From b9184a07a902ddea8258e5825397b0b43f138ab6 Mon Sep 17 00:00:00 2001 From: Waldemar Brodkorb Date: Wed, 18 Apr 2018 06:29:23 +0100 Subject: linux: bump kernel versions --- target/linux/patches/4.1.51/patch-realtime | 30260 +++++++++++++++++++++++++++ 1 file changed, 30260 insertions(+) create mode 100644 target/linux/patches/4.1.51/patch-realtime (limited to 'target/linux/patches/4.1.51/patch-realtime') diff --git a/target/linux/patches/4.1.51/patch-realtime b/target/linux/patches/4.1.51/patch-realtime new file mode 100644 index 000000000..52f9bd3d2 --- /dev/null +++ b/target/linux/patches/4.1.51/patch-realtime @@ -0,0 +1,30260 @@ +diff -Nur linux-4.1.39.orig/arch/alpha/mm/fault.c linux-4.1.39/arch/alpha/mm/fault.c +--- linux-4.1.39.orig/arch/alpha/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/alpha/mm/fault.c 2017-04-18 17:56:30.549394649 +0200 +@@ -23,8 +23,7 @@ + #include + #include + #include +- +-#include ++#include + + extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *); + +@@ -107,7 +106,7 @@ + + /* If we're in an interrupt context, or have no user context, + we must not take the fault. */ +- if (!mm || in_atomic()) ++ if (!mm || faulthandler_disabled()) + goto no_context; + + #ifdef CONFIG_ALPHA_LARGE_VMALLOC +diff -Nur linux-4.1.39.orig/arch/arc/include/asm/futex.h linux-4.1.39/arch/arc/include/asm/futex.h +--- linux-4.1.39.orig/arch/arc/include/asm/futex.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arc/include/asm/futex.h 2017-04-18 17:56:30.549394649 +0200 +@@ -53,7 +53,7 @@ + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + return -EFAULT; + +- pagefault_disable(); /* implies preempt_disable() */ ++ pagefault_disable(); + + switch (op) { + case FUTEX_OP_SET: +@@ -75,7 +75,7 @@ + ret = -ENOSYS; + } + +- pagefault_enable(); /* subsumes preempt_enable() */ ++ pagefault_enable(); + + if (!ret) { + switch (cmp) { +@@ -104,7 +104,7 @@ + return ret; + } + +-/* Compare-xchg with preemption disabled. ++/* Compare-xchg with pagefaults disabled. + * Notes: + * -Best-Effort: Exchg happens only if compare succeeds. + * If compare fails, returns; leaving retry/looping to upper layers +@@ -121,7 +121,7 @@ + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + return -EFAULT; + +- pagefault_disable(); /* implies preempt_disable() */ ++ pagefault_disable(); + + /* TBD : can use llock/scond */ + __asm__ __volatile__( +@@ -142,7 +142,7 @@ + : "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT) + : "cc", "memory"); + +- pagefault_enable(); /* subsumes preempt_enable() */ ++ pagefault_enable(); + + *uval = val; + return val; +diff -Nur linux-4.1.39.orig/arch/arc/mm/fault.c linux-4.1.39/arch/arc/mm/fault.c +--- linux-4.1.39.orig/arch/arc/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arc/mm/fault.c 2017-04-18 17:56:30.549394649 +0200 +@@ -86,7 +86,7 @@ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +diff -Nur linux-4.1.39.orig/arch/arm/include/asm/cmpxchg.h linux-4.1.39/arch/arm/include/asm/cmpxchg.h +--- linux-4.1.39.orig/arch/arm/include/asm/cmpxchg.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/include/asm/cmpxchg.h 2017-04-18 17:56:30.549394649 +0200 +@@ -129,6 +129,8 @@ + + #else /* min ARCH >= ARMv6 */ + ++#define __HAVE_ARCH_CMPXCHG 1 ++ + extern void __bad_cmpxchg(volatile void *ptr, int size); + + /* +diff -Nur linux-4.1.39.orig/arch/arm/include/asm/futex.h linux-4.1.39/arch/arm/include/asm/futex.h +--- linux-4.1.39.orig/arch/arm/include/asm/futex.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/include/asm/futex.h 2017-04-18 17:56:30.549394649 +0200 +@@ -93,6 +93,7 @@ + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + return -EFAULT; + ++ preempt_disable(); + __asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n" + "1: " TUSER(ldr) " %1, [%4]\n" + " teq %1, %2\n" +@@ -104,6 +105,8 @@ + : "cc", "memory"); + + *uval = val; ++ preempt_enable(); ++ + return ret; + } + +@@ -124,7 +127,10 @@ + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + return -EFAULT; + +- pagefault_disable(); /* implies preempt_disable() */ ++#ifndef CONFIG_SMP ++ preempt_disable(); ++#endif ++ pagefault_disable(); + + switch (op) { + case FUTEX_OP_SET: +@@ -146,7 +152,10 @@ + ret = -ENOSYS; + } + +- pagefault_enable(); /* subsumes preempt_enable() */ ++ pagefault_enable(); ++#ifndef CONFIG_SMP ++ preempt_enable(); ++#endif + + if (!ret) { + switch (cmp) { +diff -Nur linux-4.1.39.orig/arch/arm/include/asm/switch_to.h linux-4.1.39/arch/arm/include/asm/switch_to.h +--- linux-4.1.39.orig/arch/arm/include/asm/switch_to.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/include/asm/switch_to.h 2017-04-18 17:56:30.549394649 +0200 +@@ -3,6 +3,13 @@ + + #include + ++#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM ++void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p); ++#else ++static inline void ++switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } ++#endif ++ + /* + * For v7 SMP cores running a preemptible kernel we may be pre-empted + * during a TLB maintenance operation, so execute an inner-shareable dsb +@@ -22,6 +29,7 @@ + + #define switch_to(prev,next,last) \ + do { \ ++ switch_kmaps(prev, next); \ + last = __switch_to(prev,task_thread_info(prev), task_thread_info(next)); \ + } while (0) + +diff -Nur linux-4.1.39.orig/arch/arm/include/asm/thread_info.h linux-4.1.39/arch/arm/include/asm/thread_info.h +--- linux-4.1.39.orig/arch/arm/include/asm/thread_info.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/include/asm/thread_info.h 2017-04-18 17:56:30.549394649 +0200 +@@ -50,6 +50,7 @@ + struct thread_info { + unsigned long flags; /* low level flags */ + int preempt_count; /* 0 => preemptable, <0 => bug */ ++ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ + mm_segment_t addr_limit; /* address limit */ + struct task_struct *task; /* main task structure */ + __u32 cpu; /* cpu */ +@@ -147,6 +148,7 @@ + #define TIF_SIGPENDING 0 + #define TIF_NEED_RESCHED 1 + #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ ++#define TIF_NEED_RESCHED_LAZY 3 + #define TIF_UPROBE 7 + #define TIF_SYSCALL_TRACE 8 + #define TIF_SYSCALL_AUDIT 9 +@@ -160,6 +162,7 @@ + #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) + #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) + #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_UPROBE (1 << TIF_UPROBE) + #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +diff -Nur linux-4.1.39.orig/arch/arm/Kconfig linux-4.1.39/arch/arm/Kconfig +--- linux-4.1.39.orig/arch/arm/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/Kconfig 2017-04-18 17:56:30.549394649 +0200 +@@ -31,7 +31,7 @@ + select HARDIRQS_SW_RESEND + select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT) + select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 +- select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL ++ select HAVE_ARCH_JUMP_LABEL if (!XIP_KERNEL && !PREEMPT_RT_BASE) + select HAVE_ARCH_KGDB + select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT) + select HAVE_ARCH_TRACEHOOK +@@ -66,6 +66,7 @@ + select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE) + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_SYSCALL_TRACEPOINTS +diff -Nur linux-4.1.39.orig/arch/arm/kernel/asm-offsets.c linux-4.1.39/arch/arm/kernel/asm-offsets.c +--- linux-4.1.39.orig/arch/arm/kernel/asm-offsets.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/kernel/asm-offsets.c 2017-04-18 17:56:30.549394649 +0200 +@@ -65,6 +65,7 @@ + BLANK(); + DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); + DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); ++ DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); + DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); + DEFINE(TI_TASK, offsetof(struct thread_info, task)); + DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); +diff -Nur linux-4.1.39.orig/arch/arm/kernel/entry-armv.S linux-4.1.39/arch/arm/kernel/entry-armv.S +--- linux-4.1.39.orig/arch/arm/kernel/entry-armv.S 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/kernel/entry-armv.S 2017-04-18 17:56:30.549394649 +0200 +@@ -208,11 +208,18 @@ + #ifdef CONFIG_PREEMPT + get_thread_info tsk + ldr r8, [tsk, #TI_PREEMPT] @ get preempt count +- ldr r0, [tsk, #TI_FLAGS] @ get flags + teq r8, #0 @ if preempt count != 0 ++ bne 1f @ return from exeption ++ ldr r0, [tsk, #TI_FLAGS] @ get flags ++ tst r0, #_TIF_NEED_RESCHED @ if NEED_RESCHED is set ++ blne svc_preempt @ preempt! ++ ++ ldr r8, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count ++ teq r8, #0 @ if preempt lazy count != 0 + movne r0, #0 @ force flags to 0 +- tst r0, #_TIF_NEED_RESCHED ++ tst r0, #_TIF_NEED_RESCHED_LAZY + blne svc_preempt ++1: + #endif + + svc_exit r5, irq = 1 @ return from exception +@@ -227,8 +234,14 @@ + 1: bl preempt_schedule_irq @ irq en/disable is done inside + ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS + tst r0, #_TIF_NEED_RESCHED ++ bne 1b ++ tst r0, #_TIF_NEED_RESCHED_LAZY + reteq r8 @ go again +- b 1b ++ ldr r0, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count ++ teq r0, #0 @ if preempt lazy count != 0 ++ beq 1b ++ ret r8 @ go again ++ + #endif + + __und_fault: +diff -Nur linux-4.1.39.orig/arch/arm/kernel/patch.c linux-4.1.39/arch/arm/kernel/patch.c +--- linux-4.1.39.orig/arch/arm/kernel/patch.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/kernel/patch.c 2017-04-18 17:56:30.549394649 +0200 +@@ -15,7 +15,7 @@ + unsigned int insn; + }; + +-static DEFINE_SPINLOCK(patch_lock); ++static DEFINE_RAW_SPINLOCK(patch_lock); + + static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) + __acquires(&patch_lock) +@@ -32,7 +32,7 @@ + return addr; + + if (flags) +- spin_lock_irqsave(&patch_lock, *flags); ++ raw_spin_lock_irqsave(&patch_lock, *flags); + else + __acquire(&patch_lock); + +@@ -47,7 +47,7 @@ + clear_fixmap(fixmap); + + if (flags) +- spin_unlock_irqrestore(&patch_lock, *flags); ++ raw_spin_unlock_irqrestore(&patch_lock, *flags); + else + __release(&patch_lock); + } +diff -Nur linux-4.1.39.orig/arch/arm/kernel/process.c linux-4.1.39/arch/arm/kernel/process.c +--- linux-4.1.39.orig/arch/arm/kernel/process.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/kernel/process.c 2017-04-18 17:56:30.549394649 +0200 +@@ -290,6 +290,30 @@ + } + + #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); ++ + #ifdef CONFIG_KUSER_HELPERS + /* + * The vectors page is always readable from user space for the +diff -Nur linux-4.1.39.orig/arch/arm/kernel/signal.c linux-4.1.39/arch/arm/kernel/signal.c +--- linux-4.1.39.orig/arch/arm/kernel/signal.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/kernel/signal.c 2017-04-18 17:56:30.549394649 +0200 +@@ -568,7 +568,8 @@ + do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) + { + do { +- if (likely(thread_flags & _TIF_NEED_RESCHED)) { ++ if (likely(thread_flags & (_TIF_NEED_RESCHED | ++ _TIF_NEED_RESCHED_LAZY))) { + schedule(); + } else { + if (unlikely(!user_mode(regs))) +diff -Nur linux-4.1.39.orig/arch/arm/kernel/smp.c linux-4.1.39/arch/arm/kernel/smp.c +--- linux-4.1.39.orig/arch/arm/kernel/smp.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/kernel/smp.c 2017-04-18 17:56:30.549394649 +0200 +@@ -213,8 +213,6 @@ + flush_cache_louis(); + local_flush_tlb_all(); + +- clear_tasks_mm_cpumask(cpu); +- + return 0; + } + +@@ -230,6 +228,9 @@ + pr_err("CPU%u: cpu didn't die\n", cpu); + return; + } ++ ++ clear_tasks_mm_cpumask(cpu); ++ + pr_notice("CPU%u: shutdown\n", cpu); + + /* +diff -Nur linux-4.1.39.orig/arch/arm/kernel/unwind.c linux-4.1.39/arch/arm/kernel/unwind.c +--- linux-4.1.39.orig/arch/arm/kernel/unwind.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/kernel/unwind.c 2017-04-18 17:56:30.549394649 +0200 +@@ -93,7 +93,7 @@ + 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 */ +@@ -201,7 +201,7 @@ + /* 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) { +@@ -213,7 +213,7 @@ + break; + } + } +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + } + + pr_debug("%s: idx = %p\n", __func__, idx); +@@ -529,9 +529,9 @@ + 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; + } +@@ -543,9 +543,9 @@ + 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 -Nur linux-4.1.39.orig/arch/arm/kvm/arm.c linux-4.1.39/arch/arm/kvm/arm.c +--- linux-4.1.39.orig/arch/arm/kvm/arm.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/kvm/arm.c 2017-04-18 17:56:30.549394649 +0200 +@@ -473,9 +473,9 @@ + + static void vcpu_pause(struct kvm_vcpu *vcpu) + { +- wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); ++ struct swait_head *wq = kvm_arch_vcpu_wq(vcpu); + +- wait_event_interruptible(*wq, !vcpu->arch.pause); ++ swait_event_interruptible(*wq, !vcpu->arch.pause); + } + + static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu) +diff -Nur linux-4.1.39.orig/arch/arm/kvm/psci.c linux-4.1.39/arch/arm/kvm/psci.c +--- linux-4.1.39.orig/arch/arm/kvm/psci.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/kvm/psci.c 2017-04-18 17:56:30.549394649 +0200 +@@ -68,7 +68,7 @@ + { + struct kvm *kvm = source_vcpu->kvm; + struct kvm_vcpu *vcpu = NULL; +- wait_queue_head_t *wq; ++ struct swait_head *wq; + unsigned long cpu_id; + unsigned long context_id; + phys_addr_t target_pc; +@@ -117,7 +117,7 @@ + smp_mb(); /* Make sure the above is visible */ + + wq = kvm_arch_vcpu_wq(vcpu); +- wake_up_interruptible(wq); ++ swait_wake_interruptible(wq); + + return PSCI_RET_SUCCESS; + } +diff -Nur linux-4.1.39.orig/arch/arm/mach-at91/at91rm9200.c linux-4.1.39/arch/arm/mach-at91/at91rm9200.c +--- linux-4.1.39.orig/arch/arm/mach-at91/at91rm9200.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-at91/at91rm9200.c 2017-04-18 17:56:30.549394649 +0200 +@@ -13,7 +13,6 @@ + #include + + #include +-#include + + #include "generic.h" + #include "soc.h" +@@ -34,7 +33,6 @@ + + of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev); + +- arm_pm_idle = at91rm9200_idle; + at91rm9200_pm_init(); + } + +diff -Nur linux-4.1.39.orig/arch/arm/mach-at91/at91sam9.c linux-4.1.39/arch/arm/mach-at91/at91sam9.c +--- linux-4.1.39.orig/arch/arm/mach-at91/at91sam9.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-at91/at91sam9.c 2017-04-18 17:56:30.549394649 +0200 +@@ -62,8 +62,6 @@ + soc_dev = soc_device_to_device(soc); + + of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev); +- +- arm_pm_idle = at91sam9_idle; + } + + static void __init at91sam9_dt_device_init(void) +diff -Nur linux-4.1.39.orig/arch/arm/mach-at91/generic.h linux-4.1.39/arch/arm/mach-at91/generic.h +--- linux-4.1.39.orig/arch/arm/mach-at91/generic.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-at91/generic.h 2017-04-18 17:56:30.549394649 +0200 +@@ -11,27 +11,18 @@ + #ifndef _AT91_GENERIC_H + #define _AT91_GENERIC_H + +-#include +-#include +- +- /* Map io */ +-extern void __init at91_map_io(void); +-extern void __init at91_alt_map_io(void); +- +-/* idle */ +-extern void at91rm9200_idle(void); +-extern void at91sam9_idle(void); +- + #ifdef CONFIG_PM + extern void __init at91rm9200_pm_init(void); + extern void __init at91sam9260_pm_init(void); + extern void __init at91sam9g45_pm_init(void); + extern void __init at91sam9x5_pm_init(void); ++extern void __init sama5_pm_init(void); + #else + static inline void __init at91rm9200_pm_init(void) { } + static inline void __init at91sam9260_pm_init(void) { } + static inline void __init at91sam9g45_pm_init(void) { } + static inline void __init at91sam9x5_pm_init(void) { } ++static inline void __init sama5_pm_init(void) { } + #endif + + #endif /* _AT91_GENERIC_H */ +diff -Nur linux-4.1.39.orig/arch/arm/mach-at91/pm.c linux-4.1.39/arch/arm/mach-at91/pm.c +--- linux-4.1.39.orig/arch/arm/mach-at91/pm.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-at91/pm.c 2017-04-18 17:56:30.549394649 +0200 +@@ -31,10 +31,13 @@ + #include + #include + #include ++#include + + #include "generic.h" + #include "pm.h" + ++static void __iomem *pmc; ++ + /* + * FIXME: this is needed to communicate between the pinctrl driver and + * the PM implementation in the machine. Possibly part of the PM +@@ -85,7 +88,7 @@ + unsigned long scsr; + int i; + +- scsr = at91_pmc_read(AT91_PMC_SCSR); ++ scsr = readl(pmc + AT91_PMC_SCSR); + + /* USB must not be using PLLB */ + if ((scsr & at91_pm_data.uhp_udp_mask) != 0) { +@@ -99,8 +102,7 @@ + + if ((scsr & (AT91_PMC_PCK0 << i)) == 0) + continue; +- +- css = at91_pmc_read(AT91_PMC_PCKR(i)) & AT91_PMC_CSS; ++ css = readl(pmc + AT91_PMC_PCKR(i)) & AT91_PMC_CSS; + if (css != AT91_PMC_CSS_SLOW) { + pr_err("AT91: PM - Suspend-to-RAM with PCK%d src %d\n", i, css); + return 0; +@@ -143,8 +145,8 @@ + flush_cache_all(); + outer_disable(); + +- at91_suspend_sram_fn(at91_pmc_base, at91_ramc_base[0], +- at91_ramc_base[1], pm_data); ++ at91_suspend_sram_fn(pmc, at91_ramc_base[0], ++ at91_ramc_base[1], pm_data); + + outer_resume(); + } +@@ -348,6 +350,21 @@ + at91_pm_set_standby(standby); + } + ++void at91rm9200_idle(void) ++{ ++ /* ++ * Disable the processor clock. The processor will be automatically ++ * re-enabled by an interrupt or by a reset. ++ */ ++ writel(AT91_PMC_PCK, pmc + AT91_PMC_SCDR); ++} ++ ++void at91sam9_idle(void) ++{ ++ writel(AT91_PMC_PCK, pmc + AT91_PMC_SCDR); ++ cpu_do_idle(); ++} ++ + static void __init at91_pm_sram_init(void) + { + struct gen_pool *sram_pool; +@@ -394,13 +411,36 @@ + &at91_pm_suspend_in_sram, at91_pm_suspend_in_sram_sz); + } + +-static void __init at91_pm_init(void) ++static const struct of_device_id atmel_pmc_ids[] __initconst = { ++ { .compatible = "atmel,at91rm9200-pmc" }, ++ { .compatible = "atmel,at91sam9260-pmc" }, ++ { .compatible = "atmel,at91sam9g45-pmc" }, ++ { .compatible = "atmel,at91sam9n12-pmc" }, ++ { .compatible = "atmel,at91sam9x5-pmc" }, ++ { .compatible = "atmel,sama5d3-pmc" }, ++ { .compatible = "atmel,sama5d2-pmc" }, ++ { /* sentinel */ }, ++}; ++ ++static void __init at91_pm_init(void (*pm_idle)(void)) + { +- at91_pm_sram_init(); ++ struct device_node *pmc_np; + + if (at91_cpuidle_device.dev.platform_data) + platform_device_register(&at91_cpuidle_device); + ++ pmc_np = of_find_matching_node(NULL, atmel_pmc_ids); ++ pmc = of_iomap(pmc_np, 0); ++ if (!pmc) { ++ pr_err("AT91: PM not supported, PMC not found\n"); ++ return; ++ } ++ ++ if (pm_idle) ++ arm_pm_idle = pm_idle; ++ ++ at91_pm_sram_init(); ++ + if (at91_suspend_sram_fn) + suspend_set_ops(&at91_pm_ops); + else +@@ -419,7 +459,7 @@ + at91_pm_data.uhp_udp_mask = AT91RM9200_PMC_UHP | AT91RM9200_PMC_UDP; + at91_pm_data.memctrl = AT91_MEMCTRL_MC; + +- at91_pm_init(); ++ at91_pm_init(at91rm9200_idle); + } + + void __init at91sam9260_pm_init(void) +@@ -427,7 +467,7 @@ + at91_dt_ramc(); + at91_pm_data.memctrl = AT91_MEMCTRL_SDRAMC; + at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP; +- return at91_pm_init(); ++ at91_pm_init(at91sam9_idle); + } + + void __init at91sam9g45_pm_init(void) +@@ -435,7 +475,7 @@ + at91_dt_ramc(); + at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP; + at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR; +- return at91_pm_init(); ++ at91_pm_init(at91sam9_idle); + } + + void __init at91sam9x5_pm_init(void) +@@ -443,5 +483,13 @@ + at91_dt_ramc(); + at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP; + at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR; +- return at91_pm_init(); ++ at91_pm_init(at91sam9_idle); ++} ++ ++void __init sama5_pm_init(void) ++{ ++ at91_dt_ramc(); ++ at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP; ++ at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR; ++ at91_pm_init(NULL); + } +diff -Nur linux-4.1.39.orig/arch/arm/mach-at91/sama5.c linux-4.1.39/arch/arm/mach-at91/sama5.c +--- linux-4.1.39.orig/arch/arm/mach-at91/sama5.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-at91/sama5.c 2017-04-18 17:56:30.549394649 +0200 +@@ -49,7 +49,7 @@ + soc_dev = soc_device_to_device(soc); + + of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev); +- at91sam9x5_pm_init(); ++ sama5_pm_init(); + } + + static const char *sama5_dt_board_compat[] __initconst = { +diff -Nur linux-4.1.39.orig/arch/arm/mach-exynos/platsmp.c linux-4.1.39/arch/arm/mach-exynos/platsmp.c +--- linux-4.1.39.orig/arch/arm/mach-exynos/platsmp.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-exynos/platsmp.c 2017-04-18 17:56:30.549394649 +0200 +@@ -231,7 +231,7 @@ + return (void __iomem *)(S5P_VA_SCU); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void exynos_secondary_init(unsigned int cpu) + { +@@ -244,8 +244,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -259,7 +259,7 @@ + * 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 +@@ -286,7 +286,7 @@ + + if (timeout == 0) { + printk(KERN_ERR "cpu1 power enable failed"); +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + return -ETIMEDOUT; + } + } +@@ -342,7 +342,7 @@ + * calibrations, then wait for it to finish + */ + fail: +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? ret : 0; + } +diff -Nur linux-4.1.39.orig/arch/arm/mach-hisi/platmcpm.c linux-4.1.39/arch/arm/mach-hisi/platmcpm.c +--- linux-4.1.39.orig/arch/arm/mach-hisi/platmcpm.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-hisi/platmcpm.c 2017-04-18 17:56:30.549394649 +0200 +@@ -57,7 +57,7 @@ + + static void __iomem *sysctrl, *fabric; + static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER]; +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + static u32 fabric_phys_addr; + /* + * [0]: bootwrapper physical address +@@ -104,7 +104,7 @@ + if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER) + return -EINVAL; + +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + + if (hip04_cpu_table[cluster][cpu]) + goto out; +@@ -133,7 +133,7 @@ + udelay(20); + out: + hip04_cpu_table[cluster][cpu]++; +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + + return 0; + } +@@ -149,7 +149,7 @@ + + __mcpm_cpu_going_down(cpu, cluster); + +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP); + hip04_cpu_table[cluster][cpu]--; + if (hip04_cpu_table[cluster][cpu] == 1) { +@@ -162,7 +162,7 @@ + + last_man = hip04_cluster_is_down(cluster); + if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) { +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + /* Since it's Cortex A15, disable L2 prefetching. */ + asm volatile( + "mcr p15, 1, %0, c15, c0, 3 \n\t" +@@ -173,7 +173,7 @@ + hip04_set_snoop_filter(cluster, 0); + __mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN); + } else { +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + v7_exit_coherency_flush(louis); + } + +@@ -192,7 +192,7 @@ + cpu >= HIP04_MAX_CPUS_PER_CLUSTER); + + count = TIMEOUT_MSEC / POLL_MSEC; +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + for (tries = 0; tries < count; tries++) { + if (hip04_cpu_table[cluster][cpu]) { + ret = -EBUSY; +@@ -202,10 +202,10 @@ + data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster)); + if (data & CORE_WFI_STATUS(cpu)) + break; +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + /* Wait for clean L2 when the whole cluster is down. */ + msleep(POLL_MSEC); +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + } + if (tries >= count) + goto err; +@@ -220,10 +220,10 @@ + } + if (tries >= count) + goto err; +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + return 0; + err: +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + return ret; + } + +@@ -235,10 +235,10 @@ + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + if (!hip04_cpu_table[cluster][cpu]) + hip04_cpu_table[cluster][cpu] = 1; +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static void __naked hip04_mcpm_power_up_setup(unsigned int affinity_level) +diff -Nur linux-4.1.39.orig/arch/arm/mach-omap2/gpio.c linux-4.1.39/arch/arm/mach-omap2/gpio.c +--- linux-4.1.39.orig/arch/arm/mach-omap2/gpio.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-omap2/gpio.c 2017-04-18 17:56:30.549394649 +0200 +@@ -130,7 +130,6 @@ + } + + pwrdm = omap_hwmod_get_pwrdm(oh); +- pdata->loses_context = pwrdm_can_ever_lose_context(pwrdm); + + pdev = omap_device_build(name, id - 1, oh, pdata, sizeof(*pdata)); + kfree(pdata); +diff -Nur linux-4.1.39.orig/arch/arm/mach-omap2/omap-smp.c linux-4.1.39/arch/arm/mach-omap2/omap-smp.c +--- linux-4.1.39.orig/arch/arm/mach-omap2/omap-smp.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-omap2/omap-smp.c 2017-04-18 17:56:30.549394649 +0200 +@@ -43,7 +43,7 @@ + /* 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) + { +@@ -74,8 +74,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -89,7 +89,7 @@ + * 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. +@@ -166,7 +166,7 @@ + * 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 -Nur linux-4.1.39.orig/arch/arm/mach-omap2/powerdomain.c linux-4.1.39/arch/arm/mach-omap2/powerdomain.c +--- linux-4.1.39.orig/arch/arm/mach-omap2/powerdomain.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-omap2/powerdomain.c 2017-04-18 17:56:30.553394804 +0200 +@@ -1166,43 +1166,3 @@ + return count; + } + +-/** +- * pwrdm_can_ever_lose_context - can this powerdomain ever lose context? +- * @pwrdm: struct powerdomain * +- * +- * Given a struct powerdomain * @pwrdm, returns 1 if the powerdomain +- * can lose either memory or logic context or if @pwrdm is invalid, or +- * returns 0 otherwise. This function is not concerned with how the +- * powerdomain registers are programmed (i.e., to go off or not); it's +- * concerned with whether it's ever possible for this powerdomain to +- * go off while some other part of the chip is active. This function +- * assumes that every powerdomain can go to either ON or INACTIVE. +- */ +-bool pwrdm_can_ever_lose_context(struct powerdomain *pwrdm) +-{ +- int i; +- +- if (!pwrdm) { +- pr_debug("powerdomain: %s: invalid powerdomain pointer\n", +- __func__); +- return 1; +- } +- +- if (pwrdm->pwrsts & PWRSTS_OFF) +- return 1; +- +- if (pwrdm->pwrsts & PWRSTS_RET) { +- if (pwrdm->pwrsts_logic_ret & PWRSTS_OFF) +- return 1; +- +- for (i = 0; i < pwrdm->banks; i++) +- if (pwrdm->pwrsts_mem_ret[i] & PWRSTS_OFF) +- return 1; +- } +- +- for (i = 0; i < pwrdm->banks; i++) +- if (pwrdm->pwrsts_mem_on[i] & PWRSTS_OFF) +- return 1; +- +- return 0; +-} +diff -Nur linux-4.1.39.orig/arch/arm/mach-omap2/powerdomain.h linux-4.1.39/arch/arm/mach-omap2/powerdomain.h +--- linux-4.1.39.orig/arch/arm/mach-omap2/powerdomain.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-omap2/powerdomain.h 2017-04-18 17:56:30.553394804 +0200 +@@ -244,7 +244,6 @@ + int pwrdm_pre_transition(struct powerdomain *pwrdm); + int pwrdm_post_transition(struct powerdomain *pwrdm); + int pwrdm_get_context_loss_count(struct powerdomain *pwrdm); +-bool pwrdm_can_ever_lose_context(struct powerdomain *pwrdm); + + extern int omap_set_pwrdm_state(struct powerdomain *pwrdm, u8 state); + +diff -Nur linux-4.1.39.orig/arch/arm/mach-prima2/platsmp.c linux-4.1.39/arch/arm/mach-prima2/platsmp.c +--- linux-4.1.39.orig/arch/arm/mach-prima2/platsmp.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-prima2/platsmp.c 2017-04-18 17:56:30.553394804 +0200 +@@ -22,7 +22,7 @@ + + static void __iomem *clk_base; + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void sirfsoc_secondary_init(unsigned int cpu) + { +@@ -36,8 +36,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static const struct of_device_id clk_ids[] = { +@@ -75,7 +75,7 @@ + /* make sure write buffer is drained */ + mb(); + +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -107,7 +107,7 @@ + * 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 -Nur linux-4.1.39.orig/arch/arm/mach-qcom/platsmp.c linux-4.1.39/arch/arm/mach-qcom/platsmp.c +--- linux-4.1.39.orig/arch/arm/mach-qcom/platsmp.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-qcom/platsmp.c 2017-04-18 17:56:30.553394804 +0200 +@@ -46,7 +46,7 @@ + + extern void secondary_startup_arm(void); + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + #ifdef CONFIG_HOTPLUG_CPU + static void __ref qcom_cpu_die(unsigned int cpu) +@@ -60,8 +60,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int scss_release_secondary(unsigned int cpu) +@@ -284,7 +284,7 @@ + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * Send the secondary CPU a soft interrupt, thereby causing +@@ -297,7 +297,7 @@ + * 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 ret; + } +diff -Nur linux-4.1.39.orig/arch/arm/mach-spear/platsmp.c linux-4.1.39/arch/arm/mach-spear/platsmp.c +--- linux-4.1.39.orig/arch/arm/mach-spear/platsmp.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-spear/platsmp.c 2017-04-18 17:56:30.553394804 +0200 +@@ -32,7 +32,7 @@ + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void __iomem *scu_base = IOMEM(VA_SCU_BASE); + +@@ -47,8 +47,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -59,7 +59,7 @@ + * 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 +@@ -84,7 +84,7 @@ + * 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 -Nur linux-4.1.39.orig/arch/arm/mach-sti/platsmp.c linux-4.1.39/arch/arm/mach-sti/platsmp.c +--- linux-4.1.39.orig/arch/arm/mach-sti/platsmp.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-sti/platsmp.c 2017-04-18 17:56:30.553394804 +0200 +@@ -34,7 +34,7 @@ + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void sti_secondary_init(unsigned int cpu) + { +@@ -49,8 +49,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -61,7 +61,7 @@ + * 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 +@@ -92,7 +92,7 @@ + * 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 -Nur linux-4.1.39.orig/arch/arm/mach-ux500/platsmp.c linux-4.1.39/arch/arm/mach-ux500/platsmp.c +--- linux-4.1.39.orig/arch/arm/mach-ux500/platsmp.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mach-ux500/platsmp.c 2017-04-18 17:56:30.553394804 +0200 +@@ -51,7 +51,7 @@ + return NULL; + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void ux500_secondary_init(unsigned int cpu) + { +@@ -64,8 +64,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int ux500_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -76,7 +76,7 @@ + * 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 +@@ -97,7 +97,7 @@ + * 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 -Nur linux-4.1.39.orig/arch/arm/mm/fault.c linux-4.1.39/arch/arm/mm/fault.c +--- linux-4.1.39.orig/arch/arm/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mm/fault.c 2017-04-18 17:56:30.553394804 +0200 +@@ -276,7 +276,7 @@ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +@@ -430,6 +430,9 @@ + 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; + +@@ -497,6 +500,9 @@ + 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 -Nur linux-4.1.39.orig/arch/arm/mm/highmem.c linux-4.1.39/arch/arm/mm/highmem.c +--- linux-4.1.39.orig/arch/arm/mm/highmem.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/mm/highmem.c 2017-04-18 17:56:30.553394804 +0200 +@@ -54,11 +54,13 @@ + + void *kmap_atomic(struct page *page) + { ++ pte_t pte = mk_pte(page, kmap_prot); + unsigned int idx; + unsigned long vaddr; + void *kmap; + int type; + ++ preempt_disable_nort(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -92,7 +94,10 @@ + * in place, so the contained TLB flush ensures the TLB is updated + * with the new mapping. + */ +- set_fixmap_pte(idx, mk_pte(page, kmap_prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_fixmap_pte(idx, pte); + + return (void *)vaddr; + } +@@ -109,27 +114,33 @@ + + if (cache_is_vivt()) + __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(vaddr != __fix_to_virt(idx)); +- set_fixmap_pte(idx, __pte(0)); + #else + (void) idx; /* to kill a warning */ + #endif ++ set_fixmap_pte(idx, __pte(0)); + kmap_atomic_idx_pop(); + } else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) { + /* this address was obtained through kmap_high_get() */ + kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)])); + } + pagefault_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(__kunmap_atomic); + + void *kmap_atomic_pfn(unsigned long pfn) + { ++ pte_t pte = pfn_pte(pfn, kmap_prot); + unsigned long vaddr; + int idx, type; + struct page *page = pfn_to_page(pfn); + ++ preempt_disable_nort(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -140,7 +151,10 @@ + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(!pte_none(get_fixmap_pte(vaddr))); + #endif +- set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_fixmap_pte(idx, pte); + + return (void *)vaddr; + } +@@ -154,3 +168,28 @@ + + return pte_page(get_fixmap_pte(vaddr)); + } ++ ++#if defined CONFIG_PREEMPT_RT_FULL ++void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) ++{ ++ int i; ++ ++ /* ++ * Clear @prev's kmap_atomic mappings ++ */ ++ for (i = 0; i < prev_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ ++ set_fixmap_pte(idx, __pte(0)); ++ } ++ /* ++ * Restore @next_p's kmap_atomic mappings ++ */ ++ for (i = 0; i < next_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ ++ if (!pte_none(next_p->kmap_pte[i])) ++ set_fixmap_pte(idx, next_p->kmap_pte[i]); ++ } ++} ++#endif +diff -Nur linux-4.1.39.orig/arch/arm/plat-versatile/platsmp.c linux-4.1.39/arch/arm/plat-versatile/platsmp.c +--- linux-4.1.39.orig/arch/arm/plat-versatile/platsmp.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm/plat-versatile/platsmp.c 2017-04-18 17:56:30.553394804 +0200 +@@ -30,7 +30,7 @@ + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void versatile_secondary_init(unsigned int cpu) + { +@@ -43,8 +43,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -55,7 +55,7 @@ + * 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 +@@ -85,7 +85,7 @@ + * 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 -Nur linux-4.1.39.orig/arch/arm64/include/asm/futex.h linux-4.1.39/arch/arm64/include/asm/futex.h +--- linux-4.1.39.orig/arch/arm64/include/asm/futex.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm64/include/asm/futex.h 2017-04-18 17:56:30.553394804 +0200 +@@ -58,7 +58,7 @@ + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + return -EFAULT; + +- pagefault_disable(); /* implies preempt_disable() */ ++ pagefault_disable(); + + switch (op) { + case FUTEX_OP_SET: +@@ -85,7 +85,7 @@ + ret = -ENOSYS; + } + +- pagefault_enable(); /* subsumes preempt_enable() */ ++ pagefault_enable(); + + if (!ret) { + switch (cmp) { +diff -Nur linux-4.1.39.orig/arch/arm64/include/asm/thread_info.h linux-4.1.39/arch/arm64/include/asm/thread_info.h +--- linux-4.1.39.orig/arch/arm64/include/asm/thread_info.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm64/include/asm/thread_info.h 2017-04-18 17:56:30.553394804 +0200 +@@ -47,6 +47,7 @@ + mm_segment_t addr_limit; /* address limit */ + struct task_struct *task; /* main task structure */ + int preempt_count; /* 0 => preemptable, <0 => bug */ ++ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ + int cpu; /* cpu */ + }; + +@@ -101,6 +102,7 @@ + #define TIF_NEED_RESCHED 1 + #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ + #define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */ ++#define TIF_NEED_RESCHED_LAZY 4 + #define TIF_NOHZ 7 + #define TIF_SYSCALL_TRACE 8 + #define TIF_SYSCALL_AUDIT 9 +@@ -117,6 +119,7 @@ + #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) + #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) + #define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_NOHZ (1 << TIF_NOHZ) + #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +diff -Nur linux-4.1.39.orig/arch/arm64/Kconfig linux-4.1.39/arch/arm64/Kconfig +--- linux-4.1.39.orig/arch/arm64/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm64/Kconfig 2017-04-18 17:56:30.553394804 +0200 +@@ -69,8 +69,10 @@ + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP + select HAVE_RCU_TABLE_FREE ++ select HAVE_PREEMPT_LAZY + select HAVE_SYSCALL_TRACEPOINTS + select IRQ_DOMAIN ++ select IRQ_FORCED_THREADING + select MODULES_USE_ELF_RELA + select NO_BOOTMEM + select OF +@@ -599,7 +601,7 @@ + + config XEN + bool "Xen guest support on ARM64" +- depends on ARM64 && OF ++ depends on ARM64 && OF && !PREEMPT_RT_FULL + select SWIOTLB_XEN + help + Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64. +diff -Nur linux-4.1.39.orig/arch/arm64/kernel/asm-offsets.c linux-4.1.39/arch/arm64/kernel/asm-offsets.c +--- linux-4.1.39.orig/arch/arm64/kernel/asm-offsets.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm64/kernel/asm-offsets.c 2017-04-18 17:56:30.553394804 +0200 +@@ -35,6 +35,7 @@ + BLANK(); + DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); + DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); ++ DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); + DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); + DEFINE(TI_TASK, offsetof(struct thread_info, task)); + DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); +diff -Nur linux-4.1.39.orig/arch/arm64/kernel/entry.S linux-4.1.39/arch/arm64/kernel/entry.S +--- linux-4.1.39.orig/arch/arm64/kernel/entry.S 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm64/kernel/entry.S 2017-04-18 17:56:30.553394804 +0200 +@@ -380,11 +380,16 @@ + #ifdef CONFIG_PREEMPT + get_thread_info tsk + ldr w24, [tsk, #TI_PREEMPT] // get preempt count +- cbnz w24, 1f // preempt count != 0 ++ cbnz w24, 2f // preempt count != 0 + ldr x0, [tsk, #TI_FLAGS] // get flags +- tbz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? +- bl el1_preempt ++ tbnz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? ++ ++ ldr w24, [tsk, #TI_PREEMPT_LAZY] // get preempt lazy count ++ cbnz w24, 2f // preempt lazy count != 0 ++ tbz x0, #TIF_NEED_RESCHED_LAZY, 2f // needs rescheduling? + 1: ++ bl el1_preempt ++2: + #endif + #ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_on +@@ -398,6 +403,7 @@ + 1: bl preempt_schedule_irq // irq en/disable is done inside + ldr x0, [tsk, #TI_FLAGS] // get new tasks TI_FLAGS + tbnz x0, #TIF_NEED_RESCHED, 1b // needs rescheduling? ++ tbnz x0, #TIF_NEED_RESCHED_LAZY, 1b // needs rescheduling? + ret x24 + #endif + +@@ -635,6 +641,7 @@ + str x0, [sp, #S_X0] // returned x0 + work_pending: + tbnz x1, #TIF_NEED_RESCHED, work_resched ++ tbnz x1, #TIF_NEED_RESCHED_LAZY, work_resched + /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */ + ldr x2, [sp, #S_PSTATE] + mov x0, sp // 'regs' +diff -Nur linux-4.1.39.orig/arch/arm64/kernel/insn.c linux-4.1.39/arch/arm64/kernel/insn.c +--- linux-4.1.39.orig/arch/arm64/kernel/insn.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm64/kernel/insn.c 2017-04-18 17:56:30.553394804 +0200 +@@ -77,7 +77,7 @@ + } + } + +-static DEFINE_SPINLOCK(patch_lock); ++static DEFINE_RAW_SPINLOCK(patch_lock); + + static void __kprobes *patch_map(void *addr, int fixmap) + { +@@ -124,13 +124,13 @@ + unsigned long flags = 0; + int ret; + +- spin_lock_irqsave(&patch_lock, flags); ++ raw_spin_lock_irqsave(&patch_lock, flags); + waddr = patch_map(addr, FIX_TEXT_POKE0); + + ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE); + + patch_unmap(FIX_TEXT_POKE0); +- spin_unlock_irqrestore(&patch_lock, flags); ++ raw_spin_unlock_irqrestore(&patch_lock, flags); + + return ret; + } +diff -Nur linux-4.1.39.orig/arch/arm64/kernel/perf_event.c linux-4.1.39/arch/arm64/kernel/perf_event.c +--- linux-4.1.39.orig/arch/arm64/kernel/perf_event.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm64/kernel/perf_event.c 2017-04-18 17:56:30.553394804 +0200 +@@ -488,7 +488,7 @@ + } + + err = request_irq(irq, armpmu->handle_irq, +- 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 -Nur linux-4.1.39.orig/arch/arm64/mm/fault.c linux-4.1.39/arch/arm64/mm/fault.c +--- linux-4.1.39.orig/arch/arm64/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/arm64/mm/fault.c 2017-04-18 17:56:30.553394804 +0200 +@@ -211,7 +211,7 @@ + * If we're in an interrupt or have no user context, we must not take + * the fault. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +diff -Nur linux-4.1.39.orig/arch/avr32/include/asm/uaccess.h linux-4.1.39/arch/avr32/include/asm/uaccess.h +--- linux-4.1.39.orig/arch/avr32/include/asm/uaccess.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/avr32/include/asm/uaccess.h 2017-04-18 17:56:30.553394804 +0200 +@@ -106,7 +106,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -125,7 +126,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -145,7 +147,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -167,7 +170,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +diff -Nur linux-4.1.39.orig/arch/avr32/mm/fault.c linux-4.1.39/arch/avr32/mm/fault.c +--- linux-4.1.39.orig/arch/avr32/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/avr32/mm/fault.c 2017-04-18 17:56:30.553394804 +0200 +@@ -14,11 +14,11 @@ + #include + #include + #include ++#include + + #include + #include + #include +-#include + + #ifdef CONFIG_KPROBES + static inline int notify_page_fault(struct pt_regs *regs, int trap) +@@ -81,7 +81,7 @@ + * 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 (faulthandler_disabled() || !mm || regs->sr & SYSREG_BIT(GM)) + goto no_context; + + local_irq_enable(); +diff -Nur linux-4.1.39.orig/arch/cris/mm/fault.c linux-4.1.39/arch/cris/mm/fault.c +--- linux-4.1.39.orig/arch/cris/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/cris/mm/fault.c 2017-04-18 17:56:30.553394804 +0200 +@@ -8,7 +8,7 @@ + #include + #include + #include +-#include ++#include + #include + + extern int find_fixup_code(struct pt_regs *); +@@ -109,11 +109,11 @@ + info.si_code = SEGV_MAPERR; + + /* +- * If we're in an interrupt or "atomic" operation or have no ++ * If we're in an interrupt, have pagefaults disabled or have no + * user context, we must not take the fault. + */ + +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +diff -Nur linux-4.1.39.orig/arch/frv/mm/fault.c linux-4.1.39/arch/frv/mm/fault.c +--- linux-4.1.39.orig/arch/frv/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/frv/mm/fault.c 2017-04-18 17:56:30.553394804 +0200 +@@ -19,9 +19,9 @@ + #include + #include + #include ++#include + + #include +-#include + #include + + /*****************************************************************************/ +@@ -78,7 +78,7 @@ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(__frame)) +diff -Nur linux-4.1.39.orig/arch/frv/mm/highmem.c linux-4.1.39/arch/frv/mm/highmem.c +--- linux-4.1.39.orig/arch/frv/mm/highmem.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/frv/mm/highmem.c 2017-04-18 17:56:30.553394804 +0200 +@@ -42,6 +42,7 @@ + unsigned long paddr; + int type; + ++ preempt_disable(); + pagefault_disable(); + type = kmap_atomic_idx_push(); + paddr = page_to_phys(page); +@@ -85,5 +86,6 @@ + } + kmap_atomic_idx_pop(); + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); +diff -Nur linux-4.1.39.orig/arch/hexagon/include/asm/uaccess.h linux-4.1.39/arch/hexagon/include/asm/uaccess.h +--- linux-4.1.39.orig/arch/hexagon/include/asm/uaccess.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/hexagon/include/asm/uaccess.h 2017-04-18 17:56:30.553394804 +0200 +@@ -36,7 +36,8 @@ + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Checks if a pointer to a block of memory in user space is valid. + * +diff -Nur linux-4.1.39.orig/arch/ia64/mm/fault.c linux-4.1.39/arch/ia64/mm/fault.c +--- linux-4.1.39.orig/arch/ia64/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/ia64/mm/fault.c 2017-04-18 17:56:30.553394804 +0200 +@@ -11,10 +11,10 @@ + #include + #include + #include ++#include + + #include + #include +-#include + + extern int die(char *, struct pt_regs *, long); + +@@ -96,7 +96,7 @@ + /* + * If we're in an interrupt or have no user context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + #ifdef CONFIG_VIRTUAL_MEM_MAP +diff -Nur linux-4.1.39.orig/arch/Kconfig linux-4.1.39/arch/Kconfig +--- linux-4.1.39.orig/arch/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/Kconfig 2017-04-18 17:56:30.549394649 +0200 +@@ -6,6 +6,7 @@ + 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 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 -Nur linux-4.1.39.orig/arch/m32r/include/asm/uaccess.h linux-4.1.39/arch/m32r/include/asm/uaccess.h +--- linux-4.1.39.orig/arch/m32r/include/asm/uaccess.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/m32r/include/asm/uaccess.h 2017-04-18 17:56:30.553394804 +0200 +@@ -91,7 +91,8 @@ + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Checks if a pointer to a block of memory in user space is valid. + * +@@ -155,7 +156,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -175,7 +177,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -194,7 +197,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -274,7 +278,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -568,7 +573,8 @@ + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -588,7 +594,8 @@ + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. + * +@@ -606,7 +613,8 @@ + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -626,7 +634,8 @@ + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. + * +@@ -677,7 +686,8 @@ + * strlen_user: - Get the size of a string in user space. + * @str: The string to measure. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Get the size of a NUL-terminated string in user space. + * +diff -Nur linux-4.1.39.orig/arch/m32r/mm/fault.c linux-4.1.39/arch/m32r/mm/fault.c +--- linux-4.1.39.orig/arch/m32r/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/m32r/mm/fault.c 2017-04-18 17:56:30.553394804 +0200 +@@ -24,9 +24,9 @@ + #include /* For unblank_screen() */ + #include + #include ++#include + + #include +-#include + #include + #include + #include +@@ -111,10 +111,10 @@ + mm = tsk->mm; + + /* +- * 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 we're in an interrupt or have no user context or have pagefaults ++ * disabled then we must not take the fault. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto bad_area_nosemaphore; + + if (error_code & ACE_USERMODE) +diff -Nur linux-4.1.39.orig/arch/m68k/mm/fault.c linux-4.1.39/arch/m68k/mm/fault.c +--- linux-4.1.39.orig/arch/m68k/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/m68k/mm/fault.c 2017-04-18 17:56:30.557394959 +0200 +@@ -10,10 +10,10 @@ + #include + #include + #include ++#include + + #include + #include +-#include + #include + + extern void die_if_kernel(char *, struct pt_regs *, long); +@@ -81,7 +81,7 @@ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +diff -Nur linux-4.1.39.orig/arch/metag/mm/fault.c linux-4.1.39/arch/metag/mm/fault.c +--- linux-4.1.39.orig/arch/metag/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/metag/mm/fault.c 2017-04-18 17:56:30.557394959 +0200 +@@ -105,7 +105,7 @@ + + mm = tsk->mm; + +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +diff -Nur linux-4.1.39.orig/arch/metag/mm/highmem.c linux-4.1.39/arch/metag/mm/highmem.c +--- linux-4.1.39.orig/arch/metag/mm/highmem.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/metag/mm/highmem.c 2017-04-18 17:56:30.557394959 +0200 +@@ -43,7 +43,7 @@ + unsigned long vaddr; + int type; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -82,6 +82,7 @@ + } + + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +@@ -95,6 +96,7 @@ + unsigned long vaddr; + int type; + ++ preempt_disable(); + pagefault_disable(); + + type = kmap_atomic_idx_push(); +diff -Nur linux-4.1.39.orig/arch/microblaze/include/asm/uaccess.h linux-4.1.39/arch/microblaze/include/asm/uaccess.h +--- linux-4.1.39.orig/arch/microblaze/include/asm/uaccess.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/microblaze/include/asm/uaccess.h 2017-04-18 17:56:30.557394959 +0200 +@@ -178,7 +178,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -290,7 +291,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +diff -Nur linux-4.1.39.orig/arch/microblaze/mm/fault.c linux-4.1.39/arch/microblaze/mm/fault.c +--- linux-4.1.39.orig/arch/microblaze/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/microblaze/mm/fault.c 2017-04-18 17:56:30.557394959 +0200 +@@ -107,14 +107,14 @@ + if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11) + is_write = 0; + +- if (unlikely(in_atomic() || !mm)) { ++ if (unlikely(faulthandler_disabled() || !mm)) { + if (kernel_mode(regs)) + goto bad_area_nosemaphore; + +- /* in_atomic() in user mode is really bad, ++ /* faulthandler_disabled() in user mode is really bad, + as is current->mm == NULL. */ +- pr_emerg("Page fault in user mode with in_atomic(), mm = %p\n", +- mm); ++ pr_emerg("Page fault in user mode with faulthandler_disabled(), mm = %p\n", ++ mm); + pr_emerg("r15 = %lx MSR = %lx\n", + regs->r15, regs->msr); + die("Weird page fault", regs, SIGSEGV); +diff -Nur linux-4.1.39.orig/arch/microblaze/mm/highmem.c linux-4.1.39/arch/microblaze/mm/highmem.c +--- linux-4.1.39.orig/arch/microblaze/mm/highmem.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/microblaze/mm/highmem.c 2017-04-18 17:56:30.557394959 +0200 +@@ -37,7 +37,7 @@ + unsigned long vaddr; + int idx, type; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -63,6 +63,7 @@ + + if (vaddr < __fix_to_virt(FIX_KMAP_END)) { + pagefault_enable(); ++ preempt_enable(); + return; + } + +@@ -84,5 +85,6 @@ + #endif + kmap_atomic_idx_pop(); + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); +diff -Nur linux-4.1.39.orig/arch/mips/include/asm/uaccess.h linux-4.1.39/arch/mips/include/asm/uaccess.h +--- linux-4.1.39.orig/arch/mips/include/asm/uaccess.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/mips/include/asm/uaccess.h 2017-04-18 17:56:30.557394959 +0200 +@@ -104,7 +104,8 @@ + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Checks if a pointer to a block of memory in user space is valid. + * +@@ -139,7 +140,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -158,7 +160,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -178,7 +181,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -200,7 +204,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -499,7 +504,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -518,7 +524,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -538,7 +545,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -560,7 +568,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -816,7 +825,8 @@ + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -889,7 +899,8 @@ + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. + * +@@ -1076,7 +1087,8 @@ + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -1108,7 +1120,8 @@ + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. + * +@@ -1332,7 +1345,8 @@ + * strlen_user: - Get the size of a string in user space. + * @str: The string to measure. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Get the size of a NUL-terminated string in user space. + * +@@ -1401,7 +1415,8 @@ + * strnlen_user: - Get the size of a string in user space. + * @str: The string to measure. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Get the size of a NUL-terminated string in user space. + * +diff -Nur linux-4.1.39.orig/arch/mips/Kconfig linux-4.1.39/arch/mips/Kconfig +--- linux-4.1.39.orig/arch/mips/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/mips/Kconfig 2017-04-18 17:56:30.557394959 +0200 +@@ -2367,7 +2367,7 @@ + # + config HIGHMEM + bool "High Memory Support" +- depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA ++ depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA && !PREEMPT_RT_FULL + + config CPU_SUPPORTS_HIGHMEM + bool +diff -Nur linux-4.1.39.orig/arch/mips/kernel/signal-common.h linux-4.1.39/arch/mips/kernel/signal-common.h +--- linux-4.1.39.orig/arch/mips/kernel/signal-common.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/mips/kernel/signal-common.h 2017-04-18 17:56:30.557394959 +0200 +@@ -28,12 +28,7 @@ + extern int fpcsr_pending(unsigned int __user *fpcsr); + + /* Make sure we will not lose FPU ownership */ +-#ifdef CONFIG_PREEMPT +-#define lock_fpu_owner() preempt_disable() +-#define unlock_fpu_owner() preempt_enable() +-#else +-#define lock_fpu_owner() pagefault_disable() +-#define unlock_fpu_owner() pagefault_enable() +-#endif ++#define lock_fpu_owner() ({ preempt_disable(); pagefault_disable(); }) ++#define unlock_fpu_owner() ({ pagefault_enable(); preempt_enable(); }) + + #endif /* __SIGNAL_COMMON_H */ +diff -Nur linux-4.1.39.orig/arch/mips/mm/fault.c linux-4.1.39/arch/mips/mm/fault.c +--- linux-4.1.39.orig/arch/mips/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/mips/mm/fault.c 2017-04-18 17:56:30.557394959 +0200 +@@ -21,10 +21,10 @@ + #include + #include + #include ++#include + + #include + #include +-#include + #include + #include /* For VMALLOC_END */ + #include +@@ -94,7 +94,7 @@ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto bad_area_nosemaphore; + + if (user_mode(regs)) +diff -Nur linux-4.1.39.orig/arch/mips/mm/highmem.c linux-4.1.39/arch/mips/mm/highmem.c +--- linux-4.1.39.orig/arch/mips/mm/highmem.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/mips/mm/highmem.c 2017-04-18 17:56:30.557394959 +0200 +@@ -47,7 +47,7 @@ + unsigned long vaddr; + int idx, type; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -72,6 +72,7 @@ + + if (vaddr < FIXADDR_START) { // FIXME + pagefault_enable(); ++ preempt_enable(); + return; + } + +@@ -92,6 +93,7 @@ + #endif + kmap_atomic_idx_pop(); + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +@@ -104,6 +106,7 @@ + unsigned long vaddr; + int idx, type; + ++ preempt_disable(); + pagefault_disable(); + + type = kmap_atomic_idx_push(); +diff -Nur linux-4.1.39.orig/arch/mips/mm/init.c linux-4.1.39/arch/mips/mm/init.c +--- linux-4.1.39.orig/arch/mips/mm/init.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/mips/mm/init.c 2017-04-18 17:56:30.557394959 +0200 +@@ -90,6 +90,7 @@ + + BUG_ON(Page_dcache_dirty(page)); + ++ preempt_disable(); + pagefault_disable(); + idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1); + idx += in_interrupt() ? FIX_N_COLOURS : 0; +@@ -152,6 +153,7 @@ + write_c0_entryhi(old_ctx); + local_irq_restore(flags); + pagefault_enable(); ++ preempt_enable(); + } + + void copy_user_highpage(struct page *to, struct page *from, +diff -Nur linux-4.1.39.orig/arch/mn10300/include/asm/highmem.h linux-4.1.39/arch/mn10300/include/asm/highmem.h +--- linux-4.1.39.orig/arch/mn10300/include/asm/highmem.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/mn10300/include/asm/highmem.h 2017-04-18 17:56:30.557394959 +0200 +@@ -75,6 +75,7 @@ + unsigned long vaddr; + int idx, type; + ++ preempt_disable(); + pagefault_disable(); + if (page < highmem_start_page) + return page_address(page); +@@ -98,6 +99,7 @@ + + if (vaddr < FIXADDR_START) { /* FIXME */ + pagefault_enable(); ++ preempt_enable(); + return; + } + +@@ -122,6 +124,7 @@ + + kmap_atomic_idx_pop(); + pagefault_enable(); ++ preempt_enable(); + } + #endif /* __KERNEL__ */ + +diff -Nur linux-4.1.39.orig/arch/mn10300/mm/fault.c linux-4.1.39/arch/mn10300/mm/fault.c +--- linux-4.1.39.orig/arch/mn10300/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/mn10300/mm/fault.c 2017-04-18 17:56:30.557394959 +0200 +@@ -23,8 +23,8 @@ + #include + #include + #include /* For unblank_screen() */ ++#include + +-#include + #include + #include + #include +@@ -168,7 +168,7 @@ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR) +diff -Nur linux-4.1.39.orig/arch/nios2/mm/fault.c linux-4.1.39/arch/nios2/mm/fault.c +--- linux-4.1.39.orig/arch/nios2/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/nios2/mm/fault.c 2017-04-18 17:56:30.557394959 +0200 +@@ -77,7 +77,7 @@ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto bad_area_nosemaphore; + + if (user_mode(regs)) +diff -Nur linux-4.1.39.orig/arch/parisc/include/asm/cacheflush.h linux-4.1.39/arch/parisc/include/asm/cacheflush.h +--- linux-4.1.39.orig/arch/parisc/include/asm/cacheflush.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/parisc/include/asm/cacheflush.h 2017-04-18 17:56:30.557394959 +0200 +@@ -142,6 +142,7 @@ + + static inline void *kmap_atomic(struct page *page) + { ++ preempt_disable(); + pagefault_disable(); + return page_address(page); + } +@@ -150,6 +151,7 @@ + { + flush_kernel_dcache_page_addr(addr); + pagefault_enable(); ++ preempt_enable(); + } + + #define kmap_atomic_prot(page, prot) kmap_atomic(page) +diff -Nur linux-4.1.39.orig/arch/parisc/kernel/traps.c linux-4.1.39/arch/parisc/kernel/traps.c +--- linux-4.1.39.orig/arch/parisc/kernel/traps.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/parisc/kernel/traps.c 2017-04-18 17:56:30.557394959 +0200 +@@ -26,9 +26,9 @@ + #include + #include + #include ++#include + + #include +-#include + #include + #include + #include +@@ -796,7 +796,7 @@ + * unless pagefault_disable() was called before. + */ + +- if (fault_space == 0 && !in_atomic()) ++ if (fault_space == 0 && !faulthandler_disabled()) + { + /* Clean up and return if in exception table. */ + if (fixup_exception(regs)) +diff -Nur linux-4.1.39.orig/arch/parisc/mm/fault.c linux-4.1.39/arch/parisc/mm/fault.c +--- linux-4.1.39.orig/arch/parisc/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/parisc/mm/fault.c 2017-04-18 17:56:30.557394959 +0200 +@@ -15,8 +15,8 @@ + #include + #include + #include ++#include + +-#include + #include + + /* Various important other fields */ +@@ -208,7 +208,7 @@ + int fault; + unsigned int flags; + +- if (in_atomic()) ++ if (pagefault_disabled()) + goto no_context; + + tsk = current; +diff -Nur linux-4.1.39.orig/arch/powerpc/include/asm/kvm_host.h linux-4.1.39/arch/powerpc/include/asm/kvm_host.h +--- linux-4.1.39.orig/arch/powerpc/include/asm/kvm_host.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/powerpc/include/asm/kvm_host.h 2017-04-18 17:56:30.557394959 +0200 +@@ -280,7 +280,7 @@ + u8 in_guest; + struct list_head runnable_threads; + spinlock_t lock; +- wait_queue_head_t wq; ++ struct swait_head wq; + spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ + u64 stolen_tb; + u64 preempt_tb; +@@ -614,7 +614,7 @@ + u8 prodded; + u32 last_inst; + +- wait_queue_head_t *wqp; ++ struct swait_head *wqp; + struct kvmppc_vcore *vcore; + int ret; + int trap; +diff -Nur linux-4.1.39.orig/arch/powerpc/include/asm/thread_info.h linux-4.1.39/arch/powerpc/include/asm/thread_info.h +--- linux-4.1.39.orig/arch/powerpc/include/asm/thread_info.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/powerpc/include/asm/thread_info.h 2017-04-18 17:56:30.557394959 +0200 +@@ -42,6 +42,8 @@ + int cpu; /* cpu we're on */ + int preempt_count; /* 0 => preemptable, + <0 => BUG */ ++ int preempt_lazy_count; /* 0 => preemptable, ++ <0 => BUG */ + unsigned long local_flags; /* private flags for thread */ + + /* low level flags - has atomic operations done on it */ +@@ -82,8 +84,7 @@ + #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ + #define TIF_SIGPENDING 1 /* signal pending */ + #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ +-#define TIF_POLLING_NRFLAG 3 /* true if poll_idle() is polling +- TIF_NEED_RESCHED */ ++#define TIF_NEED_RESCHED_LAZY 3 /* lazy rescheduling necessary */ + #define TIF_32BIT 4 /* 32 bit binary */ + #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ + #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ +@@ -101,6 +102,8 @@ + #if defined(CONFIG_PPC64) + #define TIF_ELF2ABI 18 /* function descriptors must die! */ + #endif ++#define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling ++ TIF_NEED_RESCHED */ + + /* as above, but as bit values */ + #define _TIF_SYSCALL_TRACE (1<flags) + set_bits(irqtp->flags, &curtp->flags); + } ++#endif + + irq_hw_number_t virq_to_hw(unsigned int virq) + { +diff -Nur linux-4.1.39.orig/arch/powerpc/kernel/misc_32.S linux-4.1.39/arch/powerpc/kernel/misc_32.S +--- linux-4.1.39.orig/arch/powerpc/kernel/misc_32.S 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/powerpc/kernel/misc_32.S 2017-04-18 17:56:30.561395114 +0200 +@@ -40,6 +40,7 @@ + * We store the saved ksp_limit in the unused part + * of the STACK_FRAME_OVERHEAD + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + _GLOBAL(call_do_softirq) + mflr r0 + stw r0,4(r1) +@@ -56,6 +57,7 @@ + stw r10,THREAD+KSP_LIMIT(r2) + mtlr r0 + blr ++#endif + + /* + * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp); +diff -Nur linux-4.1.39.orig/arch/powerpc/kernel/misc_64.S linux-4.1.39/arch/powerpc/kernel/misc_64.S +--- linux-4.1.39.orig/arch/powerpc/kernel/misc_64.S 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/powerpc/kernel/misc_64.S 2017-04-18 17:56:30.561395114 +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 @@ + ld r0,16(r1) + mtlr r0 + blr ++#endif + + _GLOBAL(call_do_irq) + mflr r0 +diff -Nur linux-4.1.39.orig/arch/powerpc/kvm/book3s_hv.c linux-4.1.39/arch/powerpc/kvm/book3s_hv.c +--- linux-4.1.39.orig/arch/powerpc/kvm/book3s_hv.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/powerpc/kvm/book3s_hv.c 2017-04-18 17:56:30.561395114 +0200 +@@ -115,11 +115,11 @@ + static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) + { + int cpu = vcpu->cpu; +- wait_queue_head_t *wqp; ++ struct swait_head *wqp; + + wqp = kvm_arch_vcpu_wq(vcpu); +- if (waitqueue_active(wqp)) { +- wake_up_interruptible(wqp); ++ if (swaitqueue_active(wqp)) { ++ swait_wake_interruptible(wqp); + ++vcpu->stat.halt_wakeup; + } + +@@ -692,8 +692,8 @@ + tvcpu->arch.prodded = 1; + smp_mb(); + if (vcpu->arch.ceded) { +- if (waitqueue_active(&vcpu->wq)) { +- wake_up_interruptible(&vcpu->wq); ++ if (swaitqueue_active(&vcpu->wq)) { ++ swait_wake_interruptible(&vcpu->wq); + vcpu->stat.halt_wakeup++; + } + } +@@ -1438,7 +1438,7 @@ + INIT_LIST_HEAD(&vcore->runnable_threads); + spin_lock_init(&vcore->lock); + spin_lock_init(&vcore->stoltb_lock); +- init_waitqueue_head(&vcore->wq); ++ init_swait_head(&vcore->wq); + vcore->preempt_tb = TB_NIL; + vcore->lpcr = kvm->arch.lpcr; + vcore->first_vcpuid = core * threads_per_subcore; +@@ -2085,10 +2085,9 @@ + { + struct kvm_vcpu *vcpu; + int do_sleep = 1; ++ DEFINE_SWAITER(wait); + +- DEFINE_WAIT(wait); +- +- prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE); ++ swait_prepare(&vc->wq, &wait, TASK_INTERRUPTIBLE); + + /* + * Check one last time for pending exceptions and ceded state after +@@ -2102,7 +2101,7 @@ + } + + if (!do_sleep) { +- finish_wait(&vc->wq, &wait); ++ swait_finish(&vc->wq, &wait); + return; + } + +@@ -2110,7 +2109,7 @@ + trace_kvmppc_vcore_blocked(vc, 0); + spin_unlock(&vc->lock); + schedule(); +- finish_wait(&vc->wq, &wait); ++ swait_finish(&vc->wq, &wait); + spin_lock(&vc->lock); + vc->vcore_state = VCORE_INACTIVE; + trace_kvmppc_vcore_blocked(vc, 1); +@@ -2154,7 +2153,7 @@ + kvmppc_start_thread(vcpu); + trace_kvm_guest_enter(vcpu); + } else if (vc->vcore_state == VCORE_SLEEPING) { +- wake_up(&vc->wq); ++ swait_wake(&vc->wq); + } + + } +diff -Nur linux-4.1.39.orig/arch/powerpc/kvm/Kconfig linux-4.1.39/arch/powerpc/kvm/Kconfig +--- linux-4.1.39.orig/arch/powerpc/kvm/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/powerpc/kvm/Kconfig 2017-04-18 17:56:30.561395114 +0200 +@@ -172,6 +172,7 @@ + config KVM_MPIC + bool "KVM in-kernel MPIC emulation" + depends on KVM && E500 ++ depends on !PREEMPT_RT_FULL + select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQFD + select HAVE_KVM_IRQ_ROUTING +diff -Nur linux-4.1.39.orig/arch/powerpc/mm/fault.c linux-4.1.39/arch/powerpc/mm/fault.c +--- linux-4.1.39.orig/arch/powerpc/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/powerpc/mm/fault.c 2017-04-18 17:56:30.561395114 +0200 +@@ -33,13 +33,13 @@ + #include + #include + #include ++#include + + #include + #include + #include + #include + #include +-#include + #include + #include + #include +@@ -272,15 +272,16 @@ + if (!arch_irq_disabled_regs(regs)) + local_irq_enable(); + +- if (in_atomic() || mm == NULL) { ++ if (faulthandler_disabled() || mm == NULL) { + if (!user_mode(regs)) { + rc = SIGSEGV; + goto bail; + } +- /* in_atomic() in user mode is really bad, ++ /* faulthandler_disabled() in user mode is really bad, + as is current->mm == NULL. */ + printk(KERN_EMERG "Page fault in user mode with " +- "in_atomic() = %d mm = %p\n", in_atomic(), mm); ++ "faulthandler_disabled() = %d mm = %p\n", ++ faulthandler_disabled(), mm); + printk(KERN_EMERG "NIP = %lx MSR = %lx\n", + regs->nip, regs->msr); + die("Weird page fault", regs, SIGSEGV); +diff -Nur linux-4.1.39.orig/arch/powerpc/mm/highmem.c linux-4.1.39/arch/powerpc/mm/highmem.c +--- linux-4.1.39.orig/arch/powerpc/mm/highmem.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/powerpc/mm/highmem.c 2017-04-18 17:56:30.561395114 +0200 +@@ -34,7 +34,7 @@ + unsigned long vaddr; + int idx, type; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -59,6 +59,7 @@ + + if (vaddr < __fix_to_virt(FIX_KMAP_END)) { + pagefault_enable(); ++ preempt_enable(); + return; + } + +@@ -82,5 +83,6 @@ + + kmap_atomic_idx_pop(); + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); +diff -Nur linux-4.1.39.orig/arch/powerpc/platforms/ps3/device-init.c linux-4.1.39/arch/powerpc/platforms/ps3/device-init.c +--- linux-4.1.39.orig/arch/powerpc/platforms/ps3/device-init.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/powerpc/platforms/ps3/device-init.c 2017-04-18 17:56:30.561395114 +0200 +@@ -752,7 +752,7 @@ + } + pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op); + +- res = wait_event_interruptible(dev->done.wait, ++ res = swait_event_interruptible(dev->done.wait, + dev->done.done || kthread_should_stop()); + if (kthread_should_stop()) + res = -EINTR; +diff -Nur linux-4.1.39.orig/arch/s390/include/asm/kvm_host.h linux-4.1.39/arch/s390/include/asm/kvm_host.h +--- linux-4.1.39.orig/arch/s390/include/asm/kvm_host.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/s390/include/asm/kvm_host.h 2017-04-18 17:56:30.561395114 +0200 +@@ -419,7 +419,7 @@ + struct kvm_s390_local_interrupt { + spinlock_t lock; + struct kvm_s390_float_interrupt *float_int; +- wait_queue_head_t *wq; ++ struct swait_head *wq; + atomic_t *cpuflags; + DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS); + struct kvm_s390_irq_payload irq; +diff -Nur linux-4.1.39.orig/arch/s390/include/asm/uaccess.h linux-4.1.39/arch/s390/include/asm/uaccess.h +--- linux-4.1.39.orig/arch/s390/include/asm/uaccess.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/s390/include/asm/uaccess.h 2017-04-18 17:56:30.561395114 +0200 +@@ -98,7 +98,8 @@ + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -118,7 +119,8 @@ + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -264,7 +266,8 @@ + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. + * +@@ -290,7 +293,8 @@ + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. + * +@@ -348,7 +352,8 @@ + * strlen_user: - Get the size of a string in user space. + * @str: The string to measure. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Get the size of a NUL-terminated string in user space. + * +diff -Nur linux-4.1.39.orig/arch/s390/kvm/interrupt.c linux-4.1.39/arch/s390/kvm/interrupt.c +--- linux-4.1.39.orig/arch/s390/kvm/interrupt.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/s390/kvm/interrupt.c 2017-04-18 17:56:30.561395114 +0200 +@@ -875,13 +875,13 @@ + + void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) + { +- if (waitqueue_active(&vcpu->wq)) { ++ if (swaitqueue_active(&vcpu->wq)) { + /* + * The vcpu gave up the cpu voluntarily, mark it as a good + * yield-candidate. + */ + vcpu->preempted = true; +- wake_up_interruptible(&vcpu->wq); ++ swait_wake_interruptible(&vcpu->wq); + vcpu->stat.halt_wakeup++; + } + } +@@ -987,7 +987,7 @@ + spin_lock(&li->lock); + irq.u.pgm.code = code; + __inject_prog(vcpu, &irq); +- BUG_ON(waitqueue_active(li->wq)); ++ BUG_ON(swaitqueue_active(li->wq)); + spin_unlock(&li->lock); + return 0; + } +@@ -1006,7 +1006,7 @@ + spin_lock(&li->lock); + irq.u.pgm = *pgm_info; + rc = __inject_prog(vcpu, &irq); +- BUG_ON(waitqueue_active(li->wq)); ++ BUG_ON(swaitqueue_active(li->wq)); + spin_unlock(&li->lock); + return rc; + } +diff -Nur linux-4.1.39.orig/arch/s390/mm/fault.c linux-4.1.39/arch/s390/mm/fault.c +--- linux-4.1.39.orig/arch/s390/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/s390/mm/fault.c 2017-04-18 17:56:30.561395114 +0200 +@@ -399,7 +399,7 @@ + * user context. + */ + fault = VM_FAULT_BADCONTEXT; +- if (unlikely(!user_space_fault(regs) || in_atomic() || !mm)) ++ if (unlikely(!user_space_fault(regs) || faulthandler_disabled() || !mm)) + goto out; + + address = trans_exc_code & __FAIL_ADDR_MASK; +diff -Nur linux-4.1.39.orig/arch/score/include/asm/uaccess.h linux-4.1.39/arch/score/include/asm/uaccess.h +--- linux-4.1.39.orig/arch/score/include/asm/uaccess.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/score/include/asm/uaccess.h 2017-04-18 17:56:30.561395114 +0200 +@@ -36,7 +36,8 @@ + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Checks if a pointer to a block of memory in user space is valid. + * +@@ -61,7 +62,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -79,7 +81,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -98,7 +101,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -119,7 +123,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +diff -Nur linux-4.1.39.orig/arch/score/mm/fault.c linux-4.1.39/arch/score/mm/fault.c +--- linux-4.1.39.orig/arch/score/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/score/mm/fault.c 2017-04-18 17:56:30.561395114 +0200 +@@ -34,6 +34,7 @@ + #include + #include + #include ++#include + + /* + * This routine handles page faults. It determines the address, +@@ -73,7 +74,7 @@ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (pagefault_disabled() || !mm) + goto bad_area_nosemaphore; + + if (user_mode(regs)) +diff -Nur linux-4.1.39.orig/arch/sh/kernel/irq.c linux-4.1.39/arch/sh/kernel/irq.c +--- linux-4.1.39.orig/arch/sh/kernel/irq.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/sh/kernel/irq.c 2017-04-18 17:56:30.561395114 +0200 +@@ -147,6 +147,7 @@ + hardirq_ctx[cpu] = NULL; + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct thread_info *curctx; +@@ -174,6 +175,7 @@ + "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr" + ); + } ++#endif + #else + static inline void handle_one_irq(unsigned int irq) + { +diff -Nur linux-4.1.39.orig/arch/sh/mm/fault.c linux-4.1.39/arch/sh/mm/fault.c +--- linux-4.1.39.orig/arch/sh/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/sh/mm/fault.c 2017-04-18 17:56:30.561395114 +0200 +@@ -17,6 +17,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -438,9 +439,9 @@ + + /* + * If we're in an interrupt, have no user context or are running +- * in an atomic region then we must not take the fault: ++ * with pagefaults disabled then we must not take the fault: + */ +- if (unlikely(in_atomic() || !mm)) { ++ if (unlikely(faulthandler_disabled() || !mm)) { + bad_area_nosemaphore(regs, error_code, address); + return; + } +diff -Nur linux-4.1.39.orig/arch/sparc/Kconfig linux-4.1.39/arch/sparc/Kconfig +--- linux-4.1.39.orig/arch/sparc/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/sparc/Kconfig 2017-04-18 17:56:30.561395114 +0200 +@@ -189,12 +189,10 @@ + source kernel/Kconfig.hz + + config RWSEM_GENERIC_SPINLOCK +- bool +- default y if SPARC32 ++ def_bool PREEMPT_RT_FULL + + config RWSEM_XCHGADD_ALGORITHM +- bool +- default y if SPARC64 ++ def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL + + config GENERIC_HWEIGHT + bool +diff -Nur linux-4.1.39.orig/arch/sparc/kernel/irq_64.c linux-4.1.39/arch/sparc/kernel/irq_64.c +--- linux-4.1.39.orig/arch/sparc/kernel/irq_64.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/sparc/kernel/irq_64.c 2017-04-18 17:56:30.561395114 +0200 +@@ -849,6 +849,7 @@ + set_irq_regs(old_regs); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + void *orig_sp, *sp = softirq_stack[smp_processor_id()]; +@@ -863,6 +864,7 @@ + __asm__ __volatile__("mov %0, %%sp" + : : "r" (orig_sp)); + } ++#endif + + #ifdef CONFIG_HOTPLUG_CPU + void fixup_irqs(void) +diff -Nur linux-4.1.39.orig/arch/sparc/mm/fault_32.c linux-4.1.39/arch/sparc/mm/fault_32.c +--- linux-4.1.39.orig/arch/sparc/mm/fault_32.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/sparc/mm/fault_32.c 2017-04-18 17:56:30.561395114 +0200 +@@ -21,6 +21,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -29,7 +30,6 @@ + #include + #include + #include +-#include + + #include "mm_32.h" + +@@ -196,7 +196,7 @@ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (pagefault_disabled() || !mm) + goto no_context; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); +diff -Nur linux-4.1.39.orig/arch/sparc/mm/fault_64.c linux-4.1.39/arch/sparc/mm/fault_64.c +--- linux-4.1.39.orig/arch/sparc/mm/fault_64.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/sparc/mm/fault_64.c 2017-04-18 17:56:30.561395114 +0200 +@@ -22,12 +22,12 @@ + #include + #include + #include ++#include + + #include + #include + #include + #include +-#include + #include + #include + #include +@@ -330,7 +330,7 @@ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto intr_or_no_mm; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); +diff -Nur linux-4.1.39.orig/arch/sparc/mm/highmem.c linux-4.1.39/arch/sparc/mm/highmem.c +--- linux-4.1.39.orig/arch/sparc/mm/highmem.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/sparc/mm/highmem.c 2017-04-18 17:56:30.561395114 +0200 +@@ -53,7 +53,7 @@ + unsigned long vaddr; + long idx, type; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -91,6 +91,7 @@ + + if (vaddr < FIXADDR_START) { // FIXME + pagefault_enable(); ++ preempt_enable(); + return; + } + +@@ -126,5 +127,6 @@ + + kmap_atomic_idx_pop(); + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); +diff -Nur linux-4.1.39.orig/arch/sparc/mm/init_64.c linux-4.1.39/arch/sparc/mm/init_64.c +--- linux-4.1.39.orig/arch/sparc/mm/init_64.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/sparc/mm/init_64.c 2017-04-18 17:56:30.565395270 +0200 +@@ -2738,7 +2738,7 @@ + struct mm_struct *mm = current->mm; + struct tsb_config *tp; + +- if (in_atomic() || !mm) { ++ if (faulthandler_disabled() || !mm) { + const struct exception_table_entry *entry; + + entry = search_exception_tables(regs->tpc); +diff -Nur linux-4.1.39.orig/arch/tile/include/asm/uaccess.h linux-4.1.39/arch/tile/include/asm/uaccess.h +--- linux-4.1.39.orig/arch/tile/include/asm/uaccess.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/tile/include/asm/uaccess.h 2017-04-18 17:56:30.565395270 +0200 +@@ -78,7 +78,8 @@ + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Checks if a pointer to a block of memory in user space is valid. + * +@@ -192,7 +193,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -274,7 +276,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -330,7 +333,8 @@ + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -366,7 +370,8 @@ + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -437,7 +442,8 @@ + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to user space. Caller must check + * the specified blocks with access_ok() before calling this function. +diff -Nur linux-4.1.39.orig/arch/tile/mm/fault.c linux-4.1.39/arch/tile/mm/fault.c +--- linux-4.1.39.orig/arch/tile/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/tile/mm/fault.c 2017-04-18 17:56:30.565395270 +0200 +@@ -354,9 +354,9 @@ + + /* + * If we're in an interrupt, have no user context or are running in an +- * atomic region then we must not take the fault. ++ * region with pagefaults disabled then we must not take the fault. + */ +- if (in_atomic() || !mm) { ++ if (pagefault_disabled() || !mm) { + vma = NULL; /* happy compiler */ + goto bad_area_nosemaphore; + } +diff -Nur linux-4.1.39.orig/arch/tile/mm/highmem.c linux-4.1.39/arch/tile/mm/highmem.c +--- linux-4.1.39.orig/arch/tile/mm/highmem.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/tile/mm/highmem.c 2017-04-18 17:56:30.565395270 +0200 +@@ -201,7 +201,7 @@ + int idx, type; + pte_t *pte; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + + /* Avoid icache flushes by disallowing atomic executable mappings. */ +@@ -259,6 +259,7 @@ + } + + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +diff -Nur linux-4.1.39.orig/arch/um/kernel/trap.c linux-4.1.39/arch/um/kernel/trap.c +--- linux-4.1.39.orig/arch/um/kernel/trap.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/um/kernel/trap.c 2017-04-18 17:56:30.565395270 +0200 +@@ -35,10 +35,10 @@ + *code_out = SEGV_MAPERR; + + /* +- * If the fault was during atomic operation, don't take the fault, just ++ * If the fault was with pagefaults disabled, don't take the fault, just + * fail. + */ +- if (in_atomic()) ++ if (faulthandler_disabled()) + goto out_nosemaphore; + + if (is_user) +diff -Nur linux-4.1.39.orig/arch/unicore32/mm/fault.c linux-4.1.39/arch/unicore32/mm/fault.c +--- linux-4.1.39.orig/arch/unicore32/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/unicore32/mm/fault.c 2017-04-18 17:56:30.565395270 +0200 +@@ -218,7 +218,7 @@ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +diff -Nur linux-4.1.39.orig/arch/x86/crypto/aesni-intel_glue.c linux-4.1.39/arch/x86/crypto/aesni-intel_glue.c +--- linux-4.1.39.orig/arch/x86/crypto/aesni-intel_glue.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/crypto/aesni-intel_glue.c 2017-04-18 17:56:30.565395270 +0200 +@@ -382,14 +382,14 @@ + 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; + } +@@ -406,14 +406,14 @@ + 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; + } +@@ -430,14 +430,14 @@ + 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; + } +@@ -454,14 +454,14 @@ + 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; + } +@@ -513,18 +513,20 @@ + 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_tfm(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 -Nur linux-4.1.39.orig/arch/x86/crypto/cast5_avx_glue.c linux-4.1.39/arch/x86/crypto/cast5_avx_glue.c +--- linux-4.1.39.orig/arch/x86/crypto/cast5_avx_glue.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/crypto/cast5_avx_glue.c 2017-04-18 17:56:30.565395270 +0200 +@@ -60,7 +60,7 @@ + static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk, + bool enc) + { +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + const unsigned int bsize = CAST5_BLOCK_SIZE; + unsigned int nbytes; +@@ -76,7 +76,7 @@ + u8 *wsrc = walk->src.virt.addr; + u8 *wdst = walk->dst.virt.addr; + +- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, nbytes); + + /* Process multi-block batch */ + if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) { +@@ -104,10 +104,9 @@ + } while (nbytes >= bsize); + + done: ++ cast5_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, walk, nbytes); + } +- +- cast5_fpu_end(fpu_enabled); + return err; + } + +@@ -228,7 +227,7 @@ + static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) + { +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -237,12 +236,11 @@ + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + + while ((nbytes = walk.nbytes)) { +- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, nbytes); + nbytes = __cbc_decrypt(desc, &walk); ++ cast5_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- +- cast5_fpu_end(fpu_enabled); + return err; + } + +@@ -312,7 +310,7 @@ + static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) + { +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -321,13 +319,12 @@ + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + + while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) { +- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, nbytes); + nbytes = __ctr_crypt(desc, &walk); ++ cast5_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + +- cast5_fpu_end(fpu_enabled); +- + if (walk.nbytes) { + ctr_crypt_final(desc, &walk); + err = blkcipher_walk_done(desc, &walk, 0); +diff -Nur linux-4.1.39.orig/arch/x86/crypto/glue_helper.c linux-4.1.39/arch/x86/crypto/glue_helper.c +--- linux-4.1.39.orig/arch/x86/crypto/glue_helper.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/crypto/glue_helper.c 2017-04-18 17:56:30.565395270 +0200 +@@ -39,7 +39,7 @@ + void *ctx = crypto_blkcipher_ctx(desc->tfm); + const unsigned int bsize = 128 / 8; + unsigned int nbytes, i, func_bytes; +- bool fpu_enabled = false; ++ bool fpu_enabled; + int err; + + err = blkcipher_walk_virt(desc, walk); +@@ -49,7 +49,7 @@ + u8 *wdst = walk->dst.virt.addr; + + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- desc, fpu_enabled, nbytes); ++ desc, false, nbytes); + + for (i = 0; i < gctx->num_funcs; i++) { + func_bytes = bsize * gctx->funcs[i].num_blocks; +@@ -71,10 +71,10 @@ + } + + done: ++ glue_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); + return err; + } + +@@ -194,7 +194,7 @@ + struct scatterlist *src, unsigned int nbytes) + { + const unsigned int bsize = 128 / 8; +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -203,12 +203,12 @@ + + while ((nbytes = walk.nbytes)) { + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- desc, fpu_enabled, nbytes); ++ desc, false, nbytes); + nbytes = __glue_cbc_decrypt_128bit(gctx, desc, &walk); ++ glue_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); + return err; + } + EXPORT_SYMBOL_GPL(glue_cbc_decrypt_128bit); +@@ -277,7 +277,7 @@ + struct scatterlist *src, unsigned int nbytes) + { + const unsigned int bsize = 128 / 8; +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -286,13 +286,12 @@ + + while ((nbytes = walk.nbytes) >= bsize) { + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- desc, fpu_enabled, nbytes); ++ desc, false, nbytes); + nbytes = __glue_ctr_crypt_128bit(gctx, desc, &walk); ++ glue_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); +- + if (walk.nbytes) { + glue_ctr_crypt_final_128bit( + gctx->funcs[gctx->num_funcs - 1].fn_u.ctr, desc, &walk); +@@ -347,7 +346,7 @@ + void *tweak_ctx, void *crypt_ctx) + { + const unsigned int bsize = 128 / 8; +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -360,21 +359,21 @@ + + /* set minimum length to bsize, for tweak_fn */ + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- desc, fpu_enabled, ++ desc, false, + nbytes < bsize ? bsize : nbytes); +- + /* calculate first value of T */ + tweak_fn(tweak_ctx, walk.iv, walk.iv); ++ glue_fpu_end(fpu_enabled); + + while (nbytes) { ++ fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, ++ desc, false, nbytes); + nbytes = __glue_xts_crypt_128bit(gctx, crypt_ctx, desc, &walk); + ++ glue_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + nbytes = walk.nbytes; + } +- +- glue_fpu_end(fpu_enabled); +- + return err; + } + EXPORT_SYMBOL_GPL(glue_xts_crypt_128bit); +diff -Nur linux-4.1.39.orig/arch/x86/include/asm/preempt.h linux-4.1.39/arch/x86/include/asm/preempt.h +--- linux-4.1.39.orig/arch/x86/include/asm/preempt.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/include/asm/preempt.h 2017-04-18 17:56:30.565395270 +0200 +@@ -82,17 +82,46 @@ + * a decrement which hits zero means we have no preempt_count and should + * reschedule. + */ +-static __always_inline bool __preempt_count_dec_and_test(void) ++static __always_inline bool ____preempt_count_dec_and_test(void) + { + GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e"); + } + ++static __always_inline bool __preempt_count_dec_and_test(void) ++{ ++ if (____preempt_count_dec_and_test()) ++ return true; ++#ifdef CONFIG_PREEMPT_LAZY ++ if (current_thread_info()->preempt_lazy_count) ++ return false; ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else ++ return false; ++#endif ++} ++ + /* + * Returns true when we need to resched and can (barring IRQ state). + */ + static __always_inline bool should_resched(int preempt_offset) + { ++#ifdef CONFIG_PREEMPT_LAZY ++ u32 tmp; ++ ++ tmp = raw_cpu_read_4(__preempt_count); ++ if (tmp == preempt_offset) ++ return true; ++ ++ /* preempt count == 0 ? */ ++ tmp &= ~PREEMPT_NEED_RESCHED; ++ if (tmp) ++ return false; ++ if (current_thread_info()->preempt_lazy_count) ++ return false; ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else + return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); ++#endif + } + + #ifdef CONFIG_PREEMPT +diff -Nur linux-4.1.39.orig/arch/x86/include/asm/signal.h linux-4.1.39/arch/x86/include/asm/signal.h +--- linux-4.1.39.orig/arch/x86/include/asm/signal.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/include/asm/signal.h 2017-04-18 17:56:30.565395270 +0200 +@@ -23,6 +23,19 @@ + 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) ++#define ARCH_RT_DELAYS_SIGNAL_SEND ++#endif ++ + #ifndef CONFIG_COMPAT + typedef sigset_t compat_sigset_t; + #endif +diff -Nur linux-4.1.39.orig/arch/x86/include/asm/stackprotector.h linux-4.1.39/arch/x86/include/asm/stackprotector.h +--- linux-4.1.39.orig/arch/x86/include/asm/stackprotector.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/include/asm/stackprotector.h 2017-04-18 17:56:30.565395270 +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 @@ + * 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 -Nur linux-4.1.39.orig/arch/x86/include/asm/thread_info.h linux-4.1.39/arch/x86/include/asm/thread_info.h +--- linux-4.1.39.orig/arch/x86/include/asm/thread_info.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/include/asm/thread_info.h 2017-04-18 17:56:30.565395270 +0200 +@@ -55,6 +55,8 @@ + __u32 status; /* thread synchronous flags */ + __u32 cpu; /* current CPU */ + int saved_preempt_count; ++ int preempt_lazy_count; /* 0 => lazy preemptable ++ <0 => BUG */ + mm_segment_t addr_limit; + void __user *sysenter_return; + unsigned int sig_on_uaccess_error:1; +@@ -95,6 +97,7 @@ + #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ + #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ + #define TIF_SECCOMP 8 /* secure computing */ ++#define TIF_NEED_RESCHED_LAZY 9 /* lazy rescheduling necessary */ + #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ + #define TIF_UPROBE 12 /* breakpointed or singlestepping */ + #define TIF_NOTSC 16 /* TSC is not accessible in userland */ +@@ -119,6 +122,7 @@ + #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) + #define _TIF_SECCOMP (1 << TIF_SECCOMP) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) + #define _TIF_UPROBE (1 << TIF_UPROBE) + #define _TIF_NOTSC (1 << TIF_NOTSC) +@@ -168,6 +172,8 @@ + #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) + #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) + ++#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) ++ + #define STACK_WARN (THREAD_SIZE/8) + + /* +diff -Nur linux-4.1.39.orig/arch/x86/include/asm/uaccess_32.h linux-4.1.39/arch/x86/include/asm/uaccess_32.h +--- linux-4.1.39.orig/arch/x86/include/asm/uaccess_32.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/include/asm/uaccess_32.h 2017-04-18 17:56:30.565395270 +0200 +@@ -70,7 +70,8 @@ + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -117,7 +118,8 @@ + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. Caller must check + * the specified block with access_ok() before calling this function. +diff -Nur linux-4.1.39.orig/arch/x86/include/asm/uaccess.h linux-4.1.39/arch/x86/include/asm/uaccess.h +--- linux-4.1.39.orig/arch/x86/include/asm/uaccess.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/include/asm/uaccess.h 2017-04-18 17:56:30.565395270 +0200 +@@ -74,7 +74,8 @@ + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Checks if a pointer to a block of memory in user space is valid. + * +@@ -145,7 +146,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -240,7 +242,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -459,7 +462,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -483,7 +487,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +diff -Nur linux-4.1.39.orig/arch/x86/include/asm/uv/uv_bau.h linux-4.1.39/arch/x86/include/asm/uv/uv_bau.h +--- linux-4.1.39.orig/arch/x86/include/asm/uv/uv_bau.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/include/asm/uv/uv_bau.h 2017-04-18 17:56:30.565395270 +0200 +@@ -615,9 +615,9 @@ + cycles_t send_message; + cycles_t period_end; + cycles_t period_time; +- spinlock_t uvhub_lock; +- spinlock_t queue_lock; +- spinlock_t disable_lock; ++ raw_spinlock_t uvhub_lock; ++ raw_spinlock_t queue_lock; ++ raw_spinlock_t disable_lock; + /* tunables */ + int max_concurr; + int max_concurr_const; +@@ -776,15 +776,15 @@ + * 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 -Nur linux-4.1.39.orig/arch/x86/include/asm/uv/uv_hub.h linux-4.1.39/arch/x86/include/asm/uv/uv_hub.h +--- linux-4.1.39.orig/arch/x86/include/asm/uv/uv_hub.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/include/asm/uv/uv_hub.h 2017-04-18 17:56:30.565395270 +0200 +@@ -492,7 +492,7 @@ + unsigned short nr_online_cpus; + unsigned short pnode; + short memory_nid; +- spinlock_t nmi_lock; /* obsolete, see uv_hub_nmi */ ++ raw_spinlock_t nmi_lock; /* obsolete, see uv_hub_nmi */ + unsigned long nmi_count; /* obsolete, see uv_hub_nmi */ + }; + extern struct uv_blade_info *uv_blade_info; +diff -Nur linux-4.1.39.orig/arch/x86/Kconfig linux-4.1.39/arch/x86/Kconfig +--- linux-4.1.39.orig/arch/x86/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/Kconfig 2017-04-18 17:56:30.565395270 +0200 +@@ -22,6 +22,7 @@ + ### Arch settings + config X86 + def_bool y ++ select HAVE_PREEMPT_LAZY + select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI + select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI + select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS +@@ -203,8 +204,11 @@ + def_bool y + depends on ISA_DMA_API + ++config RWSEM_GENERIC_SPINLOCK ++ def_bool PREEMPT_RT_FULL ++ + config RWSEM_XCHGADD_ALGORITHM +- def_bool y ++ def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL + + config GENERIC_CALIBRATE_DELAY + def_bool y +@@ -838,7 +842,7 @@ + config MAXSMP + bool "Enable Maximum number of SMP Processors and NUMA Nodes" + depends on X86_64 && SMP && DEBUG_KERNEL +- 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 -Nur linux-4.1.39.orig/arch/x86/kernel/acpi/boot.c linux-4.1.39/arch/x86/kernel/acpi/boot.c +--- linux-4.1.39.orig/arch/x86/kernel/acpi/boot.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/acpi/boot.c 2017-04-18 17:56:30.565395270 +0200 +@@ -87,7 +87,9 @@ + * ->ioapic_mutex + * ->ioapic_lock + */ ++#ifdef CONFIG_X86_IO_APIC + static DEFINE_MUTEX(acpi_ioapic_lock); ++#endif + + /* -------------------------------------------------------------------------- + Boot-time Configuration +diff -Nur linux-4.1.39.orig/arch/x86/kernel/apic/io_apic.c linux-4.1.39/arch/x86/kernel/apic/io_apic.c +--- linux-4.1.39.orig/arch/x86/kernel/apic/io_apic.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/apic/io_apic.c 2017-04-18 17:56:30.565395270 +0200 +@@ -1891,7 +1891,8 @@ + 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 -Nur linux-4.1.39.orig/arch/x86/kernel/apic/x2apic_uv_x.c linux-4.1.39/arch/x86/kernel/apic/x2apic_uv_x.c +--- linux-4.1.39.orig/arch/x86/kernel/apic/x2apic_uv_x.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/apic/x2apic_uv_x.c 2017-04-18 17:56:30.569395424 +0200 +@@ -949,7 +949,7 @@ + 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); + min_pnode = min(pnode, min_pnode); + max_pnode = max(pnode, max_pnode); + blade++; +diff -Nur linux-4.1.39.orig/arch/x86/kernel/asm-offsets.c linux-4.1.39/arch/x86/kernel/asm-offsets.c +--- linux-4.1.39.orig/arch/x86/kernel/asm-offsets.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/asm-offsets.c 2017-04-18 17:56:30.569395424 +0200 +@@ -32,6 +32,7 @@ + OFFSET(TI_flags, thread_info, flags); + OFFSET(TI_status, thread_info, status); + OFFSET(TI_addr_limit, thread_info, addr_limit); ++ OFFSET(TI_preempt_lazy_count, thread_info, preempt_lazy_count); + + BLANK(); + OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx); +@@ -71,4 +72,5 @@ + + BLANK(); + DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); ++ DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED); + } +diff -Nur linux-4.1.39.orig/arch/x86/kernel/cpu/mcheck/mce.c linux-4.1.39/arch/x86/kernel/cpu/mcheck/mce.c +--- linux-4.1.39.orig/arch/x86/kernel/cpu/mcheck/mce.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/cpu/mcheck/mce.c 2017-04-18 17:56:30.569395424 +0200 +@@ -41,6 +41,8 @@ + #include + #include + #include ++#include ++#include + + #include + #include +@@ -1267,7 +1269,7 @@ + static unsigned long check_interval = INITIAL_CHECK_INTERVAL; + + static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ +-static DEFINE_PER_CPU(struct timer_list, mce_timer); ++static DEFINE_PER_CPU(struct hrtimer, mce_timer); + + static unsigned long mce_adjust_timer_default(unsigned long interval) + { +@@ -1276,32 +1278,18 @@ + + static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; + +-static void __restart_timer(struct timer_list *t, unsigned long interval) ++static enum hrtimer_restart __restart_timer(struct hrtimer *timer, unsigned long interval) + { +- unsigned long when = jiffies + interval; +- unsigned long flags; +- +- local_irq_save(flags); +- +- if (timer_pending(t)) { +- if (time_before(when, t->expires)) +- mod_timer_pinned(t, when); +- } else { +- t->expires = round_jiffies(when); +- add_timer_on(t, smp_processor_id()); +- } +- +- local_irq_restore(flags); ++ if (!interval) ++ return HRTIMER_NORESTART; ++ hrtimer_forward_now(timer, ns_to_ktime(jiffies_to_nsecs(interval))); ++ return HRTIMER_RESTART; + } + +-static void mce_timer_fn(unsigned long data) ++static enum hrtimer_restart mce_timer_fn(struct hrtimer *timer) + { +- struct timer_list *t = this_cpu_ptr(&mce_timer); +- int cpu = smp_processor_id(); + unsigned long iv; + +- WARN_ON(cpu != data); +- + iv = __this_cpu_read(mce_next_interval); + + if (mce_available(this_cpu_ptr(&cpu_info))) { +@@ -1324,7 +1312,7 @@ + + done: + __this_cpu_write(mce_next_interval, iv); +- __restart_timer(t, iv); ++ return __restart_timer(timer, iv); + } + + /* +@@ -1332,7 +1320,7 @@ + */ + void mce_timer_kick(unsigned long interval) + { +- struct timer_list *t = this_cpu_ptr(&mce_timer); ++ struct hrtimer *t = this_cpu_ptr(&mce_timer); + unsigned long iv = __this_cpu_read(mce_next_interval); + + __restart_timer(t, interval); +@@ -1347,7 +1335,7 @@ + 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) +@@ -1357,6 +1345,56 @@ + + static DECLARE_WORK(mce_trigger_work, mce_do_trigger); + ++static void __mce_notify_work(struct swork_event *event) ++{ ++ /* 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 ++static bool notify_work_ready __read_mostly; ++static struct swork_event notify_work; ++ ++static int mce_notify_work_init(void) ++{ ++ int err; ++ ++ err = swork_get(); ++ if (err) ++ return err; ++ ++ INIT_SWORK(¬ify_work, __mce_notify_work); ++ notify_work_ready = true; ++ return 0; ++} ++ ++static void mce_notify_work(void) ++{ ++ if (notify_work_ready) ++ swork_queue(¬ify_work); ++} ++#else ++static void mce_notify_work(void) ++{ ++ __mce_notify_work(NULL); ++} ++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 +@@ -1364,19 +1402,8 @@ + */ + 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); +- +- if (mce_helper[0]) +- schedule_work(&mce_trigger_work); +- +- if (__ratelimit(&ratelimit)) +- pr_info(HW_ERR "Machine check events logged\n"); +- ++ mce_notify_work(); + return 1; + } + return 0; +@@ -1649,7 +1676,7 @@ + } + } + +-static void mce_start_timer(unsigned int cpu, struct timer_list *t) ++static void mce_start_timer(unsigned int cpu, struct hrtimer *t) + { + unsigned long iv = check_interval * HZ; + +@@ -1658,16 +1685,17 @@ + + per_cpu(mce_next_interval, cpu) = iv; + +- t->expires = round_jiffies(jiffies + iv); +- add_timer_on(t, cpu); ++ hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(iv) * 1000ULL), ++ 0, HRTIMER_MODE_REL_PINNED); + } + + static void __mcheck_cpu_init_timer(void) + { +- struct timer_list *t = this_cpu_ptr(&mce_timer); ++ struct hrtimer *t = this_cpu_ptr(&mce_timer); + unsigned int cpu = smp_processor_id(); + +- setup_timer(t, mce_timer_fn, cpu); ++ hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ t->function = mce_timer_fn; + mce_start_timer(cpu, t); + } + +@@ -2345,6 +2373,8 @@ + if (!mce_available(raw_cpu_ptr(&cpu_info))) + return; + ++ hrtimer_cancel(this_cpu_ptr(&mce_timer)); ++ + if (!(action & CPU_TASKS_FROZEN)) + cmci_clear(); + for (i = 0; i < mca_cfg.banks; i++) { +@@ -2371,6 +2401,7 @@ + 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. */ +@@ -2378,7 +2409,6 @@ + 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 & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: +@@ -2398,11 +2428,9 @@ + break; + case CPU_DOWN_PREPARE: + smp_call_function_single(cpu, mce_disable_cpu, &action, 1); +- del_timer_sync(t); + break; + case CPU_DOWN_FAILED: + smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); +- mce_start_timer(cpu, t); + break; + } + +@@ -2441,6 +2469,10 @@ + goto err_out; + } + ++ err = mce_notify_work_init(); ++ if (err) ++ goto err_out; ++ + if (!zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL)) { + err = -ENOMEM; + goto err_out; +diff -Nur linux-4.1.39.orig/arch/x86/kernel/cpu/perf_event_intel_rapl.c linux-4.1.39/arch/x86/kernel/cpu/perf_event_intel_rapl.c +--- linux-4.1.39.orig/arch/x86/kernel/cpu/perf_event_intel_rapl.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/cpu/perf_event_intel_rapl.c 2017-04-18 17:56:30.569395424 +0200 +@@ -119,7 +119,7 @@ + }; + + struct rapl_pmu { +- spinlock_t lock; ++ raw_spinlock_t lock; + int n_active; /* number of active events */ + struct list_head active_list; + struct pmu *pmu; /* pointer to rapl_pmu_class */ +@@ -223,13 +223,13 @@ + if (!pmu->n_active) + return HRTIMER_NORESTART; + +- spin_lock_irqsave(&pmu->lock, flags); ++ raw_spin_lock_irqsave(&pmu->lock, flags); + + list_for_each_entry(event, &pmu->active_list, active_entry) { + rapl_event_update(event); + } + +- spin_unlock_irqrestore(&pmu->lock, flags); ++ raw_spin_unlock_irqrestore(&pmu->lock, flags); + + hrtimer_forward_now(hrtimer, pmu->timer_interval); + +@@ -266,9 +266,9 @@ + struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); + unsigned long flags; + +- spin_lock_irqsave(&pmu->lock, flags); ++ raw_spin_lock_irqsave(&pmu->lock, flags); + __rapl_pmu_event_start(pmu, event); +- spin_unlock_irqrestore(&pmu->lock, flags); ++ raw_spin_unlock_irqrestore(&pmu->lock, flags); + } + + static void rapl_pmu_event_stop(struct perf_event *event, int mode) +@@ -277,7 +277,7 @@ + struct hw_perf_event *hwc = &event->hw; + unsigned long flags; + +- spin_lock_irqsave(&pmu->lock, flags); ++ raw_spin_lock_irqsave(&pmu->lock, flags); + + /* mark event as deactivated and stopped */ + if (!(hwc->state & PERF_HES_STOPPED)) { +@@ -302,7 +302,7 @@ + hwc->state |= PERF_HES_UPTODATE; + } + +- spin_unlock_irqrestore(&pmu->lock, flags); ++ raw_spin_unlock_irqrestore(&pmu->lock, flags); + } + + static int rapl_pmu_event_add(struct perf_event *event, int mode) +@@ -311,14 +311,14 @@ + struct hw_perf_event *hwc = &event->hw; + unsigned long flags; + +- spin_lock_irqsave(&pmu->lock, flags); ++ raw_spin_lock_irqsave(&pmu->lock, flags); + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + if (mode & PERF_EF_START) + __rapl_pmu_event_start(pmu, event); + +- spin_unlock_irqrestore(&pmu->lock, flags); ++ raw_spin_unlock_irqrestore(&pmu->lock, flags); + + return 0; + } +@@ -594,7 +594,7 @@ + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); + if (!pmu) + return -1; +- spin_lock_init(&pmu->lock); ++ raw_spin_lock_init(&pmu->lock); + + INIT_LIST_HEAD(&pmu->active_list); + +diff -Nur linux-4.1.39.orig/arch/x86/kernel/dumpstack_32.c linux-4.1.39/arch/x86/kernel/dumpstack_32.c +--- linux-4.1.39.orig/arch/x86/kernel/dumpstack_32.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/dumpstack_32.c 2017-04-18 17:56:30.569395424 +0200 +@@ -42,7 +42,7 @@ + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data) + { +- const unsigned cpu = get_cpu(); ++ const unsigned cpu = get_cpu_light(); + int graph = 0; + u32 *prev_esp; + +@@ -86,7 +86,7 @@ + break; + touch_nmi_watchdog(); + } +- put_cpu(); ++ put_cpu_light(); + } + EXPORT_SYMBOL(dump_trace); + +diff -Nur linux-4.1.39.orig/arch/x86/kernel/dumpstack_64.c linux-4.1.39/arch/x86/kernel/dumpstack_64.c +--- linux-4.1.39.orig/arch/x86/kernel/dumpstack_64.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/dumpstack_64.c 2017-04-18 17:56:30.569395424 +0200 +@@ -152,7 +152,7 @@ + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data) + { +- const unsigned cpu = get_cpu(); ++ const unsigned cpu = get_cpu_light(); + struct thread_info *tinfo; + unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu); + unsigned long dummy; +@@ -241,7 +241,7 @@ + * 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); + +@@ -255,7 +255,7 @@ + int cpu; + int i; + +- preempt_disable(); ++ migrate_disable(); + cpu = smp_processor_id(); + + irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu)); +@@ -291,7 +291,7 @@ + pr_cont(" %016lx", *stack++); + touch_nmi_watchdog(); + } +- preempt_enable(); ++ migrate_enable(); + + pr_cont("\n"); + show_trace_log_lvl(task, regs, sp, bp, log_lvl); +diff -Nur linux-4.1.39.orig/arch/x86/kernel/entry_32.S linux-4.1.39/arch/x86/kernel/entry_32.S +--- linux-4.1.39.orig/arch/x86/kernel/entry_32.S 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/entry_32.S 2017-04-18 17:56:30.569395424 +0200 +@@ -359,8 +359,24 @@ + ENTRY(resume_kernel) + DISABLE_INTERRUPTS(CLBR_ANY) + need_resched: ++ # preempt count == 0 + NEED_RS set? + cmpl $0,PER_CPU_VAR(__preempt_count) ++#ifndef CONFIG_PREEMPT_LAZY + jnz restore_all ++#else ++ jz test_int_off ++ ++ # atleast preempt count == 0 ? ++ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) ++ jne restore_all ++ ++ cmpl $0,TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? ++ jnz restore_all ++ ++ testl $_TIF_NEED_RESCHED_LAZY, TI_flags(%ebp) ++ jz restore_all ++test_int_off: ++#endif + testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? + jz restore_all + call preempt_schedule_irq +@@ -594,7 +610,7 @@ + ALIGN + RING0_PTREGS_FRAME # can't unwind into user space anyway + work_pending: +- testb $_TIF_NEED_RESCHED, %cl ++ testl $_TIF_NEED_RESCHED_MASK, %ecx + jz work_notifysig + work_resched: + call schedule +@@ -607,7 +623,7 @@ + andl $_TIF_WORK_MASK, %ecx # is there any work to be done other + # than syscall tracing? + jz restore_all +- testb $_TIF_NEED_RESCHED, %cl ++ testl $_TIF_NEED_RESCHED_MASK, %ecx + jnz work_resched + + work_notifysig: # deal with pending signals and +diff -Nur linux-4.1.39.orig/arch/x86/kernel/entry_64.S linux-4.1.39/arch/x86/kernel/entry_64.S +--- linux-4.1.39.orig/arch/x86/kernel/entry_64.S 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/entry_64.S 2017-04-18 17:56:30.569395424 +0200 +@@ -370,8 +370,8 @@ + /* First do a reschedule test. */ + /* edx: work, edi: workmask */ + int_careful: +- bt $TIF_NEED_RESCHED,%edx +- jnc int_very_careful ++ testl $_TIF_NEED_RESCHED_MASK,%edx ++ jz int_very_careful + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + pushq_cfi %rdi +@@ -776,7 +776,23 @@ + bt $9,EFLAGS(%rsp) /* interrupts were off? */ + jnc 1f + 0: cmpl $0,PER_CPU_VAR(__preempt_count) ++#ifndef CONFIG_PREEMPT_LAZY + jnz 1f ++#else ++ jz do_preempt_schedule_irq ++ ++ # atleast preempt count == 0 ? ++ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) ++ jnz 1f ++ ++ GET_THREAD_INFO(%rcx) ++ cmpl $0, TI_preempt_lazy_count(%rcx) ++ jnz 1f ++ ++ bt $TIF_NEED_RESCHED_LAZY,TI_flags(%rcx) ++ jnc 1f ++do_preempt_schedule_irq: ++#endif + call preempt_schedule_irq + jmp 0b + 1: +@@ -844,8 +860,8 @@ + /* edi: workmask, edx: work */ + retint_careful: + CFI_RESTORE_STATE +- bt $TIF_NEED_RESCHED,%edx +- jnc retint_signal ++ testl $_TIF_NEED_RESCHED_MASK,%edx ++ jz retint_signal + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + pushq_cfi %rdi +@@ -1118,6 +1134,7 @@ + jmp 2b + .previous + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* Call softirq on interrupt stack. Interrupts are off. */ + ENTRY(do_softirq_own_stack) + CFI_STARTPROC +@@ -1137,6 +1154,7 @@ + ret + CFI_ENDPROC + END(do_softirq_own_stack) ++#endif + + #ifdef CONFIG_XEN + idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 +diff -Nur linux-4.1.39.orig/arch/x86/kernel/irq_32.c linux-4.1.39/arch/x86/kernel/irq_32.c +--- linux-4.1.39.orig/arch/x86/kernel/irq_32.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/irq_32.c 2017-04-18 17:56:30.569395424 +0200 +@@ -135,6 +135,7 @@ + cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu)); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct thread_info *curstk; +@@ -153,6 +154,7 @@ + + call_on_stack(__do_softirq, isp); + } ++#endif + + bool handle_irq(unsigned irq, struct pt_regs *regs) + { +diff -Nur linux-4.1.39.orig/arch/x86/kernel/kvm.c linux-4.1.39/arch/x86/kernel/kvm.c +--- linux-4.1.39.orig/arch/x86/kernel/kvm.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/kvm.c 2017-04-18 17:56:30.569395424 +0200 +@@ -36,6 +36,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -91,14 +92,14 @@ + + struct kvm_task_sleep_node { + struct hlist_node link; +- wait_queue_head_t wq; ++ struct swait_head wq; + u32 token; + int cpu; + bool halted; + }; + + static struct kvm_task_sleep_head { +- spinlock_t lock; ++ raw_spinlock_t lock; + struct hlist_head list; + } async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE]; + +@@ -122,17 +123,17 @@ + u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); + struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; + struct kvm_task_sleep_node n, *e; +- DEFINE_WAIT(wait); ++ DEFINE_SWAITER(wait); + + rcu_irq_enter(); + +- spin_lock(&b->lock); ++ raw_spin_lock(&b->lock); + e = _find_apf_task(b, token); + if (e) { + /* dummy entry exist -> wake up was delivered ahead of PF */ + hlist_del(&e->link); + kfree(e); +- spin_unlock(&b->lock); ++ raw_spin_unlock(&b->lock); + + rcu_irq_exit(); + return; +@@ -141,13 +142,13 @@ + n.token = token; + n.cpu = smp_processor_id(); + n.halted = is_idle_task(current) || preempt_count() > 1; +- init_waitqueue_head(&n.wq); ++ init_swait_head(&n.wq); + hlist_add_head(&n.link, &b->list); +- spin_unlock(&b->lock); ++ raw_spin_unlock(&b->lock); + + for (;;) { + if (!n.halted) +- prepare_to_wait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); ++ swait_prepare(&n.wq, &wait, TASK_UNINTERRUPTIBLE); + if (hlist_unhashed(&n.link)) + break; + +@@ -166,7 +167,7 @@ + } + } + if (!n.halted) +- finish_wait(&n.wq, &wait); ++ swait_finish(&n.wq, &wait); + + rcu_irq_exit(); + return; +@@ -178,8 +179,8 @@ + hlist_del_init(&n->link); + if (n->halted) + smp_send_reschedule(n->cpu); +- else if (waitqueue_active(&n->wq)) +- wake_up(&n->wq); ++ else if (swaitqueue_active(&n->wq)) ++ swait_wake(&n->wq); + } + + static void apf_task_wake_all(void) +@@ -189,14 +190,14 @@ + for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) { + struct hlist_node *p, *next; + struct kvm_task_sleep_head *b = &async_pf_sleepers[i]; +- spin_lock(&b->lock); ++ raw_spin_lock(&b->lock); + hlist_for_each_safe(p, next, &b->list) { + struct kvm_task_sleep_node *n = + hlist_entry(p, typeof(*n), link); + if (n->cpu == smp_processor_id()) + apf_task_wake_one(n); + } +- spin_unlock(&b->lock); ++ raw_spin_unlock(&b->lock); + } + } + +@@ -212,7 +213,7 @@ + } + + again: +- spin_lock(&b->lock); ++ raw_spin_lock(&b->lock); + n = _find_apf_task(b, token); + if (!n) { + /* +@@ -225,17 +226,17 @@ + * Allocation failed! Busy wait while other cpu + * handles async PF. + */ +- spin_unlock(&b->lock); ++ raw_spin_unlock(&b->lock); + cpu_relax(); + goto again; + } + n->token = token; + n->cpu = smp_processor_id(); +- init_waitqueue_head(&n->wq); ++ init_swait_head(&n->wq); + hlist_add_head(&n->link, &b->list); + } else + apf_task_wake_one(n); +- spin_unlock(&b->lock); ++ raw_spin_unlock(&b->lock); + return; + } + EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake); +@@ -486,7 +487,7 @@ + paravirt_ops_setup(); + register_reboot_notifier(&kvm_pv_reboot_nb); + for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) +- spin_lock_init(&async_pf_sleepers[i].lock); ++ raw_spin_lock_init(&async_pf_sleepers[i].lock); + if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF)) + x86_init.irqs.trap_init = kvm_apf_trap_init; + +diff -Nur linux-4.1.39.orig/arch/x86/kernel/process_32.c linux-4.1.39/arch/x86/kernel/process_32.c +--- linux-4.1.39.orig/arch/x86/kernel/process_32.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/process_32.c 2017-04-18 17:56:30.569395424 +0200 +@@ -35,6 +35,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -210,6 +211,35 @@ + } + EXPORT_SYMBOL_GPL(start_thread); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) ++{ ++ int i; ++ ++ /* ++ * Clear @prev's kmap_atomic mappings ++ */ ++ for (i = 0; i < prev_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ pte_t *ptep = kmap_pte - idx; ++ ++ kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx)); ++ } ++ /* ++ * Restore @next_p's kmap_atomic mappings ++ */ ++ for (i = 0; i < next_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ ++ if (!pte_none(next_p->kmap_pte[i])) ++ set_pte(kmap_pte - idx, next_p->kmap_pte[i]); ++ } ++} ++#else ++static inline void ++switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } ++#endif ++ + + /* + * switch_to(x,y) should switch tasks from x to y. +@@ -292,6 +322,8 @@ + task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) + __switch_to_xtra(prev_p, next_p, tss); + ++ switch_kmaps(prev_p, next_p); ++ + /* + * Leave lazy mode, flushing any hypercalls made here. + * This must be done before restoring TLS segments so +diff -Nur linux-4.1.39.orig/arch/x86/kernel/signal.c linux-4.1.39/arch/x86/kernel/signal.c +--- linux-4.1.39.orig/arch/x86/kernel/signal.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kernel/signal.c 2017-04-18 17:56:30.569395424 +0200 +@@ -726,6 +726,14 @@ + { + user_exit(); + ++#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 ++ + if (thread_info_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + +diff -Nur linux-4.1.39.orig/arch/x86/kvm/lapic.c linux-4.1.39/arch/x86/kvm/lapic.c +--- linux-4.1.39.orig/arch/x86/kvm/lapic.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kvm/lapic.c 2017-04-18 17:56:30.569395424 +0200 +@@ -1106,7 +1106,7 @@ + static void apic_timer_expired(struct kvm_lapic *apic) + { + struct kvm_vcpu *vcpu = apic->vcpu; +- wait_queue_head_t *q = &vcpu->wq; ++ struct swait_head *q = &vcpu->wq; + struct kvm_timer *ktimer = &apic->lapic_timer; + + if (atomic_read(&apic->lapic_timer.pending)) +@@ -1115,8 +1115,8 @@ + atomic_inc(&apic->lapic_timer.pending); + kvm_set_pending_timer(vcpu); + +- if (waitqueue_active(q)) +- wake_up_interruptible(q); ++ if (swaitqueue_active(q)) ++ swait_wake_interruptible(q); + + if (apic_lvtt_tscdeadline(apic)) + ktimer->expired_tscdeadline = ktimer->tscdeadline; +@@ -1169,8 +1169,36 @@ + __delay(tsc_deadline - guest_tsc); + } + ++static enum hrtimer_restart apic_timer_fn(struct hrtimer *data); ++ ++static void __apic_timer_expired(struct hrtimer *data) ++{ ++ int ret, i = 0; ++ enum hrtimer_restart r; ++ struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); ++ ++ r = apic_timer_fn(data); ++ ++ if (r == HRTIMER_RESTART) { ++ do { ++ ret = hrtimer_start_expires(data, HRTIMER_MODE_ABS); ++ if (ret == -ETIME) ++ hrtimer_add_expires_ns(&ktimer->timer, ++ ktimer->period); ++ i++; ++ } while (ret == -ETIME && i < 10); ++ ++ if (ret == -ETIME) { ++ printk_once(KERN_ERR "%s: failed to reprogram timer\n", ++ __func__); ++ WARN_ON_ONCE(1); ++ } ++ } ++} ++ + static void start_apic_timer(struct kvm_lapic *apic) + { ++ int ret; + ktime_t now; + + atomic_set(&apic->lapic_timer.pending, 0); +@@ -1201,9 +1229,11 @@ + } + } + +- hrtimer_start(&apic->lapic_timer.timer, ++ ret = hrtimer_start(&apic->lapic_timer.timer, + ktime_add_ns(now, apic->lapic_timer.period), + HRTIMER_MODE_ABS); ++ if (ret == -ETIME) ++ __apic_timer_expired(&apic->lapic_timer.timer); + + apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" + PRIx64 ", " +@@ -1235,8 +1265,10 @@ + do_div(ns, this_tsc_khz); + expire = ktime_add_ns(now, ns); + expire = ktime_sub_ns(expire, lapic_timer_advance_ns); +- hrtimer_start(&apic->lapic_timer.timer, ++ ret = hrtimer_start(&apic->lapic_timer.timer, + expire, HRTIMER_MODE_ABS); ++ if (ret == -ETIME) ++ __apic_timer_expired(&apic->lapic_timer.timer); + } else + apic_timer_expired(apic); + +@@ -1709,6 +1741,7 @@ + hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS); + apic->lapic_timer.timer.function = apic_timer_fn; ++ apic->lapic_timer.timer.irqsafe = 1; + + /* + * APIC is created enabled. This will prevent kvm_lapic_set_base from +@@ -1836,7 +1869,8 @@ + + timer = &vcpu->arch.apic->lapic_timer.timer; + if (hrtimer_cancel(timer)) +- hrtimer_start_expires(timer, HRTIMER_MODE_ABS); ++ if (hrtimer_start_expires(timer, HRTIMER_MODE_ABS) == -ETIME) ++ __apic_timer_expired(timer); + } + + /* +diff -Nur linux-4.1.39.orig/arch/x86/kvm/x86.c linux-4.1.39/arch/x86/kvm/x86.c +--- linux-4.1.39.orig/arch/x86/kvm/x86.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/kvm/x86.c 2017-04-18 17:56:30.569395424 +0200 +@@ -5837,6 +5837,13 @@ + 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_free_percpu; +diff -Nur linux-4.1.39.orig/arch/x86/lib/usercopy_32.c linux-4.1.39/arch/x86/lib/usercopy_32.c +--- linux-4.1.39.orig/arch/x86/lib/usercopy_32.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/lib/usercopy_32.c 2017-04-18 17:56:30.573395579 +0200 +@@ -647,7 +647,8 @@ + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. + * +@@ -668,7 +669,8 @@ + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. + * +diff -Nur linux-4.1.39.orig/arch/x86/mm/fault.c linux-4.1.39/arch/x86/mm/fault.c +--- linux-4.1.39.orig/arch/x86/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/mm/fault.c 2017-04-18 17:56:30.573395579 +0200 +@@ -13,6 +13,7 @@ + #include /* hstate_index_to_shift */ + #include /* prefetchw */ + #include /* exception_enter(), ... */ ++#include /* faulthandler_disabled() */ + + #include /* dotraplinkage, ... */ + #include /* pgd_*(), ... */ +@@ -1133,9 +1134,9 @@ + + /* + * If we're in an interrupt, have no user context or are running +- * in an atomic region then we must not take the fault: ++ * in a region with pagefaults disabled then we must not take the fault + */ +- if (unlikely(in_atomic() || !mm)) { ++ if (unlikely(faulthandler_disabled() || !mm)) { + bad_area_nosemaphore(regs, error_code, address); + return; + } +diff -Nur linux-4.1.39.orig/arch/x86/mm/highmem_32.c linux-4.1.39/arch/x86/mm/highmem_32.c +--- linux-4.1.39.orig/arch/x86/mm/highmem_32.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/mm/highmem_32.c 2017-04-18 17:56:30.573395579 +0200 +@@ -32,10 +32,11 @@ + */ + void *kmap_atomic_prot(struct page *page, pgprot_t prot) + { ++ pte_t pte = mk_pte(page, prot); + unsigned long vaddr; + int idx, type; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable_nort(); + pagefault_disable(); + + if (!PageHighMem(page)) +@@ -45,7 +46,10 @@ + idx = type + KM_TYPE_NR*smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + BUG_ON(!pte_none(*(kmap_pte-idx))); +- set_pte(kmap_pte-idx, mk_pte(page, prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_pte(kmap_pte-idx, pte); + arch_flush_lazy_mmu_mode(); + + return (void *)vaddr; +@@ -88,6 +92,9 @@ + * is a bad idea also, in case the page changes cacheability + * attributes or becomes a protected page in a hypervisor. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + kpte_clear_flush(kmap_pte-idx, vaddr); + kmap_atomic_idx_pop(); + arch_flush_lazy_mmu_mode(); +@@ -100,6 +107,7 @@ + #endif + + pagefault_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +diff -Nur linux-4.1.39.orig/arch/x86/mm/iomap_32.c linux-4.1.39/arch/x86/mm/iomap_32.c +--- linux-4.1.39.orig/arch/x86/mm/iomap_32.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/mm/iomap_32.c 2017-04-18 17:56:30.573395579 +0200 +@@ -56,15 +56,22 @@ + + void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) + { ++ pte_t pte = pfn_pte(pfn, prot); + unsigned long vaddr; + int idx, type; + ++ preempt_disable(); + pagefault_disable(); + + type = kmap_atomic_idx_push(); + idx = type + KM_TYPE_NR * smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); +- set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); ++ WARN_ON(!pte_none(*(kmap_pte - idx))); ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_pte(kmap_pte - idx, pte); + arch_flush_lazy_mmu_mode(); + + return (void *)vaddr; +@@ -112,10 +119,14 @@ + * is a bad idea also, in case the page changes cacheability + * attributes or becomes a protected page in a hypervisor. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + kpte_clear_flush(kmap_pte-idx, vaddr); + kmap_atomic_idx_pop(); + } + + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL_GPL(iounmap_atomic); +diff -Nur linux-4.1.39.orig/arch/x86/mm/pageattr.c linux-4.1.39/arch/x86/mm/pageattr.c +--- linux-4.1.39.orig/arch/x86/mm/pageattr.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/mm/pageattr.c 2017-04-18 17:56:30.573395579 +0200 +@@ -209,7 +209,15 @@ + int in_flags, struct page **pages) + { + unsigned int i, level; ++#ifdef CONFIG_PREEMPT ++ /* ++ * Avoid wbinvd() because it causes latencies on all CPUs, ++ * regardless of any CPU isolation that may be in effect. ++ */ ++ unsigned long do_wbinvd = 0; ++#else + unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */ ++#endif + + BUG_ON(irqs_disabled()); + +diff -Nur linux-4.1.39.orig/arch/x86/platform/uv/tlb_uv.c linux-4.1.39/arch/x86/platform/uv/tlb_uv.c +--- linux-4.1.39.orig/arch/x86/platform/uv/tlb_uv.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/platform/uv/tlb_uv.c 2017-04-18 17:56:30.573395579 +0200 +@@ -714,9 +714,9 @@ + + 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); + +@@ -736,9 +736,9 @@ + + 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); + +@@ -759,7 +759,7 @@ + cycles_t tm1; + + hmaster = bcp->uvhub_master; +- spin_lock(&hmaster->disable_lock); ++ raw_spin_lock(&hmaster->disable_lock); + if (!bcp->baudisabled) { + stat->s_bau_disabled++; + tm1 = get_cycles(); +@@ -772,7 +772,7 @@ + } + } + } +- spin_unlock(&hmaster->disable_lock); ++ raw_spin_unlock(&hmaster->disable_lock); + } + + static void count_max_concurr(int stat, struct bau_control *bcp, +@@ -835,7 +835,7 @@ + */ + 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; +@@ -968,7 +968,7 @@ + struct bau_control *hmaster; + + hmaster = bcp->uvhub_master; +- spin_lock(&hmaster->disable_lock); ++ raw_spin_lock(&hmaster->disable_lock); + if (bcp->baudisabled && (get_cycles() >= bcp->set_bau_on_time)) { + stat->s_bau_reenabled++; + for_each_present_cpu(tcpu) { +@@ -980,10 +980,10 @@ + tbcp->period_giveups = 0; + } + } +- spin_unlock(&hmaster->disable_lock); ++ raw_spin_unlock(&hmaster->disable_lock); + return 0; + } +- spin_unlock(&hmaster->disable_lock); ++ raw_spin_unlock(&hmaster->disable_lock); + return -1; + } + +@@ -1901,9 +1901,9 @@ + bcp->cong_reps = congested_reps; + bcp->disabled_period = sec_2_cycles(disabled_period); + bcp->giveup_limit = giveup_limit; +- spin_lock_init(&bcp->queue_lock); +- spin_lock_init(&bcp->uvhub_lock); +- spin_lock_init(&bcp->disable_lock); ++ raw_spin_lock_init(&bcp->queue_lock); ++ raw_spin_lock_init(&bcp->uvhub_lock); ++ raw_spin_lock_init(&bcp->disable_lock); + } + } + +diff -Nur linux-4.1.39.orig/arch/x86/platform/uv/uv_time.c linux-4.1.39/arch/x86/platform/uv/uv_time.c +--- linux-4.1.39.orig/arch/x86/platform/uv/uv_time.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/x86/platform/uv/uv_time.c 2017-04-18 17:56:30.573395579 +0200 +@@ -58,7 +58,7 @@ + + /* 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 @@ + 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 @@ + 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 @@ + 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 @@ + 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 @@ + 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 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 -Nur linux-4.1.39.orig/arch/xtensa/mm/fault.c linux-4.1.39/arch/xtensa/mm/fault.c +--- linux-4.1.39.orig/arch/xtensa/mm/fault.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/xtensa/mm/fault.c 2017-04-18 17:56:30.573395579 +0200 +@@ -15,10 +15,10 @@ + #include + #include + #include ++#include + #include + #include + #include +-#include + #include + + DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST; +@@ -57,7 +57,7 @@ + /* If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) { ++ if (faulthandler_disabled() || !mm) { + bad_page_fault(regs, address, SIGSEGV); + return; + } +diff -Nur linux-4.1.39.orig/arch/xtensa/mm/highmem.c linux-4.1.39/arch/xtensa/mm/highmem.c +--- linux-4.1.39.orig/arch/xtensa/mm/highmem.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/arch/xtensa/mm/highmem.c 2017-04-18 17:56:30.573395579 +0200 +@@ -42,6 +42,7 @@ + enum fixed_addresses idx; + unsigned long vaddr; + ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -79,6 +80,7 @@ + } + + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +diff -Nur linux-4.1.39.orig/block/blk-core.c linux-4.1.39/block/blk-core.c +--- linux-4.1.39.orig/block/blk-core.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/block/blk-core.c 2017-04-18 17:56:30.573395579 +0200 +@@ -100,6 +100,9 @@ + + INIT_LIST_HEAD(&rq->queuelist); + INIT_LIST_HEAD(&rq->timeout_list); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); ++#endif + rq->cpu = -1; + rq->q = q; + rq->__sector = (sector_t) -1; +@@ -194,7 +197,7 @@ + **/ + 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); +@@ -663,7 +666,7 @@ + q->bypass_depth = 1; + __set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags); + +- init_waitqueue_head(&q->mq_freeze_wq); ++ init_swait_head(&q->mq_freeze_wq); + + if (blkcg_init_queue(q)) + goto fail_bdi; +@@ -3079,7 +3082,7 @@ + blk_run_queue_async(q); + else + __blk_run_queue(q); +- spin_unlock(q->queue_lock); ++ spin_unlock_irq(q->queue_lock); + } + + static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) +@@ -3127,7 +3130,6 @@ + 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; +@@ -3147,11 +3149,6 @@ + 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); +@@ -3164,7 +3161,7 @@ + queue_unplugged(q, depth, from_schedule); + q = rq->q; + depth = 0; +- spin_lock(q->queue_lock); ++ spin_lock_irq(q->queue_lock); + } + + /* +@@ -3191,8 +3188,6 @@ + */ + if (q) + queue_unplugged(q, depth, from_schedule); +- +- local_irq_restore(flags); + } + + void blk_finish_plug(struct blk_plug *plug) +diff -Nur linux-4.1.39.orig/block/blk-ioc.c linux-4.1.39/block/blk-ioc.c +--- linux-4.1.39.orig/block/blk-ioc.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/block/blk-ioc.c 2017-04-18 17:56:30.573395579 +0200 +@@ -7,6 +7,7 @@ + #include + #include + #include ++#include + + #include "blk.h" + +@@ -109,7 +110,7 @@ + spin_unlock(q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); +- cpu_relax(); ++ cpu_chill(); + spin_lock_irqsave_nested(&ioc->lock, flags, 1); + } + } +@@ -187,7 +188,7 @@ + spin_unlock(icq->q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); +- cpu_relax(); ++ cpu_chill(); + goto retry; + } + } +diff -Nur linux-4.1.39.orig/block/blk-iopoll.c linux-4.1.39/block/blk-iopoll.c +--- linux-4.1.39.orig/block/blk-iopoll.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/block/blk-iopoll.c 2017-04-18 17:56:30.573395579 +0200 +@@ -35,6 +35,7 @@ + list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll)); + __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(blk_iopoll_sched); + +@@ -132,6 +133,7 @@ + __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); + + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + /** +@@ -201,6 +203,7 @@ + this_cpu_ptr(&blk_cpu_iopoll)); + __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + return NOTIFY_OK; +diff -Nur linux-4.1.39.orig/block/blk-mq.c linux-4.1.39/block/blk-mq.c +--- linux-4.1.39.orig/block/blk-mq.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/block/blk-mq.c 2017-04-18 17:56:30.573395579 +0200 +@@ -88,7 +88,7 @@ + if (!(gfp & __GFP_WAIT)) + return -EBUSY; + +- ret = wait_event_interruptible(q->mq_freeze_wq, ++ ret = swait_event_interruptible(q->mq_freeze_wq, + !q->mq_freeze_depth || blk_queue_dying(q)); + if (blk_queue_dying(q)) + return -ENODEV; +@@ -107,7 +107,7 @@ + struct request_queue *q = + container_of(ref, struct request_queue, mq_usage_counter); + +- wake_up_all(&q->mq_freeze_wq); ++ swait_wake_all(&q->mq_freeze_wq); + } + + void blk_mq_freeze_queue_start(struct request_queue *q) +@@ -127,7 +127,7 @@ + + static void blk_mq_freeze_queue_wait(struct request_queue *q) + { +- wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter)); ++ swait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter)); + } + + /* +@@ -151,7 +151,7 @@ + spin_unlock_irq(q->queue_lock); + if (wake) { + percpu_ref_reinit(&q->mq_usage_counter); +- wake_up_all(&q->mq_freeze_wq); ++ swait_wake_all(&q->mq_freeze_wq); + } + } + EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); +@@ -170,7 +170,7 @@ + * dying, we need to ensure that processes currently waiting on + * the queue are notified as well. + */ +- wake_up_all(&q->mq_freeze_wq); ++ swait_wake_all(&q->mq_freeze_wq); + } + + bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx) +@@ -217,6 +217,9 @@ + rq->resid_len = 0; + rq->sense = NULL; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); ++#endif + INIT_LIST_HEAD(&rq->timeout_list); + rq->timeout = 0; + +@@ -346,6 +349,17 @@ + } + EXPORT_SYMBOL(blk_mq_end_request); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++void __blk_mq_complete_request_remote_work(struct work_struct *work) ++{ ++ struct request *rq = container_of(work, struct request, work); ++ ++ rq->q->softirq_done_fn(rq); ++} ++ ++#else ++ + static void __blk_mq_complete_request_remote(void *data) + { + struct request *rq = data; +@@ -353,6 +367,8 @@ + rq->q->softirq_done_fn(rq); + } + ++#endif ++ + static void blk_mq_ipi_complete_request(struct request *rq) + { + struct blk_mq_ctx *ctx = rq->mq_ctx; +@@ -364,19 +380,23 @@ + return; + } + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags)) + shared = cpus_share_cache(cpu, ctx->cpu); + + if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ schedule_work_on(ctx->cpu, &rq->work); ++#else + rq->csd.func = __blk_mq_complete_request_remote; + rq->csd.info = rq; + rq->csd.flags = 0; + smp_call_function_single_async(ctx->cpu, &rq->csd); ++#endif + } else { + rq->q->softirq_done_fn(rq); + } +- put_cpu(); ++ put_cpu_light(); + } + + void __blk_mq_complete_request(struct request *rq) +@@ -905,14 +925,14 @@ + return; + + if (!async) { +- int cpu = get_cpu(); ++ int cpu = get_cpu_light(); + if (cpumask_test_cpu(cpu, hctx->cpumask)) { + __blk_mq_run_hw_queue(hctx); +- put_cpu(); ++ put_cpu_light(); + return; + } + +- put_cpu(); ++ put_cpu_light(); + } + + kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx), +@@ -1589,7 +1609,7 @@ + { + struct blk_mq_hw_ctx *hctx = data; + +- if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) ++ if (action == CPU_POST_DEAD) + return blk_mq_hctx_cpu_offline(hctx, cpu); + + /* +diff -Nur linux-4.1.39.orig/block/blk-mq-cpu.c linux-4.1.39/block/blk-mq-cpu.c +--- linux-4.1.39.orig/block/blk-mq-cpu.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/block/blk-mq-cpu.c 2017-04-18 17:56:30.573395579 +0200 +@@ -16,7 +16,7 @@ + #include "blk-mq.h" + + static LIST_HEAD(blk_mq_cpu_notify_list); +-static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock); ++static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock); + + static int blk_mq_main_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +@@ -25,7 +25,10 @@ + struct blk_mq_cpu_notifier *notify; + int ret = NOTIFY_OK; + +- raw_spin_lock(&blk_mq_cpu_notify_lock); ++ if (action != CPU_POST_DEAD) ++ return NOTIFY_OK; ++ ++ spin_lock(&blk_mq_cpu_notify_lock); + + list_for_each_entry(notify, &blk_mq_cpu_notify_list, list) { + ret = notify->notify(notify->data, action, cpu); +@@ -33,7 +36,7 @@ + break; + } + +- raw_spin_unlock(&blk_mq_cpu_notify_lock); ++ spin_unlock(&blk_mq_cpu_notify_lock); + return ret; + } + +@@ -41,16 +44,16 @@ + { + BUG_ON(!notifier->notify); + +- raw_spin_lock(&blk_mq_cpu_notify_lock); ++ spin_lock(&blk_mq_cpu_notify_lock); + list_add_tail(¬ifier->list, &blk_mq_cpu_notify_list); +- raw_spin_unlock(&blk_mq_cpu_notify_lock); ++ spin_unlock(&blk_mq_cpu_notify_lock); + } + + void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier) + { +- raw_spin_lock(&blk_mq_cpu_notify_lock); ++ spin_lock(&blk_mq_cpu_notify_lock); + list_del(¬ifier->list); +- raw_spin_unlock(&blk_mq_cpu_notify_lock); ++ spin_unlock(&blk_mq_cpu_notify_lock); + } + + void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier, +diff -Nur linux-4.1.39.orig/block/blk-mq.h linux-4.1.39/block/blk-mq.h +--- linux-4.1.39.orig/block/blk-mq.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/block/blk-mq.h 2017-04-18 17:56:30.573395579 +0200 +@@ -76,7 +76,10 @@ + static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, + unsigned int cpu) + { +- return per_cpu_ptr(q->queue_ctx, cpu); ++ struct blk_mq_ctx *ctx; ++ ++ ctx = per_cpu_ptr(q->queue_ctx, cpu); ++ return ctx; + } + + /* +@@ -87,12 +90,12 @@ + */ + static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q) + { +- return __blk_mq_get_ctx(q, get_cpu()); ++ return __blk_mq_get_ctx(q, get_cpu_light()); + } + + static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx) + { +- put_cpu(); ++ put_cpu_light(); + } + + struct blk_mq_alloc_data { +diff -Nur linux-4.1.39.orig/block/blk-softirq.c linux-4.1.39/block/blk-softirq.c +--- linux-4.1.39.orig/block/blk-softirq.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/block/blk-softirq.c 2017-04-18 17:56:30.573395579 +0200 +@@ -51,6 +51,7 @@ + raise_softirq_irqoff(BLOCK_SOFTIRQ); + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + /* +@@ -93,6 +94,7 @@ + this_cpu_ptr(&blk_cpu_done)); + raise_softirq_irqoff(BLOCK_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + return NOTIFY_OK; +@@ -150,6 +152,7 @@ + goto do_local; + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + /** +diff -Nur linux-4.1.39.orig/block/bounce.c linux-4.1.39/block/bounce.c +--- linux-4.1.39.orig/block/bounce.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/block/bounce.c 2017-04-18 17:56:30.573395579 +0200 +@@ -54,11 +54,11 @@ + unsigned long flags; + unsigned char *vto; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + vto = kmap_atomic(to->bv_page); + memcpy(vto + to->bv_offset, vfrom, to->bv_len); + kunmap_atomic(vto); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + + #else /* CONFIG_HIGHMEM */ +diff -Nur linux-4.1.39.orig/crypto/algapi.c linux-4.1.39/crypto/algapi.c +--- linux-4.1.39.orig/crypto/algapi.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/crypto/algapi.c 2017-04-18 17:56:30.573395579 +0200 +@@ -696,13 +696,13 @@ + + int crypto_register_notifier(struct notifier_block *nb) + { +- return blocking_notifier_chain_register(&crypto_chain, nb); ++ return srcu_notifier_chain_register(&crypto_chain, nb); + } + EXPORT_SYMBOL_GPL(crypto_register_notifier); + + int crypto_unregister_notifier(struct notifier_block *nb) + { +- return blocking_notifier_chain_unregister(&crypto_chain, nb); ++ return srcu_notifier_chain_unregister(&crypto_chain, nb); + } + EXPORT_SYMBOL_GPL(crypto_unregister_notifier); + +diff -Nur linux-4.1.39.orig/crypto/api.c linux-4.1.39/crypto/api.c +--- linux-4.1.39.orig/crypto/api.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/crypto/api.c 2017-04-18 17:56:30.573395579 +0200 +@@ -31,7 +31,7 @@ + DECLARE_RWSEM(crypto_alg_sem); + EXPORT_SYMBOL_GPL(crypto_alg_sem); + +-BLOCKING_NOTIFIER_HEAD(crypto_chain); ++SRCU_NOTIFIER_HEAD(crypto_chain); + EXPORT_SYMBOL_GPL(crypto_chain); + + static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg); +@@ -236,10 +236,10 @@ + { + int ok; + +- ok = blocking_notifier_call_chain(&crypto_chain, val, v); ++ ok = srcu_notifier_call_chain(&crypto_chain, val, v); + if (ok == NOTIFY_DONE) { + request_module("cryptomgr"); +- ok = blocking_notifier_call_chain(&crypto_chain, val, v); ++ ok = srcu_notifier_call_chain(&crypto_chain, val, v); + } + + return ok; +diff -Nur linux-4.1.39.orig/crypto/internal.h linux-4.1.39/crypto/internal.h +--- linux-4.1.39.orig/crypto/internal.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/crypto/internal.h 2017-04-18 17:56:30.573395579 +0200 +@@ -48,7 +48,7 @@ + + extern struct list_head crypto_alg_list; + extern struct rw_semaphore crypto_alg_sem; +-extern struct blocking_notifier_head crypto_chain; ++extern struct srcu_notifier_head crypto_chain; + + #ifdef CONFIG_PROC_FS + void __init crypto_init_proc(void); +@@ -142,7 +142,7 @@ + + static inline void crypto_notify(unsigned long val, void *v) + { +- blocking_notifier_call_chain(&crypto_chain, val, v); ++ srcu_notifier_call_chain(&crypto_chain, val, v); + } + + #endif /* _CRYPTO_INTERNAL_H */ +diff -Nur linux-4.1.39.orig/Documentation/hwlat_detector.txt linux-4.1.39/Documentation/hwlat_detector.txt +--- linux-4.1.39.orig/Documentation/hwlat_detector.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/Documentation/hwlat_detector.txt 2017-04-18 17:56:30.545394493 +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 -Nur linux-4.1.39.orig/Documentation/sysrq.txt linux-4.1.39/Documentation/sysrq.txt +--- linux-4.1.39.orig/Documentation/sysrq.txt 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/Documentation/sysrq.txt 2017-04-18 17:56:30.545394493 +0200 +@@ -59,10 +59,17 @@ + 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 -Nur linux-4.1.39.orig/Documentation/trace/histograms.txt linux-4.1.39/Documentation/trace/histograms.txt +--- linux-4.1.39.orig/Documentation/trace/histograms.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/Documentation/trace/histograms.txt 2017-04-18 17:56:30.545394493 +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 -Nur linux-4.1.39.orig/drivers/acpi/acpica/acglobal.h linux-4.1.39/drivers/acpi/acpica/acglobal.h +--- linux-4.1.39.orig/drivers/acpi/acpica/acglobal.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/acpi/acpica/acglobal.h 2017-04-18 17:56:30.573395579 +0200 +@@ -112,7 +112,7 @@ + * interrupt level + */ + ACPI_GLOBAL(acpi_spinlock, acpi_gbl_gpe_lock); /* For GPE data structs and registers */ +-ACPI_GLOBAL(acpi_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */ ++ACPI_GLOBAL(acpi_raw_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */ + ACPI_GLOBAL(acpi_spinlock, acpi_gbl_reference_count_lock); + + /* Mutex for _OSI support */ +diff -Nur linux-4.1.39.orig/drivers/acpi/acpica/hwregs.c linux-4.1.39/drivers/acpi/acpica/hwregs.c +--- linux-4.1.39.orig/drivers/acpi/acpica/hwregs.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/acpi/acpica/hwregs.c 2017-04-18 17:56:30.573395579 +0200 +@@ -269,14 +269,14 @@ + 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 -Nur linux-4.1.39.orig/drivers/acpi/acpica/hwxface.c linux-4.1.39/drivers/acpi/acpica/hwxface.c +--- linux-4.1.39.orig/drivers/acpi/acpica/hwxface.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/acpi/acpica/hwxface.c 2017-04-18 17:56:30.577395735 +0200 +@@ -374,7 +374,7 @@ + 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 +@@ -435,7 +435,7 @@ + + 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 -Nur linux-4.1.39.orig/drivers/acpi/acpica/utmutex.c linux-4.1.39/drivers/acpi/acpica/utmutex.c +--- linux-4.1.39.orig/drivers/acpi/acpica/utmutex.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/acpi/acpica/utmutex.c 2017-04-18 17:56:30.577395735 +0200 +@@ -88,7 +88,7 @@ + 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); + } +@@ -141,7 +141,7 @@ + /* 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); + acpi_os_delete_lock(acpi_gbl_reference_count_lock); + + /* Delete the reader/writer lock */ +diff -Nur linux-4.1.39.orig/drivers/ata/libata-sff.c linux-4.1.39/drivers/ata/libata-sff.c +--- linux-4.1.39.orig/drivers/ata/libata-sff.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/ata/libata-sff.c 2017-04-18 17:56:30.577395735 +0200 +@@ -678,9 +678,9 @@ + 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 @@ + 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 @@ + 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 @@ + 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 @@ + 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 -Nur linux-4.1.39.orig/drivers/block/zram/zram_drv.c linux-4.1.39/drivers/block/zram/zram_drv.c +--- linux-4.1.39.orig/drivers/block/zram/zram_drv.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/block/zram/zram_drv.c 2017-04-18 17:56:30.577395735 +0200 +@@ -386,6 +386,8 @@ + goto out_error; + } + ++ zram_meta_init_table_locks(meta, disksize); ++ + return meta; + + out_error: +@@ -484,12 +486,12 @@ + unsigned long handle; + size_t size; + +- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_lock_table(&meta->table[index]); + handle = meta->table[index].handle; + size = zram_get_obj_size(meta, index); + + if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) { +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + clear_page(mem); + return 0; + } +@@ -500,7 +502,7 @@ + else + ret = zcomp_decompress(zram->comp, cmem, size, mem); + zs_unmap_object(meta->mem_pool, handle); +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + + /* Should NEVER happen. Return bio error if it does. */ + if (unlikely(ret)) { +@@ -520,14 +522,14 @@ + struct zram_meta *meta = zram->meta; + page = bvec->bv_page; + +- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_lock_table(&meta->table[index]); + if (unlikely(!meta->table[index].handle) || + zram_test_flag(meta, index, ZRAM_ZERO)) { +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + handle_zero_page(bvec); + return 0; + } +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + + if (is_partial_io(bvec)) + /* Use a temporary buffer to decompress the page */ +@@ -622,10 +624,10 @@ + if (user_mem) + kunmap_atomic(user_mem); + /* Free memory associated with this sector now. */ +- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_lock_table(&meta->table[index]); + zram_free_page(zram, index); + zram_set_flag(meta, index, ZRAM_ZERO); +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + + atomic64_inc(&zram->stats.zero_pages); + ret = 0; +@@ -685,12 +687,12 @@ + * Free memory associated with this sector + * before overwriting unused sectors. + */ +- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_lock_table(&meta->table[index]); + zram_free_page(zram, index); + + meta->table[index].handle = handle; + zram_set_obj_size(meta, index, clen); +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + + /* Update stats */ + atomic64_add(clen, &zram->stats.compr_data_size); +@@ -762,9 +764,9 @@ + } + + while (n >= PAGE_SIZE) { +- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_lock_table(&meta->table[index]); + zram_free_page(zram, index); +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + atomic64_inc(&zram->stats.notify_free); + index++; + n -= PAGE_SIZE; +@@ -1007,9 +1009,9 @@ + zram = bdev->bd_disk->private_data; + meta = zram->meta; + +- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_lock_table(&meta->table[index]); + zram_free_page(zram, index); +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + atomic64_inc(&zram->stats.notify_free); + } + +diff -Nur linux-4.1.39.orig/drivers/block/zram/zram_drv.h linux-4.1.39/drivers/block/zram/zram_drv.h +--- linux-4.1.39.orig/drivers/block/zram/zram_drv.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/block/zram/zram_drv.h 2017-04-18 17:56:30.577395735 +0200 +@@ -78,6 +78,9 @@ + struct zram_table_entry { + unsigned long handle; + unsigned long value; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spinlock_t lock; ++#endif + }; + + struct zram_stats { +@@ -122,4 +125,42 @@ + u64 disksize; /* bytes */ + char compressor[10]; + }; ++ ++#ifndef CONFIG_PREEMPT_RT_BASE ++static inline void zram_lock_table(struct zram_table_entry *table) ++{ ++ bit_spin_lock(ZRAM_ACCESS, &table->value); ++} ++ ++static inline void zram_unlock_table(struct zram_table_entry *table) ++{ ++ bit_spin_unlock(ZRAM_ACCESS, &table->value); ++} ++ ++static inline void zram_meta_init_table_locks(struct zram_meta *meta, u64 disksize) { } ++#else /* CONFIG_PREEMPT_RT_BASE */ ++static inline void zram_lock_table(struct zram_table_entry *table) ++{ ++ spin_lock(&table->lock); ++ __set_bit(ZRAM_ACCESS, &table->value); ++} ++ ++static inline void zram_unlock_table(struct zram_table_entry *table) ++{ ++ __clear_bit(ZRAM_ACCESS, &table->value); ++ spin_unlock(&table->lock); ++} ++ ++static inline void zram_meta_init_table_locks(struct zram_meta *meta, u64 disksize) ++{ ++ size_t num_pages = disksize >> PAGE_SHIFT; ++ size_t index; ++ ++ for (index = 0; index < num_pages; index++) { ++ spinlock_t *lock = &meta->table[index].lock; ++ spin_lock_init(lock); ++ } ++} ++#endif /* CONFIG_PREEMPT_RT_BASE */ ++ + #endif +diff -Nur linux-4.1.39.orig/drivers/char/random.c linux-4.1.39/drivers/char/random.c +--- linux-4.1.39.orig/drivers/char/random.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/char/random.c 2017-04-18 17:56:30.577395735 +0200 +@@ -776,8 +776,6 @@ + } sample; + long delta, delta2, delta3; + +- preempt_disable(); +- + sample.jiffies = jiffies; + sample.cycles = random_get_entropy(); + sample.num = num; +@@ -818,7 +816,6 @@ + */ + credit_entropy_bits(r, min_t(int, fls(delta>>1), 11)); + } +- preempt_enable(); + } + + void add_input_randomness(unsigned int type, unsigned int code, +@@ -871,28 +868,27 @@ + return *(ptr + f->reg_idx++); + } + +-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 = this_cpu_ptr(&irq_randomness); +- struct pt_regs *regs = get_irq_regs(); + unsigned long now = jiffies; + cycles_t cycles = random_get_entropy(); + __u32 c_high, j_high; +- __u64 ip; + unsigned long seed; + int credit = 0; + + if (cycles == 0) +- cycles = get_reg(fast_pool, regs); ++ cycles = get_reg(fast_pool, NULL); + c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0; + j_high = (sizeof(now) > 4) ? now >> 32 : 0; + fast_pool->pool[0] ^= cycles ^ j_high ^ irq; + fast_pool->pool[1] ^= now ^ c_high; +- ip = regs ? instruction_pointer(regs) : _RET_IP_; ++ if (!ip) ++ ip = _RET_IP_; + fast_pool->pool[2] ^= ip; + fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 : +- get_reg(fast_pool, regs); ++ get_reg(fast_pool, NULL); + + fast_mix(fast_pool); + add_interrupt_bench(cycles); +diff -Nur linux-4.1.39.orig/drivers/clk/at91/pmc.c linux-4.1.39/drivers/clk/at91/pmc.c +--- linux-4.1.39.orig/drivers/clk/at91/pmc.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/clk/at91/pmc.c 2017-04-18 17:56:30.577395735 +0200 +@@ -27,21 +27,6 @@ + void __iomem *at91_pmc_base; + EXPORT_SYMBOL_GPL(at91_pmc_base); + +-void at91rm9200_idle(void) +-{ +- /* +- * Disable the processor clock. The processor will be automatically +- * re-enabled by an interrupt or by a reset. +- */ +- at91_pmc_write(AT91_PMC_SCDR, AT91_PMC_PCK); +-} +- +-void at91sam9_idle(void) +-{ +- at91_pmc_write(AT91_PMC_SCDR, AT91_PMC_PCK); +- cpu_do_idle(); +-} +- + int of_at91_get_clk_range(struct device_node *np, const char *propname, + struct clk_range *range) + { +diff -Nur linux-4.1.39.orig/drivers/clocksource/tcb_clksrc.c linux-4.1.39/drivers/clocksource/tcb_clksrc.c +--- linux-4.1.39.orig/drivers/clocksource/tcb_clksrc.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/clocksource/tcb_clksrc.c 2017-04-18 17:56:30.577395735 +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 @@ + struct tc_clkevt_device { + struct clock_event_device clkevt; + struct clk *clk; ++ u32 freq; + void __iomem *regs; + }; + +@@ -82,13 +82,6 @@ + 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 @@ + 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 @@ + 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)); +@@ -157,8 +151,12 @@ + .name = "tc_clkevt", + .features = CLOCK_EVT_FEAT_PERIODIC + | CLOCK_EVT_FEAT_ONESHOT, ++#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, + }, +@@ -178,8 +176,9 @@ + return IRQ_NONE; + } + +-static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) ++static int __init setup_clkevents(struct atmel_tc *tc, int divisor_idx) + { ++ unsigned divisor = atmel_tc_divisors[divisor_idx]; + int ret; + struct clk *t2_clk = tc->clk[2]; + int irq = tc->irq[2]; +@@ -193,7 +192,11 @@ + clkevt.regs = tc->regs; + clkevt.clk = t2_clk; + +- timer_clock = clk32k_divisor_idx; ++ timer_clock = divisor_idx; ++ if (!divisor) ++ clkevt.freq = 32768; ++ else ++ clkevt.freq = clk_get_rate(t2_clk) / divisor; + + clkevt.clkevt.cpumask = cpumask_of(0); + +@@ -203,7 +206,7 @@ + return ret; + } + +- clockevents_config_and_register(&clkevt.clkevt, 32768, 1, 0xffff); ++ clockevents_config_and_register(&clkevt.clkevt, clkevt.freq, 1, 0xffff); + + return ret; + } +@@ -340,7 +343,11 @@ + goto err_disable_t1; + + /* channel 2: periodic and oneshot timer support */ ++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + ret = setup_clkevents(tc, clk32k_divisor_idx); ++#else ++ ret = setup_clkevents(tc, best_divisor_idx); ++#endif + if (ret) + goto err_unregister_clksrc; + +diff -Nur linux-4.1.39.orig/drivers/clocksource/timer-atmel-pit.c linux-4.1.39/drivers/clocksource/timer-atmel-pit.c +--- linux-4.1.39.orig/drivers/clocksource/timer-atmel-pit.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/clocksource/timer-atmel-pit.c 2017-04-18 17:56:30.577395735 +0200 +@@ -90,6 +90,7 @@ + return elapsed; + } + ++static struct irqaction at91sam926x_pit_irq; + /* + * Clockevent device: interrupts every 1/HZ (== pit_cycles * MCK/16) + */ +@@ -100,6 +101,8 @@ + + switch (mode) { + case CLOCK_EVT_MODE_PERIODIC: ++ /* Set up irq handler */ ++ setup_irq(at91sam926x_pit_irq.irq, &at91sam926x_pit_irq); + /* update clocksource counter */ + data->cnt += data->cycle * PIT_PICNT(pit_read(data->base, AT91_PIT_PIVR)); + pit_write(data->base, AT91_PIT_MR, +@@ -113,6 +116,7 @@ + /* disable irq, leaving the clocksource active */ + pit_write(data->base, AT91_PIT_MR, + (data->cycle - 1) | AT91_PIT_PITEN); ++ remove_irq(at91sam926x_pit_irq.irq, &at91sam926x_pit_irq); + break; + case CLOCK_EVT_MODE_RESUME: + break; +diff -Nur linux-4.1.39.orig/drivers/clocksource/timer-atmel-st.c linux-4.1.39/drivers/clocksource/timer-atmel-st.c +--- linux-4.1.39.orig/drivers/clocksource/timer-atmel-st.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/clocksource/timer-atmel-st.c 2017-04-18 17:56:30.577395735 +0200 +@@ -131,6 +131,7 @@ + break; + case CLOCK_EVT_MODE_SHUTDOWN: + case CLOCK_EVT_MODE_UNUSED: ++ remove_irq(NR_IRQS_LEGACY + AT91_ID_SYS, &at91rm9200_timer_irq); + case CLOCK_EVT_MODE_RESUME: + irqmask = 0; + break; +diff -Nur linux-4.1.39.orig/drivers/cpufreq/cpufreq.c linux-4.1.39/drivers/cpufreq/cpufreq.c +--- linux-4.1.39.orig/drivers/cpufreq/cpufreq.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/cpufreq/cpufreq.c 2017-04-18 17:56:30.577395735 +0200 +@@ -64,12 +64,6 @@ + return cpufreq_driver->target_index || cpufreq_driver->target; + } + +-/* +- * rwsem to guarantee that cpufreq driver module doesn't unload during critical +- * sections +- */ +-static DECLARE_RWSEM(cpufreq_rwsem); +- + /* internal prototypes */ + static int __cpufreq_governor(struct cpufreq_policy *policy, + unsigned int event); +@@ -215,9 +209,6 @@ + if (cpu >= nr_cpu_ids) + return NULL; + +- if (!down_read_trylock(&cpufreq_rwsem)) +- return NULL; +- + /* get the cpufreq driver */ + read_lock_irqsave(&cpufreq_driver_lock, flags); + +@@ -230,9 +221,6 @@ + + read_unlock_irqrestore(&cpufreq_driver_lock, flags); + +- if (!policy) +- up_read(&cpufreq_rwsem); +- + return policy; + } + EXPORT_SYMBOL_GPL(cpufreq_cpu_get); +@@ -240,7 +228,6 @@ + void cpufreq_cpu_put(struct cpufreq_policy *policy) + { + kobject_put(&policy->kobj); +- up_read(&cpufreq_rwsem); + } + EXPORT_SYMBOL_GPL(cpufreq_cpu_put); + +@@ -765,9 +752,6 @@ + struct freq_attr *fattr = to_attr(attr); + ssize_t ret; + +- if (!down_read_trylock(&cpufreq_rwsem)) +- return -EINVAL; +- + down_read(&policy->rwsem); + + if (fattr->show) +@@ -776,7 +760,6 @@ + ret = -EIO; + + up_read(&policy->rwsem); +- up_read(&cpufreq_rwsem); + + return ret; + } +@@ -793,9 +776,6 @@ + if (!cpu_online(policy->cpu)) + goto unlock; + +- if (!down_read_trylock(&cpufreq_rwsem)) +- goto unlock; +- + down_write(&policy->rwsem); + + if (fattr->store) +@@ -804,8 +784,6 @@ + ret = -EIO; + + up_write(&policy->rwsem); +- +- up_read(&cpufreq_rwsem); + unlock: + put_online_cpus(); + +@@ -1117,16 +1095,12 @@ + if (unlikely(policy)) + return 0; + +- if (!down_read_trylock(&cpufreq_rwsem)) +- return 0; +- + /* Check if this cpu was hot-unplugged earlier and has siblings */ + read_lock_irqsave(&cpufreq_driver_lock, flags); + for_each_policy(policy) { + if (cpumask_test_cpu(cpu, policy->related_cpus)) { + read_unlock_irqrestore(&cpufreq_driver_lock, flags); + ret = cpufreq_add_policy_cpu(policy, cpu, dev); +- up_read(&cpufreq_rwsem); + return ret; + } + } +@@ -1269,8 +1243,6 @@ + + kobject_uevent(&policy->kobj, KOBJ_ADD); + +- up_read(&cpufreq_rwsem); +- + /* Callback for handling stuff after policy is ready */ + if (cpufreq_driver->ready) + cpufreq_driver->ready(policy); +@@ -1304,8 +1276,6 @@ + cpufreq_policy_free(policy); + + nomem_out: +- up_read(&cpufreq_rwsem); +- + return ret; + } + +@@ -2499,19 +2469,20 @@ + + pr_debug("unregistering driver %s\n", driver->name); + ++ /* Protect against concurrent cpu hotplug */ ++ get_online_cpus(); + subsys_interface_unregister(&cpufreq_interface); + if (cpufreq_boost_supported()) + cpufreq_sysfs_remove_file(&boost.attr); + + unregister_hotcpu_notifier(&cpufreq_cpu_notifier); + +- down_write(&cpufreq_rwsem); + write_lock_irqsave(&cpufreq_driver_lock, flags); + + cpufreq_driver = NULL; + + write_unlock_irqrestore(&cpufreq_driver_lock, flags); +- up_write(&cpufreq_rwsem); ++ put_online_cpus(); + + return 0; + } +diff -Nur linux-4.1.39.orig/drivers/cpufreq/Kconfig.x86 linux-4.1.39/drivers/cpufreq/Kconfig.x86 +--- linux-4.1.39.orig/drivers/cpufreq/Kconfig.x86 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/cpufreq/Kconfig.x86 2017-04-18 17:56:30.577395735 +0200 +@@ -123,7 +123,7 @@ + + config X86_POWERNOW_K8 + tristate "AMD Opteron/Athlon64 PowerNow!" +- depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ ++ depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ && !PREEMPT_RT_BASE + help + This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors. + Support for K10 and newer processors is now in acpi-cpufreq. +diff -Nur linux-4.1.39.orig/drivers/gpio/gpio-omap.c linux-4.1.39/drivers/gpio/gpio-omap.c +--- linux-4.1.39.orig/drivers/gpio/gpio-omap.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/gpio/gpio-omap.c 2017-04-18 17:56:30.577395735 +0200 +@@ -29,6 +29,7 @@ + #include + + #define OFF_MODE 1 ++#define OMAP4_GPIO_DEBOUNCINGTIME_MASK 0xFF + + static LIST_HEAD(omap_gpio_list); + +@@ -50,14 +51,15 @@ + struct gpio_bank { + struct list_head node; + void __iomem *base; +- u16 irq; ++ int irq; + u32 non_wakeup_gpios; + u32 enabled_non_wakeup_gpios; + struct gpio_regs context; + u32 saved_datain; + u32 level_mask; + u32 toggle_mask; +- spinlock_t lock; ++ raw_spinlock_t lock; ++ raw_spinlock_t wa_lock; + struct gpio_chip chip; + struct clk *dbck; + u32 mod_usage; +@@ -67,7 +69,7 @@ + struct device *dev; + bool is_mpuio; + bool dbck_flag; +- bool loses_context; ++ + bool context_valid; + int stride; + u32 width; +@@ -175,7 +177,7 @@ + static inline void omap_gpio_dbck_enable(struct gpio_bank *bank) + { + if (bank->dbck_enable_mask && !bank->dbck_enabled) { +- clk_prepare_enable(bank->dbck); ++ clk_enable(bank->dbck); + bank->dbck_enabled = true; + + writel_relaxed(bank->dbck_enable_mask, +@@ -193,7 +195,7 @@ + */ + writel_relaxed(0, bank->base + bank->regs->debounce_en); + +- clk_disable_unprepare(bank->dbck); ++ clk_disable(bank->dbck); + bank->dbck_enabled = false; + } + } +@@ -204,8 +206,9 @@ + * @offset: the gpio number on this @bank + * @debounce: debounce time to use + * +- * OMAP's debounce time is in 31us steps so we need +- * to convert and round up to the closest unit. ++ * OMAP's debounce time is in 31us steps ++ * = (GPIO_DEBOUNCINGTIME[7:0].DEBOUNCETIME + 1) x 31 ++ * so we need to convert and round up to the closest unit. + */ + static void omap2_set_gpio_debounce(struct gpio_bank *bank, unsigned offset, + unsigned debounce) +@@ -213,34 +216,33 @@ + void __iomem *reg; + u32 val; + u32 l; ++ bool enable = !!debounce; + + if (!bank->dbck_flag) + return; + +- if (debounce < 32) +- debounce = 0x01; +- else if (debounce > 7936) +- debounce = 0xff; +- else +- debounce = (debounce / 0x1f) - 1; ++ if (enable) { ++ debounce = DIV_ROUND_UP(debounce, 31) - 1; ++ debounce &= OMAP4_GPIO_DEBOUNCINGTIME_MASK; ++ } + + l = BIT(offset); + +- clk_prepare_enable(bank->dbck); ++ clk_enable(bank->dbck); + reg = bank->base + bank->regs->debounce; + writel_relaxed(debounce, reg); + + reg = bank->base + bank->regs->debounce_en; + val = readl_relaxed(reg); + +- if (debounce) ++ if (enable) + val |= l; + else + val &= ~l; + bank->dbck_enable_mask = val; + + writel_relaxed(val, reg); +- clk_disable_unprepare(bank->dbck); ++ clk_disable(bank->dbck); + /* + * Enable debounce clock per module. + * This call is mandatory because in omap_gpio_request() when +@@ -285,7 +287,7 @@ + bank->context.debounce = 0; + writel_relaxed(bank->context.debounce, bank->base + + bank->regs->debounce); +- clk_disable_unprepare(bank->dbck); ++ clk_disable(bank->dbck); + bank->dbck_enabled = false; + } + } +@@ -488,9 +490,6 @@ + unsigned long flags; + unsigned offset = d->hwirq; + +- if (!BANK_USED(bank)) +- pm_runtime_get_sync(bank->dev); +- + if (type & ~IRQ_TYPE_SENSE_MASK) + return -EINVAL; + +@@ -498,20 +497,28 @@ + (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 = omap_set_gpio_triggering(bank, offset, type); ++ if (retval) { ++ raw_spin_unlock_irqrestore(&bank->lock, flags); ++ goto error; ++ } + omap_gpio_init_irq(bank, offset); + if (!omap_gpio_is_input(bank, offset)) { +- spin_unlock_irqrestore(&bank->lock, flags); +- return -EINVAL; ++ raw_spin_unlock_irqrestore(&bank->lock, flags); ++ retval = -EINVAL; ++ goto error; + } +- 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); + else if (type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING)) + __irq_set_handler_locked(d->irq, handle_edge_irq); + ++ return 0; ++ ++error: + return retval; + } + +@@ -626,34 +633,30 @@ + return -EINVAL; + } + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + if (enable) + bank->context.wake_en |= gpio_bit; + else + bank->context.wake_en &= ~gpio_bit; + + writel_relaxed(bank->context.wake_en, bank->base + bank->regs->wkup_en); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } + +-static void omap_reset_gpio(struct gpio_bank *bank, unsigned offset) +-{ +- omap_set_gpio_direction(bank, offset, 1); +- omap_set_gpio_irqenable(bank, offset, 0); +- omap_clear_gpio_irqstatus(bank, offset); +- omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE); +- omap_clear_gpio_debounce(bank, offset); +-} +- + /* Use disable_irq_wake() and enable_irq_wake() functions from drivers */ + static int omap_gpio_wake_enable(struct irq_data *d, unsigned int enable) + { + struct gpio_bank *bank = omap_irq_data_get_bank(d); + unsigned offset = d->hwirq; ++ int ret; ++ ++ ret = omap_set_gpio_wakeup(bank, offset, enable); ++ if (!ret) ++ ret = irq_set_irq_wake(bank->irq, enable); + +- return omap_set_gpio_wakeup(bank, offset, enable); ++ return ret; + } + + static int omap_gpio_request(struct gpio_chip *chip, unsigned offset) +@@ -668,17 +671,10 @@ + if (!BANK_USED(bank)) + pm_runtime_get_sync(bank->dev); + +- spin_lock_irqsave(&bank->lock, flags); +- /* Set trigger to none. You need to enable the desired trigger with +- * request_irq() or set_irq_type(). Only do this if the IRQ line has +- * not already been requested. +- */ +- if (!LINE_USED(bank->irq_usage, offset)) { +- omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE); +- omap_enable_gpio_module(bank, offset); +- } ++ raw_spin_lock_irqsave(&bank->lock, flags); ++ omap_enable_gpio_module(bank, offset); + bank->mod_usage |= BIT(offset); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -688,11 +684,14 @@ + struct gpio_bank *bank = container_of(chip, struct gpio_bank, chip); + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + bank->mod_usage &= ~(BIT(offset)); ++ if (!LINE_USED(bank->irq_usage, offset)) { ++ omap_set_gpio_direction(bank, offset, 1); ++ omap_clear_gpio_debounce(bank, offset); ++ } + omap_disable_gpio_module(bank, offset); +- omap_reset_gpio(bank, 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, +@@ -711,29 +710,27 @@ + * line's interrupt handler has been run, we may miss some nested + * interrupts. + */ +-static void omap_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) ++static irqreturn_t omap_gpio_irq_handler(int irq, void *gpiobank) + { + void __iomem *isr_reg = NULL; + u32 isr; + unsigned int bit; +- struct gpio_bank *bank; +- int unmasked = 0; +- struct irq_chip *irqchip = irq_desc_get_chip(desc); +- struct gpio_chip *chip = irq_get_handler_data(irq); ++ struct gpio_bank *bank = gpiobank; ++ unsigned long wa_lock_flags; ++ unsigned long lock_flags; + +- chained_irq_enter(irqchip, desc); +- +- bank = container_of(chip, struct gpio_bank, chip); + isr_reg = bank->base + bank->regs->irqstatus; +- pm_runtime_get_sync(bank->dev); +- + if (WARN_ON(!isr_reg)) + goto exit; + ++ pm_runtime_get_sync(bank->dev); ++ + while (1) { + u32 isr_saved, level_mask = 0; + u32 enabled; + ++ raw_spin_lock_irqsave(&bank->lock, lock_flags); ++ + enabled = omap_get_gpio_irqbank_mask(bank); + isr_saved = isr = readl_relaxed(isr_reg) & enabled; + +@@ -747,12 +744,7 @@ + omap_clear_gpio_irqbank(bank, isr_saved & ~level_mask); + omap_enable_gpio_irqbank(bank, isr_saved & ~level_mask); + +- /* if there is only edge sensitive GPIO pin interrupts +- configured, we could unmask GPIO bank interrupt immediately */ +- if (!level_mask && !unmasked) { +- unmasked = 1; +- chained_irq_exit(irqchip, desc); +- } ++ raw_spin_unlock_irqrestore(&bank->lock, lock_flags); + + if (!isr) + break; +@@ -761,6 +753,7 @@ + bit = __ffs(isr); + isr &= ~(BIT(bit)); + ++ raw_spin_lock_irqsave(&bank->lock, lock_flags); + /* + * Some chips can't respond to both rising and falling + * at the same time. If this irq was requested with +@@ -771,18 +764,20 @@ + if (bank->toggle_mask & (BIT(bit))) + omap_toggle_gpio_edge_triggering(bank, bit); + ++ raw_spin_unlock_irqrestore(&bank->lock, lock_flags); ++ ++ raw_spin_lock_irqsave(&bank->wa_lock, wa_lock_flags); ++ + generic_handle_irq(irq_find_mapping(bank->chip.irqdomain, + bit)); ++ ++ raw_spin_unlock_irqrestore(&bank->wa_lock, ++ wa_lock_flags); + } + } +- /* if bank has any level sensitive GPIO pin interrupt +- configured, we must unmask the bank interrupt only after +- handler(s) are executed in order to avoid spurious bank +- interrupt */ + exit: +- if (!unmasked) +- chained_irq_exit(irqchip, desc); + pm_runtime_put(bank->dev); ++ return IRQ_HANDLED; + } + + static unsigned int omap_gpio_irq_startup(struct irq_data *d) +@@ -791,15 +786,22 @@ + unsigned long flags; + unsigned offset = d->hwirq; + +- if (!BANK_USED(bank)) +- pm_runtime_get_sync(bank->dev); ++ raw_spin_lock_irqsave(&bank->lock, flags); + +- spin_lock_irqsave(&bank->lock, flags); +- omap_gpio_init_irq(bank, offset); +- spin_unlock_irqrestore(&bank->lock, flags); ++ if (!LINE_USED(bank->mod_usage, offset)) ++ omap_set_gpio_direction(bank, offset, 1); ++ else if (!omap_gpio_is_input(bank, offset)) ++ goto err; ++ omap_enable_gpio_module(bank, offset); ++ bank->irq_usage |= BIT(offset); ++ ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + omap_gpio_unmask_irq(d); + + return 0; ++err: ++ raw_spin_unlock_irqrestore(&bank->lock, flags); ++ return -EINVAL; + } + + static void omap_gpio_irq_shutdown(struct irq_data *d) +@@ -808,11 +810,28 @@ + unsigned long flags; + unsigned offset = d->hwirq; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + bank->irq_usage &= ~(BIT(offset)); ++ omap_set_gpio_irqenable(bank, offset, 0); ++ omap_clear_gpio_irqstatus(bank, offset); ++ omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE); ++ if (!LINE_USED(bank->mod_usage, offset)) ++ omap_clear_gpio_debounce(bank, offset); + omap_disable_gpio_module(bank, offset); +- omap_reset_gpio(bank, offset); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); ++} ++ ++static void omap_gpio_irq_bus_lock(struct irq_data *data) ++{ ++ struct gpio_bank *bank = omap_irq_data_get_bank(data); ++ ++ if (!BANK_USED(bank)) ++ pm_runtime_get_sync(bank->dev); ++} ++ ++static void gpio_irq_bus_sync_unlock(struct irq_data *data) ++{ ++ struct gpio_bank *bank = omap_irq_data_get_bank(data); + + /* + * If this is the last IRQ to be freed in the bank, +@@ -836,10 +855,10 @@ + unsigned offset = d->hwirq; + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + omap_set_gpio_irqenable(bank, offset, 0); + omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + } + + static void omap_gpio_unmask_irq(struct irq_data *d) +@@ -849,7 +868,7 @@ + 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) + omap_set_gpio_triggering(bank, offset, trigger); + +@@ -861,7 +880,7 @@ + } + + omap_set_gpio_irqenable(bank, offset, 1); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + } + + /*---------------------------------------------------------------------*/ +@@ -874,9 +893,9 @@ + OMAP_MPUIO_GPIO_MASKIT / bank->stride; + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + writel_relaxed(0xffff & ~bank->context.wake_en, mask_reg); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -889,9 +908,9 @@ + OMAP_MPUIO_GPIO_MASKIT / bank->stride; + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + writel_relaxed(bank->context.wake_en, mask_reg); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -937,9 +956,9 @@ + + bank = container_of(chip, struct gpio_bank, chip); + reg = bank->base + bank->regs->direction; +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + dir = !!(readl_relaxed(reg) & BIT(offset)); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return dir; + } + +@@ -949,9 +968,9 @@ + unsigned long flags; + + bank = container_of(chip, struct gpio_bank, chip); +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + omap_set_gpio_direction(bank, offset, 1); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return 0; + } + +@@ -973,10 +992,10 @@ + 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); + omap_set_gpio_direction(bank, offset, 0); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return 0; + } + +@@ -988,9 +1007,9 @@ + + bank = container_of(chip, struct gpio_bank, chip); + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + omap2_set_gpio_debounce(bank, offset, debounce); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -1001,9 +1020,9 @@ + 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); + } + + /*---------------------------------------------------------------------*/ +@@ -1048,10 +1067,6 @@ + /* Initialize interface clk ungated, module enabled */ + if (bank->regs->ctrl) + writel_relaxed(0, base + bank->regs->ctrl); +- +- bank->dbck = clk_get(bank->dev, "dbclk"); +- if (IS_ERR(bank->dbck)) +- dev_err(bank->dev, "Could not get gpio dbck\n"); + } + + static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc) +@@ -1080,7 +1095,6 @@ + } else { + bank->chip.label = "gpio"; + bank->chip.base = gpio; +- gpio += bank->width; + } + bank->chip.ngpio = bank->width; + +@@ -1090,6 +1104,9 @@ + return ret; + } + ++ if (!bank->is_mpuio) ++ gpio += bank->width; ++ + #ifdef CONFIG_ARCH_OMAP1 + /* + * REVISIT: Once we have OMAP1 supporting SPARSE_IRQ, we can drop +@@ -1112,7 +1129,7 @@ + } + + ret = gpiochip_irqchip_add(&bank->chip, irqc, +- irq_base, omap_gpio_irq_handler, ++ irq_base, handle_bad_irq, + IRQ_TYPE_NONE); + + if (ret) { +@@ -1121,10 +1138,14 @@ + return -ENODEV; + } + +- gpiochip_set_chained_irqchip(&bank->chip, irqc, +- bank->irq, omap_gpio_irq_handler); ++ gpiochip_set_chained_irqchip(&bank->chip, irqc, bank->irq, NULL); + +- return 0; ++ ret = devm_request_irq(bank->dev, bank->irq, omap_gpio_irq_handler, ++ 0, dev_name(bank->dev), bank); ++ if (ret) ++ gpiochip_remove(&bank->chip); ++ ++ return ret; + } + + static const struct of_device_id omap_gpio_match[]; +@@ -1163,17 +1184,23 @@ + irqc->irq_unmask = omap_gpio_unmask_irq, + irqc->irq_set_type = omap_gpio_irq_type, + irqc->irq_set_wake = omap_gpio_wake_enable, ++ irqc->irq_bus_lock = omap_gpio_irq_bus_lock, ++ irqc->irq_bus_sync_unlock = gpio_irq_bus_sync_unlock, + irqc->name = dev_name(&pdev->dev); + +- res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); +- if (unlikely(!res)) { +- dev_err(dev, "Invalid IRQ resource\n"); +- return -ENODEV; ++ bank->irq = platform_get_irq(pdev, 0); ++ if (bank->irq <= 0) { ++ if (!bank->irq) ++ bank->irq = -ENXIO; ++ if (bank->irq != -EPROBE_DEFER) ++ dev_err(dev, ++ "can't get irq resource ret=%d\n", bank->irq); ++ return bank->irq; + } + +- bank->irq = res->start; + bank->dev = dev; + bank->chip.dev = dev; ++ bank->chip.owner = THIS_MODULE; + bank->dbck_flag = pdata->dbck_flag; + bank->stride = pdata->bank_stride; + bank->width = pdata->bank_width; +@@ -1183,15 +1210,9 @@ + #ifdef CONFIG_OF_GPIO + bank->chip.of_node = of_node_get(node); + #endif +- if (node) { +- if (!of_property_read_bool(node, "ti,gpio-always-on")) +- bank->loses_context = true; +- } else { +- bank->loses_context = pdata->loses_context; +- +- if (bank->loses_context) +- bank->get_context_loss_count = +- pdata->get_context_loss_count; ++ if (!node) { ++ bank->get_context_loss_count = ++ pdata->get_context_loss_count; + } + + if (bank->regs->set_dataout && bank->regs->clr_dataout) +@@ -1199,16 +1220,27 @@ + else + bank->set_dataout = omap_set_gpio_dataout_mask; + +- spin_lock_init(&bank->lock); ++ raw_spin_lock_init(&bank->lock); ++ raw_spin_lock_init(&bank->wa_lock); + + /* Static mapping, never released */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + bank->base = devm_ioremap_resource(dev, res); + if (IS_ERR(bank->base)) { +- irq_domain_remove(bank->chip.irqdomain); + return PTR_ERR(bank->base); + } + ++ if (bank->dbck_flag) { ++ bank->dbck = devm_clk_get(bank->dev, "dbclk"); ++ if (IS_ERR(bank->dbck)) { ++ dev_err(bank->dev, ++ "Could not get gpio dbck. Disable debounce\n"); ++ bank->dbck_flag = false; ++ } else { ++ clk_prepare(bank->dbck); ++ } ++ } ++ + platform_set_drvdata(pdev, bank); + + pm_runtime_enable(bank->dev); +@@ -1221,8 +1253,11 @@ + omap_gpio_mod_init(bank); + + ret = omap_gpio_chip_init(bank, irqc); +- if (ret) ++ if (ret) { ++ pm_runtime_put_sync(bank->dev); ++ pm_runtime_disable(bank->dev); + return ret; ++ } + + omap_gpio_show_rev(bank); + +@@ -1233,6 +1268,19 @@ + return 0; + } + ++static int omap_gpio_remove(struct platform_device *pdev) ++{ ++ struct gpio_bank *bank = platform_get_drvdata(pdev); ++ ++ list_del(&bank->node); ++ gpiochip_remove(&bank->chip); ++ pm_runtime_disable(bank->dev); ++ if (bank->dbck_flag) ++ clk_unprepare(bank->dbck); ++ ++ return 0; ++} ++ + #ifdef CONFIG_ARCH_OMAP2PLUS + + #if defined(CONFIG_PM) +@@ -1246,7 +1294,7 @@ + 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. +@@ -1299,7 +1347,7 @@ + bank->get_context_loss_count(bank->dev); + + omap_gpio_dbck_disable(bank); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -1314,14 +1362,14 @@ + unsigned long flags; + int c; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + + /* + * On the first resume during the probe, the context has not + * been initialised and so initialise it now. Also initialise + * the context loss count. + */ +- if (bank->loses_context && !bank->context_valid) { ++ if (!bank->context_valid) { + omap_gpio_init_context(bank); + + if (bank->get_context_loss_count) +@@ -1342,22 +1390,20 @@ + writel_relaxed(bank->context.risingdetect, + bank->base + bank->regs->risingdetect); + +- if (bank->loses_context) { +- if (!bank->get_context_loss_count) { ++ if (!bank->get_context_loss_count) { ++ omap_gpio_restore_context(bank); ++ } else { ++ c = bank->get_context_loss_count(bank->dev); ++ if (c != bank->context_loss_count) { + omap_gpio_restore_context(bank); + } else { +- c = bank->get_context_loss_count(bank->dev); +- if (c != bank->context_loss_count) { +- omap_gpio_restore_context(bank); +- } else { +- spin_unlock_irqrestore(&bank->lock, flags); +- return 0; +- } ++ raw_spin_unlock_irqrestore(&bank->lock, flags); ++ return 0; + } + } + + if (!bank->workaround_enabled) { +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return 0; + } + +@@ -1412,18 +1458,19 @@ + } + + bank->workaround_enabled = false; +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } + #endif /* CONFIG_PM */ + ++#if IS_BUILTIN(CONFIG_GPIO_OMAP) + void omap2_gpio_prepare_for_idle(int pwr_mode) + { + struct gpio_bank *bank; + + list_for_each_entry(bank, &omap_gpio_list, node) { +- if (!BANK_USED(bank) || !bank->loses_context) ++ if (!BANK_USED(bank)) + continue; + + bank->power_mode = pwr_mode; +@@ -1437,12 +1484,13 @@ + struct gpio_bank *bank; + + list_for_each_entry(bank, &omap_gpio_list, node) { +- if (!BANK_USED(bank) || !bank->loses_context) ++ if (!BANK_USED(bank)) + continue; + + pm_runtime_get_sync(bank->dev); + } + } ++#endif + + #if defined(CONFIG_PM) + static void omap_gpio_init_context(struct gpio_bank *p) +@@ -1598,6 +1646,7 @@ + + static struct platform_driver omap_gpio_driver = { + .probe = omap_gpio_probe, ++ .remove = omap_gpio_remove, + .driver = { + .name = "omap_gpio", + .pm = &gpio_pm_ops, +@@ -1615,3 +1664,13 @@ + return platform_driver_register(&omap_gpio_driver); + } + postcore_initcall(omap_gpio_drv_reg); ++ ++static void __exit omap_gpio_exit(void) ++{ ++ platform_driver_unregister(&omap_gpio_driver); ++} ++module_exit(omap_gpio_exit); ++ ++MODULE_DESCRIPTION("omap gpio driver"); ++MODULE_ALIAS("platform:gpio-omap"); ++MODULE_LICENSE("GPL v2"); +diff -Nur linux-4.1.39.orig/drivers/gpio/Kconfig linux-4.1.39/drivers/gpio/Kconfig +--- linux-4.1.39.orig/drivers/gpio/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/gpio/Kconfig 2017-04-18 17:56:30.577395735 +0200 +@@ -309,7 +309,7 @@ + family of SOCs. + + config GPIO_OMAP +- bool "TI OMAP GPIO support" if COMPILE_TEST && !ARCH_OMAP2PLUS ++ tristate "TI OMAP GPIO support" if ARCH_OMAP2PLUS || COMPILE_TEST + default y if ARCH_OMAP + depends on ARM + select GENERIC_IRQ_CHIP +diff -Nur linux-4.1.39.orig/drivers/gpu/drm/i915/i915_gem_execbuffer.c linux-4.1.39/drivers/gpu/drm/i915/i915_gem_execbuffer.c +--- linux-4.1.39.orig/drivers/gpu/drm/i915/i915_gem_execbuffer.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/gpu/drm/i915/i915_gem_execbuffer.c 2017-04-18 17:56:30.577395735 +0200 +@@ -32,6 +32,7 @@ + #include "i915_trace.h" + #include "intel_drv.h" + #include ++#include + + #define __EXEC_OBJECT_HAS_PIN (1<<31) + #define __EXEC_OBJECT_HAS_FENCE (1<<30) +@@ -465,7 +466,7 @@ + } + + /* We can't wait for rendering with pagefaults disabled */ +- if (obj->active && in_atomic()) ++ if (obj->active && pagefault_disabled()) + return -EFAULT; + + if (use_cpu_reloc(obj)) +@@ -1338,7 +1339,9 @@ + return ret; + } + ++#ifndef CONFIG_PREEMPT_RT_BASE + trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags); ++#endif + + i915_gem_execbuffer_move_to_active(vmas, ring); + i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj); +diff -Nur linux-4.1.39.orig/drivers/gpu/drm/i915/i915_gem_shrinker.c linux-4.1.39/drivers/gpu/drm/i915/i915_gem_shrinker.c +--- linux-4.1.39.orig/drivers/gpu/drm/i915/i915_gem_shrinker.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/gpu/drm/i915/i915_gem_shrinker.c 2017-04-18 17:56:30.577395735 +0200 +@@ -39,7 +39,7 @@ + if (!mutex_is_locked(mutex)) + return false; + +-#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER) ++#if (defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)) && !defined(CONFIG_PREEMPT_RT_BASE) + return mutex->owner == task; + #else + /* Since UP may be pre-empted, we cannot assume that we own the lock */ +diff -Nur linux-4.1.39.orig/drivers/gpu/drm/i915/i915_irq.c linux-4.1.39/drivers/gpu/drm/i915/i915_irq.c +--- linux-4.1.39.orig/drivers/gpu/drm/i915/i915_irq.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/gpu/drm/i915/i915_irq.c 2017-04-18 17:56:30.581395889 +0200 +@@ -676,6 +676,7 @@ + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + + /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_disable_rt(); + + /* Get optional system timestamp before query. */ + if (stime) +@@ -727,6 +728,7 @@ + *etime = ktime_get(); + + /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_enable_rt(); + + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); + +diff -Nur linux-4.1.39.orig/drivers/gpu/drm/i915/intel_display.c linux-4.1.39/drivers/gpu/drm/i915/intel_display.c +--- linux-4.1.39.orig/drivers/gpu/drm/i915/intel_display.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/gpu/drm/i915/intel_display.c 2017-04-18 17:56:30.581395889 +0200 +@@ -10084,7 +10084,7 @@ + struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + +- WARN_ON(!in_interrupt()); ++ WARN_ON_NONRT(!in_interrupt()); + + if (crtc == NULL) + return; +diff -Nur linux-4.1.39.orig/drivers/gpu/drm/i915/intel_sprite.c linux-4.1.39/drivers/gpu/drm/i915/intel_sprite.c +--- linux-4.1.39.orig/drivers/gpu/drm/i915/intel_sprite.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/gpu/drm/i915/intel_sprite.c 2017-04-18 17:56:30.581395889 +0200 +@@ -37,6 +37,7 @@ + #include "intel_drv.h" + #include + #include "i915_drv.h" ++#include + + static bool + format_is_yuv(uint32_t format) +@@ -61,6 +62,8 @@ + return DIV_ROUND_UP(usecs * mode->crtc_clock, 1000 * mode->crtc_htotal); + } + ++static DEFINE_LOCAL_IRQ_LOCK(pipe_update_lock); ++ + /** + * intel_pipe_update_start() - start update of a set of display registers + * @crtc: the crtc of which the registers are going to be updated +@@ -101,7 +104,7 @@ + if (WARN_ON(drm_crtc_vblank_get(&crtc->base))) + return false; + +- local_irq_disable(); ++ local_lock_irq(pipe_update_lock); + + trace_i915_pipe_update_start(crtc, min, max); + +@@ -123,11 +126,11 @@ + break; + } + +- local_irq_enable(); ++ local_unlock_irq(pipe_update_lock); + + timeout = schedule_timeout(timeout); + +- local_irq_disable(); ++ local_lock_irq(pipe_update_lock); + } + + finish_wait(wq, &wait); +@@ -158,7 +161,7 @@ + + trace_i915_pipe_update_end(crtc, end_vbl_count); + +- local_irq_enable(); ++ local_unlock_irq(pipe_update_lock); + + if (start_vbl_count != end_vbl_count) + DRM_ERROR("Atomic update failure on pipe %c (start=%u end=%u)\n", +diff -Nur linux-4.1.39.orig/drivers/gpu/drm/radeon/radeon_display.c linux-4.1.39/drivers/gpu/drm/radeon/radeon_display.c +--- linux-4.1.39.orig/drivers/gpu/drm/radeon/radeon_display.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/gpu/drm/radeon/radeon_display.c 2017-04-18 17:56:30.581395889 +0200 +@@ -1798,6 +1798,7 @@ + struct radeon_device *rdev = dev->dev_private; + + /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_disable_rt(); + + /* Get optional system timestamp before query. */ + if (stime) +@@ -1890,6 +1891,7 @@ + *etime = ktime_get(); + + /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_enable_rt(); + + /* Decode into vertical and horizontal scanout position. */ + *vpos = position & 0x1fff; +diff -Nur linux-4.1.39.orig/drivers/i2c/busses/i2c-omap.c linux-4.1.39/drivers/i2c/busses/i2c-omap.c +--- linux-4.1.39.orig/drivers/i2c/busses/i2c-omap.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/i2c/busses/i2c-omap.c 2017-04-18 17:56:30.581395889 +0200 +@@ -996,15 +996,12 @@ + u16 mask; + u16 stat; + +- spin_lock(&dev->lock); +- mask = omap_i2c_read_reg(dev, OMAP_I2C_IE_REG); + stat = omap_i2c_read_reg(dev, OMAP_I2C_STAT_REG); ++ mask = omap_i2c_read_reg(dev, OMAP_I2C_IE_REG); + + if (stat & mask) + ret = IRQ_WAKE_THREAD; + +- spin_unlock(&dev->lock); +- + return ret; + } + +diff -Nur linux-4.1.39.orig/drivers/ide/alim15x3.c linux-4.1.39/drivers/ide/alim15x3.c +--- linux-4.1.39.orig/drivers/ide/alim15x3.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/ide/alim15x3.c 2017-04-18 17:56:30.581395889 +0200 +@@ -234,7 +234,7 @@ + + 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 @@ + } + pci_dev_put(north); + pci_dev_put(isa_dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return 0; + } + +diff -Nur linux-4.1.39.orig/drivers/ide/hpt366.c linux-4.1.39/drivers/ide/hpt366.c +--- linux-4.1.39.orig/drivers/ide/hpt366.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/ide/hpt366.c 2017-04-18 17:56:30.581395889 +0200 +@@ -1241,7 +1241,7 @@ + + 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 @@ + 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 -Nur linux-4.1.39.orig/drivers/ide/ide-io.c linux-4.1.39/drivers/ide/ide-io.c +--- linux-4.1.39.orig/drivers/ide/ide-io.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/ide/ide-io.c 2017-04-18 17:56:30.581395889 +0200 +@@ -659,7 +659,7 @@ + /* 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 -Nur linux-4.1.39.orig/drivers/ide/ide-iops.c linux-4.1.39/drivers/ide/ide-iops.c +--- linux-4.1.39.orig/drivers/ide/ide-iops.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/ide/ide-iops.c 2017-04-18 17:56:30.585396045 +0200 +@@ -129,12 +129,12 @@ + 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 -Nur linux-4.1.39.orig/drivers/ide/ide-io-std.c linux-4.1.39/drivers/ide/ide-io-std.c +--- linux-4.1.39.orig/drivers/ide/ide-io-std.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/ide/ide-io-std.c 2017-04-18 17:56:30.581395889 +0200 +@@ -175,7 +175,7 @@ + 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 @@ + 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 @@ + 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 @@ + 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 -Nur linux-4.1.39.orig/drivers/ide/ide-probe.c linux-4.1.39/drivers/ide/ide-probe.c +--- linux-4.1.39.orig/drivers/ide/ide-probe.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/ide/ide-probe.c 2017-04-18 17:56:30.585396045 +0200 +@@ -196,10 +196,10 @@ + 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 -Nur linux-4.1.39.orig/drivers/ide/ide-taskfile.c linux-4.1.39/drivers/ide/ide-taskfile.c +--- linux-4.1.39.orig/drivers/ide/ide-taskfile.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/ide/ide-taskfile.c 2017-04-18 17:56:30.585396045 +0200 +@@ -250,7 +250,7 @@ + + page_is_high = PageHighMem(page); + if (page_is_high) +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + buf = kmap_atomic(page) + offset; + +@@ -271,7 +271,7 @@ + kunmap_atomic(buf); + + if (page_is_high) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + len -= nr_bytes; + } +@@ -414,7 +414,7 @@ + } + + 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 -Nur linux-4.1.39.orig/drivers/infiniband/ulp/ipoib/ipoib_multicast.c linux-4.1.39/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +--- linux-4.1.39.orig/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2017-04-18 17:56:30.585396045 +0200 +@@ -824,7 +824,7 @@ + + ipoib_dbg_mcast(priv, "restarting multicast task\n"); + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + netif_addr_lock(dev); + spin_lock(&priv->lock); + +@@ -906,7 +906,7 @@ + + spin_unlock(&priv->lock); + netif_addr_unlock(dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + /* + * make sure the in-flight joins have finished before we attempt +diff -Nur linux-4.1.39.orig/drivers/input/gameport/gameport.c linux-4.1.39/drivers/input/gameport/gameport.c +--- linux-4.1.39.orig/drivers/input/gameport/gameport.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/input/gameport/gameport.c 2017-04-18 17:56:30.585396045 +0200 +@@ -124,12 +124,12 @@ + 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; + } +@@ -148,11 +148,11 @@ + 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 -Nur linux-4.1.39.orig/drivers/leds/trigger/Kconfig linux-4.1.39/drivers/leds/trigger/Kconfig +--- linux-4.1.39.orig/drivers/leds/trigger/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/leds/trigger/Kconfig 2017-04-18 17:56:30.585396045 +0200 +@@ -61,7 +61,7 @@ + + config LEDS_TRIGGER_CPU + bool "LED CPU Trigger" +- depends on LEDS_TRIGGERS ++ depends on LEDS_TRIGGERS && !PREEMPT_RT_BASE + help + This allows LEDs to be controlled by active CPUs. This shows + the active CPUs across an array of LEDs so you can see which +diff -Nur linux-4.1.39.orig/drivers/md/bcache/Kconfig linux-4.1.39/drivers/md/bcache/Kconfig +--- linux-4.1.39.orig/drivers/md/bcache/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/md/bcache/Kconfig 2017-04-18 17:56:30.585396045 +0200 +@@ -1,6 +1,7 @@ + + config BCACHE + tristate "Block device as cache" ++ depends on !PREEMPT_RT_FULL + ---help--- + Allows a block device to be used as cache for other devices; uses + a btree for indexing and the layout is optimized for SSDs. +diff -Nur linux-4.1.39.orig/drivers/md/dm.c linux-4.1.39/drivers/md/dm.c +--- linux-4.1.39.orig/drivers/md/dm.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/md/dm.c 2017-04-18 17:56:30.585396045 +0200 +@@ -2141,7 +2141,7 @@ + /* Establish tio->ti before queuing work (map_tio_request) */ + tio->ti = ti; + queue_kthread_work(&md->kworker, &tio->work); +- BUG_ON(!irqs_disabled()); ++ BUG_ON_NONRT(!irqs_disabled()); + } + + goto out; +diff -Nur linux-4.1.39.orig/drivers/md/raid5.c linux-4.1.39/drivers/md/raid5.c +--- linux-4.1.39.orig/drivers/md/raid5.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/md/raid5.c 2017-04-18 17:56:30.585396045 +0200 +@@ -1918,8 +1918,9 @@ + 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++; +@@ -1975,7 +1976,8 @@ + 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(); + } + + static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp) +@@ -6375,6 +6377,7 @@ + __func__, cpu); + break; + } ++ spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock); + } + put_online_cpus(); + +diff -Nur linux-4.1.39.orig/drivers/md/raid5.h linux-4.1.39/drivers/md/raid5.h +--- linux-4.1.39.orig/drivers/md/raid5.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/md/raid5.h 2017-04-18 17:56:30.585396045 +0200 +@@ -495,6 +495,7 @@ + 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 */ + struct flex_array *scribble; /* space for constructing buffer + * lists and performing address +diff -Nur linux-4.1.39.orig/drivers/misc/hwlat_detector.c linux-4.1.39/drivers/misc/hwlat_detector.c +--- linux-4.1.39.orig/drivers/misc/hwlat_detector.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/drivers/misc/hwlat_detector.c 2017-04-18 17:56:30.585396045 +0200 +@@ -0,0 +1,1240 @@ ++/* ++ * 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 outer loop (t2 to next t1) */ ++ diff = time_to_us(time_sub(t1, last_t2)); ++ /* This shouldn't happen */ ++ if (diff < 0) { ++ pr_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) { ++ pr_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)) { ++ pr_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 = kstrtoull(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 = kstrtoul(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) { ++ pr_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 = kstrtoull(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 = kstrtoull(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; ++ ++ pr_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) ++ pr_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 -Nur linux-4.1.39.orig/drivers/misc/Kconfig linux-4.1.39/drivers/misc/Kconfig +--- linux-4.1.39.orig/drivers/misc/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/misc/Kconfig 2017-04-18 17:56:30.585396045 +0200 +@@ -54,6 +54,7 @@ + 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 +@@ -69,8 +70,7 @@ + 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 +@@ -84,6 +84,15 @@ + 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 DUMMY_IRQ + tristate "Dummy IRQ handler" + default n +@@ -113,6 +122,35 @@ + 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 -Nur linux-4.1.39.orig/drivers/misc/Makefile linux-4.1.39/drivers/misc/Makefile +--- linux-4.1.39.orig/drivers/misc/Makefile 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/misc/Makefile 2017-04-18 17:56:30.585396045 +0200 +@@ -38,6 +38,7 @@ + obj-$(CONFIG_HMC6352) += hmc6352.o + obj-y += eeprom/ + obj-y += cb710/ ++obj-$(CONFIG_HWLAT_DETECTOR) += hwlat_detector.o + obj-$(CONFIG_SPEAR13XX_PCIE_GADGET) += spear13xx_pcie_gadget.o + obj-$(CONFIG_VMWARE_BALLOON) += vmw_balloon.o + obj-$(CONFIG_ARM_CHARLCD) += arm-charlcd.o +diff -Nur linux-4.1.39.orig/drivers/mmc/host/mmci.c linux-4.1.39/drivers/mmc/host/mmci.c +--- linux-4.1.39.orig/drivers/mmc/host/mmci.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/mmc/host/mmci.c 2017-04-18 17:56:30.589396200 +0200 +@@ -1155,15 +1155,12 @@ + 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; +@@ -1203,8 +1200,6 @@ + + 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 -Nur linux-4.1.39.orig/drivers/net/ethernet/3com/3c59x.c linux-4.1.39/drivers/net/ethernet/3com/3c59x.c +--- linux-4.1.39.orig/drivers/net/ethernet/3com/3c59x.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/net/ethernet/3com/3c59x.c 2017-04-18 17:56:30.589396200 +0200 +@@ -842,9 +842,9 @@ + { + 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 + +@@ -1916,12 +1916,12 @@ + * 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 -Nur linux-4.1.39.orig/drivers/net/ethernet/atheros/atl1c/atl1c_main.c linux-4.1.39/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +--- linux-4.1.39.orig/drivers/net/ethernet/atheros/atl1c/atl1c_main.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/net/ethernet/atheros/atl1c/atl1c_main.c 2017-04-18 17:56:30.589396200 +0200 +@@ -2212,11 +2212,7 @@ + } + + 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 -Nur linux-4.1.39.orig/drivers/net/ethernet/atheros/atl1e/atl1e_main.c linux-4.1.39/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +--- linux-4.1.39.orig/drivers/net/ethernet/atheros/atl1e/atl1e_main.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/net/ethernet/atheros/atl1e/atl1e_main.c 2017-04-18 17:56:30.589396200 +0200 +@@ -1880,8 +1880,7 @@ + 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 -Nur linux-4.1.39.orig/drivers/net/ethernet/chelsio/cxgb/sge.c linux-4.1.39/drivers/net/ethernet/chelsio/cxgb/sge.c +--- linux-4.1.39.orig/drivers/net/ethernet/chelsio/cxgb/sge.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/net/ethernet/chelsio/cxgb/sge.c 2017-04-18 17:56:30.589396200 +0200 +@@ -1664,8 +1664,7 @@ + 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 -Nur linux-4.1.39.orig/drivers/net/ethernet/freescale/gianfar.c linux-4.1.39/drivers/net/ethernet/freescale/gianfar.c +--- linux-4.1.39.orig/drivers/net/ethernet/freescale/gianfar.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/net/ethernet/freescale/gianfar.c 2017-04-18 17:56:30.589396200 +0200 +@@ -1540,7 +1540,7 @@ + + if (netif_running(ndev)) { + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + + gfar_halt_nodisable(priv); +@@ -1556,7 +1556,7 @@ + gfar_write(®s->maccfg1, tempval); + + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + disable_napi(priv); + +@@ -1598,7 +1598,7 @@ + /* Disable Magic Packet mode, in case something + * else woke us up. + */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + + tempval = gfar_read(®s->maccfg2); +@@ -1608,7 +1608,7 @@ + gfar_start(priv); + + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + netif_device_attach(ndev); + +@@ -3418,14 +3418,14 @@ + dev->stats.tx_dropped++; + atomic64_inc(&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 -Nur linux-4.1.39.orig/drivers/net/ethernet/neterion/s2io.c linux-4.1.39/drivers/net/ethernet/neterion/s2io.c +--- linux-4.1.39.orig/drivers/net/ethernet/neterion/s2io.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/net/ethernet/neterion/s2io.c 2017-04-18 17:56:30.589396200 +0200 +@@ -4084,12 +4084,7 @@ + [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 -Nur linux-4.1.39.orig/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c linux-4.1.39/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +--- linux-4.1.39.orig/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c 2017-04-18 17:56:30.589396200 +0200 +@@ -2137,10 +2137,8 @@ + struct pch_gbe_tx_ring *tx_ring = adapter->tx_ring; + unsigned long flags; + +- 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 -Nur linux-4.1.39.orig/drivers/net/ethernet/realtek/8139too.c linux-4.1.39/drivers/net/ethernet/realtek/8139too.c +--- linux-4.1.39.orig/drivers/net/ethernet/realtek/8139too.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/net/ethernet/realtek/8139too.c 2017-04-18 17:56:30.593396355 +0200 +@@ -2229,7 +2229,7 @@ + struct rtl8139_private *tp = netdev_priv(dev); + const int irq = tp->pci_dev->irq; + +- disable_irq(irq); ++ disable_irq_nosync(irq); + rtl8139_interrupt(irq, dev); + enable_irq(irq); + } +diff -Nur linux-4.1.39.orig/drivers/net/ethernet/tehuti/tehuti.c linux-4.1.39/drivers/net/ethernet/tehuti/tehuti.c +--- linux-4.1.39.orig/drivers/net/ethernet/tehuti/tehuti.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/net/ethernet/tehuti/tehuti.c 2017-04-18 17:56:30.593396355 +0200 +@@ -1629,13 +1629,8 @@ + 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 -Nur linux-4.1.39.orig/drivers/net/rionet.c linux-4.1.39/drivers/net/rionet.c +--- linux-4.1.39.orig/drivers/net/rionet.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/net/rionet.c 2017-04-18 17:56:30.593396355 +0200 +@@ -174,11 +174,7 @@ + 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 = nets[rnet->mport->id].nact; +diff -Nur linux-4.1.39.orig/drivers/net/wireless/orinoco/orinoco_usb.c linux-4.1.39/drivers/net/wireless/orinoco/orinoco_usb.c +--- linux-4.1.39.orig/drivers/net/wireless/orinoco/orinoco_usb.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/net/wireless/orinoco/orinoco_usb.c 2017-04-18 17:56:30.593396355 +0200 +@@ -697,7 +697,7 @@ + while (!ctx->done.done && msecs--) + udelay(1000); + } else { +- wait_event_interruptible(ctx->done.wait, ++ swait_event_interruptible(ctx->done.wait, + ctx->done.done); + } + break; +diff -Nur linux-4.1.39.orig/drivers/pci/access.c linux-4.1.39/drivers/pci/access.c +--- linux-4.1.39.orig/drivers/pci/access.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/pci/access.c 2017-04-18 17:56:30.593396355 +0200 +@@ -561,7 +561,7 @@ + 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 -Nur linux-4.1.39.orig/drivers/pinctrl/qcom/pinctrl-msm.c linux-4.1.39/drivers/pinctrl/qcom/pinctrl-msm.c +--- linux-4.1.39.orig/drivers/pinctrl/qcom/pinctrl-msm.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/pinctrl/qcom/pinctrl-msm.c 2017-04-18 17:56:30.593396355 +0200 +@@ -59,7 +59,7 @@ + struct notifier_block restart_nb; + int irq; + +- spinlock_t lock; ++ raw_spinlock_t lock; + + DECLARE_BITMAP(dual_edge_irqs, MAX_NR_GPIO); + DECLARE_BITMAP(enabled_irqs, MAX_NR_GPIO); +@@ -155,14 +155,14 @@ + if (WARN_ON(i == g->nfuncs)) + return -EINVAL; + +- spin_lock_irqsave(&pctrl->lock, flags); ++ raw_spin_lock_irqsave(&pctrl->lock, flags); + + val = readl(pctrl->regs + g->ctl_reg); + val &= ~(0x7 << g->mux_bit); + val |= i << g->mux_bit; + writel(val, pctrl->regs + g->ctl_reg); + +- spin_unlock_irqrestore(&pctrl->lock, flags); ++ raw_spin_unlock_irqrestore(&pctrl->lock, flags); + + return 0; + } +@@ -325,14 +325,14 @@ + break; + case PIN_CONFIG_OUTPUT: + /* set output value */ +- spin_lock_irqsave(&pctrl->lock, flags); ++ raw_spin_lock_irqsave(&pctrl->lock, flags); + val = readl(pctrl->regs + g->io_reg); + if (arg) + val |= BIT(g->out_bit); + else + val &= ~BIT(g->out_bit); + writel(val, pctrl->regs + g->io_reg); +- spin_unlock_irqrestore(&pctrl->lock, flags); ++ raw_spin_unlock_irqrestore(&pctrl->lock, flags); + + /* enable output */ + arg = 1; +@@ -353,12 +353,12 @@ + return -EINVAL; + } + +- spin_lock_irqsave(&pctrl->lock, flags); ++ raw_spin_lock_irqsave(&pctrl->lock, flags); + val = readl(pctrl->regs + g->ctl_reg); + val &= ~(mask << bit); + val |= arg << bit; + writel(val, pctrl->regs + g->ctl_reg); +- spin_unlock_irqrestore(&pctrl->lock, flags); ++ raw_spin_unlock_irqrestore(&pctrl->lock, flags); + } + + return 0; +@@ -386,13 +386,13 @@ + + g = &pctrl->soc->groups[offset]; + +- spin_lock_irqsave(&pctrl->lock, flags); ++ raw_spin_lock_irqsave(&pctrl->lock, flags); + + val = readl(pctrl->regs + g->ctl_reg); + val &= ~BIT(g->oe_bit); + writel(val, pctrl->regs + g->ctl_reg); + +- spin_unlock_irqrestore(&pctrl->lock, flags); ++ raw_spin_unlock_irqrestore(&pctrl->lock, flags); + + return 0; + } +@@ -406,7 +406,7 @@ + + g = &pctrl->soc->groups[offset]; + +- spin_lock_irqsave(&pctrl->lock, flags); ++ raw_spin_lock_irqsave(&pctrl->lock, flags); + + val = readl(pctrl->regs + g->io_reg); + if (value) +@@ -419,7 +419,7 @@ + val |= BIT(g->oe_bit); + writel(val, pctrl->regs + g->ctl_reg); + +- spin_unlock_irqrestore(&pctrl->lock, flags); ++ raw_spin_unlock_irqrestore(&pctrl->lock, flags); + + return 0; + } +@@ -445,7 +445,7 @@ + + g = &pctrl->soc->groups[offset]; + +- spin_lock_irqsave(&pctrl->lock, flags); ++ raw_spin_lock_irqsave(&pctrl->lock, flags); + + val = readl(pctrl->regs + g->io_reg); + if (value) +@@ -454,7 +454,7 @@ + val &= ~BIT(g->out_bit); + writel(val, pctrl->regs + g->io_reg); + +- spin_unlock_irqrestore(&pctrl->lock, flags); ++ raw_spin_unlock_irqrestore(&pctrl->lock, flags); + } + + static int msm_gpio_request(struct gpio_chip *chip, unsigned offset) +@@ -585,7 +585,7 @@ + + g = &pctrl->soc->groups[d->hwirq]; + +- spin_lock_irqsave(&pctrl->lock, flags); ++ raw_spin_lock_irqsave(&pctrl->lock, flags); + + val = readl(pctrl->regs + g->intr_cfg_reg); + val &= ~BIT(g->intr_enable_bit); +@@ -593,7 +593,7 @@ + + clear_bit(d->hwirq, pctrl->enabled_irqs); + +- spin_unlock_irqrestore(&pctrl->lock, flags); ++ raw_spin_unlock_irqrestore(&pctrl->lock, flags); + } + + static void msm_gpio_irq_unmask(struct irq_data *d) +@@ -606,7 +606,7 @@ + + g = &pctrl->soc->groups[d->hwirq]; + +- spin_lock_irqsave(&pctrl->lock, flags); ++ raw_spin_lock_irqsave(&pctrl->lock, flags); + + val = readl(pctrl->regs + g->intr_status_reg); + val &= ~BIT(g->intr_status_bit); +@@ -618,7 +618,7 @@ + + set_bit(d->hwirq, pctrl->enabled_irqs); + +- spin_unlock_irqrestore(&pctrl->lock, flags); ++ raw_spin_unlock_irqrestore(&pctrl->lock, flags); + } + + static void msm_gpio_irq_ack(struct irq_data *d) +@@ -631,7 +631,7 @@ + + g = &pctrl->soc->groups[d->hwirq]; + +- spin_lock_irqsave(&pctrl->lock, flags); ++ raw_spin_lock_irqsave(&pctrl->lock, flags); + + val = readl(pctrl->regs + g->intr_status_reg); + if (g->intr_ack_high) +@@ -643,7 +643,7 @@ + if (test_bit(d->hwirq, pctrl->dual_edge_irqs)) + msm_gpio_update_dual_edge_pos(pctrl, g, d); + +- spin_unlock_irqrestore(&pctrl->lock, flags); ++ raw_spin_unlock_irqrestore(&pctrl->lock, flags); + } + + static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) +@@ -656,7 +656,7 @@ + + g = &pctrl->soc->groups[d->hwirq]; + +- spin_lock_irqsave(&pctrl->lock, flags); ++ raw_spin_lock_irqsave(&pctrl->lock, flags); + + /* + * For hw without possibility of detecting both edges +@@ -730,7 +730,7 @@ + if (test_bit(d->hwirq, pctrl->dual_edge_irqs)) + msm_gpio_update_dual_edge_pos(pctrl, g, d); + +- spin_unlock_irqrestore(&pctrl->lock, flags); ++ raw_spin_unlock_irqrestore(&pctrl->lock, flags); + + if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH)) + __irq_set_handler_locked(d->irq, handle_level_irq); +@@ -746,11 +746,11 @@ + struct msm_pinctrl *pctrl = to_msm_pinctrl(gc); + unsigned long flags; + +- spin_lock_irqsave(&pctrl->lock, flags); ++ raw_spin_lock_irqsave(&pctrl->lock, flags); + + irq_set_irq_wake(pctrl->irq, on); + +- spin_unlock_irqrestore(&pctrl->lock, flags); ++ raw_spin_unlock_irqrestore(&pctrl->lock, flags); + + return 0; + } +@@ -887,7 +887,7 @@ + pctrl->soc = soc_data; + pctrl->chip = msm_gpio_template; + +- spin_lock_init(&pctrl->lock); ++ raw_spin_lock_init(&pctrl->lock); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + pctrl->regs = devm_ioremap_resource(&pdev->dev, res); +diff -Nur linux-4.1.39.orig/drivers/scsi/fcoe/fcoe.c linux-4.1.39/drivers/scsi/fcoe/fcoe.c +--- linux-4.1.39.orig/drivers/scsi/fcoe/fcoe.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/scsi/fcoe/fcoe.c 2017-04-18 17:56:30.593396355 +0200 +@@ -1287,7 +1287,7 @@ + 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); +@@ -1343,7 +1343,7 @@ + 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 +@@ -1567,11 +1567,11 @@ + 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; + } +@@ -1767,11 +1767,11 @@ + return 0; + } + +- stats = per_cpu_ptr(lport->stats, get_cpu()); ++ stats = per_cpu_ptr(lport->stats, get_cpu_light()); + stats->InvalidCRCCount++; + if (stats->InvalidCRCCount < 5) + printk(KERN_WARNING "fcoe: dropping frame with CRC error\n"); +- put_cpu(); ++ put_cpu_light(); + return -EINVAL; + } + +@@ -1815,7 +1815,7 @@ + */ + hp = (struct fcoe_hdr *) skb_network_header(skb); + +- stats = per_cpu_ptr(lport->stats, get_cpu()); ++ stats = per_cpu_ptr(lport->stats, get_cpu_light()); + if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) { + if (stats->ErrorFrames < 5) + printk(KERN_WARNING "fcoe: FCoE version " +@@ -1847,13 +1847,13 @@ + 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 -Nur linux-4.1.39.orig/drivers/scsi/fcoe/fcoe_ctlr.c linux-4.1.39/drivers/scsi/fcoe/fcoe_ctlr.c +--- linux-4.1.39.orig/drivers/scsi/fcoe/fcoe_ctlr.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/scsi/fcoe/fcoe_ctlr.c 2017-04-18 17:56:30.593396355 +0200 +@@ -831,7 +831,7 @@ + + INIT_LIST_HEAD(&del_list); + +- stats = per_cpu_ptr(fip->lp->stats, get_cpu()); ++ stats = per_cpu_ptr(fip->lp->stats, get_cpu_light()); + + list_for_each_entry_safe(fcf, next, &fip->fcfs, list) { + deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2; +@@ -867,7 +867,7 @@ + sel_time = fcf->time; + } + } +- put_cpu(); ++ put_cpu_light(); + + list_for_each_entry_safe(fcf, next, &del_list, list) { + /* Removes fcf from current list */ +diff -Nur linux-4.1.39.orig/drivers/scsi/libfc/fc_exch.c linux-4.1.39/drivers/scsi/libfc/fc_exch.c +--- linux-4.1.39.orig/drivers/scsi/libfc/fc_exch.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/scsi/libfc/fc_exch.c 2017-04-18 17:56:30.593396355 +0200 +@@ -814,10 +814,10 @@ + } + 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 -Nur linux-4.1.39.orig/drivers/scsi/libsas/sas_ata.c linux-4.1.39/drivers/scsi/libsas/sas_ata.c +--- linux-4.1.39.orig/drivers/scsi/libsas/sas_ata.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/scsi/libsas/sas_ata.c 2017-04-18 17:56:30.593396355 +0200 +@@ -190,7 +190,7 @@ + /* 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 */ +@@ -255,7 +255,7 @@ + + out: + spin_lock(ap->lock); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return ret; + } + +diff -Nur linux-4.1.39.orig/drivers/scsi/qla2xxx/qla_inline.h linux-4.1.39/drivers/scsi/qla2xxx/qla_inline.h +--- linux-4.1.39.orig/drivers/scsi/qla2xxx/qla_inline.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/scsi/qla2xxx/qla_inline.h 2017-04-18 17:56:30.593396355 +0200 +@@ -59,12 +59,12 @@ + { + unsigned long flags; + struct qla_hw_data *ha = rsp->hw; +- local_irq_save(flags); ++ local_irq_save_nort(flags); + if (IS_P3P_TYPE(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 -Nur linux-4.1.39.orig/drivers/thermal/x86_pkg_temp_thermal.c linux-4.1.39/drivers/thermal/x86_pkg_temp_thermal.c +--- linux-4.1.39.orig/drivers/thermal/x86_pkg_temp_thermal.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/thermal/x86_pkg_temp_thermal.c 2017-04-18 17:56:30.593396355 +0200 +@@ -29,6 +29,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -352,7 +353,7 @@ + } + } + +-static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val) ++static void platform_thermal_notify_work(struct swork_event *event) + { + unsigned long flags; + int cpu = smp_processor_id(); +@@ -369,7 +370,7 @@ + pkg_work_scheduled[phy_id]) { + disable_pkg_thres_interrupt(); + spin_unlock_irqrestore(&pkg_work_lock, flags); +- return -EINVAL; ++ return; + } + pkg_work_scheduled[phy_id] = 1; + spin_unlock_irqrestore(&pkg_work_lock, flags); +@@ -378,9 +379,48 @@ + schedule_delayed_work_on(cpu, + &per_cpu(pkg_temp_thermal_threshold_work, cpu), + msecs_to_jiffies(notify_delay_ms)); ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static struct swork_event notify_work; ++ ++static int thermal_notify_work_init(void) ++{ ++ int err; ++ ++ err = swork_get(); ++ if (err) ++ return err; ++ ++ INIT_SWORK(¬ify_work, platform_thermal_notify_work); + return 0; + } + ++static void thermal_notify_work_cleanup(void) ++{ ++ swork_put(); ++} ++ ++static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val) ++{ ++ swork_queue(¬ify_work); ++ return 0; ++} ++ ++#else /* !CONFIG_PREEMPT_RT_FULL */ ++ ++static int thermal_notify_work_init(void) { return 0; } ++ ++static void thermal_notify_work_cleanup(void) { } ++ ++static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val) ++{ ++ platform_thermal_notify_work(NULL); ++ ++ return 0; ++} ++#endif /* CONFIG_PREEMPT_RT_FULL */ ++ + static int find_siblings_cpu(int cpu) + { + int i; +@@ -584,6 +624,9 @@ + if (!x86_match_cpu(pkg_temp_thermal_ids)) + return -ENODEV; + ++ if (!thermal_notify_work_init()) ++ return -ENODEV; ++ + spin_lock_init(&pkg_work_lock); + platform_thermal_package_notify = + pkg_temp_thermal_platform_thermal_notify; +@@ -608,7 +651,7 @@ + kfree(pkg_work_scheduled); + platform_thermal_package_notify = NULL; + platform_thermal_package_rate_control = NULL; +- ++ thermal_notify_work_cleanup(); + return -ENODEV; + } + +@@ -633,6 +676,7 @@ + mutex_unlock(&phy_dev_list_mutex); + platform_thermal_package_notify = NULL; + platform_thermal_package_rate_control = NULL; ++ thermal_notify_work_cleanup(); + for_each_online_cpu(i) + cancel_delayed_work_sync( + &per_cpu(pkg_temp_thermal_threshold_work, i)); +diff -Nur linux-4.1.39.orig/drivers/tty/serial/8250/8250_core.c linux-4.1.39/drivers/tty/serial/8250/8250_core.c +--- linux-4.1.39.orig/drivers/tty/serial/8250/8250_core.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/tty/serial/8250/8250_core.c 2017-04-18 17:56:30.593396355 +0200 +@@ -36,6 +36,7 @@ + #include + #include + #include ++#include + #include + #include + #ifdef CONFIG_SPARC +@@ -80,7 +81,16 @@ + #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) + +@@ -3366,7 +3376,7 @@ + + if (port->sysrq) + locked = 0; +- else if (oops_in_progress) ++ else if (oops_in_progress || in_kdb_printk()) + locked = spin_trylock_irqsave(&port->lock, flags); + else + spin_lock_irqsave(&port->lock, flags); +diff -Nur linux-4.1.39.orig/drivers/tty/serial/amba-pl011.c linux-4.1.39/drivers/tty/serial/amba-pl011.c +--- linux-4.1.39.orig/drivers/tty/serial/amba-pl011.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/tty/serial/amba-pl011.c 2017-04-18 17:56:30.597396510 +0200 +@@ -2000,13 +2000,19 @@ + + 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 +@@ -2028,8 +2034,7 @@ + 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 -Nur linux-4.1.39.orig/drivers/tty/serial/omap-serial.c linux-4.1.39/drivers/tty/serial/omap-serial.c +--- linux-4.1.39.orig/drivers/tty/serial/omap-serial.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/tty/serial/omap-serial.c 2017-04-18 17:56:30.597396510 +0200 +@@ -1282,13 +1282,10 @@ + + pm_runtime_get_sync(up->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 +@@ -1317,8 +1314,7 @@ + pm_runtime_mark_last_busy(up->dev); + pm_runtime_put_autosuspend(up->dev); + if (locked) +- spin_unlock(&up->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&up->port.lock, flags); + } + + static int __init +diff -Nur linux-4.1.39.orig/drivers/usb/core/hcd.c linux-4.1.39/drivers/usb/core/hcd.c +--- linux-4.1.39.orig/drivers/usb/core/hcd.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/usb/core/hcd.c 2017-04-18 17:56:30.597396510 +0200 +@@ -1684,9 +1684,9 @@ + * and no one may trigger the above deadlock situation when + * running complete() in tasklet. + */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + urb->complete(urb); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + usb_anchor_resume_wakeups(anchor); + atomic_dec(&urb->use_count); +diff -Nur linux-4.1.39.orig/drivers/usb/gadget/function/f_fs.c linux-4.1.39/drivers/usb/gadget/function/f_fs.c +--- linux-4.1.39.orig/drivers/usb/gadget/function/f_fs.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/usb/gadget/function/f_fs.c 2017-04-18 17:56:30.597396510 +0200 +@@ -1404,7 +1404,7 @@ + pr_info("%s(): freeing\n", __func__); + ffs_data_clear(ffs); + BUG_ON(waitqueue_active(&ffs->ev.waitq) || +- waitqueue_active(&ffs->ep0req_completion.wait)); ++ swaitqueue_active(&ffs->ep0req_completion.wait)); + kfree(ffs->dev_name); + kfree(ffs); + } +diff -Nur linux-4.1.39.orig/drivers/usb/gadget/legacy/inode.c linux-4.1.39/drivers/usb/gadget/legacy/inode.c +--- linux-4.1.39.orig/drivers/usb/gadget/legacy/inode.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/usb/gadget/legacy/inode.c 2017-04-18 17:56:30.597396510 +0200 +@@ -345,7 +345,7 @@ + spin_unlock_irq (&epdata->dev->lock); + + if (likely (value == 0)) { +- value = wait_event_interruptible (done.wait, done.done); ++ value = swait_event_interruptible (done.wait, done.done); + if (value != 0) { + spin_lock_irq (&epdata->dev->lock); + if (likely (epdata->ep != NULL)) { +@@ -354,7 +354,7 @@ + usb_ep_dequeue (epdata->ep, epdata->req); + spin_unlock_irq (&epdata->dev->lock); + +- wait_event (done.wait, done.done); ++ swait_event (done.wait, done.done); + if (epdata->status == -ECONNRESET) + epdata->status = -EINTR; + } else { +diff -Nur linux-4.1.39.orig/drivers/usb/gadget/udc/atmel_usba_udc.c linux-4.1.39/drivers/usb/gadget/udc/atmel_usba_udc.c +--- linux-4.1.39.orig/drivers/usb/gadget/udc/atmel_usba_udc.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/usb/gadget/udc/atmel_usba_udc.c 2017-04-18 17:56:30.597396510 +0200 +@@ -17,7 +17,9 @@ + #include + #include + #include ++#include + #include ++#include + #include + #include + #include +@@ -1889,20 +1891,15 @@ + #ifdef CONFIG_OF + static void at91sam9rl_toggle_bias(struct usba_udc *udc, int is_on) + { +- unsigned int uckr = at91_pmc_read(AT91_CKGR_UCKR); +- +- if (is_on) +- at91_pmc_write(AT91_CKGR_UCKR, uckr | AT91_PMC_BIASEN); +- else +- at91_pmc_write(AT91_CKGR_UCKR, uckr & ~(AT91_PMC_BIASEN)); ++ regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN, ++ is_on ? AT91_PMC_BIASEN : 0); + } + + static void at91sam9g45_pulse_bias(struct usba_udc *udc) + { +- unsigned int uckr = at91_pmc_read(AT91_CKGR_UCKR); +- +- at91_pmc_write(AT91_CKGR_UCKR, uckr & ~(AT91_PMC_BIASEN)); +- at91_pmc_write(AT91_CKGR_UCKR, uckr | AT91_PMC_BIASEN); ++ regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN, 0); ++ regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN, ++ AT91_PMC_BIASEN); + } + + static const struct usba_udc_errata at91sam9rl_errata = { +@@ -1939,6 +1936,9 @@ + return ERR_PTR(-EINVAL); + + udc->errata = match->data; ++ udc->pmc = syscon_regmap_lookup_by_compatible("atmel,at91sam9g45-pmc"); ++ if (udc->errata && IS_ERR(udc->pmc)) ++ return ERR_CAST(udc->pmc); + + udc->num_ep = 0; + +diff -Nur linux-4.1.39.orig/drivers/usb/gadget/udc/atmel_usba_udc.h linux-4.1.39/drivers/usb/gadget/udc/atmel_usba_udc.h +--- linux-4.1.39.orig/drivers/usb/gadget/udc/atmel_usba_udc.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/drivers/usb/gadget/udc/atmel_usba_udc.h 2017-04-18 17:56:30.597396510 +0200 +@@ -354,6 +354,8 @@ + struct dentry *debugfs_root; + struct dentry *debugfs_regs; + #endif ++ ++ struct regmap *pmc; + }; + + static inline struct usba_ep *to_usba_ep(struct usb_ep *ep) +diff -Nur linux-4.1.39.orig/fs/aio.c linux-4.1.39/fs/aio.c +--- linux-4.1.39.orig/fs/aio.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/aio.c 2017-04-18 17:56:30.597396510 +0200 +@@ -40,6 +40,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -115,7 +116,7 @@ + struct page **ring_pages; + long nr_pages; + +- struct work_struct free_work; ++ struct swork_event free_work; + + /* + * signals when all in-flight requests are done +@@ -253,6 +254,7 @@ + .mount = aio_mount, + .kill_sb = kill_anon_super, + }; ++ BUG_ON(swork_get()); + aio_mnt = kern_mount(&aio_fs); + if (IS_ERR(aio_mnt)) + panic("Failed to create aio fs mount."); +@@ -559,9 +561,9 @@ + return cancel(&kiocb->common); + } + +-static void free_ioctx(struct work_struct *work) ++static void free_ioctx(struct swork_event *sev) + { +- struct kioctx *ctx = container_of(work, struct kioctx, free_work); ++ struct kioctx *ctx = container_of(sev, struct kioctx, free_work); + + pr_debug("freeing %p\n", ctx); + +@@ -580,8 +582,8 @@ + if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count)) + complete(&ctx->rq_wait->comp); + +- INIT_WORK(&ctx->free_work, free_ioctx); +- schedule_work(&ctx->free_work); ++ INIT_SWORK(&ctx->free_work, free_ioctx); ++ swork_queue(&ctx->free_work); + } + + /* +@@ -589,9 +591,9 @@ + * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - + * now it's safe to cancel any that need to be. + */ +-static void free_ioctx_users(struct percpu_ref *ref) ++static void free_ioctx_users_work(struct swork_event *sev) + { +- struct kioctx *ctx = container_of(ref, struct kioctx, users); ++ struct kioctx *ctx = container_of(sev, struct kioctx, free_work); + struct aio_kiocb *req; + + spin_lock_irq(&ctx->ctx_lock); +@@ -610,6 +612,14 @@ + percpu_ref_put(&ctx->reqs); + } + ++static void free_ioctx_users(struct percpu_ref *ref) ++{ ++ struct kioctx *ctx = container_of(ref, struct kioctx, users); ++ ++ INIT_SWORK(&ctx->free_work, free_ioctx_users_work); ++ swork_queue(&ctx->free_work); ++} ++ + static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) + { + unsigned i, new_nr; +diff -Nur linux-4.1.39.orig/fs/autofs4/autofs_i.h linux-4.1.39/fs/autofs4/autofs_i.h +--- linux-4.1.39.orig/fs/autofs4/autofs_i.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/autofs4/autofs_i.h 2017-04-18 17:56:30.597396510 +0200 +@@ -34,6 +34,7 @@ + #include + #include + #include ++#include + #include + #include + +diff -Nur linux-4.1.39.orig/fs/autofs4/expire.c linux-4.1.39/fs/autofs4/expire.c +--- linux-4.1.39.orig/fs/autofs4/expire.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/autofs4/expire.c 2017-04-18 17:56:30.597396510 +0200 +@@ -150,7 +150,7 @@ + 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 -Nur linux-4.1.39.orig/fs/buffer.c linux-4.1.39/fs/buffer.c +--- linux-4.1.39.orig/fs/buffer.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/buffer.c 2017-04-18 17:56:30.597396510 +0200 +@@ -301,8 +301,7 @@ + * 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; +@@ -315,8 +314,7 @@ + } + 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 +@@ -328,9 +326,7 @@ + return; + + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + + /* +@@ -358,8 +354,7 @@ + } + + 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); +@@ -371,15 +366,12 @@ + } + 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); + +@@ -3325,6 +3317,7 @@ + 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 -Nur linux-4.1.39.orig/fs/dcache.c linux-4.1.39/fs/dcache.c +--- linux-4.1.39.orig/fs/dcache.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/dcache.c 2017-04-18 17:56:30.597396510 +0200 +@@ -19,6 +19,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -747,6 +748,8 @@ + */ + void dput(struct dentry *dentry) + { ++ struct dentry *parent; ++ + if (unlikely(!dentry)) + return; + +@@ -783,9 +786,18 @@ + return; + + kill_it: +- dentry = dentry_kill(dentry); +- if (dentry) { +- cond_resched(); ++ parent = dentry_kill(dentry); ++ if (parent) { ++ int r; ++ ++ if (parent == dentry) { ++ /* the task with the highest priority won't schedule */ ++ r = cond_resched(); ++ if (!r) ++ cpu_chill(); ++ } else { ++ dentry = parent; ++ } + goto repeat; + } + } +@@ -2394,7 +2406,7 @@ + if (dentry->d_lockref.count == 1) { + if (!spin_trylock(&inode->i_lock)) { + spin_unlock(&dentry->d_lock); +- cpu_relax(); ++ cpu_chill(); + goto again; + } + dentry->d_flags &= ~DCACHE_CANT_MOUNT; +diff -Nur linux-4.1.39.orig/fs/eventpoll.c linux-4.1.39/fs/eventpoll.c +--- linux-4.1.39.orig/fs/eventpoll.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/eventpoll.c 2017-04-18 17:56:30.601396665 +0200 +@@ -505,12 +505,12 @@ + */ + 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 -Nur linux-4.1.39.orig/fs/exec.c linux-4.1.39/fs/exec.c +--- linux-4.1.39.orig/fs/exec.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/exec.c 2017-04-18 17:56:30.601396665 +0200 +@@ -859,12 +859,14 @@ + } + } + task_lock(tsk); ++ preempt_disable_rt(); + active_mm = tsk->active_mm; + tsk->mm = mm; + tsk->active_mm = mm; + activate_mm(active_mm, mm); + tsk->mm->vmacache_seqnum = 0; + vmacache_flush(tsk); ++ preempt_enable_rt(); + task_unlock(tsk); + if (old_mm) { + up_read(&old_mm->mmap_sem); +diff -Nur linux-4.1.39.orig/fs/f2fs/f2fs.h linux-4.1.39/fs/f2fs/f2fs.h +--- linux-4.1.39.orig/fs/f2fs/f2fs.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/f2fs/f2fs.h 2017-04-18 17:56:30.601396665 +0200 +@@ -22,7 +22,6 @@ + + #ifdef CONFIG_F2FS_CHECK_FS + #define f2fs_bug_on(sbi, condition) BUG_ON(condition) +-#define f2fs_down_write(x, y) down_write_nest_lock(x, y) + #else + #define f2fs_bug_on(sbi, condition) \ + do { \ +@@ -31,7 +30,6 @@ + set_sbi_flag(sbi, SBI_NEED_FSCK); \ + } \ + } while (0) +-#define f2fs_down_write(x, y) down_write(x) + #endif + + /* +@@ -838,7 +836,7 @@ + + static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) + { +- f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex); ++ down_write(&sbi->cp_rwsem); + } + + static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) +diff -Nur linux-4.1.39.orig/fs/jbd/checkpoint.c linux-4.1.39/fs/jbd/checkpoint.c +--- linux-4.1.39.orig/fs/jbd/checkpoint.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/jbd/checkpoint.c 2017-04-18 17:56:30.601396665 +0200 +@@ -129,6 +129,8 @@ + 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 -Nur linux-4.1.39.orig/fs/jbd2/checkpoint.c linux-4.1.39/fs/jbd2/checkpoint.c +--- linux-4.1.39.orig/fs/jbd2/checkpoint.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/jbd2/checkpoint.c 2017-04-18 17:56:30.601396665 +0200 +@@ -116,6 +116,8 @@ + nblocks = jbd2_space_needed(journal); + while (jbd2_log_space_left(journal) < nblocks) { + write_unlock(&journal->j_state_lock); ++ if (current->plug) ++ io_schedule(); + mutex_lock(&journal->j_checkpoint_mutex); + + /* +diff -Nur linux-4.1.39.orig/fs/namespace.c linux-4.1.39/fs/namespace.c +--- linux-4.1.39.orig/fs/namespace.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/namespace.c 2017-04-18 17:56:30.601396665 +0200 +@@ -14,6 +14,7 @@ + #include + #include + #include ++#include + #include + #include + #include /* init_rootfs */ +@@ -356,8 +357,11 @@ + * incremented count after it has set MNT_WRITE_HOLD. + */ + smp_mb(); +- while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) +- cpu_relax(); ++ while (ACCESS_ONCE(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 -Nur linux-4.1.39.orig/fs/ntfs/aops.c linux-4.1.39/fs/ntfs/aops.c +--- linux-4.1.39.orig/fs/ntfs/aops.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/ntfs/aops.c 2017-04-18 17:56:30.601396665 +0200 +@@ -107,8 +107,7 @@ + "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; +@@ -123,8 +122,7 @@ + } + 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 +@@ -145,13 +143,13 @@ + 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); +@@ -159,9 +157,7 @@ + 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 -Nur linux-4.1.39.orig/fs/timerfd.c linux-4.1.39/fs/timerfd.c +--- linux-4.1.39.orig/fs/timerfd.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/timerfd.c 2017-04-18 17:56:30.601396665 +0200 +@@ -450,7 +450,10 @@ + break; + } + spin_unlock_irq(&ctx->wqh.lock); +- cpu_relax(); ++ if (isalarm(ctx)) ++ hrtimer_wait_for_timer(&ctx->t.alarm.timer); ++ else ++ hrtimer_wait_for_timer(&ctx->t.tmr); + } + + /* +diff -Nur linux-4.1.39.orig/fs/xfs/xfs_inode.c linux-4.1.39/fs/xfs/xfs_inode.c +--- linux-4.1.39.orig/fs/xfs/xfs_inode.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/xfs/xfs_inode.c 2017-04-18 17:56:30.601396665 +0200 +@@ -164,7 +164,7 @@ + (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)); + ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) != + (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); +- ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0); ++ ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0); + + if (lock_flags & XFS_IOLOCK_EXCL) + mrupdate_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags)); +@@ -212,7 +212,7 @@ + (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)); + ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) != + (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); +- ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0); ++ ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0); + + if (lock_flags & XFS_IOLOCK_EXCL) { + if (!mrtryupdate(&ip->i_iolock)) +@@ -281,7 +281,7 @@ + (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)); + ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) != + (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); +- ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0); ++ ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0); + ASSERT(lock_flags != 0); + + if (lock_flags & XFS_IOLOCK_EXCL) +@@ -364,30 +364,38 @@ + + /* + * Bump the subclass so xfs_lock_inodes() acquires each lock with a different +- * value. This shouldn't be called for page fault locking, but we also need to +- * ensure we don't overrun the number of lockdep subclasses for the iolock or +- * mmaplock as that is limited to 12 by the mmap lock lockdep annotations. ++ * value. This can be called for any type of inode lock combination, including ++ * parent locking. Care must be taken to ensure we don't overrun the subclass ++ * storage fields in the class mask we build. + */ + static inline int + xfs_lock_inumorder(int lock_mode, int subclass) + { ++ int class = 0; ++ ++ ASSERT(!(lock_mode & (XFS_ILOCK_PARENT | XFS_ILOCK_RTBITMAP | ++ XFS_ILOCK_RTSUM))); ++ + if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) { +- ASSERT(subclass + XFS_LOCK_INUMORDER < +- (1 << (XFS_MMAPLOCK_SHIFT - XFS_IOLOCK_SHIFT))); +- lock_mode |= (subclass + XFS_LOCK_INUMORDER) << XFS_IOLOCK_SHIFT; ++ ASSERT(subclass <= XFS_IOLOCK_MAX_SUBCLASS); ++ ASSERT(subclass + XFS_IOLOCK_PARENT_VAL < ++ MAX_LOCKDEP_SUBCLASSES); ++ class += subclass << XFS_IOLOCK_SHIFT; ++ if (lock_mode & XFS_IOLOCK_PARENT) ++ class += XFS_IOLOCK_PARENT_VAL << XFS_IOLOCK_SHIFT; + } + + if (lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) { +- ASSERT(subclass + XFS_LOCK_INUMORDER < +- (1 << (XFS_ILOCK_SHIFT - XFS_MMAPLOCK_SHIFT))); +- lock_mode |= (subclass + XFS_LOCK_INUMORDER) << +- XFS_MMAPLOCK_SHIFT; ++ ASSERT(subclass <= XFS_MMAPLOCK_MAX_SUBCLASS); ++ class += subclass << XFS_MMAPLOCK_SHIFT; + } + +- if (lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) +- lock_mode |= (subclass + XFS_LOCK_INUMORDER) << XFS_ILOCK_SHIFT; ++ if (lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) { ++ ASSERT(subclass <= XFS_ILOCK_MAX_SUBCLASS); ++ class += subclass << XFS_ILOCK_SHIFT; ++ } + +- return lock_mode; ++ return (lock_mode & ~XFS_LOCK_SUBCLASS_MASK) | class; + } + + /* +@@ -399,6 +407,11 @@ + * transaction (such as truncate). This can result in deadlock since the long + * running trans might need to wait for the inode we just locked in order to + * push the tail and free space in the log. ++ * ++ * xfs_lock_inodes() can only be used to lock one type of lock at a time - ++ * the iolock, the mmaplock or the ilock, but not more than one at a time. If we ++ * lock more than one at a time, lockdep will report false positives saying we ++ * have violated locking orders. + */ + void + xfs_lock_inodes( +@@ -409,8 +422,29 @@ + int attempts = 0, i, j, try_lock; + xfs_log_item_t *lp; + +- /* currently supports between 2 and 5 inodes */ ++ /* ++ * Currently supports between 2 and 5 inodes with exclusive locking. We ++ * support an arbitrary depth of locking here, but absolute limits on ++ * inodes depend on the the type of locking and the limits placed by ++ * lockdep annotations in xfs_lock_inumorder. These are all checked by ++ * the asserts. ++ */ + ASSERT(ips && inodes >= 2 && inodes <= 5); ++ ASSERT(lock_mode & (XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL | ++ XFS_ILOCK_EXCL)); ++ ASSERT(!(lock_mode & (XFS_IOLOCK_SHARED | XFS_MMAPLOCK_SHARED | ++ XFS_ILOCK_SHARED))); ++ ASSERT(!(lock_mode & XFS_IOLOCK_EXCL) || ++ inodes <= XFS_IOLOCK_MAX_SUBCLASS + 1); ++ ASSERT(!(lock_mode & XFS_MMAPLOCK_EXCL) || ++ inodes <= XFS_MMAPLOCK_MAX_SUBCLASS + 1); ++ ASSERT(!(lock_mode & XFS_ILOCK_EXCL) || ++ inodes <= XFS_ILOCK_MAX_SUBCLASS + 1); ++ ++ if (lock_mode & XFS_IOLOCK_EXCL) { ++ ASSERT(!(lock_mode & (XFS_MMAPLOCK_EXCL | XFS_ILOCK_EXCL))); ++ } else if (lock_mode & XFS_MMAPLOCK_EXCL) ++ ASSERT(!(lock_mode & XFS_ILOCK_EXCL)); + + try_lock = 0; + i = 0; +diff -Nur linux-4.1.39.orig/fs/xfs/xfs_inode.h linux-4.1.39/fs/xfs/xfs_inode.h +--- linux-4.1.39.orig/fs/xfs/xfs_inode.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/fs/xfs/xfs_inode.h 2017-04-18 17:56:30.601396665 +0200 +@@ -284,9 +284,9 @@ + * Flags for lockdep annotations. + * + * XFS_LOCK_PARENT - for directory operations that require locking a +- * parent directory inode and a child entry inode. The parent gets locked +- * with this flag so it gets a lockdep subclass of 1 and the child entry +- * lock will have a lockdep subclass of 0. ++ * parent directory inode and a child entry inode. IOLOCK requires nesting, ++ * MMAPLOCK does not support this class, ILOCK requires a single subclass ++ * to differentiate parent from child. + * + * XFS_LOCK_RTBITMAP/XFS_LOCK_RTSUM - the realtime device bitmap and summary + * inodes do not participate in the normal lock order, and thus have their +@@ -295,30 +295,63 @@ + * XFS_LOCK_INUMORDER - for locking several inodes at the some time + * with xfs_lock_inodes(). This flag is used as the starting subclass + * and each subsequent lock acquired will increment the subclass by one. +- * So the first lock acquired will have a lockdep subclass of 4, the +- * second lock will have a lockdep subclass of 5, and so on. It is +- * the responsibility of the class builder to shift this to the correct +- * portion of the lock_mode lockdep mask. ++ * However, MAX_LOCKDEP_SUBCLASSES == 8, which means we are greatly ++ * limited to the subclasses we can represent via nesting. We need at least ++ * 5 inodes nest depth for the ILOCK through rename, and we also have to support ++ * XFS_ILOCK_PARENT, which gives 6 subclasses. Then we have XFS_ILOCK_RTBITMAP ++ * and XFS_ILOCK_RTSUM, which are another 2 unique subclasses, so that's all ++ * 8 subclasses supported by lockdep. ++ * ++ * This also means we have to number the sub-classes in the lowest bits of ++ * the mask we keep, and we have to ensure we never exceed 3 bits of lockdep ++ * mask and we can't use bit-masking to build the subclasses. What a mess. ++ * ++ * Bit layout: ++ * ++ * Bit Lock Region ++ * 16-19 XFS_IOLOCK_SHIFT dependencies ++ * 20-23 XFS_MMAPLOCK_SHIFT dependencies ++ * 24-31 XFS_ILOCK_SHIFT dependencies ++ * ++ * IOLOCK values ++ * ++ * 0-3 subclass value ++ * 4-7 PARENT subclass values ++ * ++ * MMAPLOCK values ++ * ++ * 0-3 subclass value ++ * 4-7 unused ++ * ++ * ILOCK values ++ * 0-4 subclass values ++ * 5 PARENT subclass (not nestable) ++ * 6 RTBITMAP subclass (not nestable) ++ * 7 RTSUM subclass (not nestable) ++ * + */ +-#define XFS_LOCK_PARENT 1 +-#define XFS_LOCK_RTBITMAP 2 +-#define XFS_LOCK_RTSUM 3 +-#define XFS_LOCK_INUMORDER 4 +- +-#define XFS_IOLOCK_SHIFT 16 +-#define XFS_IOLOCK_PARENT (XFS_LOCK_PARENT << XFS_IOLOCK_SHIFT) ++#define XFS_IOLOCK_SHIFT 16 ++#define XFS_IOLOCK_PARENT_VAL 4 ++#define XFS_IOLOCK_MAX_SUBCLASS (XFS_IOLOCK_PARENT_VAL - 1) ++#define XFS_IOLOCK_DEP_MASK 0x000f0000 ++#define XFS_IOLOCK_PARENT (XFS_IOLOCK_PARENT_VAL << XFS_IOLOCK_SHIFT) + +-#define XFS_MMAPLOCK_SHIFT 20 ++#define XFS_MMAPLOCK_SHIFT 20 ++#define XFS_MMAPLOCK_NUMORDER 0 ++#define XFS_MMAPLOCK_MAX_SUBCLASS 3 ++#define XFS_MMAPLOCK_DEP_MASK 0x00f00000 + +-#define XFS_ILOCK_SHIFT 24 +-#define XFS_ILOCK_PARENT (XFS_LOCK_PARENT << XFS_ILOCK_SHIFT) +-#define XFS_ILOCK_RTBITMAP (XFS_LOCK_RTBITMAP << XFS_ILOCK_SHIFT) +-#define XFS_ILOCK_RTSUM (XFS_LOCK_RTSUM << XFS_ILOCK_SHIFT) ++#define XFS_ILOCK_SHIFT 24 ++#define XFS_ILOCK_PARENT_VAL 5 ++#define XFS_ILOCK_MAX_SUBCLASS (XFS_ILOCK_PARENT_VAL - 1) ++#define XFS_ILOCK_RTBITMAP_VAL 6 ++#define XFS_ILOCK_RTSUM_VAL 7 ++#define XFS_ILOCK_DEP_MASK 0xff000000 ++#define XFS_ILOCK_PARENT (XFS_ILOCK_PARENT_VAL << XFS_ILOCK_SHIFT) ++#define XFS_ILOCK_RTBITMAP (XFS_ILOCK_RTBITMAP_VAL << XFS_ILOCK_SHIFT) ++#define XFS_ILOCK_RTSUM (XFS_ILOCK_RTSUM_VAL << XFS_ILOCK_SHIFT) + +-#define XFS_IOLOCK_DEP_MASK 0x000f0000 +-#define XFS_MMAPLOCK_DEP_MASK 0x00f00000 +-#define XFS_ILOCK_DEP_MASK 0xff000000 +-#define XFS_LOCK_DEP_MASK (XFS_IOLOCK_DEP_MASK | \ ++#define XFS_LOCK_SUBCLASS_MASK (XFS_IOLOCK_DEP_MASK | \ + XFS_MMAPLOCK_DEP_MASK | \ + XFS_ILOCK_DEP_MASK) + +diff -Nur linux-4.1.39.orig/include/acpi/platform/aclinux.h linux-4.1.39/include/acpi/platform/aclinux.h +--- linux-4.1.39.orig/include/acpi/platform/aclinux.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/acpi/platform/aclinux.h 2017-04-18 17:56:30.601396665 +0200 +@@ -123,6 +123,7 @@ + + #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 + + /* Use native linux version of acpi_os_allocate_zeroed */ +@@ -141,6 +142,20 @@ + #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_thread_id + #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock + ++#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) ++ ++ + /* + * OSL interfaces used by debugger/disassembler + */ +diff -Nur linux-4.1.39.orig/include/asm-generic/bug.h linux-4.1.39/include/asm-generic/bug.h +--- linux-4.1.39.orig/include/asm-generic/bug.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/asm-generic/bug.h 2017-04-18 17:56:30.601396665 +0200 +@@ -206,6 +206,20 @@ + # 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 /* __ASSEMBLY__ */ + + #endif +diff -Nur linux-4.1.39.orig/include/asm-generic/futex.h linux-4.1.39/include/asm-generic/futex.h +--- linux-4.1.39.orig/include/asm-generic/futex.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/asm-generic/futex.h 2017-04-18 17:56:30.601396665 +0200 +@@ -8,8 +8,7 @@ + #ifndef CONFIG_SMP + /* + * The following implementation only for uniprocessor machines. +- * For UP, it's relies on the fact that pagefault_disable() also disables +- * preemption to ensure mutual exclusion. ++ * It relies on preempt_disable() ensuring mutual exclusion. + * + */ + +@@ -38,6 +37,7 @@ + if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) + oparg = 1 << oparg; + ++ preempt_disable(); + pagefault_disable(); + + ret = -EFAULT; +@@ -72,6 +72,7 @@ + + out_pagefault_enable: + pagefault_enable(); ++ preempt_enable(); + + if (ret == 0) { + switch (cmp) { +@@ -106,6 +107,7 @@ + { + u32 val; + ++ preempt_disable(); + if (unlikely(get_user(val, uaddr) != 0)) + return -EFAULT; + +@@ -113,6 +115,7 @@ + return -EFAULT; + + *uval = val; ++ preempt_enable(); + + return 0; + } +diff -Nur linux-4.1.39.orig/include/asm-generic/preempt.h linux-4.1.39/include/asm-generic/preempt.h +--- linux-4.1.39.orig/include/asm-generic/preempt.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/asm-generic/preempt.h 2017-04-18 17:56:30.601396665 +0200 +@@ -7,10 +7,10 @@ + + static __always_inline int preempt_count(void) + { +- return current_thread_info()->preempt_count; ++ return READ_ONCE(current_thread_info()->preempt_count); + } + +-static __always_inline int *preempt_count_ptr(void) ++static __always_inline volatile int *preempt_count_ptr(void) + { + return ¤t_thread_info()->preempt_count; + } +diff -Nur linux-4.1.39.orig/include/linux/blkdev.h linux-4.1.39/include/linux/blkdev.h +--- linux-4.1.39.orig/include/linux/blkdev.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/blkdev.h 2017-04-18 17:56:30.601396665 +0200 +@@ -101,6 +101,7 @@ + struct list_head queuelist; + union { + struct call_single_data csd; ++ struct work_struct work; + unsigned long fifo_time; + }; + +@@ -482,7 +483,7 @@ + struct throtl_data *td; + #endif + struct rcu_head rcu_head; +- wait_queue_head_t mq_freeze_wq; ++ struct swait_head mq_freeze_wq; + struct percpu_ref mq_usage_counter; + struct list_head all_q_node; + +diff -Nur linux-4.1.39.orig/include/linux/blk-mq.h linux-4.1.39/include/linux/blk-mq.h +--- linux-4.1.39.orig/include/linux/blk-mq.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/blk-mq.h 2017-04-18 17:56:30.601396665 +0200 +@@ -202,6 +202,7 @@ + + struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index); + struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int); ++void __blk_mq_complete_request_remote_work(struct work_struct *work); + + int blk_mq_request_started(struct request *rq); + void blk_mq_start_request(struct request *rq); +diff -Nur linux-4.1.39.orig/include/linux/bottom_half.h linux-4.1.39/include/linux/bottom_half.h +--- linux-4.1.39.orig/include/linux/bottom_half.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/bottom_half.h 2017-04-18 17:56:30.601396665 +0200 +@@ -4,6 +4,39 @@ + #include + #include + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++extern void __local_bh_disable(void); ++extern void _local_bh_enable(void); ++extern void __local_bh_enable(void); ++ ++static inline void local_bh_disable(void) ++{ ++ __local_bh_disable(); ++} ++ ++static inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) ++{ ++ __local_bh_disable(); ++} ++ ++static inline void local_bh_enable(void) ++{ ++ __local_bh_enable(); ++} ++ ++static inline void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) ++{ ++ __local_bh_enable(); ++} ++ ++static inline void local_bh_enable_ip(unsigned long ip) ++{ ++ __local_bh_enable(); ++} ++ ++#else ++ + #ifdef CONFIG_TRACE_IRQFLAGS + extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); + #else +@@ -31,5 +64,6 @@ + { + __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); + } ++#endif + + #endif /* _LINUX_BH_H */ +diff -Nur linux-4.1.39.orig/include/linux/buffer_head.h linux-4.1.39/include/linux/buffer_head.h +--- linux-4.1.39.orig/include/linux/buffer_head.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/buffer_head.h 2017-04-18 17:56:30.601396665 +0200 +@@ -75,8 +75,52 @@ + 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 -Nur linux-4.1.39.orig/include/linux/cgroup-defs.h linux-4.1.39/include/linux/cgroup-defs.h +--- linux-4.1.39.orig/include/linux/cgroup-defs.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/cgroup-defs.h 2017-04-18 17:56:30.601396665 +0200 +@@ -124,6 +124,7 @@ + /* percpu_ref killing and RCU release */ + struct rcu_head rcu_head; + struct work_struct destroy_work; ++ struct swork_event destroy_swork; + }; + + /* +diff -Nur linux-4.1.39.orig/include/linux/cgroup.h linux-4.1.39/include/linux/cgroup.h +--- linux-4.1.39.orig/include/linux/cgroup.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/cgroup.h 2017-04-18 17:56:30.605396820 +0200 +@@ -17,6 +17,8 @@ + #include + #include + #include ++#include ++#include + + #include + +diff -Nur linux-4.1.39.orig/include/linux/completion.h linux-4.1.39/include/linux/completion.h +--- linux-4.1.39.orig/include/linux/completion.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/completion.h 2017-04-18 17:56:30.605396820 +0200 +@@ -7,8 +7,7 @@ + * Atomic wait-for-completion handler data structures. + * See kernel/sched/completion.c for details. + */ +- +-#include ++#include + + /* + * struct completion - structure used to maintain state for a "completion" +@@ -24,11 +23,11 @@ + */ + struct completion { + unsigned int done; +- wait_queue_head_t wait; ++ struct swait_head wait; + }; + + #define COMPLETION_INITIALIZER(work) \ +- { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } ++ { 0, SWAIT_HEAD_INITIALIZER((work).wait) } + + #define COMPLETION_INITIALIZER_ONSTACK(work) \ + ({ init_completion(&work); work; }) +@@ -73,7 +72,7 @@ + static inline void init_completion(struct completion *x) + { + x->done = 0; +- init_waitqueue_head(&x->wait); ++ init_swait_head(&x->wait); + } + + /** +diff -Nur linux-4.1.39.orig/include/linux/cpu.h linux-4.1.39/include/linux/cpu.h +--- linux-4.1.39.orig/include/linux/cpu.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/cpu.h 2017-04-18 17:56:30.605396820 +0200 +@@ -231,6 +231,8 @@ + extern void put_online_cpus(void); + extern void cpu_hotplug_disable(void); + extern void cpu_hotplug_enable(void); ++extern void pin_current_cpu(void); ++extern void unpin_current_cpu(void); + #define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri) + #define __hotcpu_notifier(fn, pri) __cpu_notifier(fn, pri) + #define register_hotcpu_notifier(nb) register_cpu_notifier(nb) +@@ -249,6 +251,8 @@ + #define put_online_cpus() do { } while (0) + #define cpu_hotplug_disable() do { } while (0) + #define cpu_hotplug_enable() do { } while (0) ++static inline void pin_current_cpu(void) { } ++static inline void unpin_current_cpu(void) { } + #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) + #define __hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) + /* These aren't inline functions due to a GCC bug. */ +diff -Nur linux-4.1.39.orig/include/linux/delay.h linux-4.1.39/include/linux/delay.h +--- linux-4.1.39.orig/include/linux/delay.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/delay.h 2017-04-18 17:56:30.605396820 +0200 +@@ -52,4 +52,10 @@ + 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 -Nur linux-4.1.39.orig/include/linux/ftrace_event.h linux-4.1.39/include/linux/ftrace_event.h +--- linux-4.1.39.orig/include/linux/ftrace_event.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/ftrace_event.h 2017-04-18 17:56:30.605396820 +0200 +@@ -66,6 +66,9 @@ + unsigned char flags; + unsigned char preempt_count; + int pid; ++ unsigned short migrate_disable; ++ unsigned short padding; ++ unsigned char preempt_lazy_count; + }; + + #define FTRACE_MAX_EVENT \ +diff -Nur linux-4.1.39.orig/include/linux/ftrace.h linux-4.1.39/include/linux/ftrace.h +--- linux-4.1.39.orig/include/linux/ftrace.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/ftrace.h 2017-04-18 17:56:30.605396820 +0200 +@@ -682,6 +682,18 @@ + #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5)) + #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6)) + ++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 -Nur linux-4.1.39.orig/include/linux/highmem.h linux-4.1.39/include/linux/highmem.h +--- linux-4.1.39.orig/include/linux/highmem.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/highmem.h 2017-04-18 17:56:30.605396820 +0200 +@@ -7,6 +7,7 @@ + #include + #include + #include ++#include + + #include + +@@ -65,6 +66,7 @@ + + static inline void *kmap_atomic(struct page *page) + { ++ preempt_disable_nort(); + pagefault_disable(); + return page_address(page); + } +@@ -73,6 +75,7 @@ + static inline void __kunmap_atomic(void *addr) + { + pagefault_enable(); ++ preempt_enable_nort(); + } + + #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) +@@ -85,32 +88,51 @@ + + #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) + ++#ifndef CONFIG_PREEMPT_RT_FULL + DECLARE_PER_CPU(int, __kmap_atomic_idx); ++#endif + + static inline int kmap_atomic_idx_push(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1; + +-#ifdef CONFIG_DEBUG_HIGHMEM ++# ifdef CONFIG_DEBUG_HIGHMEM + WARN_ON_ONCE(in_irq() && !irqs_disabled()); + BUG_ON(idx >= KM_TYPE_NR); +-#endif ++# endif + return idx; ++#else ++ current->kmap_idx++; ++ BUG_ON(current->kmap_idx > KM_TYPE_NR); ++ return current->kmap_idx - 1; ++#endif + } + + static inline int kmap_atomic_idx(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + return __this_cpu_read(__kmap_atomic_idx) - 1; ++#else ++ return current->kmap_idx - 1; ++#endif + } + + static inline void kmap_atomic_idx_pop(void) + { +-#ifdef CONFIG_DEBUG_HIGHMEM ++#ifndef CONFIG_PREEMPT_RT_FULL ++# ifdef CONFIG_DEBUG_HIGHMEM + int idx = __this_cpu_dec_return(__kmap_atomic_idx); + + BUG_ON(idx < 0); +-#else ++# else + __this_cpu_dec(__kmap_atomic_idx); ++# endif ++#else ++ current->kmap_idx--; ++# ifdef CONFIG_DEBUG_HIGHMEM ++ BUG_ON(current->kmap_idx < 0); ++# endif + #endif + } + +diff -Nur linux-4.1.39.orig/include/linux/hrtimer.h linux-4.1.39/include/linux/hrtimer.h +--- linux-4.1.39.orig/include/linux/hrtimer.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/hrtimer.h 2017-04-18 17:56:30.605396820 +0200 +@@ -111,6 +111,11 @@ + 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 @@ + 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; +@@ -194,6 +200,9 @@ + 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]; + }; + +@@ -381,6 +390,13 @@ + 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 -Nur linux-4.1.39.orig/include/linux/idr.h linux-4.1.39/include/linux/idr.h +--- linux-4.1.39.orig/include/linux/idr.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/idr.h 2017-04-18 17:56:30.605396820 +0200 +@@ -95,10 +95,14 @@ + * Each idr_preload() should be matched with an invocation of this + * function. See idr_preload() for details. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++void idr_preload_end(void); ++#else + static inline void idr_preload_end(void) + { + preempt_enable(); + } ++#endif + + /** + * idr_find - return pointer for given id +diff -Nur linux-4.1.39.orig/include/linux/init_task.h linux-4.1.39/include/linux/init_task.h +--- linux-4.1.39.orig/include/linux/init_task.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/init_task.h 2017-04-18 17:56:30.605396820 +0200 +@@ -147,9 +147,16 @@ + # 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 ++ + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN + # define INIT_VTIME(tsk) \ +- .vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock), \ ++ .vtime_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.vtime_lock), \ ++ .vtime_seq = SEQCNT_ZERO(tsk.vtime_seq), \ + .vtime_snap = 0, \ + .vtime_snap_whence = VTIME_SYS, + #else +@@ -238,6 +245,7 @@ + .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 -Nur linux-4.1.39.orig/include/linux/interrupt.h linux-4.1.39/include/linux/interrupt.h +--- linux-4.1.39.orig/include/linux/interrupt.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/interrupt.h 2017-04-18 17:56:30.605396820 +0200 +@@ -61,6 +61,7 @@ + * interrupt handler after suspending interrupts. For system + * wakeup devices users need to implement wakeup detection in + * their interrupt handlers. ++ * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT) + */ + #define IRQF_SHARED 0x00000080 + #define IRQF_PROBE_SHARED 0x00000100 +@@ -74,6 +75,7 @@ + #define IRQF_NO_THREAD 0x00010000 + #define IRQF_EARLY_RESUME 0x00020000 + #define IRQF_COND_SUSPEND 0x00040000 ++#define IRQF_NO_SOFTIRQ_CALL 0x00080000 + + #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) + +@@ -102,6 +104,7 @@ + * @flags: flags (see IRQF_* above) + * @thread_fn: interrupt handler function for threaded interrupts + * @thread: thread pointer for threaded interrupts ++ * @secondary: pointer to secondary irqaction (force threading) + * @thread_flags: flags related to @thread + * @thread_mask: bitmask for keeping track of @thread activity + * @dir: pointer to the proc/irq/NN/name entry +@@ -113,6 +116,7 @@ + struct irqaction *next; + irq_handler_t thread_fn; + struct task_struct *thread; ++ struct irqaction *secondary; + unsigned int irq; + unsigned int flags; + unsigned long thread_flags; +@@ -184,7 +188,7 @@ + #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); +@@ -215,6 +219,7 @@ + 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); + }; +@@ -377,9 +382,13 @@ + bool state); + + #ifdef CONFIG_IRQ_FORCED_THREADING ++# 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 +@@ -435,9 +444,10 @@ + 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(); } + #ifdef __ARCH_HAS_DO_SOFTIRQ + void do_softirq_own_stack(void); + #else +@@ -446,13 +456,25 @@ + __do_softirq(); + } + #endif ++#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); ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void __raise_softirq_irqoff_ksoft(unsigned int nr); ++#else ++static inline void __raise_softirq_irqoff_ksoft(unsigned int nr) ++{ ++ __raise_softirq_irqoff(nr); ++} ++#endif + + extern void raise_softirq_irqoff(unsigned int nr); + extern void raise_softirq(unsigned int nr); ++extern void softirq_check_pending_idle(void); + + DECLARE_PER_CPU(struct task_struct *, ksoftirqd); + +@@ -474,8 +496,9 @@ + 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. +@@ -500,27 +523,36 @@ + 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_atomic(); + 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 +@@ -569,12 +601,7 @@ + smp_mb(); + } + +-static inline void tasklet_enable(struct tasklet_struct *t) +-{ +- smp_mb__before_atomic(); +- atomic_dec(&t->count); +-} +- ++extern void tasklet_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); + extern void tasklet_init(struct tasklet_struct *t, +@@ -605,6 +632,12 @@ + 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 -Nur linux-4.1.39.orig/include/linux/io-mapping.h linux-4.1.39/include/linux/io-mapping.h +--- linux-4.1.39.orig/include/linux/io-mapping.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/io-mapping.h 2017-04-18 17:56:30.605396820 +0200 +@@ -141,6 +141,7 @@ + io_mapping_map_atomic_wc(struct io_mapping *mapping, + unsigned long offset) + { ++ preempt_disable(); + pagefault_disable(); + return ((char __force __iomem *) mapping) + offset; + } +@@ -149,6 +150,7 @@ + io_mapping_unmap_atomic(void __iomem *vaddr) + { + pagefault_enable(); ++ preempt_enable(); + } + + /* Non-atomic map/unmap */ +diff -Nur linux-4.1.39.orig/include/linux/irqdesc.h linux-4.1.39/include/linux/irqdesc.h +--- linux-4.1.39.orig/include/linux/irqdesc.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/irqdesc.h 2017-04-18 17:56:30.605396820 +0200 +@@ -63,6 +63,7 @@ + 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 -Nur linux-4.1.39.orig/include/linux/irqflags.h linux-4.1.39/include/linux/irqflags.h +--- linux-4.1.39.orig/include/linux/irqflags.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/irqflags.h 2017-04-18 17:56:30.605396820 +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) || \ +@@ -148,4 +152,23 @@ + + #define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags) + ++/* ++ * 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) local_save_flags(flags) ++# define local_irq_restore_nort(flags) (void)(flags) ++# 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 -Nur linux-4.1.39.orig/include/linux/irq.h linux-4.1.39/include/linux/irq.h +--- linux-4.1.39.orig/include/linux/irq.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/irq.h 2017-04-18 17:56:30.605396820 +0200 +@@ -72,6 +72,7 @@ + * IRQ_IS_POLLED - Always polled by another interrupt. Exclude + * it from the spurious interrupt detection + * mechanism and from core side polling. ++ * IRQ_NO_SOFTIRQ_CALL - No softirq processing in the irq thread context (RT) + */ + enum { + IRQ_TYPE_NONE = 0x00000000, +@@ -97,13 +98,14 @@ + IRQ_NOTHREAD = (1 << 16), + IRQ_PER_CPU_DEVID = (1 << 17), + IRQ_IS_POLLED = (1 << 18), ++ IRQ_NO_SOFTIRQ_CALL = (1 << 19), + }; + + #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_IS_POLLED) ++ IRQ_IS_POLLED | IRQ_NO_SOFTIRQ_CALL) + + #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) + +diff -Nur linux-4.1.39.orig/include/linux/irq_work.h linux-4.1.39/include/linux/irq_work.h +--- linux-4.1.39.orig/include/linux/irq_work.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/irq_work.h 2017-04-18 17:56:30.605396820 +0200 +@@ -16,6 +16,7 @@ + #define IRQ_WORK_BUSY 2UL + #define IRQ_WORK_FLAGS 3UL + #define IRQ_WORK_LAZY 4UL /* Doesn't want IPI, wait for tick */ ++#define IRQ_WORK_HARD_IRQ 8UL /* Run hard IRQ context, even on RT */ + + struct irq_work { + unsigned long flags; +@@ -51,4 +52,10 @@ + static inline void irq_work_run(void) { } + #endif + ++#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) ++void irq_work_tick_soft(void); ++#else ++static inline void irq_work_tick_soft(void) { } ++#endif ++ + #endif /* _LINUX_IRQ_WORK_H */ +diff -Nur linux-4.1.39.orig/include/linux/jbd_common.h linux-4.1.39/include/linux/jbd_common.h +--- linux-4.1.39.orig/include/linux/jbd_common.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/jbd_common.h 2017-04-18 17:56:30.605396820 +0200 +@@ -15,32 +15,56 @@ + + 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 -Nur linux-4.1.39.orig/include/linux/kdb.h linux-4.1.39/include/linux/kdb.h +--- linux-4.1.39.orig/include/linux/kdb.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/kdb.h 2017-04-18 17:56:30.605396820 +0200 +@@ -167,6 +167,7 @@ + extern __printf(1, 2) int kdb_printf(const char *, ...); + typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...); + ++#define in_kdb_printk() (kdb_trap_printk) + extern void kdb_init(int level); + + /* Access to kdb specific polling devices */ +@@ -201,6 +202,7 @@ + extern int kdb_unregister(char *); + #else /* ! CONFIG_KGDB_KDB */ + static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; } ++#define in_kdb_printk() (0) + static inline void kdb_init(int level) {} + static inline int kdb_register(char *cmd, kdb_func_t func, char *usage, + char *help, short minlen) { return 0; } +diff -Nur linux-4.1.39.orig/include/linux/kernel.h linux-4.1.39/include/linux/kernel.h +--- linux-4.1.39.orig/include/linux/kernel.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/kernel.h 2017-04-18 17:56:30.605396820 +0200 +@@ -188,6 +188,9 @@ + */ + # define might_sleep() \ + do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) ++ ++# define might_sleep_no_state_check() \ ++ do { ___might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) + # define sched_annotate_sleep() (current->task_state_change = 0) + #else + static inline void ___might_sleep(const char *file, int line, +@@ -195,6 +198,7 @@ + static inline void __might_sleep(const char *file, int line, + int preempt_offset) { } + # define might_sleep() do { might_resched(); } while (0) ++# define might_sleep_no_state_check() do { might_resched(); } while (0) + # define sched_annotate_sleep() do { } while (0) + #endif + +@@ -244,7 +248,8 @@ + + #if defined(CONFIG_MMU) && \ + (defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)) +-void might_fault(void); ++#define might_fault() __might_fault(__FILE__, __LINE__) ++void __might_fault(const char *file, int line); + #else + static inline void might_fault(void) { } + #endif +@@ -466,6 +471,7 @@ + SYSTEM_HALT, + SYSTEM_POWER_OFF, + SYSTEM_RESTART, ++ SYSTEM_SUSPEND, + } system_state; + + #define TAINT_PROPRIETARY_MODULE 0 +diff -Nur linux-4.1.39.orig/include/linux/kvm_host.h linux-4.1.39/include/linux/kvm_host.h +--- linux-4.1.39.orig/include/linux/kvm_host.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/kvm_host.h 2017-04-18 17:56:30.605396820 +0200 +@@ -230,7 +230,7 @@ + + int fpu_active; + int guest_fpu_loaded, guest_xcr0_loaded; +- wait_queue_head_t wq; ++ struct swait_head wq; + struct pid *pid; + int sigset_active; + sigset_t sigset; +@@ -701,7 +701,7 @@ + } + #endif + +-static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) ++static inline struct swait_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) + { + #ifdef __KVM_HAVE_ARCH_WQP + return vcpu->arch.wqp; +diff -Nur linux-4.1.39.orig/include/linux/lglock.h linux-4.1.39/include/linux/lglock.h +--- linux-4.1.39.orig/include/linux/lglock.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/lglock.h 2017-04-18 17:56:30.605396820 +0200 +@@ -34,22 +34,39 @@ + #endif + + struct lglock { ++#ifndef CONFIG_PREEMPT_RT_FULL + arch_spinlock_t __percpu *lock; ++#else ++ struct rt_mutex __percpu *lock; ++#endif + #ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lock_class_key lock_key; + struct lockdep_map lock_dep_map; + #endif + }; + +-#define DEFINE_LGLOCK(name) \ ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define DEFINE_LGLOCK(name) \ + static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ + = __ARCH_SPIN_LOCK_UNLOCKED; \ + struct lglock name = { .lock = &name ## _lock } + +-#define DEFINE_STATIC_LGLOCK(name) \ ++# define DEFINE_STATIC_LGLOCK(name) \ + static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ + = __ARCH_SPIN_LOCK_UNLOCKED; \ + static struct lglock name = { .lock = &name ## _lock } ++#else ++ ++# define DEFINE_LGLOCK(name) \ ++ static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \ ++ = __RT_MUTEX_INITIALIZER( name ## _lock); \ ++ struct lglock name = { .lock = &name ## _lock } ++ ++# define DEFINE_STATIC_LGLOCK(name) \ ++ static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \ ++ = __RT_MUTEX_INITIALIZER( name ## _lock); \ ++ static struct lglock name = { .lock = &name ## _lock } ++#endif + + void lg_lock_init(struct lglock *lg, char *name); + void lg_local_lock(struct lglock *lg); +@@ -59,6 +76,12 @@ + void lg_global_lock(struct lglock *lg); + void lg_global_unlock(struct lglock *lg); + ++#ifndef CONFIG_PREEMPT_RT_FULL ++#define lg_global_trylock_relax(name) lg_global_lock(name) ++#else ++void lg_global_trylock_relax(struct lglock *lg); ++#endif ++ + #else + /* When !CONFIG_SMP, map lglock to spinlock */ + #define lglock spinlock +diff -Nur linux-4.1.39.orig/include/linux/list_bl.h linux-4.1.39/include/linux/list_bl.h +--- linux-4.1.39.orig/include/linux/list_bl.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/list_bl.h 2017-04-18 17:56:30.605396820 +0200 +@@ -2,6 +2,7 @@ + #define _LINUX_LIST_BL_H + + #include ++#include + #include + + /* +@@ -32,13 +33,24 @@ + + 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) ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++#define INIT_HLIST_BL_HEAD(h) \ ++do { \ ++ (h)->first = NULL; \ ++ raw_spin_lock_init(&(h)->lock); \ ++} while (0) ++#else ++#define INIT_HLIST_BL_HEAD(h) (h)->first = NULL ++#endif + + static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) + { +@@ -117,12 +129,26 @@ + + 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 + } + + static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) +diff -Nur linux-4.1.39.orig/include/linux/locallock.h linux-4.1.39/include/linux/locallock.h +--- linux-4.1.39.orig/include/linux/locallock.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/linux/locallock.h 2017-04-18 17:56:30.605396820 +0200 +@@ -0,0 +1,276 @@ ++#ifndef _LINUX_LOCALLOCK_H ++#define _LINUX_LOCALLOCK_H ++ ++#include ++#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) ++ ++/* ++ * spin_lock|trylock|unlock_local flavour that does not migrate disable ++ * used for __local_lock|trylock|unlock where get_local_var/put_local_var ++ * already takes care of the migrate_disable/enable ++ * for CONFIG_PREEMPT_BASE map to the normal spin_* calls. ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define spin_lock_local(lock) rt_spin_lock(lock) ++# define spin_trylock_local(lock) rt_spin_trylock(lock) ++# define spin_unlock_local(lock) rt_spin_unlock(lock) ++#else ++# define spin_lock_local(lock) spin_lock(lock) ++# define spin_trylock_local(lock) spin_trylock(lock) ++# define spin_unlock_local(lock) spin_unlock(lock) ++#endif ++ ++static inline void __local_lock(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current) { ++ spin_lock_local(&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) ++ ++#define local_lock_on(lvar, cpu) \ ++ do { __local_lock(&per_cpu(lvar, cpu)); } while (0) ++ ++static inline int __local_trylock(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current && spin_trylock_local(&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_local(&lv->lock); ++} ++ ++#define local_unlock(lvar) \ ++ do { \ ++ __local_unlock(this_cpu_ptr(&lvar)); \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_on(lvar, cpu) \ ++ do { __local_unlock(&per_cpu(lvar, cpu)); } 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(this_cpu_ptr(&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 = __this_cpu_read(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(this_cpu_ptr(&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); \ ++ this_cpu_ptr(&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 -Nur linux-4.1.39.orig/include/linux/mm_types.h linux-4.1.39/include/linux/mm_types.h +--- linux-4.1.39.orig/include/linux/mm_types.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/mm_types.h 2017-04-18 17:56:30.605396820 +0200 +@@ -11,6 +11,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -453,6 +454,9 @@ + bool tlb_flush_pending; + #endif + struct uprobes_state uprobes_state; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct rcu_head delayed_drop; ++#endif + #ifdef CONFIG_X86_INTEL_MPX + /* address of the bounds directory */ + void __user *bd_addr; +diff -Nur linux-4.1.39.orig/include/linux/module.h linux-4.1.39/include/linux/module.h +--- linux-4.1.39.orig/include/linux/module.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/module.h 2017-04-18 17:56:30.605396820 +0200 +@@ -386,6 +386,7 @@ + struct module *__module_text_address(unsigned long addr); + struct module *__module_address(unsigned long addr); + bool is_module_address(unsigned long addr); ++bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr); + bool is_module_percpu_address(unsigned long addr); + bool is_module_text_address(unsigned long addr); + +@@ -537,6 +538,11 @@ + { + return false; + } ++ ++static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr) ++{ ++ return false; ++} + + static inline bool is_module_text_address(unsigned long addr) + { +diff -Nur linux-4.1.39.orig/include/linux/mutex.h linux-4.1.39/include/linux/mutex.h +--- linux-4.1.39.orig/include/linux/mutex.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/mutex.h 2017-04-18 17:56:30.605396820 +0200 +@@ -19,6 +19,17 @@ + #include + #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: + * +@@ -99,13 +110,6 @@ + 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) \ +@@ -173,6 +177,8 @@ + 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); + + #endif /* __LINUX_MUTEX_H */ +diff -Nur linux-4.1.39.orig/include/linux/mutex_rt.h linux-4.1.39/include/linux/mutex_rt.h +--- linux-4.1.39.orig/include/linux/mutex_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/linux/mutex_rt.h 2017-04-18 17:56:30.605396820 +0200 +@@ -0,0 +1,89 @@ ++#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) ++ ++#ifdef CONFIG_DEBUG_MUTEXES ++#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock) ++#else ++static inline void mutex_destroy(struct mutex *lock) {} ++#endif ++ ++#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 -Nur linux-4.1.39.orig/include/linux/netdevice.h linux-4.1.39/include/linux/netdevice.h +--- linux-4.1.39.orig/include/linux/netdevice.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/netdevice.h 2017-04-18 17:56:30.609396976 +0200 +@@ -390,7 +390,19 @@ + typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb); + + void __napi_schedule(struct napi_struct *n); ++ ++/* ++ * When PREEMPT_RT_FULL is defined, all device interrupt handlers ++ * run as threads, and they can also be preempted (without PREEMPT_RT ++ * interrupt threads can not be preempted). Which means that calling ++ * __napi_schedule_irqoff() from an interrupt handler can be preempted ++ * and can corrupt the napi->poll_list. ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define __napi_schedule_irqoff(n) __napi_schedule(n) ++#else + void __napi_schedule_irqoff(struct napi_struct *n); ++#endif + + static inline bool napi_disable_pending(struct napi_struct *n) + { +@@ -2215,11 +2227,20 @@ + void synchronize_net(void); + int init_dummy_netdev(struct net_device *dev); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline int dev_recursion_level(void) ++{ ++ return current->xmit_recursion; ++} ++ ++#else ++ + DECLARE_PER_CPU(int, xmit_recursion); + static inline int dev_recursion_level(void) + { + return this_cpu_read(xmit_recursion); + } ++#endif + + struct net_device *dev_get_by_index(struct net *net, int ifindex); + struct net_device *__dev_get_by_index(struct net *net, int ifindex); +@@ -2510,6 +2531,7 @@ + unsigned int dropped; + struct sk_buff_head input_pkt_queue; + struct napi_struct backlog; ++ struct sk_buff_head tofree_queue; + + }; + +diff -Nur linux-4.1.39.orig/include/linux/netfilter/x_tables.h linux-4.1.39/include/linux/netfilter/x_tables.h +--- linux-4.1.39.orig/include/linux/netfilter/x_tables.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/netfilter/x_tables.h 2017-04-18 17:56:30.609396976 +0200 +@@ -3,6 +3,7 @@ + + + #include ++#include + #include + + /** +@@ -293,6 +294,8 @@ + */ + DECLARE_PER_CPU(seqcount_t, xt_recseq); + ++DECLARE_LOCAL_IRQ_LOCK(xt_write_lock); ++ + /** + * xt_write_recseq_begin - start of a write section + * +@@ -307,6 +310,9 @@ + { + 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(). +@@ -337,6 +343,7 @@ + /* 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 -Nur linux-4.1.39.orig/include/linux/notifier.h linux-4.1.39/include/linux/notifier.h +--- linux-4.1.39.orig/include/linux/notifier.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/notifier.h 2017-04-18 17:56:30.609396976 +0200 +@@ -6,7 +6,7 @@ + * + * Alan Cox + */ +- ++ + #ifndef _LINUX_NOTIFIER_H + #define _LINUX_NOTIFIER_H + #include +@@ -42,9 +42,7 @@ + * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. + * As compensation, srcu_notifier_chain_unregister() is rather expensive. + * SRCU notifier chains should be used when the chain will be called very +- * often but notifier_blocks will seldom be removed. Also, SRCU notifier +- * chains are slightly more difficult to use because they require special +- * runtime initialization. ++ * often but notifier_blocks will seldom be removed. + */ + + typedef int (*notifier_fn_t)(struct notifier_block *nb, +@@ -88,7 +86,7 @@ + (name)->head = NULL; \ + } while (0) + +-/* srcu_notifier_heads must be initialized and cleaned up dynamically */ ++/* srcu_notifier_heads must be cleaned up dynamically */ + extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); + #define srcu_cleanup_notifier_head(name) \ + cleanup_srcu_struct(&(name)->srcu); +@@ -101,7 +99,13 @@ + .head = NULL } + #define RAW_NOTIFIER_INIT(name) { \ + .head = NULL } +-/* srcu_notifier_heads cannot be initialized statically */ ++ ++#define SRCU_NOTIFIER_INIT(name, pcpu) \ ++ { \ ++ .mutex = __MUTEX_INITIALIZER(name.mutex), \ ++ .head = NULL, \ ++ .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \ ++ } + + #define ATOMIC_NOTIFIER_HEAD(name) \ + struct atomic_notifier_head name = \ +@@ -113,6 +117,18 @@ + struct raw_notifier_head name = \ + RAW_NOTIFIER_INIT(name) + ++#define _SRCU_NOTIFIER_HEAD(name, mod) \ ++ static DEFINE_PER_CPU(struct srcu_struct_array, \ ++ name##_head_srcu_array); \ ++ mod struct srcu_notifier_head name = \ ++ SRCU_NOTIFIER_INIT(name, name##_head_srcu_array) ++ ++#define SRCU_NOTIFIER_HEAD(name) \ ++ _SRCU_NOTIFIER_HEAD(name, ) ++ ++#define SRCU_NOTIFIER_HEAD_STATIC(name) \ ++ _SRCU_NOTIFIER_HEAD(name, static) ++ + #ifdef __KERNEL__ + + extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh, +@@ -182,12 +198,12 @@ + + /* + * Declared notifiers so far. I can imagine quite a few more chains +- * over time (eg laptop power reset chains, reboot chain (to clean ++ * over time (eg laptop power reset chains, reboot chain (to clean + * device units up), device [un]mount chain, module load/unload chain, +- * low memory chain, screenblank chain (for plug in modular screenblankers) ++ * low memory chain, screenblank chain (for plug in modular screenblankers) + * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... + */ +- ++ + /* CPU notfiers are defined in include/linux/cpu.h. */ + + /* netdevice notifiers are defined in include/linux/netdevice.h */ +diff -Nur linux-4.1.39.orig/include/linux/percpu.h linux-4.1.39/include/linux/percpu.h +--- linux-4.1.39.orig/include/linux/percpu.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/percpu.h 2017-04-18 17:56:30.609396976 +0200 +@@ -24,6 +24,35 @@ + PERCPU_MODULE_RESERVE) + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++#define get_local_var(var) (*({ \ ++ migrate_disable(); \ ++ this_cpu_ptr(&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) ++ ++#else ++ ++#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) ++ ++#endif ++ + /* minimum unit size, also is the maximum supported allocation size */ + #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) + +@@ -116,6 +145,7 @@ + #endif + + extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); ++extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr); + extern bool is_kernel_percpu_address(unsigned long addr); + + #if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) +diff -Nur linux-4.1.39.orig/include/linux/pid.h linux-4.1.39/include/linux/pid.h +--- linux-4.1.39.orig/include/linux/pid.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/pid.h 2017-04-18 17:56:30.609396976 +0200 +@@ -2,6 +2,7 @@ + #define _LINUX_PID_H + + #include ++#include + + enum pid_type + { +diff -Nur linux-4.1.39.orig/include/linux/platform_data/gpio-omap.h linux-4.1.39/include/linux/platform_data/gpio-omap.h +--- linux-4.1.39.orig/include/linux/platform_data/gpio-omap.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/platform_data/gpio-omap.h 2017-04-18 17:56:30.609396976 +0200 +@@ -198,7 +198,6 @@ + int bank_width; /* GPIO bank width */ + int bank_stride; /* Only needed for omap1 MPUIO */ + bool dbck_flag; /* dbck required or not - True for OMAP3&4 */ +- bool loses_context; /* whether the bank would ever lose context */ + bool is_mpuio; /* whether the bank is of type MPUIO */ + u32 non_wakeup_gpios; + +@@ -208,9 +207,17 @@ + int (*get_context_loss_count)(struct device *dev); + }; + ++#if IS_BUILTIN(CONFIG_GPIO_OMAP) + extern void omap2_gpio_prepare_for_idle(int off_mode); + extern void omap2_gpio_resume_after_idle(void); +-extern void omap_set_gpio_debounce(int gpio, int enable); +-extern void omap_set_gpio_debounce_time(int gpio, int enable); ++#else ++static inline void omap2_gpio_prepare_for_idle(int off_mode) ++{ ++} ++ ++static inline void omap2_gpio_resume_after_idle(void) ++{ ++} ++#endif + + #endif +diff -Nur linux-4.1.39.orig/include/linux/preempt.h linux-4.1.39/include/linux/preempt.h +--- linux-4.1.39.orig/include/linux/preempt.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/preempt.h 2017-04-18 17:56:30.609396976 +0200 +@@ -34,6 +34,20 @@ + #define preempt_count_inc() preempt_count_add(1) + #define preempt_count_dec() preempt_count_sub(1) + ++#ifdef CONFIG_PREEMPT_LAZY ++#define add_preempt_lazy_count(val) do { preempt_lazy_count() += (val); } while (0) ++#define sub_preempt_lazy_count(val) do { preempt_lazy_count() -= (val); } while (0) ++#define inc_preempt_lazy_count() add_preempt_lazy_count(1) ++#define dec_preempt_lazy_count() sub_preempt_lazy_count(1) ++#define preempt_lazy_count() (current_thread_info()->preempt_lazy_count) ++#else ++#define add_preempt_lazy_count(val) do { } while (0) ++#define sub_preempt_lazy_count(val) do { } while (0) ++#define inc_preempt_lazy_count() do { } while (0) ++#define dec_preempt_lazy_count() do { } while (0) ++#define preempt_lazy_count() (0) ++#endif ++ + #ifdef CONFIG_PREEMPT_COUNT + + #define preempt_disable() \ +@@ -42,13 +56,25 @@ + barrier(); \ + } while (0) + ++#define preempt_lazy_disable() \ ++do { \ ++ inc_preempt_lazy_count(); \ ++ barrier(); \ ++} while (0) ++ + #define sched_preempt_enable_no_resched() \ + do { \ + barrier(); \ + preempt_count_dec(); \ + } while (0) + +-#define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++# define preempt_check_resched_rt() preempt_check_resched() ++#else ++# define preempt_enable_no_resched() preempt_enable() ++# define preempt_check_resched_rt() barrier(); ++#endif + + #ifdef CONFIG_PREEMPT + #define preempt_enable() \ +@@ -64,6 +90,13 @@ + __preempt_schedule(); \ + } while (0) + ++#define preempt_lazy_enable() \ ++do { \ ++ dec_preempt_lazy_count(); \ ++ barrier(); \ ++ preempt_check_resched(); \ ++} while (0) ++ + #else + #define preempt_enable() \ + do { \ +@@ -122,6 +155,7 @@ + #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 */ + +@@ -141,10 +175,31 @@ + } while (0) + #define preempt_fold_need_resched() \ + do { \ +- if (tif_need_resched()) \ ++ if (tif_need_resched_now()) \ + set_preempt_need_resched(); \ + } while (0) + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define preempt_disable_rt() preempt_disable() ++# define preempt_enable_rt() preempt_enable() ++# define preempt_disable_nort() barrier() ++# define preempt_enable_nort() barrier() ++# ifdef CONFIG_SMP ++ extern void migrate_disable(void); ++ extern void migrate_enable(void); ++# else /* CONFIG_SMP */ ++# define migrate_disable() barrier() ++# define migrate_enable() barrier() ++# endif /* CONFIG_SMP */ ++#else ++# define preempt_disable_rt() barrier() ++# define preempt_enable_rt() barrier() ++# 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 -Nur linux-4.1.39.orig/include/linux/preempt_mask.h linux-4.1.39/include/linux/preempt_mask.h +--- linux-4.1.39.orig/include/linux/preempt_mask.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/preempt_mask.h 2017-04-18 17:56:30.609396976 +0200 +@@ -44,16 +44,26 @@ + #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 + + #define PREEMPT_ACTIVE_BITS 1 + #define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) + #define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT) + + #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? +@@ -64,7 +74,6 @@ + #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? +@@ -83,7 +92,11 @@ + /* + * The preempt_count offset after spin_lock() + */ ++#if !defined(CONFIG_PREEMPT_RT_FULL) + #define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET ++#else ++#define PREEMPT_LOCK_OFFSET 0 ++#endif + + /* + * The preempt_count offset needed for things like: +diff -Nur linux-4.1.39.orig/include/linux/printk.h linux-4.1.39/include/linux/printk.h +--- linux-4.1.39.orig/include/linux/printk.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/printk.h 2017-04-18 17:56:30.609396976 +0200 +@@ -115,9 +115,11 @@ + #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 + + typedef int(*printk_func_t)(const char *fmt, va_list args); +diff -Nur linux-4.1.39.orig/include/linux/radix-tree.h linux-4.1.39/include/linux/radix-tree.h +--- linux-4.1.39.orig/include/linux/radix-tree.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/radix-tree.h 2017-04-18 17:56:30.609396976 +0200 +@@ -279,6 +279,8 @@ + unsigned long first_index, unsigned int max_items); + int radix_tree_preload(gfp_t gfp_mask); + int radix_tree_maybe_preload(gfp_t gfp_mask); ++void radix_tree_preload_end(void); ++ + void radix_tree_init(void); + void *radix_tree_tag_set(struct radix_tree_root *root, + unsigned long index, unsigned int tag); +@@ -301,11 +303,6 @@ + int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag); + unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item); + +-static inline void radix_tree_preload_end(void) +-{ +- preempt_enable(); +-} +- + /** + * struct radix_tree_iter - radix tree iterator state + * +diff -Nur linux-4.1.39.orig/include/linux/random.h linux-4.1.39/include/linux/random.h +--- linux-4.1.39.orig/include/linux/random.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/random.h 2017-04-18 17:56:30.609396976 +0200 +@@ -11,7 +11,7 @@ + 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 -Nur linux-4.1.39.orig/include/linux/rcupdate.h linux-4.1.39/include/linux/rcupdate.h +--- linux-4.1.39.orig/include/linux/rcupdate.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/rcupdate.h 2017-04-18 17:56:30.609396976 +0200 +@@ -167,6 +167,9 @@ + + #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. +@@ -190,6 +193,7 @@ + */ + 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. +@@ -260,6 +264,11 @@ + * 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 */ + +@@ -283,6 +292,8 @@ + return 0; + } + ++#define sched_rcu_preempt_depth() rcu_preempt_depth() ++ + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + + /* Internal to kernel */ +@@ -463,7 +474,14 @@ + int debug_lockdep_rcu_enabled(void); + + int rcu_read_lock_held(void); ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline int rcu_read_lock_bh_held(void) ++{ ++ return rcu_read_lock_held(); ++} ++#else + int rcu_read_lock_bh_held(void); ++#endif + + /** + * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? +@@ -990,10 +1008,14 @@ + 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_watching(), + "rcu_read_lock_bh() used illegally while idle"); ++#endif + } + + /* +@@ -1003,10 +1025,14 @@ + */ + static inline void rcu_read_unlock_bh(void) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ rcu_read_unlock(); ++#else + rcu_lockdep_assert(rcu_is_watching(), + "rcu_read_unlock_bh() used illegally while idle"); + rcu_lock_release(&rcu_bh_lock_map); + __release(RCU_BH); ++#endif + local_bh_enable(); + } + +diff -Nur linux-4.1.39.orig/include/linux/rcutree.h linux-4.1.39/include/linux/rcutree.h +--- linux-4.1.39.orig/include/linux/rcutree.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/rcutree.h 2017-04-18 17:56:30.609396976 +0200 +@@ -46,7 +46,11 @@ + rcu_note_context_switch(); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define synchronize_rcu_bh synchronize_rcu ++#else + void synchronize_rcu_bh(void); ++#endif + void synchronize_sched_expedited(void); + void synchronize_rcu_expedited(void); + +@@ -74,7 +78,11 @@ + } + + void rcu_barrier(void); ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define rcu_barrier_bh rcu_barrier ++#else + void rcu_barrier_bh(void); ++#endif + void rcu_barrier_sched(void); + unsigned long get_state_synchronize_rcu(void); + void cond_synchronize_rcu(unsigned long oldstate); +@@ -85,12 +93,10 @@ + unsigned long rcu_batches_started_bh(void); + unsigned long rcu_batches_started_sched(void); + unsigned long rcu_batches_completed(void); +-unsigned long rcu_batches_completed_bh(void); + unsigned long rcu_batches_completed_sched(void); + void show_rcu_gp_kthreads(void); + + void rcu_force_quiescent_state(void); +-void rcu_bh_force_quiescent_state(void); + void rcu_sched_force_quiescent_state(void); + + void exit_rcu(void); +@@ -100,6 +106,14 @@ + + bool rcu_is_watching(void); + ++#ifndef CONFIG_PREEMPT_RT_FULL ++void rcu_bh_force_quiescent_state(void); ++unsigned 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 ++ + void rcu_all_qs(void); + + #endif /* __LINUX_RCUTREE_H */ +diff -Nur linux-4.1.39.orig/include/linux/rtmutex.h linux-4.1.39/include/linux/rtmutex.h +--- linux-4.1.39.orig/include/linux/rtmutex.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/rtmutex.h 2017-04-18 17:56:30.609396976 +0200 +@@ -14,10 +14,14 @@ + + #include + #include +-#include ++#include + + extern int max_lock_depth; /* for sysctl */ + ++#ifdef CONFIG_DEBUG_MUTEXES ++#include ++#endif ++ + /** + * The rt_mutex structure + * +@@ -31,8 +35,8 @@ + struct rb_root waiters; + struct rb_node *waiters_leftmost; + struct task_struct *owner; +-#ifdef CONFIG_DEBUG_RT_MUTEXES + int save_state; ++#ifdef CONFIG_DEBUG_RT_MUTEXES + const char *name, *file; + int line; + void *magic; +@@ -55,22 +59,33 @@ + # define rt_mutex_debug_check_no_locks_held(task) do { } while (0) + #endif + ++# define rt_mutex_init(mutex) \ ++ do { \ ++ raw_spin_lock_init(&(mutex)->wait_lock); \ ++ __rt_mutex_init(mutex, #mutex); \ ++ } while (0) ++ + #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__) + 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_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) \ + , .waiters = RB_ROOT \ + , .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) +@@ -91,6 +106,7 @@ + + extern void rt_mutex_lock(struct rt_mutex *lock); + 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); + +diff -Nur linux-4.1.39.orig/include/linux/rwlock_rt.h linux-4.1.39/include/linux/rwlock_rt.h +--- linux-4.1.39.orig/include/linux/rwlock_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/linux/rwlock_rt.h 2017-04-18 17:56:30.609396976 +0200 +@@ -0,0 +1,99 @@ ++#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); \ ++ flags = rt_read_lock_irqsave(lock); \ ++ } while (0) ++ ++#define write_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = rt_write_lock_irqsave(lock); \ ++ } while (0) ++ ++#define read_lock(lock) rt_read_lock(lock) ++ ++#define read_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_read_lock(lock); \ ++ } while (0) ++ ++#define read_lock_irq(lock) read_lock(lock) ++ ++#define write_lock(lock) rt_write_lock(lock) ++ ++#define write_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_write_lock(lock); \ ++ } while (0) ++ ++#define write_lock_irq(lock) write_lock(lock) ++ ++#define read_unlock(lock) rt_read_unlock(lock) ++ ++#define read_unlock_bh(lock) \ ++ do { \ ++ rt_read_unlock(lock); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define read_unlock_irq(lock) read_unlock(lock) ++ ++#define write_unlock(lock) rt_write_unlock(lock) ++ ++#define write_unlock_bh(lock) \ ++ do { \ ++ rt_write_unlock(lock); \ ++ 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); \ ++ } while (0) ++ ++#define write_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ rt_write_unlock(lock); \ ++ } while (0) ++ ++#endif +diff -Nur linux-4.1.39.orig/include/linux/rwlock_types.h linux-4.1.39/include/linux/rwlock_types.h +--- linux-4.1.39.orig/include/linux/rwlock_types.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/rwlock_types.h 2017-04-18 17:56:30.609396976 +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 @@ + 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 -Nur linux-4.1.39.orig/include/linux/rwlock_types_rt.h linux-4.1.39/include/linux/rwlock_types_rt.h +--- linux-4.1.39.orig/include/linux/rwlock_types_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/linux/rwlock_types_rt.h 2017-04-18 17:56:30.609396976 +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 -Nur linux-4.1.39.orig/include/linux/rwsem.h linux-4.1.39/include/linux/rwsem.h +--- linux-4.1.39.orig/include/linux/rwsem.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/rwsem.h 2017-04-18 17:56:30.609396976 +0200 +@@ -18,6 +18,10 @@ + #include + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++#include ++#else /* PREEMPT_RT_FULL */ ++ + struct rw_semaphore; + + #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK +@@ -177,4 +181,6 @@ + # define up_read_non_owner(sem) up_read(sem) + #endif + ++#endif /* !PREEMPT_RT_FULL */ ++ + #endif /* _LINUX_RWSEM_H */ +diff -Nur linux-4.1.39.orig/include/linux/rwsem_rt.h linux-4.1.39/include/linux/rwsem_rt.h +--- linux-4.1.39.orig/include/linux/rwsem_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/linux/rwsem_rt.h 2017-04-18 17:56:30.609396976 +0200 +@@ -0,0 +1,140 @@ ++#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, const char *name, ++ struct lock_class_key *key); ++ ++#define __rt_init_rwsem(sem, name, key) \ ++ do { \ ++ rt_mutex_init(&(sem)->lock); \ ++ __rt_rwsem_init((sem), (name), (key));\ ++ } while (0) ++ ++#define __init_rwsem(sem, name, key) __rt_init_rwsem(sem, name, key) ++ ++# define rt_init_rwsem(sem) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ __rt_init_rwsem((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_write_nested_lock(struct rw_semaphore *rwsem, ++ struct lockdep_map *nest); ++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_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 int rwsem_is_contended(struct rw_semaphore *sem) ++{ ++ /* rt_mutex_has_waiters() */ ++ return !RB_EMPTY_ROOT(&sem->lock.waiters); ++} ++ ++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_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); ++} ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++static inline void down_write_nest_lock(struct rw_semaphore *sem, ++ struct rw_semaphore *nest_lock) ++{ ++ rt_down_write_nested_lock(sem, &nest_lock->dep_map); ++} ++ ++#else ++ ++static inline void down_write_nest_lock(struct rw_semaphore *sem, ++ struct rw_semaphore *nest_lock) ++{ ++ rt_down_write_nested_lock(sem, NULL); ++} ++#endif ++#endif +diff -Nur linux-4.1.39.orig/include/linux/sched.h linux-4.1.39/include/linux/sched.h +--- linux-4.1.39.orig/include/linux/sched.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/sched.h 2017-04-18 17:56:30.609396976 +0200 +@@ -26,6 +26,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -175,8 +176,6 @@ + extern void calc_global_load(unsigned long ticks); + extern void update_cpu_load_nohz(void); + +-extern unsigned long get_parent_ip(unsigned long addr); +- + extern void dump_cpu_task(int cpu); + + struct seq_file; +@@ -234,10 +233,7 @@ + TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ + __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD) + +-#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) + #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) +-#define task_is_stopped_or_traced(task) \ +- ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) + #define task_contributes_to_load(task) \ + ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ + (task->flags & PF_FROZEN) == 0) +@@ -302,6 +298,11 @@ + + #endif + ++#define __set_current_state_no_track(state_value) \ ++ do { current->state = (state_value); } while (0) ++#define set_current_state_no_track(state_value) \ ++ set_mb(current->state, (state_value)) ++ + /* Task command name length */ + #define TASK_COMM_LEN 16 + +@@ -902,6 +903,50 @@ + #define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) + + /* ++ * Wake-queues are lists of tasks with a pending wakeup, whose ++ * callers have already marked the task as woken internally, ++ * and can thus carry on. A common use case is being able to ++ * do the wakeups once the corresponding user lock as been ++ * released. ++ * ++ * We hold reference to each task in the list across the wakeup, ++ * thus guaranteeing that the memory is still valid by the time ++ * the actual wakeups are performed in wake_up_q(). ++ * ++ * One per task suffices, because there's never a need for a task to be ++ * in two wake queues simultaneously; it is forbidden to abandon a task ++ * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is ++ * already in a wake queue, the wakeup will happen soon and the second ++ * waker can just skip it. ++ * ++ * The WAKE_Q macro declares and initializes the list head. ++ * wake_up_q() does NOT reinitialize the list; it's expected to be ++ * called near the end of a function, where the fact that the queue is ++ * not used again will be easy to see by inspection. ++ * ++ * Note that this can cause spurious wakeups. schedule() callers ++ * must ensure the call is done inside a loop, confirming that the ++ * wakeup condition has in fact occurred. ++ */ ++struct wake_q_node { ++ struct wake_q_node *next; ++}; ++ ++struct wake_q_head { ++ struct wake_q_node *first; ++ struct wake_q_node **lastp; ++}; ++ ++#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01) ++ ++#define WAKE_Q(name) \ ++ struct wake_q_head name = { WAKE_Q_TAIL, &name.first } ++ ++extern void wake_q_add(struct wake_q_head *head, ++ struct task_struct *task); ++extern void wake_up_q(struct wake_q_head *head); ++ ++/* + * sched-domains (multiprocessor balancing) declarations: + */ + #ifdef CONFIG_SMP +@@ -1293,6 +1338,7 @@ + + 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 */ +@@ -1329,6 +1375,12 @@ + #endif + + unsigned int policy; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int migrate_disable; ++# ifdef CONFIG_SCHED_DEBUG ++ int migrate_disable_atomic; ++# endif ++#endif + int nr_cpus_allowed; + cpumask_t cpus_allowed; + +@@ -1436,7 +1488,8 @@ + struct cputime prev_cputime; + #endif + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +- seqlock_t vtime_seqlock; ++ raw_spinlock_t vtime_lock; ++ seqcount_t vtime_seq; + unsigned long long vtime_snap; + enum { + VTIME_SLEEPING = 0, +@@ -1452,6 +1505,9 @@ + + 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 *ptracer_cred; /* Tracer's credentials at attach */ +@@ -1485,10 +1541,15 @@ + /* 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; +@@ -1514,6 +1575,8 @@ + /* Protection of the PI data structures: */ + raw_spinlock_t pi_lock; + ++ struct wake_q_node wake_q; ++ + #ifdef CONFIG_RT_MUTEXES + /* PI waiters blocked on a rt_mutex held by this task */ + struct rb_root pi_waiters; +@@ -1708,6 +1771,12 @@ + 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_MEMCG + struct memcg_oom_info { +@@ -1724,14 +1793,26 @@ + unsigned int sequential_io; + unsigned int sequential_io_avg; + #endif ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct rcu_head put_rcu; ++ int softirq_nestcnt; ++ unsigned int softirqs_raised; ++#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_ATOMIC_SLEEP + unsigned long task_state_change; + #endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int xmit_recursion; ++#endif ++ int pagefault_disabled; + }; + +-/* Future-safe accessor for struct task_struct's cpus_allowed. */ +-#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) +- + #define TNF_MIGRATED 0x01 + #define TNF_NO_GROUP 0x02 + #define TNF_SHARED 0x04 +@@ -1920,6 +2001,15 @@ + 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) +@@ -1927,6 +2017,7 @@ + if (atomic_dec_and_test(&t->usage)) + __put_task_struct(t); + } ++#endif + + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN + extern void task_cputime(struct task_struct *t, +@@ -1965,6 +2056,7 @@ + /* + * Per process flags + */ ++#define PF_IN_SOFTIRQ 0x00000001 /* Task is serving softirq */ + #define PF_EXITING 0x00000004 /* getting shut down */ + #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ + #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ +@@ -2129,6 +2221,10 @@ + + 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) +@@ -2141,6 +2237,9 @@ + 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_COMMON +@@ -2357,6 +2456,7 @@ + + 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); +@@ -2473,12 +2573,24 @@ + + /* 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 void mmput(struct mm_struct *); + /* Grab a reference to a task's mm, if it is not already going away */ +@@ -2790,6 +2902,43 @@ + return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++static inline void set_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline int test_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY)); ++} ++ ++static inline int need_resched_lazy(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline int need_resched_now(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED); ++} ++ ++#else ++static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { } ++static inline int need_resched_lazy(void) { return 0; } ++ ++static inline int need_resched_now(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED); ++} ++ ++#endif ++ + static inline int restart_syscall(void) + { + set_tsk_thread_flag(current, TIF_SIGPENDING); +@@ -2821,6 +2970,51 @@ + return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); + } + ++static inline bool __task_is_stopped_or_traced(struct task_struct *task) ++{ ++ if (task->state & (__TASK_STOPPED | __TASK_TRACED)) ++ return true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED)) ++ return true; ++#endif ++ return false; ++} ++ ++static inline bool task_is_stopped_or_traced(struct task_struct *task) ++{ ++ bool traced_stopped; ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&task->pi_lock, flags); ++ traced_stopped = __task_is_stopped_or_traced(task); ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++#else ++ traced_stopped = __task_is_stopped_or_traced(task); ++#endif ++ return traced_stopped; ++} ++ ++static inline bool task_is_traced(struct task_struct *task) ++{ ++ bool traced = false; ++ ++ if (task->state & __TASK_TRACED) ++ return true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* in case the task is sleeping on tasklist_lock */ ++ raw_spin_lock_irq(&task->pi_lock); ++ if (task->state & __TASK_TRACED) ++ traced = true; ++ else if (task->saved_state & __TASK_TRACED) ++ traced = true; ++ raw_spin_unlock_irq(&task->pi_lock); ++#endif ++ return traced; ++} ++ + /* + * cond_resched() and cond_resched_lock(): latency reduction via + * explicit rescheduling in places that are safe. The return +@@ -2842,12 +3036,16 @@ + __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 + + static inline void cond_resched_rcu(void) + { +@@ -3014,6 +3212,26 @@ + + #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 -Nur linux-4.1.39.orig/include/linux/seqlock.h linux-4.1.39/include/linux/seqlock.h +--- linux-4.1.39.orig/include/linux/seqlock.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/seqlock.h 2017-04-18 17:56:30.609396976 +0200 +@@ -219,20 +219,30 @@ + return __read_seqcount_retry(s, start); + } + +- +- +-static inline void raw_write_seqcount_begin(seqcount_t *s) ++static inline void __raw_write_seqcount_begin(seqcount_t *s) + { + s->sequence++; + smp_wmb(); + } + +-static inline void raw_write_seqcount_end(seqcount_t *s) ++static inline void raw_write_seqcount_begin(seqcount_t *s) ++{ ++ preempt_disable_rt(); ++ __raw_write_seqcount_begin(s); ++} ++ ++static inline void __raw_write_seqcount_end(seqcount_t *s) + { + smp_wmb(); + s->sequence++; + } + ++static inline void raw_write_seqcount_end(seqcount_t *s) ++{ ++ __raw_write_seqcount_end(s); ++ preempt_enable_rt(); ++} ++ + /* + * raw_write_seqcount_latch - redirect readers to even/odd copy + * @s: pointer to seqcount_t +@@ -305,10 +315,32 @@ + /* + * 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 = ACCESS_ONCE(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_unlock_wait(&sl->lock); ++ goto repeat; ++ } ++ return ret; ++} ++#endif + + static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) + { +@@ -323,36 +355,36 @@ + static inline void write_seqlock(seqlock_t *sl) + { + spin_lock(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_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); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock_bh(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_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); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock_irq(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_irq(&sl->lock); + } + +@@ -361,7 +393,7 @@ + unsigned long flags; + + spin_lock_irqsave(&sl->lock, flags); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + return flags; + } + +@@ -371,7 +403,7 @@ + static inline void + write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_irqrestore(&sl->lock, flags); + } + +diff -Nur linux-4.1.39.orig/include/linux/signal.h linux-4.1.39/include/linux/signal.h +--- linux-4.1.39.orig/include/linux/signal.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/signal.h 2017-04-18 17:56:30.609396976 +0200 +@@ -233,6 +233,7 @@ + } + + 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 -Nur linux-4.1.39.orig/include/linux/skbuff.h linux-4.1.39/include/linux/skbuff.h +--- linux-4.1.39.orig/include/linux/skbuff.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/skbuff.h 2017-04-18 17:56:30.613397130 +0200 +@@ -187,6 +187,7 @@ + + __u32 qlen; + spinlock_t lock; ++ raw_spinlock_t raw_lock; + }; + + struct sk_buff; +@@ -1337,6 +1338,12 @@ + __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 -Nur linux-4.1.39.orig/include/linux/smp.h linux-4.1.39/include/linux/smp.h +--- linux-4.1.39.orig/include/linux/smp.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/smp.h 2017-04-18 17:56:30.613397130 +0200 +@@ -185,6 +185,9 @@ + #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 -Nur linux-4.1.39.orig/include/linux/spinlock_api_smp.h linux-4.1.39/include/linux/spinlock_api_smp.h +--- linux-4.1.39.orig/include/linux/spinlock_api_smp.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/spinlock_api_smp.h 2017-04-18 17:56:30.613397130 +0200 +@@ -189,6 +189,8 @@ + return 0; + } + +-#include ++#ifndef CONFIG_PREEMPT_RT_FULL ++# include ++#endif + + #endif /* __LINUX_SPINLOCK_API_SMP_H */ +diff -Nur linux-4.1.39.orig/include/linux/spinlock.h linux-4.1.39/include/linux/spinlock.h +--- linux-4.1.39.orig/include/linux/spinlock.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/spinlock.h 2017-04-18 17:56:30.613397130 +0200 +@@ -281,7 +281,11 @@ + #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: +@@ -292,6 +296,10 @@ + # 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 + */ +@@ -426,4 +434,6 @@ + #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 -Nur linux-4.1.39.orig/include/linux/spinlock_rt.h linux-4.1.39/include/linux/spinlock_rt.h +--- linux-4.1.39.orig/include/linux/spinlock_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/linux/spinlock_rt.h 2017-04-18 17:56:30.613397130 +0200 +@@ -0,0 +1,174 @@ ++#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_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); ++extern int __lockfunc __rt_spin_trylock(struct rt_mutex *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_bh_nested(lock, subclass) \ ++ do { \ ++ local_bh_disable(); \ ++ 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_bh_nested(lock, subclass) spin_lock_bh(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 -Nur linux-4.1.39.orig/include/linux/spinlock_types.h linux-4.1.39/include/linux/spinlock_types.h +--- linux-4.1.39.orig/include/linux/spinlock_types.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/spinlock_types.h 2017-04-18 17:56:30.613397130 +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) ++# include ++# include ++# include + #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; +- }; +-#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 -Nur linux-4.1.39.orig/include/linux/spinlock_types_nort.h linux-4.1.39/include/linux/spinlock_types_nort.h +--- linux-4.1.39.orig/include/linux/spinlock_types_nort.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/linux/spinlock_types_nort.h 2017-04-18 17:56:30.613397130 +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 -Nur linux-4.1.39.orig/include/linux/spinlock_types_raw.h linux-4.1.39/include/linux/spinlock_types_raw.h +--- linux-4.1.39.orig/include/linux/spinlock_types_raw.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/linux/spinlock_types_raw.h 2017-04-18 17:56:30.613397130 +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 -Nur linux-4.1.39.orig/include/linux/spinlock_types_rt.h linux-4.1.39/include/linux/spinlock_types_rt.h +--- linux-4.1.39.orig/include/linux/spinlock_types_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/linux/spinlock_types_rt.h 2017-04-18 17:56:30.613397130 +0200 +@@ -0,0 +1,51 @@ ++#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 ++ ++#include ++ ++/* ++ * 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 -Nur linux-4.1.39.orig/include/linux/srcu.h linux-4.1.39/include/linux/srcu.h +--- linux-4.1.39.orig/include/linux/srcu.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/srcu.h 2017-04-18 17:56:30.613397130 +0200 +@@ -84,10 +84,10 @@ + + void process_srcu(struct work_struct *work); + +-#define __SRCU_STRUCT_INIT(name) \ ++#define __SRCU_STRUCT_INIT(name, pcpu_name) \ + { \ + .completed = -300, \ +- .per_cpu_ref = &name##_srcu_array, \ ++ .per_cpu_ref = &pcpu_name, \ + .queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \ + .running = false, \ + .batch_queue = RCU_BATCH_INIT(name.batch_queue), \ +@@ -104,7 +104,7 @@ + */ + #define __DEFINE_SRCU(name, is_static) \ + static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ +- is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) ++ is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_array) + #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) + #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) + +diff -Nur linux-4.1.39.orig/include/linux/swap.h linux-4.1.39/include/linux/swap.h +--- linux-4.1.39.orig/include/linux/swap.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/swap.h 2017-04-18 17:56:30.613397130 +0200 +@@ -11,6 +11,7 @@ + #include + #include + #include ++#include + #include + + struct notifier_block; +@@ -252,7 +253,8 @@ + void *workingset_eviction(struct address_space *mapping, struct page *page); + bool workingset_refault(void *shadow); + void workingset_activation(struct page *page); +-extern struct list_lru workingset_shadow_nodes; ++extern struct list_lru __workingset_shadow_nodes; ++DECLARE_LOCAL_IRQ_LOCK(workingset_shadow_lock); + + static inline unsigned int workingset_node_pages(struct radix_tree_node *node) + { +@@ -296,6 +298,7 @@ + + + /* linux/mm/swap.c */ ++DECLARE_LOCAL_IRQ_LOCK(swapvec_lock); + extern void lru_cache_add(struct page *); + extern void lru_cache_add_anon(struct page *page); + extern void lru_cache_add_file(struct page *page); +diff -Nur linux-4.1.39.orig/include/linux/thread_info.h linux-4.1.39/include/linux/thread_info.h +--- linux-4.1.39.orig/include/linux/thread_info.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/thread_info.h 2017-04-18 17:56:30.613397130 +0200 +@@ -102,7 +102,17 @@ + #define test_thread_flag(flag) \ + test_ti_thread_flag(current_thread_info(), flag) + +-#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) ++#ifdef CONFIG_PREEMPT_LAZY ++#define tif_need_resched() (test_thread_flag(TIF_NEED_RESCHED) || \ ++ test_thread_flag(TIF_NEED_RESCHED_LAZY)) ++#define tif_need_resched_now() (test_thread_flag(TIF_NEED_RESCHED)) ++#define tif_need_resched_lazy() test_thread_flag(TIF_NEED_RESCHED_LAZY)) ++ ++#else ++#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) ++#define tif_need_resched_now() test_thread_flag(TIF_NEED_RESCHED) ++#define tif_need_resched_lazy() 0 ++#endif + + #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK + /* +diff -Nur linux-4.1.39.orig/include/linux/timer.h linux-4.1.39/include/linux/timer.h +--- linux-4.1.39.orig/include/linux/timer.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/timer.h 2017-04-18 17:56:30.613397130 +0200 +@@ -241,7 +241,7 @@ + + 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 -Nur linux-4.1.39.orig/include/linux/uaccess.h linux-4.1.39/include/linux/uaccess.h +--- linux-4.1.39.orig/include/linux/uaccess.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/uaccess.h 2017-04-18 17:56:30.613397130 +0200 +@@ -1,21 +1,31 @@ + #ifndef __LINUX_UACCESS_H__ + #define __LINUX_UACCESS_H__ + +-#include ++#include + #include + ++static __always_inline void pagefault_disabled_inc(void) ++{ ++ current->pagefault_disabled++; ++} ++ ++static __always_inline void pagefault_disabled_dec(void) ++{ ++ current->pagefault_disabled--; ++ WARN_ON(current->pagefault_disabled < 0); ++} ++ + /* +- * These routines enable/disable the pagefault handler in that +- * it will not take any locks and go straight to the fixup table. ++ * These routines enable/disable the pagefault handler. If disabled, 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. ++ * User access methods will not sleep when called from a pagefault_disabled() ++ * environment. + */ + static inline void pagefault_disable(void) + { +- preempt_count_inc(); ++ migrate_disable(); ++ pagefault_disabled_inc(); + /* + * make sure to have issued the store before a pagefault + * can hit. +@@ -25,18 +35,32 @@ + + static inline void pagefault_enable(void) + { +-#ifndef CONFIG_PREEMPT + /* + * make sure to issue those last loads/stores before enabling + * the pagefault handler again. + */ + barrier(); +- preempt_count_dec(); +-#else +- preempt_enable(); +-#endif ++ pagefault_disabled_dec(); ++ migrate_enable(); + } + ++/* ++ * Is the pagefault handler disabled? If so, user access methods will not sleep. ++ */ ++#define pagefault_disabled() (current->pagefault_disabled != 0) ++ ++/* ++ * The pagefault handler is in general disabled by pagefault_disable() or ++ * when in irq context (via in_atomic()). ++ * ++ * This function should only be used by the fault handlers. Other users should ++ * stick to pagefault_disabled(). ++ * Please NEVER use preempt_disable() to disable the fault handler. With ++ * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. ++ * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. ++ */ ++#define faulthandler_disabled() (pagefault_disabled() || in_atomic()) ++ + #ifndef ARCH_HAS_NOCACHE_UACCESS + + static inline unsigned long __copy_from_user_inatomic_nocache(void *to, +diff -Nur linux-4.1.39.orig/include/linux/uprobes.h linux-4.1.39/include/linux/uprobes.h +--- linux-4.1.39.orig/include/linux/uprobes.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/uprobes.h 2017-04-18 17:56:30.613397130 +0200 +@@ -27,6 +27,7 @@ + #include + #include + #include ++#include + + struct vm_area_struct; + struct mm_struct; +diff -Nur linux-4.1.39.orig/include/linux/vmstat.h linux-4.1.39/include/linux/vmstat.h +--- linux-4.1.39.orig/include/linux/vmstat.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/vmstat.h 2017-04-18 17:56:30.613397130 +0200 +@@ -33,7 +33,9 @@ + */ + static inline void __count_vm_event(enum vm_event_item item) + { ++ preempt_disable_rt(); + raw_cpu_inc(vm_event_states.event[item]); ++ preempt_enable_rt(); + } + + static inline void count_vm_event(enum vm_event_item item) +@@ -43,7 +45,9 @@ + + static inline void __count_vm_events(enum vm_event_item item, long delta) + { ++ preempt_disable_rt(); + raw_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 -Nur linux-4.1.39.orig/include/linux/wait.h linux-4.1.39/include/linux/wait.h +--- linux-4.1.39.orig/include/linux/wait.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/linux/wait.h 2017-04-18 17:56:30.613397130 +0200 +@@ -8,6 +8,7 @@ + #include + #include + #include ++#include + + typedef struct __wait_queue wait_queue_t; + typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key); +diff -Nur linux-4.1.39.orig/include/linux/wait-simple.h linux-4.1.39/include/linux/wait-simple.h +--- linux-4.1.39.orig/include/linux/wait-simple.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/linux/wait-simple.h 2017-04-18 17:56:30.613397130 +0200 +@@ -0,0 +1,207 @@ ++#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); ++ ++/* Check whether a head has waiters enqueued */ ++static inline bool swaitqueue_active(struct swait_head *h) ++{ ++ /* Make sure the condition is visible before checking list_empty() */ ++ smp_mb(); ++ return !list_empty(&h->list); ++} ++ ++/* ++ * 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) ++ ++#define __swait_event_interruptible_timeout(wq, condition, ret) \ ++do { \ ++ DEFINE_SWAITER(__wait); \ ++ \ ++ for (;;) { \ ++ swait_prepare(&wq, &__wait, TASK_INTERRUPTIBLE); \ ++ if (condition) \ ++ break; \ ++ if (signal_pending(current)) { \ ++ ret = -ERESTARTSYS; \ ++ break; \ ++ } \ ++ ret = schedule_timeout(ret); \ ++ if (!ret) \ ++ break; \ ++ } \ ++ 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_interruptible_timeout(wq, condition, timeout) \ ++({ \ ++ int __ret = timeout; \ ++ if (!(condition)) \ ++ __swait_event_interruptible_timeout(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 -Nur linux-4.1.39.orig/include/linux/work-simple.h linux-4.1.39/include/linux/work-simple.h +--- linux-4.1.39.orig/include/linux/work-simple.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/linux/work-simple.h 2017-04-18 17:56:30.613397130 +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 -Nur linux-4.1.39.orig/include/net/dst.h linux-4.1.39/include/net/dst.h +--- linux-4.1.39.orig/include/net/dst.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/net/dst.h 2017-04-18 17:56:30.613397130 +0200 +@@ -436,7 +436,7 @@ + static inline int dst_neigh_output(struct dst_entry *dst, struct neighbour *n, + struct sk_buff *skb) + { +- const struct hh_cache *hh; ++ struct hh_cache *hh; + + if (dst->pending_confirm) { + unsigned long now = jiffies; +diff -Nur linux-4.1.39.orig/include/net/neighbour.h linux-4.1.39/include/net/neighbour.h +--- linux-4.1.39.orig/include/net/neighbour.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/net/neighbour.h 2017-04-18 17:56:30.613397130 +0200 +@@ -445,7 +445,7 @@ + } + #endif + +-static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) ++static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb) + { + unsigned int seq; + int hh_len; +@@ -500,7 +500,7 @@ + + #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 -Nur linux-4.1.39.orig/include/net/netns/ipv4.h linux-4.1.39/include/net/netns/ipv4.h +--- linux-4.1.39.orig/include/net/netns/ipv4.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/net/netns/ipv4.h 2017-04-18 17:56:30.613397130 +0200 +@@ -69,6 +69,7 @@ + + 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 -Nur linux-4.1.39.orig/include/trace/events/hist.h linux-4.1.39/include/trace/events/hist.h +--- linux-4.1.39.orig/include/trace/events/hist.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/trace/events/hist.h 2017-04-18 17:56:30.613397130 +0200 +@@ -0,0 +1,74 @@ ++#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) ++#define trace_hrtimer_interrupt_rcuidle(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 -Nur linux-4.1.39.orig/include/trace/events/latency_hist.h linux-4.1.39/include/trace/events/latency_hist.h +--- linux-4.1.39.orig/include/trace/events/latency_hist.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/include/trace/events/latency_hist.h 2017-04-18 17:56:30.613397130 +0200 +@@ -0,0 +1,29 @@ ++#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 -Nur linux-4.1.39.orig/include/trace/events/sched.h linux-4.1.39/include/trace/events/sched.h +--- linux-4.1.39.orig/include/trace/events/sched.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/include/trace/events/sched.h 2017-04-18 17:56:30.613397130 +0200 +@@ -55,9 +55,9 @@ + */ + DECLARE_EVENT_CLASS(sched_wakeup_template, + +- TP_PROTO(struct task_struct *p, int success), ++ TP_PROTO(struct task_struct *p), + +- TP_ARGS(__perf_task(p), success), ++ TP_ARGS(__perf_task(p)), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) +@@ -71,25 +71,37 @@ + 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 -Nur linux-4.1.39.orig/init/Kconfig linux-4.1.39/init/Kconfig +--- linux-4.1.39.orig/init/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/init/Kconfig 2017-04-18 17:56:30.613397130 +0200 +@@ -637,7 +637,7 @@ + + config RCU_FAST_NO_HZ + bool "Accelerate last non-dyntick-idle CPU's grace periods" +- depends on NO_HZ_COMMON && SMP ++ depends on NO_HZ_COMMON && SMP && !PREEMPT_RT_FULL + default n + help + This option permits CPUs to enter dynticks-idle state even if +@@ -664,7 +664,7 @@ + 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. +@@ -1101,6 +1101,7 @@ + config RT_GROUP_SCHED + bool "Group scheduling for SCHED_RR/FIFO" + depends on CGROUP_SCHED ++ depends on !PREEMPT_RT_FULL + default n + help + This feature lets you explicitly allocate real CPU bandwidth +@@ -1688,6 +1689,7 @@ + + config SLAB + bool "SLAB" ++ depends on !PREEMPT_RT_FULL + help + The regular slab allocator that is established and known to work + well in all environments. It organizes cache hot objects in +@@ -1706,6 +1708,7 @@ + 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 +@@ -1715,7 +1718,7 @@ + + config SLUB_CPU_PARTIAL + default y +- depends on SLUB && SMP ++ depends on SLUB && SMP && !PREEMPT_RT_FULL + bool "SLUB per cpu partial cache" + help + Per cpu partial caches accellerate objects allocation and freeing +diff -Nur linux-4.1.39.orig/init/main.c linux-4.1.39/init/main.c +--- linux-4.1.39.orig/init/main.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/init/main.c 2017-04-18 17:56:30.617397286 +0200 +@@ -525,6 +525,7 @@ + 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, NULL); +diff -Nur linux-4.1.39.orig/init/Makefile linux-4.1.39/init/Makefile +--- linux-4.1.39.orig/init/Makefile 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/init/Makefile 2017-04-18 17:56:30.613397130 +0200 +@@ -33,4 +33,4 @@ + 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 -Nur linux-4.1.39.orig/ipc/mqueue.c linux-4.1.39/ipc/mqueue.c +--- linux-4.1.39.orig/ipc/mqueue.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/ipc/mqueue.c 2017-04-18 17:56:30.617397286 +0200 +@@ -47,8 +47,7 @@ + #define RECV 1 + + #define STATE_NONE 0 +-#define STATE_PENDING 1 +-#define STATE_READY 2 ++#define STATE_READY 1 + + struct posix_msg_tree_node { + struct rb_node rb_node; +@@ -568,15 +567,12 @@ + wq_add(info, sr, ewp); + + for (;;) { +- set_current_state(TASK_INTERRUPTIBLE); ++ __set_current_state(TASK_INTERRUPTIBLE); + + spin_unlock(&info->lock); + time = schedule_hrtimeout_range_clock(timeout, 0, + HRTIMER_MODE_ABS, CLOCK_REALTIME); + +- while (ewp->state == STATE_PENDING) +- cpu_relax(); +- + if (ewp->state == STATE_READY) { + retval = 0; + goto out; +@@ -904,11 +900,15 @@ + * list of waiting receivers. A sender checks that list before adding the new + * message into the message array. If there is a waiting receiver, then it + * bypasses the message array and directly hands the message over to the +- * receiver. +- * The receiver accepts the message and returns without grabbing the queue +- * spinlock. Therefore an intermediate STATE_PENDING state and memory barriers +- * are necessary. The same algorithm is used for sysv semaphores, see +- * ipc/sem.c for more details. ++ * receiver. The receiver accepts the message and returns without grabbing the ++ * queue spinlock: ++ * ++ * - Set pointer to message. ++ * - Queue the receiver task for later wakeup (without the info->lock). ++ * - Update its state to STATE_READY. Now the receiver can continue. ++ * - Wake up the process after the lock is dropped. Should the process wake up ++ * before this wakeup (due to a timeout or a signal) it will either see ++ * STATE_READY and continue or acquire the lock to check the state again. + * + * The same algorithm is used for senders. + */ +@@ -916,21 +916,29 @@ + /* pipelined_send() - send a message directly to the task waiting in + * sys_mq_timedreceive() (without inserting message into a queue). + */ +-static inline void pipelined_send(struct mqueue_inode_info *info, ++static inline void pipelined_send(struct wake_q_head *wake_q, ++ struct mqueue_inode_info *info, + struct msg_msg *message, + struct ext_wait_queue *receiver) + { + receiver->msg = message; + list_del(&receiver->list); +- receiver->state = STATE_PENDING; +- wake_up_process(receiver->task); +- smp_wmb(); ++ wake_q_add(wake_q, receiver->task); ++ /* ++ * Rely on the implicit cmpxchg barrier from wake_q_add such ++ * that we can ensure that updating receiver->state is the last ++ * write operation: As once set, the receiver can continue, ++ * and if we don't have the reference count from the wake_q, ++ * yet, at that point we can later have a use-after-free ++ * condition and bogus wakeup. ++ */ + receiver->state = STATE_READY; + } + + /* pipelined_receive() - if there is task waiting in sys_mq_timedsend() + * gets its message and put to the queue (we have one free place for sure). */ +-static inline void pipelined_receive(struct mqueue_inode_info *info) ++static inline void pipelined_receive(struct wake_q_head *wake_q, ++ struct mqueue_inode_info *info) + { + struct ext_wait_queue *sender = wq_get_first_waiter(info, SEND); + +@@ -941,10 +949,9 @@ + } + if (msg_insert(sender->msg, info)) + return; ++ + list_del(&sender->list); +- sender->state = STATE_PENDING; +- wake_up_process(sender->task); +- smp_wmb(); ++ wake_q_add(wake_q, sender->task); + sender->state = STATE_READY; + } + +@@ -962,6 +969,7 @@ + struct timespec ts; + struct posix_msg_tree_node *new_leaf = NULL; + int ret = 0; ++ WAKE_Q(wake_q); + + if (u_abs_timeout) { + int res = prepare_timeout(u_abs_timeout, &expires, &ts); +@@ -1045,7 +1053,7 @@ + } else { + receiver = wq_get_first_waiter(info, RECV); + if (receiver) { +- pipelined_send(info, msg_ptr, receiver); ++ pipelined_send(&wake_q, info, msg_ptr, receiver); + } else { + /* adds message to the queue */ + ret = msg_insert(msg_ptr, info); +@@ -1058,6 +1066,7 @@ + } + out_unlock: + spin_unlock(&info->lock); ++ wake_up_q(&wake_q); + out_free: + if (ret) + free_msg(msg_ptr); +@@ -1144,14 +1153,17 @@ + msg_ptr = wait.msg; + } + } else { ++ WAKE_Q(wake_q); ++ + msg_ptr = msg_get(info); + + inode->i_atime = inode->i_mtime = inode->i_ctime = + CURRENT_TIME; + + /* There is now free space in queue. */ +- pipelined_receive(info); ++ pipelined_receive(&wake_q, info); + spin_unlock(&info->lock); ++ wake_up_q(&wake_q); + ret = 0; + } + if (ret == 0) { +diff -Nur linux-4.1.39.orig/ipc/msg.c linux-4.1.39/ipc/msg.c +--- linux-4.1.39.orig/ipc/msg.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/ipc/msg.c 2017-04-18 17:56:30.617397286 +0200 +@@ -188,6 +188,12 @@ + struct msg_receiver *msr, *t; + + list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { ++ /* ++ * Make sure that the wakeup doesnt preempt ++ * this CPU prematurely. (on PREEMPT_RT) ++ */ ++ preempt_disable_rt(); ++ + msr->r_msg = NULL; /* initialize expunge ordering */ + wake_up_process(msr->r_tsk); + /* +@@ -198,6 +204,8 @@ + */ + smp_mb(); + msr->r_msg = ERR_PTR(res); ++ ++ preempt_enable_rt(); + } + } + +@@ -574,6 +582,11 @@ + if (testmsg(msg, msr->r_msgtype, msr->r_mode) && + !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) { +@@ -595,12 +608,13 @@ + */ + smp_mb(); + msr->r_msg = msg; ++ preempt_enable_rt(); + + return 1; + } ++ preempt_enable_rt(); + } + } +- + return 0; + } + +diff -Nur linux-4.1.39.orig/ipc/sem.c linux-4.1.39/ipc/sem.c +--- linux-4.1.39.orig/ipc/sem.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/ipc/sem.c 2017-04-18 17:56:30.617397286 +0200 +@@ -690,6 +690,13 @@ + 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 +@@ -701,6 +708,7 @@ + q->pid = error; + + list_add_tail(&q->list, pt); ++#endif + } + + /** +@@ -714,6 +722,7 @@ + */ + static void wake_up_sem_queue_do(struct list_head *pt) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + struct sem_queue *q, *t; + int did_something; + +@@ -726,6 +735,7 @@ + } + if (did_something) + preempt_enable(); ++#endif + } + + static void unlink_queue(struct sem_array *sma, struct sem_queue *q) +diff -Nur linux-4.1.39.orig/kernel/bpf/hashtab.c linux-4.1.39/kernel/bpf/hashtab.c +--- linux-4.1.39.orig/kernel/bpf/hashtab.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/bpf/hashtab.c 2017-04-18 17:56:30.617397286 +0200 +@@ -17,7 +17,7 @@ + struct bpf_htab { + struct bpf_map map; + struct hlist_head *buckets; +- spinlock_t lock; ++ raw_spinlock_t lock; + u32 count; /* number of elements in this hashtable */ + u32 n_buckets; /* number of hash buckets */ + u32 elem_size; /* size of each element in bytes */ +@@ -82,7 +82,7 @@ + for (i = 0; i < htab->n_buckets; i++) + INIT_HLIST_HEAD(&htab->buckets[i]); + +- spin_lock_init(&htab->lock); ++ raw_spin_lock_init(&htab->lock); + htab->count = 0; + + htab->elem_size = sizeof(struct htab_elem) + +@@ -230,7 +230,7 @@ + l_new->hash = htab_map_hash(l_new->key, key_size); + + /* bpf_map_update_elem() can be called in_irq() */ +- spin_lock_irqsave(&htab->lock, flags); ++ raw_spin_lock_irqsave(&htab->lock, flags); + + head = select_bucket(htab, l_new->hash); + +@@ -266,11 +266,11 @@ + } else { + htab->count++; + } +- spin_unlock_irqrestore(&htab->lock, flags); ++ raw_spin_unlock_irqrestore(&htab->lock, flags); + + return 0; + err: +- spin_unlock_irqrestore(&htab->lock, flags); ++ raw_spin_unlock_irqrestore(&htab->lock, flags); + kfree(l_new); + return ret; + } +@@ -291,7 +291,7 @@ + + hash = htab_map_hash(key, key_size); + +- spin_lock_irqsave(&htab->lock, flags); ++ raw_spin_lock_irqsave(&htab->lock, flags); + + head = select_bucket(htab, hash); + +@@ -304,7 +304,7 @@ + ret = 0; + } + +- spin_unlock_irqrestore(&htab->lock, flags); ++ raw_spin_unlock_irqrestore(&htab->lock, flags); + return ret; + } + +diff -Nur linux-4.1.39.orig/kernel/cgroup.c linux-4.1.39/kernel/cgroup.c +--- linux-4.1.39.orig/kernel/cgroup.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/cgroup.c 2017-04-18 17:56:30.617397286 +0200 +@@ -4423,10 +4423,10 @@ + queue_work(cgroup_destroy_wq, &css->destroy_work); + } + +-static void css_release_work_fn(struct work_struct *work) ++static void css_release_work_fn(struct swork_event *sev) + { + struct cgroup_subsys_state *css = +- container_of(work, struct cgroup_subsys_state, destroy_work); ++ container_of(sev, struct cgroup_subsys_state, destroy_swork); + struct cgroup_subsys *ss = css->ss; + struct cgroup *cgrp = css->cgroup; + +@@ -4465,8 +4465,8 @@ + struct cgroup_subsys_state *css = + container_of(ref, struct cgroup_subsys_state, refcnt); + +- INIT_WORK(&css->destroy_work, css_release_work_fn); +- queue_work(cgroup_destroy_wq, &css->destroy_work); ++ INIT_SWORK(&css->destroy_swork, css_release_work_fn); ++ swork_queue(&css->destroy_swork); + } + + static void init_and_link_css(struct cgroup_subsys_state *css, +@@ -5080,6 +5080,7 @@ + */ + cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); + BUG_ON(!cgroup_destroy_wq); ++ BUG_ON(swork_get()); + + /* + * Used to destroy pidlists and separate to serve as flush domain. +diff -Nur linux-4.1.39.orig/kernel/cpu.c linux-4.1.39/kernel/cpu.c +--- linux-4.1.39.orig/kernel/cpu.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/cpu.c 2017-04-18 17:56:30.617397286 +0200 +@@ -74,8 +74,8 @@ + #endif + } cpu_hotplug = { + .active_writer = NULL, +- .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), + .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock), ++ .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), + #ifdef CONFIG_DEBUG_LOCK_ALLOC + .dep_map = {.name = "cpu_hotplug.lock" }, + #endif +@@ -88,6 +88,289 @@ + #define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map) + #define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map) + ++/** ++ * 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 ++ /* ++ * Note, on PREEMPT_RT, the hotplug lock must save the state of ++ * the task, otherwise the mutex will cause the task to fail ++ * to sleep when required. (Because it's called from migrate_disable()) ++ * ++ * The spinlock_t on PREEMPT_RT is a mutex that saves the task's ++ * state. ++ */ ++ 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 = this_cpu_ptr(&hotplug_pcp); ++ ++ if (!hp->unplug || hp->refcount || force || preempt_count() > 1 || ++ hp->unplug == current) { ++ 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 = this_cpu_ptr(&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 = this_cpu_ptr(&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) ++ 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_NO_SETAFFINITY; ++ set_cpus_allowed_ptr(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) + { +@@ -349,13 +632,15 @@ + /* 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; +@@ -363,7 +648,34 @@ + 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) { +@@ -389,8 +701,12 @@ + #endif + synchronize_rcu(); + ++ __cpu_unplug_wait(cpu); + smpboot_park_threads(cpu); + ++ /* Notifiers are done. Don't let any more tasks pin this CPU. */ ++ cpu_unplug_sync(cpu); ++ + /* + * So now all preempt/rcu users must observe !cpu_active(). + */ +@@ -427,9 +743,14 @@ + 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 -Nur linux-4.1.39.orig/kernel/cpuset.c linux-4.1.39/kernel/cpuset.c +--- linux-4.1.39.orig/kernel/cpuset.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/cpuset.c 2017-04-18 17:56:30.617397286 +0200 +@@ -284,7 +284,7 @@ + */ + + static DEFINE_MUTEX(cpuset_mutex); +-static DEFINE_SPINLOCK(callback_lock); ++static DEFINE_RAW_SPINLOCK(callback_lock); + + /* + * CPU / memory hotplug is handled asynchronously. +@@ -903,9 +903,9 @@ + continue; + rcu_read_unlock(); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cpumask_copy(cp->effective_cpus, new_cpus); +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + WARN_ON(!cgroup_on_dfl(cp->css.cgroup) && + !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); +@@ -970,9 +970,9 @@ + if (retval < 0) + return retval; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + /* use trialcs->cpus_allowed as a temp variable */ + update_cpumasks_hier(cs, trialcs->cpus_allowed); +@@ -1159,9 +1159,9 @@ + continue; + rcu_read_unlock(); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cp->effective_mems = *new_mems; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + WARN_ON(!cgroup_on_dfl(cp->css.cgroup) && + !nodes_equal(cp->mems_allowed, cp->effective_mems)); +@@ -1229,9 +1229,9 @@ + if (retval < 0) + goto done; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cs->mems_allowed = trialcs->mems_allowed; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + /* use trialcs->mems_allowed as a temp variable */ + update_nodemasks_hier(cs, &trialcs->mems_allowed); +@@ -1322,9 +1322,9 @@ + spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) + || (is_spread_page(cs) != is_spread_page(trialcs))); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cs->flags = trialcs->flags; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) + rebuild_sched_domains_locked(); +@@ -1726,7 +1726,7 @@ + cpuset_filetype_t type = seq_cft(sf)->private; + int ret = 0; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + + switch (type) { + case FILE_CPULIST: +@@ -1745,7 +1745,7 @@ + ret = -EINVAL; + } + +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + return ret; + } + +@@ -1962,12 +1962,12 @@ + + cpuset_inc(); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + if (cgroup_on_dfl(cs->css.cgroup)) { + cpumask_copy(cs->effective_cpus, parent->effective_cpus); + cs->effective_mems = parent->effective_mems; + } +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) + goto out_unlock; +@@ -1994,12 +1994,12 @@ + } + rcu_read_unlock(); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cs->mems_allowed = parent->mems_allowed; + cs->effective_mems = parent->mems_allowed; + cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); + cpumask_copy(cs->effective_cpus, parent->cpus_allowed); +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + out_unlock: + mutex_unlock(&cpuset_mutex); + return 0; +@@ -2038,7 +2038,7 @@ + static void cpuset_bind(struct cgroup_subsys_state *root_css) + { + mutex_lock(&cpuset_mutex); +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + + if (cgroup_on_dfl(root_css->cgroup)) { + cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); +@@ -2049,7 +2049,7 @@ + top_cpuset.mems_allowed = top_cpuset.effective_mems; + } + +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + mutex_unlock(&cpuset_mutex); + } + +@@ -2149,12 +2149,12 @@ + { + bool is_empty; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cpumask_copy(cs->cpus_allowed, new_cpus); + cpumask_copy(cs->effective_cpus, new_cpus); + cs->mems_allowed = *new_mems; + cs->effective_mems = *new_mems; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + /* + * Don't call update_tasks_cpumask() if the cpuset becomes empty, +@@ -2191,10 +2191,10 @@ + if (nodes_empty(*new_mems)) + *new_mems = parent_cs(cs)->effective_mems; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cpumask_copy(cs->effective_cpus, new_cpus); + cs->effective_mems = *new_mems; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + if (cpus_updated) + update_tasks_cpumask(cs); +@@ -2280,21 +2280,21 @@ + + /* synchronize cpus_allowed to cpu_active_mask */ + if (cpus_updated) { +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + if (!on_dfl) + cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); + cpumask_copy(top_cpuset.effective_cpus, &new_cpus); +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + /* we don't mess with cpumasks of tasks in top_cpuset */ + } + + /* synchronize mems_allowed to N_MEMORY */ + if (mems_updated) { +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + if (!on_dfl) + top_cpuset.mems_allowed = new_mems; + top_cpuset.effective_mems = new_mems; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + update_tasks_nodemask(&top_cpuset); + } + +@@ -2389,11 +2389,11 @@ + { + unsigned long flags; + +- spin_lock_irqsave(&callback_lock, flags); ++ raw_spin_lock_irqsave(&callback_lock, flags); + rcu_read_lock(); + guarantee_online_cpus(task_cs(tsk), pmask); + rcu_read_unlock(); +- spin_unlock_irqrestore(&callback_lock, flags); ++ raw_spin_unlock_irqrestore(&callback_lock, flags); + } + + void cpuset_cpus_allowed_fallback(struct task_struct *tsk) +@@ -2441,11 +2441,11 @@ + nodemask_t mask; + unsigned long flags; + +- spin_lock_irqsave(&callback_lock, flags); ++ raw_spin_lock_irqsave(&callback_lock, flags); + rcu_read_lock(); + guarantee_online_mems(task_cs(tsk), &mask); + rcu_read_unlock(); +- spin_unlock_irqrestore(&callback_lock, flags); ++ raw_spin_unlock_irqrestore(&callback_lock, flags); + + return mask; + } +@@ -2537,14 +2537,14 @@ + return 1; + + /* Not hardwall and node outside mems_allowed: scan up cpusets */ +- spin_lock_irqsave(&callback_lock, flags); ++ raw_spin_lock_irqsave(&callback_lock, flags); + + rcu_read_lock(); + cs = nearest_hardwall_ancestor(task_cs(current)); + allowed = node_isset(node, cs->mems_allowed); + rcu_read_unlock(); + +- spin_unlock_irqrestore(&callback_lock, flags); ++ raw_spin_unlock_irqrestore(&callback_lock, flags); + return allowed; + } + +diff -Nur linux-4.1.39.orig/kernel/debug/kdb/kdb_io.c linux-4.1.39/kernel/debug/kdb/kdb_io.c +--- linux-4.1.39.orig/kernel/debug/kdb/kdb_io.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/debug/kdb/kdb_io.c 2017-04-18 17:56:30.617397286 +0200 +@@ -554,7 +554,6 @@ + int linecount; + int colcount; + int logging, saved_loglevel = 0; +- int saved_trap_printk; + int got_printf_lock = 0; + int retlen = 0; + int fnd, len; +@@ -565,8 +564,6 @@ + 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, +@@ -855,7 +852,6 @@ + } else { + __release(kdb_printf_lock); + } +- kdb_trap_printk = saved_trap_printk; + preempt_enable(); + return retlen; + } +@@ -865,9 +861,11 @@ + va_list ap; + int r; + ++ kdb_trap_printk++; + va_start(ap, fmt); + r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap); + va_end(ap); ++ kdb_trap_printk--; + + return r; + } +diff -Nur linux-4.1.39.orig/kernel/events/core.c linux-4.1.39/kernel/events/core.c +--- linux-4.1.39.orig/kernel/events/core.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/events/core.c 2017-04-18 17:56:30.621397441 +0200 +@@ -6948,6 +6948,7 @@ + + 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 -Nur linux-4.1.39.orig/kernel/exit.c linux-4.1.39/kernel/exit.c +--- linux-4.1.39.orig/kernel/exit.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/exit.c 2017-04-18 17:56:30.621397441 +0200 +@@ -144,7 +144,7 @@ + * 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 -Nur linux-4.1.39.orig/kernel/fork.c linux-4.1.39/kernel/fork.c +--- linux-4.1.39.orig/kernel/fork.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/fork.c 2017-04-18 17:56:30.621397441 +0200 +@@ -108,7 +108,7 @@ + + 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) +@@ -244,7 +244,9 @@ + if (atomic_dec_and_test(&sig->sigcnt)) + free_signal_struct(sig); + } +- ++#ifdef CONFIG_PREEMPT_RT_BASE ++static ++#endif + void __put_task_struct(struct task_struct *tsk) + { + WARN_ON(!tsk->exit_state); +@@ -260,7 +262,18 @@ + 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 + + void __init __weak arch_task_cache_init(void) { } + +@@ -374,6 +387,7 @@ + #endif + tsk->splice_pipe = NULL; + tsk->task_frag.page = NULL; ++ tsk->wake_q.next = NULL; + + account_kernel_stack(ti, 1); + +@@ -680,6 +694,19 @@ + } + 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. + */ +@@ -1214,6 +1241,9 @@ + */ + 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; +@@ -1338,6 +1368,7 @@ + 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; +@@ -1345,7 +1376,8 @@ + p->prev_cputime.utime = p->prev_cputime.stime = 0; + #endif + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +- seqlock_init(&p->vtime_seqlock); ++ raw_spin_lock_init(&p->vtime_lock); ++ seqcount_init(&p->vtime_seq); + p->vtime_snap = 0; + p->vtime_snap_whence = VTIME_SLEEPING; + #endif +@@ -1396,6 +1428,9 @@ + p->hardirq_context = 0; + p->softirq_context = 0; + #endif ++ ++ p->pagefault_disabled = 0; ++ + #ifdef CONFIG_LOCKDEP + p->lockdep_depth = 0; /* no locks held yet */ + p->curr_chain_key = 0; +diff -Nur linux-4.1.39.orig/kernel/futex.c linux-4.1.39/kernel/futex.c +--- linux-4.1.39.orig/kernel/futex.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/futex.c 2017-04-18 17:56:30.621397441 +0200 +@@ -738,7 +738,9 @@ + * task still owns the PI-state: + */ + if (head->next != next) { ++ raw_spin_unlock_irq(&curr->pi_lock); + spin_unlock(&hb->lock); ++ raw_spin_lock_irq(&curr->pi_lock); + continue; + } + +@@ -1090,9 +1092,11 @@ + + /* + * The hash bucket lock must be held when this is called. +- * Afterwards, the futex_q must not be accessed. ++ * Afterwards, the futex_q must not be accessed. Callers ++ * must ensure to later call wake_up_q() for the actual ++ * wakeups to occur. + */ +-static void wake_futex(struct futex_q *q) ++static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q) + { + struct task_struct *p = q->task; + +@@ -1100,14 +1104,10 @@ + return; + + /* +- * We set q->lock_ptr = NULL _before_ we wake up the task. If +- * a non-futex wake up happens on another CPU then the task +- * might exit and p would dereference a non-existing task +- * struct. Prevent this by holding a reference on p across the +- * wake up. ++ * Queue the task for later wakeup for after we've released ++ * the hb->lock. wake_q_add() grabs reference to p. + */ +- get_task_struct(p); +- ++ wake_q_add(wake_q, p); + __unqueue_futex(q); + /* + * The waiting task can free the futex_q as soon as +@@ -1117,16 +1117,15 @@ + */ + smp_wmb(); + q->lock_ptr = NULL; +- +- wake_up_state(p, TASK_NORMAL); +- put_task_struct(p); + } + +-static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) ++static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this, ++ struct futex_hash_bucket *hb) + { + struct task_struct *new_owner; + struct futex_pi_state *pi_state = this->pi_state; + u32 uninitialized_var(curval), newval; ++ bool deboost; + int ret = 0; + + if (!pi_state) +@@ -1188,7 +1187,17 @@ + raw_spin_unlock_irq(&new_owner->pi_lock); + + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); +- rt_mutex_unlock(&pi_state->pi_mutex); ++ ++ deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex); ++ ++ /* ++ * We deboost after dropping hb->lock. That prevents a double ++ * wakeup on RT. ++ */ ++ spin_unlock(&hb->lock); ++ ++ if (deboost) ++ rt_mutex_adjust_prio(current); + + return 0; + } +@@ -1227,6 +1236,7 @@ + struct futex_q *this, *next; + union futex_key key = FUTEX_KEY_INIT; + int ret; ++ WAKE_Q(wake_q); + + if (!bitset) + return -EINVAL; +@@ -1254,13 +1264,14 @@ + if (!(this->bitset & bitset)) + continue; + +- wake_futex(this); ++ mark_wake_futex(&wake_q, this); + if (++ret >= nr_wake) + break; + } + } + + spin_unlock(&hb->lock); ++ wake_up_q(&wake_q); + out_put_key: + put_futex_key(&key); + out: +@@ -1279,6 +1290,7 @@ + struct futex_hash_bucket *hb1, *hb2; + struct futex_q *this, *next; + int ret, op_ret; ++ WAKE_Q(wake_q); + + retry: + ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ); +@@ -1330,7 +1342,7 @@ + ret = -EINVAL; + goto out_unlock; + } +- wake_futex(this); ++ mark_wake_futex(&wake_q, this); + if (++ret >= nr_wake) + break; + } +@@ -1344,7 +1356,7 @@ + ret = -EINVAL; + goto out_unlock; + } +- wake_futex(this); ++ mark_wake_futex(&wake_q, this); + if (++op_ret >= nr_wake2) + break; + } +@@ -1354,6 +1366,7 @@ + + out_unlock: + double_unlock_hb(hb1, hb2); ++ wake_up_q(&wake_q); + out_put_keys: + put_futex_key(&key2); + out_put_key1: +@@ -1513,6 +1526,7 @@ + struct futex_pi_state *pi_state = NULL; + struct futex_hash_bucket *hb1, *hb2; + struct futex_q *this, *next; ++ WAKE_Q(wake_q); + + if (requeue_pi) { + /* +@@ -1689,7 +1703,7 @@ + * woken by futex_unlock_pi(). + */ + if (++task_count <= nr_wake && !requeue_pi) { +- wake_futex(this); ++ mark_wake_futex(&wake_q, this); + continue; + } + +@@ -1715,6 +1729,16 @@ + 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; +@@ -1729,6 +1753,7 @@ + out_unlock: + free_pi_state(pi_state); + double_unlock_hb(hb1, hb2); ++ wake_up_q(&wake_q); + hb_waiters_dec(hb2); + + /* +@@ -2422,13 +2447,22 @@ + */ + match = futex_top_waiter(hb, &key); + if (match) { +- ret = wake_futex_pi(uaddr, uval, match); ++ ret = wake_futex_pi(uaddr, uval, match, hb); ++ ++ /* ++ * In case of success wake_futex_pi dropped the hash ++ * bucket lock. ++ */ ++ if (!ret) ++ goto out_putkey; ++ + /* + * The atomic access to the futex value generated a + * pagefault, so retry the user-access and the wakeup: + */ + if (ret == -EFAULT) + goto pi_faulted; ++ + /* + * A unconditional UNLOCK_PI op raced against a waiter + * setting the FUTEX_WAITERS bit. Try again. +@@ -2438,6 +2472,11 @@ + put_futex_key(&key); + goto retry; + } ++ ++ /* ++ * wake_futex_pi has detected invalid state. Tell user ++ * space. ++ */ + goto out_unlock; + } + +@@ -2458,6 +2497,7 @@ + + out_unlock: + spin_unlock(&hb->lock); ++out_putkey: + put_futex_key(&key); + return ret; + +@@ -2568,7 +2608,7 @@ + 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; +@@ -2593,10 +2633,7 @@ + * The waiter is allocated on our stack, manipulated by the requeue + * code while we sleep on uaddr. + */ +- debug_rt_mutex_init_waiter(&rt_waiter); +- RB_CLEAR_NODE(&rt_waiter.pi_tree_entry); +- RB_CLEAR_NODE(&rt_waiter.tree_entry); +- 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)) +@@ -2627,20 +2664,55 @@ + /* 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) { +@@ -2649,14 +2721,15 @@ + * 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); + /* + * Drop the reference to the pi state which + * the requeue_pi() code acquired for us. + */ + free_pi_state(q.pi_state); +- spin_unlock(q.lock_ptr); ++ spin_unlock(&hb2->lock); + } + } else { + /* +@@ -2669,7 +2742,8 @@ + 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 -Nur linux-4.1.39.orig/kernel/irq/handle.c linux-4.1.39/kernel/irq/handle.c +--- linux-4.1.39.orig/kernel/irq/handle.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/irq/handle.c 2017-04-18 17:56:30.621397441 +0200 +@@ -133,6 +133,8 @@ + 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; + +@@ -173,7 +175,11 @@ + 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 -Nur linux-4.1.39.orig/kernel/irq/manage.c linux-4.1.39/kernel/irq/manage.c +--- linux-4.1.39.orig/kernel/irq/manage.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/irq/manage.c 2017-04-18 17:56:30.621397441 +0200 +@@ -22,6 +22,7 @@ + #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) +@@ -30,6 +31,7 @@ + return 0; + } + early_param("threadirqs", setup_forced_irqthreads); ++# endif + #endif + + static void __synchronize_hardirq(struct irq_desc *desc) +@@ -179,6 +181,62 @@ + 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_do_set_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) + { +@@ -218,7 +276,17 @@ + + 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); + +@@ -256,10 +324,8 @@ + } + 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; +@@ -281,6 +347,13 @@ + 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 +@@ -310,6 +383,8 @@ + 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); +@@ -697,6 +772,12 @@ + return IRQ_NONE; + } + ++static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id) ++{ ++ WARN(1, "Secondary action handler called for irq %d\n", irq); ++ return IRQ_NONE; ++} ++ + static int irq_wait_for_interrupt(struct irqaction *action) + { + set_current_state(TASK_INTERRUPTIBLE); +@@ -723,7 +804,8 @@ + static void irq_finalize_oneshot(struct irq_desc *desc, + struct irqaction *action) + { +- if (!(desc->istate & IRQS_ONESHOT)) ++ if (!(desc->istate & IRQS_ONESHOT) || ++ action->handler == irq_forced_secondary_handler) + return; + again: + chip_bus_lock(desc); +@@ -825,7 +907,15 @@ + 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; + } + +@@ -877,6 +967,18 @@ + irq_finalize_oneshot(desc, action); + } + ++static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action) ++{ ++ struct irqaction *secondary = action->secondary; ++ ++ if (WARN_ON_ONCE(!secondary)) ++ return; ++ ++ raw_spin_lock_irq(&desc->lock); ++ __irq_wake_thread(desc, secondary); ++ raw_spin_unlock_irq(&desc->lock); ++} ++ + /* + * Interrupt handler thread + */ +@@ -907,7 +1009,15 @@ + action_ret = handler_fn(desc, action); + if (action_ret == IRQ_HANDLED) + atomic_inc(&desc->threads_handled); ++ if (action_ret == IRQ_WAKE_THREAD) ++ irq_wake_secondary(desc, action); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ migrate_disable(); ++ add_interrupt_randomness(action->irq, 0, ++ desc->random_ip ^ (unsigned long) action); ++ migrate_enable(); ++#endif + wake_threads_waitq(desc); + } + +@@ -951,20 +1061,36 @@ + } + EXPORT_SYMBOL_GPL(irq_wake_thread); + +-static void irq_setup_forced_threading(struct irqaction *new) ++static int irq_setup_forced_threading(struct irqaction *new) + { + if (!force_irqthreads) +- return; ++ return 0; + if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)) +- return; ++ return 0; + + new->flags |= IRQF_ONESHOT; + +- if (!new->thread_fn) { +- set_bit(IRQTF_FORCED_THREAD, &new->thread_flags); +- new->thread_fn = new->handler; +- new->handler = irq_default_primary_handler; +- } ++ /* ++ * Handle the case where we have a real primary handler and a ++ * thread handler. We force thread them as well by creating a ++ * secondary action. ++ */ ++ if (new->handler != irq_default_primary_handler && new->thread_fn) { ++ /* Allocate the secondary action */ ++ new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL); ++ if (!new->secondary) ++ return -ENOMEM; ++ new->secondary->handler = irq_forced_secondary_handler; ++ new->secondary->thread_fn = new->thread_fn; ++ new->secondary->dev_id = new->dev_id; ++ new->secondary->irq = new->irq; ++ new->secondary->name = new->name; ++ } ++ /* Deal with the primary handler */ ++ set_bit(IRQTF_FORCED_THREAD, &new->thread_flags); ++ new->thread_fn = new->handler; ++ new->handler = irq_default_primary_handler; ++ return 0; + } + + static int irq_request_resources(struct irq_desc *desc) +@@ -984,6 +1110,48 @@ + c->irq_release_resources(d); + } + ++static int ++setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary) ++{ ++ struct task_struct *t; ++ struct sched_param param = { ++ .sched_priority = MAX_USER_RT_PRIO/2, ++ }; ++ ++ if (!secondary) { ++ t = kthread_create(irq_thread, new, "irq/%d-%s", irq, ++ new->name); ++ } else { ++ t = kthread_create(irq_thread, new, "irq/%d-s-%s", irq, ++ new->name); ++ param.sched_priority += 1; ++ } ++ ++ if (IS_ERR(t)) ++ return PTR_ERR(t); ++ ++ 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 ++ * references an already freed task_struct. ++ */ ++ get_task_struct(t); ++ new->thread = t; ++ /* ++ * Tell the thread to set its affinity. This is ++ * important for shared interrupt handlers as we do ++ * not invoke setup_affinity() for the secondary ++ * handlers as everything is already set up. Even for ++ * interrupts marked with IRQF_NO_BALANCE this is ++ * correct as we want the thread to move to the cpu(s) ++ * on which the requesting code placed the interrupt. ++ */ ++ set_bit(IRQTF_AFFINITY, &new->thread_flags); ++ return 0; ++} ++ + /* + * Internal function to register an irqaction - typically used to + * allocate special interrupts that are part of the architecture. +@@ -1004,6 +1172,8 @@ + if (!try_module_get(desc->owner)) + return -ENODEV; + ++ new->irq = irq; ++ + /* + * Check whether the interrupt nests into another interrupt + * thread. +@@ -1021,8 +1191,11 @@ + */ + new->handler = irq_nested_primary_handler; + } else { +- if (irq_settings_can_thread(desc)) +- irq_setup_forced_threading(new); ++ if (irq_settings_can_thread(desc)) { ++ ret = irq_setup_forced_threading(new); ++ if (ret) ++ goto out_mput; ++ } + } + + /* +@@ -1031,37 +1204,14 @@ + * thread. + */ + 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); +- if (IS_ERR(t)) { +- ret = PTR_ERR(t); ++ ret = setup_irq_thread(new, irq, false); ++ if (ret) + goto out_mput; ++ if (new->secondary) { ++ ret = setup_irq_thread(new->secondary, irq, true); ++ if (ret) ++ goto out_thread; + } +- +- 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 +- * references an already freed task_struct. +- */ +- get_task_struct(t); +- new->thread = t; +- /* +- * Tell the thread to set its affinity. This is +- * important for shared interrupt handlers as we do +- * not invoke setup_affinity() for the secondary +- * handlers as everything is already set up. Even for +- * interrupts marked with IRQF_NO_BALANCE this is +- * correct as we want the thread to move to the cpu(s) +- * on which the requesting code placed the interrupt. +- */ +- set_bit(IRQTF_AFFINITY, &new->thread_flags); + } + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) { +@@ -1221,6 +1371,9 @@ + 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); + +@@ -1234,7 +1387,6 @@ + irq, nmsk, omsk); + } + +- new->irq = irq; + *old_ptr = new; + + irq_pm_install_action(desc, new); +@@ -1260,6 +1412,8 @@ + */ + if (new->thread) + wake_up_process(new->thread); ++ if (new->secondary) ++ wake_up_process(new->secondary->thread); + + register_irq_proc(irq, desc); + new->dir = NULL; +@@ -1290,6 +1444,13 @@ + kthread_stop(t); + put_task_struct(t); + } ++ if (new->secondary && new->secondary->thread) { ++ struct task_struct *t = new->secondary->thread; ++ ++ new->secondary->thread = NULL; ++ kthread_stop(t); ++ put_task_struct(t); ++ } + out_mput: + module_put(desc->owner); + return ret; +@@ -1397,9 +1558,14 @@ + if (action->thread) { + kthread_stop(action->thread); + put_task_struct(action->thread); ++ if (action->secondary && action->secondary->thread) { ++ kthread_stop(action->secondary->thread); ++ put_task_struct(action->secondary->thread); ++ } + } + + module_put(desc->owner); ++ kfree(action->secondary); + return action; + } + +@@ -1543,8 +1709,10 @@ + retval = __setup_irq(irq, desc, action); + chip_bus_sync_unlock(desc); + +- if (retval) ++ if (retval) { ++ kfree(action->secondary); + kfree(action); ++ } + + #ifdef CONFIG_DEBUG_SHIRQ_FIXME + if (!retval && (irqflags & IRQF_SHARED)) { +diff -Nur linux-4.1.39.orig/kernel/irq/settings.h linux-4.1.39/kernel/irq/settings.h +--- linux-4.1.39.orig/kernel/irq/settings.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/irq/settings.h 2017-04-18 17:56:30.621397441 +0200 +@@ -15,6 +15,7 @@ + _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, + _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, + _IRQ_IS_POLLED = IRQ_IS_POLLED, ++ _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL, + _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, + }; + +@@ -28,6 +29,7 @@ + #define IRQ_NESTED_THREAD GOT_YOU_MORON + #define IRQ_PER_CPU_DEVID GOT_YOU_MORON + #define IRQ_IS_POLLED GOT_YOU_MORON ++#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON + #undef IRQF_MODIFY_MASK + #define IRQF_MODIFY_MASK GOT_YOU_MORON + +@@ -38,6 +40,16 @@ + 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 -Nur linux-4.1.39.orig/kernel/irq/spurious.c linux-4.1.39/kernel/irq/spurious.c +--- linux-4.1.39.orig/kernel/irq/spurious.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/irq/spurious.c 2017-04-18 17:56:30.621397441 +0200 +@@ -444,6 +444,10 @@ + + static int __init irqfixup_setup(char *str) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); ++ return 1; ++#endif + irqfixup = 1; + printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); + printk(KERN_WARNING "This may impact system performance.\n"); +@@ -456,6 +460,10 @@ + + static int __init irqpoll_setup(char *str) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); ++ return 1; ++#endif + irqfixup = 2; + printk(KERN_WARNING "Misrouted IRQ fixup and polling support " + "enabled\n"); +diff -Nur linux-4.1.39.orig/kernel/irq_work.c linux-4.1.39/kernel/irq_work.c +--- linux-4.1.39.orig/kernel/irq_work.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/irq_work.c 2017-04-18 17:56:30.621397441 +0200 +@@ -17,6 +17,7 @@ + #include + #include + #include ++#include + #include + + +@@ -65,6 +66,8 @@ + */ + bool irq_work_queue_on(struct irq_work *work, int cpu) + { ++ struct llist_head *list; ++ + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(cpu)); + +@@ -75,7 +78,12 @@ + if (!irq_work_claim(work)) + return false; + +- if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ)) ++ list = &per_cpu(lazy_list, cpu); ++ else ++ list = &per_cpu(raised_list, cpu); ++ ++ if (llist_add(&work->llnode, list)) + arch_send_call_function_single_ipi(cpu); + + return true; +@@ -86,6 +94,9 @@ + /* Enqueue the irq work @work on the current CPU */ + bool irq_work_queue(struct irq_work *work) + { ++ struct llist_head *list; ++ bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); ++ + /* Only queue if not already pending */ + if (!irq_work_claim(work)) + return false; +@@ -93,13 +104,15 @@ + /* Queue the entry and raise the IPI if needed. */ + preempt_disable(); + +- /* If the work is "lazy", handle it from next tick if any */ +- if (work->flags & IRQ_WORK_LAZY) { +- if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && +- tick_nohz_tick_stopped()) +- arch_irq_work_raise(); +- } else { +- if (llist_add(&work->llnode, this_cpu_ptr(&raised_list))) ++ lazy_work = work->flags & IRQ_WORK_LAZY; ++ ++ if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ))) ++ list = this_cpu_ptr(&lazy_list); ++ else ++ list = this_cpu_ptr(&raised_list); ++ ++ if (llist_add(&work->llnode, list)) { ++ if (!lazy_work || tick_nohz_tick_stopped()) + arch_irq_work_raise(); + } + +@@ -116,9 +129,8 @@ + raised = this_cpu_ptr(&raised_list); + lazy = this_cpu_ptr(&lazy_list); + +- if (llist_empty(raised) || arch_irq_work_has_interrupt()) +- if (llist_empty(lazy)) +- return false; ++ if (llist_empty(raised) && llist_empty(lazy)) ++ return false; + + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); +@@ -132,7 +144,7 @@ + struct irq_work *work; + struct llist_node *llnode; + +- BUG_ON(!irqs_disabled()); ++ BUG_ON_NONRT(!irqs_disabled()); + + if (llist_empty(list)) + return; +@@ -169,7 +181,16 @@ + void irq_work_run(void) + { + irq_work_run_list(this_cpu_ptr(&raised_list)); +- irq_work_run_list(this_cpu_ptr(&lazy_list)); ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) { ++ /* ++ * NOTE: we raise softirq via IPI for safety, ++ * and execute in irq_work_tick() to move the ++ * overhead from hard to soft irq context. ++ */ ++ if (!llist_empty(this_cpu_ptr(&lazy_list))) ++ raise_softirq(TIMER_SOFTIRQ); ++ } else ++ irq_work_run_list(this_cpu_ptr(&lazy_list)); + } + EXPORT_SYMBOL_GPL(irq_work_run); + +@@ -179,8 +200,17 @@ + + if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) + irq_work_run_list(raised); ++ ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) ++ irq_work_run_list(this_cpu_ptr(&lazy_list)); ++} ++ ++#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) ++void irq_work_tick_soft(void) ++{ + irq_work_run_list(this_cpu_ptr(&lazy_list)); + } ++#endif + + /* + * Synchronize against the irq_work @entry, ensures the entry is not +diff -Nur linux-4.1.39.orig/kernel/Kconfig.locks linux-4.1.39/kernel/Kconfig.locks +--- linux-4.1.39.orig/kernel/Kconfig.locks 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/Kconfig.locks 2017-04-18 17:56:30.617397286 +0200 +@@ -225,11 +225,11 @@ + + config MUTEX_SPIN_ON_OWNER + def_bool y +- depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW ++ depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL + + config RWSEM_SPIN_ON_OWNER + def_bool y +- depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW ++ depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL + + config LOCK_SPIN_ON_OWNER + def_bool y +diff -Nur linux-4.1.39.orig/kernel/Kconfig.preempt linux-4.1.39/kernel/Kconfig.preempt +--- linux-4.1.39.orig/kernel/Kconfig.preempt 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/Kconfig.preempt 2017-04-18 17:56:30.617397286 +0200 +@@ -1,3 +1,16 @@ ++config PREEMPT ++ bool ++ select PREEMPT_COUNT ++ ++config PREEMPT_RT_BASE ++ bool ++ select PREEMPT ++ ++config HAVE_PREEMPT_LAZY ++ bool ++ ++config PREEMPT_LAZY ++ def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL + + choice + prompt "Preemption Model" +@@ -33,9 +46,9 @@ + + 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 +65,22 @@ + 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 preemptible ++ RT kernel. ++ ++config PREEMPT_RT_FULL ++ bool "Fully Preemptible Kernel (RT)" ++ depends on IRQ_FORCED_THREADING ++ select PREEMPT_RT_BASE ++ select PREEMPT_RCU ++ help ++ All and everything ++ + endchoice + + config PREEMPT_COUNT +diff -Nur linux-4.1.39.orig/kernel/ksysfs.c linux-4.1.39/kernel/ksysfs.c +--- linux-4.1.39.orig/kernel/ksysfs.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/ksysfs.c 2017-04-18 17:56:30.621397441 +0200 +@@ -136,6 +136,15 @@ + + #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) +@@ -203,6 +212,9 @@ + &vmcoreinfo_attr.attr, + #endif + &rcu_expedited_attr.attr, ++#ifdef CONFIG_PREEMPT_RT_FULL ++ &realtime_attr.attr, ++#endif + NULL + }; + +diff -Nur linux-4.1.39.orig/kernel/locking/lglock.c linux-4.1.39/kernel/locking/lglock.c +--- linux-4.1.39.orig/kernel/locking/lglock.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/locking/lglock.c 2017-04-18 17:56:30.621397441 +0200 +@@ -4,6 +4,15 @@ + #include + #include + ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define lg_lock_ptr arch_spinlock_t ++# define lg_do_lock(l) arch_spin_lock(l) ++# define lg_do_unlock(l) arch_spin_unlock(l) ++#else ++# define lg_lock_ptr struct rt_mutex ++# define lg_do_lock(l) __rt_spin_lock(l) ++# define lg_do_unlock(l) __rt_spin_unlock(l) ++#endif + /* + * Note there is no uninit, so lglocks cannot be defined in + * modules (but it's fine to use them from there) +@@ -12,51 +21,60 @@ + + void lg_lock_init(struct lglock *lg, char *name) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int i; ++ ++ for_each_possible_cpu(i) { ++ struct rt_mutex *lock = per_cpu_ptr(lg->lock, i); ++ ++ rt_mutex_init(lock); ++ } ++#endif + LOCKDEP_INIT_MAP(&lg->lock_dep_map, name, &lg->lock_key, 0); + } + EXPORT_SYMBOL(lg_lock_init); + + void lg_local_lock(struct lglock *lg) + { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + +- preempt_disable(); ++ migrate_disable(); + lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + lock = this_cpu_ptr(lg->lock); +- arch_spin_lock(lock); ++ lg_do_lock(lock); + } + EXPORT_SYMBOL(lg_local_lock); + + void lg_local_unlock(struct lglock *lg) + { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + lock = this_cpu_ptr(lg->lock); +- arch_spin_unlock(lock); +- preempt_enable(); ++ lg_do_unlock(lock); ++ migrate_enable(); + } + EXPORT_SYMBOL(lg_local_unlock); + + void lg_local_lock_cpu(struct lglock *lg, int cpu) + { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + +- preempt_disable(); ++ preempt_disable_nort(); + lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + lock = per_cpu_ptr(lg->lock, cpu); +- arch_spin_lock(lock); ++ lg_do_lock(lock); + } + EXPORT_SYMBOL(lg_local_lock_cpu); + + void lg_local_unlock_cpu(struct lglock *lg, int cpu) + { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + lock = per_cpu_ptr(lg->lock, cpu); +- arch_spin_unlock(lock); +- preempt_enable(); ++ lg_do_unlock(lock); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(lg_local_unlock_cpu); + +@@ -64,12 +82,12 @@ + { + int i; + +- preempt_disable(); ++ preempt_disable_nort(); + lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + for_each_possible_cpu(i) { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + lock = per_cpu_ptr(lg->lock, i); +- arch_spin_lock(lock); ++ lg_do_lock(lock); + } + } + EXPORT_SYMBOL(lg_global_lock); +@@ -80,10 +98,35 @@ + + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + for_each_possible_cpu(i) { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + lock = per_cpu_ptr(lg->lock, i); +- arch_spin_unlock(lock); ++ lg_do_unlock(lock); + } +- preempt_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(lg_global_unlock); ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * HACK: If you use this, you get to keep the pieces. ++ * Used in queue_stop_cpus_work() when stop machinery ++ * is called from inactive CPU, so we can't schedule. ++ */ ++# define lg_do_trylock_relax(l) \ ++ do { \ ++ while (!__rt_spin_trylock(l)) \ ++ cpu_relax(); \ ++ } while (0) ++ ++void lg_global_trylock_relax(struct lglock *lg) ++{ ++ int i; ++ ++ lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); ++ for_each_possible_cpu(i) { ++ lg_lock_ptr *lock; ++ lock = per_cpu_ptr(lg->lock, i); ++ lg_do_trylock_relax(lock); ++ } ++} ++#endif +diff -Nur linux-4.1.39.orig/kernel/locking/lockdep.c linux-4.1.39/kernel/locking/lockdep.c +--- linux-4.1.39.orig/kernel/locking/lockdep.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/locking/lockdep.c 2017-04-18 17:56:30.621397441 +0200 +@@ -668,6 +668,7 @@ + struct lockdep_subclass_key *key; + struct list_head *hash_head; + struct lock_class *class; ++ bool is_static = false; + + #ifdef CONFIG_DEBUG_LOCKDEP + /* +@@ -695,10 +696,23 @@ + + /* + * Static locks do not have their class-keys yet - for them the key +- * is the lock object itself: +- */ +- if (unlikely(!lock->key)) +- lock->key = (void *)lock; ++ * is the lock object itself. If the lock is in the per cpu area, ++ * the canonical address of the lock (per cpu offset removed) is ++ * used. ++ */ ++ if (unlikely(!lock->key)) { ++ unsigned long can_addr, addr = (unsigned long)lock; ++ ++ if (__is_kernel_percpu_address(addr, &can_addr)) ++ lock->key = (void *)can_addr; ++ else if (__is_module_percpu_address(addr, &can_addr)) ++ lock->key = (void *)can_addr; ++ else if (static_obj(lock)) ++ lock->key = (void *)lock; ++ else ++ return ERR_PTR(-EINVAL); ++ is_static = true; ++ } + + /* + * NOTE: the class-key must be unique. For dynamic locks, a static +@@ -730,7 +744,7 @@ + } + } + +- return NULL; ++ return is_static || static_obj(lock->key) ? NULL : ERR_PTR(-EINVAL); + } + + /* +@@ -748,19 +762,18 @@ + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + + class = look_up_lock_class(lock, subclass); +- if (likely(class)) ++ if (likely(!IS_ERR_OR_NULL(class))) + goto out_set_class_cache; + + /* + * Debug-check: all keys must be persistent! +- */ +- if (!static_obj(lock->key)) { ++ */ ++ if (IS_ERR(class)) { + debug_locks_off(); + printk("INFO: trying to register non-static key.\n"); + printk("the code is fine but needs lockdep annotation.\n"); + printk("turning off the locking correctness validator.\n"); + dump_stack(); +- + return NULL; + } + +@@ -3297,7 +3310,7 @@ + * Clearly if the lock hasn't been acquired _ever_, we're not + * holding it either, so report failure. + */ +- if (!class) ++ if (IS_ERR_OR_NULL(class)) + return 0; + + /* +@@ -3563,6 +3576,7 @@ + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * We dont accurately track softirq state in e.g. + * hardirq contexts (such as on 4KSTACKS), so only +@@ -3577,6 +3591,7 @@ + DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); + } + } ++#endif + + if (!debug_locks) + print_irqtrace_events(current); +@@ -3980,7 +3995,7 @@ + * If the class exists we look it up and zap it: + */ + class = look_up_lock_class(lock, j); +- if (class) ++ if (!IS_ERR_OR_NULL(class)) + zap_class(class); + } + /* +diff -Nur linux-4.1.39.orig/kernel/locking/locktorture.c linux-4.1.39/kernel/locking/locktorture.c +--- linux-4.1.39.orig/kernel/locking/locktorture.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/locking/locktorture.c 2017-04-18 17:56:30.621397441 +0200 +@@ -24,7 +24,6 @@ + #include + #include + #include +-#include + #include + #include + #include +diff -Nur linux-4.1.39.orig/kernel/locking/Makefile linux-4.1.39/kernel/locking/Makefile +--- linux-4.1.39.orig/kernel/locking/Makefile 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/locking/Makefile 2017-04-18 17:56:30.621397441 +0200 +@@ -1,5 +1,5 @@ + +-obj-y += mutex.o semaphore.o rwsem.o ++obj-y += semaphore.o + + ifdef CONFIG_FUNCTION_TRACER + CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) +@@ -8,7 +8,11 @@ + CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE) + endif + ++ifneq ($(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 +@@ -22,8 +26,11 @@ + obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o + obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o + obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o ++ifneq ($(CONFIG_PREEMPT_RT_FULL),y) + obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o + obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o ++endif + obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o ++obj-$(CONFIG_PREEMPT_RT_FULL) += rt.o + obj-$(CONFIG_QUEUE_RWLOCK) += qrwlock.o + obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o +diff -Nur linux-4.1.39.orig/kernel/locking/rt.c linux-4.1.39/kernel/locking/rt.c +--- linux-4.1.39.orig/kernel/locking/rt.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/kernel/locking/rt.c 2017-04-18 17:56:30.621397441 +0200 +@@ -0,0 +1,461 @@ ++/* ++ * 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; ++ ++ migrate_disable(); ++ ret = rt_mutex_trylock(&rwlock->lock); ++ 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; ++ ret = rt_write_trylock(rwlock); ++ 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. ++ */ ++ if (rt_mutex_owner(lock) != current) { ++ migrate_disable(); ++ ret = rt_mutex_trylock(lock); ++ if (ret) ++ rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ ++ } else if (!rwlock->read_depth) { ++ ret = 0; ++ } ++ ++ if (ret) ++ rwlock->read_depth++; ++ ++ return ret; ++} ++EXPORT_SYMBOL(rt_read_trylock); ++ ++void __lockfunc rt_write_lock(rwlock_t *rwlock) ++{ ++ rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); ++ migrate_disable(); ++ __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) { ++ migrate_disable(); ++ 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); ++ migrate_enable(); ++} ++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); ++ migrate_enable(); ++ } ++} ++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) ++ rt_mutex_unlock(&rwsem->lock); ++} ++ ++void rt_up_read(struct rw_semaphore *rwsem) ++{ ++ rwsem_release(&rwsem->dep_map, 1, _RET_IP_); ++ __rt_up_read(rwsem); ++} ++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); ++ ++void rt_down_write_nested_lock(struct rw_semaphore *rwsem, ++ struct lockdep_map *nest) ++{ ++ rwsem_acquire_nest(&rwsem->dep_map, 0, 0, nest, _RET_IP_); ++ rt_mutex_lock(&rwsem->lock); ++} ++EXPORT_SYMBOL(rt_down_write_nested_lock); ++ ++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); ++ else if (!rwsem->read_depth) ++ ret = 0; ++ ++ if (ret) { ++ rwsem->read_depth++; ++ rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); ++ } ++ 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; ++ ++ rwsem_acquire_read(&rwsem->dep_map, subclass, 0, _RET_IP_); ++ ++ if (rt_mutex_owner(lock) != current) ++ 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, 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 *)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 -Nur linux-4.1.39.orig/kernel/locking/rtmutex.c linux-4.1.39/kernel/locking/rtmutex.c +--- linux-4.1.39.orig/kernel/locking/rtmutex.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/locking/rtmutex.c 2017-04-18 17:56:30.625397596 +0200 +@@ -7,6 +7,11 @@ + * Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner + * 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/locking/rt-mutex-design.txt for details. + */ +@@ -16,6 +21,7 @@ + #include + #include + #include ++#include + + #include "rtmutex_common.h" + +@@ -69,6 +75,12 @@ + 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 +@@ -300,7 +312,7 @@ + * of task. We do not use the spin_xx_mutex() variants here as we are + * outside of the debug path.) + */ +-static void rt_mutex_adjust_prio(struct task_struct *task) ++void rt_mutex_adjust_prio(struct task_struct *task) + { + unsigned long flags; + +@@ -335,6 +347,14 @@ + return debug_rt_mutex_detect_deadlock(waiter, chwalk); + } + ++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); ++} ++ + /* + * Max number of times we'll walk the boosting chain: + */ +@@ -342,7 +362,8 @@ + + static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) + { +- return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; ++ return rt_mutex_real_waiter(p->pi_blocked_on) ? ++ p->pi_blocked_on->lock : NULL; + } + + /* +@@ -479,7 +500,7 @@ + * 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; + + /* +@@ -641,13 +662,16 @@ + * 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 [7] above changed the top waiter, + * then we need to wake the new top waiter up to try + * to get the lock. + */ +- if (prerequeue_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); + return 0; + } +@@ -740,6 +764,25 @@ + 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 + * +@@ -750,8 +793,9 @@ + * @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; + +@@ -790,8 +834,10 @@ + * If waiter is not the highest priority waiter of + * @lock, give up. + */ +- if (waiter != rt_mutex_top_waiter(lock)) ++ if (waiter != rt_mutex_top_waiter(lock)) { ++ /* XXX lock_is_stealable() ? */ + return 0; ++ } + + /* + * We can acquire the lock. Remove the waiter from the +@@ -809,14 +855,10 @@ + * not need to be dequeued. + */ + if (rt_mutex_has_waiters(lock)) { +- /* +- * If @task->prio is greater than or equal to +- * the top waiter priority (kernel view), +- * @task lost. +- */ +- if (task->prio >= rt_mutex_top_waiter(lock)->prio) +- return 0; ++ struct task_struct *pown = rt_mutex_top_waiter(lock)->task; + ++ 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 +@@ -865,6 +907,347 @@ + return 1; + } + ++#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_no_state_check(); ++ ++ 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) ++ ++static int task_blocks_on_rt_mutex(struct rt_mutex *lock, ++ struct rt_mutex_waiter *waiter, ++ struct task_struct *task, ++ enum rtmutex_chainwalk chwalk); ++/* ++ * 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); ++ ++ 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_no_track(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_no_track(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_no_track(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(!RB_EMPTY_NODE(&waiter.tree_entry)); ++ ++ raw_spin_unlock(&lock->wait_lock); ++ ++ debug_rt_mutex_free_waiter(&waiter); ++} ++ ++static void wakeup_next_waiter(struct rt_mutex *lock); ++/* ++ * Slow path to release a rt_mutex spin_lock style ++ */ ++static void noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) ++{ ++ raw_spin_lock(&lock->wait_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); ++} ++ ++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(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(struct rt_mutex *lock) ++{ ++ return rt_mutex_trylock(lock); ++} ++ ++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; ++ ret = rt_mutex_trylock(&lock->lock); ++ if (ret) { ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ } ++ 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 */ ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ static inline int __sched ++__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); ++ struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx); ++ ++ if (!hold_ctx) ++ return 0; ++ ++ if (unlikely(ctx == hold_ctx)) ++ return -EALREADY; ++ ++ if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && ++ (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { ++#ifdef CONFIG_DEBUG_MUTEXES ++ DEBUG_LOCKS_WARN_ON(ctx->contending_lock); ++ ctx->contending_lock = ww; ++#endif ++ return -EDEADLK; ++ } ++ ++ return 0; ++} ++#else ++ static inline int __sched ++__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ BUG(); ++ return 0; ++} ++ ++#endif ++ ++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. + * +@@ -896,6 +1279,23 @@ + 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; +@@ -919,7 +1319,7 @@ + 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 (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { + chain_walk = 1; +@@ -957,8 +1357,9 @@ + /* + * Wake up the next waiter on the lock. + * +- * Remove the top waiter from the current tasks pi waiter list and +- * wake it up. ++ * Remove the top waiter from the current tasks pi waiter list, ++ * wake it up and return whether the current task needs to undo ++ * a potential priority boosting. + * + * Called with lock->wait_lock held. + */ +@@ -996,7 +1397,7 @@ + * 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); + } + + /* +@@ -1010,7 +1411,7 @@ + { + bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); + struct task_struct *owner = rt_mutex_owner(lock); +- struct rt_mutex *next_lock; ++ struct rt_mutex *next_lock = NULL; + unsigned long flags; + + raw_spin_lock_irqsave(¤t->pi_lock, flags); +@@ -1035,7 +1436,8 @@ + __rt_mutex_adjust_prio(owner); + + /* Store the lock on which owner is blocked or NULL */ +- next_lock = task_blocked_on_lock(owner); ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) ++ next_lock = task_blocked_on_lock(owner); + + raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + +@@ -1071,17 +1473,17 @@ + raw_spin_lock_irqsave(&task->pi_lock, flags); + + waiter = task->pi_blocked_on; +- if (!waiter || (waiter->prio == task->prio && ++ if (!rt_mutex_real_waiter(waiter) || (waiter->prio == task->prio && + !dl_prio(task->prio))) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return; + } + next_lock = waiter->lock; +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); + + /* 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); + } +@@ -1099,7 +1501,8 @@ + static int __sched + __rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- struct rt_mutex_waiter *waiter) ++ struct rt_mutex_waiter *waiter, ++ struct ww_acquire_ctx *ww_ctx) + { + int ret = 0; + +@@ -1122,6 +1525,12 @@ + break; + } + ++ if (ww_ctx && ww_ctx->acquired > 0) { ++ ret = __mutex_lock_check_stamp(lock, ww_ctx); ++ if (ret) ++ break; ++ } ++ + raw_spin_unlock(&lock->wait_lock); + + debug_rt_mutex_print_deadlock(waiter); +@@ -1156,25 +1565,102 @@ + } + } + ++static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++#ifdef CONFIG_DEBUG_MUTEXES ++ /* ++ * If this WARN_ON triggers, you used ww_mutex_lock to acquire, ++ * but released with a normal mutex_unlock in this call. ++ * ++ * This should never happen, always use ww_mutex_unlock. ++ */ ++ DEBUG_LOCKS_WARN_ON(ww->ctx); ++ ++ /* ++ * Not quite done after calling ww_acquire_done() ? ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); ++ ++ if (ww_ctx->contending_lock) { ++ /* ++ * After -EDEADLK you tried to ++ * acquire a different ww_mutex? Bad! ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); ++ ++ /* ++ * You called ww_mutex_lock after receiving -EDEADLK, ++ * but 'forgot' to unlock everything else first? ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); ++ ww_ctx->contending_lock = NULL; ++ } ++ ++ /* ++ * Naughty, using a different class will lead to undefined behavior! ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); ++#endif ++ ww_ctx->acquired++; ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void ww_mutex_account_lock(struct rt_mutex *lock, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); ++ struct rt_mutex_waiter *waiter, *n; ++ ++ /* ++ * This branch gets optimized out for the common case, ++ * and is only important for ww_mutex_lock. ++ */ ++ ww_mutex_lock_acquired(ww, ww_ctx); ++ ww->ctx = ww_ctx; ++ ++ /* ++ * Give any possible sleeping processes the chance to wake up, ++ * so they can recheck if they have to back off. ++ */ ++ rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters, ++ tree_entry) { ++ /* XXX debug rt mutex waiter wakeup */ ++ ++ BUG_ON(waiter->lock != lock); ++ rt_mutex_wake_waiter(waiter); ++ } ++} ++ ++#else ++ ++static void ww_mutex_account_lock(struct rt_mutex *lock, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++ BUG(); ++} ++#endif ++ + /* + * Slow path lock function: + */ + static int __sched + rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx) + { + struct rt_mutex_waiter waiter; + int ret = 0; + +- debug_rt_mutex_init_waiter(&waiter); +- RB_CLEAR_NODE(&waiter.pi_tree_entry); +- RB_CLEAR_NODE(&waiter.tree_entry); ++ rt_mutex_init_waiter(&waiter, false); + + raw_spin_lock(&lock->wait_lock); + + /* Try to acquire the lock again: */ + if (try_to_take_rt_mutex(lock, current, NULL)) { ++ if (ww_ctx) ++ ww_mutex_account_lock(lock, ww_ctx); + raw_spin_unlock(&lock->wait_lock); + return 0; + } +@@ -1192,13 +1678,23 @@ + + if (likely(!ret)) + /* sleep on the mutex */ +- ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); ++ ret = __rt_mutex_slowlock(lock, state, timeout, &waiter, ++ ww_ctx); ++ else if (ww_ctx) { ++ /* ww_mutex received EDEADLK, let it become EALREADY */ ++ ret = __mutex_lock_check_stamp(lock, ww_ctx); ++ BUG_ON(!ret); ++ } + + if (unlikely(ret)) { + __set_current_state(TASK_RUNNING); + if (rt_mutex_has_waiters(lock)) + remove_waiter(lock, &waiter); +- rt_mutex_handle_deadlock(ret, chwalk, &waiter); ++ /* ww_mutex want to report EDEADLK/EALREADY, let them */ ++ if (!ww_ctx) ++ rt_mutex_handle_deadlock(ret, chwalk, &waiter); ++ } else if (ww_ctx) { ++ ww_mutex_account_lock(lock, ww_ctx); + } + + /* +@@ -1255,7 +1751,7 @@ + /* + * Slow path to release a rt-mutex: + */ +-static void __sched ++static bool __sched + rt_mutex_slowunlock(struct rt_mutex *lock) + { + raw_spin_lock(&lock->wait_lock); +@@ -1298,7 +1794,7 @@ + while (!rt_mutex_has_waiters(lock)) { + /* Drops lock->wait_lock ! */ + if (unlock_rt_mutex_safe(lock) == true) +- return; ++ return false; + /* Relock the rtmutex and try again */ + raw_spin_lock(&lock->wait_lock); + } +@@ -1311,8 +1807,7 @@ + + raw_spin_unlock(&lock->wait_lock); + +- /* Undo pi boosting if necessary: */ +- rt_mutex_adjust_prio(current); ++ return true; + } + + /* +@@ -1323,31 +1818,36 @@ + */ + static inline int + rt_mutex_fastlock(struct rt_mutex *lock, int state, ++ struct ww_acquire_ctx *ww_ctx, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk)) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx)) + { + if (likely(rt_mutex_cmpxchg(lock, NULL, current))) { + rt_mutex_deadlock_account_lock(lock, current); + return 0; + } else +- return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); ++ return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ++ ww_ctx); + } + + static inline int + rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk)) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx)) + { + 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, chwalk); ++ return slowfn(lock, state, timeout, chwalk, ww_ctx); + } + + static inline int +@@ -1363,12 +1863,14 @@ + + static inline void + rt_mutex_fastunlock(struct rt_mutex *lock, +- void (*slowfn)(struct rt_mutex *lock)) ++ bool (*slowfn)(struct rt_mutex *lock)) + { +- if (likely(rt_mutex_cmpxchg(lock, current, NULL))) ++ if (likely(rt_mutex_cmpxchg(lock, current, NULL))) { + rt_mutex_deadlock_account_unlock(current); +- else +- slowfn(lock); ++ } else if (slowfn(lock)) { ++ /* Undo pi boosting if necessary: */ ++ rt_mutex_adjust_prio(current); ++ } + } + + /** +@@ -1380,7 +1882,7 @@ + { + might_sleep(); + +- rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); ++ rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, NULL, rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock); + +@@ -1397,7 +1899,7 @@ + { + might_sleep(); + +- return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); ++ return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, NULL, rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); + +@@ -1410,11 +1912,30 @@ + might_sleep(); + + return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, +- RT_MUTEX_FULL_CHAINWALK, ++ RT_MUTEX_FULL_CHAINWALK, NULL, + rt_mutex_slowlock); + } + + /** ++ * rt_mutex_lock_killable - lock a rt_mutex killable ++ * ++ * @lock: the rt_mutex to be locked ++ * @detect_deadlock: deadlock detection on/off ++ * ++ * 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, NULL, 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 +@@ -1434,6 +1955,7 @@ + + return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, + RT_MUTEX_MIN_CHAINWALK, ++ NULL, + rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); +@@ -1463,6 +1985,22 @@ + EXPORT_SYMBOL_GPL(rt_mutex_unlock); + + /** ++ * rt_mutex_futex_unlock - Futex variant of rt_mutex_unlock ++ * @lock: the rt_mutex to be unlocked ++ * ++ * Returns: true/false indicating whether priority adjustment is ++ * required or not. ++ */ ++bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock) ++{ ++ if (likely(rt_mutex_cmpxchg(lock, current, NULL))) { ++ rt_mutex_deadlock_account_unlock(current); ++ return false; ++ } ++ return rt_mutex_slowunlock(lock); ++} ++ ++/** + * rt_mutex_destroy - mark a mutex unusable + * @lock: the mutex to be destroyed + * +@@ -1492,13 +2030,12 @@ + void __rt_mutex_init(struct rt_mutex *lock, const char *name) + { + lock->owner = NULL; +- raw_spin_lock_init(&lock->wait_lock); + lock->waiters = RB_ROOT; + lock->waiters_leftmost = NULL; + + 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 +@@ -1513,7 +2050,7 @@ + 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); +@@ -1561,6 +2098,35 @@ + 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, + RT_MUTEX_FULL_CHAINWALK); +@@ -1575,7 +2141,7 @@ + ret = 0; + } + +- if (unlikely(ret)) ++ if (ret && rt_mutex_has_waiters(lock)) + remove_waiter(lock, waiter); + + raw_spin_unlock(&lock->wait_lock); +@@ -1631,7 +2197,7 @@ + set_current_state(TASK_INTERRUPTIBLE); + + /* sleep on the mutex */ +- ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); ++ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL); + + if (unlikely(ret)) + remove_waiter(lock, waiter); +@@ -1646,3 +2212,89 @@ + + return ret; + } ++ ++static inline int ++ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH ++ unsigned tmp; ++ ++ if (ctx->deadlock_inject_countdown-- == 0) { ++ tmp = ctx->deadlock_inject_interval; ++ if (tmp > UINT_MAX/4) ++ tmp = UINT_MAX; ++ else ++ tmp = tmp*2 + tmp + tmp/2; ++ ++ ctx->deadlock_inject_interval = tmp; ++ ctx->deadlock_inject_countdown = tmp; ++ ctx->contending_lock = lock; ++ ++ ww_mutex_unlock(lock); ++ ++ return -EDEADLK; ++ } ++#endif ++ ++ return 0; ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++int __sched ++__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) ++{ ++ int ret; ++ ++ might_sleep(); ++ ++ mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_); ++ ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ww_ctx); ++ if (ret) ++ mutex_release(&lock->base.dep_map, 1, _RET_IP_); ++ else if (!ret && ww_ctx->acquired > 1) ++ return ww_mutex_deadlock_injection(lock, ww_ctx); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); ++ ++int __sched ++__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) ++{ ++ int ret; ++ ++ might_sleep(); ++ ++ mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_); ++ ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ww_ctx); ++ if (ret) ++ mutex_release(&lock->base.dep_map, 1, _RET_IP_); ++ else if (!ret && ww_ctx->acquired > 1) ++ return ww_mutex_deadlock_injection(lock, ww_ctx); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(__ww_mutex_lock); ++ ++void __sched ww_mutex_unlock(struct ww_mutex *lock) ++{ ++ int nest = !!lock->ctx; ++ ++ /* ++ * The unlocking fastpath is the 0->1 transition from 'locked' ++ * into 'unlocked' state: ++ */ ++ if (nest) { ++#ifdef CONFIG_DEBUG_MUTEXES ++ DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); ++#endif ++ if (lock->ctx->acquired > 0) ++ lock->ctx->acquired--; ++ lock->ctx = NULL; ++ } ++ ++ mutex_release(&lock->base.dep_map, nest, _RET_IP_); ++ rt_mutex_unlock(&lock->base.lock); ++} ++EXPORT_SYMBOL(ww_mutex_unlock); ++#endif +diff -Nur linux-4.1.39.orig/kernel/locking/rtmutex_common.h linux-4.1.39/kernel/locking/rtmutex_common.h +--- linux-4.1.39.orig/kernel/locking/rtmutex_common.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/locking/rtmutex_common.h 2017-04-18 17:56:30.625397596 +0200 +@@ -49,6 +49,7 @@ + struct rb_node pi_tree_entry; + struct task_struct *task; + struct rt_mutex *lock; ++ bool savestate; + #ifdef CONFIG_DEBUG_RT_MUTEXES + unsigned long ip; + struct pid *deadlock_task_pid; +@@ -119,6 +120,9 @@ + /* + * 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); +@@ -132,10 +136,24 @@ + struct rt_mutex_waiter *waiter); + extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); + ++extern bool rt_mutex_futex_unlock(struct rt_mutex *lock); ++ ++extern void rt_mutex_adjust_prio(struct task_struct *task); ++ + #ifdef CONFIG_DEBUG_RT_MUTEXES + # include "rtmutex-debug.h" + #else + # 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; ++ RB_CLEAR_NODE(&waiter->pi_tree_entry); ++ RB_CLEAR_NODE(&waiter->tree_entry); ++} ++ + #endif +diff -Nur linux-4.1.39.orig/kernel/locking/spinlock.c linux-4.1.39/kernel/locking/spinlock.c +--- linux-4.1.39.orig/kernel/locking/spinlock.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/locking/spinlock.c 2017-04-18 17:56:30.625397596 +0200 +@@ -124,8 +124,11 @@ + * __[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 + +@@ -209,6 +212,8 @@ + 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) + { +@@ -353,6 +358,8 @@ + 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 -Nur linux-4.1.39.orig/kernel/locking/spinlock_debug.c linux-4.1.39/kernel/locking/spinlock_debug.c +--- linux-4.1.39.orig/kernel/locking/spinlock_debug.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/locking/spinlock_debug.c 2017-04-18 17:56:30.625397596 +0200 +@@ -31,6 +31,7 @@ + + 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 @@ + } + + EXPORT_SYMBOL(__rwlock_init); ++#endif + + static void spin_dump(raw_spinlock_t *lock, const char *msg) + { +@@ -159,6 +161,7 @@ + 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()) +@@ -300,3 +303,5 @@ + debug_write_unlock(lock); + arch_write_unlock(&lock->raw_lock); + } ++ ++#endif +diff -Nur linux-4.1.39.orig/kernel/module.c linux-4.1.39/kernel/module.c +--- linux-4.1.39.orig/kernel/module.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/module.c 2017-04-18 17:56:30.625397596 +0200 +@@ -525,16 +525,7 @@ + memcpy(per_cpu_ptr(mod->percpu, cpu), from, size); + } + +-/** +- * is_module_percpu_address - test whether address is from module static percpu +- * @addr: address to test +- * +- * Test whether @addr belongs to module static percpu area. +- * +- * RETURNS: +- * %true if @addr is from module static percpu area +- */ +-bool is_module_percpu_address(unsigned long addr) ++bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr) + { + struct module *mod; + unsigned int cpu; +@@ -548,9 +539,11 @@ + continue; + for_each_possible_cpu(cpu) { + void *start = per_cpu_ptr(mod->percpu, cpu); ++ void *va = (void *)addr; + +- if ((void *)addr >= start && +- (void *)addr < start + mod->percpu_size) { ++ if (va >= start && va < start + mod->percpu_size) { ++ if (can_addr) ++ *can_addr = (unsigned long) (va - start); + preempt_enable(); + return true; + } +@@ -561,6 +554,20 @@ + return false; + } + ++/** ++ * is_module_percpu_address - test whether address is from module static percpu ++ * @addr: address to test ++ * ++ * Test whether @addr belongs to module static percpu area. ++ * ++ * RETURNS: ++ * %true if @addr is from module static percpu area ++ */ ++bool is_module_percpu_address(unsigned long addr) ++{ ++ return __is_module_percpu_address(addr, NULL); ++} ++ + #else /* ... !CONFIG_SMP */ + + static inline void __percpu *mod_percpu(struct module *mod) +@@ -591,6 +598,11 @@ + { + return false; + } ++ ++bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr) ++{ ++ return false; ++} + + #endif /* CONFIG_SMP */ + +diff -Nur linux-4.1.39.orig/kernel/panic.c linux-4.1.39/kernel/panic.c +--- linux-4.1.39.orig/kernel/panic.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/panic.c 2017-04-18 17:56:30.625397596 +0200 +@@ -399,9 +399,11 @@ + + 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 -Nur linux-4.1.39.orig/kernel/power/hibernate.c linux-4.1.39/kernel/power/hibernate.c +--- linux-4.1.39.orig/kernel/power/hibernate.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/power/hibernate.c 2017-04-18 17:56:30.625397596 +0200 +@@ -285,6 +285,8 @@ + + local_irq_disable(); + ++ system_state = SYSTEM_SUSPEND; ++ + error = syscore_suspend(); + if (error) { + printk(KERN_ERR "PM: Some system devices failed to power down, " +@@ -314,6 +316,7 @@ + syscore_resume(); + + Enable_irqs: ++ system_state = SYSTEM_RUNNING; + local_irq_enable(); + + Enable_cpus: +@@ -437,6 +440,7 @@ + goto Enable_cpus; + + local_irq_disable(); ++ system_state = SYSTEM_SUSPEND; + + error = syscore_suspend(); + if (error) +@@ -470,6 +474,7 @@ + syscore_resume(); + + Enable_irqs: ++ system_state = SYSTEM_RUNNING; + local_irq_enable(); + + Enable_cpus: +@@ -555,6 +560,7 @@ + goto Platform_finish; + + local_irq_disable(); ++ system_state = SYSTEM_SUSPEND; + syscore_suspend(); + if (pm_wakeup_pending()) { + error = -EAGAIN; +@@ -567,6 +573,7 @@ + + Power_up: + syscore_resume(); ++ system_state = SYSTEM_RUNNING; + local_irq_enable(); + enable_nonboot_cpus(); + +diff -Nur linux-4.1.39.orig/kernel/power/suspend.c linux-4.1.39/kernel/power/suspend.c +--- linux-4.1.39.orig/kernel/power/suspend.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/power/suspend.c 2017-04-18 17:56:30.625397596 +0200 +@@ -356,6 +356,8 @@ + arch_suspend_disable_irqs(); + BUG_ON(!irqs_disabled()); + ++ system_state = SYSTEM_SUSPEND; ++ + error = syscore_suspend(); + if (!error) { + *wakeup = pm_wakeup_pending(); +@@ -370,6 +372,8 @@ + syscore_resume(); + } + ++ system_state = SYSTEM_RUNNING; ++ + arch_suspend_enable_irqs(); + BUG_ON(irqs_disabled()); + +diff -Nur linux-4.1.39.orig/kernel/printk/printk.c linux-4.1.39/kernel/printk/printk.c +--- linux-4.1.39.orig/kernel/printk/printk.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/printk/printk.c 2017-04-18 17:56:30.625397596 +0200 +@@ -1163,6 +1163,7 @@ + { + char *text; + int len = 0; ++ int attempts = 0; + + text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); + if (!text) +@@ -1174,7 +1175,14 @@ + u64 seq; + u32 idx; + enum log_flags prev; +- ++ int num_msg; ++try_again: ++ attempts++; ++ if (attempts > 10) { ++ len = -EBUSY; ++ goto out; ++ } ++ num_msg = 0; + if (clear_seq < log_first_seq) { + /* messages are gone, move to first available one */ + clear_seq = log_first_seq; +@@ -1195,6 +1203,14 @@ + prev = msg->flags; + idx = log_next(idx); + seq++; ++ num_msg++; ++ if (num_msg > 5) { ++ num_msg = 0; ++ raw_spin_unlock_irq(&logbuf_lock); ++ raw_spin_lock_irq(&logbuf_lock); ++ if (clear_seq < log_first_seq) ++ goto try_again; ++ } + } + + /* move first record forward until length fits into the buffer */ +@@ -1208,6 +1224,14 @@ + prev = msg->flags; + idx = log_next(idx); + seq++; ++ num_msg++; ++ if (num_msg > 5) { ++ num_msg = 0; ++ raw_spin_unlock_irq(&logbuf_lock); ++ raw_spin_lock_irq(&logbuf_lock); ++ if (clear_seq < log_first_seq) ++ goto try_again; ++ } + } + + /* last message fitting into this dump */ +@@ -1248,6 +1272,7 @@ + clear_seq = log_next_seq; + clear_idx = log_next_idx; + } ++out: + raw_spin_unlock_irq(&logbuf_lock); + + kfree(text); +@@ -1401,6 +1426,12 @@ + if (!console_drivers) + return; + ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) { ++ if (in_irq() || in_nmi()) ++ return; ++ } ++ ++ migrate_disable(); + for_each_console(con) { + if (exclusive_console && con != exclusive_console) + continue; +@@ -1413,6 +1444,7 @@ + continue; + con->write(con, text, len); + } ++ migrate_enable(); + } + + /* +@@ -1473,6 +1505,15 @@ + static int console_trylock_for_printk(void) + { + unsigned int cpu = smp_processor_id(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int lock = !early_boot_irqs_disabled && (preempt_count() == 0) && ++ !irqs_disabled(); ++#else ++ int lock = 1; ++#endif ++ ++ if (!lock) ++ return 0; + + if (!console_trylock()) + return 0; +@@ -1607,6 +1648,62 @@ + return textlen; + } + ++#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 ++ + asmlinkage int vprintk_emit(int facility, int level, + const char *dict, size_t dictlen, + const char *fmt, va_list args) +@@ -1623,6 +1720,13 @@ + /* cpu currently holding logbuf_lock in this function */ + static unsigned int logbuf_cpu = UINT_MAX; + ++ /* ++ * Fall back to early_printk if a debugging subsystem has ++ * killed printk output ++ */ ++ if (unlikely(forced_early_printk(fmt, args))) ++ return 1; ++ + if (level == LOGLEVEL_SCHED) { + level = LOGLEVEL_DEFAULT; + in_sched = true; +@@ -1764,8 +1868,7 @@ + * console_sem which would prevent anyone from printing to + * console + */ +- preempt_disable(); +- ++ migrate_disable(); + /* + * Try to acquire and then immediately release the console + * semaphore. The release will print out buffers and wake up +@@ -1773,7 +1876,7 @@ + */ + if (console_trylock_for_printk()) + console_unlock(); +- preempt_enable(); ++ migrate_enable(); + lockdep_on(); + } + +@@ -1902,26 +2005,6 @@ + + #endif /* CONFIG_PRINTK */ + +-#ifdef CONFIG_EARLY_PRINTK +-struct console *early_console; +- +-asmlinkage __visible void early_printk(const char *fmt, ...) +-{ +- va_list ap; +- char buf[512]; +- int n; +- +- if (!early_console) +- return; +- +- va_start(ap, fmt); +- n = vscnprintf(buf, sizeof(buf), fmt, ap); +- va_end(ap); +- +- early_console->write(early_console, buf, n); +-} +-#endif +- + static int __add_preferred_console(char *name, int idx, char *options, + char *brl_options) + { +@@ -2143,11 +2226,16 @@ + goto out; + + len = cont_print_text(text, size); ++#ifndef CONFIG_PREEMPT_RT_FULL + raw_spin_unlock(&logbuf_lock); + stop_critical_timings(); + call_console_drivers(cont.level, text, len); + start_critical_timings(); + local_irq_restore(flags); ++#else ++ raw_spin_unlock_irqrestore(&logbuf_lock, flags); ++ call_console_drivers(cont.level, text, len); ++#endif + return; + out: + raw_spin_unlock_irqrestore(&logbuf_lock, flags); +@@ -2246,12 +2334,17 @@ + console_idx = log_next(console_idx); + console_seq++; + console_prev = msg->flags; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ raw_spin_unlock_irqrestore(&logbuf_lock, flags); ++ call_console_drivers(level, text, len); ++#else + raw_spin_unlock(&logbuf_lock); + + stop_critical_timings(); /* don't trace print latency */ + call_console_drivers(level, text, len); + start_critical_timings(); + local_irq_restore(flags); ++#endif + + if (do_cond_resched) + cond_resched(); +@@ -2304,6 +2397,11 @@ + { + struct console *c; + ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) { ++ if (in_irq() || in_nmi()) ++ return; ++ } ++ + /* + * console_unblank can no longer be called in interrupt context unless + * oops_in_progress is set to 1.. +diff -Nur linux-4.1.39.orig/kernel/ptrace.c linux-4.1.39/kernel/ptrace.c +--- linux-4.1.39.orig/kernel/ptrace.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/ptrace.c 2017-04-18 17:56:30.625397596 +0200 +@@ -137,7 +137,14 @@ + + spin_lock_irq(&task->sighand->siglock); + if (task_is_traced(task) && !__fatal_signal_pending(task)) { +- task->state = __TASK_TRACED; ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&task->pi_lock, flags); ++ if (task->state & __TASK_TRACED) ++ task->state = __TASK_TRACED; ++ else ++ task->saved_state = __TASK_TRACED; ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); + ret = true; + } + spin_unlock_irq(&task->sighand->siglock); +diff -Nur linux-4.1.39.orig/kernel/rcu/rcutorture.c linux-4.1.39/kernel/rcu/rcutorture.c +--- linux-4.1.39.orig/kernel/rcu/rcutorture.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/rcu/rcutorture.c 2017-04-18 17:56:30.625397596 +0200 +@@ -389,6 +389,7 @@ + .name = "rcu" + }; + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Definitions for rcu_bh torture testing. + */ +@@ -428,6 +429,12 @@ + .name = "rcu_bh" + }; + ++#else ++static struct rcu_torture_ops rcu_bh_ops = { ++ .ttype = INVALID_RCU_FLAVOR, ++}; ++#endif ++ + /* + * Don't even think about trying any of these in real life!!! + * The names includes "busted", and they really means it! +diff -Nur linux-4.1.39.orig/kernel/rcu/tree.c linux-4.1.39/kernel/rcu/tree.c +--- linux-4.1.39.orig/kernel/rcu/tree.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/rcu/tree.c 2017-04-18 17:56:30.625397596 +0200 +@@ -56,6 +56,11 @@ + #include + #include + #include ++#include ++#include ++#include ++#include ++#include "../time/tick-internal.h" + + #include "tree.h" + #include "rcu.h" +@@ -220,6 +225,19 @@ + } + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void rcu_preempt_qs(void); ++ ++void rcu_bh_qs(void) ++{ ++ unsigned long flags; ++ ++ /* Callers to this function, rcu_preempt_qs(), must disable irqs. */ ++ local_irq_save(flags); ++ rcu_preempt_qs(); ++ local_irq_restore(flags); ++} ++#else + void rcu_bh_qs(void) + { + if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) { +@@ -229,6 +247,7 @@ + __this_cpu_write(rcu_bh_data.passed_quiesce, 1); + } + } ++#endif + + static DEFINE_PER_CPU(int, rcu_sched_qs_mask); + +@@ -404,6 +423,7 @@ + } + EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Return the number of RCU BH batches completed thus far for debug & stats. + */ +@@ -431,6 +451,13 @@ + } + EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); + ++#else ++void rcu_force_quiescent_state(void) ++{ ++} ++EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); ++#endif ++ + /* + * Force a quiescent state for RCU-sched. + */ +@@ -1545,7 +1572,7 @@ + !ACCESS_ONCE(rsp->gp_flags) || + !rsp->gp_kthread) + return; +- wake_up(&rsp->gp_wq); ++ swait_wake(&rsp->gp_wq); + } + + /* +@@ -1986,7 +2013,7 @@ + ACCESS_ONCE(rsp->gpnum), + TPS("reqwait")); + rsp->gp_state = RCU_GP_WAIT_GPS; +- wait_event_interruptible(rsp->gp_wq, ++ swait_event_interruptible(rsp->gp_wq, + ACCESS_ONCE(rsp->gp_flags) & + RCU_GP_FLAG_INIT); + /* Locking provides needed memory barrier. */ +@@ -2015,7 +2042,7 @@ + ACCESS_ONCE(rsp->gpnum), + TPS("fqswait")); + rsp->gp_state = RCU_GP_WAIT_FQS; +- ret = wait_event_interruptible_timeout(rsp->gp_wq, ++ ret = swait_event_interruptible_timeout(rsp->gp_wq, + ((gf = ACCESS_ONCE(rsp->gp_flags)) & + RCU_GP_FLAG_FQS) || + (!ACCESS_ONCE(rnp->qsmask) && +@@ -2860,18 +2887,17 @@ + /* + * Do RCU core processing for the current CPU. + */ +-static void rcu_process_callbacks(struct softirq_action *unused) ++static void rcu_process_callbacks(void) + { + struct rcu_state *rsp; + + if (cpu_is_offline(smp_processor_id())) + return; +- trace_rcu_utilization(TPS("Start RCU core")); + for_each_rcu_flavor(rsp) + __rcu_process_callbacks(rsp); +- trace_rcu_utilization(TPS("End RCU core")); + } + ++static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); + /* + * Schedule RCU callback invocation. If the specified type of RCU + * does not support RCU priority boosting, just do a direct call, +@@ -2883,18 +2909,105 @@ + { + if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active))) + return; +- if (likely(!rsp->boost)) { +- rcu_do_batch(rsp, rdp); ++ rcu_do_batch(rsp, rdp); ++} ++ ++static void rcu_wake_cond(struct task_struct *t, int status) ++{ ++ /* ++ * If the thread is yielding, only wake it when this ++ * is invoked from idle ++ */ ++ if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current))) ++ wake_up_process(t); ++} ++ ++/* ++ * Wake up this CPU's rcuc kthread to do RCU core processing. ++ */ ++static void invoke_rcu_core(void) ++{ ++ unsigned long flags; ++ struct task_struct *t; ++ ++ if (!cpu_online(smp_processor_id())) + return; ++ local_irq_save(flags); ++ __this_cpu_write(rcu_cpu_has_work, 1); ++ t = __this_cpu_read(rcu_cpu_kthread_task); ++ if (t != NULL && current != t) ++ rcu_wake_cond(t, __this_cpu_read(rcu_cpu_kthread_status)); ++ local_irq_restore(flags); ++} ++ ++static void rcu_cpu_kthread_park(unsigned int cpu) ++{ ++ per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; ++} ++ ++static int rcu_cpu_kthread_should_run(unsigned int cpu) ++{ ++ return __this_cpu_read(rcu_cpu_has_work); ++} ++ ++/* ++ * Per-CPU kernel thread that invokes RCU callbacks. This replaces the ++ * RCU softirq used in flavors and configurations of RCU that do not ++ * support RCU priority boosting. ++ */ ++static void rcu_cpu_kthread(unsigned int cpu) ++{ ++ unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); ++ char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); ++ int spincnt; ++ ++ for (spincnt = 0; spincnt < 10; spincnt++) { ++ trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); ++ local_bh_disable(); ++ *statusp = RCU_KTHREAD_RUNNING; ++ this_cpu_inc(rcu_cpu_kthread_loops); ++ local_irq_disable(); ++ work = *workp; ++ *workp = 0; ++ local_irq_enable(); ++ if (work) ++ rcu_process_callbacks(); ++ local_bh_enable(); ++ if (*workp == 0) { ++ trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); ++ *statusp = RCU_KTHREAD_WAITING; ++ return; ++ } + } +- invoke_rcu_callbacks_kthread(); ++ *statusp = RCU_KTHREAD_YIELDING; ++ trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); ++ schedule_timeout_interruptible(2); ++ trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); ++ *statusp = RCU_KTHREAD_WAITING; + } + +-static void invoke_rcu_core(void) ++static struct smp_hotplug_thread rcu_cpu_thread_spec = { ++ .store = &rcu_cpu_kthread_task, ++ .thread_should_run = rcu_cpu_kthread_should_run, ++ .thread_fn = rcu_cpu_kthread, ++ .thread_comm = "rcuc/%u", ++ .setup = rcu_cpu_kthread_setup, ++ .park = rcu_cpu_kthread_park, ++}; ++ ++/* ++ * Spawn per-CPU RCU core processing kthreads. ++ */ ++static int __init rcu_spawn_core_kthreads(void) + { +- if (cpu_online(smp_processor_id())) +- raise_softirq(RCU_SOFTIRQ); ++ int cpu; ++ ++ for_each_possible_cpu(cpu) ++ per_cpu(rcu_cpu_has_work, cpu) = 0; ++ BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); ++ return 0; + } ++early_initcall(rcu_spawn_core_kthreads); + + /* + * Handle any core-RCU processing required by a call_rcu() invocation. +@@ -3040,6 +3153,7 @@ + } + EXPORT_SYMBOL_GPL(call_rcu_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Queue an RCU callback for invocation after a quicker grace period. + */ +@@ -3048,6 +3162,7 @@ + __call_rcu(head, func, &rcu_bh_state, -1, 0); + } + EXPORT_SYMBOL_GPL(call_rcu_bh); ++#endif + + /* + * Queue an RCU callback for lazy invocation after a grace period. +@@ -3139,6 +3254,7 @@ + } + EXPORT_SYMBOL_GPL(synchronize_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. + * +@@ -3165,6 +3281,7 @@ + wait_rcu_gp(call_rcu_bh); + } + EXPORT_SYMBOL_GPL(synchronize_rcu_bh); ++#endif + + /** + * get_state_synchronize_rcu - Snapshot current RCU state +@@ -3677,6 +3794,7 @@ + mutex_unlock(&rsp->barrier_mutex); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. + */ +@@ -3685,6 +3803,7 @@ + _rcu_barrier(&rcu_bh_state); + } + EXPORT_SYMBOL_GPL(rcu_barrier_bh); ++#endif + + /** + * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. +@@ -4021,7 +4140,7 @@ + } + } + +- init_waitqueue_head(&rsp->gp_wq); ++ init_swait_head(&rsp->gp_wq); + rnp = rsp->level[rcu_num_lvls - 1]; + for_each_possible_cpu(i) { + while (i > rnp->grphi) +@@ -4120,7 +4239,6 @@ + rcu_init_one(&rcu_bh_state, &rcu_bh_data); + rcu_init_one(&rcu_sched_state, &rcu_sched_data); + __rcu_init_preempt(); +- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + + /* + * We don't need protection against CPU-hotplug here because +diff -Nur linux-4.1.39.orig/kernel/rcu/tree.h linux-4.1.39/kernel/rcu/tree.h +--- linux-4.1.39.orig/kernel/rcu/tree.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/rcu/tree.h 2017-04-18 17:56:30.629397751 +0200 +@@ -27,6 +27,7 @@ + #include + #include + #include ++#include + + /* + * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and +@@ -210,7 +211,7 @@ + /* This can happen due to race conditions. */ + #endif /* #ifdef CONFIG_RCU_BOOST */ + #ifdef CONFIG_RCU_NOCB_CPU +- wait_queue_head_t nocb_gp_wq[2]; ++ struct swait_head nocb_gp_wq[2]; + /* Place for rcu_nocb_kthread() to wait GP. */ + #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ + int need_future_gp[2]; +@@ -349,7 +350,7 @@ + atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */ + struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */ + struct rcu_head **nocb_follower_tail; +- wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */ ++ struct swait_head nocb_wq; /* For nocb kthreads to sleep on. */ + struct task_struct *nocb_kthread; + int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ + +@@ -438,7 +439,7 @@ + unsigned long gpnum; /* Current gp number. */ + unsigned long completed; /* # of last completed gp. */ + struct task_struct *gp_kthread; /* Task for grace periods. */ +- wait_queue_head_t gp_wq; /* Where GP task waits. */ ++ struct swait_head gp_wq; /* Where GP task waits. */ + short gp_flags; /* Commands for GP task. */ + short gp_state; /* GP kthread sleep state. */ + +@@ -529,12 +530,10 @@ + DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data); + #endif /* #ifdef CONFIG_PREEMPT_RCU */ + +-#ifdef CONFIG_RCU_BOOST + DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); + DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu); + DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); + DECLARE_PER_CPU(char, rcu_cpu_has_work); +-#endif /* #ifdef CONFIG_RCU_BOOST */ + + #ifndef RCU_TREE_NONCORE + +@@ -553,10 +552,9 @@ + static void __init __rcu_init_preempt(void); + static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); + static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); +-static void invoke_rcu_callbacks_kthread(void); + static bool rcu_is_callbacks_kthread(void); ++static void rcu_cpu_kthread_setup(unsigned int cpu); + #ifdef CONFIG_RCU_BOOST +-static void rcu_preempt_do_callbacks(void); + static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, + struct rcu_node *rnp); + #endif /* #ifdef CONFIG_RCU_BOOST */ +diff -Nur linux-4.1.39.orig/kernel/rcu/tree_plugin.h linux-4.1.39/kernel/rcu/tree_plugin.h +--- linux-4.1.39.orig/kernel/rcu/tree_plugin.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/rcu/tree_plugin.h 2017-04-18 17:56:30.629397751 +0200 +@@ -24,27 +24,20 @@ + * Paul E. McKenney + */ + +-#include +-#include +-#include +-#include +-#include "../time/tick-internal.h" +- + #ifdef CONFIG_RCU_BOOST + + #include "../locking/rtmutex_common.h" + ++#endif /* #ifdef CONFIG_RCU_BOOST */ ++ + /* + * Control variables for per-CPU and per-rcu_node kthreads. These + * handle all flavors of RCU. + */ +-static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); + DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); + DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); + DEFINE_PER_CPU(char, rcu_cpu_has_work); + +-#endif /* #ifdef CONFIG_RCU_BOOST */ +- + #ifdef CONFIG_RCU_NOCB_CPU + static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ + static bool have_rcu_nocb_mask; /* Was rcu_nocb_mask allocated? */ +@@ -291,7 +284,7 @@ + } + + /* Hardware IRQ handlers cannot block, complain if they get here. */ +- if (in_irq() || in_serving_softirq()) { ++ if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { + lockdep_rcu_suspicious(__FILE__, __LINE__, + "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); + pr_alert("->rcu_read_unlock_special: %#x (b: %d, nq: %d)\n", +@@ -496,15 +489,6 @@ + t->rcu_read_unlock_special.b.need_qs = true; + } + +-#ifdef CONFIG_RCU_BOOST +- +-static void rcu_preempt_do_callbacks(void) +-{ +- rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data)); +-} +- +-#endif /* #ifdef CONFIG_RCU_BOOST */ +- + /* + * Queue a preemptible-RCU callback for invocation after a grace period. + */ +@@ -939,6 +923,19 @@ + + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + ++/* ++ * If boosting, set rcuc kthreads to realtime priority. ++ */ ++static void rcu_cpu_kthread_setup(unsigned int cpu) ++{ ++#ifdef CONFIG_RCU_BOOST ++ struct sched_param sp; ++ ++ sp.sched_priority = kthread_prio; ++ sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); ++#endif /* #ifdef CONFIG_RCU_BOOST */ ++} ++ + #ifdef CONFIG_RCU_BOOST + + #include "../locking/rtmutex_common.h" +@@ -970,16 +967,6 @@ + + #endif /* #else #ifdef CONFIG_RCU_TRACE */ + +-static void rcu_wake_cond(struct task_struct *t, int status) +-{ +- /* +- * If the thread is yielding, only wake it when this +- * is invoked from idle +- */ +- if (status != RCU_KTHREAD_YIELDING || is_idle_task(current)) +- wake_up_process(t); +-} +- + /* + * Carry out RCU priority boosting on the task indicated by ->exp_tasks + * or ->boost_tasks, advancing the pointer to the next task in the +@@ -1125,23 +1112,6 @@ + } + + /* +- * Wake up the per-CPU kthread to invoke RCU callbacks. +- */ +-static void invoke_rcu_callbacks_kthread(void) +-{ +- unsigned long flags; +- +- local_irq_save(flags); +- __this_cpu_write(rcu_cpu_has_work, 1); +- if (__this_cpu_read(rcu_cpu_kthread_task) != NULL && +- current != __this_cpu_read(rcu_cpu_kthread_task)) { +- rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task), +- __this_cpu_read(rcu_cpu_kthread_status)); +- } +- local_irq_restore(flags); +-} +- +-/* + * Is the current CPU running the RCU-callbacks kthread? + * Caller must have preemption disabled. + */ +@@ -1196,67 +1166,6 @@ + return 0; + } + +-static void rcu_kthread_do_work(void) +-{ +- rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data)); +- rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data)); +- rcu_preempt_do_callbacks(); +-} +- +-static void rcu_cpu_kthread_setup(unsigned int cpu) +-{ +- struct sched_param sp; +- +- sp.sched_priority = kthread_prio; +- sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); +-} +- +-static void rcu_cpu_kthread_park(unsigned int cpu) +-{ +- per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; +-} +- +-static int rcu_cpu_kthread_should_run(unsigned int cpu) +-{ +- return __this_cpu_read(rcu_cpu_has_work); +-} +- +-/* +- * Per-CPU kernel thread that invokes RCU callbacks. This replaces the +- * RCU softirq used in flavors and configurations of RCU that do not +- * support RCU priority boosting. +- */ +-static void rcu_cpu_kthread(unsigned int cpu) +-{ +- unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); +- char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); +- int spincnt; +- +- for (spincnt = 0; spincnt < 10; spincnt++) { +- trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); +- local_bh_disable(); +- *statusp = RCU_KTHREAD_RUNNING; +- this_cpu_inc(rcu_cpu_kthread_loops); +- local_irq_disable(); +- work = *workp; +- *workp = 0; +- local_irq_enable(); +- if (work) +- rcu_kthread_do_work(); +- local_bh_enable(); +- if (*workp == 0) { +- trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); +- *statusp = RCU_KTHREAD_WAITING; +- return; +- } +- } +- *statusp = RCU_KTHREAD_YIELDING; +- trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); +- schedule_timeout_interruptible(2); +- trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); +- *statusp = RCU_KTHREAD_WAITING; +-} +- + /* + * Set the per-rcu_node kthread's affinity to cover all CPUs that are + * served by the rcu_node in question. The CPU hotplug lock is still +@@ -1286,26 +1195,12 @@ + free_cpumask_var(cm); + } + +-static struct smp_hotplug_thread rcu_cpu_thread_spec = { +- .store = &rcu_cpu_kthread_task, +- .thread_should_run = rcu_cpu_kthread_should_run, +- .thread_fn = rcu_cpu_kthread, +- .thread_comm = "rcuc/%u", +- .setup = rcu_cpu_kthread_setup, +- .park = rcu_cpu_kthread_park, +-}; +- + /* + * Spawn boost kthreads -- called as soon as the scheduler is running. + */ + static void __init rcu_spawn_boost_kthreads(void) + { + struct rcu_node *rnp; +- int cpu; +- +- for_each_possible_cpu(cpu) +- per_cpu(rcu_cpu_has_work, cpu) = 0; +- BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); + rcu_for_each_leaf_node(rcu_state_p, rnp) + (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); + } +@@ -1328,11 +1223,6 @@ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } + +-static void invoke_rcu_callbacks_kthread(void) +-{ +- WARN_ON_ONCE(1); +-} +- + static bool rcu_is_callbacks_kthread(void) + { + return false; +@@ -1356,7 +1246,7 @@ + + #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 +@@ -1374,7 +1264,9 @@ + return rcu_cpu_has_callbacks(NULL); + } + #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ ++#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 cleaning up + * after it. +@@ -1472,6 +1364,8 @@ + return cbs_ready; + } + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready + * to invoke. If the CPU has callbacks, try to advance them. Tell the +@@ -1512,7 +1406,7 @@ + return 0; + } + #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ +- ++#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */ + /* + * Prepare a CPU for idle from an RCU perspective. The first major task + * is to sense whether nohz mode has been enabled or disabled via sysfs. +@@ -1859,7 +1753,7 @@ + */ + static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) + { +- wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); ++ swait_wake_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); + } + + /* +@@ -1877,8 +1771,8 @@ + + static void rcu_init_one_nocb(struct rcu_node *rnp) + { +- init_waitqueue_head(&rnp->nocb_gp_wq[0]); +- init_waitqueue_head(&rnp->nocb_gp_wq[1]); ++ init_swait_head(&rnp->nocb_gp_wq[0]); ++ init_swait_head(&rnp->nocb_gp_wq[1]); + } + + #ifndef CONFIG_RCU_NOCB_CPU_ALL +@@ -1903,7 +1797,7 @@ + if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) { + /* Prior smp_mb__after_atomic() orders against prior enqueue. */ + ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false; +- wake_up(&rdp_leader->nocb_wq); ++ swait_wake(&rdp_leader->nocb_wq); + } + } + +@@ -2116,7 +2010,7 @@ + */ + trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait")); + for (;;) { +- wait_event_interruptible( ++ swait_event_interruptible( + rnp->nocb_gp_wq[c & 0x1], + (d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c))); + if (likely(d)) +@@ -2144,7 +2038,7 @@ + /* Wait for callbacks to appear. */ + if (!rcu_nocb_poll) { + trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep"); +- wait_event_interruptible(my_rdp->nocb_wq, ++ swait_event_interruptible(my_rdp->nocb_wq, + !ACCESS_ONCE(my_rdp->nocb_leader_sleep)); + /* Memory barrier handled by smp_mb() calls below and repoll. */ + } else if (firsttime) { +@@ -2219,7 +2113,7 @@ + * List was empty, wake up the follower. + * Memory barriers supplied by atomic_long_add(). + */ +- wake_up(&rdp->nocb_wq); ++ swait_wake(&rdp->nocb_wq); + } + } + +@@ -2240,7 +2134,7 @@ + if (!rcu_nocb_poll) { + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + "FollowerSleep"); +- wait_event_interruptible(rdp->nocb_wq, ++ swait_event_interruptible(rdp->nocb_wq, + ACCESS_ONCE(rdp->nocb_follower_head)); + } else if (firsttime) { + /* Don't drown trace log with "Poll"! */ +@@ -2399,7 +2293,7 @@ + static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) + { + rdp->nocb_tail = &rdp->nocb_head; +- init_waitqueue_head(&rdp->nocb_wq); ++ init_swait_head(&rdp->nocb_wq); + rdp->nocb_follower_tail = &rdp->nocb_follower_head; + } + +diff -Nur linux-4.1.39.orig/kernel/rcu/update.c linux-4.1.39/kernel/rcu/update.c +--- linux-4.1.39.orig/kernel/rcu/update.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/rcu/update.c 2017-04-18 17:56:30.629397751 +0200 +@@ -227,6 +227,7 @@ + } + EXPORT_SYMBOL_GPL(rcu_read_lock_held); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? + * +@@ -253,6 +254,7 @@ + return in_softirq() || irqs_disabled(); + } + EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); ++#endif + + #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +diff -Nur linux-4.1.39.orig/kernel/relay.c linux-4.1.39/kernel/relay.c +--- linux-4.1.39.orig/kernel/relay.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/relay.c 2017-04-18 17:56:30.629397751 +0200 +@@ -339,6 +339,10 @@ + { + struct rchan_buf *buf = (struct rchan_buf *)data; + wake_up_interruptible(&buf->read_wait); ++ /* ++ * Stupid polling for now: ++ */ ++ mod_timer(&buf->timer, jiffies + 1); + } + + /** +@@ -356,6 +360,7 @@ + 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 @@ + 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 -Nur linux-4.1.39.orig/kernel/sched/completion.c linux-4.1.39/kernel/sched/completion.c +--- linux-4.1.39.orig/kernel/sched/completion.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/sched/completion.c 2017-04-18 17:56:30.633397907 +0200 +@@ -30,10 +30,10 @@ + { + unsigned long flags; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + x->done++; +- __wake_up_locked(&x->wait, TASK_NORMAL, 1); +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ __swait_wake_locked(&x->wait, TASK_NORMAL, 1); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + } + EXPORT_SYMBOL(complete); + +@@ -50,10 +50,10 @@ + { + unsigned long flags; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + x->done += UINT_MAX/2; +- __wake_up_locked(&x->wait, TASK_NORMAL, 0); +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ __swait_wake_locked(&x->wait, TASK_NORMAL, 0); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + } + EXPORT_SYMBOL(complete_all); + +@@ -62,20 +62,20 @@ + long (*action)(long), long timeout, int state) + { + if (!x->done) { +- DECLARE_WAITQUEUE(wait, current); ++ DEFINE_SWAITER(wait); + +- __add_wait_queue_tail_exclusive(&x->wait, &wait); ++ swait_prepare_locked(&x->wait, &wait); + do { + if (signal_pending_state(state, current)) { + timeout = -ERESTARTSYS; + break; + } + __set_current_state(state); +- spin_unlock_irq(&x->wait.lock); ++ raw_spin_unlock_irq(&x->wait.lock); + timeout = action(timeout); +- spin_lock_irq(&x->wait.lock); ++ raw_spin_lock_irq(&x->wait.lock); + } while (!x->done && timeout); +- __remove_wait_queue(&x->wait, &wait); ++ swait_finish_locked(&x->wait, &wait); + if (!x->done) + return timeout; + } +@@ -89,9 +89,9 @@ + { + might_sleep(); + +- spin_lock_irq(&x->wait.lock); ++ raw_spin_lock_irq(&x->wait.lock); + timeout = do_wait_for_common(x, action, timeout, state); +- spin_unlock_irq(&x->wait.lock); ++ raw_spin_unlock_irq(&x->wait.lock); + return timeout; + } + +@@ -277,12 +277,12 @@ + if (!READ_ONCE(x->done)) + return 0; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + if (!x->done) + ret = 0; + else + x->done--; +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + return ret; + } + EXPORT_SYMBOL(try_wait_for_completion); +@@ -311,7 +311,7 @@ + * after it's acquired the lock. + */ + smp_rmb(); +- spin_unlock_wait(&x->wait.lock); ++ raw_spin_unlock_wait(&x->wait.lock); + return true; + } + EXPORT_SYMBOL(completion_done); +diff -Nur linux-4.1.39.orig/kernel/sched/core.c linux-4.1.39/kernel/sched/core.c +--- linux-4.1.39.orig/kernel/sched/core.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/sched/core.c 2017-04-18 17:56:30.633397907 +0200 +@@ -282,7 +282,11 @@ + * 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 +@@ -461,6 +465,7 @@ + + 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) +@@ -541,6 +546,52 @@ + #endif + #endif + ++void wake_q_add(struct wake_q_head *head, struct task_struct *task) ++{ ++ struct wake_q_node *node = &task->wake_q; ++ ++ /* ++ * Atomically grab the task, if ->wake_q is !nil already it means ++ * its already queued (either by us or someone else) and will get the ++ * wakeup due to that. ++ * ++ * This cmpxchg() implies a full barrier, which pairs with the write ++ * barrier implied by the wakeup in wake_up_list(). ++ */ ++ if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) ++ return; ++ ++ get_task_struct(task); ++ ++ /* ++ * The head is context local, there can be no concurrency. ++ */ ++ *head->lastp = node; ++ head->lastp = &node->next; ++} ++ ++void wake_up_q(struct wake_q_head *head) ++{ ++ struct wake_q_node *node = head->first; ++ ++ while (node != WAKE_Q_TAIL) { ++ struct task_struct *task; ++ ++ task = container_of(node, struct task_struct, wake_q); ++ BUG_ON(!task); ++ /* task can safely be re-inserted now */ ++ node = node->next; ++ task->wake_q.next = NULL; ++ ++ /* ++ * wake_up_process() implies a wmb() to pair with the queueing ++ * in wake_q_add() so as not to miss wakeups. ++ */ ++ wake_up_process(task); ++ put_task_struct(task); ++ } ++} ++ + /* + * resched_curr - mark rq's current task 'to be rescheduled now'. + * +@@ -572,6 +623,38 @@ + trace_sched_wake_idle_without_ipi(cpu); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++void resched_curr_lazy(struct rq *rq) ++{ ++ struct task_struct *curr = rq->curr; ++ int cpu; ++ ++ if (!sched_feat(PREEMPT_LAZY)) { ++ resched_curr(rq); ++ return; ++ } ++ ++ lockdep_assert_held(&rq->lock); ++ ++ if (test_tsk_need_resched(curr)) ++ return; ++ ++ if (test_tsk_need_resched_lazy(curr)) ++ return; ++ ++ set_tsk_need_resched_lazy(curr); ++ ++ cpu = cpu_of(rq); ++ if (cpu == smp_processor_id()) ++ return; ++ ++ /* NEED_RESCHED_LAZY must be visible before we test polling */ ++ smp_mb(); ++ if (!tsk_is_polling(curr)) ++ smp_send_reschedule(cpu); ++} ++#endif ++ + void resched_cpu(int cpu) + { + struct rq *rq = cpu_rq(cpu); +@@ -595,12 +678,14 @@ + */ + int get_nohz_timer_target(int pinned) + { +- int cpu = smp_processor_id(); ++ int cpu; + int i; + struct sched_domain *sd; + ++ preempt_disable_rt(); ++ cpu = smp_processor_id(); + if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu)) +- return cpu; ++ goto preempt_en_rt; + + rcu_read_lock(); + for_each_domain(cpu, sd) { +@@ -613,6 +698,8 @@ + } + unlock: + rcu_read_unlock(); ++preempt_en_rt: ++ preempt_enable_rt(); + return cpu; + } + /* +@@ -1164,6 +1251,18 @@ + + static int migration_cpu_stop(void *data); + ++static bool check_task_state(struct task_struct *p, long match_state) ++{ ++ bool match = false; ++ ++ raw_spin_lock_irq(&p->pi_lock); ++ if (p->state == match_state || p->saved_state == match_state) ++ match = true; ++ raw_spin_unlock_irq(&p->pi_lock); ++ ++ return match; ++} ++ + /* + * wait_task_inactive - wait for a thread to unschedule. + * +@@ -1208,7 +1307,7 @@ + * is actually now running somewhere else! + */ + while (task_running(rq, p)) { +- if (match_state && unlikely(p->state != match_state)) ++ if (match_state && !check_task_state(p, match_state)) + return 0; + cpu_relax(); + } +@@ -1223,7 +1322,8 @@ + running = task_running(rq, p); + queued = task_on_rq_queued(p); + 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); + +@@ -1449,10 +1549,6 @@ + { + activate_task(rq, p, en_flags); + p->on_rq = TASK_ON_RQ_QUEUED; +- +- /* if a worker is waking up, notify workqueue */ +- if (p->flags & PF_WQ_WORKER) +- wq_worker_waking_up(p, cpu_of(rq)); + } + + /* +@@ -1462,9 +1558,9 @@ + ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) + { + check_preempt_curr(rq, p, wake_flags); +- trace_sched_wakeup(p, true); +- + p->state = TASK_RUNNING; ++ trace_sched_wakeup(p); ++ + #ifdef CONFIG_SMP + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); +@@ -1666,8 +1762,29 @@ + */ + smp_mb__before_spinlock(); + 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); +@@ -1732,42 +1849,6 @@ + } + + /** +- * 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 (!task_on_rq_queued(p)) +- 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. + * +@@ -1781,11 +1862,23 @@ + */ + int wake_up_process(struct task_struct *p) + { +- WARN_ON(task_is_stopped_or_traced(p)); ++ WARN_ON(__task_is_stopped_or_traced(p)); + return try_to_wake_up(p, TASK_NORMAL, 0); + } + 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); +@@ -1981,6 +2074,9 @@ + p->on_cpu = 0; + #endif + init_task_preempt_count(p); ++#ifdef CONFIG_HAVE_PREEMPT_LAZY ++ task_thread_info(p)->preempt_lazy_count = 0; ++#endif + #ifdef CONFIG_SMP + plist_node_init(&p->pushable_tasks, MAX_PRIO); + RB_CLEAR_NODE(&p->pushable_dl_tasks); +@@ -2116,7 +2212,7 @@ + rq = __task_rq_lock(p); + activate_task(rq, p, 0); + p->on_rq = TASK_ON_RQ_QUEUED; +- 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) +@@ -2253,8 +2349,12 @@ + 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)) { + if (prev->sched_class->task_dead) + prev->sched_class->task_dead(prev); +@@ -2565,16 +2665,6 @@ + } + #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)) + +@@ -2596,7 +2686,7 @@ + PREEMPT_MASK - 10); + #endif + if (preempt_count() == val) { +- unsigned long ip = get_parent_ip(CALLER_ADDR1); ++ unsigned long ip = get_lock_parent_ip(); + #ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; + #endif +@@ -2623,7 +2713,7 @@ + #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_sub(val); + } + EXPORT_SYMBOL(preempt_count_sub); +@@ -2679,6 +2769,133 @@ + 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); ++ /* mask==cpumask_of(task_cpu(p)) which has a cpumask_weight==1 */ ++ p->nr_cpus_allowed = 1; ++ ++ /* 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 ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } ++#endif ++ ++ if (p->migrate_disable) { ++ p->migrate_disable++; ++ return; ++ } ++ ++ preempt_disable(); ++ preempt_lazy_disable(); ++ 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 ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } ++#endif ++ WARN_ON_ONCE(p->migrate_disable <= 0); ++ ++ if (migrate_disable_count(p) > 1) { ++ p->migrate_disable--; ++ return; ++ } ++ ++ preempt_disable(); ++ 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->nr_cpus_allowed = cpumask_weight(mask); ++ raw_spin_unlock_irqrestore(&rq->lock, flags); ++ } else ++ p->migrate_disable = 0; ++ ++ unpin_current_cpu(); ++ preempt_enable(); ++ preempt_lazy_enable(); ++} ++EXPORT_SYMBOL(migrate_enable); ++#else ++static inline void update_migrate_disable(struct task_struct *p) { } ++#define migrate_disabled_updated(p) 0 ++#endif ++ + /* + * Pick up the highest-prio task: + */ +@@ -2785,6 +3002,8 @@ + smp_mb__before_spinlock(); + raw_spin_lock_irq(&rq->lock); + ++ update_migrate_disable(prev); ++ + rq->clock_skip_update <<= 1; /* promote REQ to ACT */ + + switch_count = &prev->nivcsw; +@@ -2794,19 +3013,6 @@ + } 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; + } +@@ -2816,6 +3022,7 @@ + + next = pick_next_task(rq, prev); + clear_tsk_need_resched(prev); ++ clear_tsk_need_resched_lazy(prev); + clear_preempt_need_resched(); + rq->clock_skip_update = 0; + +@@ -2836,8 +3043,19 @@ + + 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. ++ */ ++ if (tsk->flags & PF_WQ_WORKER) ++ 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. +@@ -2846,6 +3064,12 @@ + blk_schedule_flush_plug(tsk); + } + ++static void sched_update_worker(struct task_struct *tsk) ++{ ++ if (tsk->flags & PF_WQ_WORKER) ++ wq_worker_running(tsk); ++} ++ + asmlinkage __visible void __sched schedule(void) + { + struct task_struct *tsk = current; +@@ -2854,6 +3078,7 @@ + do { + __schedule(); + } while (need_resched()); ++ sched_update_worker(tsk); + } + EXPORT_SYMBOL(schedule); + +@@ -2903,6 +3128,30 @@ + } while (need_resched()); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++/* ++ * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is ++ * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as ++ * preempt_lazy_count counter >0. ++ */ ++static __always_inline int preemptible_lazy(void) ++{ ++ if (test_thread_flag(TIF_NEED_RESCHED)) ++ return 1; ++ if (current_thread_info()->preempt_lazy_count) ++ return 0; ++ return 1; ++} ++ ++#else ++ ++static inline int preemptible_lazy(void) ++{ ++ return 1; ++} ++ ++#endif ++ + #ifdef CONFIG_PREEMPT + /* + * this is the entry point to schedule() from in-kernel preemption +@@ -2917,6 +3166,8 @@ + */ + if (likely(!preemptible())) + return; ++ if (!preemptible_lazy()) ++ return; + + preempt_schedule_common(); + } +@@ -2944,6 +3195,8 @@ + + if (likely(!preemptible())) + return; ++ if (!preemptible_lazy()) ++ return; + + do { + __preempt_count_add(PREEMPT_ACTIVE); +@@ -2953,7 +3206,16 @@ + * an infinite recursion. + */ + prev_ctx = exception_enter(); ++ /* ++ * 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(); + exception_exit(prev_ctx); + + __preempt_count_sub(PREEMPT_ACTIVE); +@@ -4290,6 +4552,7 @@ + } + EXPORT_SYMBOL(__cond_resched_lock); + ++#ifndef CONFIG_PREEMPT_RT_FULL + int __sched __cond_resched_softirq(void) + { + BUG_ON(!in_softirq()); +@@ -4303,6 +4566,7 @@ + return 0; + } + EXPORT_SYMBOL(__cond_resched_softirq); ++#endif + + /** + * yield - yield the current processor to other threads. +@@ -4659,7 +4923,9 @@ + + /* Set the preempt count _outside_ the spinlocks! */ + init_idle_preempt_count(idle, cpu); +- ++#ifdef CONFIG_HAVE_PREEMPT_LAZY ++ task_thread_info(idle)->preempt_lazy_count = 0; ++#endif + /* + * The idle tasks have their own, simple scheduling class: + */ +@@ -4779,11 +5045,91 @@ + + void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) + { +- if (p->sched_class->set_cpus_allowed) +- p->sched_class->set_cpus_allowed(p, new_mask); ++ if (!migrate_disabled_updated(p)) { ++ if (p->sched_class->set_cpus_allowed) ++ p->sched_class->set_cpus_allowed(p, new_mask); ++ p->nr_cpus_allowed = cpumask_weight(new_mask); ++ } + + cpumask_copy(&p->cpus_allowed, new_mask); +- p->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 NO_SETAFFINITY) ++ * 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_NO_SETAFFINITY || p->state) ++ return 0; ++ ++ mutex_lock(&sched_down_mutex); ++ rq = task_rq_lock(p, &flags); ++ ++ cpumask = this_cpu_ptr(&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; + } + + /* +@@ -4829,7 +5175,7 @@ + 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); +@@ -4969,6 +5315,8 @@ + + #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. +@@ -4983,7 +5331,11 @@ + switch_mm(mm, &init_mm, current); + finish_arch_post_lock_switch(); + } +- 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; + } + + /* +@@ -5326,6 +5678,10 @@ + + case CPU_DEAD: + calc_load_migrate(rq); ++ if (per_cpu(idle_last_mm, cpu)) { ++ mmdrop(per_cpu(idle_last_mm, cpu)); ++ per_cpu(idle_last_mm, cpu) = NULL; ++ } + break; + #endif + } +@@ -7305,7 +7661,8 @@ + #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); + } +diff -Nur linux-4.1.39.orig/kernel/sched/cputime.c linux-4.1.39/kernel/sched/cputime.c +--- linux-4.1.39.orig/kernel/sched/cputime.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/sched/cputime.c 2017-04-18 17:56:30.633397907 +0200 +@@ -675,37 +675,45 @@ + + void vtime_account_system(struct task_struct *tsk) + { +- write_seqlock(&tsk->vtime_seqlock); ++ raw_spin_lock(&tsk->vtime_lock); ++ write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seq); ++ raw_spin_unlock(&tsk->vtime_lock); + } + + void vtime_gen_account_irq_exit(struct task_struct *tsk) + { +- write_seqlock(&tsk->vtime_seqlock); ++ raw_spin_lock(&tsk->vtime_lock); ++ write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + if (context_tracking_in_user()) + tsk->vtime_snap_whence = VTIME_USER; +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seq); ++ raw_spin_unlock(&tsk->vtime_lock); + } + + void vtime_account_user(struct task_struct *tsk) + { + cputime_t delta_cpu; + +- write_seqlock(&tsk->vtime_seqlock); ++ raw_spin_lock(&tsk->vtime_lock); ++ write_seqcount_begin(&tsk->vtime_seq); + delta_cpu = get_vtime_delta(tsk); + tsk->vtime_snap_whence = VTIME_SYS; + account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seq); ++ raw_spin_unlock(&tsk->vtime_lock); + } + + void vtime_user_enter(struct task_struct *tsk) + { +- write_seqlock(&tsk->vtime_seqlock); ++ raw_spin_lock(&tsk->vtime_lock); ++ write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + tsk->vtime_snap_whence = VTIME_USER; +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seq); ++ raw_spin_unlock(&tsk->vtime_lock); + } + + void vtime_guest_enter(struct task_struct *tsk) +@@ -717,19 +725,23 @@ + * synchronization against the reader (task_gtime()) + * that can thus safely catch up with a tickless delta. + */ +- write_seqlock(&tsk->vtime_seqlock); ++ raw_spin_lock(&tsk->vtime_lock); ++ write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + current->flags |= PF_VCPU; +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seq); ++ raw_spin_unlock(&tsk->vtime_lock); + } + EXPORT_SYMBOL_GPL(vtime_guest_enter); + + void vtime_guest_exit(struct task_struct *tsk) + { +- write_seqlock(&tsk->vtime_seqlock); ++ raw_spin_lock(&tsk->vtime_lock); ++ write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + current->flags &= ~PF_VCPU; +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seq); ++ raw_spin_unlock(&tsk->vtime_lock); + } + EXPORT_SYMBOL_GPL(vtime_guest_exit); + +@@ -742,24 +754,30 @@ + + void arch_vtime_task_switch(struct task_struct *prev) + { +- write_seqlock(&prev->vtime_seqlock); ++ raw_spin_lock(&prev->vtime_lock); ++ write_seqcount_begin(&prev->vtime_seq); + prev->vtime_snap_whence = VTIME_SLEEPING; +- write_sequnlock(&prev->vtime_seqlock); ++ write_seqcount_end(&prev->vtime_seq); ++ raw_spin_unlock(&prev->vtime_lock); + +- write_seqlock(¤t->vtime_seqlock); ++ raw_spin_lock(¤t->vtime_lock); ++ write_seqcount_begin(¤t->vtime_seq); + current->vtime_snap_whence = VTIME_SYS; + current->vtime_snap = sched_clock_cpu(smp_processor_id()); +- write_sequnlock(¤t->vtime_seqlock); ++ write_seqcount_end(¤t->vtime_seq); ++ raw_spin_unlock(¤t->vtime_lock); + } + + void vtime_init_idle(struct task_struct *t, int cpu) + { + unsigned long flags; + +- write_seqlock_irqsave(&t->vtime_seqlock, flags); ++ raw_spin_lock_irqsave(&t->vtime_lock, flags); ++ write_seqcount_begin(&t->vtime_seq); + t->vtime_snap_whence = VTIME_SYS; + t->vtime_snap = sched_clock_cpu(cpu); +- write_sequnlock_irqrestore(&t->vtime_seqlock, flags); ++ write_seqcount_end(&t->vtime_seq); ++ raw_spin_unlock_irqrestore(&t->vtime_lock, flags); + } + + cputime_t task_gtime(struct task_struct *t) +@@ -768,13 +786,13 @@ + cputime_t gtime; + + do { +- seq = read_seqbegin(&t->vtime_seqlock); ++ seq = read_seqcount_begin(&t->vtime_seq); + + gtime = t->gtime; + if (t->flags & PF_VCPU) + gtime += vtime_delta(t); + +- } while (read_seqretry(&t->vtime_seqlock, seq)); ++ } while (read_seqcount_retry(&t->vtime_seq, seq)); + + return gtime; + } +@@ -797,7 +815,7 @@ + *udelta = 0; + *sdelta = 0; + +- seq = read_seqbegin(&t->vtime_seqlock); ++ seq = read_seqcount_begin(&t->vtime_seq); + + if (u_dst) + *u_dst = *u_src; +@@ -821,7 +839,7 @@ + if (t->vtime_snap_whence == VTIME_SYS) + *sdelta = delta; + } +- } while (read_seqretry(&t->vtime_seqlock, seq)); ++ } while (read_seqcount_retry(&t->vtime_seq, seq)); + } + + +diff -Nur linux-4.1.39.orig/kernel/sched/deadline.c linux-4.1.39/kernel/sched/deadline.c +--- linux-4.1.39.orig/kernel/sched/deadline.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/sched/deadline.c 2017-04-18 17:56:30.633397907 +0200 +@@ -637,6 +637,7 @@ + + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + timer->function = dl_task_timer; ++ timer->irqsafe = 1; + } + + static +diff -Nur linux-4.1.39.orig/kernel/sched/debug.c linux-4.1.39/kernel/sched/debug.c +--- linux-4.1.39.orig/kernel/sched/debug.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/sched/debug.c 2017-04-18 17:56:30.633397907 +0200 +@@ -260,6 +260,9 @@ + P(rt_throttled); + PN(rt_time); + PN(rt_runtime); ++#ifdef CONFIG_SMP ++ P(rt_nr_migratory); ++#endif + + #undef PN + #undef P +@@ -648,6 +651,10 @@ + #endif + P(policy); + P(prio); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ P(migrate_disable); ++#endif ++ P(nr_cpus_allowed); + #undef PN + #undef __PN + #undef P +diff -Nur linux-4.1.39.orig/kernel/sched/fair.c linux-4.1.39/kernel/sched/fair.c +--- linux-4.1.39.orig/kernel/sched/fair.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/sched/fair.c 2017-04-18 17:56:30.637398061 +0200 +@@ -3201,7 +3201,7 @@ + ideal_runtime = sched_slice(cfs_rq, curr); + delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; + if (delta_exec > ideal_runtime) { +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + /* + * The current task ran long enough, ensure it doesn't get + * re-elected due to buddy favours. +@@ -3225,7 +3225,7 @@ + return; + + if (delta > ideal_runtime) +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + } + + static void +@@ -3366,7 +3366,7 @@ + * validating it and just reschedule. + */ + if (queued) { +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + return; + } + /* +@@ -3557,7 +3557,7 @@ + * hierarchy can be throttled + */ + if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + } + + static __always_inline +@@ -4180,7 +4180,7 @@ + + if (delta < 0) { + if (rq->curr == p) +- resched_curr(rq); ++ resched_curr_lazy(rq); + return; + } + hrtick_start(rq, delta); +@@ -5076,7 +5076,7 @@ + return; + + preempt: +- resched_curr(rq); ++ resched_curr_lazy(rq); + /* + * Only set the backward buddy when the current task is still + * on the rq. This can happen when a wakeup gets interleaved +@@ -7869,7 +7869,7 @@ + * 'current' within the tree based on its new key value. + */ + swap(curr->vruntime, se->vruntime); +- resched_curr(rq); ++ resched_curr_lazy(rq); + } + + se->vruntime -= cfs_rq->min_vruntime; +@@ -7894,7 +7894,7 @@ + */ + if (rq->curr == p) { + if (p->prio > oldprio) +- resched_curr(rq); ++ resched_curr_lazy(rq); + } else + check_preempt_curr(rq, p, 0); + } +diff -Nur linux-4.1.39.orig/kernel/sched/features.h linux-4.1.39/kernel/sched/features.h +--- linux-4.1.39.orig/kernel/sched/features.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/sched/features.h 2017-04-18 17:56:30.637398061 +0200 +@@ -50,11 +50,19 @@ + */ + SCHED_FEAT(NONTASK_CAPACITY, true) + ++#ifdef CONFIG_PREEMPT_RT_FULL ++SCHED_FEAT(TTWU_QUEUE, false) ++# ifdef CONFIG_PREEMPT_LAZY ++SCHED_FEAT(PREEMPT_LAZY, true) ++# endif ++#else ++ + /* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ + SCHED_FEAT(TTWU_QUEUE, true) ++#endif + + #ifdef HAVE_RT_PUSH_IPI + /* +diff -Nur linux-4.1.39.orig/kernel/sched/Makefile linux-4.1.39/kernel/sched/Makefile +--- linux-4.1.39.orig/kernel/sched/Makefile 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/sched/Makefile 2017-04-18 17:56:30.633397907 +0200 +@@ -13,7 +13,7 @@ + + obj-y += core.o proc.o clock.o cputime.o + obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o +-obj-y += wait.o completion.o idle.o ++obj-y += wait.o wait-simple.o work-simple.o completion.o idle.o + obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o + obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o + obj-$(CONFIG_SCHEDSTATS) += stats.o +diff -Nur linux-4.1.39.orig/kernel/sched/rt.c linux-4.1.39/kernel/sched/rt.c +--- linux-4.1.39.orig/kernel/sched/rt.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/sched/rt.c 2017-04-18 17:56:30.637398061 +0200 +@@ -44,6 +44,7 @@ + + 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; + } + +@@ -89,6 +90,7 @@ + rt_rq->push_cpu = nr_cpu_ids; + raw_spin_lock_init(&rt_rq->push_lock); + init_irq_work(&rt_rq->push_work, push_irq_work_func); ++ rt_rq->push_work.flags |= IRQ_WORK_HARD_IRQ; + #endif + #endif /* CONFIG_SMP */ + /* We start is dequeued state, because no RT tasks are queued */ +diff -Nur linux-4.1.39.orig/kernel/sched/sched.h linux-4.1.39/kernel/sched/sched.h +--- linux-4.1.39.orig/kernel/sched/sched.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/sched/sched.h 2017-04-18 17:56:30.637398061 +0200 +@@ -1093,6 +1093,7 @@ + #define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ + #define WF_FORK 0x02 /* child wakeup after fork */ + #define WF_MIGRATED 0x4 /* internal use, task got migrated */ ++#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */ + + /* + * To aid in avoiding the subversion of "niceness" due to uneven distribution +@@ -1290,6 +1291,15 @@ + extern void resched_curr(struct rq *rq); + extern void resched_cpu(int cpu); + ++#ifdef CONFIG_PREEMPT_LAZY ++extern void resched_curr_lazy(struct rq *rq); ++#else ++static inline void resched_curr_lazy(struct rq *rq) ++{ ++ resched_curr(rq); ++} ++#endif ++ + extern struct rt_bandwidth def_rt_bandwidth; + extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); + +diff -Nur linux-4.1.39.orig/kernel/sched/wait-simple.c linux-4.1.39/kernel/sched/wait-simple.c +--- linux-4.1.39.orig/kernel/sched/wait-simple.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/kernel/sched/wait-simple.c 2017-04-18 17:56:30.637398061 +0200 +@@ -0,0 +1,115 @@ ++/* ++ * 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); ++ /* We can't let the condition leak before the setting of head */ ++ smp_mb(); ++} ++ ++/* 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); ++} ++ ++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(__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(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(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 (!swaitqueue_active(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(__swait_wake); +diff -Nur linux-4.1.39.orig/kernel/sched/work-simple.c linux-4.1.39/kernel/sched/work-simple.c +--- linux-4.1.39.orig/kernel/sched/work-simple.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/kernel/sched/work-simple.c 2017-04-18 17:56:30.637398061 +0200 +@@ -0,0 +1,173 @@ ++/* ++ * 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 ++#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 -Nur linux-4.1.39.orig/kernel/signal.c linux-4.1.39/kernel/signal.c +--- linux-4.1.39.orig/kernel/signal.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/signal.c 2017-04-18 17:56:30.637398061 +0200 +@@ -14,6 +14,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -352,13 +353,45 @@ + 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; +@@ -375,7 +408,10 @@ + 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); + } +@@ -392,6 +428,13 @@ + 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) +@@ -401,6 +444,21 @@ + 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; +@@ -414,6 +472,21 @@ + } + + /* ++ * 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) +@@ -565,7 +638,7 @@ + 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 +@@ -611,6 +684,8 @@ + { + int signr; + ++ WARN_ON_ONCE(tsk != current); ++ + /* We only dequeue private signals from ourselves, we don't let + * signalfd steal them + */ +@@ -1207,8 +1282,8 @@ + * 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; +@@ -1233,6 +1308,39 @@ + 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. + */ +@@ -1267,12 +1375,12 @@ + * Disable interrupts early to avoid deadlocks. + * See rcu_read_unlock() comment header for details. + */ +- 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; + } + /* +@@ -1293,7 +1401,7 @@ + } + spin_unlock(&sighand->siglock); + rcu_read_unlock(); +- local_irq_restore(*flags); ++ local_irq_restore_nort(*flags); + } + + return sighand; +@@ -1536,7 +1644,8 @@ + */ + 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; +@@ -1897,15 +2006,7 @@ + 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(); + freezable_schedule(); + } else { + /* +diff -Nur linux-4.1.39.orig/kernel/softirq.c linux-4.1.39/kernel/softirq.c +--- linux-4.1.39.orig/kernel/softirq.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/softirq.c 2017-04-18 17:56:30.637398061 +0200 +@@ -21,10 +21,12 @@ + #include + #include + #include ++#include + #include + #include + #include + #include ++#include + #include + + #define CREATE_TRACE_POINTS +@@ -56,12 +58,108 @@ + static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp; + + DEFINE_PER_CPU(struct task_struct *, ksoftirqd); ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define TIMER_SOFTIRQS ((1 << TIMER_SOFTIRQ) | (1 << HRTIMER_SOFTIRQ)) ++DEFINE_PER_CPU(struct task_struct *, ktimer_softirqd); ++#endif + + const char * const softirq_to_name[NR_SOFTIRQS] = { + "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL", + "TASKLET", "SCHED", "HRTIMER", "RCU" + }; + ++#ifdef CONFIG_NO_HZ_COMMON ++# ifdef CONFIG_PREEMPT_RT_FULL ++ ++struct softirq_runner { ++ struct task_struct *runner[NR_SOFTIRQS]; ++}; ++ ++static DEFINE_PER_CPU(struct softirq_runner, softirq_runners); ++ ++static inline void softirq_set_runner(unsigned int sirq) ++{ ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ ++ sr->runner[sirq] = current; ++} ++ ++static inline void softirq_clr_runner(unsigned int sirq) ++{ ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ ++ sr->runner[sirq] = NULL; ++} ++ ++/* ++ * On preempt-rt a softirq running context 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; ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ u32 warnpending; ++ int i; ++ ++ if (rate_limit >= 10) ++ return; ++ ++ warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK; ++ for (i = 0; i < NR_SOFTIRQS; i++) { ++ struct task_struct *tsk = sr->runner[i]; ++ ++ /* ++ * 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. ++ */ ++ if (tsk) { ++ raw_spin_lock(&tsk->pi_lock); ++ if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { ++ /* Clear all bits pending in that task */ ++ warnpending &= ~(tsk->softirqs_raised); ++ warnpending &= ~(1 << i); ++ } ++ raw_spin_unlock(&tsk->pi_lock); ++ } ++ } ++ ++ if (warnpending) { ++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", ++ warnpending); ++ 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 && ++ (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { ++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", ++ local_softirq_pending()); ++ rate_limit++; ++ } ++} ++# endif ++ ++#else /* !CONFIG_NO_HZ_COMMON */ ++static inline void softirq_set_runner(unsigned int sirq) { } ++static inline void softirq_clr_runner(unsigned int sirq) { } ++#endif ++ + /* + * we cannot loop indefinitely here to avoid userspace starvation, + * but we also don't want to introduce a worst case 1/HZ latency +@@ -77,6 +175,79 @@ + wake_up_process(tsk); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void wakeup_timer_softirqd(void) ++{ ++ /* Interrupts are disabled: no need to stop preemption */ ++ struct task_struct *tsk = __this_cpu_read(ktimer_softirqd); ++ ++ if (tsk && tsk->state != TASK_RUNNING) ++ wake_up_process(tsk); ++} ++#endif ++ ++static void handle_softirq(unsigned int vec_nr) ++{ ++ struct softirq_action *h = softirq_vec + vec_nr; ++ int prev_count; ++ ++ 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())) { ++ pr_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_set(prev_count); ++ } ++} ++ ++#ifndef CONFIG_PREEMPT_RT_FULL ++static inline int ksoftirqd_softirq_pending(void) ++{ ++ return local_softirq_pending(); ++} ++ ++static void handle_pending_softirqs(u32 pending) ++{ ++ struct softirq_action *h = softirq_vec; ++ int softirq_bit; ++ ++ local_irq_enable(); ++ ++ h = softirq_vec; ++ ++ while ((softirq_bit = ffs(pending))) { ++ unsigned int vec_nr; ++ ++ h += softirq_bit - 1; ++ vec_nr = h - softirq_vec; ++ handle_softirq(vec_nr); ++ ++ h++; ++ pending >>= softirq_bit; ++ } ++ ++ rcu_bh_qs(); ++ local_irq_disable(); ++} ++ ++static void run_ksoftirqd(unsigned int cpu) ++{ ++ local_irq_disable(); ++ if (ksoftirqd_softirq_pending()) { ++ __do_softirq(); ++ local_irq_enable(); ++ cond_resched_rcu_qs(); ++ return; ++ } ++ local_irq_enable(); ++} ++ + /* + * preempt_count and SOFTIRQ_OFFSET usage: + * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving +@@ -116,9 +287,9 @@ + + if (preempt_count() == cnt) { + #ifdef CONFIG_DEBUG_PREEMPT +- current->preempt_disable_ip = get_parent_ip(CALLER_ADDR1); ++ current->preempt_disable_ip = get_lock_parent_ip(); + #endif +- trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); ++ trace_preempt_off(CALLER_ADDR0, get_lock_parent_ip()); + } + } + EXPORT_SYMBOL(__local_bh_disable_ip); +@@ -232,10 +403,8 @@ + unsigned long end = jiffies + MAX_SOFTIRQ_TIME; + unsigned long old_flags = current->flags; + int max_restart = MAX_SOFTIRQ_RESTART; +- struct softirq_action *h; + bool in_hardirq; + __u32 pending; +- int softirq_bit; + + /* + * Mask out PF_MEMALLOC s current task context is borrowed for the +@@ -254,36 +423,7 @@ + /* Reset the pending bitmask before enabling irqs */ + set_softirq_pending(0); + +- local_irq_enable(); +- +- h = softirq_vec; +- +- while ((softirq_bit = ffs(pending))) { +- unsigned int vec_nr; +- int prev_count; +- +- h += softirq_bit - 1; +- +- vec_nr = h - softirq_vec; +- 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())) { +- pr_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_set(prev_count); +- } +- h++; +- pending >>= softirq_bit; +- } +- +- rcu_bh_qs(); +- local_irq_disable(); ++ handle_pending_softirqs(pending); + + pending = local_softirq_pending(); + if (pending) { +@@ -320,6 +460,310 @@ + } + + /* ++ * This function must run with irqs disabled! ++ */ ++void raise_softirq_irqoff(unsigned int nr) ++{ ++ __raise_softirq_irqoff(nr); ++ ++ /* ++ * If we're in an interrupt or softirq, we're done ++ * (this also catches softirq-disabled code). We will ++ * actually run the softirq once we return from ++ * the irq or softirq. ++ * ++ * Otherwise we wake up ksoftirqd to make sure we ++ * schedule the softirq soon. ++ */ ++ if (!in_interrupt()) ++ wakeup_softirqd(); ++} ++ ++void __raise_softirq_irqoff(unsigned int nr) ++{ ++ trace_softirq_raise(nr); ++ or_softirq_pending(1UL << nr); ++} ++ ++static inline void local_bh_disable_nort(void) { local_bh_disable(); } ++static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } ++static void ksoftirqd_set_sched_params(unsigned int cpu) { } ++ ++#else /* !PREEMPT_RT_FULL */ ++ ++/* ++ * On RT we serialize softirq execution with a cpu local lock per softirq ++ */ ++static DEFINE_PER_CPU(struct local_irq_lock [NR_SOFTIRQS], local_softirq_locks); ++ ++void __init softirq_early_init(void) ++{ ++ int i; ++ ++ for (i = 0; i < NR_SOFTIRQS; i++) ++ local_irq_lock_init(local_softirq_locks[i]); ++} ++ ++static void lock_softirq(int which) ++{ ++ local_lock(local_softirq_locks[which]); ++} ++ ++static void unlock_softirq(int which) ++{ ++ local_unlock(local_softirq_locks[which]); ++} ++ ++static void do_single_softirq(int which) ++{ ++ unsigned long old_flags = current->flags; ++ ++ current->flags &= ~PF_MEMALLOC; ++ vtime_account_irq_enter(current); ++ current->flags |= PF_IN_SOFTIRQ; ++ lockdep_softirq_enter(); ++ local_irq_enable(); ++ handle_softirq(which); ++ local_irq_disable(); ++ lockdep_softirq_exit(); ++ current->flags &= ~PF_IN_SOFTIRQ; ++ vtime_account_irq_enter(current); ++ tsk_restore_flags(current, old_flags, PF_MEMALLOC); ++} ++ ++/* ++ * Called with interrupts disabled. Process softirqs which were raised ++ * in current context (or on behalf of ksoftirqd). ++ */ ++static void do_current_softirqs(void) ++{ ++ while (current->softirqs_raised) { ++ int i = __ffs(current->softirqs_raised); ++ unsigned int pending, mask = (1U << i); ++ ++ current->softirqs_raised &= ~mask; ++ local_irq_enable(); ++ ++ /* ++ * If the lock is contended, we boost the owner to ++ * process the softirq or leave the critical section ++ * now. ++ */ ++ lock_softirq(i); ++ local_irq_disable(); ++ softirq_set_runner(i); ++ /* ++ * Check with the local_softirq_pending() bits, ++ * whether we need to process this still or if someone ++ * else took care of it. ++ */ ++ pending = local_softirq_pending(); ++ if (pending & mask) { ++ set_softirq_pending(pending & ~mask); ++ do_single_softirq(i); ++ } ++ softirq_clr_runner(i); ++ WARN_ON(current->softirq_nestcnt != 1); ++ local_irq_enable(); ++ unlock_softirq(i); ++ local_irq_disable(); ++ } ++} ++ ++void __local_bh_disable(void) ++{ ++ if (++current->softirq_nestcnt == 1) ++ migrate_disable(); ++} ++EXPORT_SYMBOL(__local_bh_disable); ++ ++void __local_bh_enable(void) ++{ ++ if (WARN_ON(current->softirq_nestcnt == 0)) ++ return; ++ ++ local_irq_disable(); ++ if (current->softirq_nestcnt == 1 && current->softirqs_raised) ++ do_current_softirqs(); ++ local_irq_enable(); ++ ++ if (--current->softirq_nestcnt == 0) ++ migrate_enable(); ++} ++EXPORT_SYMBOL(__local_bh_enable); ++ ++void _local_bh_enable(void) ++{ ++ if (WARN_ON(current->softirq_nestcnt == 0)) ++ return; ++ if (--current->softirq_nestcnt == 0) ++ migrate_enable(); ++} ++EXPORT_SYMBOL(_local_bh_enable); ++ ++int in_serving_softirq(void) ++{ ++ return current->flags & PF_IN_SOFTIRQ; ++} ++EXPORT_SYMBOL(in_serving_softirq); ++ ++/* Called with preemption disabled */ ++static void run_ksoftirqd(unsigned int cpu) ++{ ++ local_irq_disable(); ++ current->softirq_nestcnt++; ++ ++ do_current_softirqs(); ++ current->softirq_nestcnt--; ++ local_irq_enable(); ++ cond_resched_rcu_qs(); ++} ++ ++/* ++ * Called from netif_rx_ni(). Preemption enabled, but migration ++ * disabled. So the cpu can't go away under us. ++ */ ++void thread_do_softirq(void) ++{ ++ if (!in_serving_softirq() && current->softirqs_raised) { ++ current->softirq_nestcnt++; ++ do_current_softirqs(); ++ current->softirq_nestcnt--; ++ } ++} ++ ++static void do_raise_softirq_irqoff(unsigned int nr) ++{ ++ unsigned int mask; ++ ++ mask = 1UL << nr; ++ ++ trace_softirq_raise(nr); ++ or_softirq_pending(mask); ++ ++ /* ++ * If we are not in a hard interrupt and inside a bh disabled ++ * region, we simply raise the flag on current. local_bh_enable() ++ * will make sure that the softirq is executed. Otherwise we ++ * delegate it to ksoftirqd. ++ */ ++ if (!in_irq() && current->softirq_nestcnt) ++ current->softirqs_raised |= mask; ++ else if (!__this_cpu_read(ksoftirqd) || !__this_cpu_read(ktimer_softirqd)) ++ return; ++ ++ if (mask & TIMER_SOFTIRQS) ++ __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask; ++ else ++ __this_cpu_read(ksoftirqd)->softirqs_raised |= mask; ++} ++ ++static void wakeup_proper_softirq(unsigned int nr) ++{ ++ if ((1UL << nr) & TIMER_SOFTIRQS) ++ wakeup_timer_softirqd(); ++ else ++ wakeup_softirqd(); ++} ++ ++ ++void __raise_softirq_irqoff(unsigned int nr) ++{ ++ do_raise_softirq_irqoff(nr); ++ if (!in_irq() && !current->softirq_nestcnt) ++ wakeup_proper_softirq(nr); ++} ++ ++/* ++ * Same as __raise_softirq_irqoff() but will process them in ksoftirqd ++ */ ++void __raise_softirq_irqoff_ksoft(unsigned int nr) ++{ ++ unsigned int mask; ++ ++ if (WARN_ON_ONCE(!__this_cpu_read(ksoftirqd) || ++ !__this_cpu_read(ktimer_softirqd))) ++ return; ++ mask = 1UL << nr; ++ ++ trace_softirq_raise(nr); ++ or_softirq_pending(mask); ++ if (mask & TIMER_SOFTIRQS) ++ __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask; ++ else ++ __this_cpu_read(ksoftirqd)->softirqs_raised |= mask; ++ wakeup_proper_softirq(nr); ++} ++ ++/* ++ * This function must run with irqs disabled! ++ */ ++void raise_softirq_irqoff(unsigned int nr) ++{ ++ do_raise_softirq_irqoff(nr); ++ ++ /* ++ * If we're in an hard interrupt we let irq return code deal ++ * with the wakeup of ksoftirqd. ++ */ ++ if (in_irq()) ++ return; ++ /* ++ * If we are in thread context but outside of a bh disabled ++ * region, we need to wake ksoftirqd as well. ++ * ++ * CHECKME: Some of the places which do that could be wrapped ++ * into local_bh_disable/enable pairs. Though it's unclear ++ * whether this is worth the effort. To find those places just ++ * raise a WARN() if the condition is met. ++ */ ++ if (!current->softirq_nestcnt) ++ wakeup_proper_softirq(nr); ++} ++ ++static inline int ksoftirqd_softirq_pending(void) ++{ ++ return current->softirqs_raised; ++} ++ ++static inline void local_bh_disable_nort(void) { } ++static inline void _local_bh_enable_nort(void) { } ++ ++static inline void ksoftirqd_set_sched_params(unsigned int cpu) ++{ ++ /* Take over all but timer pending softirqs when starting */ ++ local_irq_disable(); ++ current->softirqs_raised = local_softirq_pending() & ~TIMER_SOFTIRQS; ++ local_irq_enable(); ++} ++ ++static inline void ktimer_softirqd_set_sched_params(unsigned int cpu) ++{ ++ struct sched_param param = { .sched_priority = 1 }; ++ ++ sched_setscheduler(current, SCHED_FIFO, ¶m); ++ ++ /* Take over timer pending softirqs when starting */ ++ local_irq_disable(); ++ current->softirqs_raised = local_softirq_pending() & TIMER_SOFTIRQS; ++ local_irq_enable(); ++} ++ ++static inline void ktimer_softirqd_clr_sched_params(unsigned int cpu, ++ bool online) ++{ ++ struct sched_param param = { .sched_priority = 0 }; ++ ++ sched_setscheduler(current, SCHED_NORMAL, ¶m); ++} ++ ++static int ktimer_softirqd_should_run(unsigned int cpu) ++{ ++ return current->softirqs_raised; ++} ++ ++#endif /* PREEMPT_RT_FULL */ ++/* + * Enter an interrupt context. + */ + void irq_enter(void) +@@ -330,9 +774,9 @@ + * 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_irq_enter(); +- _local_bh_enable(); ++ _local_bh_enable_nort(); + } + + __irq_enter(); +@@ -340,6 +784,7 @@ + + static inline void invoke_softirq(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + if (!force_irqthreads) { + #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK + /* +@@ -359,6 +804,18 @@ + } else { + wakeup_softirqd(); + } ++#else /* PREEMPT_RT_FULL */ ++ unsigned long flags; ++ ++ local_irq_save(flags); ++ if (__this_cpu_read(ksoftirqd) && ++ __this_cpu_read(ksoftirqd)->softirqs_raised) ++ wakeup_softirqd(); ++ if (__this_cpu_read(ktimer_softirqd) && ++ __this_cpu_read(ktimer_softirqd)->softirqs_raised) ++ wakeup_timer_softirqd(); ++ local_irq_restore(flags); ++#endif + } + + static inline void tick_irq_exit(void) +@@ -395,26 +852,6 @@ + trace_hardirq_exit(); /* must be last! */ + } + +-/* +- * This function must run with irqs disabled! +- */ +-inline void raise_softirq_irqoff(unsigned int nr) +-{ +- __raise_softirq_irqoff(nr); +- +- /* +- * If we're in an interrupt or softirq, we're done +- * (this also catches softirq-disabled code). We will +- * actually run the softirq once we return from +- * the irq or softirq. +- * +- * Otherwise we wake up ksoftirqd to make sure we +- * schedule the softirq soon. +- */ +- if (!in_interrupt()) +- wakeup_softirqd(); +-} +- + void raise_softirq(unsigned int nr) + { + unsigned long flags; +@@ -424,12 +861,6 @@ + local_irq_restore(flags); + } + +-void __raise_softirq_irqoff(unsigned int nr) +-{ +- trace_softirq_raise(nr); +- or_softirq_pending(1UL << nr); +-} +- + void open_softirq(int nr, void (*action)(struct softirq_action *)) + { + softirq_vec[nr].action = action; +@@ -446,15 +877,45 @@ + 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, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); + local_irq_restore(flags); + } + EXPORT_SYMBOL(__tasklet_schedule); +@@ -464,10 +925,7 @@ + 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, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); + local_irq_restore(flags); + } + EXPORT_SYMBOL(__tasklet_hi_schedule); +@@ -476,82 +934,122 @@ + { + 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); ++} ++EXPORT_SYMBOL(tasklet_enable); + +- local_irq_disable(); +- list = __this_cpu_read(tasklet_vec.head); +- __this_cpu_write(tasklet_vec.head, NULL); +- __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head)); +- local_irq_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 = __this_cpu_read(tasklet_vec.head); ++ __this_cpu_write(tasklet_vec.head, NULL); ++ __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head)); ++ ++ local_irq_enable(); ++ ++ __tasklet_action(a, list); ++} ++ + static void tasklet_hi_action(struct softirq_action *a) + { + struct tasklet_struct *list; + + local_irq_disable(); ++ + list = __this_cpu_read(tasklet_hi_vec.head); + __this_cpu_write(tasklet_hi_vec.head, NULL); + __this_cpu_write(tasklet_hi_vec.tail, this_cpu_ptr(&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_enable(); + +- 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); + } + + void tasklet_init(struct tasklet_struct *t, +@@ -572,7 +1070,7 @@ + + 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); +@@ -646,25 +1144,26 @@ + open_softirq(HI_SOFTIRQ, tasklet_hi_action); + } + +-static int ksoftirqd_should_run(unsigned int cpu) +-{ +- return local_softirq_pending(); +-} +- +-static void run_ksoftirqd(unsigned int cpu) ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) ++void tasklet_unlock_wait(struct tasklet_struct *t) + { +- local_irq_disable(); +- if (local_softirq_pending()) { ++ while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { + /* +- * We can safely run softirq on inline stack, as we are not deep +- * in the task stack here. ++ * Hack for now to avoid this busy-loop: + */ +- __do_softirq(); +- local_irq_enable(); +- cond_resched_rcu_qs(); +- return; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ msleep(1); ++#else ++ barrier(); ++#endif + } +- local_irq_enable(); ++} ++EXPORT_SYMBOL(tasklet_unlock_wait); ++#endif ++ ++static int ksoftirqd_should_run(unsigned int cpu) ++{ ++ return ksoftirqd_softirq_pending(); + } + + #ifdef CONFIG_HOTPLUG_CPU +@@ -746,16 +1245,31 @@ + + static struct smp_hotplug_thread softirq_threads = { + .store = &ksoftirqd, ++ .setup = ksoftirqd_set_sched_params, + .thread_should_run = ksoftirqd_should_run, + .thread_fn = run_ksoftirqd, + .thread_comm = "ksoftirqd/%u", + }; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static struct smp_hotplug_thread softirq_timer_threads = { ++ .store = &ktimer_softirqd, ++ .setup = ktimer_softirqd_set_sched_params, ++ .cleanup = ktimer_softirqd_clr_sched_params, ++ .thread_should_run = ktimer_softirqd_should_run, ++ .thread_fn = run_ksoftirqd, ++ .thread_comm = "ktimersoftd/%u", ++}; ++#endif ++ + static __init int spawn_ksoftirqd(void) + { + register_cpu_notifier(&cpu_nfb); + + BUG_ON(smpboot_register_percpu_thread(&softirq_threads)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ BUG_ON(smpboot_register_percpu_thread(&softirq_timer_threads)); ++#endif + + return 0; + } +diff -Nur linux-4.1.39.orig/kernel/stop_machine.c linux-4.1.39/kernel/stop_machine.c +--- linux-4.1.39.orig/kernel/stop_machine.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/stop_machine.c 2017-04-18 17:56:30.637398061 +0200 +@@ -35,7 +35,7 @@ + + /* 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 */ + }; +@@ -78,7 +78,7 @@ + + 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); +@@ -86,7 +86,7 @@ + } else + cpu_stop_signal_done(work->done, false); + +- spin_unlock_irqrestore(&stopper->lock, flags); ++ raw_spin_unlock_irqrestore(&stopper->lock, flags); + } + + /** +@@ -248,7 +248,7 @@ + struct irq_cpu_stop_queue_work_info call_args; + struct multi_stop_data msdata; + +- preempt_disable(); ++ preempt_disable_nort(); + msdata = (struct multi_stop_data){ + .fn = fn, + .data = arg, +@@ -281,7 +281,7 @@ + * This relies on the stopper workqueues to be FIFO. + */ + if (!cpu_active(cpu1) || !cpu_active(cpu2)) { +- preempt_enable(); ++ preempt_enable_nort(); + return -ENOENT; + } + +@@ -295,7 +295,7 @@ + &irq_cpu_stop_queue_work, + &call_args, 1); + lg_local_unlock(&stop_cpus_lock); +- preempt_enable(); ++ preempt_enable_nort(); + + wait_for_completion(&done.completion); + +@@ -329,7 +329,7 @@ + + 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; +@@ -343,11 +343,13 @@ + } + + /* +- * 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 ++ * any of the cpus can execute it. + */ +- lg_global_lock(&stop_cpus_lock); ++ if (!inactive) ++ lg_global_lock(&stop_cpus_lock); ++ else ++ lg_global_trylock_relax(&stop_cpus_lock); + for_each_cpu(cpu, cpumask) + cpu_stop_queue_work(cpu, &per_cpu(stop_cpus_work, cpu)); + lg_global_unlock(&stop_cpus_lock); +@@ -359,7 +361,7 @@ + struct cpu_stop_done done; + + cpu_stop_init_done(&done, cpumask_weight(cpumask)); +- queue_stop_cpus_work(cpumask, fn, arg, &done); ++ queue_stop_cpus_work(cpumask, fn, arg, &done, false); + wait_for_completion(&done.completion); + return done.executed ? done.ret : -ENOENT; + } +@@ -439,9 +441,9 @@ + unsigned long flags; + int run; + +- spin_lock_irqsave(&stopper->lock, flags); ++ raw_spin_lock_irqsave(&stopper->lock, flags); + run = !list_empty(&stopper->works); +- spin_unlock_irqrestore(&stopper->lock, flags); ++ raw_spin_unlock_irqrestore(&stopper->lock, flags); + return run; + } + +@@ -453,13 +455,13 @@ + + 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; +@@ -467,6 +469,16 @@ + struct cpu_stop_done *done = work->done; + char ksym_buf[KSYM_NAME_LEN] __maybe_unused; + ++ /* ++ * Wait until the stopper finished scheduling on all ++ * cpus ++ */ ++ lg_global_lock(&stop_cpus_lock); ++ /* ++ * Let other cpu threads continue as well ++ */ ++ lg_global_unlock(&stop_cpus_lock); ++ + /* cpu stop callbacks are not allowed to sleep */ + preempt_disable(); + +@@ -500,20 +512,20 @@ + unsigned long flags; + + /* drain remaining works */ +- spin_lock_irqsave(&stopper->lock, flags); ++ raw_spin_lock_irqsave(&stopper->lock, flags); + list_for_each_entry(work, &stopper->works, list) + cpu_stop_signal_done(work->done, false); + stopper->enabled = false; +- spin_unlock_irqrestore(&stopper->lock, flags); ++ raw_spin_unlock_irqrestore(&stopper->lock, flags); + } + + static void cpu_stop_unpark(unsigned int cpu) + { + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + +- 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); + } + + static struct smp_hotplug_thread cpu_stop_threads = { +@@ -535,10 +547,12 @@ + 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); + } + ++ lg_lock_init(&stop_cpus_lock, "stop_cpus_lock"); ++ + BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads)); + stop_machine_initialized = true; + return 0; +@@ -634,7 +648,7 @@ + set_state(&msdata, MULTI_STOP_PREPARE); + cpu_stop_init_done(&done, num_active_cpus()); + queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata, +- &done); ++ &done, true); + ret = multi_cpu_stop(&msdata); + + /* Busy wait for completion. */ +diff -Nur linux-4.1.39.orig/kernel/time/hrtimer.c linux-4.1.39/kernel/time/hrtimer.c +--- linux-4.1.39.orig/kernel/time/hrtimer.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/time/hrtimer.c 2017-04-18 17:56:30.637398061 +0200 +@@ -48,11 +48,13 @@ + #include + #include + #include ++#include + #include + + #include + + #include ++#include + + #include "tick-internal.h" + +@@ -576,8 +578,7 @@ + * 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; +@@ -621,6 +622,9 @@ + 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 + */ +@@ -630,6 +634,21 @@ + base->hres_active = 0; + } + ++static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, ++ struct hrtimer_clock_base *base, ++ int wakeup) ++{ ++ if (!hrtimer_reprogram(timer, base)) ++ return 0; ++ if (!wakeup) ++ return -ETIME; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ if (!hrtimer_rt_defer(timer)) ++ return -ETIME; ++#endif ++ return 1; ++} ++ + static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) + { + ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; +@@ -695,6 +714,44 @@ + + static DECLARE_WORK(hrtimer_work, clock_was_set_work); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * RT can not call schedule_work from real interrupt context. ++ * Need to make a thread to do the real work. ++ */ ++static struct task_struct *clock_set_delay_thread; ++static bool do_clock_set_delay; ++ ++static int run_clock_set_delay(void *ignore) ++{ ++ while (!kthread_should_stop()) { ++ set_current_state(TASK_INTERRUPTIBLE); ++ if (do_clock_set_delay) { ++ do_clock_set_delay = false; ++ schedule_work(&hrtimer_work); ++ } ++ schedule(); ++ } ++ __set_current_state(TASK_RUNNING); ++ return 0; ++} ++ ++void clock_was_set_delayed(void) ++{ ++ do_clock_set_delay = true; ++ /* Make visible before waking up process */ ++ smp_wmb(); ++ wake_up_process(clock_set_delay_thread); ++} ++ ++static __init int create_clock_set_delay_thread(void) ++{ ++ clock_set_delay_thread = kthread_run(run_clock_set_delay, NULL, "kclksetdelayd"); ++ BUG_ON(!clock_set_delay_thread); ++ return 0; ++} ++early_initcall(create_clock_set_delay_thread); ++#else /* PREEMPT_RT_FULL */ + /* + * Called from timekeeping and resume code to reprogramm the hrtimer + * interrupt device on all cpus. +@@ -703,6 +760,7 @@ + { + schedule_work(&hrtimer_work); + } ++#endif + + #else + +@@ -711,6 +769,13 @@ + static inline int hrtimer_switch_to_hres(void) { return 0; } + static inline void + hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } ++static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, ++ struct hrtimer_clock_base *base, ++ int wakeup) ++{ ++ return 0; ++} ++ + static inline int hrtimer_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base) + { +@@ -718,7 +783,6 @@ + } + static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { } + static inline void retrigger_next_event(void *arg) { } +- + #endif /* CONFIG_HIGH_RES_TIMERS */ + + /* +@@ -836,6 +900,32 @@ + } + 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 + * +@@ -879,6 +969,11 @@ + 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) { +@@ -966,7 +1061,16 @@ + new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); + + timer_stats_hrtimer_set_start_info(timer); ++#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 + leftmost = enqueue_hrtimer(timer, new_base); + + if (!leftmost) { +@@ -980,15 +1084,26 @@ + * on dynticks target. + */ + wake_up_nohz_cpu(new_base->cpu_base->cpu); +- } else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases) && +- hrtimer_reprogram(timer, new_base)) { ++ } else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases)) { ++ ++ ret = hrtimer_enqueue_reprogram(timer, new_base, wakeup); ++ if (ret < 0) { ++ /* ++ * 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); ++ } else if (ret > 0) { + /* + * Only allow reprogramming if the new base is on this CPU. + * (it might still be on another CPU if the timer was pending) + * + * XXX send_remote_softirq() ? + */ +- if (wakeup) { + /* + * We need to drop cpu_base->lock to avoid a + * lock ordering issue vs. rq->lock. +@@ -996,9 +1111,7 @@ + raw_spin_unlock(&new_base->cpu_base->lock); + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + local_irq_restore(flags); +- return ret; +- } else { +- __raise_softirq_irqoff(HRTIMER_SOFTIRQ); ++ return 0; + } + } + +@@ -1089,7 +1202,7 @@ + + if (ret >= 0) + return ret; +- cpu_relax(); ++ hrtimer_wait_for_timer(timer); + } + } + EXPORT_SYMBOL_GPL(hrtimer_cancel); +@@ -1153,6 +1266,7 @@ + + 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 +@@ -1236,6 +1350,126 @@ + 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 + + /* +@@ -1246,7 +1480,7 @@ + { + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&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++; +@@ -1281,6 +1515,15 @@ + + 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 +@@ -1296,7 +1539,10 @@ + if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) + break; + +- __run_hrtimer(timer, &basenow); ++ if (!hrtimer_rt_defer(timer)) ++ __run_hrtimer(timer, &basenow); ++ else ++ raise = 1; + } + } + /* Reevaluate the clock bases for the next expiry */ +@@ -1313,7 +1559,7 @@ + if (expires_next.tv64 == KTIME_MAX || + !tick_program_event(expires_next, 0)) { + cpu_base->hang_detected = 0; +- return; ++ goto out; + } + + /* +@@ -1357,6 +1603,9 @@ + 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); + } + + /* +@@ -1392,18 +1641,18 @@ + __hrtimer_peek_ahead_timers(); + 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: + * +@@ -1436,7 +1685,7 @@ + struct timerqueue_node *node; + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); + struct hrtimer_clock_base *base; +- int index, gettime = 1; ++ int index, gettime = 1, raise = 0; + + if (hrtimer_hres_active()) + return; +@@ -1461,10 +1710,16 @@ + 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); + } + + /* +@@ -1486,16 +1741,18 @@ + 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; +@@ -1539,7 +1796,8 @@ + 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; +@@ -1556,8 +1814,10 @@ + 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; +@@ -1570,7 +1830,7 @@ + + 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: */ +@@ -1597,6 +1857,12 @@ + 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) + { +@@ -1611,6 +1877,26 @@ + 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: + */ +@@ -1622,10 +1908,14 @@ + 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); + } + + cpu_base->cpu = cpu; + hrtimer_init_hres(cpu_base); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ init_waitqueue_head(&cpu_base->wait); ++#endif + } + + #ifdef CONFIG_HOTPLUG_CPU +@@ -1731,9 +2021,7 @@ + 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 -Nur linux-4.1.39.orig/kernel/time/itimer.c linux-4.1.39/kernel/time/itimer.c +--- linux-4.1.39.orig/kernel/time/itimer.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/time/itimer.c 2017-04-18 17:56:30.637398061 +0200 +@@ -213,6 +213,7 @@ + /* 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 -Nur linux-4.1.39.orig/kernel/time/jiffies.c linux-4.1.39/kernel/time/jiffies.c +--- linux-4.1.39.orig/kernel/time/jiffies.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/time/jiffies.c 2017-04-18 17:56:30.637398061 +0200 +@@ -74,7 +74,8 @@ + .max_cycles = 10, + }; + +-__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); ++__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock); ++__cacheline_aligned_in_smp seqcount_t jiffies_seq; + + #if (BITS_PER_LONG < 64) + u64 get_jiffies_64(void) +@@ -83,9 +84,9 @@ + u64 ret; + + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + ret = jiffies_64; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + return ret; + } + EXPORT_SYMBOL(get_jiffies_64); +diff -Nur linux-4.1.39.orig/kernel/time/ntp.c linux-4.1.39/kernel/time/ntp.c +--- linux-4.1.39.orig/kernel/time/ntp.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/time/ntp.c 2017-04-18 17:56:30.637398061 +0200 +@@ -10,6 +10,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -529,10 +530,52 @@ + &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; ++ queue_delayed_work(system_power_efficient_wq, ++ &sync_cmos_work, 0); ++ } ++ schedule(); ++ } ++ __set_current_state(TASK_RUNNING); ++ return 0; ++} ++ ++void ntp_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 ++ + void ntp_notify_cmos_timer(void) + { + queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0); + } ++#endif /* CONFIG_PREEMPT_RT_FULL */ + + #else + void ntp_notify_cmos_timer(void) { } +diff -Nur linux-4.1.39.orig/kernel/time/posix-cpu-timers.c linux-4.1.39/kernel/time/posix-cpu-timers.c +--- linux-4.1.39.orig/kernel/time/posix-cpu-timers.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/time/posix-cpu-timers.c 2017-04-18 17:56:30.641398216 +0200 +@@ -3,6 +3,7 @@ + */ + + #include ++#include + #include + #include + #include +@@ -626,7 +627,7 @@ + /* + * Disarm any old timer after extracting its expiry time. + */ +- WARN_ON_ONCE(!irqs_disabled()); ++ WARN_ON_ONCE_NONRT(!irqs_disabled()); + + ret = 0; + old_incr = timer->it.cpu.incr; +@@ -1048,7 +1049,7 @@ + /* + * Now re-arm for the new expiry time. + */ +- WARN_ON_ONCE(!irqs_disabled()); ++ WARN_ON_ONCE_NONRT(!irqs_disabled()); + arm_timer(timer); + unlock_task_sighand(p, &flags); + +@@ -1114,10 +1115,11 @@ + 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; +@@ -1131,13 +1133,13 @@ + * 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; + +- WARN_ON_ONCE(!irqs_disabled()); ++ WARN_ON_ONCE_NONRT(!irqs_disabled()); + + /* + * The fast path checks that there are no expired thread or thread +@@ -1195,6 +1197,190 @@ + } + } + ++#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 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 -Nur linux-4.1.39.orig/kernel/time/posix-timers.c linux-4.1.39/kernel/time/posix-timers.c +--- linux-4.1.39.orig/kernel/time/posix-timers.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/time/posix-timers.c 2017-04-18 17:56:30.641398216 +0200 +@@ -499,6 +499,7 @@ + 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)) || +@@ -507,7 +508,8 @@ + 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); +@@ -819,6 +821,20 @@ + 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 +@@ -896,6 +912,7 @@ + if (!timr) + return -EINVAL; + ++ rcu_read_lock(); + kc = clockid_to_kclock(timr->it_clock); + if (WARN_ON_ONCE(!kc || !kc->timer_set)) + error = -EINVAL; +@@ -904,9 +921,12 @@ + + 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))) +@@ -944,10 +964,15 @@ + 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); +@@ -973,8 +998,18 @@ + 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 -Nur linux-4.1.39.orig/kernel/time/tick-broadcast-hrtimer.c linux-4.1.39/kernel/time/tick-broadcast-hrtimer.c +--- linux-4.1.39.orig/kernel/time/tick-broadcast-hrtimer.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/time/tick-broadcast-hrtimer.c 2017-04-18 17:56:30.641398216 +0200 +@@ -109,5 +109,6 @@ + { + hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + bctimer.function = bc_handler; ++ bctimer.irqsafe = true; + clockevents_register_device(&ce_broadcast_hrtimer); + } +diff -Nur linux-4.1.39.orig/kernel/time/tick-common.c linux-4.1.39/kernel/time/tick-common.c +--- linux-4.1.39.orig/kernel/time/tick-common.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/time/tick-common.c 2017-04-18 17:56:30.641398216 +0200 +@@ -78,13 +78,15 @@ + static void tick_periodic(int cpu) + { + if (tick_do_timer_cpu == cpu) { +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + + /* Keep track of the next tick event */ + tick_next_period = ktime_add(tick_next_period, tick_period); + + do_timer(1); +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } + +@@ -146,9 +148,9 @@ + ktime_t next; + + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + next = tick_next_period; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); + +diff -Nur linux-4.1.39.orig/kernel/time/tick-sched.c linux-4.1.39/kernel/time/tick-sched.c +--- linux-4.1.39.orig/kernel/time/tick-sched.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/time/tick-sched.c 2017-04-18 17:56:30.641398216 +0200 +@@ -62,7 +62,8 @@ + return; + + /* Reevalute with jiffies_lock held */ +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + + delta = ktime_sub(now, last_jiffies_update); + if (delta.tv64 >= tick_period.tv64) { +@@ -85,10 +86,12 @@ + /* Keep the tick_next_period variable up to date */ + tick_next_period = ktime_add(last_jiffies_update, tick_period); + } else { +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + return; + } +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } + +@@ -99,12 +102,14 @@ + { + ktime_t period; + +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_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(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + return period; + } + +@@ -176,6 +181,11 @@ + return false; + } + ++ if (!arch_irq_work_has_interrupt()) { ++ trace_tick_stop(0, "missing irq work interrupt\n"); ++ return false; ++ } ++ + /* sched_clock_tick() needs us? */ + #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK + /* +@@ -222,6 +232,7 @@ + + static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { + .func = nohz_full_kick_work_func, ++ .flags = IRQ_WORK_HARD_IRQ, + }; + + /* +@@ -578,10 +589,10 @@ + + /* Read jiffies and the time when jiffies were updated last */ + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + last_update = last_jiffies_update; + last_jiffies = jiffies; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + + if (rcu_needs_cpu(&rcu_delta_jiffies) || + arch_needs_cpu() || irq_work_needs_cpu()) { +@@ -759,14 +770,7 @@ + return false; + + if (unlikely(local_softirq_pending() && cpu_online(cpu))) { +- static int ratelimit; +- +- if (ratelimit < 10 && +- (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { +- pr_warn("NOHZ: local_softirq_pending %02x\n", +- (unsigned int) local_softirq_pending()); +- ratelimit++; +- } ++ softirq_check_pending_idle(); + return false; + } + +@@ -1154,6 +1158,7 @@ + * 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) */ +diff -Nur linux-4.1.39.orig/kernel/time/timekeeping.c linux-4.1.39/kernel/time/timekeeping.c +--- linux-4.1.39.orig/kernel/time/timekeeping.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/time/timekeeping.c 2017-04-18 17:56:30.641398216 +0200 +@@ -2087,8 +2087,10 @@ + */ + void xtime_update(unsigned long ticks) + { +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + do_timer(ticks); +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } +diff -Nur linux-4.1.39.orig/kernel/time/timekeeping.h linux-4.1.39/kernel/time/timekeeping.h +--- linux-4.1.39.orig/kernel/time/timekeeping.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/time/timekeeping.h 2017-04-18 17:56:30.641398216 +0200 +@@ -22,7 +22,8 @@ + extern void do_timer(unsigned long ticks); + extern void update_wall_time(void); + +-extern seqlock_t jiffies_lock; ++extern raw_spinlock_t jiffies_lock; ++extern seqcount_t jiffies_seq; + + #define CS_NAME_LEN 32 + +diff -Nur linux-4.1.39.orig/kernel/time/timer.c linux-4.1.39/kernel/time/timer.c +--- linux-4.1.39.orig/kernel/time/timer.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/time/timer.c 2017-04-18 17:56:30.641398216 +0200 +@@ -78,6 +78,9 @@ + 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; + unsigned long active_timers; +@@ -768,6 +771,36 @@ + } + } + ++#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) +@@ -798,14 +831,8 @@ + * 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; +@@ -979,6 +1006,29 @@ + } + 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_all(&(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 +@@ -1036,7 +1086,7 @@ + } + EXPORT_SYMBOL(try_to_del_timer_sync); + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + static DEFINE_PER_CPU(struct tvec_base, __tvec_bases); + + /** +@@ -1098,7 +1148,7 @@ + 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); +@@ -1219,16 +1269,18 @@ + if (irqsafe) { + spin_unlock(&base->lock); + call_timer_fn(timer, fn, data); ++ base->running_timer = NULL; + spin_lock(&base->lock); + } else { + spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn, data); ++ base->running_timer = NULL; + spin_lock_irq(&base->lock); + } + } + } +- base->running_timer = NULL; + spin_unlock_irq(&base->lock); ++ wakeup_timer_waiters(base); + } + + #ifdef CONFIG_NO_HZ_COMMON +@@ -1367,6 +1419,14 @@ + if (cpu_is_offline(smp_processor_id())) + return expires; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * On PREEMPT_RT we cannot sleep here. As a result we can't take ++ * the base lock to check when the next timer is pending and so ++ * we assume the next jiffy. ++ */ ++ return now + 1; ++#endif + spin_lock(&base->lock); + if (base->active_timers) { + if (time_before_eq(base->next_timer, base->timer_jiffies)) +@@ -1392,13 +1452,13 @@ + + /* 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(user_tick); +-#ifdef CONFIG_IRQ_WORK ++#if defined(CONFIG_IRQ_WORK) + if (in_irq()) + irq_work_tick(); + #endif +- scheduler_tick(); + run_posix_cpu_timers(p); + } + +@@ -1411,6 +1471,8 @@ + + hrtimer_run_pending(); + ++ irq_work_tick_soft(); ++ + if (time_after_eq(jiffies, base->timer_jiffies)) + __run_timers(base); + } +@@ -1566,7 +1628,7 @@ + + 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. +@@ -1590,7 +1652,7 @@ + + spin_unlock(&old_base->lock); + spin_unlock_irq(&new_base->lock); +- put_cpu_var(tvec_bases); ++ put_local_var(tvec_bases); + } + + static int timer_cpu_notify(struct notifier_block *self, +@@ -1625,6 +1687,9 @@ + base->cpu = cpu; + per_cpu(tvec_bases, cpu) = base; + spin_lock_init(&base->lock); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ init_waitqueue_head(&base->wait_for_running_timer); ++#endif + + for (j = 0; j < TVN_SIZE; j++) { + INIT_LIST_HEAD(base->tv5.vec + j); +diff -Nur linux-4.1.39.orig/kernel/trace/Kconfig linux-4.1.39/kernel/trace/Kconfig +--- linux-4.1.39.orig/kernel/trace/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/trace/Kconfig 2017-04-18 17:56:30.641398216 +0200 +@@ -187,6 +187,24 @@ + 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 +@@ -211,6 +229,24 @@ + 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 +@@ -221,6 +257,74 @@ + 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 -Nur linux-4.1.39.orig/kernel/trace/latency_hist.c linux-4.1.39/kernel/trace/latency_hist.c +--- linux-4.1.39.orig/kernel/trace/latency_hist.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.1.39/kernel/trace/latency_hist.c 2017-04-18 17:56:30.641398216 +0200 +@@ -0,0 +1,1178 @@ ++/* ++ * 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 ++ ++#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_possible(cpu) || 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 const 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 const 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 (kstrtoul(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 (kstrtoul(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; ++} ++ ++device_initcall(latency_hist_init); +diff -Nur linux-4.1.39.orig/kernel/trace/Makefile linux-4.1.39/kernel/trace/Makefile +--- linux-4.1.39.orig/kernel/trace/Makefile 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/trace/Makefile 2017-04-18 17:56:30.641398216 +0200 +@@ -36,6 +36,10 @@ + 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 -Nur linux-4.1.39.orig/kernel/trace/trace.c linux-4.1.39/kernel/trace/trace.c +--- linux-4.1.39.orig/kernel/trace/trace.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/trace/trace.c 2017-04-18 17:56:30.641398216 +0200 +@@ -1630,6 +1630,7 @@ + struct task_struct *tsk = current; + + entry->preempt_count = pc & 0xff; ++ entry->preempt_lazy_count = preempt_lazy_count(); + entry->pid = (tsk) ? tsk->pid : 0; + entry->flags = + #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT +@@ -1639,8 +1640,11 @@ + #endif + ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | + ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | +- (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | ++ (tif_need_resched_now() ? TRACE_FLAG_NEED_RESCHED : 0) | ++ (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0) | + (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); ++ ++ entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; + } + EXPORT_SYMBOL_GPL(tracing_generic_entry_update); + +@@ -2558,14 +2562,17 @@ + + static void print_lat_help_header(struct seq_file *m) + { +- seq_puts(m, "# _------=> CPU# \n" +- "# / _-----=> irqs-off \n" +- "# | / _----=> need-resched \n" +- "# || / _---=> hardirq/softirq \n" +- "# ||| / _--=> preempt-depth \n" +- "# |||| / delay \n" +- "# cmd pid ||||| time | caller \n" +- "# \\ / ||||| \\ | / \n"); ++ seq_puts(m, "# _--------=> CPU# \n" ++ "# / _-------=> irqs-off \n" ++ "# | / _------=> need-resched \n" ++ "# || / _-----=> need-resched_lazy \n" ++ "# ||| / _----=> hardirq/softirq \n" ++ "# |||| / _---=> preempt-depth \n" ++ "# ||||| / _--=> preempt-lazy-depth\n" ++ "# |||||| / _-=> migrate-disable \n" ++ "# ||||||| / delay \n" ++ "# cmd pid |||||||| time | caller \n" ++ "# \\ / |||||||| \\ | / \n"); + } + + static void print_event_info(struct trace_buffer *buf, struct seq_file *m) +@@ -2591,11 +2598,14 @@ + print_event_info(buf, m); + seq_puts(m, "# _-----=> irqs-off\n" + "# / _----=> need-resched\n" +- "# | / _---=> hardirq/softirq\n" +- "# || / _--=> preempt-depth\n" +- "# ||| / delay\n" +- "# TASK-PID CPU# |||| TIMESTAMP FUNCTION\n" +- "# | | | |||| | |\n"); ++ "# |/ _-----=> need-resched_lazy\n" ++ "# || / _---=> hardirq/softirq\n" ++ "# ||| / _--=> preempt-depth\n" ++ "# |||| / _-=> preempt-lazy-depth\n" ++ "# ||||| / _-=> migrate-disable \n" ++ "# |||||| / delay\n" ++ "# TASK-PID CPU# ||||||| TIMESTAMP FUNCTION\n" ++ "# | | | ||||||| | |\n"); + } + + void +diff -Nur linux-4.1.39.orig/kernel/trace/trace_events.c linux-4.1.39/kernel/trace/trace_events.c +--- linux-4.1.39.orig/kernel/trace/trace_events.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/trace/trace_events.c 2017-04-18 17:56:30.645398372 +0200 +@@ -162,6 +162,8 @@ + __common_field(unsigned char, flags); + __common_field(unsigned char, preempt_count); + __common_field(int, pid); ++ __common_field(unsigned short, migrate_disable); ++ __common_field(unsigned short, padding); + + return ret; + } +@@ -198,6 +200,14 @@ + + local_save_flags(fbuffer->flags); + fbuffer->pc = preempt_count(); ++ /* ++ * If CONFIG_PREEMPT is enabled, then the tracepoint itself disables ++ * preemption (adding one to the preempt_count). Since we are ++ * interested in the preempt_count at the time the tracepoint was ++ * hit, we need to subtract one to offset the increment. ++ */ ++ if (IS_ENABLED(CONFIG_PREEMPT)) ++ fbuffer->pc--; + fbuffer->ftrace_file = ftrace_file; + + fbuffer->event = +diff -Nur linux-4.1.39.orig/kernel/trace/trace.h linux-4.1.39/kernel/trace/trace.h +--- linux-4.1.39.orig/kernel/trace/trace.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/trace/trace.h 2017-04-18 17:56:30.641398216 +0200 +@@ -120,6 +120,7 @@ + * NEED_RESCHED - reschedule is requested + * HARDIRQ - inside an interrupt handler + * SOFTIRQ - inside a softirq handler ++ * NEED_RESCHED_LAZY - lazy reschedule is requested + */ + enum trace_flag_type { + TRACE_FLAG_IRQS_OFF = 0x01, +@@ -128,6 +129,7 @@ + TRACE_FLAG_HARDIRQ = 0x08, + TRACE_FLAG_SOFTIRQ = 0x10, + TRACE_FLAG_PREEMPT_RESCHED = 0x20, ++ TRACE_FLAG_NEED_RESCHED_LAZY = 0x40, + }; + + #define TRACE_BUF_SIZE 1024 +diff -Nur linux-4.1.39.orig/kernel/trace/trace_irqsoff.c linux-4.1.39/kernel/trace/trace_irqsoff.c +--- linux-4.1.39.orig/kernel/trace/trace_irqsoff.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/trace/trace_irqsoff.c 2017-04-18 17:56:30.645398372 +0200 +@@ -13,6 +13,7 @@ + #include + #include + #include ++#include + + #include "trace.h" + +@@ -433,11 +434,13 @@ + { + 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); + } +@@ -447,6 +450,7 @@ + #ifdef CONFIG_PROVE_LOCKING + void time_hardirqs_on(unsigned long a0, unsigned long a1) + { ++ trace_preemptirqsoff_hist_rcuidle(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(a0, a1); + } +@@ -455,6 +459,7 @@ + { + if (!preempt_trace() && irq_trace()) + start_critical_timing(a0, a1); ++ trace_preemptirqsoff_hist_rcuidle(IRQS_OFF, 1); + } + + #else /* !CONFIG_PROVE_LOCKING */ +@@ -480,6 +485,7 @@ + */ + void trace_hardirqs_on(void) + { ++ trace_preemptirqsoff_hist_rcuidle(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + } +@@ -489,11 +495,13 @@ + { + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); ++ trace_preemptirqsoff_hist_rcuidle(IRQS_OFF, 1); + } + EXPORT_SYMBOL(trace_hardirqs_off); + + __visible 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); + } +@@ -503,6 +511,7 @@ + { + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, caller_addr); ++ trace_preemptirqsoff_hist(IRQS_OFF, 1); + } + EXPORT_SYMBOL(trace_hardirqs_off_caller); + +@@ -512,12 +521,14 @@ + #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 -Nur linux-4.1.39.orig/kernel/trace/trace_output.c linux-4.1.39/kernel/trace/trace_output.c +--- linux-4.1.39.orig/kernel/trace/trace_output.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/trace/trace_output.c 2017-04-18 17:56:30.645398372 +0200 +@@ -430,6 +430,7 @@ + { + char hardsoft_irq; + char need_resched; ++ char need_resched_lazy; + char irqs_off; + int hardirq; + int softirq; +@@ -457,6 +458,8 @@ + need_resched = '.'; + break; + } ++ need_resched_lazy = ++ (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; + + hardsoft_irq = + (hardirq && softirq) ? 'H' : +@@ -464,14 +467,25 @@ + softirq ? 's' : + '.'; + +- trace_seq_printf(s, "%c%c%c", +- irqs_off, need_resched, hardsoft_irq); ++ trace_seq_printf(s, "%c%c%c%c", ++ irqs_off, need_resched, need_resched_lazy, ++ hardsoft_irq); + + if (entry->preempt_count) + trace_seq_printf(s, "%x", entry->preempt_count); + else + trace_seq_putc(s, '.'); + ++ if (entry->preempt_lazy_count) ++ trace_seq_printf(s, "%x", entry->preempt_lazy_count); ++ else ++ trace_seq_putc(s, '.'); ++ ++ if (entry->migrate_disable) ++ trace_seq_printf(s, "%x", entry->migrate_disable); ++ else ++ trace_seq_putc(s, '.'); ++ + return !trace_seq_has_overflowed(s); + } + +diff -Nur linux-4.1.39.orig/kernel/trace/trace_sched_switch.c linux-4.1.39/kernel/trace/trace_sched_switch.c +--- linux-4.1.39.orig/kernel/trace/trace_sched_switch.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/trace/trace_sched_switch.c 2017-04-18 17:56:30.645398372 +0200 +@@ -26,7 +26,7 @@ + } + + static void +-probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success) ++probe_sched_wakeup(void *ignore, struct task_struct *wakee) + { + if (unlikely(!sched_ref)) + return; +diff -Nur linux-4.1.39.orig/kernel/trace/trace_sched_wakeup.c linux-4.1.39/kernel/trace/trace_sched_wakeup.c +--- linux-4.1.39.orig/kernel/trace/trace_sched_wakeup.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/trace/trace_sched_wakeup.c 2017-04-18 17:56:30.645398372 +0200 +@@ -514,7 +514,7 @@ + } + + 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 -Nur linux-4.1.39.orig/kernel/user.c linux-4.1.39/kernel/user.c +--- linux-4.1.39.orig/kernel/user.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/user.c 2017-04-18 17:56:30.645398372 +0200 +@@ -161,11 +161,11 @@ + 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(kuid_t uid) +diff -Nur linux-4.1.39.orig/kernel/watchdog.c linux-4.1.39/kernel/watchdog.c +--- linux-4.1.39.orig/kernel/watchdog.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/watchdog.c 2017-04-18 17:56:30.645398372 +0200 +@@ -262,6 +262,8 @@ + + #ifdef CONFIG_HARDLOCKUP_DETECTOR + ++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, +@@ -295,13 +297,21 @@ + /* only print hardlockups once */ + if (__this_cpu_read(hard_watchdog_warn) == true) + return; ++ /* ++ * If early-printk is enabled then make sure we do not ++ * lock up in printk() and kill console logging: ++ */ ++ printk_kill(); + +- if (hardlockup_panic) ++ 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; +@@ -444,6 +454,7 @@ + /* kick off the timer for the hardlockup detector */ + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; ++ hrtimer->irqsafe = 1; + + /* Enable the perf event */ + watchdog_nmi_enable(cpu); +diff -Nur linux-4.1.39.orig/kernel/workqueue.c linux-4.1.39/kernel/workqueue.c +--- linux-4.1.39.orig/kernel/workqueue.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/workqueue.c 2017-04-18 17:56:30.645398372 +0200 +@@ -48,6 +48,8 @@ + #include + #include + #include ++#include ++#include + + #include "workqueue_internal.h" + +@@ -121,11 +123,16 @@ + * cpu or grabbing pool->lock is enough for read access. If + * POOL_DISASSOCIATED is set, it's identical to L. + * ++ * On RT we need the extra protection via rt_lock_idle_list() for ++ * the list manipulations against read access from ++ * wq_worker_sleeping(). All other places are nicely serialized via ++ * pool->lock. ++ * + * A: pool->attach_mutex protected. + * + * PL: wq_pool_mutex protected. + * +- * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads. ++ * PR: wq_pool_mutex protected for writes. RCU protected for reads. + * + * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. + * +@@ -134,7 +141,7 @@ + * + * WQ: wq->mutex protected. + * +- * WR: wq->mutex protected for writes. Sched-RCU protected for reads. ++ * WR: wq->mutex protected for writes. RCU protected for reads. + * + * MD: wq_mayday_lock protected. + */ +@@ -183,7 +190,7 @@ + atomic_t nr_running ____cacheline_aligned_in_smp; + + /* +- * Destruction of pool is sched-RCU protected to allow dereferences ++ * Destruction of pool is RCU protected to allow dereferences + * from get_work_pool(). + */ + struct rcu_head rcu; +@@ -212,7 +219,7 @@ + /* + * Release of unbound pwq is punted to system_wq. See put_pwq() + * and pwq_unbound_release_workfn() for details. pool_workqueue +- * itself is also sched-RCU protected so that the first pwq can be ++ * itself is also RCU protected so that the first pwq can be + * determined without grabbing wq->mutex. + */ + struct work_struct unbound_release_work; +@@ -334,6 +341,8 @@ + struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; + EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); + ++static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock); ++ + static int worker_thread(void *__worker); + static void copy_workqueue_attrs(struct workqueue_attrs *to, + const struct workqueue_attrs *from); +@@ -343,14 +352,14 @@ + #include + + #define assert_rcu_or_pool_mutex() \ +- rcu_lockdep_assert(rcu_read_lock_sched_held() || \ ++ rcu_lockdep_assert(rcu_read_lock_held() || \ + lockdep_is_held(&wq_pool_mutex), \ +- "sched RCU or wq_pool_mutex should be held") ++ "RCU or wq_pool_mutex should be held") + + #define assert_rcu_or_wq_mutex(wq) \ +- rcu_lockdep_assert(rcu_read_lock_sched_held() || \ ++ rcu_lockdep_assert(rcu_read_lock_held() || \ + lockdep_is_held(&wq->mutex), \ +- "sched RCU or wq->mutex should be held") ++ "RCU or wq->mutex should be held") + + #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ + rcu_lockdep_assert(rcu_read_lock_sched_held() || \ +@@ -368,7 +377,7 @@ + * @pool: iteration cursor + * @pi: integer used for iteration + * +- * This must be called either with wq_pool_mutex held or sched RCU read ++ * This must be called either with wq_pool_mutex held or RCU read + * locked. If the pool needs to be used beyond the locking in effect, the + * caller is responsible for guaranteeing that the pool stays online. + * +@@ -400,7 +409,7 @@ + * @pwq: iteration cursor + * @wq: the target workqueue + * +- * This must be called either with wq->mutex held or sched RCU read locked. ++ * This must be called either with wq->mutex held or RCU read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. + * +@@ -412,6 +421,31 @@ + if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \ + else + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static inline void rt_lock_idle_list(struct worker_pool *pool) ++{ ++ preempt_disable(); ++} ++static inline void rt_unlock_idle_list(struct worker_pool *pool) ++{ ++ preempt_enable(); ++} ++static inline void sched_lock_idle_list(struct worker_pool *pool) { } ++static inline void sched_unlock_idle_list(struct worker_pool *pool) { } ++#else ++static inline void rt_lock_idle_list(struct worker_pool *pool) { } ++static inline void rt_unlock_idle_list(struct worker_pool *pool) { } ++static inline void sched_lock_idle_list(struct worker_pool *pool) ++{ ++ spin_lock_irq(&pool->lock); ++} ++static inline void sched_unlock_idle_list(struct worker_pool *pool) ++{ ++ spin_unlock_irq(&pool->lock); ++} ++#endif ++ ++ + #ifdef CONFIG_DEBUG_OBJECTS_WORK + + static struct debug_obj_descr work_debug_descr; +@@ -562,8 +596,7 @@ + * @wq: the target workqueue + * @node: the node ID + * +- * This must be called with any of wq_pool_mutex, wq->mutex or sched RCU +- * read locked. ++ * This must be called with any of wq_pool_mutex, wq->mutex or RCU read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. + * +@@ -706,8 +739,8 @@ + * @work: the work item of interest + * + * Pools are created and destroyed under wq_pool_mutex, and allows read +- * access under sched-RCU read lock. As such, this function should be +- * called under wq_pool_mutex or with preemption disabled. ++ * access under RCU read lock. As such, this function should be ++ * called under wq_pool_mutex or inside of a rcu_read_lock() region. + * + * All fields of the returned pool are accessible as long as the above + * mentioned locking is in effect. If the returned pool needs to be used +@@ -844,51 +877,44 @@ + */ + static void wake_up_worker(struct worker_pool *pool) + { +- struct worker *worker = first_idle_worker(pool); ++ struct worker *worker; ++ ++ rt_lock_idle_list(pool); ++ ++ worker = first_idle_worker(pool); + + if (likely(worker)) + wake_up_process(worker->task); ++ ++ rt_unlock_idle_list(pool); + } + + /** +- * 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, int cpu) ++void wq_worker_running(struct task_struct *task) + { + struct worker *worker = kthread_data(task); + +- if (!(worker->flags & WORKER_NOT_RUNNING)) { +- WARN_ON_ONCE(worker->pool->cpu != cpu); ++ if (!worker->sleeping) ++ return; ++ if (!(worker->flags & WORKER_NOT_RUNNING)) + atomic_inc(&worker->pool->nr_running); +- } ++ 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) +- * +- * Return: +- * 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, int cpu) ++void wq_worker_sleeping(struct task_struct *task) + { +- struct worker *worker = kthread_data(task), *to_wakeup = NULL; ++ struct worker *worker = kthread_data(task); + struct worker_pool *pool; + + /* +@@ -897,29 +923,26 @@ + * checking NOT_RUNNING. + */ + if (worker->flags & WORKER_NOT_RUNNING) +- return NULL; ++ return; + + pool = worker->pool; + +- /* this can only happen on the local cpu */ +- if (WARN_ON_ONCE(cpu != raw_smp_processor_id() || pool->cpu != cpu)) +- return NULL; ++ if (WARN_ON_ONCE(worker->sleeping)) ++ return; ++ ++ worker->sleeping = 1; + + /* + * 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 we're bound to and +- * 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 pool +- * lock is safe. + */ + if (atomic_dec_and_test(&pool->nr_running) && +- !list_empty(&pool->worklist)) +- to_wakeup = first_idle_worker(pool); +- return to_wakeup ? to_wakeup->task : NULL; ++ !list_empty(&pool->worklist)) { ++ sched_lock_idle_list(pool); ++ wake_up_worker(pool); ++ sched_unlock_idle_list(pool); ++ } + } + + /** +@@ -1113,12 +1136,14 @@ + { + if (pwq) { + /* +- * As both pwqs and pools are sched-RCU protected, the ++ * As both pwqs and pools are RCU protected, the + * following lock operations are safe. + */ +- spin_lock_irq(&pwq->pool->lock); ++ rcu_read_lock(); ++ local_spin_lock_irq(pendingb_lock, &pwq->pool->lock); + put_pwq(pwq); +- spin_unlock_irq(&pwq->pool->lock); ++ local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock); ++ rcu_read_unlock(); + } + } + +@@ -1220,7 +1245,7 @@ + struct worker_pool *pool; + struct pool_workqueue *pwq; + +- local_irq_save(*flags); ++ local_lock_irqsave(pendingb_lock, *flags); + + /* try to steal the timer if it exists */ + if (is_dwork) { +@@ -1239,6 +1264,7 @@ + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) + return 0; + ++ rcu_read_lock(); + /* + * The queueing is in progress, or it is already queued. Try to + * steal it from ->worklist without clearing WORK_STRUCT_PENDING. +@@ -1277,14 +1303,16 @@ + set_work_pool_and_keep_pending(work, pool->id); + + spin_unlock(&pool->lock); ++ rcu_read_unlock(); + return 1; + } + spin_unlock(&pool->lock); + fail: +- local_irq_restore(*flags); ++ rcu_read_unlock(); ++ local_unlock_irqrestore(pendingb_lock, *flags); + if (work_is_canceling(work)) + return -ENOENT; +- cpu_relax(); ++ cpu_chill(); + return -EAGAIN; + } + +@@ -1353,7 +1381,7 @@ + * queued or lose PENDING. Grabbing PENDING and queueing should + * happen with IRQ disabled. + */ +- WARN_ON_ONCE(!irqs_disabled()); ++ WARN_ON_ONCE_NONRT(!irqs_disabled()); + + debug_work_activate(work); + +@@ -1361,6 +1389,8 @@ + if (unlikely(wq->flags & __WQ_DRAINING) && + WARN_ON_ONCE(!is_chained_work(wq))) + return; ++ ++ rcu_read_lock(); + retry: + if (req_cpu == WORK_CPU_UNBOUND) + cpu = raw_smp_processor_id(); +@@ -1417,10 +1447,8 @@ + /* pwq determined, queue */ + trace_workqueue_queue_work(req_cpu, pwq, work); + +- if (WARN_ON(!list_empty(&work->entry))) { +- spin_unlock(&pwq->pool->lock); +- return; +- } ++ if (WARN_ON(!list_empty(&work->entry))) ++ goto out; + + pwq->nr_in_flight[pwq->work_color]++; + work_flags = work_color_to_flags(pwq->work_color); +@@ -1436,7 +1464,9 @@ + + insert_work(pwq, work, worklist, work_flags); + ++out: + spin_unlock(&pwq->pool->lock); ++ rcu_read_unlock(); + } + + /** +@@ -1456,14 +1486,14 @@ + bool ret = false; + unsigned long flags; + +- local_irq_save(flags); ++ local_lock_irqsave(pendingb_lock,flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_work(cpu, wq, work); + ret = true; + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(queue_work_on); +@@ -1530,14 +1560,14 @@ + unsigned long flags; + + /* read the comment in __queue_work() */ +- local_irq_save(flags); ++ local_lock_irqsave(pendingb_lock, flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_delayed_work(cpu, wq, dwork, delay); + ret = true; + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(queue_delayed_work_on); +@@ -1572,7 +1602,7 @@ + + if (likely(ret >= 0)) { + __queue_delayed_work(cpu, wq, dwork, delay); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + } + + /* -ENOENT from try_to_grab_pending() becomes %true */ +@@ -1605,7 +1635,9 @@ + worker->last_active = jiffies; + + /* idle_list is LIFO */ ++ rt_lock_idle_list(pool); + list_add(&worker->entry, &pool->idle_list); ++ rt_unlock_idle_list(pool); + + if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) + mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); +@@ -1638,7 +1670,9 @@ + return; + worker_clr_flags(worker, WORKER_IDLE); + pool->nr_idle--; ++ rt_lock_idle_list(pool); + list_del_init(&worker->entry); ++ rt_unlock_idle_list(pool); + } + + static struct worker *alloc_worker(int node) +@@ -1806,7 +1840,9 @@ + pool->nr_workers--; + pool->nr_idle--; + ++ rt_lock_idle_list(pool); + list_del_init(&worker->entry); ++ rt_unlock_idle_list(pool); + worker->flags |= WORKER_DIE; + wake_up_process(worker->task); + } +@@ -2723,14 +2759,14 @@ + + might_sleep(); + +- local_irq_disable(); ++ rcu_read_lock(); + pool = get_work_pool(work); + if (!pool) { +- local_irq_enable(); ++ rcu_read_unlock(); + return false; + } + +- spin_lock(&pool->lock); ++ spin_lock_irq(&pool->lock); + /* see the comment in try_to_grab_pending() with the same code */ + pwq = get_work_pwq(work); + if (pwq) { +@@ -2757,10 +2793,11 @@ + else + lock_map_acquire_read(&pwq->wq->lockdep_map); + lock_map_release(&pwq->wq->lockdep_map); +- ++ rcu_read_unlock(); + return true; + already_gone: + spin_unlock_irq(&pool->lock); ++ rcu_read_unlock(); + return false; + } + +@@ -2847,7 +2884,7 @@ + + /* tell other tasks trying to grab @work to back off */ + mark_work_canceling(work); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + + flush_work(work); + clear_work_data(work); +@@ -2902,10 +2939,10 @@ + */ + bool flush_delayed_work(struct delayed_work *dwork) + { +- local_irq_disable(); ++ local_lock_irq(pendingb_lock); + if (del_timer_sync(&dwork->timer)) + __queue_work(dwork->cpu, dwork->wq, &dwork->work); +- local_irq_enable(); ++ local_unlock_irq(pendingb_lock); + return flush_work(&dwork->work); + } + EXPORT_SYMBOL(flush_delayed_work); +@@ -2940,7 +2977,7 @@ + + set_work_pool_and_clear_pending(&dwork->work, + get_work_pool_id(&dwork->work)); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(cancel_delayed_work); +@@ -3198,7 +3235,7 @@ + * put_unbound_pool - put a worker_pool + * @pool: worker_pool to put + * +- * Put @pool. If its refcnt reaches zero, it gets destroyed in sched-RCU ++ * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU + * safe manner. get_unbound_pool() calls this function on its failure path + * and this function should be able to release pools which went through, + * successfully or not, init_worker_pool(). +@@ -3252,8 +3289,8 @@ + del_timer_sync(&pool->idle_timer); + del_timer_sync(&pool->mayday_timer); + +- /* sched-RCU protected to allow dereferences from get_work_pool() */ +- call_rcu_sched(&pool->rcu, rcu_free_pool); ++ /* RCU protected to allow dereferences from get_work_pool() */ ++ call_rcu(&pool->rcu, rcu_free_pool); + } + + /** +@@ -3358,14 +3395,14 @@ + put_unbound_pool(pool); + mutex_unlock(&wq_pool_mutex); + +- call_rcu_sched(&pwq->rcu, rcu_free_pwq); ++ call_rcu(&pwq->rcu, rcu_free_pwq); + + /* + * If we're the last pwq going away, @wq is already dead and no one + * is gonna access it anymore. Schedule RCU free. + */ + if (is_last) +- call_rcu_sched(&wq->rcu, rcu_free_wq); ++ call_rcu(&wq->rcu, rcu_free_wq); + } + + /** +@@ -4003,7 +4040,7 @@ + * The base ref is never dropped on per-cpu pwqs. Directly + * schedule RCU free. + */ +- call_rcu_sched(&wq->rcu, rcu_free_wq); ++ call_rcu(&wq->rcu, rcu_free_wq); + } else { + /* + * We're the sole accessor of @wq at this point. Directly +@@ -4096,7 +4133,8 @@ + struct pool_workqueue *pwq; + bool ret; + +- rcu_read_lock_sched(); ++ rcu_read_lock(); ++ preempt_disable(); + + if (cpu == WORK_CPU_UNBOUND) + cpu = smp_processor_id(); +@@ -4107,7 +4145,8 @@ + pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); + + ret = !list_empty(&pwq->delayed_works); +- rcu_read_unlock_sched(); ++ preempt_enable(); ++ rcu_read_unlock(); + + return ret; + } +@@ -4133,15 +4172,15 @@ + if (work_pending(work)) + ret |= WORK_BUSY_PENDING; + +- local_irq_save(flags); ++ rcu_read_lock(); + pool = get_work_pool(work); + if (pool) { +- spin_lock(&pool->lock); ++ spin_lock_irqsave(&pool->lock, flags); + if (find_worker_executing_work(pool, work)) + ret |= WORK_BUSY_RUNNING; +- spin_unlock(&pool->lock); ++ spin_unlock_irqrestore(&pool->lock, flags); + } +- local_irq_restore(flags); ++ rcu_read_unlock(); + + return ret; + } +@@ -4330,7 +4369,7 @@ + unsigned long flags; + int pi; + +- rcu_read_lock_sched(); ++ rcu_read_lock(); + + pr_info("Showing busy workqueues and worker pools:\n"); + +@@ -4381,7 +4420,7 @@ + spin_unlock_irqrestore(&pool->lock, flags); + } + +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + } + + /* +@@ -4742,16 +4781,16 @@ + * nr_active is monotonically decreasing. It's safe + * to peek without lock. + */ +- rcu_read_lock_sched(); ++ rcu_read_lock(); + for_each_pwq(pwq, wq) { + WARN_ON_ONCE(pwq->nr_active < 0); + if (pwq->nr_active) { + busy = true; +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + goto out_unlock; + } + } +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + } + out_unlock: + mutex_unlock(&wq_pool_mutex); +@@ -4865,7 +4904,8 @@ + const char *delim = ""; + int node, written = 0; + +- rcu_read_lock_sched(); ++ get_online_cpus(); ++ rcu_read_lock(); + for_each_node(node) { + written += scnprintf(buf + written, PAGE_SIZE - written, + "%s%d:%d", delim, node, +@@ -4873,7 +4913,8 @@ + delim = " "; + } + written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); ++ put_online_cpus(); + + return written; + } +diff -Nur linux-4.1.39.orig/kernel/workqueue_internal.h linux-4.1.39/kernel/workqueue_internal.h +--- linux-4.1.39.orig/kernel/workqueue_internal.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/kernel/workqueue_internal.h 2017-04-18 17:56:30.645398372 +0200 +@@ -43,6 +43,7 @@ + unsigned long last_active; /* L: last active timestamp */ + unsigned int flags; /* X: flags */ + int id; /* I: worker id */ ++ int sleeping; /* None */ + + /* + * Opaque string set with work_set_desc(). Printed out with task +@@ -68,7 +69,7 @@ + * Scheduler hooks for concurrency managed workqueue. Only to be used from + * sched/core.c and workqueue.c. + */ +-void wq_worker_waking_up(struct task_struct *task, int cpu); +-struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu); ++void wq_worker_running(struct task_struct *task); ++void wq_worker_sleeping(struct task_struct *task); + + #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ +diff -Nur linux-4.1.39.orig/lib/debugobjects.c linux-4.1.39/lib/debugobjects.c +--- linux-4.1.39.orig/lib/debugobjects.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/lib/debugobjects.c 2017-04-18 17:56:30.645398372 +0200 +@@ -309,7 +309,10 @@ + 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); + +diff -Nur linux-4.1.39.orig/lib/dump_stack.c linux-4.1.39/lib/dump_stack.c +--- linux-4.1.39.orig/lib/dump_stack.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/lib/dump_stack.c 2017-04-18 17:56:30.645398372 +0200 +@@ -8,6 +8,7 @@ + #include + #include + #include ++#include + + static void __dump_stack(void) + { +diff -Nur linux-4.1.39.orig/lib/idr.c linux-4.1.39/lib/idr.c +--- linux-4.1.39.orig/lib/idr.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/lib/idr.c 2017-04-18 17:56:30.645398372 +0200 +@@ -30,6 +30,7 @@ + #include + #include + #include ++#include + + #define MAX_IDR_SHIFT (sizeof(int) * 8 - 1) + #define MAX_IDR_BIT (1U << MAX_IDR_SHIFT) +@@ -366,6 +367,35 @@ + idr_mark_full(pa, id); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static DEFINE_LOCAL_IRQ_LOCK(idr_lock); ++ ++static inline void idr_preload_lock(void) ++{ ++ local_lock(idr_lock); ++} ++ ++static inline void idr_preload_unlock(void) ++{ ++ local_unlock(idr_lock); ++} ++ ++void idr_preload_end(void) ++{ ++ idr_preload_unlock(); ++} ++EXPORT_SYMBOL(idr_preload_end); ++#else ++static inline void idr_preload_lock(void) ++{ ++ preempt_disable(); ++} ++ ++static inline void idr_preload_unlock(void) ++{ ++ preempt_enable(); ++} ++#endif + + /** + * idr_preload - preload for idr_alloc() +@@ -401,7 +431,7 @@ + WARN_ON_ONCE(in_interrupt()); + might_sleep_if(gfp_mask & __GFP_WAIT); + +- preempt_disable(); ++ idr_preload_lock(); + + /* + * idr_alloc() is likely to succeed w/o full idr_layer buffer and +@@ -413,9 +443,9 @@ + while (__this_cpu_read(idr_preload_cnt) < MAX_IDR_FREE) { + struct idr_layer *new; + +- preempt_enable(); ++ idr_preload_unlock(); + new = kmem_cache_zalloc(idr_layer_cache, gfp_mask); +- preempt_disable(); ++ idr_preload_lock(); + if (!new) + break; + +diff -Nur linux-4.1.39.orig/lib/Kconfig linux-4.1.39/lib/Kconfig +--- linux-4.1.39.orig/lib/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/lib/Kconfig 2017-04-18 17:56:30.645398372 +0200 +@@ -391,6 +391,7 @@ + + 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 -Nur linux-4.1.39.orig/lib/locking-selftest.c linux-4.1.39/lib/locking-selftest.c +--- linux-4.1.39.orig/lib/locking-selftest.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/lib/locking-selftest.c 2017-04-18 17:56:30.645398372 +0200 +@@ -590,6 +590,8 @@ + #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) + +@@ -605,9 +607,12 @@ + #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: + */ +@@ -640,6 +645,8 @@ + #undef E1 + #undef E2 + ++#endif ++ + /* + * Enabling irqs with an irq-safe lock held: + */ +@@ -663,6 +670,8 @@ + #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) + +@@ -678,6 +687,8 @@ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + +@@ -709,6 +720,8 @@ + #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) + +@@ -724,6 +737,8 @@ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + #undef E3 +@@ -757,6 +772,8 @@ + #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) + +@@ -772,10 +789,14 @@ + #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. + * +@@ -838,6 +859,10 @@ + #undef E2 + #undef E3 + ++#endif ++ ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * read-lock / write-lock recursion that is actually safe. + */ +@@ -876,6 +901,8 @@ + #undef E2 + #undef E3 + ++#endif ++ + /* + * read-lock / write-lock recursion that is unsafe. + */ +@@ -1858,6 +1885,7 @@ + + printk(" --------------------------------------------------------------------------\n"); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * irq-context testcases: + */ +@@ -1870,6 +1898,28 @@ + + 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 + + ww_tests(); + +diff -Nur linux-4.1.39.orig/lib/percpu_ida.c linux-4.1.39/lib/percpu_ida.c +--- linux-4.1.39.orig/lib/percpu_ida.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/lib/percpu_ida.c 2017-04-18 17:56:30.645398372 +0200 +@@ -26,6 +26,9 @@ + #include + #include + #include ++#include ++ ++static DEFINE_LOCAL_IRQ_LOCK(irq_off_lock); + + struct percpu_ida_cpu { + /* +@@ -148,13 +151,13 @@ + unsigned long flags; + int tag; + +- local_irq_save(flags); ++ local_lock_irqsave(irq_off_lock, flags); + tags = this_cpu_ptr(pool->tag_cpu); + + /* Fastpath */ + tag = alloc_local_tag(tags); + if (likely(tag >= 0)) { +- local_irq_restore(flags); ++ local_unlock_irqrestore(irq_off_lock, flags); + return tag; + } + +@@ -173,6 +176,7 @@ + + if (!tags->nr_free) + alloc_global_tags(pool, tags); ++ + if (!tags->nr_free) + steal_tags(pool, tags); + +@@ -184,7 +188,7 @@ + } + + spin_unlock(&pool->lock); +- local_irq_restore(flags); ++ local_unlock_irqrestore(irq_off_lock, flags); + + if (tag >= 0 || state == TASK_RUNNING) + break; +@@ -196,7 +200,7 @@ + + schedule(); + +- local_irq_save(flags); ++ local_lock_irqsave(irq_off_lock, flags); + tags = this_cpu_ptr(pool->tag_cpu); + } + if (state != TASK_RUNNING) +@@ -221,7 +225,7 @@ + + BUG_ON(tag >= pool->nr_tags); + +- local_irq_save(flags); ++ local_lock_irqsave(irq_off_lock, flags); + tags = this_cpu_ptr(pool->tag_cpu); + + spin_lock(&tags->lock); +@@ -253,7 +257,7 @@ + spin_unlock(&pool->lock); + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(irq_off_lock, flags); + } + EXPORT_SYMBOL_GPL(percpu_ida_free); + +@@ -345,7 +349,7 @@ + struct percpu_ida_cpu *remote; + unsigned cpu, i, err = 0; + +- local_irq_save(flags); ++ local_lock_irqsave(irq_off_lock, flags); + for_each_possible_cpu(cpu) { + remote = per_cpu_ptr(pool->tag_cpu, cpu); + spin_lock(&remote->lock); +@@ -367,7 +371,7 @@ + } + spin_unlock(&pool->lock); + out: +- local_irq_restore(flags); ++ local_unlock_irqrestore(irq_off_lock, flags); + return err; + } + EXPORT_SYMBOL_GPL(percpu_ida_for_each_free); +diff -Nur linux-4.1.39.orig/lib/radix-tree.c linux-4.1.39/lib/radix-tree.c +--- linux-4.1.39.orig/lib/radix-tree.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/lib/radix-tree.c 2017-04-18 17:56:30.645398372 +0200 +@@ -34,6 +34,7 @@ + #include + #include + #include /* in_interrupt() */ ++#include + + + /* +@@ -68,6 +69,7 @@ + struct radix_tree_node *nodes[RADIX_TREE_PRELOAD_SIZE]; + }; + static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, }; ++static DEFINE_LOCAL_IRQ_LOCK(radix_tree_preloads_lock); + + static inline void *ptr_to_indirect(void *ptr) + { +@@ -195,12 +197,13 @@ + * succeed in getting a node here (and never reach + * kmem_cache_alloc) + */ +- rtp = this_cpu_ptr(&radix_tree_preloads); ++ rtp = &get_locked_var(radix_tree_preloads_lock, radix_tree_preloads); + if (rtp->nr) { + ret = rtp->nodes[rtp->nr - 1]; + rtp->nodes[rtp->nr - 1] = NULL; + rtp->nr--; + } ++ put_locked_var(radix_tree_preloads_lock, radix_tree_preloads); + /* + * Update the allocation stack trace as this is more useful + * for debugging. +@@ -255,14 +258,14 @@ + struct radix_tree_node *node; + int ret = -ENOMEM; + +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + rtp = this_cpu_ptr(&radix_tree_preloads); + while (rtp->nr < ARRAY_SIZE(rtp->nodes)) { +- preempt_enable(); ++ local_unlock(radix_tree_preloads_lock); + node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); + if (node == NULL) + goto out; +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + rtp = this_cpu_ptr(&radix_tree_preloads); + if (rtp->nr < ARRAY_SIZE(rtp->nodes)) + rtp->nodes[rtp->nr++] = node; +@@ -301,11 +304,17 @@ + if (gfp_mask & __GFP_WAIT) + return __radix_tree_preload(gfp_mask); + /* Preloading doesn't help anything with this gfp mask, skip it */ +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + return 0; + } + EXPORT_SYMBOL(radix_tree_maybe_preload); + ++void radix_tree_preload_end(void) ++{ ++ local_unlock(radix_tree_preloads_lock); ++} ++EXPORT_SYMBOL(radix_tree_preload_end); ++ + /* + * Return the maximum key which can be store into a + * radix tree with height HEIGHT. +diff -Nur linux-4.1.39.orig/lib/scatterlist.c linux-4.1.39/lib/scatterlist.c +--- linux-4.1.39.orig/lib/scatterlist.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/lib/scatterlist.c 2017-04-18 17:56:30.645398372 +0200 +@@ -592,7 +592,7 @@ + flush_kernel_dcache_page(miter->page); + + if (miter->__flags & SG_MITER_ATOMIC) { +- WARN_ON_ONCE(preemptible()); ++ WARN_ON_ONCE(!pagefault_disabled()); + kunmap_atomic(miter->addr); + } else + kunmap(miter->page); +@@ -637,7 +637,7 @@ + if (!sg_miter_skip(&miter, skip)) + return false; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + while (sg_miter_next(&miter) && offset < buflen) { + unsigned int len; +@@ -654,7 +654,7 @@ + + sg_miter_stop(&miter); + +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return offset; + } + +diff -Nur linux-4.1.39.orig/lib/smp_processor_id.c linux-4.1.39/lib/smp_processor_id.c +--- linux-4.1.39.orig/lib/smp_processor_id.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/lib/smp_processor_id.c 2017-04-18 17:56:30.645398372 +0200 +@@ -39,8 +39,9 @@ + if (!printk_ratelimit()) + goto out_enable; + +- printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x] code: %s/%d\n", +- what1, what2, preempt_count() - 1, current->comm, current->pid); ++ printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x %08x] code: %s/%d\n", ++ what1, what2, preempt_count() - 1, __migrate_disabled(current), ++ current->comm, current->pid); + + print_symbol("caller is %s\n", (long)__builtin_return_address(0)); + dump_stack(); +diff -Nur linux-4.1.39.orig/lib/strnlen_user.c linux-4.1.39/lib/strnlen_user.c +--- linux-4.1.39.orig/lib/strnlen_user.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/lib/strnlen_user.c 2017-04-18 17:56:30.649398527 +0200 +@@ -85,7 +85,8 @@ + * @str: The string to measure. + * @count: Maximum count (including NUL character) + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Get the size of a NUL-terminated string in user space. + * +@@ -121,7 +122,8 @@ + * strlen_user: - Get the size of a user string INCLUDING final NUL. + * @str: The string to measure. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Get the size of a NUL-terminated string in user space. + * +diff -Nur linux-4.1.39.orig/Makefile linux-4.1.39/Makefile +--- linux-4.1.39.orig/Makefile 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/Makefile 2017-04-18 17:56:30.545394493 +0200 +@@ -400,7 +400,7 @@ + KBUILD_CFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ + -fno-strict-aliasing -fno-common \ + -Werror-implicit-function-declaration \ +- -Wno-format-security \ ++ -Wno-format-security -fno-PIE \ + -std=gnu89 + + KBUILD_AFLAGS_KERNEL := +diff -Nur linux-4.1.39.orig/mm/compaction.c linux-4.1.39/mm/compaction.c +--- linux-4.1.39.orig/mm/compaction.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/compaction.c 2017-04-18 17:56:30.649398527 +0200 +@@ -1423,10 +1423,12 @@ + cc->migrate_pfn & ~((1UL << cc->order) - 1); + + if (last_migrated_pfn < current_block_start) { +- cpu = get_cpu(); ++ cpu = get_cpu_light(); ++ local_lock_irq(swapvec_lock); + lru_add_drain_cpu(cpu); ++ local_unlock_irq(swapvec_lock); + drain_local_pages(zone); +- put_cpu(); ++ put_cpu_light(); + /* No more flushing until we migrate again */ + last_migrated_pfn = 0; + } +diff -Nur linux-4.1.39.orig/mm/filemap.c linux-4.1.39/mm/filemap.c +--- linux-4.1.39.orig/mm/filemap.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/filemap.c 2017-04-18 17:56:30.649398527 +0200 +@@ -167,7 +167,9 @@ + if (!workingset_node_pages(node) && + list_empty(&node->private_list)) { + node->private_data = mapping; +- list_lru_add(&workingset_shadow_nodes, &node->private_list); ++ local_lock(workingset_shadow_lock); ++ list_lru_add(&__workingset_shadow_nodes, &node->private_list); ++ local_unlock(workingset_shadow_lock); + } + } + +@@ -533,9 +535,12 @@ + * node->private_list is protected by + * mapping->tree_lock. + */ +- if (!list_empty(&node->private_list)) +- list_lru_del(&workingset_shadow_nodes, ++ if (!list_empty(&node->private_list)) { ++ local_lock(workingset_shadow_lock); ++ list_lru_del(&__workingset_shadow_nodes, + &node->private_list); ++ local_unlock(workingset_shadow_lock); ++ } + } + return 0; + } +diff -Nur linux-4.1.39.orig/mm/highmem.c linux-4.1.39/mm/highmem.c +--- linux-4.1.39.orig/mm/highmem.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/highmem.c 2017-04-18 17:56:30.649398527 +0200 +@@ -29,10 +29,11 @@ + #include + #include + +- ++#ifndef CONFIG_PREEMPT_RT_FULL + #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) + DEFINE_PER_CPU(int, __kmap_atomic_idx); + #endif ++#endif + + /* + * Virtual_count is not a pure "count". +@@ -107,8 +108,9 @@ + unsigned long totalhigh_pages __read_mostly; + EXPORT_SYMBOL(totalhigh_pages); + +- ++#ifndef CONFIG_PREEMPT_RT_FULL + EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx); ++#endif + + unsigned int nr_free_highpages (void) + { +diff -Nur linux-4.1.39.orig/mm/Kconfig linux-4.1.39/mm/Kconfig +--- linux-4.1.39.orig/mm/Kconfig 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/Kconfig 2017-04-18 17:56:30.649398527 +0200 +@@ -409,7 +409,7 @@ + + config TRANSPARENT_HUGEPAGE + bool "Transparent Hugepage Support" +- depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE ++ depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT_FULL + select COMPACTION + help + Transparent Hugepages allows the kernel to use huge pages and +diff -Nur linux-4.1.39.orig/mm/memcontrol.c linux-4.1.39/mm/memcontrol.c +--- linux-4.1.39.orig/mm/memcontrol.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/memcontrol.c 2017-04-18 17:56:30.649398527 +0200 +@@ -66,6 +66,8 @@ + #include + #include + #include ++#include ++ + #include "slab.h" + + #include +@@ -85,6 +87,7 @@ + #define do_swap_account 0 + #endif + ++static DEFINE_LOCAL_IRQ_LOCK(event_lock); + static const char * const mem_cgroup_stat_names[] = { + "cache", + "rss", +@@ -2124,14 +2127,17 @@ + */ + 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(); + } + + /* +@@ -2147,7 +2153,7 @@ + return; + /* 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; +@@ -2164,7 +2170,7 @@ + schedule_work_on(cpu, &stock->work); + } + } +- put_cpu(); ++ put_cpu_light(); + put_online_cpus(); + mutex_unlock(&percpu_charge_mutex); + } +@@ -4803,12 +4809,12 @@ + + ret = 0; + +- local_irq_disable(); ++ local_lock_irq(event_lock); + mem_cgroup_charge_statistics(to, page, nr_pages); + memcg_check_events(to, page); + mem_cgroup_charge_statistics(from, page, -nr_pages); + memcg_check_events(from, page); +- local_irq_enable(); ++ local_unlock_irq(event_lock); + out_unlock: + unlock_page(page); + out: +@@ -5551,10 +5557,10 @@ + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + } + +- local_irq_disable(); ++ local_lock_irq(event_lock); + mem_cgroup_charge_statistics(memcg, page, nr_pages); + memcg_check_events(memcg, page); +- local_irq_enable(); ++ local_unlock_irq(event_lock); + + if (do_swap_account && PageSwapCache(page)) { + swp_entry_t entry = { .val = page_private(page) }; +@@ -5610,14 +5616,14 @@ + memcg_oom_recover(memcg); + } + +- local_irq_save(flags); ++ local_lock_irqsave(event_lock, flags); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_anon); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_file); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_huge); + __this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT], pgpgout); + __this_cpu_add(memcg->stat->nr_page_events, nr_pages); + memcg_check_events(memcg, dummy_page); +- local_irq_restore(flags); ++ local_unlock_irqrestore(event_lock, flags); + + if (!mem_cgroup_is_root(memcg)) + css_put_many(&memcg->css, nr_pages); +@@ -5821,6 +5827,7 @@ + { + struct mem_cgroup *memcg; + unsigned short oldid; ++ unsigned long flags; + + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); +@@ -5843,9 +5850,11 @@ + if (!mem_cgroup_is_root(memcg)) + page_counter_uncharge(&memcg->memory, 1); + ++ local_lock_irqsave(event_lock, flags); + /* Caller disabled preemption with mapping->tree_lock */ + mem_cgroup_charge_statistics(memcg, page, -1); + memcg_check_events(memcg, page); ++ local_unlock_irqrestore(event_lock, flags); + } + + /** +diff -Nur linux-4.1.39.orig/mm/memory.c linux-4.1.39/mm/memory.c +--- linux-4.1.39.orig/mm/memory.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/memory.c 2017-04-18 17:56:30.649398527 +0200 +@@ -3753,7 +3753,7 @@ + } + + #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) +-void might_fault(void) ++void __might_fault(const char *file, int line) + { + /* + * Some code (nfs/sunrpc) uses socket ops on kernel memory while +@@ -3763,21 +3763,15 @@ + */ + if (segment_eq(get_fs(), KERNEL_DS)) + return; +- +- /* +- * it would be nicer only to annotate paths which are not under +- * pagefault_disable, however that requires a larger audit and +- * providing helpers like get_user_atomic. +- */ +- if (in_atomic()) ++ if (pagefault_disabled()) + return; +- +- __might_sleep(__FILE__, __LINE__, 0); +- ++ __might_sleep(file, line, 0); ++#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) + if (current->mm) + might_lock_read(¤t->mm->mmap_sem); ++#endif + } +-EXPORT_SYMBOL(might_fault); ++EXPORT_SYMBOL(__might_fault); + #endif + + #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) +diff -Nur linux-4.1.39.orig/mm/mmu_context.c linux-4.1.39/mm/mmu_context.c +--- linux-4.1.39.orig/mm/mmu_context.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/mmu_context.c 2017-04-18 17:56:30.649398527 +0200 +@@ -23,6 +23,7 @@ + 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); +@@ -30,6 +31,7 @@ + } + tsk->mm = mm; + switch_mm(active_mm, mm, tsk); ++ preempt_enable_rt(); + task_unlock(tsk); + #ifdef finish_arch_post_lock_switch + finish_arch_post_lock_switch(); +diff -Nur linux-4.1.39.orig/mm/page_alloc.c linux-4.1.39/mm/page_alloc.c +--- linux-4.1.39.orig/mm/page_alloc.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/page_alloc.c 2017-04-18 17:56:30.649398527 +0200 +@@ -60,6 +60,7 @@ + #include + #include + #include ++#include + #include + + #include +@@ -233,6 +234,18 @@ + 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) +@@ -701,7 +714,7 @@ + } + + /* +- * 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. + * +@@ -712,18 +725,51 @@ + * 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 nr_scanned; ++ unsigned long flags; ++ ++ spin_lock_irqsave(&zone->lock, flags); + +- spin_lock(&zone->lock); + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); + ++ while (!list_empty(list)) { ++ struct page *page = list_first_entry(list, struct page, lru); ++ int mt; /* migratetype of the to-be-freed page */ ++ ++ /* must delete as __free_one_page list manipulates */ ++ list_del(&page->lru); ++ ++ mt = get_freepage_migratetype(page); ++ if (unlikely(has_isolate_pageblock(zone))) ++ mt = get_pageblock_migratetype(page); ++ ++ /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ ++ __free_one_page(page, page_to_pfn(page), zone, 0, mt); ++ trace_mm_page_pcpu_drain(page, 0, mt); ++ to_free--; ++ } ++ WARN_ON(to_free != 0); ++ 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; ++ int batch_free = 0; ++ + while (to_free) { + struct page *page; + struct list_head *list; +@@ -739,7 +785,7 @@ + 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. */ +@@ -747,21 +793,11 @@ + batch_free = to_free; + + 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); +- if (unlikely(has_isolate_pageblock(zone))) +- mt = get_pageblock_migratetype(page); +- +- /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ +- __free_one_page(page, page_to_pfn(page), zone, 0, mt); +- trace_mm_page_pcpu_drain(page, 0, mt); ++ 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, +@@ -770,7 +806,9 @@ + int migratetype) + { + unsigned long nr_scanned; +- spin_lock(&zone->lock); ++ unsigned long flags; ++ ++ spin_lock_irqsave(&zone->lock, flags); + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); +@@ -780,7 +818,7 @@ + migratetype = get_pfnblock_migratetype(page, pfn); + } + __free_one_page(page, pfn, zone, order, migratetype); +- spin_unlock(&zone->lock); ++ spin_unlock_irqrestore(&zone->lock, flags); + } + + static int free_tail_pages_check(struct page *head_page, struct page *page) +@@ -845,11 +883,11 @@ + return; + + migratetype = get_pfnblock_migratetype(page, pfn); +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + __count_vm_events(PGFREE, 1 << order); + set_freepage_migratetype(page, migratetype); + free_one_page(page_zone(page), page, pfn, order, migratetype); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + void __init __free_pages_bootmem(struct page *page, unsigned long pfn, +@@ -1396,16 +1434,18 @@ + void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) + { + unsigned long flags; ++ LIST_HEAD(dst); + int to_drain, batch; + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + batch = READ_ONCE(pcp->batch); + to_drain = min(pcp->count, batch); + if (to_drain > 0) { +- 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 + +@@ -1421,16 +1461,21 @@ + unsigned long flags; + 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); + } + + /* +@@ -1516,8 +1561,17 @@ + else + cpumask_clear_cpu(cpu, &cpus_with_pcps); + } ++#ifndef CONFIG_PREEMPT_RT_BASE + on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages, + zone, 1); ++#else ++ for_each_cpu(cpu, &cpus_with_pcps) { ++ if (zone) ++ drain_pages_zone(cpu, zone); ++ else ++ drain_pages(cpu); ++ } ++#endif + } + + #ifdef CONFIG_HIBERNATION +@@ -1573,7 +1627,7 @@ + + migratetype = get_pfnblock_migratetype(page, pfn); + set_freepage_migratetype(page, migratetype); +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + __count_vm_event(PGFREE); + + /* +@@ -1599,12 +1653,17 @@ + pcp->count++; + if (pcp->count >= pcp->high) { + unsigned long batch = READ_ONCE(pcp->batch); +- free_pcppages_bulk(zone, batch, pcp); ++ LIST_HEAD(dst); ++ ++ isolate_pcp_pages(batch, pcp, &dst); + pcp->count -= batch; ++ local_unlock_irqrestore(pa_lock, flags); ++ free_pcppages_bulk(zone, batch, &dst); ++ return; + } + + out: +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + /* +@@ -1735,7 +1794,7 @@ + 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)) { +@@ -1767,13 +1826,15 @@ + */ + WARN_ON_ONCE(order > 1); + } +- spin_lock_irqsave(&zone->lock, flags); ++ local_spin_lock_irqsave(pa_lock, &zone->lock, flags); + 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_freepage_migratetype(page)); ++ spin_unlock(&zone->lock); + } + + __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); +@@ -1783,13 +1844,13 @@ + + __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_PAGE(bad_range(zone, page), page); + return page; + + failed: +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + return NULL; + } + +@@ -5680,6 +5741,7 @@ + void __init page_alloc_init(void) + { + hotcpu_notifier(page_alloc_cpu_notify, 0); ++ local_irq_lock_init(pa_lock); + } + + /* +@@ -6575,7 +6637,7 @@ + struct per_cpu_pageset *pset; + + /* avoid races with drain_pages() */ +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + if (zone->pageset != &boot_pageset) { + for_each_online_cpu(cpu) { + pset = per_cpu_ptr(zone->pageset, cpu); +@@ -6584,7 +6646,7 @@ + free_percpu(zone->pageset); + zone->pageset = &boot_pageset; + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + #ifdef CONFIG_MEMORY_HOTREMOVE +diff -Nur linux-4.1.39.orig/mm/percpu.c linux-4.1.39/mm/percpu.c +--- linux-4.1.39.orig/mm/percpu.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/percpu.c 2017-04-18 17:56:30.649398527 +0200 +@@ -1282,18 +1282,7 @@ + } + EXPORT_SYMBOL_GPL(free_percpu); + +-/** +- * is_kernel_percpu_address - test whether address is from static percpu area +- * @addr: address to test +- * +- * Test whether @addr belongs to in-kernel static percpu area. Module +- * static percpu areas are not considered. For those, use +- * is_module_percpu_address(). +- * +- * RETURNS: +- * %true if @addr is from in-kernel static percpu area, %false otherwise. +- */ +-bool is_kernel_percpu_address(unsigned long addr) ++bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr) + { + #ifdef CONFIG_SMP + const size_t static_size = __per_cpu_end - __per_cpu_start; +@@ -1302,16 +1291,36 @@ + + for_each_possible_cpu(cpu) { + void *start = per_cpu_ptr(base, cpu); ++ void *va = (void *)addr; + +- if ((void *)addr >= start && (void *)addr < start + static_size) ++ if (va >= start && va < start + static_size) { ++ if (can_addr) ++ *can_addr = (unsigned long) (va - start); + return true; +- } ++ } ++ } + #endif + /* on UP, can't distinguish from other static vars, always false */ + return false; + } + + /** ++ * is_kernel_percpu_address - test whether address is from static percpu area ++ * @addr: address to test ++ * ++ * Test whether @addr belongs to in-kernel static percpu area. Module ++ * static percpu areas are not considered. For those, use ++ * is_module_percpu_address(). ++ * ++ * RETURNS: ++ * %true if @addr is from in-kernel static percpu area, %false otherwise. ++ */ ++bool is_kernel_percpu_address(unsigned long addr) ++{ ++ return __is_kernel_percpu_address(addr, NULL); ++} ++ ++/** + * per_cpu_ptr_to_phys - convert translated percpu address to physical address + * @addr: the address to be converted to physical address + * +diff -Nur linux-4.1.39.orig/mm/slab.h linux-4.1.39/mm/slab.h +--- linux-4.1.39.orig/mm/slab.h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/slab.h 2017-04-18 17:56:30.649398527 +0200 +@@ -330,7 +330,11 @@ + * The slab lists for all objects. + */ + struct kmem_cache_node { ++#ifdef CONFIG_SLUB ++ raw_spinlock_t list_lock; ++#else + spinlock_t list_lock; ++#endif + + #ifdef CONFIG_SLAB + struct list_head slabs_partial; /* partial list first, better asm code */ +diff -Nur linux-4.1.39.orig/mm/slub.c linux-4.1.39/mm/slub.c +--- linux-4.1.39.orig/mm/slub.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/slub.c 2017-04-18 17:56:30.653398681 +0200 +@@ -1069,7 +1069,7 @@ + { + struct kmem_cache_node *n = get_node(s, page_to_nid(page)); + +- spin_lock_irqsave(&n->list_lock, *flags); ++ raw_spin_lock_irqsave(&n->list_lock, *flags); + slab_lock(page); + + if (!check_slab(s, page)) +@@ -1116,7 +1116,7 @@ + + fail: + slab_unlock(page); +- spin_unlock_irqrestore(&n->list_lock, *flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, *flags); + slab_fix(s, "Object at 0x%p not freed", object); + return NULL; + } +@@ -1242,6 +1242,12 @@ + + #endif /* CONFIG_SLUB_DEBUG */ + ++struct slub_free_list { ++ raw_spinlock_t lock; ++ struct list_head list; ++}; ++static DEFINE_PER_CPU(struct slub_free_list, slub_free_list); ++ + /* + * Hooks for other subsystems that check memory allocations. In a typical + * production configuration these hooks all should produce no code at all. +@@ -1306,6 +1312,17 @@ + kasan_slab_free(s, x); + } + ++static void setup_object(struct kmem_cache *s, struct page *page, ++ void *object) ++{ ++ setup_object_debug(s, page, object); ++ if (unlikely(s->ctor)) { ++ kasan_unpoison_object_data(s, object); ++ s->ctor(object); ++ kasan_poison_object_data(s, object); ++ } ++} ++ + /* + * Slab allocation and freeing + */ +@@ -1336,10 +1353,17 @@ + struct page *page; + struct kmem_cache_order_objects oo = s->oo; + gfp_t alloc_gfp; ++ void *start, *p; ++ int idx, order; ++ bool enableirqs; + + flags &= gfp_allowed_mask; + +- if (flags & __GFP_WAIT) ++ enableirqs = (flags & __GFP_WAIT) != 0; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ enableirqs |= system_state == SYSTEM_RUNNING; ++#endif ++ if (enableirqs) + local_irq_enable(); + + flags |= s->allocflags; +@@ -1359,13 +1383,13 @@ + * Try a lower order alloc if possible + */ + page = alloc_slab_page(s, alloc_gfp, node, oo); +- +- if (page) +- stat(s, ORDER_FALLBACK); ++ if (unlikely(!page)) ++ goto out; ++ stat(s, ORDER_FALLBACK); + } + +- if (kmemcheck_enabled && page +- && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) { ++ if (kmemcheck_enabled && ++ !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) { + int pages = 1 << oo_order(oo); + + kmemcheck_alloc_shadow(page, oo_order(oo), alloc_gfp, node); +@@ -1380,51 +1404,9 @@ + kmemcheck_mark_unallocated_pages(page, pages); + } + +- if (flags & __GFP_WAIT) +- local_irq_disable(); +- if (!page) +- return NULL; +- + 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)) { +- kasan_unpoison_object_data(s, object); +- s->ctor(object); +- kasan_poison_object_data(s, object); +- } +-} +- +-static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) +-{ +- struct page *page; +- void *start; +- void *p; +- int order; +- int idx; +- +- if (unlikely(flags & GFP_SLAB_BUG_MASK)) { +- pr_emerg("gfp: %u\n", flags & GFP_SLAB_BUG_MASK); +- BUG(); +- } +- +- page = allocate_slab(s, +- flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node); +- if (!page) +- goto out; + + order = compound_order(page); +- inc_slabs_node(s, page_to_nid(page), page->objects); + page->slab_cache = s; + __SetPageSlab(page); + if (page_is_pfmemalloc(page)) +@@ -1448,10 +1430,34 @@ + page->freelist = start; + page->inuse = page->objects; + page->frozen = 1; ++ + out: ++ if (enableirqs) ++ 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); +@@ -1483,6 +1489,16 @@ + memcg_uncharge_slab(s, order); + } + ++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_slab(page->slab_cache, page); ++ } ++} ++ + #define need_reserve_slab_rcu \ + (sizeof(((struct page *)NULL)->lru) < sizeof(struct rcu_head)) + +@@ -1517,6 +1533,12 @@ + } + + call_rcu(head, rcu_free_slab); ++ } else if (irqs_disabled()) { ++ struct slub_free_list *f = this_cpu_ptr(&slub_free_list); ++ ++ raw_spin_lock(&f->lock); ++ list_add(&page->lru, &f->list); ++ raw_spin_unlock(&f->lock); + } else + __free_slab(s, page); + } +@@ -1630,7 +1652,7 @@ + if (!n || !n->nr_partial) + return NULL; + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + list_for_each_entry_safe(page, page2, &n->partial, lru) { + void *t; + +@@ -1655,7 +1677,7 @@ + break; + + } +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + return object; + } + +@@ -1901,7 +1923,7 @@ + * that acquire_slab() will see a slab page that + * is frozen + */ +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + } else { + m = M_FULL; +@@ -1912,7 +1934,7 @@ + * slabs from diagnostic functions will not see + * any frozen slabs. + */ +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + } + +@@ -1947,7 +1969,7 @@ + goto redo; + + if (lock) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + if (m == M_FREE) { + stat(s, DEACTIVATE_EMPTY); +@@ -1979,10 +2001,10 @@ + n2 = get_node(s, page_to_nid(page)); + if (n != n2) { + if (n) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + n = n2; +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + + do { +@@ -2011,7 +2033,7 @@ + } + + if (n) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + while (discard_page) { + page = discard_page; +@@ -2050,14 +2072,21 @@ + pobjects = oldpage->pobjects; + pages = oldpage->pages; + if (drain && pobjects > s->cpu_partial) { ++ struct slub_free_list *f; + unsigned long flags; ++ LIST_HEAD(tofree); + /* + * partial array is full. Move the existing + * set to the per node partial list. + */ + local_irq_save(flags); + unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); ++ f = this_cpu_ptr(&slub_free_list); ++ raw_spin_lock(&f->lock); ++ list_splice_init(&f->list, &tofree); ++ raw_spin_unlock(&f->lock); + local_irq_restore(flags); ++ free_delayed(&tofree); + oldpage = NULL; + pobjects = 0; + pages = 0; +@@ -2129,7 +2158,22 @@ + + static void flush_all(struct kmem_cache *s) + { ++ LIST_HEAD(tofree); ++ int cpu; ++ + on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC); ++ for_each_online_cpu(cpu) { ++ struct slub_free_list *f; ++ ++ if (!has_cpu_slab(cpu, s)) ++ continue; ++ ++ f = &per_cpu(slub_free_list, cpu); ++ raw_spin_lock_irq(&f->lock); ++ list_splice_init(&f->list, &tofree); ++ raw_spin_unlock_irq(&f->lock); ++ free_delayed(&tofree); ++ } + } + + /* +@@ -2165,10 +2209,10 @@ + unsigned long x = 0; + struct page *page; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, lru) + x += get_count(page); +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return x; + } + #endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */ +@@ -2305,9 +2349,11 @@ + static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + unsigned long addr, struct kmem_cache_cpu *c) + { ++ struct slub_free_list *f; + void *freelist; + struct page *page; + unsigned long flags; ++ LIST_HEAD(tofree); + + local_irq_save(flags); + #ifdef CONFIG_PREEMPT +@@ -2375,7 +2421,13 @@ + VM_BUG_ON(!c->page->frozen); + c->freelist = get_freepointer(s, freelist); + c->tid = next_tid(c->tid); ++out: ++ f = this_cpu_ptr(&slub_free_list); ++ raw_spin_lock(&f->lock); ++ list_splice_init(&f->list, &tofree); ++ raw_spin_unlock(&f->lock); + local_irq_restore(flags); ++ free_delayed(&tofree); + return freelist; + + new_slab: +@@ -2392,8 +2444,7 @@ + + if (unlikely(!freelist)) { + slab_out_of_memory(s, gfpflags, node); +- local_irq_restore(flags); +- return NULL; ++ goto out; + } + + page = c->page; +@@ -2408,8 +2459,7 @@ + deactivate_slab(s, page, get_freepointer(s, freelist)); + c->page = NULL; + c->freelist = NULL; +- local_irq_restore(flags); +- return freelist; ++ goto out; + } + + /* +@@ -2593,7 +2643,7 @@ + + do { + if (unlikely(n)) { +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + n = NULL; + } + prior = page->freelist; +@@ -2625,7 +2675,7 @@ + * Otherwise the list_lock will synchronize with + * other processors updating the list of slabs. + */ +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + } + } +@@ -2667,7 +2717,7 @@ + add_partial(n, page, DEACTIVATE_TO_TAIL); + stat(s, FREE_ADD_PARTIAL); + } +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return; + + slab_empty: +@@ -2682,7 +2732,7 @@ + remove_full(s, n, page); + } + +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + stat(s, FREE_SLAB); + discard_slab(s, page); + } +@@ -2881,7 +2931,7 @@ + init_kmem_cache_node(struct kmem_cache_node *n) + { + n->nr_partial = 0; +- spin_lock_init(&n->list_lock); ++ raw_spin_lock_init(&n->list_lock); + INIT_LIST_HEAD(&n->partial); + #ifdef CONFIG_SLUB_DEBUG + atomic_long_set(&n->nr_slabs, 0); +@@ -3463,7 +3513,7 @@ + for (i = 0; i < SHRINK_PROMOTE_MAX; i++) + INIT_LIST_HEAD(promote + i); + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + /* + * Build lists of slabs to discard or promote. +@@ -3494,7 +3544,7 @@ + for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--) + list_splice(promote + i, &n->partial); + +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + + /* Release empty slabs */ + list_for_each_entry_safe(page, t, &discard, lru) +@@ -3670,6 +3720,12 @@ + { + static __initdata struct kmem_cache boot_kmem_cache, + boot_kmem_cache_node; ++ int cpu; ++ ++ for_each_possible_cpu(cpu) { ++ raw_spin_lock_init(&per_cpu(slub_free_list, cpu).lock); ++ INIT_LIST_HEAD(&per_cpu(slub_free_list, cpu).list); ++ } + + if (debug_guardpage_minorder()) + slub_max_order = 0; +@@ -3912,7 +3968,7 @@ + struct page *page; + unsigned long flags; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + list_for_each_entry(page, &n->partial, lru) { + validate_slab_slab(s, page, map); +@@ -3934,7 +3990,7 @@ + s->name, count, atomic_long_read(&n->nr_slabs)); + + out: +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return count; + } + +@@ -4122,12 +4178,12 @@ + if (!atomic_long_read(&n->nr_slabs)) + continue; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, lru) + process_slab(&t, s, page, alloc, map); + list_for_each_entry(page, &n->full, lru) + process_slab(&t, s, page, alloc, map); +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + } + + for (i = 0; i < t.count; i++) { +diff -Nur linux-4.1.39.orig/mm/swap.c linux-4.1.39/mm/swap.c +--- linux-4.1.39.orig/mm/swap.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/swap.c 2017-04-18 17:56:30.653398681 +0200 +@@ -32,6 +32,7 @@ + #include + #include + #include ++#include + + #include "internal.h" + +@@ -45,6 +46,9 @@ + static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); + static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs); + ++static DEFINE_LOCAL_IRQ_LOCK(rotate_lock); ++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. +@@ -481,11 +485,11 @@ + unsigned long flags; + + page_cache_get(page); +- local_irq_save(flags); ++ local_lock_irqsave(rotate_lock, flags); + pvec = this_cpu_ptr(&lru_rotate_pvecs); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_move_tail(pvec); +- local_irq_restore(flags); ++ local_unlock_irqrestore(rotate_lock, flags); + } + } + +@@ -536,12 +540,13 @@ + 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) || PageCompound(page)) + pagevec_lru_move_fn(pvec, __activate_page, NULL); +- put_cpu_var(activate_page_pvecs); ++ put_locked_var(swapvec_lock, activate_page_pvecs); + } + } + +@@ -567,7 +572,7 @@ + + static void __lru_cache_activate_page(struct page *page) + { +- struct pagevec *pvec = &get_cpu_var(lru_add_pvec); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); + int i; + + /* +@@ -589,7 +594,7 @@ + } + } + +- put_cpu_var(lru_add_pvec); ++ put_locked_var(swapvec_lock, lru_add_pvec); + } + + /* +@@ -628,12 +633,12 @@ + + static void __lru_cache_add(struct page *page) + { +- struct pagevec *pvec = &get_cpu_var(lru_add_pvec); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); + + page_cache_get(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) + __pagevec_lru_add(pvec); +- put_cpu_var(lru_add_pvec); ++ put_locked_var(swapvec_lock, lru_add_pvec); + } + + /** +@@ -813,9 +818,15 @@ + unsigned long flags; + + /* No harm done if a racing interrupt already did this */ +- local_irq_save(flags); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ local_lock_irqsave_on(rotate_lock, flags, cpu); ++ pagevec_move_tail(pvec); ++ local_unlock_irqrestore_on(rotate_lock, flags, cpu); ++#else ++ local_lock_irqsave(rotate_lock, flags); + pagevec_move_tail(pvec); +- local_irq_restore(flags); ++ local_unlock_irqrestore(rotate_lock, flags); ++#endif + } + + pvec = &per_cpu(lru_deactivate_file_pvecs, cpu); +@@ -843,26 +854,47 @@ + return; + + if (likely(get_page_unless_zero(page))) { +- struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ lru_deactivate_file_pvecs); + + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); +- put_cpu_var(lru_deactivate_file_pvecs); ++ put_locked_var(swapvec_lock, lru_deactivate_file_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); + } + ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work) ++{ ++ local_lock_on(swapvec_lock, cpu); ++ lru_add_drain_cpu(cpu); ++ local_unlock_on(swapvec_lock, cpu); ++} ++ ++#else ++ + static void lru_add_drain_per_cpu(struct work_struct *dummy) + { + lru_add_drain(); + } + + static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); ++static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work) ++{ ++ struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); ++ ++ INIT_WORK(work, lru_add_drain_per_cpu); ++ schedule_work_on(cpu, work); ++ cpumask_set_cpu(cpu, has_work); ++} ++#endif + + void lru_add_drain_all(void) + { +@@ -875,20 +907,17 @@ + cpumask_clear(&has_work); + + for_each_online_cpu(cpu) { +- struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); +- + if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || + pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) || +- need_activate_page_drain(cpu)) { +- INIT_WORK(work, lru_add_drain_per_cpu); +- schedule_work_on(cpu, work); +- cpumask_set_cpu(cpu, &has_work); +- } ++ need_activate_page_drain(cpu)) ++ remote_lru_add_drain(cpu, &has_work); + } + ++#ifndef CONFIG_PREEMPT_RT_BASE + for_each_cpu(cpu, &has_work) + flush_work(&per_cpu(lru_add_drain_work, cpu)); ++#endif + + put_online_cpus(); + mutex_unlock(&lock); +diff -Nur linux-4.1.39.orig/mm/truncate.c linux-4.1.39/mm/truncate.c +--- linux-4.1.39.orig/mm/truncate.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/truncate.c 2017-04-18 17:56:30.653398681 +0200 +@@ -56,8 +56,11 @@ + * protected by mapping->tree_lock. + */ + if (!workingset_node_shadows(node) && +- !list_empty(&node->private_list)) +- list_lru_del(&workingset_shadow_nodes, &node->private_list); ++ !list_empty(&node->private_list)) { ++ local_lock(workingset_shadow_lock); ++ list_lru_del(&__workingset_shadow_nodes, &node->private_list); ++ local_unlock(workingset_shadow_lock); ++ } + __radix_tree_delete_node(&mapping->page_tree, node); + unlock: + spin_unlock_irq(&mapping->tree_lock); +diff -Nur linux-4.1.39.orig/mm/vmalloc.c linux-4.1.39/mm/vmalloc.c +--- linux-4.1.39.orig/mm/vmalloc.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/vmalloc.c 2017-04-18 17:56:30.653398681 +0200 +@@ -819,7 +819,7 @@ + struct vmap_block *vb; + struct vmap_area *va; + unsigned long vb_idx; +- int node, err; ++ int node, err, cpu; + void *vaddr; + + node = numa_node_id(); +@@ -862,11 +862,12 @@ + BUG_ON(err); + radix_tree_preload_end(); + +- vbq = &get_cpu_var(vmap_block_queue); ++ cpu = get_cpu_light(); ++ vbq = this_cpu_ptr(&vmap_block_queue); + spin_lock(&vbq->lock); + list_add_tail_rcu(&vb->free_list, &vbq->free); + spin_unlock(&vbq->lock); +- put_cpu_var(vmap_block_queue); ++ put_cpu_light(); + + return vaddr; + } +@@ -935,6 +936,7 @@ + struct vmap_block *vb; + void *vaddr = NULL; + unsigned int order; ++ int cpu; + + BUG_ON(size & ~PAGE_MASK); + BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); +@@ -949,7 +951,8 @@ + order = get_order(size); + + rcu_read_lock(); +- vbq = &get_cpu_var(vmap_block_queue); ++ cpu = get_cpu_light(); ++ vbq = this_cpu_ptr(&vmap_block_queue); + list_for_each_entry_rcu(vb, &vbq->free, free_list) { + unsigned long pages_off; + +@@ -972,7 +975,7 @@ + break; + } + +- put_cpu_var(vmap_block_queue); ++ put_cpu_light(); + rcu_read_unlock(); + + /* Allocate new block if nothing was found */ +diff -Nur linux-4.1.39.orig/mm/vmstat.c linux-4.1.39/mm/vmstat.c +--- linux-4.1.39.orig/mm/vmstat.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/vmstat.c 2017-04-18 17:56:30.653398681 +0200 +@@ -226,6 +226,7 @@ + long x; + long t; + ++ preempt_disable_rt(); + x = delta + __this_cpu_read(*p); + + t = __this_cpu_read(pcp->stat_threshold); +@@ -235,6 +236,7 @@ + x = 0; + } + __this_cpu_write(*p, x); ++ preempt_enable_rt(); + } + EXPORT_SYMBOL(__mod_zone_page_state); + +@@ -267,6 +269,7 @@ + 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)) { +@@ -275,6 +278,7 @@ + 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) +@@ -289,6 +293,7 @@ + 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)) { +@@ -297,6 +302,7 @@ + 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 -Nur linux-4.1.39.orig/mm/workingset.c linux-4.1.39/mm/workingset.c +--- linux-4.1.39.orig/mm/workingset.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/workingset.c 2017-04-18 17:56:30.653398681 +0200 +@@ -264,7 +264,8 @@ + * point where they would still be useful. + */ + +-struct list_lru workingset_shadow_nodes; ++struct list_lru __workingset_shadow_nodes; ++DEFINE_LOCAL_IRQ_LOCK(workingset_shadow_lock); + + static unsigned long count_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +@@ -274,9 +275,9 @@ + unsigned long pages; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ +- local_irq_disable(); +- shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc); +- local_irq_enable(); ++ local_lock_irq(workingset_shadow_lock); ++ shadow_nodes = list_lru_shrink_count(&__workingset_shadow_nodes, sc); ++ local_unlock_irq(workingset_shadow_lock); + + pages = node_present_pages(sc->nid); + /* +@@ -363,9 +364,9 @@ + spin_unlock(&mapping->tree_lock); + ret = LRU_REMOVED_RETRY; + out: +- local_irq_enable(); ++ local_unlock_irq(workingset_shadow_lock); + cond_resched(); +- local_irq_disable(); ++ local_lock_irq(workingset_shadow_lock); + spin_lock(lru_lock); + return ret; + } +@@ -376,10 +377,10 @@ + unsigned long ret; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ +- local_irq_disable(); +- ret = list_lru_shrink_walk(&workingset_shadow_nodes, sc, ++ local_lock_irq(workingset_shadow_lock); ++ ret = list_lru_shrink_walk(&__workingset_shadow_nodes, sc, + shadow_lru_isolate, NULL); +- local_irq_enable(); ++ local_unlock_irq(workingset_shadow_lock); + return ret; + } + +@@ -400,7 +401,7 @@ + { + int ret; + +- ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key); ++ ret = list_lru_init_key(&__workingset_shadow_nodes, &shadow_nodes_key); + if (ret) + goto err; + ret = register_shrinker(&workingset_shadow_shrinker); +@@ -408,7 +409,7 @@ + goto err_list_lru; + return 0; + err_list_lru: +- list_lru_destroy(&workingset_shadow_nodes); ++ list_lru_destroy(&__workingset_shadow_nodes); + err: + return ret; + } +diff -Nur linux-4.1.39.orig/mm/zsmalloc.c linux-4.1.39/mm/zsmalloc.c +--- linux-4.1.39.orig/mm/zsmalloc.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/mm/zsmalloc.c 2017-04-18 17:56:30.653398681 +0200 +@@ -68,6 +68,7 @@ + #include + #include + #include ++#include + + /* + * This must be power of 2 and greater than of equal to sizeof(link_free). +@@ -398,6 +399,7 @@ + + /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ + static DEFINE_PER_CPU(struct mapping_area, zs_map_area); ++static DEFINE_LOCAL_IRQ_LOCK(zs_map_area_lock); + + static int is_first_page(struct page *page) + { +@@ -1289,7 +1291,7 @@ + class = pool->size_class[class_idx]; + off = obj_idx_to_offset(page, obj_idx, class->size); + +- area = &get_cpu_var(zs_map_area); ++ area = &get_locked_var(zs_map_area_lock, zs_map_area); + area->vm_mm = mm; + if (off + class->size <= PAGE_SIZE) { + /* this object is contained entirely within a page */ +@@ -1342,7 +1344,7 @@ + + __zs_unmap_object(area, pages, off, class->size); + } +- put_cpu_var(zs_map_area); ++ put_locked_var(zs_map_area_lock, zs_map_area); + unpin_tag(handle); + } + EXPORT_SYMBOL_GPL(zs_unmap_object); +diff -Nur linux-4.1.39.orig/net/core/dev.c linux-4.1.39/net/core/dev.c +--- linux-4.1.39.orig/net/core/dev.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/net/core/dev.c 2017-04-18 17:56:30.653398681 +0200 +@@ -184,6 +184,7 @@ + static DEFINE_HASHTABLE(napi_hash, 8); + + static seqcount_t devnet_rename_seq; ++static DEFINE_MUTEX(devnet_rename_mutex); + + static inline void dev_base_seq_inc(struct net *net) + { +@@ -205,14 +206,14 @@ + 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 + } + +@@ -852,7 +853,8 @@ + strcpy(name, dev->name); + rcu_read_unlock(); + if (read_seqcount_retry(&devnet_rename_seq, seq)) { +- cond_resched(); ++ mutex_lock(&devnet_rename_mutex); ++ mutex_unlock(&devnet_rename_mutex); + goto retry; + } + +@@ -1121,20 +1123,17 @@ + if (dev->flags & IFF_UP) + return -EBUSY; + +- write_seqcount_begin(&devnet_rename_seq); ++ mutex_lock(&devnet_rename_mutex); ++ __raw_write_seqcount_begin(&devnet_rename_seq); + +- if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { +- write_seqcount_end(&devnet_rename_seq); +- return 0; +- } ++ if (strncmp(newname, dev->name, IFNAMSIZ) == 0) ++ goto outunlock; + + memcpy(oldname, dev->name, IFNAMSIZ); + + err = dev_get_valid_name(net, dev, newname); +- if (err < 0) { +- write_seqcount_end(&devnet_rename_seq); +- return err; +- } ++ if (err < 0) ++ goto outunlock; + + if (oldname[0] && !strchr(oldname, '%')) + netdev_info(dev, "renamed from %s\n", oldname); +@@ -1147,11 +1146,12 @@ + if (ret) { + memcpy(dev->name, oldname, IFNAMSIZ); + dev->name_assign_type = old_assign_type; +- write_seqcount_end(&devnet_rename_seq); +- return ret; ++ err = ret; ++ goto outunlock; + } + +- write_seqcount_end(&devnet_rename_seq); ++ __raw_write_seqcount_end(&devnet_rename_seq); ++ mutex_unlock(&devnet_rename_mutex); + + netdev_adjacent_rename_links(dev, oldname); + +@@ -1172,7 +1172,8 @@ + /* err >= 0 after dev_alloc_name() or stores the first errno */ + if (err >= 0) { + err = ret; +- write_seqcount_begin(&devnet_rename_seq); ++ mutex_lock(&devnet_rename_mutex); ++ __raw_write_seqcount_begin(&devnet_rename_seq); + memcpy(dev->name, oldname, IFNAMSIZ); + memcpy(oldname, newname, IFNAMSIZ); + dev->name_assign_type = old_assign_type; +@@ -1185,6 +1186,11 @@ + } + + return err; ++ ++outunlock: ++ __raw_write_seqcount_end(&devnet_rename_seq); ++ mutex_unlock(&devnet_rename_mutex); ++ return err; + } + + /** +@@ -2214,6 +2220,7 @@ + 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) +@@ -2295,6 +2302,7 @@ + __this_cpu_write(softnet_data.completion_queue, skb); + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__dev_kfree_skb_irq); + +@@ -2820,7 +2828,11 @@ + * This permits __QDISC___STATE_RUNNING owner to get the lock more + * often and dequeue packets faster. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ contended = true; ++#else + contended = qdisc_is_running(q); ++#endif + if (unlikely(contended)) + spin_lock(&q->busylock); + +@@ -2880,9 +2892,44 @@ + #define skb_update_prio(skb) + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++static inline int xmit_rec_read(void) ++{ ++ return current->xmit_recursion; ++} ++ ++static inline void xmit_rec_inc(void) ++{ ++ current->xmit_recursion++; ++} ++ ++static inline void xmit_rec_dec(void) ++{ ++ current->xmit_recursion--; ++} ++ ++#else ++ + DEFINE_PER_CPU(int, xmit_recursion); + EXPORT_SYMBOL(xmit_recursion); + ++static inline int xmit_rec_read(void) ++{ ++ return __this_cpu_read(xmit_recursion); ++} ++ ++static inline void xmit_rec_inc(void) ++{ ++ __this_cpu_inc(xmit_recursion); ++} ++ ++static inline int xmit_rec_dec(void) ++{ ++ __this_cpu_dec(xmit_recursion); ++} ++#endif ++ + #define RECURSION_LIMIT 10 + + /** +@@ -2984,7 +3031,7 @@ + + if (txq->xmit_lock_owner != cpu) { + +- if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT) ++ if (xmit_rec_read() > RECURSION_LIMIT) + goto recursion_alert; + + skb = validate_xmit_skb(skb, dev); +@@ -2994,9 +3041,9 @@ + HARD_TX_LOCK(dev, txq, cpu); + + if (!netif_xmit_stopped(txq)) { +- __this_cpu_inc(xmit_recursion); ++ xmit_rec_inc(); + skb = dev_hard_start_xmit(skb, dev, txq, &rc); +- __this_cpu_dec(xmit_recursion); ++ xmit_rec_dec(); + if (dev_xmit_complete(rc)) { + HARD_TX_UNLOCK(dev, txq); + goto out; +@@ -3370,6 +3417,7 @@ + rps_unlock(sd); + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + + atomic_long_inc(&skb->dev->rx_dropped); + kfree_skb(skb); +@@ -3388,7 +3436,7 @@ + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu; + +- preempt_disable(); ++ migrate_disable(); + rcu_read_lock(); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); +@@ -3398,13 +3446,13 @@ + 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; + } +@@ -3438,16 +3486,44 @@ + + trace_netif_rx_ni_entry(skb); + +- preempt_disable(); ++ local_bh_disable(); + err = netif_rx_internal(skb); +- if (local_softirq_pending()) +- do_softirq(); +- preempt_enable(); ++ local_bh_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 = this_cpu_ptr(&softnet_data); +@@ -3489,7 +3565,7 @@ + head = head->next_sched; + + root_lock = qdisc_lock(q); +- if (spin_trylock(root_lock)) { ++ if (take_root_lock(root_lock)) { + smp_mb__before_atomic(); + clear_bit(__QDISC_STATE_SCHED, + &q->state); +@@ -3886,7 +3962,7 @@ + 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); + } + } +@@ -3895,10 +3971,13 @@ + 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) +@@ -4350,6 +4429,7 @@ + sd->rps_ipi_list = NULL; + + local_irq_enable(); ++ preempt_check_resched_rt(); + + /* Send pending IPI's to kick RPS processing on remote cpus. */ + while (remsd) { +@@ -4363,6 +4443,7 @@ + } else + #endif + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) +@@ -4444,9 +4525,11 @@ + local_irq_save(flags); + ____napi_schedule(this_cpu_ptr(&softnet_data), n); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__napi_schedule); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * __napi_schedule_irqoff - schedule for receive + * @n: entry to schedule +@@ -4458,6 +4541,7 @@ + ____napi_schedule(this_cpu_ptr(&softnet_data), n); + } + EXPORT_SYMBOL(__napi_schedule_irqoff); ++#endif + + void __napi_complete(struct napi_struct *n) + { +@@ -4682,13 +4766,21 @@ + struct softnet_data *sd = this_cpu_ptr(&softnet_data); + unsigned long time_limit = jiffies + 2; + int budget = netdev_budget; ++ struct sk_buff_head tofree_q; ++ struct sk_buff *skb; + LIST_HEAD(list); + LIST_HEAD(repoll); + ++ __skb_queue_head_init(&tofree_q); ++ + local_irq_disable(); ++ skb_queue_splice_init(&sd->tofree_queue, &tofree_q); + list_splice_init(&sd->poll_list, &list); + local_irq_enable(); + ++ while ((skb = __skb_dequeue(&tofree_q))) ++ kfree_skb(skb); ++ + for (;;) { + struct napi_struct *n; + +@@ -4718,7 +4810,7 @@ + list_splice_tail(&repoll, &list); + list_splice(&list, &sd->poll_list); + if (!list_empty(&sd->poll_list)) +- __raise_softirq_irqoff(NET_RX_SOFTIRQ); ++ __raise_softirq_irqoff_ksoft(NET_RX_SOFTIRQ); + + net_rps_action_and_irq_enable(sd); + } +@@ -6932,7 +7024,7 @@ + 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(); +@@ -7173,16 +7265,20 @@ + + 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))) { + netif_rx_ni(skb); + input_queue_head_incr(oldsd); + } +- while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { ++ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { + netif_rx_ni(skb); + input_queue_head_incr(oldsd); + } ++ while ((skb = __skb_dequeue(&oldsd->tofree_queue))) { ++ kfree_skb(skb); ++ } + + return NOTIFY_OK; + } +@@ -7484,8 +7580,9 @@ + for_each_possible_cpu(i) { + struct softnet_data *sd = &per_cpu(softnet_data, i); + +- 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); + INIT_LIST_HEAD(&sd->poll_list); + sd->output_queue_tailp = &sd->output_queue; + #ifdef CONFIG_RPS +diff -Nur linux-4.1.39.orig/net/core/skbuff.c linux-4.1.39/net/core/skbuff.c +--- linux-4.1.39.orig/net/core/skbuff.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/net/core/skbuff.c 2017-04-18 17:56:30.657398836 +0200 +@@ -63,6 +63,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -358,6 +359,8 @@ + }; + static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); + static DEFINE_PER_CPU(struct netdev_alloc_cache, napi_alloc_cache); ++static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock); ++static DEFINE_LOCAL_IRQ_LOCK(napi_alloc_cache_lock); + + static struct page *__page_frag_refill(struct netdev_alloc_cache *nc, + gfp_t gfp_mask) +@@ -435,9 +438,9 @@ + unsigned long flags; + void *data; + +- local_irq_save(flags); ++ local_lock_irqsave(netdev_alloc_lock, flags); + data = __alloc_page_frag(&netdev_alloc_cache, fragsz, gfp_mask); +- local_irq_restore(flags); ++ local_unlock_irqrestore(netdev_alloc_lock, flags); + return data; + } + +@@ -456,7 +459,12 @@ + + static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) + { +- return __alloc_page_frag(&napi_alloc_cache, fragsz, gfp_mask); ++ void *data; ++ ++ local_lock(napi_alloc_cache_lock); ++ data = __alloc_page_frag(&napi_alloc_cache, fragsz, gfp_mask); ++ local_unlock(napi_alloc_cache_lock); ++ return data; + } + + void *napi_alloc_frag(unsigned int fragsz) +diff -Nur linux-4.1.39.orig/net/core/sock.c linux-4.1.39/net/core/sock.c +--- linux-4.1.39.orig/net/core/sock.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/net/core/sock.c 2017-04-18 17:56:30.657398836 +0200 +@@ -2369,12 +2369,11 @@ + 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 -Nur linux-4.1.39.orig/net/ipv4/icmp.c linux-4.1.39/net/ipv4/icmp.c +--- linux-4.1.39.orig/net/ipv4/icmp.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/net/ipv4/icmp.c 2017-04-18 17:56:30.657398836 +0200 +@@ -69,6 +69,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -77,6 +78,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -203,6 +205,8 @@ + * + * On SMP we have one ICMP socket per-cpu. + */ ++static DEFINE_LOCAL_IRQ_LOCK(icmp_sk_lock); ++ + static struct sock *icmp_sk(struct net *net) + { + return *this_cpu_ptr(net->ipv4.icmp_sk); +@@ -214,12 +218,14 @@ + + local_bh_disable(); + ++ local_lock(icmp_sk_lock); + sk = icmp_sk(net); + + if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { + /* This can happen if the output path signals a + * dst_link_failure() for an outgoing ICMP packet. + */ ++ local_unlock(icmp_sk_lock); + local_bh_enable(); + return NULL; + } +@@ -229,6 +235,7 @@ + static inline void icmp_xmit_unlock(struct sock *sk) + { + spin_unlock_bh(&sk->sk_lock.slock); ++ local_unlock(icmp_sk_lock); + } + + int sysctl_icmp_msgs_per_sec __read_mostly = 1000; +@@ -356,6 +363,7 @@ + struct sock *sk; + struct sk_buff *skb; + ++ local_lock(icmp_sk_lock); + sk = icmp_sk(dev_net((*rt)->dst.dev)); + if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param, + icmp_param->data_len+icmp_param->head_len, +@@ -378,6 +386,7 @@ + skb->ip_summed = CHECKSUM_NONE; + ip_push_pending_frames(sk, fl4); + } ++ local_unlock(icmp_sk_lock); + } + + /* +@@ -867,6 +876,30 @@ + } + + /* ++ * 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 +@@ -893,6 +926,11 @@ + 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); ++ } + } + /* should there be an ICMP stat for ignored echos? */ + return true; +diff -Nur linux-4.1.39.orig/net/ipv4/sysctl_net_ipv4.c linux-4.1.39/net/ipv4/sysctl_net_ipv4.c +--- linux-4.1.39.orig/net/ipv4/sysctl_net_ipv4.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/net/ipv4/sysctl_net_ipv4.c 2017-04-18 17:56:30.657398836 +0200 +@@ -779,6 +779,13 @@ + .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 -Nur linux-4.1.39.orig/net/ipv4/tcp_ipv4.c linux-4.1.39/net/ipv4/tcp_ipv4.c +--- linux-4.1.39.orig/net/ipv4/tcp_ipv4.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/net/ipv4/tcp_ipv4.c 2017-04-18 17:56:30.657398836 +0200 +@@ -62,6 +62,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -563,6 +564,7 @@ + } + EXPORT_SYMBOL(tcp_v4_send_check); + ++static DEFINE_LOCAL_IRQ_LOCK(tcp_sk_lock); + /* + * This routine will send an RST to the other tcp. + * +@@ -684,10 +686,13 @@ + arg.bound_dev_if = sk->sk_bound_dev_if; + + arg.tos = ip_hdr(skb)->tos; ++ ++ local_lock(tcp_sk_lock); + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, &TCP_SKB_CB(skb)->header.h4.opt, + ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, + &arg, arg.iov[0].iov_len); ++ local_unlock(tcp_sk_lock); + + TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); + TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); +@@ -769,10 +774,12 @@ + if (oif) + arg.bound_dev_if = oif; + arg.tos = tos; ++ local_lock(tcp_sk_lock); + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, &TCP_SKB_CB(skb)->header.h4.opt, + ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, + &arg, arg.iov[0].iov_len); ++ local_unlock(tcp_sk_lock); + + TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); + } +diff -Nur linux-4.1.39.orig/net/mac80211/rx.c linux-4.1.39/net/mac80211/rx.c +--- linux-4.1.39.orig/net/mac80211/rx.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/net/mac80211/rx.c 2017-04-18 17:56:30.657398836 +0200 +@@ -3580,7 +3580,7 @@ + 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 >= IEEE80211_NUM_BANDS)) + goto drop; +diff -Nur linux-4.1.39.orig/net/netfilter/core.c linux-4.1.39/net/netfilter/core.c +--- linux-4.1.39.orig/net/netfilter/core.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/net/netfilter/core.c 2017-04-18 17:56:30.657398836 +0200 +@@ -22,11 +22,17 @@ + #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 -Nur linux-4.1.39.orig/net/packet/af_packet.c linux-4.1.39/net/packet/af_packet.c +--- linux-4.1.39.orig/net/packet/af_packet.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/net/packet/af_packet.c 2017-04-18 17:56:30.657398836 +0200 +@@ -63,6 +63,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -698,7 +699,7 @@ + if (BLOCK_NUM_PKTS(pbd)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ +- cpu_relax(); ++ cpu_chill(); + } + } + +@@ -960,7 +961,7 @@ + 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 -Nur linux-4.1.39.orig/net/rds/ib_rdma.c linux-4.1.39/net/rds/ib_rdma.c +--- linux-4.1.39.orig/net/rds/ib_rdma.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/net/rds/ib_rdma.c 2017-04-18 17:56:30.657398836 +0200 +@@ -34,6 +34,7 @@ + #include + #include + #include ++#include + + #include "rds.h" + #include "ib.h" +@@ -286,7 +287,7 @@ + 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 -Nur linux-4.1.39.orig/net/sched/sch_generic.c linux-4.1.39/net/sched/sch_generic.c +--- linux-4.1.39.orig/net/sched/sch_generic.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/net/sched/sch_generic.c 2017-04-18 17:56:30.657398836 +0200 +@@ -899,7 +899,7 @@ + /* Wait for outstanding qdisc_run calls. */ + list_for_each_entry(dev, head, close_list) + while (some_qdisc_is_busy(dev)) +- yield(); ++ msleep(1); + } + + void dev_deactivate(struct net_device *dev) +diff -Nur linux-4.1.39.orig/net/sunrpc/svc_xprt.c linux-4.1.39/net/sunrpc/svc_xprt.c +--- linux-4.1.39.orig/net/sunrpc/svc_xprt.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/net/sunrpc/svc_xprt.c 2017-04-18 17:56:30.657398836 +0200 +@@ -341,7 +341,7 @@ + goto out; + } + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + pool = svc_pool_for_cpu(xprt->xpt_server, cpu); + + atomic_long_inc(&pool->sp_stats.packets); +@@ -377,7 +377,7 @@ + + atomic_long_inc(&pool->sp_stats.threads_woken); + wake_up_process(rqstp->rq_task); +- put_cpu(); ++ put_cpu_light(); + goto out; + } + rcu_read_unlock(); +@@ -398,7 +398,7 @@ + goto redo_search; + } + rqstp = NULL; +- put_cpu(); ++ put_cpu_light(); + out: + trace_svc_xprt_do_enqueue(xprt, rqstp); + } +diff -Nur linux-4.1.39.orig/scripts/mkcompile_h linux-4.1.39/scripts/mkcompile_h +--- linux-4.1.39.orig/scripts/mkcompile_h 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/scripts/mkcompile_h 2017-04-18 17:56:30.657398836 +0200 +@@ -4,7 +4,8 @@ + ARCH=$2 + SMP=$3 + PREEMPT=$4 +-CC=$5 ++RT=$5 ++CC=$6 + + vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; } + +@@ -57,6 +58,7 @@ + CONFIG_FLAGS="" + if [ -n "$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 -Nur linux-4.1.39.orig/sound/core/pcm_native.c linux-4.1.39/sound/core/pcm_native.c +--- linux-4.1.39.orig/sound/core/pcm_native.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/sound/core/pcm_native.c 2017-04-18 17:56:30.661398992 +0200 +@@ -135,7 +135,7 @@ + void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream) + { + if (!substream->pcm->nonatomic) +- local_irq_disable(); ++ local_irq_disable_nort(); + snd_pcm_stream_lock(substream); + } + EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq); +@@ -150,7 +150,7 @@ + { + snd_pcm_stream_unlock(substream); + if (!substream->pcm->nonatomic) +- local_irq_enable(); ++ local_irq_enable_nort(); + } + EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irq); + +@@ -158,7 +158,7 @@ + { + unsigned long flags = 0; + if (!substream->pcm->nonatomic) +- local_irq_save(flags); ++ local_irq_save_nort(flags); + snd_pcm_stream_lock(substream); + return flags; + } +@@ -176,7 +176,7 @@ + { + snd_pcm_stream_unlock(substream); + if (!substream->pcm->nonatomic) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irqrestore); + +diff -Nur linux-4.1.39.orig/sound/soc/intel/atom/sst/sst.c linux-4.1.39/sound/soc/intel/atom/sst/sst.c +--- linux-4.1.39.orig/sound/soc/intel/atom/sst/sst.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/sound/soc/intel/atom/sst/sst.c 2017-04-18 17:56:30.661398992 +0200 +@@ -368,8 +368,8 @@ + * initialize by FW or driver when firmware is loaded + */ + spin_lock_irqsave(&ctx->ipc_spin_lock, irq_flags); +- sst_shim_write64(shim, SST_IMRX, shim_regs->imrx), +- sst_shim_write64(shim, SST_CSR, shim_regs->csr), ++ sst_shim_write64(shim, SST_IMRX, shim_regs->imrx); ++ sst_shim_write64(shim, SST_CSR, shim_regs->csr); + spin_unlock_irqrestore(&ctx->ipc_spin_lock, irq_flags); + } + +diff -Nur linux-4.1.39.orig/virt/kvm/async_pf.c linux-4.1.39/virt/kvm/async_pf.c +--- linux-4.1.39.orig/virt/kvm/async_pf.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/virt/kvm/async_pf.c 2017-04-18 17:56:30.661398992 +0200 +@@ -94,8 +94,8 @@ + + trace_kvm_async_pf_completed(addr, gva); + +- if (waitqueue_active(&vcpu->wq)) +- wake_up_interruptible(&vcpu->wq); ++ if (swaitqueue_active(&vcpu->wq)) ++ swait_wake_interruptible(&vcpu->wq); + + mmput(mm); + kvm_put_kvm(vcpu->kvm); +diff -Nur linux-4.1.39.orig/virt/kvm/kvm_main.c linux-4.1.39/virt/kvm/kvm_main.c +--- linux-4.1.39.orig/virt/kvm/kvm_main.c 2017-03-13 21:04:36.000000000 +0100 ++++ linux-4.1.39/virt/kvm/kvm_main.c 2017-04-18 17:56:30.661398992 +0200 +@@ -220,7 +220,7 @@ + vcpu->kvm = kvm; + vcpu->vcpu_id = id; + vcpu->pid = NULL; +- init_waitqueue_head(&vcpu->wq); ++ init_swait_head(&vcpu->wq); + kvm_async_pf_vcpu_init(vcpu); + + page = alloc_page(GFP_KERNEL | __GFP_ZERO); +@@ -1782,7 +1782,7 @@ + void kvm_vcpu_block(struct kvm_vcpu *vcpu) + { + ktime_t start, cur; +- DEFINE_WAIT(wait); ++ DEFINE_SWAITER(wait); + bool waited = false; + + start = cur = ktime_get(); +@@ -1803,7 +1803,7 @@ + } + + for (;;) { +- prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); ++ swait_prepare(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + + if (kvm_vcpu_check_block(vcpu) < 0) + break; +@@ -1812,7 +1812,7 @@ + schedule(); + } + +- finish_wait(&vcpu->wq, &wait); ++ swait_finish(&vcpu->wq, &wait); + cur = ktime_get(); + + out: +@@ -1828,11 +1828,11 @@ + { + int me; + int cpu = vcpu->cpu; +- wait_queue_head_t *wqp; ++ struct swait_head *wqp; + + wqp = kvm_arch_vcpu_wq(vcpu); +- if (waitqueue_active(wqp)) { +- wake_up_interruptible(wqp); ++ if (swaitqueue_active(wqp)) { ++ swait_wake_interruptible(wqp); + ++vcpu->stat.halt_wakeup; + } + +@@ -1933,7 +1933,7 @@ + continue; + if (vcpu == me) + continue; +- if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) ++ if (swaitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) + continue; + if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) + continue; -- cgit v1.2.3