helper) ++ return -ENOMEM; ++ ++ return 0; ++} ++ ++static void mce_notify_work(void) ++{ ++ if (mce_notify_helper) ++ wake_up_process(mce_notify_helper); ++} ++#else ++static void mce_notify_work(void) ++{ ++ __mce_notify_work(); ++} ++static inline int mce_notify_work_init(void) { return 0; } ++#endif ++ + /* + * Notify the user(s) about new machine check events. + * Can be called from interrupt context, but not from machine check/NMI +@@ -1304,24 +1362,8 @@ static DECLARE_WORK(mce_trigger_work, mc + */ + int mce_notify_irq(void) + { +- /* Not more than two messages every minute */ +- static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); +- + if (test_and_clear_bit(0, &mce_need_notify)) { +- /* wake processes polling /dev/mcelog */ +- wake_up_interruptible(&mce_chrdev_wait); +- +- /* +- * There is no risk of missing notifications because +- * work_pending is always cleared before the function is +- * executed. +- */ +- if (mce_helper[0] && !work_pending(&mce_trigger_work)) +- schedule_work(&mce_trigger_work); +- +- if (__ratelimit(&ratelimit)) +- pr_info(HW_ERR "Machine check events logged\n"); +- ++ mce_notify_work(); + return 1; + } + return 0; +@@ -1517,10 +1559,11 @@ static void __mcheck_cpu_init_vendor(str + + static void __mcheck_cpu_init_timer(void) + { +- struct timer_list *t = &__get_cpu_var(mce_timer); +- int *n = &__get_cpu_var(mce_next_interval); ++ struct hrtimer *t = &__get_cpu_var(mce_timer); ++ unsigned long *n = &__get_cpu_var(mce_next_interval); + +- setup_timer(t, mce_start_timer, smp_processor_id()); ++ hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ t->function = mce_start_timer; + + if (mce_ignore_ce) + return; +@@ -1528,8 +1571,9 @@ static void __mcheck_cpu_init_timer(void + *n = check_interval * HZ; + if (!*n) + return; +- t->expires = round_jiffies(jiffies + *n); +- add_timer_on(t, smp_processor_id()); ++ ++ hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(*n) * 1000ULL), ++ 0 , HRTIMER_MODE_REL_PINNED); + } + + /* Handle unconfigured int18 (should never happen) */ +@@ -2181,6 +2225,8 @@ static void __cpuinit mce_disable_cpu(vo + if (!mce_available(__this_cpu_ptr(&cpu_info))) + return; + ++ hrtimer_cancel(&__get_cpu_var(mce_timer)); ++ + if (!(action & CPU_TASKS_FROZEN)) + cmci_clear(); + for (i = 0; i < banks; i++) { +@@ -2207,6 +2253,7 @@ static void __cpuinit mce_reenable_cpu(v + if (b->init) + wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); + } ++ __mcheck_cpu_init_timer(); + } + + /* Get notified when a cpu comes on/off. Be hotplug friendly. */ +@@ -2214,7 +2261,6 @@ static int __cpuinit + mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) + { + unsigned int cpu = (unsigned long)hcpu; +- struct timer_list *t = &per_cpu(mce_timer, cpu); + + switch (action) { + case CPU_ONLINE: +@@ -2231,16 +2277,10 @@ mce_cpu_callback(struct notifier_block * + break; + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: +- del_timer_sync(t); + smp_call_function_single(cpu, mce_disable_cpu, &action, 1); + break; + case CPU_DOWN_FAILED: + case CPU_DOWN_FAILED_FROZEN: +- if (!mce_ignore_ce && check_interval) { +- t->expires = round_jiffies(jiffies + +- __get_cpu_var(mce_next_interval)); +- add_timer_on(t, cpu); +- } + smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); + break; + case CPU_POST_DEAD: +@@ -2301,6 +2341,8 @@ static __init int mcheck_init_device(voi + /* register character device /dev/mcelog */ + misc_register(&mce_chrdev_device); + ++ err = mce_notify_work_init(); ++ + return err; + } + device_initcall(mcheck_init_device); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/dumpstack_64.c sun8i-rt/arch/x86/kernel/dumpstack_64.c +--- sun8i/arch/x86/kernel/dumpstack_64.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/dumpstack_64.c 2016-08-22 18:26:54.568298459 +0200 +@@ -114,7 +114,7 @@ void dump_trace(struct task_struct *task + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data) + { +- const unsigned cpu = get_cpu(); ++ const unsigned cpu = get_cpu_light(); + unsigned long *irq_stack_end = + (unsigned long *)per_cpu(irq_stack_ptr, cpu); + unsigned used = 0; +@@ -191,7 +191,7 @@ void dump_trace(struct task_struct *task + * This handles the process stack: + */ + bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph); +- put_cpu(); ++ put_cpu_light(); + } + EXPORT_SYMBOL(dump_trace); + +@@ -205,7 +205,7 @@ show_stack_log_lvl(struct task_struct *t + int cpu; + int i; + +- preempt_disable(); ++ migrate_disable(); + cpu = smp_processor_id(); + + irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu)); +@@ -238,7 +238,7 @@ show_stack_log_lvl(struct task_struct *t + printk(KERN_CONT " %016lx", *stack++); + touch_nmi_watchdog(); + } +- preempt_enable(); ++ migrate_enable(); + + printk(KERN_CONT "\n"); + show_trace_log_lvl(task, regs, sp, bp, log_lvl); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/early_printk.c sun8i-rt/arch/x86/kernel/early_printk.c +--- sun8i/arch/x86/kernel/early_printk.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/early_printk.c 2016-08-22 16:29:00.332217128 +0200 +@@ -169,25 +169,9 @@ static struct console early_serial_conso + .index = -1, + }; + +-/* Direct interface for emergencies */ +-static struct console *early_console = &early_vga_console; +-static int __initdata early_console_initialized; +- +-asmlinkage void early_printk(const char *fmt, ...) +-{ +- char buf[512]; +- int n; +- va_list ap; +- +- va_start(ap, fmt); +- n = vscnprintf(buf, sizeof(buf), fmt, ap); +- early_console->write(early_console, buf, n); +- va_end(ap); +-} +- + static inline void early_console_register(struct console *con, int keep_early) + { +- if (early_console->index != -1) { ++ if (con->index != -1) { + printk(KERN_CRIT "ERROR: earlyprintk= %s already used\n", + con->name); + return; +@@ -207,9 +191,8 @@ static int __init setup_early_printk(cha + if (!buf) + return 0; + +- if (early_console_initialized) ++ if (early_console) + return 0; +- early_console_initialized = 1; + + keep = (strstr(buf, "keep") != NULL); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/entry_64.S sun8i-rt/arch/x86/kernel/entry_64.S +--- sun8i/arch/x86/kernel/entry_64.S 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/entry_64.S 2016-08-22 17:23:13.544254529 +0200 +@@ -1258,6 +1258,7 @@ ENTRY(kernel_execve) + CFI_ENDPROC + END(kernel_execve) + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* Call softirq on interrupt stack. Interrupts are off. */ + ENTRY(call_softirq) + CFI_STARTPROC +@@ -1277,6 +1278,7 @@ ENTRY(call_softirq) + ret + CFI_ENDPROC + END(call_softirq) ++#endif + + #ifdef CONFIG_XEN + zeroentry xen_hypervisor_callback xen_do_hypervisor_callback +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/hpet.c sun8i-rt/arch/x86/kernel/hpet.c +--- sun8i/arch/x86/kernel/hpet.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/hpet.c 2016-08-22 15:56:39.412194814 +0200 +@@ -8,6 +8,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -570,6 +571,30 @@ static void init_one_hpet_msi_clockevent + #define RESERVE_TIMERS 0 + #endif + ++static int __init dmi_disable_hpet_msi(const struct dmi_system_id *d) ++{ ++ hpet_msi_disable = 1; ++ return 0; ++} ++ ++static struct dmi_system_id __initdata dmi_hpet_table[] = { ++ /* ++ * MSI based per cpu timers lose interrupts when intel_idle() ++ * is enabled - independent of the c-state. With idle=poll the ++ * problem cannot be observed. We have no idea yet, whether ++ * this is a W510 specific issue or a general chipset oddity. ++ */ ++ { ++ .callback = dmi_disable_hpet_msi, ++ .ident = "Lenovo W510", ++ .matches = { ++ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), ++ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W510"), ++ }, ++ }, ++ {} ++}; ++ + static void hpet_msi_capability_lookup(unsigned int start_timer) + { + unsigned int id; +@@ -577,6 +602,8 @@ static void hpet_msi_capability_lookup(u + unsigned int num_timers_used = 0; + int i; + ++ dmi_check_system(dmi_hpet_table); ++ + if (hpet_msi_disable) + return; + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/irq_32.c sun8i-rt/arch/x86/kernel/irq_32.c +--- sun8i/arch/x86/kernel/irq_32.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/irq_32.c 2016-08-22 17:23:13.544254529 +0200 +@@ -149,6 +149,7 @@ void __cpuinit irq_ctx_init(int cpu) + cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu)); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + asmlinkage void do_softirq(void) + { + unsigned long flags; +@@ -179,6 +180,7 @@ asmlinkage void do_softirq(void) + + local_irq_restore(flags); + } ++#endif + + bool handle_irq(unsigned irq, struct pt_regs *regs) + { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/irq_64.c sun8i-rt/arch/x86/kernel/irq_64.c +--- sun8i/arch/x86/kernel/irq_64.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/irq_64.c 2016-08-22 17:23:13.544254529 +0200 +@@ -88,7 +88,7 @@ bool handle_irq(unsigned irq, struct pt_ + return true; + } + +- ++#ifndef CONFIG_PREEMPT_RT_FULL + extern void call_softirq(void); + + asmlinkage void do_softirq(void) +@@ -108,3 +108,4 @@ asmlinkage void do_softirq(void) + } + local_irq_restore(flags); + } ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/irq_work.c sun8i-rt/arch/x86/kernel/irq_work.c +--- sun8i/arch/x86/kernel/irq_work.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/irq_work.c 2016-08-22 17:43:31.676268534 +0200 +@@ -18,6 +18,7 @@ void smp_irq_work_interrupt(struct pt_re + irq_exit(); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void arch_irq_work_raise(void) + { + #ifdef CONFIG_X86_LOCAL_APIC +@@ -28,3 +29,4 @@ void arch_irq_work_raise(void) + apic_wait_icr_idle(); + #endif + } ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/kprobes.c sun8i-rt/arch/x86/kernel/kprobes.c +--- sun8i/arch/x86/kernel/kprobes.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/kprobes.c 2016-08-22 15:56:09.116194465 +0200 +@@ -486,7 +486,6 @@ setup_singlestep(struct kprobe *p, struc + * stepping. + */ + regs->ip = (unsigned long)p->ainsn.insn; +- preempt_enable_no_resched(); + return; + } + #endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/process_32.c sun8i-rt/arch/x86/kernel/process_32.c +--- sun8i/arch/x86/kernel/process_32.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/process_32.c 2016-08-22 18:10:52.352287397 +0200 +@@ -36,6 +36,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -285,6 +286,41 @@ __switch_to(struct task_struct *prev_p, + task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) + __switch_to_xtra(prev_p, next_p, tss); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * Save @prev's kmap_atomic stack ++ */ ++ prev_p->kmap_idx = __this_cpu_read(__kmap_atomic_idx); ++ if (unlikely(prev_p->kmap_idx)) { ++ int i; ++ ++ for (i = 0; i < prev_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ ++ pte_t *ptep = kmap_pte - idx; ++ prev_p->kmap_pte[i] = *ptep; ++ kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx)); ++ } ++ ++ __this_cpu_write(__kmap_atomic_idx, 0); ++ } ++ ++ /* ++ * Restore @next_p's kmap_atomic stack ++ */ ++ if (unlikely(next_p->kmap_idx)) { ++ int i; ++ ++ __this_cpu_write(__kmap_atomic_idx, next_p->kmap_idx); ++ ++ for (i = 0; i < next_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ ++ set_pte(kmap_pte - idx, next_p->kmap_pte[i]); ++ } ++ } ++#endif ++ + /* + * Leave lazy mode, flushing any hypercalls made here. + * This must be done before restoring TLS segments so +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/signal.c sun8i-rt/arch/x86/kernel/signal.c +--- sun8i/arch/x86/kernel/signal.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/signal.c 2016-08-22 16:02:35.808198911 +0200 +@@ -824,6 +824,15 @@ do_notify_resume(struct pt_regs *regs, v + mce_notify_process(); + #endif /* CONFIG_X86_64 && CONFIG_X86_MCE */ + ++#ifdef ARCH_RT_DELAYS_SIGNAL_SEND ++ if (unlikely(current->forced_info.si_signo)) { ++ struct task_struct *t = current; ++ force_sig_info(t->forced_info.si_signo, ++ &t->forced_info, t); ++ t->forced_info.si_signo = 0; ++ } ++#endif ++ + /* deal with pending signal delivery */ + if (thread_info_flags & _TIF_SIGPENDING) + do_signal(regs); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kernel/traps.c sun8i-rt/arch/x86/kernel/traps.c +--- sun8i/arch/x86/kernel/traps.c 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/arch/x86/kernel/traps.c 2016-08-22 16:22:41.440212772 +0200 +@@ -87,9 +87,21 @@ static inline void conditional_sti(struc + local_irq_enable(); + } + +-static inline void preempt_conditional_sti(struct pt_regs *regs) ++static inline void conditional_sti_ist(struct pt_regs *regs) + { ++#ifdef CONFIG_X86_64 ++ /* ++ * X86_64 uses a per CPU stack on the IST for certain traps ++ * like int3. The task can not be preempted when using one ++ * of these stacks, thus preemption must be disabled, otherwise ++ * the stack can be corrupted if the task is scheduled out, ++ * and another task comes in and uses this stack. ++ * ++ * On x86_32 the task keeps its own stack and it is OK if the ++ * task schedules out. ++ */ + inc_preempt_count(); ++#endif + if (regs->flags & X86_EFLAGS_IF) + local_irq_enable(); + } +@@ -100,11 +112,13 @@ static inline void conditional_cli(struc + local_irq_disable(); + } + +-static inline void preempt_conditional_cli(struct pt_regs *regs) ++static inline void conditional_cli_ist(struct pt_regs *regs) + { + if (regs->flags & X86_EFLAGS_IF) + local_irq_disable(); ++#ifdef CONFIG_X86_64 + dec_preempt_count(); ++#endif + } + + static void __kprobes +@@ -332,9 +346,9 @@ dotraplinkage void __kprobes do_int3(str + * as we may switch to the interrupt stack. + */ + debug_stack_usage_inc(); +- preempt_conditional_sti(regs); ++ conditional_sti_ist(regs); + do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); +- preempt_conditional_cli(regs); ++ conditional_cli_ist(regs); + debug_stack_usage_dec(); + } + +@@ -464,12 +478,12 @@ dotraplinkage void __kprobes do_debug(st + debug_stack_usage_inc(); + + /* It's safe to allow irq's after DR6 has been saved */ +- preempt_conditional_sti(regs); ++ conditional_sti_ist(regs); + + if (regs->flags & X86_VM_MASK) { + handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, + X86_TRAP_DB); +- preempt_conditional_cli(regs); ++ conditional_cli_ist(regs); + debug_stack_usage_dec(); + return; + } +@@ -489,7 +503,7 @@ dotraplinkage void __kprobes do_debug(st + si_code = get_si_code(tsk->thread.debugreg6); + if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) + send_sigtrap(tsk, regs, error_code, si_code); +- preempt_conditional_cli(regs); ++ conditional_cli_ist(regs); + debug_stack_usage_dec(); + + return; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/kvm/x86.c sun8i-rt/arch/x86/kvm/x86.c +--- sun8i/arch/x86/kvm/x86.c 2016-08-22 14:14:41.000000000 +0200 ++++ sun8i-rt/arch/x86/kvm/x86.c 2016-08-22 17:49:07.092272390 +0200 +@@ -4899,6 +4899,13 @@ int kvm_arch_init(void *opaque) + goto out; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { ++ printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n"); ++ return -EOPNOTSUPP; ++ } ++#endif ++ + r = kvm_mmu_module_init(); + if (r) + goto out; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/mm/fault.c sun8i-rt/arch/x86/mm/fault.c +--- sun8i/arch/x86/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/x86/mm/fault.c 2016-08-22 16:13:41.868206569 +0200 +@@ -1100,7 +1100,7 @@ do_page_fault(struct pt_regs *regs, unsi + * If we're in an interrupt, have no user context or are running + * in an atomic region then we must not take the fault: + */ +- if (unlikely(in_atomic() || !mm)) { ++ if (unlikely(!mm || pagefault_disabled())) { + bad_area_nosemaphore(regs, error_code, address); + return; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/mm/highmem_32.c sun8i-rt/arch/x86/mm/highmem_32.c +--- sun8i/arch/x86/mm/highmem_32.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/mm/highmem_32.c 2016-08-22 16:17:08.436208943 +0200 +@@ -43,7 +43,7 @@ void *kmap_atomic_prot(struct page *page + type = kmap_atomic_idx_push(); + idx = type + KM_TYPE_NR*smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); +- BUG_ON(!pte_none(*(kmap_pte-idx))); ++ WARN_ON(!pte_none(*(kmap_pte-idx))); + set_pte(kmap_pte-idx, mk_pte(page, prot)); + arch_flush_lazy_mmu_mode(); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/platform/uv/tlb_uv.c sun8i-rt/arch/x86/platform/uv/tlb_uv.c +--- sun8i/arch/x86/platform/uv/tlb_uv.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/platform/uv/tlb_uv.c 2016-08-22 18:23:44.708296276 +0200 +@@ -39,7 +39,7 @@ static int timeout_base_ns[] = { + static int timeout_us; + static int nobau; + static int baudisabled; +-static spinlock_t disable_lock; ++static raw_spinlock_t disable_lock; + static cycles_t congested_cycles; + + /* tunables: */ +@@ -545,7 +545,7 @@ int handle_uv2_busy(struct bau_control * + cycles_t ttm; + + stat->s_uv2_wars++; +- spin_lock(&hmaster->uvhub_lock); ++ raw_spin_lock(&hmaster->uvhub_lock); + /* try for the original first */ + if (busy_one != normal) { + if (!normal_busy(bcp)) +@@ -595,12 +595,12 @@ int handle_uv2_busy(struct bau_control * + * free up. + */ + stat->s_uv2_war_waits++; +- spin_unlock(&hmaster->uvhub_lock); ++ raw_spin_unlock(&hmaster->uvhub_lock); + ttm = get_cycles(); + do { + cpu_relax(); + } while (normal_busy(bcp)); +- spin_lock(&hmaster->uvhub_lock); ++ raw_spin_lock(&hmaster->uvhub_lock); + /* switch to the original descriptor */ + bcp->using_desc = normal; + bau_desc_old = bcp->descriptor_base; +@@ -610,7 +610,7 @@ int handle_uv2_busy(struct bau_control * + bau_desc_new += (ITEMS_PER_DESC * normal); + *bau_desc_new = *bau_desc_old; /* copy the entire descriptor */ + } +- spin_unlock(&hmaster->uvhub_lock); ++ raw_spin_unlock(&hmaster->uvhub_lock); + return FLUSH_RETRY_BUSYBUG; + } + +@@ -724,9 +724,9 @@ static void destination_plugged(struct b + + quiesce_local_uvhub(hmaster); + +- spin_lock(&hmaster->queue_lock); ++ raw_spin_lock(&hmaster->queue_lock); + reset_with_ipi(&bau_desc->distribution, bcp); +- spin_unlock(&hmaster->queue_lock); ++ raw_spin_unlock(&hmaster->queue_lock); + + end_uvhub_quiesce(hmaster); + +@@ -746,9 +746,9 @@ static void destination_timeout(struct b + + quiesce_local_uvhub(hmaster); + +- spin_lock(&hmaster->queue_lock); ++ raw_spin_lock(&hmaster->queue_lock); + reset_with_ipi(&bau_desc->distribution, bcp); +- spin_unlock(&hmaster->queue_lock); ++ raw_spin_unlock(&hmaster->queue_lock); + + end_uvhub_quiesce(hmaster); + +@@ -765,7 +765,7 @@ static void disable_for_congestion(struc + struct ptc_stats *stat) + { + /* let only one cpu do this disabling */ +- spin_lock(&disable_lock); ++ raw_spin_lock(&disable_lock); + + if (!baudisabled && bcp->period_requests && + ((bcp->period_time / bcp->period_requests) > congested_cycles)) { +@@ -784,7 +784,7 @@ static void disable_for_congestion(struc + } + } + +- spin_unlock(&disable_lock); ++ raw_spin_unlock(&disable_lock); + } + + static void count_max_concurr(int stat, struct bau_control *bcp, +@@ -833,7 +833,7 @@ static void record_send_stats(cycles_t t + */ + static void uv1_throttle(struct bau_control *hmaster, struct ptc_stats *stat) + { +- spinlock_t *lock = &hmaster->uvhub_lock; ++ raw_spinlock_t *lock = &hmaster->uvhub_lock; + atomic_t *v; + + v = &hmaster->active_descriptor_count; +@@ -1850,8 +1850,8 @@ static void __init init_per_cpu_tunables + bcp->cong_reps = congested_reps; + bcp->cong_period = congested_period; + bcp->clocks_per_100_usec = usec_2_cycles(100); +- spin_lock_init(&bcp->queue_lock); +- spin_lock_init(&bcp->uvhub_lock); ++ raw_spin_lock_init(&bcp->queue_lock); ++ raw_spin_lock_init(&bcp->uvhub_lock); + } + } + +@@ -2078,7 +2078,7 @@ static int __init uv_bau_init(void) + } + + nuvhubs = uv_num_possible_blades(); +- spin_lock_init(&disable_lock); ++ raw_spin_lock_init(&disable_lock); + congested_cycles = usec_2_cycles(congested_respns_us); + + uv_base_pnode = 0x7fffffff; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/x86/platform/uv/uv_time.c sun8i-rt/arch/x86/platform/uv/uv_time.c +--- sun8i/arch/x86/platform/uv/uv_time.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/arch/x86/platform/uv/uv_time.c 2016-08-22 18:23:44.708296276 +0200 +@@ -58,7 +58,7 @@ static DEFINE_PER_CPU(struct clock_event + + /* There is one of these allocated per node */ + struct uv_rtc_timer_head { +- spinlock_t lock; ++ raw_spinlock_t lock; + /* next cpu waiting for timer, local node relative: */ + int next_cpu; + /* number of cpus on this node: */ +@@ -178,7 +178,7 @@ static __init int uv_rtc_allocate_timers + uv_rtc_deallocate_timers(); + return -ENOMEM; + } +- spin_lock_init(&head->lock); ++ raw_spin_lock_init(&head->lock); + head->ncpus = uv_blade_nr_possible_cpus(bid); + head->next_cpu = -1; + blade_info[bid] = head; +@@ -232,7 +232,7 @@ static int uv_rtc_set_timer(int cpu, u64 + unsigned long flags; + int next_cpu; + +- spin_lock_irqsave(&head->lock, flags); ++ raw_spin_lock_irqsave(&head->lock, flags); + + next_cpu = head->next_cpu; + *t = expires; +@@ -244,12 +244,12 @@ static int uv_rtc_set_timer(int cpu, u64 + if (uv_setup_intr(cpu, expires)) { + *t = ULLONG_MAX; + uv_rtc_find_next_timer(head, pnode); +- spin_unlock_irqrestore(&head->lock, flags); ++ raw_spin_unlock_irqrestore(&head->lock, flags); + return -ETIME; + } + } + +- spin_unlock_irqrestore(&head->lock, flags); ++ raw_spin_unlock_irqrestore(&head->lock, flags); + return 0; + } + +@@ -268,7 +268,7 @@ static int uv_rtc_unset_timer(int cpu, i + unsigned long flags; + int rc = 0; + +- spin_lock_irqsave(&head->lock, flags); ++ raw_spin_lock_irqsave(&head->lock, flags); + + if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force) + rc = 1; +@@ -280,7 +280,7 @@ static int uv_rtc_unset_timer(int cpu, i + uv_rtc_find_next_timer(head, pnode); + } + +- spin_unlock_irqrestore(&head->lock, flags); ++ raw_spin_unlock_irqrestore(&head->lock, flags); + + return rc; + } +@@ -300,13 +300,18 @@ static int uv_rtc_unset_timer(int cpu, i + static cycle_t uv_read_rtc(struct clocksource *cs) + { + unsigned long offset; ++ cycle_t cycles; + ++ preempt_disable(); + if (uv_get_min_hub_revision_id() == 1) + offset = 0; + else + offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE; + +- return (cycle_t)uv_read_local_mmr(UVH_RTC | offset); ++ cycles = (cycle_t)uv_read_local_mmr(UVH_RTC | offset); ++ preempt_enable(); ++ ++ return cycles; + } + + /* +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/arch/xtensa/mm/fault.c sun8i-rt/arch/xtensa/mm/fault.c +--- sun8i/arch/xtensa/mm/fault.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/arch/xtensa/mm/fault.c 2016-08-22 16:13:41.868206569 +0200 +@@ -56,7 +56,7 @@ void do_page_fault(struct pt_regs *regs) + /* If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) { ++ if (!mm || pagefault_disabled()) { + bad_page_fault(regs, address, SIGSEGV); + return; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/block/blk-core.c sun8i-rt/block/blk-core.c +--- sun8i/block/blk-core.c 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/block/blk-core.c 2016-08-22 17:39:01.896265432 +0200 +@@ -237,7 +237,7 @@ EXPORT_SYMBOL(blk_delay_queue); + **/ + void blk_start_queue(struct request_queue *q) + { +- WARN_ON(!irqs_disabled()); ++ WARN_ON_NONRT(!irqs_disabled()); + + queue_flag_clear(QUEUE_FLAG_STOPPED, q); + __blk_run_queue(q); +@@ -302,7 +302,11 @@ void __blk_run_queue(struct request_queu + { + if (unlikely(blk_queue_stopped(q))) + return; +- ++ /* ++ * q->request_fn() can drop q->queue_lock and reenable ++ * interrupts, but must return with q->queue_lock held and ++ * interrupts disabled. ++ */ + q->request_fn(q); + } + EXPORT_SYMBOL(__blk_run_queue); +@@ -2782,11 +2786,11 @@ static void queue_unplugged(struct reque + * this lock). + */ + if (from_schedule) { +- spin_unlock(q->queue_lock); ++ spin_unlock_irq(q->queue_lock); + blk_run_queue_async(q); + } else { + __blk_run_queue(q); +- spin_unlock(q->queue_lock); ++ spin_unlock_irq(q->queue_lock); + } + + } +@@ -2812,7 +2816,6 @@ static void flush_plug_callbacks(struct + void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) + { + struct request_queue *q; +- unsigned long flags; + struct request *rq; + LIST_HEAD(list); + unsigned int depth; +@@ -2833,11 +2836,6 @@ void blk_flush_plug_list(struct blk_plug + q = NULL; + depth = 0; + +- /* +- * Save and disable interrupts here, to avoid doing it for every +- * queue lock we have to take. +- */ +- local_irq_save(flags); + while (!list_empty(&list)) { + rq = list_entry_rq(list.next); + list_del_init(&rq->queuelist); +@@ -2850,7 +2848,7 @@ void blk_flush_plug_list(struct blk_plug + queue_unplugged(q, depth, from_schedule); + q = rq->q; + depth = 0; +- spin_lock(q->queue_lock); ++ spin_lock_irq(q->queue_lock); + } + + /* +@@ -2877,8 +2875,6 @@ void blk_flush_plug_list(struct blk_plug + */ + if (q) + queue_unplugged(q, depth, from_schedule); +- +- local_irq_restore(flags); + } + + void blk_finish_plug(struct blk_plug *plug) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/block/blk-ioc.c sun8i-rt/block/blk-ioc.c +--- sun8i/block/blk-ioc.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/block/blk-ioc.c 2016-08-22 18:07:40.848285195 +0200 +@@ -8,6 +8,7 @@ + #include + #include /* for max_pfn/max_low_pfn */ + #include ++#include + + #include "blk.h" + +@@ -110,7 +111,7 @@ static void ioc_release_fn(struct work_s + spin_unlock(q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); +- cpu_relax(); ++ cpu_chill(); + spin_lock_irqsave_nested(&ioc->lock, flags, 1); + } + } +@@ -188,7 +189,7 @@ retry: + spin_unlock(icq->q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); +- cpu_relax(); ++ cpu_chill(); + goto retry; + } + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/block/blk-iopoll.c sun8i-rt/block/blk-iopoll.c +--- sun8i/block/blk-iopoll.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/block/blk-iopoll.c 2016-08-22 17:51:53.960274309 +0200 +@@ -38,6 +38,7 @@ void blk_iopoll_sched(struct blk_iopoll + list_add_tail(&iop->list, &__get_cpu_var(blk_cpu_iopoll)); + __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(blk_iopoll_sched); + +@@ -135,6 +136,7 @@ static void blk_iopoll_softirq(struct so + __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); + + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + /** +@@ -204,6 +206,7 @@ static int __cpuinit blk_iopoll_cpu_noti + &__get_cpu_var(blk_cpu_iopoll)); + __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + return NOTIFY_OK; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/block/blk-softirq.c sun8i-rt/block/blk-softirq.c +--- sun8i/block/blk-softirq.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/block/blk-softirq.c 2016-08-22 17:51:53.960274309 +0200 +@@ -51,6 +51,7 @@ static void trigger_softirq(void *data) + raise_softirq_irqoff(BLOCK_SOFTIRQ); + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + /* +@@ -93,6 +94,7 @@ static int __cpuinit blk_cpu_notify(stru + &__get_cpu_var(blk_cpu_done)); + raise_softirq_irqoff(BLOCK_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + return NOTIFY_OK; +@@ -150,6 +152,7 @@ do_local: + goto do_local; + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + /** +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/Documentation/hwlat_detector.txt sun8i-rt/Documentation/hwlat_detector.txt +--- sun8i/Documentation/hwlat_detector.txt 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/Documentation/hwlat_detector.txt 2016-08-22 16:23:41.604213464 +0200 +@@ -0,0 +1,64 @@ ++Introduction: ++------------- ++ ++The module hwlat_detector is a special purpose kernel module that is used to ++detect large system latencies induced by the behavior of certain underlying ++hardware or firmware, independent of Linux itself. The code was developed ++originally to detect SMIs (System Management Interrupts) on x86 systems, ++however there is nothing x86 specific about this patchset. It was ++originally written for use by the "RT" patch since the Real Time ++kernel is highly latency sensitive. ++ ++SMIs are usually not serviced by the Linux kernel, which typically does not ++even know that they are occuring. SMIs are instead are set up by BIOS code ++and are serviced by BIOS code, usually for "critical" events such as ++management of thermal sensors and fans. Sometimes though, SMIs are used for ++other tasks and those tasks can spend an inordinate amount of time in the ++handler (sometimes measured in milliseconds). Obviously this is a problem if ++you are trying to keep event service latencies down in the microsecond range. ++ ++The hardware latency detector works by hogging all of the cpus for configurable ++amounts of time (by calling stop_machine()), polling the CPU Time Stamp Counter ++for some period, then looking for gaps in the TSC data. Any gap indicates a ++time when the polling was interrupted and since the machine is stopped and ++interrupts turned off the only thing that could do that would be an SMI. ++ ++Note that the SMI detector should *NEVER* be used in a production environment. ++It is intended to be run manually to determine if the hardware platform has a ++problem with long system firmware service routines. ++ ++Usage: ++------ ++ ++Loading the module hwlat_detector passing the parameter "enabled=1" (or by ++setting the "enable" entry in "hwlat_detector" debugfs toggled on) is the only ++step required to start the hwlat_detector. It is possible to redefine the ++threshold in microseconds (us) above which latency spikes will be taken ++into account (parameter "threshold="). ++ ++Example: ++ ++ # modprobe hwlat_detector enabled=1 threshold=100 ++ ++After the module is loaded, it creates a directory named "hwlat_detector" under ++the debugfs mountpoint, "/debug/hwlat_detector" for this text. It is necessary ++to have debugfs mounted, which might be on /sys/debug on your system. ++ ++The /debug/hwlat_detector interface contains the following files: ++ ++count - number of latency spikes observed since last reset ++enable - a global enable/disable toggle (0/1), resets count ++max - maximum hardware latency actually observed (usecs) ++sample - a pipe from which to read current raw sample data ++ in the format ++ (can be opened O_NONBLOCK for a single sample) ++threshold - minimum latency value to be considered (usecs) ++width - time period to sample with CPUs held (usecs) ++ must be less than the total window size (enforced) ++window - total period of sampling, width being inside (usecs) ++ ++By default we will set width to 500,000 and window to 1,000,000, meaning that ++we will sample every 1,000,000 usecs (1s) for 500,000 usecs (0.5s). If we ++observe any latencies that exceed the threshold (initially 100 usecs), ++then we write to a global sample ring buffer of 8K samples, which is ++consumed by reading from the "sample" (pipe) debugfs file interface. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/Documentation/kernel-parameters.txt sun8i-rt/Documentation/kernel-parameters.txt +--- sun8i/Documentation/kernel-parameters.txt 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/Documentation/kernel-parameters.txt 2016-08-22 15:56:21.220194604 +0200 +@@ -2472,6 +2472,15 @@ bytes respectively. Such letter suffixes + + sched_debug [KNL] Enables verbose scheduler debug messages. + ++ skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate ++ xtime_lock contention on larger systems, and/or RCU lock ++ contention on all systems with CONFIG_MAXSMP set. ++ Format: { "0" | "1" } ++ 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1" ++ 1 -- enable. ++ Note: increases power consumption, thus should only be ++ enabled if running jitter sensitive (HPC/RT) workloads. ++ + security= [SECURITY] Choose a security module to enable at boot. + If this boot parameter is not specified, only the first + security module asking for security registration will be +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/Documentation/sysrq.txt sun8i-rt/Documentation/sysrq.txt +--- sun8i/Documentation/sysrq.txt 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/Documentation/sysrq.txt 2016-08-22 17:47:50.120271505 +0200 +@@ -57,10 +57,17 @@ On PowerPC - Press 'ALT - Print Screen ( + On other - If you know of the key combos for other architectures, please + let me know so I can add them to this section. + +-On all - write a character to /proc/sysrq-trigger. e.g.: +- ++On all - write a character to /proc/sysrq-trigger, e.g.: + echo t > /proc/sysrq-trigger + ++On all - Enable network SysRq by writing a cookie to icmp_echo_sysrq, e.g. ++ echo 0x01020304 >/proc/sys/net/ipv4/icmp_echo_sysrq ++ Send an ICMP echo request with this pattern plus the particular ++ SysRq command key. Example: ++ # ping -c1 -s57 -p0102030468 ++ will trigger the SysRq-H (help) command. ++ ++ + * What are the 'command' keys? + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 'b' - Will immediately reboot the system without syncing or unmounting +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/Documentation/trace/histograms.txt sun8i-rt/Documentation/trace/histograms.txt +--- sun8i/Documentation/trace/histograms.txt 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/Documentation/trace/histograms.txt 2016-08-22 16:23:25.124213274 +0200 +@@ -0,0 +1,186 @@ ++ Using the Linux Kernel Latency Histograms ++ ++ ++This document gives a short explanation how to enable, configure and use ++latency histograms. Latency histograms are primarily relevant in the ++context of real-time enabled kernels (CONFIG_PREEMPT/CONFIG_PREEMPT_RT) ++and are used in the quality management of the Linux real-time ++capabilities. ++ ++ ++* Purpose of latency histograms ++ ++A latency histogram continuously accumulates the frequencies of latency ++data. There are two types of histograms ++- potential sources of latencies ++- effective latencies ++ ++ ++* Potential sources of latencies ++ ++Potential sources of latencies are code segments where interrupts, ++preemption or both are disabled (aka critical sections). To create ++histograms of potential sources of latency, the kernel stores the time ++stamp at the start of a critical section, determines the time elapsed ++when the end of the section is reached, and increments the frequency ++counter of that latency value - irrespective of whether any concurrently ++running process is affected by latency or not. ++- Configuration items (in the Kernel hacking/Tracers submenu) ++ CONFIG_INTERRUPT_OFF_LATENCY ++ CONFIG_PREEMPT_OFF_LATENCY ++ ++ ++* Effective latencies ++ ++Effective latencies are actually occuring during wakeup of a process. To ++determine effective latencies, the kernel stores the time stamp when a ++process is scheduled to be woken up, and determines the duration of the ++wakeup time shortly before control is passed over to this process. Note ++that the apparent latency in user space may be somewhat longer, since the ++process may be interrupted after control is passed over to it but before ++the execution in user space takes place. Simply measuring the interval ++between enqueuing and wakeup may also not appropriate in cases when a ++process is scheduled as a result of a timer expiration. The timer may have ++missed its deadline, e.g. due to disabled interrupts, but this latency ++would not be registered. Therefore, the offsets of missed timers are ++recorded in a separate histogram. If both wakeup latency and missed timer ++offsets are configured and enabled, a third histogram may be enabled that ++records the overall latency as a sum of the timer latency, if any, and the ++wakeup latency. This histogram is called "timerandwakeup". ++- Configuration items (in the Kernel hacking/Tracers submenu) ++ CONFIG_WAKEUP_LATENCY ++ CONFIG_MISSED_TIMER_OFSETS ++ ++ ++* Usage ++ ++The interface to the administration of the latency histograms is located ++in the debugfs file system. To mount it, either enter ++ ++mount -t sysfs nodev /sys ++mount -t debugfs nodev /sys/kernel/debug ++ ++from shell command line level, or add ++ ++nodev /sys sysfs defaults 0 0 ++nodev /sys/kernel/debug debugfs defaults 0 0 ++ ++to the file /etc/fstab. All latency histogram related files are then ++available in the directory /sys/kernel/debug/tracing/latency_hist. A ++particular histogram type is enabled by writing non-zero to the related ++variable in the /sys/kernel/debug/tracing/latency_hist/enable directory. ++Select "preemptirqsoff" for the histograms of potential sources of ++latencies and "wakeup" for histograms of effective latencies etc. The ++histogram data - one per CPU - are available in the files ++ ++/sys/kernel/debug/tracing/latency_hist/preemptoff/CPUx ++/sys/kernel/debug/tracing/latency_hist/irqsoff/CPUx ++/sys/kernel/debug/tracing/latency_hist/preemptirqsoff/CPUx ++/sys/kernel/debug/tracing/latency_hist/wakeup/CPUx ++/sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio/CPUx ++/sys/kernel/debug/tracing/latency_hist/missed_timer_offsets/CPUx ++/sys/kernel/debug/tracing/latency_hist/timerandwakeup/CPUx ++ ++The histograms are reset by writing non-zero to the file "reset" in a ++particular latency directory. To reset all latency data, use ++ ++#!/bin/sh ++ ++TRACINGDIR=/sys/kernel/debug/tracing ++HISTDIR=$TRACINGDIR/latency_hist ++ ++if test -d $HISTDIR ++then ++ cd $HISTDIR ++ for i in `find . | grep /reset$` ++ do ++ echo 1 >$i ++ done ++fi ++ ++ ++* Data format ++ ++Latency data are stored with a resolution of one microsecond. The ++maximum latency is 10,240 microseconds. The data are only valid, if the ++overflow register is empty. Every output line contains the latency in ++microseconds in the first row and the number of samples in the second ++row. To display only lines with a positive latency count, use, for ++example, ++ ++grep -v " 0$" /sys/kernel/debug/tracing/latency_hist/preemptoff/CPU0 ++ ++#Minimum latency: 0 microseconds. ++#Average latency: 0 microseconds. ++#Maximum latency: 25 microseconds. ++#Total samples: 3104770694 ++#There are 0 samples greater or equal than 10240 microseconds ++#usecs samples ++ 0 2984486876 ++ 1 49843506 ++ 2 58219047 ++ 3 5348126 ++ 4 2187960 ++ 5 3388262 ++ 6 959289 ++ 7 208294 ++ 8 40420 ++ 9 4485 ++ 10 14918 ++ 11 18340 ++ 12 25052 ++ 13 19455 ++ 14 5602 ++ 15 969 ++ 16 47 ++ 17 18 ++ 18 14 ++ 19 1 ++ 20 3 ++ 21 2 ++ 22 5 ++ 23 2 ++ 25 1 ++ ++ ++* Wakeup latency of a selected process ++ ++To only collect wakeup latency data of a particular process, write the ++PID of the requested process to ++ ++/sys/kernel/debug/tracing/latency_hist/wakeup/pid ++ ++PIDs are not considered, if this variable is set to 0. ++ ++ ++* Details of the process with the highest wakeup latency so far ++ ++Selected data of the process that suffered from the highest wakeup ++latency that occurred in a particular CPU are available in the file ++ ++/sys/kernel/debug/tracing/latency_hist/wakeup/max_latency-CPUx. ++ ++In addition, other relevant system data at the time when the ++latency occurred are given. ++ ++The format of the data is (all in one line): ++ () \ ++<- ++ ++The value of is only relevant in the combined timer ++and wakeup latency recording. In the wakeup recording, it is ++always 0, in the missed_timer_offsets recording, it is the same ++as . ++ ++When retrospectively searching for the origin of a latency and ++tracing was not enabled, it may be helpful to know the name and ++some basic data of the task that (finally) was switching to the ++late real-tlme task. In addition to the victim's data, also the ++data of the possible culprit are therefore displayed after the ++"<-" symbol. ++ ++Finally, the timestamp of the time when the latency occurred ++in . after the most recent system boot ++is provided. ++ ++These data are also reset when the wakeup histogram is reset. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/acpi/acpica/acglobal.h sun8i-rt/drivers/acpi/acpica/acglobal.h +--- sun8i/drivers/acpi/acpica/acglobal.h 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/drivers/acpi/acpica/acglobal.h 2016-08-22 18:11:04.468287536 +0200 +@@ -251,7 +251,7 @@ ACPI_EXTERN u8 acpi_gbl_global_lock_pend + * interrupt level + */ + ACPI_EXTERN acpi_spinlock acpi_gbl_gpe_lock; /* For GPE data structs and registers */ +-ACPI_EXTERN acpi_spinlock acpi_gbl_hardware_lock; /* For ACPI H/W except GPE registers */ ++ACPI_EXTERN acpi_raw_spinlock acpi_gbl_hardware_lock; /* For ACPI H/W except GPE registers */ + + /***************************************************************************** + * +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/acpi/acpica/hwregs.c sun8i-rt/drivers/acpi/acpica/hwregs.c +--- sun8i/drivers/acpi/acpica/hwregs.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/drivers/acpi/acpica/hwregs.c 2016-08-22 18:11:04.468287536 +0200 +@@ -271,14 +271,14 @@ acpi_status acpi_hw_clear_acpi_status(vo + ACPI_BITMASK_ALL_FIXED_STATUS, + ACPI_FORMAT_UINT64(acpi_gbl_xpm1a_status.address))); + +- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); ++ raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); + + /* Clear the fixed events in PM1 A/B */ + + status = acpi_hw_register_write(ACPI_REGISTER_PM1_STATUS, + ACPI_BITMASK_ALL_FIXED_STATUS); + +- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); ++ raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); + + if (ACPI_FAILURE(status)) + goto exit; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/acpi/acpica/hwxface.c sun8i-rt/drivers/acpi/acpica/hwxface.c +--- sun8i/drivers/acpi/acpica/hwxface.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/drivers/acpi/acpica/hwxface.c 2016-08-22 18:11:04.472287536 +0200 +@@ -366,7 +366,7 @@ acpi_status acpi_write_bit_register(u32 + return_ACPI_STATUS(AE_BAD_PARAMETER); + } + +- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); ++ raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); + + /* + * At this point, we know that the parent register is one of the +@@ -427,7 +427,7 @@ acpi_status acpi_write_bit_register(u32 + + unlock_and_exit: + +- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); ++ raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); + return_ACPI_STATUS(status); + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/acpi/acpica/utmutex.c sun8i-rt/drivers/acpi/acpica/utmutex.c +--- sun8i/drivers/acpi/acpica/utmutex.c 2016-08-22 14:14:13.000000000 +0200 ++++ sun8i-rt/drivers/acpi/acpica/utmutex.c 2016-08-22 18:11:04.472287536 +0200 +@@ -88,7 +88,7 @@ acpi_status acpi_ut_mutex_initialize(voi + return_ACPI_STATUS (status); + } + +- status = acpi_os_create_lock (&acpi_gbl_hardware_lock); ++ status = acpi_os_create_raw_lock (&acpi_gbl_hardware_lock); + if (ACPI_FAILURE (status)) { + return_ACPI_STATUS (status); + } +@@ -135,7 +135,7 @@ void acpi_ut_mutex_terminate(void) + /* Delete the spinlocks */ + + acpi_os_delete_lock(acpi_gbl_gpe_lock); +- acpi_os_delete_lock(acpi_gbl_hardware_lock); ++ acpi_os_delete_raw_lock(acpi_gbl_hardware_lock); + + /* Delete the reader/writer lock */ + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/ata/libata-sff.c sun8i-rt/drivers/ata/libata-sff.c +--- sun8i/drivers/ata/libata-sff.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/drivers/ata/libata-sff.c 2016-08-22 16:31:02.088218528 +0200 +@@ -678,9 +678,9 @@ unsigned int ata_sff_data_xfer_noirq(str + unsigned long flags; + unsigned int consumed; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + consumed = ata_sff_data_xfer32(dev, buf, buflen, rw); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + return consumed; + } +@@ -719,7 +719,7 @@ static void ata_pio_sector(struct ata_qu + unsigned long flags; + + /* FIXME: use a bounce buffer */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + buf = kmap_atomic(page); + + /* do the actual data transfer */ +@@ -727,7 +727,7 @@ static void ata_pio_sector(struct ata_qu + do_write); + + kunmap_atomic(buf); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } else { + buf = page_address(page); + ap->ops->sff_data_xfer(qc->dev, buf + offset, qc->sect_size, +@@ -864,7 +864,7 @@ next_sg: + unsigned long flags; + + /* FIXME: use bounce buffer */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + buf = kmap_atomic(page); + + /* do the actual data transfer */ +@@ -872,7 +872,7 @@ next_sg: + count, rw); + + kunmap_atomic(buf); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } else { + buf = page_address(page); + consumed = ap->ops->sff_data_xfer(dev, buf + offset, +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/char/random.c sun8i-rt/drivers/char/random.c +--- sun8i/drivers/char/random.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/drivers/char/random.c 2016-08-22 18:01:43.184281083 +0200 +@@ -448,7 +448,7 @@ static struct entropy_store input_pool = + .poolinfo = &poolinfo_table[0], + .name = "input", + .limit = 1, +- .lock = __SPIN_LOCK_UNLOCKED(&input_pool.lock), ++ .lock = __SPIN_LOCK_UNLOCKED(input_pool.lock), + .pool = input_pool_data + }; + +@@ -457,7 +457,7 @@ static struct entropy_store blocking_poo + .name = "blocking", + .limit = 1, + .pull = &input_pool, +- .lock = __SPIN_LOCK_UNLOCKED(&blocking_pool.lock), ++ .lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock), + .pool = blocking_pool_data + }; + +@@ -465,7 +465,7 @@ static struct entropy_store nonblocking_ + .poolinfo = &poolinfo_table[1], + .name = "nonblocking", + .pull = &input_pool, +- .lock = __SPIN_LOCK_UNLOCKED(&nonblocking_pool.lock), ++ .lock = __SPIN_LOCK_UNLOCKED(nonblocking_pool.lock), + .pool = nonblocking_pool_data + }; + +@@ -679,8 +679,11 @@ static void add_timer_randomness(struct + preempt_disable(); + /* if over the trickle threshold, use only 1 in 4096 samples */ + if (input_pool.entropy_count > trickle_thresh && +- ((__this_cpu_inc_return(trickle_count) - 1) & 0xfff)) +- goto out; ++ ((__this_cpu_inc_return(trickle_count) - 1) & 0xfff)) { ++ preempt_enable(); ++ return; ++ } ++ preempt_enable(); + + sample.jiffies = jiffies; + sample.cycles = get_cycles(); +@@ -722,8 +725,6 @@ static void add_timer_randomness(struct + credit_entropy_bits(&input_pool, + min_t(int, fls(delta>>1), 11)); + } +-out: +- preempt_enable(); + } + + void add_input_randomness(unsigned int type, unsigned int code, +@@ -744,18 +745,16 @@ EXPORT_SYMBOL_GPL(add_input_randomness); + + static DEFINE_PER_CPU(struct fast_pool, irq_randomness); + +-void add_interrupt_randomness(int irq, int irq_flags) ++void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) + { + struct entropy_store *r; + struct fast_pool *fast_pool = &__get_cpu_var(irq_randomness); +- struct pt_regs *regs = get_irq_regs(); + unsigned long now = jiffies; + __u32 input[4], cycles = get_cycles(); + + input[0] = cycles ^ jiffies; + input[1] = irq; +- if (regs) { +- __u64 ip = instruction_pointer(regs); ++ if (ip) { + input[2] = ip; + input[3] = ip >> 32; + } +@@ -769,7 +768,11 @@ void add_interrupt_randomness(int irq, i + fast_pool->last = now; + + r = nonblocking_pool.initialized ? &input_pool : &nonblocking_pool; ++#ifndef CONFIG_PREEMPT_RT_FULL + __mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool), NULL); ++#else ++ mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool), NULL); ++#endif + /* + * If we don't have a valid cycle counter, and we see + * back-to-back timer interrupts, then skip giving credit for +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/clocksource/tcb_clksrc.c sun8i-rt/drivers/clocksource/tcb_clksrc.c +--- sun8i/drivers/clocksource/tcb_clksrc.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/clocksource/tcb_clksrc.c 2016-08-22 16:03:35.728199600 +0200 +@@ -23,8 +23,7 @@ + * this 32 bit free-running counter. the second channel is not used. + * + * - The third channel may be used to provide a 16-bit clockevent +- * source, used in either periodic or oneshot mode. This runs +- * at 32 KiHZ, and can handle delays of up to two seconds. ++ * source, used in either periodic or oneshot mode. + * + * A boot clocksource and clockevent source are also currently needed, + * unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so +@@ -74,6 +73,7 @@ static struct clocksource clksrc = { + struct tc_clkevt_device { + struct clock_event_device clkevt; + struct clk *clk; ++ u32 freq; + void __iomem *regs; + }; + +@@ -82,13 +82,6 @@ static struct tc_clkevt_device *to_tc_cl + return container_of(clkevt, struct tc_clkevt_device, clkevt); + } + +-/* For now, we always use the 32K clock ... this optimizes for NO_HZ, +- * because using one of the divided clocks would usually mean the +- * tick rate can never be less than several dozen Hz (vs 0.5 Hz). +- * +- * A divided clock could be good for high resolution timers, since +- * 30.5 usec resolution can seem "low". +- */ + static u32 timer_clock; + + static void tc_mode(enum clock_event_mode m, struct clock_event_device *d) +@@ -111,11 +104,12 @@ static void tc_mode(enum clock_event_mod + case CLOCK_EVT_MODE_PERIODIC: + clk_enable(tcd->clk); + +- /* slow clock, count up to RC, then irq and restart */ ++ /* count up to RC, then irq and restart */ + __raw_writel(timer_clock + | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, + regs + ATMEL_TC_REG(2, CMR)); +- __raw_writel((32768 + HZ/2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); ++ __raw_writel((tcd->freq + HZ/2)/HZ, ++ tcaddr + ATMEL_TC_REG(2, RC)); + + /* Enable clock and interrupts on RC compare */ + __raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); +@@ -128,7 +122,7 @@ static void tc_mode(enum clock_event_mod + case CLOCK_EVT_MODE_ONESHOT: + clk_enable(tcd->clk); + +- /* slow clock, count up to RC, then irq and stop */ ++ /* count up to RC, then irq and stop */ + __raw_writel(timer_clock | ATMEL_TC_CPCSTOP + | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, + regs + ATMEL_TC_REG(2, CMR)); +@@ -158,8 +152,12 @@ static struct tc_clkevt_device clkevt = + .features = CLOCK_EVT_FEAT_PERIODIC + | CLOCK_EVT_FEAT_ONESHOT, + .shift = 32, ++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + /* Should be lower than at91rm9200's system timer */ + .rating = 125, ++#else ++ .rating = 200, ++#endif + .set_next_event = tc_next_event, + .set_mode = tc_mode, + }, +@@ -185,8 +183,9 @@ static struct irqaction tc_irqaction = { + .handler = ch2_irq, + }; + +-static void __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) ++static void __init setup_clkevents(struct atmel_tc *tc, int divisor_idx) + { ++ unsigned divisor = atmel_tc_divisors[divisor_idx]; + struct clk *t2_clk = tc->clk[2]; + int irq = tc->irq[2]; + +@@ -194,11 +193,17 @@ static void __init setup_clkevents(struc + clkevt.clk = t2_clk; + tc_irqaction.dev_id = &clkevt; + +- timer_clock = clk32k_divisor_idx; ++ timer_clock = divisor_idx; + +- clkevt.clkevt.mult = div_sc(32768, NSEC_PER_SEC, clkevt.clkevt.shift); +- clkevt.clkevt.max_delta_ns +- = clockevent_delta2ns(0xffff, &clkevt.clkevt); ++ if (!divisor) ++ clkevt.freq = 32768; ++ else ++ clkevt.freq = clk_get_rate(t2_clk)/divisor; ++ ++ clkevt.clkevt.mult = div_sc(clkevt.freq, NSEC_PER_SEC, ++ clkevt.clkevt.shift); ++ clkevt.clkevt.max_delta_ns = ++ clockevent_delta2ns(0xffff, &clkevt.clkevt); + clkevt.clkevt.min_delta_ns = clockevent_delta2ns(1, &clkevt.clkevt) + 1; + clkevt.clkevt.cpumask = cpumask_of(0); + +@@ -327,8 +332,11 @@ static int __init tcb_clksrc_init(void) + clocksource_register_hz(&clksrc, divided_rate); + + /* channel 2: periodic and oneshot timer support */ ++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + setup_clkevents(tc, clk32k_divisor_idx); +- ++#else ++ setup_clkevents(tc, best_divisor_idx); ++#endif + return 0; + } + arch_initcall(tcb_clksrc_init); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/gpio/gpio-omap.c sun8i-rt/drivers/gpio/gpio-omap.c +--- sun8i/drivers/gpio/gpio-omap.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/gpio/gpio-omap.c 2016-08-22 18:20:00.492293698 +0200 +@@ -67,7 +67,7 @@ struct gpio_bank { + u32 saved_risingdetect; + u32 level_mask; + u32 toggle_mask; +- spinlock_t lock; ++ raw_spinlock_t lock; + struct gpio_chip chip; + struct clk *dbck; + u32 mod_usage; +@@ -395,9 +395,9 @@ static int gpio_irq_type(struct irq_data + (type & (IRQ_TYPE_LEVEL_LOW|IRQ_TYPE_LEVEL_HIGH))) + return -EINVAL; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + retval = _set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), type); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH)) + __irq_set_handler_locked(d->irq, handle_level_irq); +@@ -514,14 +514,14 @@ static int _set_gpio_wakeup(struct gpio_ + return -EINVAL; + } + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + if (enable) + bank->suspend_wakeup |= gpio_bit; + else + bank->suspend_wakeup &= ~gpio_bit; + + __raw_writel(bank->suspend_wakeup, bank->base + bank->regs->wkup_en); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -555,7 +555,7 @@ static int omap_gpio_request(struct gpio + if (!bank->mod_usage) + pm_runtime_get_sync(bank->dev); + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + /* Set trigger to none. You need to enable the desired trigger with + * request_irq() or set_irq_type(). + */ +@@ -581,7 +581,7 @@ static int omap_gpio_request(struct gpio + + bank->mod_usage |= 1 << offset; + +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -592,7 +592,7 @@ static void omap_gpio_free(struct gpio_c + void __iomem *base = bank->base; + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + + if (bank->regs->wkup_en) { + /* Disable wake-up during idle for dynamic tick */ +@@ -615,7 +615,7 @@ static void omap_gpio_free(struct gpio_c + } + + _reset_gpio(bank, bank->chip.base + offset); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + /* + * If this is the last gpio to be freed in the bank, +@@ -720,9 +720,9 @@ static void gpio_irq_shutdown(struct irq + unsigned int gpio = irq_to_gpio(bank, d->irq); + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + _reset_gpio(bank, gpio); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + } + + static void gpio_ack_irq(struct irq_data *d) +@@ -739,10 +739,10 @@ static void gpio_mask_irq(struct irq_dat + unsigned int gpio = irq_to_gpio(bank, d->irq); + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + _set_gpio_irqenable(bank, gpio, 0); + _set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), IRQ_TYPE_NONE); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + } + + static void gpio_unmask_irq(struct irq_data *d) +@@ -753,7 +753,7 @@ static void gpio_unmask_irq(struct irq_d + u32 trigger = irqd_get_trigger_type(d); + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + if (trigger) + _set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), trigger); + +@@ -765,7 +765,7 @@ static void gpio_unmask_irq(struct irq_d + } + + _set_gpio_irqenable(bank, gpio, 1); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + } + + static struct irq_chip gpio_irq_chip = { +@@ -788,10 +788,10 @@ static int omap_mpuio_suspend_noirq(stru + OMAP_MPUIO_GPIO_MASKIT / bank->stride; + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + bank->saved_wakeup = __raw_readl(mask_reg); + __raw_writel(0xffff & ~bank->suspend_wakeup, mask_reg); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -804,9 +804,9 @@ static int omap_mpuio_resume_noirq(struc + OMAP_MPUIO_GPIO_MASKIT / bank->stride; + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + __raw_writel(bank->saved_wakeup, mask_reg); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -849,9 +849,9 @@ static int gpio_input(struct gpio_chip * + unsigned long flags; + + bank = container_of(chip, struct gpio_bank, chip); +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + _set_gpio_direction(bank, offset, 1); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return 0; + } + +@@ -882,10 +882,10 @@ static int gpio_output(struct gpio_chip + unsigned long flags; + + bank = container_of(chip, struct gpio_bank, chip); +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + bank->set_dataout(bank, offset, value); + _set_gpio_direction(bank, offset, 0); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return 0; + } + +@@ -903,9 +903,9 @@ static int gpio_debounce(struct gpio_chi + dev_err(bank->dev, "Could not get gpio dbck\n"); + } + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + _set_gpio_debounce(bank, offset, debounce); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -916,9 +916,9 @@ static void gpio_set(struct gpio_chip *c + unsigned long flags; + + bank = container_of(chip, struct gpio_bank, chip); +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + bank->set_dataout(bank, offset, value); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + } + + static int gpio_2irq(struct gpio_chip *chip, unsigned offset) +@@ -1109,7 +1109,7 @@ static int __devinit omap_gpio_probe(str + else + bank->set_dataout = _set_gpio_dataout_mask; + +- spin_lock_init(&bank->lock); ++ raw_spin_lock_init(&bank->lock); + + /* Static mapping, never released */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); +@@ -1169,11 +1169,11 @@ static int omap_gpio_suspend(struct devi + + wakeup_enable = bank->base + bank->regs->wkup_en; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + bank->saved_wakeup = __raw_readl(wakeup_enable); + _gpio_rmw(base, bank->regs->wkup_en, 0xffffffff, 0); + _gpio_rmw(base, bank->regs->wkup_en, bank->suspend_wakeup, 1); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -1191,10 +1191,10 @@ static int omap_gpio_resume(struct devic + if (!bank->regs->wkup_en || !bank->saved_wakeup) + return 0; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + _gpio_rmw(base, bank->regs->wkup_en, 0xffffffff, 0); + _gpio_rmw(base, bank->regs->wkup_en, bank->saved_wakeup, 1); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -1211,7 +1211,7 @@ static int omap_gpio_runtime_suspend(str + unsigned long flags; + u32 wake_low, wake_hi; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + + /* + * Only edges can generate a wakeup event to the PRCM. +@@ -1263,7 +1263,7 @@ update_gpio_context_count: + bank->get_context_loss_count(bank->dev); + + _gpio_dbck_disable(bank); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -1276,7 +1276,7 @@ static int omap_gpio_runtime_resume(stru + u32 l = 0, gen, gen0, gen1; + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + _gpio_dbck_enable(bank); + + /* +@@ -1291,7 +1291,7 @@ static int omap_gpio_runtime_resume(stru + bank->base + bank->regs->risingdetect); + + if (!bank->workaround_enabled) { +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return 0; + } + +@@ -1302,7 +1302,7 @@ static int omap_gpio_runtime_resume(stru + !context_lost_cnt_after) { + omap_gpio_restore_context(bank); + } else { +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return 0; + } + } +@@ -1361,7 +1361,7 @@ static int omap_gpio_runtime_resume(stru + } + + bank->workaround_enabled = false; +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/gpu/drm/drm_irq.c sun8i-rt/drivers/gpu/drm/drm_irq.c +--- sun8i/drivers/gpu/drm/drm_irq.c 2016-08-22 14:14:35.000000000 +0200 ++++ sun8i-rt/drivers/gpu/drm/drm_irq.c 2016-08-22 18:15:57.056290900 +0200 +@@ -619,11 +619,6 @@ int drm_calc_vbltimestamp_from_scanoutpo + * code gets preempted or delayed for some reason. + */ + for (i = 0; i < DRM_TIMESTAMP_MAXRETRIES; i++) { +- /* Disable preemption to make it very likely to +- * succeed in the first iteration even on PREEMPT_RT kernel. +- */ +- preempt_disable(); +- + /* Get system timestamp before query. */ + do_gettimeofday(&stime); + +@@ -633,8 +628,6 @@ int drm_calc_vbltimestamp_from_scanoutpo + /* Get system timestamp after query. */ + do_gettimeofday(&raw_time); + +- preempt_enable(); +- + /* Return as no-op if scanout query unsupported or failed. */ + if (!(vbl_status & DRM_SCANOUTPOS_VALID)) { + DRM_DEBUG("crtc %d : scanoutpos query failed [%d].\n", +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/gpu/drm/i915/i915_gem_execbuffer.c sun8i-rt/drivers/gpu/drm/i915/i915_gem_execbuffer.c +--- sun8i/drivers/gpu/drm/i915/i915_gem_execbuffer.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/gpu/drm/i915/i915_gem_execbuffer.c 2016-08-22 18:13:48.920289427 +0200 +@@ -1297,7 +1297,9 @@ i915_gem_do_execbuffer(struct drm_device + goto err; + } + ++#ifndef CONFIG_PREEMPT_RT_BASE + trace_i915_gem_ring_dispatch(ring, seqno); ++#endif + + exec_start = batch_obj->gtt_offset + args->batch_start_offset; + exec_len = args->batch_len; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/ide/alim15x3.c sun8i-rt/drivers/ide/alim15x3.c +--- sun8i/drivers/ide/alim15x3.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/ide/alim15x3.c 2016-08-22 16:31:15.240218679 +0200 +@@ -234,7 +234,7 @@ static int init_chipset_ali15x3(struct p + + isa_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL); + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + if (m5229_revision < 0xC2) { + /* +@@ -325,7 +325,7 @@ out: + } + pci_dev_put(north); + pci_dev_put(isa_dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return 0; + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/ide/hpt366.c sun8i-rt/drivers/ide/hpt366.c +--- sun8i/drivers/ide/hpt366.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/ide/hpt366.c 2016-08-22 16:31:15.240218679 +0200 +@@ -1241,7 +1241,7 @@ static int __devinit init_dma_hpt366(ide + + dma_old = inb(base + 2); + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + dma_new = dma_old; + pci_read_config_byte(dev, hwif->channel ? 0x4b : 0x43, &masterdma); +@@ -1252,7 +1252,7 @@ static int __devinit init_dma_hpt366(ide + if (dma_new != dma_old) + outb(dma_new, base + 2); + +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + printk(KERN_INFO " %s: BM-DMA at 0x%04lx-0x%04lx\n", + hwif->name, base, base + 7); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/ide/ide-io.c sun8i-rt/drivers/ide/ide-io.c +--- sun8i/drivers/ide/ide-io.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/ide/ide-io.c 2016-08-22 16:31:15.240218679 +0200 +@@ -659,7 +659,7 @@ void ide_timer_expiry (unsigned long dat + /* disable_irq_nosync ?? */ + disable_irq(hwif->irq); + /* local CPU only, as if we were handling an interrupt */ +- local_irq_disable(); ++ local_irq_disable_nort(); + if (hwif->polling) { + startstop = handler(drive); + } else if (drive_is_ready(drive)) { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/ide/ide-iops.c sun8i-rt/drivers/ide/ide-iops.c +--- sun8i/drivers/ide/ide-iops.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/ide/ide-iops.c 2016-08-22 16:31:15.240218679 +0200 +@@ -129,12 +129,12 @@ int __ide_wait_stat(ide_drive_t *drive, + if ((stat & ATA_BUSY) == 0) + break; + +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + *rstat = stat; + return -EBUSY; + } + } +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + /* + * Allow status to settle, then read it again. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/ide/ide-io-std.c sun8i-rt/drivers/ide/ide-io-std.c +--- sun8i/drivers/ide/ide-io-std.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/ide/ide-io-std.c 2016-08-22 16:31:15.240218679 +0200 +@@ -175,7 +175,7 @@ void ide_input_data(ide_drive_t *drive, + unsigned long uninitialized_var(flags); + + if ((io_32bit & 2) && !mmio) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + ata_vlb_sync(io_ports->nsect_addr); + } + +@@ -186,7 +186,7 @@ void ide_input_data(ide_drive_t *drive, + insl(data_addr, buf, words); + + if ((io_32bit & 2) && !mmio) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + if (((len + 1) & 3) < 2) + return; +@@ -219,7 +219,7 @@ void ide_output_data(ide_drive_t *drive, + unsigned long uninitialized_var(flags); + + if ((io_32bit & 2) && !mmio) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + ata_vlb_sync(io_ports->nsect_addr); + } + +@@ -230,7 +230,7 @@ void ide_output_data(ide_drive_t *drive, + outsl(data_addr, buf, words); + + if ((io_32bit & 2) && !mmio) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + if (((len + 1) & 3) < 2) + return; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/ide/ide-probe.c sun8i-rt/drivers/ide/ide-probe.c +--- sun8i/drivers/ide/ide-probe.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/ide/ide-probe.c 2016-08-22 16:31:15.240218679 +0200 +@@ -196,10 +196,10 @@ static void do_identify(ide_drive_t *dri + int bswap = 1; + + /* local CPU only; some systems need this */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + /* read 512 bytes of id info */ + hwif->tp_ops->input_data(drive, NULL, id, SECTOR_SIZE); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + drive->dev_flags |= IDE_DFLAG_ID_READ; + #ifdef DEBUG +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/ide/ide-taskfile.c sun8i-rt/drivers/ide/ide-taskfile.c +--- sun8i/drivers/ide/ide-taskfile.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/ide/ide-taskfile.c 2016-08-22 16:31:15.240218679 +0200 +@@ -251,7 +251,7 @@ void ide_pio_bytes(ide_drive_t *drive, s + + page_is_high = PageHighMem(page); + if (page_is_high) +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + buf = kmap_atomic(page) + offset; + +@@ -272,7 +272,7 @@ void ide_pio_bytes(ide_drive_t *drive, s + kunmap_atomic(buf); + + if (page_is_high) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + len -= nr_bytes; + } +@@ -415,7 +415,7 @@ static ide_startstop_t pre_task_out_intr + } + + if ((drive->dev_flags & IDE_DFLAG_UNMASK) == 0) +- local_irq_disable(); ++ local_irq_disable_nort(); + + ide_set_handler(drive, &task_pio_intr, WAIT_WORSTCASE); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/idle/i7300_idle.c sun8i-rt/drivers/idle/i7300_idle.c +--- sun8i/drivers/idle/i7300_idle.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/idle/i7300_idle.c 2016-08-22 15:58:41.284196215 +0200 +@@ -75,7 +75,7 @@ static unsigned long past_skip; + + static struct pci_dev *fbd_dev; + +-static spinlock_t i7300_idle_lock; ++static raw_spinlock_t i7300_idle_lock; + static int i7300_idle_active; + + static u8 i7300_idle_thrtctl_saved; +@@ -457,7 +457,7 @@ static int i7300_idle_notifier(struct no + idle_begin_time = ktime_get(); + } + +- spin_lock_irqsave(&i7300_idle_lock, flags); ++ raw_spin_lock_irqsave(&i7300_idle_lock, flags); + if (val == IDLE_START) { + + cpumask_set_cpu(smp_processor_id(), idle_cpumask); +@@ -506,7 +506,7 @@ static int i7300_idle_notifier(struct no + } + } + end: +- spin_unlock_irqrestore(&i7300_idle_lock, flags); ++ raw_spin_unlock_irqrestore(&i7300_idle_lock, flags); + return 0; + } + +@@ -548,7 +548,7 @@ struct debugfs_file_info { + + static int __init i7300_idle_init(void) + { +- spin_lock_init(&i7300_idle_lock); ++ raw_spin_lock_init(&i7300_idle_lock); + total_us = 0; + + if (i7300_idle_platform_probe(&fbd_dev, &ioat_dev, forceload)) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/infiniband/ulp/ipoib/ipoib_multicast.c sun8i-rt/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +--- sun8i/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2016-08-22 16:31:30.000218849 +0200 +@@ -799,7 +799,7 @@ void ipoib_mcast_restart_task(struct wor + + ipoib_mcast_stop_thread(dev, 0); + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + netif_addr_lock(dev); + spin_lock(&priv->lock); + +@@ -881,7 +881,7 @@ void ipoib_mcast_restart_task(struct wor + + spin_unlock(&priv->lock); + netif_addr_unlock(dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + /* We have to cancel outside of the spinlock */ + list_for_each_entry_safe(mcast, tmcast, &remove_list, list) { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/input/gameport/gameport.c sun8i-rt/drivers/input/gameport/gameport.c +--- sun8i/drivers/input/gameport/gameport.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/input/gameport/gameport.c 2016-08-22 16:31:44.824219019 +0200 +@@ -87,12 +87,12 @@ static int gameport_measure_speed(struct + tx = 1 << 30; + + for(i = 0; i < 50; i++) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + GET_TIME(t1); + for (t = 0; t < 50; t++) gameport_read(gameport); + GET_TIME(t2); + GET_TIME(t3); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + udelay(i * 10); + if ((t = DELTA(t2,t1) - DELTA(t3,t2)) < tx) tx = t; + } +@@ -111,11 +111,11 @@ static int gameport_measure_speed(struct + tx = 1 << 30; + + for(i = 0; i < 50; i++) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + rdtscl(t1); + for (t = 0; t < 50; t++) gameport_read(gameport); + rdtscl(t2); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + udelay(i * 10); + if (t2 - t1 < tx) tx = t2 - t1; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/md/dm.c sun8i-rt/drivers/md/dm.c +--- sun8i/drivers/md/dm.c 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/drivers/md/dm.c 2016-08-22 17:49:49.064272873 +0200 +@@ -1676,14 +1676,14 @@ static void dm_request_fn(struct request + if (map_request(ti, clone, md)) + goto requeued; + +- BUG_ON(!irqs_disabled()); ++ BUG_ON_NONRT(!irqs_disabled()); + spin_lock(q->queue_lock); + } + + goto out; + + requeued: +- BUG_ON(!irqs_disabled()); ++ BUG_ON_NONRT(!irqs_disabled()); + spin_lock(q->queue_lock); + + delay_and_out: +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/md/raid5.c sun8i-rt/drivers/md/raid5.c +--- sun8i/drivers/md/raid5.c 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/drivers/md/raid5.c 2016-08-22 17:24:33.276255446 +0200 +@@ -1321,8 +1321,9 @@ static void __raid_run_ops(struct stripe + struct raid5_percpu *percpu; + unsigned long cpu; + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + percpu = per_cpu_ptr(conf->percpu, cpu); ++ spin_lock(&percpu->lock); + if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { + ops_run_biofill(sh); + overlap_clear++; +@@ -1374,7 +1375,8 @@ static void __raid_run_ops(struct stripe + if (test_and_clear_bit(R5_Overlap, &dev->flags)) + wake_up(&sh->raid_conf->wait_for_overlap); + } +- put_cpu(); ++ spin_unlock(&percpu->lock); ++ put_cpu_light(); + } + + #ifdef CONFIG_MULTICORE_RAID456 +@@ -4693,8 +4695,10 @@ static int alloc_scratch_buffer(struct r + { + if (conf->level == 6 && !percpu->spare_page) + percpu->spare_page = alloc_page(GFP_KERNEL); +- if (!percpu->scribble) ++ if (!percpu->scribble) { + percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL); ++ spin_lock_init(&percpu->lock); ++ } + + if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) { + free_scratch_buffer(conf, percpu); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/md/raid5.h sun8i-rt/drivers/md/raid5.h +--- sun8i/drivers/md/raid5.h 2016-08-22 14:14:35.000000000 +0200 ++++ sun8i-rt/drivers/md/raid5.h 2016-08-22 17:24:33.276255446 +0200 +@@ -418,6 +418,7 @@ struct r5conf { + int recovery_disabled; + /* per cpu variables */ + struct raid5_percpu { ++ spinlock_t lock; /* Protection for -RT */ + struct page *spare_page; /* Used when checking P/Q in raid6 */ + void *scribble; /* space for constructing buffer + * lists and performing address +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/misc/hwlat_detector.c sun8i-rt/drivers/misc/hwlat_detector.c +--- sun8i/drivers/misc/hwlat_detector.c 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/drivers/misc/hwlat_detector.c 2016-08-22 18:15:33.536290629 +0200 +@@ -0,0 +1,1239 @@ ++/* ++ * hwlat_detector.c - A simple Hardware Latency detector. ++ * ++ * Use this module to detect large system latencies induced by the behavior of ++ * certain underlying system hardware or firmware, independent of Linux itself. ++ * The code was developed originally to detect the presence of SMIs on Intel ++ * and AMD systems, although there is no dependency upon x86 herein. ++ * ++ * The classical example usage of this module is in detecting the presence of ++ * SMIs or System Management Interrupts on Intel and AMD systems. An SMI is a ++ * somewhat special form of hardware interrupt spawned from earlier CPU debug ++ * modes in which the (BIOS/EFI/etc.) firmware arranges for the South Bridge ++ * LPC (or other device) to generate a special interrupt under certain ++ * circumstances, for example, upon expiration of a special SMI timer device, ++ * due to certain external thermal readings, on certain I/O address accesses, ++ * and other situations. An SMI hits a special CPU pin, triggers a special ++ * SMI mode (complete with special memory map), and the OS is unaware. ++ * ++ * Although certain hardware-inducing latencies are necessary (for example, ++ * a modern system often requires an SMI handler for correct thermal control ++ * and remote management) they can wreak havoc upon any OS-level performance ++ * guarantees toward low-latency, especially when the OS is not even made ++ * aware of the presence of these interrupts. For this reason, we need a ++ * somewhat brute force mechanism to detect these interrupts. In this case, ++ * we do it by hogging all of the CPU(s) for configurable timer intervals, ++ * sampling the built-in CPU timer, looking for discontiguous readings. ++ * ++ * WARNING: This implementation necessarily introduces latencies. Therefore, ++ * you should NEVER use this module in a production environment ++ * requiring any kind of low-latency performance guarantee(s). ++ * ++ * Copyright (C) 2008-2009 Jon Masters, Red Hat, Inc. ++ * ++ * Includes useful feedback from Clark Williams ++ * ++ * This file is licensed under the terms of the GNU General Public ++ * License version 2. This program is licensed "as is" without any ++ * warranty of any kind, whether express or implied. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#define BUF_SIZE_DEFAULT 262144UL /* 8K*(sizeof(entry)) */ ++#define BUF_FLAGS (RB_FL_OVERWRITE) /* no block on full */ ++#define U64STR_SIZE 22 /* 20 digits max */ ++ ++#define VERSION "1.0.0" ++#define BANNER "hwlat_detector: " ++#define DRVNAME "hwlat_detector" ++#define DEFAULT_SAMPLE_WINDOW 1000000 /* 1s */ ++#define DEFAULT_SAMPLE_WIDTH 500000 /* 0.5s */ ++#define DEFAULT_LAT_THRESHOLD 10 /* 10us */ ++ ++/* Module metadata */ ++ ++MODULE_LICENSE("GPL"); ++MODULE_AUTHOR("Jon Masters "); ++MODULE_DESCRIPTION("A simple hardware latency detector"); ++MODULE_VERSION(VERSION); ++ ++/* Module parameters */ ++ ++static int debug; ++static int enabled; ++static int threshold; ++ ++module_param(debug, int, 0); /* enable debug */ ++module_param(enabled, int, 0); /* enable detector */ ++module_param(threshold, int, 0); /* latency threshold */ ++ ++/* Buffering and sampling */ ++ ++static struct ring_buffer *ring_buffer; /* sample buffer */ ++static DEFINE_MUTEX(ring_buffer_mutex); /* lock changes */ ++static unsigned long buf_size = BUF_SIZE_DEFAULT; ++static struct task_struct *kthread; /* sampling thread */ ++ ++/* DebugFS filesystem entries */ ++ ++static struct dentry *debug_dir; /* debugfs directory */ ++static struct dentry *debug_max; /* maximum TSC delta */ ++static struct dentry *debug_count; /* total detect count */ ++static struct dentry *debug_sample_width; /* sample width us */ ++static struct dentry *debug_sample_window; /* sample window us */ ++static struct dentry *debug_sample; /* raw samples us */ ++static struct dentry *debug_threshold; /* threshold us */ ++static struct dentry *debug_enable; /* enable/disable */ ++ ++/* Individual samples and global state */ ++ ++struct sample; /* latency sample */ ++struct data; /* Global state */ ++ ++/* Sampling functions */ ++static int __buffer_add_sample(struct sample *sample); ++static struct sample *buffer_get_sample(struct sample *sample); ++ ++/* Threading and state */ ++static int kthread_fn(void *unused); ++static int start_kthread(void); ++static int stop_kthread(void); ++static void __reset_stats(void); ++static int init_stats(void); ++ ++/* Debugfs interface */ ++static ssize_t simple_data_read(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos, const u64 *entry); ++static ssize_t simple_data_write(struct file *filp, const char __user *ubuf, ++ size_t cnt, loff_t *ppos, u64 *entry); ++static int debug_sample_fopen(struct inode *inode, struct file *filp); ++static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos); ++static int debug_sample_release(struct inode *inode, struct file *filp); ++static int debug_enable_fopen(struct inode *inode, struct file *filp); ++static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos); ++static ssize_t debug_enable_fwrite(struct file *file, ++ const char __user *user_buffer, ++ size_t user_size, loff_t *offset); ++ ++/* Initialization functions */ ++static int init_debugfs(void); ++static void free_debugfs(void); ++static int detector_init(void); ++static void detector_exit(void); ++ ++/* Individual latency samples are stored here when detected and packed into ++ * the ring_buffer circular buffer, where they are overwritten when ++ * more than buf_size/sizeof(sample) samples are received. */ ++struct sample { ++ u64 seqnum; /* unique sequence */ ++ u64 duration; /* ktime delta */ ++ u64 outer_duration; /* ktime delta (outer loop) */ ++ struct timespec timestamp; /* wall time */ ++ unsigned long lost; ++}; ++ ++/* keep the global state somewhere. */ ++static struct data { ++ ++ struct mutex lock; /* protect changes */ ++ ++ u64 count; /* total since reset */ ++ u64 max_sample; /* max hardware latency */ ++ u64 threshold; /* sample threshold level */ ++ ++ u64 sample_window; /* total sampling window (on+off) */ ++ u64 sample_width; /* active sampling portion of window */ ++ ++ atomic_t sample_open; /* whether the sample file is open */ ++ ++ wait_queue_head_t wq; /* waitqeue for new sample values */ ++ ++} data; ++ ++/** ++ * __buffer_add_sample - add a new latency sample recording to the ring buffer ++ * @sample: The new latency sample value ++ * ++ * This receives a new latency sample and records it in a global ring buffer. ++ * No additional locking is used in this case. ++ */ ++static int __buffer_add_sample(struct sample *sample) ++{ ++ return ring_buffer_write(ring_buffer, ++ sizeof(struct sample), sample); ++} ++ ++/** ++ * buffer_get_sample - remove a hardware latency sample from the ring buffer ++ * @sample: Pre-allocated storage for the sample ++ * ++ * This retrieves a hardware latency sample from the global circular buffer ++ */ ++static struct sample *buffer_get_sample(struct sample *sample) ++{ ++ struct ring_buffer_event *e = NULL; ++ struct sample *s = NULL; ++ unsigned int cpu = 0; ++ ++ if (!sample) ++ return NULL; ++ ++ mutex_lock(&ring_buffer_mutex); ++ for_each_online_cpu(cpu) { ++ e = ring_buffer_consume(ring_buffer, cpu, NULL, &sample->lost); ++ if (e) ++ break; ++ } ++ ++ if (e) { ++ s = ring_buffer_event_data(e); ++ memcpy(sample, s, sizeof(struct sample)); ++ } else ++ sample = NULL; ++ mutex_unlock(&ring_buffer_mutex); ++ ++ return sample; ++} ++ ++#ifndef CONFIG_TRACING ++#define time_type ktime_t ++#define time_get() ktime_get() ++#define time_to_us(x) ktime_to_us(x) ++#define time_sub(a, b) ktime_sub(a, b) ++#define init_time(a, b) (a).tv64 = b ++#define time_u64(a) (a).tv64 ++#else ++#define time_type u64 ++#define time_get() trace_clock_local() ++#define time_to_us(x) div_u64(x, 1000) ++#define time_sub(a, b) ((a) - (b)) ++#define init_time(a, b) a = b ++#define time_u64(a) a ++#endif ++/** ++ * get_sample - sample the CPU TSC and look for likely hardware latencies ++ * ++ * Used to repeatedly capture the CPU TSC (or similar), looking for potential ++ * hardware-induced latency. Called with interrupts disabled and with data.lock held. ++ */ ++static int get_sample(void) ++{ ++ time_type start, t1, t2, last_t2; ++ s64 diff, total = 0; ++ u64 sample = 0; ++ u64 outer_sample = 0; ++ int ret = -1; ++ ++ init_time(last_t2, 0); ++ start = time_get(); /* start timestamp */ ++ ++ do { ++ ++ t1 = time_get(); /* we'll look for a discontinuity */ ++ t2 = time_get(); ++ ++ if (time_u64(last_t2)) { ++ /* Check the delta from the outer loop (t2 to next t1) */ ++ diff = time_to_us(time_sub(t1, last_t2)); ++ /* This shouldn't happen */ ++ if (diff < 0) { ++ printk(KERN_ERR BANNER "time running backwards\n"); ++ goto out; ++ } ++ if (diff > outer_sample) ++ outer_sample = diff; ++ } ++ last_t2 = t2; ++ ++ total = time_to_us(time_sub(t2, start)); /* sample width */ ++ ++ /* This checks the inner loop (t1 to t2) */ ++ diff = time_to_us(time_sub(t2, t1)); /* current diff */ ++ ++ /* This shouldn't happen */ ++ if (diff < 0) { ++ printk(KERN_ERR BANNER "time running backwards\n"); ++ goto out; ++ } ++ ++ if (diff > sample) ++ sample = diff; /* only want highest value */ ++ ++ } while (total <= data.sample_width); ++ ++ ret = 0; ++ ++ /* If we exceed the threshold value, we have found a hardware latency */ ++ if (sample > data.threshold || outer_sample > data.threshold) { ++ struct sample s; ++ ++ ret = 1; ++ ++ data.count++; ++ s.seqnum = data.count; ++ s.duration = sample; ++ s.outer_duration = outer_sample; ++ s.timestamp = CURRENT_TIME; ++ __buffer_add_sample(&s); ++ ++ /* Keep a running maximum ever recorded hardware latency */ ++ if (sample > data.max_sample) ++ data.max_sample = sample; ++ } ++ ++out: ++ return ret; ++} ++ ++/* ++ * kthread_fn - The CPU time sampling/hardware latency detection kernel thread ++ * @unused: A required part of the kthread API. ++ * ++ * Used to periodically sample the CPU TSC via a call to get_sample. We ++ * disable interrupts, which does (intentionally) introduce latency since we ++ * need to ensure nothing else might be running (and thus pre-empting). ++ * Obviously this should never be used in production environments. ++ * ++ * Currently this runs on which ever CPU it was scheduled on, but most ++ * real-worald hardware latency situations occur across several CPUs, ++ * but we might later generalize this if we find there are any actualy ++ * systems with alternate SMI delivery or other hardware latencies. ++ */ ++static int kthread_fn(void *unused) ++{ ++ int ret; ++ u64 interval; ++ ++ while (!kthread_should_stop()) { ++ ++ mutex_lock(&data.lock); ++ ++ local_irq_disable(); ++ ret = get_sample(); ++ local_irq_enable(); ++ ++ if (ret > 0) ++ wake_up(&data.wq); /* wake up reader(s) */ ++ ++ interval = data.sample_window - data.sample_width; ++ do_div(interval, USEC_PER_MSEC); /* modifies interval value */ ++ ++ mutex_unlock(&data.lock); ++ ++ if (msleep_interruptible(interval)) ++ break; ++ } ++ ++ return 0; ++} ++ ++/** ++ * start_kthread - Kick off the hardware latency sampling/detector kthread ++ * ++ * This starts a kernel thread that will sit and sample the CPU timestamp ++ * counter (TSC or similar) and look for potential hardware latencies. ++ */ ++static int start_kthread(void) ++{ ++ kthread = kthread_run(kthread_fn, NULL, ++ DRVNAME); ++ if (IS_ERR(kthread)) { ++ printk(KERN_ERR BANNER "could not start sampling thread\n"); ++ enabled = 0; ++ return -ENOMEM; ++ } ++ ++ return 0; ++} ++ ++/** ++ * stop_kthread - Inform the hardware latency samping/detector kthread to stop ++ * ++ * This kicks the running hardware latency sampling/detector kernel thread and ++ * tells it to stop sampling now. Use this on unload and at system shutdown. ++ */ ++static int stop_kthread(void) ++{ ++ int ret; ++ ++ ret = kthread_stop(kthread); ++ ++ return ret; ++} ++ ++/** ++ * __reset_stats - Reset statistics for the hardware latency detector ++ * ++ * We use data to store various statistics and global state. We call this ++ * function in order to reset those when "enable" is toggled on or off, and ++ * also at initialization. Should be called with data.lock held. ++ */ ++static void __reset_stats(void) ++{ ++ data.count = 0; ++ data.max_sample = 0; ++ ring_buffer_reset(ring_buffer); /* flush out old sample entries */ ++} ++ ++/** ++ * init_stats - Setup global state statistics for the hardware latency detector ++ * ++ * We use data to store various statistics and global state. We also use ++ * a global ring buffer (ring_buffer) to keep raw samples of detected hardware ++ * induced system latencies. This function initializes these structures and ++ * allocates the global ring buffer also. ++ */ ++static int init_stats(void) ++{ ++ int ret = -ENOMEM; ++ ++ mutex_init(&data.lock); ++ init_waitqueue_head(&data.wq); ++ atomic_set(&data.sample_open, 0); ++ ++ ring_buffer = ring_buffer_alloc(buf_size, BUF_FLAGS); ++ ++ if (WARN(!ring_buffer, KERN_ERR BANNER ++ "failed to allocate ring buffer!\n")) ++ goto out; ++ ++ __reset_stats(); ++ data.threshold = threshold ?: DEFAULT_LAT_THRESHOLD; /* threshold us */ ++ data.sample_window = DEFAULT_SAMPLE_WINDOW; /* window us */ ++ data.sample_width = DEFAULT_SAMPLE_WIDTH; /* width us */ ++ ++ ret = 0; ++ ++out: ++ return ret; ++ ++} ++ ++/* ++ * simple_data_read - Wrapper read function for global state debugfs entries ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * @entry: The entry to read from ++ * ++ * This function provides a generic read implementation for the global state ++ * "data" structure debugfs filesystem entries. It would be nice to use ++ * simple_attr_read directly, but we need to make sure that the data.lock ++ * is held during the actual read. ++ */ ++static ssize_t simple_data_read(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos, const u64 *entry) ++{ ++ char buf[U64STR_SIZE]; ++ u64 val = 0; ++ int len = 0; ++ ++ memset(buf, 0, sizeof(buf)); ++ ++ if (!entry) ++ return -EFAULT; ++ ++ mutex_lock(&data.lock); ++ val = *entry; ++ mutex_unlock(&data.lock); ++ ++ len = snprintf(buf, sizeof(buf), "%llu\n", (unsigned long long)val); ++ ++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); ++ ++} ++ ++/* ++ * simple_data_write - Wrapper write function for global state debugfs entries ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to write value from ++ * @cnt: The maximum number of bytes to write ++ * @ppos: The current "file" position ++ * @entry: The entry to write to ++ * ++ * This function provides a generic write implementation for the global state ++ * "data" structure debugfs filesystem entries. It would be nice to use ++ * simple_attr_write directly, but we need to make sure that the data.lock ++ * is held during the actual write. ++ */ ++static ssize_t simple_data_write(struct file *filp, const char __user *ubuf, ++ size_t cnt, loff_t *ppos, u64 *entry) ++{ ++ char buf[U64STR_SIZE]; ++ int csize = min(cnt, sizeof(buf)); ++ u64 val = 0; ++ int err = 0; ++ ++ memset(buf, '\0', sizeof(buf)); ++ if (copy_from_user(buf, ubuf, csize)) ++ return -EFAULT; ++ ++ buf[U64STR_SIZE-1] = '\0'; /* just in case */ ++ err = strict_strtoull(buf, 10, &val); ++ if (err) ++ return -EINVAL; ++ ++ mutex_lock(&data.lock); ++ *entry = val; ++ mutex_unlock(&data.lock); ++ ++ return csize; ++} ++ ++/** ++ * debug_count_fopen - Open function for "count" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "count" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_count_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_count_fread - Read function for "count" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "count" debugfs ++ * interface to the hardware latency detector. Can be used to read the ++ * number of latency readings exceeding the configured threshold since ++ * the detector was last reset (e.g. by writing a zero into "count"). ++ */ ++static ssize_t debug_count_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.count); ++} ++ ++/** ++ * debug_count_fwrite - Write function for "count" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "count" debugfs ++ * interface to the hardware latency detector. Can be used to write a ++ * desired value, especially to zero the total count. ++ */ ++static ssize_t debug_count_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ return simple_data_write(filp, ubuf, cnt, ppos, &data.count); ++} ++ ++/** ++ * debug_enable_fopen - Dummy open function for "enable" debugfs interface ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "enable" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_enable_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_enable_fread - Read function for "enable" debugfs interface ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "enable" debugfs ++ * interface to the hardware latency detector. Can be used to determine ++ * whether the detector is currently enabled ("0\n" or "1\n" returned). ++ */ ++static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ char buf[4]; ++ ++ if ((cnt < sizeof(buf)) || (*ppos)) ++ return 0; ++ ++ buf[0] = enabled ? '1' : '0'; ++ buf[1] = '\n'; ++ buf[2] = '\0'; ++ if (copy_to_user(ubuf, buf, strlen(buf))) ++ return -EFAULT; ++ return *ppos = strlen(buf); ++} ++ ++/** ++ * debug_enable_fwrite - Write function for "enable" debugfs interface ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "enable" debugfs ++ * interface to the hardware latency detector. Can be used to enable or ++ * disable the detector, which will have the side-effect of possibly ++ * also resetting the global stats and kicking off the measuring ++ * kthread (on an enable) or the converse (upon a disable). ++ */ ++static ssize_t debug_enable_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ char buf[4]; ++ int csize = min(cnt, sizeof(buf)); ++ long val = 0; ++ int err = 0; ++ ++ memset(buf, '\0', sizeof(buf)); ++ if (copy_from_user(buf, ubuf, csize)) ++ return -EFAULT; ++ ++ buf[sizeof(buf)-1] = '\0'; /* just in case */ ++ err = strict_strtoul(buf, 10, &val); ++ if (0 != err) ++ return -EINVAL; ++ ++ if (val) { ++ if (enabled) ++ goto unlock; ++ enabled = 1; ++ __reset_stats(); ++ if (start_kthread()) ++ return -EFAULT; ++ } else { ++ if (!enabled) ++ goto unlock; ++ enabled = 0; ++ err = stop_kthread(); ++ if (err) { ++ printk(KERN_ERR BANNER "cannot stop kthread\n"); ++ return -EFAULT; ++ } ++ wake_up(&data.wq); /* reader(s) should return */ ++ } ++unlock: ++ return csize; ++} ++ ++/** ++ * debug_max_fopen - Open function for "max" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "max" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_max_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_max_fread - Read function for "max" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "max" debugfs ++ * interface to the hardware latency detector. Can be used to determine ++ * the maximum latency value observed since it was last reset. ++ */ ++static ssize_t debug_max_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.max_sample); ++} ++ ++/** ++ * debug_max_fwrite - Write function for "max" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "max" debugfs ++ * interface to the hardware latency detector. Can be used to reset the ++ * maximum or set it to some other desired value - if, then, subsequent ++ * measurements exceed this value, the maximum will be updated. ++ */ ++static ssize_t debug_max_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ return simple_data_write(filp, ubuf, cnt, ppos, &data.max_sample); ++} ++ ++ ++/** ++ * debug_sample_fopen - An open function for "sample" debugfs interface ++ * @inode: The in-kernel inode representation of this debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function handles opening the "sample" file within the hardware ++ * latency detector debugfs directory interface. This file is used to read ++ * raw samples from the global ring_buffer and allows the user to see a ++ * running latency history. Can be opened blocking or non-blocking, ++ * affecting whether it behaves as a buffer read pipe, or does not. ++ * Implements simple locking to prevent multiple simultaneous use. ++ */ ++static int debug_sample_fopen(struct inode *inode, struct file *filp) ++{ ++ if (!atomic_add_unless(&data.sample_open, 1, 1)) ++ return -EBUSY; ++ else ++ return 0; ++} ++ ++/** ++ * debug_sample_fread - A read function for "sample" debugfs interface ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that will contain the samples read ++ * @cnt: The maximum bytes to read from the debugfs "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function handles reading from the "sample" file within the hardware ++ * latency detector debugfs directory interface. This file is used to read ++ * raw samples from the global ring_buffer and allows the user to see a ++ * running latency history. By default this will block pending a new ++ * value written into the sample buffer, unless there are already a ++ * number of value(s) waiting in the buffer, or the sample file was ++ * previously opened in a non-blocking mode of operation. ++ */ ++static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ int len = 0; ++ char buf[64]; ++ struct sample *sample = NULL; ++ ++ if (!enabled) ++ return 0; ++ ++ sample = kzalloc(sizeof(struct sample), GFP_KERNEL); ++ if (!sample) ++ return -ENOMEM; ++ ++ while (!buffer_get_sample(sample)) { ++ ++ DEFINE_WAIT(wait); ++ ++ if (filp->f_flags & O_NONBLOCK) { ++ len = -EAGAIN; ++ goto out; ++ } ++ ++ prepare_to_wait(&data.wq, &wait, TASK_INTERRUPTIBLE); ++ schedule(); ++ finish_wait(&data.wq, &wait); ++ ++ if (signal_pending(current)) { ++ len = -EINTR; ++ goto out; ++ } ++ ++ if (!enabled) { /* enable was toggled */ ++ len = 0; ++ goto out; ++ } ++ } ++ ++ len = snprintf(buf, sizeof(buf), "%010lu.%010lu\t%llu\t%llu\n", ++ sample->timestamp.tv_sec, ++ sample->timestamp.tv_nsec, ++ sample->duration, ++ sample->outer_duration); ++ ++ ++ /* handling partial reads is more trouble than it's worth */ ++ if (len > cnt) ++ goto out; ++ ++ if (copy_to_user(ubuf, buf, len)) ++ len = -EFAULT; ++ ++out: ++ kfree(sample); ++ return len; ++} ++ ++/** ++ * debug_sample_release - Release function for "sample" debugfs interface ++ * @inode: The in-kernel inode represenation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function completes the close of the debugfs interface "sample" file. ++ * Frees the sample_open "lock" so that other users may open the interface. ++ */ ++static int debug_sample_release(struct inode *inode, struct file *filp) ++{ ++ atomic_dec(&data.sample_open); ++ ++ return 0; ++} ++ ++/** ++ * debug_threshold_fopen - Open function for "threshold" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "threshold" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_threshold_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_threshold_fread - Read function for "threshold" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "threshold" debugfs ++ * interface to the hardware latency detector. It can be used to determine ++ * the current threshold level at which a latency will be recorded in the ++ * global ring buffer, typically on the order of 10us. ++ */ ++static ssize_t debug_threshold_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.threshold); ++} ++ ++/** ++ * debug_threshold_fwrite - Write function for "threshold" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "threshold" debugfs ++ * interface to the hardware latency detector. It can be used to configure ++ * the threshold level at which any subsequently detected latencies will ++ * be recorded into the global ring buffer. ++ */ ++static ssize_t debug_threshold_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ int ret; ++ ++ ret = simple_data_write(filp, ubuf, cnt, ppos, &data.threshold); ++ ++ if (enabled) ++ wake_up_process(kthread); ++ ++ return ret; ++} ++ ++/** ++ * debug_width_fopen - Open function for "width" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "width" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_width_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_width_fread - Read function for "width" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "width" debugfs ++ * interface to the hardware latency detector. It can be used to determine ++ * for how many us of the total window us we will actively sample for any ++ * hardware-induced latecy periods. Obviously, it is not possible to ++ * sample constantly and have the system respond to a sample reader, or, ++ * worse, without having the system appear to have gone out to lunch. ++ */ ++static ssize_t debug_width_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_width); ++} ++ ++/** ++ * debug_width_fwrite - Write function for "width" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "width" debugfs ++ * interface to the hardware latency detector. It can be used to configure ++ * for how many us of the total window us we will actively sample for any ++ * hardware-induced latency periods. Obviously, it is not possible to ++ * sample constantly and have the system respond to a sample reader, or, ++ * worse, without having the system appear to have gone out to lunch. It ++ * is enforced that width is less that the total window size. ++ */ ++static ssize_t debug_width_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ char buf[U64STR_SIZE]; ++ int csize = min(cnt, sizeof(buf)); ++ u64 val = 0; ++ int err = 0; ++ ++ memset(buf, '\0', sizeof(buf)); ++ if (copy_from_user(buf, ubuf, csize)) ++ return -EFAULT; ++ ++ buf[U64STR_SIZE-1] = '\0'; /* just in case */ ++ err = strict_strtoull(buf, 10, &val); ++ if (0 != err) ++ return -EINVAL; ++ ++ mutex_lock(&data.lock); ++ if (val < data.sample_window) ++ data.sample_width = val; ++ else { ++ mutex_unlock(&data.lock); ++ return -EINVAL; ++ } ++ mutex_unlock(&data.lock); ++ ++ if (enabled) ++ wake_up_process(kthread); ++ ++ return csize; ++} ++ ++/** ++ * debug_window_fopen - Open function for "window" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "window" debugfs ++ * interface to the hardware latency detector. The window is the total time ++ * in us that will be considered one sample period. Conceptually, windows ++ * occur back-to-back and contain a sample width period during which ++ * actual sampling occurs. ++ */ ++static int debug_window_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_window_fread - Read function for "window" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "window" debugfs ++ * interface to the hardware latency detector. The window is the total time ++ * in us that will be considered one sample period. Conceptually, windows ++ * occur back-to-back and contain a sample width period during which ++ * actual sampling occurs. Can be used to read the total window size. ++ */ ++static ssize_t debug_window_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_window); ++} ++ ++/** ++ * debug_window_fwrite - Write function for "window" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "window" debufds ++ * interface to the hardware latency detetector. The window is the total time ++ * in us that will be considered one sample period. Conceptually, windows ++ * occur back-to-back and contain a sample width period during which ++ * actual sampling occurs. Can be used to write a new total window size. It ++ * is enfoced that any value written must be greater than the sample width ++ * size, or an error results. ++ */ ++static ssize_t debug_window_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ char buf[U64STR_SIZE]; ++ int csize = min(cnt, sizeof(buf)); ++ u64 val = 0; ++ int err = 0; ++ ++ memset(buf, '\0', sizeof(buf)); ++ if (copy_from_user(buf, ubuf, csize)) ++ return -EFAULT; ++ ++ buf[U64STR_SIZE-1] = '\0'; /* just in case */ ++ err = strict_strtoull(buf, 10, &val); ++ if (0 != err) ++ return -EINVAL; ++ ++ mutex_lock(&data.lock); ++ if (data.sample_width < val) ++ data.sample_window = val; ++ else { ++ mutex_unlock(&data.lock); ++ return -EINVAL; ++ } ++ mutex_unlock(&data.lock); ++ ++ return csize; ++} ++ ++/* ++ * Function pointers for the "count" debugfs file operations ++ */ ++static const struct file_operations count_fops = { ++ .open = debug_count_fopen, ++ .read = debug_count_fread, ++ .write = debug_count_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "enable" debugfs file operations ++ */ ++static const struct file_operations enable_fops = { ++ .open = debug_enable_fopen, ++ .read = debug_enable_fread, ++ .write = debug_enable_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "max" debugfs file operations ++ */ ++static const struct file_operations max_fops = { ++ .open = debug_max_fopen, ++ .read = debug_max_fread, ++ .write = debug_max_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "sample" debugfs file operations ++ */ ++static const struct file_operations sample_fops = { ++ .open = debug_sample_fopen, ++ .read = debug_sample_fread, ++ .release = debug_sample_release, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "threshold" debugfs file operations ++ */ ++static const struct file_operations threshold_fops = { ++ .open = debug_threshold_fopen, ++ .read = debug_threshold_fread, ++ .write = debug_threshold_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "width" debugfs file operations ++ */ ++static const struct file_operations width_fops = { ++ .open = debug_width_fopen, ++ .read = debug_width_fread, ++ .write = debug_width_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "window" debugfs file operations ++ */ ++static const struct file_operations window_fops = { ++ .open = debug_window_fopen, ++ .read = debug_window_fread, ++ .write = debug_window_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/** ++ * init_debugfs - A function to initialize the debugfs interface files ++ * ++ * This function creates entries in debugfs for "hwlat_detector", including ++ * files to read values from the detector, current samples, and the ++ * maximum sample that has been captured since the hardware latency ++ * dectector was started. ++ */ ++static int init_debugfs(void) ++{ ++ int ret = -ENOMEM; ++ ++ debug_dir = debugfs_create_dir(DRVNAME, NULL); ++ if (!debug_dir) ++ goto err_debug_dir; ++ ++ debug_sample = debugfs_create_file("sample", 0444, ++ debug_dir, NULL, ++ &sample_fops); ++ if (!debug_sample) ++ goto err_sample; ++ ++ debug_count = debugfs_create_file("count", 0444, ++ debug_dir, NULL, ++ &count_fops); ++ if (!debug_count) ++ goto err_count; ++ ++ debug_max = debugfs_create_file("max", 0444, ++ debug_dir, NULL, ++ &max_fops); ++ if (!debug_max) ++ goto err_max; ++ ++ debug_sample_window = debugfs_create_file("window", 0644, ++ debug_dir, NULL, ++ &window_fops); ++ if (!debug_sample_window) ++ goto err_window; ++ ++ debug_sample_width = debugfs_create_file("width", 0644, ++ debug_dir, NULL, ++ &width_fops); ++ if (!debug_sample_width) ++ goto err_width; ++ ++ debug_threshold = debugfs_create_file("threshold", 0644, ++ debug_dir, NULL, ++ &threshold_fops); ++ if (!debug_threshold) ++ goto err_threshold; ++ ++ debug_enable = debugfs_create_file("enable", 0644, ++ debug_dir, &enabled, ++ &enable_fops); ++ if (!debug_enable) ++ goto err_enable; ++ ++ else { ++ ret = 0; ++ goto out; ++ } ++ ++err_enable: ++ debugfs_remove(debug_threshold); ++err_threshold: ++ debugfs_remove(debug_sample_width); ++err_width: ++ debugfs_remove(debug_sample_window); ++err_window: ++ debugfs_remove(debug_max); ++err_max: ++ debugfs_remove(debug_count); ++err_count: ++ debugfs_remove(debug_sample); ++err_sample: ++ debugfs_remove(debug_dir); ++err_debug_dir: ++out: ++ return ret; ++} ++ ++/** ++ * free_debugfs - A function to cleanup the debugfs file interface ++ */ ++static void free_debugfs(void) ++{ ++ /* could also use a debugfs_remove_recursive */ ++ debugfs_remove(debug_enable); ++ debugfs_remove(debug_threshold); ++ debugfs_remove(debug_sample_width); ++ debugfs_remove(debug_sample_window); ++ debugfs_remove(debug_max); ++ debugfs_remove(debug_count); ++ debugfs_remove(debug_sample); ++ debugfs_remove(debug_dir); ++} ++ ++/** ++ * detector_init - Standard module initialization code ++ */ ++static int detector_init(void) ++{ ++ int ret = -ENOMEM; ++ ++ printk(KERN_INFO BANNER "version %s\n", VERSION); ++ ++ ret = init_stats(); ++ if (0 != ret) ++ goto out; ++ ++ ret = init_debugfs(); ++ if (0 != ret) ++ goto err_stats; ++ ++ if (enabled) ++ ret = start_kthread(); ++ ++ goto out; ++ ++err_stats: ++ ring_buffer_free(ring_buffer); ++out: ++ return ret; ++ ++} ++ ++/** ++ * detector_exit - Standard module cleanup code ++ */ ++static void detector_exit(void) ++{ ++ int err; ++ ++ if (enabled) { ++ enabled = 0; ++ err = stop_kthread(); ++ if (err) ++ printk(KERN_ERR BANNER "cannot stop kthread\n"); ++ } ++ ++ free_debugfs(); ++ ring_buffer_free(ring_buffer); /* free up the ring buffer */ ++ ++} ++ ++module_init(detector_init); ++module_exit(detector_exit); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/misc/Kconfig sun8i-rt/drivers/misc/Kconfig +--- sun8i/drivers/misc/Kconfig 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/misc/Kconfig 2016-08-22 17:47:10.112271045 +0200 +@@ -89,6 +89,7 @@ config AB8500_PWM + config ATMEL_TCLIB + bool "Atmel AT32/AT91 Timer/Counter Library" + depends on (AVR32 || ARCH_AT91) ++ default y if PREEMPT_RT_FULL + help + Select this if you want a library to allocate the Timer/Counter + blocks found on many Atmel processors. This facilitates using +@@ -104,8 +105,7 @@ config ATMEL_TCB_CLKSRC + are combined to make a single 32-bit timer. + + When GENERIC_CLOCKEVENTS is defined, the third timer channel +- may be used as a clock event device supporting oneshot mode +- (delays of up to two seconds) based on the 32 KiHz clock. ++ may be used as a clock event device supporting oneshot mode. + + config ATMEL_TCB_CLKSRC_BLOCK + int +@@ -119,6 +119,14 @@ config ATMEL_TCB_CLKSRC_BLOCK + TC can be used for other purposes, such as PWM generation and + interval timing. + ++config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK ++ bool "TC Block use 32 KiHz clock" ++ depends on ATMEL_TCB_CLKSRC ++ default y if !PREEMPT_RT_FULL ++ help ++ Select this to use 32 KiHz base clock rate as TC block clock ++ source for clock events. ++ + config IBM_ASM + tristate "Device driver for IBM RSA service processor" + depends on X86 && PCI && INPUT && EXPERIMENTAL +@@ -140,6 +148,35 @@ config IBM_ASM + for information on the specific driver level and support statement + for your IBM server. + ++config HWLAT_DETECTOR ++ tristate "Testing module to detect hardware-induced latencies" ++ depends on DEBUG_FS ++ depends on RING_BUFFER ++ default m ++ ---help--- ++ A simple hardware latency detector. Use this module to detect ++ large latencies introduced by the behavior of the underlying ++ system firmware external to Linux. We do this using periodic ++ use of stop_machine to grab all available CPUs and measure ++ for unexplainable gaps in the CPU timestamp counter(s). By ++ default, the module is not enabled until the "enable" file ++ within the "hwlat_detector" debugfs directory is toggled. ++ ++ This module is often used to detect SMI (System Management ++ Interrupts) on x86 systems, though is not x86 specific. To ++ this end, we default to using a sample window of 1 second, ++ during which we will sample for 0.5 seconds. If an SMI or ++ similar event occurs during that time, it is recorded ++ into an 8K samples global ring buffer until retreived. ++ ++ WARNING: This software should never be enabled (it can be built ++ but should not be turned on after it is loaded) in a production ++ environment where high latencies are a concern since the ++ sampling mechanism actually introduces latencies for ++ regular tasks while the CPU(s) are being held. ++ ++ If unsure, say N ++ + config PHANTOM + tristate "Sensable PHANToM (PCI)" + depends on PCI +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/misc/Makefile sun8i-rt/drivers/misc/Makefile +--- sun8i/drivers/misc/Makefile 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/misc/Makefile 2016-08-22 16:24:54.968214307 +0200 +@@ -51,6 +51,7 @@ obj-y += carma/ + obj-$(CONFIG_USB_SWITCH_FSA9480) += fsa9480.o + obj-$(CONFIG_ALTERA_STAPL) +=altera-stapl/ + obj-$(CONFIG_MAX8997_MUIC) += max8997-muic.o ++obj-$(CONFIG_HWLAT_DETECTOR) += hwlat_detector.o + obj-$(CONFIG_WL127X_RFKILL) += wl127x-rfkill.o + obj-$(CONFIG_SENSORS_AK8975) += akm8975.o + obj-$(CONFIG_SUNXI_VIBRATOR) += sunxi-vibrator.o +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/mmc/host/mmci.c sun8i-rt/drivers/mmc/host/mmci.c +--- sun8i/drivers/mmc/host/mmci.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/mmc/host/mmci.c 2016-08-22 18:08:08.484285513 +0200 +@@ -910,15 +910,12 @@ static irqreturn_t mmci_pio_irq(int irq, + struct sg_mapping_iter *sg_miter = &host->sg_miter; + struct variant_data *variant = host->variant; + void __iomem *base = host->base; +- unsigned long flags; + u32 status; + + status = readl(base + MMCISTATUS); + + dev_dbg(mmc_dev(host->mmc), "irq1 (pio) %08x\n", status); + +- local_irq_save(flags); +- + do { + unsigned int remain, len; + char *buffer; +@@ -958,8 +955,6 @@ static irqreturn_t mmci_pio_irq(int irq, + + sg_miter_stop(sg_miter); + +- local_irq_restore(flags); +- + /* + * If we have less than the fifo 'half-full' threshold to transfer, + * trigger a PIO interrupt as soon as any data is available. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/3com/3c59x.c sun8i-rt/drivers/net/ethernet/3com/3c59x.c +--- sun8i/drivers/net/ethernet/3com/3c59x.c 2016-08-22 14:14:34.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/3com/3c59x.c 2016-08-22 16:35:33.916221653 +0200 +@@ -842,9 +842,9 @@ static void poll_vortex(struct net_devic + { + struct vortex_private *vp = netdev_priv(dev); + unsigned long flags; +- local_irq_save(flags); ++ local_irq_save_nort(flags); + (vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + #endif + +@@ -1920,12 +1920,12 @@ static void vortex_tx_timeout(struct net + * Block interrupts because vortex_interrupt does a bare spin_lock() + */ + unsigned long flags; +- local_irq_save(flags); ++ local_irq_save_nort(flags); + if (vp->full_bus_master_tx) + boomerang_interrupt(dev->irq, dev); + else + vortex_interrupt(dev->irq, dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/atheros/atl1c/atl1c_main.c sun8i-rt/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +--- sun8i/drivers/net/ethernet/atheros/atl1c/atl1c_main.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/atheros/atl1c/atl1c_main.c 2016-08-22 16:35:18.704221478 +0200 +@@ -2239,11 +2239,7 @@ static netdev_tx_t atl1c_xmit_frame(stru + } + + tpd_req = atl1c_cal_tpd_req(skb); +- if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) { +- if (netif_msg_pktdata(adapter)) +- dev_info(&adapter->pdev->dev, "tx locked\n"); +- return NETDEV_TX_LOCKED; +- } ++ spin_lock_irqsave(&adapter->tx_lock, flags); + + if (atl1c_tpd_avail(adapter, type) < tpd_req) { + /* no enough descriptor, just stop queue */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/atheros/atl1e/atl1e_main.c sun8i-rt/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +--- sun8i/drivers/net/ethernet/atheros/atl1e/atl1e_main.c 2016-08-22 14:14:35.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/atheros/atl1e/atl1e_main.c 2016-08-22 16:35:18.708221478 +0200 +@@ -1861,8 +1861,7 @@ static netdev_tx_t atl1e_xmit_frame(stru + return NETDEV_TX_OK; + } + tpd_req = atl1e_cal_tdp_req(skb); +- if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) +- return NETDEV_TX_LOCKED; ++ spin_lock_irqsave(&adapter->tx_lock, flags); + + if (atl1e_tpd_avail(adapter) < tpd_req) { + /* no enough descriptor, just stop queue */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/cadence/at91_ether.c sun8i-rt/drivers/net/ethernet/cadence/at91_ether.c +--- sun8i/drivers/net/ethernet/cadence/at91_ether.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/cadence/at91_ether.c 2016-08-22 16:08:10.276202756 +0200 +@@ -201,7 +201,9 @@ static irqreturn_t at91ether_phy_interru + struct net_device *dev = (struct net_device *) dev_id; + struct at91_private *lp = netdev_priv(dev); + unsigned int phy; ++ unsigned long flags; + ++ spin_lock_irqsave(&lp->lock, flags); + /* + * This hander is triggered on both edges, but the PHY chips expect + * level-triggering. We therefore have to check if the PHY actually has +@@ -243,6 +245,7 @@ static irqreturn_t at91ether_phy_interru + + done: + disable_mdi(); ++ spin_unlock_irqrestore(&lp->lock, flags); + + return IRQ_HANDLED; + } +@@ -399,9 +402,11 @@ static void at91ether_check_link(unsigne + struct net_device *dev = (struct net_device *) dev_id; + struct at91_private *lp = netdev_priv(dev); + ++ spin_lock_irq(&lp->lock); + enable_mdi(); + update_linkspeed(dev, 1); + disable_mdi(); ++ spin_unlock_irq(&lp->lock); + + mod_timer(&lp->check_timer, jiffies + LINK_POLL_INTERVAL); + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/chelsio/cxgb/sge.c sun8i-rt/drivers/net/ethernet/chelsio/cxgb/sge.c +--- sun8i/drivers/net/ethernet/chelsio/cxgb/sge.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/chelsio/cxgb/sge.c 2016-08-22 16:35:18.708221478 +0200 +@@ -1678,8 +1678,7 @@ static int t1_sge_tx(struct sk_buff *skb + struct cmdQ *q = &sge->cmdQ[qid]; + unsigned int credits, pidx, genbit, count, use_sched_skb = 0; + +- if (!spin_trylock(&q->lock)) +- return NETDEV_TX_LOCKED; ++ spin_lock(&q->lock); + + reclaim_completed_tx(sge, q); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/dec/tulip/tulip_core.c sun8i-rt/drivers/net/ethernet/dec/tulip/tulip_core.c +--- sun8i/drivers/net/ethernet/dec/tulip/tulip_core.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/dec/tulip/tulip_core.c 2016-08-22 16:03:53.752199807 +0200 +@@ -1946,6 +1946,7 @@ static void __devexit tulip_remove_one ( + pci_iounmap(pdev, tp->base_addr); + free_netdev (dev); + pci_release_regions (pdev); ++ pci_disable_device (pdev); + pci_set_drvdata (pdev, NULL); + + /* pci_power_off (pdev, -1); */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/freescale/gianfar.c sun8i-rt/drivers/net/ethernet/freescale/gianfar.c +--- sun8i/drivers/net/ethernet/freescale/gianfar.c 2016-08-22 14:14:35.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/freescale/gianfar.c 2016-08-22 18:18:37.276292742 +0200 +@@ -1257,7 +1257,7 @@ static int gfar_suspend(struct device *d + + if (netif_running(ndev)) { + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + lock_rx_qs(priv); + +@@ -1275,7 +1275,7 @@ static int gfar_suspend(struct device *d + + unlock_rx_qs(priv); + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + disable_napi(priv); + +@@ -1316,7 +1316,7 @@ static int gfar_resume(struct device *de + /* Disable Magic Packet mode, in case something + * else woke us up. + */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + lock_rx_qs(priv); + +@@ -1328,7 +1328,7 @@ static int gfar_resume(struct device *de + + unlock_rx_qs(priv); + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + netif_device_attach(ndev); + +@@ -1652,7 +1652,7 @@ void stop_gfar(struct net_device *dev) + + + /* Lock it down */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + lock_rx_qs(priv); + +@@ -1660,7 +1660,7 @@ void stop_gfar(struct net_device *dev) + + unlock_rx_qs(priv); + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + /* Free the IRQs */ + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { +@@ -2312,7 +2312,7 @@ void gfar_vlan_mode(struct net_device *d + u32 tempval; + + regs = priv->gfargrp[0].regs; +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_rx_qs(priv); + + if (features & NETIF_F_HW_VLAN_TX) { +@@ -2344,7 +2344,7 @@ void gfar_vlan_mode(struct net_device *d + gfar_change_mtu(dev, dev->mtu); + + unlock_rx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + + static int gfar_change_mtu(struct net_device *dev, int new_mtu) +@@ -2956,7 +2956,7 @@ static void adjust_link(struct net_devic + struct phy_device *phydev = priv->phydev; + int new_state = 0; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + + if (phydev->link) { +@@ -3023,7 +3023,7 @@ static void adjust_link(struct net_devic + if (new_state && netif_msg_link(priv)) + phy_print_status(phydev); + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + + /* Update the hash table based on the current list of multicast +@@ -3223,14 +3223,14 @@ static irqreturn_t gfar_error(int irq, v + dev->stats.tx_dropped++; + priv->extra_stats.tx_underrun++; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + + /* Reactivate the Tx Queues */ + gfar_write(®s->tstat, gfargrp->tstat); + + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + netif_dbg(priv, tx_err, dev, "Transmit Error\n"); + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/freescale/gianfar_ethtool.c sun8i-rt/drivers/net/ethernet/freescale/gianfar_ethtool.c +--- sun8i/drivers/net/ethernet/freescale/gianfar_ethtool.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/freescale/gianfar_ethtool.c 2016-08-22 18:18:37.276292742 +0200 +@@ -486,7 +486,7 @@ static int gfar_sringparam(struct net_de + + /* Halt TX and RX, and process the frames which + * have already been received */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + lock_rx_qs(priv); + +@@ -494,7 +494,7 @@ static int gfar_sringparam(struct net_de + + unlock_rx_qs(priv); + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + for (i = 0; i < priv->num_rx_queues; i++) + gfar_clean_rx_ring(priv->rx_queue[i], +@@ -535,7 +535,7 @@ int gfar_set_features(struct net_device + if (dev->flags & IFF_UP) { + /* Halt TX and RX, and process the frames which + * have already been received */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + lock_rx_qs(priv); + +@@ -543,7 +543,7 @@ int gfar_set_features(struct net_device + + unlock_tx_qs(priv); + unlock_rx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + for (i = 0; i < priv->num_rx_queues; i++) + gfar_clean_rx_ring(priv->rx_queue[i], +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/freescale/gianfar_sysfs.c sun8i-rt/drivers/net/ethernet/freescale/gianfar_sysfs.c +--- sun8i/drivers/net/ethernet/freescale/gianfar_sysfs.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/freescale/gianfar_sysfs.c 2016-08-22 18:18:37.276292742 +0200 +@@ -68,7 +68,7 @@ static ssize_t gfar_set_bd_stash(struct + return count; + + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_rx_qs(priv); + + /* Set the new stashing value */ +@@ -84,7 +84,7 @@ static ssize_t gfar_set_bd_stash(struct + gfar_write(®s->attr, temp); + + unlock_rx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + return count; + } +@@ -112,7 +112,7 @@ static ssize_t gfar_set_rx_stash_size(st + if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_BUF_STASHING)) + return count; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_rx_qs(priv); + + if (length > priv->rx_buffer_size) +@@ -140,7 +140,7 @@ static ssize_t gfar_set_rx_stash_size(st + + out: + unlock_rx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + return count; + } +@@ -171,7 +171,7 @@ static ssize_t gfar_set_rx_stash_index(s + if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_BUF_STASHING)) + return count; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_rx_qs(priv); + + if (index > priv->rx_stash_size) +@@ -189,7 +189,7 @@ static ssize_t gfar_set_rx_stash_index(s + + out: + unlock_rx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + return count; + } +@@ -219,7 +219,7 @@ static ssize_t gfar_set_fifo_threshold(s + if (length > GFAR_MAX_FIFO_THRESHOLD) + return count; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + + priv->fifo_threshold = length; +@@ -230,7 +230,7 @@ static ssize_t gfar_set_fifo_threshold(s + gfar_write(®s->fifo_tx_thr, temp); + + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + return count; + } +@@ -259,7 +259,7 @@ static ssize_t gfar_set_fifo_starve(stru + if (num > GFAR_MAX_FIFO_STARVE) + return count; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + + priv->fifo_starve = num; +@@ -270,7 +270,7 @@ static ssize_t gfar_set_fifo_starve(stru + gfar_write(®s->fifo_tx_starve, temp); + + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + return count; + } +@@ -300,7 +300,7 @@ static ssize_t gfar_set_fifo_starve_off( + if (num > GFAR_MAX_FIFO_STARVE_OFF) + return count; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + + priv->fifo_starve_off = num; +@@ -311,7 +311,7 @@ static ssize_t gfar_set_fifo_starve_off( + gfar_write(®s->fifo_tx_starve_shutoff, temp); + + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + return count; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/ibm/ehea/ehea_main.c sun8i-rt/drivers/net/ethernet/ibm/ehea/ehea_main.c +--- sun8i/drivers/net/ethernet/ibm/ehea/ehea_main.c 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/ibm/ehea/ehea_main.c 2016-08-22 16:04:23.604200150 +0200 +@@ -1308,7 +1308,7 @@ static int ehea_reg_interrupts(struct ne + "%s-queue%d", dev->name, i); + ret = ibmebus_request_irq(pr->eq->attr.ist1, + ehea_recv_irq_handler, +- IRQF_DISABLED, pr->int_send_name, ++ IRQF_NO_THREAD, pr->int_send_name, + pr); + if (ret) { + netdev_err(dev, "failed registering irq for ehea_queue port_res_nr:%d, ist=%X\n", +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/neterion/s2io.c sun8i-rt/drivers/net/ethernet/neterion/s2io.c +--- sun8i/drivers/net/ethernet/neterion/s2io.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/neterion/s2io.c 2016-08-22 16:35:18.708221478 +0200 +@@ -4089,12 +4089,7 @@ static netdev_tx_t s2io_xmit(struct sk_b + [skb->priority & (MAX_TX_FIFOS - 1)]; + fifo = &mac_control->fifos[queue]; + +- if (do_spin_lock) +- spin_lock_irqsave(&fifo->tx_lock, flags); +- else { +- if (unlikely(!spin_trylock_irqsave(&fifo->tx_lock, flags))) +- return NETDEV_TX_LOCKED; +- } ++ spin_lock_irqsave(&fifo->tx_lock, flags); + + if (sp->config.multiq) { + if (__netif_subqueue_stopped(dev, fifo->fifo_no)) { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c sun8i-rt/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +--- sun8i/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c 2016-08-22 16:35:18.708221478 +0200 +@@ -2128,10 +2128,9 @@ static int pch_gbe_xmit_frame(struct sk_ + adapter->stats.tx_length_errors++; + return NETDEV_TX_OK; + } +- if (!spin_trylock_irqsave(&tx_ring->tx_lock, flags)) { +- /* Collision - tell upper layer to requeue */ +- return NETDEV_TX_LOCKED; +- } ++ ++ spin_lock_irqsave(&tx_ring->tx_lock, flags); ++ + if (unlikely(!PCH_GBE_DESC_UNUSED(tx_ring))) { + netif_stop_queue(netdev); + spin_unlock_irqrestore(&tx_ring->tx_lock, flags); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/realtek/8139too.c sun8i-rt/drivers/net/ethernet/realtek/8139too.c +--- sun8i/drivers/net/ethernet/realtek/8139too.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/realtek/8139too.c 2016-08-22 16:04:07.792199969 +0200 +@@ -2240,7 +2240,7 @@ static irqreturn_t rtl8139_interrupt (in + */ + static void rtl8139_poll_controller(struct net_device *dev) + { +- disable_irq(dev->irq); ++ disable_irq_nosync(dev->irq); + rtl8139_interrupt(dev->irq, dev); + enable_irq(dev->irq); + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/ethernet/tehuti/tehuti.c sun8i-rt/drivers/net/ethernet/tehuti/tehuti.c +--- sun8i/drivers/net/ethernet/tehuti/tehuti.c 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/drivers/net/ethernet/tehuti/tehuti.c 2016-08-22 16:35:18.708221478 +0200 +@@ -1606,13 +1606,8 @@ static netdev_tx_t bdx_tx_transmit(struc + unsigned long flags; + + ENTER; +- local_irq_save(flags); +- if (!spin_trylock(&priv->tx_lock)) { +- local_irq_restore(flags); +- DBG("%s[%s]: TX locked, returning NETDEV_TX_LOCKED\n", +- BDX_DRV_NAME, ndev->name); +- return NETDEV_TX_LOCKED; +- } ++ ++ spin_lock_irqsave(&priv->tx_lock, flags); + + /* build tx descriptor */ + BDX_ASSERT(f->m.wptr >= f->m.memsz); /* started with valid wptr */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/Kconfig sun8i-rt/drivers/net/Kconfig +--- sun8i/drivers/net/Kconfig 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/net/Kconfig 2016-08-22 17:58:34.956278919 +0200 +@@ -156,6 +156,7 @@ config MACVTAP + + config NETCONSOLE + tristate "Network console logging support" ++ depends on !PREEMPT_RT_FULL + ---help--- + If you want to log kernel messages over the network, enable this. + See for details. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/net/rionet.c sun8i-rt/drivers/net/rionet.c +--- sun8i/drivers/net/rionet.c 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/net/rionet.c 2016-08-22 16:35:18.712221478 +0200 +@@ -178,11 +178,7 @@ static int rionet_start_xmit(struct sk_b + unsigned long flags; + int add_num = 1; + +- local_irq_save(flags); +- if (!spin_trylock(&rnet->tx_lock)) { +- local_irq_restore(flags); +- return NETDEV_TX_LOCKED; +- } ++ spin_lock_irqsave(&rnet->tx_lock, flags); + + if (is_multicast_ether_addr(eth->h_dest)) + add_num = nact; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/of/base.c sun8i-rt/drivers/of/base.c +--- sun8i/drivers/of/base.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/drivers/of/base.c 2016-08-22 16:18:11.100209664 +0200 +@@ -54,7 +54,7 @@ static DEFINE_MUTEX(of_aliases_mutex); + /* use when traversing tree through the allnext, child, sibling, + * or parent members of struct device_node. + */ +-DEFINE_RWLOCK(devtree_lock); ++DEFINE_RAW_SPINLOCK(devtree_lock); + + int of_n_addr_cells(struct device_node *np) + { +@@ -163,16 +163,14 @@ void of_node_put(struct device_node *nod + EXPORT_SYMBOL(of_node_put); + #endif /* CONFIG_OF_DYNAMIC */ + +-struct property *of_find_property(const struct device_node *np, +- const char *name, +- int *lenp) ++static struct property *__of_find_property(const struct device_node *np, ++ const char *name, int *lenp) + { + struct property *pp; + + if (!np) + return NULL; + +- read_lock(&devtree_lock); + for (pp = np->properties; pp != 0; pp = pp->next) { + if (of_prop_cmp(pp->name, name) == 0) { + if (lenp != 0) +@@ -180,7 +178,20 @@ struct property *of_find_property(const + break; + } + } +- read_unlock(&devtree_lock); ++ ++ return pp; ++} ++ ++struct property *of_find_property(const struct device_node *np, ++ const char *name, ++ int *lenp) ++{ ++ struct property *pp; ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&devtree_lock, flags); ++ pp = __of_find_property(np, name, lenp); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + + return pp; + } +@@ -198,13 +209,13 @@ struct device_node *of_find_all_nodes(st + { + struct device_node *np; + +- read_lock(&devtree_lock); ++ raw_spin_lock(&devtree_lock); + np = prev ? prev->allnext : allnodes; + for (; np != NULL; np = np->allnext) + if (of_node_get(np)) + break; + of_node_put(prev); +- read_unlock(&devtree_lock); ++ raw_spin_unlock(&devtree_lock); + return np; + } + EXPORT_SYMBOL(of_find_all_nodes); +@@ -213,8 +224,20 @@ EXPORT_SYMBOL(of_find_all_nodes); + * Find a property with a given name for a given node + * and return the value. + */ ++static const void *__of_get_property(const struct device_node *np, ++ const char *name, int *lenp) ++{ ++ struct property *pp = __of_find_property(np, name, lenp); ++ ++ return pp ? pp->value : NULL; ++} ++ ++/* ++ * Find a property with a given name for a given node ++ * and return the value. ++ */ + const void *of_get_property(const struct device_node *np, const char *name, +- int *lenp) ++ int *lenp) + { + struct property *pp = of_find_property(np, name, lenp); + +@@ -225,13 +248,13 @@ EXPORT_SYMBOL(of_get_property); + /** Checks if the given "compat" string matches one of the strings in + * the device's "compatible" property + */ +-int of_device_is_compatible(const struct device_node *device, +- const char *compat) ++static int __of_device_is_compatible(const struct device_node *device, ++ const char *compat) + { + const char* cp; +- int cplen, l; ++ int uninitialized_var(cplen), l; + +- cp = of_get_property(device, "compatible", &cplen); ++ cp = __of_get_property(device, "compatible", &cplen); + if (cp == NULL) + return 0; + while (cplen > 0) { +@@ -244,6 +267,21 @@ int of_device_is_compatible(const struct + + return 0; + } ++ ++/** Checks if the given "compat" string matches one of the strings in ++ * the device's "compatible" property ++ */ ++int of_device_is_compatible(const struct device_node *device, ++ const char *compat) ++{ ++ unsigned long flags; ++ int res; ++ ++ raw_spin_lock_irqsave(&devtree_lock, flags); ++ res = __of_device_is_compatible(device, compat); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); ++ return res; ++} + EXPORT_SYMBOL(of_device_is_compatible); + + /** +@@ -303,13 +341,14 @@ EXPORT_SYMBOL(of_device_is_available); + struct device_node *of_get_parent(const struct device_node *node) + { + struct device_node *np; ++ unsigned long flags; + + if (!node) + return NULL; + +- read_lock(&devtree_lock); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + np = of_node_get(node->parent); +- read_unlock(&devtree_lock); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + return np; + } + EXPORT_SYMBOL(of_get_parent); +@@ -328,14 +367,15 @@ EXPORT_SYMBOL(of_get_parent); + struct device_node *of_get_next_parent(struct device_node *node) + { + struct device_node *parent; ++ unsigned long flags; + + if (!node) + return NULL; + +- read_lock(&devtree_lock); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + parent = of_node_get(node->parent); + of_node_put(node); +- read_unlock(&devtree_lock); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + return parent; + } + +@@ -351,14 +391,15 @@ struct device_node *of_get_next_child(co + struct device_node *prev) + { + struct device_node *next; ++ unsigned long flags; + +- read_lock(&devtree_lock); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + next = prev ? prev->sibling : node->child; + for (; next; next = next->sibling) + if (of_node_get(next)) + break; + of_node_put(prev); +- read_unlock(&devtree_lock); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + return next; + } + EXPORT_SYMBOL(of_get_next_child); +@@ -373,14 +414,15 @@ EXPORT_SYMBOL(of_get_next_child); + struct device_node *of_find_node_by_path(const char *path) + { + struct device_node *np = allnodes; ++ unsigned long flags; + +- read_lock(&devtree_lock); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + for (; np; np = np->allnext) { + if (np->full_name && (of_node_cmp(np->full_name, path) == 0) + && of_node_get(np)) + break; + } +- read_unlock(&devtree_lock); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + return np; + } + EXPORT_SYMBOL(of_find_node_by_path); +@@ -400,15 +442,16 @@ struct device_node *of_find_node_by_name + const char *name) + { + struct device_node *np; ++ unsigned long flags; + +- read_lock(&devtree_lock); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + np = from ? from->allnext : allnodes; + for (; np; np = np->allnext) + if (np->name && (of_node_cmp(np->name, name) == 0) + && of_node_get(np)) + break; + of_node_put(from); +- read_unlock(&devtree_lock); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + return np; + } + EXPORT_SYMBOL(of_find_node_by_name); +@@ -429,15 +472,16 @@ struct device_node *of_find_node_by_type + const char *type) + { + struct device_node *np; ++ unsigned long flags; + +- read_lock(&devtree_lock); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + np = from ? from->allnext : allnodes; + for (; np; np = np->allnext) + if (np->type && (of_node_cmp(np->type, type) == 0) + && of_node_get(np)) + break; + of_node_put(from); +- read_unlock(&devtree_lock); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + return np; + } + EXPORT_SYMBOL(of_find_node_by_type); +@@ -460,18 +504,20 @@ struct device_node *of_find_compatible_n + const char *type, const char *compatible) + { + struct device_node *np; ++ unsigned long flags; + +- read_lock(&devtree_lock); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + np = from ? from->allnext : allnodes; + for (; np; np = np->allnext) { + if (type + && !(np->type && (of_node_cmp(np->type, type) == 0))) + continue; +- if (of_device_is_compatible(np, compatible) && of_node_get(np)) ++ if (__of_device_is_compatible(np, compatible) && ++ of_node_get(np)) + break; + } + of_node_put(from); +- read_unlock(&devtree_lock); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + return np; + } + EXPORT_SYMBOL(of_find_compatible_node); +@@ -493,8 +539,9 @@ struct device_node *of_find_node_with_pr + { + struct device_node *np; + struct property *pp; ++ unsigned long flags; + +- read_lock(&devtree_lock); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + np = from ? from->allnext : allnodes; + for (; np; np = np->allnext) { + for (pp = np->properties; pp != 0; pp = pp->next) { +@@ -506,20 +553,14 @@ struct device_node *of_find_node_with_pr + } + out: + of_node_put(from); +- read_unlock(&devtree_lock); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + return np; + } + EXPORT_SYMBOL(of_find_node_with_property); + +-/** +- * of_match_node - Tell if an device_node has a matching of_match structure +- * @matches: array of of device match structures to search in +- * @node: the of device structure to match against +- * +- * Low level utility function used by device matching. +- */ +-const struct of_device_id *of_match_node(const struct of_device_id *matches, +- const struct device_node *node) ++static ++const struct of_device_id *__of_match_node(const struct of_device_id *matches, ++ const struct device_node *node) + { + if (!matches) + return NULL; +@@ -533,14 +574,33 @@ const struct of_device_id *of_match_node + match &= node->type + && !strcmp(matches->type, node->type); + if (matches->compatible[0]) +- match &= of_device_is_compatible(node, +- matches->compatible); ++ match &= __of_device_is_compatible(node, ++ matches->compatible); + if (match) + return matches; + matches++; + } + return NULL; + } ++ ++/** ++ * of_match_node - Tell if an device_node has a matching of_match structure ++ * @matches: array of of device match structures to search in ++ * @node: the of device structure to match against ++ * ++ * Low level utility function used by device matching. ++ */ ++const struct of_device_id *of_match_node(const struct of_device_id *matches, ++ const struct device_node *node) ++{ ++ const struct of_device_id *match; ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&devtree_lock, flags); ++ match = __of_match_node(matches, node); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); ++ return match; ++} + EXPORT_SYMBOL(of_match_node); + + /** +@@ -559,15 +619,16 @@ struct device_node *of_find_matching_nod + const struct of_device_id *matches) + { + struct device_node *np; ++ unsigned long flags; + +- read_lock(&devtree_lock); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + np = from ? from->allnext : allnodes; + for (; np; np = np->allnext) { +- if (of_match_node(matches, np) && of_node_get(np)) ++ if (__of_match_node(matches, np) && of_node_get(np)) + break; + } + of_node_put(from); +- read_unlock(&devtree_lock); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + return np; + } + EXPORT_SYMBOL(of_find_matching_node); +@@ -610,12 +671,12 @@ struct device_node *of_find_node_by_phan + { + struct device_node *np; + +- read_lock(&devtree_lock); ++ raw_spin_lock(&devtree_lock); + for (np = allnodes; np; np = np->allnext) + if (np->phandle == handle) + break; + of_node_get(np); +- read_unlock(&devtree_lock); ++ raw_spin_unlock(&devtree_lock); + return np; + } + EXPORT_SYMBOL(of_find_node_by_phandle); +@@ -943,18 +1004,18 @@ int prom_add_property(struct device_node + unsigned long flags; + + prop->next = NULL; +- write_lock_irqsave(&devtree_lock, flags); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + next = &np->properties; + while (*next) { + if (strcmp(prop->name, (*next)->name) == 0) { + /* duplicate ! don't insert it */ +- write_unlock_irqrestore(&devtree_lock, flags); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + return -1; + } + next = &(*next)->next; + } + *next = prop; +- write_unlock_irqrestore(&devtree_lock, flags); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + + #ifdef CONFIG_PROC_DEVICETREE + /* try to add to proc as well if it was initialized */ +@@ -979,7 +1040,7 @@ int prom_remove_property(struct device_n + unsigned long flags; + int found = 0; + +- write_lock_irqsave(&devtree_lock, flags); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + next = &np->properties; + while (*next) { + if (*next == prop) { +@@ -992,7 +1053,7 @@ int prom_remove_property(struct device_n + } + next = &(*next)->next; + } +- write_unlock_irqrestore(&devtree_lock, flags); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + + if (!found) + return -ENODEV; +@@ -1022,7 +1083,7 @@ int prom_update_property(struct device_n + unsigned long flags; + int found = 0; + +- write_lock_irqsave(&devtree_lock, flags); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + next = &np->properties; + while (*next) { + if (*next == oldprop) { +@@ -1036,7 +1097,7 @@ int prom_update_property(struct device_n + } + next = &(*next)->next; + } +- write_unlock_irqrestore(&devtree_lock, flags); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + + if (!found) + return -ENODEV; +@@ -1066,12 +1127,12 @@ void of_attach_node(struct device_node * + { + unsigned long flags; + +- write_lock_irqsave(&devtree_lock, flags); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + np->sibling = np->parent->child; + np->allnext = allnodes; + np->parent->child = np; + allnodes = np; +- write_unlock_irqrestore(&devtree_lock, flags); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + } + + /** +@@ -1085,7 +1146,7 @@ void of_detach_node(struct device_node * + struct device_node *parent; + unsigned long flags; + +- write_lock_irqsave(&devtree_lock, flags); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + + parent = np->parent; + if (!parent) +@@ -1116,7 +1177,7 @@ void of_detach_node(struct device_node * + of_node_set_flag(np, OF_DETACHED); + + out_unlock: +- write_unlock_irqrestore(&devtree_lock, flags); ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + } + #endif /* defined(CONFIG_OF_DYNAMIC) */ + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/pci/access.c sun8i-rt/drivers/pci/access.c +--- sun8i/drivers/pci/access.c 2016-08-22 14:14:41.000000000 +0200 ++++ sun8i-rt/drivers/pci/access.c 2016-08-22 16:23:11.200213114 +0200 +@@ -522,7 +522,7 @@ void pci_cfg_access_unlock(struct pci_de + WARN_ON(!dev->block_cfg_access); + + dev->block_cfg_access = 0; +- wake_up_all(&pci_cfg_wait); ++ wake_up_all_locked(&pci_cfg_wait); + raw_spin_unlock_irqrestore(&pci_lock, flags); + } + EXPORT_SYMBOL_GPL(pci_cfg_access_unlock); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/scsi/fcoe/fcoe.c sun8i-rt/drivers/scsi/fcoe/fcoe.c +--- sun8i/drivers/scsi/fcoe/fcoe.c 2016-08-22 14:14:15.000000000 +0200 ++++ sun8i-rt/drivers/scsi/fcoe/fcoe.c 2016-08-22 17:49:20.536272545 +0200 +@@ -1222,7 +1222,7 @@ static void fcoe_percpu_thread_destroy(u + struct sk_buff *skb; + #ifdef CONFIG_SMP + struct fcoe_percpu_s *p0; +- unsigned targ_cpu = get_cpu(); ++ unsigned targ_cpu = get_cpu_light(); + #endif /* CONFIG_SMP */ + + FCOE_DBG("Destroying receive thread for CPU %d\n", cpu); +@@ -1278,7 +1278,7 @@ static void fcoe_percpu_thread_destroy(u + kfree_skb(skb); + spin_unlock_bh(&p->fcoe_rx_list.lock); + } +- put_cpu(); ++ put_cpu_light(); + #else + /* + * This a non-SMP scenario where the singular Rx thread is +@@ -1494,11 +1494,11 @@ err2: + static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen) + { + struct fcoe_percpu_s *fps; +- int rc; ++ int rc, cpu = get_cpu_light(); + +- fps = &get_cpu_var(fcoe_percpu); ++ fps = &per_cpu(fcoe_percpu, cpu); + rc = fcoe_get_paged_crc_eof(skb, tlen, fps); +- put_cpu_var(fcoe_percpu); ++ put_cpu_light(); + + return rc; + } +@@ -1738,7 +1738,7 @@ static void fcoe_recv_frame(struct sk_bu + */ + hp = (struct fcoe_hdr *) skb_network_header(skb); + +- stats = per_cpu_ptr(lport->dev_stats, get_cpu()); ++ stats = per_cpu_ptr(lport->dev_stats, get_cpu_light()); + if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) { + if (stats->ErrorFrames < 5) + printk(KERN_WARNING "fcoe: FCoE version " +@@ -1770,13 +1770,13 @@ static void fcoe_recv_frame(struct sk_bu + goto drop; + + if (!fcoe_filter_frames(lport, fp)) { +- put_cpu(); ++ put_cpu_light(); + fc_exch_recv(lport, fp); + return; + } + drop: + stats->ErrorFrames++; +- put_cpu(); ++ put_cpu_light(); + kfree_skb(skb); + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/scsi/fcoe/fcoe_ctlr.c sun8i-rt/drivers/scsi/fcoe/fcoe_ctlr.c +--- sun8i/drivers/scsi/fcoe/fcoe_ctlr.c 2016-08-22 14:14:15.000000000 +0200 ++++ sun8i-rt/drivers/scsi/fcoe/fcoe_ctlr.c 2016-08-22 17:49:20.536272545 +0200 +@@ -719,7 +719,7 @@ static unsigned long fcoe_ctlr_age_fcfs( + unsigned long sel_time = 0; + struct fcoe_dev_stats *stats; + +- stats = per_cpu_ptr(fip->lp->dev_stats, get_cpu()); ++ stats = per_cpu_ptr(fip->lp->dev_stats, get_cpu_light()); + + list_for_each_entry_safe(fcf, next, &fip->fcfs, list) { + deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2; +@@ -752,7 +752,7 @@ static unsigned long fcoe_ctlr_age_fcfs( + sel_time = fcf->time; + } + } +- put_cpu(); ++ put_cpu_light(); + if (sel_time && !fip->sel_fcf && !fip->sel_time) { + sel_time += msecs_to_jiffies(FCOE_CTLR_START_DELAY); + fip->sel_time = sel_time; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/scsi/libfc/fc_exch.c sun8i-rt/drivers/scsi/libfc/fc_exch.c +--- sun8i/drivers/scsi/libfc/fc_exch.c 2016-08-22 14:14:15.000000000 +0200 ++++ sun8i-rt/drivers/scsi/libfc/fc_exch.c 2016-08-22 17:49:20.536272545 +0200 +@@ -724,10 +724,10 @@ static struct fc_exch *fc_exch_em_alloc( + } + memset(ep, 0, sizeof(*ep)); + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + pool = per_cpu_ptr(mp->pool, cpu); + spin_lock_bh(&pool->lock); +- put_cpu(); ++ put_cpu_light(); + + /* peek cache of free slot */ + if (pool->left != FC_XID_UNKNOWN) { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/scsi/libsas/sas_ata.c sun8i-rt/drivers/scsi/libsas/sas_ata.c +--- sun8i/drivers/scsi/libsas/sas_ata.c 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/drivers/scsi/libsas/sas_ata.c 2016-08-22 18:24:36.892296876 +0200 +@@ -191,7 +191,7 @@ static unsigned int sas_ata_qc_issue(str + /* TODO: audit callers to ensure they are ready for qc_issue to + * unconditionally re-enable interrupts + */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + spin_unlock(ap->lock); + + /* If the device fell off, no sense in issuing commands */ +@@ -261,7 +261,7 @@ static unsigned int sas_ata_qc_issue(str + + out: + spin_lock(ap->lock); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return ret; + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/scsi/qla2xxx/qla_inline.h sun8i-rt/drivers/scsi/qla2xxx/qla_inline.h +--- sun8i/drivers/scsi/qla2xxx/qla_inline.h 2016-08-22 14:14:15.000000000 +0200 ++++ sun8i-rt/drivers/scsi/qla2xxx/qla_inline.h 2016-08-22 17:52:13.608274535 +0200 +@@ -36,12 +36,12 @@ qla2x00_poll(struct rsp_que *rsp) + { + unsigned long flags; + struct qla_hw_data *ha = rsp->hw; +- local_irq_save(flags); ++ local_irq_save_nort(flags); + if (IS_QLA82XX(ha)) + qla82xx_poll(0, rsp); + else + ha->isp_ops->intr_handler(0, rsp); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + + static inline uint8_t * +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/tty/serial/8250/8250.c sun8i-rt/drivers/tty/serial/8250/8250.c +--- sun8i/drivers/tty/serial/8250/8250.c 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/drivers/tty/serial/8250/8250.c 2016-08-22 17:48:05.632271684 +0200 +@@ -38,6 +38,7 @@ + #include + #include + #include ++#include + #ifdef CONFIG_SPARC + #include + #endif +@@ -85,7 +86,16 @@ static unsigned int skip_txen_test; /* f + #define DEBUG_INTR(fmt...) do { } while (0) + #endif + +-#define PASS_LIMIT 512 ++/* ++ * On -rt we can have a more delays, and legitimately ++ * so - so don't drop work spuriously and spam the ++ * syslog: ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define PASS_LIMIT 1000000 ++#else ++# define PASS_LIMIT 512 ++#endif + + #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE) + +@@ -2965,14 +2975,10 @@ serial8250_console_write(struct console + + touch_nmi_watchdog(); + +- local_irq_save(flags); +- if (port->sysrq) { +- /* serial8250_handle_irq() already took the lock */ +- locked = 0; +- } else if (oops_in_progress) { +- locked = spin_trylock(&port->lock); +- } else +- spin_lock(&port->lock); ++ if (port->sysrq || oops_in_progress || in_kdb_printk()) ++ locked = spin_trylock_irqsave(&port->lock, flags); ++ else ++ spin_lock_irqsave(&port->lock, flags); + + /* + * First save the IER then disable the interrupts +@@ -3004,8 +3010,7 @@ serial8250_console_write(struct console + serial8250_modem_status(up); + + if (locked) +- spin_unlock(&port->lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&port->lock, flags); + } + + static int __init serial8250_console_setup(struct console *co, char *options) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/tty/serial/amba-pl011.c sun8i-rt/drivers/tty/serial/amba-pl011.c +--- sun8i/drivers/tty/serial/amba-pl011.c 2016-08-22 14:14:15.000000000 +0200 ++++ sun8i-rt/drivers/tty/serial/amba-pl011.c 2016-08-22 18:07:52.220285326 +0200 +@@ -1788,13 +1788,19 @@ pl011_console_write(struct console *co, + + clk_enable(uap->clk); + +- local_irq_save(flags); ++ /* ++ * local_irq_save(flags); ++ * ++ * This local_irq_save() is nonsense. If we come in via sysrq ++ * handling then interrupts are already disabled. Aside of ++ * that the port.sysrq check is racy on SMP regardless. ++ */ + if (uap->port.sysrq) + locked = 0; + else if (oops_in_progress) +- locked = spin_trylock(&uap->port.lock); ++ locked = spin_trylock_irqsave(&uap->port.lock, flags); + else +- spin_lock(&uap->port.lock); ++ spin_lock_irqsave(&uap->port.lock, flags); + + /* + * First save the CR then disable the interrupts +@@ -1816,8 +1822,7 @@ pl011_console_write(struct console *co, + writew(old_cr, uap->port.membase + UART011_CR); + + if (locked) +- spin_unlock(&uap->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&uap->port.lock, flags); + + clk_disable(uap->clk); + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/tty/serial/imx.c sun8i-rt/drivers/tty/serial/imx.c +--- sun8i/drivers/tty/serial/imx.c 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/drivers/tty/serial/imx.c 2016-08-22 18:11:15.716287665 +0200 +@@ -1215,8 +1215,14 @@ imx_console_write(struct console *co, co + struct imx_port_ucrs old_ucr; + unsigned int ucr1; + unsigned long flags; ++ int locked = 1; + +- spin_lock_irqsave(&sport->port.lock, flags); ++ if (sport->port.sysrq) ++ locked = 0; ++ else if (oops_in_progress) ++ locked = spin_trylock_irqsave(&sport->port.lock, flags); ++ else ++ spin_lock_irqsave(&sport->port.lock, flags); + + /* + * First, save UCR1/2/3 and then disable interrupts +@@ -1243,7 +1249,8 @@ imx_console_write(struct console *co, co + + imx_port_ucrs_restore(&sport->port, &old_ucr); + +- spin_unlock_irqrestore(&sport->port.lock, flags); ++ if (locked) ++ spin_unlock_irqrestore(&sport->port.lock, flags); + } + + /* +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/tty/serial/omap-serial.c sun8i-rt/drivers/tty/serial/omap-serial.c +--- sun8i/drivers/tty/serial/omap-serial.c 2016-08-22 14:14:15.000000000 +0200 ++++ sun8i-rt/drivers/tty/serial/omap-serial.c 2016-08-22 17:37:52.336264633 +0200 +@@ -1064,13 +1064,10 @@ serial_omap_console_write(struct console + + pm_runtime_get_sync(&up->pdev->dev); + +- local_irq_save(flags); +- if (up->port.sysrq) +- locked = 0; +- else if (oops_in_progress) +- locked = spin_trylock(&up->port.lock); ++ if (up->port.sysrq || oops_in_progress) ++ locked = spin_trylock_irqsave(&up->port.lock, flags); + else +- spin_lock(&up->port.lock); ++ spin_lock_irqsave(&up->port.lock, flags); + + /* + * First save the IER then disable the interrupts +@@ -1099,8 +1096,7 @@ serial_omap_console_write(struct console + pm_runtime_mark_last_busy(&up->pdev->dev); + pm_runtime_put_autosuspend(&up->pdev->dev); + if (locked) +- spin_unlock(&up->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&up->port.lock, flags); + } + + static int __init +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/tty/tty_buffer.c sun8i-rt/drivers/tty/tty_buffer.c +--- sun8i/drivers/tty/tty_buffer.c 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/drivers/tty/tty_buffer.c 2016-08-22 17:37:36.728264453 +0200 +@@ -496,10 +496,14 @@ void tty_flip_buffer_push(struct tty_str + tty->buf.tail->commit = tty->buf.tail->used; + spin_unlock_irqrestore(&tty->buf.lock, flags); + ++#ifndef CONFIG_PREEMPT_RT_FULL + if (tty->low_latency) + flush_to_ldisc(&tty->buf.work); + else + schedule_work(&tty->buf.work); ++#else ++ flush_to_ldisc(&tty->buf.work); ++#endif + } + EXPORT_SYMBOL(tty_flip_buffer_push); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/tty/tty_ldisc.c sun8i-rt/drivers/tty/tty_ldisc.c +--- sun8i/drivers/tty/tty_ldisc.c 2016-08-22 14:14:15.000000000 +0200 ++++ sun8i-rt/drivers/tty/tty_ldisc.c 2016-08-22 16:32:50.140219770 +0200 +@@ -53,7 +53,7 @@ static void put_ldisc(struct tty_ldisc * + * We really want an "atomic_dec_and_lock_irqsave()", + * but we don't have it, so this does it by hand. + */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + if (atomic_dec_and_lock(&ld->users, &tty_ldisc_lock)) { + struct tty_ldisc_ops *ldo = ld->ops; + +@@ -64,7 +64,7 @@ static void put_ldisc(struct tty_ldisc * + kfree(ld); + return; + } +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + wake_up(&tty_ldisc_idle); + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/usb/core/hcd.c sun8i-rt/drivers/usb/core/hcd.c +--- sun8i/drivers/usb/core/hcd.c 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/drivers/usb/core/hcd.c 2016-08-22 16:32:37.896219629 +0200 +@@ -2143,7 +2143,7 @@ irqreturn_t usb_hcd_irq (int irq, void * + * when the first handler doesn't use it. So let's just + * assume it's never used. + */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + if (unlikely(HCD_DEAD(hcd) || !HCD_HW_ACCESSIBLE(hcd))) + rc = IRQ_NONE; +@@ -2152,7 +2152,7 @@ irqreturn_t usb_hcd_irq (int irq, void * + else + rc = IRQ_HANDLED; + +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return rc; + } + EXPORT_SYMBOL_GPL(usb_hcd_irq); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/usb/gadget/ci13xxx_udc.c sun8i-rt/drivers/usb/gadget/ci13xxx_udc.c +--- sun8i/drivers/usb/gadget/ci13xxx_udc.c 2016-08-22 14:14:15.000000000 +0200 ++++ sun8i-rt/drivers/usb/gadget/ci13xxx_udc.c 2016-08-22 16:22:53.940212916 +0200 +@@ -834,7 +834,7 @@ static struct { + } dbg_data = { + .idx = 0, + .tty = 0, +- .lck = __RW_LOCK_UNLOCKED(lck) ++ .lck = __RW_LOCK_UNLOCKED(dbg_data.lck) + }; + + /** +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/drivers/usb/host/ohci-hcd.c sun8i-rt/drivers/usb/host/ohci-hcd.c +--- sun8i/drivers/usb/host/ohci-hcd.c 2016-08-22 14:14:15.000000000 +0200 ++++ sun8i-rt/drivers/usb/host/ohci-hcd.c 2016-08-22 16:36:00.220221955 +0200 +@@ -858,9 +858,13 @@ static irqreturn_t ohci_irq (struct usb_ + } + + if (ints & OHCI_INTR_WDH) { +- spin_lock (&ohci->lock); +- dl_done_list (ohci); +- spin_unlock (&ohci->lock); ++ if (ohci->hcca->done_head == 0) { ++ ints &= ~OHCI_INTR_WDH; ++ } else { ++ spin_lock (&ohci->lock); ++ dl_done_list (ohci); ++ spin_unlock (&ohci->lock); ++ } + } + + if (quirk_zfmicro(ohci) && (ints & OHCI_INTR_SF)) { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/autofs4/autofs_i.h sun8i-rt/fs/autofs4/autofs_i.h +--- sun8i/fs/autofs4/autofs_i.h 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/fs/autofs4/autofs_i.h 2016-08-22 17:52:51.880274975 +0200 +@@ -34,6 +34,7 @@ + #include + #include + #include ++#include + #include + #include + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/autofs4/expire.c sun8i-rt/fs/autofs4/expire.c +--- sun8i/fs/autofs4/expire.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/fs/autofs4/expire.c 2016-08-22 17:52:51.880274975 +0200 +@@ -162,7 +162,7 @@ again: + parent = p->d_parent; + if (!spin_trylock(&parent->d_lock)) { + spin_unlock(&p->d_lock); +- cpu_relax(); ++ cpu_chill(); + goto relock; + } + spin_unlock(&p->d_lock); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/btrfs/ctree.c sun8i-rt/fs/btrfs/ctree.c +--- sun8i/fs/btrfs/ctree.c 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/fs/btrfs/ctree.c 2016-08-22 18:25:31.204297501 +0200 +@@ -77,7 +77,7 @@ noinline void btrfs_clear_path_blocking( + { + int i; + +-#ifdef CONFIG_DEBUG_LOCK_ALLOC ++#if (defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_PREEMPT_RT_BASE)) + /* lockdep really cares that we take all of these spinlocks + * in the right order. If any of the locks in the path are not + * currently blocking, it is going to complain. So, make really +@@ -104,7 +104,7 @@ noinline void btrfs_clear_path_blocking( + } + } + +-#ifdef CONFIG_DEBUG_LOCK_ALLOC ++#if (defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_PREEMPT_RT_BASE)) + if (held) + btrfs_clear_lock_blocking_rw(held, held_rw); + #endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/buffer.c sun8i-rt/fs/buffer.c +--- sun8i/fs/buffer.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/fs/buffer.c 2016-08-22 16:33:55.384220520 +0200 +@@ -281,8 +281,7 @@ static void end_buffer_async_read(struct + * decide that the page is now completely done. + */ + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + clear_buffer_async_read(bh); + unlock_buffer(bh); + tmp = bh; +@@ -295,8 +294,7 @@ static void end_buffer_async_read(struct + } + tmp = tmp->b_this_page; + } while (tmp != bh); +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + + /* + * If none of the buffers had errors and they are all +@@ -308,9 +306,7 @@ static void end_buffer_async_read(struct + return; + + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + + /* +@@ -344,8 +340,7 @@ void end_buffer_async_write(struct buffe + } + + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + + clear_buffer_async_write(bh); + unlock_buffer(bh); +@@ -357,15 +352,12 @@ void end_buffer_async_write(struct buffe + } + tmp = tmp->b_this_page; + } +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + end_page_writeback(page); + return; + + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + EXPORT_SYMBOL(end_buffer_async_write); + +@@ -3204,6 +3196,7 @@ struct buffer_head *alloc_buffer_head(gf + struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); + if (ret) { + INIT_LIST_HEAD(&ret->b_assoc_buffers); ++ buffer_head_init_locks(ret); + preempt_disable(); + __this_cpu_inc(bh_accounting.nr); + recalc_bh_state(); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/dcache.c sun8i-rt/fs/dcache.c +--- sun8i/fs/dcache.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/fs/dcache.c 2016-08-22 17:52:51.880274975 +0200 +@@ -37,6 +37,7 @@ + #include + #include + #include ++#include + #include "internal.h" + #include "mount.h" + +@@ -472,7 +473,7 @@ static inline struct dentry *dentry_kill + if (inode && !spin_trylock(&inode->i_lock)) { + relock: + spin_unlock(&dentry->d_lock); +- cpu_relax(); ++ cpu_chill(); + return dentry; /* try again with same dentry */ + } + if (IS_ROOT(dentry)) +@@ -858,7 +859,7 @@ relock: + + if (!spin_trylock(&dentry->d_lock)) { + spin_unlock(&dcache_lru_lock); +- cpu_relax(); ++ cpu_chill(); + goto relock; + } + +@@ -2054,7 +2055,7 @@ again: + if (dentry->d_count == 1) { + if (inode && !spin_trylock(&inode->i_lock)) { + spin_unlock(&dentry->d_lock); +- cpu_relax(); ++ cpu_chill(); + goto again; + } + dentry->d_flags &= ~DCACHE_CANT_MOUNT; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/eventpoll.c sun8i-rt/fs/eventpoll.c +--- sun8i/fs/eventpoll.c 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/fs/eventpoll.c 2016-08-22 17:42:11.340267610 +0200 +@@ -496,12 +496,12 @@ static int ep_poll_wakeup_proc(void *pri + */ + static void ep_poll_safewake(wait_queue_head_t *wq) + { +- int this_cpu = get_cpu(); ++ int this_cpu = get_cpu_light(); + + ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS, + ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu); + +- put_cpu(); ++ put_cpu_light(); + } + + static void ep_remove_wait_queue(struct eppoll_entry *pwq) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/exec.c sun8i-rt/fs/exec.c +--- sun8i/fs/exec.c 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/fs/exec.c 2016-08-22 17:38:45.912265249 +0200 +@@ -840,10 +840,12 @@ static int exec_mmap(struct mm_struct *m + } + } + task_lock(tsk); ++ preempt_disable_rt(); + active_mm = tsk->active_mm; + tsk->mm = mm; + tsk->active_mm = mm; + activate_mm(active_mm, mm); ++ preempt_enable_rt(); + task_unlock(tsk); + arch_pick_mmap_layout(mm); + if (old_mm) { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/file.c sun8i-rt/fs/file.c +--- sun8i/fs/file.c 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/fs/file.c 2016-08-22 17:39:01.896265432 +0200 +@@ -105,14 +105,14 @@ void free_fdtable_rcu(struct rcu_head *r + kfree(fdt->open_fds); + kfree(fdt); + } else { +- fddef = &get_cpu_var(fdtable_defer_list); ++ fddef = &per_cpu(fdtable_defer_list, get_cpu_light()); + spin_lock(&fddef->lock); + fdt->next = fddef->next; + fddef->next = fdt; + /* vmallocs are handled from the workqueue context */ + schedule_work(&fddef->wq); + spin_unlock(&fddef->lock); +- put_cpu_var(fdtable_defer_list); ++ put_cpu_light(); + } + } + +@@ -421,7 +421,7 @@ struct files_struct init_files = { + .close_on_exec = init_files.close_on_exec_init, + .open_fds = init_files.open_fds_init, + }, +- .file_lock = __SPIN_LOCK_UNLOCKED(init_task.file_lock), ++ .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), + }; + + /* +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/jbd/checkpoint.c sun8i-rt/fs/jbd/checkpoint.c +--- sun8i/fs/jbd/checkpoint.c 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/fs/jbd/checkpoint.c 2016-08-22 18:00:39.500280351 +0200 +@@ -129,6 +129,8 @@ void __log_wait_for_space(journal_t *jou + if (journal->j_flags & JFS_ABORT) + return; + spin_unlock(&journal->j_state_lock); ++ if (current->plug) ++ io_schedule(); + mutex_lock(&journal->j_checkpoint_mutex); + + /* +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/jbd2/checkpoint.c sun8i-rt/fs/jbd2/checkpoint.c +--- sun8i/fs/jbd2/checkpoint.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/fs/jbd2/checkpoint.c 2016-08-22 18:18:14.432292479 +0200 +@@ -125,6 +125,8 @@ void __jbd2_log_wait_for_space(journal_t + if (journal->j_flags & JBD2_ABORT) + return; + write_unlock(&journal->j_state_lock); ++ if (current->plug) ++ io_schedule(); + mutex_lock(&journal->j_checkpoint_mutex); + + /* +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/namespace.c sun8i-rt/fs/namespace.c +--- sun8i/fs/namespace.c 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/fs/namespace.c 2016-08-22 17:52:51.880274975 +0200 +@@ -20,6 +20,7 @@ + #include /* get_fs_root et.al. */ + #include /* fsnotify_vfsmount_delete */ + #include ++#include + #include "pnode.h" + #include "internal.h" + +@@ -313,8 +314,11 @@ int mnt_want_write(struct vfsmount *m) + * incremented count after it has set MNT_WRITE_HOLD. + */ + smp_mb(); +- while (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) +- cpu_relax(); ++ while (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) { ++ preempt_enable(); ++ cpu_chill(); ++ preempt_disable(); ++ } + /* + * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will + * be set to match its requirements. So we must not load that until +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/ntfs/aops.c sun8i-rt/fs/ntfs/aops.c +--- sun8i/fs/ntfs/aops.c 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/fs/ntfs/aops.c 2016-08-22 17:39:15.588265590 +0200 +@@ -108,8 +108,7 @@ static void ntfs_end_buffer_async_read(s + "0x%llx.", (unsigned long long)bh->b_blocknr); + } + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + clear_buffer_async_read(bh); + unlock_buffer(bh); + tmp = bh; +@@ -124,8 +123,7 @@ static void ntfs_end_buffer_async_read(s + } + tmp = tmp->b_this_page; + } while (tmp != bh); +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + /* + * If none of the buffers had errors then we can set the page uptodate, + * but we first have to perform the post read mst fixups, if the +@@ -146,13 +144,13 @@ static void ntfs_end_buffer_async_read(s + recs = PAGE_CACHE_SIZE / rec_size; + /* Should have been verified before we got here... */ + BUG_ON(!recs); +- local_irq_save(flags); ++ local_irq_save_nort(flags); + kaddr = kmap_atomic(page); + for (i = 0; i < recs; i++) + post_read_mst_fixup((NTFS_RECORD*)(kaddr + + i * rec_size), rec_size); + kunmap_atomic(kaddr); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + flush_dcache_page(page); + if (likely(page_uptodate && !PageError(page))) + SetPageUptodate(page); +@@ -160,9 +158,7 @@ static void ntfs_end_buffer_async_read(s + unlock_page(page); + return; + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + + /** +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/timerfd.c sun8i-rt/fs/timerfd.c +--- sun8i/fs/timerfd.c 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/fs/timerfd.c 2016-08-22 17:11:14.400246262 +0200 +@@ -385,7 +385,7 @@ SYSCALL_DEFINE4(timerfd_settime, int, uf + break; + } + spin_unlock_irq(&ctx->wqh.lock); +- cpu_relax(); ++ hrtimer_wait_for_timer(&ctx->tmr); + } + + /* +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/fs/xfs/xfs_linux.h sun8i-rt/fs/xfs/xfs_linux.h +--- sun8i/fs/xfs/xfs_linux.h 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/fs/xfs/xfs_linux.h 2016-08-22 18:26:07.060297913 +0200 +@@ -97,7 +97,7 @@ + /* + * Feature macros (disable/enable) + */ +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT_FULL) + #define HAVE_PERCPU_SB /* per cpu superblock counters are a 2.6 feature */ + #else + #undef HAVE_PERCPU_SB /* per cpu superblock counters are a 2.6 feature */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/acpi/platform/aclinux.h sun8i-rt/include/acpi/platform/aclinux.h +--- sun8i/include/acpi/platform/aclinux.h 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/include/acpi/platform/aclinux.h 2016-08-22 18:11:04.472287536 +0200 +@@ -72,6 +72,7 @@ + + #define acpi_cache_t struct kmem_cache + #define acpi_spinlock spinlock_t * ++#define acpi_raw_spinlock raw_spinlock_t * + #define acpi_cpu_flags unsigned long + + #else /* !__KERNEL__ */ +@@ -175,6 +176,19 @@ static inline void *acpi_os_acquire_obje + lock ? AE_OK : AE_NO_MEMORY; \ + }) + ++#define acpi_os_create_raw_lock(__handle) \ ++({ \ ++ raw_spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock)); \ ++ \ ++ if (lock) { \ ++ *(__handle) = lock; \ ++ raw_spin_lock_init(*(__handle)); \ ++ } \ ++ lock ? AE_OK : AE_NO_MEMORY; \ ++}) ++ ++#define acpi_os_delete_raw_lock(__handle) kfree(__handle) ++ + #endif /* __KERNEL__ */ + + #endif /* __ACLINUX_H__ */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/asm-generic/bug.h sun8i-rt/include/asm-generic/bug.h +--- sun8i/include/asm-generic/bug.h 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/include/asm-generic/bug.h 2016-08-22 16:30:14.880217985 +0200 +@@ -3,6 +3,10 @@ + + #include + ++#ifndef __ASSEMBLY__ ++extern void __WARN_ON(const char *func, const char *file, const int line); ++#endif /* __ASSEMBLY__ */ ++ + #ifdef CONFIG_BUG + + #ifdef CONFIG_GENERIC_BUG +@@ -202,4 +206,18 @@ extern void warn_slowpath_null(const cha + # define WARN_ON_SMP(x) ({0;}) + #endif + ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define BUG_ON_RT(c) BUG_ON(c) ++# define BUG_ON_NONRT(c) do { } while (0) ++# define WARN_ON_RT(condition) WARN_ON(condition) ++# define WARN_ON_NONRT(condition) do { } while (0) ++# define WARN_ON_ONCE_NONRT(condition) do { } while (0) ++#else ++# define BUG_ON_RT(c) do { } while (0) ++# define BUG_ON_NONRT(c) BUG_ON(c) ++# define WARN_ON_RT(condition) do { } while (0) ++# define WARN_ON_NONRT(condition) WARN_ON(condition) ++# define WARN_ON_ONCE_NONRT(condition) WARN_ON_ONCE(condition) ++#endif ++ + #endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/asm-generic/cmpxchg-local.h sun8i-rt/include/asm-generic/cmpxchg-local.h +--- sun8i/include/asm-generic/cmpxchg-local.h 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/include/asm-generic/cmpxchg-local.h 2016-08-22 16:02:50.136199076 +0200 +@@ -21,7 +21,7 @@ static inline unsigned long __cmpxchg_lo + if (size == 8 && sizeof(unsigned long) != 8) + wrong_size_cmpxchg(ptr); + +- local_irq_save(flags); ++ raw_local_irq_save(flags); + switch (size) { + case 1: prev = *(u8 *)ptr; + if (prev == old) +@@ -42,7 +42,7 @@ static inline unsigned long __cmpxchg_lo + default: + wrong_size_cmpxchg(ptr); + } +- local_irq_restore(flags); ++ raw_local_irq_restore(flags); + return prev; + } + +@@ -55,11 +55,11 @@ static inline u64 __cmpxchg64_local_gene + u64 prev; + unsigned long flags; + +- local_irq_save(flags); ++ raw_local_irq_save(flags); + prev = *(u64 *)ptr; + if (prev == old) + *(u64 *)ptr = new; +- local_irq_restore(flags); ++ raw_local_irq_restore(flags); + return prev; + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/buffer_head.h sun8i-rt/include/linux/buffer_head.h +--- sun8i/include/linux/buffer_head.h 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/include/linux/buffer_head.h 2016-08-22 16:34:07.440220659 +0200 +@@ -72,8 +72,52 @@ struct buffer_head { + struct address_space *b_assoc_map; /* mapping this buffer is + associated with */ + atomic_t b_count; /* users using this buffer_head */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spinlock_t b_uptodate_lock; ++#if defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \ ++ defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE) ++ spinlock_t b_state_lock; ++ spinlock_t b_journal_head_lock; ++#endif ++#endif + }; + ++static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh) ++{ ++ unsigned long flags; ++ ++#ifndef CONFIG_PREEMPT_RT_BASE ++ local_irq_save(flags); ++ bit_spin_lock(BH_Uptodate_Lock, &bh->b_state); ++#else ++ spin_lock_irqsave(&bh->b_uptodate_lock, flags); ++#endif ++ return flags; ++} ++ ++static inline void ++bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags) ++{ ++#ifndef CONFIG_PREEMPT_RT_BASE ++ bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state); ++ local_irq_restore(flags); ++#else ++ spin_unlock_irqrestore(&bh->b_uptodate_lock, flags); ++#endif ++} ++ ++static inline void buffer_head_init_locks(struct buffer_head *bh) ++{ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spin_lock_init(&bh->b_uptodate_lock); ++#if defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \ ++ defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE) ++ spin_lock_init(&bh->b_state_lock); ++ spin_lock_init(&bh->b_journal_head_lock); ++#endif ++#endif ++} ++ + /* + * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() + * and buffer_foo() functions. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/console.h sun8i-rt/include/linux/console.h +--- sun8i/include/linux/console.h 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/include/linux/console.h 2016-08-22 16:29:00.332217128 +0200 +@@ -135,6 +135,7 @@ struct console { + for (con = console_drivers; con != NULL; con = con->next) + + extern int console_set_on_cmdline; ++extern struct console *early_console; + + extern int add_preferred_console(char *name, int idx, char *options); + extern int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, char *options); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/cpu.h sun8i-rt/include/linux/cpu.h +--- sun8i/include/linux/cpu.h 2016-08-22 14:14:35.000000000 +0200 ++++ sun8i-rt/include/linux/cpu.h 2016-08-22 17:15:32.024249223 +0200 +@@ -177,6 +177,8 @@ extern struct bus_type cpu_subsys; + + extern void get_online_cpus(void); + extern void put_online_cpus(void); ++extern void pin_current_cpu(void); ++extern void unpin_current_cpu(void); + extern void cpu_hotplug_disable(void); + extern void cpu_hotplug_enable(void); + #define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri) +@@ -201,6 +203,8 @@ static inline void cpu_hotplug_driver_un + + #define get_online_cpus() do { } while (0) + #define put_online_cpus() do { } while (0) ++static inline void pin_current_cpu(void) { } ++static inline void unpin_current_cpu(void) { } + #define cpu_hotplug_disable() do { } while (0) + #define cpu_hotplug_enable() do { } while (0) + #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/delay.h sun8i-rt/include/linux/delay.h +--- sun8i/include/linux/delay.h 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/include/linux/delay.h 2016-08-22 18:17:17.304291822 +0200 +@@ -52,4 +52,10 @@ static inline void ssleep(unsigned int s + msleep(seconds * 1000); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void cpu_chill(void); ++#else ++# define cpu_chill() cpu_relax() ++#endif ++ + #endif /* defined(_LINUX_DELAY_H) */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/ftrace_event.h sun8i-rt/include/linux/ftrace_event.h +--- sun8i/include/linux/ftrace_event.h 2016-08-22 14:14:35.000000000 +0200 ++++ sun8i-rt/include/linux/ftrace_event.h 2016-08-22 17:17:23.372250504 +0200 +@@ -49,7 +49,8 @@ struct trace_entry { + unsigned char flags; + unsigned char preempt_count; + int pid; +- int padding; ++ unsigned short migrate_disable; ++ unsigned short padding; + }; + + #define FTRACE_MAX_EVENT \ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/ftrace.h sun8i-rt/include/linux/ftrace.h +--- sun8i/include/linux/ftrace.h 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/include/linux/ftrace.h 2016-08-22 18:28:44.868299727 +0200 +@@ -476,6 +476,18 @@ static inline void __ftrace_enabled_rest + # endif + #endif /* ifndef HAVE_ARCH_CALLER_ADDR */ + ++static inline unsigned long get_lock_parent_ip(void) ++{ ++ unsigned long addr = CALLER_ADDR0; ++ ++ if (!in_lock_functions(addr)) ++ return addr; ++ addr = CALLER_ADDR1; ++ if (!in_lock_functions(addr)) ++ return addr; ++ return CALLER_ADDR2; ++} ++ + #ifdef CONFIG_IRQSOFF_TRACER + extern void time_hardirqs_on(unsigned long a0, unsigned long a1); + extern void time_hardirqs_off(unsigned long a0, unsigned long a1); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/hardirq.h sun8i-rt/include/linux/hardirq.h +--- sun8i/include/linux/hardirq.h 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/include/linux/hardirq.h 2016-08-22 17:22:46.452254218 +0200 +@@ -60,7 +60,11 @@ + #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) + #define NMI_OFFSET (1UL << NMI_SHIFT) + +-#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) ++#else ++# define SOFTIRQ_DISABLE_OFFSET (0) ++#endif + + #ifndef PREEMPT_ACTIVE + #define PREEMPT_ACTIVE_BITS 1 +@@ -73,10 +77,17 @@ + #endif + + #define hardirq_count() (preempt_count() & HARDIRQ_MASK) +-#define softirq_count() (preempt_count() & SOFTIRQ_MASK) + #define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ + | NMI_MASK)) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define softirq_count() (preempt_count() & SOFTIRQ_MASK) ++# define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) ++#else ++# define softirq_count() (0UL) ++extern int in_serving_softirq(void); ++#endif ++ + /* + * Are we doing bottom half or hardware interrupt processing? + * Are we in a softirq context? Interrupt context? +@@ -86,7 +97,6 @@ + #define in_irq() (hardirq_count()) + #define in_softirq() (softirq_count()) + #define in_interrupt() (irq_count()) +-#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) + + /* + * Are we in NMI context? +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/hrtimer.h sun8i-rt/include/linux/hrtimer.h +--- sun8i/include/linux/hrtimer.h 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/include/linux/hrtimer.h 2016-08-22 17:59:43.240279704 +0200 +@@ -111,6 +111,11 @@ struct hrtimer { + enum hrtimer_restart (*function)(struct hrtimer *); + struct hrtimer_clock_base *base; + unsigned long state; ++ struct list_head cb_entry; ++ int irqsafe; ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ ktime_t praecox; ++#endif + #ifdef CONFIG_TIMER_STATS + int start_pid; + void *start_site; +@@ -147,6 +152,7 @@ struct hrtimer_clock_base { + int index; + clockid_t clockid; + struct timerqueue_head active; ++ struct list_head expired; + ktime_t resolution; + ktime_t (*get_time)(void); + ktime_t softirq_time; +@@ -189,6 +195,9 @@ struct hrtimer_cpu_base { + unsigned long nr_hangs; + ktime_t max_hang_time; + #endif ++#ifdef CONFIG_PREEMPT_RT_BASE ++ wait_queue_head_t wait; ++#endif + struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; + }; + +@@ -382,6 +391,13 @@ static inline int hrtimer_restart(struct + return hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + } + ++/* Softirq preemption could deadlock timer removal */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ extern void hrtimer_wait_for_timer(const struct hrtimer *timer); ++#else ++# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0) ++#endif ++ + /* Query timers: */ + extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); + extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/idr.h sun8i-rt/include/linux/idr.h +--- sun8i/include/linux/idr.h 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/include/linux/idr.h 2016-08-22 16:22:53.940212916 +0200 +@@ -136,7 +136,7 @@ struct ida { + struct ida_bitmap *free_bitmap; + }; + +-#define IDA_INIT(name) { .idr = IDR_INIT(name), .free_bitmap = NULL, } ++#define IDA_INIT(name) { .idr = IDR_INIT((name).idr), .free_bitmap = NULL, } + #define DEFINE_IDA(name) struct ida name = IDA_INIT(name) + + int ida_pre_get(struct ida *ida, gfp_t gfp_mask); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/init_task.h sun8i-rt/include/linux/init_task.h +--- sun8i/include/linux/init_task.h 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/include/linux/init_task.h 2016-08-22 17:11:27.068246407 +0200 +@@ -142,6 +142,12 @@ extern struct task_group root_task_group + # define INIT_PERF_EVENTS(tsk) + #endif + ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define INIT_TIMER_LIST .posix_timer_list = NULL, ++#else ++# define INIT_TIMER_LIST ++#endif ++ + #define INIT_TASK_COMM "swapper" + + /* +@@ -197,6 +203,7 @@ extern struct task_group root_task_group + .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ + .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ + .timer_slack_ns = 50000, /* 50 usec default slack */ \ ++ INIT_TIMER_LIST \ + .pids = { \ + [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \ + [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/interrupt.h sun8i-rt/include/linux/interrupt.h +--- sun8i/include/linux/interrupt.h 2016-08-22 14:14:16.000000000 +0200 ++++ sun8i-rt/include/linux/interrupt.h 2016-08-22 18:15:12.612290389 +0200 +@@ -59,6 +59,7 @@ + * IRQF_NO_THREAD - Interrupt cannot be threaded + * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device + * resume time. ++ * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT) + */ + #define IRQF_DISABLED 0x00000020 + #define IRQF_SAMPLE_RANDOM 0x00000040 +@@ -73,6 +74,7 @@ + #define IRQF_FORCE_RESUME 0x00008000 + #define IRQF_NO_THREAD 0x00010000 + #define IRQF_EARLY_RESUME 0x00020000 ++#define IRQF_NO_SOFTIRQ_CALL 0x00040000 + + #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) + +@@ -217,7 +219,7 @@ extern void devm_free_irq(struct device + #ifdef CONFIG_LOCKDEP + # define local_irq_enable_in_hardirq() do { } while (0) + #else +-# define local_irq_enable_in_hardirq() local_irq_enable() ++# define local_irq_enable_in_hardirq() local_irq_enable_nort() + #endif + + extern void disable_irq_nosync(unsigned int irq); +@@ -267,6 +269,7 @@ struct irq_affinity_notify { + unsigned int irq; + struct kref kref; + struct work_struct work; ++ struct list_head list; + void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask); + void (*release)(struct kref *ref); + }; +@@ -394,9 +397,13 @@ static inline int disable_irq_wake(unsig + + + #ifdef CONFIG_IRQ_FORCED_THREADING +-extern bool force_irqthreads; ++# ifndef CONFIG_PREEMPT_RT_BASE ++ extern bool force_irqthreads; ++# else ++# define force_irqthreads (true) ++# endif + #else +-#define force_irqthreads (0) ++#define force_irqthreads (false) + #endif + + #ifndef __ARCH_SET_SOFTIRQ_PENDING +@@ -450,8 +457,14 @@ struct softirq_action + void (*action)(struct softirq_action *); + }; + ++#ifndef CONFIG_PREEMPT_RT_FULL + asmlinkage void do_softirq(void); + asmlinkage void __do_softirq(void); ++static inline void thread_do_softirq(void) { do_softirq(); } ++#else ++extern void thread_do_softirq(void); ++#endif ++ + extern void open_softirq(int nr, void (*action)(struct softirq_action *)); + extern void softirq_init(void); + extern void __raise_softirq_irqoff(unsigned int nr); +@@ -459,6 +472,8 @@ extern void __raise_softirq_irqoff(unsig + extern void raise_softirq_irqoff(unsigned int nr); + extern void raise_softirq(unsigned int nr); + ++extern void softirq_check_pending_idle(void); ++ + /* This is the worklist that queues up per-cpu softirq work. + * + * send_remote_sendirq() adds work to these lists, and +@@ -499,8 +514,9 @@ extern void __send_remote_softirq(struct + to be executed on some cpu at least once after this. + * If the tasklet is already scheduled, but its execution is still not + started, it will be executed only once. +- * If this tasklet is already running on another CPU (or schedule is called +- from tasklet itself), it is rescheduled for later. ++ * If this tasklet is already running on another CPU, it is rescheduled ++ for later. ++ * Schedule must not be called from the tasklet itself (a lockup occurs) + * Tasklet is strictly serialized wrt itself, but not + wrt another tasklets. If client needs some intertask synchronization, + he makes it with spinlocks. +@@ -525,27 +541,36 @@ struct tasklet_struct name = { NULL, 0, + enum + { + TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */ +- TASKLET_STATE_RUN /* Tasklet is running (SMP only) */ ++ TASKLET_STATE_RUN, /* Tasklet is running (SMP only) */ ++ TASKLET_STATE_PENDING /* Tasklet is pending */ + }; + +-#ifdef CONFIG_SMP ++#define TASKLET_STATEF_SCHED (1 << TASKLET_STATE_SCHED) ++#define TASKLET_STATEF_RUN (1 << TASKLET_STATE_RUN) ++#define TASKLET_STATEF_PENDING (1 << TASKLET_STATE_PENDING) ++ ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + static inline int tasklet_trylock(struct tasklet_struct *t) + { + return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state); + } + ++static inline int tasklet_tryunlock(struct tasklet_struct *t) ++{ ++ return cmpxchg(&t->state, TASKLET_STATEF_RUN, 0) == TASKLET_STATEF_RUN; ++} ++ + static inline void tasklet_unlock(struct tasklet_struct *t) + { + smp_mb__before_clear_bit(); + clear_bit(TASKLET_STATE_RUN, &(t)->state); + } + +-static inline void tasklet_unlock_wait(struct tasklet_struct *t) +-{ +- while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); } +-} ++extern void tasklet_unlock_wait(struct tasklet_struct *t); ++ + #else + #define tasklet_trylock(t) 1 ++#define tasklet_tryunlock(t) 1 + #define tasklet_unlock_wait(t) do { } while (0) + #define tasklet_unlock(t) do { } while (0) + #endif +@@ -594,17 +619,8 @@ static inline void tasklet_disable(struc + smp_mb(); + } + +-static inline void tasklet_enable(struct tasklet_struct *t) +-{ +- smp_mb__before_atomic_dec(); +- atomic_dec(&t->count); +-} +- +-static inline void tasklet_hi_enable(struct tasklet_struct *t) +-{ +- smp_mb__before_atomic_dec(); +- atomic_dec(&t->count); +-} ++extern void tasklet_enable(struct tasklet_struct *t); ++extern void tasklet_hi_enable(struct tasklet_struct *t); + + extern void tasklet_kill(struct tasklet_struct *t); + extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); +@@ -636,6 +652,12 @@ void tasklet_hrtimer_cancel(struct taskl + tasklet_kill(&ttimer->tasklet); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void softirq_early_init(void); ++#else ++static inline void softirq_early_init(void) { } ++#endif ++ + /* + * Autoprobing for irqs: + * +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/irqdesc.h sun8i-rt/include/linux/irqdesc.h +--- sun8i/include/linux/irqdesc.h 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/include/linux/irqdesc.h 2016-08-22 18:01:43.184281083 +0200 +@@ -56,6 +56,7 @@ struct irq_desc { + unsigned int irqs_unhandled; + atomic_t threads_handled; + int threads_handled_last; ++ u64 random_ip; + raw_spinlock_t lock; + struct cpumask *percpu_enabled; + #ifdef CONFIG_SMP +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/irqflags.h sun8i-rt/include/linux/irqflags.h +--- sun8i/include/linux/irqflags.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/irqflags.h 2016-08-22 17:21:32.532253368 +0200 +@@ -25,8 +25,6 @@ + # define trace_softirqs_enabled(p) ((p)->softirqs_enabled) + # define trace_hardirq_enter() do { current->hardirq_context++; } while (0) + # define trace_hardirq_exit() do { current->hardirq_context--; } while (0) +-# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) +-# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) + # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1, + #else + # define trace_hardirqs_on() do { } while (0) +@@ -39,9 +37,15 @@ + # define trace_softirqs_enabled(p) 0 + # define trace_hardirq_enter() do { } while (0) + # define trace_hardirq_exit() do { } while (0) ++# define INIT_TRACE_IRQFLAGS ++#endif ++ ++#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL) ++# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) ++# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) ++#else + # define lockdep_softirq_enter() do { } while (0) + # define lockdep_softirq_exit() do { } while (0) +-# define INIT_TRACE_IRQFLAGS + #endif + + #if defined(CONFIG_IRQSOFF_TRACER) || \ +@@ -147,4 +151,23 @@ + + #endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */ + ++/* ++ * local_irq* variants depending on RT/!RT ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define local_irq_disable_nort() do { } while (0) ++# define local_irq_enable_nort() do { } while (0) ++# define local_irq_save_nort(flags) do { local_save_flags(flags); } while (0) ++# define local_irq_restore_nort(flags) do { (void)(flags); } while (0) ++# define local_irq_disable_rt() local_irq_disable() ++# define local_irq_enable_rt() local_irq_enable() ++#else ++# define local_irq_disable_nort() local_irq_disable() ++# define local_irq_enable_nort() local_irq_enable() ++# define local_irq_save_nort(flags) local_irq_save(flags) ++# define local_irq_restore_nort(flags) local_irq_restore(flags) ++# define local_irq_disable_rt() do { } while (0) ++# define local_irq_enable_rt() do { } while (0) ++#endif ++ + #endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/irq.h sun8i-rt/include/linux/irq.h +--- sun8i/include/linux/irq.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/irq.h 2016-08-22 17:24:03.564255105 +0200 +@@ -73,6 +73,7 @@ typedef void (*irq_preflow_handler_t)(st + * IRQ_MOVE_PCNTXT - Interrupt can be migrated from process context + * IRQ_NESTED_TRHEAD - Interrupt nests into another thread + * IRQ_PER_CPU_DEVID - Dev_id is a per-cpu variable ++ * IRQ_NO_SOFTIRQ_CALL - No softirq processing in the irq thread context (RT) + */ + enum { + IRQ_TYPE_NONE = 0x00000000, +@@ -97,12 +98,14 @@ enum { + IRQ_NESTED_THREAD = (1 << 15), + IRQ_NOTHREAD = (1 << 16), + IRQ_PER_CPU_DEVID = (1 << 17), ++ IRQ_NO_SOFTIRQ_CALL = (1 << 18), + }; + + #define IRQF_MODIFY_MASK \ + (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ + IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ +- IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID) ++ IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ ++ IRQ_NO_SOFTIRQ_CALL) + + #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/jbd_common.h sun8i-rt/include/linux/jbd_common.h +--- sun8i/include/linux/jbd_common.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/jbd_common.h 2016-08-22 16:34:07.440220659 +0200 +@@ -37,32 +37,56 @@ static inline struct journal_head *bh2jh + + static inline void jbd_lock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(BH_State, &bh->b_state); ++#else ++ spin_lock(&bh->b_state_lock); ++#endif + } + + static inline int jbd_trylock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + return bit_spin_trylock(BH_State, &bh->b_state); ++#else ++ return spin_trylock(&bh->b_state_lock); ++#endif + } + + static inline int jbd_is_locked_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + return bit_spin_is_locked(BH_State, &bh->b_state); ++#else ++ return spin_is_locked(&bh->b_state_lock); ++#endif + } + + static inline void jbd_unlock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_State, &bh->b_state); ++#else ++ spin_unlock(&bh->b_state_lock); ++#endif + } + + static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(BH_JournalHead, &bh->b_state); ++#else ++ spin_lock(&bh->b_journal_head_lock); ++#endif + } + + static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_JournalHead, &bh->b_state); ++#else ++ spin_unlock(&bh->b_journal_head_lock); ++#endif + } + + #endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/jump_label.h sun8i-rt/include/linux/jump_label.h +--- sun8i/include/linux/jump_label.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/jump_label.h 2016-08-22 17:43:03.892268215 +0200 +@@ -51,7 +51,8 @@ + #include + #include + +-#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) ++#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) && \ ++ !defined(CONFIG_PREEMPT_BASE) + + struct static_key { + atomic_t enabled; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/kdb.h sun8i-rt/include/linux/kdb.h +--- sun8i/include/linux/kdb.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/kdb.h 2016-08-22 17:48:05.632271684 +0200 +@@ -150,12 +150,14 @@ extern int kdb_register(char *, kdb_func + extern int kdb_register_repeat(char *, kdb_func_t, char *, char *, + short, kdb_repeat_t); + extern int kdb_unregister(char *); ++#define in_kdb_printk() (kdb_trap_printk) + #else /* ! CONFIG_KGDB_KDB */ + #define kdb_printf(...) + #define kdb_init(x) + #define kdb_register(...) + #define kdb_register_repeat(...) + #define kdb_uregister(x) ++#define in_kdb_printk() (0) + #endif /* CONFIG_KGDB_KDB */ + enum { + KDB_NOT_INITIALIZED, +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/kernel.h sun8i-rt/include/linux/kernel.h +--- sun8i/include/linux/kernel.h 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/include/linux/kernel.h 2016-08-22 16:17:41.052209318 +0200 +@@ -375,7 +375,7 @@ extern enum system_states { + SYSTEM_HALT, + SYSTEM_POWER_OFF, + SYSTEM_RESTART, +- SYSTEM_SUSPEND_DISK, ++ SYSTEM_SUSPEND, + } system_state; + + #define TAINT_PROPRIETARY_MODULE 0 +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/lglock.h sun8i-rt/include/linux/lglock.h +--- sun8i/include/linux/lglock.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/lglock.h 2016-08-22 17:51:25.032273976 +0200 +@@ -71,6 +71,8 @@ + extern void name##_global_lock_online(void); \ + extern void name##_global_unlock_online(void); \ + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #define DEFINE_LGLOCK(name) \ + \ + DEFINE_SPINLOCK(name##_cpu_lock); \ +@@ -197,4 +199,130 @@ + preempt_enable(); \ + } \ + EXPORT_SYMBOL(name##_global_unlock); ++ ++#else /* !PREEMPT_RT_FULL */ ++#define DEFINE_LGLOCK(name) \ ++ \ ++ DEFINE_PER_CPU(struct rt_mutex, name##_lock); \ ++ DEFINE_SPINLOCK(name##_cpu_lock); \ ++ cpumask_t name##_cpus __read_mostly; \ ++ DEFINE_LGLOCK_LOCKDEP(name); \ ++ \ ++ static int \ ++ name##_lg_cpu_callback(struct notifier_block *nb, \ ++ unsigned long action, void *hcpu) \ ++ { \ ++ switch (action & ~CPU_TASKS_FROZEN) { \ ++ case CPU_UP_PREPARE: \ ++ spin_lock(&name##_cpu_lock); \ ++ cpu_set((unsigned long)hcpu, name##_cpus); \ ++ spin_unlock(&name##_cpu_lock); \ ++ break; \ ++ case CPU_UP_CANCELED: case CPU_DEAD: \ ++ spin_lock(&name##_cpu_lock); \ ++ cpu_clear((unsigned long)hcpu, name##_cpus); \ ++ spin_unlock(&name##_cpu_lock); \ ++ } \ ++ return NOTIFY_OK; \ ++ } \ ++ static struct notifier_block name##_lg_cpu_notifier = { \ ++ .notifier_call = name##_lg_cpu_callback, \ ++ }; \ ++ void name##_lock_init(void) { \ ++ int i; \ ++ LOCKDEP_INIT_MAP(&name##_lock_dep_map, #name, &name##_lock_key, 0); \ ++ for_each_possible_cpu(i) { \ ++ struct rt_mutex *lock; \ ++ lock = &per_cpu(name##_lock, i); \ ++ rt_mutex_init(lock); \ ++ } \ ++ register_hotcpu_notifier(&name##_lg_cpu_notifier); \ ++ get_online_cpus(); \ ++ for_each_online_cpu(i) \ ++ cpu_set(i, name##_cpus); \ ++ put_online_cpus(); \ ++ } \ ++ EXPORT_SYMBOL(name##_lock_init); \ ++ \ ++ void name##_local_lock(void) { \ ++ struct rt_mutex *lock; \ ++ migrate_disable(); \ ++ rwlock_acquire_read(&name##_lock_dep_map, 0, 0, _THIS_IP_); \ ++ lock = &__get_cpu_var(name##_lock); \ ++ __rt_spin_lock(lock); \ ++ } \ ++ EXPORT_SYMBOL(name##_local_lock); \ ++ \ ++ void name##_local_unlock(void) { \ ++ struct rt_mutex *lock; \ ++ rwlock_release(&name##_lock_dep_map, 1, _THIS_IP_); \ ++ lock = &__get_cpu_var(name##_lock); \ ++ __rt_spin_unlock(lock); \ ++ migrate_enable(); \ ++ } \ ++ EXPORT_SYMBOL(name##_local_unlock); \ ++ \ ++ void name##_local_lock_cpu(int cpu) { \ ++ struct rt_mutex *lock; \ ++ rwlock_acquire_read(&name##_lock_dep_map, 0, 0, _THIS_IP_); \ ++ lock = &per_cpu(name##_lock, cpu); \ ++ __rt_spin_lock(lock); \ ++ } \ ++ EXPORT_SYMBOL(name##_local_lock_cpu); \ ++ \ ++ void name##_local_unlock_cpu(int cpu) { \ ++ struct rt_mutex *lock; \ ++ rwlock_release(&name##_lock_dep_map, 1, _THIS_IP_); \ ++ lock = &per_cpu(name##_lock, cpu); \ ++ __rt_spin_unlock(lock); \ ++ } \ ++ EXPORT_SYMBOL(name##_local_unlock_cpu); \ ++ \ ++ void name##_global_lock_online(void) { \ ++ int i; \ ++ rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \ ++ spin_lock(&name##_cpu_lock); \ ++ for_each_cpu(i, &name##_cpus) { \ ++ struct rt_mutex *lock; \ ++ lock = &per_cpu(name##_lock, i); \ ++ __rt_spin_lock(lock); \ ++ } \ ++ } \ ++ EXPORT_SYMBOL(name##_global_lock_online); \ ++ \ ++ void name##_global_unlock_online(void) { \ ++ int i; \ ++ rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \ ++ for_each_cpu(i, &name##_cpus) { \ ++ struct rt_mutex *lock; \ ++ lock = &per_cpu(name##_lock, i); \ ++ __rt_spin_unlock(lock); \ ++ } \ ++ spin_unlock(&name##_cpu_lock); \ ++ } \ ++ EXPORT_SYMBOL(name##_global_unlock_online); \ ++ \ ++ void name##_global_lock(void) { \ ++ int i; \ ++ rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \ ++ for_each_possible_cpu(i) { \ ++ struct rt_mutex *lock; \ ++ lock = &per_cpu(name##_lock, i); \ ++ __rt_spin_lock(lock); \ ++ } \ ++ } \ ++ EXPORT_SYMBOL(name##_global_lock); \ ++ \ ++ void name##_global_unlock(void) { \ ++ int i; \ ++ rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \ ++ for_each_possible_cpu(i) { \ ++ struct rt_mutex *lock; \ ++ lock = &per_cpu(name##_lock, i); \ ++ __rt_spin_unlock(lock); \ ++ } \ ++ } \ ++ EXPORT_SYMBOL(name##_global_unlock); ++#endif /* PRREMPT_RT_FULL */ ++ + #endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/list_bl.h sun8i-rt/include/linux/list_bl.h +--- sun8i/include/linux/list_bl.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/list_bl.h 2016-08-22 18:13:04.784288919 +0200 +@@ -2,6 +2,7 @@ + #define _LINUX_LIST_BL_H + + #include ++#include + #include + + /* +@@ -32,13 +33,22 @@ + + struct hlist_bl_head { + struct hlist_bl_node *first; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ raw_spinlock_t lock; ++#endif + }; + + struct hlist_bl_node { + struct hlist_bl_node *next, **pprev; + }; +-#define INIT_HLIST_BL_HEAD(ptr) \ +- ((ptr)->first = NULL) ++ ++static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h) ++{ ++ h->first = NULL; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ raw_spin_lock_init(&h->lock); ++#endif ++} + + static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) + { +@@ -117,12 +127,26 @@ static inline void hlist_bl_del_init(str + + static inline void hlist_bl_lock(struct hlist_bl_head *b) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(0, (unsigned long *)b); ++#else ++ raw_spin_lock(&b->lock); ++#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) ++ __set_bit(0, (unsigned long *)b); ++#endif ++#endif + } + + static inline void hlist_bl_unlock(struct hlist_bl_head *b) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + __bit_spin_unlock(0, (unsigned long *)b); ++#else ++#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) ++ __clear_bit(0, (unsigned long *)b); ++#endif ++ raw_spin_unlock(&b->lock); ++#endif + } + + /** +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/list.h sun8i-rt/include/linux/list.h +--- sun8i/include/linux/list.h 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/include/linux/list.h 2016-08-22 16:18:26.860209845 +0200 +@@ -362,6 +362,17 @@ static inline void list_splice_tail_init + list_entry((ptr)->next, type, member) + + /** ++ * list_last_entry - get the last element from a list ++ * @ptr: the list head to take the element from. ++ * @type: the type of the struct this is embedded in. ++ * @member: the name of the list_struct within the struct. ++ * ++ * Note, that list is expected to be not empty. ++ */ ++#define list_last_entry(ptr, type, member) \ ++ list_entry((ptr)->prev, type, member) ++ ++/** + * list_next_entry - get the next element in list + * @pos: the type * to cursor + * @member: the name of the list_struct within the struct. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/locallock.h sun8i-rt/include/linux/locallock.h +--- sun8i/include/linux/locallock.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/linux/locallock.h 2016-08-22 18:04:05.304282717 +0200 +@@ -0,0 +1,253 @@ ++#ifndef _LINUX_LOCALLOCK_H ++#define _LINUX_LOCALLOCK_H ++ ++#include ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ ++#ifdef CONFIG_DEBUG_SPINLOCK ++# define LL_WARN(cond) WARN_ON(cond) ++#else ++# define LL_WARN(cond) do { } while (0) ++#endif ++ ++/* ++ * per cpu lock based substitute for local_irq_*() ++ */ ++struct local_irq_lock { ++ spinlock_t lock; ++ struct task_struct *owner; ++ int nestcnt; ++ unsigned long flags; ++}; ++ ++#define DEFINE_LOCAL_IRQ_LOCK(lvar) \ ++ DEFINE_PER_CPU(struct local_irq_lock, lvar) = { \ ++ .lock = __SPIN_LOCK_UNLOCKED((lvar).lock) } ++ ++#define DECLARE_LOCAL_IRQ_LOCK(lvar) \ ++ DECLARE_PER_CPU(struct local_irq_lock, lvar) ++ ++#define local_irq_lock_init(lvar) \ ++ do { \ ++ int __cpu; \ ++ for_each_possible_cpu(__cpu) \ ++ spin_lock_init(&per_cpu(lvar, __cpu).lock); \ ++ } while (0) ++ ++static inline void __local_lock(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current) { ++ spin_lock(&lv->lock); ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ } ++ lv->nestcnt++; ++} ++ ++#define local_lock(lvar) \ ++ do { __local_lock(&get_local_var(lvar)); } while (0) ++ ++static inline int __local_trylock(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current && spin_trylock(&lv->lock)) { ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ lv->nestcnt = 1; ++ return 1; ++ } ++ return 0; ++} ++ ++#define local_trylock(lvar) \ ++ ({ \ ++ int __locked; \ ++ __locked = __local_trylock(&get_local_var(lvar)); \ ++ if (!__locked) \ ++ put_local_var(lvar); \ ++ __locked; \ ++ }) ++ ++static inline void __local_unlock(struct local_irq_lock *lv) ++{ ++ LL_WARN(lv->nestcnt == 0); ++ LL_WARN(lv->owner != current); ++ if (--lv->nestcnt) ++ return; ++ ++ lv->owner = NULL; ++ spin_unlock(&lv->lock); ++} ++ ++#define local_unlock(lvar) \ ++ do { \ ++ __local_unlock(&__get_cpu_var(lvar)); \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++static inline void __local_lock_irq(struct local_irq_lock *lv) ++{ ++ spin_lock_irqsave(&lv->lock, lv->flags); ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ lv->nestcnt = 1; ++} ++ ++#define local_lock_irq(lvar) \ ++ do { __local_lock_irq(&get_local_var(lvar)); } while (0) ++ ++#define local_lock_irq_on(lvar, cpu) \ ++ do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0) ++ ++static inline void __local_unlock_irq(struct local_irq_lock *lv) ++{ ++ LL_WARN(!lv->nestcnt); ++ LL_WARN(lv->owner != current); ++ lv->owner = NULL; ++ lv->nestcnt = 0; ++ spin_unlock_irq(&lv->lock); ++} ++ ++#define local_unlock_irq(lvar) \ ++ do { \ ++ __local_unlock_irq(&__get_cpu_var(lvar)); \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_irq_on(lvar, cpu) \ ++ do { \ ++ __local_unlock_irq(&per_cpu(lvar, cpu)); \ ++ } while (0) ++ ++static inline int __local_lock_irqsave(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current) { ++ __local_lock_irq(lv); ++ return 0; ++ } else { ++ lv->nestcnt++; ++ return 1; ++ } ++} ++ ++#define local_lock_irqsave(lvar, _flags) \ ++ do { \ ++ if (__local_lock_irqsave(&get_local_var(lvar))) \ ++ put_local_var(lvar); \ ++ _flags = __get_cpu_var(lvar).flags; \ ++ } while (0) ++ ++#define local_lock_irqsave_on(lvar, _flags, cpu) \ ++ do { \ ++ __local_lock_irqsave(&per_cpu(lvar, cpu)); \ ++ _flags = per_cpu(lvar, cpu).flags; \ ++ } while (0) ++ ++static inline int __local_unlock_irqrestore(struct local_irq_lock *lv, ++ unsigned long flags) ++{ ++ LL_WARN(!lv->nestcnt); ++ LL_WARN(lv->owner != current); ++ if (--lv->nestcnt) ++ return 0; ++ ++ lv->owner = NULL; ++ spin_unlock_irqrestore(&lv->lock, lv->flags); ++ return 1; ++} ++ ++#define local_unlock_irqrestore(lvar, flags) \ ++ do { \ ++ if (__local_unlock_irqrestore(&__get_cpu_var(lvar), flags)) \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_irqrestore_on(lvar, flags, cpu) \ ++ do { \ ++ __local_unlock_irqrestore(&per_cpu(lvar, cpu), flags); \ ++ } while (0) ++ ++#define local_spin_trylock_irq(lvar, lock) \ ++ ({ \ ++ int __locked; \ ++ local_lock_irq(lvar); \ ++ __locked = spin_trylock(lock); \ ++ if (!__locked) \ ++ local_unlock_irq(lvar); \ ++ __locked; \ ++ }) ++ ++#define local_spin_lock_irq(lvar, lock) \ ++ do { \ ++ local_lock_irq(lvar); \ ++ spin_lock(lock); \ ++ } while (0) ++ ++#define local_spin_unlock_irq(lvar, lock) \ ++ do { \ ++ spin_unlock(lock); \ ++ local_unlock_irq(lvar); \ ++ } while (0) ++ ++#define local_spin_lock_irqsave(lvar, lock, flags) \ ++ do { \ ++ local_lock_irqsave(lvar, flags); \ ++ spin_lock(lock); \ ++ } while (0) ++ ++#define local_spin_unlock_irqrestore(lvar, lock, flags) \ ++ do { \ ++ spin_unlock(lock); \ ++ local_unlock_irqrestore(lvar, flags); \ ++ } while (0) ++ ++#define get_locked_var(lvar, var) \ ++ (*({ \ ++ local_lock(lvar); \ ++ &__get_cpu_var(var); \ ++ })) ++ ++#define put_locked_var(lvar, var) local_unlock(lvar) ++ ++#define local_lock_cpu(lvar) \ ++ ({ \ ++ local_lock(lvar); \ ++ smp_processor_id(); \ ++ }) ++ ++#define local_unlock_cpu(lvar) local_unlock(lvar) ++ ++#else /* PREEMPT_RT_BASE */ ++ ++#define DEFINE_LOCAL_IRQ_LOCK(lvar) __typeof__(const int) lvar ++#define DECLARE_LOCAL_IRQ_LOCK(lvar) extern __typeof__(const int) lvar ++ ++static inline void local_irq_lock_init(int lvar) { } ++ ++#define local_lock(lvar) preempt_disable() ++#define local_unlock(lvar) preempt_enable() ++#define local_lock_irq(lvar) local_irq_disable() ++#define local_unlock_irq(lvar) local_irq_enable() ++#define local_lock_irqsave(lvar, flags) local_irq_save(flags) ++#define local_unlock_irqrestore(lvar, flags) local_irq_restore(flags) ++ ++#define local_spin_trylock_irq(lvar, lock) spin_trylock_irq(lock) ++#define local_spin_lock_irq(lvar, lock) spin_lock_irq(lock) ++#define local_spin_unlock_irq(lvar, lock) spin_unlock_irq(lock) ++#define local_spin_lock_irqsave(lvar, lock, flags) \ ++ spin_lock_irqsave(lock, flags) ++#define local_spin_unlock_irqrestore(lvar, lock, flags) \ ++ spin_unlock_irqrestore(lock, flags) ++ ++#define get_locked_var(lvar, var) get_cpu_var(var) ++#define put_locked_var(lvar, var) put_cpu_var(var) ++ ++#define local_lock_cpu(lvar) get_cpu() ++#define local_unlock_cpu(lvar) put_cpu() ++ ++#endif ++ ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/mm.h sun8i-rt/include/linux/mm.h +--- sun8i/include/linux/mm.h 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/include/linux/mm.h 2016-08-22 17:06:07.200242730 +0200 +@@ -1216,27 +1216,59 @@ static inline pmd_t *pmd_alloc(struct mm + * overflow into the next struct page (as it might with DEBUG_SPINLOCK). + * When freeing, reset page->mapping so free_pages_check won't complain. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #define __pte_lockptr(page) &((page)->ptl) +-#define pte_lock_init(_page) do { \ +- spin_lock_init(__pte_lockptr(_page)); \ +-} while (0) ++ ++static inline struct page *pte_lock_init(struct page *page) ++{ ++ spin_lock_init(__pte_lockptr(page)); ++ return page; ++} ++ + #define pte_lock_deinit(page) ((page)->mapping = NULL) ++ ++#else /* !PREEMPT_RT_FULL */ ++ ++/* ++ * On PREEMPT_RT_FULL the spinlock_t's are too large to embed in the ++ * page frame, hence it only has a pointer and we need to dynamically ++ * allocate the lock when we allocate PTE-pages. ++ * ++ * This is an overall win, since only a small fraction of the pages ++ * will be PTE pages under normal circumstances. ++ */ ++ ++#define __pte_lockptr(page) ((page)->ptl) ++ ++extern struct page *pte_lock_init(struct page *page); ++extern void pte_lock_deinit(struct page *page); ++ ++#endif /* PREEMPT_RT_FULL */ ++ + #define pte_lockptr(mm, pmd) ({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));}) + #else /* !USE_SPLIT_PTLOCKS */ + /* + * We use mm->page_table_lock to guard all pagetable pages of the mm. + */ +-#define pte_lock_init(page) do {} while (0) ++static inline struct page *pte_lock_init(struct page *page) { return page; } + #define pte_lock_deinit(page) do {} while (0) + #define pte_lockptr(mm, pmd) ({(void)(pmd); &(mm)->page_table_lock;}) + #endif /* USE_SPLIT_PTLOCKS */ + +-static inline void pgtable_page_ctor(struct page *page) ++static inline struct page *__pgtable_page_ctor(struct page *page) + { +- pte_lock_init(page); +- inc_zone_page_state(page, NR_PAGETABLE); ++ page = pte_lock_init(page); ++ if (page) ++ inc_zone_page_state(page, NR_PAGETABLE); ++ return page; + } + ++#define pgtable_page_ctor(page) \ ++do { \ ++ page = __pgtable_page_ctor(page); \ ++} while (0) ++ + static inline void pgtable_page_dtor(struct page *page) + { + pte_lock_deinit(page); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/mm_types.h sun8i-rt/include/linux/mm_types.h +--- sun8i/include/linux/mm_types.h 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/include/linux/mm_types.h 2016-08-22 17:12:39.840247244 +0200 +@@ -12,6 +12,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -128,7 +129,11 @@ struct page { + * system if PG_buddy is set. + */ + #if USE_SPLIT_PTLOCKS +- spinlock_t ptl; ++# ifndef CONFIG_PREEMPT_RT_FULL ++ spinlock_t ptl; ++# else ++ spinlock_t *ptl; ++# endif + #endif + struct kmem_cache *slab; /* SLUB: Pointer to slab */ + struct page *first_page; /* Compound tail pages */ +@@ -399,6 +404,9 @@ struct mm_struct { + #ifdef CONFIG_CPUMASK_OFFSTACK + struct cpumask cpumask_allocation; + #endif ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct rcu_head delayed_drop; ++#endif + }; + + static inline void mm_init_cpumask(struct mm_struct *mm) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/mutex.h sun8i-rt/include/linux/mutex.h +--- sun8i/include/linux/mutex.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/mutex.h 2016-08-22 17:33:30.488261622 +0200 +@@ -17,6 +17,17 @@ + + #include + ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ ++ , .dep_map = { .name = #lockname } ++#else ++# define __DEP_MAP_MUTEX_INITIALIZER(lockname) ++#endif ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include ++#else ++ + /* + * Simple, straightforward mutexes with strict semantics: + * +@@ -95,13 +106,6 @@ do { \ + static inline void mutex_destroy(struct mutex *lock) {} + #endif + +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ +- , .dep_map = { .name = #lockname } +-#else +-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) +-#endif +- + #define __MUTEX_INITIALIZER(lockname) \ + { .count = ATOMIC_INIT(1) \ + , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ +@@ -167,6 +171,9 @@ extern int __must_check mutex_lock_killa + */ + extern int mutex_trylock(struct mutex *lock); + extern void mutex_unlock(struct mutex *lock); ++ ++#endif /* !PREEMPT_RT_FULL */ ++ + extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); + + #ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/mutex_rt.h sun8i-rt/include/linux/mutex_rt.h +--- sun8i/include/linux/mutex_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/linux/mutex_rt.h 2016-08-22 17:33:30.488261622 +0200 +@@ -0,0 +1,84 @@ ++#ifndef __LINUX_MUTEX_RT_H ++#define __LINUX_MUTEX_RT_H ++ ++#ifndef __LINUX_MUTEX_H ++#error "Please include mutex.h" ++#endif ++ ++#include ++ ++/* FIXME: Just for __lockfunc */ ++#include ++ ++struct mutex { ++ struct rt_mutex lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++}; ++ ++#define __MUTEX_INITIALIZER(mutexname) \ ++ { \ ++ .lock = __RT_MUTEX_INITIALIZER(mutexname.lock) \ ++ __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ ++ } ++ ++#define DEFINE_MUTEX(mutexname) \ ++ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) ++ ++extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key); ++extern void __lockfunc _mutex_lock(struct mutex *lock); ++extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock); ++extern int __lockfunc _mutex_lock_killable(struct mutex *lock); ++extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass); ++extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock); ++extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass); ++extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass); ++extern int __lockfunc _mutex_trylock(struct mutex *lock); ++extern void __lockfunc _mutex_unlock(struct mutex *lock); ++ ++#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->lock) ++#define mutex_lock(l) _mutex_lock(l) ++#define mutex_lock_interruptible(l) _mutex_lock_interruptible(l) ++#define mutex_lock_killable(l) _mutex_lock_killable(l) ++#define mutex_trylock(l) _mutex_trylock(l) ++#define mutex_unlock(l) _mutex_unlock(l) ++#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock) ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define mutex_lock_nested(l, s) _mutex_lock_nested(l, s) ++# define mutex_lock_interruptible_nested(l, s) \ ++ _mutex_lock_interruptible_nested(l, s) ++# define mutex_lock_killable_nested(l, s) \ ++ _mutex_lock_killable_nested(l, s) ++ ++# define mutex_lock_nest_lock(lock, nest_lock) \ ++do { \ ++ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ ++ _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ ++} while (0) ++ ++#else ++# define mutex_lock_nested(l, s) _mutex_lock(l) ++# define mutex_lock_interruptible_nested(l, s) \ ++ _mutex_lock_interruptible(l) ++# define mutex_lock_killable_nested(l, s) \ ++ _mutex_lock_killable(l) ++# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) ++#endif ++ ++# define mutex_init(mutex) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(mutex)->lock); \ ++ __mutex_do_init((mutex), #mutex, &__key); \ ++} while (0) ++ ++# define __mutex_init(mutex, name, key) \ ++do { \ ++ rt_mutex_init(&(mutex)->lock); \ ++ __mutex_do_init((mutex), name, key); \ ++} while (0) ++ ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/netdevice.h sun8i-rt/include/linux/netdevice.h +--- sun8i/include/linux/netdevice.h 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/include/linux/netdevice.h 2016-08-22 18:16:56.648291585 +0200 +@@ -1109,7 +1109,7 @@ struct net_device { + unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */ + unsigned char addr_assign_type; /* hw address assignment type */ + unsigned char addr_len; /* hardware address length */ +- unsigned char neigh_priv_len; ++ unsigned short neigh_priv_len; + unsigned short dev_id; /* for shared network cards */ + + spinlock_t addr_list_lock; +@@ -1747,6 +1747,7 @@ struct softnet_data { + unsigned dropped; + struct sk_buff_head input_pkt_queue; + struct napi_struct backlog; ++ struct sk_buff_head tofree_queue; + }; + + static inline void input_queue_head_incr(struct softnet_data *sd) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/netfilter/x_tables.h sun8i-rt/include/linux/netfilter/x_tables.h +--- sun8i/include/linux/netfilter/x_tables.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/netfilter/x_tables.h 2016-08-22 18:04:05.304282717 +0200 +@@ -186,6 +186,7 @@ struct xt_counters_info { + #ifdef __KERNEL__ + + #include ++#include + + /** + * struct xt_action_param - parameters for matches/targets +@@ -466,6 +467,8 @@ extern void xt_free_table_info(struct xt + */ + DECLARE_PER_CPU(seqcount_t, xt_recseq); + ++DECLARE_LOCAL_IRQ_LOCK(xt_write_lock); ++ + /** + * xt_write_recseq_begin - start of a write section + * +@@ -480,6 +483,9 @@ static inline unsigned int xt_write_recs + { + unsigned int addend; + ++ /* RT protection */ ++ local_lock(xt_write_lock); ++ + /* + * Low order bit of sequence is set if we already + * called xt_write_recseq_begin(). +@@ -510,6 +516,7 @@ static inline void xt_write_recseq_end(u + /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ + smp_wmb(); + __this_cpu_add(xt_recseq.sequence, addend); ++ local_unlock(xt_write_lock); + } + + /* +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/of.h sun8i-rt/include/linux/of.h +--- sun8i/include/linux/of.h 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/include/linux/of.h 2016-08-22 16:18:11.100209664 +0200 +@@ -90,7 +90,7 @@ static inline void of_node_put(struct de + extern struct device_node *allnodes; + extern struct device_node *of_chosen; + extern struct device_node *of_aliases; +-extern rwlock_t devtree_lock; ++extern raw_spinlock_t devtree_lock; + + static inline bool of_have_populated_dt(void) + { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/page_cgroup.h sun8i-rt/include/linux/page_cgroup.h +--- sun8i/include/linux/page_cgroup.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/page_cgroup.h 2016-08-22 16:33:41.596220362 +0200 +@@ -24,6 +24,9 @@ enum { + */ + struct page_cgroup { + unsigned long flags; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spinlock_t pcg_lock; ++#endif + struct mem_cgroup *mem_cgroup; + }; + +@@ -74,12 +77,20 @@ static inline void lock_page_cgroup(stru + * Don't take this lock in IRQ context. + * This lock is for pc->mem_cgroup, USED, MIGRATION + */ ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(PCG_LOCK, &pc->flags); ++#else ++ spin_lock(&pc->pcg_lock); ++#endif + } + + static inline void unlock_page_cgroup(struct page_cgroup *pc) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(PCG_LOCK, &pc->flags); ++#else ++ spin_unlock(&pc->pcg_lock); ++#endif + } + + #else /* CONFIG_CGROUP_MEM_RES_CTLR */ +@@ -102,6 +113,10 @@ static inline void __init page_cgroup_in + { + } + ++static inline void page_cgroup_lock_init(struct page_cgroup *pc) ++{ ++} ++ + #endif /* CONFIG_CGROUP_MEM_RES_CTLR */ + + #include +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/percpu.h sun8i-rt/include/linux/percpu.h +--- sun8i/include/linux/percpu.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/percpu.h 2016-08-22 17:24:19.400255287 +0200 +@@ -48,6 +48,31 @@ + preempt_enable(); \ + } while (0) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define get_local_var(var) get_cpu_var(var) ++# define put_local_var(var) put_cpu_var(var) ++# define get_local_ptr(var) get_cpu_ptr(var) ++# define put_local_ptr(var) put_cpu_ptr(var) ++#else ++# define get_local_var(var) (*({ \ ++ migrate_disable(); \ ++ &__get_cpu_var(var); })) ++ ++# define put_local_var(var) do { \ ++ (void)&(var); \ ++ migrate_enable(); \ ++} while (0) ++ ++# define get_local_ptr(var) ({ \ ++ migrate_disable(); \ ++ this_cpu_ptr(var); }) ++ ++# define put_local_ptr(var) do { \ ++ (void)(var); \ ++ migrate_enable(); \ ++} while (0) ++#endif ++ + /* minimum unit size, also is the maximum supported allocation size */ + #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/pid.h sun8i-rt/include/linux/pid.h +--- sun8i/include/linux/pid.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/pid.h 2016-08-22 16:21:16.228211792 +0200 +@@ -2,6 +2,7 @@ + #define _LINUX_PID_H + + #include ++#include + + enum pid_type + { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/preempt.h sun8i-rt/include/linux/preempt.h +--- sun8i/include/linux/preempt.h 2016-08-22 14:14:34.000000000 +0200 ++++ sun8i-rt/include/linux/preempt.h 2016-08-22 17:51:53.960274309 +0200 +@@ -54,11 +54,17 @@ do { \ + dec_preempt_count(); \ + } while (0) + +-#define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++#ifndef CONFIG_PREEMPT_RT_BASE ++# define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++# define preempt_check_resched_rt() do { } while (0) ++#else ++# define preempt_enable_no_resched() preempt_enable() ++# define preempt_check_resched_rt() preempt_check_resched() ++#endif + + #define preempt_enable() \ + do { \ +- preempt_enable_no_resched(); \ ++ sched_preempt_enable_no_resched(); \ + barrier(); \ + preempt_check_resched(); \ + } while (0) +@@ -107,9 +113,31 @@ do { \ + #define preempt_disable_notrace() barrier() + #define preempt_enable_no_resched_notrace() barrier() + #define preempt_enable_notrace() barrier() ++#define preempt_check_resched_rt() barrier() + + #endif /* CONFIG_PREEMPT_COUNT */ + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define preempt_disable_rt() preempt_disable() ++# define preempt_enable_rt() preempt_enable() ++# define preempt_disable_nort() do { } while (0) ++# define preempt_enable_nort() do { } while (0) ++# ifdef CONFIG_SMP ++ extern void migrate_disable(void); ++ extern void migrate_enable(void); ++# else /* CONFIG_SMP */ ++# define migrate_disable() do { } while (0) ++# define migrate_enable() do { } while (0) ++# endif /* CONFIG_SMP */ ++#else ++# define preempt_disable_rt() do { } while (0) ++# define preempt_enable_rt() do { } while (0) ++# define preempt_disable_nort() preempt_disable() ++# define preempt_enable_nort() preempt_enable() ++# define migrate_disable() preempt_disable() ++# define migrate_enable() preempt_enable() ++#endif ++ + #ifdef CONFIG_PREEMPT_NOTIFIERS + + struct preempt_notifier; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/printk.h sun8i-rt/include/linux/printk.h +--- sun8i/include/linux/printk.h 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/include/linux/printk.h 2016-08-22 16:29:27.592217441 +0200 +@@ -88,8 +88,15 @@ int no_printk(const char *fmt, ...) + return 0; + } + ++#ifdef CONFIG_EARLY_PRINTK + extern asmlinkage __printf(1, 2) + void early_printk(const char *fmt, ...); ++extern void printk_kill(void); ++#else ++static inline __printf(1, 2) __cold ++void early_printk(const char *s, ...) { } ++static inline void printk_kill(void) { } ++#endif + + extern int printk_needs_cpu(int cpu); + extern void printk_tick(void); +@@ -114,7 +121,6 @@ extern int __printk_ratelimit(const char + #define printk_ratelimit() __printk_ratelimit(__func__) + extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, + unsigned int interval_msec); +- + extern int printk_delay_msec; + extern int dmesg_restrict; + extern int kptr_restrict; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/radix-tree.h sun8i-rt/include/linux/radix-tree.h +--- sun8i/include/linux/radix-tree.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/radix-tree.h 2016-08-22 17:06:52.672243253 +0200 +@@ -230,7 +230,13 @@ unsigned long radix_tree_next_hole(struc + unsigned long index, unsigned long max_scan); + unsigned long radix_tree_prev_hole(struct radix_tree_root *root, + unsigned long index, unsigned long max_scan); ++ ++#ifndef CONFIG_PREEMPT_RT_FULL + int radix_tree_preload(gfp_t gfp_mask); ++#else ++static inline int radix_tree_preload(gfp_t gm) { return 0; } ++#endif ++ + void radix_tree_init(void); + void *radix_tree_tag_set(struct radix_tree_root *root, + unsigned long index, unsigned int tag); +@@ -255,7 +261,7 @@ unsigned long radix_tree_locate_item(str + + static inline void radix_tree_preload_end(void) + { +- preempt_enable(); ++ preempt_enable_nort(); + } + + /** +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/random.h sun8i-rt/include/linux/random.h +--- sun8i/include/linux/random.h 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/include/linux/random.h 2016-08-22 18:01:43.184281083 +0200 +@@ -51,7 +51,7 @@ struct rnd_state { + extern void add_device_randomness(const void *, unsigned int); + extern void add_input_randomness(unsigned int type, unsigned int code, + unsigned int value); +-extern void add_interrupt_randomness(int irq, int irq_flags); ++extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip); + + extern void get_random_bytes(void *buf, int nbytes); + extern void get_random_bytes_arch(void *buf, int nbytes); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/rcupdate.h sun8i-rt/include/linux/rcupdate.h +--- sun8i/include/linux/rcupdate.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/rcupdate.h 2016-08-22 17:36:13.444263496 +0200 +@@ -101,6 +101,9 @@ extern void call_rcu(struct rcu_head *he + + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define call_rcu_bh call_rcu ++#else + /** + * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. + * @head: structure to be used for queueing the RCU updates. +@@ -121,6 +124,7 @@ extern void call_rcu(struct rcu_head *he + */ + extern void call_rcu_bh(struct rcu_head *head, + void (*func)(struct rcu_head *head)); ++#endif + + /** + * call_rcu_sched() - Queue an RCU for invocation after sched grace period. +@@ -156,6 +160,11 @@ void synchronize_rcu(void); + * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. + */ + #define rcu_preempt_depth() (current->rcu_read_lock_nesting) ++#ifndef CONFIG_PREEMPT_RT_FULL ++#define sched_rcu_preempt_depth() rcu_preempt_depth() ++#else ++static inline int sched_rcu_preempt_depth(void) { return 0; } ++#endif + + #else /* #ifdef CONFIG_PREEMPT_RCU */ + +@@ -179,6 +188,8 @@ static inline int rcu_preempt_depth(void + return 0; + } + ++#define sched_rcu_preempt_depth() rcu_preempt_depth() ++ + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + + /* Internal to kernel */ +@@ -324,7 +335,14 @@ static inline int rcu_read_lock_held(voi + * rcu_read_lock_bh_held() is defined out of line to avoid #include-file + * hell. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline int rcu_read_lock_bh_held(void) ++{ ++ return rcu_read_lock_held(); ++} ++#else + extern int rcu_read_lock_bh_held(void); ++#endif + + /** + * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? +@@ -773,10 +791,14 @@ static inline void rcu_read_unlock(void) + static inline void rcu_read_lock_bh(void) + { + local_bh_disable(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ rcu_read_lock(); ++#else + __acquire(RCU_BH); + rcu_lock_acquire(&rcu_bh_lock_map); + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_lock_bh() used illegally while idle"); ++#endif + } + + /* +@@ -786,10 +808,14 @@ static inline void rcu_read_lock_bh(void + */ + static inline void rcu_read_unlock_bh(void) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ rcu_read_unlock(); ++#else + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_unlock_bh() used illegally while idle"); + rcu_lock_release(&rcu_bh_lock_map); + __release(RCU_BH); ++#endif + local_bh_enable(); + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/rcutree.h sun8i-rt/include/linux/rcutree.h +--- sun8i/include/linux/rcutree.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/rcutree.h 2016-08-22 17:35:43.800263155 +0200 +@@ -57,7 +57,11 @@ static inline void exit_rcu(void) + + #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ + ++#ifndef CONFIG_PREEMPT_RT_FULL + extern void synchronize_rcu_bh(void); ++#else ++# define synchronize_rcu_bh synchronize_rcu ++#endif + extern void synchronize_sched_expedited(void); + extern void synchronize_rcu_expedited(void); + +@@ -85,19 +89,29 @@ static inline void synchronize_rcu_bh_ex + } + + extern void rcu_barrier(void); ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define rcu_barrier_bh rcu_barrier ++#else + extern void rcu_barrier_bh(void); ++#endif + extern void rcu_barrier_sched(void); + + extern unsigned long rcutorture_testseq; + extern unsigned long rcutorture_vernum; + extern long rcu_batches_completed(void); +-extern long rcu_batches_completed_bh(void); + extern long rcu_batches_completed_sched(void); + + extern void rcu_force_quiescent_state(void); +-extern void rcu_bh_force_quiescent_state(void); + extern void rcu_sched_force_quiescent_state(void); + ++#ifndef CONFIG_PREEMPT_RT_FULL ++extern void rcu_bh_force_quiescent_state(void); ++extern long rcu_batches_completed_bh(void); ++#else ++# define rcu_bh_force_quiescent_state rcu_force_quiescent_state ++# define rcu_batches_completed_bh rcu_batches_completed ++#endif ++ + /* A context switch is a grace period for RCU-sched and RCU-bh. */ + static inline int rcu_blocking_is_gp(void) + { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/rtmutex.h sun8i-rt/include/linux/rtmutex.h +--- sun8i/include/linux/rtmutex.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/rtmutex.h 2016-08-22 18:21:41.012294854 +0200 +@@ -14,7 +14,7 @@ + + #include + #include +-#include ++#include + + extern int max_lock_depth; /* for sysctl */ + +@@ -29,9 +29,10 @@ struct rt_mutex { + raw_spinlock_t wait_lock; + struct plist_head wait_list; + struct task_struct *owner; +-#ifdef CONFIG_DEBUG_RT_MUTEXES + int save_state; +- const char *name, *file; ++#ifdef CONFIG_DEBUG_RT_MUTEXES ++ const char *file; ++ const char *name; + int line; + void *magic; + #endif +@@ -56,19 +57,39 @@ struct hrtimer_sleeper; + #ifdef CONFIG_DEBUG_RT_MUTEXES + # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ + , .name = #mutexname, .file = __FILE__, .line = __LINE__ +-# define rt_mutex_init(mutex) __rt_mutex_init(mutex, __func__) ++ ++# define rt_mutex_init(mutex) \ ++ do { \ ++ raw_spin_lock_init(&(mutex)->wait_lock); \ ++ __rt_mutex_init(mutex, #mutex); \ ++ } while (0) ++ + extern void rt_mutex_debug_task_free(struct task_struct *tsk); + #else + # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) +-# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL) ++ ++# define rt_mutex_init(mutex) \ ++ do { \ ++ raw_spin_lock_init(&(mutex)->wait_lock); \ ++ __rt_mutex_init(mutex, #mutex); \ ++ } while (0) ++ + # define rt_mutex_debug_task_free(t) do { } while (0) + #endif + +-#define __RT_MUTEX_INITIALIZER(mutexname) \ +- { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ ++#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ + , .wait_list = PLIST_HEAD_INIT(mutexname.wait_list) \ + , .owner = NULL \ +- __DEBUG_RT_MUTEX_INITIALIZER(mutexname)} ++ __DEBUG_RT_MUTEX_INITIALIZER(mutexname) ++ ++ ++#define __RT_MUTEX_INITIALIZER(mutexname) \ ++ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) } ++ ++#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \ ++ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ ++ , .save_state = 1 } + + #define DEFINE_RT_MUTEX(mutexname) \ + struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) +@@ -88,11 +109,10 @@ extern void __rt_mutex_init(struct rt_mu + extern void rt_mutex_destroy(struct rt_mutex *lock); + + extern void rt_mutex_lock(struct rt_mutex *lock); +-extern int rt_mutex_lock_interruptible(struct rt_mutex *lock, +- int detect_deadlock); ++extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); ++extern int rt_mutex_lock_killable(struct rt_mutex *lock); + extern int rt_mutex_timed_lock(struct rt_mutex *lock, +- struct hrtimer_sleeper *timeout, +- int detect_deadlock); ++ struct hrtimer_sleeper *timeout); + + extern int rt_mutex_trylock(struct rt_mutex *lock); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/rwlock_rt.h sun8i-rt/include/linux/rwlock_rt.h +--- sun8i/include/linux/rwlock_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/linux/rwlock_rt.h 2016-08-22 17:34:01.268261976 +0200 +@@ -0,0 +1,123 @@ ++#ifndef __LINUX_RWLOCK_RT_H ++#define __LINUX_RWLOCK_RT_H ++ ++#ifndef __LINUX_SPINLOCK_H ++#error Do not include directly. Use spinlock.h ++#endif ++ ++#define rwlock_init(rwl) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(rwl)->lock); \ ++ __rt_rwlock_init(rwl, #rwl, &__key); \ ++} while (0) ++ ++extern void __lockfunc rt_write_lock(rwlock_t *rwlock); ++extern void __lockfunc rt_read_lock(rwlock_t *rwlock); ++extern int __lockfunc rt_write_trylock(rwlock_t *rwlock); ++extern int __lockfunc rt_write_trylock_irqsave(rwlock_t *trylock, unsigned long *flags); ++extern int __lockfunc rt_read_trylock(rwlock_t *rwlock); ++extern void __lockfunc rt_write_unlock(rwlock_t *rwlock); ++extern void __lockfunc rt_read_unlock(rwlock_t *rwlock); ++extern unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock); ++extern unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock); ++extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key); ++ ++#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock)) ++#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock)) ++ ++#define write_trylock_irqsave(lock, flags) \ ++ __cond_lock(lock, rt_write_trylock_irqsave(lock, &flags)) ++ ++#define read_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ migrate_disable(); \ ++ flags = rt_read_lock_irqsave(lock); \ ++ } while (0) ++ ++#define write_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ migrate_disable(); \ ++ flags = rt_write_lock_irqsave(lock); \ ++ } while (0) ++ ++#define read_lock(lock) \ ++ do { \ ++ migrate_disable(); \ ++ rt_read_lock(lock); \ ++ } while (0) ++ ++#define read_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ migrate_disable(); \ ++ rt_read_lock(lock); \ ++ } while (0) ++ ++#define read_lock_irq(lock) read_lock(lock) ++ ++#define write_lock(lock) \ ++ do { \ ++ migrate_disable(); \ ++ rt_write_lock(lock); \ ++ } while (0) ++ ++#define write_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ migrate_disable(); \ ++ rt_write_lock(lock); \ ++ } while (0) ++ ++#define write_lock_irq(lock) write_lock(lock) ++ ++#define read_unlock(lock) \ ++ do { \ ++ rt_read_unlock(lock); \ ++ migrate_enable(); \ ++ } while (0) ++ ++#define read_unlock_bh(lock) \ ++ do { \ ++ rt_read_unlock(lock); \ ++ migrate_enable(); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define read_unlock_irq(lock) read_unlock(lock) ++ ++#define write_unlock(lock) \ ++ do { \ ++ rt_write_unlock(lock); \ ++ migrate_enable(); \ ++ } while (0) ++ ++#define write_unlock_bh(lock) \ ++ do { \ ++ rt_write_unlock(lock); \ ++ migrate_enable(); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define write_unlock_irq(lock) write_unlock(lock) ++ ++#define read_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ rt_read_unlock(lock); \ ++ migrate_enable(); \ ++ } while (0) ++ ++#define write_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ rt_write_unlock(lock); \ ++ migrate_enable(); \ ++ } while (0) ++ ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/rwlock_types.h sun8i-rt/include/linux/rwlock_types.h +--- sun8i/include/linux/rwlock_types.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/rwlock_types.h 2016-08-22 17:34:17.240262160 +0200 +@@ -1,6 +1,10 @@ + #ifndef __LINUX_RWLOCK_TYPES_H + #define __LINUX_RWLOCK_TYPES_H + ++#if !defined(__LINUX_SPINLOCK_TYPES_H) ++# error "Do not include directly, include spinlock_types.h" ++#endif ++ + /* + * include/linux/rwlock_types.h - generic rwlock type definitions + * and initializers +@@ -43,6 +47,7 @@ typedef struct { + RW_DEP_MAP_INIT(lockname) } + #endif + +-#define DEFINE_RWLOCK(x) rwlock_t x = __RW_LOCK_UNLOCKED(x) ++#define DEFINE_RWLOCK(name) \ ++ rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name) + + #endif /* __LINUX_RWLOCK_TYPES_H */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/rwlock_types_rt.h sun8i-rt/include/linux/rwlock_types_rt.h +--- sun8i/include/linux/rwlock_types_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/linux/rwlock_types_rt.h 2016-08-22 17:33:15.232261447 +0200 +@@ -0,0 +1,33 @@ ++#ifndef __LINUX_RWLOCK_TYPES_RT_H ++#define __LINUX_RWLOCK_TYPES_RT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++/* ++ * rwlocks - rtmutex which allows single reader recursion ++ */ ++typedef struct { ++ struct rt_mutex lock; ++ int read_depth; ++ unsigned int break_lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} rwlock_t; ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } ++#else ++# define RW_DEP_MAP_INIT(lockname) ++#endif ++ ++#define __RW_LOCK_UNLOCKED(name) \ ++ { .lock = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.lock), \ ++ RW_DEP_MAP_INIT(name) } ++ ++#define DEFINE_RWLOCK(name) \ ++ rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name) ++ ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/rwsem.h sun8i-rt/include/linux/rwsem.h +--- sun8i/include/linux/rwsem.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/rwsem.h 2016-08-22 17:33:46.052261801 +0200 +@@ -16,6 +16,10 @@ + + #include + ++#ifdef CONFIG_PREEMPT_RT_FULL ++#include ++#else /* PREEMPT_RT_FULL */ ++ + struct rw_semaphore; + + #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK +@@ -130,4 +134,6 @@ extern void down_write_nested(struct rw_ + # define down_write_nested(sem, subclass) down_write(sem) + #endif + ++#endif /* !PREEMPT_RT_FULL */ ++ + #endif /* _LINUX_RWSEM_H */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/rwsem_rt.h sun8i-rt/include/linux/rwsem_rt.h +--- sun8i/include/linux/rwsem_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/linux/rwsem_rt.h 2016-08-22 17:33:46.052261801 +0200 +@@ -0,0 +1,105 @@ ++#ifndef _LINUX_RWSEM_RT_H ++#define _LINUX_RWSEM_RT_H ++ ++#ifndef _LINUX_RWSEM_H ++#error "Include rwsem.h" ++#endif ++ ++/* ++ * RW-semaphores are a spinlock plus a reader-depth count. ++ * ++ * Note that the semantics are different from the usual ++ * Linux rw-sems, in PREEMPT_RT mode we do not allow ++ * multiple readers to hold the lock at once, we only allow ++ * a read-lock owner to read-lock recursively. This is ++ * better for latency, makes the implementation inherently ++ * fair and makes it simpler as well. ++ */ ++ ++#include ++ ++struct rw_semaphore { ++ struct rt_mutex lock; ++ int read_depth; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++}; ++ ++#define __RWSEM_INITIALIZER(name) \ ++ { .lock = __RT_MUTEX_INITIALIZER(name.lock), \ ++ RW_DEP_MAP_INIT(name) } ++ ++#define DECLARE_RWSEM(lockname) \ ++ struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) ++ ++extern void __rt_rwsem_init(struct rw_semaphore *rwsem, char *name, ++ struct lock_class_key *key); ++ ++# define rt_init_rwsem(sem) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(sem)->lock); \ ++ __rt_rwsem_init((sem), #sem, &__key); \ ++} while (0) ++ ++extern void rt_down_write(struct rw_semaphore *rwsem); ++extern void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass); ++extern void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass); ++extern void rt_down_read(struct rw_semaphore *rwsem); ++extern int rt_down_write_trylock(struct rw_semaphore *rwsem); ++extern int rt_down_read_trylock(struct rw_semaphore *rwsem); ++extern void rt_up_read(struct rw_semaphore *rwsem); ++extern void rt_up_write(struct rw_semaphore *rwsem); ++extern void rt_downgrade_write(struct rw_semaphore *rwsem); ++ ++#define init_rwsem(sem) rt_init_rwsem(sem) ++#define rwsem_is_locked(s) rt_mutex_is_locked(&(s)->lock) ++ ++static inline void down_read(struct rw_semaphore *sem) ++{ ++ rt_down_read(sem); ++} ++ ++static inline int down_read_trylock(struct rw_semaphore *sem) ++{ ++ return rt_down_read_trylock(sem); ++} ++ ++static inline void down_write(struct rw_semaphore *sem) ++{ ++ rt_down_write(sem); ++} ++ ++static inline int down_write_trylock(struct rw_semaphore *sem) ++{ ++ return rt_down_write_trylock(sem); ++} ++ ++static inline void up_read(struct rw_semaphore *sem) ++{ ++ rt_up_read(sem); ++} ++ ++static inline void up_write(struct rw_semaphore *sem) ++{ ++ rt_up_write(sem); ++} ++ ++static inline void downgrade_write(struct rw_semaphore *sem) ++{ ++ rt_downgrade_write(sem); ++} ++ ++static inline void down_read_nested(struct rw_semaphore *sem, int subclass) ++{ ++ return rt_down_read_nested(sem, subclass); ++} ++ ++static inline void down_write_nested(struct rw_semaphore *sem, int subclass) ++{ ++ rt_down_write_nested(sem, subclass); ++} ++ ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/sched.h sun8i-rt/include/linux/sched.h +--- sun8i/include/linux/sched.h 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/include/linux/sched.h 2016-08-22 18:28:44.868299727 +0200 +@@ -63,6 +63,7 @@ struct sched_param { + #include + #include + ++#include + #include + #include + #include +@@ -90,6 +91,7 @@ struct sched_param { + #include + #include + #include ++#include + + #include + +@@ -148,8 +150,6 @@ extern unsigned long nr_running_avg_cpu( + extern void calc_global_load(unsigned long ticks); + extern void update_cpu_load_nohz(void); + +-extern unsigned long get_parent_ip(unsigned long addr); +- + struct seq_file; + struct cfs_rq; + struct task_group; +@@ -1123,6 +1123,7 @@ struct sched_domain; + #define WF_SYNC 0x01 /* waker goes to sleep after wakup */ + #define WF_FORK 0x02 /* child wakeup after fork */ + #define WF_MIGRATED 0x04 /* internal use, task got migrated */ ++#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */ + + #define ENQUEUE_WAKEUP 1 + #define ENQUEUE_HEAD 2 +@@ -1314,6 +1315,7 @@ enum perf_event_task_context { + + struct task_struct { + volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ ++ volatile long saved_state; /* saved state for "spinlock sleepers" */ + void *stack; + atomic_t usage; + unsigned int flags; /* per process flags, defined below */ +@@ -1353,6 +1355,12 @@ struct task_struct { + #endif + + unsigned int policy; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int migrate_disable; ++#ifdef CONFIG_SCHED_DEBUG ++ int migrate_disable_atomic; ++#endif ++#endif + cpumask_t cpus_allowed; + + #ifdef CONFIG_PREEMPT_RCU +@@ -1458,6 +1466,9 @@ struct task_struct { + + struct task_cputime cputime_expires; + struct list_head cpu_timers[3]; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct task_struct *posix_timer_list; ++#endif + + /* process credentials */ + const struct cred __rcu *real_cred; /* objective and real subjective task +@@ -1491,10 +1502,15 @@ struct task_struct { + /* signal handlers */ + struct signal_struct *signal; + struct sighand_struct *sighand; ++ struct sigqueue *sigqueue_cache; + + sigset_t blocked, real_blocked; + sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */ + struct sigpending pending; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* TODO: move me into ->restart_block ? */ ++ struct siginfo forced_info; ++#endif + + unsigned long sas_ss_sp; + size_t sas_ss_size; +@@ -1529,6 +1545,9 @@ struct task_struct { + /* mutex deadlock detection */ + struct mutex_waiter *blocked_on; + #endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int pagefault_disabled; ++#endif + #ifdef CONFIG_TRACE_IRQFLAGS + unsigned int irq_events; + unsigned long hardirq_enable_ip; +@@ -1661,6 +1680,12 @@ struct task_struct { + unsigned long trace; + /* bitmask and counter of trace recursion */ + unsigned long trace_recursion; ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ u64 preempt_timestamp_hist; ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ long timer_offset; ++#endif ++#endif + #endif /* CONFIG_TRACING */ + #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */ + struct memcg_batch_info { +@@ -1673,10 +1698,32 @@ struct task_struct { + #ifdef CONFIG_HAVE_HW_BREAKPOINT + atomic_t ptrace_bp_refcnt; + #endif ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct rcu_head put_rcu; ++ int softirq_nestcnt; ++#endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++# if defined CONFIG_HIGHMEM || defined CONFIG_X86_32 ++ int kmap_idx; ++ pte_t kmap_pte[KM_TYPE_NR]; ++# endif ++#endif ++ ++#ifdef CONFIG_DEBUG_PREEMPT ++ unsigned long preempt_disable_ip; ++#endif + }; + +-/* Future-safe accessor for struct task_struct's cpus_allowed. */ +-#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline bool cur_pf_disabled(void) { return current->pagefault_disabled; } ++#else ++static inline bool cur_pf_disabled(void) { return false; } ++#endif ++ ++static inline bool pagefault_disabled(void) ++{ ++ return in_atomic() || cur_pf_disabled(); ++} + + /* + * Priority of a process goes from 0..MAX_PRIO-1, valid RT +@@ -1846,6 +1893,15 @@ extern struct pid *cad_pid; + extern void free_task(struct task_struct *tsk); + #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) + ++#ifdef CONFIG_PREEMPT_RT_BASE ++extern void __put_task_struct_cb(struct rcu_head *rhp); ++ ++static inline void put_task_struct(struct task_struct *t) ++{ ++ if (atomic_dec_and_test(&t->usage)) ++ call_rcu(&t->put_rcu, __put_task_struct_cb); ++} ++#else + extern void __put_task_struct(struct task_struct *t); + + static inline void put_task_struct(struct task_struct *t) +@@ -1853,6 +1909,7 @@ static inline void put_task_struct(struc + if (atomic_dec_and_test(&t->usage)) + __put_task_struct(t); + } ++#endif + + extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st); + extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st); +@@ -1879,6 +1936,7 @@ extern int task_free_unregister(struct n + #define PF_FROZEN 0x00010000 /* frozen for system suspend */ + #define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */ + #define PF_KSWAPD 0x00040000 /* I am kswapd */ ++#define PF_STOMPER 0x00080000 /* I am a stomp machine thread */ + #define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ + #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ + #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ +@@ -1990,6 +2048,10 @@ extern void do_set_cpus_allowed(struct t + + extern int set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask); ++int migrate_me(void); ++void tell_sched_cpu_down_begin(int cpu); ++void tell_sched_cpu_down_done(int cpu); ++ + #else + static inline void do_set_cpus_allowed(struct task_struct *p, + const struct cpumask *new_mask) +@@ -2002,6 +2064,9 @@ static inline int set_cpus_allowed_ptr(s + return -EINVAL; + return 0; + } ++static inline int migrate_me(void) { return 0; } ++static inline void tell_sched_cpu_down_begin(int cpu) { } ++static inline void tell_sched_cpu_down_done(int cpu) { } + #endif + + #ifdef CONFIG_NO_HZ +@@ -2177,6 +2242,7 @@ extern unsigned int sysctl_sched_cfs_ban + #ifdef CONFIG_RT_MUTEXES + extern int rt_mutex_getprio(struct task_struct *p); + extern void rt_mutex_setprio(struct task_struct *p, int prio); ++extern int rt_mutex_check_prio(struct task_struct *task, int newprio); + extern void rt_mutex_adjust_pi(struct task_struct *p); + static inline bool tsk_is_pi_blocked(struct task_struct *tsk) + { +@@ -2187,6 +2253,10 @@ static inline int rt_mutex_getprio(struc + { + return p->normal_prio; + } ++static inline int rt_mutex_check_prio(struct task_struct *task, int newprio) ++{ ++ return 0; ++} + # define rt_mutex_adjust_pi(p) do { } while (0) + static inline bool tsk_is_pi_blocked(struct task_struct *tsk) + { +@@ -2279,6 +2349,7 @@ extern void xtime_update(unsigned long t + + extern int wake_up_state(struct task_struct *tsk, unsigned int state); + extern int wake_up_process(struct task_struct *tsk); ++extern int wake_up_lock_sleeper(struct task_struct * tsk); + extern void wake_up_new_task(struct task_struct *tsk); + #ifdef CONFIG_SMP + extern void kick_process(struct task_struct *tsk); +@@ -2369,12 +2440,24 @@ extern struct mm_struct * mm_alloc(void) + + /* mmdrop drops the mm and the page tables */ + extern void __mmdrop(struct mm_struct *); ++ + static inline void mmdrop(struct mm_struct * mm) + { + if (unlikely(atomic_dec_and_test(&mm->mm_count))) + __mmdrop(mm); + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++extern void __mmdrop_delayed(struct rcu_head *rhp); ++static inline void mmdrop_delayed(struct mm_struct *mm) ++{ ++ if (atomic_dec_and_test(&mm->mm_count)) ++ call_rcu(&mm->delayed_drop, __mmdrop_delayed); ++} ++#else ++# define mmdrop_delayed(mm) mmdrop(mm) ++#endif ++ + /* mmput gets rid of the mappings and all user-space */ + extern int mmput(struct mm_struct *); + /* Grab a reference to a task's mm, if it is not already going away */ +@@ -2719,7 +2802,7 @@ extern int _cond_resched(void); + + extern int __cond_resched_lock(spinlock_t *lock); + +-#ifdef CONFIG_PREEMPT_COUNT ++#if defined(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT_FULL) + #define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET + #else + #define PREEMPT_LOCK_OFFSET 0 +@@ -2730,12 +2813,16 @@ extern int __cond_resched_lock(spinlock_ + __cond_resched_lock(lock); \ + }) + ++#ifndef CONFIG_PREEMPT_RT_FULL + extern int __cond_resched_softirq(void); + + #define cond_resched_softirq() ({ \ + __might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ + __cond_resched_softirq(); \ + }) ++#else ++# define cond_resched_softirq() cond_resched() ++#endif + + /* + * Does a critical section need to be broken due to another +@@ -2807,6 +2894,26 @@ static inline void set_task_cpu(struct t + + #endif /* CONFIG_SMP */ + ++static inline int __migrate_disabled(struct task_struct *p) ++{ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ return p->migrate_disable; ++#else ++ return 0; ++#endif ++} ++ ++/* Future-safe accessor for struct task_struct's cpus_allowed. */ ++static inline const struct cpumask *tsk_cpus_allowed(struct task_struct *p) ++{ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (p->migrate_disable) ++ return cpumask_of(task_cpu(p)); ++#endif ++ ++ return &p->cpus_allowed; ++} ++ + extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); + extern long sched_getaffinity(pid_t pid, struct cpumask *mask); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/seqlock.h sun8i-rt/include/linux/seqlock.h +--- sun8i/include/linux/seqlock.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/seqlock.h 2016-08-22 17:50:16.728273191 +0200 +@@ -30,92 +30,12 @@ + #include + #include + +-typedef struct { +- unsigned sequence; +- spinlock_t lock; +-} seqlock_t; +- +-/* +- * These macros triggered gcc-3.x compile-time problems. We think these are +- * OK now. Be cautious. +- */ +-#define __SEQLOCK_UNLOCKED(lockname) \ +- { 0, __SPIN_LOCK_UNLOCKED(lockname) } +- +-#define seqlock_init(x) \ +- do { \ +- (x)->sequence = 0; \ +- spin_lock_init(&(x)->lock); \ +- } while (0) +- +-#define DEFINE_SEQLOCK(x) \ +- seqlock_t x = __SEQLOCK_UNLOCKED(x) +- +-/* Lock out other writers and update the count. +- * Acts like a normal spin_lock/unlock. +- * Don't need preempt_disable() because that is in the spin_lock already. +- */ +-static inline void write_seqlock(seqlock_t *sl) +-{ +- spin_lock(&sl->lock); +- ++sl->sequence; +- smp_wmb(); +-} +- +-static inline void write_sequnlock(seqlock_t *sl) +-{ +- smp_wmb(); +- sl->sequence++; +- spin_unlock(&sl->lock); +-} +- +-static inline int write_tryseqlock(seqlock_t *sl) +-{ +- int ret = spin_trylock(&sl->lock); +- +- if (ret) { +- ++sl->sequence; +- smp_wmb(); +- } +- return ret; +-} +- +-/* Start of read calculation -- fetch last complete writer token */ +-static __always_inline unsigned read_seqbegin(const seqlock_t *sl) +-{ +- unsigned ret; +- +-repeat: +- ret = ACCESS_ONCE(sl->sequence); +- if (unlikely(ret & 1)) { +- cpu_relax(); +- goto repeat; +- } +- smp_rmb(); +- +- return ret; +-} +- +-/* +- * Test if reader processed invalid data. +- * +- * If sequence value changed then writer changed data while in section. +- */ +-static __always_inline int read_seqretry(const seqlock_t *sl, unsigned start) +-{ +- smp_rmb(); +- +- return unlikely(sl->sequence != start); +-} +- +- + /* + * Version using sequence counter only. + * This can be used when code has its own mutex protecting the + * updating starting before the write_seqcountbeqin() and ending + * after the write_seqcount_end(). + */ +- + typedef struct seqcount { + unsigned sequence; + } seqcount_t; +@@ -218,7 +138,6 @@ static inline int __read_seqcount_retry( + static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) + { + smp_rmb(); +- + return __read_seqcount_retry(s, start); + } + +@@ -227,18 +146,30 @@ static inline int read_seqcount_retry(co + * Sequence counter only version assumes that callers are using their + * own mutexing. + */ +-static inline void write_seqcount_begin(seqcount_t *s) ++static inline void __write_seqcount_begin(seqcount_t *s) + { + s->sequence++; + smp_wmb(); + } + +-static inline void write_seqcount_end(seqcount_t *s) ++static inline void write_seqcount_begin(seqcount_t *s) ++{ ++ preempt_disable_rt(); ++ __write_seqcount_begin(s); ++} ++ ++static inline void __write_seqcount_end(seqcount_t *s) + { + smp_wmb(); + s->sequence++; + } + ++static inline void write_seqcount_end(seqcount_t *s) ++{ ++ __write_seqcount_end(s); ++ preempt_enable_rt(); ++} ++ + /** + * write_seqcount_barrier - invalidate in-progress read-side seq operations + * @s: pointer to seqcount_t +@@ -252,31 +183,124 @@ static inline void write_seqcount_barrie + s->sequence+=2; + } + ++typedef struct { ++ struct seqcount seqcount; ++ spinlock_t lock; ++} seqlock_t; ++ + /* +- * Possible sw/hw IRQ protected versions of the interfaces. ++ * These macros triggered gcc-3.x compile-time problems. We think these are ++ * OK now. Be cautious. + */ +-#define write_seqlock_irqsave(lock, flags) \ +- do { local_irq_save(flags); write_seqlock(lock); } while (0) +-#define write_seqlock_irq(lock) \ +- do { local_irq_disable(); write_seqlock(lock); } while (0) +-#define write_seqlock_bh(lock) \ +- do { local_bh_disable(); write_seqlock(lock); } while (0) ++#define __SEQLOCK_UNLOCKED(lockname) \ ++ { \ ++ .seqcount = SEQCNT_ZERO, \ ++ .lock = __SPIN_LOCK_UNLOCKED(lockname) \ ++ } + +-#define write_sequnlock_irqrestore(lock, flags) \ +- do { write_sequnlock(lock); local_irq_restore(flags); } while(0) +-#define write_sequnlock_irq(lock) \ +- do { write_sequnlock(lock); local_irq_enable(); } while(0) +-#define write_sequnlock_bh(lock) \ +- do { write_sequnlock(lock); local_bh_enable(); } while(0) ++#define seqlock_init(x) \ ++ do { \ ++ seqcount_init(&(x)->seqcount); \ ++ spin_lock_init(&(x)->lock); \ ++ } while (0) + +-#define read_seqbegin_irqsave(lock, flags) \ +- ({ local_irq_save(flags); read_seqbegin(lock); }) ++#define DEFINE_SEQLOCK(x) \ ++ seqlock_t x = __SEQLOCK_UNLOCKED(x) + +-#define read_seqretry_irqrestore(lock, iv, flags) \ +- ({ \ +- int ret = read_seqretry(lock, iv); \ +- local_irq_restore(flags); \ +- ret; \ +- }) ++/* ++ * Read side functions for starting and finalizing a read side section. ++ */ ++#ifndef CONFIG_PREEMPT_RT_FULL ++static inline unsigned read_seqbegin(const seqlock_t *sl) ++{ ++ return read_seqcount_begin(&sl->seqcount); ++} ++#else ++/* ++ * Starvation safe read side for RT ++ */ ++static inline unsigned read_seqbegin(seqlock_t *sl) ++{ ++ unsigned ret; ++ ++repeat: ++ ret = sl->seqcount.sequence; ++ if (unlikely(ret & 1)) { ++ /* ++ * Take the lock and let the writer proceed (i.e. evtl ++ * boost it), otherwise we could loop here forever. ++ */ ++ spin_lock(&sl->lock); ++ spin_unlock(&sl->lock); ++ goto repeat; ++ } ++ return ret; ++} ++#endif ++ ++static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) ++{ ++ return read_seqcount_retry(&sl->seqcount, start); ++} ++ ++/* ++ * Lock out other writers and update the count. ++ * Acts like a normal spin_lock/unlock. ++ * Don't need preempt_disable() because that is in the spin_lock already. ++ */ ++static inline void write_seqlock(seqlock_t *sl) ++{ ++ spin_lock(&sl->lock); ++ __write_seqcount_begin(&sl->seqcount); ++} ++ ++static inline void write_sequnlock(seqlock_t *sl) ++{ ++ __write_seqcount_end(&sl->seqcount); ++ spin_unlock(&sl->lock); ++} ++ ++static inline void write_seqlock_bh(seqlock_t *sl) ++{ ++ spin_lock_bh(&sl->lock); ++ __write_seqcount_begin(&sl->seqcount); ++} ++ ++static inline void write_sequnlock_bh(seqlock_t *sl) ++{ ++ __write_seqcount_end(&sl->seqcount); ++ spin_unlock_bh(&sl->lock); ++} ++ ++static inline void write_seqlock_irq(seqlock_t *sl) ++{ ++ spin_lock_irq(&sl->lock); ++ __write_seqcount_begin(&sl->seqcount); ++} ++ ++static inline void write_sequnlock_irq(seqlock_t *sl) ++{ ++ __write_seqcount_end(&sl->seqcount); ++ spin_unlock_irq(&sl->lock); ++} ++ ++static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) ++{ ++ unsigned long flags; ++ ++ spin_lock_irqsave(&sl->lock, flags); ++ __write_seqcount_begin(&sl->seqcount); ++ return flags; ++} ++ ++#define write_seqlock_irqsave(lock, flags) \ ++ do { flags = __write_seqlock_irqsave(lock); } while (0) ++ ++static inline void ++write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) ++{ ++ __write_seqcount_end(&sl->seqcount); ++ spin_unlock_irqrestore(&sl->lock, flags); ++} + + #endif /* __LINUX_SEQLOCK_H */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/signal.h sun8i-rt/include/linux/signal.h +--- sun8i/include/linux/signal.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/signal.h 2016-08-22 16:02:09.040198603 +0200 +@@ -229,6 +229,7 @@ static inline void init_sigpending(struc + } + + extern void flush_sigqueue(struct sigpending *queue); ++extern void flush_task_sigqueue(struct task_struct *tsk); + + /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ + static inline int valid_signal(unsigned long sig) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/skbuff.h sun8i-rt/include/linux/skbuff.h +--- sun8i/include/linux/skbuff.h 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/include/linux/skbuff.h 2016-08-22 17:43:15.860268352 +0200 +@@ -132,6 +132,7 @@ struct sk_buff_head { + + __u32 qlen; + spinlock_t lock; ++ raw_spinlock_t raw_lock; + }; + + struct sk_buff; +@@ -984,6 +985,12 @@ static inline void skb_queue_head_init(s + __skb_queue_head_init(list); + } + ++static inline void skb_queue_head_init_raw(struct sk_buff_head *list) ++{ ++ raw_spin_lock_init(&list->raw_lock); ++ __skb_queue_head_init(list); ++} ++ + static inline void skb_queue_head_init_class(struct sk_buff_head *list, + struct lock_class_key *class) + { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/smp.h sun8i-rt/include/linux/smp.h +--- sun8i/include/linux/smp.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/smp.h 2016-08-22 17:18:23.108251190 +0200 +@@ -80,7 +80,6 @@ void __smp_call_function_single(int cpui + + int smp_call_function_any(const struct cpumask *mask, + smp_call_func_t func, void *info, int wait); +- + /* + * Generic and arch helpers + */ +@@ -219,6 +218,9 @@ smp_call_function_any(const struct cpuma + #define get_cpu() ({ preempt_disable(); smp_processor_id(); }) + #define put_cpu() preempt_enable() + ++#define get_cpu_light() ({ migrate_disable(); smp_processor_id(); }) ++#define put_cpu_light() migrate_enable() ++ + /* + * Callback to arch code if there's nosmp or maxcpus=0 on the + * boot command line: +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/spinlock_api_smp.h sun8i-rt/include/linux/spinlock_api_smp.h +--- sun8i/include/linux/spinlock_api_smp.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/spinlock_api_smp.h 2016-08-22 17:34:01.268261976 +0200 +@@ -191,6 +191,8 @@ static inline int __raw_spin_trylock_bh( + return 0; + } + +-#include ++#ifndef CONFIG_PREEMPT_RT_FULL ++# include ++#endif + + #endif /* __LINUX_SPINLOCK_API_SMP_H */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/spinlock.h sun8i-rt/include/linux/spinlock.h +--- sun8i/include/linux/spinlock.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/spinlock.h 2016-08-22 17:34:01.268261976 +0200 +@@ -254,7 +254,11 @@ static inline void do_raw_spin_unlock(ra + #define raw_spin_can_lock(lock) (!raw_spin_is_locked(lock)) + + /* Include rwlock functions */ +-#include ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include ++#else ++# include ++#endif + + /* + * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: +@@ -265,6 +269,10 @@ static inline void do_raw_spin_unlock(ra + # include + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include ++#else /* PREEMPT_RT_FULL */ ++ + /* + * Map the spin_lock functions to the raw variants for PREEMPT_RT=n + */ +@@ -394,4 +402,6 @@ extern int _atomic_dec_and_lock(atomic_t + #define atomic_dec_and_lock(atomic, lock) \ + __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) + ++#endif /* !PREEMPT_RT_FULL */ ++ + #endif /* __LINUX_SPINLOCK_H */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/spinlock_rt.h sun8i-rt/include/linux/spinlock_rt.h +--- sun8i/include/linux/spinlock_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/linux/spinlock_rt.h 2016-08-22 18:16:46.624291470 +0200 +@@ -0,0 +1,169 @@ ++#ifndef __LINUX_SPINLOCK_RT_H ++#define __LINUX_SPINLOCK_RT_H ++ ++#ifndef __LINUX_SPINLOCK_H ++#error Do not include directly. Use spinlock.h ++#endif ++ ++#include ++ ++extern void ++__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key); ++ ++#define spin_lock_init(slock) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(slock)->lock); \ ++ __rt_spin_lock_init(slock, #slock, &__key); \ ++} while (0) ++ ++extern void __lockfunc rt_spin_lock(spinlock_t *lock); ++extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock); ++extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass); ++extern void __lockfunc rt_spin_unlock(spinlock_t *lock); ++extern void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock); ++extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock); ++extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags); ++extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock); ++extern int __lockfunc rt_spin_trylock(spinlock_t *lock); ++extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock); ++ ++/* ++ * lockdep-less calls, for derived types like rwlock: ++ * (for trylock they can use rt_mutex_trylock() directly. ++ */ ++extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock); ++extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock); ++ ++#define spin_lock_local(lock) rt_spin_lock(lock) ++#define spin_unlock_local(lock) rt_spin_unlock(lock) ++ ++#define spin_lock(lock) \ ++ do { \ ++ migrate_disable(); \ ++ rt_spin_lock(lock); \ ++ } while (0) ++ ++#define spin_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ migrate_disable(); \ ++ rt_spin_lock(lock); \ ++ } while (0) ++ ++#define spin_lock_irq(lock) spin_lock(lock) ++ ++#define spin_do_trylock(lock) __cond_lock(lock, rt_spin_trylock(lock)) ++ ++#define spin_trylock(lock) \ ++({ \ ++ int __locked; \ ++ migrate_disable(); \ ++ __locked = spin_do_trylock(lock); \ ++ if (!__locked) \ ++ migrate_enable(); \ ++ __locked; \ ++}) ++ ++#ifdef CONFIG_LOCKDEP ++# define spin_lock_nested(lock, subclass) \ ++ do { \ ++ migrate_disable(); \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++ ++# define spin_lock_irqsave_nested(lock, flags, subclass) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ migrate_disable(); \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++#else ++# define spin_lock_nested(lock, subclass) spin_lock(lock) ++ ++# define spin_lock_irqsave_nested(lock, flags, subclass) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ spin_lock(lock); \ ++ } while (0) ++#endif ++ ++#define spin_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ spin_lock(lock); \ ++ } while (0) ++ ++static inline unsigned long spin_lock_trace_flags(spinlock_t *lock) ++{ ++ unsigned long flags = 0; ++#ifdef CONFIG_TRACE_IRQFLAGS ++ flags = rt_spin_lock_trace_flags(lock); ++#else ++ spin_lock(lock); /* lock_local */ ++#endif ++ return flags; ++} ++ ++/* FIXME: we need rt_spin_lock_nest_lock */ ++#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0) ++ ++#define spin_unlock(lock) \ ++ do { \ ++ rt_spin_unlock(lock); \ ++ migrate_enable(); \ ++ } while (0) ++ ++#define spin_unlock_bh(lock) \ ++ do { \ ++ rt_spin_unlock(lock); \ ++ migrate_enable(); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define spin_unlock_irq(lock) spin_unlock(lock) ++ ++#define spin_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ spin_unlock(lock); \ ++ } while (0) ++ ++#define spin_trylock_bh(lock) __cond_lock(lock, rt_spin_trylock_bh(lock)) ++#define spin_trylock_irq(lock) spin_trylock(lock) ++ ++#define spin_trylock_irqsave(lock, flags) \ ++ rt_spin_trylock_irqsave(lock, &(flags)) ++ ++#define spin_unlock_wait(lock) rt_spin_unlock_wait(lock) ++ ++#ifdef CONFIG_GENERIC_LOCKBREAK ++# define spin_is_contended(lock) ((lock)->break_lock) ++#else ++# define spin_is_contended(lock) (((void)(lock), 0)) ++#endif ++ ++static inline int spin_can_lock(spinlock_t *lock) ++{ ++ return !rt_mutex_is_locked(&lock->lock); ++} ++ ++static inline int spin_is_locked(spinlock_t *lock) ++{ ++ return rt_mutex_is_locked(&lock->lock); ++} ++ ++static inline void assert_spin_locked(spinlock_t *lock) ++{ ++ BUG_ON(!spin_is_locked(lock)); ++} ++ ++#define atomic_dec_and_lock(atomic, lock) \ ++ atomic_dec_and_spin_lock(atomic, lock) ++ ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/spinlock_types.h sun8i-rt/include/linux/spinlock_types.h +--- sun8i/include/linux/spinlock_types.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/spinlock_types.h 2016-08-22 17:33:15.232261447 +0200 +@@ -9,80 +9,15 @@ + * Released under the General Public License (GPL). + */ + +-#if defined(CONFIG_SMP) +-# include +-#else +-# include +-#endif +- +-#include +- +-typedef struct raw_spinlock { +- arch_spinlock_t raw_lock; +-#ifdef CONFIG_GENERIC_LOCKBREAK +- unsigned int break_lock; +-#endif +-#ifdef CONFIG_DEBUG_SPINLOCK +- unsigned int magic, owner_cpu; +- void *owner; +-#endif +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +- struct lockdep_map dep_map; +-#endif +-} raw_spinlock_t; +- +-#define SPINLOCK_MAGIC 0xdead4ead +- +-#define SPINLOCK_OWNER_INIT ((void *)-1L) +- +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } +-#else +-# define SPIN_DEP_MAP_INIT(lockname) +-#endif ++#include + +-#ifdef CONFIG_DEBUG_SPINLOCK +-# define SPIN_DEBUG_INIT(lockname) \ +- .magic = SPINLOCK_MAGIC, \ +- .owner_cpu = -1, \ +- .owner = SPINLOCK_OWNER_INIT, ++#ifndef CONFIG_PREEMPT_RT_FULL ++# include ++# include + #else +-# define SPIN_DEBUG_INIT(lockname) +-#endif +- +-#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ +- { \ +- .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ +- SPIN_DEBUG_INIT(lockname) \ +- SPIN_DEP_MAP_INIT(lockname) } +- +-#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ +- (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) +- +-#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) +- +-typedef struct spinlock { +- union { +- struct raw_spinlock rlock; +- +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) +- struct { +- u8 __padding[LOCK_PADSIZE]; +- struct lockdep_map dep_map; +- }; ++# include ++# include ++# include + #endif +- }; +-} spinlock_t; +- +-#define __SPIN_LOCK_INITIALIZER(lockname) \ +- { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } +- +-#define __SPIN_LOCK_UNLOCKED(lockname) \ +- (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) +- +-#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) +- +-#include + + #endif /* __LINUX_SPINLOCK_TYPES_H */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/spinlock_types_nort.h sun8i-rt/include/linux/spinlock_types_nort.h +--- sun8i/include/linux/spinlock_types_nort.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/linux/spinlock_types_nort.h 2016-08-22 17:32:47.200261125 +0200 +@@ -0,0 +1,33 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_NORT_H ++#define __LINUX_SPINLOCK_TYPES_NORT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++/* ++ * The non RT version maps spinlocks to raw_spinlocks ++ */ ++typedef struct spinlock { ++ union { ++ struct raw_spinlock rlock; ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) ++ struct { ++ u8 __padding[LOCK_PADSIZE]; ++ struct lockdep_map dep_map; ++ }; ++#endif ++ }; ++} spinlock_t; ++ ++#define __SPIN_LOCK_INITIALIZER(lockname) \ ++ { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } ++ ++#define __SPIN_LOCK_UNLOCKED(lockname) \ ++ (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) ++ ++#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) ++ ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/spinlock_types_raw.h sun8i-rt/include/linux/spinlock_types_raw.h +--- sun8i/include/linux/spinlock_types_raw.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/linux/spinlock_types_raw.h 2016-08-22 17:32:47.200261125 +0200 +@@ -0,0 +1,56 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_RAW_H ++#define __LINUX_SPINLOCK_TYPES_RAW_H ++ ++#if defined(CONFIG_SMP) ++# include ++#else ++# include ++#endif ++ ++#include ++ ++typedef struct raw_spinlock { ++ arch_spinlock_t raw_lock; ++#ifdef CONFIG_GENERIC_LOCKBREAK ++ unsigned int break_lock; ++#endif ++#ifdef CONFIG_DEBUG_SPINLOCK ++ unsigned int magic, owner_cpu; ++ void *owner; ++#endif ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} raw_spinlock_t; ++ ++#define SPINLOCK_MAGIC 0xdead4ead ++ ++#define SPINLOCK_OWNER_INIT ((void *)-1L) ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } ++#else ++# define SPIN_DEP_MAP_INIT(lockname) ++#endif ++ ++#ifdef CONFIG_DEBUG_SPINLOCK ++# define SPIN_DEBUG_INIT(lockname) \ ++ .magic = SPINLOCK_MAGIC, \ ++ .owner_cpu = -1, \ ++ .owner = SPINLOCK_OWNER_INIT, ++#else ++# define SPIN_DEBUG_INIT(lockname) ++#endif ++ ++#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ ++ { \ ++ .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ ++ SPIN_DEBUG_INIT(lockname) \ ++ SPIN_DEP_MAP_INIT(lockname) } ++ ++#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ ++ (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) ++ ++#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) ++ ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/spinlock_types_rt.h sun8i-rt/include/linux/spinlock_types_rt.h +--- sun8i/include/linux/spinlock_types_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/linux/spinlock_types_rt.h 2016-08-22 17:33:15.232261447 +0200 +@@ -0,0 +1,49 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_RT_H ++#define __LINUX_SPINLOCK_TYPES_RT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++/* ++ * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field: ++ */ ++typedef struct spinlock { ++ struct rt_mutex lock; ++ unsigned int break_lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} spinlock_t; ++ ++#ifdef CONFIG_DEBUG_RT_MUTEXES ++# define __RT_SPIN_INITIALIZER(name) \ ++ { \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ ++ .save_state = 1, \ ++ .file = __FILE__, \ ++ .line = __LINE__ , \ ++ } ++#else ++# define __RT_SPIN_INITIALIZER(name) \ ++ { \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ ++ .save_state = 1, \ ++ } ++#endif ++ ++/* ++.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock) ++*/ ++ ++#define __SPIN_LOCK_UNLOCKED(name) \ ++ { .lock = __RT_SPIN_INITIALIZER(name.lock), \ ++ SPIN_DEP_MAP_INIT(name) } ++ ++#define __DEFINE_SPINLOCK(name) \ ++ spinlock_t name = __SPIN_LOCK_UNLOCKED(name) ++ ++#define DEFINE_SPINLOCK(name) \ ++ spinlock_t name __cacheline_aligned_in_smp = __SPIN_LOCK_UNLOCKED(name) ++ ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/sysctl.h sun8i-rt/include/linux/sysctl.h +--- sun8i/include/linux/sysctl.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/sysctl.h 2016-08-22 16:21:29.280211942 +0200 +@@ -933,6 +933,7 @@ enum + #include + #include + #include ++#include + + /* For the /proc/sys support */ + struct ctl_table; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/timer.h sun8i-rt/include/linux/timer.h +--- sun8i/include/linux/timer.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/timer.h 2016-08-22 17:08:34.488244423 +0200 +@@ -276,7 +276,7 @@ extern void add_timer(struct timer_list + + extern int try_to_del_timer_sync(struct timer_list *timer); + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + extern int del_timer_sync(struct timer_list *timer); + #else + # define del_timer_sync(t) del_timer(t) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/uaccess.h sun8i-rt/include/linux/uaccess.h +--- sun8i/include/linux/uaccess.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/uaccess.h 2016-08-22 16:15:56.436208116 +0200 +@@ -6,38 +6,37 @@ + + /* + * These routines enable/disable the pagefault handler in that +- * it will not take any locks and go straight to the fixup table. +- * +- * They have great resemblance to the preempt_disable/enable calls +- * and in fact they are identical; this is because currently there is +- * no other way to make the pagefault handlers do this. So we do +- * disable preemption but we don't necessarily care about that. ++ * it will not take any MM locks and go straight to the fixup table. + */ +-static inline void pagefault_disable(void) ++static inline void raw_pagefault_disable(void) + { + inc_preempt_count(); +- /* +- * make sure to have issued the store before a pagefault +- * can hit. +- */ + barrier(); + } + +-static inline void pagefault_enable(void) ++static inline void raw_pagefault_enable(void) + { +- /* +- * make sure to issue those last loads/stores before enabling +- * the pagefault handler again. +- */ + barrier(); + dec_preempt_count(); +- /* +- * make sure we do.. +- */ + barrier(); + preempt_check_resched(); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL ++static inline void pagefault_disable(void) ++{ ++ raw_pagefault_disable(); ++} ++ ++static inline void pagefault_enable(void) ++{ ++ raw_pagefault_enable(); ++} ++#else ++extern void pagefault_disable(void); ++extern void pagefault_enable(void); ++#endif ++ + #ifndef ARCH_HAS_NOCACHE_UACCESS + + static inline unsigned long __copy_from_user_inatomic_nocache(void *to, +@@ -77,9 +76,9 @@ static inline unsigned long __copy_from_ + mm_segment_t old_fs = get_fs(); \ + \ + set_fs(KERNEL_DS); \ +- pagefault_disable(); \ ++ raw_pagefault_disable(); \ + ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval)); \ +- pagefault_enable(); \ ++ raw_pagefault_enable(); \ + set_fs(old_fs); \ + ret; \ + }) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/vmstat.h sun8i-rt/include/linux/vmstat.h +--- sun8i/include/linux/vmstat.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/linux/vmstat.h 2016-08-22 17:05:41.752242437 +0200 +@@ -29,7 +29,9 @@ DECLARE_PER_CPU(struct vm_event_state, v + + static inline void __count_vm_event(enum vm_event_item item) + { ++ preempt_disable_rt(); + __this_cpu_inc(vm_event_states.event[item]); ++ preempt_enable_rt(); + } + + static inline void count_vm_event(enum vm_event_item item) +@@ -39,7 +41,9 @@ static inline void count_vm_event(enum v + + static inline void __count_vm_events(enum vm_event_item item, long delta) + { ++ preempt_disable_rt(); + __this_cpu_add(vm_event_states.event[item], delta); ++ preempt_enable_rt(); + } + + static inline void count_vm_events(enum vm_event_item item, long delta) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/wait-simple.h sun8i-rt/include/linux/wait-simple.h +--- sun8i/include/linux/wait-simple.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/linux/wait-simple.h 2016-08-22 18:11:30.460287835 +0200 +@@ -0,0 +1,172 @@ ++#ifndef _LINUX_WAIT_SIMPLE_H ++#define _LINUX_WAIT_SIMPLE_H ++ ++#include ++#include ++ ++#include ++ ++struct swaiter { ++ struct task_struct *task; ++ struct list_head node; ++}; ++ ++#define DEFINE_SWAITER(name) \ ++ struct swaiter name = { \ ++ .task = current, \ ++ .node = LIST_HEAD_INIT((name).node), \ ++ } ++ ++struct swait_head { ++ raw_spinlock_t lock; ++ struct list_head list; ++}; ++ ++#define SWAIT_HEAD_INITIALIZER(name) { \ ++ .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ ++ .list = LIST_HEAD_INIT((name).list), \ ++ } ++ ++#define DEFINE_SWAIT_HEAD(name) \ ++ struct swait_head name = SWAIT_HEAD_INITIALIZER(name) ++ ++extern void __init_swait_head(struct swait_head *h, struct lock_class_key *key); ++ ++#define init_swait_head(swh) \ ++ do { \ ++ static struct lock_class_key __key; \ ++ \ ++ __init_swait_head((swh), &__key); \ ++ } while (0) ++ ++/* ++ * Waiter functions ++ */ ++extern void swait_prepare_locked(struct swait_head *head, struct swaiter *w); ++extern void swait_prepare(struct swait_head *head, struct swaiter *w, int state); ++extern void swait_finish_locked(struct swait_head *head, struct swaiter *w); ++extern void swait_finish(struct swait_head *head, struct swaiter *w); ++ ++/* ++ * Wakeup functions ++ */ ++extern unsigned int __swait_wake(struct swait_head *head, unsigned int state, unsigned int num); ++extern unsigned int __swait_wake_locked(struct swait_head *head, unsigned int state, unsigned int num); ++ ++#define swait_wake(head) __swait_wake(head, TASK_NORMAL, 1) ++#define swait_wake_interruptible(head) __swait_wake(head, TASK_INTERRUPTIBLE, 1) ++#define swait_wake_all(head) __swait_wake(head, TASK_NORMAL, 0) ++#define swait_wake_all_interruptible(head) __swait_wake(head, TASK_INTERRUPTIBLE, 0) ++ ++/* ++ * Event API ++ */ ++#define __swait_event(wq, condition) \ ++do { \ ++ DEFINE_SWAITER(__wait); \ ++ \ ++ for (;;) { \ ++ swait_prepare(&wq, &__wait, TASK_UNINTERRUPTIBLE); \ ++ if (condition) \ ++ break; \ ++ schedule(); \ ++ } \ ++ swait_finish(&wq, &__wait); \ ++} while (0) ++ ++/** ++ * swait_event - sleep until a condition gets true ++ * @wq: the waitqueue to wait on ++ * @condition: a C expression for the event to wait for ++ * ++ * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the ++ * @condition evaluates to true. The @condition is checked each time ++ * the waitqueue @wq is woken up. ++ * ++ * wake_up() has to be called after changing any variable that could ++ * change the result of the wait condition. ++ */ ++#define swait_event(wq, condition) \ ++do { \ ++ if (condition) \ ++ break; \ ++ __swait_event(wq, condition); \ ++} while (0) ++ ++#define __swait_event_interruptible(wq, condition, ret) \ ++do { \ ++ DEFINE_SWAITER(__wait); \ ++ \ ++ for (;;) { \ ++ swait_prepare(&wq, &__wait, TASK_INTERRUPTIBLE); \ ++ if (condition) \ ++ break; \ ++ if (signal_pending(current)) { \ ++ ret = -ERESTARTSYS; \ ++ break; \ ++ } \ ++ schedule(); \ ++ } \ ++ swait_finish(&wq, &__wait); \ ++} while (0) ++ ++/** ++ * swait_event_interruptible - sleep until a condition gets true ++ * @wq: the waitqueue to wait on ++ * @condition: a C expression for the event to wait for ++ * ++ * The process is put to sleep (TASK_INTERRUPTIBLE) until the ++ * @condition evaluates to true. The @condition is checked each time ++ * the waitqueue @wq is woken up. ++ * ++ * wake_up() has to be called after changing any variable that could ++ * change the result of the wait condition. ++ */ ++#define swait_event_interruptible(wq, condition) \ ++({ \ ++ int __ret = 0; \ ++ if (!(condition)) \ ++ __swait_event_interruptible(wq, condition, __ret); \ ++ __ret; \ ++}) ++ ++#define __swait_event_timeout(wq, condition, ret) \ ++do { \ ++ DEFINE_SWAITER(__wait); \ ++ \ ++ for (;;) { \ ++ swait_prepare(&wq, &__wait, TASK_UNINTERRUPTIBLE); \ ++ if (condition) \ ++ break; \ ++ ret = schedule_timeout(ret); \ ++ if (!ret) \ ++ break; \ ++ } \ ++ swait_finish(&wq, &__wait); \ ++} while (0) ++ ++/** ++ * swait_event_timeout - sleep until a condition gets true or a timeout elapses ++ * @wq: the waitqueue to wait on ++ * @condition: a C expression for the event to wait for ++ * @timeout: timeout, in jiffies ++ * ++ * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the ++ * @condition evaluates to true. The @condition is checked each time ++ * the waitqueue @wq is woken up. ++ * ++ * wake_up() has to be called after changing any variable that could ++ * change the result of the wait condition. ++ * ++ * The function returns 0 if the @timeout elapsed, and the remaining ++ * jiffies if the condition evaluated to true before the timeout elapsed. ++ */ ++#define swait_event_timeout(wq, condition, timeout) \ ++({ \ ++ long __ret = timeout; \ ++ if (!(condition)) \ ++ __swait_event_timeout(wq, condition, __ret); \ ++ __ret; \ ++}) ++ ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/linux/work-simple.h sun8i-rt/include/linux/work-simple.h +--- sun8i/include/linux/work-simple.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/linux/work-simple.h 2016-08-22 18:24:57.020297108 +0200 +@@ -0,0 +1,24 @@ ++#ifndef _LINUX_SWORK_H ++#define _LINUX_SWORK_H ++ ++#include ++ ++struct swork_event { ++ struct list_head item; ++ unsigned long flags; ++ void (*func)(struct swork_event *); ++}; ++ ++static inline void INIT_SWORK(struct swork_event *event, ++ void (*func)(struct swork_event *)) ++{ ++ event->flags = 0; ++ event->func = func; ++} ++ ++bool swork_queue(struct swork_event *sev); ++ ++int swork_get(void); ++void swork_put(void); ++ ++#endif /* _LINUX_SWORK_H */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/net/neighbour.h sun8i-rt/include/net/neighbour.h +--- sun8i/include/net/neighbour.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/net/neighbour.h 2016-08-22 17:50:16.728273191 +0200 +@@ -394,7 +394,7 @@ struct neighbour_cb { + + #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) + +-static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, ++static inline void neigh_ha_snapshot(char *dst, struct neighbour *n, + const struct net_device *dev) + { + unsigned int seq; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/net/netns/ipv4.h sun8i-rt/include/net/netns/ipv4.h +--- sun8i/include/net/netns/ipv4.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/net/netns/ipv4.h 2016-08-22 17:47:50.120271505 +0200 +@@ -47,6 +47,7 @@ struct netns_ipv4 { + + int sysctl_icmp_echo_ignore_all; + int sysctl_icmp_echo_ignore_broadcasts; ++ int sysctl_icmp_echo_sysrq; + int sysctl_icmp_ignore_bogus_error_responses; + int sysctl_icmp_ratelimit; + int sysctl_icmp_ratemask; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/trace/events/hist.h sun8i-rt/include/trace/events/hist.h +--- sun8i/include/trace/events/hist.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/trace/events/hist.h 2016-08-22 18:28:21.656299460 +0200 +@@ -0,0 +1,70 @@ ++#undef TRACE_SYSTEM ++#define TRACE_SYSTEM hist ++ ++#if !defined(_TRACE_HIST_H) || defined(TRACE_HEADER_MULTI_READ) ++#define _TRACE_HIST_H ++ ++#include "latency_hist.h" ++#include ++ ++#if !defined(CONFIG_PREEMPT_OFF_HIST) && !defined(CONFIG_INTERRUPT_OFF_HIST) ++#define trace_preemptirqsoff_hist(a,b) ++#define trace_preemptirqsoff_hist_rcuidle(a, b) ++#else ++TRACE_EVENT(preemptirqsoff_hist, ++ ++ TP_PROTO(int reason, int starthist), ++ ++ TP_ARGS(reason, starthist), ++ ++ TP_STRUCT__entry( ++ __field(int, reason ) ++ __field(int, starthist ) ++ ), ++ ++ TP_fast_assign( ++ __entry->reason = reason; ++ __entry->starthist = starthist; ++ ), ++ ++ TP_printk("reason=%s starthist=%s", getaction(__entry->reason), ++ __entry->starthist ? "start" : "stop") ++); ++#endif ++ ++#ifndef CONFIG_MISSED_TIMER_OFFSETS_HIST ++#define trace_hrtimer_interrupt(a,b,c,d) ++#else ++TRACE_EVENT(hrtimer_interrupt, ++ ++ TP_PROTO(int cpu, long long offset, struct task_struct *curr, struct task_struct *task), ++ ++ TP_ARGS(cpu, offset, curr, task), ++ ++ TP_STRUCT__entry( ++ __field(int, cpu ) ++ __field(long long, offset ) ++ __array(char, ccomm, TASK_COMM_LEN) ++ __field(int, cprio ) ++ __array(char, tcomm, TASK_COMM_LEN) ++ __field(int, tprio ) ++ ), ++ ++ TP_fast_assign( ++ __entry->cpu = cpu; ++ __entry->offset = offset; ++ memcpy(__entry->ccomm, curr->comm, TASK_COMM_LEN); ++ __entry->cprio = curr->prio; ++ memcpy(__entry->tcomm, task != NULL ? task->comm : "", task != NULL ? TASK_COMM_LEN : 7); ++ __entry->tprio = task != NULL ? task->prio : -1; ++ ), ++ ++ TP_printk("cpu=%d offset=%lld curr=%s[%d] thread=%s[%d]", ++ __entry->cpu, __entry->offset, __entry->ccomm, __entry->cprio, __entry->tcomm, __entry->tprio) ++); ++#endif ++ ++#endif /* _TRACE_HIST_H */ ++ ++/* This part must be outside protection */ ++#include +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/trace/events/latency_hist.h sun8i-rt/include/trace/events/latency_hist.h +--- sun8i/include/trace/events/latency_hist.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/include/trace/events/latency_hist.h 2016-08-22 16:23:25.124213274 +0200 +@@ -0,0 +1,30 @@ ++#ifndef _LATENCY_HIST_H ++#define _LATENCY_HIST_H ++ ++enum hist_action { ++ IRQS_ON, ++ PREEMPT_ON, ++ TRACE_STOP, ++ IRQS_OFF, ++ PREEMPT_OFF, ++ TRACE_START, ++}; ++ ++static char *actions[] = { ++ "IRQS_ON", ++ "PREEMPT_ON", ++ "TRACE_STOP", ++ "IRQS_OFF", ++ "PREEMPT_OFF", ++ "TRACE_START", ++}; ++ ++static inline char *getaction(int action) ++{ ++ if (action >= 0 && action <= sizeof(actions)/sizeof(actions[0])) ++ return(actions[action]); ++ return("unknown"); ++} ++ ++#endif /* _LATENCY_HIST_H */ ++ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/trace/events/sched.h sun8i-rt/include/trace/events/sched.h +--- sun8i/include/trace/events/sched.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/include/trace/events/sched.h 2016-08-22 18:27:20.624298758 +0200 +@@ -55,9 +55,9 @@ TRACE_EVENT(sched_kthread_stop_ret, + */ + DECLARE_EVENT_CLASS(sched_wakeup_template, + +- TP_PROTO(struct task_struct *p, int success), ++ TP_PROTO(struct task_struct *p), + +- TP_ARGS(p, success), ++ TP_ARGS(p), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) +@@ -71,25 +71,37 @@ DECLARE_EVENT_CLASS(sched_wakeup_templat + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; +- __entry->success = success; ++ __entry->success = 1; /* rudiment, kill when possible */ + __entry->target_cpu = task_cpu(p); + ), + +- TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d", ++ TP_printk("comm=%s pid=%d prio=%d target_cpu=%03d", + __entry->comm, __entry->pid, __entry->prio, +- __entry->success, __entry->target_cpu) ++ __entry->target_cpu) + ); + ++ /* ++ * Tracepoint called when waking a task; this tracepoint is guaranteed to be ++ * called from the waking context. ++ */ ++DEFINE_EVENT(sched_wakeup_template, sched_waking, ++ TP_PROTO(struct task_struct *p), ++ TP_ARGS(p)); ++ ++ /* ++ * Tracepoint called when the task is actually woken; p->state == TASK_RUNNNG. ++ * It it not always called from the waking context. ++ */ + DEFINE_EVENT(sched_wakeup_template, sched_wakeup, +- TP_PROTO(struct task_struct *p, int success), +- TP_ARGS(p, success)); ++ TP_PROTO(struct task_struct *p), ++ TP_ARGS(p)); + + /* + * Tracepoint for waking up a new task: + */ + DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, +- TP_PROTO(struct task_struct *p, int success), +- TP_ARGS(p, success)); ++ TP_PROTO(struct task_struct *p), ++ TP_ARGS(p)); + + #ifdef CREATE_TRACE_POINTS + static inline long __trace_sched_switch_state(struct task_struct *p) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/include/trace/ftrace.h sun8i-rt/include/trace/ftrace.h +--- sun8i/include/trace/ftrace.h 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/include/trace/ftrace.h 2016-08-22 18:29:19.632300127 +0200 +@@ -530,6 +530,9 @@ ftrace_raw_event_##call(void *__data, pr + \ + local_save_flags(irq_flags); \ + pc = preempt_count(); \ ++ /* Account for tracepoint preempt disable */ \ ++ if (IS_ENABLED(CONFIG_PREEMPT)) \ ++ pc--; \ + \ + __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \ + \ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/init/Kconfig sun8i-rt/init/Kconfig +--- sun8i/init/Kconfig 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/init/Kconfig 2016-08-22 18:18:48.548292871 +0200 +@@ -474,7 +474,7 @@ config RCU_FANOUT_EXACT + + config RCU_FAST_NO_HZ + bool "Accelerate last non-dyntick-idle CPU's grace periods" +- depends on NO_HZ && SMP ++ depends on NO_HZ && SMP && !PREEMPT_RT_FULL + default n + help + This option causes RCU to attempt to accelerate grace periods +@@ -499,7 +499,7 @@ config TREE_RCU_TRACE + config RCU_BOOST + bool "Enable RCU priority boosting" + depends on RT_MUTEXES && PREEMPT_RCU +- default n ++ default y if PREEMPT_RT_FULL + help + This option boosts the priority of preempted RCU readers that + block the current preemptible RCU grace period for too long. +@@ -747,6 +747,7 @@ config RT_GROUP_SCHED + bool "Group scheduling for SCHED_RR/FIFO" + depends on EXPERIMENTAL + depends on CGROUP_SCHED ++ depends on !PREEMPT_RT_FULL + default n + help + This feature lets you explicitly allocate real CPU bandwidth +@@ -1272,6 +1273,7 @@ config SLAB + + config SLUB + bool "SLUB (Unqueued Allocator)" ++ depends on !PREEMPT_RT_FULL + help + SLUB is a slab allocator that minimizes cache line usage + instead of managing queues of cached objects (SLAB approach). +@@ -1283,6 +1285,7 @@ config SLUB + config SLOB + depends on EXPERT + bool "SLOB (Simple Allocator)" ++ depends on !PREEMPT_RT_FULL + help + SLOB replaces the stock allocator with a drastically simpler + allocator. SLOB is generally more space efficient but +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/init/main.c sun8i-rt/init/main.c +--- sun8i/init/main.c 2016-08-22 14:14:41.000000000 +0200 ++++ sun8i-rt/init/main.c 2016-08-22 18:02:00.552281283 +0200 +@@ -68,6 +68,7 @@ + #include + #include + #include ++#include + #include + + #include +@@ -503,6 +504,7 @@ asmlinkage void __init start_kernel(void + setup_command_line(command_line); + setup_nr_cpu_ids(); + setup_per_cpu_areas(); ++ softirq_early_init(); + smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ + + build_all_zonelists(NULL); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/init/Makefile sun8i-rt/init/Makefile +--- sun8i/init/Makefile 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/init/Makefile 2016-08-22 17:58:48.808279078 +0200 +@@ -29,4 +29,4 @@ silent_chk_compile.h = : + include/generated/compile.h: FORCE + @$($(quiet)chk_compile.h) + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \ +- "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)" ++ "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)" +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/ipc/mqueue.c sun8i-rt/ipc/mqueue.c +--- sun8i/ipc/mqueue.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/ipc/mqueue.c 2016-08-22 17:07:34.472243733 +0200 +@@ -813,12 +813,17 @@ static inline void pipelined_send(struct + struct msg_msg *message, + struct ext_wait_queue *receiver) + { ++ /* ++ * Keep them in one critical section for PREEMPT_RT: ++ */ ++ preempt_disable_rt(); + receiver->msg = message; + list_del(&receiver->list); + receiver->state = STATE_PENDING; + wake_up_process(receiver->task); + smp_wmb(); + receiver->state = STATE_READY; ++ preempt_enable_rt(); + } + + /* pipelined_receive() - if there is task waiting in sys_mq_timedsend() +@@ -832,15 +837,19 @@ static inline void pipelined_receive(str + wake_up_interruptible(&info->wait_q); + return; + } ++ /* ++ * Keep them in one critical section for PREEMPT_RT: ++ */ ++ preempt_disable_rt(); + msg_insert(sender->msg, info); + list_del(&sender->list); + sender->state = STATE_PENDING; + wake_up_process(sender->task); + smp_wmb(); + sender->state = STATE_READY; ++ preempt_enable_rt(); + } +- +-SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, ++ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, + size_t, msg_len, unsigned int, msg_prio, + const struct timespec __user *, u_abs_timeout) + { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/ipc/msg.c sun8i-rt/ipc/msg.c +--- sun8i/ipc/msg.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/ipc/msg.c 2016-08-22 17:07:20.728243575 +0200 +@@ -259,12 +259,20 @@ static void expunge_all(struct msg_queue + while (tmp != &msq->q_receivers) { + struct msg_receiver *msr; + ++ /* ++ * Make sure that the wakeup doesnt preempt ++ * this CPU prematurely. (on PREEMPT_RT) ++ */ ++ preempt_disable_rt(); ++ + msr = list_entry(tmp, struct msg_receiver, r_list); + tmp = tmp->next; + msr->r_msg = NULL; + wake_up_process(msr->r_tsk); + smp_mb(); + msr->r_msg = ERR_PTR(res); ++ ++ preempt_enable_rt(); + } + } + +@@ -613,6 +621,12 @@ static inline int pipelined_send(struct + !security_msg_queue_msgrcv(msq, msg, msr->r_tsk, + msr->r_msgtype, msr->r_mode)) { + ++ /* ++ * Make sure that the wakeup doesnt preempt ++ * this CPU prematurely. (on PREEMPT_RT) ++ */ ++ preempt_disable_rt(); ++ + list_del(&msr->r_list); + if (msr->r_maxsize < msg->m_ts) { + msr->r_msg = NULL; +@@ -626,9 +640,11 @@ static inline int pipelined_send(struct + wake_up_process(msr->r_tsk); + smp_mb(); + msr->r_msg = msg; ++ preempt_enable_rt(); + + return 1; + } ++ preempt_enable_rt(); + } + } + return 0; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/ipc/sem.c sun8i-rt/ipc/sem.c +--- sun8i/ipc/sem.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/ipc/sem.c 2016-08-22 17:48:52.404272221 +0200 +@@ -461,6 +461,13 @@ undo: + static void wake_up_sem_queue_prepare(struct list_head *pt, + struct sem_queue *q, int error) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct task_struct *p = q->sleeper; ++ get_task_struct(p); ++ q->status = error; ++ wake_up_process(p); ++ put_task_struct(p); ++#else + if (list_empty(pt)) { + /* + * Hold preempt off so that we don't get preempted and have the +@@ -472,6 +479,7 @@ static void wake_up_sem_queue_prepare(st + q->pid = error; + + list_add_tail(&q->simple_list, pt); ++#endif + } + + /** +@@ -485,6 +493,7 @@ static void wake_up_sem_queue_prepare(st + */ + static void wake_up_sem_queue_do(struct list_head *pt) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + struct sem_queue *q, *t; + int did_something; + +@@ -497,6 +506,7 @@ static void wake_up_sem_queue_do(struct + } + if (did_something) + preempt_enable(); ++#endif + } + + static void unlink_queue(struct sem_array *sma, struct sem_queue *q) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/cpu.c sun8i-rt/kernel/cpu.c +--- sun8i/kernel/cpu.c 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/kernel/cpu.c 2016-08-22 18:16:06.360291007 +0200 +@@ -58,6 +58,284 @@ static struct { + .refcount = 0, + }; + ++/** ++ * hotplug_pcp - per cpu hotplug descriptor ++ * @unplug: set when pin_current_cpu() needs to sync tasks ++ * @sync_tsk: the task that waits for tasks to finish pinned sections ++ * @refcount: counter of tasks in pinned sections ++ * @grab_lock: set when the tasks entering pinned sections should wait ++ * @synced: notifier for @sync_tsk to tell cpu_down it's finished ++ * @mutex: the mutex to make tasks wait (used when @grab_lock is true) ++ * @mutex_init: zero if the mutex hasn't been initialized yet. ++ * ++ * Although @unplug and @sync_tsk may point to the same task, the @unplug ++ * is used as a flag and still exists after @sync_tsk has exited and ++ * @sync_tsk set to NULL. ++ */ ++struct hotplug_pcp { ++ struct task_struct *unplug; ++ struct task_struct *sync_tsk; ++ int refcount; ++ int grab_lock; ++ struct completion synced; ++ struct completion unplug_wait; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ spinlock_t lock; ++#else ++ struct mutex mutex; ++#endif ++ int mutex_init; ++}; ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define hotplug_lock(hp) rt_spin_lock(&(hp)->lock) ++# define hotplug_unlock(hp) rt_spin_unlock(&(hp)->lock) ++#else ++# define hotplug_lock(hp) mutex_lock(&(hp)->mutex) ++# define hotplug_unlock(hp) mutex_unlock(&(hp)->mutex) ++#endif ++ ++static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp); ++ ++/** ++ * pin_current_cpu - Prevent the current cpu from being unplugged ++ * ++ * Lightweight version of get_online_cpus() to prevent cpu from being ++ * unplugged when code runs in a migration disabled region. ++ * ++ * Must be called with preemption disabled (preempt_count = 1)! ++ */ ++void pin_current_cpu(void) ++{ ++ struct hotplug_pcp *hp; ++ int force = 0; ++ ++retry: ++ hp = &__get_cpu_var(hotplug_pcp); ++ ++ if (!hp->unplug || hp->refcount || force || preempt_count() > 1 || ++ hp->unplug == current || (current->flags & PF_STOMPER)) { ++ hp->refcount++; ++ return; ++ } ++ ++ if (hp->grab_lock) { ++ preempt_enable(); ++ hotplug_lock(hp); ++ hotplug_unlock(hp); ++ } else { ++ preempt_enable(); ++ /* ++ * Try to push this task off of this CPU. ++ */ ++ if (!migrate_me()) { ++ preempt_disable(); ++ hp = &__get_cpu_var(hotplug_pcp); ++ if (!hp->grab_lock) { ++ /* ++ * Just let it continue it's already pinned ++ * or about to sleep. ++ */ ++ force = 1; ++ goto retry; ++ } ++ preempt_enable(); ++ } ++ } ++ preempt_disable(); ++ goto retry; ++} ++ ++/** ++ * unpin_current_cpu - Allow unplug of current cpu ++ * ++ * Must be called with preemption or interrupts disabled! ++ */ ++void unpin_current_cpu(void) ++{ ++ struct hotplug_pcp *hp = &__get_cpu_var(hotplug_pcp); ++ ++ WARN_ON(hp->refcount <= 0); ++ ++ /* This is safe. sync_unplug_thread is pinned to this cpu */ ++ if (!--hp->refcount && hp->unplug && hp->unplug != current && ++ !(current->flags & PF_STOMPER)) ++ wake_up_process(hp->unplug); ++} ++ ++static void wait_for_pinned_cpus(struct hotplug_pcp *hp) ++{ ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ while (hp->refcount) { ++ schedule_preempt_disabled(); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ } ++} ++ ++static int sync_unplug_thread(void *data) ++{ ++ struct hotplug_pcp *hp = data; ++ ++ wait_for_completion(&hp->unplug_wait); ++ preempt_disable(); ++ hp->unplug = current; ++ wait_for_pinned_cpus(hp); ++ ++ /* ++ * This thread will synchronize the cpu_down() with threads ++ * that have pinned the CPU. When the pinned CPU count reaches ++ * zero, we inform the cpu_down code to continue to the next step. ++ */ ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ preempt_enable(); ++ complete(&hp->synced); ++ ++ /* ++ * If all succeeds, the next step will need tasks to wait till ++ * the CPU is offline before continuing. To do this, the grab_lock ++ * is set and tasks going into pin_current_cpu() will block on the ++ * mutex. But we still need to wait for those that are already in ++ * pinned CPU sections. If the cpu_down() failed, the kthread_should_stop() ++ * will kick this thread out. ++ */ ++ while (!hp->grab_lock && !kthread_should_stop()) { ++ schedule(); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ } ++ ++ /* Make sure grab_lock is seen before we see a stale completion */ ++ smp_mb(); ++ ++ /* ++ * Now just before cpu_down() enters stop machine, we need to make ++ * sure all tasks that are in pinned CPU sections are out, and new ++ * tasks will now grab the lock, keeping them from entering pinned ++ * CPU sections. ++ */ ++ if (!kthread_should_stop()) { ++ preempt_disable(); ++ wait_for_pinned_cpus(hp); ++ preempt_enable(); ++ complete(&hp->synced); ++ } ++ ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ while (!kthread_should_stop()) { ++ schedule(); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ } ++ set_current_state(TASK_RUNNING); ++ ++ /* ++ * Force this thread off this CPU as it's going down and ++ * we don't want any more work on this CPU. ++ */ ++ current->flags &= ~PF_THREAD_BOUND; ++ do_set_cpus_allowed(current, cpu_present_mask); ++ migrate_me(); ++ return 0; ++} ++ ++static void __cpu_unplug_sync(struct hotplug_pcp *hp) ++{ ++ wake_up_process(hp->sync_tsk); ++ wait_for_completion(&hp->synced); ++} ++ ++static void __cpu_unplug_wait(unsigned int cpu) ++{ ++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); ++ ++ complete(&hp->unplug_wait); ++ wait_for_completion(&hp->synced); ++} ++ ++/* ++ * Start the sync_unplug_thread on the target cpu and wait for it to ++ * complete. ++ */ ++static int cpu_unplug_begin(unsigned int cpu) ++{ ++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); ++ int err; ++ ++ /* Protected by cpu_hotplug.lock */ ++ if (!hp->mutex_init) { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ spin_lock_init(&hp->lock); ++#else ++ mutex_init(&hp->mutex); ++#endif ++ hp->mutex_init = 1; ++ } ++ ++ /* Inform the scheduler to migrate tasks off this CPU */ ++ tell_sched_cpu_down_begin(cpu); ++ ++ init_completion(&hp->synced); ++ init_completion(&hp->unplug_wait); ++ ++ hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); ++ if (IS_ERR(hp->sync_tsk)) { ++ err = PTR_ERR(hp->sync_tsk); ++ hp->sync_tsk = NULL; ++ return err; ++ } ++ kthread_bind(hp->sync_tsk, cpu); ++ ++ /* ++ * Wait for tasks to get out of the pinned sections, ++ * it's still OK if new tasks enter. Some CPU notifiers will ++ * wait for tasks that are going to enter these sections and ++ * we must not have them block. ++ */ ++ wake_up_process(hp->sync_tsk); ++ return 0; ++} ++ ++static void cpu_unplug_sync(unsigned int cpu) ++{ ++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); ++ ++ init_completion(&hp->synced); ++ /* The completion needs to be initialzied before setting grab_lock */ ++ smp_wmb(); ++ ++ /* Grab the mutex before setting grab_lock */ ++ hotplug_lock(hp); ++ hp->grab_lock = 1; ++ ++ /* ++ * The CPU notifiers have been completed. ++ * Wait for tasks to get out of pinned CPU sections and have new ++ * tasks block until the CPU is completely down. ++ */ ++ __cpu_unplug_sync(hp); ++ ++ /* All done with the sync thread */ ++ kthread_stop(hp->sync_tsk); ++ hp->sync_tsk = NULL; ++} ++ ++static void cpu_unplug_done(unsigned int cpu) ++{ ++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); ++ ++ hp->unplug = NULL; ++ /* Let all tasks know cpu unplug is finished before cleaning up */ ++ smp_wmb(); ++ ++ if (hp->sync_tsk) ++ kthread_stop(hp->sync_tsk); ++ ++ if (hp->grab_lock) { ++ hotplug_unlock(hp); ++ /* protected by cpu_hotplug.lock */ ++ hp->grab_lock = 0; ++ } ++ tell_sched_cpu_down_done(cpu); ++} ++ + void get_online_cpus(void) + { + might_sleep(); +@@ -231,13 +509,15 @@ static int __ref take_cpu_down(void *_pa + /* Requires cpu_add_remove_lock to be held */ + static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) + { +- int err, nr_calls = 0; ++ int mycpu, err, nr_calls = 0; + void *hcpu = (void *)(long)cpu; + unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; + struct take_cpu_down_param tcd_param = { + .mod = mod, + .hcpu = hcpu, + }; ++ cpumask_var_t cpumask; ++ cpumask_var_t cpumask_org; + + if (num_online_cpus() == 1) + return -EBUSY; +@@ -245,7 +525,34 @@ static int __ref _cpu_down(unsigned int + if (!cpu_online(cpu)) + return -EINVAL; + ++ /* Move the downtaker off the unplug cpu */ ++ if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) ++ return -ENOMEM; ++ if (!alloc_cpumask_var(&cpumask_org, GFP_KERNEL)) { ++ free_cpumask_var(cpumask); ++ return -ENOMEM; ++ } ++ ++ cpumask_copy(cpumask_org, tsk_cpus_allowed(current)); ++ cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu)); ++ set_cpus_allowed_ptr(current, cpumask); ++ free_cpumask_var(cpumask); ++ migrate_disable(); ++ mycpu = smp_processor_id(); ++ if (mycpu == cpu) { ++ printk(KERN_ERR "Yuck! Still on unplug CPU\n!"); ++ migrate_enable(); ++ err = -EBUSY; ++ goto restore_cpus; ++ } ++ migrate_enable(); ++ + cpu_hotplug_begin(); ++ err = cpu_unplug_begin(cpu); ++ if (err) { ++ printk("cpu_unplug_begin(%d) failed\n", cpu); ++ goto out_cancel; ++ } + + err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); + if (err) { +@@ -256,6 +563,11 @@ static int __ref _cpu_down(unsigned int + goto out_release; + } + ++ __cpu_unplug_wait(cpu); ++ ++ /* Notifiers are done. Don't let any more tasks pin this CPU. */ ++ cpu_unplug_sync(cpu); ++ + err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); + if (err) { + /* CPU didn't die: tell everyone. Can't complain. */ +@@ -284,9 +596,14 @@ static int __ref _cpu_down(unsigned int + check_for_tasks(cpu); + + out_release: ++ cpu_unplug_done(cpu); ++out_cancel: + cpu_hotplug_done(); + if (!err) + cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); ++restore_cpus: ++ set_cpus_allowed_ptr(current, cpumask_org); ++ free_cpumask_var(cpumask_org); + return err; + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/cred.c sun8i-rt/kernel/cred.c +--- sun8i/kernel/cred.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/cred.c 2016-08-22 16:22:53.940212916 +0200 +@@ -36,7 +36,7 @@ static struct kmem_cache *cred_jar; + static struct thread_group_cred init_tgcred = { + .usage = ATOMIC_INIT(2), + .tgid = 0, +- .lock = __SPIN_LOCK_UNLOCKED(init_cred.tgcred.lock), ++ .lock = __SPIN_LOCK_UNLOCKED(init_tgcred.lock), + }; + #endif + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/debug/kdb/kdb_io.c sun8i-rt/kernel/debug/kdb/kdb_io.c +--- sun8i/kernel/debug/kdb/kdb_io.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/debug/kdb/kdb_io.c 2016-08-22 17:48:05.632271684 +0200 +@@ -562,7 +562,6 @@ int vkdb_printf(const char *fmt, va_list + int linecount; + int colcount; + int logging, saved_loglevel = 0; +- int saved_trap_printk; + int got_printf_lock = 0; + int retlen = 0; + int fnd, len; +@@ -573,8 +572,6 @@ int vkdb_printf(const char *fmt, va_list + unsigned long uninitialized_var(flags); + + preempt_disable(); +- saved_trap_printk = kdb_trap_printk; +- kdb_trap_printk = 0; + + /* Serialize kdb_printf if multiple cpus try to write at once. + * But if any cpu goes recursive in kdb, just print the output, +@@ -852,7 +849,6 @@ kdb_print_out: + } else { + __release(kdb_printf_lock); + } +- kdb_trap_printk = saved_trap_printk; + preempt_enable(); + return retlen; + } +@@ -862,9 +858,11 @@ int kdb_printf(const char *fmt, ...) + va_list ap; + int r; + ++ kdb_trap_printk++; + va_start(ap, fmt); + r = vkdb_printf(fmt, ap); + va_end(ap); ++ kdb_trap_printk--; + + return r; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/events/core.c sun8i-rt/kernel/events/core.c +--- sun8i/kernel/events/core.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/kernel/events/core.c 2016-08-22 18:00:51.692280491 +0200 +@@ -5589,6 +5589,7 @@ static void perf_swevent_init_hrtimer(st + + hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hwc->hrtimer.function = perf_swevent_hrtimer; ++ hwc->hrtimer.irqsafe = 1; + + /* + * Since hrtimers have a fixed rate, we can do a static freq->period +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/exit.c sun8i-rt/kernel/exit.c +--- sun8i/kernel/exit.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/kernel/exit.c 2016-08-22 16:02:09.040198603 +0200 +@@ -144,7 +144,7 @@ static void __exit_signal(struct task_st + * Do this under ->siglock, we can race with another thread + * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. + */ +- flush_sigqueue(&tsk->pending); ++ flush_task_sigqueue(tsk); + tsk->sighand = NULL; + spin_unlock(&sighand->siglock); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/fork.c sun8i-rt/kernel/fork.c +--- sun8i/kernel/fork.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/kernel/fork.c 2016-08-22 17:34:17.240262160 +0200 +@@ -91,7 +91,7 @@ int max_threads; /* tunable limit on nr + + DEFINE_PER_CPU(unsigned long, process_counts) = 0; + +-__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ ++DEFINE_RWLOCK(tasklist_lock); /* outer */ + + #ifdef CONFIG_PROVE_RCU + int lockdep_tasklist_lock_is_held(void) +@@ -218,7 +218,18 @@ void __put_task_struct(struct task_struc + if (!profile_handoff_task(tsk)) + free_task(tsk); + } ++#ifndef CONFIG_PREEMPT_RT_BASE + EXPORT_SYMBOL_GPL(__put_task_struct); ++#else ++void __put_task_struct_cb(struct rcu_head *rhp) ++{ ++ struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu); ++ ++ __put_task_struct(tsk); ++ ++} ++EXPORT_SYMBOL_GPL(__put_task_struct_cb); ++#endif + + /* + * macro override instead of weak attribute alias, to workaround +@@ -579,6 +590,19 @@ void __mmdrop(struct mm_struct *mm) + } + EXPORT_SYMBOL_GPL(__mmdrop); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++/* ++ * RCU callback for delayed mm drop. Not strictly rcu, but we don't ++ * want another facility to make this work. ++ */ ++void __mmdrop_delayed(struct rcu_head *rhp) ++{ ++ struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); ++ ++ __mmdrop(mm); ++} ++#endif ++ + /* + * Decrement the use count and release all resources for an mm. + */ +@@ -1123,6 +1147,9 @@ void mm_init_owner(struct mm_struct *mm, + */ + static void posix_cpu_timers_init(struct task_struct *tsk) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ tsk->posix_timer_list = NULL; ++#endif + tsk->cputime_expires.prof_exp = 0; + tsk->cputime_expires.virt_exp = 0; + tsk->cputime_expires.sched_exp = 0; +@@ -1230,6 +1257,7 @@ static struct task_struct *copy_process( + spin_lock_init(&p->alloc_lock); + + init_sigpending(&p->pending); ++ p->sigqueue_cache = NULL; + + p->utime = p->stime = p->gtime = 0; + p->utimescaled = p->stimescaled = 0; +@@ -1288,6 +1316,9 @@ static struct task_struct *copy_process( + p->hardirq_context = 0; + p->softirq_context = 0; + #endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++ p->pagefault_disabled = 0; ++#endif + #ifdef CONFIG_LOCKDEP + p->lockdep_depth = 0; /* no locks held yet */ + p->curr_chain_key = 0; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/futex.c sun8i-rt/kernel/futex.c +--- sun8i/kernel/futex.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/kernel/futex.c 2016-08-22 18:23:21.740296012 +0200 +@@ -646,95 +646,89 @@ void exit_pi_state_list(struct task_stru + * [10] There is no transient state which leaves owner and user space + * TID out of sync. + */ +-static int +-lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, +- union futex_key *key, struct futex_pi_state **ps) ++ ++/* ++ * Validate that the existing waiter has a pi_state and sanity check ++ * the pi_state against the user space value. If correct, attach to ++ * it. ++ */ ++static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state, ++ struct futex_pi_state **ps) + { +- struct futex_pi_state *pi_state = NULL; +- struct futex_q *this, *next; +- struct plist_head *head; +- struct task_struct *p; + pid_t pid = uval & FUTEX_TID_MASK; + +- head = &hb->chain; ++ /* ++ * Userspace might have messed up non-PI and PI futexes [3] ++ */ ++ if (unlikely(!pi_state)) ++ return -EINVAL; + +- plist_for_each_entry_safe(this, next, head, list) { +- if (match_futex(&this->key, key)) { +- /* +- * Sanity check the waiter before increasing +- * the refcount and attaching to it. +- */ +- pi_state = this->pi_state; ++ WARN_ON(!atomic_read(&pi_state->refcount)); ++ ++ /* ++ * Handle the owner died case: ++ */ ++ if (uval & FUTEX_OWNER_DIED) { ++ /* ++ * exit_pi_state_list sets owner to NULL and wakes the ++ * topmost waiter. The task which acquires the ++ * pi_state->rt_mutex will fixup owner. ++ */ ++ if (!pi_state->owner) { + /* +- * Userspace might have messed up non-PI and +- * PI futexes [3] ++ * No pi state owner, but the user space TID ++ * is not 0. Inconsistent state. [5] + */ +- if (unlikely(!pi_state)) ++ if (pid) + return -EINVAL; +- +- WARN_ON(!atomic_read(&pi_state->refcount)); +- + /* +- * Handle the owner died case: ++ * Take a ref on the state and return success. [4] + */ +- if (uval & FUTEX_OWNER_DIED) { +- /* +- * exit_pi_state_list sets owner to NULL and +- * wakes the topmost waiter. The task which +- * acquires the pi_state->rt_mutex will fixup +- * owner. +- */ +- if (!pi_state->owner) { +- /* +- * No pi state owner, but the user +- * space TID is not 0. Inconsistent +- * state. [5] +- */ +- if (pid) +- return -EINVAL; +- /* +- * Take a ref on the state and +- * return. [4] +- */ +- goto out_state; +- } ++ goto out_state; ++ } + +- /* +- * If TID is 0, then either the dying owner +- * has not yet executed exit_pi_state_list() +- * or some waiter acquired the rtmutex in the +- * pi state, but did not yet fixup the TID in +- * user space. +- * +- * Take a ref on the state and return. [6] +- */ +- if (!pid) +- goto out_state; +- } else { +- /* +- * If the owner died bit is not set, +- * then the pi_state must have an +- * owner. [7] +- */ +- if (!pi_state->owner) +- return -EINVAL; +- } ++ /* ++ * If TID is 0, then either the dying owner has not ++ * yet executed exit_pi_state_list() or some waiter ++ * acquired the rtmutex in the pi state, but did not ++ * yet fixup the TID in user space. ++ * ++ * Take a ref on the state and return success. [6] ++ */ ++ if (!pid) ++ goto out_state; ++ } else { ++ /* ++ * If the owner died bit is not set, then the pi_state ++ * must have an owner. [7] ++ */ ++ if (!pi_state->owner) ++ return -EINVAL; ++ } + +- /* +- * Bail out if user space manipulated the +- * futex value. If pi state exists then the +- * owner TID must be the same as the user +- * space TID. [9/10] +- */ +- if (pid != task_pid_vnr(pi_state->owner)) +- return -EINVAL; ++ /* ++ * Bail out if user space manipulated the futex value. If pi ++ * state exists then the owner TID must be the same as the ++ * user space TID. [9/10] ++ */ ++ if (pid != task_pid_vnr(pi_state->owner)) ++ return -EINVAL; ++out_state: ++ atomic_inc(&pi_state->refcount); ++ *ps = pi_state; ++ return 0; ++} + +- out_state: +- atomic_inc(&pi_state->refcount); +- *ps = pi_state; +- return 0; +- } +- } ++/* ++ * Lookup the task for the TID provided from user space and attach to ++ * it after doing proper sanity checks. ++ */ ++static int attach_to_pi_owner(u32 uval, union futex_key *key, ++ struct futex_pi_state **ps) ++{ ++ pid_t pid = uval & FUTEX_TID_MASK; ++ struct futex_pi_state *pi_state; ++ struct task_struct *p; + + /* + * We are the first waiter - try to look up the real owner and attach +@@ -777,7 +771,7 @@ lookup_pi_state(u32 uval, struct futex_h + pi_state = alloc_pi_state(); + + /* +- * Initialize the pi_mutex in locked state and make 'p' ++ * Initialize the pi_mutex in locked state and make @p + * the owner of it: + */ + rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p); +@@ -797,6 +791,36 @@ lookup_pi_state(u32 uval, struct futex_h + return 0; + } + ++static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, ++ union futex_key *key, struct futex_pi_state **ps) ++{ ++ struct futex_q *match = futex_top_waiter(hb, key); ++ ++ /* ++ * If there is a waiter on that futex, validate it and ++ * attach to the pi_state when the validation succeeds. ++ */ ++ if (match) ++ return attach_to_pi_state(uval, match->pi_state, ps); ++ ++ /* ++ * We are the first waiter - try to look up the owner based on ++ * @uval and attach to it. ++ */ ++ return attach_to_pi_owner(uval, key, ps); ++} ++ ++static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval) ++{ ++ u32 uninitialized_var(curval); ++ ++ if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))) ++ return -EFAULT; ++ ++ /*If user space value changed, let the caller retry */ ++ return curval != uval ? -EAGAIN : 0; ++} ++ + /** + * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex + * @uaddr: the pi futex user address +@@ -820,113 +844,69 @@ static int futex_lock_pi_atomic(u32 __us + struct futex_pi_state **ps, + struct task_struct *task, int set_waiters) + { +- int lock_taken, ret, force_take = 0; +- u32 uval, newval, curval, vpid = task_pid_vnr(task); +- +-retry: +- ret = lock_taken = 0; ++ u32 uval, newval, vpid = task_pid_vnr(task); ++ struct futex_q *match; ++ int ret; + + /* +- * To avoid races, we attempt to take the lock here again +- * (by doing a 0 -> TID atomic cmpxchg), while holding all +- * the locks. It will most likely not succeed. ++ * Read the user space value first so we can validate a few ++ * things before proceeding further. + */ +- newval = vpid; +- if (set_waiters) +- newval |= FUTEX_WAITERS; +- +- if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval))) ++ if (get_futex_value_locked(&uval, uaddr)) + return -EFAULT; + + /* + * Detect deadlocks. + */ +- if ((unlikely((curval & FUTEX_TID_MASK) == vpid))) ++ if ((unlikely((uval & FUTEX_TID_MASK) == vpid))) + return -EDEADLK; + + /* +- * Surprise - we got the lock, but we do not trust user space at all. +- */ +- if (unlikely(!curval)) { +- /* +- * We verify whether there is kernel state for this +- * futex. If not, we can safely assume, that the 0 -> +- * TID transition is correct. If state exists, we do +- * not bother to fixup the user space state as it was +- * corrupted already. +- */ +- return futex_top_waiter(hb, key) ? -EINVAL : 1; +- } +- +- uval = curval; +- +- /* +- * Set the FUTEX_WAITERS flag, so the owner will know it has someone +- * to wake at the next unlock. ++ * Lookup existing state first. If it exists, try to attach to ++ * its pi_state. + */ +- newval = curval | FUTEX_WAITERS; ++ match = futex_top_waiter(hb, key); ++ if (match) ++ return attach_to_pi_state(uval, match->pi_state, ps); + + /* +- * Should we force take the futex? See below. ++ * No waiter and user TID is 0. We are here because the ++ * waiters or the owner died bit is set or called from ++ * requeue_cmp_pi or for whatever reason something took the ++ * syscall. + */ +- if (unlikely(force_take)) { ++ if (!(uval & FUTEX_TID_MASK)) { + /* +- * Keep the OWNER_DIED and the WAITERS bit and set the +- * new TID value. ++ * We take over the futex. No other waiters and the user space ++ * TID is 0. We preserve the owner died bit. + */ +- newval = (curval & ~FUTEX_TID_MASK) | vpid; +- force_take = 0; +- lock_taken = 1; +- } ++ newval = uval & FUTEX_OWNER_DIED; ++ newval |= vpid; + +- if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))) +- return -EFAULT; +- if (unlikely(curval != uval)) +- goto retry; ++ /* The futex requeue_pi code can enforce the waiters bit */ ++ if (set_waiters) ++ newval |= FUTEX_WAITERS; ++ ++ ret = lock_pi_update_atomic(uaddr, uval, newval); ++ /* If the take over worked, return 1 */ ++ return ret < 0 ? ret : 1; ++ } + + /* +- * We took the lock due to forced take over. ++ * First waiter. Set the waiters bit before attaching ourself to ++ * the owner. If owner tries to unlock, it will be forced into ++ * the kernel and blocked on hb->lock. + */ +- if (unlikely(lock_taken)) +- return 1; +- ++ newval = uval | FUTEX_WAITERS; ++ ret = lock_pi_update_atomic(uaddr, uval, newval); ++ if (ret) ++ return ret; + /* +- * We dont have the lock. Look up the PI state (or create it if +- * we are the first waiter): ++ * If the update of the user space value succeeded, we try to ++ * attach to the owner. If that fails, no harm done, we only ++ * set the FUTEX_WAITERS bit in the user space variable. + */ +- ret = lookup_pi_state(uval, hb, key, ps); +- +- if (unlikely(ret)) { +- switch (ret) { +- case -ESRCH: +- /* +- * We failed to find an owner for this +- * futex. So we have no pi_state to block +- * on. This can happen in two cases: +- * +- * 1) The owner died +- * 2) A stale FUTEX_WAITERS bit +- * +- * Re-read the futex value. +- */ +- if (get_futex_value_locked(&curval, uaddr)) +- return -EFAULT; +- +- /* +- * If the owner died or we have a stale +- * WAITERS bit the owner TID in the user space +- * futex is 0. +- */ +- if (!(curval & FUTEX_TID_MASK)) { +- force_take = 1; +- goto retry; +- } +- default: +- break; +- } +- } +- +- return ret; ++ return attach_to_pi_owner(uval, key, ps); + } + + /** +@@ -1042,22 +1022,6 @@ static int wake_futex_pi(u32 __user *uad + return 0; + } + +-static int unlock_futex_pi(u32 __user *uaddr, u32 uval) +-{ +- u32 uninitialized_var(oldval); +- +- /* +- * There is no waiter, so we unlock the futex. The owner died +- * bit has not to be preserved here. We are the owner: +- */ +- if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0)) +- return -EFAULT; +- if (oldval != uval) +- return -EAGAIN; +- +- return 0; +-} +- + /* + * Express the locking dependencies for lockdep: + */ +@@ -1514,7 +1478,12 @@ retry_private: + goto retry; + goto out; + case -EAGAIN: +- /* The owner was exiting, try again. */ ++ /* ++ * Two reasons for this: ++ * - Owner is exiting and we just wait for the ++ * exit to complete. ++ * - The user space value changed. ++ */ + free_pi_state(pi_state); + pi_state = NULL; + double_unlock_hb(hb1, hb2); +@@ -1575,12 +1544,22 @@ retry_private: + this->pi_state = pi_state; + ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex, + this->rt_waiter, +- this->task, 1); ++ this->task); + if (ret == 1) { + /* We got the lock. */ + requeue_pi_wake_futex(this, &key2, hb2); + drop_count++; + continue; ++ } else if (ret == -EAGAIN) { ++ /* ++ * Waiter was woken by timeout or ++ * signal and has set pi_blocked_on to ++ * PI_WAKEUP_INPROGRESS before we ++ * tried to enqueue it on the rtmutex. ++ */ ++ this->pi_state = NULL; ++ free_pi_state(pi_state); ++ continue; + } else if (ret) { + /* -EDEADLK */ + this->pi_state = NULL; +@@ -2159,8 +2138,10 @@ retry_private: + goto uaddr_faulted; + case -EAGAIN: + /* +- * Task is exiting and we just wait for the +- * exit to complete. ++ * Two reasons for this: ++ * - Task is exiting and we just wait for the ++ * exit to complete. ++ * - The user space value changed. + */ + queue_unlock(&q, hb); + put_futex_key(&q.key); +@@ -2180,9 +2161,9 @@ retry_private: + /* + * Block on the PI mutex: + */ +- if (!trylock) +- ret = rt_mutex_timed_lock(&q.pi_state->pi_mutex, to, 1); +- else { ++ if (!trylock) { ++ ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to); ++ } else { + ret = rt_mutex_trylock(&q.pi_state->pi_mutex); + /* Fixup the trylock return value: */ + ret = ret ? 0 : -EWOULDBLOCK; +@@ -2244,11 +2225,10 @@ uaddr_faulted: + */ + static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) + { +- struct futex_hash_bucket *hb; +- struct futex_q *this, *next; +- struct plist_head *head; ++ u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current); + union futex_key key = FUTEX_KEY_INIT; +- u32 uval, vpid = task_pid_vnr(current); ++ struct futex_hash_bucket *hb; ++ struct futex_q *match; + int ret; + + retry: +@@ -2261,61 +2241,50 @@ retry: + return -EPERM; + + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE); +- if (unlikely(ret != 0)) +- goto out; ++ if (ret) ++ return ret; + + hb = hash_futex(&key); + spin_lock(&hb->lock); + + /* +- * To avoid races, try to do the TID -> 0 atomic transition +- * again. If it succeeds then we can return without waking +- * anyone else up. We only try this if neither the waiters nor +- * the owner died bit are set. +- */ +- if (!(uval & ~FUTEX_TID_MASK) && +- cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0)) +- goto pi_faulted; +- /* +- * Rare case: we managed to release the lock atomically, +- * no need to wake anyone else up: +- */ +- if (unlikely(uval == vpid)) +- goto out_unlock; +- +- /* +- * Ok, other tasks may need to be woken up - check waiters +- * and do the wakeup if necessary: ++ * Check waiters first. We do not trust user space values at ++ * all and we at least want to know if user space fiddled ++ * with the futex value instead of blindly unlocking. + */ +- head = &hb->chain; +- +- plist_for_each_entry_safe(this, next, head, list) { +- if (!match_futex (&this->key, &key)) +- continue; +- ret = wake_futex_pi(uaddr, uval, this); ++ match = futex_top_waiter(hb, &key); ++ if (match) { ++ ret = wake_futex_pi(uaddr, uval, match); + /* +- * The atomic access to the futex value +- * generated a pagefault, so retry the +- * user-access and the wakeup: ++ * The atomic access to the futex value generated a ++ * pagefault, so retry the user-access and the wakeup: + */ + if (ret == -EFAULT) + goto pi_faulted; + goto out_unlock; + } ++ + /* +- * No waiters - kernel unlocks the futex: ++ * We have no kernel internal state, i.e. no waiters in the ++ * kernel. Waiters which are about to queue themselves are stuck ++ * on hb->lock. So we can safely ignore them. We do neither ++ * preserve the WAITERS bit not the OWNER_DIED one. We are the ++ * owner. + */ +- ret = unlock_futex_pi(uaddr, uval); +- if (ret == -EFAULT) ++ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) + goto pi_faulted; + ++ /* ++ * If uval has changed, let user space handle it. ++ */ ++ ret = (curval == uval) ? 0 : -EAGAIN; ++ + out_unlock: + spin_unlock(&hb->lock); + put_futex_key(&key); +- +-out: + return ret; + ++ + pi_faulted: + spin_unlock(&hb->lock); + put_futex_key(&key); +@@ -2423,7 +2392,7 @@ static int futex_wait_requeue_pi(u32 __u + struct hrtimer_sleeper timeout, *to = NULL; + struct rt_mutex_waiter rt_waiter; + struct rt_mutex *pi_mutex = NULL; +- struct futex_hash_bucket *hb; ++ struct futex_hash_bucket *hb, *hb2; + union futex_key key2 = FUTEX_KEY_INIT; + struct futex_q q = futex_q_init; + int res, ret; +@@ -2448,8 +2417,7 @@ static int futex_wait_requeue_pi(u32 __u + * The waiter is allocated on our stack, manipulated by the requeue + * code while we sleep on uaddr. + */ +- debug_rt_mutex_init_waiter(&rt_waiter); +- rt_waiter.task = NULL; ++ rt_mutex_init_waiter(&rt_waiter, false); + + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); + if (unlikely(ret != 0)) +@@ -2489,20 +2457,55 @@ static int futex_wait_requeue_pi(u32 __u + /* Queue the futex_q, drop the hb lock, wait for wakeup. */ + futex_wait_queue_me(hb, &q, to); + +- spin_lock(&hb->lock); +- ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); +- spin_unlock(&hb->lock); +- if (ret) +- goto out_put_keys; ++ /* ++ * On RT we must avoid races with requeue and trying to block ++ * on two mutexes (hb->lock and uaddr2's rtmutex) by ++ * serializing access to pi_blocked_on with pi_lock. ++ */ ++ raw_spin_lock_irq(¤t->pi_lock); ++ if (current->pi_blocked_on) { ++ /* ++ * We have been requeued or are in the process of ++ * being requeued. ++ */ ++ raw_spin_unlock_irq(¤t->pi_lock); ++ } else { ++ /* ++ * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS ++ * prevents a concurrent requeue from moving us to the ++ * uaddr2 rtmutex. After that we can safely acquire ++ * (and possibly block on) hb->lock. ++ */ ++ current->pi_blocked_on = PI_WAKEUP_INPROGRESS; ++ raw_spin_unlock_irq(¤t->pi_lock); ++ ++ spin_lock(&hb->lock); ++ ++ /* ++ * Clean up pi_blocked_on. We might leak it otherwise ++ * when we succeeded with the hb->lock in the fast ++ * path. ++ */ ++ raw_spin_lock_irq(¤t->pi_lock); ++ current->pi_blocked_on = NULL; ++ raw_spin_unlock_irq(¤t->pi_lock); ++ ++ ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); ++ spin_unlock(&hb->lock); ++ if (ret) ++ goto out_put_keys; ++ } + + /* +- * In order for us to be here, we know our q.key == key2, and since +- * we took the hb->lock above, we also know that futex_requeue() has +- * completed and we no longer have to concern ourselves with a wakeup +- * race with the atomic proxy lock acquisition by the requeue code. The +- * futex_requeue dropped our key1 reference and incremented our key2 +- * reference count. ++ * In order to be here, we have either been requeued, are in ++ * the process of being requeued, or requeue successfully ++ * acquired uaddr2 on our behalf. If pi_blocked_on was ++ * non-null above, we may be racing with a requeue. Do not ++ * rely on q->lock_ptr to be hb2->lock until after blocking on ++ * hb->lock or hb2->lock. The futex_requeue dropped our key1 ++ * reference and incremented our key2 reference count. + */ ++ hb2 = hash_futex(&key2); + + /* Check if the requeue code acquired the second futex for us. */ + if (!q.rt_waiter) { +@@ -2511,9 +2514,10 @@ static int futex_wait_requeue_pi(u32 __u + * did a lock-steal - fix up the PI-state in that case. + */ + if (q.pi_state && (q.pi_state->owner != current)) { +- spin_lock(q.lock_ptr); ++ spin_lock(&hb2->lock); ++ BUG_ON(&hb2->lock != q.lock_ptr); + ret = fixup_pi_state_owner(uaddr2, &q, current); +- spin_unlock(q.lock_ptr); ++ spin_unlock(&hb2->lock); + } + } else { + /* +@@ -2523,10 +2527,11 @@ static int futex_wait_requeue_pi(u32 __u + */ + WARN_ON(!q.pi_state); + pi_mutex = &q.pi_state->pi_mutex; +- ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1); ++ ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter); + debug_rt_mutex_free_waiter(&rt_waiter); + +- spin_lock(q.lock_ptr); ++ spin_lock(&hb2->lock); ++ BUG_ON(&hb2->lock != q.lock_ptr); + /* + * Fixup the pi_state owner and possibly acquire the lock if we + * haven't already. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/hrtimer.c sun8i-rt/kernel/hrtimer.c +--- sun8i/kernel/hrtimer.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/kernel/hrtimer.c 2016-08-22 18:19:47.396293548 +0200 +@@ -50,6 +50,7 @@ + #include + + #include ++#include + + /* + * The timer bases: +@@ -616,8 +617,7 @@ static int hrtimer_reprogram(struct hrti + * When the callback is running, we do not reprogram the clock event + * device. The timer callback is either running on a different CPU or + * the callback is executed in the hrtimer_interrupt context. The +- * reprogramming is handled either by the softirq, which called the +- * callback or at the end of the hrtimer_interrupt. ++ * reprogramming is handled at the end of the hrtimer_interrupt. + */ + if (hrtimer_callback_running(timer)) + return 0; +@@ -652,6 +652,9 @@ static int hrtimer_reprogram(struct hrti + return res; + } + ++static void __run_hrtimer(struct hrtimer *timer, ktime_t *now); ++static int hrtimer_rt_defer(struct hrtimer *timer); ++ + /* + * Initialize the high resolution related parts of cpu_base + */ +@@ -760,6 +763,11 @@ static inline int hrtimer_enqueue_reprog + } + static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { } + static inline void retrigger_next_event(void *arg) { } ++static inline int hrtimer_reprogram(struct hrtimer *timer, ++ struct hrtimer_clock_base *base) ++{ ++ return 0; ++} + + #endif /* CONFIG_HIGH_RES_TIMERS */ + +@@ -879,6 +887,32 @@ u64 hrtimer_forward(struct hrtimer *time + } + EXPORT_SYMBOL_GPL(hrtimer_forward); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define wake_up_timer_waiters(b) wake_up(&(b)->wait) ++ ++/** ++ * hrtimer_wait_for_timer - Wait for a running timer ++ * ++ * @timer: timer to wait for ++ * ++ * The function waits in case the timers callback function is ++ * currently executed on the waitqueue of the timer base. The ++ * waitqueue is woken up after the timer callback function has ++ * finished execution. ++ */ ++void hrtimer_wait_for_timer(const struct hrtimer *timer) ++{ ++ struct hrtimer_clock_base *base = timer->base; ++ ++ if (base && base->cpu_base && !timer->irqsafe) ++ wait_event(base->cpu_base->wait, ++ !(timer->state & HRTIMER_STATE_CALLBACK)); ++} ++ ++#else ++# define wake_up_timer_waiters(b) do { } while (0) ++#endif ++ + /* + * enqueue_hrtimer - internal function to (re)start a timer + * +@@ -922,6 +956,11 @@ static void __remove_hrtimer(struct hrti + if (!(timer->state & HRTIMER_STATE_ENQUEUED)) + goto out; + ++ if (unlikely(!list_empty(&timer->cb_entry))) { ++ list_del_init(&timer->cb_entry); ++ goto out; ++ } ++ + next_timer = timerqueue_getnext(&base->active); + timerqueue_del(&base->active, &timer->node); + if (&timer->node == next_timer) { +@@ -1008,6 +1047,17 @@ int __hrtimer_start_range_ns(struct hrti + /* Switch the timer base, if necessary: */ + new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); + ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ { ++ ktime_t now = new_base->get_time(); ++ ++ if (ktime_to_ns(tim) < ktime_to_ns(now)) ++ timer->praecox = now; ++ else ++ timer->praecox = ktime_set(0, 0); ++ } ++#endif ++ + timer_stats_hrtimer_set_start_info(timer); + + leftmost = enqueue_hrtimer(timer, new_base); +@@ -1020,7 +1070,17 @@ int __hrtimer_start_range_ns(struct hrti + */ + if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases) + && hrtimer_enqueue_reprogram(timer, new_base)) { +- if (wakeup) { ++ ++ if (wakeup ++#ifdef CONFIG_PREEMPT_RT_BASE ++ /* ++ * Move softirq based timers away from the rbtree in ++ * case it expired already. Otherwise we would have a ++ * stale base->first entry until the softirq runs. ++ */ ++ && hrtimer_rt_defer(timer) ++#endif ++ ) { + /* + * We need to drop cpu_base->lock to avoid a + * lock ordering issue vs. rq->lock. +@@ -1029,9 +1089,18 @@ int __hrtimer_start_range_ns(struct hrti + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + local_irq_restore(flags); + return ret; +- } else { +- __raise_softirq_irqoff(HRTIMER_SOFTIRQ); + } ++ ++ /* ++ * In case we failed to reprogram the timer (mostly ++ * because out current timer is already elapsed), ++ * remove it again and report a failure. This avoids ++ * stale base->first entries. ++ */ ++ debug_deactivate(timer); ++ __remove_hrtimer(timer, new_base, ++ timer->state & HRTIMER_STATE_CALLBACK, 0); ++ ret = -ETIME; + } + + unlock_hrtimer_base(timer, &flags); +@@ -1118,7 +1187,7 @@ int hrtimer_cancel(struct hrtimer *timer + + if (ret >= 0) + return ret; +- cpu_relax(); ++ hrtimer_wait_for_timer(timer); + } + } + EXPORT_SYMBOL_GPL(hrtimer_cancel); +@@ -1197,6 +1266,7 @@ static void __hrtimer_init(struct hrtime + + base = hrtimer_clockid_to_base(clock_id); + timer->base = &cpu_base->clock_base[base]; ++ INIT_LIST_HEAD(&timer->cb_entry); + timerqueue_init(&timer->node); + + #ifdef CONFIG_TIMER_STATS +@@ -1283,6 +1353,126 @@ static void __run_hrtimer(struct hrtimer + timer->state &= ~HRTIMER_STATE_CALLBACK; + } + ++static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer); ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer, ++ struct hrtimer_clock_base *base) ++{ ++ /* ++ * Note, we clear the callback flag before we requeue the ++ * timer otherwise we trigger the callback_running() check ++ * in hrtimer_reprogram(). ++ */ ++ timer->state &= ~HRTIMER_STATE_CALLBACK; ++ ++ if (restart != HRTIMER_NORESTART) { ++ BUG_ON(hrtimer_active(timer)); ++ /* ++ * Enqueue the timer, if it's the leftmost timer then ++ * we need to reprogram it. ++ */ ++ if (!enqueue_hrtimer(timer, base)) ++ return; ++ ++#ifndef CONFIG_HIGH_RES_TIMERS ++ } ++#else ++ if (base->cpu_base->hres_active && ++ hrtimer_reprogram(timer, base)) ++ goto requeue; ++ ++ } else if (hrtimer_active(timer)) { ++ /* ++ * If the timer was rearmed on another CPU, reprogram ++ * the event device. ++ */ ++ if (&timer->node == base->active.next && ++ base->cpu_base->hres_active && ++ hrtimer_reprogram(timer, base)) ++ goto requeue; ++ } ++ return; ++ ++requeue: ++ /* ++ * Timer is expired. Thus move it from tree to pending list ++ * again. ++ */ ++ __remove_hrtimer(timer, base, timer->state, 0); ++ list_add_tail(&timer->cb_entry, &base->expired); ++#endif ++} ++ ++/* ++ * The changes in mainline which removed the callback modes from ++ * hrtimer are not yet working with -rt. The non wakeup_process() ++ * based callbacks which involve sleeping locks need to be treated ++ * seperately. ++ */ ++static void hrtimer_rt_run_pending(void) ++{ ++ enum hrtimer_restart (*fn)(struct hrtimer *); ++ struct hrtimer_cpu_base *cpu_base; ++ struct hrtimer_clock_base *base; ++ struct hrtimer *timer; ++ int index, restart; ++ ++ local_irq_disable(); ++ cpu_base = &per_cpu(hrtimer_bases, smp_processor_id()); ++ ++ raw_spin_lock(&cpu_base->lock); ++ ++ for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) { ++ base = &cpu_base->clock_base[index]; ++ ++ while (!list_empty(&base->expired)) { ++ timer = list_first_entry(&base->expired, ++ struct hrtimer, cb_entry); ++ ++ /* ++ * Same as the above __run_hrtimer function ++ * just we run with interrupts enabled. ++ */ ++ debug_hrtimer_deactivate(timer); ++ __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0); ++ timer_stats_account_hrtimer(timer); ++ fn = timer->function; ++ ++ raw_spin_unlock_irq(&cpu_base->lock); ++ restart = fn(timer); ++ raw_spin_lock_irq(&cpu_base->lock); ++ ++ hrtimer_rt_reprogram(restart, timer, base); ++ } ++ } ++ ++ raw_spin_unlock_irq(&cpu_base->lock); ++ ++ wake_up_timer_waiters(cpu_base); ++} ++ ++static int hrtimer_rt_defer(struct hrtimer *timer) ++{ ++ if (timer->irqsafe) ++ return 0; ++ ++ __remove_hrtimer(timer, timer->base, timer->state, 0); ++ list_add_tail(&timer->cb_entry, &timer->base->expired); ++ return 1; ++} ++ ++#else ++ ++static inline void hrtimer_rt_run_pending(void) ++{ ++ hrtimer_peek_ahead_timers(); ++} ++ ++static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; } ++ ++#endif ++ + #ifdef CONFIG_HIGH_RES_TIMERS + + /* +@@ -1293,7 +1483,7 @@ void hrtimer_interrupt(struct clock_even + { + struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); + ktime_t expires_next, now, entry_time, delta; +- int i, retries = 0; ++ int i, retries = 0, raise = 0; + + BUG_ON(!cpu_base->hres_active); + cpu_base->nr_events++; +@@ -1328,6 +1518,15 @@ retry: + + timer = container_of(node, struct hrtimer, node); + ++ trace_hrtimer_interrupt(raw_smp_processor_id(), ++ ktime_to_ns(ktime_sub(ktime_to_ns(timer->praecox) ? ++ timer->praecox : hrtimer_get_expires(timer), ++ basenow)), ++ current, ++ timer->function == hrtimer_wakeup ? ++ container_of(timer, struct hrtimer_sleeper, ++ timer)->task : NULL); ++ + /* + * The immediate goal for using the softexpires is + * minimizing wakeups, not running timers at the +@@ -1353,7 +1552,10 @@ retry: + break; + } + +- __run_hrtimer(timer, &basenow); ++ if (!hrtimer_rt_defer(timer)) ++ __run_hrtimer(timer, &basenow); ++ else ++ raise = 1; + } + } + +@@ -1368,7 +1570,7 @@ retry: + if (expires_next.tv64 == KTIME_MAX || + !tick_program_event(expires_next, 0)) { + cpu_base->hang_detected = 0; +- return; ++ goto out; + } + + /* +@@ -1412,6 +1614,9 @@ retry: + tick_program_event(expires_next, 1); + printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n", + ktime_to_ns(delta)); ++out: ++ if (raise) ++ raise_softirq_irqoff(HRTIMER_SOFTIRQ); + } + + /* +@@ -1448,17 +1653,17 @@ void hrtimer_peek_ahead_timers(void) + local_irq_restore(flags); + } + +-static void run_hrtimer_softirq(struct softirq_action *h) +-{ +- hrtimer_peek_ahead_timers(); +-} +- + #else /* CONFIG_HIGH_RES_TIMERS */ + + static inline void __hrtimer_peek_ahead_timers(void) { } + + #endif /* !CONFIG_HIGH_RES_TIMERS */ + ++static void run_hrtimer_softirq(struct softirq_action *h) ++{ ++ hrtimer_rt_run_pending(); ++} ++ + /* + * Called from timer softirq every jiffy, expire hrtimers: + * +@@ -1491,7 +1696,7 @@ void hrtimer_run_queues(void) + struct timerqueue_node *node; + struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); + struct hrtimer_clock_base *base; +- int index, gettime = 1; ++ int index, gettime = 1, raise = 0; + + if (hrtimer_hres_active()) + return; +@@ -1516,10 +1721,16 @@ void hrtimer_run_queues(void) + hrtimer_get_expires_tv64(timer)) + break; + +- __run_hrtimer(timer, &base->softirq_time); ++ if (!hrtimer_rt_defer(timer)) ++ __run_hrtimer(timer, &base->softirq_time); ++ else ++ raise = 1; + } + raw_spin_unlock(&cpu_base->lock); + } ++ ++ if (raise) ++ raise_softirq_irqoff(HRTIMER_SOFTIRQ); + } + + /* +@@ -1541,16 +1752,18 @@ static enum hrtimer_restart hrtimer_wake + void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) + { + sl->timer.function = hrtimer_wakeup; ++ sl->timer.irqsafe = 1; + sl->task = task; + } + EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); + +-static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) ++static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode, ++ unsigned long state) + { + hrtimer_init_sleeper(t, current); + + do { +- set_current_state(TASK_INTERRUPTIBLE); ++ set_current_state(state); + hrtimer_start_expires(&t->timer, mode); + if (!hrtimer_active(&t->timer)) + t->task = NULL; +@@ -1594,7 +1807,8 @@ long __sched hrtimer_nanosleep_restart(s + HRTIMER_MODE_ABS); + hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); + +- if (do_nanosleep(&t, HRTIMER_MODE_ABS)) ++ /* cpu_chill() does not care about restart state. */ ++ if (do_nanosleep(&t, HRTIMER_MODE_ABS, TASK_INTERRUPTIBLE)) + goto out; + + rmtp = restart->nanosleep.rmtp; +@@ -1611,8 +1825,10 @@ out: + return ret; + } + +-long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, +- const enum hrtimer_mode mode, const clockid_t clockid) ++static long ++__hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, ++ const enum hrtimer_mode mode, const clockid_t clockid, ++ unsigned long state) + { + struct restart_block *restart; + struct hrtimer_sleeper t; +@@ -1625,7 +1841,7 @@ long hrtimer_nanosleep(struct timespec * + + hrtimer_init_on_stack(&t.timer, clockid, mode); + hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack); +- if (do_nanosleep(&t, mode)) ++ if (do_nanosleep(&t, mode, state)) + goto out; + + /* Absolute timers do not update the rmtp value and restart: */ +@@ -1652,6 +1868,12 @@ out: + return ret; + } + ++long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, ++ const enum hrtimer_mode mode, const clockid_t clockid) ++{ ++ return __hrtimer_nanosleep(rqtp, rmtp, mode, clockid, TASK_INTERRUPTIBLE); ++} ++ + SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp, + struct timespec __user *, rmtp) + { +@@ -1666,6 +1888,26 @@ SYSCALL_DEFINE2(nanosleep, struct timesp + return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * Sleep for 1 ms in hope whoever holds what we want will let it go. ++ */ ++void cpu_chill(void) ++{ ++ struct timespec tu = { ++ .tv_nsec = NSEC_PER_MSEC, ++ }; ++ unsigned int freeze_flag = current->flags & PF_NOFREEZE; ++ ++ current->flags |= PF_NOFREEZE; ++ __hrtimer_nanosleep(&tu, NULL, HRTIMER_MODE_REL, CLOCK_MONOTONIC, ++ TASK_UNINTERRUPTIBLE); ++ if (!freeze_flag) ++ current->flags &= ~PF_NOFREEZE; ++} ++EXPORT_SYMBOL(cpu_chill); ++#endif ++ + /* + * Functions related to boot-time initialization: + */ +@@ -1677,9 +1919,13 @@ static void __cpuinit init_hrtimers_cpu( + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { + cpu_base->clock_base[i].cpu_base = cpu_base; + timerqueue_init_head(&cpu_base->clock_base[i].active); ++ INIT_LIST_HEAD(&cpu_base->clock_base[i].expired); + } + + hrtimer_init_hres(cpu_base); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ init_waitqueue_head(&cpu_base->wait); ++#endif + } + + #ifdef CONFIG_HOTPLUG_CPU +@@ -1792,9 +2038,7 @@ void __init hrtimers_init(void) + hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, + (void *)(long)smp_processor_id()); + register_cpu_notifier(&hrtimers_nb); +-#ifdef CONFIG_HIGH_RES_TIMERS + open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq); +-#endif + } + + /** +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/irq/handle.c sun8i-rt/kernel/irq/handle.c +--- sun8i/kernel/irq/handle.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/irq/handle.c 2016-08-22 18:01:43.184281083 +0200 +@@ -132,6 +132,8 @@ static void irq_wake_thread(struct irq_d + irqreturn_t + handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) + { ++ struct pt_regs *regs = get_irq_regs(); ++ u64 ip = regs ? instruction_pointer(regs) : 0; + irqreturn_t retval = IRQ_NONE; + unsigned int flags = 0, irq = desc->irq_data.irq; + +@@ -172,7 +174,11 @@ handle_irq_event_percpu(struct irq_desc + action = action->next; + } while (action); + +- add_interrupt_randomness(irq, flags); ++#ifndef CONFIG_PREEMPT_RT_FULL ++ add_interrupt_randomness(irq, flags, ip); ++#else ++ desc->random_ip = ip; ++#endif + + if (!noirqdebug) + note_interrupt(irq, desc, retval); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/irq/manage.c sun8i-rt/kernel/irq/manage.c +--- sun8i/kernel/irq/manage.c 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/kernel/irq/manage.c 2016-08-22 18:15:23.684290516 +0200 +@@ -18,6 +18,7 @@ + #include "internals.h" + + #ifdef CONFIG_IRQ_FORCED_THREADING ++# ifndef CONFIG_PREEMPT_RT_BASE + __read_mostly bool force_irqthreads; + + static int __init setup_forced_irqthreads(char *arg) +@@ -26,6 +27,7 @@ static int __init setup_forced_irqthread + return 0; + } + early_param("threadirqs", setup_forced_irqthreads); ++# endif + #endif + + /** +@@ -139,6 +141,62 @@ static inline void + irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { } + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void _irq_affinity_notify(struct irq_affinity_notify *notify); ++static struct task_struct *set_affinity_helper; ++static LIST_HEAD(affinity_list); ++static DEFINE_RAW_SPINLOCK(affinity_list_lock); ++ ++static int set_affinity_thread(void *unused) ++{ ++ while (1) { ++ struct irq_affinity_notify *notify; ++ int empty; ++ ++ set_current_state(TASK_INTERRUPTIBLE); ++ ++ raw_spin_lock_irq(&affinity_list_lock); ++ empty = list_empty(&affinity_list); ++ raw_spin_unlock_irq(&affinity_list_lock); ++ ++ if (empty) ++ schedule(); ++ if (kthread_should_stop()) ++ break; ++ set_current_state(TASK_RUNNING); ++try_next: ++ notify = NULL; ++ ++ raw_spin_lock_irq(&affinity_list_lock); ++ if (!list_empty(&affinity_list)) { ++ notify = list_first_entry(&affinity_list, ++ struct irq_affinity_notify, list); ++ list_del_init(¬ify->list); ++ } ++ raw_spin_unlock_irq(&affinity_list_lock); ++ ++ if (!notify) ++ continue; ++ _irq_affinity_notify(notify); ++ goto try_next; ++ } ++ return 0; ++} ++ ++static void init_helper_thread(void) ++{ ++ if (set_affinity_helper) ++ return; ++ set_affinity_helper = kthread_run(set_affinity_thread, NULL, ++ "affinity-cb"); ++ WARN_ON(IS_ERR(set_affinity_helper)); ++} ++#else ++ ++static inline void init_helper_thread(void) { } ++ ++#endif ++ + int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask) + { + struct irq_chip *chip = irq_data_get_irq_chip(data); +@@ -164,7 +222,17 @@ int __irq_set_affinity_locked(struct irq + + if (desc->affinity_notify) { + kref_get(&desc->affinity_notify->kref); ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ raw_spin_lock(&affinity_list_lock); ++ if (list_empty(&desc->affinity_notify->list)) ++ list_add_tail(&affinity_list, ++ &desc->affinity_notify->list); ++ raw_spin_unlock(&affinity_list_lock); ++ wake_up_process(set_affinity_helper); ++#else + schedule_work(&desc->affinity_notify->work); ++#endif + } + irqd_set(data, IRQD_AFFINITY_SET); + +@@ -205,10 +273,8 @@ int irq_set_affinity_hint(unsigned int i + } + EXPORT_SYMBOL_GPL(irq_set_affinity_hint); + +-static void irq_affinity_notify(struct work_struct *work) ++static void _irq_affinity_notify(struct irq_affinity_notify *notify) + { +- struct irq_affinity_notify *notify = +- container_of(work, struct irq_affinity_notify, work); + struct irq_desc *desc = irq_to_desc(notify->irq); + cpumask_var_t cpumask; + unsigned long flags; +@@ -230,6 +296,13 @@ out: + kref_put(¬ify->kref, notify->release); + } + ++static void irq_affinity_notify(struct work_struct *work) ++{ ++ struct irq_affinity_notify *notify = ++ container_of(work, struct irq_affinity_notify, work); ++ _irq_affinity_notify(notify); ++} ++ + /** + * irq_set_affinity_notifier - control notification of IRQ affinity changes + * @irq: Interrupt for which to enable/disable notification +@@ -259,6 +332,8 @@ irq_set_affinity_notifier(unsigned int i + notify->irq = irq; + kref_init(¬ify->kref); + INIT_WORK(¬ify->work, irq_affinity_notify); ++ INIT_LIST_HEAD(¬ify->list); ++ init_helper_thread(); + } + + raw_spin_lock_irqsave(&desc->lock, flags); +@@ -756,7 +831,15 @@ irq_forced_thread_fn(struct irq_desc *de + local_bh_disable(); + ret = action->thread_fn(action->irq, action->dev_id); + irq_finalize_oneshot(desc, action); +- local_bh_enable(); ++ /* ++ * Interrupts which have real time requirements can be set up ++ * to avoid softirq processing in the thread handler. This is ++ * safe as these interrupts do not raise soft interrupts. ++ */ ++ if (irq_settings_no_softirq_call(desc)) ++ _local_bh_enable(); ++ else ++ local_bh_enable(); + return ret; + } + +@@ -786,9 +869,6 @@ static void wake_threads_waitq(struct ir + */ + static int irq_thread(void *data) + { +- static const struct sched_param param = { +- .sched_priority = MAX_USER_RT_PRIO/2, +- }; + struct irqaction *action = data; + struct irq_desc *desc = irq_to_desc(action->irq); + irqreturn_t (*handler_fn)(struct irq_desc *desc, +@@ -800,7 +880,6 @@ static int irq_thread(void *data) + else + handler_fn = irq_thread_fn; + +- sched_setscheduler(current, SCHED_FIFO, ¶m); + current->irq_thread = 1; + + while (!irq_wait_for_interrupt(action)) { +@@ -812,6 +891,12 @@ static int irq_thread(void *data) + if (action_ret == IRQ_HANDLED) + atomic_inc(&desc->threads_handled); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ migrate_disable(); ++ add_interrupt_randomness(action->irq, 0, ++ desc->random_ip ^ (u64) action); ++ migrate_enable(); ++#endif + wake_threads_waitq(desc); + } + +@@ -927,6 +1012,9 @@ __setup_irq(unsigned int irq, struct irq + */ + if (new->thread_fn && !nested) { + struct task_struct *t; ++ static const struct sched_param param = { ++ .sched_priority = MAX_USER_RT_PRIO/2, ++ }; + + t = kthread_create(irq_thread, new, "irq/%d-%s", irq, + new->name); +@@ -934,6 +1022,9 @@ __setup_irq(unsigned int irq, struct irq + ret = PTR_ERR(t); + goto out_mput; + } ++ ++ sched_setscheduler_nocheck(t, SCHED_FIFO, ¶m); ++ + /* + * We keep the reference to the task struct even if + * the thread dies to avoid that the interrupt code +@@ -1071,6 +1162,9 @@ __setup_irq(unsigned int irq, struct irq + irqd_set(&desc->irq_data, IRQD_NO_BALANCING); + } + ++ if (new->flags & IRQF_NO_SOFTIRQ_CALL) ++ irq_settings_set_no_softirq_call(desc); ++ + /* Set default affinity mask once everything is setup */ + setup_affinity(irq, desc, mask); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/irq/settings.h sun8i-rt/kernel/irq/settings.h +--- sun8i/kernel/irq/settings.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/irq/settings.h 2016-08-22 17:24:03.564255105 +0200 +@@ -14,6 +14,7 @@ enum { + _IRQ_NO_BALANCING = IRQ_NO_BALANCING, + _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, + _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, ++ _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL, + _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, + }; + +@@ -26,6 +27,7 @@ enum { + #define IRQ_NOAUTOEN GOT_YOU_MORON + #define IRQ_NESTED_THREAD GOT_YOU_MORON + #define IRQ_PER_CPU_DEVID GOT_YOU_MORON ++#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON + #undef IRQF_MODIFY_MASK + #define IRQF_MODIFY_MASK GOT_YOU_MORON + +@@ -36,6 +38,16 @@ irq_settings_clr_and_set(struct irq_desc + desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); + } + ++static inline bool irq_settings_no_softirq_call(struct irq_desc *desc) ++{ ++ return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL; ++} ++ ++static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc) ++{ ++ desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL; ++} ++ + static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) + { + return desc->status_use_accessors & _IRQ_PER_CPU; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/irq/spurious.c sun8i-rt/kernel/irq/spurious.c +--- sun8i/kernel/irq/spurious.c 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/kernel/irq/spurious.c 2016-08-22 16:34:54.084221195 +0200 +@@ -438,6 +438,11 @@ MODULE_PARM_DESC(noirqdebug, "Disable ir + + static int __init irqfixup_setup(char *str) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ printk(KERN_WARNING "irqfixup boot option not supported " ++ "w/ CONFIG_PREEMPT_RT\n"); ++ return 1; ++#endif + irqfixup = 1; + printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); + printk(KERN_WARNING "This may impact system performance.\n"); +@@ -450,6 +455,11 @@ module_param(irqfixup, int, 0644); + + static int __init irqpoll_setup(char *str) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ printk(KERN_WARNING "irqpoll boot option not supported " ++ "w/ CONFIG_PREEMPT_RT\n"); ++ return 1; ++#endif + irqfixup = 2; + printk(KERN_WARNING "Misrouted IRQ fixup and polling support " + "enabled\n"); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/irq_work.c sun8i-rt/kernel/irq_work.c +--- sun8i/kernel/irq_work.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/irq_work.c 2016-08-22 17:43:31.676268534 +0200 +@@ -107,8 +107,10 @@ void irq_work_run(void) + if (llist_empty(this_list)) + return; + ++#ifndef CONFIG_PREEMPT_RT_FULL + BUG_ON(!in_irq()); + BUG_ON(!irqs_disabled()); ++#endif + + llnode = llist_del_all(this_list); + while (llnode != NULL) { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/itimer.c sun8i-rt/kernel/itimer.c +--- sun8i/kernel/itimer.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/itimer.c 2016-08-22 17:10:03.008245441 +0200 +@@ -213,6 +213,7 @@ again: + /* We are sharing ->siglock with it_real_fn() */ + if (hrtimer_try_to_cancel(timer) < 0) { + spin_unlock_irq(&tsk->sighand->siglock); ++ hrtimer_wait_for_timer(&tsk->signal->real_timer); + goto again; + } + expires = timeval_to_ktime(value->it_value); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/Kconfig.locks sun8i-rt/kernel/Kconfig.locks +--- sun8i/kernel/Kconfig.locks 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/Kconfig.locks 2016-08-22 17:21:48.440253551 +0200 +@@ -199,4 +199,4 @@ config INLINE_WRITE_UNLOCK_IRQRESTORE + def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE + + config MUTEX_SPIN_ON_OWNER +- def_bool SMP && !DEBUG_MUTEXES ++ def_bool SMP && !DEBUG_MUTEXES && !PREEMPT_RT_FULL +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/Kconfig.preempt sun8i-rt/kernel/Kconfig.preempt +--- sun8i/kernel/Kconfig.preempt 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/Kconfig.preempt 2016-08-22 17:58:48.808279078 +0200 +@@ -1,3 +1,10 @@ ++config PREEMPT ++ bool ++ select PREEMPT_COUNT ++ ++config PREEMPT_RT_BASE ++ bool ++ select PREEMPT + + choice + prompt "Preemption Model" +@@ -33,9 +40,9 @@ config PREEMPT_VOLUNTARY + + Select this if you are building a kernel for a desktop system. + +-config PREEMPT ++config PREEMPT__LL + bool "Preemptible Kernel (Low-Latency Desktop)" +- select PREEMPT_COUNT ++ select PREEMPT + select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK + help + This option reduces the latency of the kernel by making +@@ -52,6 +59,21 @@ config PREEMPT + embedded system with latency requirements in the milliseconds + range. + ++config PREEMPT_RTB ++ bool "Preemptible Kernel (Basic RT)" ++ select PREEMPT_RT_BASE ++ help ++ This option is basically the same as (Low-Latency Desktop) but ++ enables changes which are preliminary for the full preemptiple ++ RT kernel. ++ ++config PREEMPT_RT_FULL ++ bool "Fully Preemptible Kernel (RT)" ++ depends on IRQ_FORCED_THREADING ++ select PREEMPT_RT_BASE ++ help ++ All and everything ++ + endchoice + + config PREEMPT_COUNT +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/ksysfs.c sun8i-rt/kernel/ksysfs.c +--- sun8i/kernel/ksysfs.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/ksysfs.c 2016-08-22 17:48:23.048271884 +0200 +@@ -133,6 +133,15 @@ KERNEL_ATTR_RO(vmcoreinfo); + + #endif /* CONFIG_KEXEC */ + ++#if defined(CONFIG_PREEMPT_RT_FULL) ++static ssize_t realtime_show(struct kobject *kobj, ++ struct kobj_attribute *attr, char *buf) ++{ ++ return sprintf(buf, "%d\n", 1); ++} ++KERNEL_ATTR_RO(realtime); ++#endif ++ + /* whether file capabilities are enabled */ + static ssize_t fscaps_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +@@ -182,6 +191,9 @@ static struct attribute * kernel_attrs[] + &kexec_crash_size_attr.attr, + &vmcoreinfo_attr.attr, + #endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++ &realtime_attr.attr, ++#endif + NULL + }; + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/lockdep.c sun8i-rt/kernel/lockdep.c +--- sun8i/kernel/lockdep.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/lockdep.c 2016-08-22 17:21:32.532253368 +0200 +@@ -3495,6 +3495,7 @@ static void check_flags(unsigned long fl + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * We dont accurately track softirq state in e.g. + * hardirq contexts (such as on 4KSTACKS), so only +@@ -3509,6 +3510,7 @@ static void check_flags(unsigned long fl + DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); + } + } ++#endif + + if (!debug_locks) + print_irqtrace_events(current); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/Makefile sun8i-rt/kernel/Makefile +--- sun8i/kernel/Makefile 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/Makefile 2016-08-22 18:11:30.464287835 +0200 +@@ -7,10 +7,10 @@ obj-y = fork.o exec_domain.o panic.o + sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ + signal.o sys.o kmod.o workqueue.o pid.o \ + rcupdate.o extable.o params.o posix-timers.o \ +- kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ +- hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ ++ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o \ ++ hrtimer.o nsproxy.o srcu.o semaphore.o \ + notifier.o ksysfs.o cred.o \ +- async.o range.o groups.o ++ async.o range.o groups.o wait-simple.o + + ifdef CONFIG_FUNCTION_TRACER + # Do not trace debug files and internal ftrace files +@@ -29,7 +29,11 @@ obj-$(CONFIG_FREEZER) += freezer.o + obj-$(CONFIG_PROFILING) += profile.o + obj-$(CONFIG_STACKTRACE) += stacktrace.o + obj-y += time/ ++ifneq ($(CONFIG_PREEMPT_RT_FULL),y) ++obj-y += mutex.o + obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o ++obj-y += rwsem.o ++endif + obj-$(CONFIG_LOCKDEP) += lockdep.o + ifeq ($(CONFIG_PROC_FS),y) + obj-$(CONFIG_LOCKDEP) += lockdep_proc.o +@@ -41,6 +45,7 @@ endif + obj-$(CONFIG_RT_MUTEXES) += rtmutex.o + obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o + obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o ++obj-$(CONFIG_PREEMPT_RT_FULL) += rt.o + obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o + obj-$(CONFIG_SMP) += smp.o + ifneq ($(CONFIG_SMP),y) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/panic.c sun8i-rt/kernel/panic.c +--- sun8i/kernel/panic.c 2016-08-22 14:14:34.000000000 +0200 ++++ sun8i-rt/kernel/panic.c 2016-08-22 17:07:06.308243409 +0200 +@@ -377,9 +377,11 @@ static u64 oops_id; + + static int init_oops_id(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + if (!oops_id) + get_random_bytes(&oops_id, sizeof(oops_id)); + else ++#endif + oops_id++; + + return 0; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/posix-cpu-timers.c sun8i-rt/kernel/posix-cpu-timers.c +--- sun8i/kernel/posix-cpu-timers.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/posix-cpu-timers.c 2016-08-22 17:11:58.180246765 +0200 +@@ -682,7 +682,7 @@ static int posix_cpu_timer_set(struct k_ + /* + * Disarm any old timer after extracting its expiry time. + */ +- BUG_ON(!irqs_disabled()); ++ BUG_ON_NONRT(!irqs_disabled()); + + ret = 0; + old_incr = timer->it.cpu.incr; +@@ -1198,7 +1198,7 @@ void posix_cpu_timer_schedule(struct k_i + /* + * Now re-arm for the new expiry time. + */ +- BUG_ON(!irqs_disabled()); ++ BUG_ON_NONRT(!irqs_disabled()); + arm_timer(timer); + spin_unlock(&p->sighand->siglock); + +@@ -1262,10 +1262,11 @@ static inline int fastpath_timer_check(s + sig = tsk->signal; + if (sig->cputimer.running) { + struct task_cputime group_sample; ++ unsigned long flags; + +- raw_spin_lock(&sig->cputimer.lock); ++ raw_spin_lock_irqsave(&sig->cputimer.lock, flags); + group_sample = sig->cputimer.cputime; +- raw_spin_unlock(&sig->cputimer.lock); ++ raw_spin_unlock_irqrestore(&sig->cputimer.lock, flags); + + if (task_cputime_expired(&group_sample, &sig->cputime_expires)) + return 1; +@@ -1279,13 +1280,13 @@ static inline int fastpath_timer_check(s + * already updated our counts. We need to check if any timers fire now. + * Interrupts are disabled. + */ +-void run_posix_cpu_timers(struct task_struct *tsk) ++static void __run_posix_cpu_timers(struct task_struct *tsk) + { + LIST_HEAD(firing); + struct k_itimer *timer, *next; + unsigned long flags; + +- BUG_ON(!irqs_disabled()); ++ BUG_ON_NONRT(!irqs_disabled()); + + /* + * The fast path checks that there are no expired thread or thread +@@ -1343,6 +1344,190 @@ void run_posix_cpu_timers(struct task_st + } + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++#include ++#include ++DEFINE_PER_CPU(struct task_struct *, posix_timer_task); ++DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist); ++ ++static int posix_cpu_timers_thread(void *data) ++{ ++ int cpu = (long)data; ++ ++ BUG_ON(per_cpu(posix_timer_task,cpu) != current); ++ ++ while (!kthread_should_stop()) { ++ struct task_struct *tsk = NULL; ++ struct task_struct *next = NULL; ++ ++ if (cpu_is_offline(cpu)) ++ goto wait_to_die; ++ ++ /* grab task list */ ++ raw_local_irq_disable(); ++ tsk = per_cpu(posix_timer_tasklist, cpu); ++ per_cpu(posix_timer_tasklist, cpu) = NULL; ++ raw_local_irq_enable(); ++ ++ /* its possible the list is empty, just return */ ++ if (!tsk) { ++ set_current_state(TASK_INTERRUPTIBLE); ++ schedule(); ++ __set_current_state(TASK_RUNNING); ++ continue; ++ } ++ ++ /* Process task list */ ++ while (1) { ++ /* save next */ ++ next = tsk->posix_timer_list; ++ ++ /* run the task timers, clear its ptr and ++ * unreference it ++ */ ++ __run_posix_cpu_timers(tsk); ++ tsk->posix_timer_list = NULL; ++ put_task_struct(tsk); ++ ++ /* check if this is the last on the list */ ++ if (next == tsk) ++ break; ++ tsk = next; ++ } ++ } ++ return 0; ++ ++wait_to_die: ++ /* Wait for kthread_stop */ ++ set_current_state(TASK_INTERRUPTIBLE); ++ while (!kthread_should_stop()) { ++ schedule(); ++ set_current_state(TASK_INTERRUPTIBLE); ++ } ++ __set_current_state(TASK_RUNNING); ++ return 0; ++} ++ ++static inline int __fastpath_timer_check(struct task_struct *tsk) ++{ ++ /* tsk == current, ensure it is safe to use ->signal/sighand */ ++ if (unlikely(tsk->exit_state)) ++ return 0; ++ ++ if (!task_cputime_zero(&tsk->cputime_expires)) ++ return 1; ++ ++ if (!task_cputime_zero(&tsk->signal->cputime_expires)) ++ return 1; ++ ++ return 0; ++} ++ ++void run_posix_cpu_timers(struct task_struct *tsk) ++{ ++ unsigned long cpu = smp_processor_id(); ++ struct task_struct *tasklist; ++ ++ BUG_ON(!irqs_disabled()); ++ if(!per_cpu(posix_timer_task, cpu)) ++ return; ++ /* get per-cpu references */ ++ tasklist = per_cpu(posix_timer_tasklist, cpu); ++ ++ /* check to see if we're already queued */ ++ if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) { ++ get_task_struct(tsk); ++ if (tasklist) { ++ tsk->posix_timer_list = tasklist; ++ } else { ++ /* ++ * The list is terminated by a self-pointing ++ * task_struct ++ */ ++ tsk->posix_timer_list = tsk; ++ } ++ per_cpu(posix_timer_tasklist, cpu) = tsk; ++ ++ wake_up_process(per_cpu(posix_timer_task, cpu)); ++ } ++} ++ ++/* ++ * posix_cpu_thread_call - callback that gets triggered when a CPU is added. ++ * Here we can start up the necessary migration thread for the new CPU. ++ */ ++static int posix_cpu_thread_call(struct notifier_block *nfb, ++ unsigned long action, void *hcpu) ++{ ++ int cpu = (long)hcpu; ++ struct task_struct *p; ++ struct sched_param param; ++ ++ switch (action) { ++ case CPU_UP_PREPARE: ++ p = kthread_create(posix_cpu_timers_thread, hcpu, ++ "posixcputmr/%d",cpu); ++ if (IS_ERR(p)) ++ return NOTIFY_BAD; ++ p->flags |= PF_NOFREEZE; ++ kthread_bind(p, cpu); ++ /* Must be high prio to avoid getting starved */ ++ param.sched_priority = MAX_RT_PRIO-1; ++ sched_setscheduler(p, SCHED_FIFO, ¶m); ++ per_cpu(posix_timer_task,cpu) = p; ++ break; ++ case CPU_ONLINE: ++ /* Strictly unneccessary, as first user will wake it. */ ++ wake_up_process(per_cpu(posix_timer_task,cpu)); ++ break; ++#ifdef CONFIG_HOTPLUG_CPU ++ case CPU_UP_CANCELED: ++ /* Unbind it from offline cpu so it can run. Fall thru. */ ++ kthread_bind(per_cpu(posix_timer_task, cpu), ++ cpumask_any(cpu_online_mask)); ++ kthread_stop(per_cpu(posix_timer_task,cpu)); ++ per_cpu(posix_timer_task,cpu) = NULL; ++ break; ++ case CPU_DEAD: ++ kthread_stop(per_cpu(posix_timer_task,cpu)); ++ per_cpu(posix_timer_task,cpu) = NULL; ++ break; ++#endif ++ } ++ return NOTIFY_OK; ++} ++ ++/* Register at highest priority so that task migration (migrate_all_tasks) ++ * happens before everything else. ++ */ ++static struct notifier_block __devinitdata posix_cpu_thread_notifier = { ++ .notifier_call = posix_cpu_thread_call, ++ .priority = 10 ++}; ++ ++static int __init posix_cpu_thread_init(void) ++{ ++ void *hcpu = (void *)(long)smp_processor_id(); ++ /* Start one for boot CPU. */ ++ unsigned long cpu; ++ ++ /* init the per-cpu posix_timer_tasklets */ ++ for_each_possible_cpu(cpu) ++ per_cpu(posix_timer_tasklist, cpu) = NULL; ++ ++ posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, hcpu); ++ posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, hcpu); ++ register_cpu_notifier(&posix_cpu_thread_notifier); ++ return 0; ++} ++early_initcall(posix_cpu_thread_init); ++#else /* CONFIG_PREEMPT_RT_BASE */ ++void run_posix_cpu_timers(struct task_struct *tsk) ++{ ++ __run_posix_cpu_timers(tsk); ++} ++#endif /* CONFIG_PREEMPT_RT_BASE */ ++ + /* + * Set one of the process-wide special case CPU timers or RLIMIT_CPU. + * The tsk->sighand->siglock must be held by the caller. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/posix-timers.c sun8i-rt/kernel/posix-timers.c +--- sun8i/kernel/posix-timers.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/kernel/posix-timers.c 2016-08-22 17:10:03.008245441 +0200 +@@ -439,6 +439,7 @@ static enum hrtimer_restart posix_timer_ + static struct pid *good_sigevent(sigevent_t * event) + { + struct task_struct *rtn = current->group_leader; ++ int sig = event->sigev_signo; + + if ((event->sigev_notify & SIGEV_THREAD_ID ) && + (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) || +@@ -447,7 +448,8 @@ static struct pid *good_sigevent(sigeven + return NULL; + + if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) && +- ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX))) ++ (sig <= 0 || sig > SIGRTMAX || sig_kernel_only(sig) || ++ sig_kernel_coredump(sig))) + return NULL; + + return task_pid(rtn); +@@ -772,6 +774,20 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_ + return overrun; + } + ++/* ++ * Protected by RCU! ++ */ ++static void timer_wait_for_callback(struct k_clock *kc, struct k_itimer *timr) ++{ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (kc->timer_set == common_timer_set) ++ hrtimer_wait_for_timer(&timr->it.real.timer); ++ else ++ /* FIXME: Whacky hack for posix-cpu-timers */ ++ schedule_timeout(1); ++#endif ++} ++ + /* Set a POSIX.1b interval timer. */ + /* timr->it_lock is taken. */ + static int +@@ -849,6 +865,7 @@ retry: + if (!timr) + return -EINVAL; + ++ rcu_read_lock(); + kc = clockid_to_kclock(timr->it_clock); + if (WARN_ON_ONCE(!kc || !kc->timer_set)) + error = -EINVAL; +@@ -857,9 +874,12 @@ retry: + + unlock_timer(timr, flag); + if (error == TIMER_RETRY) { ++ timer_wait_for_callback(kc, timr); + rtn = NULL; // We already got the old time... ++ rcu_read_unlock(); + goto retry; + } ++ rcu_read_unlock(); + + if (old_setting && !error && + copy_to_user(old_setting, &old_spec, sizeof (old_spec))) +@@ -897,10 +917,15 @@ retry_delete: + if (!timer) + return -EINVAL; + ++ rcu_read_lock(); + if (timer_delete_hook(timer) == TIMER_RETRY) { + unlock_timer(timer, flags); ++ timer_wait_for_callback(clockid_to_kclock(timer->it_clock), ++ timer); ++ rcu_read_unlock(); + goto retry_delete; + } ++ rcu_read_unlock(); + + spin_lock(¤t->sighand->siglock); + list_del(&timer->list); +@@ -926,8 +951,18 @@ static void itimer_delete(struct k_itime + retry_delete: + spin_lock_irqsave(&timer->it_lock, flags); + ++ /* On RT we can race with a deletion */ ++ if (!timer->it_signal) { ++ unlock_timer(timer, flags); ++ return; ++ } ++ + if (timer_delete_hook(timer) == TIMER_RETRY) { ++ rcu_read_lock(); + unlock_timer(timer, flags); ++ timer_wait_for_callback(clockid_to_kclock(timer->it_clock), ++ timer); ++ rcu_read_unlock(); + goto retry_delete; + } + list_del(&timer->list); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/power/hibernate.c sun8i-rt/kernel/power/hibernate.c +--- sun8i/kernel/power/hibernate.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/kernel/power/hibernate.c 2016-08-22 16:17:41.052209318 +0200 +@@ -272,6 +272,8 @@ static int create_image(int platform_mod + + local_irq_disable(); + ++ system_state = SYSTEM_SUSPEND; ++ + error = syscore_suspend(); + if (error) { + printk(KERN_ERR "PM: Some system devices failed to power down, " +@@ -307,6 +309,7 @@ static int create_image(int platform_mod + syscore_resume(); + + Enable_irqs: ++ system_state = SYSTEM_RUNNING; + local_irq_enable(); + + Enable_cpus: +@@ -432,6 +435,7 @@ static int resume_target_kernel(bool pla + goto Enable_cpus; + + local_irq_disable(); ++ system_state = SYSTEM_SUSPEND; + + error = syscore_suspend(); + if (error) +@@ -473,6 +477,7 @@ static int resume_target_kernel(bool pla + syscore_resume(); + + Enable_irqs: ++ system_state = SYSTEM_RUNNING; + local_irq_enable(); + + Enable_cpus: +@@ -561,6 +566,7 @@ int hibernation_platform_enter(void) + goto Platform_finish; + + local_irq_disable(); ++ system_state = SYSTEM_SUSPEND; + syscore_suspend(); + if (pm_wakeup_pending()) { + error = -EAGAIN; +@@ -573,6 +579,7 @@ int hibernation_platform_enter(void) + + Power_up: + syscore_resume(); ++ system_state = SYSTEM_RUNNING; + local_irq_enable(); + enable_nonboot_cpus(); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/power/suspend.c sun8i-rt/kernel/power/suspend.c +--- sun8i/kernel/power/suspend.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/power/suspend.c 2016-08-22 16:17:41.052209318 +0200 +@@ -170,6 +170,8 @@ static int suspend_enter(suspend_state_t + arch_suspend_disable_irqs(); + BUG_ON(!irqs_disabled()); + ++ system_state = SYSTEM_SUSPEND; ++ + error = syscore_suspend(); + if (!error) { + *wakeup = pm_wakeup_pending(); +@@ -180,6 +182,8 @@ static int suspend_enter(suspend_state_t + syscore_resume(); + } + ++ system_state = SYSTEM_RUNNING; ++ + arch_suspend_enable_irqs(); + BUG_ON(irqs_disabled()); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/printk.c sun8i-rt/kernel/printk.c +--- sun8i/kernel/printk.c 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/kernel/printk.c 2016-08-22 17:46:09.464270348 +0200 +@@ -47,13 +47,6 @@ + #define CREATE_TRACE_POINTS + #include + +-/* +- * Architectures can override it: +- */ +-void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...) +-{ +-} +- + #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) + + #ifdef CONFIG_DEBUG_LL +@@ -565,6 +558,7 @@ static void __call_console_drivers(unsig + { + struct console *con; + ++ migrate_disable(); + for_each_console(con) { + if (exclusive_console && con != exclusive_console) + continue; +@@ -573,8 +567,65 @@ static void __call_console_drivers(unsig + (con->flags & CON_ANYTIME))) + con->write(con, &LOG_BUF(start), end - start); + } ++ migrate_enable(); ++} ++ ++#ifdef CONFIG_EARLY_PRINTK ++struct console *early_console; ++ ++static void early_vprintk(const char *fmt, va_list ap) ++{ ++ if (early_console) { ++ char buf[512]; ++ int n = vscnprintf(buf, sizeof(buf), fmt, ap); ++ ++ early_console->write(early_console, buf, n); ++ } ++} ++ ++asmlinkage void early_printk(const char *fmt, ...) ++{ ++ va_list ap; ++ ++ va_start(ap, fmt); ++ early_vprintk(fmt, ap); ++ va_end(ap); ++} ++ ++/* ++ * This is independent of any log levels - a global ++ * kill switch that turns off all of printk. ++ * ++ * Used by the NMI watchdog if early-printk is enabled. ++ */ ++static bool __read_mostly printk_killswitch; ++ ++static int __init force_early_printk_setup(char *str) ++{ ++ printk_killswitch = true; ++ return 0; ++} ++early_param("force_early_printk", force_early_printk_setup); ++ ++void printk_kill(void) ++{ ++ printk_killswitch = true; + } + ++static int forced_early_printk(const char *fmt, va_list ap) ++{ ++ if (!printk_killswitch) ++ return 0; ++ early_vprintk(fmt, ap); ++ return 1; ++} ++#else ++static inline int forced_early_printk(const char *fmt, va_list ap) ++{ ++ return 0; ++} ++#endif ++ + static bool __read_mostly ignore_loglevel; + + static int __init ignore_loglevel_setup(char *str) +@@ -852,12 +903,18 @@ static inline int can_use_console(unsign + * interrupts disabled. It should return with 'lockbuf_lock' + * released but interrupts still disabled. + */ +-static int console_trylock_for_printk(unsigned int cpu) ++static int console_trylock_for_printk(unsigned int cpu, unsigned long flags) + __releases(&logbuf_lock) + { + int retval = 0, wake = 0; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int lock = !early_boot_irqs_disabled && !irqs_disabled_flags(flags) && ++ (preempt_count() <= 1); ++#else ++ int lock = 1; ++#endif + +- if (console_trylock()) { ++ if (lock && console_trylock()) { + retval = 1; + + /* +@@ -908,6 +965,13 @@ asmlinkage int vprintk(const char *fmt, + size_t plen; + char special; + ++ /* ++ * Fall back to early_printk if a debugging subsystem has ++ * killed printk output ++ */ ++ if (unlikely(forced_early_printk(fmt, args))) ++ return 1; ++ + boot_delay_msec(); + printk_delay(); + +@@ -1033,8 +1097,15 @@ asmlinkage int vprintk(const char *fmt, + * will release 'logbuf_lock' regardless of whether it + * actually gets the semaphore or not. + */ +- if (console_trylock_for_printk(this_cpu)) ++ if (console_trylock_for_printk(this_cpu, flags)) { ++#ifndef CONFIG_PREEMPT_RT_FULL ++ console_unlock(); ++#else ++ raw_local_irq_restore(flags); + console_unlock(); ++ raw_local_irq_save(flags); ++#endif ++ } + + lockdep_on(); + out_restore_irqs: +@@ -1309,8 +1380,8 @@ void printk_tick(void) + + int printk_needs_cpu(int cpu) + { +- if (cpu_is_offline(cpu)) +- printk_tick(); ++ if (unlikely(cpu_is_offline(cpu))) ++ __this_cpu_write(printk_pending, 0); + return __this_cpu_read(printk_pending); + } + +@@ -1369,12 +1440,16 @@ again: + _log_end = log_end; + con_start = log_end; /* Flush */ + } +- ++#ifndef CONFIG_PREEMPT_RT_FULL + raw_spin_unlock(&logbuf_lock); + stop_critical_timings(); /* don't trace print latency */ + call_console_drivers(_con_start, _log_end); + start_critical_timings(); + local_irq_restore(flags); ++#else ++ raw_spin_unlock_irqrestore(&logbuf_lock, flags); ++ call_console_drivers(_con_start, _log_end); ++#endif + } + console_locked = 0; + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rcupdate.c sun8i-rt/kernel/rcupdate.c +--- sun8i/kernel/rcupdate.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/rcupdate.c 2016-08-22 17:35:31.784263017 +0200 +@@ -77,6 +77,7 @@ int debug_lockdep_rcu_enabled(void) + } + EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? + * +@@ -103,6 +104,7 @@ int rcu_read_lock_bh_held(void) + return in_softirq() || irqs_disabled(); + } + EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); ++#endif + + #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rcutiny.c sun8i-rt/kernel/rcutiny.c +--- sun8i/kernel/rcutiny.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/kernel/rcutiny.c 2016-08-22 17:35:56.276263298 +0200 +@@ -373,6 +373,7 @@ void call_rcu_sched(struct rcu_head *hea + } + EXPORT_SYMBOL_GPL(call_rcu_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Post an RCU bottom-half callback to be invoked after any subsequent + * quiescent state. +@@ -382,3 +383,4 @@ void call_rcu_bh(struct rcu_head *head, + __call_rcu(head, func, &rcu_bh_ctrlblk); + } + EXPORT_SYMBOL_GPL(call_rcu_bh); ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rcutiny_plugin.h sun8i-rt/kernel/rcutiny_plugin.h +--- sun8i/kernel/rcutiny_plugin.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/rcutiny_plugin.h 2016-08-22 18:11:41.860287966 +0200 +@@ -26,6 +26,7 @@ + #include + #include + #include ++#include + + /* Global control variables for rcupdate callback mechanism. */ + struct rcu_ctrlblk { +@@ -261,7 +262,7 @@ static void show_tiny_preempt_stats(stru + + /* Controls for rcu_kthread() kthread. */ + static struct task_struct *rcu_kthread_task; +-static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq); ++static DEFINE_SWAIT_HEAD(rcu_kthread_wq); + static unsigned long have_rcu_kthread_work; + + /* +@@ -572,7 +573,7 @@ static noinline void rcu_read_unlock_spe + rcu_preempt_cpu_qs(); + + /* Hardware IRQ handlers cannot block. */ +- if (in_irq() || in_serving_softirq()) { ++ if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { + local_irq_restore(flags); + return; + } +@@ -754,7 +755,7 @@ void synchronize_rcu(void) + } + EXPORT_SYMBOL_GPL(synchronize_rcu); + +-static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); ++static DEFINE_SWAIT_HEAD(sync_rcu_preempt_exp_wq); + static unsigned long sync_rcu_preempt_exp_count; + static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); + +@@ -776,7 +777,7 @@ static int rcu_preempted_readers_exp(voi + */ + static void rcu_report_exp_done(void) + { +- wake_up(&sync_rcu_preempt_exp_wq); ++ swait_wake(&sync_rcu_preempt_exp_wq); + } + + /* +@@ -828,8 +829,8 @@ void synchronize_rcu_expedited(void) + else { + rcu_initiate_boost(); + local_irq_restore(flags); +- wait_event(sync_rcu_preempt_exp_wq, +- !rcu_preempted_readers_exp()); ++ swait_event(sync_rcu_preempt_exp_wq, ++ !rcu_preempted_readers_exp()); + } + + /* Clean up and exit. */ +@@ -917,7 +918,7 @@ static void invoke_rcu_callbacks(void) + { + have_rcu_kthread_work = 1; + if (rcu_kthread_task != NULL) +- wake_up(&rcu_kthread_wq); ++ swait_wake(&rcu_kthread_wq); + } + + #ifdef CONFIG_RCU_TRACE +@@ -947,8 +948,8 @@ static int rcu_kthread(void *arg) + unsigned long flags; + + for (;;) { +- wait_event_interruptible(rcu_kthread_wq, +- have_rcu_kthread_work != 0); ++ swait_event_interruptible(rcu_kthread_wq, ++ have_rcu_kthread_work != 0); + morework = rcu_boost(); + local_irq_save(flags); + work = have_rcu_kthread_work; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rcutorture.c sun8i-rt/kernel/rcutorture.c +--- sun8i/kernel/rcutorture.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/rcutorture.c 2016-08-22 18:28:33.752299599 +0200 +@@ -485,6 +485,7 @@ static struct rcu_torture_ops rcu_expedi + .name = "rcu_expedited" + }; + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Definitions for rcu_bh torture testing. + */ +@@ -558,6 +559,12 @@ static struct rcu_torture_ops rcu_bh_exp + .name = "rcu_bh_expedited" + }; + ++#else ++static struct rcu_torture_ops rcu_bh_ops = { ++ .ttype = INVALID_RCU_FLAVOR, ++}; ++#endif ++ + /* + * Definitions for srcu torture testing. + */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rcutree.c sun8i-rt/kernel/rcutree.c +--- sun8i/kernel/rcutree.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/rcutree.c 2016-08-22 18:17:07.116291705 +0200 +@@ -172,6 +172,19 @@ void rcu_sched_qs(int cpu) + rdp->passed_quiesce = 1; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void rcu_preempt_qs(int cpu); ++ ++void rcu_bh_qs(int cpu) ++{ ++ unsigned long flags; ++ ++ /* Callers to this function, rcu_preempt_qs(), must disable irqs. */ ++ local_irq_save(flags); ++ rcu_preempt_qs(cpu); ++ local_irq_restore(flags); ++} ++#else + void rcu_bh_qs(int cpu) + { + struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); +@@ -182,6 +195,7 @@ void rcu_bh_qs(int cpu) + trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs"); + rdp->passed_quiesce = 1; + } ++#endif + + /* + * Note a context switch. This is a quiescent state for RCU-sched, +@@ -228,6 +242,7 @@ long rcu_batches_completed_sched(void) + } + EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Return the number of RCU BH batches processed thus far for debug & stats. + */ +@@ -245,6 +260,7 @@ void rcu_bh_force_quiescent_state(void) + force_quiescent_state(&rcu_bh_state, 0); + } + EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); ++#endif + + /* + * Record the number of times rcutorture tests have been initiated and +@@ -1886,6 +1902,7 @@ void call_rcu_sched(struct rcu_head *hea + } + EXPORT_SYMBOL_GPL(call_rcu_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Queue an RCU callback for invocation after a quicker grace period. + */ +@@ -1894,6 +1911,7 @@ void call_rcu_bh(struct rcu_head *head, + __call_rcu(head, func, &rcu_bh_state, 0); + } + EXPORT_SYMBOL_GPL(call_rcu_bh); ++#endif + + /** + * synchronize_sched - wait until an rcu-sched grace period has elapsed. +@@ -1930,6 +1948,7 @@ void synchronize_sched(void) + } + EXPORT_SYMBOL_GPL(synchronize_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. + * +@@ -1950,6 +1969,7 @@ void synchronize_rcu_bh(void) + wait_rcu_gp(call_rcu_bh); + } + EXPORT_SYMBOL_GPL(synchronize_rcu_bh); ++#endif + + static atomic_t sync_sched_expedited_started = ATOMIC_INIT(0); + static atomic_t sync_sched_expedited_done = ATOMIC_INIT(0); +@@ -2225,6 +2245,7 @@ static void _rcu_barrier(struct rcu_stat + mutex_unlock(&rcu_barrier_mutex); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. + */ +@@ -2233,6 +2254,7 @@ void rcu_barrier_bh(void) + _rcu_barrier(&rcu_bh_state, call_rcu_bh); + } + EXPORT_SYMBOL_GPL(rcu_barrier_bh); ++#endif + + /** + * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rcutree_plugin.h sun8i-rt/kernel/rcutree_plugin.h +--- sun8i/kernel/rcutree_plugin.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/rcutree_plugin.h 2016-08-22 17:36:39.484263795 +0200 +@@ -339,7 +339,7 @@ static noinline void rcu_read_unlock_spe + } + + /* Hardware IRQ handlers cannot block. */ +- if (in_irq() || in_serving_softirq()) { ++ if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { + local_irq_restore(flags); + return; + } +@@ -1899,7 +1899,7 @@ static void __cpuinit rcu_prepare_kthrea + + #endif /* #else #ifdef CONFIG_RCU_BOOST */ + +-#if !defined(CONFIG_RCU_FAST_NO_HZ) ++#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) + + /* + * Check to see if any future RCU-related work will need to be done +@@ -1914,6 +1914,9 @@ int rcu_needs_cpu(int cpu) + { + return rcu_cpu_has_callbacks(cpu); + } ++#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */ ++ ++#if !defined(CONFIG_RCU_FAST_NO_HZ) + + /* + * Because we do not have RCU_FAST_NO_HZ, don't bother initializing for it. +@@ -1984,6 +1987,7 @@ static DEFINE_PER_CPU(struct hrtimer, rc + static ktime_t rcu_idle_gp_wait; /* If some non-lazy callbacks. */ + static ktime_t rcu_idle_lazy_gp_wait; /* If only lazy callbacks. */ + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Allow the CPU to enter dyntick-idle mode if either: (1) There are no + * callbacks on this CPU, (2) this CPU has not yet attempted to enter +@@ -2001,6 +2005,7 @@ int rcu_needs_cpu(int cpu) + /* Otherwise, RCU needs the CPU only if it recently tried and failed. */ + return per_cpu(rcu_dyntick_holdoff, cpu) == jiffies; + } ++#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */ + + /* + * Does the specified flavor of RCU have non-lazy callbacks pending on +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/relay.c sun8i-rt/kernel/relay.c +--- sun8i/kernel/relay.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/relay.c 2016-08-22 17:07:49.248243903 +0200 +@@ -340,6 +340,10 @@ static void wakeup_readers(unsigned long + { + struct rchan_buf *buf = (struct rchan_buf *)data; + wake_up_interruptible(&buf->read_wait); ++ /* ++ * Stupid polling for now: ++ */ ++ mod_timer(&buf->timer, jiffies + 1); + } + + /** +@@ -357,6 +361,7 @@ static void __relay_reset(struct rchan_b + init_waitqueue_head(&buf->read_wait); + kref_init(&buf->kref); + setup_timer(&buf->timer, wakeup_readers, (unsigned long)buf); ++ mod_timer(&buf->timer, jiffies + 1); + } else + del_timer_sync(&buf->timer); + +@@ -739,15 +744,6 @@ size_t relay_switch_subbuf(struct rchan_ + else + buf->early_bytes += buf->chan->subbuf_size - + buf->padding[old_subbuf]; +- smp_mb(); +- if (waitqueue_active(&buf->read_wait)) +- /* +- * Calling wake_up_interruptible() from here +- * will deadlock if we happen to be logging +- * from the scheduler (trying to re-grab +- * rq->lock), so defer it. +- */ +- mod_timer(&buf->timer, jiffies + 1); + } + + old = buf->data; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/res_counter.c sun8i-rt/kernel/res_counter.c +--- sun8i/kernel/res_counter.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/res_counter.c 2016-08-22 16:32:25.480219487 +0200 +@@ -43,7 +43,7 @@ int res_counter_charge(struct res_counte + struct res_counter *c, *u; + + *limit_fail_at = NULL; +- local_irq_save(flags); ++ local_irq_save_nort(flags); + for (c = counter; c != NULL; c = c->parent) { + spin_lock(&c->lock); + ret = res_counter_charge_locked(c, val); +@@ -62,7 +62,7 @@ undo: + spin_unlock(&u->lock); + } + done: +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return ret; + } + +@@ -104,13 +104,13 @@ void res_counter_uncharge(struct res_cou + unsigned long flags; + struct res_counter *c; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + for (c = counter; c != NULL; c = c->parent) { + spin_lock(&c->lock); + res_counter_uncharge_locked(c, val); + spin_unlock(&c->lock); + } +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rt.c sun8i-rt/kernel/rt.c +--- sun8i/kernel/rt.c 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/kernel/rt.c 2016-08-22 18:21:41.012294854 +0200 +@@ -0,0 +1,446 @@ ++/* ++ * kernel/rt.c ++ * ++ * Real-Time Preemption Support ++ * ++ * started by Ingo Molnar: ++ * ++ * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar ++ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner ++ * ++ * historic credit for proving that Linux spinlocks can be implemented via ++ * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow ++ * and others) who prototyped it on 2.4 and did lots of comparative ++ * research and analysis; TimeSys, for proving that you can implement a ++ * fully preemptible kernel via the use of IRQ threading and mutexes; ++ * Bill Huey for persuasively arguing on lkml that the mutex model is the ++ * right one; and to MontaVista, who ported pmutexes to 2.6. ++ * ++ * This code is a from-scratch implementation and is not based on pmutexes, ++ * but the idea of converting spinlocks to mutexes is used here too. ++ * ++ * lock debugging, locking tree, deadlock detection: ++ * ++ * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey ++ * Released under the General Public License (GPL). ++ * ++ * Includes portions of the generic R/W semaphore implementation from: ++ * ++ * Copyright (c) 2001 David Howells (dhowells@redhat.com). ++ * - Derived partially from idea by Andrea Arcangeli ++ * - Derived also from comments by Linus ++ * ++ * Pending ownership of locks and ownership stealing: ++ * ++ * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt ++ * ++ * (also by Steven Rostedt) ++ * - Converted single pi_lock to individual task locks. ++ * ++ * By Esben Nielsen: ++ * Doing priority inheritance with help of the scheduler. ++ * ++ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner ++ * - major rework based on Esben Nielsens initial patch ++ * - replaced thread_info references by task_struct refs ++ * - removed task->pending_owner dependency ++ * - BKL drop/reacquire for semaphore style locks to avoid deadlocks ++ * in the scheduler return path as discussed with Steven Rostedt ++ * ++ * Copyright (C) 2006, Kihon Technologies Inc. ++ * Steven Rostedt ++ * - debugged and patched Thomas Gleixner's rework. ++ * - added back the cmpxchg to the rework. ++ * - turned atomic require back on for SMP. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#include "rtmutex_common.h" ++ ++/* ++ * struct mutex functions ++ */ ++void __mutex_do_init(struct mutex *mutex, const char *name, ++ struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); ++ lockdep_init_map(&mutex->dep_map, name, key, 0); ++#endif ++ mutex->lock.save_state = 0; ++} ++EXPORT_SYMBOL(__mutex_do_init); ++ ++void __lockfunc _mutex_lock(struct mutex *lock) ++{ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ rt_mutex_lock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_lock); ++ ++int __lockfunc _mutex_lock_interruptible(struct mutex *lock) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ ret = rt_mutex_lock_interruptible(&lock->lock); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_interruptible); ++ ++int __lockfunc _mutex_lock_killable(struct mutex *lock) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ ret = rt_mutex_lock_killable(&lock->lock); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_killable); ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass) ++{ ++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); ++ rt_mutex_lock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_lock_nested); ++ ++void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) ++{ ++ mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_); ++ rt_mutex_lock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_lock_nest_lock); ++ ++int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass) ++{ ++ int ret; ++ ++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); ++ ret = rt_mutex_lock_interruptible(&lock->lock); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_interruptible_nested); ++ ++int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); ++ ret = rt_mutex_lock_killable(&lock->lock); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_killable_nested); ++#endif ++ ++int __lockfunc _mutex_trylock(struct mutex *lock) ++{ ++ int ret = rt_mutex_trylock(&lock->lock); ++ ++ if (ret) ++ mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_trylock); ++ ++void __lockfunc _mutex_unlock(struct mutex *lock) ++{ ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ rt_mutex_unlock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_unlock); ++ ++/* ++ * rwlock_t functions ++ */ ++int __lockfunc rt_write_trylock(rwlock_t *rwlock) ++{ ++ int ret = rt_mutex_trylock(&rwlock->lock); ++ ++ migrate_disable(); ++ if (ret) ++ rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ ++ return ret; ++} ++EXPORT_SYMBOL(rt_write_trylock); ++ ++int __lockfunc rt_write_trylock_irqsave(rwlock_t *rwlock, unsigned long *flags) ++{ ++ int ret; ++ ++ *flags = 0; ++ migrate_disable(); ++ ret = rt_write_trylock(rwlock); ++ if (!ret) ++ migrate_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_write_trylock_irqsave); ++ ++int __lockfunc rt_read_trylock(rwlock_t *rwlock) ++{ ++ struct rt_mutex *lock = &rwlock->lock; ++ int ret = 1; ++ ++ /* ++ * recursive read locks succeed when current owns the lock, ++ * but not when read_depth == 0 which means that the lock is ++ * write locked. ++ */ ++ migrate_disable(); ++ if (rt_mutex_owner(lock) != current) { ++ ret = rt_mutex_trylock(lock); ++ if (ret) ++ rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); ++ } else if (!rwlock->read_depth) { ++ ret = 0; ++ } ++ ++ if (ret) ++ rwlock->read_depth++; ++ else ++ migrate_enable(); ++ ++ return ret; ++} ++EXPORT_SYMBOL(rt_read_trylock); ++ ++void __lockfunc rt_write_lock(rwlock_t *rwlock) ++{ ++ rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); ++ __rt_spin_lock(&rwlock->lock); ++} ++EXPORT_SYMBOL(rt_write_lock); ++ ++void __lockfunc rt_read_lock(rwlock_t *rwlock) ++{ ++ struct rt_mutex *lock = &rwlock->lock; ++ ++ /* ++ * recursive read locks succeed when current owns the lock ++ */ ++ if (rt_mutex_owner(lock) != current) { ++ rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); ++ __rt_spin_lock(lock); ++ } ++ rwlock->read_depth++; ++} ++ ++EXPORT_SYMBOL(rt_read_lock); ++ ++void __lockfunc rt_write_unlock(rwlock_t *rwlock) ++{ ++ /* NOTE: we always pass in '1' for nested, for simplicity */ ++ rwlock_release(&rwlock->dep_map, 1, _RET_IP_); ++ __rt_spin_unlock(&rwlock->lock); ++} ++EXPORT_SYMBOL(rt_write_unlock); ++ ++void __lockfunc rt_read_unlock(rwlock_t *rwlock) ++{ ++ /* Release the lock only when read_depth is down to 0 */ ++ if (--rwlock->read_depth == 0) { ++ rwlock_release(&rwlock->dep_map, 1, _RET_IP_); ++ __rt_spin_unlock(&rwlock->lock); ++ } ++} ++EXPORT_SYMBOL(rt_read_unlock); ++ ++unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock) ++{ ++ rt_write_lock(rwlock); ++ ++ return 0; ++} ++EXPORT_SYMBOL(rt_write_lock_irqsave); ++ ++unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock) ++{ ++ rt_read_lock(rwlock); ++ ++ return 0; ++} ++EXPORT_SYMBOL(rt_read_lock_irqsave); ++ ++void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock)); ++ lockdep_init_map(&rwlock->dep_map, name, key, 0); ++#endif ++ rwlock->lock.save_state = 1; ++ rwlock->read_depth = 0; ++} ++EXPORT_SYMBOL(__rt_rwlock_init); ++ ++/* ++ * rw_semaphores ++ */ ++ ++void rt_up_write(struct rw_semaphore *rwsem) ++{ ++ rwsem_release(&rwsem->dep_map, 1, _RET_IP_); ++ rt_mutex_unlock(&rwsem->lock); ++} ++EXPORT_SYMBOL(rt_up_write); ++ ++void rt_up_read(struct rw_semaphore *rwsem) ++{ ++ if (--rwsem->read_depth == 0) { ++ rwsem_release(&rwsem->dep_map, 1, _RET_IP_); ++ rt_mutex_unlock(&rwsem->lock); ++ } ++} ++EXPORT_SYMBOL(rt_up_read); ++ ++/* ++ * downgrade a write lock into a read lock ++ * - just wake up any readers at the front of the queue ++ */ ++void rt_downgrade_write(struct rw_semaphore *rwsem) ++{ ++ BUG_ON(rt_mutex_owner(&rwsem->lock) != current); ++ rwsem->read_depth = 1; ++} ++EXPORT_SYMBOL(rt_downgrade_write); ++ ++int rt_down_write_trylock(struct rw_semaphore *rwsem) ++{ ++ int ret = rt_mutex_trylock(&rwsem->lock); ++ ++ if (ret) ++ rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(rt_down_write_trylock); ++ ++void rt_down_write(struct rw_semaphore *rwsem) ++{ ++ rwsem_acquire(&rwsem->dep_map, 0, 0, _RET_IP_); ++ rt_mutex_lock(&rwsem->lock); ++} ++EXPORT_SYMBOL(rt_down_write); ++ ++void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass) ++{ ++ rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_); ++ rt_mutex_lock(&rwsem->lock); ++} ++EXPORT_SYMBOL(rt_down_write_nested); ++ ++int rt_down_read_trylock(struct rw_semaphore *rwsem) ++{ ++ struct rt_mutex *lock = &rwsem->lock; ++ int ret = 1; ++ ++ /* ++ * recursive read locks succeed when current owns the rwsem, ++ * but not when read_depth == 0 which means that the rwsem is ++ * write locked. ++ */ ++ if (rt_mutex_owner(lock) != current) { ++ ret = rt_mutex_trylock(&rwsem->lock); ++ if (ret) ++ rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); ++ } else if (!rwsem->read_depth) { ++ ret = 0; ++ } ++ ++ if (ret) ++ rwsem->read_depth++; ++ return ret; ++} ++EXPORT_SYMBOL(rt_down_read_trylock); ++ ++static void __rt_down_read(struct rw_semaphore *rwsem, int subclass) ++{ ++ struct rt_mutex *lock = &rwsem->lock; ++ ++ if (rt_mutex_owner(lock) != current) { ++ rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_); ++ rt_mutex_lock(&rwsem->lock); ++ } ++ rwsem->read_depth++; ++} ++ ++void rt_down_read(struct rw_semaphore *rwsem) ++{ ++ __rt_down_read(rwsem, 0); ++} ++EXPORT_SYMBOL(rt_down_read); ++ ++void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass) ++{ ++ __rt_down_read(rwsem, subclass); ++} ++EXPORT_SYMBOL(rt_down_read_nested); ++ ++void __rt_rwsem_init(struct rw_semaphore *rwsem, char *name, ++ struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)rwsem, sizeof(*rwsem)); ++ lockdep_init_map(&rwsem->dep_map, name, key, 0); ++#endif ++ rwsem->read_depth = 0; ++ rwsem->lock.save_state = 0; ++} ++EXPORT_SYMBOL(__rt_rwsem_init); ++ ++/** ++ * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 ++ * @cnt: the atomic which we are to dec ++ * @lock: the mutex to return holding if we dec to 0 ++ * ++ * return true and hold lock if we dec to 0, return false otherwise ++ */ ++int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) ++{ ++ /* dec if we can't possibly hit 0 */ ++ if (atomic_add_unless(cnt, -1, 1)) ++ return 0; ++ /* we might hit 0, so take the lock */ ++ mutex_lock(lock); ++ if (!atomic_dec_and_test(cnt)) { ++ /* when we actually did the dec, we didn't hit 0 */ ++ mutex_unlock(lock); ++ return 0; ++ } ++ /* we hit 0, and we hold the lock */ ++ return 1; ++} ++EXPORT_SYMBOL(atomic_dec_and_mutex_lock); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rtmutex.c sun8i-rt/kernel/rtmutex.c +--- sun8i/kernel/rtmutex.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/kernel/rtmutex.c 2016-08-22 18:27:34.696298920 +0200 +@@ -8,6 +8,12 @@ + * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt + * Copyright (C) 2006 Esben Nielsen + * ++ * Adaptive Spinlocks: ++ * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich, ++ * and Peter Morreale, ++ * Adaptive Spinlocks simplification: ++ * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt ++ * + * See Documentation/rt-mutex-design.txt for details. + */ + #include +@@ -67,6 +73,12 @@ static void fixup_rt_mutex_waiters(struc + clear_rt_mutex_waiters(lock); + } + ++static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) ++{ ++ return waiter && waiter != PI_WAKEUP_INPROGRESS && ++ waiter != PI_REQUEUE_INPROGRESS; ++} ++ + /* + * We can speed up the acquire/release, if the architecture + * supports cmpxchg and if there's no debugging state to be set up +@@ -142,6 +154,37 @@ static inline bool unlock_rt_mutex_safe( + } + #endif + ++static inline void ++rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) ++{ ++ plist_add(&waiter->list_entry, &lock->wait_list); ++} ++ ++static inline void ++rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) ++{ ++ plist_del(&waiter->list_entry, &lock->wait_list); ++} ++ ++static inline void ++rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter) ++{ ++ waiter->pi_list_entry.prio = waiter->list_entry.prio; ++ plist_add(&waiter->pi_list_entry, &task->pi_waiters); ++} ++ ++static inline void ++rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter) ++{ ++ plist_del(&waiter->pi_list_entry, &task->pi_waiters); ++} ++ ++static inline void init_lists(struct rt_mutex *lock) ++{ ++ if (unlikely(!lock->wait_list.node_list.prev)) ++ plist_head_init(&lock->wait_list); ++} ++ + /* + * Calculate task priority from the waiter list priority + * +@@ -158,6 +201,18 @@ int rt_mutex_getprio(struct task_struct + } + + /* ++ * Called by sched_setscheduler() to check whether the priority change ++ * is overruled by a possible priority boosting. ++ */ ++int rt_mutex_check_prio(struct task_struct *task, int newprio) ++{ ++ if (!task_has_pi_waiters(task)) ++ return 0; ++ ++ return task_top_pi_waiter(task)->pi_list_entry.prio <= newprio; ++} ++ ++/* + * Adjust the priority of a task, after its pi_waiters got modified. + * + * This can be both boosting and unboosting. task->pi_lock must be held. +@@ -188,6 +243,40 @@ static void rt_mutex_adjust_prio(struct + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + } + ++static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter) ++{ ++ if (waiter->savestate) ++ wake_up_lock_sleeper(waiter->task); ++ else ++ wake_up_process(waiter->task); ++} ++ ++/* ++ * Deadlock detection is conditional: ++ * ++ * If CONFIG_DEBUG_RT_MUTEXES=n, deadlock detection is only conducted ++ * if the detect argument is == RT_MUTEX_FULL_CHAINWALK. ++ * ++ * If CONFIG_DEBUG_RT_MUTEXES=y, deadlock detection is always ++ * conducted independent of the detect argument. ++ * ++ * If the waiter argument is NULL this indicates the deboost path and ++ * deadlock detection is disabled independent of the detect argument ++ * and the config settings. ++ */ ++static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, ++ enum rtmutex_chainwalk chwalk) ++{ ++ /* ++ * This is just a wrapper function for the following call, ++ * because debug_rt_mutex_detect_deadlock() smells like a magic ++ * debug feature and I wanted to keep the cond function in the ++ * main source file along with the comments instead of having ++ * two of the same in the headers. ++ */ ++ return debug_rt_mutex_detect_deadlock(waiter, chwalk); ++} ++ + /* + * Max number of times we'll walk the boosting chain: + */ +@@ -202,21 +291,65 @@ static inline struct rt_mutex *task_bloc + * Adjust the priority chain. Also used for deadlock detection. + * Decreases task's usage by one - may thus free the task. + * Returns 0 or -EDEADLK. ++ * ++ * Chain walk basics and protection scope ++ * ++ * [R] refcount on task ++ * [P] task->pi_lock held ++ * [L] rtmutex->wait_lock held ++ * ++ * Step Description Protected by ++ * function arguments: ++ * @task [R] ++ * @orig_lock if != NULL @top_task is blocked on it ++ * @next_lock Unprotected. Cannot be ++ * dereferenced. Only used for ++ * comparison. ++ * @orig_waiter if != NULL @top_task is blocked on it ++ * @top_task current, or in case of proxy ++ * locking protected by calling ++ * code ++ * again: ++ * loop_sanity_check(); ++ * retry: ++ * [1] lock(task->pi_lock); [R] acquire [P] ++ * [2] waiter = task->pi_blocked_on; [P] ++ * [3] check_exit_conditions_1(); [P] ++ * [4] lock = waiter->lock; [P] ++ * [5] if (!try_lock(lock->wait_lock)) { [P] try to acquire [L] ++ * unlock(task->pi_lock); release [P] ++ * goto retry; ++ * } ++ * [6] check_exit_conditions_2(); [P] + [L] ++ * [7] requeue_lock_waiter(lock, waiter); [P] + [L] ++ * [8] unlock(task->pi_lock); release [P] ++ * put_task_struct(task); release [R] ++ * [9] check_exit_conditions_3(); [L] ++ * [10] task = owner(lock); [L] ++ * get_task_struct(task); [L] acquire [R] ++ * lock(task->pi_lock); [L] acquire [P] ++ * [11] requeue_pi_waiter(tsk, waiters(lock));[P] + [L] ++ * [12] check_exit_conditions_4(); [P] + [L] ++ * [13] unlock(task->pi_lock); release [P] ++ * unlock(lock->wait_lock); release [L] ++ * goto again; + */ + static int rt_mutex_adjust_prio_chain(struct task_struct *task, +- int deadlock_detect, ++ enum rtmutex_chainwalk chwalk, + struct rt_mutex *orig_lock, + struct rt_mutex *next_lock, + struct rt_mutex_waiter *orig_waiter, + struct task_struct *top_task) + { +- struct rt_mutex *lock; + struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter; +- int detect_deadlock, ret = 0, depth = 0; ++ struct rt_mutex_waiter *prerequeue_top_waiter; ++ int ret = 0, depth = 0; ++ struct rt_mutex *lock; ++ bool detect_deadlock; + unsigned long flags; ++ bool requeue = true; + +- detect_deadlock = debug_rt_mutex_detect_deadlock(orig_waiter, +- deadlock_detect); ++ detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk); + + /* + * The (de)boosting is a step by step approach with a lot of +@@ -225,6 +358,9 @@ static int rt_mutex_adjust_prio_chain(st + * carefully whether things change under us. + */ + again: ++ /* ++ * We limit the lock chain length for each invocation. ++ */ + if (++depth > max_lock_depth) { + static int prev_max; + +@@ -242,19 +378,34 @@ static int rt_mutex_adjust_prio_chain(st + + return -EDEADLK; + } ++ ++ /* ++ * We are fully preemptible here and only hold the refcount on ++ * @task. So everything can have changed under us since the ++ * caller or our own code below (goto retry/again) dropped all ++ * locks. ++ */ + retry: + /* +- * Task can not go away as we did a get_task() before ! ++ * [1] Task cannot go away as we did a get_task() before ! + */ + raw_spin_lock_irqsave(&task->pi_lock, flags); + ++ /* ++ * [2] Get the waiter on which @task is blocked on. ++ */ + waiter = task->pi_blocked_on; ++ ++ /* ++ * [3] check_exit_conditions_1() protected by task->pi_lock. ++ */ ++ + /* + * Check whether the end of the boosting chain has been + * reached or the state of the chain has changed while we + * dropped the locks. + */ +- if (!waiter) ++ if (!rt_mutex_real_waiter(waiter)) + goto out_unlock_pi; + + /* +@@ -286,20 +437,41 @@ static int rt_mutex_adjust_prio_chain(st + goto out_unlock_pi; + /* + * If deadlock detection is off, we stop here if we +- * are not the top pi waiter of the task. ++ * are not the top pi waiter of the task. If deadlock ++ * detection is enabled we continue, but stop the ++ * requeueing in the chain walk. + */ +- if (!detect_deadlock && top_waiter != task_top_pi_waiter(task)) +- goto out_unlock_pi; ++ if (top_waiter != task_top_pi_waiter(task)) { ++ if (!detect_deadlock) ++ goto out_unlock_pi; ++ else ++ requeue = false; ++ } + } + + /* +- * When deadlock detection is off then we check, if further +- * priority adjustment is necessary. ++ * If the waiter priority is the same as the task priority ++ * then there is no further priority adjustment necessary. If ++ * deadlock detection is off, we stop the chain walk. If its ++ * enabled we continue, but stop the requeueing in the chain ++ * walk. + */ +- if (!detect_deadlock && waiter->list_entry.prio == task->prio) +- goto out_unlock_pi; ++ if (waiter->list_entry.prio == task->prio) { ++ if (!detect_deadlock) ++ goto out_unlock_pi; ++ else ++ requeue = false; ++ } + ++ /* ++ * [4] Get the next lock ++ */ + lock = waiter->lock; ++ /* ++ * [5] We need to trylock here as we are holding task->pi_lock, ++ * which is the reverse lock order versus the other rtmutex ++ * operations. ++ */ + if (!raw_spin_trylock(&lock->wait_lock)) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + cpu_relax(); +@@ -307,81 +479,183 @@ static int rt_mutex_adjust_prio_chain(st + } + + /* ++ * [6] check_exit_conditions_2() protected by task->pi_lock and ++ * lock->wait_lock. ++ * + * Deadlock detection. If the lock is the same as the original + * lock which caused us to walk the lock chain or if the + * current lock is owned by the task which initiated the chain + * walk, we detected a deadlock. + */ + if (lock == orig_lock || rt_mutex_owner(lock) == top_task) { +- debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock); ++ debug_rt_mutex_deadlock(chwalk, orig_waiter, lock); + raw_spin_unlock(&lock->wait_lock); + ret = -EDEADLK; + goto out_unlock_pi; + } + +- top_waiter = rt_mutex_top_waiter(lock); ++ /* ++ * If we just follow the lock chain for deadlock detection, no ++ * need to do all the requeue operations. To avoid a truckload ++ * of conditionals around the various places below, just do the ++ * minimum chain walk checks. ++ */ ++ if (!requeue) { ++ /* ++ * No requeue[7] here. Just release @task [8] ++ */ ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ put_task_struct(task); + +- /* Requeue the waiter */ +- plist_del(&waiter->list_entry, &lock->wait_list); ++ /* ++ * [9] check_exit_conditions_3 protected by lock->wait_lock. ++ * If there is no owner of the lock, end of chain. ++ */ ++ if (!rt_mutex_owner(lock)) { ++ raw_spin_unlock(&lock->wait_lock); ++ return 0; ++ } ++ ++ /* [10] Grab the next task, i.e. owner of @lock */ ++ task = rt_mutex_owner(lock); ++ get_task_struct(task); ++ raw_spin_lock_irqsave(&task->pi_lock, flags); ++ ++ /* ++ * No requeue [11] here. We just do deadlock detection. ++ * ++ * [12] Store whether owner is blocked ++ * itself. Decision is made after dropping the locks ++ */ ++ next_lock = task_blocked_on_lock(task); ++ /* ++ * Get the top waiter for the next iteration ++ */ ++ top_waiter = rt_mutex_top_waiter(lock); ++ ++ /* [13] Drop locks */ ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ raw_spin_unlock(&lock->wait_lock); ++ ++ /* If owner is not blocked, end of chain. */ ++ if (!next_lock) ++ goto out_put_task; ++ goto again; ++ } ++ ++ /* ++ * Store the current top waiter before doing the requeue ++ * operation on @lock. We need it for the boost/deboost ++ * decision below. ++ */ ++ prerequeue_top_waiter = rt_mutex_top_waiter(lock); ++ ++ /* [7] Requeue the waiter in the lock waiter list. */ ++ rt_mutex_dequeue(lock, waiter); + waiter->list_entry.prio = task->prio; +- plist_add(&waiter->list_entry, &lock->wait_list); ++ rt_mutex_enqueue(lock, waiter); + +- /* Release the task */ ++ /* [8] Release the task */ + raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ put_task_struct(task); ++ ++ /* ++ * [9] check_exit_conditions_3 protected by lock->wait_lock. ++ * ++ * We must abort the chain walk if there is no lock owner even ++ * in the dead lock detection case, as we have nothing to ++ * follow here. This is the end of the chain we are walking. ++ */ + if (!rt_mutex_owner(lock)) { ++ struct rt_mutex_waiter *lock_top_waiter; ++ + /* +- * If the requeue above changed the top waiter, then we need +- * to wake the new top waiter up to try to get the lock. ++ * If the requeue [7] above changed the top waiter, ++ * then we need to wake the new top waiter up to try ++ * to get the lock. + */ +- +- if (top_waiter != rt_mutex_top_waiter(lock)) +- wake_up_process(rt_mutex_top_waiter(lock)->task); ++ lock_top_waiter = rt_mutex_top_waiter(lock); ++ if (prerequeue_top_waiter != lock_top_waiter) ++ rt_mutex_wake_waiter(lock_top_waiter); + raw_spin_unlock(&lock->wait_lock); +- goto out_put_task; ++ return 0; + } +- put_task_struct(task); + +- /* Grab the next task */ ++ /* [10] Grab the next task, i.e. the owner of @lock */ + task = rt_mutex_owner(lock); + get_task_struct(task); + raw_spin_lock_irqsave(&task->pi_lock, flags); + ++ /* [11] requeue the pi waiters if necessary */ + if (waiter == rt_mutex_top_waiter(lock)) { +- /* Boost the owner */ +- plist_del(&top_waiter->pi_list_entry, &task->pi_waiters); +- waiter->pi_list_entry.prio = waiter->list_entry.prio; +- plist_add(&waiter->pi_list_entry, &task->pi_waiters); ++ /* ++ * The waiter became the new top (highest priority) ++ * waiter on the lock. Replace the previous top waiter ++ * in the owner tasks pi waiters list with this waiter ++ * and adjust the priority of the owner. ++ */ ++ rt_mutex_dequeue_pi(task, prerequeue_top_waiter); ++ rt_mutex_enqueue_pi(task, waiter); + __rt_mutex_adjust_prio(task); + +- } else if (top_waiter == waiter) { +- /* Deboost the owner */ +- plist_del(&waiter->pi_list_entry, &task->pi_waiters); ++ } else if (prerequeue_top_waiter == waiter) { ++ /* ++ * The waiter was the top waiter on the lock, but is ++ * no longer the top prority waiter. Replace waiter in ++ * the owner tasks pi waiters list with the new top ++ * (highest priority) waiter and adjust the priority ++ * of the owner. ++ * The new top waiter is stored in @waiter so that ++ * @waiter == @top_waiter evaluates to true below and ++ * we continue to deboost the rest of the chain. ++ */ ++ rt_mutex_dequeue_pi(task, waiter); + waiter = rt_mutex_top_waiter(lock); +- waiter->pi_list_entry.prio = waiter->list_entry.prio; +- plist_add(&waiter->pi_list_entry, &task->pi_waiters); ++ rt_mutex_enqueue_pi(task, waiter); + __rt_mutex_adjust_prio(task); ++ } else { ++ /* ++ * Nothing changed. No need to do any priority ++ * adjustment. ++ */ + } + + /* ++ * [12] check_exit_conditions_4() protected by task->pi_lock ++ * and lock->wait_lock. The actual decisions are made after we ++ * dropped the locks. ++ * + * Check whether the task which owns the current lock is pi + * blocked itself. If yes we store a pointer to the lock for + * the lock chain change detection above. After we dropped + * task->pi_lock next_lock cannot be dereferenced anymore. + */ + next_lock = task_blocked_on_lock(task); ++ /* ++ * Store the top waiter of @lock for the end of chain walk ++ * decision below. ++ */ ++ top_waiter = rt_mutex_top_waiter(lock); + ++ /* [13] Drop the locks */ + raw_spin_unlock_irqrestore(&task->pi_lock, flags); +- +- top_waiter = rt_mutex_top_waiter(lock); + raw_spin_unlock(&lock->wait_lock); + + /* ++ * Make the actual exit decisions [12], based on the stored ++ * values. ++ * + * We reached the end of the lock chain. Stop right here. No + * point to go back just to figure that out. + */ + if (!next_lock) + goto out_put_task; + ++ /* ++ * If the current waiter is not the top waiter on the lock, ++ * then we can stop the chain walk here if we are not in full ++ * deadlock detection mode. ++ */ + if (!detect_deadlock && waiter != top_waiter) + goto out_put_task; + +@@ -395,82 +669,146 @@ static int rt_mutex_adjust_prio_chain(st + return ret; + } + ++ ++#define STEAL_NORMAL 0 ++#define STEAL_LATERAL 1 ++ ++/* ++ * Note that RT tasks are excluded from lateral-steals to prevent the ++ * introduction of an unbounded latency ++ */ ++static inline int lock_is_stealable(struct task_struct *task, ++ struct task_struct *pendowner, int mode) ++{ ++ if (mode == STEAL_NORMAL || rt_task(task)) { ++ if (task->prio >= pendowner->prio) ++ return 0; ++ } else if (task->prio > pendowner->prio) ++ return 0; ++ return 1; ++} ++ + /* + * Try to take an rt-mutex + * + * Must be called with lock->wait_lock held. + * +- * @lock: the lock to be acquired. +- * @task: the task which wants to acquire the lock +- * @waiter: the waiter that is queued to the lock's wait list. (could be NULL) ++ * @lock: The lock to be acquired. ++ * @task: The task which wants to acquire the lock ++ * @waiter: The waiter that is queued to the lock's wait list if the ++ * callsite called task_blocked_on_lock(), otherwise NULL + */ +-static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, +- struct rt_mutex_waiter *waiter) ++static int ++__try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, ++ struct rt_mutex_waiter *waiter, int mode) + { ++ unsigned long flags; ++ + /* +- * We have to be careful here if the atomic speedups are +- * enabled, such that, when +- * - no other waiter is on the lock +- * - the lock has been released since we did the cmpxchg +- * the lock can be released or taken while we are doing the +- * checks and marking the lock with RT_MUTEX_HAS_WAITERS. ++ * Before testing whether we can acquire @lock, we set the ++ * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all ++ * other tasks which try to modify @lock into the slow path ++ * and they serialize on @lock->wait_lock. + * +- * The atomic acquire/release aware variant of +- * mark_rt_mutex_waiters uses a cmpxchg loop. After setting +- * the WAITERS bit, the atomic release / acquire can not +- * happen anymore and lock->wait_lock protects us from the +- * non-atomic case. ++ * The RT_MUTEX_HAS_WAITERS bit can have a transitional state ++ * as explained at the top of this file if and only if: + * +- * Note, that this might set lock->owner = +- * RT_MUTEX_HAS_WAITERS in the case the lock is not contended +- * any more. This is fixed up when we take the ownership. +- * This is the transitional state explained at the top of this file. ++ * - There is a lock owner. The caller must fixup the ++ * transient state if it does a trylock or leaves the lock ++ * function due to a signal or timeout. ++ * ++ * - @task acquires the lock and there are no other ++ * waiters. This is undone in rt_mutex_set_owner(@task) at ++ * the end of this function. + */ + mark_rt_mutex_waiters(lock); + ++ /* ++ * If @lock has an owner, give up. ++ */ + if (rt_mutex_owner(lock)) + return 0; + + /* +- * It will get the lock because of one of these conditions: +- * 1) there is no waiter +- * 2) higher priority than waiters +- * 3) it is top waiter ++ * If @waiter != NULL, @task has already enqueued the waiter ++ * into @lock waiter list. If @waiter == NULL then this is a ++ * trylock attempt. + */ +- if (rt_mutex_has_waiters(lock)) { +- if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) { +- if (!waiter || waiter != rt_mutex_top_waiter(lock)) +- return 0; +- } +- } +- +- if (waiter || rt_mutex_has_waiters(lock)) { +- unsigned long flags; +- struct rt_mutex_waiter *top; +- +- raw_spin_lock_irqsave(&task->pi_lock, flags); ++ if (waiter) { ++ /* ++ * If waiter is not the highest priority waiter of ++ * @lock, give up. ++ */ ++ if (waiter != rt_mutex_top_waiter(lock)) ++ return 0; + +- /* remove the queued waiter. */ +- if (waiter) { +- plist_del(&waiter->list_entry, &lock->wait_list); +- task->pi_blocked_on = NULL; +- } ++ /* ++ * We can acquire the lock. Remove the waiter from the ++ * lock waiters list. ++ */ ++ rt_mutex_dequeue(lock, waiter); + ++ } else { + /* +- * We have to enqueue the top waiter(if it exists) into +- * task->pi_waiters list. ++ * If the lock has waiters already we check whether @task is ++ * eligible to take over the lock. ++ * ++ * If there are no other waiters, @task can acquire ++ * the lock. @task->pi_blocked_on is NULL, so it does ++ * not need to be dequeued. + */ + if (rt_mutex_has_waiters(lock)) { +- top = rt_mutex_top_waiter(lock); +- top->pi_list_entry.prio = top->list_entry.prio; +- plist_add(&top->pi_list_entry, &task->pi_waiters); ++ struct task_struct *pown = rt_mutex_top_waiter(lock)->task; ++ ++ /* ++ * If @task->prio is greater than or equal to ++ * the top waiter priority (kernel view), ++ * @task lost. ++ */ ++ if (task != pown && !lock_is_stealable(task, pown, mode)) ++ return 0; ++ ++ /* ++ * The current top waiter stays enqueued. We ++ * don't have to change anything in the lock ++ * waiters order. ++ */ ++ } else { ++ /* ++ * No waiters. Take the lock without the ++ * pi_lock dance.@task->pi_blocked_on is NULL ++ * and we have no waiters to enqueue in @task ++ * pi waiters list. ++ */ ++ goto takeit; + } +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); + } + ++ /* ++ * Clear @task->pi_blocked_on. Requires protection by ++ * @task->pi_lock. Redundant operation for the @waiter == NULL ++ * case, but conditionals are more expensive than a redundant ++ * store. ++ */ ++ raw_spin_lock_irqsave(&task->pi_lock, flags); ++ task->pi_blocked_on = NULL; ++ /* ++ * Finish the lock acquisition. @task is the new owner. If ++ * other waiters exist we have to insert the highest priority ++ * waiter into @task->pi_waiters list. ++ */ ++ if (rt_mutex_has_waiters(lock)) ++ rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock)); ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ ++takeit: + /* We got the lock. */ + debug_rt_mutex_lock(lock); + ++ /* ++ * This either preserves the RT_MUTEX_HAS_WAITERS bit if there ++ * are still waiters or clears it. ++ */ + rt_mutex_set_owner(lock, task); + + rt_mutex_deadlock_account_lock(lock, task); +@@ -478,6 +816,13 @@ static int try_to_take_rt_mutex(struct r + return 1; + } + ++static inline int ++try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, ++ struct rt_mutex_waiter *waiter) ++{ ++ return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL); ++} ++ + /* + * Task blocks on lock. + * +@@ -488,7 +833,7 @@ static int try_to_take_rt_mutex(struct r + static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task, +- int detect_deadlock) ++ enum rtmutex_chainwalk chwalk) + { + struct task_struct *owner = rt_mutex_owner(lock); + struct rt_mutex_waiter *top_waiter = waiter; +@@ -509,6 +854,23 @@ static int task_blocks_on_rt_mutex(struc + return -EDEADLK; + + raw_spin_lock_irqsave(&task->pi_lock, flags); ++ ++ /* ++ * In the case of futex requeue PI, this will be a proxy ++ * lock. The task will wake unaware that it is enqueueed on ++ * this lock. Avoid blocking on two locks and corrupting ++ * pi_blocked_on via the PI_WAKEUP_INPROGRESS ++ * flag. futex_wait_requeue_pi() sets this when it wakes up ++ * before requeue (due to a signal or timeout). Do not enqueue ++ * the task if PI_WAKEUP_INPROGRESS is set. ++ */ ++ if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ return -EAGAIN; ++ } ++ ++ BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); ++ + __rt_mutex_adjust_prio(task); + waiter->task = task; + waiter->lock = lock; +@@ -518,7 +880,7 @@ static int task_blocks_on_rt_mutex(struc + /* Get the top priority waiter on the lock */ + if (rt_mutex_has_waiters(lock)) + top_waiter = rt_mutex_top_waiter(lock); +- plist_add(&waiter->list_entry, &lock->wait_list); ++ rt_mutex_enqueue(lock, waiter); + + task->pi_blocked_on = waiter; + +@@ -529,13 +891,13 @@ static int task_blocks_on_rt_mutex(struc + + raw_spin_lock_irqsave(&owner->pi_lock, flags); + if (waiter == rt_mutex_top_waiter(lock)) { +- plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters); +- plist_add(&waiter->pi_list_entry, &owner->pi_waiters); ++ rt_mutex_dequeue_pi(owner, top_waiter); ++ rt_mutex_enqueue_pi(owner, waiter); + + __rt_mutex_adjust_prio(owner); +- if (owner->pi_blocked_on) ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) + chain_walk = 1; +- } else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) { ++ } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { + chain_walk = 1; + } + +@@ -560,7 +922,7 @@ static int task_blocks_on_rt_mutex(struc + + raw_spin_unlock(&lock->wait_lock); + +- res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, ++ res = rt_mutex_adjust_prio_chain(owner, chwalk, lock, + next_lock, waiter, task); + + raw_spin_lock(&lock->wait_lock); +@@ -591,7 +953,7 @@ static void wakeup_next_waiter(struct rt + * boosted mode and go back to normal after releasing + * lock->wait_lock. + */ +- plist_del(&waiter->pi_list_entry, ¤t->pi_waiters); ++ rt_mutex_dequeue_pi(current, waiter); + + /* + * As we are waking up the top waiter, and the waiter stays +@@ -610,7 +972,7 @@ static void wakeup_next_waiter(struct rt + * long as we hold lock->wait_lock. The waiter task needs to + * acquire it in order to dequeue the waiter. + */ +- wake_up_process(waiter->task); ++ rt_mutex_wake_waiter(waiter); + } + + /* +@@ -622,41 +984,44 @@ static void wakeup_next_waiter(struct rt + static void remove_waiter(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter) + { +- int first = (waiter == rt_mutex_top_waiter(lock)); ++ bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); + struct task_struct *owner = rt_mutex_owner(lock); + struct rt_mutex *next_lock = NULL; + unsigned long flags; + + raw_spin_lock_irqsave(¤t->pi_lock, flags); +- plist_del(&waiter->list_entry, &lock->wait_list); ++ rt_mutex_dequeue(lock, waiter); + current->pi_blocked_on = NULL; + raw_spin_unlock_irqrestore(¤t->pi_lock, flags); + +- if (!owner) ++ /* ++ * Only update priority if the waiter was the highest priority ++ * waiter of the lock and there is an owner to update. ++ */ ++ if (!owner || !is_top_waiter) + return; + +- if (first) { +- +- raw_spin_lock_irqsave(&owner->pi_lock, flags); ++ raw_spin_lock_irqsave(&owner->pi_lock, flags); + +- plist_del(&waiter->pi_list_entry, &owner->pi_waiters); ++ rt_mutex_dequeue_pi(owner, waiter); + +- if (rt_mutex_has_waiters(lock)) { +- struct rt_mutex_waiter *next; ++ if (rt_mutex_has_waiters(lock)) ++ rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock)); + +- next = rt_mutex_top_waiter(lock); +- plist_add(&next->pi_list_entry, &owner->pi_waiters); +- } +- __rt_mutex_adjust_prio(owner); ++ __rt_mutex_adjust_prio(owner); + +- /* Store the lock on which owner is blocked or NULL */ ++ /* Store the lock on which owner is blocked or NULL */ ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) + next_lock = task_blocked_on_lock(owner); + +- raw_spin_unlock_irqrestore(&owner->pi_lock, flags); +- } ++ raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + + WARN_ON(!plist_node_empty(&waiter->pi_list_entry)); + ++ /* ++ * Don't walk the chain, if the owner task is not blocked ++ * itself. ++ */ + if (!next_lock) + return; + +@@ -665,7 +1030,8 @@ static void remove_waiter(struct rt_mute + + raw_spin_unlock(&lock->wait_lock); + +- rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current); ++ rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock, ++ next_lock, NULL, current); + + raw_spin_lock(&lock->wait_lock); + } +@@ -684,24 +1050,340 @@ void rt_mutex_adjust_pi(struct task_stru + raw_spin_lock_irqsave(&task->pi_lock, flags); + + waiter = task->pi_blocked_on; +- if (!waiter || waiter->list_entry.prio == task->prio) { ++ if (!rt_mutex_real_waiter(waiter) || ++ waiter->list_entry.prio == task->prio) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return; + } +- next_lock = waiter->lock; +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); + ++ next_lock = waiter->lock; + /* gets dropped in rt_mutex_adjust_prio_chain()! */ + get_task_struct(task); ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL, ++ next_lock, NULL, task); ++} + +- rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task); ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * preemptible spin_lock functions: ++ */ ++static inline void rt_spin_lock_fastlock(struct rt_mutex *lock, ++ void (*slowfn)(struct rt_mutex *lock)) ++{ ++ might_sleep(); ++ ++ if (likely(rt_mutex_cmpxchg(lock, NULL, current))) ++ rt_mutex_deadlock_account_lock(lock, current); ++ else ++ slowfn(lock); ++} ++ ++static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock, ++ void (*slowfn)(struct rt_mutex *lock)) ++{ ++ if (likely(rt_mutex_cmpxchg(lock, current, NULL))) ++ rt_mutex_deadlock_account_unlock(current); ++ else ++ slowfn(lock); ++} ++ ++#ifdef CONFIG_SMP ++/* ++ * Note that owner is a speculative pointer and dereferencing relies ++ * on rcu_read_lock() and the check against the lock owner. ++ */ ++static int adaptive_wait(struct rt_mutex *lock, ++ struct task_struct *owner) ++{ ++ int res = 0; ++ ++ rcu_read_lock(); ++ for (;;) { ++ if (owner != rt_mutex_owner(lock)) ++ break; ++ /* ++ * Ensure that owner->on_cpu is dereferenced _after_ ++ * checking the above to be valid. ++ */ ++ barrier(); ++ if (!owner->on_cpu) { ++ res = 1; ++ break; ++ } ++ cpu_relax(); ++ } ++ rcu_read_unlock(); ++ return res; ++} ++#else ++static int adaptive_wait(struct rt_mutex *lock, ++ struct task_struct *orig_owner) ++{ ++ return 1; ++} ++#endif ++ ++# define pi_lock(lock) raw_spin_lock_irq(lock) ++# define pi_unlock(lock) raw_spin_unlock_irq(lock) ++ ++/* ++ * Slow path lock function spin_lock style: this variant is very ++ * careful not to miss any non-lock wakeups. ++ * ++ * We store the current state under p->pi_lock in p->saved_state and ++ * the try_to_wake_up() code handles this accordingly. ++ */ ++static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock) ++{ ++ struct task_struct *lock_owner, *self = current; ++ struct rt_mutex_waiter waiter, *top_waiter; ++ int ret; ++ ++ rt_mutex_init_waiter(&waiter, true); ++ ++ raw_spin_lock(&lock->wait_lock); ++ init_lists(lock); ++ ++ if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) { ++ raw_spin_unlock(&lock->wait_lock); ++ return; ++ } ++ ++ BUG_ON(rt_mutex_owner(lock) == self); ++ ++ /* ++ * We save whatever state the task is in and we'll restore it ++ * after acquiring the lock taking real wakeups into account ++ * as well. We are serialized via pi_lock against wakeups. See ++ * try_to_wake_up(). ++ */ ++ pi_lock(&self->pi_lock); ++ self->saved_state = self->state; ++ __set_current_state(TASK_UNINTERRUPTIBLE); ++ pi_unlock(&self->pi_lock); ++ ++ ret = task_blocks_on_rt_mutex(lock, &waiter, self, RT_MUTEX_MIN_CHAINWALK); ++ BUG_ON(ret); ++ ++ for (;;) { ++ /* Try to acquire the lock again. */ ++ if (__try_to_take_rt_mutex(lock, self, &waiter, STEAL_LATERAL)) ++ break; ++ ++ top_waiter = rt_mutex_top_waiter(lock); ++ lock_owner = rt_mutex_owner(lock); ++ ++ raw_spin_unlock(&lock->wait_lock); ++ ++ debug_rt_mutex_print_deadlock(&waiter); ++ ++ if (top_waiter != &waiter || adaptive_wait(lock, lock_owner)) ++ schedule_rt_mutex(lock); ++ ++ raw_spin_lock(&lock->wait_lock); ++ ++ pi_lock(&self->pi_lock); ++ __set_current_state(TASK_UNINTERRUPTIBLE); ++ pi_unlock(&self->pi_lock); ++ } ++ ++ /* ++ * Restore the task state to current->saved_state. We set it ++ * to the original state above and the try_to_wake_up() code ++ * has possibly updated it when a real (non-rtmutex) wakeup ++ * happened while we were blocked. Clear saved_state so ++ * try_to_wakeup() does not get confused. ++ */ ++ pi_lock(&self->pi_lock); ++ __set_current_state(self->saved_state); ++ self->saved_state = TASK_RUNNING; ++ pi_unlock(&self->pi_lock); ++ ++ /* ++ * try_to_take_rt_mutex() sets the waiter bit ++ * unconditionally. We might have to fix that up: ++ */ ++ fixup_rt_mutex_waiters(lock); ++ ++ BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock)); ++ BUG_ON(!plist_node_empty(&waiter.list_entry)); ++ ++ raw_spin_unlock(&lock->wait_lock); ++ ++ debug_rt_mutex_free_waiter(&waiter); ++} ++ ++/* ++ * Slow path to release a rt_mutex spin_lock style ++ */ ++static void __sched __rt_spin_lock_slowunlock(struct rt_mutex *lock) ++{ ++ debug_rt_mutex_unlock(lock); ++ ++ rt_mutex_deadlock_account_unlock(current); ++ ++ if (!rt_mutex_has_waiters(lock)) { ++ lock->owner = NULL; ++ raw_spin_unlock(&lock->wait_lock); ++ return; ++ } ++ ++ wakeup_next_waiter(lock); ++ ++ raw_spin_unlock(&lock->wait_lock); ++ ++ /* Undo pi boosting.when necessary */ ++ rt_mutex_adjust_prio(current); ++} ++ ++static void noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) ++{ ++ raw_spin_lock(&lock->wait_lock); ++ __rt_spin_lock_slowunlock(lock); ++} ++ ++static void noinline __sched rt_spin_lock_slowunlock_hirq(struct rt_mutex *lock) ++{ ++ int ret; ++ ++ do { ++ ret = raw_spin_trylock(&lock->wait_lock); ++ } while (!ret); ++ ++ __rt_spin_lock_slowunlock(lock); ++} ++ ++void __lockfunc rt_spin_lock(spinlock_t *lock) ++{ ++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); ++ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++} ++EXPORT_SYMBOL(rt_spin_lock); ++ ++void __lockfunc __rt_spin_lock(struct rt_mutex *lock) ++{ ++ rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock); ++} ++EXPORT_SYMBOL(__rt_spin_lock); ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) ++{ ++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); ++ spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); ++} ++EXPORT_SYMBOL(rt_spin_lock_nested); ++#endif ++ ++void __lockfunc rt_spin_unlock(spinlock_t *lock) ++{ ++ /* NOTE: we always pass in '1' for nested, for simplicity */ ++ spin_release(&lock->dep_map, 1, _RET_IP_); ++ rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); ++} ++EXPORT_SYMBOL(rt_spin_unlock); ++ ++void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock) ++{ ++ /* NOTE: we always pass in '1' for nested, for simplicity */ ++ spin_release(&lock->dep_map, 1, _RET_IP_); ++ rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock_hirq); ++} ++ ++void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) ++{ ++ rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); ++} ++EXPORT_SYMBOL(__rt_spin_unlock); ++ ++/* ++ * Wait for the lock to get unlocked: instead of polling for an unlock ++ * (like raw spinlocks do), we lock and unlock, to force the kernel to ++ * schedule if there's contention: ++ */ ++void __lockfunc rt_spin_unlock_wait(spinlock_t *lock) ++{ ++ spin_lock(lock); ++ spin_unlock(lock); ++} ++EXPORT_SYMBOL(rt_spin_unlock_wait); ++ ++int __lockfunc rt_spin_trylock(spinlock_t *lock) ++{ ++ int ret = rt_mutex_trylock(&lock->lock); ++ ++ if (ret) ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock); ++ ++int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) ++{ ++ int ret; ++ ++ local_bh_disable(); ++ ret = rt_mutex_trylock(&lock->lock); ++ if (ret) { ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ } else ++ local_bh_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock_bh); ++ ++int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) ++{ ++ int ret; ++ ++ *flags = 0; ++ migrate_disable(); ++ ret = rt_mutex_trylock(&lock->lock); ++ if (ret) ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock_irqsave); ++ ++int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock) ++{ ++ /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ ++ if (atomic_add_unless(atomic, -1, 1)) ++ return 0; ++ migrate_disable(); ++ rt_spin_lock(lock); ++ if (atomic_dec_and_test(atomic)) ++ return 1; ++ rt_spin_unlock(lock); ++ migrate_enable(); ++ return 0; ++} ++EXPORT_SYMBOL(atomic_dec_and_spin_lock); ++ ++void ++__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)lock, sizeof(*lock)); ++ lockdep_init_map(&lock->dep_map, name, key, 0); ++#endif + } ++EXPORT_SYMBOL(__rt_spin_lock_init); ++ ++#endif /* PREEMPT_RT_FULL */ + + /** + * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop + * @lock: the rt_mutex to take + * @state: the state the task should block in (TASK_INTERRUPTIBLE +- * or TASK_UNINTERRUPTIBLE) ++ * or TASK_UNINTERRUPTIBLE) + * @timeout: the pre-initialized and started timer, or NULL for none + * @waiter: the pre-initialized rt_mutex_waiter + * +@@ -772,14 +1454,15 @@ static void rt_mutex_handle_deadlock(int + static int __sched + rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- int detect_deadlock) ++ enum rtmutex_chainwalk chwalk) + { + struct rt_mutex_waiter waiter; + int ret = 0; + +- debug_rt_mutex_init_waiter(&waiter); ++ rt_mutex_init_waiter(&waiter, false); + + raw_spin_lock(&lock->wait_lock); ++ init_lists(lock); + + /* Try to acquire the lock again: */ + if (try_to_take_rt_mutex(lock, current, NULL)) { +@@ -796,7 +1479,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, + timeout->task = NULL; + } + +- ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock); ++ ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk); + + if (likely(!ret)) + ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); +@@ -804,8 +1487,9 @@ rt_mutex_slowlock(struct rt_mutex *lock, + set_current_state(TASK_RUNNING); + + if (unlikely(ret)) { +- remove_waiter(lock, &waiter); +- rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter); ++ if (rt_mutex_has_waiters(lock)) ++ remove_waiter(lock, &waiter); ++ rt_mutex_handle_deadlock(ret, chwalk, &waiter); + } + + /* +@@ -828,22 +1512,33 @@ rt_mutex_slowlock(struct rt_mutex *lock, + /* + * Slow path try-lock function: + */ +-static inline int +-rt_mutex_slowtrylock(struct rt_mutex *lock) ++static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) + { +- int ret = 0; ++ int ret; + +- raw_spin_lock(&lock->wait_lock); ++ /* ++ * If the lock already has an owner we fail to get the lock. ++ * This can be done without taking the @lock->wait_lock as ++ * it is only being read, and this is a trylock anyway. ++ */ ++ if (rt_mutex_owner(lock)) ++ return 0; + +- if (likely(rt_mutex_owner(lock) != current)) { ++ /* ++ * The mutex has currently no owner. Lock the wait lock and ++ * try to acquire the lock. ++ */ ++ if (!raw_spin_trylock(&lock->wait_lock)) ++ return 0; ++ init_lists(lock); + +- ret = try_to_take_rt_mutex(lock, current, NULL); +- /* +- * try_to_take_rt_mutex() sets the lock waiters +- * bit unconditionally. Clean this up. +- */ +- fixup_rt_mutex_waiters(lock); +- } ++ ret = try_to_take_rt_mutex(lock, current, NULL); ++ ++ /* ++ * try_to_take_rt_mutex() sets the lock waiters bit ++ * unconditionally. Clean this up. ++ */ ++ fixup_rt_mutex_waiters(lock); + + raw_spin_unlock(&lock->wait_lock); + +@@ -921,30 +1616,31 @@ rt_mutex_slowunlock(struct rt_mutex *loc + */ + static inline int + rt_mutex_fastlock(struct rt_mutex *lock, int state, +- int detect_deadlock, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- int detect_deadlock)) ++ enum rtmutex_chainwalk chwalk)) + { +- if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) { ++ if (likely(rt_mutex_cmpxchg(lock, NULL, current))) { + rt_mutex_deadlock_account_lock(lock, current); + return 0; + } else +- return slowfn(lock, state, NULL, detect_deadlock); ++ return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); + } + + static inline int + rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, +- struct hrtimer_sleeper *timeout, int detect_deadlock, ++ struct hrtimer_sleeper *timeout, ++ enum rtmutex_chainwalk chwalk, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- int detect_deadlock)) ++ enum rtmutex_chainwalk chwalk)) + { +- if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) { ++ if (chwalk == RT_MUTEX_MIN_CHAINWALK && ++ likely(rt_mutex_cmpxchg(lock, NULL, current))) { + rt_mutex_deadlock_account_lock(lock, current); + return 0; + } else +- return slowfn(lock, state, timeout, detect_deadlock); ++ return slowfn(lock, state, timeout, chwalk); + } + + static inline int +@@ -977,54 +1673,77 @@ void __sched rt_mutex_lock(struct rt_mut + { + might_sleep(); + +- rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, 0, rt_mutex_slowlock); ++ rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock); + + /** + * rt_mutex_lock_interruptible - lock a rt_mutex interruptible + * +- * @lock: the rt_mutex to be locked +- * @detect_deadlock: deadlock detection on/off ++ * @lock: the rt_mutex to be locked + * + * Returns: +- * 0 on success +- * -EINTR when interrupted by a signal +- * -EDEADLK when the lock would deadlock (when deadlock detection is on) ++ * 0 on success ++ * -EINTR when interrupted by a signal + */ +-int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock, +- int detect_deadlock) ++int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) + { + might_sleep(); + +- return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, +- detect_deadlock, rt_mutex_slowlock); ++ return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); + ++/* ++ * Futex variant with full deadlock detection. ++ */ ++int rt_mutex_timed_futex_lock(struct rt_mutex *lock, ++ struct hrtimer_sleeper *timeout) ++{ ++ might_sleep(); ++ ++ return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, ++ RT_MUTEX_FULL_CHAINWALK, rt_mutex_slowlock); ++} ++ ++/** ++ * rt_mutex_lock_killable - lock a rt_mutex killable ++ * ++ * @lock: the rt_mutex to be locked ++ * ++ * Returns: ++ * 0 on success ++ * -EINTR when interrupted by a signal ++ * -EDEADLK when the lock would deadlock (when deadlock detection is on) ++ */ ++int __sched rt_mutex_lock_killable(struct rt_mutex *lock) ++{ ++ might_sleep(); ++ ++ return rt_mutex_fastlock(lock, TASK_KILLABLE, rt_mutex_slowlock); ++} ++EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); ++ + /** + * rt_mutex_timed_lock - lock a rt_mutex interruptible + * the timeout structure is provided + * by the caller + * +- * @lock: the rt_mutex to be locked ++ * @lock: the rt_mutex to be locked + * @timeout: timeout structure or NULL (no timeout) +- * @detect_deadlock: deadlock detection on/off + * + * Returns: +- * 0 on success +- * -EINTR when interrupted by a signal ++ * 0 on success ++ * -EINTR when interrupted by a signal + * -ETIMEDOUT when the timeout expired +- * -EDEADLK when the lock would deadlock (when deadlock detection is on) + */ + int +-rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout, +- int detect_deadlock) ++rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) + { + might_sleep(); + + return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, +- detect_deadlock, rt_mutex_slowlock); ++ RT_MUTEX_MIN_CHAINWALK, rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); + +@@ -1082,12 +1801,11 @@ EXPORT_SYMBOL_GPL(rt_mutex_destroy); + void __rt_mutex_init(struct rt_mutex *lock, const char *name) + { + lock->owner = NULL; +- raw_spin_lock_init(&lock->wait_lock); + plist_head_init(&lock->wait_list); + + debug_rt_mutex_init(lock, name); + } +-EXPORT_SYMBOL_GPL(__rt_mutex_init); ++EXPORT_SYMBOL(__rt_mutex_init); + + /** + * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a +@@ -1102,7 +1820,7 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init); + void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner) + { +- __rt_mutex_init(lock, NULL); ++ rt_mutex_init(lock); + debug_rt_mutex_proxy_lock(lock, proxy_owner); + rt_mutex_set_owner(lock, proxy_owner); + rt_mutex_deadlock_account_lock(lock, proxy_owner); +@@ -1129,7 +1847,6 @@ void rt_mutex_proxy_unlock(struct rt_mut + * @lock: the rt_mutex to take + * @waiter: the pre-initialized rt_mutex_waiter + * @task: the task to prepare +- * @detect_deadlock: perform deadlock detection (1) or not (0) + * + * Returns: + * 0 - task blocked on lock +@@ -1140,7 +1857,7 @@ void rt_mutex_proxy_unlock(struct rt_mut + */ + int rt_mutex_start_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, +- struct task_struct *task, int detect_deadlock) ++ struct task_struct *task) + { + int ret; + +@@ -1151,8 +1868,38 @@ int rt_mutex_start_proxy_lock(struct rt_ + return 1; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * In PREEMPT_RT there's an added race. ++ * If the task, that we are about to requeue, times out, ++ * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue ++ * to skip this task. But right after the task sets ++ * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then ++ * block on the spin_lock(&hb->lock), which in RT is an rtmutex. ++ * This will replace the PI_WAKEUP_INPROGRESS with the actual ++ * lock that it blocks on. We *must not* place this task ++ * on this proxy lock in that case. ++ * ++ * To prevent this race, we first take the task's pi_lock ++ * and check if it has updated its pi_blocked_on. If it has, ++ * we assume that it woke up and we return -EAGAIN. ++ * Otherwise, we set the task's pi_blocked_on to ++ * PI_REQUEUE_INPROGRESS, so that if the task is waking up ++ * it will know that we are in the process of requeuing it. ++ */ ++ raw_spin_lock_irq(&task->pi_lock); ++ if (task->pi_blocked_on) { ++ raw_spin_unlock_irq(&task->pi_lock); ++ raw_spin_unlock(&lock->wait_lock); ++ return -EAGAIN; ++ } ++ task->pi_blocked_on = PI_REQUEUE_INPROGRESS; ++ raw_spin_unlock_irq(&task->pi_lock); ++#endif ++ + /* We enforce deadlock detection for futexes */ +- ret = task_blocks_on_rt_mutex(lock, waiter, task, 1); ++ ret = task_blocks_on_rt_mutex(lock, waiter, task, ++ RT_MUTEX_FULL_CHAINWALK); + + if (ret && !rt_mutex_owner(lock)) { + /* +@@ -1164,7 +1911,7 @@ int rt_mutex_start_proxy_lock(struct rt_ + ret = 0; + } + +- if (unlikely(ret)) ++ if (ret && rt_mutex_has_waiters(lock)) + remove_waiter(lock, waiter); + + raw_spin_unlock(&lock->wait_lock); +@@ -1198,22 +1945,20 @@ struct task_struct *rt_mutex_next_owner( + * rt_mutex_finish_proxy_lock() - Complete lock acquisition + * @lock: the rt_mutex we were woken on + * @to: the timeout, null if none. hrtimer should already have +- * been started. ++ * been started. + * @waiter: the pre-initialized rt_mutex_waiter +- * @detect_deadlock: perform deadlock detection (1) or not (0) + * + * Complete the lock acquisition started our behalf by another thread. + * + * Returns: + * 0 - success +- * <0 - error, one of -EINTR, -ETIMEDOUT, or -EDEADLK ++ * <0 - error, one of -EINTR, -ETIMEDOUT + * + * Special API call for PI-futex requeue support + */ + int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *to, +- struct rt_mutex_waiter *waiter, +- int detect_deadlock) ++ struct rt_mutex_waiter *waiter) + { + int ret; + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rtmutex_common.h sun8i-rt/kernel/rtmutex_common.h +--- sun8i/kernel/rtmutex_common.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/rtmutex_common.h 2016-08-22 18:21:56.728295035 +0200 +@@ -49,6 +49,7 @@ struct rt_mutex_waiter { + struct plist_node pi_list_entry; + struct task_struct *task; + struct rt_mutex *lock; ++ bool savestate; + #ifdef CONFIG_DEBUG_RT_MUTEXES + unsigned long ip; + struct pid *deadlock_task_pid; +@@ -101,8 +102,26 @@ static inline struct task_struct *rt_mut + } + + /* ++ * Constants for rt mutex functions which have a selectable deadlock ++ * detection. ++ * ++ * RT_MUTEX_MIN_CHAINWALK: Stops the lock chain walk when there are ++ * no further PI adjustments to be made. ++ * ++ * RT_MUTEX_FULL_CHAINWALK: Invoke deadlock detection with a full ++ * walk of the lock chain. ++ */ ++enum rtmutex_chainwalk { ++ RT_MUTEX_MIN_CHAINWALK, ++ RT_MUTEX_FULL_CHAINWALK, ++}; ++ ++/* + * PI-futex support (proxy locking functions, etc.): + */ ++#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) ++#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) ++ + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); + extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner); +@@ -110,12 +129,11 @@ extern void rt_mutex_proxy_unlock(struct + struct task_struct *proxy_owner); + extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, +- struct task_struct *task, +- int detect_deadlock); ++ struct task_struct *task); + extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *to, +- struct rt_mutex_waiter *waiter, +- int detect_deadlock); ++ struct rt_mutex_waiter *waiter); ++extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); + + #ifdef CONFIG_DEBUG_RT_MUTEXES + # include "rtmutex-debug.h" +@@ -123,4 +141,12 @@ extern int rt_mutex_finish_proxy_lock(st + # include "rtmutex.h" + #endif + ++static inline void ++rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate) ++{ ++ debug_rt_mutex_init_waiter(waiter); ++ waiter->task = NULL; ++ waiter->savestate = savestate; ++} ++ + #endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rtmutex-debug.c sun8i-rt/kernel/rtmutex-debug.c +--- sun8i/kernel/rtmutex-debug.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/rtmutex-debug.c 2016-08-22 18:21:56.728295035 +0200 +@@ -65,12 +65,13 @@ void rt_mutex_debug_task_free(struct tas + * the deadlock. We print when we return. act_waiter can be NULL in + * case of a remove waiter operation. + */ +-void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *act_waiter, ++void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk, ++ struct rt_mutex_waiter *act_waiter, + struct rt_mutex *lock) + { + struct task_struct *task; + +- if (!debug_locks || detect || !act_waiter) ++ if (!debug_locks || chwalk == RT_MUTEX_FULL_CHAINWALK || !act_waiter) + return; + + task = rt_mutex_owner(act_waiter->lock); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rtmutex-debug.h sun8i-rt/kernel/rtmutex-debug.h +--- sun8i/kernel/rtmutex-debug.h 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/kernel/rtmutex-debug.h 2016-08-22 18:21:56.728295035 +0200 +@@ -20,14 +20,15 @@ extern void debug_rt_mutex_unlock(struct + extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock, + struct task_struct *powner); + extern void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock); +-extern void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *waiter, ++extern void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk, ++ struct rt_mutex_waiter *waiter, + struct rt_mutex *lock); + extern void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter); + # define debug_rt_mutex_reset_waiter(w) \ + do { (w)->deadlock_lock = NULL; } while (0) + +-static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter, +- int detect) ++static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter, ++ enum rtmutex_chainwalk walk) + { + return (waiter != NULL); + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rtmutex.h sun8i-rt/kernel/rtmutex.h +--- sun8i/kernel/rtmutex.h 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/kernel/rtmutex.h 2016-08-22 18:21:56.728295035 +0200 +@@ -22,10 +22,15 @@ + #define debug_rt_mutex_init(m, n) do { } while (0) + #define debug_rt_mutex_deadlock(d, a ,l) do { } while (0) + #define debug_rt_mutex_print_deadlock(w) do { } while (0) +-#define debug_rt_mutex_detect_deadlock(w,d) (d) + #define debug_rt_mutex_reset_waiter(w) do { } while (0) + + static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w) + { + WARN(1, "rtmutex deadlock detected\n"); + } ++ ++static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *w, ++ enum rtmutex_chainwalk walk) ++{ ++ return walk == RT_MUTEX_FULL_CHAINWALK; ++} +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/rtmutex-tester.c sun8i-rt/kernel/rtmutex-tester.c +--- sun8i/kernel/rtmutex-tester.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/rtmutex-tester.c 2016-08-22 18:21:41.012294854 +0200 +@@ -14,7 +14,7 @@ + #include + #include + +-#include "rtmutex.h" ++#include "rtmutex_common.h" + + #define MAX_RT_TEST_THREADS 8 + #define MAX_RT_TEST_MUTEXES 8 +@@ -105,7 +105,7 @@ static int handle_op(struct test_thread_ + + td->mutexes[id] = 1; + td->event = atomic_add_return(1, &rttest_event); +- ret = rt_mutex_lock_interruptible(&mutexes[id], 0); ++ ret = rt_mutex_lock_interruptible(&mutexes[id]); + td->event = atomic_add_return(1, &rttest_event); + td->mutexes[id] = ret ? 0 : 4; + return ret ? -EINTR : 0; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/sched/core.c sun8i-rt/kernel/sched/core.c +--- sun8i/kernel/sched/core.c 2016-08-22 14:14:41.000000000 +0200 ++++ sun8i-rt/kernel/sched/core.c 2016-08-22 18:28:44.872299727 +0200 +@@ -263,7 +263,11 @@ late_initcall(sched_init_debug); + * Number of tasks to iterate in a single balance run. + * Limited because this is done with IRQs disabled. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + const_debug unsigned int sysctl_sched_nr_migrate = 32; ++#else ++const_debug unsigned int sysctl_sched_nr_migrate = 8; ++#endif + + /* + * period over which we average the RT time consumption, measured +@@ -480,6 +484,7 @@ static void init_rq_hrtick(struct rq *rq + + hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rq->hrtick_timer.function = hrtick; ++ rq->hrtick_timer.irqsafe = 1; + } + #else /* CONFIG_SCHED_HRTICK */ + static inline void hrtick_clear(struct rq *rq) +@@ -1169,7 +1174,8 @@ unsigned long wait_task_inactive(struct + * is actually now running somewhere else! + */ + while (task_running(rq, p)) { +- if (match_state && unlikely(p->state != match_state)) ++ if (match_state && unlikely(p->state != match_state) ++ && unlikely(p->saved_state != match_state)) + return 0; + cpu_relax(); + } +@@ -1184,7 +1190,8 @@ unsigned long wait_task_inactive(struct + running = task_running(rq, p); + on_rq = p->on_rq; + ncsw = 0; +- if (!match_state || p->state == match_state) ++ if (!match_state || p->state == match_state ++ || p->saved_state == match_state) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_rq_unlock(rq, p, &flags); + +@@ -1399,10 +1406,6 @@ static void ttwu_activate(struct rq *rq, + { + activate_task(rq, p, en_flags); + p->on_rq = 1; +- +- /* if a worker is waking up, notify workqueue */ +- if (p->flags & PF_WQ_WORKER) +- wq_worker_waking_up(p, cpu_of(rq)); + } + + /* +@@ -1411,10 +1414,11 @@ static void ttwu_activate(struct rq *rq, + static void + ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) + { +- trace_sched_wakeup(p, true); + check_preempt_curr(rq, p, wake_flags); + + p->state = TASK_RUNNING; ++ trace_sched_wakeup(p); ++ + #ifdef CONFIG_SMP + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); +@@ -1595,8 +1599,29 @@ try_to_wake_up(struct task_struct *p, un + + smp_wmb(); + raw_spin_lock_irqsave(&p->pi_lock, flags); +- if (!(p->state & state)) ++ if (!(p->state & state)) { ++ /* ++ * The task might be running due to a spinlock sleeper ++ * wakeup. Check the saved state and set it to running ++ * if the wakeup condition is true. ++ */ ++ if (!(wake_flags & WF_LOCK_SLEEPER)) { ++ if (p->saved_state & state) { ++ p->saved_state = TASK_RUNNING; ++ success = 1; ++ } ++ } + goto out; ++ } ++ ++ /* ++ * If this is a regular wakeup, then we can unconditionally ++ * clear the saved state of a "lock sleeper". ++ */ ++ if (!(wake_flags & WF_LOCK_SLEEPER)) ++ p->saved_state = TASK_RUNNING; ++ ++ trace_sched_waking(p); + + success = 1; /* we're going to change ->state */ + cpu = task_cpu(p); +@@ -1652,42 +1677,6 @@ out: + } + + /** +- * try_to_wake_up_local - try to wake up a local task with rq lock held +- * @p: the thread to be awakened +- * +- * Put @p on the run-queue if it's not already there. The caller must +- * ensure that this_rq() is locked, @p is bound to this_rq() and not +- * the current task. +- */ +-static void try_to_wake_up_local(struct task_struct *p) +-{ +- struct rq *rq = task_rq(p); +- +- if (WARN_ON_ONCE(rq != this_rq()) || +- WARN_ON_ONCE(p == current)) +- return; +- +- lockdep_assert_held(&rq->lock); +- +- if (!raw_spin_trylock(&p->pi_lock)) { +- raw_spin_unlock(&rq->lock); +- raw_spin_lock(&p->pi_lock); +- raw_spin_lock(&rq->lock); +- } +- +- if (!(p->state & TASK_NORMAL)) +- goto out; +- +- if (!p->on_rq) +- ttwu_activate(rq, p, ENQUEUE_WAKEUP); +- +- ttwu_do_wakeup(rq, p, 0); +- ttwu_stat(p, smp_processor_id(), 0); +-out: +- raw_spin_unlock(&p->pi_lock); +-} +- +-/** + * wake_up_process - Wake up a specific process + * @p: The process to be woken up. + * +@@ -1705,6 +1694,18 @@ int wake_up_process(struct task_struct * + } + EXPORT_SYMBOL(wake_up_process); + ++/** ++ * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock" ++ * @p: The process to be woken up. ++ * ++ * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate ++ * the nature of the wakeup. ++ */ ++int wake_up_lock_sleeper(struct task_struct *p) ++{ ++ return try_to_wake_up(p, TASK_ALL, WF_LOCK_SLEEPER); ++} ++ + int wake_up_state(struct task_struct *p, unsigned int state) + { + return try_to_wake_up(p, state, 0); +@@ -1864,7 +1865,7 @@ void wake_up_new_task(struct task_struct + rq = __task_rq_lock(p); + activate_task(rq, p, 0); + p->on_rq = 1; +- trace_sched_wakeup_new(p, true); ++ trace_sched_wakeup_new(p); + check_preempt_curr(rq, p, WF_FORK); + #ifdef CONFIG_SMP + if (p->sched_class->task_woken) +@@ -2003,8 +2004,12 @@ static void finish_task_switch(struct rq + finish_arch_post_lock_switch(); + + fire_sched_in_preempt_notifiers(current); ++ /* ++ * We use mmdrop_delayed() here so we don't have to do the ++ * full __mmdrop() when we are the last user. ++ */ + if (mm) +- mmdrop(mm); ++ mmdrop_delayed(mm); + if (unlikely(prev_state == TASK_DEAD)) { + /* + * Remove function-return probe instances associated with this +@@ -3342,16 +3347,6 @@ void scheduler_tick(void) + #endif + } + +-notrace unsigned long get_parent_ip(unsigned long addr) +-{ +- if (in_lock_functions(addr)) { +- addr = CALLER_ADDR2; +- if (in_lock_functions(addr)) +- addr = CALLER_ADDR3; +- } +- return addr; +-} +- + #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ + defined(CONFIG_PREEMPT_TRACER)) + +@@ -3372,8 +3367,13 @@ void __kprobes add_preempt_count(int val + DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= + PREEMPT_MASK - 10); + #endif +- if (preempt_count() == val) +- trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); ++ if (preempt_count() == val) { ++ unsigned long ip = get_lock_parent_ip(); ++#ifdef CONFIG_DEBUG_PREEMPT ++ current->preempt_disable_ip = ip; ++#endif ++ trace_preempt_off(CALLER_ADDR0, ip); ++ } + } + EXPORT_SYMBOL(add_preempt_count); + +@@ -3394,7 +3394,7 @@ void __kprobes sub_preempt_count(int val + #endif + + if (preempt_count() == val) +- trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); ++ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); + preempt_count() -= val; + } + EXPORT_SYMBOL(sub_preempt_count); +@@ -3416,6 +3416,13 @@ static noinline void __schedule_bug(stru + print_modules(); + if (irqs_disabled()) + print_irqtrace_events(prev); ++#ifdef DEBUG_PREEMPT ++ if (in_atomic_preempt_off()) { ++ pr_err("Preemption disabled at:"); ++ print_ip_sym(current->preempt_disable_ip); ++ pr_cont("\n"); ++ } ++#endif + dump_stack(); + } + +@@ -3438,6 +3445,126 @@ static inline void schedule_debug(struct + schedstat_inc(this_rq(), sched_count); + } + ++#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_SMP) ++#define MIGRATE_DISABLE_SET_AFFIN (1<<30) /* Can't make a negative */ ++#define migrate_disabled_updated(p) ((p)->migrate_disable & MIGRATE_DISABLE_SET_AFFIN) ++#define migrate_disable_count(p) ((p)->migrate_disable & ~MIGRATE_DISABLE_SET_AFFIN) ++ ++static inline void update_migrate_disable(struct task_struct *p) ++{ ++ const struct cpumask *mask; ++ ++ if (likely(!p->migrate_disable)) ++ return; ++ ++ /* Did we already update affinity? */ ++ if (unlikely(migrate_disabled_updated(p))) ++ return; ++ ++ /* ++ * Since this is always current we can get away with only locking ++ * rq->lock, the ->cpus_allowed value can normally only be changed ++ * while holding both p->pi_lock and rq->lock, but seeing that this ++ * is current, we cannot actually be waking up, so all code that ++ * relies on serialization against p->pi_lock is out of scope. ++ * ++ * Having rq->lock serializes us against things like ++ * set_cpus_allowed_ptr() that can still happen concurrently. ++ */ ++ mask = tsk_cpus_allowed(p); ++ ++ if (p->sched_class->set_cpus_allowed) ++ p->sched_class->set_cpus_allowed(p, mask); ++ p->rt.nr_cpus_allowed = cpumask_weight(mask); ++ ++ /* Let migrate_enable know to fix things back up */ ++ p->migrate_disable |= MIGRATE_DISABLE_SET_AFFIN; ++} ++ ++void migrate_disable(void) ++{ ++ struct task_struct *p = current; ++ ++ if (in_atomic() || irqs_disabled()) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic++; ++#endif ++ return; ++ } ++ ++#ifdef CONFIG_SCHED_DEBUG ++ WARN_ON_ONCE(p->migrate_disable_atomic); ++#endif ++ ++ preempt_disable(); ++ if (p->migrate_disable) { ++ p->migrate_disable++; ++ preempt_enable(); ++ return; ++ } ++ ++ pin_current_cpu(); ++ p->migrate_disable = 1; ++ preempt_enable(); ++} ++EXPORT_SYMBOL(migrate_disable); ++ ++void migrate_enable(void) ++{ ++ struct task_struct *p = current; ++ const struct cpumask *mask; ++ unsigned long flags; ++ struct rq *rq; ++ ++ if (in_atomic() || irqs_disabled()) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic--; ++#endif ++ return; ++ } ++ ++#ifdef CONFIG_SCHED_DEBUG ++ WARN_ON_ONCE(p->migrate_disable_atomic); ++#endif ++ WARN_ON_ONCE(p->migrate_disable <= 0); ++ ++ preempt_disable(); ++ if (migrate_disable_count(p) > 1) { ++ p->migrate_disable--; ++ preempt_enable(); ++ return; ++ } ++ ++ if (unlikely(migrate_disabled_updated(p))) { ++ /* ++ * Undo whatever update_migrate_disable() did, also see there ++ * about locking. ++ */ ++ rq = this_rq(); ++ raw_spin_lock_irqsave(&rq->lock, flags); ++ ++ /* ++ * Clearing migrate_disable causes tsk_cpus_allowed to ++ * show the tasks original cpu affinity. ++ */ ++ p->migrate_disable = 0; ++ mask = tsk_cpus_allowed(p); ++ if (p->sched_class->set_cpus_allowed) ++ p->sched_class->set_cpus_allowed(p, mask); ++ p->rt.nr_cpus_allowed = cpumask_weight(mask); ++ raw_spin_unlock_irqrestore(&rq->lock, flags); ++ } else ++ p->migrate_disable = 0; ++ ++ unpin_current_cpu(); ++ preempt_enable(); ++} ++EXPORT_SYMBOL(migrate_enable); ++#else ++static inline void update_migrate_disable(struct task_struct *p) { } ++#define migrate_disabled_updated(p) 0 ++#endif ++ + static void put_prev_task(struct rq *rq, struct task_struct *prev) + { + if (prev->on_rq || rq->skip_clock_update < 0) +@@ -3497,6 +3624,8 @@ need_resched: + + raw_spin_lock_irq(&rq->lock); + ++ update_migrate_disable(prev); ++ + switch_count = &prev->nivcsw; + if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { + if (unlikely(signal_pending_state(prev->state, prev))) { +@@ -3504,19 +3633,6 @@ need_resched: + } else { + deactivate_task(rq, prev, DEQUEUE_SLEEP); + prev->on_rq = 0; +- +- /* +- * If a worker went to sleep, notify and ask workqueue +- * whether it wants to wake up a task to maintain +- * concurrency. +- */ +- if (prev->flags & PF_WQ_WORKER) { +- struct task_struct *to_wakeup; +- +- to_wakeup = wq_worker_sleeping(prev, cpu); +- if (to_wakeup) +- try_to_wake_up_local(to_wakeup); +- } + } + switch_count = &prev->nvcsw; + } +@@ -3557,9 +3673,22 @@ need_resched: + + static inline void sched_submit_work(struct task_struct *tsk) + { +- if (!tsk->state || tsk_is_pi_blocked(tsk)) ++ if (!tsk->state) + return; + /* ++ * If a worker went to sleep, notify and ask workqueue whether ++ * it wants to wake up a task to maintain concurrency. ++ * Only call wake up if prev isn't blocked on a sleeping ++ * spin lock. ++ */ ++ if (tsk->flags & PF_WQ_WORKER && !tsk->saved_state) ++ wq_worker_sleeping(tsk); ++ ++ ++ if (tsk_is_pi_blocked(tsk)) ++ return; ++ ++ /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. + */ +@@ -3567,12 +3696,19 @@ static inline void sched_submit_work(str + blk_schedule_flush_plug(tsk); + } + ++static inline void sched_update_worker(struct task_struct *tsk) ++{ ++ if (tsk->flags & PF_WQ_WORKER) ++ wq_worker_running(tsk); ++} ++ + asmlinkage void __sched schedule(void) + { + struct task_struct *tsk = current; + + sched_submit_work(tsk); + __schedule(); ++ sched_update_worker(tsk); + } + EXPORT_SYMBOL(schedule); + +@@ -3652,7 +3788,16 @@ asmlinkage void __sched notrace preempt_ + + do { + add_preempt_count_notrace(PREEMPT_ACTIVE); ++ /* ++ * The add/subtract must not be traced by the function ++ * tracer. But we still want to account for the ++ * preempt off latency tracer. Since the _notrace versions ++ * of add/subtract skip the accounting for latency tracer ++ * we must force it manually. ++ */ ++ start_critical_timings(); + __schedule(); ++ stop_critical_timings(); + sub_preempt_count_notrace(PREEMPT_ACTIVE); + + /* +@@ -4097,7 +4242,8 @@ EXPORT_SYMBOL(sleep_on_timeout); + * This function changes the 'effective' priority of a task. It does + * not touch ->normal_prio like __setscheduler(). + * +- * Used by the rt_mutex code to implement priority inheritance logic. ++ * Used by the rt_mutex code to implement priority inheritance ++ * logic. Call site only calls if the priority of the task changed. + */ + void rt_mutex_setprio(struct task_struct *p, int prio) + { +@@ -4326,12 +4472,19 @@ static struct task_struct *find_process_ + extern struct cpumask hmp_slow_cpu_mask; + + /* Actually do priority change: must hold rq lock. */ +-static void +-__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) ++static void __setscheduler_params(struct task_struct *p, int policy, int prio) + { + p->policy = policy; + p->rt_priority = prio; + p->normal_prio = normal_prio(p); ++ set_load_weight(p); ++} ++ ++/* Actually do priority change: must hold rq lock. */ ++static void ++__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) ++{ ++ __setscheduler_params(p, policy, prio); + /* we are holding p->pi_lock already */ + p->prio = rt_mutex_getprio(p); + if (rt_prio(p->prio)) { +@@ -4346,7 +4499,6 @@ __setscheduler(struct rq *rq, struct tas + } + else + p->sched_class = &fair_sched_class; +- set_load_weight(p); + } + + /* +@@ -4371,6 +4523,7 @@ static bool check_same_owner(struct task + static int __sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param, bool user) + { ++ int newprio = MAX_RT_PRIO - 1 - param->sched_priority; + int retval, oldprio, oldpolicy = -1, on_rq, running; + unsigned long flags; + const struct sched_class *prev_class; +@@ -4466,11 +4619,13 @@ recheck: + } + + /* +- * If not changing anything there's no need to proceed further: ++ * If not changing anything there's no need to proceed ++ * further, but store a possible modification of ++ * reset_on_fork. + */ + if (unlikely(policy == p->policy && (!rt_policy(policy) || + param->sched_priority == p->rt_priority))) { +- ++ p->sched_reset_on_fork = reset_on_fork; + __task_rq_unlock(rq); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + return 0; +@@ -4497,6 +4652,25 @@ recheck: + task_rq_unlock(rq, p, &flags); + goto recheck; + } ++ ++ p->sched_reset_on_fork = reset_on_fork; ++ oldprio = p->prio; ++ ++ /* ++ * Special case for priority boosted tasks. ++ * ++ * If the new priority is lower or equal (user space view) ++ * than the current (boosted) priority, we just store the new ++ * normal parameters and do not touch the scheduler class and ++ * the runqueue. This will be done when the task deboost ++ * itself. ++ */ ++ if (rt_mutex_check_prio(p, newprio)) { ++ __setscheduler_params(p, policy, param->sched_priority); ++ task_rq_unlock(rq, p, &flags); ++ return 0; ++ } ++ + on_rq = p->on_rq; + running = task_current(rq, p); + if (on_rq) +@@ -4504,9 +4678,6 @@ recheck: + if (running) + p->sched_class->put_prev_task(rq, p); + +- p->sched_reset_on_fork = reset_on_fork; +- +- oldprio = p->prio; + prev_class = p->sched_class; + __setscheduler(rq, p, policy, param->sched_priority); + +@@ -4865,9 +5036,17 @@ static inline int should_resched(void) + + static void __cond_resched(void) + { +- add_preempt_count(PREEMPT_ACTIVE); +- __schedule(); +- sub_preempt_count(PREEMPT_ACTIVE); ++ do { ++ add_preempt_count(PREEMPT_ACTIVE); ++ __schedule(); ++ sub_preempt_count(PREEMPT_ACTIVE); ++ /* ++ * Check again in case we missed a preemption ++ * opportunity between schedule and now. ++ */ ++ barrier(); ++ ++ } while (need_resched()); + } + + int __sched _cond_resched(void) +@@ -4908,6 +5087,7 @@ int __cond_resched_lock(spinlock_t *lock + } + EXPORT_SYMBOL(__cond_resched_lock); + ++#ifndef CONFIG_PREEMPT_RT_FULL + int __sched __cond_resched_softirq(void) + { + BUG_ON(!in_softirq()); +@@ -4921,6 +5101,7 @@ int __sched __cond_resched_softirq(void) + return 0; + } + EXPORT_SYMBOL(__cond_resched_softirq); ++#endif + + /** + * yield - yield the current processor to other threads. +@@ -5254,6 +5435,7 @@ void __cpuinit init_idle(struct task_str + rcu_read_unlock(); + + rq->curr = rq->idle = idle; ++ idle->on_rq = 1; + #if defined(CONFIG_SMP) + idle->on_cpu = 1; + #endif +@@ -5275,11 +5457,90 @@ void __cpuinit init_idle(struct task_str + #ifdef CONFIG_SMP + void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) + { +- if (p->sched_class && p->sched_class->set_cpus_allowed) +- p->sched_class->set_cpus_allowed(p, new_mask); +- ++ if (!migrate_disabled_updated(p)) { ++ if (p->sched_class && p->sched_class->set_cpus_allowed) ++ p->sched_class->set_cpus_allowed(p, new_mask); ++ p->rt.nr_cpus_allowed = cpumask_weight(new_mask); ++ } + cpumask_copy(&p->cpus_allowed, new_mask); +- p->rt.nr_cpus_allowed = cpumask_weight(new_mask); ++} ++ ++static DEFINE_PER_CPU(struct cpumask, sched_cpumasks); ++static DEFINE_MUTEX(sched_down_mutex); ++static cpumask_t sched_down_cpumask; ++ ++void tell_sched_cpu_down_begin(int cpu) ++{ ++ mutex_lock(&sched_down_mutex); ++ cpumask_set_cpu(cpu, &sched_down_cpumask); ++ mutex_unlock(&sched_down_mutex); ++} ++ ++void tell_sched_cpu_down_done(int cpu) ++{ ++ mutex_lock(&sched_down_mutex); ++ cpumask_clear_cpu(cpu, &sched_down_cpumask); ++ mutex_unlock(&sched_down_mutex); ++} ++ ++/** ++ * migrate_me - try to move the current task off this cpu ++ * ++ * Used by the pin_current_cpu() code to try to get tasks ++ * to move off the current CPU as it is going down. ++ * It will only move the task if the task isn't pinned to ++ * the CPU (with migrate_disable, affinity or THREAD_BOUND) ++ * and the task has to be in a RUNNING state. Otherwise the ++ * movement of the task will wake it up (change its state ++ * to running) when the task did not expect it. ++ * ++ * Returns 1 if it succeeded in moving the current task ++ * 0 otherwise. ++ */ ++int migrate_me(void) ++{ ++ struct task_struct *p = current; ++ struct migration_arg arg; ++ struct cpumask *cpumask; ++ struct cpumask *mask; ++ unsigned long flags; ++ unsigned int dest_cpu; ++ struct rq *rq; ++ ++ /* ++ * We can not migrate tasks bounded to a CPU or tasks not ++ * running. The movement of the task will wake it up. ++ */ ++ if (p->flags & PF_THREAD_BOUND || p->state) ++ return 0; ++ ++ mutex_lock(&sched_down_mutex); ++ rq = task_rq_lock(p, &flags); ++ ++ cpumask = &__get_cpu_var(sched_cpumasks); ++ mask = &p->cpus_allowed; ++ ++ cpumask_andnot(cpumask, mask, &sched_down_cpumask); ++ ++ if (!cpumask_weight(cpumask)) { ++ /* It's only on this CPU? */ ++ task_rq_unlock(rq, p, &flags); ++ mutex_unlock(&sched_down_mutex); ++ return 0; ++ } ++ ++ dest_cpu = cpumask_any_and(cpu_active_mask, cpumask); ++ ++ arg.task = p; ++ arg.dest_cpu = dest_cpu; ++ ++ task_rq_unlock(rq, p, &flags); ++ ++ stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); ++ tlb_migrate_finish(p->mm); ++ mutex_unlock(&sched_down_mutex); ++ ++ return 1; + } + + /* +@@ -5330,7 +5591,7 @@ int set_cpus_allowed_ptr(struct task_str + do_set_cpus_allowed(p, new_mask); + + /* Can the task run on the task's current CPU? If so, we're done */ +- if (cpumask_test_cpu(task_cpu(p), new_mask)) ++ if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) + goto out; + + dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); +@@ -5419,6 +5680,8 @@ static int migration_cpu_stop(void *data + + #ifdef CONFIG_HOTPLUG_CPU + ++static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm); ++ + /* + * Ensures that the idle task is using init_mm right before its cpu goes + * offline. +@@ -5431,7 +5694,12 @@ void idle_task_exit(void) + + if (mm != &init_mm) + switch_mm(mm, &init_mm, current); +- mmdrop(mm); ++ ++ /* ++ * Defer the cleanup to an alive cpu. On RT we can neither ++ * call mmdrop() nor mmdrop_delayed() from here. ++ */ ++ per_cpu(idle_last_mm, smp_processor_id()) = mm; + } + + /* +@@ -5758,6 +6026,12 @@ migration_call(struct notifier_block *nf + migrate_nr_uninterruptible(rq); + calc_global_load_remove(rq); + break; ++ case CPU_DEAD: ++ if (per_cpu(idle_last_mm, cpu)) { ++ mmdrop(per_cpu(idle_last_mm, cpu)); ++ per_cpu(idle_last_mm, cpu) = NULL; ++ } ++ break; + #endif + } + +@@ -7427,7 +7701,8 @@ void __init sched_init(void) + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + static inline int preempt_count_equals(int preempt_offset) + { +- int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); ++ int nested = (preempt_count() & ~PREEMPT_ACTIVE) + ++ sched_rcu_preempt_depth(); + + return (nested == preempt_offset); + } +@@ -7445,7 +7720,8 @@ void __might_sleep(const char *file, int + static unsigned long prev_jiffy; /* ratelimiting */ + + rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ +- if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || ++ if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && ++ !is_idle_task(current)) || + oops_in_progress) + return; + if (system_state != SYSTEM_RUNNING && +@@ -7466,6 +7742,13 @@ void __might_sleep(const char *file, int + debug_show_held_locks(current); + if (irqs_disabled()) + print_irqtrace_events(current); ++#ifdef DEBUG_PREEMPT ++ if (!preempt_count_equals(preempt_offset)) { ++ pr_err("Preemption disabled at:"); ++ print_ip_sym(current->preempt_disable_ip); ++ pr_cont("\n"); ++ } ++#endif + dump_stack(); + } + EXPORT_SYMBOL(__might_sleep); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/sched/debug.c sun8i-rt/kernel/sched/debug.c +--- sun8i/kernel/sched/debug.c 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/kernel/sched/debug.c 2016-08-22 17:18:41.256251399 +0200 +@@ -262,6 +262,9 @@ void print_rt_rq(struct seq_file *m, int + P(rt_throttled); + PN(rt_time); + PN(rt_runtime); ++#ifdef CONFIG_SMP ++ P(rt_nr_migratory); ++#endif + + #undef PN + #undef P +@@ -510,6 +513,10 @@ void proc_sched_show_task(struct task_st + P(se.load.weight); + P(policy); + P(prio); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ P(migrate_disable); ++#endif ++ P(rt.nr_cpus_allowed); + #undef PN + #undef __PN + #undef P +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/sched/features.h sun8i-rt/kernel/sched/features.h +--- sun8i/kernel/sched/features.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/sched/features.h 2016-08-22 17:14:09.940248280 +0200 +@@ -60,11 +60,15 @@ SCHED_FEAT(OWNER_SPIN, true) + */ + SCHED_FEAT(NONTASK_POWER, true) + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ + SCHED_FEAT(TTWU_QUEUE, true) ++#else ++SCHED_FEAT(TTWU_QUEUE, false) ++#endif + + SCHED_FEAT(FORCE_SD_OVERLAP, false) + SCHED_FEAT(RT_RUNTIME_SHARE, true) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/sched/Makefile sun8i-rt/kernel/sched/Makefile +--- sun8i/kernel/sched/Makefile 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/sched/Makefile 2016-08-22 18:24:57.020297108 +0200 +@@ -12,6 +12,7 @@ CFLAGS_core.o := $(PROFILING) -fno-omit- + endif + + obj-y += core.o clock.o idle_task.o fair.o rt.o stop_task.o ++obj-y += work-simple.o + obj-$(CONFIG_SMP) += cpupri.o + obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o + obj-$(CONFIG_SCHEDSTATS) += stats.o +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/sched/rt.c sun8i-rt/kernel/sched/rt.c +--- sun8i/kernel/sched/rt.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/kernel/sched/rt.c 2016-08-22 17:10:26.268245708 +0200 +@@ -41,6 +41,7 @@ void init_rt_bandwidth(struct rt_bandwid + + hrtimer_init(&rt_b->rt_period_timer, + CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ rt_b->rt_period_timer.irqsafe = 1; + rt_b->rt_period_timer.function = sched_rt_period_timer; + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/sched/work-simple.c sun8i-rt/kernel/sched/work-simple.c +--- sun8i/kernel/sched/work-simple.c 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/kernel/sched/work-simple.c 2016-08-22 18:24:57.020297108 +0200 +@@ -0,0 +1,172 @@ ++/* ++ * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@bmw-carit.de ++ * ++ * Provides a framework for enqueuing callbacks from irq context ++ * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++ ++#define SWORK_EVENT_PENDING (1 << 0) ++ ++static DEFINE_MUTEX(worker_mutex); ++static struct sworker *glob_worker; ++ ++struct sworker { ++ struct list_head events; ++ struct swait_head wq; ++ ++ raw_spinlock_t lock; ++ ++ struct task_struct *task; ++ int refs; ++}; ++ ++static bool swork_readable(struct sworker *worker) ++{ ++ bool r; ++ ++ if (kthread_should_stop()) ++ return true; ++ ++ raw_spin_lock_irq(&worker->lock); ++ r = !list_empty(&worker->events); ++ raw_spin_unlock_irq(&worker->lock); ++ ++ return r; ++} ++ ++static int swork_kthread(void *arg) ++{ ++ struct sworker *worker = arg; ++ ++ for (;;) { ++ swait_event_interruptible(worker->wq, ++ swork_readable(worker)); ++ if (kthread_should_stop()) ++ break; ++ ++ raw_spin_lock_irq(&worker->lock); ++ while (!list_empty(&worker->events)) { ++ struct swork_event *sev; ++ ++ sev = list_first_entry(&worker->events, ++ struct swork_event, item); ++ list_del(&sev->item); ++ raw_spin_unlock_irq(&worker->lock); ++ ++ WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING, ++ &sev->flags)); ++ sev->func(sev); ++ raw_spin_lock_irq(&worker->lock); ++ } ++ raw_spin_unlock_irq(&worker->lock); ++ } ++ return 0; ++} ++ ++static struct sworker *swork_create(void) ++{ ++ struct sworker *worker; ++ ++ worker = kzalloc(sizeof(*worker), GFP_KERNEL); ++ if (!worker) ++ return ERR_PTR(-ENOMEM); ++ ++ INIT_LIST_HEAD(&worker->events); ++ raw_spin_lock_init(&worker->lock); ++ init_swait_head(&worker->wq); ++ ++ worker->task = kthread_run(swork_kthread, worker, "kswork"); ++ if (IS_ERR(worker->task)) { ++ kfree(worker); ++ return ERR_PTR(-ENOMEM); ++ } ++ ++ return worker; ++} ++ ++static void swork_destroy(struct sworker *worker) ++{ ++ kthread_stop(worker->task); ++ ++ WARN_ON(!list_empty(&worker->events)); ++ kfree(worker); ++} ++ ++/** ++ * swork_queue - queue swork ++ * ++ * Returns %false if @work was already on a queue, %true otherwise. ++ * ++ * The work is queued and processed on a random CPU ++ */ ++bool swork_queue(struct swork_event *sev) ++{ ++ unsigned long flags; ++ ++ if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags)) ++ return false; ++ ++ raw_spin_lock_irqsave(&glob_worker->lock, flags); ++ list_add_tail(&sev->item, &glob_worker->events); ++ raw_spin_unlock_irqrestore(&glob_worker->lock, flags); ++ ++ swait_wake(&glob_worker->wq); ++ return true; ++} ++EXPORT_SYMBOL_GPL(swork_queue); ++ ++/** ++ * swork_get - get an instance of the sworker ++ * ++ * Returns an negative error code if the initialization if the worker did not ++ * work, %0 otherwise. ++ * ++ */ ++int swork_get(void) ++{ ++ struct sworker *worker; ++ ++ mutex_lock(&worker_mutex); ++ if (!glob_worker) { ++ worker = swork_create(); ++ if (IS_ERR(worker)) { ++ mutex_unlock(&worker_mutex); ++ return -ENOMEM; ++ } ++ ++ glob_worker = worker; ++ } ++ ++ glob_worker->refs++; ++ mutex_unlock(&worker_mutex); ++ ++ return 0; ++} ++EXPORT_SYMBOL_GPL(swork_get); ++ ++/** ++ * swork_put - puts an instance of the sworker ++ * ++ * Will destroy the sworker thread. This function must not be called until all ++ * queued events have been completed. ++ */ ++void swork_put(void) ++{ ++ mutex_lock(&worker_mutex); ++ ++ glob_worker->refs--; ++ if (glob_worker->refs > 0) ++ goto out; ++ ++ swork_destroy(glob_worker); ++ glob_worker = NULL; ++out: ++ mutex_unlock(&worker_mutex); ++} ++EXPORT_SYMBOL_GPL(swork_put); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/signal.c sun8i-rt/kernel/signal.c +--- sun8i/kernel/signal.c 2016-08-22 14:14:34.000000000 +0200 ++++ sun8i-rt/kernel/signal.c 2016-08-22 16:33:15.980220067 +0200 +@@ -345,13 +345,45 @@ static bool task_participate_group_stop( + return false; + } + ++#ifdef __HAVE_ARCH_CMPXCHG ++static inline struct sigqueue *get_task_cache(struct task_struct *t) ++{ ++ struct sigqueue *q = t->sigqueue_cache; ++ ++ if (cmpxchg(&t->sigqueue_cache, q, NULL) != q) ++ return NULL; ++ return q; ++} ++ ++static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) ++{ ++ if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL) ++ return 0; ++ return 1; ++} ++ ++#else ++ ++static inline struct sigqueue *get_task_cache(struct task_struct *t) ++{ ++ return NULL; ++} ++ ++static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) ++{ ++ return 1; ++} ++ ++#endif ++ + /* + * allocate a new signal queue record + * - this may be called without locks if and only if t == current, otherwise an + * appropriate lock must be held to stop the target task from exiting + */ + static struct sigqueue * +-__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit) ++__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags, ++ int override_rlimit, int fromslab) + { + struct sigqueue *q = NULL; + struct user_struct *user; +@@ -368,7 +400,10 @@ __sigqueue_alloc(int sig, struct task_st + if (override_rlimit || + atomic_read(&user->sigpending) <= + task_rlimit(t, RLIMIT_SIGPENDING)) { +- q = kmem_cache_alloc(sigqueue_cachep, flags); ++ if (!fromslab) ++ q = get_task_cache(t); ++ if (!q) ++ q = kmem_cache_alloc(sigqueue_cachep, flags); + } else { + print_dropped_signal(sig); + } +@@ -385,6 +420,13 @@ __sigqueue_alloc(int sig, struct task_st + return q; + } + ++static struct sigqueue * ++__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, ++ int override_rlimit) ++{ ++ return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0); ++} ++ + static void __sigqueue_free(struct sigqueue *q) + { + if (q->flags & SIGQUEUE_PREALLOC) +@@ -394,6 +436,21 @@ static void __sigqueue_free(struct sigqu + kmem_cache_free(sigqueue_cachep, q); + } + ++static void sigqueue_free_current(struct sigqueue *q) ++{ ++ struct user_struct *up; ++ ++ if (q->flags & SIGQUEUE_PREALLOC) ++ return; ++ ++ up = q->user; ++ if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) { ++ atomic_dec(&up->sigpending); ++ free_uid(up); ++ } else ++ __sigqueue_free(q); ++} ++ + void flush_sigqueue(struct sigpending *queue) + { + struct sigqueue *q; +@@ -407,6 +464,21 @@ void flush_sigqueue(struct sigpending *q + } + + /* ++ * Called from __exit_signal. Flush tsk->pending and ++ * tsk->sigqueue_cache ++ */ ++void flush_task_sigqueue(struct task_struct *tsk) ++{ ++ struct sigqueue *q; ++ ++ flush_sigqueue(&tsk->pending); ++ ++ q = get_task_cache(tsk); ++ if (q) ++ kmem_cache_free(sigqueue_cachep, q); ++} ++ ++/* + * Flush all pending signals for a task. + */ + void __flush_signals(struct task_struct *t) +@@ -558,7 +630,7 @@ static void collect_signal(int sig, stru + still_pending: + list_del_init(&first->list); + copy_siginfo(info, &first->info); +- __sigqueue_free(first); ++ sigqueue_free_current(first); + } else { + /* + * Ok, it wasn't in the queue. This must be +@@ -604,6 +676,8 @@ int dequeue_signal(struct task_struct *t + { + int signr; + ++ WARN_ON_ONCE(tsk != current); ++ + /* We only dequeue private signals from ourselves, we don't let + * signalfd steal them + */ +@@ -683,6 +757,10 @@ int dequeue_signal(struct task_struct *t + void signal_wake_up_state(struct task_struct *t, unsigned int state) + { + set_tsk_thread_flag(t, TIF_SIGPENDING); ++ ++ if (unlikely(t == current)) ++ return; ++ + /* + * TASK_WAKEKILL also means wake it up in the stopped/traced/killable + * case. We don't check t->state here because there is a race with it +@@ -1232,8 +1310,8 @@ int do_send_sig_info(int sig, struct sig + * We don't want to have recursive SIGSEGV's etc, for example, + * that is why we also clear SIGNAL_UNKILLABLE. + */ +-int +-force_sig_info(int sig, struct siginfo *info, struct task_struct *t) ++static int ++do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t) + { + unsigned long int flags; + int ret, blocked, ignored; +@@ -1258,6 +1336,39 @@ force_sig_info(int sig, struct siginfo * + return ret; + } + ++int force_sig_info(int sig, struct siginfo *info, struct task_struct *t) ++{ ++/* ++ * On some archs, PREEMPT_RT has to delay sending a signal from a trap ++ * since it can not enable preemption, and the signal code's spin_locks ++ * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will ++ * send the signal on exit of the trap. ++ */ ++#ifdef ARCH_RT_DELAYS_SIGNAL_SEND ++ if (in_atomic()) { ++ if (WARN_ON_ONCE(t != current)) ++ return 0; ++ if (WARN_ON_ONCE(t->forced_info.si_signo)) ++ return 0; ++ ++ if (is_si_special(info)) { ++ WARN_ON_ONCE(info != SEND_SIG_PRIV); ++ t->forced_info.si_signo = sig; ++ t->forced_info.si_errno = 0; ++ t->forced_info.si_code = SI_KERNEL; ++ t->forced_info.si_pid = 0; ++ t->forced_info.si_uid = 0; ++ } else { ++ t->forced_info = *info; ++ } ++ ++ set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); ++ return 0; ++ } ++#endif ++ return do_force_sig_info(sig, info, t); ++} ++ + /* + * Nuke all other threads in the group. + */ +@@ -1288,12 +1399,12 @@ struct sighand_struct *__lock_task_sigha + struct sighand_struct *sighand; + + for (;;) { +- local_irq_save(*flags); ++ local_irq_save_nort(*flags); + rcu_read_lock(); + sighand = rcu_dereference(tsk->sighand); + if (unlikely(sighand == NULL)) { + rcu_read_unlock(); +- local_irq_restore(*flags); ++ local_irq_restore_nort(*flags); + break; + } + +@@ -1304,7 +1415,7 @@ struct sighand_struct *__lock_task_sigha + } + spin_unlock(&sighand->siglock); + rcu_read_unlock(); +- local_irq_restore(*flags); ++ local_irq_restore_nort(*flags); + } + + return sighand; +@@ -1551,7 +1662,8 @@ EXPORT_SYMBOL(kill_pid); + */ + struct sigqueue *sigqueue_alloc(void) + { +- struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0); ++ /* Preallocated sigqueue objects always from the slabcache ! */ ++ struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1); + + if (q) + q->flags |= SIGQUEUE_PREALLOC; +@@ -1910,15 +2022,7 @@ static void ptrace_stop(int exit_code, i + if (gstop_done && ptrace_reparented(current)) + do_notify_parent_cldstop(current, false, why); + +- /* +- * Don't want to allow preemption here, because +- * sys_ptrace() needs this task to be inactive. +- * +- * XXX: implement read_unlock_no_resched(). +- */ +- preempt_disable(); + read_unlock(&tasklist_lock); +- preempt_enable_no_resched(); + schedule(); + } else { + /* +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/softirq.c sun8i-rt/kernel/softirq.c +--- sun8i/kernel/softirq.c 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/kernel/softirq.c 2016-08-22 18:28:44.872299727 +0200 +@@ -21,9 +21,11 @@ + #include + #include + #include ++#include + #include + #include + #include ++#include + + #define CREATE_TRACE_POINTS + #include +@@ -61,6 +63,67 @@ char *softirq_to_name[NR_SOFTIRQS] = { + "TASKLET", "SCHED", "HRTIMER", "RCU" + }; + ++#ifdef CONFIG_NO_HZ ++# ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * On preempt-rt a softirq might be blocked on a lock. There might be ++ * no other runnable task on this CPU because the lock owner runs on ++ * some other CPU. So we have to go into idle with the pending bit ++ * set. Therefor we need to check this otherwise we warn about false ++ * positives which confuses users and defeats the whole purpose of ++ * this test. ++ * ++ * This code is called with interrupts disabled. ++ */ ++void softirq_check_pending_idle(void) ++{ ++ static int rate_limit; ++ u32 warnpending = 0, pending = local_softirq_pending(); ++ ++ if (rate_limit >= 10) ++ return; ++ ++ if (pending) { ++ struct task_struct *tsk; ++ ++ tsk = __get_cpu_var(ksoftirqd); ++ /* ++ * The wakeup code in rtmutex.c wakes up the task ++ * _before_ it sets pi_blocked_on to NULL under ++ * tsk->pi_lock. So we need to check for both: state ++ * and pi_blocked_on. ++ */ ++ raw_spin_lock(&tsk->pi_lock); ++ ++ if (!tsk->pi_blocked_on && !(tsk->state == TASK_RUNNING)) ++ warnpending = 1; ++ ++ raw_spin_unlock(&tsk->pi_lock); ++ } ++ ++ if (warnpending) { ++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", ++ pending); ++ rate_limit++; ++ } ++} ++# else ++/* ++ * On !PREEMPT_RT we just printk rate limited: ++ */ ++void softirq_check_pending_idle(void) ++{ ++ static int rate_limit; ++ ++ if (rate_limit < 10) { ++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", ++ local_softirq_pending()); ++ rate_limit++; ++ } ++} ++# endif ++#endif ++ + /* + * we cannot loop indefinitely here to avoid userspace starvation, + * but we also don't want to introduce a worst case 1/HZ latency +@@ -76,6 +139,36 @@ static void wakeup_softirqd(void) + wake_up_process(tsk); + } + ++static void handle_pending_softirqs(u32 pending, int cpu, int need_rcu_bh_qs) ++{ ++ struct softirq_action *h = softirq_vec; ++ unsigned int prev_count = preempt_count(); ++ ++ local_irq_enable(); ++ for ( ; pending; h++, pending >>= 1) { ++ unsigned int vec_nr = h - softirq_vec; ++ ++ if (!(pending & 1)) ++ continue; ++ ++ kstat_incr_softirqs_this_cpu(vec_nr); ++ trace_softirq_entry(vec_nr); ++ h->action(h); ++ trace_softirq_exit(vec_nr); ++ if (unlikely(prev_count != preempt_count())) { ++ printk(KERN_ERR ++ "huh, entered softirq %u %s %p with preempt_count %08x exited with %08x?\n", ++ vec_nr, softirq_to_name[vec_nr], h->action, ++ prev_count, (unsigned int) preempt_count()); ++ preempt_count() = prev_count; ++ } ++ if (need_rcu_bh_qs) ++ rcu_bh_qs(cpu); ++ } ++ local_irq_disable(); ++} ++ ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * preempt_count and SOFTIRQ_OFFSET usage: + * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving +@@ -114,7 +207,7 @@ static void __local_bh_disable(unsigned + raw_local_irq_restore(flags); + + if (preempt_count() == cnt) +- trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); ++ trace_preempt_off(CALLER_ADDR0, get_lock_parent_ip()); + } + #else /* !CONFIG_TRACE_IRQFLAGS */ + static inline void __local_bh_disable(unsigned long ip, unsigned int cnt) +@@ -209,9 +302,46 @@ EXPORT_SYMBOL(local_bh_enable_ip); + #define MAX_SOFTIRQ_TIME msecs_to_jiffies(2) + #define MAX_SOFTIRQ_RESTART 10 + ++#ifdef CONFIG_TRACE_IRQFLAGS ++/* ++ * Convoluted means of passing __do_softirq() a message through the various ++ * architecture execute_on_stack() bits. ++ * ++ * When we run softirqs from irq_exit() and thus on the hardirq stack we need ++ * to keep the lockdep irq context tracking as tight as possible in order to ++ * not miss-qualify lock contexts and miss possible deadlocks. ++ */ ++static DEFINE_PER_CPU(int, softirq_from_hardirq); ++ ++static inline void lockdep_softirq_from_hardirq(void) ++{ ++ this_cpu_write(softirq_from_hardirq, 1); ++} ++ ++static inline void lockdep_softirq_start(void) ++{ ++ if (this_cpu_read(softirq_from_hardirq)) ++ trace_hardirq_exit(); ++ lockdep_softirq_enter(); ++} ++ ++static inline void lockdep_softirq_end(void) ++{ ++ lockdep_softirq_exit(); ++ if (this_cpu_read(softirq_from_hardirq)) { ++ this_cpu_write(softirq_from_hardirq, 0); ++ trace_hardirq_enter(); ++ } ++} ++ ++#else ++static inline void lockdep_softirq_from_hardirq(void) { } ++static inline void lockdep_softirq_start(void) { } ++static inline void lockdep_softirq_end(void) { } ++#endif ++ + asmlinkage void __do_softirq(void) + { +- struct softirq_action *h; + __u32 pending; + unsigned long end = jiffies + MAX_SOFTIRQ_TIME; + int cpu; +@@ -221,44 +351,15 @@ asmlinkage void __do_softirq(void) + account_system_vtime(current); + + __local_bh_disable((unsigned long)__builtin_return_address(0), +- SOFTIRQ_OFFSET); +- lockdep_softirq_enter(); ++ SOFTIRQ_OFFSET); ++ lockdep_softirq_start(); + + cpu = smp_processor_id(); + restart: + /* Reset the pending bitmask before enabling irqs */ + set_softirq_pending(0); + +- local_irq_enable(); +- +- h = softirq_vec; +- +- do { +- if (pending & 1) { +- unsigned int vec_nr = h - softirq_vec; +- int prev_count = preempt_count(); +- +- kstat_incr_softirqs_this_cpu(vec_nr); +- +- trace_softirq_entry(vec_nr); +- h->action(h); +- trace_softirq_exit(vec_nr); +- if (unlikely(prev_count != preempt_count())) { +- printk(KERN_ERR "huh, entered softirq %u %s %p" +- "with preempt_count %08x," +- " exited with %08x?\n", vec_nr, +- softirq_to_name[vec_nr], h->action, +- prev_count, preempt_count()); +- preempt_count() = prev_count; +- } +- +- rcu_bh_qs(cpu); +- } +- h++; +- pending >>= 1; +- } while (pending); +- +- local_irq_disable(); ++ handle_pending_softirqs(pending, cpu, 1); + + pending = local_softirq_pending(); + if (pending) { +@@ -269,12 +370,32 @@ restart: + wakeup_softirqd(); + } + +- lockdep_softirq_exit(); ++ lockdep_softirq_end(); + + account_system_vtime(current); + __local_bh_enable(SOFTIRQ_OFFSET); + } + ++/* ++ * Called with preemption disabled from run_ksoftirqd() ++ */ ++static int ksoftirqd_do_softirq(int cpu) ++{ ++ /* ++ * Preempt disable stops cpu going offline. ++ * If already offline, we'll be on wrong CPU: ++ * don't process. ++ */ ++ if (cpu_is_offline(cpu)) ++ return -1; ++ ++ local_irq_disable(); ++ if (local_softirq_pending()) ++ __do_softirq(); ++ local_irq_enable(); ++ return 0; ++} ++ + #ifndef __ARCH_HAS_DO_SOFTIRQ + + asmlinkage void do_softirq(void) +@@ -297,6 +418,191 @@ asmlinkage void do_softirq(void) + + #endif + ++static inline void local_bh_disable_nort(void) { local_bh_disable(); } ++static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } ++static inline void ksoftirqd_set_sched_params(void) { } ++static inline void ksoftirqd_clr_sched_params(void) { } ++ ++#else /* !PREEMPT_RT_FULL */ ++ ++/* ++ * On RT we serialize softirq execution with a cpu local lock ++ */ ++static DEFINE_LOCAL_IRQ_LOCK(local_softirq_lock); ++static DEFINE_PER_CPU(struct task_struct *, local_softirq_runner); ++ ++static void __do_softirq_common(int need_rcu_bh_qs); ++ ++void __do_softirq(void) ++{ ++ __do_softirq_common(0); ++} ++ ++void __init softirq_early_init(void) ++{ ++ local_irq_lock_init(local_softirq_lock); ++} ++ ++void local_bh_disable(void) ++{ ++ migrate_disable(); ++ current->softirq_nestcnt++; ++} ++EXPORT_SYMBOL(local_bh_disable); ++ ++void local_bh_enable(void) ++{ ++ if (WARN_ON(current->softirq_nestcnt == 0)) ++ return; ++ ++ if ((current->softirq_nestcnt == 1) && ++ local_softirq_pending() && ++ local_trylock(local_softirq_lock)) { ++ ++ local_irq_disable(); ++ if (local_softirq_pending()) ++ __do_softirq(); ++ local_irq_enable(); ++ local_unlock(local_softirq_lock); ++ WARN_ON(current->softirq_nestcnt != 1); ++ } ++ current->softirq_nestcnt--; ++ migrate_enable(); ++} ++EXPORT_SYMBOL(local_bh_enable); ++ ++void local_bh_enable_ip(unsigned long ip) ++{ ++ local_bh_enable(); ++} ++EXPORT_SYMBOL(local_bh_enable_ip); ++ ++void _local_bh_enable(void) ++{ ++ current->softirq_nestcnt--; ++ migrate_enable(); ++} ++EXPORT_SYMBOL(_local_bh_enable); ++ ++/* For tracing */ ++int notrace __in_softirq(void) ++{ ++ if (__get_cpu_var(local_softirq_lock).owner == current) ++ return __get_cpu_var(local_softirq_lock).nestcnt; ++ return 0; ++} ++ ++int in_serving_softirq(void) ++{ ++ int res; ++ ++ preempt_disable(); ++ res = __get_cpu_var(local_softirq_runner) == current; ++ preempt_enable(); ++ return res; ++} ++EXPORT_SYMBOL(in_serving_softirq); ++ ++/* ++ * Called with bh and local interrupts disabled. For full RT cpu must ++ * be pinned. ++ */ ++static void __do_softirq_common(int need_rcu_bh_qs) ++{ ++ u32 pending = local_softirq_pending(); ++ int cpu = smp_processor_id(); ++ ++ current->softirq_nestcnt++; ++ ++ /* Reset the pending bitmask before enabling irqs */ ++ set_softirq_pending(0); ++ ++ __get_cpu_var(local_softirq_runner) = current; ++ ++ lockdep_softirq_enter(); ++ ++ handle_pending_softirqs(pending, cpu, need_rcu_bh_qs); ++ ++ pending = local_softirq_pending(); ++ if (pending) ++ wakeup_softirqd(); ++ ++ lockdep_softirq_exit(); ++ __get_cpu_var(local_softirq_runner) = NULL; ++ ++ current->softirq_nestcnt--; ++} ++ ++static int __thread_do_softirq(int cpu) ++{ ++ /* ++ * Prevent the current cpu from going offline. ++ * pin_current_cpu() can reenable preemption and block on the ++ * hotplug mutex. When it returns, the current cpu is ++ * pinned. It might be the wrong one, but the offline check ++ * below catches that. ++ */ ++ pin_current_cpu(); ++ /* ++ * If called from ksoftirqd (cpu >= 0) we need to check ++ * whether we are on the wrong cpu due to cpu offlining. If ++ * called via thread_do_softirq() no action required. ++ */ ++ if (cpu >= 0 && cpu_is_offline(cpu)) { ++ unpin_current_cpu(); ++ return -1; ++ } ++ preempt_enable(); ++ local_lock(local_softirq_lock); ++ local_irq_disable(); ++ /* ++ * We cannot switch stacks on RT as we want to be able to ++ * schedule! ++ */ ++ if (local_softirq_pending()) ++ __do_softirq_common(cpu >= 0); ++ unpin_current_cpu(); ++ local_irq_enable(); ++ local_unlock(local_softirq_lock); ++ preempt_disable(); ++ return 0; ++} ++ ++/* ++ * Called from netif_rx_ni(). Preemption enabled. ++ */ ++void thread_do_softirq(void) ++{ ++ if (!in_serving_softirq()) { ++ preempt_disable(); ++ __thread_do_softirq(-1); ++ preempt_enable(); ++ } ++} ++ ++static int ksoftirqd_do_softirq(int cpu) ++{ ++ return __thread_do_softirq(cpu); ++} ++ ++static inline void local_bh_disable_nort(void) { } ++static inline void _local_bh_enable_nort(void) { } ++ ++static inline void ksoftirqd_set_sched_params(void) ++{ ++ struct sched_param param = { .sched_priority = 1 }; ++ ++ sched_setscheduler(current, SCHED_FIFO, ¶m); ++} ++ ++static inline void ksoftirqd_clr_sched_params(void) ++{ ++ struct sched_param param = { .sched_priority = 0 }; ++ ++ sched_setscheduler(current, SCHED_NORMAL, ¶m); ++} ++ ++#endif /* PREEMPT_RT_FULL */ + /* + * Enter an interrupt context. + */ +@@ -310,9 +616,9 @@ void irq_enter(void) + * Prevent raise_softirq from needlessly waking up ksoftirqd + * here, as softirq will be serviced on return from interrupt. + */ +- local_bh_disable(); ++ local_bh_disable_nort(); + tick_check_idle(cpu); +- _local_bh_enable(); ++ _local_bh_enable_nort(); + } + + __irq_enter(); +@@ -320,7 +626,9 @@ void irq_enter(void) + + static inline void invoke_softirq(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + if (!force_irqthreads) { ++ lockdep_softirq_from_hardirq(); + #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED + __do_softirq(); + #else +@@ -332,6 +640,9 @@ static inline void invoke_softirq(void) + wakeup_softirqd(); + __local_bh_enable(SOFTIRQ_OFFSET); + } ++#else ++ wakeup_softirqd(); ++#endif + } + + /* +@@ -340,7 +651,6 @@ static inline void invoke_softirq(void) + void irq_exit(void) + { + account_system_vtime(current); +- trace_hardirq_exit(); + sub_preempt_count(IRQ_EXIT_OFFSET); + if (!in_interrupt() && local_softirq_pending()) + invoke_softirq(); +@@ -351,6 +661,7 @@ void irq_exit(void) + tick_nohz_irq_exit(); + #endif + rcu_irq_exit(); ++ trace_hardirq_exit(); /* must be last! */ + sched_preempt_enable_no_resched(); + } + +@@ -406,15 +717,45 @@ struct tasklet_head + static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec); + static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec); + ++static void inline ++__tasklet_common_schedule(struct tasklet_struct *t, struct tasklet_head *head, unsigned int nr) ++{ ++ if (tasklet_trylock(t)) { ++again: ++ /* We may have been preempted before tasklet_trylock ++ * and __tasklet_action may have already run. ++ * So double check the sched bit while the takslet ++ * is locked before adding it to the list. ++ */ ++ if (test_bit(TASKLET_STATE_SCHED, &t->state)) { ++ t->next = NULL; ++ *head->tail = t; ++ head->tail = &(t->next); ++ raise_softirq_irqoff(nr); ++ tasklet_unlock(t); ++ } else { ++ /* This is subtle. If we hit the corner case above ++ * It is possible that we get preempted right here, ++ * and another task has successfully called ++ * tasklet_schedule(), then this function, and ++ * failed on the trylock. Thus we must be sure ++ * before releasing the tasklet lock, that the ++ * SCHED_BIT is clear. Otherwise the tasklet ++ * may get its SCHED_BIT set, but not added to the ++ * list ++ */ ++ if (!tasklet_tryunlock(t)) ++ goto again; ++ } ++ } ++} ++ + void __tasklet_schedule(struct tasklet_struct *t) + { + unsigned long flags; + + local_irq_save(flags); +- t->next = NULL; +- *__this_cpu_read(tasklet_vec.tail) = t; +- __this_cpu_write(tasklet_vec.tail, &(t->next)); +- raise_softirq_irqoff(TASKLET_SOFTIRQ); ++ __tasklet_common_schedule(t, &__get_cpu_var(tasklet_vec), TASKLET_SOFTIRQ); + local_irq_restore(flags); + } + +@@ -425,10 +766,7 @@ void __tasklet_hi_schedule(struct taskle + unsigned long flags; + + local_irq_save(flags); +- t->next = NULL; +- *__this_cpu_read(tasklet_hi_vec.tail) = t; +- __this_cpu_write(tasklet_hi_vec.tail, &(t->next)); +- raise_softirq_irqoff(HI_SOFTIRQ); ++ __tasklet_common_schedule(t, &__get_cpu_var(tasklet_hi_vec), HI_SOFTIRQ); + local_irq_restore(flags); + } + +@@ -436,50 +774,119 @@ EXPORT_SYMBOL(__tasklet_hi_schedule); + + void __tasklet_hi_schedule_first(struct tasklet_struct *t) + { +- BUG_ON(!irqs_disabled()); +- +- t->next = __this_cpu_read(tasklet_hi_vec.head); +- __this_cpu_write(tasklet_hi_vec.head, t); +- __raise_softirq_irqoff(HI_SOFTIRQ); ++ __tasklet_hi_schedule(t); + } + + EXPORT_SYMBOL(__tasklet_hi_schedule_first); + +-static void tasklet_action(struct softirq_action *a) ++void tasklet_enable(struct tasklet_struct *t) + { +- struct tasklet_struct *list; ++ if (!atomic_dec_and_test(&t->count)) ++ return; ++ if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) ++ tasklet_schedule(t); ++} + +- local_irq_disable(); +- list = __this_cpu_read(tasklet_vec.head); +- __this_cpu_write(tasklet_vec.head, NULL); +- __this_cpu_write(tasklet_vec.tail, &__get_cpu_var(tasklet_vec).head); +- local_irq_enable(); ++EXPORT_SYMBOL(tasklet_enable); ++ ++void tasklet_hi_enable(struct tasklet_struct *t) ++{ ++ if (!atomic_dec_and_test(&t->count)) ++ return; ++ if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) ++ tasklet_hi_schedule(t); ++} ++ ++EXPORT_SYMBOL(tasklet_hi_enable); ++ ++static void ++__tasklet_action(struct softirq_action *a, struct tasklet_struct *list) ++{ ++ int loops = 1000000; + + while (list) { + struct tasklet_struct *t = list; + + list = list->next; + +- if (tasklet_trylock(t)) { +- if (!atomic_read(&t->count)) { +- if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) +- BUG(); +- t->func(t->data); +- tasklet_unlock(t); +- continue; +- } +- tasklet_unlock(t); ++ /* ++ * Should always succeed - after a tasklist got on the ++ * list (after getting the SCHED bit set from 0 to 1), ++ * nothing but the tasklet softirq it got queued to can ++ * lock it: ++ */ ++ if (!tasklet_trylock(t)) { ++ WARN_ON(1); ++ continue; + } + +- local_irq_disable(); + t->next = NULL; +- *__this_cpu_read(tasklet_vec.tail) = t; +- __this_cpu_write(tasklet_vec.tail, &(t->next)); +- __raise_softirq_irqoff(TASKLET_SOFTIRQ); +- local_irq_enable(); ++ ++ /* ++ * If we cannot handle the tasklet because it's disabled, ++ * mark it as pending. tasklet_enable() will later ++ * re-schedule the tasklet. ++ */ ++ if (unlikely(atomic_read(&t->count))) { ++out_disabled: ++ /* implicit unlock: */ ++ wmb(); ++ t->state = TASKLET_STATEF_PENDING; ++ continue; ++ } ++ ++ /* ++ * After this point on the tasklet might be rescheduled ++ * on another CPU, but it can only be added to another ++ * CPU's tasklet list if we unlock the tasklet (which we ++ * dont do yet). ++ */ ++ if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) ++ WARN_ON(1); ++ ++again: ++ t->func(t->data); ++ ++ /* ++ * Try to unlock the tasklet. We must use cmpxchg, because ++ * another CPU might have scheduled or disabled the tasklet. ++ * We only allow the STATE_RUN -> 0 transition here. ++ */ ++ while (!tasklet_tryunlock(t)) { ++ /* ++ * If it got disabled meanwhile, bail out: ++ */ ++ if (atomic_read(&t->count)) ++ goto out_disabled; ++ /* ++ * If it got scheduled meanwhile, re-execute ++ * the tasklet function: ++ */ ++ if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) ++ goto again; ++ if (!--loops) { ++ printk("hm, tasklet state: %08lx\n", t->state); ++ WARN_ON(1); ++ tasklet_unlock(t); ++ break; ++ } ++ } + } + } + ++static void tasklet_action(struct softirq_action *a) ++{ ++ struct tasklet_struct *list; ++ ++ local_irq_disable(); ++ list = __get_cpu_var(tasklet_vec).head; ++ __get_cpu_var(tasklet_vec).head = NULL; ++ __get_cpu_var(tasklet_vec).tail = &__get_cpu_var(tasklet_vec).head; ++ local_irq_enable(); ++ ++ __tasklet_action(a, list); ++} ++ + static void tasklet_hi_action(struct softirq_action *a) + { + struct tasklet_struct *list; +@@ -490,29 +897,7 @@ static void tasklet_hi_action(struct sof + __this_cpu_write(tasklet_hi_vec.tail, &__get_cpu_var(tasklet_hi_vec).head); + local_irq_enable(); + +- while (list) { +- struct tasklet_struct *t = list; +- +- list = list->next; +- +- if (tasklet_trylock(t)) { +- if (!atomic_read(&t->count)) { +- if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) +- BUG(); +- t->func(t->data); +- tasklet_unlock(t); +- continue; +- } +- tasklet_unlock(t); +- } +- +- local_irq_disable(); +- t->next = NULL; +- *__this_cpu_read(tasklet_hi_vec.tail) = t; +- __this_cpu_write(tasklet_hi_vec.tail, &(t->next)); +- __raise_softirq_irqoff(HI_SOFTIRQ); +- local_irq_enable(); +- } ++ __tasklet_action(a, list); + } + + +@@ -535,7 +920,7 @@ void tasklet_kill(struct tasklet_struct + + while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { + do { +- yield(); ++ msleep(1); + } while (test_bit(TASKLET_STATE_SCHED, &t->state)); + } + tasklet_unlock_wait(t); +@@ -741,28 +1126,39 @@ void __init softirq_init(void) + open_softirq(HI_SOFTIRQ, tasklet_hi_action); + } + ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) ++void tasklet_unlock_wait(struct tasklet_struct *t) ++{ ++ while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { ++ /* ++ * Hack for now to avoid this busy-loop: ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ msleep(1); ++#else ++ barrier(); ++#endif ++ } ++} ++EXPORT_SYMBOL(tasklet_unlock_wait); ++#endif ++ + static int run_ksoftirqd(void * __bind_cpu) + { ++ ksoftirqd_set_sched_params(); ++ + set_current_state(TASK_INTERRUPTIBLE); + + while (!kthread_should_stop()) { + preempt_disable(); +- if (!local_softirq_pending()) { ++ if (!local_softirq_pending()) + schedule_preempt_disabled(); +- } + + __set_current_state(TASK_RUNNING); + + while (local_softirq_pending()) { +- /* Preempt disable stops cpu going offline. +- If already offline, we'll be on wrong CPU: +- don't process */ +- if (cpu_is_offline((long)__bind_cpu)) ++ if (ksoftirqd_do_softirq((long) __bind_cpu)) + goto wait_to_die; +- local_irq_disable(); +- if (local_softirq_pending()) +- __do_softirq(); +- local_irq_enable(); + sched_preempt_enable_no_resched(); + cond_resched(); + preempt_disable(); +@@ -776,6 +1172,7 @@ static int run_ksoftirqd(void * __bind_c + + wait_to_die: + preempt_enable(); ++ ksoftirqd_clr_sched_params(); + /* Wait for kthread_stop */ + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { +@@ -852,9 +1249,8 @@ static int __cpuinit cpu_callback(struct + int hotcpu = (unsigned long)hcpu; + struct task_struct *p; + +- switch (action) { ++ switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: +- case CPU_UP_PREPARE_FROZEN: + p = kthread_create_on_node(run_ksoftirqd, + hcpu, + cpu_to_node(hotcpu), +@@ -867,19 +1263,16 @@ static int __cpuinit cpu_callback(struct + per_cpu(ksoftirqd, hotcpu) = p; + break; + case CPU_ONLINE: +- case CPU_ONLINE_FROZEN: + wake_up_process(per_cpu(ksoftirqd, hotcpu)); + break; + #ifdef CONFIG_HOTPLUG_CPU + case CPU_UP_CANCELED: +- case CPU_UP_CANCELED_FROZEN: + if (!per_cpu(ksoftirqd, hotcpu)) + break; + /* Unbind so it can run. Fall thru. */ + kthread_bind(per_cpu(ksoftirqd, hotcpu), + cpumask_any(cpu_online_mask)); +- case CPU_DEAD: +- case CPU_DEAD_FROZEN: { ++ case CPU_POST_DEAD: { + static const struct sched_param param = { + .sched_priority = MAX_RT_PRIO-1 + }; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/spinlock.c sun8i-rt/kernel/spinlock.c +--- sun8i/kernel/spinlock.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/spinlock.c 2016-08-22 17:34:01.268261976 +0200 +@@ -110,8 +110,11 @@ void __lockfunc __raw_##op##_lock_bh(loc + * __[spin|read|write]_lock_bh() + */ + BUILD_LOCK_OPS(spin, raw_spinlock); ++ ++#ifndef CONFIG_PREEMPT_RT_FULL + BUILD_LOCK_OPS(read, rwlock); + BUILD_LOCK_OPS(write, rwlock); ++#endif + + #endif + +@@ -195,6 +198,8 @@ void __lockfunc _raw_spin_unlock_bh(raw_ + EXPORT_SYMBOL(_raw_spin_unlock_bh); + #endif + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #ifndef CONFIG_INLINE_READ_TRYLOCK + int __lockfunc _raw_read_trylock(rwlock_t *lock) + { +@@ -339,6 +344,8 @@ void __lockfunc _raw_write_unlock_bh(rwl + EXPORT_SYMBOL(_raw_write_unlock_bh); + #endif + ++#endif /* !PREEMPT_RT_FULL */ ++ + #ifdef CONFIG_DEBUG_LOCK_ALLOC + + void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/stop_machine.c sun8i-rt/kernel/stop_machine.c +--- sun8i/kernel/stop_machine.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/stop_machine.c 2016-08-22 18:03:05.136282025 +0200 +@@ -29,12 +29,12 @@ struct cpu_stop_done { + atomic_t nr_todo; /* nr left to execute */ + bool executed; /* actually executed? */ + int ret; /* collected return value */ +- struct completion completion; /* fired if nr_todo reaches 0 */ ++ struct task_struct *waiter; /* woken when nr_todo reaches 0 */ + }; + + /* the actual stopper, one per every possible cpu, enabled on online cpus */ + struct cpu_stopper { +- spinlock_t lock; ++ raw_spinlock_t lock; + bool enabled; /* is this stopper enabled? */ + struct list_head works; /* list of pending works */ + struct task_struct *thread; /* stopper thread */ +@@ -47,7 +47,7 @@ static void cpu_stop_init_done(struct cp + { + memset(done, 0, sizeof(*done)); + atomic_set(&done->nr_todo, nr_todo); +- init_completion(&done->completion); ++ done->waiter = current; + } + + /* signal completion unless @done is NULL */ +@@ -56,8 +56,10 @@ static void cpu_stop_signal_done(struct + if (done) { + if (executed) + done->executed = true; +- if (atomic_dec_and_test(&done->nr_todo)) +- complete(&done->completion); ++ if (atomic_dec_and_test(&done->nr_todo)) { ++ wake_up_process(done->waiter); ++ done->waiter = NULL; ++ } + } + } + +@@ -67,7 +69,7 @@ static void cpu_stop_queue_work(struct c + { + unsigned long flags; + +- spin_lock_irqsave(&stopper->lock, flags); ++ raw_spin_lock_irqsave(&stopper->lock, flags); + + if (stopper->enabled) { + list_add_tail(&work->list, &stopper->works); +@@ -75,7 +77,23 @@ static void cpu_stop_queue_work(struct c + } else + cpu_stop_signal_done(work->done, false); + +- spin_unlock_irqrestore(&stopper->lock, flags); ++ raw_spin_unlock_irqrestore(&stopper->lock, flags); ++} ++ ++static void wait_for_stop_done(struct cpu_stop_done *done) ++{ ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ while (atomic_read(&done->nr_todo)) { ++ schedule(); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ } ++ /* ++ * We need to wait until cpu_stop_signal_done() has cleared ++ * done->waiter. ++ */ ++ while (done->waiter) ++ cpu_relax(); ++ set_current_state(TASK_RUNNING); + } + + /** +@@ -109,7 +127,7 @@ int stop_one_cpu(unsigned int cpu, cpu_s + + cpu_stop_init_done(&done, 1); + cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), &work); +- wait_for_completion(&done.completion); ++ wait_for_stop_done(&done); + return done.executed ? done.ret : -ENOENT; + } + +@@ -135,11 +153,12 @@ void stop_one_cpu_nowait(unsigned int cp + + /* static data for stop_cpus */ + static DEFINE_MUTEX(stop_cpus_mutex); ++static DEFINE_MUTEX(stopper_lock); + static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work); + + static void queue_stop_cpus_work(const struct cpumask *cpumask, + cpu_stop_fn_t fn, void *arg, +- struct cpu_stop_done *done) ++ struct cpu_stop_done *done, bool inactive) + { + struct cpu_stop_work *work; + unsigned int cpu; +@@ -153,15 +172,19 @@ static void queue_stop_cpus_work(const s + } + + /* +- * Disable preemption while queueing to avoid getting +- * preempted by a stopper which might wait for other stoppers +- * to enter @fn which can lead to deadlock. ++ * Make sure that all work is queued on all cpus before we ++ * any of the cpus can execute it. + */ +- preempt_disable(); ++ if (!inactive) { ++ mutex_lock(&stopper_lock); ++ } else { ++ while (!mutex_trylock(&stopper_lock)) ++ cpu_relax(); ++ } + for_each_cpu(cpu, cpumask) + cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), + &per_cpu(stop_cpus_work, cpu)); +- preempt_enable(); ++ mutex_unlock(&stopper_lock); + } + + static int __stop_cpus(const struct cpumask *cpumask, +@@ -170,8 +193,8 @@ static int __stop_cpus(const struct cpum + struct cpu_stop_done done; + + cpu_stop_init_done(&done, cpumask_weight(cpumask)); +- queue_stop_cpus_work(cpumask, fn, arg, &done); +- wait_for_completion(&done.completion); ++ queue_stop_cpus_work(cpumask, fn, arg, &done, false); ++ wait_for_stop_done(&done); + return done.executed ? done.ret : -ENOENT; + } + +@@ -259,13 +282,13 @@ repeat: + } + + work = NULL; +- spin_lock_irq(&stopper->lock); ++ raw_spin_lock_irq(&stopper->lock); + if (!list_empty(&stopper->works)) { + work = list_first_entry(&stopper->works, + struct cpu_stop_work, list); + list_del_init(&work->list); + } +- spin_unlock_irq(&stopper->lock); ++ raw_spin_unlock_irq(&stopper->lock); + + if (work) { + cpu_stop_fn_t fn = work->fn; +@@ -275,6 +298,16 @@ repeat: + + __set_current_state(TASK_RUNNING); + ++ /* ++ * Wait until the stopper finished scheduling on all ++ * cpus ++ */ ++ mutex_lock(&stopper_lock); ++ /* ++ * Let other cpu threads continue as well ++ */ ++ mutex_unlock(&stopper_lock); ++ + /* cpu stop callbacks are not allowed to sleep */ + preempt_disable(); + +@@ -289,7 +322,13 @@ repeat: + kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL, + ksym_buf), arg); + ++ /* ++ * Make sure that the wakeup and setting done->waiter ++ * to NULL is atomic. ++ */ ++ local_irq_disable(); + cpu_stop_signal_done(done, true); ++ local_irq_enable(); + } else + schedule(); + +@@ -317,6 +356,7 @@ static int __cpuinit cpu_stop_cpu_callba + if (IS_ERR(p)) + return notifier_from_errno(PTR_ERR(p)); + get_task_struct(p); ++ p->flags |= PF_STOMPER; + kthread_bind(p, cpu); + sched_set_stop_task(cpu, p); + stopper->thread = p; +@@ -326,9 +366,9 @@ static int __cpuinit cpu_stop_cpu_callba + /* strictly unnecessary, as first user will wake it */ + wake_up_process(stopper->thread); + /* mark enabled */ +- spin_lock_irq(&stopper->lock); ++ raw_spin_lock_irq(&stopper->lock); + stopper->enabled = true; +- spin_unlock_irq(&stopper->lock); ++ raw_spin_unlock_irq(&stopper->lock); + break; + + #ifdef CONFIG_HOTPLUG_CPU +@@ -341,11 +381,11 @@ static int __cpuinit cpu_stop_cpu_callba + /* kill the stopper */ + kthread_stop(stopper->thread); + /* drain remaining works */ +- spin_lock_irq(&stopper->lock); ++ raw_spin_lock_irq(&stopper->lock); + list_for_each_entry(work, &stopper->works, list) + cpu_stop_signal_done(work->done, false); + stopper->enabled = false; +- spin_unlock_irq(&stopper->lock); ++ raw_spin_unlock_irq(&stopper->lock); + /* release the stopper */ + put_task_struct(stopper->thread); + stopper->thread = NULL; +@@ -376,7 +416,7 @@ static int __init cpu_stop_init(void) + for_each_possible_cpu(cpu) { + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + +- spin_lock_init(&stopper->lock); ++ raw_spin_lock_init(&stopper->lock); + INIT_LIST_HEAD(&stopper->works); + } + +@@ -566,11 +606,11 @@ int stop_machine_from_inactive_cpu(int ( + set_state(&smdata, STOPMACHINE_PREPARE); + cpu_stop_init_done(&done, num_active_cpus()); + queue_stop_cpus_work(cpu_active_mask, stop_machine_cpu_stop, &smdata, +- &done); ++ &done, true); + ret = stop_machine_cpu_stop(&smdata); + + /* Busy wait for completion. */ +- while (!completion_done(&done.completion)) ++ while (atomic_read(&done.nr_todo)) + cpu_relax(); + + mutex_unlock(&stop_cpus_mutex); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/time/jiffies.c sun8i-rt/kernel/time/jiffies.c +--- sun8i/kernel/time/jiffies.c 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/kernel/time/jiffies.c 2016-08-22 15:58:27.456196056 +0200 +@@ -80,9 +80,9 @@ u64 get_jiffies_64(void) + u64 ret; + + do { +- seq = read_seqbegin(&xtime_lock); ++ seq = read_seqcount_begin(&xtime_seq); + ret = jiffies_64; +- } while (read_seqretry(&xtime_lock, seq)); ++ } while (read_seqcount_retry(&xtime_seq, seq)); + return ret; + } + EXPORT_SYMBOL(get_jiffies_64); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/time/ntp.c sun8i-rt/kernel/time/ntp.c +--- sun8i/kernel/time/ntp.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/kernel/time/ntp.c 2016-08-22 18:13:58.480289536 +0200 +@@ -10,6 +10,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -22,7 +23,7 @@ + * NTP timekeeping variables: + */ + +-DEFINE_SPINLOCK(ntp_lock); ++DEFINE_RAW_SPINLOCK(ntp_lock); + + + /* USER_HZ period (usecs): */ +@@ -347,7 +348,7 @@ void ntp_clear(void) + { + unsigned long flags; + +- spin_lock_irqsave(&ntp_lock, flags); ++ raw_spin_lock_irqsave(&ntp_lock, flags); + + time_adjust = 0; /* stop active adjtime() */ + time_status |= STA_UNSYNC; +@@ -361,7 +362,7 @@ void ntp_clear(void) + + /* Clear PPS state variables */ + pps_clear(); +- spin_unlock_irqrestore(&ntp_lock, flags); ++ raw_spin_unlock_irqrestore(&ntp_lock, flags); + + } + +@@ -371,9 +372,9 @@ u64 ntp_tick_length(void) + unsigned long flags; + s64 ret; + +- spin_lock_irqsave(&ntp_lock, flags); ++ raw_spin_lock_irqsave(&ntp_lock, flags); + ret = tick_length; +- spin_unlock_irqrestore(&ntp_lock, flags); ++ raw_spin_unlock_irqrestore(&ntp_lock, flags); + return ret; + } + +@@ -394,7 +395,7 @@ int second_overflow(unsigned long secs) + int leap = 0; + unsigned long flags; + +- spin_lock_irqsave(&ntp_lock, flags); ++ raw_spin_lock_irqsave(&ntp_lock, flags); + + /* + * Leap second processing. If in leap-insert state at the end of the +@@ -480,7 +481,7 @@ int second_overflow(unsigned long secs) + + + out: +- spin_unlock_irqrestore(&ntp_lock, flags); ++ raw_spin_unlock_irqrestore(&ntp_lock, flags); + + return leap; + } +@@ -531,10 +532,49 @@ static void sync_cmos_clock(struct work_ + schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next)); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * RT can not call schedule_delayed_work from real interrupt context. ++ * Need to make a thread to do the real work. ++ */ ++static struct task_struct *cmos_delay_thread; ++static bool do_cmos_delay; ++ ++static int run_cmos_delay(void *ignore) ++{ ++ while (!kthread_should_stop()) { ++ set_current_state(TASK_INTERRUPTIBLE); ++ if (do_cmos_delay) { ++ do_cmos_delay = false; ++ schedule_delayed_work(&sync_cmos_work, 0); ++ } ++ schedule(); ++ } ++ __set_current_state(TASK_RUNNING); ++ return 0; ++} ++ ++static void notify_cmos_timer(void) ++{ ++ do_cmos_delay = true; ++ /* Make visible before waking up process */ ++ smp_wmb(); ++ wake_up_process(cmos_delay_thread); ++} ++ ++static __init int create_cmos_delay_thread(void) ++{ ++ cmos_delay_thread = kthread_run(run_cmos_delay, NULL, "kcmosdelayd"); ++ BUG_ON(!cmos_delay_thread); ++ return 0; ++} ++early_initcall(create_cmos_delay_thread); ++#else + static void notify_cmos_timer(void) + { + schedule_delayed_work(&sync_cmos_work, 0); + } ++#endif /* CONFIG_PREEMPT_RT_FULL */ + + #else + static inline void notify_cmos_timer(void) { } +@@ -673,7 +713,7 @@ int do_adjtimex(struct timex *txc) + + getnstimeofday(&ts); + +- spin_lock_irq(&ntp_lock); ++ raw_spin_lock_irq(&ntp_lock); + + if (txc->modes & ADJ_ADJTIME) { + long save_adjust = time_adjust; +@@ -715,7 +755,7 @@ int do_adjtimex(struct timex *txc) + /* fill PPS status fields */ + pps_fill_timex(txc); + +- spin_unlock_irq(&ntp_lock); ++ raw_spin_unlock_irq(&ntp_lock); + + txc->time.tv_sec = ts.tv_sec; + txc->time.tv_usec = ts.tv_nsec; +@@ -913,7 +953,7 @@ void hardpps(const struct timespec *phas + + pts_norm = pps_normalize_ts(*phase_ts); + +- spin_lock_irqsave(&ntp_lock, flags); ++ raw_spin_lock_irqsave(&ntp_lock, flags); + + /* clear the error bits, they will be set again if needed */ + time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR); +@@ -926,7 +966,7 @@ void hardpps(const struct timespec *phas + * just start the frequency interval */ + if (unlikely(pps_fbase.tv_sec == 0)) { + pps_fbase = *raw_ts; +- spin_unlock_irqrestore(&ntp_lock, flags); ++ raw_spin_unlock_irqrestore(&ntp_lock, flags); + return; + } + +@@ -941,7 +981,7 @@ void hardpps(const struct timespec *phas + time_status |= STA_PPSJITTER; + /* restart the frequency calibration interval */ + pps_fbase = *raw_ts; +- spin_unlock_irqrestore(&ntp_lock, flags); ++ raw_spin_unlock_irqrestore(&ntp_lock, flags); + pr_err("hardpps: PPSJITTER: bad pulse\n"); + return; + } +@@ -958,7 +998,7 @@ void hardpps(const struct timespec *phas + + hardpps_update_phase(pts_norm.nsec); + +- spin_unlock_irqrestore(&ntp_lock, flags); ++ raw_spin_unlock_irqrestore(&ntp_lock, flags); + } + EXPORT_SYMBOL(hardpps); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/time/tick-common.c sun8i-rt/kernel/time/tick-common.c +--- sun8i/kernel/time/tick-common.c 2016-08-22 14:14:34.000000000 +0200 ++++ sun8i-rt/kernel/time/tick-common.c 2016-08-22 15:58:27.456196056 +0200 +@@ -63,13 +63,15 @@ int tick_is_oneshot_available(void) + static void tick_periodic(int cpu) + { + if (tick_do_timer_cpu == cpu) { +- write_seqlock(&xtime_lock); ++ raw_spin_lock(&xtime_lock); ++ write_seqcount_begin(&xtime_seq); + + /* Keep track of the next tick event */ + tick_next_period = ktime_add(tick_next_period, tick_period); + + do_timer(1); +- write_sequnlock(&xtime_lock); ++ write_seqcount_end(&xtime_seq); ++ raw_spin_unlock(&xtime_lock); + } + + update_process_times(user_mode(get_irq_regs())); +@@ -130,9 +132,9 @@ void tick_setup_periodic(struct clock_ev + ktime_t next; + + do { +- seq = read_seqbegin(&xtime_lock); ++ seq = read_seqcount_begin(&xtime_seq); + next = tick_next_period; +- } while (read_seqretry(&xtime_lock, seq)); ++ } while (read_seqcount_retry(&xtime_seq, seq)); + + clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/time/tick-internal.h sun8i-rt/kernel/time/tick-internal.h +--- sun8i/kernel/time/tick-internal.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/time/tick-internal.h 2016-08-22 15:58:27.456196056 +0200 +@@ -141,4 +141,5 @@ static inline int tick_device_is_functio + #endif + + extern void do_timer(unsigned long ticks); +-extern seqlock_t xtime_lock; ++extern raw_spinlock_t xtime_lock; ++extern seqcount_t xtime_seq; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/time/tick-sched.c sun8i-rt/kernel/time/tick-sched.c +--- sun8i/kernel/time/tick-sched.c 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/kernel/time/tick-sched.c 2016-08-22 17:21:17.492253195 +0200 +@@ -56,7 +56,8 @@ static void tick_do_update_jiffies64(kti + return; + + /* Reevalute with xtime_lock held */ +- write_seqlock(&xtime_lock); ++ raw_spin_lock(&xtime_lock); ++ write_seqcount_begin(&xtime_seq); + + delta = ktime_sub(now, last_jiffies_update); + if (delta.tv64 >= tick_period.tv64) { +@@ -79,7 +80,8 @@ static void tick_do_update_jiffies64(kti + /* Keep the tick_next_period variable up to date */ + tick_next_period = ktime_add(last_jiffies_update, tick_period); + } +- write_sequnlock(&xtime_lock); ++ write_seqcount_end(&xtime_seq); ++ raw_spin_unlock(&xtime_lock); + } + + /* +@@ -89,12 +91,14 @@ static ktime_t tick_init_jiffy_update(vo + { + ktime_t period; + +- write_seqlock(&xtime_lock); ++ raw_spin_lock(&xtime_lock); ++ write_seqcount_begin(&xtime_seq); + /* Did we start the jiffies update yet ? */ + if (last_jiffies_update.tv64 == 0) + last_jiffies_update = tick_next_period; + period = last_jiffies_update; +- write_sequnlock(&xtime_lock); ++ write_seqcount_end(&xtime_seq); ++ raw_spin_unlock(&xtime_lock); + return period; + } + +@@ -305,24 +309,18 @@ static void tick_nohz_stop_sched_tick(st + return; + + if (unlikely(local_softirq_pending() && cpu_online(cpu))) { +- static int ratelimit; +- +- if (ratelimit < 10) { +- printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", +- (unsigned int) local_softirq_pending()); +- ratelimit++; +- } ++ softirq_check_pending_idle(); + return; + } + + ts->idle_calls++; + /* Read jiffies and the time when jiffies were updated last */ + do { +- seq = read_seqbegin(&xtime_lock); ++ seq = read_seqcount_begin(&xtime_seq); + last_update = last_jiffies_update; + last_jiffies = jiffies; + time_delta = timekeeping_max_deferment(); +- } while (read_seqretry(&xtime_lock, seq)); ++ } while (read_seqcount_retry(&xtime_seq, seq)); + + if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) || + arch_needs_cpu(cpu)) { +@@ -824,6 +822,16 @@ static enum hrtimer_restart tick_sched_t + return HRTIMER_RESTART; + } + ++static int sched_skew_tick; ++ ++static int __init skew_tick(char *str) ++{ ++ get_option(&str, &sched_skew_tick); ++ ++ return 0; ++} ++early_param("skew_tick", skew_tick); ++ + /** + * tick_setup_sched_timer - setup the tick emulation timer + */ +@@ -836,11 +844,20 @@ void tick_setup_sched_timer(void) + * Emulate tick processing via per-CPU hrtimers: + */ + hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ++ ts->sched_timer.irqsafe = 1; + ts->sched_timer.function = tick_sched_timer; + + /* Get the next period (per cpu) */ + hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); + ++ /* Offset the tick to avert xtime_lock contention. */ ++ if (sched_skew_tick) { ++ u64 offset = ktime_to_ns(tick_period) >> 1; ++ do_div(offset, num_possible_cpus()); ++ offset *= smp_processor_id(); ++ hrtimer_add_expires_ns(&ts->sched_timer, offset); ++ } ++ + for (;;) { + hrtimer_forward(&ts->sched_timer, now, tick_period); + hrtimer_start_expires(&ts->sched_timer, +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/time/timekeeping.c sun8i-rt/kernel/time/timekeeping.c +--- sun8i/kernel/time/timekeeping.c 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/kernel/time/timekeeping.c 2016-08-22 18:01:28.248280911 +0200 +@@ -76,8 +76,9 @@ struct timekeeper { + /* Offset clock monotonic -> clock boottime */ + ktime_t offs_boot; + +- /* Seqlock for all timekeeper values */ +- seqlock_t lock; ++ /* Open coded seqlock for all timekeeper values */ ++ seqcount_t seq; ++ raw_spinlock_t lock; + }; + + static struct timekeeper timekeeper; +@@ -86,7 +87,8 @@ static struct timekeeper timekeeper; + * This read-write spinlock protects us from races in SMP while + * playing with xtime. + */ +-__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); ++__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(xtime_lock); ++seqcount_t xtime_seq; + + + /* flag for if timekeeping is suspended */ +@@ -243,7 +245,7 @@ void getnstimeofday(struct timespec *ts) + WARN_ON(timekeeping_suspended); + + do { +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + + *ts = timekeeper.xtime; + nsecs = timekeeping_get_ns(); +@@ -251,7 +253,7 @@ void getnstimeofday(struct timespec *ts) + /* If arch requires, add in gettimeoffset() */ + nsecs += arch_gettimeoffset(); + +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + + timespec_add_ns(ts, nsecs); + } +@@ -266,7 +268,7 @@ ktime_t ktime_get(void) + WARN_ON(timekeeping_suspended); + + do { +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + secs = timekeeper.xtime.tv_sec + + timekeeper.wall_to_monotonic.tv_sec; + nsecs = timekeeper.xtime.tv_nsec + +@@ -275,7 +277,7 @@ ktime_t ktime_get(void) + /* If arch requires, add in gettimeoffset() */ + nsecs += arch_gettimeoffset(); + +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + /* + * Use ktime_set/ktime_add_ns to create a proper ktime on + * 32-bit architectures without CONFIG_KTIME_SCALAR. +@@ -301,14 +303,14 @@ void ktime_get_ts(struct timespec *ts) + WARN_ON(timekeeping_suspended); + + do { +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + *ts = timekeeper.xtime; + tomono = timekeeper.wall_to_monotonic; + nsecs = timekeeping_get_ns(); + /* If arch requires, add in gettimeoffset() */ + nsecs += arch_gettimeoffset(); + +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + + set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, + ts->tv_nsec + tomono.tv_nsec + nsecs); +@@ -336,7 +338,7 @@ void getnstime_raw_and_real(struct times + do { + u32 arch_offset; + +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + + *ts_raw = timekeeper.raw_time; + *ts_real = timekeeper.xtime; +@@ -349,7 +351,7 @@ void getnstime_raw_and_real(struct times + nsecs_raw += arch_offset; + nsecs_real += arch_offset; + +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + + timespec_add_ns(ts_raw, nsecs_raw); + timespec_add_ns(ts_real, nsecs_real); +@@ -388,7 +390,8 @@ int do_settimeofday(const struct timespe + if (!timespec_valid_strict(tv)) + return -EINVAL; + +- write_seqlock_irqsave(&timekeeper.lock, flags); ++ raw_spin_lock_irqsave(&timekeeper.lock, flags); ++ write_seqcount_begin(&timekeeper.seq); + + timekeeping_forward_now(); + +@@ -400,7 +403,8 @@ int do_settimeofday(const struct timespe + timekeeper.xtime = *tv; + timekeeping_update(true); + +- write_sequnlock_irqrestore(&timekeeper.lock, flags); ++ write_seqcount_end(&timekeeper.seq); ++ raw_spin_unlock_irqrestore(&timekeeper.lock, flags); + + /* signal hrtimers about time change */ + clock_was_set(); +@@ -426,7 +430,8 @@ int timekeeping_inject_offset(struct tim + if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) + return -EINVAL; + +- write_seqlock_irqsave(&timekeeper.lock, flags); ++ raw_spin_lock_irqsave(&timekeeper.lock, flags); ++ write_seqcount_begin(&timekeeper.seq); + + timekeeping_forward_now(); + +@@ -443,7 +448,8 @@ int timekeeping_inject_offset(struct tim + error: /* even if we error out, we forwarded the time, so call update */ + timekeeping_update(true); + +- write_sequnlock_irqrestore(&timekeeper.lock, flags); ++ write_seqcount_end(&timekeeper.seq); ++ raw_spin_unlock_irqrestore(&timekeeper.lock, flags); + + /* signal hrtimers about time change */ + clock_was_set(); +@@ -464,7 +470,8 @@ static int change_clocksource(void *data + + new = (struct clocksource *) data; + +- write_seqlock_irqsave(&timekeeper.lock, flags); ++ raw_spin_lock_irqsave(&timekeeper.lock, flags); ++ write_seqcount_begin(&timekeeper.seq); + + timekeeping_forward_now(); + if (!new->enable || new->enable(new) == 0) { +@@ -475,7 +482,8 @@ static int change_clocksource(void *data + } + timekeeping_update(true); + +- write_sequnlock_irqrestore(&timekeeper.lock, flags); ++ write_seqcount_end(&timekeeper.seq); ++ raw_spin_unlock_irqrestore(&timekeeper.lock, flags); + + return 0; + } +@@ -522,11 +530,11 @@ void getrawmonotonic(struct timespec *ts + s64 nsecs; + + do { +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + nsecs = timekeeping_get_ns_raw(); + *ts = timekeeper.raw_time; + +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + + timespec_add_ns(ts, nsecs); + } +@@ -542,11 +550,11 @@ int timekeeping_valid_for_hres(void) + int ret; + + do { +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + + ret = timekeeper.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; + +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + + return ret; + } +@@ -559,11 +567,11 @@ u64 timekeeping_max_deferment(void) + unsigned long seq; + u64 ret; + do { +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + + ret = timekeeper.clock->max_idle_ns; + +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + + return ret; + } +@@ -623,11 +631,13 @@ void __init timekeeping_init(void) + boot.tv_nsec = 0; + } + +- seqlock_init(&timekeeper.lock); ++ raw_spin_lock_init(&timekeeper.lock); ++ seqcount_init(&timekeeper.seq); + + ntp_init(); + +- write_seqlock_irqsave(&timekeeper.lock, flags); ++ raw_spin_lock_irqsave(&timekeeper.lock, flags); ++ write_seqcount_begin(&timekeeper.seq); + clock = clocksource_default_clock(); + if (clock->enable) + clock->enable(clock); +@@ -646,7 +656,8 @@ void __init timekeeping_init(void) + update_rt_offset(); + timekeeper.total_sleep_time.tv_sec = 0; + timekeeper.total_sleep_time.tv_nsec = 0; +- write_sequnlock_irqrestore(&timekeeper.lock, flags); ++ write_seqcount_end(&timekeeper.seq); ++ raw_spin_unlock_irqrestore(&timekeeper.lock, flags); + } + + /* time in seconds when suspend began */ +@@ -700,7 +711,8 @@ void timekeeping_inject_sleeptime(struct + if (!(ts.tv_sec == 0 && ts.tv_nsec == 0)) + return; + +- write_seqlock_irqsave(&timekeeper.lock, flags); ++ raw_spin_lock_irqsave(&timekeeper.lock, flags); ++ write_seqcount_begin(&timekeeper.seq); + + timekeeping_forward_now(); + +@@ -708,7 +720,8 @@ void timekeeping_inject_sleeptime(struct + + timekeeping_update(true); + +- write_sequnlock_irqrestore(&timekeeper.lock, flags); ++ write_seqcount_end(&timekeeper.seq); ++ raw_spin_unlock_irqrestore(&timekeeper.lock, flags); + + /* signal hrtimers about time change */ + clock_was_set(); +@@ -731,7 +744,8 @@ static void timekeeping_resume(void) + + clocksource_resume(); + +- write_seqlock_irqsave(&timekeeper.lock, flags); ++ raw_spin_lock_irqsave(&timekeeper.lock, flags); ++ write_seqcount_begin(&timekeeper.seq); + + if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) { + ts = timespec_sub(ts, timekeeping_suspend_time); +@@ -742,7 +756,8 @@ static void timekeeping_resume(void) + timekeeper.ntp_error = 0; + timekeeping_suspended = 0; + timekeeping_update(false); +- write_sequnlock_irqrestore(&timekeeper.lock, flags); ++ write_seqcount_end(&timekeeper.seq); ++ raw_spin_unlock_irqrestore(&timekeeper.lock, flags); + + touch_softlockup_watchdog(); + +@@ -760,7 +775,8 @@ static int timekeeping_suspend(void) + + read_persistent_clock(&timekeeping_suspend_time); + +- write_seqlock_irqsave(&timekeeper.lock, flags); ++ raw_spin_lock_irqsave(&timekeeper.lock, flags); ++ write_seqcount_begin(&timekeeper.seq); + timekeeping_forward_now(); + timekeeping_suspended = 1; + +@@ -783,7 +799,8 @@ static int timekeeping_suspend(void) + timekeeping_suspend_time = + timespec_add(timekeeping_suspend_time, delta_delta); + } +- write_sequnlock_irqrestore(&timekeeper.lock, flags); ++ write_seqcount_end(&timekeeper.seq); ++ raw_spin_unlock_irqrestore(&timekeeper.lock, flags); + + clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); + clocksource_suspend(); +@@ -1046,7 +1063,8 @@ static void update_wall_time(void) + unsigned int clock_set = 0; + unsigned long flags; + +- write_seqlock_irqsave(&timekeeper.lock, flags); ++ raw_spin_lock_irqsave(&timekeeper.lock, flags); ++ write_seqcount_begin(&timekeeper.seq); + + /* Make sure we're fully resumed: */ + if (unlikely(timekeeping_suspended)) +@@ -1139,7 +1157,8 @@ static void update_wall_time(void) + timekeeping_update(false); + + out: +- write_sequnlock_irqrestore(&timekeeper.lock, flags); ++ write_seqcount_end(&timekeeper.seq); ++ raw_spin_unlock_irqrestore(&timekeeper.lock, flags); + + if (clock_set) + clock_was_set_delayed(); +@@ -1188,13 +1207,13 @@ void get_monotonic_boottime(struct times + WARN_ON(timekeeping_suspended); + + do { +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + *ts = timekeeper.xtime; + tomono = timekeeper.wall_to_monotonic; + sleep = timekeeper.total_sleep_time; + nsecs = timekeeping_get_ns(); + +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + + set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec, + (s64)ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs); +@@ -1245,10 +1264,10 @@ struct timespec current_kernel_time(void + unsigned long seq; + + do { +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + + now = timekeeper.xtime; +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + + return now; + } +@@ -1260,11 +1279,11 @@ struct timespec get_monotonic_coarse(voi + unsigned long seq; + + do { +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + + now = timekeeper.xtime; + mono = timekeeper.wall_to_monotonic; +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + + set_normalized_timespec(&now, now.tv_sec + mono.tv_sec, + now.tv_nsec + mono.tv_nsec); +@@ -1296,11 +1315,11 @@ void get_xtime_and_monotonic_and_sleep_o + unsigned long seq; + + do { +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + *xtim = timekeeper.xtime; + *wtom = timekeeper.wall_to_monotonic; + *sleep = timekeeper.total_sleep_time; +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + } + + #ifdef CONFIG_HIGH_RES_TIMERS +@@ -1319,7 +1338,7 @@ ktime_t ktime_get_update_offsets(ktime_t + u64 secs, nsecs; + + do { +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + + secs = timekeeper.xtime.tv_sec; + nsecs = timekeeper.xtime.tv_nsec; +@@ -1329,7 +1348,7 @@ ktime_t ktime_get_update_offsets(ktime_t + + *offs_real = timekeeper.offs_real; + *offs_boot = timekeeper.offs_boot; +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + + now = ktime_add_ns(ktime_set(secs, 0), nsecs); + now = ktime_sub(now, *offs_real); +@@ -1346,9 +1365,9 @@ ktime_t ktime_get_monotonic_offset(void) + struct timespec wtom; + + do { +- seq = read_seqbegin(&timekeeper.lock); ++ seq = read_seqcount_begin(&timekeeper.seq); + wtom = timekeeper.wall_to_monotonic; +- } while (read_seqretry(&timekeeper.lock, seq)); ++ } while (read_seqcount_retry(&timekeeper.seq, seq)); + + return timespec_to_ktime(wtom); + } +@@ -1363,7 +1382,9 @@ EXPORT_SYMBOL_GPL(ktime_get_monotonic_of + */ + void xtime_update(unsigned long ticks) + { +- write_seqlock(&xtime_lock); ++ raw_spin_lock(&xtime_lock); ++ write_seqcount_begin(&xtime_seq); + do_timer(ticks); +- write_sequnlock(&xtime_lock); ++ write_seqcount_end(&xtime_seq); ++ raw_spin_unlock(&xtime_lock); + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/timer.c sun8i-rt/kernel/timer.c +--- sun8i/kernel/timer.c 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/kernel/timer.c 2016-08-22 18:16:46.624291470 +0200 +@@ -76,6 +76,9 @@ struct tvec_root { + struct tvec_base { + spinlock_t lock; + struct timer_list *running_timer; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ wait_queue_head_t wait_for_running_timer; ++#endif + unsigned long timer_jiffies; + unsigned long next_timer; + struct tvec_root tv1; +@@ -703,6 +706,36 @@ static struct tvec_base *lock_timer_base + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL ++static inline struct tvec_base *switch_timer_base(struct timer_list *timer, ++ struct tvec_base *old, ++ struct tvec_base *new) ++{ ++ /* See the comment in lock_timer_base() */ ++ timer_set_base(timer, NULL); ++ spin_unlock(&old->lock); ++ spin_lock(&new->lock); ++ timer_set_base(timer, new); ++ return new; ++} ++#else ++static inline struct tvec_base *switch_timer_base(struct timer_list *timer, ++ struct tvec_base *old, ++ struct tvec_base *new) ++{ ++ /* ++ * We cannot do the above because we might be preempted and ++ * then the preempter would see NULL and loop forever. ++ */ ++ if (spin_trylock(&new->lock)) { ++ timer_set_base(timer, new); ++ spin_unlock(&old->lock); ++ return new; ++ } ++ return old; ++} ++#endif ++ + static inline int + __mod_timer(struct timer_list *timer, unsigned long expires, + bool pending_only, int pinned) +@@ -729,12 +762,15 @@ __mod_timer(struct timer_list *timer, un + + debug_activate(timer, expires); + ++ preempt_disable_rt(); + cpu = smp_processor_id(); + + #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) + if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) + cpu = get_nohz_timer_target(); + #endif ++ preempt_enable_rt(); ++ + new_base = per_cpu(tvec_bases, cpu); + + if (base != new_base) { +@@ -745,14 +781,8 @@ __mod_timer(struct timer_list *timer, un + * handler yet has not finished. This also guarantees that + * the timer is serialized wrt itself. + */ +- if (likely(base->running_timer != timer)) { +- /* See the comment in lock_timer_base() */ +- timer_set_base(timer, NULL); +- spin_unlock(&base->lock); +- base = new_base; +- spin_lock(&base->lock); +- timer_set_base(timer, base); +- } ++ if (likely(base->running_timer != timer)) ++ base = switch_timer_base(timer, base, new_base); + } + + timer->expires = expires; +@@ -935,6 +965,29 @@ void add_timer_on(struct timer_list *tim + } + EXPORT_SYMBOL_GPL(add_timer_on); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * Wait for a running timer ++ */ ++static void wait_for_running_timer(struct timer_list *timer) ++{ ++ struct tvec_base *base = timer->base; ++ ++ if (base->running_timer == timer) ++ wait_event(base->wait_for_running_timer, ++ base->running_timer != timer); ++} ++ ++# define wakeup_timer_waiters(b) wake_up(&(b)->wait_for_running_timer) ++#else ++static inline void wait_for_running_timer(struct timer_list *timer) ++{ ++ cpu_relax(); ++} ++ ++# define wakeup_timer_waiters(b) do { } while (0) ++#endif ++ + /** + * del_timer - deactive a timer. + * @timer: the timer to be deactivated +@@ -1007,7 +1060,7 @@ out: + } + EXPORT_SYMBOL(try_to_del_timer_sync); + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + /** + * del_timer_sync - deactivate a timer and wait for the handler to finish. + * @timer: the timer to be deactivated +@@ -1067,7 +1120,7 @@ int del_timer_sync(struct timer_list *ti + int ret = try_to_del_timer_sync(timer); + if (ret >= 0) + return ret; +- cpu_relax(); ++ wait_for_running_timer(timer); + } + } + EXPORT_SYMBOL(del_timer_sync); +@@ -1178,10 +1231,11 @@ static inline void __run_timers(struct t + + spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn, data); ++ base->running_timer = NULL; + spin_lock_irq(&base->lock); + } + } +- base->running_timer = NULL; ++ wakeup_timer_waiters(base); + spin_unlock_irq(&base->lock); + } + +@@ -1320,6 +1374,23 @@ unsigned long get_next_timer_interrupt(u + */ + if (cpu_is_offline(smp_processor_id())) + return now + NEXT_TIMER_MAX_DELTA; ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * On PREEMPT_RT we cannot sleep here. If the trylock does not ++ * succeed then we return the worst-case 'expires in 1 tick' ++ * value. We use the rt functions here directly to avoid a ++ * migrate_disable() call. ++ */ ++ if (spin_do_trylock(&base->lock)) { ++ if (time_before_eq(base->next_timer, base->timer_jiffies)) ++ base->next_timer = __next_timer_interrupt(base); ++ expires = base->next_timer; ++ rt_spin_unlock_after_trylock_in_irq(&base->lock); ++ } else { ++ expires = now + 1; ++ } ++#else + spin_lock(&base->lock); + if (time_before_eq(base->next_timer, base->timer_jiffies)) + base->next_timer = __next_timer_interrupt(base); +@@ -1328,7 +1399,7 @@ unsigned long get_next_timer_interrupt(u + + if (time_before_eq(expires, now)) + return now; +- ++#endif + return cmp_next_hrtimer_event(now, expires); + } + #endif +@@ -1344,14 +1415,13 @@ void update_process_times(int user_tick) + + /* Note: this timer irq context must be accounted for as well. */ + account_process_tick(p, user_tick); ++ scheduler_tick(); + run_local_timers(); + rcu_check_callbacks(cpu, user_tick); +- printk_tick(); +-#ifdef CONFIG_IRQ_WORK ++#if defined(CONFIG_IRQ_WORK) && !defined(CONFIG_PREEMPT_RT_FULL) + if (in_irq()) + irq_work_run(); + #endif +- scheduler_tick(); + run_posix_cpu_timers(p); + } + +@@ -1362,6 +1432,11 @@ static void run_timer_softirq(struct sof + { + struct tvec_base *base = __this_cpu_read(tvec_bases); + ++#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) ++ irq_work_run(); ++#endif ++ ++ printk_tick(); + hrtimer_run_pending(); + + if (time_after_eq(jiffies, base->timer_jiffies)) +@@ -1683,12 +1758,14 @@ static int __cpuinit init_timers_cpu(int + base = &boot_tvec_bases; + } + spin_lock_init(&base->lock); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ init_waitqueue_head(&base->wait_for_running_timer); ++#endif + tvec_base_done[cpu] = 1; + } else { + base = per_cpu(tvec_bases, cpu); + } + +- + for (j = 0; j < TVN_SIZE; j++) { + INIT_LIST_HEAD(base->tv5.vec + j); + INIT_LIST_HEAD(base->tv4.vec + j); +@@ -1727,7 +1804,7 @@ static void __cpuinit migrate_timers(int + + BUG_ON(cpu_online(cpu)); + old_base = per_cpu(tvec_bases, cpu); +- new_base = get_cpu_var(tvec_bases); ++ new_base = get_local_var(tvec_bases); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. +@@ -1748,7 +1825,7 @@ static void __cpuinit migrate_timers(int + + spin_unlock(&old_base->lock); + spin_unlock_irq(&new_base->lock); +- put_cpu_var(tvec_bases); ++ put_local_var(tvec_bases); + } + #endif /* CONFIG_HOTPLUG_CPU */ + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/trace/Kconfig sun8i-rt/kernel/trace/Kconfig +--- sun8i/kernel/trace/Kconfig 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/trace/Kconfig 2016-08-22 16:23:25.128213274 +0200 +@@ -195,6 +195,24 @@ config IRQSOFF_TRACER + enabled. This option and the preempt-off timing option can be + used together or separately.) + ++config INTERRUPT_OFF_HIST ++ bool "Interrupts-off Latency Histogram" ++ depends on IRQSOFF_TRACER ++ help ++ This option generates continuously updated histograms (one per cpu) ++ of the duration of time periods with interrupts disabled. The ++ histograms are disabled by default. To enable them, write a non-zero ++ number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff ++ ++ If PREEMPT_OFF_HIST is also selected, additional histograms (one ++ per cpu) are generated that accumulate the duration of time periods ++ when both interrupts and preemption are disabled. The histogram data ++ will be located in the debug file system at ++ ++ /sys/kernel/debug/tracing/latency_hist/irqsoff ++ + config PREEMPT_TRACER + bool "Preemption-off Latency Tracer" + default n +@@ -217,6 +235,24 @@ config PREEMPT_TRACER + enabled. This option and the irqs-off timing option can be + used together or separately.) + ++config PREEMPT_OFF_HIST ++ bool "Preemption-off Latency Histogram" ++ depends on PREEMPT_TRACER ++ help ++ This option generates continuously updated histograms (one per cpu) ++ of the duration of time periods with preemption disabled. The ++ histograms are disabled by default. To enable them, write a non-zero ++ number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff ++ ++ If INTERRUPT_OFF_HIST is also selected, additional histograms (one ++ per cpu) are generated that accumulate the duration of time periods ++ when both interrupts and preemption are disabled. The histogram data ++ will be located in the debug file system at ++ ++ /sys/kernel/debug/tracing/latency_hist/preemptoff ++ + config SCHED_TRACER + bool "Scheduling Latency Tracer" + select GENERIC_TRACER +@@ -226,6 +262,74 @@ config SCHED_TRACER + This tracer tracks the latency of the highest priority task + to be scheduled in, starting from the point it has woken up. + ++config WAKEUP_LATENCY_HIST ++ bool "Scheduling Latency Histogram" ++ depends on SCHED_TRACER ++ help ++ This option generates continuously updated histograms (one per cpu) ++ of the scheduling latency of the highest priority task. ++ The histograms are disabled by default. To enable them, write a ++ non-zero number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/wakeup ++ ++ Two different algorithms are used, one to determine the latency of ++ processes that exclusively use the highest priority of the system and ++ another one to determine the latency of processes that share the ++ highest system priority with other processes. The former is used to ++ improve hardware and system software, the latter to optimize the ++ priority design of a given system. The histogram data will be ++ located in the debug file system at ++ ++ /sys/kernel/debug/tracing/latency_hist/wakeup ++ ++ and ++ ++ /sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio ++ ++ If both Scheduling Latency Histogram and Missed Timer Offsets ++ Histogram are selected, additional histogram data will be collected ++ that contain, in addition to the wakeup latency, the timer latency, in ++ case the wakeup was triggered by an expired timer. These histograms ++ are available in the ++ ++ /sys/kernel/debug/tracing/latency_hist/timerandwakeup ++ ++ directory. They reflect the apparent interrupt and scheduling latency ++ and are best suitable to determine the worst-case latency of a given ++ system. To enable these histograms, write a non-zero number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup ++ ++config MISSED_TIMER_OFFSETS_HIST ++ depends on HIGH_RES_TIMERS ++ select GENERIC_TRACER ++ bool "Missed Timer Offsets Histogram" ++ help ++ Generate a histogram of missed timer offsets in microseconds. The ++ histograms are disabled by default. To enable them, write a non-zero ++ number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/missed_timer_offsets ++ ++ The histogram data will be located in the debug file system at ++ ++ /sys/kernel/debug/tracing/latency_hist/missed_timer_offsets ++ ++ If both Scheduling Latency Histogram and Missed Timer Offsets ++ Histogram are selected, additional histogram data will be collected ++ that contain, in addition to the wakeup latency, the timer latency, in ++ case the wakeup was triggered by an expired timer. These histograms ++ are available in the ++ ++ /sys/kernel/debug/tracing/latency_hist/timerandwakeup ++ ++ directory. They reflect the apparent interrupt and scheduling latency ++ and are best suitable to determine the worst-case latency of a given ++ system. To enable these histograms, write a non-zero number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup ++ + config ENABLE_DEFAULT_TRACERS + bool "Trace process context switches and events" + depends on !GENERIC_TRACER +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/trace/latency_hist.c sun8i-rt/kernel/trace/latency_hist.c +--- sun8i/kernel/trace/latency_hist.c 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/kernel/trace/latency_hist.c 2016-08-22 18:28:58.120299879 +0200 +@@ -0,0 +1,1176 @@ ++/* ++ * kernel/trace/latency_hist.c ++ * ++ * Add support for histograms of preemption-off latency and ++ * interrupt-off latency and wakeup latency, it depends on ++ * Real-Time Preemption Support. ++ * ++ * Copyright (C) 2005 MontaVista Software, Inc. ++ * Yi Yang ++ * ++ * Converted to work with the new latency tracer. ++ * Copyright (C) 2008 Red Hat, Inc. ++ * Steven Rostedt ++ * ++ */ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#include "trace.h" ++#include ++ ++#define NSECS_PER_USECS 1000L ++ ++#define CREATE_TRACE_POINTS ++#include ++ ++enum { ++ IRQSOFF_LATENCY = 0, ++ PREEMPTOFF_LATENCY, ++ PREEMPTIRQSOFF_LATENCY, ++ WAKEUP_LATENCY, ++ WAKEUP_LATENCY_SHAREDPRIO, ++ MISSED_TIMER_OFFSETS, ++ TIMERANDWAKEUP_LATENCY, ++ MAX_LATENCY_TYPE, ++}; ++ ++#define MAX_ENTRY_NUM 10240 ++ ++struct hist_data { ++ atomic_t hist_mode; /* 0 log, 1 don't log */ ++ long offset; /* set it to MAX_ENTRY_NUM/2 for a bipolar scale */ ++ long min_lat; ++ long max_lat; ++ unsigned long long below_hist_bound_samples; ++ unsigned long long above_hist_bound_samples; ++ long long accumulate_lat; ++ unsigned long long total_samples; ++ unsigned long long hist_array[MAX_ENTRY_NUM]; ++}; ++ ++struct enable_data { ++ int latency_type; ++ int enabled; ++}; ++ ++static char *latency_hist_dir_root = "latency_hist"; ++ ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++static DEFINE_PER_CPU(struct hist_data, irqsoff_hist); ++static char *irqsoff_hist_dir = "irqsoff"; ++static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start); ++static DEFINE_PER_CPU(int, hist_irqsoff_counting); ++#endif ++ ++#ifdef CONFIG_PREEMPT_OFF_HIST ++static DEFINE_PER_CPU(struct hist_data, preemptoff_hist); ++static char *preemptoff_hist_dir = "preemptoff"; ++static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start); ++static DEFINE_PER_CPU(int, hist_preemptoff_counting); ++#endif ++ ++#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) ++static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist); ++static char *preemptirqsoff_hist_dir = "preemptirqsoff"; ++static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start); ++static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting); ++#endif ++ ++#if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST) ++static notrace void probe_preemptirqsoff_hist(void *v, int reason, int start); ++static struct enable_data preemptirqsoff_enabled_data = { ++ .latency_type = PREEMPTIRQSOFF_LATENCY, ++ .enabled = 0, ++}; ++#endif ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++struct maxlatproc_data { ++ char comm[FIELD_SIZEOF(struct task_struct, comm)]; ++ char current_comm[FIELD_SIZEOF(struct task_struct, comm)]; ++ int pid; ++ int current_pid; ++ int prio; ++ int current_prio; ++ long latency; ++ long timeroffset; ++ cycle_t timestamp; ++}; ++#endif ++ ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist); ++static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio); ++static char *wakeup_latency_hist_dir = "wakeup"; ++static char *wakeup_latency_hist_dir_sharedprio = "sharedprio"; ++static notrace void probe_wakeup_latency_hist_start(void *v, ++ struct task_struct *p); ++static notrace void probe_wakeup_latency_hist_stop(void *v, ++ struct task_struct *prev, struct task_struct *next); ++static notrace void probe_sched_migrate_task(void *, ++ struct task_struct *task, int cpu); ++static struct enable_data wakeup_latency_enabled_data = { ++ .latency_type = WAKEUP_LATENCY, ++ .enabled = 0, ++}; ++static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc); ++static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc_sharedprio); ++static DEFINE_PER_CPU(struct task_struct *, wakeup_task); ++static DEFINE_PER_CPU(int, wakeup_sharedprio); ++static unsigned long wakeup_pid; ++#endif ++ ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++static DEFINE_PER_CPU(struct hist_data, missed_timer_offsets); ++static char *missed_timer_offsets_dir = "missed_timer_offsets"; ++static notrace void probe_hrtimer_interrupt(void *v, int cpu, ++ long long offset, struct task_struct *curr, struct task_struct *task); ++static struct enable_data missed_timer_offsets_enabled_data = { ++ .latency_type = MISSED_TIMER_OFFSETS, ++ .enabled = 0, ++}; ++static DEFINE_PER_CPU(struct maxlatproc_data, missed_timer_offsets_maxlatproc); ++static unsigned long missed_timer_offsets_pid; ++#endif ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static DEFINE_PER_CPU(struct hist_data, timerandwakeup_latency_hist); ++static char *timerandwakeup_latency_hist_dir = "timerandwakeup"; ++static struct enable_data timerandwakeup_enabled_data = { ++ .latency_type = TIMERANDWAKEUP_LATENCY, ++ .enabled = 0, ++}; ++static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc); ++#endif ++ ++void notrace latency_hist(int latency_type, int cpu, long latency, ++ long timeroffset, cycle_t stop, ++ struct task_struct *p) ++{ ++ struct hist_data *my_hist; ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ struct maxlatproc_data *mp = NULL; ++#endif ++ ++ if (cpu < 0 || cpu >= NR_CPUS || latency_type < 0 || ++ latency_type >= MAX_LATENCY_TYPE) ++ return; ++ ++ switch (latency_type) { ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ case IRQSOFF_LATENCY: ++ my_hist = &per_cpu(irqsoff_hist, cpu); ++ break; ++#endif ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ case PREEMPTOFF_LATENCY: ++ my_hist = &per_cpu(preemptoff_hist, cpu); ++ break; ++#endif ++#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) ++ case PREEMPTIRQSOFF_LATENCY: ++ my_hist = &per_cpu(preemptirqsoff_hist, cpu); ++ break; ++#endif ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ case WAKEUP_LATENCY: ++ my_hist = &per_cpu(wakeup_latency_hist, cpu); ++ mp = &per_cpu(wakeup_maxlatproc, cpu); ++ break; ++ case WAKEUP_LATENCY_SHAREDPRIO: ++ my_hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); ++ mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); ++ break; ++#endif ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ case MISSED_TIMER_OFFSETS: ++ my_hist = &per_cpu(missed_timer_offsets, cpu); ++ mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); ++ break; ++#endif ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ case TIMERANDWAKEUP_LATENCY: ++ my_hist = &per_cpu(timerandwakeup_latency_hist, cpu); ++ mp = &per_cpu(timerandwakeup_maxlatproc, cpu); ++ break; ++#endif ++ ++ default: ++ return; ++ } ++ ++ latency += my_hist->offset; ++ ++ if (atomic_read(&my_hist->hist_mode) == 0) ++ return; ++ ++ if (latency < 0 || latency >= MAX_ENTRY_NUM) { ++ if (latency < 0) ++ my_hist->below_hist_bound_samples++; ++ else ++ my_hist->above_hist_bound_samples++; ++ } else ++ my_hist->hist_array[latency]++; ++ ++ if (unlikely(latency > my_hist->max_lat || ++ my_hist->min_lat == LONG_MAX)) { ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ if (latency_type == WAKEUP_LATENCY || ++ latency_type == WAKEUP_LATENCY_SHAREDPRIO || ++ latency_type == MISSED_TIMER_OFFSETS || ++ latency_type == TIMERANDWAKEUP_LATENCY) { ++ strncpy(mp->comm, p->comm, sizeof(mp->comm)); ++ strncpy(mp->current_comm, current->comm, ++ sizeof(mp->current_comm)); ++ mp->pid = task_pid_nr(p); ++ mp->current_pid = task_pid_nr(current); ++ mp->prio = p->prio; ++ mp->current_prio = current->prio; ++ mp->latency = latency; ++ mp->timeroffset = timeroffset; ++ mp->timestamp = stop; ++ } ++#endif ++ my_hist->max_lat = latency; ++ } ++ if (unlikely(latency < my_hist->min_lat)) ++ my_hist->min_lat = latency; ++ my_hist->total_samples++; ++ my_hist->accumulate_lat += latency; ++} ++ ++static void *l_start(struct seq_file *m, loff_t *pos) ++{ ++ loff_t *index_ptr = NULL; ++ loff_t index = *pos; ++ struct hist_data *my_hist = m->private; ++ ++ if (index == 0) { ++ char minstr[32], avgstr[32], maxstr[32]; ++ ++ atomic_dec(&my_hist->hist_mode); ++ ++ if (likely(my_hist->total_samples)) { ++ long avg = (long) div64_s64(my_hist->accumulate_lat, ++ my_hist->total_samples); ++ snprintf(minstr, sizeof(minstr), "%ld", ++ my_hist->min_lat - my_hist->offset); ++ snprintf(avgstr, sizeof(avgstr), "%ld", ++ avg - my_hist->offset); ++ snprintf(maxstr, sizeof(maxstr), "%ld", ++ my_hist->max_lat - my_hist->offset); ++ } else { ++ strcpy(minstr, ""); ++ strcpy(avgstr, minstr); ++ strcpy(maxstr, minstr); ++ } ++ ++ seq_printf(m, "#Minimum latency: %s microseconds\n" ++ "#Average latency: %s microseconds\n" ++ "#Maximum latency: %s microseconds\n" ++ "#Total samples: %llu\n" ++ "#There are %llu samples lower than %ld" ++ " microseconds.\n" ++ "#There are %llu samples greater or equal" ++ " than %ld microseconds.\n" ++ "#usecs\t%16s\n", ++ minstr, avgstr, maxstr, ++ my_hist->total_samples, ++ my_hist->below_hist_bound_samples, ++ -my_hist->offset, ++ my_hist->above_hist_bound_samples, ++ MAX_ENTRY_NUM - my_hist->offset, ++ "samples"); ++ } ++ if (index < MAX_ENTRY_NUM) { ++ index_ptr = kmalloc(sizeof(loff_t), GFP_KERNEL); ++ if (index_ptr) ++ *index_ptr = index; ++ } ++ ++ return index_ptr; ++} ++ ++static void *l_next(struct seq_file *m, void *p, loff_t *pos) ++{ ++ loff_t *index_ptr = p; ++ struct hist_data *my_hist = m->private; ++ ++ if (++*pos >= MAX_ENTRY_NUM) { ++ atomic_inc(&my_hist->hist_mode); ++ return NULL; ++ } ++ *index_ptr = *pos; ++ return index_ptr; ++} ++ ++static void l_stop(struct seq_file *m, void *p) ++{ ++ kfree(p); ++} ++ ++static int l_show(struct seq_file *m, void *p) ++{ ++ int index = *(loff_t *) p; ++ struct hist_data *my_hist = m->private; ++ ++ seq_printf(m, "%6ld\t%16llu\n", index - my_hist->offset, ++ my_hist->hist_array[index]); ++ return 0; ++} ++ ++static struct seq_operations latency_hist_seq_op = { ++ .start = l_start, ++ .next = l_next, ++ .stop = l_stop, ++ .show = l_show ++}; ++ ++static int latency_hist_open(struct inode *inode, struct file *file) ++{ ++ int ret; ++ ++ ret = seq_open(file, &latency_hist_seq_op); ++ if (!ret) { ++ struct seq_file *seq = file->private_data; ++ seq->private = inode->i_private; ++ } ++ return ret; ++} ++ ++static struct file_operations latency_hist_fops = { ++ .open = latency_hist_open, ++ .read = seq_read, ++ .llseek = seq_lseek, ++ .release = seq_release, ++}; ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static void clear_maxlatprocdata(struct maxlatproc_data *mp) ++{ ++ mp->comm[0] = mp->current_comm[0] = '\0'; ++ mp->prio = mp->current_prio = mp->pid = mp->current_pid = ++ mp->latency = mp->timeroffset = -1; ++ mp->timestamp = 0; ++} ++#endif ++ ++static void hist_reset(struct hist_data *hist) ++{ ++ atomic_dec(&hist->hist_mode); ++ ++ memset(hist->hist_array, 0, sizeof(hist->hist_array)); ++ hist->below_hist_bound_samples = 0ULL; ++ hist->above_hist_bound_samples = 0ULL; ++ hist->min_lat = LONG_MAX; ++ hist->max_lat = LONG_MIN; ++ hist->total_samples = 0ULL; ++ hist->accumulate_lat = 0LL; ++ ++ atomic_inc(&hist->hist_mode); ++} ++ ++static ssize_t ++latency_hist_reset(struct file *file, const char __user *a, ++ size_t size, loff_t *off) ++{ ++ int cpu; ++ struct hist_data *hist = NULL; ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ struct maxlatproc_data *mp = NULL; ++#endif ++ off_t latency_type = (off_t) file->private_data; ++ ++ for_each_online_cpu(cpu) { ++ ++ switch (latency_type) { ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ case PREEMPTOFF_LATENCY: ++ hist = &per_cpu(preemptoff_hist, cpu); ++ break; ++#endif ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ case IRQSOFF_LATENCY: ++ hist = &per_cpu(irqsoff_hist, cpu); ++ break; ++#endif ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ case PREEMPTIRQSOFF_LATENCY: ++ hist = &per_cpu(preemptirqsoff_hist, cpu); ++ break; ++#endif ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ case WAKEUP_LATENCY: ++ hist = &per_cpu(wakeup_latency_hist, cpu); ++ mp = &per_cpu(wakeup_maxlatproc, cpu); ++ break; ++ case WAKEUP_LATENCY_SHAREDPRIO: ++ hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); ++ mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); ++ break; ++#endif ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ case MISSED_TIMER_OFFSETS: ++ hist = &per_cpu(missed_timer_offsets, cpu); ++ mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); ++ break; ++#endif ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ case TIMERANDWAKEUP_LATENCY: ++ hist = &per_cpu(timerandwakeup_latency_hist, cpu); ++ mp = &per_cpu(timerandwakeup_maxlatproc, cpu); ++ break; ++#endif ++ } ++ ++ hist_reset(hist); ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ if (latency_type == WAKEUP_LATENCY || ++ latency_type == WAKEUP_LATENCY_SHAREDPRIO || ++ latency_type == MISSED_TIMER_OFFSETS || ++ latency_type == TIMERANDWAKEUP_LATENCY) ++ clear_maxlatprocdata(mp); ++#endif ++ } ++ ++ return size; ++} ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static ssize_t ++show_pid(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) ++{ ++ char buf[64]; ++ int r; ++ unsigned long *this_pid = file->private_data; ++ ++ r = snprintf(buf, sizeof(buf), "%lu\n", *this_pid); ++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); ++} ++ ++static ssize_t do_pid(struct file *file, const char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ char buf[64]; ++ unsigned long pid; ++ unsigned long *this_pid = file->private_data; ++ ++ if (cnt >= sizeof(buf)) ++ return -EINVAL; ++ ++ if (copy_from_user(&buf, ubuf, cnt)) ++ return -EFAULT; ++ ++ buf[cnt] = '\0'; ++ ++ if (strict_strtoul(buf, 10, &pid)) ++ return(-EINVAL); ++ ++ *this_pid = pid; ++ ++ return cnt; ++} ++#endif ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static ssize_t ++show_maxlatproc(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) ++{ ++ int r; ++ struct maxlatproc_data *mp = file->private_data; ++ int strmaxlen = (TASK_COMM_LEN * 2) + (8 * 8); ++ unsigned long long t; ++ unsigned long usecs, secs; ++ char *buf; ++ ++ if (mp->pid == -1 || mp->current_pid == -1) { ++ buf = "(none)\n"; ++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, ++ strlen(buf)); ++ } ++ ++ buf = kmalloc(strmaxlen, GFP_KERNEL); ++ if (buf == NULL) ++ return -ENOMEM; ++ ++ t = ns2usecs(mp->timestamp); ++ usecs = do_div(t, USEC_PER_SEC); ++ secs = (unsigned long) t; ++ r = snprintf(buf, strmaxlen, ++ "%d %d %ld (%ld) %s <- %d %d %s %lu.%06lu\n", mp->pid, ++ MAX_RT_PRIO-1 - mp->prio, mp->latency, mp->timeroffset, mp->comm, ++ mp->current_pid, MAX_RT_PRIO-1 - mp->current_prio, mp->current_comm, ++ secs, usecs); ++ r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); ++ kfree(buf); ++ return r; ++} ++#endif ++ ++static ssize_t ++show_enable(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) ++{ ++ char buf[64]; ++ struct enable_data *ed = file->private_data; ++ int r; ++ ++ r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled); ++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); ++} ++ ++static ssize_t ++do_enable(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) ++{ ++ char buf[64]; ++ long enable; ++ struct enable_data *ed = file->private_data; ++ ++ if (cnt >= sizeof(buf)) ++ return -EINVAL; ++ ++ if (copy_from_user(&buf, ubuf, cnt)) ++ return -EFAULT; ++ ++ buf[cnt] = 0; ++ ++ if (strict_strtol(buf, 10, &enable)) ++ return(-EINVAL); ++ ++ if ((enable && ed->enabled) || (!enable && !ed->enabled)) ++ return cnt; ++ ++ if (enable) { ++ int ret; ++ ++ switch (ed->latency_type) { ++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) ++ case PREEMPTIRQSOFF_LATENCY: ++ ret = register_trace_preemptirqsoff_hist( ++ probe_preemptirqsoff_hist, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_preemptirqsoff_hist " ++ "to trace_preemptirqsoff_hist\n"); ++ return ret; ++ } ++ break; ++#endif ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ case WAKEUP_LATENCY: ++ ret = register_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_wakeup_latency_hist_start " ++ "to trace_sched_wakeup\n"); ++ return ret; ++ } ++ ret = register_trace_sched_wakeup_new( ++ probe_wakeup_latency_hist_start, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_wakeup_latency_hist_start " ++ "to trace_sched_wakeup_new\n"); ++ unregister_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ return ret; ++ } ++ ret = register_trace_sched_switch( ++ probe_wakeup_latency_hist_stop, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_wakeup_latency_hist_stop " ++ "to trace_sched_switch\n"); ++ unregister_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_wakeup_new( ++ probe_wakeup_latency_hist_start, NULL); ++ return ret; ++ } ++ ret = register_trace_sched_migrate_task( ++ probe_sched_migrate_task, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_sched_migrate_task " ++ "to trace_sched_migrate_task\n"); ++ unregister_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_wakeup_new( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_switch( ++ probe_wakeup_latency_hist_stop, NULL); ++ return ret; ++ } ++ break; ++#endif ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ case MISSED_TIMER_OFFSETS: ++ ret = register_trace_hrtimer_interrupt( ++ probe_hrtimer_interrupt, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_hrtimer_interrupt " ++ "to trace_hrtimer_interrupt\n"); ++ return ret; ++ } ++ break; ++#endif ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ case TIMERANDWAKEUP_LATENCY: ++ if (!wakeup_latency_enabled_data.enabled || ++ !missed_timer_offsets_enabled_data.enabled) ++ return -EINVAL; ++ break; ++#endif ++ default: ++ break; ++ } ++ } else { ++ switch (ed->latency_type) { ++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) ++ case PREEMPTIRQSOFF_LATENCY: ++ { ++ int cpu; ++ ++ unregister_trace_preemptirqsoff_hist( ++ probe_preemptirqsoff_hist, NULL); ++ for_each_online_cpu(cpu) { ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ per_cpu(hist_irqsoff_counting, ++ cpu) = 0; ++#endif ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ per_cpu(hist_preemptoff_counting, ++ cpu) = 0; ++#endif ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ per_cpu(hist_preemptirqsoff_counting, ++ cpu) = 0; ++#endif ++ } ++ } ++ break; ++#endif ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ case WAKEUP_LATENCY: ++ { ++ int cpu; ++ ++ unregister_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_wakeup_new( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_switch( ++ probe_wakeup_latency_hist_stop, NULL); ++ unregister_trace_sched_migrate_task( ++ probe_sched_migrate_task, NULL); ++ ++ for_each_online_cpu(cpu) { ++ per_cpu(wakeup_task, cpu) = NULL; ++ per_cpu(wakeup_sharedprio, cpu) = 0; ++ } ++ } ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ timerandwakeup_enabled_data.enabled = 0; ++#endif ++ break; ++#endif ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ case MISSED_TIMER_OFFSETS: ++ unregister_trace_hrtimer_interrupt( ++ probe_hrtimer_interrupt, NULL); ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ timerandwakeup_enabled_data.enabled = 0; ++#endif ++ break; ++#endif ++ default: ++ break; ++ } ++ } ++ ed->enabled = enable; ++ return cnt; ++} ++ ++static const struct file_operations latency_hist_reset_fops = { ++ .open = tracing_open_generic, ++ .write = latency_hist_reset, ++}; ++ ++static const struct file_operations enable_fops = { ++ .open = tracing_open_generic, ++ .read = show_enable, ++ .write = do_enable, ++}; ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static const struct file_operations pid_fops = { ++ .open = tracing_open_generic, ++ .read = show_pid, ++ .write = do_pid, ++}; ++ ++static const struct file_operations maxlatproc_fops = { ++ .open = tracing_open_generic, ++ .read = show_maxlatproc, ++}; ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) ++static notrace void probe_preemptirqsoff_hist(void *v, int reason, ++ int starthist) ++{ ++ int cpu = raw_smp_processor_id(); ++ int time_set = 0; ++ ++ if (starthist) { ++ cycle_t uninitialized_var(start); ++ ++ if (!preempt_count() && !irqs_disabled()) ++ return; ++ ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ if ((reason == IRQS_OFF || reason == TRACE_START) && ++ !per_cpu(hist_irqsoff_counting, cpu)) { ++ per_cpu(hist_irqsoff_counting, cpu) = 1; ++ start = ftrace_now(cpu); ++ time_set++; ++ per_cpu(hist_irqsoff_start, cpu) = start; ++ } ++#endif ++ ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ if ((reason == PREEMPT_OFF || reason == TRACE_START) && ++ !per_cpu(hist_preemptoff_counting, cpu)) { ++ per_cpu(hist_preemptoff_counting, cpu) = 1; ++ if (!(time_set++)) ++ start = ftrace_now(cpu); ++ per_cpu(hist_preemptoff_start, cpu) = start; ++ } ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ if (per_cpu(hist_irqsoff_counting, cpu) && ++ per_cpu(hist_preemptoff_counting, cpu) && ++ !per_cpu(hist_preemptirqsoff_counting, cpu)) { ++ per_cpu(hist_preemptirqsoff_counting, cpu) = 1; ++ if (!time_set) ++ start = ftrace_now(cpu); ++ per_cpu(hist_preemptirqsoff_start, cpu) = start; ++ } ++#endif ++ } else { ++ cycle_t uninitialized_var(stop); ++ ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ if ((reason == IRQS_ON || reason == TRACE_STOP) && ++ per_cpu(hist_irqsoff_counting, cpu)) { ++ cycle_t start = per_cpu(hist_irqsoff_start, cpu); ++ ++ stop = ftrace_now(cpu); ++ time_set++; ++ if (start) { ++ long latency = ((long) (stop - start)) / ++ NSECS_PER_USECS; ++ ++ latency_hist(IRQSOFF_LATENCY, cpu, latency, 0, ++ stop, NULL); ++ } ++ per_cpu(hist_irqsoff_counting, cpu) = 0; ++ } ++#endif ++ ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ if ((reason == PREEMPT_ON || reason == TRACE_STOP) && ++ per_cpu(hist_preemptoff_counting, cpu)) { ++ cycle_t start = per_cpu(hist_preemptoff_start, cpu); ++ ++ if (!(time_set++)) ++ stop = ftrace_now(cpu); ++ if (start) { ++ long latency = ((long) (stop - start)) / ++ NSECS_PER_USECS; ++ ++ latency_hist(PREEMPTOFF_LATENCY, cpu, latency, ++ 0, stop, NULL); ++ } ++ per_cpu(hist_preemptoff_counting, cpu) = 0; ++ } ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ if ((!per_cpu(hist_irqsoff_counting, cpu) || ++ !per_cpu(hist_preemptoff_counting, cpu)) && ++ per_cpu(hist_preemptirqsoff_counting, cpu)) { ++ cycle_t start = per_cpu(hist_preemptirqsoff_start, cpu); ++ ++ if (!time_set) ++ stop = ftrace_now(cpu); ++ if (start) { ++ long latency = ((long) (stop - start)) / ++ NSECS_PER_USECS; ++ ++ latency_hist(PREEMPTIRQSOFF_LATENCY, cpu, ++ latency, 0, stop, NULL); ++ } ++ per_cpu(hist_preemptirqsoff_counting, cpu) = 0; ++ } ++#endif ++ } ++} ++#endif ++ ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++static DEFINE_RAW_SPINLOCK(wakeup_lock); ++static notrace void probe_sched_migrate_task(void *v, struct task_struct *task, ++ int cpu) ++{ ++ int old_cpu = task_cpu(task); ++ ++ if (cpu != old_cpu) { ++ unsigned long flags; ++ struct task_struct *cpu_wakeup_task; ++ ++ raw_spin_lock_irqsave(&wakeup_lock, flags); ++ ++ cpu_wakeup_task = per_cpu(wakeup_task, old_cpu); ++ if (task == cpu_wakeup_task) { ++ put_task_struct(cpu_wakeup_task); ++ per_cpu(wakeup_task, old_cpu) = NULL; ++ cpu_wakeup_task = per_cpu(wakeup_task, cpu) = task; ++ get_task_struct(cpu_wakeup_task); ++ } ++ ++ raw_spin_unlock_irqrestore(&wakeup_lock, flags); ++ } ++} ++ ++static notrace void probe_wakeup_latency_hist_start(void *v, ++ struct task_struct *p) ++{ ++ unsigned long flags; ++ struct task_struct *curr = current; ++ int cpu = task_cpu(p); ++ struct task_struct *cpu_wakeup_task; ++ ++ raw_spin_lock_irqsave(&wakeup_lock, flags); ++ ++ cpu_wakeup_task = per_cpu(wakeup_task, cpu); ++ ++ if (wakeup_pid) { ++ if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || ++ p->prio == curr->prio) ++ per_cpu(wakeup_sharedprio, cpu) = 1; ++ if (likely(wakeup_pid != task_pid_nr(p))) ++ goto out; ++ } else { ++ if (likely(!rt_task(p)) || ++ (cpu_wakeup_task && p->prio > cpu_wakeup_task->prio) || ++ p->prio > curr->prio) ++ goto out; ++ if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || ++ p->prio == curr->prio) ++ per_cpu(wakeup_sharedprio, cpu) = 1; ++ } ++ ++ if (cpu_wakeup_task) ++ put_task_struct(cpu_wakeup_task); ++ cpu_wakeup_task = per_cpu(wakeup_task, cpu) = p; ++ get_task_struct(cpu_wakeup_task); ++ cpu_wakeup_task->preempt_timestamp_hist = ++ ftrace_now(raw_smp_processor_id()); ++out: ++ raw_spin_unlock_irqrestore(&wakeup_lock, flags); ++} ++ ++static notrace void probe_wakeup_latency_hist_stop(void *v, ++ struct task_struct *prev, struct task_struct *next) ++{ ++ unsigned long flags; ++ int cpu = task_cpu(next); ++ long latency; ++ cycle_t stop; ++ struct task_struct *cpu_wakeup_task; ++ ++ raw_spin_lock_irqsave(&wakeup_lock, flags); ++ ++ cpu_wakeup_task = per_cpu(wakeup_task, cpu); ++ ++ if (cpu_wakeup_task == NULL) ++ goto out; ++ ++ /* Already running? */ ++ if (unlikely(current == cpu_wakeup_task)) ++ goto out_reset; ++ ++ if (next != cpu_wakeup_task) { ++ if (next->prio < cpu_wakeup_task->prio) ++ goto out_reset; ++ ++ if (next->prio == cpu_wakeup_task->prio) ++ per_cpu(wakeup_sharedprio, cpu) = 1; ++ ++ goto out; ++ } ++ ++ if (current->prio == cpu_wakeup_task->prio) ++ per_cpu(wakeup_sharedprio, cpu) = 1; ++ ++ /* ++ * The task we are waiting for is about to be switched to. ++ * Calculate latency and store it in histogram. ++ */ ++ stop = ftrace_now(raw_smp_processor_id()); ++ ++ latency = ((long) (stop - next->preempt_timestamp_hist)) / ++ NSECS_PER_USECS; ++ ++ if (per_cpu(wakeup_sharedprio, cpu)) { ++ latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop, ++ next); ++ per_cpu(wakeup_sharedprio, cpu) = 0; ++ } else { ++ latency_hist(WAKEUP_LATENCY, cpu, latency, 0, stop, next); ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ if (timerandwakeup_enabled_data.enabled) { ++ latency_hist(TIMERANDWAKEUP_LATENCY, cpu, ++ next->timer_offset + latency, next->timer_offset, ++ stop, next); ++ } ++#endif ++ } ++ ++out_reset: ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ next->timer_offset = 0; ++#endif ++ put_task_struct(cpu_wakeup_task); ++ per_cpu(wakeup_task, cpu) = NULL; ++out: ++ raw_spin_unlock_irqrestore(&wakeup_lock, flags); ++} ++#endif ++ ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++static notrace void probe_hrtimer_interrupt(void *v, int cpu, ++ long long latency_ns, struct task_struct *curr, struct task_struct *task) ++{ ++ if (latency_ns <= 0 && task != NULL && rt_task(task) && ++ (task->prio < curr->prio || ++ (task->prio == curr->prio && ++ !cpumask_test_cpu(cpu, &task->cpus_allowed)))) { ++ long latency; ++ cycle_t now; ++ ++ if (missed_timer_offsets_pid) { ++ if (likely(missed_timer_offsets_pid != ++ task_pid_nr(task))) ++ return; ++ } ++ ++ now = ftrace_now(cpu); ++ latency = (long) div_s64(-latency_ns, NSECS_PER_USECS); ++ latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now, ++ task); ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ task->timer_offset = latency; ++#endif ++ } ++} ++#endif ++ ++static __init int latency_hist_init(void) ++{ ++ struct dentry *latency_hist_root = NULL; ++ struct dentry *dentry; ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ struct dentry *dentry_sharedprio; ++#endif ++ struct dentry *entry; ++ struct dentry *enable_root; ++ int i = 0; ++ struct hist_data *my_hist; ++ char name[64]; ++ char *cpufmt = "CPU%d"; ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ char *cpufmt_maxlatproc = "max_latency-CPU%d"; ++ struct maxlatproc_data *mp = NULL; ++#endif ++ ++ dentry = tracing_init_dentry(); ++ latency_hist_root = debugfs_create_dir(latency_hist_dir_root, dentry); ++ enable_root = debugfs_create_dir("enable", latency_hist_root); ++ ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(irqsoff_hist, i), &latency_hist_fops); ++ my_hist = &per_cpu(irqsoff_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ } ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops); ++#endif ++ ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ dentry = debugfs_create_dir(preemptoff_hist_dir, ++ latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(preemptoff_hist, i), &latency_hist_fops); ++ my_hist = &per_cpu(preemptoff_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ } ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops); ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ dentry = debugfs_create_dir(preemptirqsoff_hist_dir, ++ latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops); ++ my_hist = &per_cpu(preemptirqsoff_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ } ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops); ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) ++ entry = debugfs_create_file("preemptirqsoff", 0644, ++ enable_root, (void *)&preemptirqsoff_enabled_data, ++ &enable_fops); ++#endif ++ ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ dentry = debugfs_create_dir(wakeup_latency_hist_dir, ++ latency_hist_root); ++ dentry_sharedprio = debugfs_create_dir( ++ wakeup_latency_hist_dir_sharedprio, dentry); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(wakeup_latency_hist, i), ++ &latency_hist_fops); ++ my_hist = &per_cpu(wakeup_latency_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ ++ entry = debugfs_create_file(name, 0444, dentry_sharedprio, ++ &per_cpu(wakeup_latency_hist_sharedprio, i), ++ &latency_hist_fops); ++ my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ ++ sprintf(name, cpufmt_maxlatproc, i); ++ ++ mp = &per_cpu(wakeup_maxlatproc, i); ++ entry = debugfs_create_file(name, 0444, dentry, mp, ++ &maxlatproc_fops); ++ clear_maxlatprocdata(mp); ++ ++ mp = &per_cpu(wakeup_maxlatproc_sharedprio, i); ++ entry = debugfs_create_file(name, 0444, dentry_sharedprio, mp, ++ &maxlatproc_fops); ++ clear_maxlatprocdata(mp); ++ } ++ entry = debugfs_create_file("pid", 0644, dentry, ++ (void *)&wakeup_pid, &pid_fops); ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)WAKEUP_LATENCY, &latency_hist_reset_fops); ++ entry = debugfs_create_file("reset", 0644, dentry_sharedprio, ++ (void *)WAKEUP_LATENCY_SHAREDPRIO, &latency_hist_reset_fops); ++ entry = debugfs_create_file("wakeup", 0644, ++ enable_root, (void *)&wakeup_latency_enabled_data, ++ &enable_fops); ++#endif ++ ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ dentry = debugfs_create_dir(missed_timer_offsets_dir, ++ latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(missed_timer_offsets, i), &latency_hist_fops); ++ my_hist = &per_cpu(missed_timer_offsets, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ ++ sprintf(name, cpufmt_maxlatproc, i); ++ mp = &per_cpu(missed_timer_offsets_maxlatproc, i); ++ entry = debugfs_create_file(name, 0444, dentry, mp, ++ &maxlatproc_fops); ++ clear_maxlatprocdata(mp); ++ } ++ entry = debugfs_create_file("pid", 0644, dentry, ++ (void *)&missed_timer_offsets_pid, &pid_fops); ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)MISSED_TIMER_OFFSETS, &latency_hist_reset_fops); ++ entry = debugfs_create_file("missed_timer_offsets", 0644, ++ enable_root, (void *)&missed_timer_offsets_enabled_data, ++ &enable_fops); ++#endif ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ dentry = debugfs_create_dir(timerandwakeup_latency_hist_dir, ++ latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(timerandwakeup_latency_hist, i), ++ &latency_hist_fops); ++ my_hist = &per_cpu(timerandwakeup_latency_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ ++ sprintf(name, cpufmt_maxlatproc, i); ++ mp = &per_cpu(timerandwakeup_maxlatproc, i); ++ entry = debugfs_create_file(name, 0444, dentry, mp, ++ &maxlatproc_fops); ++ clear_maxlatprocdata(mp); ++ } ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)TIMERANDWAKEUP_LATENCY, &latency_hist_reset_fops); ++ entry = debugfs_create_file("timerandwakeup", 0644, ++ enable_root, (void *)&timerandwakeup_enabled_data, ++ &enable_fops); ++#endif ++ return 0; ++} ++ ++__initcall(latency_hist_init); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/trace/Makefile sun8i-rt/kernel/trace/Makefile +--- sun8i/kernel/trace/Makefile 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/trace/Makefile 2016-08-22 16:23:25.128213274 +0200 +@@ -36,6 +36,10 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace_f + obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o + obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o + obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o ++obj-$(CONFIG_INTERRUPT_OFF_HIST) += latency_hist.o ++obj-$(CONFIG_PREEMPT_OFF_HIST) += latency_hist.o ++obj-$(CONFIG_WAKEUP_LATENCY_HIST) += latency_hist.o ++obj-$(CONFIG_MISSED_TIMER_OFFSETS_HIST) += latency_hist.o + obj-$(CONFIG_NOP_TRACER) += trace_nop.o + obj-$(CONFIG_STACK_TRACER) += trace_stack.o + obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/trace/ring_buffer.c sun8i-rt/kernel/trace/ring_buffer.c +--- sun8i/kernel/trace/ring_buffer.c 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/kernel/trace/ring_buffer.c 2016-08-22 17:50:56.700273650 +0200 +@@ -446,7 +446,7 @@ struct ring_buffer_per_cpu { + int cpu; + atomic_t record_disabled; + struct ring_buffer *buffer; +- raw_spinlock_t reader_lock; /* serialize readers */ ++ spinlock_t reader_lock; /* serialize readers */ + arch_spinlock_t lock; + struct lock_class_key lock_key; + struct list_head *pages; +@@ -1017,6 +1017,44 @@ static int rb_allocate_pages(struct ring + return -ENOMEM; + } + ++static inline int ok_to_lock(void) ++{ ++ if (in_nmi()) ++ return 0; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (in_atomic() || irqs_disabled()) ++ return 0; ++#endif ++ return 1; ++} ++ ++static int ++read_buffer_lock(struct ring_buffer_per_cpu *cpu_buffer, ++ unsigned long *flags) ++{ ++ /* ++ * If an NMI die dumps out the content of the ring buffer ++ * do not grab locks. We also permanently disable the ring ++ * buffer too. A one time deal is all you get from reading ++ * the ring buffer from an NMI. ++ */ ++ if (!ok_to_lock()) { ++ if (spin_trylock_irqsave(&cpu_buffer->reader_lock, *flags)) ++ return 1; ++ tracing_off_permanent(); ++ return 0; ++ } ++ spin_lock_irqsave(&cpu_buffer->reader_lock, *flags); ++ return 1; ++} ++ ++static void ++read_buffer_unlock(struct ring_buffer_per_cpu *cpu_buffer, ++ unsigned long flags, int locked) ++{ ++ if (locked) ++ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); ++} + static struct ring_buffer_per_cpu * + rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) + { +@@ -1032,7 +1070,7 @@ rb_allocate_cpu_buffer(struct ring_buffe + + cpu_buffer->cpu = cpu; + cpu_buffer->buffer = buffer; +- raw_spin_lock_init(&cpu_buffer->reader_lock); ++ spin_lock_init(&cpu_buffer->reader_lock); + lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key); + cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; + +@@ -1227,9 +1265,11 @@ rb_remove_pages(struct ring_buffer_per_c + { + struct buffer_page *bpage; + struct list_head *p; ++ unsigned long flags; + unsigned i; ++ int locked; + +- raw_spin_lock_irq(&cpu_buffer->reader_lock); ++ locked = read_buffer_lock(cpu_buffer, &flags); + rb_head_page_deactivate(cpu_buffer); + + for (i = 0; i < nr_pages; i++) { +@@ -1247,7 +1287,7 @@ rb_remove_pages(struct ring_buffer_per_c + rb_check_pages(cpu_buffer); + + out: +- raw_spin_unlock_irq(&cpu_buffer->reader_lock); ++ read_buffer_unlock(cpu_buffer, flags, locked); + } + + static void +@@ -1256,9 +1296,11 @@ rb_insert_pages(struct ring_buffer_per_c + { + struct buffer_page *bpage; + struct list_head *p; ++ unsigned long flags; + unsigned i; ++ int locked; + +- raw_spin_lock_irq(&cpu_buffer->reader_lock); ++ locked = read_buffer_lock(cpu_buffer, &flags); + rb_head_page_deactivate(cpu_buffer); + + for (i = 0; i < nr_pages; i++) { +@@ -1273,7 +1315,7 @@ rb_insert_pages(struct ring_buffer_per_c + rb_check_pages(cpu_buffer); + + out: +- raw_spin_unlock_irq(&cpu_buffer->reader_lock); ++ read_buffer_unlock(cpu_buffer, flags, locked); + } + + /** +@@ -2721,7 +2763,7 @@ unsigned long ring_buffer_oldest_event_t + return 0; + + cpu_buffer = buffer->buffers[cpu]; +- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); ++ spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + /* + * if the tail is on reader_page, oldest time stamp is on the reader + * page +@@ -2732,7 +2774,7 @@ unsigned long ring_buffer_oldest_event_t + bpage = rb_set_head_page(cpu_buffer); + if (bpage) + ret = bpage->page->time_stamp; +- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); ++ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + return ret; + } +@@ -2896,15 +2938,16 @@ void ring_buffer_iter_reset(struct ring_ + { + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; ++ int locked; + + if (!iter) + return; + + cpu_buffer = iter->cpu_buffer; + +- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); ++ locked = read_buffer_lock(cpu_buffer, &flags); + rb_iter_reset(iter); +- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); ++ read_buffer_unlock(cpu_buffer, flags, locked); + } + EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); + +@@ -3324,21 +3367,6 @@ rb_iter_peek(struct ring_buffer_iter *it + } + EXPORT_SYMBOL_GPL(ring_buffer_iter_peek); + +-static inline int rb_ok_to_lock(void) +-{ +- /* +- * If an NMI die dumps out the content of the ring buffer +- * do not grab locks. We also permanently disable the ring +- * buffer too. A one time deal is all you get from reading +- * the ring buffer from an NMI. +- */ +- if (likely(!in_nmi())) +- return 1; +- +- tracing_off_permanent(); +- return 0; +-} +- + /** + * ring_buffer_peek - peek at the next event to be read + * @buffer: The ring buffer to read +@@ -3356,22 +3384,17 @@ ring_buffer_peek(struct ring_buffer *buf + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + struct ring_buffer_event *event; + unsigned long flags; +- int dolock; ++ int locked; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return NULL; + +- dolock = rb_ok_to_lock(); + again: +- local_irq_save(flags); +- if (dolock) +- raw_spin_lock(&cpu_buffer->reader_lock); ++ locked = read_buffer_lock(cpu_buffer, &flags); + event = rb_buffer_peek(cpu_buffer, ts, lost_events); + if (event && event->type_len == RINGBUF_TYPE_PADDING) + rb_advance_reader(cpu_buffer); +- if (dolock) +- raw_spin_unlock(&cpu_buffer->reader_lock); +- local_irq_restore(flags); ++ read_buffer_unlock(cpu_buffer, flags, locked); + + if (event && event->type_len == RINGBUF_TYPE_PADDING) + goto again; +@@ -3393,11 +3416,12 @@ ring_buffer_iter_peek(struct ring_buffer + struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + struct ring_buffer_event *event; + unsigned long flags; ++ int locked; + + again: +- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); ++ locked = read_buffer_lock(cpu_buffer, &flags); + event = rb_iter_peek(iter, ts); +- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); ++ read_buffer_unlock(cpu_buffer, flags, locked); + + if (event && event->type_len == RINGBUF_TYPE_PADDING) + goto again; +@@ -3423,9 +3447,7 @@ ring_buffer_consume(struct ring_buffer * + struct ring_buffer_per_cpu *cpu_buffer; + struct ring_buffer_event *event = NULL; + unsigned long flags; +- int dolock; +- +- dolock = rb_ok_to_lock(); ++ int locked; + + again: + /* might be called in atomic */ +@@ -3435,9 +3457,7 @@ ring_buffer_consume(struct ring_buffer * + goto out; + + cpu_buffer = buffer->buffers[cpu]; +- local_irq_save(flags); +- if (dolock) +- raw_spin_lock(&cpu_buffer->reader_lock); ++ locked = read_buffer_lock(cpu_buffer, &flags); + + event = rb_buffer_peek(cpu_buffer, ts, lost_events); + if (event) { +@@ -3445,9 +3465,8 @@ ring_buffer_consume(struct ring_buffer * + rb_advance_reader(cpu_buffer); + } + +- if (dolock) +- raw_spin_unlock(&cpu_buffer->reader_lock); +- local_irq_restore(flags); ++ read_buffer_unlock(cpu_buffer, flags, locked); ++ + + out: + preempt_enable(); +@@ -3532,17 +3551,18 @@ ring_buffer_read_start(struct ring_buffe + { + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; ++ int locked; + + if (!iter) + return; + + cpu_buffer = iter->cpu_buffer; + +- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); ++ locked = read_buffer_lock(cpu_buffer, &flags); + arch_spin_lock(&cpu_buffer->lock); + rb_iter_reset(iter); + arch_spin_unlock(&cpu_buffer->lock); +- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); ++ read_buffer_unlock(cpu_buffer, flags, locked); + } + EXPORT_SYMBOL_GPL(ring_buffer_read_start); + +@@ -3576,8 +3596,9 @@ ring_buffer_read(struct ring_buffer_iter + struct ring_buffer_event *event; + struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + unsigned long flags; ++ int locked; + +- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); ++ locked = read_buffer_lock(cpu_buffer, &flags); + again: + event = rb_iter_peek(iter, ts); + if (!event) +@@ -3588,7 +3609,7 @@ ring_buffer_read(struct ring_buffer_iter + + rb_advance_iter(iter); + out: +- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); ++ read_buffer_unlock(cpu_buffer, flags, locked); + + return event; + } +@@ -3653,13 +3674,14 @@ void ring_buffer_reset_cpu(struct ring_b + { + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + unsigned long flags; ++ int locked; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return; + + atomic_inc(&cpu_buffer->record_disabled); + +- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); ++ locked = read_buffer_lock(cpu_buffer, &flags); + + if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing))) + goto out; +@@ -3671,7 +3693,7 @@ void ring_buffer_reset_cpu(struct ring_b + arch_spin_unlock(&cpu_buffer->lock); + + out: +- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); ++ read_buffer_unlock(cpu_buffer, flags, locked); + + atomic_dec(&cpu_buffer->record_disabled); + } +@@ -3698,22 +3720,16 @@ int ring_buffer_empty(struct ring_buffer + { + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; +- int dolock; ++ int locked; + int cpu; + int ret; + +- dolock = rb_ok_to_lock(); +- + /* yes this is racy, but if you don't like the race, lock the buffer */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; +- local_irq_save(flags); +- if (dolock) +- raw_spin_lock(&cpu_buffer->reader_lock); ++ locked = read_buffer_lock(cpu_buffer, &flags); + ret = rb_per_cpu_empty(cpu_buffer); +- if (dolock) +- raw_spin_unlock(&cpu_buffer->reader_lock); +- local_irq_restore(flags); ++ read_buffer_unlock(cpu_buffer, flags, locked); + + if (!ret) + return 0; +@@ -3732,22 +3748,16 @@ int ring_buffer_empty_cpu(struct ring_bu + { + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; +- int dolock; ++ int locked; + int ret; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 1; + +- dolock = rb_ok_to_lock(); +- + cpu_buffer = buffer->buffers[cpu]; +- local_irq_save(flags); +- if (dolock) +- raw_spin_lock(&cpu_buffer->reader_lock); ++ locked = read_buffer_lock(cpu_buffer, &flags); + ret = rb_per_cpu_empty(cpu_buffer); +- if (dolock) +- raw_spin_unlock(&cpu_buffer->reader_lock); +- local_irq_restore(flags); ++ read_buffer_unlock(cpu_buffer, flags, locked); + + return ret; + } +@@ -3922,6 +3932,7 @@ int ring_buffer_read_page(struct ring_bu + unsigned int commit; + unsigned int read; + u64 save_timestamp; ++ int locked; + int ret = -1; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) +@@ -3943,7 +3954,7 @@ int ring_buffer_read_page(struct ring_bu + if (!bpage) + goto out; + +- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); ++ locked = read_buffer_lock(cpu_buffer, &flags); + + reader = rb_get_reader_page(cpu_buffer); + if (!reader) +@@ -4067,7 +4078,7 @@ int ring_buffer_read_page(struct ring_bu + memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit); + + out_unlock: +- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); ++ read_buffer_unlock(cpu_buffer, flags, locked); + + out: + return ret; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/trace/trace.c sun8i-rt/kernel/trace/trace.c +--- sun8i/kernel/trace/trace.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/kernel/trace/trace.c 2016-08-22 17:20:32.940252683 +0200 +@@ -414,11 +414,13 @@ EXPORT_SYMBOL_GPL(tracing_is_on); + */ + void trace_wake_up(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + const unsigned long delay = msecs_to_jiffies(2); + + if (trace_flags & TRACE_ITER_BLOCK) + return; + schedule_delayed_work(&wakeup_work, delay); ++#endif + } + + static int __init set_buf_size(char *str) +@@ -788,6 +790,12 @@ update_max_tr_single(struct trace_array + } + #endif /* CONFIG_TRACER_MAX_TRACE */ + ++#ifndef CONFIG_PREEMPT_RT_FULL ++static void default_wait_pipe(struct trace_iterator *iter); ++#else ++#define default_wait_pipe poll_wait_pipe ++#endif ++ + /** + * register_tracer - register a tracer with the ftrace system. + * @type - the plugin for the tracer +@@ -1211,6 +1219,8 @@ tracing_generic_entry_update(struct trac + ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | + ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | + (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); ++ ++ entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; + } + EXPORT_SYMBOL_GPL(tracing_generic_entry_update); + +@@ -1969,9 +1979,10 @@ static void print_lat_help_header(struct + seq_puts(m, "# | / _----=> need-resched \n"); + seq_puts(m, "# || / _---=> hardirq/softirq \n"); + seq_puts(m, "# ||| / _--=> preempt-depth \n"); +- seq_puts(m, "# |||| / delay \n"); +- seq_puts(m, "# cmd pid ||||| time | caller \n"); +- seq_puts(m, "# \\ / ||||| \\ | / \n"); ++ seq_puts(m, "# |||| / _--=> migrate-disable\n"); ++ seq_puts(m, "# ||||| / delay \n"); ++ seq_puts(m, "# cmd pid |||||| time | caller \n"); ++ seq_puts(m, "# \\ / ||||| \\ | / \n"); + } + + static void print_event_info(struct trace_array *tr, struct seq_file *m) +@@ -3429,6 +3440,7 @@ static int tracing_release_pipe(struct i + return 0; + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + static unsigned int + tracing_poll_pipe(struct file *filp, poll_table *poll_table) + { +@@ -3450,8 +3462,7 @@ tracing_poll_pipe(struct file *filp, pol + } + } + +- +-void default_wait_pipe(struct trace_iterator *iter) ++static void default_wait_pipe(struct trace_iterator *iter) + { + DEFINE_WAIT(wait); + +@@ -3462,6 +3473,20 @@ void default_wait_pipe(struct trace_iter + + finish_wait(&trace_wait, &wait); + } ++#else ++static unsigned int ++tracing_poll_pipe(struct file *filp, poll_table *poll_table) ++{ ++ struct trace_iterator *iter = filp->private_data; ++ ++ if ((trace_flags & TRACE_ITER_BLOCK) || !trace_empty(iter)) ++ return POLLIN | POLLRDNORM; ++ poll_wait_pipe(iter); ++ if (!trace_empty(iter)) ++ return POLLIN | POLLRDNORM; ++ return 0; ++} ++#endif + + /* + * This is a make-shift waitqueue. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/trace/trace_clock.c sun8i-rt/kernel/trace/trace_clock.c +--- sun8i/kernel/trace/trace_clock.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/trace/trace_clock.c 2016-08-22 18:14:19.480289778 +0200 +@@ -44,6 +44,7 @@ u64 notrace trace_clock_local(void) + + return clock; + } ++EXPORT_SYMBOL_GPL(trace_clock_local); + + /* + * trace_clock(): 'between' trace clock. Not completely serialized, +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/trace/trace_events.c sun8i-rt/kernel/trace/trace_events.c +--- sun8i/kernel/trace/trace_events.c 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/kernel/trace/trace_events.c 2016-08-22 17:17:39.920250694 +0200 +@@ -116,7 +116,8 @@ static int trace_define_common_fields(vo + __common_field(unsigned char, flags); + __common_field(unsigned char, preempt_count); + __common_field(int, pid); +- __common_field(int, padding); ++ __common_field(unsigned short, migrate_disable); ++ __common_field(unsigned short, padding); + + return ret; + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/trace/trace.h sun8i-rt/kernel/trace/trace.h +--- sun8i/kernel/trace/trace.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/trace/trace.h 2016-08-22 17:20:32.940252683 +0200 +@@ -358,7 +358,6 @@ void trace_init_global_iter(struct trace + + void tracing_iter_reset(struct trace_iterator *iter, int cpu); + +-void default_wait_pipe(struct trace_iterator *iter); + void poll_wait_pipe(struct trace_iterator *iter); + + void ftrace(struct trace_array *tr, +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/trace/trace_irqsoff.c sun8i-rt/kernel/trace/trace_irqsoff.c +--- sun8i/kernel/trace/trace_irqsoff.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/trace/trace_irqsoff.c 2016-08-22 18:28:21.656299460 +0200 +@@ -17,6 +17,7 @@ + #include + + #include "trace.h" ++#include + + static struct trace_array *irqsoff_trace __read_mostly; + static int tracer_enabled __read_mostly; +@@ -437,11 +438,13 @@ void start_critical_timings(void) + { + if (preempt_trace() || irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); ++ trace_preemptirqsoff_hist_rcuidle(TRACE_START, 1); + } + EXPORT_SYMBOL_GPL(start_critical_timings); + + void stop_critical_timings(void) + { ++ trace_preemptirqsoff_hist_rcuidle(TRACE_STOP, 0); + if (preempt_trace() || irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + } +@@ -451,6 +454,7 @@ EXPORT_SYMBOL_GPL(stop_critical_timings) + #ifdef CONFIG_PROVE_LOCKING + void time_hardirqs_on(unsigned long a0, unsigned long a1) + { ++ trace_preemptirqsoff_hist(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(a0, a1); + } +@@ -459,6 +463,7 @@ void time_hardirqs_off(unsigned long a0, + { + if (!preempt_trace() && irq_trace()) + start_critical_timing(a0, a1); ++ trace_preemptirqsoff_hist(IRQS_OFF, 1); + } + + #else /* !CONFIG_PROVE_LOCKING */ +@@ -484,6 +489,7 @@ inline void print_irqtrace_events(struct + */ + void trace_hardirqs_on(void) + { ++ trace_preemptirqsoff_hist_rcuidle(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + } +@@ -493,11 +499,13 @@ void trace_hardirqs_off(void) + { + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); ++ trace_preemptirqsoff_hist_rcuidle(IRQS_OFF, 1); + } + EXPORT_SYMBOL(trace_hardirqs_off); + + void trace_hardirqs_on_caller(unsigned long caller_addr) + { ++ trace_preemptirqsoff_hist(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, caller_addr); + } +@@ -507,6 +515,7 @@ void trace_hardirqs_off_caller(unsigned + { + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, caller_addr); ++ trace_preemptirqsoff_hist(IRQS_OFF, 1); + } + EXPORT_SYMBOL(trace_hardirqs_off_caller); + +@@ -516,12 +525,14 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller) + #ifdef CONFIG_PREEMPT_TRACER + void trace_preempt_on(unsigned long a0, unsigned long a1) + { ++ trace_preemptirqsoff_hist(PREEMPT_ON, 0); + if (preempt_trace() && !irq_trace()) + stop_critical_timing(a0, a1); + } + + void trace_preempt_off(unsigned long a0, unsigned long a1) + { ++ trace_preemptirqsoff_hist(PREEMPT_ON, 1); + if (preempt_trace() && !irq_trace()) + start_critical_timing(a0, a1); + } +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/trace/trace_output.c sun8i-rt/kernel/trace/trace_output.c +--- sun8i/kernel/trace/trace_output.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/trace/trace_output.c 2016-08-22 17:17:23.376250504 +0200 +@@ -593,6 +593,11 @@ int trace_print_lat_fmt(struct trace_seq + else + ret = trace_seq_putc(s, '.'); + ++ if (entry->migrate_disable) ++ ret = trace_seq_printf(s, "%x", entry->migrate_disable); ++ else ++ ret = trace_seq_putc(s, '.'); ++ + return ret; + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/trace/trace_sched_switch.c sun8i-rt/kernel/trace/trace_sched_switch.c +--- sun8i/kernel/trace/trace_sched_switch.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/trace/trace_sched_switch.c 2016-08-22 18:27:20.628298759 +0200 +@@ -108,7 +108,7 @@ tracing_sched_wakeup_trace(struct trace_ + } + + static void +-probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success) ++probe_sched_wakeup(void *ignore, struct task_struct *wakee) + { + struct trace_array_cpu *data; + unsigned long flags; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/trace/trace_sched_wakeup.c sun8i-rt/kernel/trace/trace_sched_wakeup.c +--- sun8i/kernel/trace/trace_sched_wakeup.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/trace/trace_sched_wakeup.c 2016-08-22 18:27:20.628298759 +0200 +@@ -414,7 +414,7 @@ static void wakeup_reset(struct trace_ar + } + + static void +-probe_wakeup(void *ignore, struct task_struct *p, int success) ++probe_wakeup(void *ignore, struct task_struct *p) + { + struct trace_array_cpu *data; + int cpu = smp_processor_id(); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/user.c sun8i-rt/kernel/user.c +--- sun8i/kernel/user.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/user.c 2016-08-22 16:32:12.416219336 +0200 +@@ -129,11 +129,11 @@ void free_uid(struct user_struct *up) + if (!up) + return; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + if (atomic_dec_and_lock(&up->__count, &uidhash_lock)) + free_user(up, flags); + else +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + + struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/wait-simple.c sun8i-rt/kernel/wait-simple.c +--- sun8i/kernel/wait-simple.c 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/kernel/wait-simple.c 2016-08-22 18:11:30.464287835 +0200 +@@ -0,0 +1,119 @@ ++/* ++ * Simple waitqueues without fancy flags and callbacks ++ * ++ * (C) 2011 Thomas Gleixner ++ * ++ * Based on kernel/wait.c ++ * ++ * For licencing details see kernel-base/COPYING ++ */ ++#include ++#include ++#include ++#include ++ ++/* Adds w to head->list. Must be called with head->lock locked. */ ++static inline void __swait_enqueue(struct swait_head *head, struct swaiter *w) ++{ ++ list_add(&w->node, &head->list); ++} ++ ++/* Removes w from head->list. Must be called with head->lock locked. */ ++static inline void __swait_dequeue(struct swaiter *w) ++{ ++ list_del_init(&w->node); ++} ++ ++/* Check whether a head has waiters enqueued */ ++static inline bool swait_head_has_waiters(struct swait_head *h) ++{ ++ return !list_empty(&h->list); ++} ++ ++void __init_swait_head(struct swait_head *head, struct lock_class_key *key) ++{ ++ raw_spin_lock_init(&head->lock); ++ lockdep_set_class(&head->lock, key); ++ INIT_LIST_HEAD(&head->list); ++} ++EXPORT_SYMBOL_GPL(__init_swait_head); ++ ++void swait_prepare_locked(struct swait_head *head, struct swaiter *w) ++{ ++ w->task = current; ++ if (list_empty(&w->node)) ++ __swait_enqueue(head, w); ++} ++ ++void swait_prepare(struct swait_head *head, struct swaiter *w, int state) ++{ ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&head->lock, flags); ++ swait_prepare_locked(head, w); ++ __set_current_state(state); ++ raw_spin_unlock_irqrestore(&head->lock, flags); ++} ++EXPORT_SYMBOL_GPL(swait_prepare); ++ ++void swait_finish_locked(struct swait_head *head, struct swaiter *w) ++{ ++ __set_current_state(TASK_RUNNING); ++ if (w->task) ++ __swait_dequeue(w); ++} ++ ++void swait_finish(struct swait_head *head, struct swaiter *w) ++{ ++ unsigned long flags; ++ ++ __set_current_state(TASK_RUNNING); ++ if (w->task) { ++ raw_spin_lock_irqsave(&head->lock, flags); ++ __swait_dequeue(w); ++ raw_spin_unlock_irqrestore(&head->lock, flags); ++ } ++} ++EXPORT_SYMBOL_GPL(swait_finish); ++ ++unsigned int ++__swait_wake_locked(struct swait_head *head, unsigned int state, unsigned int num) ++{ ++ struct swaiter *curr, *next; ++ int woken = 0; ++ ++ list_for_each_entry_safe(curr, next, &head->list, node) { ++ if (wake_up_state(curr->task, state)) { ++ __swait_dequeue(curr); ++ /* ++ * The waiting task can free the waiter as ++ * soon as curr->task = NULL is written, ++ * without taking any locks. A memory barrier ++ * is required here to prevent the following ++ * store to curr->task from getting ahead of ++ * the dequeue operation. ++ */ ++ smp_wmb(); ++ curr->task = NULL; ++ if (++woken == num) ++ break; ++ } ++ } ++ return woken; ++} ++ ++unsigned int ++__swait_wake(struct swait_head *head, unsigned int state, unsigned int num) ++{ ++ unsigned long flags; ++ int woken; ++ ++ if (!swait_head_has_waiters(head)) ++ return 0; ++ ++ raw_spin_lock_irqsave(&head->lock, flags); ++ woken = __swait_wake_locked(head, state, num); ++ raw_spin_unlock_irqrestore(&head->lock, flags); ++ return woken; ++} ++EXPORT_SYMBOL_GPL(__swait_wake); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/watchdog.c sun8i-rt/kernel/watchdog.c +--- sun8i/kernel/watchdog.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/kernel/watchdog.c 2016-08-22 17:10:26.268245708 +0200 +@@ -276,6 +276,8 @@ static int is_softlockup(unsigned long t + + #ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI + ++static DEFINE_RAW_SPINLOCK(watchdog_output_lock); ++ + static struct perf_event_attr wd_hw_attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, +@@ -310,10 +312,19 @@ static void watchdog_overflow_callback(s + if (__this_cpu_read(hard_watchdog_warn) == true) + return; + +- if (hardlockup_panic) ++ /* ++ * If early-printk is enabled then make sure we do not ++ * lock up in printk() and kill console logging: ++ */ ++ printk_kill(); ++ ++ if (hardlockup_panic) { + panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu); +- else ++ } else { ++ raw_spin_lock(&watchdog_output_lock); + WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu); ++ raw_spin_unlock(&watchdog_output_lock); ++ } + + __this_cpu_write(hard_watchdog_warn, true); + return; +@@ -550,6 +561,7 @@ static void watchdog_prepare_cpu(int cpu + WARN_ON(per_cpu(softlockup_watchdog, cpu)); + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; ++ hrtimer->irqsafe = 1; + } + + static int watchdog_enable(int cpu) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/workqueue.c sun8i-rt/kernel/workqueue.c +--- sun8i/kernel/workqueue.c 2016-08-22 14:14:37.000000000 +0200 ++++ sun8i-rt/kernel/workqueue.c 2016-08-22 18:19:29.144293338 +0200 +@@ -138,6 +138,7 @@ struct worker { + unsigned int flags; /* X: flags */ + int id; /* I: worker id */ + struct work_struct rebind_work; /* L: rebind worker to cpu */ ++ int sleeping; /* None */ + }; + + /* +@@ -318,6 +319,31 @@ static inline int __next_wq_cpu(int cpu, + (cpu) < WORK_CPU_NONE; \ + (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq))) + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static inline void rt_lock_idle_list(struct global_cwq *gcwq) ++{ ++ preempt_disable(); ++} ++static inline void rt_unlock_idle_list(struct global_cwq *gcwq) ++{ ++ preempt_enable(); ++} ++static inline void sched_lock_idle_list(struct global_cwq *gcwq) { } ++static inline void sched_unlock_idle_list(struct global_cwq *gcwq) { } ++#else ++static inline void rt_lock_idle_list(struct global_cwq *gcwq) { } ++static inline void rt_unlock_idle_list(struct global_cwq *gcwq) { } ++static inline void sched_lock_idle_list(struct global_cwq *gcwq) ++{ ++ spin_lock_irq(&gcwq->lock); ++} ++static inline void sched_unlock_idle_list(struct global_cwq *gcwq) ++{ ++ spin_unlock_irq(&gcwq->lock); ++} ++#endif ++ ++ + #ifdef CONFIG_DEBUG_OBJECTS_WORK + + static struct debug_obj_descr work_debug_descr; +@@ -649,73 +675,69 @@ static struct worker *first_worker(struc + */ + static void wake_up_worker(struct global_cwq *gcwq) + { +- struct worker *worker = first_worker(gcwq); ++ struct worker *worker; ++ ++ rt_lock_idle_list(gcwq); ++ ++ worker = first_worker(gcwq); + + if (likely(worker)) + wake_up_process(worker->task); ++ ++ rt_unlock_idle_list(gcwq); + } + + /** +- * wq_worker_waking_up - a worker is waking up +- * @task: task waking up +- * @cpu: CPU @task is waking up to +- * +- * This function is called during try_to_wake_up() when a worker is +- * being awoken. ++ * wq_worker_running - a worker is running again ++ * @task: task returning from sleep + * +- * CONTEXT: +- * spin_lock_irq(rq->lock) ++ * This function is called when a worker returns from schedule() + */ +-void wq_worker_waking_up(struct task_struct *task, unsigned int cpu) ++void wq_worker_running(struct task_struct *task) + { + struct worker *worker = kthread_data(task); + ++ if (!worker->sleeping) ++ return; + if (!(worker->flags & WORKER_NOT_RUNNING)) +- atomic_inc(get_gcwq_nr_running(cpu)); ++ atomic_inc(get_gcwq_nr_running(smp_processor_id())); ++ worker->sleeping = 0; + } + + /** + * wq_worker_sleeping - a worker is going to sleep + * @task: task going to sleep +- * @cpu: CPU in question, must be the current CPU number + * +- * This function is called during schedule() when a busy worker is +- * going to sleep. Worker on the same cpu can be woken up by +- * returning pointer to its task. +- * +- * CONTEXT: +- * spin_lock_irq(rq->lock) +- * +- * RETURNS: +- * Worker task on @cpu to wake up, %NULL if none. ++ * This function is called from schedule() when a busy worker is ++ * going to sleep. + */ +-struct task_struct *wq_worker_sleeping(struct task_struct *task, +- unsigned int cpu) ++void wq_worker_sleeping(struct task_struct *task) + { +- struct worker *worker = kthread_data(task), *to_wakeup = NULL; +- struct global_cwq *gcwq = get_gcwq(cpu); +- atomic_t *nr_running = get_gcwq_nr_running(cpu); ++ struct worker *worker = kthread_data(task); ++ struct global_cwq *gcwq; ++ int cpu; + + if (worker->flags & WORKER_NOT_RUNNING) +- return NULL; ++ return; + +- /* this can only happen on the local cpu */ +- BUG_ON(cpu != raw_smp_processor_id()); ++ if (WARN_ON_ONCE(worker->sleeping)) ++ return; ++ ++ worker->sleeping = 1; + ++ cpu = smp_processor_id(); ++ gcwq = get_gcwq(cpu); + /* + * The counterpart of the following dec_and_test, implied mb, + * worklist not empty test sequence is in insert_work(). + * Please read comment there. +- * +- * NOT_RUNNING is clear. This means that trustee is not in +- * charge and we're running on the local cpu w/ rq lock held +- * and preemption disabled, which in turn means that none else +- * could be manipulating idle_list, so dereferencing idle_list +- * without gcwq lock is safe. + */ +- if (atomic_dec_and_test(nr_running) && !list_empty(&gcwq->worklist)) +- to_wakeup = first_worker(gcwq); +- return to_wakeup ? to_wakeup->task : NULL; ++ if (atomic_dec_and_test(get_gcwq_nr_running(cpu)) && ++ !list_empty(&gcwq->worklist)) { ++ sched_lock_idle_list(gcwq); ++ wake_up_worker(gcwq); ++ sched_unlock_idle_list(gcwq); ++ } + } + + /** +@@ -1085,8 +1107,8 @@ int queue_work(struct workqueue_struct * + { + int ret; + +- ret = queue_work_on(get_cpu(), wq, work); +- put_cpu(); ++ ret = queue_work_on(get_cpu_light(), wq, work); ++ put_cpu_light(); + + return ret; + } +@@ -1230,13 +1252,8 @@ static void worker_enter_idle(struct wor + } else + wake_up_all(&gcwq->trustee_wait); + +- /* +- * Sanity check nr_running. Because trustee releases gcwq->lock +- * between setting %WORKER_ROGUE and zapping nr_running, the +- * warning may trigger spuriously. Check iff trustee is idle. +- */ +- WARN_ON_ONCE(gcwq->trustee_state == TRUSTEE_DONE && +- gcwq->nr_workers == gcwq->nr_idle && ++ /* sanity check nr_running */ ++ WARN_ON_ONCE(gcwq->nr_workers == gcwq->nr_idle && + atomic_read(get_gcwq_nr_running(gcwq->cpu))); + } + +@@ -3579,6 +3596,25 @@ static int __devinit workqueue_cpu_callb + kthread_stop(new_trustee); + return NOTIFY_BAD; + } ++ break; ++ case CPU_POST_DEAD: ++ case CPU_UP_CANCELED: ++ case CPU_DOWN_FAILED: ++ case CPU_ONLINE: ++ break; ++ case CPU_DYING: ++ /* ++ * We access this lockless. We are on the dying CPU ++ * and called from stomp machine. ++ * ++ * Before this, the trustee and all workers except for ++ * the ones which are still executing works from ++ * before the last CPU down must be on the cpu. After ++ * this, they'll all be diasporas. ++ */ ++ gcwq->flags |= GCWQ_DISASSOCIATED; ++ default: ++ goto out; + } + + /* some are called w/ irq disabled, don't disturb irq status */ +@@ -3598,16 +3634,6 @@ static int __devinit workqueue_cpu_callb + gcwq->first_idle = new_worker; + break; + +- case CPU_DYING: +- /* +- * Before this, the trustee and all workers except for +- * the ones which are still executing works from +- * before the last CPU down must be on the cpu. After +- * this, they'll all be diasporas. +- */ +- gcwq->flags |= GCWQ_DISASSOCIATED; +- break; +- + case CPU_POST_DEAD: + gcwq->trustee_state = TRUSTEE_BUTCHER; + /* fall through */ +@@ -3641,6 +3667,7 @@ static int __devinit workqueue_cpu_callb + + spin_unlock_irqrestore(&gcwq->lock, flags); + ++out: + return notifier_from_errno(0); + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/kernel/workqueue_sched.h sun8i-rt/kernel/workqueue_sched.h +--- sun8i/kernel/workqueue_sched.h 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/kernel/workqueue_sched.h 2016-08-22 15:57:05.832195117 +0200 +@@ -4,6 +4,5 @@ + * Scheduler hooks for concurrency managed workqueue. Only to be + * included from sched.c and workqueue.c. + */ +-void wq_worker_waking_up(struct task_struct *task, unsigned int cpu); +-struct task_struct *wq_worker_sleeping(struct task_struct *task, +- unsigned int cpu); ++void wq_worker_running(struct task_struct *task); ++void wq_worker_sleeping(struct task_struct *task); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/lib/debugobjects.c sun8i-rt/lib/debugobjects.c +--- sun8i/lib/debugobjects.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/lib/debugobjects.c 2016-08-22 17:42:44.512267992 +0200 +@@ -310,7 +310,10 @@ __debug_object_init(void *addr, struct d + struct debug_obj *obj; + unsigned long flags; + +- fill_pool(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (preempt_count() == 0 && !irqs_disabled()) ++#endif ++ fill_pool(); + + db = get_bucket((unsigned long) addr); + +@@ -1053,9 +1056,9 @@ static int __init debug_objects_replace_ + } + } + ++ local_irq_enable(); + printk(KERN_DEBUG "ODEBUG: %d of %d active objects replaced\n", cnt, + obj_pool_used); +- local_irq_enable(); + return 0; + free: + hlist_for_each_entry_safe(obj, node, tmp, &objects, node) { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/lib/Kconfig sun8i-rt/lib/Kconfig +--- sun8i/lib/Kconfig 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/lib/Kconfig 2016-08-22 17:50:02.648273029 +0200 +@@ -303,6 +303,7 @@ config CHECK_SIGNATURE + + config CPUMASK_OFFSTACK + bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS ++ depends on !PREEMPT_RT_FULL + help + Use dynamic allocation for cpumask_var_t, instead of putting + them on the stack. This is a bit more expensive, but avoids +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/lib/Kconfig.debug sun8i-rt/lib/Kconfig.debug +--- sun8i/lib/Kconfig.debug 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/lib/Kconfig.debug 2016-08-22 16:34:22.444220831 +0200 +@@ -151,7 +151,7 @@ config DEBUG_KERNEL + + config DEBUG_SHIRQ + bool "Debug shared IRQ handlers" +- depends on DEBUG_KERNEL && GENERIC_HARDIRQS ++ depends on DEBUG_KERNEL && GENERIC_HARDIRQS && !PREEMPT_RT_BASE + help + Enable this to generate a spurious interrupt as soon as a shared + interrupt handler is registered, and just before one is deregistered. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/lib/locking-selftest.c sun8i-rt/lib/locking-selftest.c +--- sun8i/lib/locking-selftest.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/lib/locking-selftest.c 2016-08-22 18:25:18.932297359 +0200 +@@ -47,10 +47,10 @@ __setup("debug_locks_verbose=", setup_de + * Normal standalone locks, for the circular and irq-context + * dependency tests: + */ +-static DEFINE_SPINLOCK(lock_A); +-static DEFINE_SPINLOCK(lock_B); +-static DEFINE_SPINLOCK(lock_C); +-static DEFINE_SPINLOCK(lock_D); ++static DEFINE_RAW_SPINLOCK(lock_A); ++static DEFINE_RAW_SPINLOCK(lock_B); ++static DEFINE_RAW_SPINLOCK(lock_C); ++static DEFINE_RAW_SPINLOCK(lock_D); + + static DEFINE_RWLOCK(rwlock_A); + static DEFINE_RWLOCK(rwlock_B); +@@ -73,12 +73,12 @@ static DECLARE_RWSEM(rwsem_D); + * but X* and Y* are different classes. We do this so that + * we do not trigger a real lockup: + */ +-static DEFINE_SPINLOCK(lock_X1); +-static DEFINE_SPINLOCK(lock_X2); +-static DEFINE_SPINLOCK(lock_Y1); +-static DEFINE_SPINLOCK(lock_Y2); +-static DEFINE_SPINLOCK(lock_Z1); +-static DEFINE_SPINLOCK(lock_Z2); ++static DEFINE_RAW_SPINLOCK(lock_X1); ++static DEFINE_RAW_SPINLOCK(lock_X2); ++static DEFINE_RAW_SPINLOCK(lock_Y1); ++static DEFINE_RAW_SPINLOCK(lock_Y2); ++static DEFINE_RAW_SPINLOCK(lock_Z1); ++static DEFINE_RAW_SPINLOCK(lock_Z2); + + static DEFINE_RWLOCK(rwlock_X1); + static DEFINE_RWLOCK(rwlock_X2); +@@ -107,10 +107,10 @@ static DECLARE_RWSEM(rwsem_Z2); + */ + #define INIT_CLASS_FUNC(class) \ + static noinline void \ +-init_class_##class(spinlock_t *lock, rwlock_t *rwlock, struct mutex *mutex, \ +- struct rw_semaphore *rwsem) \ ++init_class_##class(raw_spinlock_t *lock, rwlock_t *rwlock, \ ++ struct mutex *mutex, struct rw_semaphore *rwsem)\ + { \ +- spin_lock_init(lock); \ ++ raw_spin_lock_init(lock); \ + rwlock_init(rwlock); \ + mutex_init(mutex); \ + init_rwsem(rwsem); \ +@@ -168,10 +168,10 @@ static void init_shared_classes(void) + * Shortcuts for lock/unlock API variants, to keep + * the testcases compact: + */ +-#define L(x) spin_lock(&lock_##x) +-#define U(x) spin_unlock(&lock_##x) ++#define L(x) raw_spin_lock(&lock_##x) ++#define U(x) raw_spin_unlock(&lock_##x) + #define LU(x) L(x); U(x) +-#define SI(x) spin_lock_init(&lock_##x) ++#define SI(x) raw_spin_lock_init(&lock_##x) + + #define WL(x) write_lock(&rwlock_##x) + #define WU(x) write_unlock(&rwlock_##x) +@@ -569,6 +569,8 @@ GENERATE_TESTCASE(init_held_rsem) + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock) + +@@ -584,9 +586,12 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Enabling hardirqs with a softirq-safe lock held: + */ +@@ -619,6 +624,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A + #undef E1 + #undef E2 + ++#endif ++ + /* + * Enabling irqs with an irq-safe lock held: + */ +@@ -642,6 +649,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock) + +@@ -657,6 +666,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + +@@ -688,6 +699,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock) + +@@ -703,6 +716,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + #undef E3 +@@ -736,6 +751,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_ + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock) + +@@ -751,10 +768,14 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + #undef E3 + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * read-lock / write-lock irq inversion. + * +@@ -817,6 +838,10 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_inver + #undef E2 + #undef E3 + ++#endif ++ ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * read-lock / write-lock recursion that is actually safe. + */ +@@ -855,6 +880,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_ + #undef E2 + #undef E3 + ++#endif ++ + /* + * read-lock / write-lock recursion that is unsafe. + */ +@@ -911,7 +938,7 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_ + + #define I2(x) \ + do { \ +- spin_lock_init(&lock_##x); \ ++ raw_spin_lock_init(&lock_##x); \ + rwlock_init(&rwlock_##x); \ + mutex_init(&mutex_##x); \ + init_rwsem(&rwsem_##x); \ +@@ -1175,6 +1202,7 @@ void locking_selftest(void) + + printk(" --------------------------------------------------------------------------\n"); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * irq-context testcases: + */ +@@ -1187,6 +1215,28 @@ void locking_selftest(void) + + DO_TESTCASE_6x2("irq read-recursion", irq_read_recursion); + // DO_TESTCASE_6x2B("irq read-recursion #2", irq_read_recursion2); ++#else ++ /* On -rt, we only do hardirq context test for raw spinlock */ ++ DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 12); ++ DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 21); ++ ++ DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 12); ++ DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 21); ++ ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 123); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 132); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 213); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 231); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 312); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 321); ++ ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 123); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 132); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 213); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 231); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 312); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 321); ++#endif + + if (unexpected_testcase_failures) { + printk("-----------------------------------------------------------------\n"); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/lib/Makefile sun8i-rt/lib/Makefile +--- sun8i/lib/Makefile 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/lib/Makefile 2016-08-22 17:33:46.052261801 +0200 +@@ -38,8 +38,11 @@ obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o + obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o + obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o + obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o ++ ++ifneq ($(CONFIG_PREEMPT_RT_FULL),y) + lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o + lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o ++endif + + GCOV_PROFILE_hweight.o := n + CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS)) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/lib/radix-tree.c sun8i-rt/lib/radix-tree.c +--- sun8i/lib/radix-tree.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/lib/radix-tree.c 2016-08-22 17:06:52.672243253 +0200 +@@ -202,12 +202,13 @@ radix_tree_node_alloc(struct radix_tree_ + * succeed in getting a node here (and never reach + * kmem_cache_alloc) + */ +- rtp = &__get_cpu_var(radix_tree_preloads); ++ rtp = &get_cpu_var(radix_tree_preloads); + if (rtp->nr) { + ret = rtp->nodes[rtp->nr - 1]; + rtp->nodes[rtp->nr - 1] = NULL; + rtp->nr--; + } ++ put_cpu_var(radix_tree_preloads); + } + if (ret == NULL) + ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); +@@ -242,6 +243,7 @@ radix_tree_node_free(struct radix_tree_n + call_rcu(&node->rcu_head, radix_tree_node_rcu_free); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Load up this CPU's radix_tree_node buffer with sufficient objects to + * ensure that the addition of a single element in the tree cannot fail. On +@@ -276,6 +278,7 @@ out: + return ret; + } + EXPORT_SYMBOL(radix_tree_preload); ++#endif + + /* + * Return the maximum key which can be store into a +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/lib/scatterlist.c sun8i-rt/lib/scatterlist.c +--- sun8i/lib/scatterlist.c 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/lib/scatterlist.c 2016-08-22 16:33:01.800219904 +0200 +@@ -424,7 +424,7 @@ void sg_miter_stop(struct sg_mapping_ite + flush_kernel_dcache_page(miter->page); + + if (miter->__flags & SG_MITER_ATOMIC) { +- WARN_ON(!irqs_disabled()); ++ WARN_ON_NONRT(!irqs_disabled()); + kunmap_atomic(miter->addr); + } else + kunmap(miter->page); +@@ -464,7 +464,7 @@ static size_t sg_copy_buffer(struct scat + + sg_miter_start(&miter, sgl, nents, sg_flags); + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + while (sg_miter_next(&miter) && offset < buflen) { + unsigned int len; +@@ -481,7 +481,7 @@ static size_t sg_copy_buffer(struct scat + + sg_miter_stop(&miter); + +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return offset; + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/lib/smp_processor_id.c sun8i-rt/lib/smp_processor_id.c +--- sun8i/lib/smp_processor_id.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/lib/smp_processor_id.c 2016-08-22 17:18:23.108251190 +0200 +@@ -39,9 +39,9 @@ notrace unsigned int debug_smp_processor + if (!printk_ratelimit()) + goto out_enable; + +- printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x] " +- "code: %s/%d\n", +- preempt_count() - 1, current->comm, current->pid); ++ printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x %08x] " ++ "code: %s/%d\n", preempt_count() - 1, ++ __migrate_disabled(current), current->comm, current->pid); + print_symbol("caller is %s\n", (long)__builtin_return_address(0)); + dump_stack(); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/lib/spinlock_debug.c sun8i-rt/lib/spinlock_debug.c +--- sun8i/lib/spinlock_debug.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/lib/spinlock_debug.c 2016-08-22 17:34:01.268261976 +0200 +@@ -31,6 +31,7 @@ void __raw_spin_lock_init(raw_spinlock_t + + EXPORT_SYMBOL(__raw_spin_lock_init); + ++#ifndef CONFIG_PREEMPT_RT_FULL + void __rwlock_init(rwlock_t *lock, const char *name, + struct lock_class_key *key) + { +@@ -48,6 +49,7 @@ void __rwlock_init(rwlock_t *lock, const + } + + EXPORT_SYMBOL(__rwlock_init); ++#endif + + static void spin_dump(raw_spinlock_t *lock, const char *msg) + { +@@ -155,6 +157,7 @@ void do_raw_spin_unlock(raw_spinlock_t * + arch_spin_unlock(&lock->raw_lock); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + static void rwlock_bug(rwlock_t *lock, const char *msg) + { + if (!debug_locks_off()) +@@ -296,3 +299,5 @@ void do_raw_write_unlock(rwlock_t *lock) + debug_write_unlock(lock); + arch_write_unlock(&lock->raw_lock); + } ++ ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/localversion-rt sun8i-rt/localversion-rt +--- sun8i/localversion-rt 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-rt/localversion-rt 2016-08-22 18:29:42.328300388 +0200 +@@ -0,0 +1 @@ ++-rt143 +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/MAINTAINERS sun8i-rt/MAINTAINERS +--- sun8i/MAINTAINERS 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/MAINTAINERS 2016-08-22 16:23:41.608213464 +0200 +@@ -3081,6 +3081,15 @@ L: linuxppc-dev@lists.ozlabs.org + S: Odd Fixes + F: drivers/tty/hvc/ + ++HARDWARE LATENCY DETECTOR ++P: Jon Masters ++M: jcm@jonmasters.org ++W: http://www.kernel.org/pub/linux/kernel/people/jcm/hwlat_detector/ ++S: Supported ++L: linux-kernel@vger.kernel.org ++F: Documentation/hwlat_detector.txt ++F: drivers/misc/hwlat_detector.c ++ + HARDWARE MONITORING + M: Jean Delvare + M: Guenter Roeck +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/mm/filemap.c sun8i-rt/mm/filemap.c +--- sun8i/mm/filemap.c 2016-08-22 14:14:41.000000000 +0200 ++++ sun8i-rt/mm/filemap.c 2016-08-22 16:16:10.936208282 +0200 +@@ -2036,7 +2036,7 @@ size_t iov_iter_copy_from_user_atomic(st + char *kaddr; + size_t copied; + +- BUG_ON(!in_atomic()); ++ BUG_ON(!pagefault_disabled()); + kaddr = kmap_atomic(page); + if (likely(i->nr_segs == 1)) { + int left; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/mm/Kconfig sun8i-rt/mm/Kconfig +--- sun8i/mm/Kconfig 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/mm/Kconfig 2016-08-22 17:58:34.956278919 +0200 +@@ -318,7 +318,7 @@ config NOMMU_INITIAL_TRIM_EXCESS + + config TRANSPARENT_HUGEPAGE + bool "Transparent Hugepage Support" +- depends on X86 && MMU ++ depends on X86 && MMU && !PREEMPT_RT_FULL + select COMPACTION + help + Transparent Hugepages allows the kernel to use huge pages and +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/mm/memcontrol.c sun8i-rt/mm/memcontrol.c +--- sun8i/mm/memcontrol.c 2016-08-22 14:14:35.000000000 +0200 ++++ sun8i-rt/mm/memcontrol.c 2016-08-22 18:24:46.736296989 +0200 +@@ -2061,14 +2061,17 @@ static void drain_local_stock(struct wor + */ + static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) + { +- struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock); ++ struct memcg_stock_pcp *stock; ++ int cpu = get_cpu_light(); ++ ++ stock = &per_cpu(memcg_stock, cpu); + + if (stock->cached != memcg) { /* reset if necessary */ + drain_stock(stock); + stock->cached = memcg; + } + stock->nr_pages += nr_pages; +- put_cpu_var(memcg_stock); ++ put_cpu_light(); + } + + /* +@@ -2082,7 +2085,7 @@ static void drain_all_stock(struct mem_c + + /* Notify other cpus that system-wide "drain" is running */ + get_online_cpus(); +- curcpu = get_cpu(); ++ curcpu = get_cpu_light(); + for_each_online_cpu(cpu) { + struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); + struct mem_cgroup *memcg; +@@ -2099,7 +2102,7 @@ static void drain_all_stock(struct mem_c + schedule_work_on(cpu, &stock->work); + } + } +- put_cpu(); ++ put_cpu_light(); + + if (!sync) + goto out; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/mm/memory.c sun8i-rt/mm/memory.c +--- sun8i/mm/memory.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/mm/memory.c 2016-08-22 17:48:36.284272036 +0200 +@@ -3542,6 +3542,32 @@ unlock: + return 0; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++void pagefault_disable(void) ++{ ++ migrate_disable(); ++ current->pagefault_disabled++; ++ /* ++ * make sure to have issued the store before a pagefault ++ * can hit. ++ */ ++ barrier(); ++} ++EXPORT_SYMBOL_GPL(pagefault_disable); ++ ++void pagefault_enable(void) ++{ ++ /* ++ * make sure to issue those last loads/stores before enabling ++ * the pagefault handler again. ++ */ ++ barrier(); ++ current->pagefault_disabled--; ++ migrate_enable(); ++} ++EXPORT_SYMBOL_GPL(pagefault_enable); ++#endif ++ + /* + * By the time we get here, we already hold the mm semaphore + */ +@@ -4096,3 +4122,35 @@ void copy_user_huge_page(struct page *ds + } + } + #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ ++ ++#if defined(CONFIG_PREEMPT_RT_FULL) && (USE_SPLIT_PTLOCKS > 0) ++/* ++ * Heinous hack, relies on the caller doing something like: ++ * ++ * pte = alloc_pages(PGALLOC_GFP, 0); ++ * if (pte) ++ * pgtable_page_ctor(pte); ++ * return pte; ++ * ++ * This ensures we release the page and return NULL when the ++ * lock allocation fails. ++ */ ++struct page *pte_lock_init(struct page *page) ++{ ++ page->ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL); ++ if (page->ptl) { ++ spin_lock_init(__pte_lockptr(page)); ++ } else { ++ __free_page(page); ++ page = NULL; ++ } ++ return page; ++} ++ ++void pte_lock_deinit(struct page *page) ++{ ++ kfree(page->ptl); ++ page->mapping = NULL; ++} ++ ++#endif +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/mm/mmu_context.c sun8i-rt/mm/mmu_context.c +--- sun8i/mm/mmu_context.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/mm/mmu_context.c 2016-08-22 17:38:45.916265249 +0200 +@@ -26,6 +26,7 @@ void use_mm(struct mm_struct *mm) + struct task_struct *tsk = current; + + task_lock(tsk); ++ preempt_disable_rt(); + active_mm = tsk->active_mm; + if (active_mm != mm) { + atomic_inc(&mm->mm_count); +@@ -33,6 +34,7 @@ void use_mm(struct mm_struct *mm) + } + tsk->mm = mm; + switch_mm(active_mm, mm, tsk); ++ preempt_enable_rt(); + task_unlock(tsk); + + if (active_mm != mm) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/mm/page_alloc.c sun8i-rt/mm/page_alloc.c +--- sun8i/mm/page_alloc.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/mm/page_alloc.c 2016-08-22 18:02:26.064281576 +0200 +@@ -58,6 +58,7 @@ + #include + #include + #include ++#include + #include + + #include +@@ -219,6 +220,18 @@ EXPORT_SYMBOL(nr_node_ids); + EXPORT_SYMBOL(nr_online_nodes); + #endif + ++static DEFINE_LOCAL_IRQ_LOCK(pa_lock); ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define cpu_lock_irqsave(cpu, flags) \ ++ local_lock_irqsave_on(pa_lock, flags, cpu) ++# define cpu_unlock_irqrestore(cpu, flags) \ ++ local_unlock_irqrestore_on(pa_lock, flags, cpu) ++#else ++# define cpu_lock_irqsave(cpu, flags) local_irq_save(flags) ++# define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags) ++#endif ++ + int page_group_by_mobility_disabled __read_mostly; + + void set_pageblock_migratetype(struct page *page, int migratetype) +@@ -628,7 +641,7 @@ static inline int free_pages_check(struc + } + + /* +- * Frees a number of pages from the PCP lists ++ * Frees a number of pages which have been collected from the pcp lists. + * Assumes all pages on list are in same zone, and of same order. + * count is the number of pages to free. + * +@@ -639,15 +652,41 @@ static inline int free_pages_check(struc + * pinned" detection logic. + */ + static void free_pcppages_bulk(struct zone *zone, int count, +- struct per_cpu_pages *pcp) ++ struct list_head *list) + { +- int migratetype = 0; +- int batch_free = 0; + int to_free = count; ++ unsigned long flags; + +- spin_lock(&zone->lock); ++ spin_lock_irqsave(&zone->lock, flags); + zone->pages_scanned = 0; + ++ while (!list_empty(list)) { ++ struct page *page = list_first_entry(list, struct page, lru); ++ ++ /* must delete as __free_one_page list manipulates */ ++ list_del(&page->lru); ++ /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ ++ __free_one_page(page, zone, 0, page_private(page)); ++ trace_mm_page_pcpu_drain(page, 0, page_private(page)); ++ to_free--; ++ } ++ WARN_ON(to_free != 0); ++ __mod_zone_page_state(zone, NR_FREE_PAGES, count); ++ spin_unlock_irqrestore(&zone->lock, flags); ++} ++ ++/* ++ * Moves a number of pages from the PCP lists to free list which ++ * is freed outside of the locked region. ++ * ++ * Assumes all pages on list are in same zone, and of same order. ++ * count is the number of pages to free. ++ */ ++static void isolate_pcp_pages(int to_free, struct per_cpu_pages *src, ++ struct list_head *dst) ++{ ++ int migratetype = 0, batch_free = 0; ++ + while (to_free) { + struct page *page; + struct list_head *list; +@@ -663,7 +702,7 @@ static void free_pcppages_bulk(struct zo + batch_free++; + if (++migratetype == MIGRATE_PCPTYPES) + migratetype = 0; +- list = &pcp->lists[migratetype]; ++ list = &src->lists[migratetype]; + } while (list_empty(list)); + + /* This is the only non-empty list. Free them all. */ +@@ -673,33 +712,26 @@ static void free_pcppages_bulk(struct zo + do { + int mt; /* migratetype of the to-be-freed page */ + +- page = list_entry(list->prev, struct page, lru); +- /* must delete as __free_one_page list manipulates */ ++ page = list_last_entry(list, struct page, lru); + list_del(&page->lru); + mt = get_freepage_migratetype(page); +- /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ +- __free_one_page(page, zone, 0, mt); +- trace_mm_page_pcpu_drain(page, 0, mt); +- if (likely(get_pageblock_migratetype(page) != MIGRATE_ISOLATE)) { +- __mod_zone_page_state(zone, NR_FREE_PAGES, 1); +- if (is_migrate_cma(mt)) +- __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1); +- } ++ list_add(&page->lru, dst); + } while (--to_free && --batch_free && !list_empty(list)); + } +- spin_unlock(&zone->lock); + } + + static void free_one_page(struct zone *zone, struct page *page, int order, + int migratetype) + { +- spin_lock(&zone->lock); ++ unsigned long flags; ++ ++ spin_lock_irqsave(&zone->lock, flags); + zone->pages_scanned = 0; + + __free_one_page(page, zone, order, migratetype); + if (unlikely(migratetype != MIGRATE_ISOLATE)) + __mod_zone_freepage_state(zone, 1 << order, migratetype); +- spin_unlock(&zone->lock); ++ spin_unlock_irqrestore(&zone->lock, flags); + } + + static bool free_pages_prepare(struct page *page, unsigned int order) +@@ -736,13 +768,13 @@ static void __free_pages_ok(struct page + if (!free_pages_prepare(page, order)) + return; + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + if (unlikely(wasMlocked)) + free_page_mlock(page); + __count_vm_events(PGFREE, 1 << order); + free_one_page(page_zone(page), page, order, + get_pageblock_migratetype(page)); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + void __meminit __free_pages_bootmem(struct page *page, unsigned int order) +@@ -1218,16 +1250,18 @@ static int rmqueue_bulk(struct zone *zon + void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) + { + unsigned long flags; ++ LIST_HEAD(dst); + int to_drain; + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + if (pcp->count >= pcp->batch) + to_drain = pcp->batch; + else + to_drain = pcp->count; +- free_pcppages_bulk(zone, to_drain, pcp); ++ isolate_pcp_pages(to_drain, pcp, &dst); + pcp->count -= to_drain; +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); ++ free_pcppages_bulk(zone, to_drain, &dst); + } + #endif + +@@ -1246,16 +1280,21 @@ static void drain_pages(unsigned int cpu + for_each_populated_zone(zone) { + struct per_cpu_pageset *pset; + struct per_cpu_pages *pcp; ++ LIST_HEAD(dst); ++ int count; + +- local_irq_save(flags); ++ cpu_lock_irqsave(cpu, flags); + pset = per_cpu_ptr(zone->pageset, cpu); + + pcp = &pset->pcp; +- if (pcp->count) { +- free_pcppages_bulk(zone, pcp->count, pcp); ++ count = pcp->count; ++ if (count) { ++ isolate_pcp_pages(count, pcp, &dst); + pcp->count = 0; + } +- local_irq_restore(flags); ++ cpu_unlock_irqrestore(cpu, flags); ++ if (count) ++ free_pcppages_bulk(zone, count, &dst); + } + } + +@@ -1308,7 +1347,12 @@ void drain_all_pages(void) + else + cpumask_clear_cpu(cpu, &cpus_with_pcps); + } ++#ifndef CONFIG_PREEMPT_RT_BASE + on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1); ++#else ++ for_each_cpu(cpu, &cpus_with_pcps) ++ drain_pages(cpu); ++#endif + } + + #ifdef CONFIG_HIBERNATION +@@ -1364,7 +1408,7 @@ void free_hot_cold_page(struct page *pag + + migratetype = get_pageblock_migratetype(page); + set_freepage_migratetype(page, migratetype); +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + if (unlikely(wasMlocked)) + free_page_mlock(page); + __count_vm_event(PGFREE); +@@ -1392,12 +1436,19 @@ void free_hot_cold_page(struct page *pag + list_add(&page->lru, &pcp->lists[migratetype]); + pcp->count++; + if (pcp->count >= pcp->high) { +- free_pcppages_bulk(zone, pcp->batch, pcp); ++ LIST_HEAD(dst); ++ int count; ++ ++ isolate_pcp_pages(pcp->batch, pcp, &dst); + pcp->count -= pcp->batch; ++ count = pcp->batch; ++ local_unlock_irqrestore(pa_lock, flags); ++ free_pcppages_bulk(zone, count, &dst); ++ return; + } + + out: +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + /* +@@ -1515,7 +1566,7 @@ again: + struct per_cpu_pages *pcp; + struct list_head *list; + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + pcp = &this_cpu_ptr(zone->pageset)->pcp; + list = &pcp->lists[migratetype]; + if (list_empty(list)) { +@@ -1548,21 +1599,23 @@ again: + */ + WARN_ON_ONCE(order > 1); + } +- spin_lock_irqsave(&zone->lock, flags); ++ local_spin_lock_irqsave(pa_lock, &zone->lock, flags); + if (gfp_flags & __GFP_CMA) + page = __rmqueue_cma(zone, order, migratetype); + else + page = __rmqueue(zone, order, migratetype); +- spin_unlock(&zone->lock); +- if (!page) ++ if (!page) { ++ spin_unlock(&zone->lock); + goto failed; ++ } + __mod_zone_freepage_state(zone, -(1 << order), + get_pageblock_migratetype(page)); ++ spin_unlock(&zone->lock); + } + + __count_zone_vm_events(PGALLOC, zone, 1 << order); + zone_statistics(preferred_zone, zone, gfp_flags); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + + VM_BUG_ON(bad_range(zone, page)); + if (prep_new_page(page, order, gfp_flags)) +@@ -1570,7 +1623,7 @@ again: + return page; + + failed: +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + return NULL; + } + +@@ -2185,8 +2238,8 @@ __alloc_pages_direct_compact(gfp_t gfp_m + if (*did_some_progress != COMPACT_SKIPPED) { + + /* Page migration frees to the PCP lists but we want merging */ +- drain_pages(get_cpu()); +- put_cpu(); ++ drain_pages(get_cpu_light()); ++ put_cpu_light(); + + page = get_page_from_freelist(gfp_mask, nodemask, + order, zonelist, high_zoneidx, +@@ -4063,14 +4116,16 @@ static int __zone_pcp_update(void *data) + for_each_possible_cpu(cpu) { + struct per_cpu_pageset *pset; + struct per_cpu_pages *pcp; ++ LIST_HEAD(dst); + + pset = per_cpu_ptr(zone->pageset, cpu); + pcp = &pset->pcp; + +- local_irq_save(flags); +- free_pcppages_bulk(zone, pcp->count, pcp); ++ cpu_lock_irqsave(cpu, flags); ++ isolate_pcp_pages(pcp->count, pcp, &dst); ++ free_pcppages_bulk(zone, pcp->count, &dst); + setup_pageset(pset, batch); +- local_irq_restore(flags); ++ cpu_unlock_irqrestore(cpu, flags); + } + return 0; + } +@@ -5101,6 +5156,7 @@ static int page_alloc_cpu_notify(struct + void __init page_alloc_init(void) + { + hotcpu_notifier(page_alloc_cpu_notify, 0); ++ local_irq_lock_init(pa_lock); + } + + /* +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/mm/page_cgroup.c sun8i-rt/mm/page_cgroup.c +--- sun8i/mm/page_cgroup.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/mm/page_cgroup.c 2016-08-22 16:33:41.596220362 +0200 +@@ -13,6 +13,14 @@ + + static unsigned long total_usage; + ++static void page_cgroup_lock_init(struct page_cgroup *pc, int nr_pages) ++{ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ for (; nr_pages; nr_pages--, pc++) ++ spin_lock_init(&pc->pcg_lock); ++#endif ++} ++ + #if !defined(CONFIG_SPARSEMEM) + + +@@ -60,6 +68,7 @@ static int __init alloc_node_page_cgroup + return -ENOMEM; + NODE_DATA(nid)->node_page_cgroup = base; + total_usage += table_size; ++ page_cgroup_lock_init(base, nr_pages); + return 0; + } + +@@ -150,6 +159,8 @@ static int __meminit init_section_page_c + return -ENOMEM; + } + ++ page_cgroup_lock_init(base, PAGES_PER_SECTION); ++ + /* + * The passed "pfn" may not be aligned to SECTION. For the calculation + * we need to apply a mask. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/mm/slab.c sun8i-rt/mm/slab.c +--- sun8i/mm/slab.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/mm/slab.c 2016-08-22 18:03:15.932282149 +0200 +@@ -116,6 +116,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -611,6 +612,12 @@ int slab_is_available(void) + return g_cpucache_up >= EARLY; + } + ++/* ++ * Guard access to the cache-chain. ++ */ ++static DEFINE_MUTEX(cache_chain_mutex); ++static struct list_head cache_chain; ++ + #ifdef CONFIG_LOCKDEP + + /* +@@ -672,38 +679,41 @@ static void slab_set_debugobj_lock_class + slab_set_debugobj_lock_classes_node(cachep, node); + } + +-static void init_node_lock_keys(int q) ++static void init_lock_keys(struct kmem_cache *cachep, int node) + { +- struct cache_sizes *s = malloc_sizes; ++ struct kmem_list3 *l3; + + if (g_cpucache_up < LATE) + return; + +- for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) { +- struct kmem_list3 *l3; ++ l3 = cachep->nodelists[node]; ++ if (!l3 || OFF_SLAB(cachep)) ++ return; + +- l3 = s->cs_cachep->nodelists[q]; +- if (!l3 || OFF_SLAB(s->cs_cachep)) +- continue; ++ slab_set_lock_classes(cachep, &on_slab_l3_key, &on_slab_alc_key, node); ++} + +- slab_set_lock_classes(s->cs_cachep, &on_slab_l3_key, +- &on_slab_alc_key, q); +- } ++static void init_node_lock_keys(int node) ++{ ++ struct kmem_cache *cachep; ++ ++ list_for_each_entry(cachep, &cache_chain, next) ++ init_lock_keys(cachep, node); + } + +-static inline void init_lock_keys(void) ++static inline void init_cachep_lock_keys(struct kmem_cache *cachep) + { + int node; + + for_each_node(node) +- init_node_lock_keys(node); ++ init_lock_keys(cachep, node); + } + #else +-static void init_node_lock_keys(int q) ++static void init_node_lock_keys(int node) + { + } + +-static inline void init_lock_keys(void) ++static void init_cachep_lock_keys(struct kmem_cache *cachep) + { + } + +@@ -716,19 +726,79 @@ static void slab_set_debugobj_lock_class + } + #endif + ++static DEFINE_PER_CPU(struct delayed_work, slab_reap_work); ++static DEFINE_PER_CPU(struct list_head, slab_free_list); ++static DEFINE_LOCAL_IRQ_LOCK(slab_lock); ++ ++#ifndef CONFIG_PREEMPT_RT_BASE ++# define slab_on_each_cpu(func, cp) on_each_cpu(func, cp, 1) ++#else + /* +- * Guard access to the cache-chain. ++ * execute func() for all CPUs. On PREEMPT_RT we dont actually have ++ * to run on the remote CPUs - we only have to take their CPU-locks. ++ * (This is a rare operation, so cacheline bouncing is not an issue.) + */ +-static DEFINE_MUTEX(cache_chain_mutex); +-static struct list_head cache_chain; ++static void ++slab_on_each_cpu(void (*func)(void *arg, int this_cpu), void *arg) ++{ ++ unsigned int i; + +-static DEFINE_PER_CPU(struct delayed_work, slab_reap_work); ++ get_cpu_light(); ++ for_each_online_cpu(i) ++ func(arg, i); ++ put_cpu_light(); ++} ++ ++static void lock_slab_on(unsigned int cpu) ++{ ++ local_lock_irq_on(slab_lock, cpu); ++} ++ ++static void unlock_slab_on(unsigned int cpu) ++{ ++ local_unlock_irq_on(slab_lock, cpu); ++} ++#endif ++ ++static void free_delayed(struct list_head *h) ++{ ++ while(!list_empty(h)) { ++ struct page *page = list_first_entry(h, struct page, lru); ++ ++ list_del(&page->lru); ++ __free_pages(page, page->index); ++ } ++} ++ ++static void unlock_l3_and_free_delayed(spinlock_t *list_lock) ++{ ++ LIST_HEAD(tmp); ++ ++ list_splice_init(&__get_cpu_var(slab_free_list), &tmp); ++ local_spin_unlock_irq(slab_lock, list_lock); ++ free_delayed(&tmp); ++} ++ ++static void unlock_slab_and_free_delayed(unsigned long flags) ++{ ++ LIST_HEAD(tmp); ++ ++ list_splice_init(&__get_cpu_var(slab_free_list), &tmp); ++ local_unlock_irqrestore(slab_lock, flags); ++ free_delayed(&tmp); ++} + + static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) + { + return cachep->array[smp_processor_id()]; + } + ++static inline struct array_cache *cpu_cache_get_on_cpu(struct kmem_cache *cachep, ++ int cpu) ++{ ++ return cachep->array[cpu]; ++} ++ + static inline struct kmem_cache *__find_general_cachep(size_t size, + gfp_t gfpflags) + { +@@ -1077,9 +1147,10 @@ static void reap_alien(struct kmem_cache + if (l3->alien) { + struct array_cache *ac = l3->alien[node]; + +- if (ac && ac->avail && spin_trylock_irq(&ac->lock)) { ++ if (ac && ac->avail && ++ local_spin_trylock_irq(slab_lock, &ac->lock)) { + __drain_alien_cache(cachep, ac, node); +- spin_unlock_irq(&ac->lock); ++ local_spin_unlock_irq(slab_lock, &ac->lock); + } + } + } +@@ -1094,9 +1165,9 @@ static void drain_alien_cache(struct kme + for_each_online_node(i) { + ac = alien[i]; + if (ac) { +- spin_lock_irqsave(&ac->lock, flags); ++ local_spin_lock_irqsave(slab_lock, &ac->lock, flags); + __drain_alien_cache(cachep, ac, i); +- spin_unlock_irqrestore(&ac->lock, flags); ++ local_spin_unlock_irqrestore(slab_lock, &ac->lock, flags); + } + } + } +@@ -1175,11 +1246,11 @@ static int init_cache_nodelists_node(int + cachep->nodelists[node] = l3; + } + +- spin_lock_irq(&cachep->nodelists[node]->list_lock); ++ local_spin_lock_irq(slab_lock, &cachep->nodelists[node]->list_lock); + cachep->nodelists[node]->free_limit = + (1 + nr_cpus_node(node)) * + cachep->batchcount + cachep->num; +- spin_unlock_irq(&cachep->nodelists[node]->list_lock); ++ local_spin_unlock_irq(slab_lock, &cachep->nodelists[node]->list_lock); + } + return 0; + } +@@ -1204,7 +1275,7 @@ static void __cpuinit cpuup_canceled(lon + if (!l3) + goto free_array_cache; + +- spin_lock_irq(&l3->list_lock); ++ local_spin_lock_irq(slab_lock, &l3->list_lock); + + /* Free limit for this kmem_list3 */ + l3->free_limit -= cachep->batchcount; +@@ -1212,7 +1283,7 @@ static void __cpuinit cpuup_canceled(lon + free_block(cachep, nc->entry, nc->avail, node); + + if (!cpumask_empty(mask)) { +- spin_unlock_irq(&l3->list_lock); ++ unlock_l3_and_free_delayed(&l3->list_lock); + goto free_array_cache; + } + +@@ -1226,7 +1297,7 @@ static void __cpuinit cpuup_canceled(lon + alien = l3->alien; + l3->alien = NULL; + +- spin_unlock_irq(&l3->list_lock); ++ unlock_l3_and_free_delayed(&l3->list_lock); + + kfree(shared); + if (alien) { +@@ -1300,7 +1371,7 @@ static int __cpuinit cpuup_prepare(long + l3 = cachep->nodelists[node]; + BUG_ON(!l3); + +- spin_lock_irq(&l3->list_lock); ++ local_spin_lock_irq(slab_lock, &l3->list_lock); + if (!l3->shared) { + /* + * We are serialised from CPU_DEAD or +@@ -1315,7 +1386,7 @@ static int __cpuinit cpuup_prepare(long + alien = NULL; + } + #endif +- spin_unlock_irq(&l3->list_lock); ++ local_spin_unlock_irq(slab_lock, &l3->list_lock); + kfree(shared); + free_alien_cache(alien); + if (cachep->flags & SLAB_DEBUG_OBJECTS) +@@ -1506,6 +1577,10 @@ void __init kmem_cache_init(void) + if (num_possible_nodes() == 1) + use_alien_caches = 0; + ++ local_irq_lock_init(slab_lock); ++ for_each_possible_cpu(i) ++ INIT_LIST_HEAD(&per_cpu(slab_free_list, i)); ++ + for (i = 0; i < NUM_INIT_LISTS; i++) { + kmem_list3_init(&initkmem_list3[i]); + if (i < MAX_NUMNODES) +@@ -1687,14 +1762,13 @@ void __init kmem_cache_init_late(void) + + /* 6) resize the head arrays to their final sizes */ + mutex_lock(&cache_chain_mutex); +- list_for_each_entry(cachep, &cache_chain, next) ++ list_for_each_entry(cachep, &cache_chain, next) { + if (enable_cpucache(cachep, GFP_NOWAIT)) + BUG(); ++ init_cachep_lock_keys(cachep); ++ } + mutex_unlock(&cache_chain_mutex); + +- /* Annotate slab for lockdep -- annotate the malloc caches */ +- init_lock_keys(); +- + /* Done! */ + g_cpucache_up = FULL; + +@@ -1834,12 +1908,14 @@ static void *kmem_getpages(struct kmem_c + /* + * Interface to system's page release. + */ +-static void kmem_freepages(struct kmem_cache *cachep, void *addr) ++static void kmem_freepages(struct kmem_cache *cachep, void *addr, bool delayed) + { + unsigned long i = (1 << cachep->gfporder); +- struct page *page = virt_to_page(addr); ++ struct page *page, *basepage = virt_to_page(addr); + const unsigned long nr_freed = i; + ++ page = basepage; ++ + kmemcheck_free_shadow(page, cachep->gfporder); + + if (cachep->flags & SLAB_RECLAIM_ACCOUNT) +@@ -1855,7 +1931,13 @@ static void kmem_freepages(struct kmem_c + } + if (current->reclaim_state) + current->reclaim_state->reclaimed_slab += nr_freed; +- free_pages((unsigned long)addr, cachep->gfporder); ++ ++ if (!delayed) { ++ free_pages((unsigned long)addr, cachep->gfporder); ++ } else { ++ basepage->index = cachep->gfporder; ++ list_add(&basepage->lru, &__get_cpu_var(slab_free_list)); ++ } + } + + static void kmem_rcu_free(struct rcu_head *head) +@@ -1863,7 +1945,7 @@ static void kmem_rcu_free(struct rcu_hea + struct slab_rcu *slab_rcu = (struct slab_rcu *)head; + struct kmem_cache *cachep = slab_rcu->cachep; + +- kmem_freepages(cachep, slab_rcu->addr); ++ kmem_freepages(cachep, slab_rcu->addr, false); + if (OFF_SLAB(cachep)) + kmem_cache_free(cachep->slabp_cache, slab_rcu); + } +@@ -2082,7 +2164,8 @@ static void slab_destroy_debugcheck(stru + * Before calling the slab must have been unlinked from the cache. The + * cache-lock is not held/needed. + */ +-static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp) ++static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp, ++ bool delayed) + { + void *addr = slabp->s_mem - slabp->colouroff; + +@@ -2095,7 +2178,7 @@ static void slab_destroy(struct kmem_cac + slab_rcu->addr = addr; + call_rcu(&slab_rcu->head, kmem_rcu_free); + } else { +- kmem_freepages(cachep, addr); ++ kmem_freepages(cachep, addr, delayed); + if (OFF_SLAB(cachep)) + kmem_cache_free(cachep->slabp_cache, slabp); + } +@@ -2544,6 +2627,8 @@ kmem_cache_create (const char *name, siz + slab_set_debugobj_lock_classes(cachep); + } + ++ init_cachep_lock_keys(cachep); ++ + /* cache setup completed, link it into the list */ + list_add(&cachep->next, &cache_chain); + oops: +@@ -2561,7 +2646,7 @@ EXPORT_SYMBOL(kmem_cache_create); + #if DEBUG + static void check_irq_off(void) + { +- BUG_ON(!irqs_disabled()); ++ BUG_ON_NONRT(!irqs_disabled()); + } + + static void check_irq_on(void) +@@ -2596,26 +2681,43 @@ static void drain_array(struct kmem_cach + struct array_cache *ac, + int force, int node); + +-static void do_drain(void *arg) ++static void __do_drain(void *arg, unsigned int cpu) + { + struct kmem_cache *cachep = arg; + struct array_cache *ac; +- int node = numa_mem_id(); ++ int node = cpu_to_mem(cpu); + +- check_irq_off(); +- ac = cpu_cache_get(cachep); ++ ac = cpu_cache_get_on_cpu(cachep, cpu); + spin_lock(&cachep->nodelists[node]->list_lock); + free_block(cachep, ac->entry, ac->avail, node); + spin_unlock(&cachep->nodelists[node]->list_lock); + ac->avail = 0; + } + ++#ifndef CONFIG_PREEMPT_RT_BASE ++static void do_drain(void *arg) ++{ ++ __do_drain(arg, smp_processor_id()); ++} ++#else ++static void do_drain(void *arg, int cpu) ++{ ++ LIST_HEAD(tmp); ++ ++ lock_slab_on(cpu); ++ __do_drain(arg, cpu); ++ list_splice_init(&per_cpu(slab_free_list, cpu), &tmp); ++ unlock_slab_on(cpu); ++ free_delayed(&tmp); ++} ++#endif ++ + static void drain_cpu_caches(struct kmem_cache *cachep) + { + struct kmem_list3 *l3; + int node; + +- on_each_cpu(do_drain, cachep, 1); ++ slab_on_each_cpu(do_drain, cachep); + check_irq_on(); + for_each_online_node(node) { + l3 = cachep->nodelists[node]; +@@ -2646,10 +2748,10 @@ static int drain_freelist(struct kmem_ca + nr_freed = 0; + while (nr_freed < tofree && !list_empty(&l3->slabs_free)) { + +- spin_lock_irq(&l3->list_lock); ++ local_spin_lock_irq(slab_lock, &l3->list_lock); + p = l3->slabs_free.prev; + if (p == &l3->slabs_free) { +- spin_unlock_irq(&l3->list_lock); ++ local_spin_unlock_irq(slab_lock, &l3->list_lock); + goto out; + } + +@@ -2663,8 +2765,8 @@ static int drain_freelist(struct kmem_ca + * to the cache. + */ + l3->free_objects -= cache->num; +- spin_unlock_irq(&l3->list_lock); +- slab_destroy(cache, slabp); ++ local_spin_unlock_irq(slab_lock, &l3->list_lock); ++ slab_destroy(cache, slabp, false); + nr_freed++; + } + out: +@@ -2958,7 +3060,7 @@ static int cache_grow(struct kmem_cache + offset *= cachep->colour_off; + + if (local_flags & __GFP_WAIT) +- local_irq_enable(); ++ local_unlock_irq(slab_lock); + + /* + * The test for missing atomic flag is performed here, rather than +@@ -2988,7 +3090,7 @@ static int cache_grow(struct kmem_cache + cache_init_objs(cachep, slabp); + + if (local_flags & __GFP_WAIT) +- local_irq_disable(); ++ local_lock_irq(slab_lock); + check_irq_off(); + spin_lock(&l3->list_lock); + +@@ -2999,10 +3101,10 @@ static int cache_grow(struct kmem_cache + spin_unlock(&l3->list_lock); + return 1; + opps1: +- kmem_freepages(cachep, objp); ++ kmem_freepages(cachep, objp, false); + failed: + if (local_flags & __GFP_WAIT) +- local_irq_disable(); ++ local_lock_irq(slab_lock); + return 0; + } + +@@ -3396,11 +3498,11 @@ retry: + * set and go into memory reserves if necessary. + */ + if (local_flags & __GFP_WAIT) +- local_irq_enable(); ++ local_unlock_irq(slab_lock); + kmem_flagcheck(cache, flags); + obj = kmem_getpages(cache, local_flags, numa_mem_id()); + if (local_flags & __GFP_WAIT) +- local_irq_disable(); ++ local_lock_irq(slab_lock); + if (obj) { + /* + * Insert into the appropriate per node queues +@@ -3518,7 +3620,7 @@ __cache_alloc_node(struct kmem_cache *ca + return NULL; + + cache_alloc_debugcheck_before(cachep, flags); +- local_irq_save(save_flags); ++ local_lock_irqsave(slab_lock, save_flags); + + if (nodeid == NUMA_NO_NODE) + nodeid = slab_node; +@@ -3543,7 +3645,7 @@ __cache_alloc_node(struct kmem_cache *ca + /* ___cache_alloc_node can fall back to other nodes */ + ptr = ____cache_alloc_node(cachep, flags, nodeid); + out: +- local_irq_restore(save_flags); ++ local_unlock_irqrestore(slab_lock, save_flags); + ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller); + kmemleak_alloc_recursive(ptr, obj_size(cachep), 1, cachep->flags, + flags); +@@ -3603,9 +3705,9 @@ __cache_alloc(struct kmem_cache *cachep, + return NULL; + + cache_alloc_debugcheck_before(cachep, flags); +- local_irq_save(save_flags); ++ local_lock_irqsave(slab_lock, save_flags); + objp = __do_cache_alloc(cachep, flags); +- local_irq_restore(save_flags); ++ local_unlock_irqrestore(slab_lock, save_flags); + objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller); + kmemleak_alloc_recursive(objp, obj_size(cachep), 1, cachep->flags, + flags); +@@ -3653,7 +3755,7 @@ static void free_block(struct kmem_cache + * a different cache, refer to comments before + * alloc_slabmgmt. + */ +- slab_destroy(cachep, slabp); ++ slab_destroy(cachep, slabp, true); + } else { + list_add(&slabp->list, &l3->slabs_free); + } +@@ -3915,12 +4017,12 @@ void kmem_cache_free(struct kmem_cache * + { + unsigned long flags; + +- local_irq_save(flags); + debug_check_no_locks_freed(objp, obj_size(cachep)); + if (!(cachep->flags & SLAB_DEBUG_OBJECTS)) + debug_check_no_obj_freed(objp, obj_size(cachep)); ++ local_lock_irqsave(slab_lock, flags); + __cache_free(cachep, objp, __builtin_return_address(0)); +- local_irq_restore(flags); ++ unlock_slab_and_free_delayed(flags); + + trace_kmem_cache_free(_RET_IP_, objp); + } +@@ -3944,13 +4046,13 @@ void kfree(const void *objp) + + if (unlikely(ZERO_OR_NULL_PTR(objp))) + return; +- local_irq_save(flags); + kfree_debugcheck(objp); + c = virt_to_cache(objp); + debug_check_no_locks_freed(objp, obj_size(c)); + debug_check_no_obj_freed(objp, obj_size(c)); ++ local_lock_irqsave(slab_lock, flags); + __cache_free(c, (void *)objp, __builtin_return_address(0)); +- local_irq_restore(flags); ++ unlock_slab_and_free_delayed(flags); + } + EXPORT_SYMBOL(kfree); + +@@ -3993,7 +4095,7 @@ static int alloc_kmemlist(struct kmem_ca + if (l3) { + struct array_cache *shared = l3->shared; + +- spin_lock_irq(&l3->list_lock); ++ local_spin_lock_irq(slab_lock, &l3->list_lock); + + if (shared) + free_block(cachep, shared->entry, +@@ -4006,7 +4108,8 @@ static int alloc_kmemlist(struct kmem_ca + } + l3->free_limit = (1 + nr_cpus_node(node)) * + cachep->batchcount + cachep->num; +- spin_unlock_irq(&l3->list_lock); ++ unlock_l3_and_free_delayed(&l3->list_lock); ++ + kfree(shared); + free_alien_cache(new_alien); + continue; +@@ -4053,18 +4156,31 @@ struct ccupdate_struct { + struct array_cache *new[0]; + }; + +-static void do_ccupdate_local(void *info) ++static void __do_ccupdate_local(void *info, int cpu) + { + struct ccupdate_struct *new = info; + struct array_cache *old; + +- check_irq_off(); +- old = cpu_cache_get(new->cachep); ++ old = cpu_cache_get_on_cpu(new->cachep, cpu); + +- new->cachep->array[smp_processor_id()] = new->new[smp_processor_id()]; +- new->new[smp_processor_id()] = old; ++ new->cachep->array[cpu] = new->new[cpu]; ++ new->new[cpu] = old; + } + ++#ifndef CONFIG_PREEMPT_RT_BASE ++static void do_ccupdate_local(void *info) ++{ ++ __do_ccupdate_local(info, smp_processor_id()); ++} ++#else ++static void do_ccupdate_local(void *info, int cpu) ++{ ++ lock_slab_on(cpu); ++ __do_ccupdate_local(info, cpu); ++ unlock_slab_on(cpu); ++} ++#endif ++ + /* Always called with the cache_chain_mutex held */ + static int do_tune_cpucache(struct kmem_cache *cachep, int limit, + int batchcount, int shared, gfp_t gfp) +@@ -4089,7 +4205,7 @@ static int do_tune_cpucache(struct kmem_ + } + new->cachep = cachep; + +- on_each_cpu(do_ccupdate_local, (void *)new, 1); ++ slab_on_each_cpu(do_ccupdate_local, (void *)new); + + check_irq_on(); + cachep->batchcount = batchcount; +@@ -4100,9 +4216,11 @@ static int do_tune_cpucache(struct kmem_ + struct array_cache *ccold = new->new[i]; + if (!ccold) + continue; +- spin_lock_irq(&cachep->nodelists[cpu_to_mem(i)]->list_lock); ++ local_spin_lock_irq(slab_lock, ++ &cachep->nodelists[cpu_to_mem(i)]->list_lock); + free_block(cachep, ccold->entry, ccold->avail, cpu_to_mem(i)); +- spin_unlock_irq(&cachep->nodelists[cpu_to_mem(i)]->list_lock); ++ ++ unlock_l3_and_free_delayed(&cachep->nodelists[cpu_to_mem(i)]->list_lock); + kfree(ccold); + } + kfree(new); +@@ -4178,7 +4296,7 @@ static void drain_array(struct kmem_cach + if (ac->touched && !force) { + ac->touched = 0; + } else { +- spin_lock_irq(&l3->list_lock); ++ local_spin_lock_irq(slab_lock, &l3->list_lock); + if (ac->avail) { + tofree = force ? ac->avail : (ac->limit + 4) / 5; + if (tofree > ac->avail) +@@ -4188,7 +4306,7 @@ static void drain_array(struct kmem_cach + memmove(ac->entry, &(ac->entry[tofree]), + sizeof(void *) * ac->avail); + } +- spin_unlock_irq(&l3->list_lock); ++ local_spin_unlock_irq(slab_lock, &l3->list_lock); + } + } + +@@ -4327,7 +4445,7 @@ static int s_show(struct seq_file *m, vo + continue; + + check_irq_on(); +- spin_lock_irq(&l3->list_lock); ++ local_spin_lock_irq(slab_lock, &l3->list_lock); + + list_for_each_entry(slabp, &l3->slabs_full, list) { + if (slabp->inuse != cachep->num && !error) +@@ -4352,7 +4470,7 @@ static int s_show(struct seq_file *m, vo + if (l3->shared) + shared_avail += l3->shared->avail; + +- spin_unlock_irq(&l3->list_lock); ++ local_spin_unlock_irq(slab_lock, &l3->list_lock); + } + num_slabs += active_slabs; + num_objs = num_slabs * cachep->num; +@@ -4581,13 +4699,13 @@ static int leaks_show(struct seq_file *m + continue; + + check_irq_on(); +- spin_lock_irq(&l3->list_lock); ++ local_spin_lock_irq(slab_lock, &l3->list_lock); + + list_for_each_entry(slabp, &l3->slabs_full, list) + handle_slab(n, cachep, slabp); + list_for_each_entry(slabp, &l3->slabs_partial, list) + handle_slab(n, cachep, slabp); +- spin_unlock_irq(&l3->list_lock); ++ local_spin_unlock_irq(slab_lock, &l3->list_lock); + } + name = cachep->name; + if (n[0] == n[1]) { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/mm/slub.c sun8i-rt/mm/slub.c +--- sun8i/mm/slub.c 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/mm/slub.c 2016-08-22 18:25:53.240297754 +0200 +@@ -1266,6 +1266,14 @@ static inline void slab_free_hook(struct + + #endif /* CONFIG_SLUB_DEBUG */ + ++static void setup_object(struct kmem_cache *s, struct page *page, ++ void *object) ++{ ++ setup_object_debug(s, page, object); ++ if (unlikely(s->ctor)) ++ s->ctor(object); ++} ++ + /* + * Slab allocation and freeing + */ +@@ -1287,6 +1295,8 @@ static struct page *allocate_slab(struct + struct page *page; + struct kmem_cache_order_objects oo = s->oo; + gfp_t alloc_gfp; ++ void *start, *last, *p; ++ int idx, order; + + flags &= gfp_allowed_mask; + +@@ -1309,17 +1319,11 @@ static struct page *allocate_slab(struct + * Try a lower order alloc if possible + */ + page = alloc_slab_page(flags, node, oo); +- +- if (page) +- stat(s, ORDER_FALLBACK); ++ if (unlikely(!page)) ++ goto out; ++ stat(s, ORDER_FALLBACK); + } + +- if (flags & __GFP_WAIT) +- local_irq_disable(); +- +- if (!page) +- return NULL; +- + if (kmemcheck_enabled + && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) { + int pages = 1 << oo_order(oo); +@@ -1337,37 +1341,6 @@ static struct page *allocate_slab(struct + } + + page->objects = oo_objects(oo); +- mod_zone_page_state(page_zone(page), +- (s->flags & SLAB_RECLAIM_ACCOUNT) ? +- NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE, +- 1 << oo_order(oo)); +- +- return page; +-} +- +-static void setup_object(struct kmem_cache *s, struct page *page, +- void *object) +-{ +- setup_object_debug(s, page, object); +- if (unlikely(s->ctor)) +- s->ctor(object); +-} +- +-static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) +-{ +- struct page *page; +- void *start; +- void *last; +- void *p; +- +- BUG_ON(flags & GFP_SLAB_BUG_MASK); +- +- page = allocate_slab(s, +- flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node); +- if (!page) +- goto out; +- +- inc_slabs_node(s, page_to_nid(page), page->objects); + page->slab = s; + page->flags |= 1 << PG_slab; + +@@ -1388,10 +1361,34 @@ static struct page *new_slab(struct kmem + page->freelist = start; + page->inuse = page->objects; + page->frozen = 1; ++ + out: ++ if (flags & __GFP_WAIT) ++ local_irq_disable(); ++ if (!page) ++ return NULL; ++ ++ mod_zone_page_state(page_zone(page), ++ (s->flags & SLAB_RECLAIM_ACCOUNT) ? ++ NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE, ++ 1 << oo_order(oo)); ++ ++ inc_slabs_node(s, page_to_nid(page), page->objects); ++ + return page; + } + ++static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) ++{ ++ if (unlikely(flags & GFP_SLAB_BUG_MASK)) { ++ pr_emerg("gfp: %u\n", flags & GFP_SLAB_BUG_MASK); ++ BUG(); ++ } ++ ++ return allocate_slab(s, ++ flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node); ++} ++ + static void __free_slab(struct kmem_cache *s, struct page *page) + { + int order = compound_order(page); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/mm/swap.c sun8i-rt/mm/swap.c +--- sun8i/mm/swap.c 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/mm/swap.c 2016-08-22 18:12:03.120288210 +0200 +@@ -31,6 +31,7 @@ + #include + #include + #include ++#include + + #include "internal.h" + +@@ -41,6 +42,9 @@ static DEFINE_PER_CPU(struct pagevec[NR_ + static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); + static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs); + ++static DEFINE_LOCAL_IRQ_LOCK(rotate_lock); ++static DEFINE_LOCAL_IRQ_LOCK(swapvec_lock); ++ + /* + * This path almost never happens for VM activity - pages are normally + * freed via pagevecs. But it gets used by networking. +@@ -344,11 +348,11 @@ void rotate_reclaimable_page(struct page + unsigned long flags; + + page_cache_get(page); +- local_irq_save(flags); ++ local_lock_irqsave(rotate_lock, flags); + pvec = &__get_cpu_var(lru_rotate_pvecs); + if (!pagevec_add(pvec, page)) + pagevec_move_tail(pvec); +- local_irq_restore(flags); ++ local_unlock_irqrestore(rotate_lock, flags); + } + } + +@@ -404,12 +408,13 @@ static void activate_page_drain(int cpu) + void activate_page(struct page *page) + { + if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { +- struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ activate_page_pvecs); + + page_cache_get(page); + if (!pagevec_add(pvec, page)) + pagevec_lru_move_fn(pvec, __activate_page, NULL); +- put_cpu_var(activate_page_pvecs); ++ put_locked_var(swapvec_lock, activate_page_pvecs); + } + } + +@@ -449,12 +454,12 @@ EXPORT_SYMBOL(mark_page_accessed); + + void __lru_cache_add(struct page *page, enum lru_list lru) + { +- struct pagevec *pvec = &get_cpu_var(lru_add_pvecs)[lru]; ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvecs)[lru]; + + page_cache_get(page); + if (!pagevec_add(pvec, page)) + __pagevec_lru_add(pvec, lru); +- put_cpu_var(lru_add_pvecs); ++ put_locked_var(swapvec_lock, lru_add_pvecs); + } + EXPORT_SYMBOL(__lru_cache_add); + +@@ -589,9 +594,9 @@ void lru_add_drain_cpu(int cpu) + unsigned long flags; + + /* No harm done if a racing interrupt already did this */ +- local_irq_save(flags); ++ local_lock_irqsave(rotate_lock, flags); + pagevec_move_tail(pvec); +- local_irq_restore(flags); ++ local_unlock_irqrestore(rotate_lock, flags); + } + + pvec = &per_cpu(lru_deactivate_pvecs, cpu); +@@ -619,18 +624,19 @@ void deactivate_page(struct page *page) + return; + + if (likely(get_page_unless_zero(page))) { +- struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ lru_deactivate_pvecs); + + if (!pagevec_add(pvec, page)) + pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); +- put_cpu_var(lru_deactivate_pvecs); ++ put_locked_var(swapvec_lock, lru_deactivate_pvecs); + } + } + + void lru_add_drain(void) + { +- lru_add_drain_cpu(get_cpu()); +- put_cpu(); ++ lru_add_drain_cpu(local_lock_cpu(swapvec_lock)); ++ local_unlock_cpu(swapvec_lock); + } + + static void lru_add_drain_per_cpu(struct work_struct *dummy) +@@ -837,6 +843,15 @@ unsigned pagevec_lookup_tag(struct pagev + } + EXPORT_SYMBOL(pagevec_lookup_tag); + ++/* Early setup for the local locks */ ++static int __init swap_init_locks(void) ++{ ++ local_irq_lock_init(rotate_lock); ++ local_irq_lock_init(swapvec_lock); ++ return 1; ++} ++early_initcall(swap_init_locks); ++ + /* + * Perform any setup for the swap system + */ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/mm/vmalloc.c sun8i-rt/mm/vmalloc.c +--- sun8i/mm/vmalloc.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/mm/vmalloc.c 2016-08-22 17:42:28.756267811 +0200 +@@ -788,7 +788,7 @@ static struct vmap_block *new_vmap_block + struct vmap_block *vb; + struct vmap_area *va; + unsigned long vb_idx; +- int node, err; ++ int node, err, cpu; + + node = numa_node_id(); + +@@ -827,12 +827,13 @@ static struct vmap_block *new_vmap_block + BUG_ON(err); + radix_tree_preload_end(); + +- vbq = &get_cpu_var(vmap_block_queue); ++ cpu = get_cpu_light(); ++ vbq = &__get_cpu_var(vmap_block_queue); + vb->vbq = vbq; + spin_lock(&vbq->lock); + list_add_rcu(&vb->free_list, &vbq->free); + spin_unlock(&vbq->lock); +- put_cpu_var(vmap_block_queue); ++ put_cpu_light(); + + return vb; + } +@@ -906,7 +907,7 @@ static void *vb_alloc(unsigned long size + struct vmap_block *vb; + unsigned long addr = 0; + unsigned int order; +- int purge = 0; ++ int purge = 0, cpu; + + BUG_ON(size & ~PAGE_MASK); + BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); +@@ -914,7 +915,8 @@ static void *vb_alloc(unsigned long size + + again: + rcu_read_lock(); +- vbq = &get_cpu_var(vmap_block_queue); ++ cpu = get_cpu_light(); ++ vbq = &__get_cpu_var(vmap_block_queue); + list_for_each_entry_rcu(vb, &vbq->free, free_list) { + int i; + +@@ -951,7 +953,7 @@ next: + if (purge) + purge_fragmented_blocks_thiscpu(); + +- put_cpu_var(vmap_block_queue); ++ put_cpu_light(); + rcu_read_unlock(); + + if (!addr) { +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/mm/vmstat.c sun8i-rt/mm/vmstat.c +--- sun8i/mm/vmstat.c 2016-08-22 14:14:42.000000000 +0200 ++++ sun8i-rt/mm/vmstat.c 2016-08-22 17:05:41.752242437 +0200 +@@ -219,6 +219,7 @@ void __mod_zone_page_state(struct zone * + long x; + long t; + ++ preempt_disable_rt(); + x = delta + __this_cpu_read(*p); + + t = __this_cpu_read(pcp->stat_threshold); +@@ -228,6 +229,7 @@ void __mod_zone_page_state(struct zone * + x = 0; + } + __this_cpu_write(*p, x); ++ preempt_enable_rt(); + } + EXPORT_SYMBOL(__mod_zone_page_state); + +@@ -260,6 +262,7 @@ void __inc_zone_state(struct zone *zone, + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { +@@ -268,6 +271,7 @@ void __inc_zone_state(struct zone *zone, + zone_page_state_add(v + overstep, zone, item); + __this_cpu_write(*p, -overstep); + } ++ preempt_enable_rt(); + } + + void __inc_zone_page_state(struct page *page, enum zone_stat_item item) +@@ -282,6 +286,7 @@ void __dec_zone_state(struct zone *zone, + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { +@@ -290,6 +295,7 @@ void __dec_zone_state(struct zone *zone, + zone_page_state_add(v - overstep, zone, item); + __this_cpu_write(*p, overstep); + } ++ preempt_enable_rt(); + } + + void __dec_zone_page_state(struct page *page, enum zone_stat_item item) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/net/core/dev.c sun8i-rt/net/core/dev.c +--- sun8i/net/core/dev.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/net/core/dev.c 2016-08-22 18:27:06.568298597 +0200 +@@ -220,14 +220,14 @@ static inline struct hlist_head *dev_ind + static inline void rps_lock(struct softnet_data *sd) + { + #ifdef CONFIG_RPS +- spin_lock(&sd->input_pkt_queue.lock); ++ raw_spin_lock(&sd->input_pkt_queue.raw_lock); + #endif + } + + static inline void rps_unlock(struct softnet_data *sd) + { + #ifdef CONFIG_RPS +- spin_unlock(&sd->input_pkt_queue.lock); ++ raw_spin_unlock(&sd->input_pkt_queue.raw_lock); + #endif + } + +@@ -1823,6 +1823,7 @@ static inline void __netif_reschedule(st + sd->output_queue_tailp = &q->next_sched; + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + void __netif_schedule(struct Qdisc *q) +@@ -1844,6 +1845,7 @@ void dev_kfree_skb_irq(struct sk_buff *s + sd->completion_queue = skb; + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + } + EXPORT_SYMBOL(dev_kfree_skb_irq); +@@ -2907,6 +2909,7 @@ drop: + rps_unlock(sd); + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + + atomic_long_inc(&skb->dev->rx_dropped); + kfree_skb(skb); +@@ -2944,7 +2947,7 @@ int netif_rx(struct sk_buff *skb) + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu; + +- preempt_disable(); ++ migrate_disable(); + rcu_read_lock(); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); +@@ -2954,13 +2957,13 @@ int netif_rx(struct sk_buff *skb) + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + + rcu_read_unlock(); +- preempt_enable(); ++ migrate_enable(); + } else + #endif + { + unsigned int qtail; +- ret = enqueue_to_backlog(skb, get_cpu(), &qtail); +- put_cpu(); ++ ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail); ++ put_cpu_light(); + } + return ret; + } +@@ -2970,16 +2973,46 @@ int netif_rx_ni(struct sk_buff *skb) + { + int err; + +- preempt_disable(); ++ migrate_disable(); + err = netif_rx(skb); + if (local_softirq_pending()) +- do_softirq(); +- preempt_enable(); ++ thread_do_softirq(); ++ migrate_enable(); + + return err; + } + EXPORT_SYMBOL(netif_rx_ni); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * RT runs ksoftirqd as a real time thread and the root_lock is a ++ * "sleeping spinlock". If the trylock fails then we can go into an ++ * infinite loop when ksoftirqd preempted the task which actually ++ * holds the lock, because we requeue q and raise NET_TX softirq ++ * causing ksoftirqd to loop forever. ++ * ++ * It's safe to use spin_lock on RT here as softirqs run in thread ++ * context and cannot deadlock against the thread which is holding ++ * root_lock. ++ * ++ * On !RT the trylock might fail, but there we bail out from the ++ * softirq loop after 10 attempts which we can't do on RT. And the ++ * task holding root_lock cannot be preempted, so the only downside of ++ * that trylock is that we need 10 loops to decide that we should have ++ * given up in the first one :) ++ */ ++static inline int take_root_lock(spinlock_t *lock) ++{ ++ spin_lock(lock); ++ return 1; ++} ++#else ++static inline int take_root_lock(spinlock_t *lock) ++{ ++ return spin_trylock(lock); ++} ++#endif ++ + static void net_tx_action(struct softirq_action *h) + { + struct softnet_data *sd = &__get_cpu_var(softnet_data); +@@ -3018,7 +3051,7 @@ static void net_tx_action(struct softirq + head = head->next_sched; + + root_lock = qdisc_lock(q); +- if (spin_trylock(root_lock)) { ++ if (take_root_lock(root_lock)) { + smp_mb__before_clear_bit(); + clear_bit(__QDISC_STATE_SCHED, + &q->state); +@@ -3345,7 +3378,7 @@ static void flush_backlog(void *arg) + skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { + if (skb->dev == dev) { + __skb_unlink(skb, &sd->input_pkt_queue); +- kfree_skb(skb); ++ __skb_queue_tail(&sd->tofree_queue, skb); + input_queue_head_incr(sd); + } + } +@@ -3354,10 +3387,13 @@ static void flush_backlog(void *arg) + skb_queue_walk_safe(&sd->process_queue, skb, tmp) { + if (skb->dev == dev) { + __skb_unlink(skb, &sd->process_queue); +- kfree_skb(skb); ++ __skb_queue_tail(&sd->tofree_queue, skb); + input_queue_head_incr(sd); + } + } ++ ++ if (!skb_queue_empty(&sd->tofree_queue)) ++ raise_softirq_irqoff(NET_RX_SOFTIRQ); + } + + static int napi_gro_complete(struct sk_buff *skb) +@@ -3696,6 +3732,7 @@ static void net_rps_action_and_irq_enabl + } else + #endif + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + static int process_backlog(struct napi_struct *napi, int quota) +@@ -3770,6 +3807,7 @@ void __napi_schedule(struct napi_struct + local_irq_save(flags); + ____napi_schedule(&__get_cpu_var(softnet_data), n); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__napi_schedule); + +@@ -3844,10 +3882,17 @@ static void net_rx_action(struct softirq + struct softnet_data *sd = &__get_cpu_var(softnet_data); + unsigned long time_limit = jiffies + 2; + int budget = netdev_budget; ++ struct sk_buff *skb; + void *have; + + local_irq_disable(); + ++ while ((skb = __skb_dequeue(&sd->tofree_queue))) { ++ local_irq_enable(); ++ kfree_skb(skb); ++ local_irq_disable(); ++ } ++ + while (!list_empty(&sd->poll_list)) { + struct napi_struct *n; + int work, weight; +@@ -6038,7 +6083,7 @@ EXPORT_SYMBOL(free_netdev); + void synchronize_net(void) + { + might_sleep(); +- if (rtnl_is_locked()) ++ if (rtnl_is_locked() && !IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) + synchronize_rcu_expedited(); + else + synchronize_rcu(); +@@ -6261,6 +6306,7 @@ static int dev_cpu_callback(struct notif + + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + + /* Process offline CPU's input_pkt_queue */ + while ((skb = __skb_dequeue(&oldsd->process_queue))) { +@@ -6271,6 +6317,9 @@ static int dev_cpu_callback(struct notif + netif_rx(skb); + input_queue_head_incr(oldsd); + } ++ while ((skb = __skb_dequeue(&oldsd->tofree_queue))) { ++ kfree_skb(skb); ++ } + + return NOTIFY_OK; + } +@@ -6535,8 +6584,9 @@ static int __init net_dev_init(void) + struct softnet_data *sd = &per_cpu(softnet_data, i); + + memset(sd, 0, sizeof(*sd)); +- skb_queue_head_init(&sd->input_pkt_queue); +- skb_queue_head_init(&sd->process_queue); ++ skb_queue_head_init_raw(&sd->input_pkt_queue); ++ skb_queue_head_init_raw(&sd->process_queue); ++ skb_queue_head_init_raw(&sd->tofree_queue); + sd->completion_queue = NULL; + INIT_LIST_HEAD(&sd->poll_list); + sd->output_queue = NULL; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/net/core/sock.c sun8i-rt/net/core/sock.c +--- sun8i/net/core/sock.c 2016-08-22 14:14:36.000000000 +0200 ++++ sun8i-rt/net/core/sock.c 2016-08-22 16:21:44.132212113 +0200 +@@ -2138,12 +2138,11 @@ void lock_sock_nested(struct sock *sk, i + if (sk->sk_lock.owned) + __lock_sock(sk); + sk->sk_lock.owned = 1; +- spin_unlock(&sk->sk_lock.slock); ++ spin_unlock_bh(&sk->sk_lock.slock); + /* + * The sk_lock has mutex_lock() semantics here: + */ + mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); +- local_bh_enable(); + } + EXPORT_SYMBOL(lock_sock_nested); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/net/ipv4/icmp.c sun8i-rt/net/ipv4/icmp.c +--- sun8i/net/ipv4/icmp.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/net/ipv4/icmp.c 2016-08-22 17:47:50.120271505 +0200 +@@ -69,6 +69,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -799,6 +800,30 @@ out_err: + } + + /* ++ * 32bit and 64bit have different timestamp length, so we check for ++ * the cookie at offset 20 and verify it is repeated at offset 50 ++ */ ++#define CO_POS0 20 ++#define CO_POS1 50 ++#define CO_SIZE sizeof(int) ++#define ICMP_SYSRQ_SIZE 57 ++ ++/* ++ * We got a ICMP_SYSRQ_SIZE sized ping request. Check for the cookie ++ * pattern and if it matches send the next byte as a trigger to sysrq. ++ */ ++static void icmp_check_sysrq(struct net *net, struct sk_buff *skb) ++{ ++ int cookie = htonl(net->ipv4.sysctl_icmp_echo_sysrq); ++ char *p = skb->data; ++ ++ if (!memcmp(&cookie, p + CO_POS0, CO_SIZE) && ++ !memcmp(&cookie, p + CO_POS1, CO_SIZE) && ++ p[CO_POS0 + CO_SIZE] == p[CO_POS1 + CO_SIZE]) ++ handle_sysrq(p[CO_POS0 + CO_SIZE]); ++} ++ ++/* + * Handle ICMP_ECHO ("ping") requests. + * + * RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo +@@ -825,6 +850,11 @@ static void icmp_echo(struct sk_buff *sk + icmp_param.data_len = skb->len; + icmp_param.head_len = sizeof(struct icmphdr); + icmp_reply(&icmp_param, skb); ++ ++ if (skb->len == ICMP_SYSRQ_SIZE && ++ net->ipv4.sysctl_icmp_echo_sysrq) { ++ icmp_check_sysrq(net, skb); ++ } + } + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/net/ipv4/route.c sun8i-rt/net/ipv4/route.c +--- sun8i/net/ipv4/route.c 2016-08-22 14:14:38.000000000 +0200 ++++ sun8i-rt/net/ipv4/route.c 2016-08-22 17:08:04.812244082 +0200 +@@ -253,7 +253,7 @@ struct rt_hash_bucket { + }; + + #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \ +- defined(CONFIG_PROVE_LOCKING) ++ defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_PREEMPT_RT_FULL) + /* + * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks + * The size of this table is a power of two and depends on the number of CPUS. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/net/ipv4/sysctl_net_ipv4.c sun8i-rt/net/ipv4/sysctl_net_ipv4.c +--- sun8i/net/ipv4/sysctl_net_ipv4.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/net/ipv4/sysctl_net_ipv4.c 2016-08-22 17:47:50.120271505 +0200 +@@ -732,6 +732,13 @@ static struct ctl_table ipv4_net_table[] + .proc_handler = proc_dointvec + }, + { ++ .procname = "icmp_echo_sysrq", ++ .data = &init_net.ipv4.sysctl_icmp_echo_sysrq, ++ .maxlen = sizeof(int), ++ .mode = 0644, ++ .proc_handler = proc_dointvec ++ }, ++ { + .procname = "icmp_ignore_bogus_error_responses", + .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses, + .maxlen = sizeof(int), +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/net/mac80211/rx.c sun8i-rt/net/mac80211/rx.c +--- sun8i/net/mac80211/rx.c 2016-08-22 14:14:39.000000000 +0200 ++++ sun8i-rt/net/mac80211/rx.c 2016-08-22 16:33:29.628220224 +0200 +@@ -3071,7 +3071,7 @@ void ieee80211_rx(struct ieee80211_hw *h + struct ieee80211_supported_band *sband; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + +- WARN_ON_ONCE(softirq_count() == 0); ++ WARN_ON_ONCE_NONRT(softirq_count() == 0); + + if (WARN_ON(status->band < 0 || + status->band >= IEEE80211_NUM_BANDS)) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/net/netfilter/core.c sun8i-rt/net/netfilter/core.c +--- sun8i/net/netfilter/core.c 2016-08-22 14:14:17.000000000 +0200 ++++ sun8i-rt/net/netfilter/core.c 2016-08-22 18:04:05.304282717 +0200 +@@ -20,11 +20,17 @@ + #include + #include + #include ++#include + #include + #include + + #include "nf_internals.h" + ++#ifdef CONFIG_PREEMPT_RT_BASE ++DEFINE_LOCAL_IRQ_LOCK(xt_write_lock); ++EXPORT_PER_CPU_SYMBOL(xt_write_lock); ++#endif ++ + static DEFINE_MUTEX(afinfo_mutex); + + const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly; +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/net/packet/af_packet.c sun8i-rt/net/packet/af_packet.c +--- sun8i/net/packet/af_packet.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/net/packet/af_packet.c 2016-08-22 17:53:05.448275131 +0200 +@@ -88,6 +88,7 @@ + #include + #include + #include ++#include + + #ifdef CONFIG_INET + #include +@@ -680,7 +681,7 @@ static void prb_retire_rx_blk_timer_expi + if (BLOCK_NUM_PKTS(pbd)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ +- cpu_relax(); ++ cpu_chill(); + } + } + +@@ -925,7 +926,7 @@ static void prb_retire_current_block(str + if (!(status & TP_STATUS_BLK_TMO)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ +- cpu_relax(); ++ cpu_chill(); + } + } + prb_close_block(pkc, pbd, po, status); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/net/rds/ib_rdma.c sun8i-rt/net/rds/ib_rdma.c +--- sun8i/net/rds/ib_rdma.c 2016-08-22 14:14:40.000000000 +0200 ++++ sun8i-rt/net/rds/ib_rdma.c 2016-08-22 17:53:05.448275131 +0200 +@@ -34,6 +34,7 @@ + #include + #include + #include ++#include + + #include "rds.h" + #include "ib.h" +@@ -286,7 +287,7 @@ static inline void wait_clean_list_grace + for_each_online_cpu(cpu) { + flag = &per_cpu(clean_list_grace, cpu); + while (test_bit(CLEAN_LIST_BUSY_BIT, flag)) +- cpu_relax(); ++ cpu_chill(); + } + } + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/net/sched/sch_generic.c sun8i-rt/net/sched/sch_generic.c +--- sun8i/net/sched/sch_generic.c 2016-08-22 14:14:18.000000000 +0200 ++++ sun8i-rt/net/sched/sch_generic.c 2016-08-22 18:18:05.176292373 +0200 +@@ -848,7 +848,7 @@ void dev_deactivate_many(struct list_hea + /* Wait for outstanding qdisc_run calls. */ + list_for_each_entry(dev, head, unreg_list) + while (some_qdisc_is_busy(dev)) +- yield(); ++ msleep(1); + } + + void dev_deactivate(struct net_device *dev) +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/net/sunrpc/svc_xprt.c sun8i-rt/net/sunrpc/svc_xprt.c +--- sun8i/net/sunrpc/svc_xprt.c 2016-08-22 14:14:18.000000000 +0200 ++++ sun8i-rt/net/sunrpc/svc_xprt.c 2016-08-22 18:25:08.700297242 +0200 +@@ -323,9 +323,9 @@ void svc_xprt_enqueue(struct svc_xprt *x + if (!svc_xprt_has_something_to_do(xprt)) + return; + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + pool = svc_pool_for_cpu(xprt->xpt_server, cpu); +- put_cpu(); ++ put_cpu_light(); + + spin_lock_bh(&pool->sp_lock); + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i/scripts/mkcompile_h sun8i-rt/scripts/mkcompile_h +--- sun8i/scripts/mkcompile_h 2016-08-22 14:14:18.000000000 +0200 ++++ sun8i-rt/scripts/mkcompile_h 2016-08-22 17:58:48.808279078 +0200 +@@ -4,7 +4,8 @@ TARGET=$1 + ARCH=$2 + SMP=$3 + PREEMPT=$4 +-CC=$5 ++RT=$5 ++CC=$6 + + vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; } + +@@ -57,6 +58,7 @@ UTS_VERSION="#$VERSION" + CONFIG_FLAGS="" + if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi + if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi ++if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi + UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP" + + # Truncate to maximum length diff --git a/patch/kernel/sun8i-default/30002-disable-sunxi-ss-when-no-highmem.patch b/patch/kernel/sun8i-default/30002-disable-sunxi-ss-when-no-highmem.patch new file mode 100644 index 0000000000..c882c63838 --- /dev/null +++ b/patch/kernel/sun8i-default/30002-disable-sunxi-ss-when-no-highmem.patch @@ -0,0 +1,10 @@ +--- sun8i/drivers/crypto/sunxi/Kconfig 2016-08-22 14:14:14.000000000 +0200 ++++ sun8i-rt/drivers/crypto/sunxi/Kconfig 2016-08-22 23:21:56.412501973 +0200 +@@ -1,6 +1,6 @@ + config CRYPTO_SUNXI + tristate "SUNXI SS controller" +- depends on ARCH_SUNXI ++ depends on ARCH_SUNXI && HIGHMEM + help + To compile this driver as a module, choose M here: the module + will be called caam. diff --git a/patch/kernel/sun8i-default/30003-fix-timerfd.patch b/patch/kernel/sun8i-default/30003-fix-timerfd.patch new file mode 100644 index 0000000000..f450012da3 --- /dev/null +++ b/patch/kernel/sun8i-default/30003-fix-timerfd.patch @@ -0,0 +1,11 @@ +--- sun8i/fs/timerfd.c 2016-08-22 22:52:24.564481603 +0200 ++++ sun8i-rt/fs/timerfd.c 2016-08-22 20:15:39.076373470 +0200 +@@ -385,7 +385,7 @@ SYSCALL_DEFINE4(timerfd_settime, int, uf + break; + } + spin_unlock_irq(&ctx->wqh.lock); +- hrtimer_wait_for_timer(&ctx->tmr); ++ hrtimer_wait_for_timer(&ctx->t.tmr); + } + + /* diff --git a/patch/kernel/sun8i-default/30004-add-irqpriority.patch b/patch/kernel/sun8i-default/30004-add-irqpriority.patch new file mode 100644 index 0000000000..88f50024cb --- /dev/null +++ b/patch/kernel/sun8i-default/30004-add-irqpriority.patch @@ -0,0 +1,200 @@ +diff -uprNHd -x '*.orig' -x '*.rej' sun8i-test-old/arch/arm/common/gic.c sun8i-test/arch/arm/common/gic.c +--- sun8i/arch/arm/common/gic.c 2016-08-22 23:01:38.000000000 +0200 ++++ sun8i-rt/arch/arm/common/gic.c 2016-08-22 23:06:46.736491515 +0200 +@@ -36,6 +36,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -92,6 +93,19 @@ struct irq_chip gic_arch_extn = { + .irq_set_wake = NULL, + }; + ++/* ++ * Map generic interrupt priority levels (irqpriority_t) to GIC_DIST_PRI ++ * register value. Value should be mapped using table index assignment: ++ * [priority level] = which allow us to be compatible ++ * in case of irqpriority_t (see include/linux/irqpriority.h) further ++ * modification. ++ */ ++static unsigned int priority_map [IRQP_LEVELS_NR] = { ++ [IRQP_HIGH] = 0x00000000, ++ [IRQP_DEFAULT] = 0xa0a0a0a0, ++ [IRQP_LOW] = 0xe0e0e0e0, ++}; ++ + #ifndef MAX_GIC_NR + #define MAX_GIC_NR 1 + #endif +@@ -424,12 +438,32 @@ static void gic_handle_cascade_irq(unsig + chained_irq_exit(chip, desc); + } + ++int gic_set_priority(struct irq_data *data, irqpriority_t priority) ++{ ++ unsigned int hw_irq = gic_irq(data); ++ u32 cur_priority; ++ ++ if (hw_irq < 32) ++ { ++ printk("gic_set_priority: cant set irq %i to pri %i\r\n", hw_irq, priority_map[priority]); ++ return -EINVAL; ++ } ++ ++ raw_spin_lock(&irq_controller_lock); ++ cur_priority = readl_relaxed(gic_dist_base(data) + GIC_DIST_PRI + (hw_irq / 4) * 4); ++ cur_priority = priority_map[priority]; ++ writel_relaxed(cur_priority, gic_dist_base(data) + GIC_DIST_PRI + (hw_irq / 4) * 4); ++ raw_spin_unlock(&irq_controller_lock); ++ return 0; ++} ++ + static struct irq_chip gic_chip = { + .name = "GIC", + .irq_mask = gic_mask_irq, + .irq_unmask = gic_unmask_irq, + .irq_eoi = gic_eoi_irq, + .irq_set_type = gic_set_type, ++ .irq_set_priority = gic_set_priority, + .irq_retrigger = gic_retrigger, + #ifdef CONFIG_SMP + .irq_set_affinity = gic_set_affinity, +diff -uprNHd -x '*.orig' -x '*.rej' sun8i-test-old/include/linux/interrupt.h sun8i-test/include/linux/interrupt.h +--- sun8i-test-old/include/linux/interrupt.h 2016-08-22 23:01:38.000000000 +0200 ++++ sun8i-test/include/linux/interrupt.h 2016-08-22 23:05:52.300490889 +0200 +@@ -75,6 +75,7 @@ + #define IRQF_NO_THREAD 0x00010000 + #define IRQF_EARLY_RESUME 0x00020000 + #define IRQF_NO_SOFTIRQ_CALL 0x00040000 ++#define IRQF_HIGH_PRIORITY 0x00080000 + + #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) + +diff -uprNHd -x '*.orig' -x '*.rej' sun8i-test-old/include/linux/irq.h sun8i-test/include/linux/irq.h +--- sun8i-test-old/include/linux/irq.h 2016-08-22 23:01:38.000000000 +0200 ++++ sun8i-test/include/linux/irq.h 2016-08-22 23:05:52.316490889 +0200 +@@ -20,6 +20,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -324,6 +325,7 @@ struct irq_chip { + int (*irq_retrigger)(struct irq_data *data); + int (*irq_set_type)(struct irq_data *data, unsigned int flow_type); + int (*irq_set_wake)(struct irq_data *data, unsigned int on); ++ int (*irq_set_priority)(struct irq_data *data, irqpriority_t priority); + + void (*irq_bus_lock)(struct irq_data *data); + void (*irq_bus_sync_unlock)(struct irq_data *data); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i-test-old/include/linux/irqpriority.h sun8i-test/include/linux/irqpriority.h +--- sun8i-test-old/include/linux/irqpriority.h 1970-01-01 01:00:00.000000000 +0100 ++++ sun8i-test/include/linux/irqpriority.h 2016-08-22 23:05:52.316490889 +0200 +@@ -0,0 +1,24 @@ ++#ifndef _LINUX_IRQPRIORITY_H ++#define _LINUX_IRQPRIORITY_H ++ ++/** ++ * enum irqpriority ++ * @IRQP_HIGH address to low response latency interrupt e.g. error ++ * signaling ++ * @IRQP_DEFAULT default priority and set for all interrupt sources ++ * during interrupt controller initialization ++ * @IRQP_LOW interrupt which doesn't really care about response ++ * latency ++ * @... place for priority extension ++ */ ++enum irqpriority { ++ IRQP_HIGH = 0, ++ IRQP_DEFAULT, ++ IRQP_LOW, ++ ++ IRQP_LEVELS_NR ++}; ++ ++typedef enum irqpriority irqpriority_t; ++ ++#endif /* _LINUX_IRQPRIORITY_H */ +\ Kein Zeilenumbruch am Dateiende. +diff -uprNHd -x '*.orig' -x '*.rej' sun8i-test-old/kernel/irq/chip.c sun8i-test/kernel/irq/chip.c +--- sun8i-test-old/kernel/irq/chip.c 2016-08-22 23:01:38.000000000 +0200 ++++ sun8i-test/kernel/irq/chip.c 2016-08-22 23:05:52.316490889 +0200 +@@ -14,6 +14,7 @@ + #include + #include + #include ++#include + #include + + #include +@@ -254,6 +255,14 @@ void unmask_irq(struct irq_desc *desc) + } + } + ++int irq_set_priority(struct irq_desc *desc, irqpriority_t priority) ++{ ++ if (!desc->irq_data.chip->irq_set_priority) ++ return -EINVAL; ++ ++ return desc->irq_data.chip->irq_set_priority(&desc->irq_data, priority); ++} ++ + /* + * handle_nested_irq - Handle a nested irq from a irq thread + * @irq: the interrupt number +diff -uprNHd -x '*.orig' -x '*.rej' sun8i-test-old/kernel/irq/internals.h sun8i-test/kernel/irq/internals.h +--- sun8i-test-old/kernel/irq/internals.h 2016-08-22 23:01:38.000000000 +0200 ++++ sun8i-test/kernel/irq/internals.h 2016-08-22 23:05:52.316490889 +0200 +@@ -73,6 +73,7 @@ extern void irq_percpu_enable(struct irq + extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu); + extern void mask_irq(struct irq_desc *desc); + extern void unmask_irq(struct irq_desc *desc); ++extern int irq_set_priority(struct irq_desc *desc, irqpriority_t priority); + + #ifdef CONFIG_SPARSE_IRQ + extern void irq_lock_sparse(void); +diff -uprNHd -x '*.orig' -x '*.rej' sun8i-test-old/kernel/irq/manage.c sun8i-test/kernel/irq/manage.c +--- sun8i-test-old/kernel/irq/manage.c 2016-08-22 23:01:38.000000000 +0200 ++++ sun8i-test/kernel/irq/manage.c 2016-08-22 23:05:52.316490889 +0200 +@@ -12,6 +12,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -1061,11 +1062,12 @@ __setup_irq(unsigned int irq, struct irq + * the same type (level, edge, polarity). So both flag + * fields must have IRQF_SHARED set and the bits which + * set the trigger type must match. Also all must +- * agree on ONESHOT. ++ * agree on ONESHOT and IRQF_HIGH_PRIORITY. + */ + if (!((old->flags & new->flags) & IRQF_SHARED) || + ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK) || +- ((old->flags ^ new->flags) & IRQF_ONESHOT)) { +++ ((old->flags ^ new->flags) & IRQF_ONESHOT) || +++ ((old->flags ^ new->flags) & IRQF_HIGH_PRIORITY)) { + old_name = old->name; + goto mismatch; + } +@@ -1150,6 +1152,13 @@ __setup_irq(unsigned int irq, struct irq + if (new->flags & IRQF_ONESHOT) + desc->istate |= IRQS_ONESHOT; + ++ if (new->flags & IRQF_HIGH_PRIORITY) { ++ printk("%s: setting high priority\r\n", new->name); ++ ret = irq_set_priority(desc, IRQP_HIGH); ++ if (ret) ++ goto out_mask; ++ } ++ + if (irq_settings_can_autoenable(desc)) + irq_startup(desc, true); + else diff --git a/patch/kernel/sun8i-default/30005-make-irq-set-affinity-hint-work-properly.patch b/patch/kernel/sun8i-default/30005-make-irq-set-affinity-hint-work-properly.patch new file mode 100644 index 0000000000..69fedc7e72 --- /dev/null +++ b/patch/kernel/sun8i-default/30005-make-irq-set-affinity-hint-work-properly.patch @@ -0,0 +1,12 @@ +--- sun8i/kernel/irq/manage.c 2016-08-22 23:36:31.000000000 +0200 ++++ sun8i-rt/kernel/irq/manage.c 2016-08-23 13:22:07.461081538 +0200 +@@ -270,6 +270,9 @@ int irq_set_affinity_hint(unsigned int i + return -EINVAL; + desc->affinity_hint = m; + irq_put_desc_unlock(desc, flags); ++ /* set the initial affinity to prevent every interrupt being on CPU0 */ ++ irq_set_affinity(irq, m); ++ + return 0; + } + EXPORT_SYMBOL_GPL(irq_set_affinity_hint);