diff -Nur linux-4.4.38.orig/arch/arm/include/asm/switch_to.h linux-4.4.38/arch/arm/include/asm/switch_to.h --- linux-4.4.38.orig/arch/arm/include/asm/switch_to.h 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/include/asm/switch_to.h 2017-01-01 21:00:17.997608452 +0100 @@ -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 @@ -25,6 +32,7 @@ #define switch_to(prev,next,last) \ do { \ __complete_pending_tlbi(); \ + switch_kmaps(prev, next); \ last = __switch_to(prev,task_thread_info(prev), task_thread_info(next)); \ } while (0) diff -Nur linux-4.4.38.orig/arch/arm/include/asm/thread_info.h linux-4.4.38/arch/arm/include/asm/thread_info.h --- linux-4.4.38.orig/arch/arm/include/asm/thread_info.h 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/include/asm/thread_info.h 2017-01-01 21:00:18.017609733 +0100 @@ -49,6 +49,7 @@ 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 */ @@ -142,7 +143,8 @@ #define TIF_SYSCALL_TRACE 4 /* syscall trace active */ #define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ -#define TIF_SECCOMP 7 /* seccomp syscall filtering active */ +#define TIF_SECCOMP 8 /* seccomp syscall filtering active */ +#define TIF_NEED_RESCHED_LAZY 7 #define TIF_NOHZ 12 /* in adaptive nohz mode */ #define TIF_USING_IWMMXT 17 @@ -152,6 +154,7 @@ #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) @@ -167,7 +170,8 @@ * Change these and you break ASM code in entry-common.S */ #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ - _TIF_NOTIFY_RESUME | _TIF_UPROBE) + _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_NEED_RESCHED_LAZY) #endif /* __KERNEL__ */ #endif /* __ASM_ARM_THREAD_INFO_H */ diff -Nur linux-4.4.38.orig/arch/arm/Kconfig linux-4.4.38/arch/arm/Kconfig --- linux-4.4.38.orig/arch/arm/Kconfig 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/Kconfig 2017-01-01 21:00:17.929604080 +0100 @@ -33,7 +33,7 @@ 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 && !CPU_ENDIAN_BE32 + select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !PREEMPT_RT_BASE select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT) select HAVE_ARCH_TRACEHOOK @@ -68,6 +68,7 @@ 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-4.4.38.orig/arch/arm/kernel/asm-offsets.c linux-4.4.38/arch/arm/kernel/asm-offsets.c --- linux-4.4.38.orig/arch/arm/kernel/asm-offsets.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/kernel/asm-offsets.c 2017-01-01 21:00:18.041611275 +0100 @@ -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-4.4.38.orig/arch/arm/kernel/entry-armv.S linux-4.4.38/arch/arm/kernel/entry-armv.S --- linux-4.4.38.orig/arch/arm/kernel/entry-armv.S 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/kernel/entry-armv.S 2017-01-01 21:00:18.057612302 +0100 @@ -215,11 +215,18 @@ #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 @@ -234,8 +241,14 @@ 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-4.4.38.orig/arch/arm/kernel/entry-common.S linux-4.4.38/arch/arm/kernel/entry-common.S --- linux-4.4.38.orig/arch/arm/kernel/entry-common.S 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/kernel/entry-common.S 2017-01-01 21:00:18.057612302 +0100 @@ -36,7 +36,9 @@ UNWIND(.cantunwind ) disable_irq_notrace @ disable interrupts ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing - tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK + tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP) + bne fast_work_pending + tst r1, #_TIF_SECCOMP bne fast_work_pending /* perform architecture specific actions before user return */ @@ -62,8 +64,11 @@ str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 disable_irq_notrace @ disable interrupts ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing - tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK + tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP) + bne do_slower_path + tst r1, #_TIF_SECCOMP beq no_work_pending +do_slower_path: UNWIND(.fnend ) ENDPROC(ret_fast_syscall) diff -Nur linux-4.4.38.orig/arch/arm/kernel/process.c linux-4.4.38/arch/arm/kernel/process.c --- linux-4.4.38.orig/arch/arm/kernel/process.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/kernel/process.c 2017-01-01 21:00:18.065612816 +0100 @@ -319,6 +319,30 @@ } #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-4.4.38.orig/arch/arm/kernel/signal.c linux-4.4.38/arch/arm/kernel/signal.c --- linux-4.4.38.orig/arch/arm/kernel/signal.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/kernel/signal.c 2017-01-01 21:00:18.065612816 +0100 @@ -572,7 +572,8 @@ */ trace_hardirqs_off(); 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-4.4.38.orig/arch/arm/kernel/smp.c linux-4.4.38/arch/arm/kernel/smp.c --- linux-4.4.38.orig/arch/arm/kernel/smp.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/kernel/smp.c 2017-01-01 21:00:18.069613077 +0100 @@ -230,8 +230,6 @@ flush_cache_louis(); local_flush_tlb_all(); - clear_tasks_mm_cpumask(cpu); - return 0; } @@ -247,6 +245,9 @@ 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-4.4.38.orig/arch/arm/kernel/unwind.c linux-4.4.38/arch/arm/kernel/unwind.c --- linux-4.4.38.orig/arch/arm/kernel/unwind.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/kernel/unwind.c 2017-01-01 21:00:18.069613077 +0100 @@ -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-4.4.38.orig/arch/arm/kvm/arm.c linux-4.4.38/arch/arm/kvm/arm.c --- linux-4.4.38.orig/arch/arm/kvm/arm.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/kvm/arm.c 2017-01-01 21:00:18.085614105 +0100 @@ -496,18 +496,18 @@ struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { - wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); + struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); vcpu->arch.pause = false; - wake_up_interruptible(wq); + swake_up(wq); } } static void vcpu_sleep(struct kvm_vcpu *vcpu) { - wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); + struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); - wait_event_interruptible(*wq, ((!vcpu->arch.power_off) && + swait_event_interruptible(*wq, ((!vcpu->arch.power_off) && (!vcpu->arch.pause))); } @@ -566,7 +566,7 @@ * involves poking the GIC, which must be done in a * non-preemptible context. */ - preempt_disable(); + migrate_disable(); kvm_timer_flush_hwstate(vcpu); kvm_vgic_flush_hwstate(vcpu); @@ -585,7 +585,7 @@ local_irq_enable(); kvm_timer_sync_hwstate(vcpu); kvm_vgic_sync_hwstate(vcpu); - preempt_enable(); + migrate_enable(); continue; } @@ -639,7 +639,7 @@ kvm_vgic_sync_hwstate(vcpu); - preempt_enable(); + migrate_enable(); ret = handle_exit(vcpu, run, ret); } diff -Nur linux-4.4.38.orig/arch/arm/kvm/psci.c linux-4.4.38/arch/arm/kvm/psci.c --- linux-4.4.38.orig/arch/arm/kvm/psci.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/kvm/psci.c 2017-01-01 21:00:18.105615386 +0100 @@ -70,7 +70,7 @@ { struct kvm *kvm = source_vcpu->kvm; struct kvm_vcpu *vcpu = NULL; - wait_queue_head_t *wq; + struct swait_queue_head *wq; unsigned long cpu_id; unsigned long context_id; phys_addr_t target_pc; @@ -119,7 +119,7 @@ smp_mb(); /* Make sure the above is visible */ wq = kvm_arch_vcpu_wq(vcpu); - wake_up_interruptible(wq); + swake_up(wq); return PSCI_RET_SUCCESS; } diff -Nur linux-4.4.38.orig/arch/arm/mach-at91/at91rm9200.c linux-4.4.38/arch/arm/mach-at91/at91rm9200.c --- linux-4.4.38.orig/arch/arm/mach-at91/at91rm9200.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-at91/at91rm9200.c 2017-01-01 21:00:18.109615647 +0100 @@ -12,7 +12,6 @@ #include #include -#include #include "generic.h" #include "soc.h" @@ -33,7 +32,6 @@ of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev); - arm_pm_idle = at91rm9200_idle; at91rm9200_pm_init(); } diff -Nur linux-4.4.38.orig/arch/arm/mach-at91/at91sam9.c linux-4.4.38/arch/arm/mach-at91/at91sam9.c --- linux-4.4.38.orig/arch/arm/mach-at91/at91sam9.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-at91/at91sam9.c 2017-01-01 21:00:18.109615647 +0100 @@ -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-4.4.38.orig/arch/arm/mach-at91/generic.h linux-4.4.38/arch/arm/mach-at91/generic.h --- linux-4.4.38.orig/arch/arm/mach-at91/generic.h 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-at91/generic.h 2017-01-01 21:00:18.109615647 +0100 @@ -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-4.4.38.orig/arch/arm/mach-at91/Kconfig linux-4.4.38/arch/arm/mach-at91/Kconfig --- linux-4.4.38.orig/arch/arm/mach-at91/Kconfig 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-at91/Kconfig 2017-01-01 21:00:18.109615647 +0100 @@ -99,6 +99,7 @@ config COMMON_CLK_AT91 bool select COMMON_CLK + select MFD_SYSCON config HAVE_AT91_SMD bool diff -Nur linux-4.4.38.orig/arch/arm/mach-at91/pm.c linux-4.4.38/arch/arm/mach-at91/pm.c --- linux-4.4.38.orig/arch/arm/mach-at91/pm.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-at91/pm.c 2017-01-01 21:00:18.113615900 +0100 @@ -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 @@ -87,7 +90,7 @@ 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) { @@ -101,8 +104,7 @@ 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; @@ -145,8 +147,8 @@ 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(); } @@ -353,6 +355,21 @@ 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; @@ -399,13 +416,36 @@ &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 @@ -424,7 +464,7 @@ 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) @@ -432,7 +472,7 @@ 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) @@ -440,7 +480,7 @@ 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) @@ -448,5 +488,13 @@ 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-4.4.38.orig/arch/arm/mach-at91/sama5.c linux-4.4.38/arch/arm/mach-at91/sama5.c --- linux-4.4.38.orig/arch/arm/mach-at91/sama5.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-at91/sama5.c 2017-01-01 21:00:18.113615900 +0100 @@ -51,7 +51,7 @@ 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 *const sama5_dt_board_compat[] __initconst = { diff -Nur linux-4.4.38.orig/arch/arm/mach-exynos/platsmp.c linux-4.4.38/arch/arm/mach-exynos/platsmp.c --- linux-4.4.38.orig/arch/arm/mach-exynos/platsmp.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-exynos/platsmp.c 2017-01-01 21:00:18.137617441 +0100 @@ -230,7 +230,7 @@ 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) { @@ -243,8 +243,8 @@ /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } int exynos_set_boot_addr(u32 core_id, unsigned long boot_addr) @@ -308,7 +308,7 @@ * 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 @@ -335,7 +335,7 @@ if (timeout == 0) { printk(KERN_ERR "cpu1 power enable failed"); - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return -ETIMEDOUT; } } @@ -381,7 +381,7 @@ * 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-4.4.38.orig/arch/arm/mach-hisi/platmcpm.c linux-4.4.38/arch/arm/mach-hisi/platmcpm.c --- linux-4.4.38.orig/arch/arm/mach-hisi/platmcpm.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-hisi/platmcpm.c 2017-01-01 21:00:18.157618732 +0100 @@ -61,7 +61,7 @@ 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 @@ -113,7 +113,7 @@ 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; @@ -147,7 +147,7 @@ out: hip04_cpu_table[cluster][cpu]++; - spin_unlock_irq(&boot_lock); + raw_spin_unlock_irq(&boot_lock); return 0; } @@ -162,11 +162,11 @@ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); hip04_cpu_table[cluster][cpu]--; if (hip04_cpu_table[cluster][cpu] == 1) { /* A power_up request went ahead of us. */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return; } else if (hip04_cpu_table[cluster][cpu] > 1) { pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu); @@ -174,7 +174,7 @@ } last_man = hip04_cluster_is_down(cluster); - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); if (last_man) { /* Since it's Cortex A15, disable L2 prefetching. */ asm volatile( @@ -203,7 +203,7 @@ 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]) goto err; @@ -211,10 +211,10 @@ 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; @@ -231,10 +231,10 @@ goto err; if (hip04_cluster_is_down(cluster)) hip04_set_snoop_filter(cluster, 0); - spin_unlock_irq(&boot_lock); + raw_spin_unlock_irq(&boot_lock); return 1; err: - spin_unlock_irq(&boot_lock); + raw_spin_unlock_irq(&boot_lock); return 0; } #endif diff -Nur linux-4.4.38.orig/arch/arm/mach-imx/Kconfig linux-4.4.38/arch/arm/mach-imx/Kconfig --- linux-4.4.38.orig/arch/arm/mach-imx/Kconfig 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-imx/Kconfig 2017-01-01 21:00:18.157618732 +0100 @@ -524,7 +524,7 @@ bool "i.MX6 Quad/DualLite support" select ARM_ERRATA_764369 if SMP select HAVE_ARM_SCU if SMP - select HAVE_ARM_TWD if SMP + select HAVE_ARM_TWD select PCI_DOMAINS if PCI select PINCTRL_IMX6Q select SOC_IMX6 diff -Nur linux-4.4.38.orig/arch/arm/mach-omap2/omap-smp.c linux-4.4.38/arch/arm/mach-omap2/omap-smp.c --- linux-4.4.38.orig/arch/arm/mach-omap2/omap-smp.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-omap2/omap-smp.c 2017-01-01 21:00:18.193621044 +0100 @@ -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-4.4.38.orig/arch/arm/mach-prima2/platsmp.c linux-4.4.38/arch/arm/mach-prima2/platsmp.c --- linux-4.4.38.orig/arch/arm/mach-prima2/platsmp.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-prima2/platsmp.c 2017-01-01 21:00:18.221622840 +0100 @@ -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-4.4.38.orig/arch/arm/mach-qcom/platsmp.c linux-4.4.38/arch/arm/mach-qcom/platsmp.c --- linux-4.4.38.orig/arch/arm/mach-qcom/platsmp.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-qcom/platsmp.c 2017-01-01 21:00:18.261625413 +0100 @@ -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 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-4.4.38.orig/arch/arm/mach-spear/platsmp.c linux-4.4.38/arch/arm/mach-spear/platsmp.c --- linux-4.4.38.orig/arch/arm/mach-spear/platsmp.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-spear/platsmp.c 2017-01-01 21:00:18.305628239 +0100 @@ -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-4.4.38.orig/arch/arm/mach-sti/platsmp.c linux-4.4.38/arch/arm/mach-sti/platsmp.c --- linux-4.4.38.orig/arch/arm/mach-sti/platsmp.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mach-sti/platsmp.c 2017-01-01 21:00:18.341630548 +0100 @@ -35,7 +35,7 @@ sync_cache_w(&pen_release); } -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static void sti_secondary_init(unsigned int cpu) { @@ -48,8 +48,8 @@ /* * 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) @@ -60,7 +60,7 @@ * 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 @@ -91,7 +91,7 @@ * 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-4.4.38.orig/arch/arm/mm/fault.c linux-4.4.38/arch/arm/mm/fault.c --- linux-4.4.38.orig/arch/arm/mm/fault.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mm/fault.c 2017-01-01 21:00:18.345630809 +0100 @@ -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-4.4.38.orig/arch/arm/mm/highmem.c linux-4.4.38/arch/arm/mm/highmem.c --- linux-4.4.38.orig/arch/arm/mm/highmem.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/mm/highmem.c 2017-01-01 21:00:18.349631062 +0100 @@ -34,6 +34,11 @@ return *ptep; } +static unsigned int fixmap_idx(int type) +{ + return FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); +} + void *kmap(struct page *page) { might_sleep(); @@ -54,12 +59,13 @@ 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(); + preempt_disable_nort(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); @@ -79,7 +85,7 @@ type = kmap_atomic_idx_push(); - idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); + idx = fixmap_idx(type); vaddr = __fix_to_virt(idx); #ifdef CONFIG_DEBUG_HIGHMEM /* @@ -93,7 +99,10 @@ * 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; } @@ -106,44 +115,75 @@ if (kvaddr >= (void *)FIXADDR_START) { type = kmap_atomic_idx(); - idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); + idx = fixmap_idx(type); 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(); + 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(); + preempt_disable_nort(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); type = kmap_atomic_idx_push(); - idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); + idx = fixmap_idx(type); vaddr = __fix_to_virt(idx); #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; } +#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 = fixmap_idx(i); + + set_fixmap_pte(idx, __pte(0)); + } + /* + * Restore @next_p's kmap_atomic mappings + */ + for (i = 0; i < next_p->kmap_idx; i++) { + int idx = fixmap_idx(i); + + if (!pte_none(next_p->kmap_pte[i])) + set_fixmap_pte(idx, next_p->kmap_pte[i]); + } +} +#endif diff -Nur linux-4.4.38.orig/arch/arm/plat-versatile/platsmp.c linux-4.4.38/arch/arm/plat-versatile/platsmp.c --- linux-4.4.38.orig/arch/arm/plat-versatile/platsmp.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm/plat-versatile/platsmp.c 2017-01-01 21:00:18.381633117 +0100 @@ -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-4.4.38.orig/arch/arm64/include/asm/thread_info.h linux-4.4.38/arch/arm64/include/asm/thread_info.h --- linux-4.4.38.orig/arch/arm64/include/asm/thread_info.h 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm64/include/asm/thread_info.h 2017-01-01 21:00:18.465638510 +0100 @@ -49,6 +49,7 @@ 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 */ }; @@ -103,6 +104,7 @@ #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 @@ -118,6 +120,7 @@ #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) @@ -126,7 +129,8 @@ #define _TIF_32BIT (1 << TIF_32BIT) #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ - _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE) + _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ + _TIF_NEED_RESCHED_LAZY) #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ diff -Nur linux-4.4.38.orig/arch/arm64/Kconfig linux-4.4.38/arch/arm64/Kconfig --- linux-4.4.38.orig/arch/arm64/Kconfig 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm64/Kconfig 2017-01-01 21:00:18.425635948 +0100 @@ -76,6 +76,7 @@ select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE + select HAVE_PREEMPT_LAZY select HAVE_SYSCALL_TRACEPOINTS select IOMMU_DMA if IOMMU_SUPPORT select IRQ_DOMAIN @@ -582,7 +583,7 @@ 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-4.4.38.orig/arch/arm64/kernel/asm-offsets.c linux-4.4.38/arch/arm64/kernel/asm-offsets.c --- linux-4.4.38.orig/arch/arm64/kernel/asm-offsets.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm64/kernel/asm-offsets.c 2017-01-01 21:00:18.465638510 +0100 @@ -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-4.4.38.orig/arch/arm64/kernel/entry.S linux-4.4.38/arch/arm64/kernel/entry.S --- linux-4.4.38.orig/arch/arm64/kernel/entry.S 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/arm64/kernel/entry.S 2017-01-01 21:00:18.469638771 +0100 @@ -376,11 +376,16 @@ #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 @@ -394,6 +399,7 @@ 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 @@ -638,6 +644,7 @@ */ 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-4.4.38.orig/arch/Kconfig linux-4.4.38/arch/Kconfig --- linux-4.4.38.orig/arch/Kconfig 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/Kconfig 2017-01-01 21:00:17.865599969 +0100 @@ -9,6 +9,7 @@ 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 @@ -52,6 +53,7 @@ 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-4.4.38.orig/arch/mips/Kconfig linux-4.4.38/arch/mips/Kconfig --- linux-4.4.38.orig/arch/mips/Kconfig 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/mips/Kconfig 2017-01-01 21:00:18.493640313 +0100 @@ -2410,7 +2410,7 @@ # 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-4.4.38.orig/arch/mips/kvm/mips.c linux-4.4.38/arch/mips/kvm/mips.c --- linux-4.4.38.orig/arch/mips/kvm/mips.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/mips/kvm/mips.c 2017-01-01 21:00:18.509641339 +0100 @@ -454,8 +454,8 @@ dvcpu->arch.wait = 0; - if (waitqueue_active(&dvcpu->wq)) - wake_up_interruptible(&dvcpu->wq); + if (swait_active(&dvcpu->wq)) + swake_up(&dvcpu->wq); return 0; } @@ -1183,8 +1183,8 @@ kvm_mips_callbacks->queue_timer_int(vcpu); vcpu->arch.wait = 0; - if (waitqueue_active(&vcpu->wq)) - wake_up_interruptible(&vcpu->wq); + if (swait_active(&vcpu->wq)) + swake_up(&vcpu->wq); } /* low level hrtimer wake routine */ diff -Nur linux-4.4.38.orig/arch/powerpc/include/asm/kvm_host.h linux-4.4.38/arch/powerpc/include/asm/kvm_host.h --- linux-4.4.38.orig/arch/powerpc/include/asm/kvm_host.h 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/powerpc/include/asm/kvm_host.h 2017-01-01 21:00:18.529642625 +0100 @@ -286,7 +286,7 @@ struct list_head runnable_threads; struct list_head preempt_list; spinlock_t lock; - wait_queue_head_t wq; + struct swait_queue_head wq; spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ u64 stolen_tb; u64 preempt_tb; @@ -626,7 +626,7 @@ u8 prodded; u32 last_inst; - wait_queue_head_t *wqp; + struct swait_queue_head *wqp; struct kvmppc_vcore *vcore; int ret; int trap; diff -Nur linux-4.4.38.orig/arch/powerpc/include/asm/thread_info.h linux-4.4.38/arch/powerpc/include/asm/thread_info.h --- linux-4.4.38.orig/arch/powerpc/include/asm/thread_info.h 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/powerpc/include/asm/thread_info.h 2017-01-01 21:00:18.537643140 +0100 @@ -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-4.4.38.orig/arch/powerpc/kernel/misc_32.S linux-4.4.38/arch/powerpc/kernel/misc_32.S --- linux-4.4.38.orig/arch/powerpc/kernel/misc_32.S 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/powerpc/kernel/misc_32.S 2017-01-01 21:00:18.561644685 +0100 @@ -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-4.4.38.orig/arch/powerpc/kernel/misc_64.S linux-4.4.38/arch/powerpc/kernel/misc_64.S --- linux-4.4.38.orig/arch/powerpc/kernel/misc_64.S 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/powerpc/kernel/misc_64.S 2017-01-01 21:00:18.561644685 +0100 @@ -30,6 +30,7 @@ .text +#ifndef CONFIG_PREEMPT_RT_FULL _GLOBAL(call_do_softirq) mflr r0 std r0,16(r1) @@ -40,6 +41,7 @@ ld r0,16(r1) mtlr r0 blr +#endif _GLOBAL(call_do_irq) mflr r0 diff -Nur linux-4.4.38.orig/arch/powerpc/kvm/book3s_hv.c linux-4.4.38/arch/powerpc/kvm/book3s_hv.c --- linux-4.4.38.orig/arch/powerpc/kvm/book3s_hv.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/powerpc/kvm/book3s_hv.c 2017-01-01 21:00:18.589646480 +0100 @@ -114,11 +114,11 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) { int cpu; - wait_queue_head_t *wqp; + struct swait_queue_head *wqp; wqp = kvm_arch_vcpu_wq(vcpu); - if (waitqueue_active(wqp)) { - wake_up_interruptible(wqp); + if (swait_active(wqp)) { + swake_up(wqp); ++vcpu->stat.halt_wakeup; } @@ -707,8 +707,8 @@ tvcpu->arch.prodded = 1; smp_mb(); if (vcpu->arch.ceded) { - if (waitqueue_active(&vcpu->wq)) { - wake_up_interruptible(&vcpu->wq); + if (swait_active(&vcpu->wq)) { + swake_up(&vcpu->wq); vcpu->stat.halt_wakeup++; } } @@ -1447,7 +1447,7 @@ INIT_LIST_HEAD(&vcore->runnable_threads); spin_lock_init(&vcore->lock); spin_lock_init(&vcore->stoltb_lock); - init_waitqueue_head(&vcore->wq); + init_swait_queue_head(&vcore->wq); vcore->preempt_tb = TB_NIL; vcore->lpcr = kvm->arch.lpcr; vcore->first_vcpuid = core * threads_per_subcore; @@ -2519,10 +2519,9 @@ { struct kvm_vcpu *vcpu; int do_sleep = 1; + DECLARE_SWAITQUEUE(wait); - DEFINE_WAIT(wait); - - prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE); /* * Check one last time for pending exceptions and ceded state after @@ -2536,7 +2535,7 @@ } if (!do_sleep) { - finish_wait(&vc->wq, &wait); + finish_swait(&vc->wq, &wait); return; } @@ -2544,7 +2543,7 @@ trace_kvmppc_vcore_blocked(vc, 0); spin_unlock(&vc->lock); schedule(); - finish_wait(&vc->wq, &wait); + finish_swait(&vc->wq, &wait); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; trace_kvmppc_vcore_blocked(vc, 1); @@ -2600,7 +2599,7 @@ kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { - wake_up(&vc->wq); + swake_up(&vc->wq); } } diff -Nur linux-4.4.38.orig/arch/powerpc/kvm/Kconfig linux-4.4.38/arch/powerpc/kvm/Kconfig --- linux-4.4.38.orig/arch/powerpc/kvm/Kconfig 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/powerpc/kvm/Kconfig 2017-01-01 21:00:18.573645449 +0100 @@ -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-4.4.38.orig/arch/powerpc/platforms/ps3/device-init.c linux-4.4.38/arch/powerpc/platforms/ps3/device-init.c --- linux-4.4.38.orig/arch/powerpc/platforms/ps3/device-init.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/powerpc/platforms/ps3/device-init.c 2017-01-01 21:00:18.605647510 +0100 @@ -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-4.4.38.orig/arch/s390/include/asm/kvm_host.h linux-4.4.38/arch/s390/include/asm/kvm_host.h --- linux-4.4.38.orig/arch/s390/include/asm/kvm_host.h 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/s390/include/asm/kvm_host.h 2017-01-01 21:00:18.613648025 +0100 @@ -427,7 +427,7 @@ struct kvm_s390_local_interrupt { spinlock_t lock; struct kvm_s390_float_interrupt *float_int; - wait_queue_head_t *wq; + struct swait_queue_head *wq; atomic_t *cpuflags; DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS); struct kvm_s390_irq_payload irq; diff -Nur linux-4.4.38.orig/arch/s390/kvm/interrupt.c linux-4.4.38/arch/s390/kvm/interrupt.c --- linux-4.4.38.orig/arch/s390/kvm/interrupt.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/s390/kvm/interrupt.c 2017-01-01 21:00:18.625648792 +0100 @@ -868,13 +868,13 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) { - if (waitqueue_active(&vcpu->wq)) { + if (swait_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); + swake_up(&vcpu->wq); vcpu->stat.halt_wakeup++; } } diff -Nur linux-4.4.38.orig/arch/sh/kernel/irq.c linux-4.4.38/arch/sh/kernel/irq.c --- linux-4.4.38.orig/arch/sh/kernel/irq.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/sh/kernel/irq.c 2017-01-01 21:00:18.629649053 +0100 @@ -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-4.4.38.orig/arch/sparc/Kconfig linux-4.4.38/arch/sparc/Kconfig --- linux-4.4.38.orig/arch/sparc/Kconfig 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/sparc/Kconfig 2017-01-01 21:00:18.637649567 +0100 @@ -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-4.4.38.orig/arch/sparc/kernel/irq_64.c linux-4.4.38/arch/sparc/kernel/irq_64.c --- linux-4.4.38.orig/arch/sparc/kernel/irq_64.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/sparc/kernel/irq_64.c 2017-01-01 21:00:18.645650077 +0100 @@ -854,6 +854,7 @@ 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()]; @@ -868,6 +869,7 @@ __asm__ __volatile__("mov %0, %%sp" : : "r" (orig_sp)); } +#endif #ifdef CONFIG_HOTPLUG_CPU void fixup_irqs(void) diff -Nur linux-4.4.38.orig/arch/x86/crypto/aesni-intel_glue.c linux-4.4.38/arch/x86/crypto/aesni-intel_glue.c --- linux-4.4.38.orig/arch/x86/crypto/aesni-intel_glue.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/x86/crypto/aesni-intel_glue.c 2017-01-01 21:00:18.677652130 +0100 @@ -383,14 +383,14 @@ 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; } @@ -407,14 +407,14 @@ 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; } @@ -431,14 +431,14 @@ 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; } @@ -455,14 +455,14 @@ 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; } @@ -514,18 +514,20 @@ 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-4.4.38.orig/arch/x86/crypto/cast5_avx_glue.c linux-4.4.38/arch/x86/crypto/cast5_avx_glue.c --- linux-4.4.38.orig/arch/x86/crypto/cast5_avx_glue.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/x86/crypto/cast5_avx_glue.c 2017-01-01 21:00:18.685652651 +0100 @@ -59,7 +59,7 @@ 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; @@ -75,7 +75,7 @@ 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) { @@ -103,10 +103,9 @@ } while (nbytes >= bsize); done: + cast5_fpu_end(fpu_enabled); err = blkcipher_walk_done(desc, walk, nbytes); } - - cast5_fpu_end(fpu_enabled); return err; } @@ -227,7 +226,7 @@ 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; @@ -236,12 +235,11 @@ 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; } @@ -311,7 +309,7 @@ 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; @@ -320,13 +318,12 @@ 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-4.4.38.orig/arch/x86/crypto/glue_helper.c linux-4.4.38/arch/x86/crypto/glue_helper.c --- linux-4.4.38.orig/arch/x86/crypto/glue_helper.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/x86/crypto/glue_helper.c 2017-01-01 21:00:18.689652904 +0100 @@ -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-4.4.38.orig/arch/x86/entry/common.c linux-4.4.38/arch/x86/entry/common.c --- linux-4.4.38.orig/arch/x86/entry/common.c 2016-12-10 19:08:05.000000000 +0100 +++ linux-4.4.38/arch/x86/entry/common.c 2017-01-01 21:00:18.701653672 +0100 @@ -220,7 +220,7 @@ #define EXIT_TO_USERMODE_LOOP_FLAGS \ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ - _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY) + _TIF_NEED_RESCHED_MASK | _TIF_USER_RETURN_NOTIFY