diff -Nur linux-3.18.9.orig/arch/alpha/mm/fault.c linux-3.18.9/arch/alpha/mm/fault.c --- linux-3.18.9.orig/arch/alpha/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/alpha/mm/fault.c 2015-03-15 16:03:03.672094877 -0500 @@ -107,7 +107,7 @@ /* If we're in an interrupt context, or have no user context, we must not take the fault. */ - if (!mm || in_atomic()) + if (!mm || pagefault_disabled()) goto no_context; #ifdef CONFIG_ALPHA_LARGE_VMALLOC diff -Nur linux-3.18.9.orig/arch/arm/include/asm/cmpxchg.h linux-3.18.9/arch/arm/include/asm/cmpxchg.h --- linux-3.18.9.orig/arch/arm/include/asm/cmpxchg.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/include/asm/cmpxchg.h 2015-03-15 16:03:03.672094877 -0500 @@ -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-3.18.9.orig/arch/arm/include/asm/futex.h linux-3.18.9/arch/arm/include/asm/futex.h --- linux-3.18.9.orig/arch/arm/include/asm/futex.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/include/asm/futex.h 2015-03-15 16:03:03.672094877 -0500 @@ -93,6 +93,8 @@ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; + preempt_disable_rt(); + __asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n" "1: " TUSER(ldr) " %1, [%4]\n" " teq %1, %2\n" @@ -104,6 +106,8 @@ : "cc", "memory"); *uval = val; + + preempt_enable_rt(); return ret; } diff -Nur linux-3.18.9.orig/arch/arm/include/asm/switch_to.h linux-3.18.9/arch/arm/include/asm/switch_to.h --- linux-3.18.9.orig/arch/arm/include/asm/switch_to.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/include/asm/switch_to.h 2015-03-15 16:03:03.672094877 -0500 @@ -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-3.18.9.orig/arch/arm/include/asm/thread_info.h linux-3.18.9/arch/arm/include/asm/thread_info.h --- linux-3.18.9.orig/arch/arm/include/asm/thread_info.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/include/asm/thread_info.h 2015-03-15 16:03:03.672094877 -0500 @@ -51,6 +51,7 @@ 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 */ struct exec_domain *exec_domain; /* execution domain */ @@ -149,6 +150,7 @@ #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 @@ -162,6 +164,7 @@ #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-3.18.9.orig/arch/arm/Kconfig linux-3.18.9/arch/arm/Kconfig --- linux-3.18.9.orig/arch/arm/Kconfig 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/Kconfig 2015-03-15 16:03:03.672094877 -0500 @@ -62,6 +62,7 @@ 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-3.18.9.orig/arch/arm/kernel/asm-offsets.c linux-3.18.9/arch/arm/kernel/asm-offsets.c --- linux-3.18.9.orig/arch/arm/kernel/asm-offsets.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/kernel/asm-offsets.c 2015-03-15 16:03:03.672094877 -0500 @@ -64,6 +64,7 @@ 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_EXEC_DOMAIN, offsetof(struct thread_info, exec_domain)); diff -Nur linux-3.18.9.orig/arch/arm/kernel/entry-armv.S linux-3.18.9/arch/arm/kernel/entry-armv.S --- linux-3.18.9.orig/arch/arm/kernel/entry-armv.S 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/kernel/entry-armv.S 2015-03-15 16:03:03.672094877 -0500 @@ -207,11 +207,18 @@ #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 @@ -226,6 +233,8 @@ 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 #endif diff -Nur linux-3.18.9.orig/arch/arm/kernel/process.c linux-3.18.9/arch/arm/kernel/process.c --- linux-3.18.9.orig/arch/arm/kernel/process.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/kernel/process.c 2015-03-15 16:03:03.672094877 -0500 @@ -431,6 +431,30 @@ } #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-3.18.9.orig/arch/arm/kernel/signal.c linux-3.18.9/arch/arm/kernel/signal.c --- linux-3.18.9.orig/arch/arm/kernel/signal.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/kernel/signal.c 2015-03-15 16:03:03.672094877 -0500 @@ -574,7 +574,8 @@ 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-3.18.9.orig/arch/arm/kernel/smp.c linux-3.18.9/arch/arm/kernel/smp.c --- linux-3.18.9.orig/arch/arm/kernel/smp.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/kernel/smp.c 2015-03-15 16:03:03.672094877 -0500 @@ -506,12 +506,14 @@ } #ifdef CONFIG_IRQ_WORK +#ifndef CONFIG_PREEMPT_RT_FULL void arch_irq_work_raise(void) { if (arch_irq_work_has_interrupt()) smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK); } #endif +#endif #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST void tick_broadcast(const struct cpumask *mask) diff -Nur linux-3.18.9.orig/arch/arm/kernel/unwind.c linux-3.18.9/arch/arm/kernel/unwind.c --- linux-3.18.9.orig/arch/arm/kernel/unwind.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/kernel/unwind.c 2015-03-15 16:03:03.672094877 -0500 @@ -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); @@ -530,9 +530,9 @@ 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; } @@ -544,9 +544,9 @@ 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-3.18.9.orig/arch/arm/mach-at91/at91rm9200_time.c linux-3.18.9/arch/arm/mach-at91/at91rm9200_time.c --- linux-3.18.9.orig/arch/arm/mach-at91/at91rm9200_time.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/mach-at91/at91rm9200_time.c 2015-03-15 16:03:03.672094877 -0500 @@ -135,6 +135,7 @@ 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-3.18.9.orig/arch/arm/mach-exynos/platsmp.c linux-3.18.9/arch/arm/mach-exynos/platsmp.c --- linux-3.18.9.orig/arch/arm/mach-exynos/platsmp.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/mach-exynos/platsmp.c 2015-03-15 16:03:03.672094877 -0500 @@ -137,7 +137,7 @@ 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) { @@ -150,8 +150,8 @@ /* * 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) @@ -165,7 +165,7 @@ * 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 @@ -192,7 +192,7 @@ if (timeout == 0) { printk(KERN_ERR "cpu1 power enable failed"); - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return -ETIMEDOUT; } } @@ -242,7 +242,7 @@ * 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-3.18.9.orig/arch/arm/mach-hisi/platmcpm.c linux-3.18.9/arch/arm/mach-hisi/platmcpm.c --- linux-3.18.9.orig/arch/arm/mach-hisi/platmcpm.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/mach-hisi/platmcpm.c 2015-03-15 16:03:03.672094877 -0500 @@ -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-3.18.9.orig/arch/arm/mach-omap2/omap-smp.c linux-3.18.9/arch/arm/mach-omap2/omap-smp.c --- linux-3.18.9.orig/arch/arm/mach-omap2/omap-smp.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/mach-omap2/omap-smp.c 2015-03-15 16:03:03.672094877 -0500 @@ -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-3.18.9.orig/arch/arm/mach-prima2/platsmp.c linux-3.18.9/arch/arm/mach-prima2/platsmp.c --- linux-3.18.9.orig/arch/arm/mach-prima2/platsmp.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/mach-prima2/platsmp.c 2015-03-15 16:03:03.676094877 -0500 @@ -23,7 +23,7 @@ static void __iomem *scu_base; static void __iomem *rsc_base; -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static struct map_desc scu_io_desc __initdata = { .length = SZ_4K, @@ -56,8 +56,8 @@ /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } static struct of_device_id rsc_ids[] = { @@ -95,7 +95,7 @@ /* 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 @@ -127,7 +127,7 @@ * 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-3.18.9.orig/arch/arm/mach-qcom/platsmp.c linux-3.18.9/arch/arm/mach-qcom/platsmp.c --- linux-3.18.9.orig/arch/arm/mach-qcom/platsmp.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/mach-qcom/platsmp.c 2015-03-15 16:03:03.676094877 -0500 @@ -46,7 +46,7 @@ extern void secondary_startup(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-3.18.9.orig/arch/arm/mach-spear/platsmp.c linux-3.18.9/arch/arm/mach-spear/platsmp.c --- linux-3.18.9.orig/arch/arm/mach-spear/platsmp.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/mach-spear/platsmp.c 2015-03-15 16:03:03.676094877 -0500 @@ -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-3.18.9.orig/arch/arm/mach-sti/platsmp.c linux-3.18.9/arch/arm/mach-sti/platsmp.c --- linux-3.18.9.orig/arch/arm/mach-sti/platsmp.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/mach-sti/platsmp.c 2015-03-15 16:03:03.676094877 -0500 @@ -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-3.18.9.orig/arch/arm/mach-ux500/platsmp.c linux-3.18.9/arch/arm/mach-ux500/platsmp.c --- linux-3.18.9.orig/arch/arm/mach-ux500/platsmp.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/mach-ux500/platsmp.c 2015-03-15 16:03:03.676094877 -0500 @@ -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-3.18.9.orig/arch/arm/mm/fault.c linux-3.18.9/arch/arm/mm/fault.c --- linux-3.18.9.orig/arch/arm/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/mm/fault.c 2015-03-15 16:03:03.676094877 -0500 @@ -277,7 +277,7 @@ * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto no_context; if (user_mode(regs)) @@ -431,6 +431,9 @@ 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; @@ -498,6 +501,9 @@ 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-3.18.9.orig/arch/arm/mm/highmem.c linux-3.18.9/arch/arm/mm/highmem.c --- linux-3.18.9.orig/arch/arm/mm/highmem.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/mm/highmem.c 2015-03-15 16:03:03.676094877 -0500 @@ -53,6 +53,7 @@ void *kmap_atomic(struct page *page) { + pte_t pte = mk_pte(page, kmap_prot); unsigned int idx; unsigned long vaddr; void *kmap; @@ -91,7 +92,10 @@ * 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; } @@ -108,12 +112,15 @@ 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() */ @@ -125,6 +132,7 @@ 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); @@ -139,7 +147,10 @@ #ifdef CONFIG_DEBUG_HIGHMEM BUG_ON(!pte_none(*(fixmap_page_table + idx))); #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; } @@ -153,3 +164,28 @@ 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-3.18.9.orig/arch/arm/plat-versatile/platsmp.c linux-3.18.9/arch/arm/plat-versatile/platsmp.c --- linux-3.18.9.orig/arch/arm/plat-versatile/platsmp.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm/plat-versatile/platsmp.c 2015-03-15 16:03:03.676094877 -0500 @@ -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-3.18.9.orig/arch/arm64/kernel/smp.c linux-3.18.9/arch/arm64/kernel/smp.c --- linux-3.18.9.orig/arch/arm64/kernel/smp.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/arm64/kernel/smp.c 2015-03-15 16:03:03.676094877 -0500 @@ -529,12 +529,14 @@ } #ifdef CONFIG_IRQ_WORK +#ifndef CONFIG_PREEMPT_RT_FULL void arch_irq_work_raise(void) { if (__smp_cross_call) smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK); } #endif +#endif static DEFINE_RAW_SPINLOCK(stop_lock); diff -Nur linux-3.18.9.orig/arch/avr32/mm/fault.c linux-3.18.9/arch/avr32/mm/fault.c --- linux-3.18.9.orig/arch/avr32/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/avr32/mm/fault.c 2015-03-15 16:03:03.676094877 -0500 @@ -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 (!mm || regs->sr & SYSREG_BIT(GM) || pagefault_disabled()) goto no_context; local_irq_enable(); diff -Nur linux-3.18.9.orig/arch/cris/mm/fault.c linux-3.18.9/arch/cris/mm/fault.c --- linux-3.18.9.orig/arch/cris/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/cris/mm/fault.c 2015-03-15 16:03:03.676094877 -0500 @@ -113,7 +113,7 @@ * user context, we must not take the fault. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto no_context; if (user_mode(regs)) diff -Nur linux-3.18.9.orig/arch/frv/mm/fault.c linux-3.18.9/arch/frv/mm/fault.c --- linux-3.18.9.orig/arch/frv/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/frv/mm/fault.c 2015-03-15 16:03:03.676094877 -0500 @@ -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 (!mm || pagefault_disabled()) goto no_context; if (user_mode(__frame)) diff -Nur linux-3.18.9.orig/arch/ia64/mm/fault.c linux-3.18.9/arch/ia64/mm/fault.c --- linux-3.18.9.orig/arch/ia64/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/ia64/mm/fault.c 2015-03-15 16:03:03.676094877 -0500 @@ -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 (!mm || pagefault_disabled()) goto no_context; #ifdef CONFIG_VIRTUAL_MEM_MAP diff -Nur linux-3.18.9.orig/arch/Kconfig linux-3.18.9/arch/Kconfig --- linux-3.18.9.orig/arch/Kconfig 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/Kconfig 2015-03-15 16:03:03.676094877 -0500 @@ -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 diff -Nur linux-3.18.9.orig/arch/m32r/mm/fault.c linux-3.18.9/arch/m32r/mm/fault.c --- linux-3.18.9.orig/arch/m32r/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/m32r/mm/fault.c 2015-03-15 16:03:03.676094877 -0500 @@ -114,7 +114,7 @@ * If we're in an interrupt or have no user context or are running in an * atomic region then we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto bad_area_nosemaphore; if (error_code & ACE_USERMODE) diff -Nur linux-3.18.9.orig/arch/m68k/mm/fault.c linux-3.18.9/arch/m68k/mm/fault.c --- linux-3.18.9.orig/arch/m68k/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/m68k/mm/fault.c 2015-03-15 16:03:03.676094877 -0500 @@ -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 (!mm || pagefault_disabled()) goto no_context; if (user_mode(regs)) diff -Nur linux-3.18.9.orig/arch/microblaze/mm/fault.c linux-3.18.9/arch/microblaze/mm/fault.c --- linux-3.18.9.orig/arch/microblaze/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/microblaze/mm/fault.c 2015-03-15 16:03:03.676094877 -0500 @@ -107,7 +107,7 @@ if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11) is_write = 0; - if (unlikely(in_atomic() || !mm)) { + if (unlikely(!mm || pagefault_disabled())) { if (kernel_mode(regs)) goto bad_area_nosemaphore; diff -Nur linux-3.18.9.orig/arch/mips/Kconfig linux-3.18.9/arch/mips/Kconfig --- linux-3.18.9.orig/arch/mips/Kconfig 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/mips/Kconfig 2015-03-15 16:03:03.676094877 -0500 @@ -2196,7 +2196,7 @@ # 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-3.18.9.orig/arch/mips/kernel/signal.c linux-3.18.9/arch/mips/kernel/signal.c --- linux-3.18.9.orig/arch/mips/kernel/signal.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/mips/kernel/signal.c 2015-03-15 16:03:03.676094877 -0500 @@ -613,6 +613,7 @@ __u32 thread_info_flags) { local_irq_enable(); + preempt_check_resched(); user_exit(); diff -Nur linux-3.18.9.orig/arch/mips/mm/fault.c linux-3.18.9/arch/mips/mm/fault.c --- linux-3.18.9.orig/arch/mips/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/mips/mm/fault.c 2015-03-15 16:03:03.676094877 -0500 @@ -89,7 +89,7 @@ * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto bad_area_nosemaphore; if (user_mode(regs)) diff -Nur linux-3.18.9.orig/arch/mips/mm/init.c linux-3.18.9/arch/mips/mm/init.c --- linux-3.18.9.orig/arch/mips/mm/init.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/mips/mm/init.c 2015-03-15 16:03:03.676094877 -0500 @@ -90,7 +90,7 @@ BUG_ON(Page_dcache_dirty(page)); - pagefault_disable(); + raw_pagefault_disable(); idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1); idx += in_interrupt() ? FIX_N_COLOURS : 0; vaddr = __fix_to_virt(FIX_CMAP_END - idx); @@ -146,7 +146,7 @@ tlbw_use_hazard(); write_c0_entryhi(old_ctx); local_irq_restore(flags); - pagefault_enable(); + raw_pagefault_enable(); } void copy_user_highpage(struct page *to, struct page *from, diff -Nur linux-3.18.9.orig/arch/mn10300/mm/fault.c linux-3.18.9/arch/mn10300/mm/fault.c --- linux-3.18.9.orig/arch/mn10300/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/mn10300/mm/fault.c 2015-03-15 16:03:03.676094877 -0500 @@ -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 (!mm || pagefault_disabled()) goto no_context; if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR) diff -Nur linux-3.18.9.orig/arch/parisc/mm/fault.c linux-3.18.9/arch/parisc/mm/fault.c --- linux-3.18.9.orig/arch/parisc/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/parisc/mm/fault.c 2015-03-15 16:03:03.676094877 -0500 @@ -207,7 +207,7 @@ int fault; unsigned int flags; - if (in_atomic()) + if (pagefault_disabled()) goto no_context; tsk = current; diff -Nur linux-3.18.9.orig/arch/powerpc/include/asm/thread_info.h linux-3.18.9/arch/powerpc/include/asm/thread_info.h --- linux-3.18.9.orig/arch/powerpc/include/asm/thread_info.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/powerpc/include/asm/thread_info.h 2015-03-15 16:03:03.676094877 -0500 @@ -43,6 +43,8 @@ int cpu; /* cpu we're on */ int preempt_count; /* 0 => preemptable, <0 => BUG */ + int preempt_lazy_count; /* 0 => preemptable, + <0 => BUG */ struct restart_block restart_block; unsigned long local_flags; /* private flags for thread */ @@ -88,8 +90,7 @@ #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 */ @@ -107,6 +108,8 @@ #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-3.18.9.orig/arch/powerpc/kernel/misc_32.S linux-3.18.9/arch/powerpc/kernel/misc_32.S --- linux-3.18.9.orig/arch/powerpc/kernel/misc_32.S 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/powerpc/kernel/misc_32.S 2015-03-15 16:03:03.680094877 -0500 @@ -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-3.18.9.orig/arch/powerpc/kernel/misc_64.S linux-3.18.9/arch/powerpc/kernel/misc_64.S --- linux-3.18.9.orig/arch/powerpc/kernel/misc_64.S 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/powerpc/kernel/misc_64.S 2015-03-15 16:03:03.680094877 -0500 @@ -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-3.18.9.orig/arch/powerpc/kernel/time.c linux-3.18.9/arch/powerpc/kernel/time.c --- linux-3.18.9.orig/arch/powerpc/kernel/time.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/powerpc/kernel/time.c 2015-03-15 16:03:03.680094877 -0500 @@ -424,7 +424,7 @@ EXPORT_SYMBOL(profile_pc); #endif -#ifdef CONFIG_IRQ_WORK +#if defined(CONFIG_IRQ_WORK) && !defined(CONFIG_PREEMPT_RT_FULL) /* * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable... diff -Nur linux-3.18.9.orig/arch/powerpc/mm/fault.c linux-3.18.9/arch/powerpc/mm/fault.c --- linux-3.18.9.orig/arch/powerpc/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/powerpc/mm/fault.c 2015-03-15 16:03:03.680094877 -0500 @@ -273,7 +273,7 @@ if (!arch_irq_disabled_regs(regs)) local_irq_enable(); - if (in_atomic() || mm == NULL) { + if (in_atomic() || mm == NULL || pagefault_disabled()) { if (!user_mode(regs)) { rc = SIGSEGV; goto bail; diff -Nur linux-3.18.9.orig/arch/s390/mm/fault.c linux-3.18.9/arch/s390/mm/fault.c --- linux-3.18.9.orig/arch/s390/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/s390/mm/fault.c 2015-03-15 16:03:03.680094877 -0500 @@ -435,7 +435,8 @@ * user context. */ fault = VM_FAULT_BADCONTEXT; - if (unlikely(!user_space_fault(regs) || in_atomic() || !mm)) + if (unlikely(!user_space_fault(regs) || !mm || + tsk->pagefault_disabled)) goto out; address = trans_exc_code & __FAIL_ADDR_MASK; diff -Nur linux-3.18.9.orig/arch/score/mm/fault.c linux-3.18.9/arch/score/mm/fault.c --- linux-3.18.9.orig/arch/score/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/score/mm/fault.c 2015-03-15 16:03:03.680094877 -0500 @@ -73,7 +73,7 @@ * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto bad_area_nosemaphore; if (user_mode(regs)) diff -Nur linux-3.18.9.orig/arch/sh/kernel/irq.c linux-3.18.9/arch/sh/kernel/irq.c --- linux-3.18.9.orig/arch/sh/kernel/irq.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/sh/kernel/irq.c 2015-03-15 16:03:03.680094877 -0500 @@ -149,6 +149,7 @@ hardirq_ctx[cpu] = NULL; } +#ifndef CONFIG_PREEMPT_RT_FULL void do_softirq_own_stack(void) { struct thread_info *curctx; @@ -176,6 +177,7 @@ "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr" ); } +#endif #else static inline void handle_one_irq(unsigned int irq) { diff -Nur linux-3.18.9.orig/arch/sh/mm/fault.c linux-3.18.9/arch/sh/mm/fault.c --- linux-3.18.9.orig/arch/sh/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/sh/mm/fault.c 2015-03-15 16:03:03.680094877 -0500 @@ -440,7 +440,7 @@ * If we're in an interrupt, have no user context or are running * in an atomic region then we must not take the fault: */ - if (unlikely(in_atomic() || !mm)) { + if (unlikely(!mm || pagefault_disabled())) { bad_area_nosemaphore(regs, error_code, address); return; } diff -Nur linux-3.18.9.orig/arch/sparc/Kconfig linux-3.18.9/arch/sparc/Kconfig --- linux-3.18.9.orig/arch/sparc/Kconfig 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/sparc/Kconfig 2015-03-15 16:03:03.680094877 -0500 @@ -182,12 +182,10 @@ 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 @@ -528,6 +526,10 @@ source "fs/Kconfig.binfmt" +config EARLY_PRINTK + bool + default y + config COMPAT bool depends on SPARC64 diff -Nur linux-3.18.9.orig/arch/sparc/kernel/irq_64.c linux-3.18.9/arch/sparc/kernel/irq_64.c --- linux-3.18.9.orig/arch/sparc/kernel/irq_64.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/sparc/kernel/irq_64.c 2015-03-15 16:03:03.680094877 -0500 @@ -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-3.18.9.orig/arch/sparc/kernel/pcr.c linux-3.18.9/arch/sparc/kernel/pcr.c --- linux-3.18.9.orig/arch/sparc/kernel/pcr.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/sparc/kernel/pcr.c 2015-03-15 16:03:03.684094876 -0500 @@ -43,10 +43,12 @@ set_irq_regs(old_regs); } +#ifndef CONFIG_PREEMPT_RT_FULL void arch_irq_work_raise(void) { set_softint(1 << PIL_DEFERRED_PCR_WORK); } +#endif const struct pcr_ops *pcr_ops; EXPORT_SYMBOL_GPL(pcr_ops); diff -Nur linux-3.18.9.orig/arch/sparc/kernel/setup_32.c linux-3.18.9/arch/sparc/kernel/setup_32.c --- linux-3.18.9.orig/arch/sparc/kernel/setup_32.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/sparc/kernel/setup_32.c 2015-03-15 16:03:03.684094876 -0500 @@ -309,6 +309,7 @@ boot_flags_init(*cmdline_p); + early_console = &prom_early_console; register_console(&prom_early_console); printk("ARCH: "); diff -Nur linux-3.18.9.orig/arch/sparc/kernel/setup_64.c linux-3.18.9/arch/sparc/kernel/setup_64.c --- linux-3.18.9.orig/arch/sparc/kernel/setup_64.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/sparc/kernel/setup_64.c 2015-03-15 16:03:03.684094876 -0500 @@ -563,6 +563,12 @@ pause_patch(); } +static inline void register_prom_console(void) +{ + early_console = &prom_early_console; + register_console(&prom_early_console); +} + void __init setup_arch(char **cmdline_p) { /* Initialize PROM console and command line. */ @@ -574,7 +580,7 @@ #ifdef CONFIG_EARLYFB if (btext_find_display()) #endif - register_console(&prom_early_console); + register_prom_console(); if (tlb_type == hypervisor) printk("ARCH: SUN4V\n"); diff -Nur linux-3.18.9.orig/arch/sparc/mm/fault_32.c linux-3.18.9/arch/sparc/mm/fault_32.c --- linux-3.18.9.orig/arch/sparc/mm/fault_32.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/sparc/mm/fault_32.c 2015-03-15 16:03:03.684094876 -0500 @@ -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 (!mm || pagefault_disabled()) goto no_context; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); diff -Nur linux-3.18.9.orig/arch/sparc/mm/fault_64.c linux-3.18.9/arch/sparc/mm/fault_64.c --- linux-3.18.9.orig/arch/sparc/mm/fault_64.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/sparc/mm/fault_64.c 2015-03-15 16:03:03.684094876 -0500 @@ -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 (!mm || pagefault_disabled()) goto intr_or_no_mm; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); diff -Nur linux-3.18.9.orig/arch/tile/mm/fault.c linux-3.18.9/arch/tile/mm/fault.c --- linux-3.18.9.orig/arch/tile/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/tile/mm/fault.c 2015-03-15 16:03:03.684094876 -0500 @@ -357,7 +357,7 @@ * If we're in an interrupt, have no user context or are running in an * atomic region then we must not take the fault. */ - if (in_atomic() || !mm) { + if (!mm || pagefault_disabled()) { vma = NULL; /* happy compiler */ goto bad_area_nosemaphore; } diff -Nur linux-3.18.9.orig/arch/um/kernel/trap.c linux-3.18.9/arch/um/kernel/trap.c --- linux-3.18.9.orig/arch/um/kernel/trap.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/um/kernel/trap.c 2015-03-15 16:03:03.684094876 -0500 @@ -38,7 +38,7 @@ * If the fault was during atomic operation, don't take the fault, just * fail. */ - if (in_atomic()) + if (pagefault_disabled()) goto out_nosemaphore; if (is_user) diff -Nur linux-3.18.9.orig/arch/x86/crypto/aesni-intel_glue.c linux-3.18.9/arch/x86/crypto/aesni-intel_glue.c --- linux-3.18.9.orig/arch/x86/crypto/aesni-intel_glue.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/crypto/aesni-intel_glue.c 2015-03-15 16:03:03.684094876 -0500 @@ -381,14 +381,14 @@ 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; } @@ -405,14 +405,14 @@ 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; } @@ -429,14 +429,14 @@ 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; } @@ -453,14 +453,14 @@ 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; } @@ -512,18 +512,20 @@ 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-3.18.9.orig/arch/x86/crypto/cast5_avx_glue.c linux-3.18.9/arch/x86/crypto/cast5_avx_glue.c --- linux-3.18.9.orig/arch/x86/crypto/cast5_avx_glue.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/crypto/cast5_avx_glue.c 2015-03-15 16:03:03.684094876 -0500 @@ -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-3.18.9.orig/arch/x86/crypto/glue_helper.c linux-3.18.9/arch/x86/crypto/glue_helper.c --- linux-3.18.9.orig/arch/x86/crypto/glue_helper.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/crypto/glue_helper.c 2015-03-15 16:03:03.684094876 -0500 @@ -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); @@ -278,7 +278,7 @@ 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; @@ -287,13 +287,12 @@ 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); @@ -348,7 +347,7 @@ 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; @@ -361,21 +360,21 @@ /* 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-3.18.9.orig/arch/x86/include/asm/preempt.h linux-3.18.9/arch/x86/include/asm/preempt.h --- linux-3.18.9.orig/arch/x86/include/asm/preempt.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/include/asm/preempt.h 2015-03-15 16:03:03.684094876 -0500 @@ -85,17 +85,33 @@ * 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 + 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(void) { +#ifdef CONFIG_PREEMPT_LAZY + return unlikely(!raw_cpu_read_4(__preempt_count) || \ + test_thread_flag(TIF_NEED_RESCHED_LAZY)); +#else return unlikely(!raw_cpu_read_4(__preempt_count)); +#endif } #ifdef CONFIG_PREEMPT diff -Nur linux-3.18.9.orig/arch/x86/include/asm/signal.h linux-3.18.9/arch/x86/include/asm/signal.h --- linux-3.18.9.orig/arch/x86/include/asm/signal.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/include/asm/signal.h 2015-03-15 16:03:03.684094876 -0500 @@ -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) && defined(CONFIG_X86_64) +#define ARCH_RT_DELAYS_SIGNAL_SEND +#endif + #ifndef CONFIG_COMPAT typedef sigset_t compat_sigset_t; #endif diff -Nur linux-3.18.9.orig/arch/x86/include/asm/stackprotector.h linux-3.18.9/arch/x86/include/asm/stackprotector.h --- linux-3.18.9.orig/arch/x86/include/asm/stackprotector.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/include/asm/stackprotector.h 2015-03-15 16:03:03.684094876 -0500 @@ -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-3.18.9.orig/arch/x86/include/asm/thread_info.h linux-3.18.9/arch/x86/include/asm/thread_info.h --- linux-3.18.9.orig/arch/x86/include/asm/thread_info.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/include/asm/thread_info.h 2015-03-15 16:03:03.684094876 -0500 @@ -30,6 +30,8 @@ __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; struct restart_block restart_block; void __user *sysenter_return; @@ -75,6 +77,7 @@ #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_MCE_NOTIFY 10 /* notify userspace of an MCE */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_UPROBE 12 /* breakpointed or singlestepping */ @@ -100,6 +103,7 @@ #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_MCE_NOTIFY (1 << TIF_MCE_NOTIFY) #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_UPROBE (1 << TIF_UPROBE) @@ -150,6 +154,8 @@ #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) #define KERNEL_STACK_OFFSET (5*(BITS_PER_LONG/8)) diff -Nur linux-3.18.9.orig/arch/x86/include/asm/uv/uv_bau.h linux-3.18.9/arch/x86/include/asm/uv/uv_bau.h --- linux-3.18.9.orig/arch/x86/include/asm/uv/uv_bau.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/include/asm/uv/uv_bau.h 2015-03-15 16:03:03.684094876 -0500 @@ -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-3.18.9.orig/arch/x86/include/asm/uv/uv_hub.h linux-3.18.9/arch/x86/include/asm/uv/uv_hub.h --- linux-3.18.9.orig/arch/x86/include/asm/uv/uv_hub.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/include/asm/uv/uv_hub.h 2015-03-15 16:03:03.684094876 -0500 @@ -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-3.18.9.orig/arch/x86/Kconfig linux-3.18.9/arch/x86/Kconfig --- linux-3.18.9.orig/arch/x86/Kconfig 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/Kconfig 2015-03-15 16:03:03.684094876 -0500 @@ -21,6 +21,7 @@ ### Arch settings config X86 def_bool y + select HAVE_PREEMPT_LAZY if X86_32 select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_FAST_MULTIPLIER @@ -197,8 +198,11 @@ 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 @@ -811,7 +815,7 @@ 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-3.18.9.orig/arch/x86/kernel/apic/io_apic.c linux-3.18.9/arch/x86/kernel/apic/io_apic.c --- linux-3.18.9.orig/arch/x86/kernel/apic/io_apic.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/kernel/apic/io_apic.c 2015-03-15 16:03:03.688094875 -0500 @@ -2494,7 +2494,8 @@ 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-3.18.9.orig/arch/x86/kernel/apic/x2apic_uv_x.c linux-3.18.9/arch/x86/kernel/apic/x2apic_uv_x.c --- linux-3.18.9.orig/arch/x86/kernel/apic/x2apic_uv_x.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/kernel/apic/x2apic_uv_x.c 2015-03-15 16:03:03.688094875 -0500 @@ -918,7 +918,7 @@ 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-3.18.9.orig/arch/x86/kernel/asm-offsets.c linux-3.18.9/arch/x86/kernel/asm-offsets.c --- linux-3.18.9.orig/arch/x86/kernel/asm-offsets.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/kernel/asm-offsets.c 2015-03-15 16:03:03.688094875 -0500 @@ -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-3.18.9.orig/arch/x86/kernel/cpu/mcheck/mce.c linux-3.18.9/arch/x86/kernel/cpu/mcheck/mce.c --- linux-3.18.9.orig/arch/x86/kernel/cpu/mcheck/mce.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/kernel/cpu/mcheck/mce.c 2015-03-15 16:03:03.688094875 -0500 @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -41,6 +42,7 @@ #include #include #include +#include #include #include @@ -1266,7 +1268,7 @@ static unsigned long check_interval = 5 * 60; /* 5 minutes */ 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) { @@ -1283,14 +1285,11 @@ return test_and_clear_bit(0, v); } -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); unsigned long iv; int notify; - WARN_ON(smp_processor_id() != data); - if (mce_available(this_cpu_ptr(&cpu_info))) { machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_poll_banks)); @@ -1313,9 +1312,11 @@ __this_cpu_write(mce_next_interval, iv); /* Might have become 0 after CMCI storm subsided */ if (iv) { - t->expires = jiffies + iv; - add_timer_on(t, smp_processor_id()); + hrtimer_forward_now(timer, ns_to_ktime( + jiffies_to_usecs(iv) * 1000ULL)); + return HRTIMER_RESTART; } + return HRTIMER_NORESTART; } /* @@ -1323,28 +1324,37 @@ */ void mce_timer_kick(unsigned long interval) { - struct timer_list *t = this_cpu_ptr(&mce_timer); - unsigned long when = jiffies + interval; + struct hrtimer *t = this_cpu_ptr(&mce_timer); unsigned long iv = __this_cpu_read(mce_next_interval); - if (timer_pending(t)) { - if (time_before(when, t->expires)) - mod_timer_pinned(t, when); + if (hrtimer_active(t)) { + s64 exp; + s64 intv_us; + + intv_us = jiffies_to_usecs(interval); + exp = ktime_to_us(hrtimer_expires_remaining(t)); + if (intv_us < exp) { + hrtimer_cancel(t); + hrtimer_start_range_ns(t, + ns_to_ktime(intv_us * 1000), + 0, HRTIMER_MODE_REL_PINNED); + } } else { - t->expires = round_jiffies(when); - add_timer_on(t, smp_processor_id()); + hrtimer_start_range_ns(t, + ns_to_ktime(jiffies_to_usecs(interval) * 1000ULL), + 0, HRTIMER_MODE_REL_PINNED); } if (interval < iv) __this_cpu_write(mce_next_interval, interval); } -/* Must not be called in IRQ context where del_timer_sync() can deadlock */ +/* Must not be called in IRQ context where hrtimer_cancel() can deadlock */ static void mce_timer_delete_all(void) { int cpu; for_each_online_cpu(cpu) - del_timer_sync(&per_cpu(mce_timer, cpu)); + hrtimer_cancel(&per_cpu(mce_timer, cpu)); } static void mce_do_trigger(struct work_struct *work) @@ -1354,6 +1364,68 @@ static DECLARE_WORK(mce_trigger_work, mce_do_trigger); +static void __mce_notify_work(void) +{ + /* Not more than two messages every minute */ + static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); + + /* wake processes polling /dev/mcelog */ + wake_up_interruptible(&mce_chrdev_wait); + + /* + * There is no risk of missing notifications because + * work_pending is always cleared before the function is + * executed. + */ + if (mce_helper[0] && !work_pending(&mce_trigger_work)) + schedule_work(&mce_trigger_work); + + if (__ratelimit(&ratelimit)) + pr_info(HW_ERR "Machine check events logged\n"); +} + +#ifdef CONFIG_PREEMPT_RT_FULL +struct task_struct *mce_notify_helper; + +static int mce_notify_helper_thread(void *unused) +{ + while (1) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + if (kthread_should_stop()) + break; + __mce_notify_work(); + } + return 0; +} + +static int mce_notify_work_init(void) +{ + mce_notify_helper = kthread_run(mce_notify_helper_thread, NULL, + "mce-notify"); + if (!mce_notify_helper) + return -ENOMEM; + + return 0; +} + +static void mce_notify_work(void) +{ + if (WARN_ON_ONCE(!mce_notify_helper)) { + pr_info(HW_ERR "Machine check event before MCE init; ignored\n"); + return; + } + + wake_up_process(mce_notify_helper); +} +#else +static void mce_notify_work(void) +{ + __mce_notify_work(); +} +static inline int mce_notify_work_init(void) { return 0; } +#endif + /* * Notify the user(s) about new machine check events. * Can be called from interrupt context, but not from machine check/NMI @@ -1361,19 +1433,8 @@ */ 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; @@ -1644,7 +1705,7 @@ } } -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; @@ -1653,16 +1714,17 @@ 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); } @@ -2339,6 +2401,8 @@ 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++) { @@ -2365,6 +2429,7 @@ 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. */ @@ -2372,7 +2437,6 @@ 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: @@ -2392,11 +2456,9 @@ 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; } @@ -2471,8 +2533,15 @@ if (err) goto err_register; + err = mce_notify_work_init(); + if (err) + goto err_notify; + return 0; +err_notify: + misc_deregister(&mce_chrdev_device); + err_register: unregister_syscore_ops(&mce_syscore_ops); diff -Nur linux-3.18.9.orig/arch/x86/kernel/entry_32.S linux-3.18.9/arch/x86/kernel/entry_32.S --- linux-3.18.9.orig/arch/x86/kernel/entry_32.S 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/kernel/entry_32.S 2015-03-15 16:03:03.688094875 -0500 @@ -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 @@ -591,7 +607,7 @@ 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 @@ -604,7 +620,7 @@ 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-3.18.9.orig/arch/x86/kernel/entry_64.S linux-3.18.9/arch/x86/kernel/entry_64.S --- linux-3.18.9.orig/arch/x86/kernel/entry_64.S 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/kernel/entry_64.S 2015-03-15 16:03:03.688094875 -0500 @@ -451,8 +451,8 @@ /* Handle reschedules */ /* edx: work, edi: workmask */ sysret_careful: - bt $TIF_NEED_RESCHED,%edx - jnc sysret_signal + testl $_TIF_NEED_RESCHED_MASK,%edx + jz sysret_signal TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi @@ -551,8 +551,8 @@ /* 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 @@ -867,8 +867,8 @@ /* 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 @@ -900,7 +900,22 @@ /* rcx: threadinfo. interrupts off. */ ENTRY(retint_kernel) cmpl $0,PER_CPU_VAR(__preempt_count) +#ifndef CONFIG_PREEMPT_LAZY jnz retint_restore_args +#else + jz check_int_off + + # atleast preempt count == 0 ? + cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) + jnz retint_restore_args + + cmpl $0, TI_preempt_lazy_count(%rcx) + jnz retint_restore_args + + bt $TIF_NEED_RESCHED_LAZY,TI_flags(%rcx) + jnc retint_restore_args +check_int_off: +#endif bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ jnc retint_restore_args call preempt_schedule_irq @@ -1116,6 +1131,7 @@ jmp 2b .previous +#ifndef CONFIG_PREEMPT_RT_FULL /* Call softirq on interrupt stack. Interrupts are off. */ ENTRY(do_softirq_own_stack) CFI_STARTPROC @@ -1135,6 +1151,7 @@ ret CFI_ENDPROC END(do_softirq_own_stack) +#endif #ifdef CONFIG_XEN idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 @@ -1299,7 +1316,7 @@ movq %rsp,%rdi /* &pt_regs */ call sync_regs movq %rax,%rsp /* switch stack for scheduling */ - testl $_TIF_NEED_RESCHED,%ebx + testl $_TIF_NEED_RESCHED_MASK,%ebx jnz paranoid_schedule movl %ebx,%edx /* arg3: thread flags */ TRACE_IRQS_ON diff -Nur linux-3.18.9.orig/arch/x86/kernel/irq_32.c linux-3.18.9/arch/x86/kernel/irq_32.c --- linux-3.18.9.orig/arch/x86/kernel/irq_32.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/kernel/irq_32.c 2015-03-15 16:03:03.688094875 -0500 @@ -142,6 +142,7 @@ 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; @@ -160,6 +161,7 @@ call_on_stack(__do_softirq, isp); } +#endif bool handle_irq(unsigned irq, struct pt_regs *regs) { diff -Nur linux-3.18.9.orig/arch/x86/kernel/irq_work.c linux-3.18.9/arch/x86/kernel/irq_work.c --- linux-3.18.9.orig/arch/x86/kernel/irq_work.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/kernel/irq_work.c 2015-03-15 16:03:03.688094875 -0500 @@ -38,6 +38,7 @@ exiting_irq(); } +#ifndef CONFIG_PREEMPT_RT_FULL void arch_irq_work_raise(void) { #ifdef CONFIG_X86_LOCAL_APIC @@ -48,3 +49,4 @@ apic_wait_icr_idle(); #endif } +#endif diff -Nur linux-3.18.9.orig/arch/x86/kernel/process_32.c linux-3.18.9/arch/x86/kernel/process_32.c --- linux-3.18.9.orig/arch/x86/kernel/process_32.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/kernel/process_32.c 2015-03-15 16:03:03.688094875 -0500 @@ -35,6 +35,7 @@ #include #include #include +#include #include #include @@ -214,6 +215,35 @@ } 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. @@ -301,6 +331,8 @@ 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-3.18.9.orig/arch/x86/kernel/signal.c linux-3.18.9/arch/x86/kernel/signal.c --- linux-3.18.9.orig/arch/x86/kernel/signal.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/kernel/signal.c 2015-03-15 16:03:03.688094875 -0500 @@ -746,6 +746,14 @@ mce_notify_process(); #endif /* CONFIG_X86_64 && CONFIG_X86_MCE */ +#ifdef ARCH_RT_DELAYS_SIGNAL_SEND + if (unlikely(current->forced_info.si_signo)) { + struct task_struct *t = current; + force_sig_info(t->forced_info.si_signo, &t->forced_info, t); + t->forced_info.si_signo = 0; + } +#endif + if (thread_info_flags & _TIF_UPROBE) uprobe_notify_resume(regs); diff -Nur linux-3.18.9.orig/arch/x86/kernel/traps.c linux-3.18.9/arch/x86/kernel/traps.c --- linux-3.18.9.orig/arch/x86/kernel/traps.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/kernel/traps.c 2015-03-15 16:03:03.688094875 -0500 @@ -87,9 +87,21 @@ local_irq_enable(); } -static inline void preempt_conditional_sti(struct pt_regs *regs) +static inline void conditional_sti_ist(struct pt_regs *regs) { +#ifdef CONFIG_X86_64 + /* + * X86_64 uses a per CPU stack on the IST for certain traps + * like int3. The task can not be preempted when using one + * of these stacks, thus preemption must be disabled, otherwise + * the stack can be corrupted if the task is scheduled out, + * and another task comes in and uses this stack. + * + * On x86_32 the task keeps its own stack and it is OK if the + * task schedules out. + */ preempt_count_inc(); +#endif if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); } @@ -100,11 +112,13 @@ local_irq_disable(); } -static inline void preempt_conditional_cli(struct pt_regs *regs) +static inline void conditional_cli_ist(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) local_irq_disable(); +#ifdef CONFIG_X86_64 preempt_count_dec(); +#endif } static nokprobe_inline int @@ -372,9 +386,9 @@ * as we may switch to the interrupt stack. */ debug_stack_usage_inc(); - preempt_conditional_sti(regs); + conditional_sti_ist(regs); do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); - preempt_conditional_cli(regs); + conditional_cli_ist(regs); debug_stack_usage_dec(); exit: exception_exit(prev_state); @@ -517,12 +531,12 @@ debug_stack_usage_inc(); /* It's safe to allow irq's after DR6 has been saved */ - preempt_conditional_sti(regs); + conditional_sti_ist(regs); if (regs->flags & X86_VM_MASK) { handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, X86_TRAP_DB); - preempt_conditional_cli(regs); + conditional_cli_ist(regs); debug_stack_usage_dec(); goto exit; } @@ -542,7 +556,7 @@ si_code = get_si_code(tsk->thread.debugreg6); if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) send_sigtrap(tsk, regs, error_code, si_code); - preempt_conditional_cli(regs); + conditional_cli_ist(regs); debug_stack_usage_dec(); exit: diff -Nur linux-3.18.9.orig/arch/x86/kvm/x86.c linux-3.18.9/arch/x86/kvm/x86.c --- linux-3.18.9.orig/arch/x86/kvm/x86.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/kvm/x86.c 2015-03-15 16:03:03.696094875 -0500 @@ -5773,6 +5773,13 @@ 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-3.18.9.orig/arch/x86/kvm/x86.c.orig linux-3.18.9/arch/x86/kvm/x86.c.orig --- linux-3.18.9.orig/arch/x86/kvm/x86.c.orig 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/arch/x86/kvm/x86.c.orig 2015-03-06 16:53:42.000000000 -0600 @@ -0,0 +1,7824 @@ +/* + * Kernel-based Virtual Machine driver for Linux + * + * derived from drivers/kvm/kvm_main.c + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright (C) 2008 Qumranet, Inc. + * Copyright IBM Corporation, 2008 + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * + * Authors: + * Avi Kivity + * Yaniv Kamay + * Amit Shah + * Ben-Ami Yassour + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include +#include "irq.h" +#include "mmu.h" +#include "i8254.h" +#include "tss.h" +#include "kvm_cache_regs.h" +#include "x86.h" +#include "cpuid.h" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include "trace.h" + +#include +#include +#include +#include +#include +#include +#include /* Ugh! */ +#include +#include +#include + +#define MAX_IO_MSRS 256 +#define KVM_MAX_MCE_BANKS 32 +#define KVM_MCE_CAP_SUPPORTED (MCG_CTL_P | MCG_SER_P) + +#define emul_to_vcpu(ctxt) \ + container_of(ctxt, struct kvm_vcpu, arch.emulate_ctxt) + +/* EFER defaults: + * - enable syscall per default because its emulated by KVM + * - enable LME and LMA per default on 64 bit KVM + */ +#ifdef CONFIG_X86_64 +static +u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); +#else +static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); +#endif + +#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM +#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU + +static void update_cr8_intercept(struct kvm_vcpu *vcpu); +static void process_nmi(struct kvm_vcpu *vcpu); +static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); + +struct kvm_x86_ops *kvm_x86_ops; +EXPORT_SYMBOL_GPL(kvm_x86_ops); + +static bool ignore_msrs = 0; +module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); + +unsigned int min_timer_period_us = 500; +module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); + +bool kvm_has_tsc_control; +EXPORT_SYMBOL_GPL(kvm_has_tsc_control); +u32 kvm_max_guest_tsc_khz; +EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz); + +/* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ +static u32 tsc_tolerance_ppm = 250; +module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); + +static bool backwards_tsc_observed = false; + +#define KVM_NR_SHARED_MSRS 16 + +struct kvm_shared_msrs_global { + int nr; + u32 msrs[KVM_NR_SHARED_MSRS]; +}; + +struct kvm_shared_msrs { + struct user_return_notifier urn; + bool registered; + struct kvm_shared_msr_values { + u64 host; + u64 curr; + } values[KVM_NR_SHARED_MSRS]; +}; + +static struct kvm_shared_msrs_global __read_mostly shared_msrs_global; +static struct kvm_shared_msrs __percpu *shared_msrs; + +struct kvm_stats_debugfs_item debugfs_entries[] = { + { "pf_fixed", VCPU_STAT(pf_fixed) }, + { "pf_guest", VCPU_STAT(pf_guest) }, + { "tlb_flush", VCPU_STAT(tlb_flush) }, + { "invlpg", VCPU_STAT(invlpg) }, + { "exits", VCPU_STAT(exits) }, + { "io_exits", VCPU_STAT(io_exits) }, + { "mmio_exits", VCPU_STAT(mmio_exits) }, + { "signal_exits", VCPU_STAT(signal_exits) }, + { "irq_window", VCPU_STAT(irq_window_exits) }, + { "nmi_window", VCPU_STAT(nmi_window_exits) }, + { "halt_exits", VCPU_STAT(halt_exits) }, + { "halt_wakeup", VCPU_STAT(halt_wakeup) }, + { "hypercalls", VCPU_STAT(hypercalls) }, + { "request_irq", VCPU_STAT(request_irq_exits) }, + { "irq_exits", VCPU_STAT(irq_exits) }, + { "host_state_reload", VCPU_STAT(host_state_reload) }, + { "efer_reload", VCPU_STAT(efer_reload) }, + { "fpu_reload", VCPU_STAT(fpu_reload) }, + { "insn_emulation", VCPU_STAT(insn_emulation) }, + { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) }, + { "irq_injections", VCPU_STAT(irq_injections) }, + { "nmi_injections", VCPU_STAT(nmi_injections) }, + { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) }, + { "mmu_pte_write", VM_STAT(mmu_pte_write) }, + { "mmu_pte_updated", VM_STAT(mmu_pte_updated) }, + { "mmu_pde_zapped", VM_STAT(mmu_pde_zapped) }, + { "mmu_flooded", VM_STAT(mmu_flooded) }, + { "mmu_recycled", VM_STAT(mmu_recycled) }, + { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, + { "mmu_unsync", VM_STAT(mmu_unsync) }, + { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, + { "largepages", VM_STAT(lpages) }, + { NULL } +}; + +u64 __read_mostly host_xcr0; + +static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt); + +static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) +{ + int i; + for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU); i++) + vcpu->arch.apf.gfns[i] = ~0; +} + +static void kvm_on_user_return(struct user_return_notifier *urn) +{ + unsigned slot; + struct kvm_shared_msrs *locals + = container_of(urn, struct kvm_shared_msrs, urn); + struct kvm_shared_msr_values *values; + + for (slot = 0; slot < shared_msrs_global.nr; ++slot) { + values = &locals->values[slot]; + if (values->host != values->curr) { + wrmsrl(shared_msrs_global.msrs[slot], values->host); + values->curr = values->host; + } + } + locals->registered = false; + user_return_notifier_unregister(urn); +} + +static void shared_msr_update(unsigned slot, u32 msr) +{ + u64 value; + unsigned int cpu = smp_processor_id(); + struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + + /* only read, and nobody should modify it at this time, + * so don't need lock */ + if (slot >= shared_msrs_global.nr) { + printk(KERN_ERR "kvm: invalid MSR slot!"); + return; + } + rdmsrl_safe(msr, &value); + smsr->values[slot].host = value; + smsr->values[slot].curr = value; +} + +void kvm_define_shared_msr(unsigned slot, u32 msr) +{ + BUG_ON(slot >= KVM_NR_SHARED_MSRS); + if (slot >= shared_msrs_global.nr) + shared_msrs_global.nr = slot + 1; + shared_msrs_global.msrs[slot] = msr; + /* we need ensured the shared_msr_global have been updated */ + smp_wmb(); +} +EXPORT_SYMBOL_GPL(kvm_define_shared_msr); + +static void kvm_shared_msr_cpu_online(void) +{ + unsigned i; + + for (i = 0; i < shared_msrs_global.nr; ++i) + shared_msr_update(i, shared_msrs_global.msrs[i]); +} + +int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) +{ + unsigned int cpu = smp_processor_id(); + struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + int err; + + if (((value ^ smsr->values[slot].curr) & mask) == 0) + return 0; + smsr->values[slot].curr = value; + err = wrmsrl_safe(shared_msrs_global.msrs[slot], value); + if (err) + return 1; + + if (!smsr->registered) { + smsr->urn.on_user_return = kvm_on_user_return; + user_return_notifier_register(&smsr->urn); + smsr->registered = true; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_shared_msr); + +static void drop_user_return_notifiers(void) +{ + unsigned int cpu = smp_processor_id(); + struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + + if (smsr->registered) + kvm_on_user_return(&smsr->urn); +} + +u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.apic_base; +} +EXPORT_SYMBOL_GPL(kvm_get_apic_base); + +int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + u64 old_state = vcpu->arch.apic_base & + (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); + u64 new_state = msr_info->data & + (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); + u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | + 0x2ff | (guest_cpuid_has_x2apic(vcpu) ? 0 : X2APIC_ENABLE); + + if (!msr_info->host_initiated && + ((msr_info->data & reserved_bits) != 0 || + new_state == X2APIC_ENABLE || + (new_state == MSR_IA32_APICBASE_ENABLE && + old_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) || + (new_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) && + old_state == 0))) + return 1; + + kvm_lapic_set_base(vcpu, msr_info->data); + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_apic_base); + +asmlinkage __visible void kvm_spurious_fault(void) +{ + /* Fault while not rebooting. We want the trace. */ + BUG(); +} +EXPORT_SYMBOL_GPL(kvm_spurious_fault); + +#define EXCPT_BENIGN 0 +#define EXCPT_CONTRIBUTORY 1 +#define EXCPT_PF 2 + +static int exception_class(int vector) +{ + switch (vector) { + case PF_VECTOR: + return EXCPT_PF; + case DE_VECTOR: + case TS_VECTOR: + case NP_VECTOR: + case SS_VECTOR: + case GP_VECTOR: + return EXCPT_CONTRIBUTORY; + default: + break; + } + return EXCPT_BENIGN; +} + +#define EXCPT_FAULT 0 +#define EXCPT_TRAP 1 +#define EXCPT_ABORT 2 +#define EXCPT_INTERRUPT 3 + +static int exception_type(int vector) +{ + unsigned int mask; + + if (WARN_ON(vector > 31 || vector == NMI_VECTOR)) + return EXCPT_INTERRUPT; + + mask = 1 << vector; + + /* #DB is trap, as instruction watchpoints are handled elsewhere */ + if (mask & ((1 << DB_VECTOR) | (1 << BP_VECTOR) | (1 << OF_VECTOR))) + return EXCPT_TRAP; + + if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR))) + return EXCPT_ABORT; + + /* Reserved exceptions will result in fault */ + return EXCPT_FAULT; +} + +static void kvm_multiple_exception(struct kvm_vcpu *vcpu, + unsigned nr, bool has_error, u32 error_code, + bool reinject) +{ + u32 prev_nr; + int class1, class2; + + kvm_make_request(KVM_REQ_EVENT, vcpu); + + if (!vcpu->arch.exception.pending) { + queue: + vcpu->arch.exception.pending = true; + vcpu->arch.exception.has_error_code = has_error; + vcpu->arch.exception.nr = nr; + vcpu->arch.exception.error_code = error_code; + vcpu->arch.exception.reinject = reinject; + return; + } + + /* to check exception */ + prev_nr = vcpu->arch.exception.nr; + if (prev_nr == DF_VECTOR) { + /* triple fault -> shutdown */ + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + return; + } + class1 = exception_class(prev_nr); + class2 = exception_class(nr); + if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) + || (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) { + /* generate double fault per SDM Table 5-5 */ + vcpu->arch.exception.pending = true; + vcpu->arch.exception.has_error_code = true; + vcpu->arch.exception.nr = DF_VECTOR; + vcpu->arch.exception.error_code = 0; + } else + /* replace previous exception with a new one in a hope + that instruction re-execution will regenerate lost + exception */ + goto queue; +} + +void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr) +{ + kvm_multiple_exception(vcpu, nr, false, 0, false); +} +EXPORT_SYMBOL_GPL(kvm_queue_exception); + +void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr) +{ + kvm_multiple_exception(vcpu, nr, false, 0, true); +} +EXPORT_SYMBOL_GPL(kvm_requeue_exception); + +void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) +{ + if (err) + kvm_inject_gp(vcpu, 0); + else + kvm_x86_ops->skip_emulated_instruction(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_complete_insn_gp); + +void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) +{ + ++vcpu->stat.pf_guest; + vcpu->arch.cr2 = fault->address; + kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code); +} +EXPORT_SYMBOL_GPL(kvm_inject_page_fault); + +static bool kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) +{ + if (mmu_is_nested(vcpu) && !fault->nested_page_fault) + vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault); + else + vcpu->arch.mmu.inject_page_fault(vcpu, fault); + + return fault->nested_page_fault; +} + +void kvm_inject_nmi(struct kvm_vcpu *vcpu) +{ + atomic_inc(&vcpu->arch.nmi_queued); + kvm_make_request(KVM_REQ_NMI, vcpu); +} +EXPORT_SYMBOL_GPL(kvm_inject_nmi); + +void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) +{ + kvm_multiple_exception(vcpu, nr, true, error_code, false); +} +EXPORT_SYMBOL_GPL(kvm_queue_exception_e); + +void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) +{ + kvm_multiple_exception(vcpu, nr, true, error_code, true); +} +EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); + +/* + * Checks if cpl <= required_cpl; if true, return true. Otherwise queue + * a #GP and return false. + */ +bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) +{ + if (kvm_x86_ops->get_cpl(vcpu) <= required_cpl) + return true; + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return false; +} +EXPORT_SYMBOL_GPL(kvm_require_cpl); + +/* + * This function will be used to read from the physical memory of the currently + * running guest. The difference to kvm_read_guest_page is that this function + * can read from guest physical or from the guest's guest physical memory. + */ +int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gfn_t ngfn, void *data, int offset, int len, + u32 access) +{ + struct x86_exception exception; + gfn_t real_gfn; + gpa_t ngpa; + + ngpa = gfn_to_gpa(ngfn); + real_gfn = mmu->translate_gpa(vcpu, ngpa, access, &exception); + if (real_gfn == UNMAPPED_GVA) + return -EFAULT; + + real_gfn = gpa_to_gfn(real_gfn); + + return kvm_read_guest_page(vcpu->kvm, real_gfn, data, offset, len); +} +EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu); + +int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, + void *data, int offset, int len, u32 access) +{ + return kvm_read_guest_page_mmu(vcpu, vcpu->arch.walk_mmu, gfn, + data, offset, len, access); +} + +/* + * Load the pae pdptrs. Return true is they are all valid. + */ +int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) +{ + gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; + unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2; + int i; + int ret; + u64 pdpte[ARRAY_SIZE(mmu->pdptrs)]; + + ret = kvm_read_guest_page_mmu(vcpu, mmu, pdpt_gfn, pdpte, + offset * sizeof(u64), sizeof(pdpte), + PFERR_USER_MASK|PFERR_WRITE_MASK); + if (ret < 0) { + ret = 0; + goto out; + } + for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { + if (is_present_gpte(pdpte[i]) && + (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) { + ret = 0; + goto out; + } + } + ret = 1; + + memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); + __set_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_avail); + __set_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_dirty); +out: + + return ret; +} +EXPORT_SYMBOL_GPL(load_pdptrs); + +static bool pdptrs_changed(struct kvm_vcpu *vcpu) +{ + u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)]; + bool changed = true; + int offset; + gfn_t gfn; + int r; + + if (is_long_mode(vcpu) || !is_pae(vcpu)) + return false; + + if (!test_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_avail)) + return true; + + gfn = (kvm_read_cr3(vcpu) & ~31u) >> PAGE_SHIFT; + offset = (kvm_read_cr3(vcpu) & ~31u) & (PAGE_SIZE - 1); + r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte), + PFERR_USER_MASK | PFERR_WRITE_MASK); + if (r < 0) + goto out; + changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0; +out: + + return changed; +} + +int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +{ + unsigned long old_cr0 = kvm_read_cr0(vcpu); + unsigned long update_bits = X86_CR0_PG | X86_CR0_WP | + X86_CR0_CD | X86_CR0_NW; + + cr0 |= X86_CR0_ET; + +#ifdef CONFIG_X86_64 + if (cr0 & 0xffffffff00000000UL) + return 1; +#endif + + cr0 &= ~CR0_RESERVED_BITS; + + if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) + return 1; + + if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) + return 1; + + if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { +#ifdef CONFIG_X86_64 + if ((vcpu->arch.efer & EFER_LME)) { + int cs_db, cs_l; + + if (!is_pae(vcpu)) + return 1; + kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + if (cs_l) + return 1; + } else +#endif + if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, + kvm_read_cr3(vcpu))) + return 1; + } + + if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) + return 1; + + kvm_x86_ops->set_cr0(vcpu, cr0); + + if ((cr0 ^ old_cr0) & X86_CR0_PG) { + kvm_clear_async_pf_completion_queue(vcpu); + kvm_async_pf_hash_reset(vcpu); + } + + if ((cr0 ^ old_cr0) & update_bits) + kvm_mmu_reset_context(vcpu); + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_cr0); + +void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) +{ + (void)kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f)); +} +EXPORT_SYMBOL_GPL(kvm_lmsw); + +static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +{ + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && + !vcpu->guest_xcr0_loaded) { + /* kvm_set_xcr() also depends on this */ + xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); + vcpu->guest_xcr0_loaded = 1; + } +} + +static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +{ + if (vcpu->guest_xcr0_loaded) { + if (vcpu->arch.xcr0 != host_xcr0) + xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); + vcpu->guest_xcr0_loaded = 0; + } +} + +int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) +{ + u64 xcr0 = xcr; + u64 old_xcr0 = vcpu->arch.xcr0; + u64 valid_bits; + + /* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now */ + if (index != XCR_XFEATURE_ENABLED_MASK) + return 1; + if (!(xcr0 & XSTATE_FP)) + return 1; + if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE)) + return 1; + + /* + * Do not allow the guest to set bits that we do not support + * saving. However, xcr0 bit 0 is always set, even if the + * emulated CPU does not support XSAVE (see fx_init). + */ + valid_bits = vcpu->arch.guest_supported_xcr0 | XSTATE_FP; + if (xcr0 & ~valid_bits) + return 1; + + if ((!(xcr0 & XSTATE_BNDREGS)) != (!(xcr0 & XSTATE_BNDCSR))) + return 1; + + kvm_put_guest_xcr0(vcpu); + vcpu->arch.xcr0 = xcr0; + + if ((xcr0 ^ old_xcr0) & XSTATE_EXTEND_MASK) + kvm_update_cpuid(vcpu); + return 0; +} + +int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) +{ + if (kvm_x86_ops->get_cpl(vcpu) != 0 || + __kvm_set_xcr(vcpu, index, xcr)) { + kvm_inject_gp(vcpu, 0); + return 1; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_xcr); + +int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + unsigned long old_cr4 = kvm_read_cr4(vcpu); + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | + X86_CR4_PAE | X86_CR4_SMEP; + if (cr4 & CR4_RESERVED_BITS) + return 1; + + if (!guest_cpuid_has_xsave(vcpu) && (cr4 & X86_CR4_OSXSAVE)) + return 1; + + if (!guest_cpuid_has_smep(vcpu) && (cr4 & X86_CR4_SMEP)) + return 1; + + if (!guest_cpuid_has_smap(vcpu) && (cr4 & X86_CR4_SMAP)) + return 1; + + if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_FSGSBASE)) + return 1; + + if (is_long_mode(vcpu)) { + if (!(cr4 & X86_CR4_PAE)) + return 1; + } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) + && ((cr4 ^ old_cr4) & pdptr_bits) + && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, + kvm_read_cr3(vcpu))) + return 1; + + if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { + if (!guest_cpuid_has_pcid(vcpu)) + return 1; + + /* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */ + if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu)) + return 1; + } + + if (kvm_x86_ops->set_cr4(vcpu, cr4)) + return 1; + + if (((cr4 ^ old_cr4) & pdptr_bits) || + (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) + kvm_mmu_reset_context(vcpu); + + if ((cr4 ^ old_cr4) & X86_CR4_SMAP) + update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false); + + if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE) + kvm_update_cpuid(vcpu); + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_cr4); + +int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +{ + if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) { + kvm_mmu_sync_roots(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + return 0; + } + + if (is_long_mode(vcpu)) { + if (cr3 & CR3_L_MODE_RESERVED_BITS) + return 1; + } else if (is_pae(vcpu) && is_paging(vcpu) && + !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + return 1; + + vcpu->arch.cr3 = cr3; + __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_mmu_new_cr3(vcpu); + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_cr3); + +int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) +{ + if (cr8 & CR8_RESERVED_BITS) + return 1; + if (irqchip_in_kernel(vcpu->kvm)) + kvm_lapic_set_tpr(vcpu, cr8); + else + vcpu->arch.cr8 = cr8; + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_cr8); + +unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) +{ + if (irqchip_in_kernel(vcpu->kvm)) + return kvm_lapic_get_cr8(vcpu); + else + return vcpu->arch.cr8; +} +EXPORT_SYMBOL_GPL(kvm_get_cr8); + +static void kvm_update_dr6(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + kvm_x86_ops->set_dr6(vcpu, vcpu->arch.dr6); +} + +static void kvm_update_dr7(struct kvm_vcpu *vcpu) +{ + unsigned long dr7; + + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + dr7 = vcpu->arch.guest_debug_dr7; + else + dr7 = vcpu->arch.dr7; + kvm_x86_ops->set_dr7(vcpu, dr7); + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED; + if (dr7 & DR7_BP_EN_MASK) + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED; +} + +static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) +{ + u64 fixed = DR6_FIXED_1; + + if (!guest_cpuid_has_rtm(vcpu)) + fixed |= DR6_RTM; + return fixed; +} + +static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) +{ + switch (dr) { + case 0 ... 3: + vcpu->arch.db[dr] = val; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + vcpu->arch.eff_db[dr] = val; + break; + case 4: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; /* #UD */ + /* fall through */ + case 6: + if (val & 0xffffffff00000000ULL) + return -1; /* #GP */ + vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu); + kvm_update_dr6(vcpu); + break; + case 5: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; /* #UD */ + /* fall through */ + default: /* 7 */ + if (val & 0xffffffff00000000ULL) + return -1; /* #GP */ + vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; + kvm_update_dr7(vcpu); + break; + } + + return 0; +} + +int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) +{ + int res; + + res = __kvm_set_dr(vcpu, dr, val); + if (res > 0) + kvm_queue_exception(vcpu, UD_VECTOR); + else if (res < 0) + kvm_inject_gp(vcpu, 0); + + return res; +} +EXPORT_SYMBOL_GPL(kvm_set_dr); + +static int _kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +{ + switch (dr) { + case 0 ... 3: + *val = vcpu->arch.db[dr]; + break; + case 4: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; + /* fall through */ + case 6: + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + *val = vcpu->arch.dr6; + else + *val = kvm_x86_ops->get_dr6(vcpu); + break; + case 5: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; + /* fall through */ + default: /* 7 */ + *val = vcpu->arch.dr7; + break; + } + + return 0; +} + +int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +{ + if (_kvm_get_dr(vcpu, dr, val)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_get_dr); + +bool kvm_rdpmc(struct kvm_vcpu *vcpu) +{ + u32 ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); + u64 data; + int err; + + err = kvm_pmu_read_pmc(vcpu, ecx, &data); + if (err) + return err; + kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data); + kvm_register_write(vcpu, VCPU_REGS_RDX, data >> 32); + return err; +} +EXPORT_SYMBOL_GPL(kvm_rdpmc); + +/* + * List of msr numbers which we expose to userspace through KVM_GET_MSRS + * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. + * + * This list is modified at module load time to reflect the + * capabilities of the host cpu. This capabilities test skips MSRs that are + * kvm-specific. Those are put in the beginning of the list. + */ + +#define KVM_SAVE_MSRS_BEGIN 12 +static u32 msrs_to_save[] = { + MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, + HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, + HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, + MSR_KVM_PV_EOI_EN, + MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, + MSR_STAR, +#ifdef CONFIG_X86_64 + MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, +#endif + MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, + MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS +}; + +static unsigned num_msrs_to_save; + +static const u32 emulated_msrs[] = { + MSR_IA32_TSC_ADJUST, + MSR_IA32_TSCDEADLINE, + MSR_IA32_MISC_ENABLE, + MSR_IA32_MCG_STATUS, + MSR_IA32_MCG_CTL, +}; + +bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + if (efer & efer_reserved_bits) + return false; + + if (efer & EFER_FFXSR) { + struct kvm_cpuid_entry2 *feat; + + feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) + return false; + } + + if (efer & EFER_SVME) { + struct kvm_cpuid_entry2 *feat; + + feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) + return false; + } + + return true; +} +EXPORT_SYMBOL_GPL(kvm_valid_efer); + +static int set_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + u64 old_efer = vcpu->arch.efer; + + if (!kvm_valid_efer(vcpu, efer)) + return 1; + + if (is_paging(vcpu) + && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) + return 1; + + efer &= ~EFER_LMA; + efer |= vcpu->arch.efer & EFER_LMA; + + kvm_x86_ops->set_efer(vcpu, efer); + + /* Update reserved bits */ + if ((efer ^ old_efer) & EFER_NX) + kvm_mmu_reset_context(vcpu); + + return 0; +} + +void kvm_enable_efer_bits(u64 mask) +{ + efer_reserved_bits &= ~mask; +} +EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); + +/* + * Writes msr value into into the appropriate "register". + * Returns 0 on success, non-0 otherwise. + * Assumes vcpu_load() was already called. + */ +int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) +{ + switch (msr->index) { + case MSR_FS_BASE: + case MSR_GS_BASE: + case MSR_KERNEL_GS_BASE: + case MSR_CSTAR: + case MSR_LSTAR: + if (is_noncanonical_address(msr->data)) + return 1; + break; + case MSR_IA32_SYSENTER_EIP: + case MSR_IA32_SYSENTER_ESP: + /* + * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if + * non-canonical address is written on Intel but not on + * AMD (which ignores the top 32-bits, because it does + * not implement 64-bit SYSENTER). + * + * 64-bit code should hence be able to write a non-canonical + * value on AMD. Making the address canonical ensures that + * vmentry does not fail on Intel after writing a non-canonical + * value, and that something deterministic happens if the guest + * invokes 64-bit SYSENTER. + */ + msr->data = get_canonical(msr->data); + } + return kvm_x86_ops->set_msr(vcpu, msr); +} +EXPORT_SYMBOL_GPL(kvm_set_msr); + +/* + * Adapt set_msr() to msr_io()'s calling convention + */ +static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + struct msr_data msr; + + msr.data = *data; + msr.index = index; + msr.host_initiated = true; + return kvm_set_msr(vcpu, &msr); +} + +#ifdef CONFIG_X86_64 +struct pvclock_gtod_data { + seqcount_t seq; + + struct { /* extract of a clocksource struct */ + int vclock_mode; + cycle_t cycle_last; + cycle_t mask; + u32 mult; + u32 shift; + } clock; + + u64 boot_ns; + u64 nsec_base; +}; + +static struct pvclock_gtod_data pvclock_gtod_data; + +static void update_pvclock_gtod(struct timekeeper *tk) +{ + struct pvclock_gtod_data *vdata = &pvclock_gtod_data; + u64 boot_ns; + + boot_ns = ktime_to_ns(ktime_add(tk->tkr.base_mono, tk->offs_boot)); + + write_seqcount_begin(&vdata->seq); + + /* copy pvclock gtod data */ + vdata->clock.vclock_mode = tk->tkr.clock->archdata.vclock_mode; + vdata->clock.cycle_last = tk->tkr.cycle_last; + vdata->clock.mask = tk->tkr.mask; + vdata->clock.mult = tk->tkr.mult; + vdata->clock.shift = tk->tkr.shift; + + vdata->boot_ns = boot_ns; + vdata->nsec_base = tk->tkr.xtime_nsec; + + write_seqcount_end(&vdata->seq); +} +#endif + + +static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) +{ + int version; + int r; + struct pvclock_wall_clock wc; + struct timespec boot; + + if (!wall_clock) + return; + + r = kvm_read_guest(kvm, wall_clock, &version, sizeof(version)); + if (r) + return; + + if (version & 1) + ++version; /* first time write, random junk */ + + ++version; + + kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); + + /* + * The guest calculates current wall clock time by adding + * system time (updated by kvm_guest_time_update below) to the + * wall clock specified here. guest system time equals host + * system time for us, thus we must fill in host boot time here. + */ + getboottime(&boot); + + if (kvm->arch.kvmclock_offset) { + struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset); + boot = timespec_sub(boot, ts); + } + wc.sec = boot.tv_sec; + wc.nsec = boot.tv_nsec; + wc.version = version; + + kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc)); + + version++; + kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); +} + +static uint32_t div_frac(uint32_t dividend, uint32_t divisor) +{ + uint32_t quotient, remainder; + + /* Don't try to replace with do_div(), this one calculates + * "(dividend << 32) / divisor" */ + __asm__ ( "divl %4" + : "=a" (quotient), "=d" (remainder) + : "0" (0), "1" (dividend), "r" (divisor) ); + return quotient; +} + +static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz, + s8 *pshift, u32 *pmultiplier) +{ + uint64_t scaled64; + int32_t shift = 0; + uint64_t tps64; + uint32_t tps32; + + tps64 = base_khz * 1000LL; + scaled64 = scaled_khz * 1000LL; + while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) { + tps64 >>= 1; + shift--; + } + + tps32 = (uint32_t)tps64; + while (tps32 <= scaled64 || scaled64 & 0xffffffff00000000ULL) { + if (scaled64 & 0xffffffff00000000ULL || tps32 & 0x80000000) + scaled64 >>= 1; + else + tps32 <<= 1; + shift++; + } + + *pshift = shift; + *pmultiplier = div_frac(scaled64, tps32); + + pr_debug("%s: base_khz %u => %u, shift %d, mul %u\n", + __func__, base_khz, scaled_khz, shift, *pmultiplier); +} + +static inline u64 get_kernel_ns(void) +{ + return ktime_get_boot_ns(); +} + +#ifdef CONFIG_X86_64 +static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); +#endif + +static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); +unsigned long max_tsc_khz; + +static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) +{ + return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); +} + +static u32 adjust_tsc_khz(u32 khz, s32 ppm) +{ + u64 v = (u64)khz * (1000000 + ppm); + do_div(v, 1000000); + return v; +} + +static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) +{ + u32 thresh_lo, thresh_hi; + int use_scaling = 0; + + /* tsc_khz can be zero if TSC calibration fails */ + if (this_tsc_khz == 0) + return; + + /* Compute a scale to convert nanoseconds in TSC cycles */ + kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000, + &vcpu->arch.virtual_tsc_shift, + &vcpu->arch.virtual_tsc_mult); + vcpu->arch.virtual_tsc_khz = this_tsc_khz; + + /* + * Compute the variation in TSC rate which is acceptable + * within the range of tolerance and decide if the + * rate being applied is within that bounds of the hardware + * rate. If so, no scaling or compensation need be done. + */ + thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm); + thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm); + if (this_tsc_khz < thresh_lo || this_tsc_khz > thresh_hi) { + pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi); + use_scaling = 1; + } + kvm_x86_ops->set_tsc_khz(vcpu, this_tsc_khz, use_scaling); +} + +static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) +{ + u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.this_tsc_nsec, + vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); + tsc += vcpu->arch.this_tsc_write; + return tsc; +} + +void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_X86_64 + bool vcpus_matched; + struct kvm_arch *ka = &vcpu->kvm->arch; + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + + vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == + atomic_read(&vcpu->kvm->online_vcpus)); + + /* + * Once the masterclock is enabled, always perform request in + * order to update it. + * + * In order to enable masterclock, the host clocksource must be TSC + * and the vcpus need to have matched TSCs. When that happens, + * perform request to enable masterclock. + */ + if (ka->use_master_clock || + (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched)) + kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); + + trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, + atomic_read(&vcpu->kvm->online_vcpus), + ka->use_master_clock, gtod->clock.vclock_mode); +#endif +} + +static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) +{ + u64 curr_offset = kvm_x86_ops->read_tsc_offset(vcpu); + vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; +} + +void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) +{ + struct kvm *kvm = vcpu->kvm; + u64 offset, ns, elapsed; + unsigned long flags; + s64 usdiff; + bool matched; + bool already_matched; + u64 data = msr->data; + + raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); + offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); + ns = get_kernel_ns(); + elapsed = ns - kvm->arch.last_tsc_nsec; + + if (vcpu->arch.virtual_tsc_khz) { + int faulted = 0; + + /* n.b - signed multiplication and division required */ + usdiff = data - kvm->arch.last_tsc_write; +#ifdef CONFIG_X86_64 + usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz; +#else + /* do_div() only does unsigned */ + asm("1: idivl %[divisor]\n" + "2: xor %%edx, %%edx\n" + " movl $0, %[faulted]\n" + "3:\n" + ".section .fixup,\"ax\"\n" + "4: movl $1, %[faulted]\n" + " jmp 3b\n" + ".previous\n" + + _ASM_EXTABLE(1b, 4b) + + : "=A"(usdiff), [faulted] "=r" (faulted) + : "A"(usdiff * 1000), [divisor] "rm"(vcpu->arch.virtual_tsc_khz)); + +#endif + do_div(elapsed, 1000); + usdiff -= elapsed; + if (usdiff < 0) + usdiff = -usdiff; + + /* idivl overflow => difference is larger than USEC_PER_SEC */ + if (faulted) + usdiff = USEC_PER_SEC; + } else + usdiff = USEC_PER_SEC; /* disable TSC match window below */ + + /* + * Special case: TSC write with a small delta (1 second) of virtual + * cycle time against real time is interpreted as an attempt to + * synchronize the CPU. + * + * For a reliable TSC, we can match TSC offsets, and for an unstable + * TSC, we add elapsed time in this computation. We could let the + * compensation code attempt to catch up if we fall behind, but + * it's better to try to match offsets from the beginning. + */ + if (usdiff < USEC_PER_SEC && + vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) { + if (!check_tsc_unstable()) { + offset = kvm->arch.cur_tsc_offset; + pr_debug("kvm: matched tsc offset for %llu\n", data); + } else { + u64 delta = nsec_to_cycles(vcpu, elapsed); + data += delta; + offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); + pr_debug("kvm: adjusted tsc offset by %llu\n", delta); + } + matched = true; + already_matched = (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation); + } else { + /* + * We split periods of matched TSC writes into generations. + * For each generation, we track the original measured + * nanosecond time, offset, and write, so if TSCs are in + * sync, we can match exact offset, and if not, we can match + * exact software computation in compute_guest_tsc() + * + * These values are tracked in kvm->arch.cur_xxx variables. + */ + kvm->arch.cur_tsc_generation++; + kvm->arch.cur_tsc_nsec = ns; + kvm->arch.cur_tsc_write = data; + kvm->arch.cur_tsc_offset = offset; + matched = false; + pr_debug("kvm: new tsc generation %llu, clock %llu\n", + kvm->arch.cur_tsc_generation, data); + } + + /* + * We also track th most recent recorded KHZ, write and time to + * allow the matching interval to be extended at each write. + */ + kvm->arch.last_tsc_nsec = ns; + kvm->arch.last_tsc_write = data; + kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz; + + vcpu->arch.last_guest_tsc = data; + + /* Keep track of which generation this VCPU has synchronized to */ + vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation; + vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; + vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; + + if (guest_cpuid_has_tsc_adjust(vcpu) && !msr->host_initiated) + update_ia32_tsc_adjust_msr(vcpu, offset); + kvm_x86_ops->write_tsc_offset(vcpu, offset); + raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); + + spin_lock(&kvm->arch.pvclock_gtod_sync_lock); + if (!matched) { + kvm->arch.nr_vcpus_matched_tsc = 0; + } else if (!already_matched) { + kvm->arch.nr_vcpus_matched_tsc++; + } + + kvm_track_tsc_matching(vcpu); + spin_unlock(&kvm->arch.pvclock_gtod_sync_lock); +} + +EXPORT_SYMBOL_GPL(kvm_write_tsc); + +#ifdef CONFIG_X86_64 + +static cycle_t read_tsc(void) +{ + cycle_t ret; + u64 last; + + /* + * Empirically, a fence (of type that depends on the CPU) + * before rdtsc is enough to ensure that rdtsc is ordered + * with respect to loads. The various CPU manuals are unclear + * as to whether rdtsc can be reordered with later loads, + * but no one has ever seen it happen. + */ + rdtsc_barrier(); + ret = (cycle_t)vget_cycles(); + + last = pvclock_gtod_data.clock.cycle_last; + + if (likely(ret >= last)) + return ret; + + /* + * GCC likes to generate cmov here, but this branch is extremely + * predictable (it's just a funciton of time and the likely is + * very likely) and there's a data dependence, so force GCC + * to generate a branch instead. I don't barrier() because + * we don't actually need a barrier, and if this function + * ever gets inlined it will generate worse code. + */ + asm volatile (""); + return last; +} + +static inline u64 vgettsc(cycle_t *cycle_now) +{ + long v; + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + + *cycle_now = read_tsc(); + + v = (*cycle_now - gtod->clock.cycle_last) & gtod->clock.mask; + return v * gtod->clock.mult; +} + +static int do_monotonic_boot(s64 *t, cycle_t *cycle_now) +{ + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + unsigned long seq; + int mode; + u64 ns; + + do { + seq = read_seqcount_begin(>od->seq); + mode = gtod->clock.vclock_mode; + ns = gtod->nsec_base; + ns += vgettsc(cycle_now); + ns >>= gtod->clock.shift; + ns += gtod->boot_ns; + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + *t = ns; + + return mode; +} + +/* returns true if host is using tsc clocksource */ +static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now) +{ + /* checked again under seqlock below */ + if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC) + return false; + + return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC; +} +#endif + +/* + * + * Assuming a stable TSC across physical CPUS, and a stable TSC + * across virtual CPUs, the following condition is possible. + * Each numbered line represents an event visible to both + * CPUs at the next numbered event. + * + * "timespecX" represents host monotonic time. "tscX" represents + * RDTSC value. + * + * VCPU0 on CPU0 | VCPU1 on CPU1 + * + * 1. read timespec0,tsc0 + * 2. | timespec1 = timespec0 + N + * | tsc1 = tsc0 + M + * 3. transition to guest | transition to guest + * 4. ret0 = timespec0 + (rdtsc - tsc0) | + * 5. | ret1 = timespec1 + (rdtsc - tsc1) + * | ret1 = timespec0 + N + (rdtsc - (tsc0 + M)) + * + * Since ret0 update is visible to VCPU1 at time 5, to obey monotonicity: + * + * - ret0 < ret1 + * - timespec0 + (rdtsc - tsc0) < timespec0 + N + (rdtsc - (tsc0 + M)) + * ... + * - 0 < N - M => M < N + * + * That is, when timespec0 != timespec1, M < N. Unfortunately that is not + * always the case (the difference between two distinct xtime instances + * might be smaller then the difference between corresponding TSC reads, + * when updating guest vcpus pvclock areas). + * + * To avoid that problem, do not allow visibility of distinct + * system_timestamp/tsc_timestamp values simultaneously: use a master + * copy of host monotonic time values. Update that master copy + * in lockstep. + * + * Rely on synchronization of host TSCs and guest TSCs for monotonicity. + * + */ + +static void pvclock_update_vm_gtod_copy(struct kvm *kvm) +{ +#ifdef CONFIG_X86_64 + struct kvm_arch *ka = &kvm->arch; + int vclock_mode; + bool host_tsc_clocksource, vcpus_matched; + + vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == + atomic_read(&kvm->online_vcpus)); + + /* + * If the host uses TSC clock, then passthrough TSC as stable + * to the guest. + */ + host_tsc_clocksource = kvm_get_time_and_clockread( + &ka->master_kernel_ns, + &ka->master_cycle_now); + + ka->use_master_clock = host_tsc_clocksource && vcpus_matched + && !backwards_tsc_observed; + + if (ka->use_master_clock) + atomic_set(&kvm_guest_has_master_clock, 1); + + vclock_mode = pvclock_gtod_data.clock.vclock_mode; + trace_kvm_update_master_clock(ka->use_master_clock, vclock_mode, + vcpus_matched); +#endif +} + +static void kvm_gen_update_masterclock(struct kvm *kvm) +{ +#ifdef CONFIG_X86_64 + int i; + struct kvm_vcpu *vcpu; + struct kvm_arch *ka = &kvm->arch; + + spin_lock(&ka->pvclock_gtod_sync_lock); + kvm_make_mclock_inprogress_request(kvm); + /* no guest entries from this point */ + pvclock_update_vm_gtod_copy(kvm); + + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + + /* guest entries allowed */ + kvm_for_each_vcpu(i, vcpu, kvm) + clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests); + + spin_unlock(&ka->pvclock_gtod_sync_lock); +#endif +} + +static int kvm_guest_time_update(struct kvm_vcpu *v) +{ + unsigned long flags, this_tsc_khz; + struct kvm_vcpu_arch *vcpu = &v->arch; + struct kvm_arch *ka = &v->kvm->arch; + s64 kernel_ns; + u64 tsc_timestamp, host_tsc; + struct pvclock_vcpu_time_info guest_hv_clock; + u8 pvclock_flags; + bool use_master_clock; + + kernel_ns = 0; + host_tsc = 0; + + /* + * If the host uses TSC clock, then passthrough TSC as stable + * to the guest. + */ + spin_lock(&ka->pvclock_gtod_sync_lock); + use_master_clock = ka->use_master_clock; + if (use_master_clock) { + host_tsc = ka->master_cycle_now; + kernel_ns = ka->master_kernel_ns; + } + spin_unlock(&ka->pvclock_gtod_sync_lock); + + /* Keep irq disabled to prevent changes to the clock */ + local_irq_save(flags); + this_tsc_khz = __this_cpu_read(cpu_tsc_khz); + if (unlikely(this_tsc_khz == 0)) { + local_irq_restore(flags); + kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); + return 1; + } + if (!use_master_clock) { + host_tsc = native_read_tsc(); + kernel_ns = get_kernel_ns(); + } + + tsc_timestamp = kvm_x86_ops->read_l1_tsc(v, host_tsc); + + /* + * We may have to catch up the TSC to match elapsed wall clock + * time for two reasons, even if kvmclock is used. + * 1) CPU could have been running below the maximum TSC rate + * 2) Broken TSC compensation resets the base at each VCPU + * entry to avoid unknown leaps of TSC even when running + * again on the same CPU. This may cause apparent elapsed + * time to disappear, and the guest to stand still or run + * very slowly. + */ + if (vcpu->tsc_catchup) { + u64 tsc = compute_guest_tsc(v, kernel_ns); + if (tsc > tsc_timestamp) { + adjust_tsc_offset_guest(v, tsc - tsc_timestamp); + tsc_timestamp = tsc; + } + } + + local_irq_restore(flags); + + if (!vcpu->pv_time_enabled) + return 0; + + if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) { + kvm_get_time_scale(NSEC_PER_SEC / 1000, this_tsc_khz, + &vcpu->hv_clock.tsc_shift, + &vcpu->hv_clock.tsc_to_system_mul); + vcpu->hw_tsc_khz = this_tsc_khz; + } + + /* With all the info we got, fill in the values */ + vcpu->hv_clock.tsc_timestamp = tsc_timestamp; + vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; + vcpu->last_guest_tsc = tsc_timestamp; + + /* + * The interface expects us to write an even number signaling that the + * update is finished. Since the guest won't see the intermediate + * state, we just increase by 2 at the end. + */ + vcpu->hv_clock.version += 2; + + if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time, + &guest_hv_clock, sizeof(guest_hv_clock)))) + return 0; + + /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ + pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED); + + if (vcpu->pvclock_set_guest_stopped_request) { + pvclock_flags |= PVCLOCK_GUEST_STOPPED; + vcpu->pvclock_set_guest_stopped_request = false; + } + + /* If the host uses TSC clocksource, then it is stable */ + if (use_master_clock) + pvclock_flags |= PVCLOCK_TSC_STABLE_BIT; + + vcpu->hv_clock.flags = pvclock_flags; + + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock)); + return 0; +} + +/* + * kvmclock updates which are isolated to a given vcpu, such as + * vcpu->cpu migration, should not allow system_timestamp from + * the rest of the vcpus to remain static. Otherwise ntp frequency + * correction applies to one vcpu's system_timestamp but not + * the others. + * + * So in those cases, request a kvmclock update for all vcpus. + * We need to rate-limit these requests though, as they can + * considerably slow guests that have a large number of vcpus. + * The time for a remote vcpu to update its kvmclock is bound + * by the delay we use to rate-limit the updates. + */ + +#define KVMCLOCK_UPDATE_DELAY msecs_to_jiffies(100) + +static void kvmclock_update_fn(struct work_struct *work) +{ + int i; + struct delayed_work *dwork = to_delayed_work(work); + struct kvm_arch *ka = container_of(dwork, struct kvm_arch, + kvmclock_update_work); + struct kvm *kvm = container_of(ka, struct kvm, arch); + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + kvm_vcpu_kick(vcpu); + } +} + +static void kvm_gen_kvmclock_update(struct kvm_vcpu *v) +{ + struct kvm *kvm = v->kvm; + + kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); + schedule_delayed_work(&kvm->arch.kvmclock_update_work, + KVMCLOCK_UPDATE_DELAY); +} + +#define KVMCLOCK_SYNC_PERIOD (300 * HZ) + +static void kvmclock_sync_fn(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct kvm_arch *ka = container_of(dwork, struct kvm_arch, + kvmclock_sync_work); + struct kvm *kvm = container_of(ka, struct kvm, arch); + + schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0); + schedule_delayed_work(&kvm->arch.kvmclock_sync_work, + KVMCLOCK_SYNC_PERIOD); +} + +static bool msr_mtrr_valid(unsigned msr) +{ + switch (msr) { + case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1: + case MSR_MTRRfix64K_00000: + case MSR_MTRRfix16K_80000: + case MSR_MTRRfix16K_A0000: + case MSR_MTRRfix4K_C0000: + case MSR_MTRRfix4K_C8000: + case MSR_MTRRfix4K_D0000: + case MSR_MTRRfix4K_D8000: + case MSR_MTRRfix4K_E0000: + case MSR_MTRRfix4K_E8000: + case MSR_MTRRfix4K_F0000: + case MSR_MTRRfix4K_F8000: + case MSR_MTRRdefType: + case MSR_IA32_CR_PAT: + return true; + case 0x2f8: + return true; + } + return false; +} + +static bool valid_pat_type(unsigned t) +{ + return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */ +} + +static bool valid_mtrr_type(unsigned t) +{ + return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */ +} + +bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + int i; + u64 mask; + + if (!msr_mtrr_valid(msr)) + return false; + + if (msr == MSR_IA32_CR_PAT) { + for (i = 0; i < 8; i++) + if (!valid_pat_type((data >> (i * 8)) & 0xff)) + return false; + return true; + } else if (msr == MSR_MTRRdefType) { + if (data & ~0xcff) + return false; + return valid_mtrr_type(data & 0xff); + } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) { + for (i = 0; i < 8 ; i++) + if (!valid_mtrr_type((data >> (i * 8)) & 0xff)) + return false; + return true; + } + + /* variable MTRRs */ + WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR)); + + mask = (~0ULL) << cpuid_maxphyaddr(vcpu); + if ((msr & 1) == 0) { + /* MTRR base */ + if (!valid_mtrr_type(data & 0xff)) + return false; + mask |= 0xf00; + } else + /* MTRR mask */ + mask |= 0x7ff; + if (data & mask) { + kvm_inject_gp(vcpu, 0); + return false; + } + + return true; +} +EXPORT_SYMBOL_GPL(kvm_mtrr_valid); + +static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; + + if (!kvm_mtrr_valid(vcpu, msr, data)) + return 1; + + if (msr == MSR_MTRRdefType) { + vcpu->arch.mtrr_state.def_type = data; + vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10; + } else if (msr == MSR_MTRRfix64K_00000) + p[0] = data; + else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) + p[1 + msr - MSR_MTRRfix16K_80000] = data; + else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) + p[3 + msr - MSR_MTRRfix4K_C0000] = data; + else if (msr == MSR_IA32_CR_PAT) + vcpu->arch.pat = data; + else { /* Variable MTRRs */ + int idx, is_mtrr_mask; + u64 *pt; + + idx = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * idx; + if (!is_mtrr_mask) + pt = + (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; + else + pt = + (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; + *pt = data; + } + + kvm_mmu_reset_context(vcpu); + return 0; +} + +static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + u64 mcg_cap = vcpu->arch.mcg_cap; + unsigned bank_num = mcg_cap & 0xff; + + switch (msr) { + case MSR_IA32_MCG_STATUS: + vcpu->arch.mcg_status = data; + break; + case MSR_IA32_MCG_CTL: + if (!(mcg_cap & MCG_CTL_P)) + return 1; + if (data != 0 && data != ~(u64)0) + return -1; + vcpu->arch.mcg_ctl = data; + break; + default: + if (msr >= MSR_IA32_MC0_CTL && + msr < MSR_IA32_MCx_CTL(bank_num)) { + u32 offset = msr - MSR_IA32_MC0_CTL; + /* only 0 or all 1s can be written to IA32_MCi_CTL + * some Linux kernels though clear bit 10 in bank 4 to + * workaround a BIOS/GART TBL issue on AMD K8s, ignore + * this to avoid an uncatched #GP in the guest + */ + if ((offset & 0x3) == 0 && + data != 0 && (data | (1 << 10)) != ~(u64)0) + return -1; + vcpu->arch.mce_banks[offset] = data; + break; + } + return 1; + } + return 0; +} + +static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) +{ + struct kvm *kvm = vcpu->kvm; + int lm = is_long_mode(vcpu); + u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64 + : (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32; + u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 + : kvm->arch.xen_hvm_config.blob_size_32; + u32 page_num = data & ~PAGE_MASK; + u64 page_addr = data & PAGE_MASK; + u8 *page; + int r; + + r = -E2BIG; + if (page_num >= blob_size) + goto out; + r = -ENOMEM; + page = memdup_user(blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE); + if (IS_ERR(page)) { + r = PTR_ERR(page); + goto out; + } + if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE)) + goto out_free; + r = 0; +out_free: + kfree(page); +out: + return r; +} + +static bool kvm_hv_hypercall_enabled(struct kvm *kvm) +{ + return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE; +} + +static bool kvm_hv_msr_partition_wide(u32 msr) +{ + bool r = false; + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + case HV_X64_MSR_HYPERCALL: + case HV_X64_MSR_REFERENCE_TSC: + case HV_X64_MSR_TIME_REF_COUNT: + r = true; + break; + } + + return r; +} + +static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + struct kvm *kvm = vcpu->kvm; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + kvm->arch.hv_guest_os_id = data; + /* setting guest os id to zero disables hypercall page */ + if (!kvm->arch.hv_guest_os_id) + kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE; + break; + case HV_X64_MSR_HYPERCALL: { + u64 gfn; + unsigned long addr; + u8 instructions[4]; + + /* if guest os id is not set hypercall should remain disabled */ + if (!kvm->arch.hv_guest_os_id) + break; + if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) { + kvm->arch.hv_hypercall = data; + break; + } + gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT; + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return 1; + kvm_x86_ops->patch_hypercall(vcpu, instructions); + ((unsigned char *)instructions)[3] = 0xc3; /* ret */ + if (__copy_to_user((void __user *)addr, instructions, 4)) + return 1; + kvm->arch.hv_hypercall = data; + mark_page_dirty(kvm, gfn); + break; + } + case HV_X64_MSR_REFERENCE_TSC: { + u64 gfn; + HV_REFERENCE_TSC_PAGE tsc_ref; + memset(&tsc_ref, 0, sizeof(tsc_ref)); + kvm->arch.hv_tsc_page = data; + if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + break; + gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; + if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT, + &tsc_ref, sizeof(tsc_ref))) + return 1; + mark_page_dirty(kvm, gfn); + break; + } + default: + vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " + "data 0x%llx\n", msr, data); + return 1; + } + return 0; +} + +static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + switch (msr) { + case HV_X64_MSR_APIC_ASSIST_PAGE: { + u64 gfn; + unsigned long addr; + + if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { + vcpu->arch.hv_vapic = data; + if (kvm_lapic_enable_pv_eoi(vcpu, 0)) + return 1; + break; + } + gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; + addr = gfn_to_hva(vcpu->kvm, gfn); + if (kvm_is_error_hva(addr)) + return 1; + if (__clear_user((void __user *)addr, PAGE_SIZE)) + return 1; + vcpu->arch.hv_vapic = data; + mark_page_dirty(vcpu->kvm, gfn); + if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED)) + return 1; + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); + default: + vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " + "data 0x%llx\n", msr, data); + return 1; + } + + return 0; +} + +static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) +{ + gpa_t gpa = data & ~0x3f; + + /* Bits 2:5 are reserved, Should be zero */ + if (data & 0x3c) + return 1; + + vcpu->arch.apf.msr_val = data; + + if (!(data & KVM_ASYNC_PF_ENABLED)) { + kvm_clear_async_pf_completion_queue(vcpu); + kvm_async_pf_hash_reset(vcpu); + return 0; + } + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, + sizeof(u32))) + return 1; + + vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS); + kvm_async_pf_wakeup_all(vcpu); + return 0; +} + +static void kvmclock_reset(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pv_time_enabled = false; +} + +static void accumulate_steal_time(struct kvm_vcpu *vcpu) +{ + u64 delta; + + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) + return; + + delta = current->sched_info.run_delay - vcpu->arch.st.last_steal; + vcpu->arch.st.last_steal = current->sched_info.run_delay; + vcpu->arch.st.accum_steal = delta; +} + +static void record_steal_time(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) + return; + + if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) + return; + + vcpu->arch.st.steal.steal += vcpu->arch.st.accum_steal; + vcpu->arch.st.steal.version += 2; + vcpu->arch.st.accum_steal = 0; + + kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); +} + +int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + bool pr = false; + u32 msr = msr_info->index; + u64 data = msr_info->data; + + switch (msr) { + case MSR_AMD64_NB_CFG: + case MSR_IA32_UCODE_REV: + case MSR_IA32_UCODE_WRITE: + case MSR_VM_HSAVE_PA: + case MSR_AMD64_PATCH_LOADER: + case MSR_AMD64_BU_CFG2: + break; + + case MSR_EFER: + return set_efer(vcpu, data); + case MSR_K7_HWCR: + data &= ~(u64)0x40; /* ignore flush filter disable */ + data &= ~(u64)0x100; /* ignore ignne emulation enable */ + data &= ~(u64)0x8; /* ignore TLB cache disable */ + data &= ~(u64)0x40000; /* ignore Mc status write enable */ + if (data != 0) { + vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", + data); + return 1; + } + break; + case MSR_FAM10H_MMIO_CONF_BASE: + if (data != 0) { + vcpu_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: " + "0x%llx\n", data); + return 1; + } + break; + case MSR_IA32_DEBUGCTLMSR: + if (!data) { + /* We support the non-activated case already */ + break; + } else if (data & ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_BTF)) { + /* Values other than LBR and BTF are vendor-specific, + thus reserved and should throw a #GP */ + return 1; + } + vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", + __func__, data); + break; + case 0x200 ... 0x2ff: + return set_msr_mtrr(vcpu, msr, data); + case MSR_IA32_APICBASE: + return kvm_set_apic_base(vcpu, msr_info); + case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + return kvm_x2apic_msr_write(vcpu, msr, data); + case MSR_IA32_TSCDEADLINE: + kvm_set_lapic_tscdeadline_msr(vcpu, data); + break; + case MSR_IA32_TSC_ADJUST: + if (guest_cpuid_has_tsc_adjust(vcpu)) { + if (!msr_info->host_initiated) { + u64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; + kvm_x86_ops->adjust_tsc_offset(vcpu, adj, true); + } + vcpu->arch.ia32_tsc_adjust_msr = data; + } + break; + case MSR_IA32_MISC_ENABLE: + vcpu->arch.ia32_misc_enable_msr = data; + break; + case MSR_KVM_WALL_CLOCK_NEW: + case MSR_KVM_WALL_CLOCK: + vcpu->kvm->arch.wall_clock = data; + kvm_write_wall_clock(vcpu->kvm, data); + break; + case MSR_KVM_SYSTEM_TIME_NEW: + case MSR_KVM_SYSTEM_TIME: { + u64 gpa_offset; + kvmclock_reset(vcpu); + + vcpu->arch.time = data; + kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); + + /* we verify if the enable bit is set... */ + if (!(data & 1)) + break; + + gpa_offset = data & ~(PAGE_MASK | 1); + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + &vcpu->arch.pv_time, data & ~1ULL, + sizeof(struct pvclock_vcpu_time_info))) + vcpu->arch.pv_time_enabled = false; + else + vcpu->arch.pv_time_enabled = true; + + break; + } + case MSR_KVM_ASYNC_PF_EN: + if (kvm_pv_enable_async_pf(vcpu, data)) + return 1; + break; + case MSR_KVM_STEAL_TIME: + + if (unlikely(!sched_info_on())) + return 1; + + if (data & KVM_STEAL_RESERVED_MASK) + return 1; + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, + data & KVM_STEAL_VALID_BITS, + sizeof(struct kvm_steal_time))) + return 1; + + vcpu->arch.st.msr_val = data; + + if (!(data & KVM_MSR_ENABLED)) + break; + + vcpu->arch.st.last_steal = current->sched_info.run_delay; + + preempt_disable(); + accumulate_steal_time(vcpu); + preempt_enable(); + + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + + break; + case MSR_KVM_PV_EOI_EN: + if (kvm_lapic_enable_pv_eoi(vcpu, data)) + return 1; + break; + + case MSR_IA32_MCG_CTL: + case MSR_IA32_MCG_STATUS: + case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: + return set_msr_mce(vcpu, msr, data); + + /* Performance counters are not protected by a CPUID bit, + * so we should check all of them in the generic path for the sake of + * cross vendor migration. + * Writing a zero into the event select MSRs disables them, + * which we perfectly emulate ;-). Any other value should be at least + * reported, some guests depend on them. + */ + case MSR_K7_EVNTSEL0: + case MSR_K7_EVNTSEL1: + case MSR_K7_EVNTSEL2: + case MSR_K7_EVNTSEL3: + if (data != 0) + vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); + break; + /* at least RHEL 4 unconditionally writes to the perfctr registers, + * so we ignore writes to make it happy. + */ + case MSR_K7_PERFCTR0: + case MSR_K7_PERFCTR1: + case MSR_K7_PERFCTR2: + case MSR_K7_PERFCTR3: + vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); + break; + case MSR_P6_PERFCTR0: + case MSR_P6_PERFCTR1: + pr = true; + case MSR_P6_EVNTSEL0: + case MSR_P6_EVNTSEL1: + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_set_msr(vcpu, msr_info); + + if (pr || data != 0) + vcpu_unimpl(vcpu, "disabled perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); + break; + case MSR_K7_CLK_CTL: + /* + * Ignore all writes to this no longer documented MSR. + * Writes are only relevant for old K7 processors, + * all pre-dating SVM, but a recommended workaround from + * AMD for these chips. It is possible to specify the + * affected processor models on the command line, hence + * the need to ignore the workaround. + */ + break; + case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: + if (kvm_hv_msr_partition_wide(msr)) { + int r; + mutex_lock(&vcpu->kvm->lock); + r = set_msr_hyperv_pw(vcpu, msr, data); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return set_msr_hyperv(vcpu, msr, data); + break; + case MSR_IA32_BBL_CR_CTL3: + /* Drop writes to this legacy MSR -- see rdmsr + * counterpart for further detail. + */ + vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data); + break; + case MSR_AMD64_OSVW_ID_LENGTH: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + vcpu->arch.osvw.length = data; + break; + case MSR_AMD64_OSVW_STATUS: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + vcpu->arch.osvw.status = data; + break; + default: + if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) + return xen_hvm_config(vcpu, data); + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_set_msr(vcpu, msr_info); + if (!ignore_msrs) { + vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", + msr, data); + return 1; + } else { + vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", + msr, data); + break; + } + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_msr_common); + + +/* + * Reads an msr value (of 'msr_index') into 'pdata'. + * Returns 0 on success, non-0 otherwise. + * Assumes vcpu_load() was already called. + */ +int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) +{ + return kvm_x86_ops->get_msr(vcpu, msr_index, pdata); +} + +static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; + + if (!msr_mtrr_valid(msr)) + return 1; + + if (msr == MSR_MTRRdefType) + *pdata = vcpu->arch.mtrr_state.def_type + + (vcpu->arch.mtrr_state.enabled << 10); + else if (msr == MSR_MTRRfix64K_00000) + *pdata = p[0]; + else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) + *pdata = p[1 + msr - MSR_MTRRfix16K_80000]; + else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) + *pdata = p[3 + msr - MSR_MTRRfix4K_C0000]; + else if (msr == MSR_IA32_CR_PAT) + *pdata = vcpu->arch.pat; + else { /* Variable MTRRs */ + int idx, is_mtrr_mask; + u64 *pt; + + idx = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * idx; + if (!is_mtrr_mask) + pt = + (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; + else + pt = + (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; + *pdata = *pt; + } + + return 0; +} + +static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data; + u64 mcg_cap = vcpu->arch.mcg_cap; + unsigned bank_num = mcg_cap & 0xff; + + switch (msr) { + case MSR_IA32_P5_MC_ADDR: + case MSR_IA32_P5_MC_TYPE: + data = 0; + break; + case MSR_IA32_MCG_CAP: + data = vcpu->arch.mcg_cap; + break; + case MSR_IA32_MCG_CTL: + if (!(mcg_cap & MCG_CTL_P)) + return 1; + data = vcpu->arch.mcg_ctl; + break; + case MSR_IA32_MCG_STATUS: + data = vcpu->arch.mcg_status; + break; + default: + if (msr >= MSR_IA32_MC0_CTL && + msr < MSR_IA32_MCx_CTL(bank_num)) { + u32 offset = msr - MSR_IA32_MC0_CTL; + data = vcpu->arch.mce_banks[offset]; + break; + } + return 1; + } + *pdata = data; + return 0; +} + +static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + struct kvm *kvm = vcpu->kvm; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + data = kvm->arch.hv_guest_os_id; + break; + case HV_X64_MSR_HYPERCALL: + data = kvm->arch.hv_hypercall; + break; + case HV_X64_MSR_TIME_REF_COUNT: { + data = + div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); + break; + } + case HV_X64_MSR_REFERENCE_TSC: + data = kvm->arch.hv_tsc_page; + break; + default: + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + + *pdata = data; + return 0; +} + +static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + + switch (msr) { + case HV_X64_MSR_VP_INDEX: { + int r; + struct kvm_vcpu *v; + kvm_for_each_vcpu(r, v, vcpu->kvm) { + if (v == vcpu) { + data = r; + break; + } + } + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); + case HV_X64_MSR_APIC_ASSIST_PAGE: + data = vcpu->arch.hv_vapic; + break; + default: + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + *pdata = data; + return 0; +} + +int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data; + + switch (msr) { + case MSR_IA32_PLATFORM_ID: + case MSR_IA32_EBL_CR_POWERON: + case MSR_IA32_DEBUGCTLMSR: + case MSR_IA32_LASTBRANCHFROMIP: + case MSR_IA32_LASTBRANCHTOIP: + case MSR_IA32_LASTINTFROMIP: + case MSR_IA32_LASTINTTOIP: + case MSR_K8_SYSCFG: + case MSR_K7_HWCR: + case MSR_VM_HSAVE_PA: + case MSR_K7_EVNTSEL0: + case MSR_K7_EVNTSEL1: + case MSR_K7_EVNTSEL2: + case MSR_K7_EVNTSEL3: + case MSR_K7_PERFCTR0: + case MSR_K7_PERFCTR1: + case MSR_K7_PERFCTR2: + case MSR_K7_PERFCTR3: + case MSR_K8_INT_PENDING_MSG: + case MSR_AMD64_NB_CFG: + case MSR_FAM10H_MMIO_CONF_BASE: + case MSR_AMD64_BU_CFG2: + data = 0; + break; + case MSR_P6_PERFCTR0: + case MSR_P6_PERFCTR1: + case MSR_P6_EVNTSEL0: + case MSR_P6_EVNTSEL1: + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_get_msr(vcpu, msr, pdata); + data = 0; + break; + case MSR_IA32_UCODE_REV: + data = 0x100000000ULL; + break; + case MSR_MTRRcap: + data = 0x500 | KVM_NR_VAR_MTRR; + break; + case 0x200 ... 0x2ff: + return get_msr_mtrr(vcpu, msr, pdata); + case 0xcd: /* fsb frequency */ + data = 3; + break; + /* + * MSR_EBC_FREQUENCY_ID + * Conservative value valid for even the basic CPU models. + * Models 0,1: 000 in bits 23:21 indicating a bus speed of + * 100MHz, model 2 000 in bits 18:16 indicating 100MHz, + * and 266MHz for model 3, or 4. Set Core Clock + * Frequency to System Bus Frequency Ratio to 1 (bits + * 31:24) even though these are only valid for CPU + * models > 2, however guests may end up dividing or + * multiplying by zero otherwise. + */ + case MSR_EBC_FREQUENCY_ID: + data = 1 << 24; + break; + case MSR_IA32_APICBASE: + data = kvm_get_apic_base(vcpu); + break; + case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + return kvm_x2apic_msr_read(vcpu, msr, pdata); + break; + case MSR_IA32_TSCDEADLINE: + data = kvm_get_lapic_tscdeadline_msr(vcpu); + break; + case MSR_IA32_TSC_ADJUST: + data = (u64)vcpu->arch.ia32_tsc_adjust_msr; + break; + case MSR_IA32_MISC_ENABLE: + data = vcpu->arch.ia32_misc_enable_msr; + break; + case MSR_IA32_PERF_STATUS: + /* TSC increment by tick */ + data = 1000ULL; + /* CPU multiplier */ + data |= (((uint64_t)4ULL) << 40); + break; + case MSR_EFER: + data = vcpu->arch.efer; + break; + case MSR_KVM_WALL_CLOCK: + case MSR_KVM_WALL_CLOCK_NEW: + data = vcpu->kvm->arch.wall_clock; + break; + case MSR_KVM_SYSTEM_TIME: + case MSR_KVM_SYSTEM_TIME_NEW: + data = vcpu->arch.time; + break; + case MSR_KVM_ASYNC_PF_EN: + data = vcpu->arch.apf.msr_val; + break; + case MSR_KVM_STEAL_TIME: + data = vcpu->arch.st.msr_val; + break; + case MSR_KVM_PV_EOI_EN: + data = vcpu->arch.pv_eoi.msr_val; + break; + case MSR_IA32_P5_MC_ADDR: + case MSR_IA32_P5_MC_TYPE: + case MSR_IA32_MCG_CAP: + case MSR_IA32_MCG_CTL: + case MSR_IA32_MCG_STATUS: + case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: + return get_msr_mce(vcpu, msr, pdata); + case MSR_K7_CLK_CTL: + /* + * Provide expected ramp-up count for K7. All other + * are set to zero, indicating minimum divisors for + * every field. + * + * This prevents guest kernels on AMD host with CPU + * type 6, model 8 and higher from exploding due to + * the rdmsr failing. + */ + data = 0x20000000; + break; + case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: + if (kvm_hv_msr_partition_wide(msr)) { + int r; + mutex_lock(&vcpu->kvm->lock); + r = get_msr_hyperv_pw(vcpu, msr, pdata); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return get_msr_hyperv(vcpu, msr, pdata); + break; + case MSR_IA32_BBL_CR_CTL3: + /* This legacy MSR exists but isn't fully documented in current + * silicon. It is however accessed by winxp in very narrow + * scenarios where it sets bit #19, itself documented as + * a "reserved" bit. Best effort attempt to source coherent + * read data here should the balance of the register be + * interpreted by the guest: + * + * L2 cache control register 3: 64GB range, 256KB size, + * enabled, latency 0x1, configured + */ + data = 0xbe702111; + break; + case MSR_AMD64_OSVW_ID_LENGTH: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + data = vcpu->arch.osvw.length; + break; + case MSR_AMD64_OSVW_STATUS: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + data = vcpu->arch.osvw.status; + break; + default: + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_get_msr(vcpu, msr, pdata); + if (!ignore_msrs) { + vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); + return 1; + } else { + vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr); + data = 0; + } + break; + } + *pdata = data; + return 0; +} +EXPORT_SYMBOL_GPL(kvm_get_msr_common); + +/* + * Read or write a bunch of msrs. All parameters are kernel addresses. + * + * @return number of msrs set successfully. + */ +static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, + struct kvm_msr_entry *entries, + int (*do_msr)(struct kvm_vcpu *vcpu, + unsigned index, u64 *data)) +{ + int i, idx; + + idx = srcu_read_lock(&vcpu->kvm->srcu); + for (i = 0; i < msrs->nmsrs; ++i) + if (do_msr(vcpu, entries[i].index, &entries[i].data)) + break; + srcu_read_unlock(&vcpu->kvm->srcu, idx); + + return i; +} + +/* + * Read or write a bunch of msrs. Parameters are user addresses. + * + * @return number of msrs set successfully. + */ +static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, + int (*do_msr)(struct kvm_vcpu *vcpu, + unsigned index, u64 *data), + int writeback) +{ + struct kvm_msrs msrs; + struct kvm_msr_entry *entries; + int r, n; + unsigned size; + + r = -EFAULT; + if (copy_from_user(&msrs, user_msrs, sizeof msrs)) + goto out; + + r = -E2BIG; + if (msrs.nmsrs >= MAX_IO_MSRS) + goto out; + + size = sizeof(struct kvm_msr_entry) * msrs.nmsrs; + entries = memdup_user(user_msrs->entries, size); + if (IS_ERR(entries)) { + r = PTR_ERR(entries); + goto out; + } + + r = n = __msr_io(vcpu, &msrs, entries, do_msr); + if (r < 0) + goto out_free; + + r = -EFAULT; + if (writeback && copy_to_user(user_msrs->entries, entries, size)) + goto out_free; + + r = n; + +out_free: + kfree(entries); +out: + return r; +} + +int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) +{ + int r; + + switch (ext) { + case KVM_CAP_IRQCHIP: + case KVM_CAP_HLT: + case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: + case KVM_CAP_SET_TSS_ADDR: + case KVM_CAP_EXT_CPUID: + case KVM_CAP_EXT_EMUL_CPUID: + case KVM_CAP_CLOCKSOURCE: + case KVM_CAP_PIT: + case KVM_CAP_NOP_IO_DELAY: + case KVM_CAP_MP_STATE: + case KVM_CAP_SYNC_MMU: + case KVM_CAP_USER_NMI: + case KVM_CAP_REINJECT_CONTROL: + case KVM_CAP_IRQ_INJECT_STATUS: + case KVM_CAP_IRQFD: + case KVM_CAP_IOEVENTFD: + case KVM_CAP_IOEVENTFD_NO_LENGTH: + case KVM_CAP_PIT2: + case KVM_CAP_PIT_STATE2: + case KVM_CAP_SET_IDENTITY_MAP_ADDR: + case KVM_CAP_XEN_HVM: + case KVM_CAP_ADJUST_CLOCK: + case KVM_CAP_VCPU_EVENTS: + case KVM_CAP_HYPERV: + case KVM_CAP_HYPERV_VAPIC: + case KVM_CAP_HYPERV_SPIN: + case KVM_CAP_PCI_SEGMENT: + case KVM_CAP_DEBUGREGS: + case KVM_CAP_X86_ROBUST_SINGLESTEP: + case KVM_CAP_XSAVE: + case KVM_CAP_ASYNC_PF: + case KVM_CAP_GET_TSC_KHZ: + case KVM_CAP_KVMCLOCK_CTRL: + case KVM_CAP_READONLY_MEM: + case KVM_CAP_HYPERV_TIME: + case KVM_CAP_IOAPIC_POLARITY_IGNORED: +#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT + case KVM_CAP_ASSIGN_DEV_IRQ: + case KVM_CAP_PCI_2_3: +#endif + r = 1; + break; + case KVM_CAP_COALESCED_MMIO: + r = KVM_COALESCED_MMIO_PAGE_OFFSET; + break; + case KVM_CAP_VAPIC: + r = !kvm_x86_ops->cpu_has_accelerated_tpr(); + break; + case KVM_CAP_NR_VCPUS: + r = KVM_SOFT_MAX_VCPUS; + break; + case KVM_CAP_MAX_VCPUS: + r = KVM_MAX_VCPUS; + break; + case KVM_CAP_NR_MEMSLOTS: + r = KVM_USER_MEM_SLOTS; + break; + case KVM_CAP_PV_MMU: /* obsolete */ + r = 0; + break; +#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT + case KVM_CAP_IOMMU: + r = iommu_present(&pci_bus_type); + break; +#endif + case KVM_CAP_MCE: + r = KVM_MAX_MCE_BANKS; + break; + case KVM_CAP_XCRS: + r = cpu_has_xsave; + break; + case KVM_CAP_TSC_CONTROL: + r = kvm_has_tsc_control; + break; + case KVM_CAP_TSC_DEADLINE_TIMER: + r = boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER); + break; + default: + r = 0; + break; + } + return r; + +} + +long kvm_arch_dev_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + void __user *argp = (void __user *)arg; + long r; + + switch (ioctl) { + case KVM_GET_MSR_INDEX_LIST: { + struct kvm_msr_list __user *user_msr_list = argp; + struct kvm_msr_list msr_list; + unsigned n; + + r = -EFAULT; + if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list)) + goto out; + n = msr_list.nmsrs; + msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs); + if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list)) + goto out; + r = -E2BIG; + if (n < msr_list.nmsrs) + goto out; + r = -EFAULT; + if (copy_to_user(user_msr_list->indices, &msrs_to_save, + num_msrs_to_save * sizeof(u32))) + goto out; + if (copy_to_user(user_msr_list->indices + num_msrs_to_save, + &emulated_msrs, + ARRAY_SIZE(emulated_msrs) * sizeof(u32))) + goto out; + r = 0; + break; + } + case KVM_GET_SUPPORTED_CPUID: + case KVM_GET_EMULATED_CPUID: { + struct kvm_cpuid2 __user *cpuid_arg = argp; + struct kvm_cpuid2 cpuid; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) + goto out; + + r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries, + ioctl); + if (r) + goto out; + + r = -EFAULT; + if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid)) + goto out; + r = 0; + break; + } + case KVM_X86_GET_MCE_CAP_SUPPORTED: { + u64 mce_cap; + + mce_cap = KVM_MCE_CAP_SUPPORTED; + r = -EFAULT; + if (copy_to_user(argp, &mce_cap, sizeof mce_cap)) + goto out; + r = 0; + break; + } + default: + r = -EINVAL; + } +out: + return r; +} + +static void wbinvd_ipi(void *garbage) +{ + wbinvd(); +} + +static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) +{ + return kvm_arch_has_noncoherent_dma(vcpu->kvm); +} + +void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + /* Address WBINVD may be executed by guest */ + if (need_emulate_wbinvd(vcpu)) { + if (kvm_x86_ops->has_wbinvd_exit()) + cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); + else if (vcpu->cpu != -1 && vcpu->cpu != cpu) + smp_call_function_single(vcpu->cpu, + wbinvd_ipi, NULL, 1); + } + + kvm_x86_ops->vcpu_load(vcpu, cpu); + + /* Apply any externally detected TSC adjustments (due to suspend) */ + if (unlikely(vcpu->arch.tsc_offset_adjustment)) { + adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); + vcpu->arch.tsc_offset_adjustment = 0; + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + } + + if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) { + s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 : + native_read_tsc() - vcpu->arch.last_host_tsc; + if (tsc_delta < 0) + mark_tsc_unstable("KVM discovered backwards TSC"); + if (check_tsc_unstable()) { + u64 offset = kvm_x86_ops->compute_tsc_offset(vcpu, + vcpu->arch.last_guest_tsc); + kvm_x86_ops->write_tsc_offset(vcpu, offset); + vcpu->arch.tsc_catchup = 1; + } + /* + * On a host with synchronized TSC, there is no need to update + * kvmclock on vcpu->cpu migration + */ + if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1) + kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); + if (vcpu->cpu != cpu) + kvm_migrate_timers(vcpu); + vcpu->cpu = cpu; + } + + accumulate_steal_time(vcpu); + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); +} + +void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->vcpu_put(vcpu); + kvm_put_guest_fpu(vcpu); + vcpu->arch.last_host_tsc = native_read_tsc(); +} + +static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, + struct kvm_lapic_state *s) +{ + kvm_x86_ops->sync_pir_to_irr(vcpu); + memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s); + + return 0; +} + +static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, + struct kvm_lapic_state *s) +{ + kvm_apic_post_state_restore(vcpu, s); + update_cr8_intercept(vcpu); + + return 0; +} + +static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, + struct kvm_interrupt *irq) +{ + if (irq->irq >= KVM_NR_INTERRUPTS) + return -EINVAL; + if (irqchip_in_kernel(vcpu->kvm)) + return -ENXIO; + + kvm_queue_interrupt(vcpu, irq->irq, false); + kvm_make_request(KVM_REQ_EVENT, vcpu); + + return 0; +} + +static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) +{ + kvm_inject_nmi(vcpu); + + return 0; +} + +static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, + struct kvm_tpr_access_ctl *tac) +{ + if (tac->flags) + return -EINVAL; + vcpu->arch.tpr_access_reporting = !!tac->enabled; + return 0; +} + +static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, + u64 mcg_cap) +{ + int r; + unsigned bank_num = mcg_cap & 0xff, bank; + + r = -EINVAL; + if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS) + goto out; + if (mcg_cap & ~(KVM_MCE_CAP_SUPPORTED | 0xff | 0xff0000)) + goto out; + r = 0; + vcpu->arch.mcg_cap = mcg_cap; + /* Init IA32_MCG_CTL to all 1s */ + if (mcg_cap & MCG_CTL_P) + vcpu->arch.mcg_ctl = ~(u64)0; + /* Init IA32_MCi_CTL to all 1s */ + for (bank = 0; bank < bank_num; bank++) + vcpu->arch.mce_banks[bank*4] = ~(u64)0; +out: + return r; +} + +static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, + struct kvm_x86_mce *mce) +{ + u64 mcg_cap = vcpu->arch.mcg_cap; + unsigned bank_num = mcg_cap & 0xff; + u64 *banks = vcpu->arch.mce_banks; + + if (mce->bank >= bank_num || !(mce->status & MCI_STATUS_VAL)) + return -EINVAL; + /* + * if IA32_MCG_CTL is not all 1s, the uncorrected error + * reporting is disabled + */ + if ((mce->status & MCI_STATUS_UC) && (mcg_cap & MCG_CTL_P) && + vcpu->arch.mcg_ctl != ~(u64)0) + return 0; + banks += 4 * mce->bank; + /* + * if IA32_MCi_CTL is not all 1s, the uncorrected error + * reporting is disabled for the bank + */ + if ((mce->status & MCI_STATUS_UC) && banks[0] != ~(u64)0) + return 0; + if (mce->status & MCI_STATUS_UC) { + if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) || + !kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) { + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + return 0; + } + if (banks[1] & MCI_STATUS_VAL) + mce->status |= MCI_STATUS_OVER; + banks[2] = mce->addr; + banks[3] = mce->misc; + vcpu->arch.mcg_status = mce->mcg_status; + banks[1] = mce->status; + kvm_queue_exception(vcpu, MC_VECTOR); + } else if (!(banks[1] & MCI_STATUS_VAL) + || !(banks[1] & MCI_STATUS_UC)) { + if (banks[1] & MCI_STATUS_VAL) + mce->status |= MCI_STATUS_OVER; + banks[2] = mce->addr; + banks[3] = mce->misc; + banks[1] = mce->status; + } else + banks[1] |= MCI_STATUS_OVER; + return 0; +} + +static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + process_nmi(vcpu); + events->exception.injected = + vcpu->arch.exception.pending && + !kvm_exception_is_soft(vcpu->arch.exception.nr); + events->exception.nr = vcpu->arch.exception.nr; + events->exception.has_error_code = vcpu->arch.exception.has_error_code; + events->exception.pad = 0; + events->exception.error_code = vcpu->arch.exception.error_code; + + events->interrupt.injected = + vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft; + events->interrupt.nr = vcpu->arch.interrupt.nr; + events->interrupt.soft = 0; + events->interrupt.shadow = kvm_x86_ops->get_interrupt_shadow(vcpu); + + events->nmi.injected = vcpu->arch.nmi_injected; + events->nmi.pending = vcpu->arch.nmi_pending != 0; + events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); + events->nmi.pad = 0; + + events->sipi_vector = 0; /* never valid when reporting to user space */ + + events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING + | KVM_VCPUEVENT_VALID_SHADOW); + memset(&events->reserved, 0, sizeof(events->reserved)); +} + +static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING + | KVM_VCPUEVENT_VALID_SIPI_VECTOR + | KVM_VCPUEVENT_VALID_SHADOW)) + return -EINVAL; + + process_nmi(vcpu); + vcpu->arch.exception.pending = events->exception.injected; + vcpu->arch.exception.nr = events->exception.nr; + vcpu->arch.exception.has_error_code = events->exception.has_error_code; + vcpu->arch.exception.error_code = events->exception.error_code; + + vcpu->arch.interrupt.pending = events->interrupt.injected; + vcpu->arch.interrupt.nr = events->interrupt.nr; + vcpu->arch.interrupt.soft = events->interrupt.soft; + if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) + kvm_x86_ops->set_interrupt_shadow(vcpu, + events->interrupt.shadow); + + vcpu->arch.nmi_injected = events->nmi.injected; + if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) + vcpu->arch.nmi_pending = events->nmi.pending; + kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked); + + if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && + kvm_vcpu_has_lapic(vcpu)) + vcpu->arch.apic->sipi_vector = events->sipi_vector; + + kvm_make_request(KVM_REQ_EVENT, vcpu); + + return 0; +} + +static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) +{ + unsigned long val; + + memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); + _kvm_get_dr(vcpu, 6, &val); + dbgregs->dr6 = val; + dbgregs->dr7 = vcpu->arch.dr7; + dbgregs->flags = 0; + memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved)); +} + +static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) +{ + if (dbgregs->flags) + return -EINVAL; + + memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); + vcpu->arch.dr6 = dbgregs->dr6; + kvm_update_dr6(vcpu); + vcpu->arch.dr7 = dbgregs->dr7; + kvm_update_dr7(vcpu); + + return 0; +} + +#define XSTATE_COMPACTION_ENABLED (1ULL << 63) + +static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) +{ + struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave; + u64 xstate_bv = xsave->xsave_hdr.xstate_bv; + u64 valid; + + /* + * Copy legacy XSAVE area, to avoid complications with CPUID + * leaves 0 and 1 in the loop below. + */ + memcpy(dest, xsave, XSAVE_HDR_OFFSET); + + /* Set XSTATE_BV */ + *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv; + + /* + * Copy each region from the possibly compacted offset to the + * non-compacted offset. + */ + valid = xstate_bv & ~XSTATE_FPSSE; + while (valid) { + u64 feature = valid & -valid; + int index = fls64(feature) - 1; + void *src = get_xsave_addr(xsave, feature); + + if (src) { + u32 size, offset, ecx, edx; + cpuid_count(XSTATE_CPUID, index, + &size, &offset, &ecx, &edx); + memcpy(dest + offset, src, size); + } + + valid -= feature; + } +} + +static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) +{ + struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave; + u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET); + u64 valid; + + /* + * Copy legacy XSAVE area, to avoid complications with CPUID + * leaves 0 and 1 in the loop below. + */ + memcpy(xsave, src, XSAVE_HDR_OFFSET); + + /* Set XSTATE_BV and possibly XCOMP_BV. */ + xsave->xsave_hdr.xstate_bv = xstate_bv; + if (cpu_has_xsaves) + xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; + + /* + * Copy each region from the non-compacted offset to the + * possibly compacted offset. + */ + valid = xstate_bv & ~XSTATE_FPSSE; + while (valid) { + u64 feature = valid & -valid; + int index = fls64(feature) - 1; + void *dest = get_xsave_addr(xsave, feature); + + if (dest) { + u32 size, offset, ecx, edx; + cpuid_count(XSTATE_CPUID, index, + &size, &offset, &ecx, &edx); + memcpy(dest, src + offset, size); + } else + WARN_ON_ONCE(1); + + valid -= feature; + } +} + +static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) +{ + if (cpu_has_xsave) { + memset(guest_xsave, 0, sizeof(struct kvm_xsave)); + fill_xsave((u8 *) guest_xsave->region, vcpu); + } else { + memcpy(guest_xsave->region, + &vcpu->arch.guest_fpu.state->fxsave, + sizeof(struct i387_fxsave_struct)); + *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] = + XSTATE_FPSSE; + } +} + +static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) +{ + u64 xstate_bv = + *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; + + if (cpu_has_xsave) { + /* + * Here we allow setting states that are not present in + * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility + * with old userspace. + */ + if (xstate_bv & ~kvm_supported_xcr0()) + return -EINVAL; + load_xsave(vcpu, (u8 *)guest_xsave->region); + } else { + if (xstate_bv & ~XSTATE_FPSSE) + return -EINVAL; + memcpy(&vcpu->arch.guest_fpu.state->fxsave, + guest_xsave->region, sizeof(struct i387_fxsave_struct)); + } + return 0; +} + +static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, + struct kvm_xcrs *guest_xcrs) +{ + if (!cpu_has_xsave) { + guest_xcrs->nr_xcrs = 0; + return; + } + + guest_xcrs->nr_xcrs = 1; + guest_xcrs->flags = 0; + guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK; + guest_xcrs->xcrs[0].value = vcpu->arch.xcr0; +} + +static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, + struct kvm_xcrs *guest_xcrs) +{ + int i, r = 0; + + if (!cpu_has_xsave) + return -EINVAL; + + if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags) + return -EINVAL; + + for (i = 0; i < guest_xcrs->nr_xcrs; i++) + /* Only support XCR0 currently */ + if (guest_xcrs->xcrs[i].xcr == XCR_XFEATURE_ENABLED_MASK) { + r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK, + guest_xcrs->xcrs[i].value); + break; + } + if (r) + r = -EINVAL; + return r; +} + +/* + * kvm_set_guest_paused() indicates to the guest kernel that it has been + * stopped by the hypervisor. This function will be called from the host only. + * EINVAL is returned when the host attempts to set the flag for a guest that + * does not support pv clocks. + */ +static int kvm_set_guest_paused(struct kvm_vcpu *vcpu) +{ + if (!vcpu->arch.pv_time_enabled) + return -EINVAL; + vcpu->arch.pvclock_set_guest_stopped_request = true; + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + return 0; +} + +long kvm_arch_vcpu_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + int r; + union { + struct kvm_lapic_state *lapic; + struct kvm_xsave *xsave; + struct kvm_xcrs *xcrs; + void *buffer; + } u; + + u.buffer = NULL; + switch (ioctl) { + case KVM_GET_LAPIC: { + r = -EINVAL; + if (!vcpu->arch.apic) + goto out; + u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); + + r = -ENOMEM; + if (!u.lapic) + goto out; + r = kvm_vcpu_ioctl_get_lapic(vcpu, u.lapic); + if (r) + goto out; + r = -EFAULT; + if (copy_to_user(argp, u.lapic, sizeof(struct kvm_lapic_state))) + goto out; + r = 0; + break; + } + case KVM_SET_LAPIC: { + r = -EINVAL; + if (!vcpu->arch.apic) + goto out; + u.lapic = memdup_user(argp, sizeof(*u.lapic)); + if (IS_ERR(u.lapic)) + return PTR_ERR(u.lapic); + + r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic); + break; + } + case KVM_INTERRUPT: { + struct kvm_interrupt irq; + + r = -EFAULT; + if (copy_from_user(&irq, argp, sizeof irq)) + goto out; + r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); + break; + } + case KVM_NMI: { + r = kvm_vcpu_ioctl_nmi(vcpu); + break; + } + case KVM_SET_CPUID: { + struct kvm_cpuid __user *cpuid_arg = argp; + struct kvm_cpuid cpuid; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) + goto out; + r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries); + break; + } + case KVM_SET_CPUID2: { + struct kvm_cpuid2 __user *cpuid_arg = argp; + struct kvm_cpuid2 cpuid; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) + goto out; + r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid, + cpuid_arg->entries); + break; + } + case KVM_GET_CPUID2: { + struct kvm_cpuid2 __user *cpuid_arg = argp; + struct kvm_cpuid2 cpuid; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) + goto out; + r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid, + cpuid_arg->entries); + if (r) + goto out; + r = -EFAULT; + if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid)) + goto out; + r = 0; + break; + } + case KVM_GET_MSRS: + r = msr_io(vcpu, argp, kvm_get_msr, 1); + break; + case KVM_SET_MSRS: + r = msr_io(vcpu, argp, do_set_msr, 0); + break; + case KVM_TPR_ACCESS_REPORTING: { + struct kvm_tpr_access_ctl tac; + + r = -EFAULT; + if (copy_from_user(&tac, argp, sizeof tac)) + goto out; + r = vcpu_ioctl_tpr_access_reporting(vcpu, &tac); + if (r) + goto out; + r = -EFAULT; + if (copy_to_user(argp, &tac, sizeof tac)) + goto out; + r = 0; + break; + }; + case KVM_SET_VAPIC_ADDR: { + struct kvm_vapic_addr va; + + r = -EINVAL; + if (!irqchip_in_kernel(vcpu->kvm)) + goto out; + r = -EFAULT; + if (copy_from_user(&va, argp, sizeof va)) + goto out; + r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); + break; + } + case KVM_X86_SETUP_MCE: { + u64 mcg_cap; + + r = -EFAULT; + if (copy_from_user(&mcg_cap, argp, sizeof mcg_cap)) + goto out; + r = kvm_vcpu_ioctl_x86_setup_mce(vcpu, mcg_cap); + break; + } + case KVM_X86_SET_MCE: { + struct kvm_x86_mce mce; + + r = -EFAULT; + if (copy_from_user(&mce, argp, sizeof mce)) + goto out; + r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce); + break; + } + case KVM_GET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events); + + r = -EFAULT; + if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events))) + break; + r = 0; + break; + } + case KVM_SET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + r = -EFAULT; + if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events))) + break; + + r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); + break; + } + case KVM_GET_DEBUGREGS: { + struct kvm_debugregs dbgregs; + + kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); + + r = -EFAULT; + if (copy_to_user(argp, &dbgregs, + sizeof(struct kvm_debugregs))) + break; + r = 0; + break; + } + case KVM_SET_DEBUGREGS: { + struct kvm_debugregs dbgregs; + + r = -EFAULT; + if (copy_from_user(&dbgregs, argp, + sizeof(struct kvm_debugregs))) + break; + + r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs); + break; + } + case KVM_GET_XSAVE: { + u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL); + r = -ENOMEM; + if (!u.xsave) + break; + + kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave); + + r = -EFAULT; + if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave))) + break; + r = 0; + break; + } + case KVM_SET_XSAVE: { + u.xsave = memdup_user(argp, sizeof(*u.xsave)); + if (IS_ERR(u.xsave)) + return PTR_ERR(u.xsave); + + r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); + break; + } + case KVM_GET_XCRS: { + u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL); + r = -ENOMEM; + if (!u.xcrs) + break; + + kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs); + + r = -EFAULT; + if (copy_to_user(argp, u.xcrs, + sizeof(struct kvm_xcrs))) + break; + r = 0; + break; + } + case KVM_SET_XCRS: { + u.xcrs = memdup_user(argp, sizeof(*u.xcrs)); + if (IS_ERR(u.xcrs)) + return PTR_ERR(u.xcrs); + + r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs); + break; + } + case KVM_SET_TSC_KHZ: { + u32 user_tsc_khz; + + r = -EINVAL; + user_tsc_khz = (u32)arg; + + if (user_tsc_khz >= kvm_max_guest_tsc_khz) + goto out; + + if (user_tsc_khz == 0) + user_tsc_khz = tsc_khz; + + kvm_set_tsc_khz(vcpu, user_tsc_khz); + + r = 0; + goto out; + } + case KVM_GET_TSC_KHZ: { + r = vcpu->arch.virtual_tsc_khz; + goto out; + } + case KVM_KVMCLOCK_CTRL: { + r = kvm_set_guest_paused(vcpu); + goto out; + } + default: + r = -EINVAL; + } +out: + kfree(u.buffer); + return r; +} + +int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) +{ + return VM_FAULT_SIGBUS; +} + +static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) +{ + int ret; + + if (addr > (unsigned int)(-3 * PAGE_SIZE)) + return -EINVAL; + ret = kvm_x86_ops->set_tss_addr(kvm, addr); + return ret; +} + +static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, + u64 ident_addr) +{ + kvm->arch.ept_identity_map_addr = ident_addr; + return 0; +} + +static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, + u32 kvm_nr_mmu_pages) +{ + if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) + return -EINVAL; + + mutex_lock(&kvm->slots_lock); + + kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages); + kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages; + + mutex_unlock(&kvm->slots_lock); + return 0; +} + +static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) +{ + return kvm->arch.n_max_mmu_pages; +} + +static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) +{ + int r; + + r = 0; + switch (chip->chip_id) { + case KVM_IRQCHIP_PIC_MASTER: + memcpy(&chip->chip.pic, + &pic_irqchip(kvm)->pics[0], + sizeof(struct kvm_pic_state)); + break; + case KVM_IRQCHIP_PIC_SLAVE: + memcpy(&chip->chip.pic, + &pic_irqchip(kvm)->pics[1], + sizeof(struct kvm_pic_state)); + break; + case KVM_IRQCHIP_IOAPIC: + r = kvm_get_ioapic(kvm, &chip->chip.ioapic); + break; + default: + r = -EINVAL; + break; + } + return r; +} + +static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) +{ + int r; + + r = 0; + switch (chip->chip_id) { + case KVM_IRQCHIP_PIC_MASTER: + spin_lock(&pic_irqchip(kvm)->lock); + memcpy(&pic_irqchip(kvm)->pics[0], + &chip->chip.pic, + sizeof(struct kvm_pic_state)); + spin_unlock(&pic_irqchip(kvm)->lock); + break; + case KVM_IRQCHIP_PIC_SLAVE: + spin_lock(&pic_irqchip(kvm)->lock); + memcpy(&pic_irqchip(kvm)->pics[1], + &chip->chip.pic, + sizeof(struct kvm_pic_state)); + spin_unlock(&pic_irqchip(kvm)->lock); + break; + case KVM_IRQCHIP_IOAPIC: + r = kvm_set_ioapic(kvm, &chip->chip.ioapic); + break; + default: + r = -EINVAL; + break; + } + kvm_pic_update_irq(pic_irqchip(kvm)); + return r; +} + +static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) +{ + int r = 0; + + mutex_lock(&kvm->arch.vpit->pit_state.lock); + memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state)); + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + return r; +} + +static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) +{ + int r = 0; + + mutex_lock(&kvm->arch.vpit->pit_state.lock); + memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state)); + kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0); + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + return r; +} + +static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) +{ + int r = 0; + + mutex_lock(&kvm->arch.vpit->pit_state.lock); + memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels, + sizeof(ps->channels)); + ps->flags = kvm->arch.vpit->pit_state.flags; + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + memset(&ps->reserved, 0, sizeof(ps->reserved)); + return r; +} + +static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) +{ + int r = 0, start = 0; + u32 prev_legacy, cur_legacy; + mutex_lock(&kvm->arch.vpit->pit_state.lock); + prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; + cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY; + if (!prev_legacy && cur_legacy) + start = 1; + memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels, + sizeof(kvm->arch.vpit->pit_state.channels)); + kvm->arch.vpit->pit_state.flags = ps->flags; + kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start); + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + return r; +} + +static int kvm_vm_ioctl_reinject(struct kvm *kvm, + struct kvm_reinject_control *control) +{ + if (!kvm->arch.vpit) + return -ENXIO; + mutex_lock(&kvm->arch.vpit->pit_state.lock); + kvm->arch.vpit->pit_state.reinject = control->pit_reinject; + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + return 0; +} + +/** + * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot + * @kvm: kvm instance + * @log: slot id and address to which we copy the log + * + * We need to keep it in mind that VCPU threads can write to the bitmap + * concurrently. So, to avoid losing data, we keep the following order for + * each bit: + * + * 1. Take a snapshot of the bit and clear it if needed. + * 2. Write protect the corresponding page. + * 3. Flush TLB's if needed. + * 4. Copy the snapshot to the userspace. + * + * Between 2 and 3, the guest may write to the page using the remaining TLB + * entry. This is not a problem because the page will be reported dirty at + * step 4 using the snapshot taken before and step 3 ensures that successive + * writes will be logged for the next call. + */ +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +{ + int r; + struct kvm_memory_slot *memslot; + unsigned long n, i; + unsigned long *dirty_bitmap; + unsigned long *dirty_bitmap_buffer; + bool is_dirty = false; + + mutex_lock(&kvm->slots_lock); + + r = -EINVAL; + if (log->slot >= KVM_USER_MEM_SLOTS) + goto out; + + memslot = id_to_memslot(kvm->memslots, log->slot); + + dirty_bitmap = memslot->dirty_bitmap; + r = -ENOENT; + if (!dirty_bitmap) + goto out; + + n = kvm_dirty_bitmap_bytes(memslot); + + dirty_bitmap_buffer = dirty_bitmap + n / sizeof(long); + memset(dirty_bitmap_buffer, 0, n); + + spin_lock(&kvm->mmu_lock); + + for (i = 0; i < n / sizeof(long); i++) { + unsigned long mask; + gfn_t offset; + + if (!dirty_bitmap[i]) + continue; + + is_dirty = true; + + mask = xchg(&dirty_bitmap[i], 0); + dirty_bitmap_buffer[i] = mask; + + offset = i * BITS_PER_LONG; + kvm_mmu_write_protect_pt_masked(kvm, memslot, offset, mask); + } + + spin_unlock(&kvm->mmu_lock); + + /* See the comments in kvm_mmu_slot_remove_write_access(). */ + lockdep_assert_held(&kvm->slots_lock); + + /* + * All the TLBs can be flushed out of mmu lock, see the comments in + * kvm_mmu_slot_remove_write_access(). + */ + if (is_dirty) + kvm_flush_remote_tlbs(kvm); + + r = -EFAULT; + if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n)) + goto out; + + r = 0; +out: + mutex_unlock(&kvm->slots_lock); + return r; +} + +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, + bool line_status) +{ + if (!irqchip_in_kernel(kvm)) + return -ENXIO; + + irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + irq_event->irq, irq_event->level, + line_status); + return 0; +} + +long kvm_arch_vm_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm *kvm = filp->private_data; + void __user *argp = (void __user *)arg; + int r = -ENOTTY; + /* + * This union makes it completely explicit to gcc-3.x + * that these two variables' stack usage should be + * combined, not added together. + */ + union { + struct kvm_pit_state ps; + struct kvm_pit_state2 ps2; + struct kvm_pit_config pit_config; + } u; + + switch (ioctl) { + case KVM_SET_TSS_ADDR: + r = kvm_vm_ioctl_set_tss_addr(kvm, arg); + break; + case KVM_SET_IDENTITY_MAP_ADDR: { + u64 ident_addr; + + r = -EFAULT; + if (copy_from_user(&ident_addr, argp, sizeof ident_addr)) + goto out; + r = kvm_vm_ioctl_set_identity_map_addr(kvm, ident_addr); + break; + } + case KVM_SET_NR_MMU_PAGES: + r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); + break; + case KVM_GET_NR_MMU_PAGES: + r = kvm_vm_ioctl_get_nr_mmu_pages(kvm); + break; + case KVM_CREATE_IRQCHIP: { + struct kvm_pic *vpic; + + mutex_lock(&kvm->lock); + r = -EEXIST; + if (kvm->arch.vpic) + goto create_irqchip_unlock; + r = -EINVAL; + if (atomic_read(&kvm->online_vcpus)) + goto create_irqchip_unlock; + r = -ENOMEM; + vpic = kvm_create_pic(kvm); + if (vpic) { + r = kvm_ioapic_init(kvm); + if (r) { + mutex_lock(&kvm->slots_lock); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev_master); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev_slave); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev_eclr); + mutex_unlock(&kvm->slots_lock); + kfree(vpic); + goto create_irqchip_unlock; + } + } else + goto create_irqchip_unlock; + smp_wmb(); + kvm->arch.vpic = vpic; + smp_wmb(); + r = kvm_setup_default_irq_routing(kvm); + if (r) { + mutex_lock(&kvm->slots_lock); + mutex_lock(&kvm->irq_lock); + kvm_ioapic_destroy(kvm); + kvm_destroy_pic(kvm); + mutex_unlock(&kvm->irq_lock); + mutex_unlock(&kvm->slots_lock); + } + create_irqchip_unlock: + mutex_unlock(&kvm->lock); + break; + } + case KVM_CREATE_PIT: + u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY; + goto create_pit; + case KVM_CREATE_PIT2: + r = -EFAULT; + if (copy_from_user(&u.pit_config, argp, + sizeof(struct kvm_pit_config))) + goto out; + create_pit: + mutex_lock(&kvm->slots_lock); + r = -EEXIST; + if (kvm->arch.vpit) + goto create_pit_unlock; + r = -ENOMEM; + kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags); + if (kvm->arch.vpit) + r = 0; + create_pit_unlock: + mutex_unlock(&kvm->slots_lock); + break; + case KVM_GET_IRQCHIP: { + /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ + struct kvm_irqchip *chip; + + chip = memdup_user(argp, sizeof(*chip)); + if (IS_ERR(chip)) { + r = PTR_ERR(chip); + goto out; + } + + r = -ENXIO; + if (!irqchip_in_kernel(kvm)) + goto get_irqchip_out; + r = kvm_vm_ioctl_get_irqchip(kvm, chip); + if (r) + goto get_irqchip_out; + r = -EFAULT; + if (copy_to_user(argp, chip, sizeof *chip)) + goto get_irqchip_out; + r = 0; + get_irqchip_out: + kfree(chip); + break; + } + case KVM_SET_IRQCHIP: { + /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ + struct kvm_irqchip *chip; + + chip = memdup_user(argp, sizeof(*chip)); + if (IS_ERR(chip)) { + r = PTR_ERR(chip); + goto out; + } + + r = -ENXIO; + if (!irqchip_in_kernel(kvm)) + goto set_irqchip_out; + r = kvm_vm_ioctl_set_irqchip(kvm, chip); + if (r) + goto set_irqchip_out; + r = 0; + set_irqchip_out: + kfree(chip); + break; + } + case KVM_GET_PIT: { + r = -EFAULT; + if (copy_from_user(&u.ps, argp, sizeof(struct kvm_pit_state))) + goto out; + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; + r = kvm_vm_ioctl_get_pit(kvm, &u.ps); + if (r) + goto out; + r = -EFAULT; + if (copy_to_user(argp, &u.ps, sizeof(struct kvm_pit_state))) + goto out; + r = 0; + break; + } + case KVM_SET_PIT: { + r = -EFAULT; + if (copy_from_user(&u.ps, argp, sizeof u.ps)) + goto out; + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; + r = kvm_vm_ioctl_set_pit(kvm, &u.ps); + break; + } + case KVM_GET_PIT2: { + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; + r = kvm_vm_ioctl_get_pit2(kvm, &u.ps2); + if (r) + goto out; + r = -EFAULT; + if (copy_to_user(argp, &u.ps2, sizeof(u.ps2))) + goto out; + r = 0; + break; + } + case KVM_SET_PIT2: { + r = -EFAULT; + if (copy_from_user(&u.ps2, argp, sizeof(u.ps2))) + goto out; + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; + r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); + break; + } + case KVM_REINJECT_CONTROL: { + struct kvm_reinject_control control; + r = -EFAULT; + if (copy_from_user(&control, argp, sizeof(control))) + goto out; + r = kvm_vm_ioctl_reinject(kvm, &control); + break; + } + case KVM_XEN_HVM_CONFIG: { + r = -EFAULT; + if (copy_from_user(&kvm->arch.xen_hvm_config, argp, + sizeof(struct kvm_xen_hvm_config))) + goto out; + r = -EINVAL; + if (kvm->arch.xen_hvm_config.flags) + goto out; + r = 0; + break; + } + case KVM_SET_CLOCK: { + struct kvm_clock_data user_ns; + u64 now_ns; + s64 delta; + + r = -EFAULT; + if (copy_from_user(&user_ns, argp, sizeof(user_ns))) + goto out; + + r = -EINVAL; + if (user_ns.flags) + goto out; + + r = 0; + local_irq_disable(); + now_ns = get_kernel_ns(); + delta = user_ns.clock - now_ns; + local_irq_enable(); + kvm->arch.kvmclock_offset = delta; + kvm_gen_update_masterclock(kvm); + break; + } + case KVM_GET_CLOCK: { + struct kvm_clock_data user_ns; + u64 now_ns; + + local_irq_disable(); + now_ns = get_kernel_ns(); + user_ns.clock = kvm->arch.kvmclock_offset + now_ns; + local_irq_enable(); + user_ns.flags = 0; + memset(&user_ns.pad, 0, sizeof(user_ns.pad)); + + r = -EFAULT; + if (copy_to_user(argp, &user_ns, sizeof(user_ns))) + goto out; + r = 0; + break; + } + + default: + ; + } +out: + return r; +} + +static void kvm_init_msr_list(void) +{ + u32 dummy[2]; + unsigned i, j; + + /* skip the first msrs in the list. KVM-specific */ + for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) { + if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) + continue; + + /* + * Even MSRs that are valid in the host may not be exposed + * to the guests in some cases. We could work around this + * in VMX with the generic MSR save/load machinery, but it + * is not really worthwhile since it will really only + * happen with nested virtualization. + */ + switch (msrs_to_save[i]) { + case MSR_IA32_BNDCFGS: + if (!kvm_x86_ops->mpx_supported()) + continue; + break; + default: + break; + } + + if (j < i) + msrs_to_save[j] = msrs_to_save[i]; + j++; + } + num_msrs_to_save = j; +} + +static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, + const void *v) +{ + int handled = 0; + int n; + + do { + n = min(len, 8); + if (!(vcpu->arch.apic && + !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, n, v)) + && kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + break; + handled += n; + addr += n; + len -= n; + v += n; + } while (len); + + return handled; +} + +static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) +{ + int handled = 0; + int n; + + do { + n = min(len, 8); + if (!(vcpu->arch.apic && + !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, n, v)) + && kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + break; + trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v); + handled += n; + addr += n; + len -= n; + v += n; + } while (len); + + return handled; +} + +static void kvm_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + kvm_x86_ops->set_segment(vcpu, var, seg); +} + +void kvm_get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + kvm_x86_ops->get_segment(vcpu, var, seg); +} + +gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, + struct x86_exception *exception) +{ + gpa_t t_gpa; + + BUG_ON(!mmu_is_nested(vcpu)); + + /* NPT walks are always user-walks */ + access |= PFERR_USER_MASK; + t_gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, exception); + + return t_gpa; +} + +gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, + struct x86_exception *exception) +{ + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); +} + + gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, + struct x86_exception *exception) +{ + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + access |= PFERR_FETCH_MASK; + return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); +} + +gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, + struct x86_exception *exception) +{ + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + access |= PFERR_WRITE_MASK; + return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); +} + +/* uses this to access any guest's mapped memory without checking CPL */ +gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, + struct x86_exception *exception) +{ + return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, exception); +} + +static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, + struct kvm_vcpu *vcpu, u32 access, + struct x86_exception *exception) +{ + void *data = val; + int r = X86EMUL_CONTINUE; + + while (bytes) { + gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access, + exception); + unsigned offset = addr & (PAGE_SIZE-1); + unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); + int ret; + + if (gpa == UNMAPPED_GVA) + return X86EMUL_PROPAGATE_FAULT; + ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, data, + offset, toread); + if (ret < 0) { + r = X86EMUL_IO_NEEDED; + goto out; + } + + bytes -= toread; + data += toread; + addr += toread; + } +out: + return r; +} + +/* used for instruction fetching */ +static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, + gva_t addr, void *val, unsigned int bytes, + struct x86_exception *exception) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + unsigned offset; + int ret; + + /* Inline kvm_read_guest_virt_helper for speed. */ + gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access|PFERR_FETCH_MASK, + exception); + if (unlikely(gpa == UNMAPPED_GVA)) + return X86EMUL_PROPAGATE_FAULT; + + offset = addr & (PAGE_SIZE-1); + if (WARN_ON(offset + bytes > PAGE_SIZE)) + bytes = (unsigned)PAGE_SIZE - offset; + ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, val, + offset, bytes); + if (unlikely(ret < 0)) + return X86EMUL_IO_NEEDED; + + return X86EMUL_CONTINUE; +} + +int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt, + gva_t addr, void *val, unsigned int bytes, + struct x86_exception *exception) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + + return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, + exception); +} +EXPORT_SYMBOL_GPL(kvm_read_guest_virt); + +static int kvm_read_guest_virt_system(struct x86_emulate_ctxt *ctxt, + gva_t addr, void *val, unsigned int bytes, + struct x86_exception *exception) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception); +} + +int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, + gva_t addr, void *val, + unsigned int bytes, + struct x86_exception *exception) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + void *data = val; + int r = X86EMUL_CONTINUE; + + while (bytes) { + gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, + PFERR_WRITE_MASK, + exception); + unsigned offset = addr & (PAGE_SIZE-1); + unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); + int ret; + + if (gpa == UNMAPPED_GVA) + return X86EMUL_PROPAGATE_FAULT; + ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite); + if (ret < 0) { + r = X86EMUL_IO_NEEDED; + goto out; + } + + bytes -= towrite; + data += towrite; + addr += towrite; + } +out: + return r; +} +EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); + +static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, + gpa_t *gpa, struct x86_exception *exception, + bool write) +{ + u32 access = ((kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0) + | (write ? PFERR_WRITE_MASK : 0); + + if (vcpu_match_mmio_gva(vcpu, gva) + && !permission_fault(vcpu, vcpu->arch.walk_mmu, + vcpu->arch.access, access)) { + *gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT | + (gva & (PAGE_SIZE - 1)); + trace_vcpu_match_mmio(gva, *gpa, write, false); + return 1; + } + + *gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + + if (*gpa == UNMAPPED_GVA) + return -1; + + /* For APIC access vmexit */ + if ((*gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + return 1; + + if (vcpu_match_mmio_gpa(vcpu, *gpa)) { + trace_vcpu_match_mmio(gva, *gpa, write, true); + return 1; + } + + return 0; +} + +int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, + const void *val, int bytes) +{ + int ret; + + ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); + if (ret < 0) + return 0; + kvm_mmu_pte_write(vcpu, gpa, val, bytes); + return 1; +} + +struct read_write_emulator_ops { + int (*read_write_prepare)(struct kvm_vcpu *vcpu, void *val, + int bytes); + int (*read_write_emulate)(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes); + int (*read_write_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, + int bytes, void *val); + int (*read_write_exit_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes); + bool write; +}; + +static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) +{ + if (vcpu->mmio_read_completed) { + trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, + vcpu->mmio_fragments[0].gpa, *(u64 *)val); + vcpu->mmio_read_completed = 0; + return 1; + } + + return 0; +} + +static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + return !kvm_read_guest(vcpu->kvm, gpa, val, bytes); +} + +static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + return emulator_write_phys(vcpu, gpa, val, bytes); +} + +static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val) +{ + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val); + return vcpu_mmio_write(vcpu, gpa, bytes, val); +} + +static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0); + return X86EMUL_IO_NEEDED; +} + +static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0]; + + memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len)); + return X86EMUL_CONTINUE; +} + +static const struct read_write_emulator_ops read_emultor = { + .read_write_prepare = read_prepare, + .read_write_emulate = read_emulate, + .read_write_mmio = vcpu_mmio_read, + .read_write_exit_mmio = read_exit_mmio, +}; + +static const struct read_write_emulator_ops write_emultor = { + .read_write_emulate = write_emulate, + .read_write_mmio = write_mmio, + .read_write_exit_mmio = write_exit_mmio, + .write = true, +}; + +static int emulator_read_write_onepage(unsigned long addr, void *val, + unsigned int bytes, + struct x86_exception *exception, + struct kvm_vcpu *vcpu, + const struct read_write_emulator_ops *ops) +{ + gpa_t gpa; + int handled, ret; + bool write = ops->write; + struct kvm_mmio_fragment *frag; + + ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); + + if (ret < 0) + return X86EMUL_PROPAGATE_FAULT; + + /* For APIC access vmexit */ + if (ret) + goto mmio; + + if (ops->read_write_emulate(vcpu, gpa, val, bytes)) + return X86EMUL_CONTINUE; + +mmio: + /* + * Is this MMIO handled locally? + */ + handled = ops->read_write_mmio(vcpu, gpa, bytes, val); + if (handled == bytes) + return X86EMUL_CONTINUE; + + gpa += handled; + bytes -= handled; + val += handled; + + WARN_ON(vcpu->mmio_nr_fragments >= KVM_MAX_MMIO_FRAGMENTS); + frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++]; + frag->gpa = gpa; + frag->data = val; + frag->len = bytes; + return X86EMUL_CONTINUE; +} + +int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, + void *val, unsigned int bytes, + struct x86_exception *exception, + const struct read_write_emulator_ops *ops) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + gpa_t gpa; + int rc; + + if (ops->read_write_prepare && + ops->read_write_prepare(vcpu, val, bytes)) + return X86EMUL_CONTINUE; + + vcpu->mmio_nr_fragments = 0; + + /* Crossing a page boundary? */ + if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { + int now; + + now = -addr & ~PAGE_MASK; + rc = emulator_read_write_onepage(addr, val, now, exception, + vcpu, ops); + + if (rc != X86EMUL_CONTINUE) + return rc; + addr += now; + val += now; + bytes -= now; + } + + rc = emulator_read_write_onepage(addr, val, bytes, exception, + vcpu, ops); + if (rc != X86EMUL_CONTINUE) + return rc; + + if (!vcpu->mmio_nr_fragments) + return rc; + + gpa = vcpu->mmio_fragments[0].gpa; + + vcpu->mmio_needed = 1; + vcpu->mmio_cur_fragment = 0; + + vcpu->run->mmio.len = min(8u, vcpu->mmio_fragments[0].len); + vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write; + vcpu->run->exit_reason = KVM_EXIT_MMIO; + vcpu->run->mmio.phys_addr = gpa; + + return ops->read_write_exit_mmio(vcpu, gpa, val, bytes); +} + +static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, + void *val, + unsigned int bytes, + struct x86_exception *exception) +{ + return emulator_read_write(ctxt, addr, val, bytes, + exception, &read_emultor); +} + +int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, + const void *val, + unsigned int bytes, + struct x86_exception *exception) +{ + return emulator_read_write(ctxt, addr, (void *)val, bytes, + exception, &write_emultor); +} + +#define CMPXCHG_TYPE(t, ptr, old, new) \ + (cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old)) + +#ifdef CONFIG_X86_64 +# define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new) +#else +# define CMPXCHG64(ptr, old, new) \ + (cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old)) +#endif + +static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, + const void *old, + const void *new, + unsigned int bytes, + struct x86_exception *exception) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + gpa_t gpa; + struct page *page; + char *kaddr; + bool exchanged; + + /* guests cmpxchg8b have to be emulated atomically */ + if (bytes > 8 || (bytes & (bytes - 1))) + goto emul_write; + + gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL); + + if (gpa == UNMAPPED_GVA || + (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + goto emul_write; + + if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) + goto emul_write; + + page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + if (is_error_page(page)) + goto emul_write; + + kaddr = kmap_atomic(page); + kaddr += offset_in_page(gpa); + switch (bytes) { + case 1: + exchanged = CMPXCHG_TYPE(u8, kaddr, old, new); + break; + case 2: + exchanged = CMPXCHG_TYPE(u16, kaddr, old, new); + break; + case 4: + exchanged = CMPXCHG_TYPE(u32, kaddr, old, new); + break; + case 8: + exchanged = CMPXCHG64(kaddr, old, new); + break; + default: + BUG(); + } + kunmap_atomic(kaddr); + kvm_release_page_dirty(page); + + if (!exchanged) + return X86EMUL_CMPXCHG_FAILED; + + mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT); + kvm_mmu_pte_write(vcpu, gpa, new, bytes); + + return X86EMUL_CONTINUE; + +emul_write: + printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); + + return emulator_write_emulated(ctxt, addr, new, bytes, exception); +} + +static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) +{ + /* TODO: String I/O for in kernel device */ + int r; + + if (vcpu->arch.pio.in) + r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port, + vcpu->arch.pio.size, pd); + else + r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, + vcpu->arch.pio.port, vcpu->arch.pio.size, + pd); + return r; +} + +static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, + unsigned short port, void *val, + unsigned int count, bool in) +{ + vcpu->arch.pio.port = port; + vcpu->arch.pio.in = in; + vcpu->arch.pio.count = count; + vcpu->arch.pio.size = size; + + if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { + vcpu->arch.pio.count = 0; + return 1; + } + + vcpu->run->exit_reason = KVM_EXIT_IO; + vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; + vcpu->run->io.size = size; + vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; + vcpu->run->io.count = count; + vcpu->run->io.port = port; + + return 0; +} + +static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, void *val, + unsigned int count) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + int ret; + + if (vcpu->arch.pio.count) + goto data_avail; + + ret = emulator_pio_in_out(vcpu, size, port, val, count, true); + if (ret) { +data_avail: + memcpy(val, vcpu->arch.pio_data, size * count); + trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data); + vcpu->arch.pio.count = 0; + return 1; + } + + return 0; +} + +static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, + const void *val, unsigned int count) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + memcpy(vcpu->arch.pio_data, val, size * count); + trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data); + return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); +} + +static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) +{ + return kvm_x86_ops->get_segment_base(vcpu, seg); +} + +static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) +{ + kvm_mmu_invlpg(emul_to_vcpu(ctxt), address); +} + +int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) +{ + if (!need_emulate_wbinvd(vcpu)) + return X86EMUL_CONTINUE; + + if (kvm_x86_ops->has_wbinvd_exit()) { + int cpu = get_cpu(); + + cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); + smp_call_function_many(vcpu->arch.wbinvd_dirty_mask, + wbinvd_ipi, NULL, 1); + put_cpu(); + cpumask_clear(vcpu->arch.wbinvd_dirty_mask); + } else + wbinvd(); + return X86EMUL_CONTINUE; +} +EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd); + +static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) +{ + kvm_emulate_wbinvd(emul_to_vcpu(ctxt)); +} + +int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) +{ + return _kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); +} + +int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) +{ + + return __kvm_set_dr(emul_to_vcpu(ctxt), dr, value); +} + +static u64 mk_cr_64(u64 curr_cr, u32 new_val) +{ + return (curr_cr & ~((1ULL << 32) - 1)) | new_val; +} + +static unsigned long emulator_get_cr(struct x86_emulate_ctxt *ctxt, int cr) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + unsigned long value; + + switch (cr) { + case 0: + value = kvm_read_cr0(vcpu); + break; + case 2: + value = vcpu->arch.cr2; + break; + case 3: + value = kvm_read_cr3(vcpu); + break; + case 4: + value = kvm_read_cr4(vcpu); + break; + case 8: + value = kvm_get_cr8(vcpu); + break; + default: + kvm_err("%s: unexpected cr %u\n", __func__, cr); + return 0; + } + + return value; +} + +static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + int res = 0; + + switch (cr) { + case 0: + res = kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val)); + break; + case 2: + vcpu->arch.cr2 = val; + break; + case 3: + res = kvm_set_cr3(vcpu, val); + break; + case 4: + res = kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val)); + break; + case 8: + res = kvm_set_cr8(vcpu, val); + break; + default: + kvm_err("%s: unexpected cr %u\n", __func__, cr); + res = -1; + } + + return res; +} + +static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) +{ + return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt)); +} + +static void emulator_get_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) +{ + kvm_x86_ops->get_gdt(emul_to_vcpu(ctxt), dt); +} + +static void emulator_get_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) +{ + kvm_x86_ops->get_idt(emul_to_vcpu(ctxt), dt); +} + +static void emulator_set_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) +{ + kvm_x86_ops->set_gdt(emul_to_vcpu(ctxt), dt); +} + +static void emulator_set_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) +{ + kvm_x86_ops->set_idt(emul_to_vcpu(ctxt), dt); +} + +static unsigned long emulator_get_cached_segment_base( + struct x86_emulate_ctxt *ctxt, int seg) +{ + return get_segment_base(emul_to_vcpu(ctxt), seg); +} + +static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector, + struct desc_struct *desc, u32 *base3, + int seg) +{ + struct kvm_segment var; + + kvm_get_segment(emul_to_vcpu(ctxt), &var, seg); + *selector = var.selector; + + if (var.unusable) { + memset(desc, 0, sizeof(*desc)); + return false; + } + + if (var.g) + var.limit >>= 12; + set_desc_limit(desc, var.limit); + set_desc_base(desc, (unsigned long)var.base); +#ifdef CONFIG_X86_64 + if (base3) + *base3 = var.base >> 32; +#endif + desc->type = var.type; + desc->s = var.s; + desc->dpl = var.dpl; + desc->p = var.present; + desc->avl = var.avl; + desc->l = var.l; + desc->d = var.db; + desc->g = var.g; + + return true; +} + +static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector, + struct desc_struct *desc, u32 base3, + int seg) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + struct kvm_segment var; + + var.selector = selector; + var.base = get_desc_base(desc); +#ifdef CONFIG_X86_64 + var.base |= ((u64)base3) << 32; +#endif + var.limit = get_desc_limit(desc); + if (desc->g) + var.limit = (var.limit << 12) | 0xfff; + var.type = desc->type; + var.dpl = desc->dpl; + var.db = desc->d; + var.s = desc->s; + var.l = desc->l; + var.g = desc->g; + var.avl = desc->avl; + var.present = desc->p; + var.unusable = !var.present; + var.padding = 0; + + kvm_set_segment(vcpu, &var, seg); + return; +} + +static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 *pdata) +{ + return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); +} + +static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 data) +{ + struct msr_data msr; + + msr.data = data; + msr.index = msr_index; + msr.host_initiated = false; + return kvm_set_msr(emul_to_vcpu(ctxt), &msr); +} + +static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, + u32 pmc) +{ + return kvm_pmu_check_pmc(emul_to_vcpu(ctxt), pmc); +} + +static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, + u32 pmc, u64 *pdata) +{ + return kvm_pmu_read_pmc(emul_to_vcpu(ctxt), pmc, pdata); +} + +static void emulator_halt(struct x86_emulate_ctxt *ctxt) +{ + emul_to_vcpu(ctxt)->arch.halt_request = 1; +} + +static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt) +{ + preempt_disable(); + kvm_load_guest_fpu(emul_to_vcpu(ctxt)); + /* + * CR0.TS may reference the host fpu state, not the guest fpu state, + * so it may be clear at this point. + */ + clts(); +} + +static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt) +{ + preempt_enable(); +} + +static int emulator_intercept(struct x86_emulate_ctxt *ctxt, + struct x86_instruction_info *info, + enum x86_intercept_stage stage) +{ + return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage); +} + +static void emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx); +} + +static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg) +{ + return kvm_register_read(emul_to_vcpu(ctxt), reg); +} + +static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulong val) +{ + kvm_register_write(emul_to_vcpu(ctxt), reg, val); +} + +static const struct x86_emulate_ops emulate_ops = { + .read_gpr = emulator_read_gpr, + .write_gpr = emulator_write_gpr, + .read_std = kvm_read_guest_virt_system, + .write_std = kvm_write_guest_virt_system, + .fetch = kvm_fetch_guest_virt, + .read_emulated = emulator_read_emulated, + .write_emulated = emulator_write_emulated, + .cmpxchg_emulated = emulator_cmpxchg_emulated, + .invlpg = emulator_invlpg, + .pio_in_emulated = emulator_pio_in_emulated, + .pio_out_emulated = emulator_pio_out_emulated, + .get_segment = emulator_get_segment, + .set_segment = emulator_set_segment, + .get_cached_segment_base = emulator_get_cached_segment_base, + .get_gdt = emulator_get_gdt, + .get_idt = emulator_get_idt, + .set_gdt = emulator_set_gdt, + .set_idt = emulator_set_idt, + .get_cr = emulator_get_cr, + .set_cr = emulator_set_cr, + .cpl = emulator_get_cpl, + .get_dr = emulator_get_dr, + .set_dr = emulator_set_dr, + .set_msr = emulator_set_msr, + .get_msr = emulator_get_msr, + .check_pmc = emulator_check_pmc, + .read_pmc = emulator_read_pmc, + .halt = emulator_halt, + .wbinvd = emulator_wbinvd, + .fix_hypercall = emulator_fix_hypercall, + .get_fpu = emulator_get_fpu, + .put_fpu = emulator_put_fpu, + .intercept = emulator_intercept, + .get_cpuid = emulator_get_cpuid, +}; + +static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) +{ + u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(vcpu); + /* + * an sti; sti; sequence only disable interrupts for the first + * instruction. So, if the last instruction, be it emulated or + * not, left the system with the INT_STI flag enabled, it + * means that the last instruction is an sti. We should not + * leave the flag on in this case. The same goes for mov ss + */ + if (int_shadow & mask) + mask = 0; + if (unlikely(int_shadow || mask)) { + kvm_x86_ops->set_interrupt_shadow(vcpu, mask); + if (!mask) + kvm_make_request(KVM_REQ_EVENT, vcpu); + } +} + +static bool inject_emulated_exception(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + if (ctxt->exception.vector == PF_VECTOR) + return kvm_propagate_fault(vcpu, &ctxt->exception); + + if (ctxt->exception.error_code_valid) + kvm_queue_exception_e(vcpu, ctxt->exception.vector, + ctxt->exception.error_code); + else + kvm_queue_exception(vcpu, ctxt->exception.vector); + return false; +} + +static void init_emulate_ctxt(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + int cs_db, cs_l; + + kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + + ctxt->eflags = kvm_get_rflags(vcpu); + ctxt->eip = kvm_rip_read(vcpu); + ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : + (ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 : + (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : + cs_db ? X86EMUL_MODE_PROT32 : + X86EMUL_MODE_PROT16; + ctxt->guest_mode = is_guest_mode(vcpu); + + init_decode_cache(ctxt); + vcpu->arch.emulate_regs_need_sync_from_vcpu = false; +} + +int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) +{ + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + int ret; + + init_emulate_ctxt(vcpu); + + ctxt->op_bytes = 2; + ctxt->ad_bytes = 2; + ctxt->_eip = ctxt->eip + inc_eip; + ret = emulate_int_real(ctxt, irq); + + if (ret != X86EMUL_CONTINUE) + return EMULATE_FAIL; + + ctxt->eip = ctxt->_eip; + kvm_rip_write(vcpu, ctxt->eip); + kvm_set_rflags(vcpu, ctxt->eflags); + + if (irq == NMI_VECTOR) + vcpu->arch.nmi_pending = 0; + else + vcpu->arch.interrupt.pending = false; + + return EMULATE_DONE; +} +EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); + +static int handle_emulation_failure(struct kvm_vcpu *vcpu) +{ + int r = EMULATE_DONE; + + ++vcpu->stat.insn_emulation_fail; + trace_kvm_emulate_insn_failed(vcpu); + if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + r = EMULATE_FAIL; + } + kvm_queue_exception(vcpu, UD_VECTOR); + + return r; +} + +static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, + bool write_fault_to_shadow_pgtable, + int emulation_type) +{ + gpa_t gpa = cr2; + pfn_t pfn; + + if (emulation_type & EMULTYPE_NO_REEXECUTE) + return false; + + if (!vcpu->arch.mmu.direct_map) { + /* + * Write permission should be allowed since only + * write access need to be emulated. + */ + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + + /* + * If the mapping is invalid in guest, let cpu retry + * it to generate fault. + */ + if (gpa == UNMAPPED_GVA) + return true; + } + + /* + * Do not retry the unhandleable instruction if it faults on the + * readonly host memory, otherwise it will goto a infinite loop: + * retry instruction -> write #PF -> emulation fail -> retry + * instruction -> ... + */ + pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa)); + + /* + * If the instruction failed on the error pfn, it can not be fixed, + * report the error to userspace. + */ + if (is_error_noslot_pfn(pfn)) + return false; + + kvm_release_pfn_clean(pfn); + + /* The instructions are well-emulated on direct mmu. */ + if (vcpu->arch.mmu.direct_map) { + unsigned int indirect_shadow_pages; + + spin_lock(&vcpu->kvm->mmu_lock); + indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages; + spin_unlock(&vcpu->kvm->mmu_lock); + + if (indirect_shadow_pages) + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + + return true; + } + + /* + * if emulation was due to access to shadowed page table + * and it failed try to unshadow page and re-enter the + * guest to let CPU execute the instruction. + */ + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + + /* + * If the access faults on its page table, it can not + * be fixed by unprotecting shadow page and it should + * be reported to userspace. + */ + return !write_fault_to_shadow_pgtable; +} + +static bool retry_instruction(struct x86_emulate_ctxt *ctxt, + unsigned long cr2, int emulation_type) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + unsigned long last_retry_eip, last_retry_addr, gpa = cr2; + + last_retry_eip = vcpu->arch.last_retry_eip; + last_retry_addr = vcpu->arch.last_retry_addr; + + /* + * If the emulation is caused by #PF and it is non-page_table + * writing instruction, it means the VM-EXIT is caused by shadow + * page protected, we can zap the shadow page and retry this + * instruction directly. + * + * Note: if the guest uses a non-page-table modifying instruction + * on the PDE that points to the instruction, then we will unmap + * the instruction and go to an infinite loop. So, we cache the + * last retried eip and the last fault address, if we meet the eip + * and the address again, we can break out of the potential infinite + * loop. + */ + vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; + + if (!(emulation_type & EMULTYPE_RETRY)) + return false; + + if (x86_page_table_writing_insn(ctxt)) + return false; + + if (ctxt->eip == last_retry_eip && last_retry_addr == cr2) + return false; + + vcpu->arch.last_retry_eip = ctxt->eip; + vcpu->arch.last_retry_addr = cr2; + + if (!vcpu->arch.mmu.direct_map) + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + + return true; +} + +static int complete_emulated_mmio(struct kvm_vcpu *vcpu); +static int complete_emulated_pio(struct kvm_vcpu *vcpu); + +static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, + unsigned long *db) +{ + u32 dr6 = 0; + int i; + u32 enable, rwlen; + + enable = dr7; + rwlen = dr7 >> 16; + for (i = 0; i < 4; i++, enable >>= 2, rwlen >>= 4) + if ((enable & 3) && (rwlen & 15) == type && db[i] == addr) + dr6 |= (1 << i); + return dr6; +} + +static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflags, int *r) +{ + struct kvm_run *kvm_run = vcpu->run; + + /* + * rflags is the old, "raw" value of the flags. The new value has + * not been saved yet. + * + * This is correct even for TF set by the guest, because "the + * processor will not generate this exception after the instruction + * that sets the TF flag". + */ + if (unlikely(rflags & X86_EFLAGS_TF)) { + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | + DR6_RTM; + kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + *r = EMULATE_USER_EXIT; + } else { + vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF; + /* + * "Certain debug exceptions may clear bit 0-3. The + * remaining contents of the DR6 register are never + * cleared by the processor". + */ + vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 |= DR6_BS | DR6_RTM; + kvm_queue_exception(vcpu, DB_VECTOR); + } + } +} + +static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) +{ + struct kvm_run *kvm_run = vcpu->run; + unsigned long eip = vcpu->arch.emulate_ctxt.eip; + u32 dr6 = 0; + + if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) && + (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) { + dr6 = kvm_vcpu_check_hw_bp(eip, 0, + vcpu->arch.guest_debug_dr7, + vcpu->arch.eff_db); + + if (dr6 != 0) { + kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM; + kvm_run->debug.arch.pc = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); + + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + *r = EMULATE_USER_EXIT; + return true; + } + } + + if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK) && + !(kvm_get_rflags(vcpu) & X86_EFLAGS_RF)) { + dr6 = kvm_vcpu_check_hw_bp(eip, 0, + vcpu->arch.dr7, + vcpu->arch.db); + + if (dr6 != 0) { + vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 |= dr6 | DR6_RTM; + kvm_queue_exception(vcpu, DB_VECTOR); + *r = EMULATE_DONE; + return true; + } + } + + return false; +} + +int x86_emulate_instruction(struct kvm_vcpu *vcpu, + unsigned long cr2, + int emulation_type, + void *insn, + int insn_len) +{ + int r; + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + bool writeback = true; + bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable; + + /* + * Clear write_fault_to_shadow_pgtable here to ensure it is + * never reused. + */ + vcpu->arch.write_fault_to_shadow_pgtable = false; + kvm_clear_exception_queue(vcpu); + + if (!(emulation_type & EMULTYPE_NO_DECODE)) { + init_emulate_ctxt(vcpu); + + /* + * We will reenter on the same instruction since + * we do not set complete_userspace_io. This does not + * handle watchpoints yet, those would be handled in + * the emulate_ops. + */ + if (kvm_vcpu_check_breakpoint(vcpu, &r)) + return r; + + ctxt->interruptibility = 0; + ctxt->have_exception = false; + ctxt->exception.vector = -1; + ctxt->perm_ok = false; + + ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; + + r = x86_decode_insn(ctxt, insn, insn_len); + + trace_kvm_emulate_insn_start(vcpu); + ++vcpu->stat.insn_emulation; + if (r != EMULATION_OK) { + if (emulation_type & EMULTYPE_TRAP_UD) + return EMULATE_FAIL; + if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, + emulation_type)) + return EMULATE_DONE; + if (emulation_type & EMULTYPE_SKIP) + return EMULATE_FAIL; + return handle_emulation_failure(vcpu); + } + } + + if (emulation_type & EMULTYPE_SKIP) { + kvm_rip_write(vcpu, ctxt->_eip); + if (ctxt->eflags & X86_EFLAGS_RF) + kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF); + return EMULATE_DONE; + } + + if (retry_instruction(ctxt, cr2, emulation_type)) + return EMULATE_DONE; + + /* this is needed for vmware backdoor interface to work since it + changes registers values during IO operation */ + if (vcpu->arch.emulate_regs_need_sync_from_vcpu) { + vcpu->arch.emulate_regs_need_sync_from_vcpu = false; + emulator_invalidate_register_cache(ctxt); + } + +restart: + r = x86_emulate_insn(ctxt); + + if (r == EMULATION_INTERCEPTED) + return EMULATE_DONE; + + if (r == EMULATION_FAILED) { + if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, + emulation_type)) + return EMULATE_DONE; + + return handle_emulation_failure(vcpu); + } + + if (ctxt->have_exception) { + r = EMULATE_DONE; + if (inject_emulated_exception(vcpu)) + return r; + } else if (vcpu->arch.pio.count) { + if (!vcpu->arch.pio.in) { + /* FIXME: return into emulator if single-stepping. */ + vcpu->arch.pio.count = 0; + } else { + writeback = false; + vcpu->arch.complete_userspace_io = complete_emulated_pio; + } + r = EMULATE_USER_EXIT; + } else if (vcpu->mmio_needed) { + if (!vcpu->mmio_is_write) + writeback = false; + r = EMULATE_USER_EXIT; + vcpu->arch.complete_userspace_io = complete_emulated_mmio; + } else if (r == EMULATION_RESTART) + goto restart; + else + r = EMULATE_DONE; + + if (writeback) { + unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); + toggle_interruptibility(vcpu, ctxt->interruptibility); + vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + kvm_rip_write(vcpu, ctxt->eip); + if (r == EMULATE_DONE) + kvm_vcpu_check_singlestep(vcpu, rflags, &r); + __kvm_set_rflags(vcpu, ctxt->eflags); + + /* + * For STI, interrupts are shadowed; so KVM_REQ_EVENT will + * do nothing, and it will be requested again as soon as + * the shadow expires. But we still need to check here, + * because POPF has no interrupt shadow. + */ + if (unlikely((ctxt->eflags & ~rflags) & X86_EFLAGS_IF)) + kvm_make_request(KVM_REQ_EVENT, vcpu); + } else + vcpu->arch.emulate_regs_need_sync_to_vcpu = true; + + return r; +} +EXPORT_SYMBOL_GPL(x86_emulate_instruction); + +int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) +{ + unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX); + int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt, + size, port, &val, 1); + /* do not return to emulator after return from userspace */ + vcpu->arch.pio.count = 0; + return ret; +} +EXPORT_SYMBOL_GPL(kvm_fast_pio_out); + +static void tsc_bad(void *info) +{ + __this_cpu_write(cpu_tsc_khz, 0); +} + +static void tsc_khz_changed(void *data) +{ + struct cpufreq_freqs *freq = data; + unsigned long khz = 0; + + if (data) + khz = freq->new; + else if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + khz = cpufreq_quick_get(raw_smp_processor_id()); + if (!khz) + khz = tsc_khz; + __this_cpu_write(cpu_tsc_khz, khz); +} + +static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct cpufreq_freqs *freq = data; + struct kvm *kvm; + struct kvm_vcpu *vcpu; + int i, send_ipi = 0; + + /* + * We allow guests to temporarily run on slowing clocks, + * provided we notify them after, or to run on accelerating + * clocks, provided we notify them before. Thus time never + * goes backwards. + * + * However, we have a problem. We can't atomically update + * the frequency of a given CPU from this function; it is + * merely a notifier, which can be called from any CPU. + * Changing the TSC frequency at arbitrary points in time + * requires a recomputation of local variables related to + * the TSC for each VCPU. We must flag these local variables + * to be updated and be sure the update takes place with the + * new frequency before any guests proceed. + * + * Unfortunately, the combination of hotplug CPU and frequency + * change creates an intractable locking scenario; the order + * of when these callouts happen is undefined with respect to + * CPU hotplug, and they can race with each other. As such, + * merely setting per_cpu(cpu_tsc_khz) = X during a hotadd is + * undefined; you can actually have a CPU frequency change take + * place in between the computation of X and the setting of the + * variable. To protect against this problem, all updates of + * the per_cpu tsc_khz variable are done in an interrupt + * protected IPI, and all callers wishing to update the value + * must wait for a synchronous IPI to complete (which is trivial + * if the caller is on the CPU already). This establishes the + * necessary total order on variable updates. + * + * Note that because a guest time update may take place + * anytime after the setting of the VCPU's request bit, the + * correct TSC value must be set before the request. However, + * to ensure the update actually makes it to any guest which + * starts running in hardware virtualization between the set + * and the acquisition of the spinlock, we must also ping the + * CPU after setting the request bit. + * + */ + + if (val == CPUFREQ_PRECHANGE && freq->old > freq->new) + return 0; + if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new) + return 0; + + smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); + + spin_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->cpu != freq->cpu) + continue; + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + if (vcpu->cpu != smp_processor_id()) + send_ipi = 1; + } + } + spin_unlock(&kvm_lock); + + if (freq->old < freq->new && send_ipi) { + /* + * We upscale the frequency. Must make the guest + * doesn't see old kvmclock values while running with + * the new frequency, otherwise we risk the guest sees + * time go backwards. + * + * In case we update the frequency for another cpu + * (which might be in guest context) send an interrupt + * to kick the cpu out of guest context. Next time + * guest context is entered kvmclock will be updated, + * so the guest will not see stale values. + */ + smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); + } + return 0; +} + +static struct notifier_block kvmclock_cpufreq_notifier_block = { + .notifier_call = kvmclock_cpufreq_notifier +}; + +static int kvmclock_cpu_notifier(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + + switch (action) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + smp_call_function_single(cpu, tsc_khz_changed, NULL, 1); + break; + case CPU_DOWN_PREPARE: + smp_call_function_single(cpu, tsc_bad, NULL, 1); + break; + } + return NOTIFY_OK; +} + +static struct notifier_block kvmclock_cpu_notifier_block = { + .notifier_call = kvmclock_cpu_notifier, + .priority = -INT_MAX +}; + +static void kvm_timer_init(void) +{ + int cpu; + + max_tsc_khz = tsc_khz; + + cpu_notifier_register_begin(); + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { +#ifdef CONFIG_CPU_FREQ + struct cpufreq_policy policy; + memset(&policy, 0, sizeof(policy)); + cpu = get_cpu(); + cpufreq_get_policy(&policy, cpu); + if (policy.cpuinfo.max_freq) + max_tsc_khz = policy.cpuinfo.max_freq; + put_cpu(); +#endif + cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); + } + pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz); + for_each_online_cpu(cpu) + smp_call_function_single(cpu, tsc_khz_changed, NULL, 1); + + __register_hotcpu_notifier(&kvmclock_cpu_notifier_block); + cpu_notifier_register_done(); + +} + +static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu); + +int kvm_is_in_guest(void) +{ + return __this_cpu_read(current_vcpu) != NULL; +} + +static int kvm_is_user_mode(void) +{ + int user_mode = 3; + + if (__this_cpu_read(current_vcpu)) + user_mode = kvm_x86_ops->get_cpl(__this_cpu_read(current_vcpu)); + + return user_mode != 0; +} + +static unsigned long kvm_get_guest_ip(void) +{ + unsigned long ip = 0; + + if (__this_cpu_read(current_vcpu)) + ip = kvm_rip_read(__this_cpu_read(current_vcpu)); + + return ip; +} + +static struct perf_guest_info_callbacks kvm_guest_cbs = { + .is_in_guest = kvm_is_in_guest, + .is_user_mode = kvm_is_user_mode, + .get_guest_ip = kvm_get_guest_ip, +}; + +void kvm_before_handle_nmi(struct kvm_vcpu *vcpu) +{ + __this_cpu_write(current_vcpu, vcpu); +} +EXPORT_SYMBOL_GPL(kvm_before_handle_nmi); + +void kvm_after_handle_nmi(struct kvm_vcpu *vcpu) +{ + __this_cpu_write(current_vcpu, NULL); +} +EXPORT_SYMBOL_GPL(kvm_after_handle_nmi); + +static void kvm_set_mmio_spte_mask(void) +{ + u64 mask; + int maxphyaddr = boot_cpu_data.x86_phys_bits; + + /* + * Set the reserved bits and the present bit of an paging-structure + * entry to generate page fault with PFER.RSV = 1. + */ + /* Mask the reserved physical address bits. */ + mask = rsvd_bits(maxphyaddr, 51); + + /* Bit 62 is always reserved for 32bit host. */ + mask |= 0x3ull << 62; + + /* Set the present bit. */ + mask |= 1ull; + +#ifdef CONFIG_X86_64 + /* + * If reserved bit is not supported, clear the present bit to disable + * mmio page fault. + */ + if (maxphyaddr == 52) + mask &= ~1ull; +#endif + + kvm_mmu_set_mmio_spte_mask(mask); +} + +#ifdef CONFIG_X86_64 +static void pvclock_gtod_update_fn(struct work_struct *work) +{ + struct kvm *kvm; + + struct kvm_vcpu *vcpu; + int i; + + spin_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); + atomic_set(&kvm_guest_has_master_clock, 0); + spin_unlock(&kvm_lock); +} + +static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); + +/* + * Notification about pvclock gtod data update. + */ +static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, + void *priv) +{ + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + struct timekeeper *tk = priv; + + update_pvclock_gtod(tk); + + /* disable master clock if host does not trust, or does not + * use, TSC clocksource + */ + if (gtod->clock.vclock_mode != VCLOCK_TSC && + atomic_read(&kvm_guest_has_master_clock) != 0) + queue_work(system_long_wq, &pvclock_gtod_work); + + return 0; +} + +static struct notifier_block pvclock_gtod_notifier = { + .notifier_call = pvclock_gtod_notify, +}; +#endif + +int kvm_arch_init(void *opaque) +{ + int r; + struct kvm_x86_ops *ops = opaque; + + if (kvm_x86_ops) { + printk(KERN_ERR "kvm: already loaded the other module\n"); + r = -EEXIST; + goto out; + } + + if (!ops->cpu_has_kvm_support()) { + printk(KERN_ERR "kvm: no hardware support\n"); + r = -EOPNOTSUPP; + goto out; + } + if (ops->disabled_by_bios()) { + printk(KERN_ERR "kvm: disabled by bios\n"); + r = -EOPNOTSUPP; + goto out; + } + + r = -ENOMEM; + shared_msrs = alloc_percpu(struct kvm_shared_msrs); + if (!shared_msrs) { + printk(KERN_ERR "kvm: failed to allocate percpu kvm_shared_msrs\n"); + goto out; + } + + r = kvm_mmu_module_init(); + if (r) + goto out_free_percpu; + + kvm_set_mmio_spte_mask(); + + kvm_x86_ops = ops; + kvm_init_msr_list(); + + kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, + PT_DIRTY_MASK, PT64_NX_MASK, 0); + + kvm_timer_init(); + + perf_register_guest_info_callbacks(&kvm_guest_cbs); + + if (cpu_has_xsave) + host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + + kvm_lapic_init(); +#ifdef CONFIG_X86_64 + pvclock_gtod_register_notifier(&pvclock_gtod_notifier); +#endif + + return 0; + +out_free_percpu: + free_percpu(shared_msrs); +out: + return r; +} + +void kvm_arch_exit(void) +{ + perf_unregister_guest_info_callbacks(&kvm_guest_cbs); + + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); + unregister_hotcpu_notifier(&kvmclock_cpu_notifier_block); +#ifdef CONFIG_X86_64 + pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); +#endif + kvm_x86_ops = NULL; + kvm_mmu_module_exit(); + free_percpu(shared_msrs); +} + +int kvm_emulate_halt(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.halt_exits; + if (irqchip_in_kernel(vcpu->kvm)) { + vcpu->arch.mp_state = KVM_MP_STATE_HALTED; + return 1; + } else { + vcpu->run->exit_reason = KVM_EXIT_HLT; + return 0; + } +} +EXPORT_SYMBOL_GPL(kvm_emulate_halt); + +int kvm_hv_hypercall(struct kvm_vcpu *vcpu) +{ + u64 param, ingpa, outgpa, ret; + uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0; + bool fast, longmode; + + /* + * hypercall generates UD from non zero cpl and real mode + * per HYPER-V spec + */ + if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 0; + } + + longmode = is_64_bit_mode(vcpu); + + if (!longmode) { + param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff); + ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff); + outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff); + } +#ifdef CONFIG_X86_64 + else { + param = kvm_register_read(vcpu, VCPU_REGS_RCX); + ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX); + outgpa = kvm_register_read(vcpu, VCPU_REGS_R8); + } +#endif + + code = param & 0xffff; + fast = (param >> 16) & 0x1; + rep_cnt = (param >> 32) & 0xfff; + rep_idx = (param >> 48) & 0xfff; + + trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); + + switch (code) { + case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT: + kvm_vcpu_on_spin(vcpu); + break; + default: + res = HV_STATUS_INVALID_HYPERCALL_CODE; + break; + } + + ret = res | (((u64)rep_done & 0xfff) << 32); + if (longmode) { + kvm_register_write(vcpu, VCPU_REGS_RAX, ret); + } else { + kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32); + kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff); + } + + return 1; +} + +/* + * kvm_pv_kick_cpu_op: Kick a vcpu. + * + * @apicid - apicid of vcpu to be kicked. + */ +static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) +{ + struct kvm_lapic_irq lapic_irq; + + lapic_irq.shorthand = 0; + lapic_irq.dest_mode = 0; + lapic_irq.dest_id = apicid; + + lapic_irq.delivery_mode = APIC_DM_REMRD; + kvm_irq_delivery_to_apic(kvm, 0, &lapic_irq, NULL); +} + +int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) +{ + unsigned long nr, a0, a1, a2, a3, ret; + int op_64_bit, r = 1; + + if (kvm_hv_hypercall_enabled(vcpu->kvm)) + return kvm_hv_hypercall(vcpu); + + nr = kvm_register_read(vcpu, VCPU_REGS_RAX); + a0 = kvm_register_read(vcpu, VCPU_REGS_RBX); + a1 = kvm_register_read(vcpu, VCPU_REGS_RCX); + a2 = kvm_register_read(vcpu, VCPU_REGS_RDX); + a3 = kvm_register_read(vcpu, VCPU_REGS_RSI); + + trace_kvm_hypercall(nr, a0, a1, a2, a3); + + op_64_bit = is_64_bit_mode(vcpu); + if (!op_64_bit) { + nr &= 0xFFFFFFFF; + a0 &= 0xFFFFFFFF; + a1 &= 0xFFFFFFFF; + a2 &= 0xFFFFFFFF; + a3 &= 0xFFFFFFFF; + } + + if (kvm_x86_ops->get_cpl(vcpu) != 0) { + ret = -KVM_EPERM; + goto out; + } + + switch (nr) { + case KVM_HC_VAPIC_POLL_IRQ: + ret = 0; + break; + case KVM_HC_KICK_CPU: + kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1); + ret = 0; + break; + default: + ret = -KVM_ENOSYS; + break; + } +out: + if (!op_64_bit) + ret = (u32)ret; + kvm_register_write(vcpu, VCPU_REGS_RAX, ret); + ++vcpu->stat.hypercalls; + return r; +} +EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); + +static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + char instruction[3]; + unsigned long rip = kvm_rip_read(vcpu); + + kvm_x86_ops->patch_hypercall(vcpu, instruction); + + return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); +} + +/* + * Check if userspace requested an interrupt window, and that the + * interrupt window is open. + * + * No need to exit to userspace if we already have an interrupt queued. + */ +static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) +{ + return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) && + vcpu->run->request_interrupt_window && + kvm_arch_interrupt_allowed(vcpu)); +} + +static void post_kvm_run_save(struct kvm_vcpu *vcpu) +{ + struct kvm_run *kvm_run = vcpu->run; + + kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; + kvm_run->cr8 = kvm_get_cr8(vcpu); + kvm_run->apic_base = kvm_get_apic_base(vcpu); + if (irqchip_in_kernel(vcpu->kvm)) + kvm_run->ready_for_interrupt_injection = 1; + else + kvm_run->ready_for_interrupt_injection = + kvm_arch_interrupt_allowed(vcpu) && + !kvm_cpu_has_interrupt(vcpu) && + !kvm_event_needs_reinjection(vcpu); +} + +static void update_cr8_intercept(struct kvm_vcpu *vcpu) +{ + int max_irr, tpr; + + if (!kvm_x86_ops->update_cr8_intercept) + return; + + if (!vcpu->arch.apic) + return; + + if (!vcpu->arch.apic->vapic_addr) + max_irr = kvm_lapic_find_highest_irr(vcpu); + else + max_irr = -1; + + if (max_irr != -1) + max_irr >>= 4; + + tpr = kvm_lapic_get_cr8(vcpu); + + kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); +} + +static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) +{ + int r; + + /* try to reinject previous events if any */ + if (vcpu->arch.exception.pending) { + trace_kvm_inj_exception(vcpu->arch.exception.nr, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code); + + if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT) + __kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) | + X86_EFLAGS_RF); + + kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code, + vcpu->arch.exception.reinject); + return 0; + } + + if (vcpu->arch.nmi_injected) { + kvm_x86_ops->set_nmi(vcpu); + return 0; + } + + if (vcpu->arch.interrupt.pending) { + kvm_x86_ops->set_irq(vcpu); + return 0; + } + + if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { + r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + if (r != 0) + return r; + } + + /* try to inject new event if pending */ + if (vcpu->arch.nmi_pending) { + if (kvm_x86_ops->nmi_allowed(vcpu)) { + --vcpu->arch.nmi_pending; + vcpu->arch.nmi_injected = true; + kvm_x86_ops->set_nmi(vcpu); + } + } else if (kvm_cpu_has_injectable_intr(vcpu)) { + /* + * Because interrupts can be injected asynchronously, we are + * calling check_nested_events again here to avoid a race condition. + * See https://lkml.org/lkml/2014/7/2/60 for discussion about this + * proposal and current concerns. Perhaps we should be setting + * KVM_REQ_EVENT only on certain events and not unconditionally? + */ + if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { + r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + if (r != 0) + return r; + } + if (kvm_x86_ops->interrupt_allowed(vcpu)) { + kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), + false); + kvm_x86_ops->set_irq(vcpu); + } + } + return 0; +} + +static void process_nmi(struct kvm_vcpu *vcpu) +{ + unsigned limit = 2; + + /* + * x86 is limited to one NMI running, and one NMI pending after it. + * If an NMI is already in progress, limit further NMIs to just one. + * Otherwise, allow two (and we'll inject the first one immediately). + */ + if (kvm_x86_ops->get_nmi_mask(vcpu) || vcpu->arch.nmi_injected) + limit = 1; + + vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); + vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); + kvm_make_request(KVM_REQ_EVENT, vcpu); +} + +static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) +{ + u64 eoi_exit_bitmap[4]; + u32 tmr[8]; + + if (!kvm_apic_hw_enabled(vcpu->arch.apic)) + return; + + memset(eoi_exit_bitmap, 0, 32); + memset(tmr, 0, 32); + + kvm_ioapic_scan_entry(vcpu, eoi_exit_bitmap, tmr); + kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); + kvm_apic_update_tmr(vcpu, tmr); +} + +static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.tlb_flush; + kvm_x86_ops->tlb_flush(vcpu); +} + +void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) +{ + struct page *page = NULL; + + if (!irqchip_in_kernel(vcpu->kvm)) + return; + + if (!kvm_x86_ops->set_apic_access_page_addr) + return; + + page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); + kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page)); + + /* + * Do not pin apic access page in memory, the MMU notifier + * will call us again if it is migrated or swapped out. + */ + put_page(page); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); + +void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, + unsigned long address) +{ + /* + * The physical address of apic access page is stored in the VMCS. + * Update it when it becomes invalid. + */ + if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT)) + kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); +} + +/* + * Returns 1 to let __vcpu_run() continue the guest execution loop without + * exiting to the userspace. Otherwise, the value will be returned to the + * userspace. + */ +static int vcpu_enter_guest(struct kvm_vcpu *vcpu) +{ + int r; + bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && + vcpu->run->request_interrupt_window; + bool req_immediate_exit = false; + + if (vcpu->requests) { + if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) + kvm_mmu_unload(vcpu); + if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) + __kvm_migrate_timers(vcpu); + if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu)) + kvm_gen_update_masterclock(vcpu->kvm); + if (kvm_check_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu)) + kvm_gen_kvmclock_update(vcpu); + if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) { + r = kvm_guest_time_update(vcpu); + if (unlikely(r)) + goto out; + } + if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu)) + kvm_mmu_sync_roots(vcpu); + if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) + kvm_vcpu_flush_tlb(vcpu); + if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; + r = 0; + goto out; + } + if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; + r = 0; + goto out; + } + if (kvm_check_request(KVM_REQ_DEACTIVATE_FPU, vcpu)) { + vcpu->fpu_active = 0; + kvm_x86_ops->fpu_deactivate(vcpu); + } + if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { + /* Page is swapped out. Do synthetic halt */ + vcpu->arch.apf.halted = true; + r = 1; + goto out; + } + if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) + record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_NMI, vcpu)) + process_nmi(vcpu); + if (kvm_check_request(KVM_REQ_PMU, vcpu)) + kvm_handle_pmu_event(vcpu); + if (kvm_check_request(KVM_REQ_PMI, vcpu)) + kvm_deliver_pmi(vcpu); + if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu)) + vcpu_scan_ioapic(vcpu); + if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) + kvm_vcpu_reload_apic_access_page(vcpu); + } + + if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { + kvm_apic_accept_events(vcpu); + if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { + r = 1; + goto out; + } + + if (inject_pending_event(vcpu, req_int_win) != 0) + req_immediate_exit = true; + /* enable NMI/IRQ window open exits if needed */ + else if (vcpu->arch.nmi_pending) + kvm_x86_ops->enable_nmi_window(vcpu); + else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) + kvm_x86_ops->enable_irq_window(vcpu); + + if (kvm_lapic_enabled(vcpu)) { + /* + * Update architecture specific hints for APIC + * virtual interrupt delivery. + */ + if (kvm_x86_ops->hwapic_irr_update) + kvm_x86_ops->hwapic_irr_update(vcpu, + kvm_lapic_find_highest_irr(vcpu)); + update_cr8_intercept(vcpu); + kvm_lapic_sync_to_vapic(vcpu); + } + } + + r = kvm_mmu_reload(vcpu); + if (unlikely(r)) { + goto cancel_injection; + } + + preempt_disable(); + + kvm_x86_ops->prepare_guest_switch(vcpu); + if (vcpu->fpu_active) + kvm_load_guest_fpu(vcpu); + kvm_load_guest_xcr0(vcpu); + + vcpu->mode = IN_GUEST_MODE; + + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + + /* We should set ->mode before check ->requests, + * see the comment in make_all_cpus_request. + */ + smp_mb__after_srcu_read_unlock(); + + local_irq_disable(); + + if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests + || need_resched() || signal_pending(current)) { + vcpu->mode = OUTSIDE_GUEST_MODE; + smp_wmb(); + local_irq_enable(); + preempt_enable(); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + r = 1; + goto cancel_injection; + } + + if (req_immediate_exit) + smp_send_reschedule(vcpu->cpu); + + kvm_guest_enter(); + + if (unlikely(vcpu->arch.switch_db_regs)) { + set_debugreg(0, 7); + set_debugreg(vcpu->arch.eff_db[0], 0); + set_debugreg(vcpu->arch.eff_db[1], 1); + set_debugreg(vcpu->arch.eff_db[2], 2); + set_debugreg(vcpu->arch.eff_db[3], 3); + set_debugreg(vcpu->arch.dr6, 6); + } + + trace_kvm_entry(vcpu->vcpu_id); + kvm_x86_ops->run(vcpu); + + /* + * Do this here before restoring debug registers on the host. And + * since we do this before handling the vmexit, a DR access vmexit + * can (a) read the correct value of the debug registers, (b) set + * KVM_DEBUGREG_WONT_EXIT again. + */ + if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { + int i; + + WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); + kvm_x86_ops->sync_dirty_debug_regs(vcpu); + for (i = 0; i < KVM_NR_DB_REGS; i++) + vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + } + + /* + * If the guest has used debug registers, at least dr7 + * will be disabled while returning to the host. + * If we don't have active breakpoints in the host, we don't + * care about the messed up debug address registers. But if + * we have some of them active, restore the old state. + */ + if (hw_breakpoint_active()) + hw_breakpoint_restore(); + + vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, + native_read_tsc()); + + vcpu->mode = OUTSIDE_GUEST_MODE; + smp_wmb(); + + /* Interrupt is enabled by handle_external_intr() */ + kvm_x86_ops->handle_external_intr(vcpu); + + ++vcpu->stat.exits; + + /* + * We must have an instruction between local_irq_enable() and + * kvm_guest_exit(), so the timer interrupt isn't delayed by + * the interrupt shadow. The stat.exits increment will do nicely. + * But we need to prevent reordering, hence this barrier(): + */ + barrier(); + + kvm_guest_exit(); + + preempt_enable(); + + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + /* + * Profile KVM exit RIPs: + */ + if (unlikely(prof_on == KVM_PROFILING)) { + unsigned long rip = kvm_rip_read(vcpu); + profile_hit(KVM_PROFILING, (void *)rip); + } + + if (unlikely(vcpu->arch.tsc_always_catchup)) + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + + if (vcpu->arch.apic_attention) + kvm_lapic_sync_from_vapic(vcpu); + + r = kvm_x86_ops->handle_exit(vcpu); + return r; + +cancel_injection: + kvm_x86_ops->cancel_injection(vcpu); + if (unlikely(vcpu->arch.apic_attention)) + kvm_lapic_sync_from_vapic(vcpu); +out: + return r; +} + + +static int __vcpu_run(struct kvm_vcpu *vcpu) +{ + int r; + struct kvm *kvm = vcpu->kvm; + + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + + r = 1; + while (r > 0) { + if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted) + r = vcpu_enter_guest(vcpu); + else { + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_block(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) { + kvm_apic_accept_events(vcpu); + switch(vcpu->arch.mp_state) { + case KVM_MP_STATE_HALTED: + vcpu->arch.pv.pv_unhalted = false; + vcpu->arch.mp_state = + KVM_MP_STATE_RUNNABLE; + case KVM_MP_STATE_RUNNABLE: + vcpu->arch.apf.halted = false; + break; + case KVM_MP_STATE_INIT_RECEIVED: + break; + default: + r = -EINTR; + break; + } + } + } + + if (r <= 0) + break; + + clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests); + if (kvm_cpu_has_pending_timer(vcpu)) + kvm_inject_pending_timer_irqs(vcpu); + + if (dm_request_for_irq_injection(vcpu)) { + r = -EINTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; + ++vcpu->stat.request_irq_exits; + } + + kvm_check_async_pf_completion(vcpu); + + if (signal_pending(current)) { + r = -EINTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; + ++vcpu->stat.signal_exits; + } + if (need_resched()) { + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + cond_resched(); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + } + } + + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + + return r; +} + +static inline int complete_emulated_io(struct kvm_vcpu *vcpu) +{ + int r; + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + if (r != EMULATE_DONE) + return 0; + return 1; +} + +static int complete_emulated_pio(struct kvm_vcpu *vcpu) +{ + BUG_ON(!vcpu->arch.pio.count); + + return complete_emulated_io(vcpu); +} + +/* + * Implements the following, as a state machine: + * + * read: + * for each fragment + * for each mmio piece in the fragment + * write gpa, len + * exit + * copy data + * execute insn + * + * write: + * for each fragment + * for each mmio piece in the fragment + * write gpa, len + * copy data + * exit + */ +static int complete_emulated_mmio(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + struct kvm_mmio_fragment *frag; + unsigned len; + + BUG_ON(!vcpu->mmio_needed); + + /* Complete previous fragment */ + frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment]; + len = min(8u, frag->len); + if (!vcpu->mmio_is_write) + memcpy(frag->data, run->mmio.data, len); + + if (frag->len <= 8) { + /* Switch to the next fragment. */ + frag++; + vcpu->mmio_cur_fragment++; + } else { + /* Go forward to the next mmio piece. */ + frag->data += len; + frag->gpa += len; + frag->len -= len; + } + + if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) { + vcpu->mmio_needed = 0; + + /* FIXME: return into emulator if single-stepping. */ + if (vcpu->mmio_is_write) + return 1; + vcpu->mmio_read_completed = 1; + return complete_emulated_io(vcpu); + } + + run->exit_reason = KVM_EXIT_MMIO; + run->mmio.phys_addr = frag->gpa; + if (vcpu->mmio_is_write) + memcpy(run->mmio.data, frag->data, min(8u, frag->len)); + run->mmio.len = min(8u, frag->len); + run->mmio.is_write = vcpu->mmio_is_write; + vcpu->arch.complete_userspace_io = complete_emulated_mmio; + return 0; +} + + +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + int r; + sigset_t sigsaved; + + if (!tsk_used_math(current) && init_fpu(current)) + return -ENOMEM; + + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); + + if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { + kvm_vcpu_block(vcpu); + kvm_apic_accept_events(vcpu); + clear_bit(KVM_REQ_UNHALT, &vcpu->requests); + r = -EAGAIN; + goto out; + } + + /* re-sync apic's tpr */ + if (!irqchip_in_kernel(vcpu->kvm)) { + if (kvm_set_cr8(vcpu, kvm_run->cr8) != 0) { + r = -EINVAL; + goto out; + } + } + + if (unlikely(vcpu->arch.complete_userspace_io)) { + int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io; + vcpu->arch.complete_userspace_io = NULL; + r = cui(vcpu); + if (r <= 0) + goto out; + } else + WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed); + + r = __vcpu_run(vcpu); + +out: + post_kvm_run_save(vcpu); + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + return r; +} + +int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + if (vcpu->arch.emulate_regs_need_sync_to_vcpu) { + /* + * We are here if userspace calls get_regs() in the middle of + * instruction emulation. Registers state needs to be copied + * back from emulation context to vcpu. Userspace shouldn't do + * that usually, but some bad designed PV devices (vmware + * backdoor interface) need this to work + */ + emulator_writeback_register_cache(&vcpu->arch.emulate_ctxt); + vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + } + regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX); + regs->rbx = kvm_register_read(vcpu, VCPU_REGS_RBX); + regs->rcx = kvm_register_read(vcpu, VCPU_REGS_RCX); + regs->rdx = kvm_register_read(vcpu, VCPU_REGS_RDX); + regs->rsi = kvm_register_read(vcpu, VCPU_REGS_RSI); + regs->rdi = kvm_register_read(vcpu, VCPU_REGS_RDI); + regs->rsp = kvm_register_read(vcpu, VCPU_REGS_RSP); + regs->rbp = kvm_register_read(vcpu, VCPU_REGS_RBP); +#ifdef CONFIG_X86_64 + regs->r8 = kvm_register_read(vcpu, VCPU_REGS_R8); + regs->r9 = kvm_register_read(vcpu, VCPU_REGS_R9); + regs->r10 = kvm_register_read(vcpu, VCPU_REGS_R10); + regs->r11 = kvm_register_read(vcpu, VCPU_REGS_R11); + regs->r12 = kvm_register_read(vcpu, VCPU_REGS_R12); + regs->r13 = kvm_register_read(vcpu, VCPU_REGS_R13); + regs->r14 = kvm_register_read(vcpu, VCPU_REGS_R14); + regs->r15 = kvm_register_read(vcpu, VCPU_REGS_R15); +#endif + + regs->rip = kvm_rip_read(vcpu); + regs->rflags = kvm_get_rflags(vcpu); + + return 0; +} + +int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + vcpu->arch.emulate_regs_need_sync_from_vcpu = true; + vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + + kvm_register_write(vcpu, VCPU_REGS_RAX, regs->rax); + kvm_register_write(vcpu, VCPU_REGS_RBX, regs->rbx); + kvm_register_write(vcpu, VCPU_REGS_RCX, regs->rcx); + kvm_register_write(vcpu, VCPU_REGS_RDX, regs->rdx); + kvm_register_write(vcpu, VCPU_REGS_RSI, regs->rsi); + kvm_register_write(vcpu, VCPU_REGS_RDI, regs->rdi); + kvm_register_write(vcpu, VCPU_REGS_RSP, regs->rsp); + kvm_register_write(vcpu, VCPU_REGS_RBP, regs->rbp); +#ifdef CONFIG_X86_64 + kvm_register_write(vcpu, VCPU_REGS_R8, regs->r8); + kvm_register_write(vcpu, VCPU_REGS_R9, regs->r9); + kvm_register_write(vcpu, VCPU_REGS_R10, regs->r10); + kvm_register_write(vcpu, VCPU_REGS_R11, regs->r11); + kvm_register_write(vcpu, VCPU_REGS_R12, regs->r12); + kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13); + kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14); + kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15); +#endif + + kvm_rip_write(vcpu, regs->rip); + kvm_set_rflags(vcpu, regs->rflags); + + vcpu->arch.exception.pending = false; + + kvm_make_request(KVM_REQ_EVENT, vcpu); + + return 0; +} + +void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) +{ + struct kvm_segment cs; + + kvm_get_segment(vcpu, &cs, VCPU_SREG_CS); + *db = cs.db; + *l = cs.l; +} +EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); + +int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + struct desc_ptr dt; + + kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); + kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); + kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES); + kvm_get_segment(vcpu, &sregs->fs, VCPU_SREG_FS); + kvm_get_segment(vcpu, &sregs->gs, VCPU_SREG_GS); + kvm_get_segment(vcpu, &sregs->ss, VCPU_SREG_SS); + + kvm_get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); + kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); + + kvm_x86_ops->get_idt(vcpu, &dt); + sregs->idt.limit = dt.size; + sregs->idt.base = dt.address; + kvm_x86_ops->get_gdt(vcpu, &dt); + sregs->gdt.limit = dt.size; + sregs->gdt.base = dt.address; + + sregs->cr0 = kvm_read_cr0(vcpu); + sregs->cr2 = vcpu->arch.cr2; + sregs->cr3 = kvm_read_cr3(vcpu); + sregs->cr4 = kvm_read_cr4(vcpu); + sregs->cr8 = kvm_get_cr8(vcpu); + sregs->efer = vcpu->arch.efer; + sregs->apic_base = kvm_get_apic_base(vcpu); + + memset(sregs->interrupt_bitmap, 0, sizeof sregs->interrupt_bitmap); + + if (vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft) + set_bit(vcpu->arch.interrupt.nr, + (unsigned long *)sregs->interrupt_bitmap); + + return 0; +} + +int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + kvm_apic_accept_events(vcpu); + if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && + vcpu->arch.pv.pv_unhalted) + mp_state->mp_state = KVM_MP_STATE_RUNNABLE; + else + mp_state->mp_state = vcpu->arch.mp_state; + + return 0; +} + +int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + if (!kvm_vcpu_has_lapic(vcpu) && + mp_state->mp_state != KVM_MP_STATE_RUNNABLE) + return -EINVAL; + + if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) { + vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; + set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events); + } else + vcpu->arch.mp_state = mp_state->mp_state; + kvm_make_request(KVM_REQ_EVENT, vcpu); + return 0; +} + +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, + int reason, bool has_error_code, u32 error_code) +{ + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + int ret; + + init_emulate_ctxt(vcpu); + + ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason, + has_error_code, error_code); + + if (ret) + return EMULATE_FAIL; + + kvm_rip_write(vcpu, ctxt->eip); + kvm_set_rflags(vcpu, ctxt->eflags); + kvm_make_request(KVM_REQ_EVENT, vcpu); + return EMULATE_DONE; +} +EXPORT_SYMBOL_GPL(kvm_task_switch); + +int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + struct msr_data apic_base_msr; + int mmu_reset_needed = 0; + int pending_vec, max_bits, idx; + struct desc_ptr dt; + + if (!guest_cpuid_has_xsave(vcpu) && (sregs->cr4 & X86_CR4_OSXSAVE)) + return -EINVAL; + + dt.size = sregs->idt.limit; + dt.address = sregs->idt.base; + kvm_x86_ops->set_idt(vcpu, &dt); + dt.size = sregs->gdt.limit; + dt.address = sregs->gdt.base; + kvm_x86_ops->set_gdt(vcpu, &dt); + + vcpu->arch.cr2 = sregs->cr2; + mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; + vcpu->arch.cr3 = sregs->cr3; + __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + + kvm_set_cr8(vcpu, sregs->cr8); + + mmu_reset_needed |= vcpu->arch.efer != sregs->efer; + kvm_x86_ops->set_efer(vcpu, sregs->efer); + apic_base_msr.data = sregs->apic_base; + apic_base_msr.host_initiated = true; + kvm_set_apic_base(vcpu, &apic_base_msr); + + mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; + kvm_x86_ops->set_cr0(vcpu, sregs->cr0); + vcpu->arch.cr0 = sregs->cr0; + + mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; + kvm_x86_ops->set_cr4(vcpu, sregs->cr4); + if (sregs->cr4 & X86_CR4_OSXSAVE) + kvm_update_cpuid(vcpu); + + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (!is_long_mode(vcpu) && is_pae(vcpu)) { + load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + mmu_reset_needed = 1; + } + srcu_read_unlock(&vcpu->kvm->srcu, idx); + + if (mmu_reset_needed) + kvm_mmu_reset_context(vcpu); + + max_bits = KVM_NR_INTERRUPTS; + pending_vec = find_first_bit( + (const unsigned long *)sregs->interrupt_bitmap, max_bits); + if (pending_vec < max_bits) { + kvm_queue_interrupt(vcpu, pending_vec, false); + pr_debug("Set back pending irq %d\n", pending_vec); + } + + kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); + kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); + kvm_set_segment(vcpu, &sregs->es, VCPU_SREG_ES); + kvm_set_segment(vcpu, &sregs->fs, VCPU_SREG_FS); + kvm_set_segment(vcpu, &sregs->gs, VCPU_SREG_GS); + kvm_set_segment(vcpu, &sregs->ss, VCPU_SREG_SS); + + kvm_set_segment(vcpu, &sregs->tr, VCPU_SREG_TR); + kvm_set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); + + update_cr8_intercept(vcpu); + + /* Older userspace won't unhalt the vcpu on reset. */ + if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 && + sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 && + !is_protmode(vcpu)) + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + + kvm_make_request(KVM_REQ_EVENT, vcpu); + + return 0; +} + +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) +{ + unsigned long rflags; + int i, r; + + if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { + r = -EBUSY; + if (vcpu->arch.exception.pending) + goto out; + if (dbg->control & KVM_GUESTDBG_INJECT_DB) + kvm_queue_exception(vcpu, DB_VECTOR); + else + kvm_queue_exception(vcpu, BP_VECTOR); + } + + /* + * Read rflags as long as potentially injected trace flags are still + * filtered out. + */ + rflags = kvm_get_rflags(vcpu); + + vcpu->guest_debug = dbg->control; + if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) + vcpu->guest_debug = 0; + + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { + for (i = 0; i < KVM_NR_DB_REGS; ++i) + vcpu->arch.eff_db[i] = dbg->arch.debugreg[i]; + vcpu->arch.guest_debug_dr7 = dbg->arch.debugreg[7]; + } else { + for (i = 0; i < KVM_NR_DB_REGS; i++) + vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + } + kvm_update_dr7(vcpu); + + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); + + /* + * Trigger an rflags update that will inject or remove the trace + * flags. + */ + kvm_set_rflags(vcpu, rflags); + + kvm_x86_ops->update_db_bp_intercept(vcpu); + + r = 0; + +out: + + return r; +} + +/* + * Translate a guest virtual address to a guest physical address. + */ +int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, + struct kvm_translation *tr) +{ + unsigned long vaddr = tr->linear_address; + gpa_t gpa; + int idx; + + idx = srcu_read_lock(&vcpu->kvm->srcu); + gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + tr->physical_address = gpa; + tr->valid = gpa != UNMAPPED_GVA; + tr->writeable = 1; + tr->usermode = 0; + + return 0; +} + +int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + struct i387_fxsave_struct *fxsave = + &vcpu->arch.guest_fpu.state->fxsave; + + memcpy(fpu->fpr, fxsave->st_space, 128); + fpu->fcw = fxsave->cwd; + fpu->fsw = fxsave->swd; + fpu->ftwx = fxsave->twd; + fpu->last_opcode = fxsave->fop; + fpu->last_ip = fxsave->rip; + fpu->last_dp = fxsave->rdp; + memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space); + + return 0; +} + +int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + struct i387_fxsave_struct *fxsave = + &vcpu->arch.guest_fpu.state->fxsave; + + memcpy(fxsave->st_space, fpu->fpr, 128); + fxsave->cwd = fpu->fcw; + fxsave->swd = fpu->fsw; + fxsave->twd = fpu->ftwx; + fxsave->fop = fpu->last_opcode; + fxsave->rip = fpu->last_ip; + fxsave->rdp = fpu->last_dp; + memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space); + + return 0; +} + +int fx_init(struct kvm_vcpu *vcpu) +{ + int err; + + err = fpu_alloc(&vcpu->arch.guest_fpu); + if (err) + return err; + + fpu_finit(&vcpu->arch.guest_fpu); + if (cpu_has_xsaves) + vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv = + host_xcr0 | XSTATE_COMPACTION_ENABLED; + + /* + * Ensure guest xcr0 is valid for loading + */ + vcpu->arch.xcr0 = XSTATE_FP; + + vcpu->arch.cr0 |= X86_CR0_ET; + + return 0; +} +EXPORT_SYMBOL_GPL(fx_init); + +static void fx_free(struct kvm_vcpu *vcpu) +{ + fpu_free(&vcpu->arch.guest_fpu); +} + +void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) +{ + if (vcpu->guest_fpu_loaded) + return; + + /* + * Restore all possible states in the guest, + * and assume host would use all available bits. + * Guest xcr0 would be loaded later. + */ + kvm_put_guest_xcr0(vcpu); + vcpu->guest_fpu_loaded = 1; + __kernel_fpu_begin(); + fpu_restore_checking(&vcpu->arch.guest_fpu); + trace_kvm_fpu(1); +} + +void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) +{ + kvm_put_guest_xcr0(vcpu); + + if (!vcpu->guest_fpu_loaded) + return; + + vcpu->guest_fpu_loaded = 0; + fpu_save_init(&vcpu->arch.guest_fpu); + __kernel_fpu_end(); + ++vcpu->stat.fpu_reload; + kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); + trace_kvm_fpu(0); +} + +void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) +{ + kvmclock_reset(vcpu); + + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); + fx_free(vcpu); + kvm_x86_ops->vcpu_free(vcpu); +} + +struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, + unsigned int id) +{ + if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) + printk_once(KERN_WARNING + "kvm: SMP vm created on host with unstable TSC; " + "guest TSC will not be reliable\n"); + return kvm_x86_ops->vcpu_create(kvm, id); +} + +int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) +{ + int r; + + vcpu->arch.mtrr_state.have_fixed = 1; + r = vcpu_load(vcpu); + if (r) + return r; + kvm_vcpu_reset(vcpu); + kvm_mmu_setup(vcpu); + vcpu_put(vcpu); + + return r; +} + +int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) +{ + int r; + struct msr_data msr; + struct kvm *kvm = vcpu->kvm; + + r = vcpu_load(vcpu); + if (r) + return r; + msr.data = 0x0; + msr.index = MSR_IA32_TSC; + msr.host_initiated = true; + kvm_write_tsc(vcpu, &msr); + vcpu_put(vcpu); + + schedule_delayed_work(&kvm->arch.kvmclock_sync_work, + KVMCLOCK_SYNC_PERIOD); + + return r; +} + +void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + int r; + vcpu->arch.apf.msr_val = 0; + + r = vcpu_load(vcpu); + BUG_ON(r); + kvm_mmu_unload(vcpu); + vcpu_put(vcpu); + + fx_free(vcpu); + kvm_x86_ops->vcpu_free(vcpu); +} + +void kvm_vcpu_reset(struct kvm_vcpu *vcpu) +{ + atomic_set(&vcpu->arch.nmi_queued, 0); + vcpu->arch.nmi_pending = 0; + vcpu->arch.nmi_injected = false; + kvm_clear_interrupt_queue(vcpu); + kvm_clear_exception_queue(vcpu); + + memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); + vcpu->arch.dr6 = DR6_INIT; + kvm_update_dr6(vcpu); + vcpu->arch.dr7 = DR7_FIXED_1; + kvm_update_dr7(vcpu); + + kvm_make_request(KVM_REQ_EVENT, vcpu); + vcpu->arch.apf.msr_val = 0; + vcpu->arch.st.msr_val = 0; + + kvmclock_reset(vcpu); + + kvm_clear_async_pf_completion_queue(vcpu); + kvm_async_pf_hash_reset(vcpu); + vcpu->arch.apf.halted = false; + + kvm_pmu_reset(vcpu); + + memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); + vcpu->arch.regs_avail = ~0; + vcpu->arch.regs_dirty = ~0; + + kvm_x86_ops->vcpu_reset(vcpu); +} + +void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector) +{ + struct kvm_segment cs; + + kvm_get_segment(vcpu, &cs, VCPU_SREG_CS); + cs.selector = vector << 8; + cs.base = vector << 12; + kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); + kvm_rip_write(vcpu, 0); +} + +int kvm_arch_hardware_enable(void) +{ + struct kvm *kvm; + struct kvm_vcpu *vcpu; + int i; + int ret; + u64 local_tsc; + u64 max_tsc = 0; + bool stable, backwards_tsc = false; + + kvm_shared_msr_cpu_online(); + ret = kvm_x86_ops->hardware_enable(); + if (ret != 0) + return ret; + + local_tsc = native_read_tsc(); + stable = !check_tsc_unstable(); + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!stable && vcpu->cpu == smp_processor_id()) + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + if (stable && vcpu->arch.last_host_tsc > local_tsc) { + backwards_tsc = true; + if (vcpu->arch.last_host_tsc > max_tsc) + max_tsc = vcpu->arch.last_host_tsc; + } + } + } + + /* + * Sometimes, even reliable TSCs go backwards. This happens on + * platforms that reset TSC during suspend or hibernate actions, but + * maintain synchronization. We must compensate. Fortunately, we can + * detect that condition here, which happens early in CPU bringup, + * before any KVM threads can be running. Unfortunately, we can't + * bring the TSCs fully up to date with real time, as we aren't yet far + * enough into CPU bringup that we know how much real time has actually + * elapsed; our helper function, get_kernel_ns() will be using boot + * variables that haven't been updated yet. + * + * So we simply find the maximum observed TSC above, then record the + * adjustment to TSC in each VCPU. When the VCPU later gets loaded, + * the adjustment will be applied. Note that we accumulate + * adjustments, in case multiple suspend cycles happen before some VCPU + * gets a chance to run again. In the event that no KVM threads get a + * chance to run, we will miss the entire elapsed period, as we'll have + * reset last_host_tsc, so VCPUs will not have the TSC adjusted and may + * loose cycle time. This isn't too big a deal, since the loss will be + * uniform across all VCPUs (not to mention the scenario is extremely + * unlikely). It is possible that a second hibernate recovery happens + * much faster than a first, causing the observed TSC here to be + * smaller; this would require additional padding adjustment, which is + * why we set last_host_tsc to the local tsc observed here. + * + * N.B. - this code below runs only on platforms with reliable TSC, + * as that is the only way backwards_tsc is set above. Also note + * that this runs for ALL vcpus, which is not a bug; all VCPUs should + * have the same delta_cyc adjustment applied if backwards_tsc + * is detected. Note further, this adjustment is only done once, + * as we reset last_host_tsc on all VCPUs to stop this from being + * called multiple times (one for each physical CPU bringup). + * + * Platforms with unreliable TSCs don't have to deal with this, they + * will be compensated by the logic in vcpu_load, which sets the TSC to + * catchup mode. This will catchup all VCPUs to real time, but cannot + * guarantee that they stay in perfect synchronization. + */ + if (backwards_tsc) { + u64 delta_cyc = max_tsc - local_tsc; + backwards_tsc_observed = true; + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_for_each_vcpu(i, vcpu, kvm) { + vcpu->arch.tsc_offset_adjustment += delta_cyc; + vcpu->arch.last_host_tsc = local_tsc; + kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); + } + + /* + * We have to disable TSC offset matching.. if you were + * booting a VM while issuing an S4 host suspend.... + * you may have some problem. Solving this issue is + * left as an exercise to the reader. + */ + kvm->arch.last_tsc_nsec = 0; + kvm->arch.last_tsc_write = 0; + } + + } + return 0; +} + +void kvm_arch_hardware_disable(void) +{ + kvm_x86_ops->hardware_disable(); + drop_user_return_notifiers(); +} + +int kvm_arch_hardware_setup(void) +{ + return kvm_x86_ops->hardware_setup(); +} + +void kvm_arch_hardware_unsetup(void) +{ + kvm_x86_ops->hardware_unsetup(); +} + +void kvm_arch_check_processor_compat(void *rtn) +{ + kvm_x86_ops->check_processor_compatibility(rtn); +} + +bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) +{ + return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL); +} + +struct static_key kvm_no_apic_vcpu __read_mostly; + +int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) +{ + struct page *page; + struct kvm *kvm; + int r; + + BUG_ON(vcpu->kvm == NULL); + kvm = vcpu->kvm; + + vcpu->arch.pv.pv_unhalted = false; + vcpu->arch.emulate_ctxt.ops = &emulate_ops; + if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu)) + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + else + vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; + + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) { + r = -ENOMEM; + goto fail; + } + vcpu->arch.pio_data = page_address(page); + + kvm_set_tsc_khz(vcpu, max_tsc_khz); + + r = kvm_mmu_create(vcpu); + if (r < 0) + goto fail_free_pio_data; + + if (irqchip_in_kernel(kvm)) { + r = kvm_create_lapic(vcpu); + if (r < 0) + goto fail_mmu_destroy; + } else + static_key_slow_inc(&kvm_no_apic_vcpu); + + vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, + GFP_KERNEL); + if (!vcpu->arch.mce_banks) { + r = -ENOMEM; + goto fail_free_lapic; + } + vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; + + if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL)) { + r = -ENOMEM; + goto fail_free_mce_banks; + } + + r = fx_init(vcpu); + if (r) + goto fail_free_wbinvd_dirty_mask; + + vcpu->arch.ia32_tsc_adjust_msr = 0x0; + vcpu->arch.pv_time_enabled = false; + + vcpu->arch.guest_supported_xcr0 = 0; + vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + + kvm_async_pf_hash_reset(vcpu); + kvm_pmu_init(vcpu); + + return 0; +fail_free_wbinvd_dirty_mask: + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); +fail_free_mce_banks: + kfree(vcpu->arch.mce_banks); +fail_free_lapic: + kvm_free_lapic(vcpu); +fail_mmu_destroy: + kvm_mmu_destroy(vcpu); +fail_free_pio_data: + free_page((unsigned long)vcpu->arch.pio_data); +fail: + return r; +} + +void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) +{ + int idx; + + kvm_pmu_destroy(vcpu); + kfree(vcpu->arch.mce_banks); + kvm_free_lapic(vcpu); + idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_mmu_destroy(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + free_page((unsigned long)vcpu->arch.pio_data); + if (!irqchip_in_kernel(vcpu->kvm)) + static_key_slow_dec(&kvm_no_apic_vcpu); +} + +void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) +{ + kvm_x86_ops->sched_in(vcpu, cpu); +} + +int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) +{ + if (type) + return -EINVAL; + + INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); + INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); + atomic_set(&kvm->arch.noncoherent_dma_count, 0); + + /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ + set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); + /* Reserve bit 1 of irq_sources_bitmap for irqfd-resampler */ + set_bit(KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, + &kvm->arch.irq_sources_bitmap); + + raw_spin_lock_init(&kvm->arch.tsc_write_lock); + mutex_init(&kvm->arch.apic_map_lock); + spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); + + pvclock_update_vm_gtod_copy(kvm); + + INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); + INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); + + return 0; +} + +static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) +{ + int r; + r = vcpu_load(vcpu); + BUG_ON(r); + kvm_mmu_unload(vcpu); + vcpu_put(vcpu); +} + +static void kvm_free_vcpus(struct kvm *kvm) +{ + unsigned int i; + struct kvm_vcpu *vcpu; + + /* + * Unpin any mmu pages first. + */ + kvm_for_each_vcpu(i, vcpu, kvm) { + kvm_clear_async_pf_completion_queue(vcpu); + kvm_unload_vcpu_mmu(vcpu); + } + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_arch_vcpu_free(vcpu); + + mutex_lock(&kvm->lock); + for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) + kvm->vcpus[i] = NULL; + + atomic_set(&kvm->online_vcpus, 0); + mutex_unlock(&kvm->lock); +} + +void kvm_arch_sync_events(struct kvm *kvm) +{ + cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work); + cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work); + kvm_free_all_assigned_devices(kvm); + kvm_free_pit(kvm); +} + +void kvm_arch_destroy_vm(struct kvm *kvm) +{ + if (current->mm == kvm->mm) { + /* + * Free memory regions allocated on behalf of userspace, + * unless the the memory map has changed due to process exit + * or fd copying. + */ + struct kvm_userspace_memory_region mem; + memset(&mem, 0, sizeof(mem)); + mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; + kvm_set_memory_region(kvm, &mem); + + mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; + kvm_set_memory_region(kvm, &mem); + + mem.slot = TSS_PRIVATE_MEMSLOT; + kvm_set_memory_region(kvm, &mem); + } + kvm_iommu_unmap_guest(kvm); + kfree(kvm->arch.vpic); + kfree(kvm->arch.vioapic); + kvm_free_vcpus(kvm); + kfree(rcu_dereference_check(kvm->arch.apic_map, 1)); +} + +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) +{ + int i; + + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) { + kvm_kvfree(free->arch.rmap[i]); + free->arch.rmap[i] = NULL; + } + if (i == 0) + continue; + + if (!dont || free->arch.lpage_info[i - 1] != + dont->arch.lpage_info[i - 1]) { + kvm_kvfree(free->arch.lpage_info[i - 1]); + free->arch.lpage_info[i - 1] = NULL; + } + } +} + +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) +{ + int i; + + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + unsigned long ugfn; + int lpages; + int level = i + 1; + + lpages = gfn_to_index(slot->base_gfn + npages - 1, + slot->base_gfn, level) + 1; + + slot->arch.rmap[i] = + kvm_kvzalloc(lpages * sizeof(*slot->arch.rmap[i])); + if (!slot->arch.rmap[i]) + goto out_free; + if (i == 0) + continue; + + slot->arch.lpage_info[i - 1] = kvm_kvzalloc(lpages * + sizeof(*slot->arch.lpage_info[i - 1])); + if (!slot->arch.lpage_info[i - 1]) + goto out_free; + + if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1)) + slot->arch.lpage_info[i - 1][0].write_count = 1; + if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1)) + slot->arch.lpage_info[i - 1][lpages - 1].write_count = 1; + ugfn = slot->userspace_addr >> PAGE_SHIFT; + /* + * If the gfn and userspace address are not aligned wrt each + * other, or if explicitly asked to, disable large page + * support for this slot + */ + if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) || + !kvm_largepages_enabled()) { + unsigned long j; + + for (j = 0; j < lpages; ++j) + slot->arch.lpage_info[i - 1][j].write_count = 1; + } + } + + return 0; + +out_free: + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + kvm_kvfree(slot->arch.rmap[i]); + slot->arch.rmap[i] = NULL; + if (i == 0) + continue; + + kvm_kvfree(slot->arch.lpage_info[i - 1]); + slot->arch.lpage_info[i - 1] = NULL; + } + return -ENOMEM; +} + +void kvm_arch_memslots_updated(struct kvm *kvm) +{ + /* + * memslots->generation has been incremented. + * mmio generation may have reached its maximum value. + */ + kvm_mmu_invalidate_mmio_sptes(kvm); +} + +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) +{ + /* + * Only private memory slots need to be mapped here since + * KVM_SET_MEMORY_REGION ioctl is no longer supported. + */ + if ((memslot->id >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_CREATE)) { + unsigned long userspace_addr; + + /* + * MAP_SHARED to prevent internal slot pages from being moved + * by fork()/COW. + */ + userspace_addr = vm_mmap(NULL, 0, memslot->npages * PAGE_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, 0); + + if (IS_ERR((void *)userspace_addr)) + return PTR_ERR((void *)userspace_addr); + + memslot->userspace_addr = userspace_addr; + } + + return 0; +} + +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + enum kvm_mr_change change) +{ + + int nr_mmu_pages = 0; + + if ((mem->slot >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_DELETE)) { + int ret; + + ret = vm_munmap(old->userspace_addr, + old->npages * PAGE_SIZE); + if (ret < 0) + printk(KERN_WARNING + "kvm_vm_ioctl_set_memory_region: " + "failed to munmap memory\n"); + } + + if (!kvm->arch.n_requested_mmu_pages) + nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); + + if (nr_mmu_pages) + kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); + /* + * Write protect all pages for dirty logging. + * + * All the sptes including the large sptes which point to this + * slot are set to readonly. We can not create any new large + * spte on this slot until the end of the logging. + * + * See the comments in fast_page_fault(). + */ + if ((change != KVM_MR_DELETE) && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES)) + kvm_mmu_slot_remove_write_access(kvm, mem->slot); +} + +void kvm_arch_flush_shadow_all(struct kvm *kvm) +{ + kvm_mmu_invalidate_zap_all_pages(kvm); +} + +void kvm_arch_flush_shadow_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + kvm_mmu_invalidate_zap_all_pages(kvm); +} + +int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) +{ + if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) + kvm_x86_ops->check_nested_events(vcpu, false); + + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted) + || !list_empty_careful(&vcpu->async_pf.done) + || kvm_apic_has_events(vcpu) + || vcpu->arch.pv.pv_unhalted + || atomic_read(&vcpu->arch.nmi_queued) || + (kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_has_interrupt(vcpu)); +} + +int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; +} + +int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) +{ + return kvm_x86_ops->interrupt_allowed(vcpu); +} + +bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip) +{ + unsigned long current_rip = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); + + return current_rip == linear_rip; +} +EXPORT_SYMBOL_GPL(kvm_is_linear_rip); + +unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) +{ + unsigned long rflags; + + rflags = kvm_x86_ops->get_rflags(vcpu); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + rflags &= ~X86_EFLAGS_TF; + return rflags; +} +EXPORT_SYMBOL_GPL(kvm_get_rflags); + +static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && + kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip)) + rflags |= X86_EFLAGS_TF; + kvm_x86_ops->set_rflags(vcpu, rflags); +} + +void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + __kvm_set_rflags(vcpu, rflags); + kvm_make_request(KVM_REQ_EVENT, vcpu); +} +EXPORT_SYMBOL_GPL(kvm_set_rflags); + +void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) +{ + int r; + + if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) || + work->wakeup_all) + return; + + r = kvm_mmu_reload(vcpu); + if (unlikely(r)) + return; + + if (!vcpu->arch.mmu.direct_map && + work->arch.cr3 != vcpu->arch.mmu.get_cr3(vcpu)) + return; + + vcpu->arch.mmu.page_fault(vcpu, work->gva, 0, true); +} + +static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) +{ + return hash_32(gfn & 0xffffffff, order_base_2(ASYNC_PF_PER_VCPU)); +} + +static inline u32 kvm_async_pf_next_probe(u32 key) +{ + return (key + 1) & (roundup_pow_of_two(ASYNC_PF_PER_VCPU) - 1); +} + +static void kvm_add_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + u32 key = kvm_async_pf_hash_fn(gfn); + + while (vcpu->arch.apf.gfns[key] != ~0) + key = kvm_async_pf_next_probe(key); + + vcpu->arch.apf.gfns[key] = gfn; +} + +static u32 kvm_async_pf_gfn_slot(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + int i; + u32 key = kvm_async_pf_hash_fn(gfn); + + for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU) && + (vcpu->arch.apf.gfns[key] != gfn && + vcpu->arch.apf.gfns[key] != ~0); i++) + key = kvm_async_pf_next_probe(key); + + return key; +} + +bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + return vcpu->arch.apf.gfns[kvm_async_pf_gfn_slot(vcpu, gfn)] == gfn; +} + +static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + u32 i, j, k; + + i = j = kvm_async_pf_gfn_slot(vcpu, gfn); + while (true) { + vcpu->arch.apf.gfns[i] = ~0; + do { + j = kvm_async_pf_next_probe(j); + if (vcpu->arch.apf.gfns[j] == ~0) + return; + k = kvm_async_pf_hash_fn(vcpu->arch.apf.gfns[j]); + /* + * k lies cyclically in ]i,j] + * | i.k.j | + * |....j i.k.| or |.k..j i...| + */ + } while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j)); + vcpu->arch.apf.gfns[i] = vcpu->arch.apf.gfns[j]; + i = j; + } +} + +static int apf_put_user(struct kvm_vcpu *vcpu, u32 val) +{ + + return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &val, + sizeof(val)); +} + +void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, + struct kvm_async_pf *work) +{ + struct x86_exception fault; + + trace_kvm_async_pf_not_present(work->arch.token, work->gva); + kvm_add_async_pf_gfn(vcpu, work->arch.gfn); + + if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) || + (vcpu->arch.apf.send_user_only && + kvm_x86_ops->get_cpl(vcpu) == 0)) + kvm_make_request(KVM_REQ_APF_HALT, vcpu); + else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) { + fault.vector = PF_VECTOR; + fault.error_code_valid = true; + fault.error_code = 0; + fault.nested_page_fault = false; + fault.address = work->arch.token; + kvm_inject_page_fault(vcpu, &fault); + } +} + +void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, + struct kvm_async_pf *work) +{ + struct x86_exception fault; + + trace_kvm_async_pf_ready(work->arch.token, work->gva); + if (work->wakeup_all) + work->arch.token = ~0; /* broadcast wakeup */ + else + kvm_del_async_pf_gfn(vcpu, work->arch.gfn); + + if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) && + !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) { + fault.vector = PF_VECTOR; + fault.error_code_valid = true; + fault.error_code = 0; + fault.nested_page_fault = false; + fault.address = work->arch.token; + kvm_inject_page_fault(vcpu, &fault); + } + vcpu->arch.apf.halted = false; + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; +} + +bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED)) + return true; + else + return !kvm_event_needs_reinjection(vcpu) && + kvm_x86_ops->interrupt_allowed(vcpu); +} + +void kvm_arch_register_noncoherent_dma(struct kvm *kvm) +{ + atomic_inc(&kvm->arch.noncoherent_dma_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma); + +void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) +{ + atomic_dec(&kvm->arch.noncoherent_dma_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma); + +bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) +{ + return atomic_read(&kvm->arch.noncoherent_dma_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); + +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window); diff -Nur linux-3.18.9.orig/arch/x86/mm/fault.c linux-3.18.9/arch/x86/mm/fault.c --- linux-3.18.9.orig/arch/x86/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/mm/fault.c 2015-03-15 16:03:03.696094875 -0500 @@ -1128,7 +1128,7 @@ * If we're in an interrupt, have no user context or are running * in an atomic region then we must not take the fault: */ - if (unlikely(in_atomic() || !mm)) { + if (unlikely(!mm || pagefault_disabled())) { bad_area_nosemaphore(regs, error_code, address); return; } diff -Nur linux-3.18.9.orig/arch/x86/mm/highmem_32.c linux-3.18.9/arch/x86/mm/highmem_32.c --- linux-3.18.9.orig/arch/x86/mm/highmem_32.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/mm/highmem_32.c 2015-03-15 16:03:03.696094875 -0500 @@ -32,6 +32,7 @@ */ void *kmap_atomic_prot(struct page *page, pgprot_t prot) { + pte_t pte = mk_pte(page, prot); unsigned long vaddr; int idx, type; @@ -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(); diff -Nur linux-3.18.9.orig/arch/x86/mm/iomap_32.c linux-3.18.9/arch/x86/mm/iomap_32.c --- linux-3.18.9.orig/arch/x86/mm/iomap_32.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/mm/iomap_32.c 2015-03-15 16:03:03.696094875 -0500 @@ -56,6 +56,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) { + pte_t pte = pfn_pte(pfn, prot); unsigned long vaddr; int idx, type; @@ -64,7 +65,12 @@ 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; @@ -110,6 +116,9 @@ * 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(); } diff -Nur linux-3.18.9.orig/arch/x86/platform/uv/tlb_uv.c linux-3.18.9/arch/x86/platform/uv/tlb_uv.c --- linux-3.18.9.orig/arch/x86/platform/uv/tlb_uv.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/platform/uv/tlb_uv.c 2015-03-15 16:03:03.696094875 -0500 @@ -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; } @@ -1899,9 +1899,9 @@ 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-3.18.9.orig/arch/x86/platform/uv/uv_time.c linux-3.18.9/arch/x86/platform/uv/uv_time.c --- linux-3.18.9.orig/arch/x86/platform/uv/uv_time.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/x86/platform/uv/uv_time.c 2015-03-15 16:03:03.696094875 -0500 @@ -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-3.18.9.orig/arch/xtensa/mm/fault.c linux-3.18.9/arch/xtensa/mm/fault.c --- linux-3.18.9.orig/arch/xtensa/mm/fault.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/arch/xtensa/mm/fault.c 2015-03-15 16:03:03.696094875 -0500 @@ -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 (!mm || pagefault_disabled()) { bad_page_fault(regs, address, SIGSEGV); return; } diff -Nur linux-3.18.9.orig/block/blk-core.c linux-3.18.9/block/blk-core.c --- linux-3.18.9.orig/block/blk-core.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/block/blk-core.c 2015-03-15 16:03:03.696094875 -0500 @@ -100,6 +100,9 @@ INIT_LIST_HEAD(&rq->queuelist); INIT_LIST_HEAD(&rq->timeout_list); +#if 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); @@ -627,7 +630,7 @@ 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; @@ -3037,7 +3040,7 @@ 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) @@ -3085,7 +3088,6 @@ 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; @@ -3105,11 +3107,6 @@ 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); @@ -3122,7 +3119,7 @@ queue_unplugged(q, depth, from_schedule); q = rq->q; depth = 0; - spin_lock(q->queue_lock); + spin_lock_irq(q->queue_lock); } /* @@ -3149,8 +3146,6 @@ */ if (q) queue_unplugged(q, depth, from_schedule); - - local_irq_restore(flags); } void blk_finish_plug(struct blk_plug *plug) diff -Nur linux-3.18.9.orig/block/blk-ioc.c linux-3.18.9/block/blk-ioc.c --- linux-3.18.9.orig/block/blk-ioc.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/block/blk-ioc.c 2015-03-15 16:03:03.696094875 -0500 @@ -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-3.18.9.orig/block/blk-iopoll.c linux-3.18.9/block/blk-iopoll.c --- linux-3.18.9.orig/block/blk-iopoll.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/block/blk-iopoll.c 2015-03-15 16:03:03.696094875 -0500 @@ -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-3.18.9.orig/block/blk-mq.c linux-3.18.9/block/blk-mq.c --- linux-3.18.9.orig/block/blk-mq.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/block/blk-mq.c 2015-03-15 16:03:03.696094875 -0500 @@ -85,7 +85,7 @@ if (percpu_ref_tryget_live(&q->mq_usage_counter)) return 0; - 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; @@ -104,7 +104,7 @@ 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); } static void blk_mq_freeze_queue_start(struct request_queue *q) @@ -123,7 +123,7 @@ 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)); } /* @@ -146,7 +146,7 @@ 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); } } @@ -194,6 +194,9 @@ rq->resid_len = 0; rq->sense = NULL; +#if CONFIG_PREEMPT_RT_FULL + INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); +#endif INIT_LIST_HEAD(&rq->timeout_list); rq->timeout = 0; @@ -313,6 +316,17 @@ } 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; @@ -320,6 +334,8 @@ 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; @@ -331,19 +347,23 @@ 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)) { +#if 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) @@ -814,9 +834,9 @@ test_bit(BLK_MQ_S_STOPPED, &hctx->state)) continue; - preempt_disable(); + migrate_disable(); blk_mq_run_hw_queue(hctx, async); - preempt_enable(); + migrate_enable(); } } EXPORT_SYMBOL(blk_mq_run_queues); @@ -843,9 +863,9 @@ { clear_bit(BLK_MQ_S_STOPPED, &hctx->state); - preempt_disable(); + migrate_disable(); blk_mq_run_hw_queue(hctx, false); - preempt_enable(); + migrate_enable(); } EXPORT_SYMBOL(blk_mq_start_hw_queue); @@ -870,9 +890,9 @@ continue; clear_bit(BLK_MQ_S_STOPPED, &hctx->state); - preempt_disable(); + migrate_disable(); blk_mq_run_hw_queue(hctx, async); - preempt_enable(); + migrate_enable(); } } EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues); @@ -1494,7 +1514,7 @@ { 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); else if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) return blk_mq_hctx_cpu_online(hctx, cpu); diff -Nur linux-3.18.9.orig/block/blk-mq-cpu.c linux-3.18.9/block/blk-mq-cpu.c --- linux-3.18.9.orig/block/blk-mq-cpu.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/block/blk-mq-cpu.c 2015-03-15 16:03:03.696094875 -0500 @@ -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-3.18.9.orig/block/blk-mq.h linux-3.18.9/block/blk-mq.h --- linux-3.18.9.orig/block/blk-mq.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/block/blk-mq.h 2015-03-15 16:03:03.700094875 -0500 @@ -73,7 +73,10 @@ 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; } /* @@ -84,12 +87,12 @@ */ 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-3.18.9.orig/block/blk-softirq.c linux-3.18.9/block/blk-softirq.c --- linux-3.18.9.orig/block/blk-softirq.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/block/blk-softirq.c 2015-03-15 16:03:03.700094875 -0500 @@ -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-3.18.9.orig/block/bounce.c linux-3.18.9/block/bounce.c --- linux-3.18.9.orig/block/bounce.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/block/bounce.c 2015-03-15 16:03:03.700094875 -0500 @@ -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-3.18.9.orig/crypto/algapi.c linux-3.18.9/crypto/algapi.c --- linux-3.18.9.orig/crypto/algapi.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/crypto/algapi.c 2015-03-15 16:03:03.700094875 -0500 @@ -698,13 +698,13 @@ 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-3.18.9.orig/crypto/api.c linux-3.18.9/crypto/api.c --- linux-3.18.9.orig/crypto/api.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/crypto/api.c 2015-03-15 16:03:03.700094875 -0500 @@ -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-3.18.9.orig/crypto/internal.h linux-3.18.9/crypto/internal.h --- linux-3.18.9.orig/crypto/internal.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/crypto/internal.h 2015-03-15 16:03:03.700094875 -0500 @@ -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-3.18.9.orig/Documentation/hwlat_detector.txt linux-3.18.9/Documentation/hwlat_detector.txt --- linux-3.18.9.orig/Documentation/hwlat_detector.txt 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/Documentation/hwlat_detector.txt 2015-03-15 16:03:03.704094875 -0500 @@ -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-3.18.9.orig/Documentation/sysrq.txt linux-3.18.9/Documentation/sysrq.txt --- linux-3.18.9.orig/Documentation/sysrq.txt 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/Documentation/sysrq.txt 2015-03-15 16:03:03.704094875 -0500 @@ -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-3.18.9.orig/Documentation/trace/histograms.txt linux-3.18.9/Documentation/trace/histograms.txt --- linux-3.18.9.orig/Documentation/trace/histograms.txt 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/Documentation/trace/histograms.txt 2015-03-15 16:03:03.704094875 -0500 @@ -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-3.18.9.orig/drivers/acpi/acpica/acglobal.h linux-3.18.9/drivers/acpi/acpica/acglobal.h --- linux-3.18.9.orig/drivers/acpi/acpica/acglobal.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/acpi/acpica/acglobal.h 2015-03-15 16:03:03.704094875 -0500 @@ -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-3.18.9.orig/drivers/acpi/acpica/hwregs.c linux-3.18.9/drivers/acpi/acpica/hwregs.c --- linux-3.18.9.orig/drivers/acpi/acpica/hwregs.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/acpi/acpica/hwregs.c 2015-03-15 16:03:03.704094875 -0500 @@ -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-3.18.9.orig/drivers/acpi/acpica/hwxface.c linux-3.18.9/drivers/acpi/acpica/hwxface.c --- linux-3.18.9.orig/drivers/acpi/acpica/hwxface.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/acpi/acpica/hwxface.c 2015-03-15 16:03:03.704094875 -0500 @@ -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-3.18.9.orig/drivers/acpi/acpica/utmutex.c linux-3.18.9/drivers/acpi/acpica/utmutex.c --- linux-3.18.9.orig/drivers/acpi/acpica/utmutex.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/acpi/acpica/utmutex.c 2015-03-15 16:03:03.704094875 -0500 @@ -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-3.18.9.orig/drivers/ata/libata-sff.c linux-3.18.9/drivers/ata/libata-sff.c --- linux-3.18.9.orig/drivers/ata/libata-sff.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/ata/libata-sff.c 2015-03-15 16:03:03.704094875 -0500 @@ -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-3.18.9.orig/drivers/char/random.c linux-3.18.9/drivers/char/random.c --- linux-3.18.9.orig/drivers/char/random.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/char/random.c 2015-03-15 16:03:03.708094875 -0500 @@ -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-3.18.9.orig/drivers/clocksource/tcb_clksrc.c linux-3.18.9/drivers/clocksource/tcb_clksrc.c --- linux-3.18.9.orig/drivers/clocksource/tcb_clksrc.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/clocksource/tcb_clksrc.c 2015-03-15 16:03:03.708094875 -0500 @@ -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-3.18.9.orig/drivers/clocksource/timer-atmel-pit.c linux-3.18.9/drivers/clocksource/timer-atmel-pit.c --- linux-3.18.9.orig/drivers/clocksource/timer-atmel-pit.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/clocksource/timer-atmel-pit.c 2015-03-15 16:03:03.708094875 -0500 @@ -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-3.18.9.orig/drivers/gpio/gpio-omap.c linux-3.18.9/drivers/gpio/gpio-omap.c --- linux-3.18.9.orig/drivers/gpio/gpio-omap.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/gpio/gpio-omap.c 2015-03-15 16:03:03.708094875 -0500 @@ -57,7 +57,7 @@ u32 saved_datain; u32 level_mask; u32 toggle_mask; - spinlock_t lock; + raw_spinlock_t lock; struct gpio_chip chip; struct clk *dbck; u32 mod_usage; @@ -503,19 +503,19 @@ (type & (IRQ_TYPE_LEVEL_LOW|IRQ_TYPE_LEVEL_HIGH))) return -EINVAL; - spin_lock_irqsave(&bank->lock, flags); + raw_spin_lock_irqsave(&bank->lock, flags); offset = GPIO_INDEX(bank, gpio); retval = omap_set_gpio_triggering(bank, offset, type); if (!LINE_USED(bank->mod_usage, offset)) { omap_enable_gpio_module(bank, offset); omap_set_gpio_direction(bank, offset, 1); } else if (!omap_gpio_is_input(bank, BIT(offset))) { - spin_unlock_irqrestore(&bank->lock, flags); + raw_spin_unlock_irqrestore(&bank->lock, flags); return -EINVAL; } bank->irq_usage |= BIT(GPIO_INDEX(bank, gpio)); - 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); @@ -633,14 +633,14 @@ 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; } @@ -675,7 +675,7 @@ if (!BANK_USED(bank)) pm_runtime_get_sync(bank->dev); - spin_lock_irqsave(&bank->lock, flags); + raw_spin_lock_irqsave(&bank->lock, flags); /* Set trigger to none. You need to enable the desired trigger with * request_irq() or set_irq_type(). Only do this if the IRQ line has * not already been requested. @@ -685,7 +685,7 @@ 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; } @@ -695,11 +695,11 @@ 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)); omap_disable_gpio_module(bank, offset); omap_reset_gpio(bank, bank->chip.base + offset); - spin_unlock_irqrestore(&bank->lock, flags); + raw_spin_unlock_irqrestore(&bank->lock, flags); /* * If this is the last gpio to be freed in the bank, @@ -799,12 +799,12 @@ unsigned long flags; unsigned offset = GPIO_INDEX(bank, gpio); - spin_lock_irqsave(&bank->lock, flags); + raw_spin_lock_irqsave(&bank->lock, flags); gpio_unlock_as_irq(&bank->chip, offset); bank->irq_usage &= ~(BIT(offset)); omap_disable_gpio_module(bank, offset); omap_reset_gpio(bank, gpio); - spin_unlock_irqrestore(&bank->lock, flags); + raw_spin_unlock_irqrestore(&bank->lock, flags); /* * If this is the last IRQ to be freed in the bank, @@ -828,10 +828,10 @@ unsigned int gpio = omap_irq_to_gpio(bank, d->hwirq); unsigned long flags; - spin_lock_irqsave(&bank->lock, flags); + raw_spin_lock_irqsave(&bank->lock, flags); omap_set_gpio_irqenable(bank, gpio, 0); omap_set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), IRQ_TYPE_NONE); - spin_unlock_irqrestore(&bank->lock, flags); + raw_spin_unlock_irqrestore(&bank->lock, flags); } static void omap_gpio_unmask_irq(struct irq_data *d) @@ -842,7 +842,7 @@ 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, GPIO_INDEX(bank, gpio), trigger); @@ -854,7 +854,7 @@ } omap_set_gpio_irqenable(bank, gpio, 1); - spin_unlock_irqrestore(&bank->lock, flags); + raw_spin_unlock_irqrestore(&bank->lock, flags); } /*---------------------------------------------------------------------*/ @@ -867,9 +867,9 @@ 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; } @@ -882,9 +882,9 @@ 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; } @@ -930,9 +930,9 @@ 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; } @@ -942,9 +942,9 @@ 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; } @@ -968,10 +968,10 @@ 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; } @@ -983,9 +983,9 @@ 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; } @@ -996,9 +996,9 @@ 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); } /*---------------------------------------------------------------------*/ @@ -1223,7 +1223,7 @@ else bank->set_dataout = omap_set_gpio_dataout_mask; - spin_lock_init(&bank->lock); + raw_spin_lock_init(&bank->lock); /* Static mapping, never released */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -1270,7 +1270,7 @@ 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. @@ -1323,7 +1323,7 @@ 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; } @@ -1338,7 +1338,7 @@ 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 @@ -1374,14 +1374,14 @@ if (c != bank->context_loss_count) { omap_gpio_restore_context(bank); } else { - spin_unlock_irqrestore(&bank->lock, flags); + 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; } @@ -1436,7 +1436,7 @@ } bank->workaround_enabled = false; - spin_unlock_irqrestore(&bank->lock, flags); + raw_spin_unlock_irqrestore(&bank->lock, flags); return 0; } diff -Nur linux-3.18.9.orig/drivers/gpu/drm/i915/i915_gem.c linux-3.18.9/drivers/gpu/drm/i915/i915_gem.c --- linux-3.18.9.orig/drivers/gpu/drm/i915/i915_gem.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/gpu/drm/i915/i915_gem.c 2015-03-15 16:03:03.712094875 -0500 @@ -5144,7 +5144,7 @@ if (!mutex_is_locked(mutex)) return false; -#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES) +#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES) && !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-3.18.9.orig/drivers/gpu/drm/i915/i915_gem_execbuffer.c linux-3.18.9/drivers/gpu/drm/i915/i915_gem_execbuffer.c --- linux-3.18.9.orig/drivers/gpu/drm/i915/i915_gem_execbuffer.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/gpu/drm/i915/i915_gem_execbuffer.c 2015-03-15 16:03:03.712094875 -0500 @@ -1170,7 +1170,9 @@ return ret; } +#ifndef CONFIG_PREEMPT_RT_BASE trace_i915_gem_ring_dispatch(ring, intel_ring_get_seqno(ring), flags); +#endif i915_gem_execbuffer_move_to_active(vmas, ring); i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj); diff -Nur linux-3.18.9.orig/drivers/i2c/busses/i2c-omap.c linux-3.18.9/drivers/i2c/busses/i2c-omap.c --- linux-3.18.9.orig/drivers/i2c/busses/i2c-omap.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/i2c/busses/i2c-omap.c 2015-03-15 16:03:03.712094875 -0500 @@ -875,15 +875,12 @@ 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-3.18.9.orig/drivers/ide/alim15x3.c linux-3.18.9/drivers/ide/alim15x3.c --- linux-3.18.9.orig/drivers/ide/alim15x3.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/ide/alim15x3.c 2015-03-15 16:03:03.712094875 -0500 @@ -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-3.18.9.orig/drivers/ide/hpt366.c linux-3.18.9/drivers/ide/hpt366.c --- linux-3.18.9.orig/drivers/ide/hpt366.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/ide/hpt366.c 2015-03-15 16:03:03.716094875 -0500 @@ -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-3.18.9.orig/drivers/ide/ide-io.c linux-3.18.9/drivers/ide/ide-io.c --- linux-3.18.9.orig/drivers/ide/ide-io.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/ide/ide-io.c 2015-03-15 16:03:03.716094875 -0500 @@ -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-3.18.9.orig/drivers/ide/ide-iops.c linux-3.18.9/drivers/ide/ide-iops.c --- linux-3.18.9.orig/drivers/ide/ide-iops.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/ide/ide-iops.c 2015-03-15 16:03:03.716094875 -0500 @@ -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-3.18.9.orig/drivers/ide/ide-io-std.c linux-3.18.9/drivers/ide/ide-io-std.c --- linux-3.18.9.orig/drivers/ide/ide-io-std.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/ide/ide-io-std.c 2015-03-15 16:03:03.716094875 -0500 @@ -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-3.18.9.orig/drivers/ide/ide-probe.c linux-3.18.9/drivers/ide/ide-probe.c --- linux-3.18.9.orig/drivers/ide/ide-probe.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/ide/ide-probe.c 2015-03-15 16:03:03.716094875 -0500 @@ -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-3.18.9.orig/drivers/ide/ide-taskfile.c linux-3.18.9/drivers/ide/ide-taskfile.c --- linux-3.18.9.orig/drivers/ide/ide-taskfile.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/ide/ide-taskfile.c 2015-03-15 16:03:03.716094875 -0500 @@ -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-3.18.9.orig/drivers/infiniband/ulp/ipoib/ipoib_multicast.c linux-3.18.9/drivers/infiniband/ulp/ipoib/ipoib_multicast.c --- linux-3.18.9.orig/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2015-03-15 16:03:03.716094875 -0500 @@ -796,7 +796,7 @@ ipoib_mcast_stop_thread(dev, 0); - local_irq_save(flags); + local_irq_save_nort(flags); netif_addr_lock(dev); spin_lock(&priv->lock); @@ -878,7 +878,7 @@ spin_unlock(&priv->lock); netif_addr_unlock(dev); - local_irq_restore(flags); + local_irq_restore_nort(flags); /* We have to cancel outside of the spinlock */ list_for_each_entry_safe(mcast, tmcast, &remove_list, list) { diff -Nur linux-3.18.9.orig/drivers/input/gameport/gameport.c linux-3.18.9/drivers/input/gameport/gameport.c --- linux-3.18.9.orig/drivers/input/gameport/gameport.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/input/gameport/gameport.c 2015-03-15 16:03:03.716094875 -0500 @@ -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-3.18.9.orig/drivers/leds/trigger/Kconfig linux-3.18.9/drivers/leds/trigger/Kconfig --- linux-3.18.9.orig/drivers/leds/trigger/Kconfig 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/leds/trigger/Kconfig 2015-03-15 16:03:03.716094875 -0500 @@ -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-3.18.9.orig/drivers/md/bcache/Kconfig linux-3.18.9/drivers/md/bcache/Kconfig --- linux-3.18.9.orig/drivers/md/bcache/Kconfig 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/md/bcache/Kconfig 2015-03-15 16:03:03.720094875 -0500 @@ -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-3.18.9.orig/drivers/md/dm.c linux-3.18.9/drivers/md/dm.c --- linux-3.18.9.orig/drivers/md/dm.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/md/dm.c 2015-03-15 16:03:03.720094875 -0500 @@ -1898,14 +1898,14 @@ if (map_request(ti, clone, md)) goto requeued; - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); spin_lock(q->queue_lock); } goto out; requeued: - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); spin_lock(q->queue_lock); delay_and_out: diff -Nur linux-3.18.9.orig/drivers/md/raid5.c linux-3.18.9/drivers/md/raid5.c --- linux-3.18.9.orig/drivers/md/raid5.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/md/raid5.c 2015-03-15 16:03:03.724094875 -0500 @@ -1649,8 +1649,9 @@ 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++; @@ -1702,7 +1703,8 @@ 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 int grow_one_stripe(struct r5conf *conf, int hash) @@ -5708,6 +5710,7 @@ __func__, cpu); break; } + spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock); } put_online_cpus(); diff -Nur linux-3.18.9.orig/drivers/md/raid5.c.orig linux-3.18.9/drivers/md/raid5.c.orig --- linux-3.18.9.orig/drivers/md/raid5.c.orig 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/drivers/md/raid5.c.orig 2015-03-06 16:53:42.000000000 -0600 @@ -0,0 +1,7144 @@ +/* + * raid5.c : Multiple Devices driver for Linux + * Copyright (C) 1996, 1997 Ingo Molnar, Miguel de Icaza, Gadi Oxman + * Copyright (C) 1999, 2000 Ingo Molnar + * Copyright (C) 2002, 2003 H. Peter Anvin + * + * RAID-4/5/6 management functions. + * Thanks to Penguin Computing for making the RAID-6 development possible + * by donating a test server! + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * You should have received a copy of the GNU General Public License + * (for example /usr/src/linux/COPYING); if not, write to the Free + * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +/* + * BITMAP UNPLUGGING: + * + * The sequencing for updating the bitmap reliably is a little + * subtle (and I got it wrong the first time) so it deserves some + * explanation. + * + * We group bitmap updates into batches. Each batch has a number. + * We may write out several batches at once, but that isn't very important. + * conf->seq_write is the number of the last batch successfully written. + * conf->seq_flush is the number of the last batch that was closed to + * new additions. + * When we discover that we will need to write to any block in a stripe + * (in add_stripe_bio) we update the in-memory bitmap and record in sh->bm_seq + * the number of the batch it will be in. This is seq_flush+1. + * When we are ready to do a write, if that batch hasn't been written yet, + * we plug the array and queue the stripe for later. + * When an unplug happens, we increment bm_flush, thus closing the current + * batch. + * When we notice that bm_flush > bm_write, we write out all pending updates + * to the bitmap, and advance bm_write to where bm_flush was. + * This may occasionally write a bit out twice, but is sure never to + * miss any bits. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "md.h" +#include "raid5.h" +#include "raid0.h" +#include "bitmap.h" + +#define cpu_to_group(cpu) cpu_to_node(cpu) +#define ANY_GROUP NUMA_NO_NODE + +static bool devices_handle_discard_safely = false; +module_param(devices_handle_discard_safely, bool, 0644); +MODULE_PARM_DESC(devices_handle_discard_safely, + "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions"); +static struct workqueue_struct *raid5_wq; +/* + * Stripe cache + */ + +#define NR_STRIPES 256 +#define STRIPE_SIZE PAGE_SIZE +#define STRIPE_SHIFT (PAGE_SHIFT - 9) +#define STRIPE_SECTORS (STRIPE_SIZE>>9) +#define IO_THRESHOLD 1 +#define BYPASS_THRESHOLD 1 +#define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head)) +#define HASH_MASK (NR_HASH - 1) +#define MAX_STRIPE_BATCH 8 + +static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect) +{ + int hash = (sect >> STRIPE_SHIFT) & HASH_MASK; + return &conf->stripe_hashtbl[hash]; +} + +static inline int stripe_hash_locks_hash(sector_t sect) +{ + return (sect >> STRIPE_SHIFT) & STRIPE_HASH_LOCKS_MASK; +} + +static inline void lock_device_hash_lock(struct r5conf *conf, int hash) +{ + spin_lock_irq(conf->hash_locks + hash); + spin_lock(&conf->device_lock); +} + +static inline void unlock_device_hash_lock(struct r5conf *conf, int hash) +{ + spin_unlock(&conf->device_lock); + spin_unlock_irq(conf->hash_locks + hash); +} + +static inline void lock_all_device_hash_locks_irq(struct r5conf *conf) +{ + int i; + local_irq_disable(); + spin_lock(conf->hash_locks); + for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++) + spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks); + spin_lock(&conf->device_lock); +} + +static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf) +{ + int i; + spin_unlock(&conf->device_lock); + for (i = NR_STRIPE_HASH_LOCKS; i; i--) + spin_unlock(conf->hash_locks + i - 1); + local_irq_enable(); +} + +/* bio's attached to a stripe+device for I/O are linked together in bi_sector + * order without overlap. There may be several bio's per stripe+device, and + * a bio could span several devices. + * When walking this list for a particular stripe+device, we must never proceed + * beyond a bio that extends past this device, as the next bio might no longer + * be valid. + * This function is used to determine the 'next' bio in the list, given the sector + * of the current stripe+device + */ +static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector) +{ + int sectors = bio_sectors(bio); + if (bio->bi_iter.bi_sector + sectors < sector + STRIPE_SECTORS) + return bio->bi_next; + else + return NULL; +} + +/* + * We maintain a biased count of active stripes in the bottom 16 bits of + * bi_phys_segments, and a count of processed stripes in the upper 16 bits + */ +static inline int raid5_bi_processed_stripes(struct bio *bio) +{ + atomic_t *segments = (atomic_t *)&bio->bi_phys_segments; + return (atomic_read(segments) >> 16) & 0xffff; +} + +static inline int raid5_dec_bi_active_stripes(struct bio *bio) +{ + atomic_t *segments = (atomic_t *)&bio->bi_phys_segments; + return atomic_sub_return(1, segments) & 0xffff; +} + +static inline void raid5_inc_bi_active_stripes(struct bio *bio) +{ + atomic_t *segments = (atomic_t *)&bio->bi_phys_segments; + atomic_inc(segments); +} + +static inline void raid5_set_bi_processed_stripes(struct bio *bio, + unsigned int cnt) +{ + atomic_t *segments = (atomic_t *)&bio->bi_phys_segments; + int old, new; + + do { + old = atomic_read(segments); + new = (old & 0xffff) | (cnt << 16); + } while (atomic_cmpxchg(segments, old, new) != old); +} + +static inline void raid5_set_bi_stripes(struct bio *bio, unsigned int cnt) +{ + atomic_t *segments = (atomic_t *)&bio->bi_phys_segments; + atomic_set(segments, cnt); +} + +/* Find first data disk in a raid6 stripe */ +static inline int raid6_d0(struct stripe_head *sh) +{ + if (sh->ddf_layout) + /* ddf always start from first device */ + return 0; + /* md starts just after Q block */ + if (sh->qd_idx == sh->disks - 1) + return 0; + else + return sh->qd_idx + 1; +} +static inline int raid6_next_disk(int disk, int raid_disks) +{ + disk++; + return (disk < raid_disks) ? disk : 0; +} + +/* When walking through the disks in a raid5, starting at raid6_d0, + * We need to map each disk to a 'slot', where the data disks are slot + * 0 .. raid_disks-3, the parity disk is raid_disks-2 and the Q disk + * is raid_disks-1. This help does that mapping. + */ +static int raid6_idx_to_slot(int idx, struct stripe_head *sh, + int *count, int syndrome_disks) +{ + int slot = *count; + + if (sh->ddf_layout) + (*count)++; + if (idx == sh->pd_idx) + return syndrome_disks; + if (idx == sh->qd_idx) + return syndrome_disks + 1; + if (!sh->ddf_layout) + (*count)++; + return slot; +} + +static void return_io(struct bio *return_bi) +{ + struct bio *bi = return_bi; + while (bi) { + + return_bi = bi->bi_next; + bi->bi_next = NULL; + bi->bi_iter.bi_size = 0; + trace_block_bio_complete(bdev_get_queue(bi->bi_bdev), + bi, 0); + bio_endio(bi, 0); + bi = return_bi; + } +} + +static void print_raid5_conf (struct r5conf *conf); + +static int stripe_operations_active(struct stripe_head *sh) +{ + return sh->check_state || sh->reconstruct_state || + test_bit(STRIPE_BIOFILL_RUN, &sh->state) || + test_bit(STRIPE_COMPUTE_RUN, &sh->state); +} + +static void raid5_wakeup_stripe_thread(struct stripe_head *sh) +{ + struct r5conf *conf = sh->raid_conf; + struct r5worker_group *group; + int thread_cnt; + int i, cpu = sh->cpu; + + if (!cpu_online(cpu)) { + cpu = cpumask_any(cpu_online_mask); + sh->cpu = cpu; + } + + if (list_empty(&sh->lru)) { + struct r5worker_group *group; + group = conf->worker_groups + cpu_to_group(cpu); + list_add_tail(&sh->lru, &group->handle_list); + group->stripes_cnt++; + sh->group = group; + } + + if (conf->worker_cnt_per_group == 0) { + md_wakeup_thread(conf->mddev->thread); + return; + } + + group = conf->worker_groups + cpu_to_group(sh->cpu); + + group->workers[0].working = true; + /* at least one worker should run to avoid race */ + queue_work_on(sh->cpu, raid5_wq, &group->workers[0].work); + + thread_cnt = group->stripes_cnt / MAX_STRIPE_BATCH - 1; + /* wakeup more workers */ + for (i = 1; i < conf->worker_cnt_per_group && thread_cnt > 0; i++) { + if (group->workers[i].working == false) { + group->workers[i].working = true; + queue_work_on(sh->cpu, raid5_wq, + &group->workers[i].work); + thread_cnt--; + } + } +} + +static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh, + struct list_head *temp_inactive_list) +{ + BUG_ON(!list_empty(&sh->lru)); + BUG_ON(atomic_read(&conf->active_stripes)==0); + if (test_bit(STRIPE_HANDLE, &sh->state)) { + if (test_bit(STRIPE_DELAYED, &sh->state) && + !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { + list_add_tail(&sh->lru, &conf->delayed_list); + if (atomic_read(&conf->preread_active_stripes) + < IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + } else if (test_bit(STRIPE_BIT_DELAY, &sh->state) && + sh->bm_seq - conf->seq_write > 0) + list_add_tail(&sh->lru, &conf->bitmap_list); + else { + clear_bit(STRIPE_DELAYED, &sh->state); + clear_bit(STRIPE_BIT_DELAY, &sh->state); + if (conf->worker_cnt_per_group == 0) { + list_add_tail(&sh->lru, &conf->handle_list); + } else { + raid5_wakeup_stripe_thread(sh); + return; + } + } + md_wakeup_thread(conf->mddev->thread); + } else { + BUG_ON(stripe_operations_active(sh)); + if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + if (atomic_dec_return(&conf->preread_active_stripes) + < IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + atomic_dec(&conf->active_stripes); + if (!test_bit(STRIPE_EXPANDING, &sh->state)) + list_add_tail(&sh->lru, temp_inactive_list); + } +} + +static void __release_stripe(struct r5conf *conf, struct stripe_head *sh, + struct list_head *temp_inactive_list) +{ + if (atomic_dec_and_test(&sh->count)) + do_release_stripe(conf, sh, temp_inactive_list); +} + +/* + * @hash could be NR_STRIPE_HASH_LOCKS, then we have a list of inactive_list + * + * Be careful: Only one task can add/delete stripes from temp_inactive_list at + * given time. Adding stripes only takes device lock, while deleting stripes + * only takes hash lock. + */ +static void release_inactive_stripe_list(struct r5conf *conf, + struct list_head *temp_inactive_list, + int hash) +{ + int size; + bool do_wakeup = false; + unsigned long flags; + + if (hash == NR_STRIPE_HASH_LOCKS) { + size = NR_STRIPE_HASH_LOCKS; + hash = NR_STRIPE_HASH_LOCKS - 1; + } else + size = 1; + while (size) { + struct list_head *list = &temp_inactive_list[size - 1]; + + /* + * We don't hold any lock here yet, get_active_stripe() might + * remove stripes from the list + */ + if (!list_empty_careful(list)) { + spin_lock_irqsave(conf->hash_locks + hash, flags); + if (list_empty(conf->inactive_list + hash) && + !list_empty(list)) + atomic_dec(&conf->empty_inactive_list_nr); + list_splice_tail_init(list, conf->inactive_list + hash); + do_wakeup = true; + spin_unlock_irqrestore(conf->hash_locks + hash, flags); + } + size--; + hash--; + } + + if (do_wakeup) { + wake_up(&conf->wait_for_stripe); + if (conf->retry_read_aligned) + md_wakeup_thread(conf->mddev->thread); + } +} + +/* should hold conf->device_lock already */ +static int release_stripe_list(struct r5conf *conf, + struct list_head *temp_inactive_list) +{ + struct stripe_head *sh; + int count = 0; + struct llist_node *head; + + head = llist_del_all(&conf->released_stripes); + head = llist_reverse_order(head); + while (head) { + int hash; + + sh = llist_entry(head, struct stripe_head, release_list); + head = llist_next(head); + /* sh could be readded after STRIPE_ON_RELEASE_LIST is cleard */ + smp_mb(); + clear_bit(STRIPE_ON_RELEASE_LIST, &sh->state); + /* + * Don't worry the bit is set here, because if the bit is set + * again, the count is always > 1. This is true for + * STRIPE_ON_UNPLUG_LIST bit too. + */ + hash = sh->hash_lock_index; + __release_stripe(conf, sh, &temp_inactive_list[hash]); + count++; + } + + return count; +} + +static void release_stripe(struct stripe_head *sh) +{ + struct r5conf *conf = sh->raid_conf; + unsigned long flags; + struct list_head list; + int hash; + bool wakeup; + + /* Avoid release_list until the last reference. + */ + if (atomic_add_unless(&sh->count, -1, 1)) + return; + + if (unlikely(!conf->mddev->thread) || + test_and_set_bit(STRIPE_ON_RELEASE_LIST, &sh->state)) + goto slow_path; + wakeup = llist_add(&sh->release_list, &conf->released_stripes); + if (wakeup) + md_wakeup_thread(conf->mddev->thread); + return; +slow_path: + local_irq_save(flags); + /* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */ + if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) { + INIT_LIST_HEAD(&list); + hash = sh->hash_lock_index; + do_release_stripe(conf, sh, &list); + spin_unlock(&conf->device_lock); + release_inactive_stripe_list(conf, &list, hash); + } + local_irq_restore(flags); +} + +static inline void remove_hash(struct stripe_head *sh) +{ + pr_debug("remove_hash(), stripe %llu\n", + (unsigned long long)sh->sector); + + hlist_del_init(&sh->hash); +} + +static inline void insert_hash(struct r5conf *conf, struct stripe_head *sh) +{ + struct hlist_head *hp = stripe_hash(conf, sh->sector); + + pr_debug("insert_hash(), stripe %llu\n", + (unsigned long long)sh->sector); + + hlist_add_head(&sh->hash, hp); +} + +/* find an idle stripe, make sure it is unhashed, and return it. */ +static struct stripe_head *get_free_stripe(struct r5conf *conf, int hash) +{ + struct stripe_head *sh = NULL; + struct list_head *first; + + if (list_empty(conf->inactive_list + hash)) + goto out; + first = (conf->inactive_list + hash)->next; + sh = list_entry(first, struct stripe_head, lru); + list_del_init(first); + remove_hash(sh); + atomic_inc(&conf->active_stripes); + BUG_ON(hash != sh->hash_lock_index); + if (list_empty(conf->inactive_list + hash)) + atomic_inc(&conf->empty_inactive_list_nr); +out: + return sh; +} + +static void shrink_buffers(struct stripe_head *sh) +{ + struct page *p; + int i; + int num = sh->raid_conf->pool_size; + + for (i = 0; i < num ; i++) { + WARN_ON(sh->dev[i].page != sh->dev[i].orig_page); + p = sh->dev[i].page; + if (!p) + continue; + sh->dev[i].page = NULL; + put_page(p); + } +} + +static int grow_buffers(struct stripe_head *sh) +{ + int i; + int num = sh->raid_conf->pool_size; + + for (i = 0; i < num; i++) { + struct page *page; + + if (!(page = alloc_page(GFP_KERNEL))) { + return 1; + } + sh->dev[i].page = page; + sh->dev[i].orig_page = page; + } + return 0; +} + +static void raid5_build_block(struct stripe_head *sh, int i, int previous); +static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous, + struct stripe_head *sh); + +static void init_stripe(struct stripe_head *sh, sector_t sector, int previous) +{ + struct r5conf *conf = sh->raid_conf; + int i, seq; + + BUG_ON(atomic_read(&sh->count) != 0); + BUG_ON(test_bit(STRIPE_HANDLE, &sh->state)); + BUG_ON(stripe_operations_active(sh)); + + pr_debug("init_stripe called, stripe %llu\n", + (unsigned long long)sector); +retry: + seq = read_seqcount_begin(&conf->gen_lock); + sh->generation = conf->generation - previous; + sh->disks = previous ? conf->previous_raid_disks : conf->raid_disks; + sh->sector = sector; + stripe_set_idx(sector, conf, previous, sh); + sh->state = 0; + + for (i = sh->disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + + if (dev->toread || dev->read || dev->towrite || dev->written || + test_bit(R5_LOCKED, &dev->flags)) { + printk(KERN_ERR "sector=%llx i=%d %p %p %p %p %d\n", + (unsigned long long)sh->sector, i, dev->toread, + dev->read, dev->towrite, dev->written, + test_bit(R5_LOCKED, &dev->flags)); + WARN_ON(1); + } + dev->flags = 0; + raid5_build_block(sh, i, previous); + } + if (read_seqcount_retry(&conf->gen_lock, seq)) + goto retry; + insert_hash(conf, sh); + sh->cpu = smp_processor_id(); +} + +static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector, + short generation) +{ + struct stripe_head *sh; + + pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector); + hlist_for_each_entry(sh, stripe_hash(conf, sector), hash) + if (sh->sector == sector && sh->generation == generation) + return sh; + pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector); + return NULL; +} + +/* + * Need to check if array has failed when deciding whether to: + * - start an array + * - remove non-faulty devices + * - add a spare + * - allow a reshape + * This determination is simple when no reshape is happening. + * However if there is a reshape, we need to carefully check + * both the before and after sections. + * This is because some failed devices may only affect one + * of the two sections, and some non-in_sync devices may + * be insync in the section most affected by failed devices. + */ +static int calc_degraded(struct r5conf *conf) +{ + int degraded, degraded2; + int i; + + rcu_read_lock(); + degraded = 0; + for (i = 0; i < conf->previous_raid_disks; i++) { + struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev); + if (rdev && test_bit(Faulty, &rdev->flags)) + rdev = rcu_dereference(conf->disks[i].replacement); + if (!rdev || test_bit(Faulty, &rdev->flags)) + degraded++; + else if (test_bit(In_sync, &rdev->flags)) + ; + else + /* not in-sync or faulty. + * If the reshape increases the number of devices, + * this is being recovered by the reshape, so + * this 'previous' section is not in_sync. + * If the number of devices is being reduced however, + * the device can only be part of the array if + * we are reverting a reshape, so this section will + * be in-sync. + */ + if (conf->raid_disks >= conf->previous_raid_disks) + degraded++; + } + rcu_read_unlock(); + if (conf->raid_disks == conf->previous_raid_disks) + return degraded; + rcu_read_lock(); + degraded2 = 0; + for (i = 0; i < conf->raid_disks; i++) { + struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev); + if (rdev && test_bit(Faulty, &rdev->flags)) + rdev = rcu_dereference(conf->disks[i].replacement); + if (!rdev || test_bit(Faulty, &rdev->flags)) + degraded2++; + else if (test_bit(In_sync, &rdev->flags)) + ; + else + /* not in-sync or faulty. + * If reshape increases the number of devices, this + * section has already been recovered, else it + * almost certainly hasn't. + */ + if (conf->raid_disks <= conf->previous_raid_disks) + degraded2++; + } + rcu_read_unlock(); + if (degraded2 > degraded) + return degraded2; + return degraded; +} + +static int has_failed(struct r5conf *conf) +{ + int degraded; + + if (conf->mddev->reshape_position == MaxSector) + return conf->mddev->degraded > conf->max_degraded; + + degraded = calc_degraded(conf); + if (degraded > conf->max_degraded) + return 1; + return 0; +} + +static struct stripe_head * +get_active_stripe(struct r5conf *conf, sector_t sector, + int previous, int noblock, int noquiesce) +{ + struct stripe_head *sh; + int hash = stripe_hash_locks_hash(sector); + + pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector); + + spin_lock_irq(conf->hash_locks + hash); + + do { + wait_event_lock_irq(conf->wait_for_stripe, + conf->quiesce == 0 || noquiesce, + *(conf->hash_locks + hash)); + sh = __find_stripe(conf, sector, conf->generation - previous); + if (!sh) { + if (!conf->inactive_blocked) + sh = get_free_stripe(conf, hash); + if (noblock && sh == NULL) + break; + if (!sh) { + conf->inactive_blocked = 1; + wait_event_lock_irq( + conf->wait_for_stripe, + !list_empty(conf->inactive_list + hash) && + (atomic_read(&conf->active_stripes) + < (conf->max_nr_stripes * 3 / 4) + || !conf->inactive_blocked), + *(conf->hash_locks + hash)); + conf->inactive_blocked = 0; + } else { + init_stripe(sh, sector, previous); + atomic_inc(&sh->count); + } + } else if (!atomic_inc_not_zero(&sh->count)) { + spin_lock(&conf->device_lock); + if (!atomic_read(&sh->count)) { + if (!test_bit(STRIPE_HANDLE, &sh->state)) + atomic_inc(&conf->active_stripes); + BUG_ON(list_empty(&sh->lru) && + !test_bit(STRIPE_EXPANDING, &sh->state)); + list_del_init(&sh->lru); + if (sh->group) { + sh->group->stripes_cnt--; + sh->group = NULL; + } + } + atomic_inc(&sh->count); + spin_unlock(&conf->device_lock); + } + } while (sh == NULL); + + spin_unlock_irq(conf->hash_locks + hash); + return sh; +} + +/* Determine if 'data_offset' or 'new_data_offset' should be used + * in this stripe_head. + */ +static int use_new_offset(struct r5conf *conf, struct stripe_head *sh) +{ + sector_t progress = conf->reshape_progress; + /* Need a memory barrier to make sure we see the value + * of conf->generation, or ->data_offset that was set before + * reshape_progress was updated. + */ + smp_rmb(); + if (progress == MaxSector) + return 0; + if (sh->generation == conf->generation - 1) + return 0; + /* We are in a reshape, and this is a new-generation stripe, + * so use new_data_offset. + */ + return 1; +} + +static void +raid5_end_read_request(struct bio *bi, int error); +static void +raid5_end_write_request(struct bio *bi, int error); + +static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) +{ + struct r5conf *conf = sh->raid_conf; + int i, disks = sh->disks; + + might_sleep(); + + for (i = disks; i--; ) { + int rw; + int replace_only = 0; + struct bio *bi, *rbi; + struct md_rdev *rdev, *rrdev = NULL; + if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) { + if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags)) + rw = WRITE_FUA; + else + rw = WRITE; + if (test_bit(R5_Discard, &sh->dev[i].flags)) + rw |= REQ_DISCARD; + } else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags)) + rw = READ; + else if (test_and_clear_bit(R5_WantReplace, + &sh->dev[i].flags)) { + rw = WRITE; + replace_only = 1; + } else + continue; + if (test_and_clear_bit(R5_SyncIO, &sh->dev[i].flags)) + rw |= REQ_SYNC; + + bi = &sh->dev[i].req; + rbi = &sh->dev[i].rreq; /* For writing to replacement */ + + rcu_read_lock(); + rrdev = rcu_dereference(conf->disks[i].replacement); + smp_mb(); /* Ensure that if rrdev is NULL, rdev won't be */ + rdev = rcu_dereference(conf->disks[i].rdev); + if (!rdev) { + rdev = rrdev; + rrdev = NULL; + } + if (rw & WRITE) { + if (replace_only) + rdev = NULL; + if (rdev == rrdev) + /* We raced and saw duplicates */ + rrdev = NULL; + } else { + if (test_bit(R5_ReadRepl, &sh->dev[i].flags) && rrdev) + rdev = rrdev; + rrdev = NULL; + } + + if (rdev && test_bit(Faulty, &rdev->flags)) + rdev = NULL; + if (rdev) + atomic_inc(&rdev->nr_pending); + if (rrdev && test_bit(Faulty, &rrdev->flags)) + rrdev = NULL; + if (rrdev) + atomic_inc(&rrdev->nr_pending); + rcu_read_unlock(); + + /* We have already checked bad blocks for reads. Now + * need to check for writes. We never accept write errors + * on the replacement, so we don't to check rrdev. + */ + while ((rw & WRITE) && rdev && + test_bit(WriteErrorSeen, &rdev->flags)) { + sector_t first_bad; + int bad_sectors; + int bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS, + &first_bad, &bad_sectors); + if (!bad) + break; + + if (bad < 0) { + set_bit(BlockedBadBlocks, &rdev->flags); + if (!conf->mddev->external && + conf->mddev->flags) { + /* It is very unlikely, but we might + * still need to write out the + * bad block log - better give it + * a chance*/ + md_check_recovery(conf->mddev); + } + /* + * Because md_wait_for_blocked_rdev + * will dec nr_pending, we must + * increment it first. + */ + atomic_inc(&rdev->nr_pending); + md_wait_for_blocked_rdev(rdev, conf->mddev); + } else { + /* Acknowledged bad block - skip the write */ + rdev_dec_pending(rdev, conf->mddev); + rdev = NULL; + } + } + + if (rdev) { + if (s->syncing || s->expanding || s->expanded + || s->replacing) + md_sync_acct(rdev->bdev, STRIPE_SECTORS); + + set_bit(STRIPE_IO_STARTED, &sh->state); + + bio_reset(bi); + bi->bi_bdev = rdev->bdev; + bi->bi_rw = rw; + bi->bi_end_io = (rw & WRITE) + ? raid5_end_write_request + : raid5_end_read_request; + bi->bi_private = sh; + + pr_debug("%s: for %llu schedule op %ld on disc %d\n", + __func__, (unsigned long long)sh->sector, + bi->bi_rw, i); + atomic_inc(&sh->count); + if (use_new_offset(conf, sh)) + bi->bi_iter.bi_sector = (sh->sector + + rdev->new_data_offset); + else + bi->bi_iter.bi_sector = (sh->sector + + rdev->data_offset); + if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) + bi->bi_rw |= REQ_NOMERGE; + + if (test_bit(R5_SkipCopy, &sh->dev[i].flags)) + WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags)); + sh->dev[i].vec.bv_page = sh->dev[i].page; + bi->bi_vcnt = 1; + bi->bi_io_vec[0].bv_len = STRIPE_SIZE; + bi->bi_io_vec[0].bv_offset = 0; + bi->bi_iter.bi_size = STRIPE_SIZE; + /* + * If this is discard request, set bi_vcnt 0. We don't + * want to confuse SCSI because SCSI will replace payload + */ + if (rw & REQ_DISCARD) + bi->bi_vcnt = 0; + if (rrdev) + set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags); + + if (conf->mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(bi->bi_bdev), + bi, disk_devt(conf->mddev->gendisk), + sh->dev[i].sector); + generic_make_request(bi); + } + if (rrdev) { + if (s->syncing || s->expanding || s->expanded + || s->replacing) + md_sync_acct(rrdev->bdev, STRIPE_SECTORS); + + set_bit(STRIPE_IO_STARTED, &sh->state); + + bio_reset(rbi); + rbi->bi_bdev = rrdev->bdev; + rbi->bi_rw = rw; + BUG_ON(!(rw & WRITE)); + rbi->bi_end_io = raid5_end_write_request; + rbi->bi_private = sh; + + pr_debug("%s: for %llu schedule op %ld on " + "replacement disc %d\n", + __func__, (unsigned long long)sh->sector, + rbi->bi_rw, i); + atomic_inc(&sh->count); + if (use_new_offset(conf, sh)) + rbi->bi_iter.bi_sector = (sh->sector + + rrdev->new_data_offset); + else + rbi->bi_iter.bi_sector = (sh->sector + + rrdev->data_offset); + if (test_bit(R5_SkipCopy, &sh->dev[i].flags)) + WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags)); + sh->dev[i].rvec.bv_page = sh->dev[i].page; + rbi->bi_vcnt = 1; + rbi->bi_io_vec[0].bv_len = STRIPE_SIZE; + rbi->bi_io_vec[0].bv_offset = 0; + rbi->bi_iter.bi_size = STRIPE_SIZE; + /* + * If this is discard request, set bi_vcnt 0. We don't + * want to confuse SCSI because SCSI will replace payload + */ + if (rw & REQ_DISCARD) + rbi->bi_vcnt = 0; + if (conf->mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev), + rbi, disk_devt(conf->mddev->gendisk), + sh->dev[i].sector); + generic_make_request(rbi); + } + if (!rdev && !rrdev) { + if (rw & WRITE) + set_bit(STRIPE_DEGRADED, &sh->state); + pr_debug("skip op %ld on disc %d for sector %llu\n", + bi->bi_rw, i, (unsigned long long)sh->sector); + clear_bit(R5_LOCKED, &sh->dev[i].flags); + set_bit(STRIPE_HANDLE, &sh->state); + } + } +} + +static struct dma_async_tx_descriptor * +async_copy_data(int frombio, struct bio *bio, struct page **page, + sector_t sector, struct dma_async_tx_descriptor *tx, + struct stripe_head *sh) +{ + struct bio_vec bvl; + struct bvec_iter iter; + struct page *bio_page; + int page_offset; + struct async_submit_ctl submit; + enum async_tx_flags flags = 0; + + if (bio->bi_iter.bi_sector >= sector) + page_offset = (signed)(bio->bi_iter.bi_sector - sector) * 512; + else + page_offset = (signed)(sector - bio->bi_iter.bi_sector) * -512; + + if (frombio) + flags |= ASYNC_TX_FENCE; + init_async_submit(&submit, flags, tx, NULL, NULL, NULL); + + bio_for_each_segment(bvl, bio, iter) { + int len = bvl.bv_len; + int clen; + int b_offset = 0; + + if (page_offset < 0) { + b_offset = -page_offset; + page_offset += b_offset; + len -= b_offset; + } + + if (len > 0 && page_offset + len > STRIPE_SIZE) + clen = STRIPE_SIZE - page_offset; + else + clen = len; + + if (clen > 0) { + b_offset += bvl.bv_offset; + bio_page = bvl.bv_page; + if (frombio) { + if (sh->raid_conf->skip_copy && + b_offset == 0 && page_offset == 0 && + clen == STRIPE_SIZE) + *page = bio_page; + else + tx = async_memcpy(*page, bio_page, page_offset, + b_offset, clen, &submit); + } else + tx = async_memcpy(bio_page, *page, b_offset, + page_offset, clen, &submit); + } + /* chain the operations */ + submit.depend_tx = tx; + + if (clen < len) /* hit end of page */ + break; + page_offset += len; + } + + return tx; +} + +static void ops_complete_biofill(void *stripe_head_ref) +{ + struct stripe_head *sh = stripe_head_ref; + struct bio *return_bi = NULL; + int i; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + /* clear completed biofills */ + for (i = sh->disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + + /* acknowledge completion of a biofill operation */ + /* and check if we need to reply to a read request, + * new R5_Wantfill requests are held off until + * !STRIPE_BIOFILL_RUN + */ + if (test_and_clear_bit(R5_Wantfill, &dev->flags)) { + struct bio *rbi, *rbi2; + + BUG_ON(!dev->read); + rbi = dev->read; + dev->read = NULL; + while (rbi && rbi->bi_iter.bi_sector < + dev->sector + STRIPE_SECTORS) { + rbi2 = r5_next_bio(rbi, dev->sector); + if (!raid5_dec_bi_active_stripes(rbi)) { + rbi->bi_next = return_bi; + return_bi = rbi; + } + rbi = rbi2; + } + } + } + clear_bit(STRIPE_BIOFILL_RUN, &sh->state); + + return_io(return_bi); + + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); +} + +static void ops_run_biofill(struct stripe_head *sh) +{ + struct dma_async_tx_descriptor *tx = NULL; + struct async_submit_ctl submit; + int i; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + for (i = sh->disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (test_bit(R5_Wantfill, &dev->flags)) { + struct bio *rbi; + spin_lock_irq(&sh->stripe_lock); + dev->read = rbi = dev->toread; + dev->toread = NULL; + spin_unlock_irq(&sh->stripe_lock); + while (rbi && rbi->bi_iter.bi_sector < + dev->sector + STRIPE_SECTORS) { + tx = async_copy_data(0, rbi, &dev->page, + dev->sector, tx, sh); + rbi = r5_next_bio(rbi, dev->sector); + } + } + } + + atomic_inc(&sh->count); + init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_biofill, sh, NULL); + async_trigger_callback(&submit); +} + +static void mark_target_uptodate(struct stripe_head *sh, int target) +{ + struct r5dev *tgt; + + if (target < 0) + return; + + tgt = &sh->dev[target]; + set_bit(R5_UPTODATE, &tgt->flags); + BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags)); + clear_bit(R5_Wantcompute, &tgt->flags); +} + +static void ops_complete_compute(void *stripe_head_ref) +{ + struct stripe_head *sh = stripe_head_ref; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + /* mark the computed target(s) as uptodate */ + mark_target_uptodate(sh, sh->ops.target); + mark_target_uptodate(sh, sh->ops.target2); + + clear_bit(STRIPE_COMPUTE_RUN, &sh->state); + if (sh->check_state == check_state_compute_run) + sh->check_state = check_state_compute_result; + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); +} + +/* return a pointer to the address conversion region of the scribble buffer */ +static addr_conv_t *to_addr_conv(struct stripe_head *sh, + struct raid5_percpu *percpu) +{ + return percpu->scribble + sizeof(struct page *) * (sh->disks + 2); +} + +static struct dma_async_tx_descriptor * +ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu) +{ + int disks = sh->disks; + struct page **xor_srcs = percpu->scribble; + int target = sh->ops.target; + struct r5dev *tgt = &sh->dev[target]; + struct page *xor_dest = tgt->page; + int count = 0; + struct dma_async_tx_descriptor *tx; + struct async_submit_ctl submit; + int i; + + pr_debug("%s: stripe %llu block: %d\n", + __func__, (unsigned long long)sh->sector, target); + BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags)); + + for (i = disks; i--; ) + if (i != target) + xor_srcs[count++] = sh->dev[i].page; + + atomic_inc(&sh->count); + + init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL, + ops_complete_compute, sh, to_addr_conv(sh, percpu)); + if (unlikely(count == 1)) + tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit); + else + tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit); + + return tx; +} + +/* set_syndrome_sources - populate source buffers for gen_syndrome + * @srcs - (struct page *) array of size sh->disks + * @sh - stripe_head to parse + * + * Populates srcs in proper layout order for the stripe and returns the + * 'count' of sources to be used in a call to async_gen_syndrome. The P + * destination buffer is recorded in srcs[count] and the Q destination + * is recorded in srcs[count+1]]. + */ +static int set_syndrome_sources(struct page **srcs, struct stripe_head *sh) +{ + int disks = sh->disks; + int syndrome_disks = sh->ddf_layout ? disks : (disks - 2); + int d0_idx = raid6_d0(sh); + int count; + int i; + + for (i = 0; i < disks; i++) + srcs[i] = NULL; + + count = 0; + i = d0_idx; + do { + int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks); + + srcs[slot] = sh->dev[i].page; + i = raid6_next_disk(i, disks); + } while (i != d0_idx); + + return syndrome_disks; +} + +static struct dma_async_tx_descriptor * +ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu) +{ + int disks = sh->disks; + struct page **blocks = percpu->scribble; + int target; + int qd_idx = sh->qd_idx; + struct dma_async_tx_descriptor *tx; + struct async_submit_ctl submit; + struct r5dev *tgt; + struct page *dest; + int i; + int count; + + if (sh->ops.target < 0) + target = sh->ops.target2; + else if (sh->ops.target2 < 0) + target = sh->ops.target; + else + /* we should only have one valid target */ + BUG(); + BUG_ON(target < 0); + pr_debug("%s: stripe %llu block: %d\n", + __func__, (unsigned long long)sh->sector, target); + + tgt = &sh->dev[target]; + BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags)); + dest = tgt->page; + + atomic_inc(&sh->count); + + if (target == qd_idx) { + count = set_syndrome_sources(blocks, sh); + blocks[count] = NULL; /* regenerating p is not necessary */ + BUG_ON(blocks[count+1] != dest); /* q should already be set */ + init_async_submit(&submit, ASYNC_TX_FENCE, NULL, + ops_complete_compute, sh, + to_addr_conv(sh, percpu)); + tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); + } else { + /* Compute any data- or p-drive using XOR */ + count = 0; + for (i = disks; i-- ; ) { + if (i == target || i == qd_idx) + continue; + blocks[count++] = sh->dev[i].page; + } + + init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, + NULL, ops_complete_compute, sh, + to_addr_conv(sh, percpu)); + tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit); + } + + return tx; +} + +static struct dma_async_tx_descriptor * +ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu) +{ + int i, count, disks = sh->disks; + int syndrome_disks = sh->ddf_layout ? disks : disks-2; + int d0_idx = raid6_d0(sh); + int faila = -1, failb = -1; + int target = sh->ops.target; + int target2 = sh->ops.target2; + struct r5dev *tgt = &sh->dev[target]; + struct r5dev *tgt2 = &sh->dev[target2]; + struct dma_async_tx_descriptor *tx; + struct page **blocks = percpu->scribble; + struct async_submit_ctl submit; + + pr_debug("%s: stripe %llu block1: %d block2: %d\n", + __func__, (unsigned long long)sh->sector, target, target2); + BUG_ON(target < 0 || target2 < 0); + BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags)); + BUG_ON(!test_bit(R5_Wantcompute, &tgt2->flags)); + + /* we need to open-code set_syndrome_sources to handle the + * slot number conversion for 'faila' and 'failb' + */ + for (i = 0; i < disks ; i++) + blocks[i] = NULL; + count = 0; + i = d0_idx; + do { + int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks); + + blocks[slot] = sh->dev[i].page; + + if (i == target) + faila = slot; + if (i == target2) + failb = slot; + i = raid6_next_disk(i, disks); + } while (i != d0_idx); + + BUG_ON(faila == failb); + if (failb < faila) + swap(faila, failb); + pr_debug("%s: stripe: %llu faila: %d failb: %d\n", + __func__, (unsigned long long)sh->sector, faila, failb); + + atomic_inc(&sh->count); + + if (failb == syndrome_disks+1) { + /* Q disk is one of the missing disks */ + if (faila == syndrome_disks) { + /* Missing P+Q, just recompute */ + init_async_submit(&submit, ASYNC_TX_FENCE, NULL, + ops_complete_compute, sh, + to_addr_conv(sh, percpu)); + return async_gen_syndrome(blocks, 0, syndrome_disks+2, + STRIPE_SIZE, &submit); + } else { + struct page *dest; + int data_target; + int qd_idx = sh->qd_idx; + + /* Missing D+Q: recompute D from P, then recompute Q */ + if (target == qd_idx) + data_target = target2; + else + data_target = target; + + count = 0; + for (i = disks; i-- ; ) { + if (i == data_target || i == qd_idx) + continue; + blocks[count++] = sh->dev[i].page; + } + dest = sh->dev[data_target].page; + init_async_submit(&submit, + ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, + NULL, NULL, NULL, + to_addr_conv(sh, percpu)); + tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, + &submit); + + count = set_syndrome_sources(blocks, sh); + init_async_submit(&submit, ASYNC_TX_FENCE, tx, + ops_complete_compute, sh, + to_addr_conv(sh, percpu)); + return async_gen_syndrome(blocks, 0, count+2, + STRIPE_SIZE, &submit); + } + } else { + init_async_submit(&submit, ASYNC_TX_FENCE, NULL, + ops_complete_compute, sh, + to_addr_conv(sh, percpu)); + if (failb == syndrome_disks) { + /* We're missing D+P. */ + return async_raid6_datap_recov(syndrome_disks+2, + STRIPE_SIZE, faila, + blocks, &submit); + } else { + /* We're missing D+D. */ + return async_raid6_2data_recov(syndrome_disks+2, + STRIPE_SIZE, faila, failb, + blocks, &submit); + } + } +} + +static void ops_complete_prexor(void *stripe_head_ref) +{ + struct stripe_head *sh = stripe_head_ref; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); +} + +static struct dma_async_tx_descriptor * +ops_run_prexor(struct stripe_head *sh, struct raid5_percpu *percpu, + struct dma_async_tx_descriptor *tx) +{ + int disks = sh->disks; + struct page **xor_srcs = percpu->scribble; + int count = 0, pd_idx = sh->pd_idx, i; + struct async_submit_ctl submit; + + /* existing parity data subtracted */ + struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + /* Only process blocks that are known to be uptodate */ + if (test_bit(R5_Wantdrain, &dev->flags)) + xor_srcs[count++] = dev->page; + } + + init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx, + ops_complete_prexor, sh, to_addr_conv(sh, percpu)); + tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit); + + return tx; +} + +static struct dma_async_tx_descriptor * +ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) +{ + int disks = sh->disks; + int i; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + struct bio *chosen; + + if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) { + struct bio *wbi; + + spin_lock_irq(&sh->stripe_lock); + chosen = dev->towrite; + dev->towrite = NULL; + BUG_ON(dev->written); + wbi = dev->written = chosen; + spin_unlock_irq(&sh->stripe_lock); + WARN_ON(dev->page != dev->orig_page); + + while (wbi && wbi->bi_iter.bi_sector < + dev->sector + STRIPE_SECTORS) { + if (wbi->bi_rw & REQ_FUA) + set_bit(R5_WantFUA, &dev->flags); + if (wbi->bi_rw & REQ_SYNC) + set_bit(R5_SyncIO, &dev->flags); + if (wbi->bi_rw & REQ_DISCARD) + set_bit(R5_Discard, &dev->flags); + else { + tx = async_copy_data(1, wbi, &dev->page, + dev->sector, tx, sh); + if (dev->page != dev->orig_page) { + set_bit(R5_SkipCopy, &dev->flags); + clear_bit(R5_UPTODATE, &dev->flags); + clear_bit(R5_OVERWRITE, &dev->flags); + } + } + wbi = r5_next_bio(wbi, dev->sector); + } + } + } + + return tx; +} + +static void ops_complete_reconstruct(void *stripe_head_ref) +{ + struct stripe_head *sh = stripe_head_ref; + int disks = sh->disks; + int pd_idx = sh->pd_idx; + int qd_idx = sh->qd_idx; + int i; + bool fua = false, sync = false, discard = false; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + for (i = disks; i--; ) { + fua |= test_bit(R5_WantFUA, &sh->dev[i].flags); + sync |= test_bit(R5_SyncIO, &sh->dev[i].flags); + discard |= test_bit(R5_Discard, &sh->dev[i].flags); + } + + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + + if (dev->written || i == pd_idx || i == qd_idx) { + if (!discard && !test_bit(R5_SkipCopy, &dev->flags)) + set_bit(R5_UPTODATE, &dev->flags); + if (fua) + set_bit(R5_WantFUA, &dev->flags); + if (sync) + set_bit(R5_SyncIO, &dev->flags); + } + } + + if (sh->reconstruct_state == reconstruct_state_drain_run) + sh->reconstruct_state = reconstruct_state_drain_result; + else if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) + sh->reconstruct_state = reconstruct_state_prexor_drain_result; + else { + BUG_ON(sh->reconstruct_state != reconstruct_state_run); + sh->reconstruct_state = reconstruct_state_result; + } + + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); +} + +static void +ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu, + struct dma_async_tx_descriptor *tx) +{ + int disks = sh->disks; + struct page **xor_srcs = percpu->scribble; + struct async_submit_ctl submit; + int count = 0, pd_idx = sh->pd_idx, i; + struct page *xor_dest; + int prexor = 0; + unsigned long flags; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + for (i = 0; i < sh->disks; i++) { + if (pd_idx == i) + continue; + if (!test_bit(R5_Discard, &sh->dev[i].flags)) + break; + } + if (i >= sh->disks) { + atomic_inc(&sh->count); + set_bit(R5_Discard, &sh->dev[pd_idx].flags); + ops_complete_reconstruct(sh); + return; + } + /* check if prexor is active which means only process blocks + * that are part of a read-modify-write (written) + */ + if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) { + prexor = 1; + xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page; + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (dev->written) + xor_srcs[count++] = dev->page; + } + } else { + xor_dest = sh->dev[pd_idx].page; + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (i != pd_idx) + xor_srcs[count++] = dev->page; + } + } + + /* 1/ if we prexor'd then the dest is reused as a source + * 2/ if we did not prexor then we are redoing the parity + * set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST + * for the synchronous xor case + */ + flags = ASYNC_TX_ACK | + (prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST); + + atomic_inc(&sh->count); + + init_async_submit(&submit, flags, tx, ops_complete_reconstruct, sh, + to_addr_conv(sh, percpu)); + if (unlikely(count == 1)) + tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit); + else + tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit); +} + +static void +ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu, + struct dma_async_tx_descriptor *tx) +{ + struct async_submit_ctl submit; + struct page **blocks = percpu->scribble; + int count, i; + + pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); + + for (i = 0; i < sh->disks; i++) { + if (sh->pd_idx == i || sh->qd_idx == i) + continue; + if (!test_bit(R5_Discard, &sh->dev[i].flags)) + break; + } + if (i >= sh->disks) { + atomic_inc(&sh->count); + set_bit(R5_Discard, &sh->dev[sh->pd_idx].flags); + set_bit(R5_Discard, &sh->dev[sh->qd_idx].flags); + ops_complete_reconstruct(sh); + return; + } + + count = set_syndrome_sources(blocks, sh); + + atomic_inc(&sh->count); + + init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_reconstruct, + sh, to_addr_conv(sh, percpu)); + async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); +} + +static void ops_complete_check(void *stripe_head_ref) +{ + struct stripe_head *sh = stripe_head_ref; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + sh->check_state = check_state_check_result; + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); +} + +static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu) +{ + int disks = sh->disks; + int pd_idx = sh->pd_idx; + int qd_idx = sh->qd_idx; + struct page *xor_dest; + struct page **xor_srcs = percpu->scribble; + struct dma_async_tx_descriptor *tx; + struct async_submit_ctl submit; + int count; + int i; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + count = 0; + xor_dest = sh->dev[pd_idx].page; + xor_srcs[count++] = xor_dest; + for (i = disks; i--; ) { + if (i == pd_idx || i == qd_idx) + continue; + xor_srcs[count++] = sh->dev[i].page; + } + + init_async_submit(&submit, 0, NULL, NULL, NULL, + to_addr_conv(sh, percpu)); + tx = async_xor_val(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, + &sh->ops.zero_sum_result, &submit); + + atomic_inc(&sh->count); + init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_check, sh, NULL); + tx = async_trigger_callback(&submit); +} + +static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu, int checkp) +{ + struct page **srcs = percpu->scribble; + struct async_submit_ctl submit; + int count; + + pr_debug("%s: stripe %llu checkp: %d\n", __func__, + (unsigned long long)sh->sector, checkp); + + count = set_syndrome_sources(srcs, sh); + if (!checkp) + srcs[count] = NULL; + + atomic_inc(&sh->count); + init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check, + sh, to_addr_conv(sh, percpu)); + async_syndrome_val(srcs, 0, count+2, STRIPE_SIZE, + &sh->ops.zero_sum_result, percpu->spare_page, &submit); +} + +static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) +{ + int overlap_clear = 0, i, disks = sh->disks; + struct dma_async_tx_descriptor *tx = NULL; + struct r5conf *conf = sh->raid_conf; + int level = conf->level; + struct raid5_percpu *percpu; + unsigned long cpu; + + cpu = get_cpu(); + percpu = per_cpu_ptr(conf->percpu, cpu); + if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { + ops_run_biofill(sh); + overlap_clear++; + } + + if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request)) { + if (level < 6) + tx = ops_run_compute5(sh, percpu); + else { + if (sh->ops.target2 < 0 || sh->ops.target < 0) + tx = ops_run_compute6_1(sh, percpu); + else + tx = ops_run_compute6_2(sh, percpu); + } + /* terminate the chain if reconstruct is not set to be run */ + if (tx && !test_bit(STRIPE_OP_RECONSTRUCT, &ops_request)) + async_tx_ack(tx); + } + + if (test_bit(STRIPE_OP_PREXOR, &ops_request)) + tx = ops_run_prexor(sh, percpu, tx); + + if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) { + tx = ops_run_biodrain(sh, tx); + overlap_clear++; + } + + if (test_bit(STRIPE_OP_RECONSTRUCT, &ops_request)) { + if (level < 6) + ops_run_reconstruct5(sh, percpu, tx); + else + ops_run_reconstruct6(sh, percpu, tx); + } + + if (test_bit(STRIPE_OP_CHECK, &ops_request)) { + if (sh->check_state == check_state_run) + ops_run_check_p(sh, percpu); + else if (sh->check_state == check_state_run_q) + ops_run_check_pq(sh, percpu, 0); + else if (sh->check_state == check_state_run_pq) + ops_run_check_pq(sh, percpu, 1); + else + BUG(); + } + + if (overlap_clear) + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (test_and_clear_bit(R5_Overlap, &dev->flags)) + wake_up(&sh->raid_conf->wait_for_overlap); + } + put_cpu(); +} + +static int grow_one_stripe(struct r5conf *conf, int hash) +{ + struct stripe_head *sh; + sh = kmem_cache_zalloc(conf->slab_cache, GFP_KERNEL); + if (!sh) + return 0; + + sh->raid_conf = conf; + + spin_lock_init(&sh->stripe_lock); + + if (grow_buffers(sh)) { + shrink_buffers(sh); + kmem_cache_free(conf->slab_cache, sh); + return 0; + } + sh->hash_lock_index = hash; + /* we just created an active stripe so... */ + atomic_set(&sh->count, 1); + atomic_inc(&conf->active_stripes); + INIT_LIST_HEAD(&sh->lru); + release_stripe(sh); + return 1; +} + +static int grow_stripes(struct r5conf *conf, int num) +{ + struct kmem_cache *sc; + int devs = max(conf->raid_disks, conf->previous_raid_disks); + int hash; + + if (conf->mddev->gendisk) + sprintf(conf->cache_name[0], + "raid%d-%s", conf->level, mdname(conf->mddev)); + else + sprintf(conf->cache_name[0], + "raid%d-%p", conf->level, conf->mddev); + sprintf(conf->cache_name[1], "%s-alt", conf->cache_name[0]); + + conf->active_name = 0; + sc = kmem_cache_create(conf->cache_name[conf->active_name], + sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev), + 0, 0, NULL); + if (!sc) + return 1; + conf->slab_cache = sc; + conf->pool_size = devs; + hash = conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS; + while (num--) { + if (!grow_one_stripe(conf, hash)) + return 1; + conf->max_nr_stripes++; + hash = (hash + 1) % NR_STRIPE_HASH_LOCKS; + } + return 0; +} + +/** + * scribble_len - return the required size of the scribble region + * @num - total number of disks in the array + * + * The size must be enough to contain: + * 1/ a struct page pointer for each device in the array +2 + * 2/ room to convert each entry in (1) to its corresponding dma + * (dma_map_page()) or page (page_address()) address. + * + * Note: the +2 is for the destination buffers of the ddf/raid6 case where we + * calculate over all devices (not just the data blocks), using zeros in place + * of the P and Q blocks. + */ +static size_t scribble_len(int num) +{ + size_t len; + + len = sizeof(struct page *) * (num+2) + sizeof(addr_conv_t) * (num+2); + + return len; +} + +static int resize_stripes(struct r5conf *conf, int newsize) +{ + /* Make all the stripes able to hold 'newsize' devices. + * New slots in each stripe get 'page' set to a new page. + * + * This happens in stages: + * 1/ create a new kmem_cache and allocate the required number of + * stripe_heads. + * 2/ gather all the old stripe_heads and transfer the pages across + * to the new stripe_heads. This will have the side effect of + * freezing the array as once all stripe_heads have been collected, + * no IO will be possible. Old stripe heads are freed once their + * pages have been transferred over, and the old kmem_cache is + * freed when all stripes are done. + * 3/ reallocate conf->disks to be suitable bigger. If this fails, + * we simple return a failre status - no need to clean anything up. + * 4/ allocate new pages for the new slots in the new stripe_heads. + * If this fails, we don't bother trying the shrink the + * stripe_heads down again, we just leave them as they are. + * As each stripe_head is processed the new one is released into + * active service. + * + * Once step2 is started, we cannot afford to wait for a write, + * so we use GFP_NOIO allocations. + */ + struct stripe_head *osh, *nsh; + LIST_HEAD(newstripes); + struct disk_info *ndisks; + unsigned long cpu; + int err; + struct kmem_cache *sc; + int i; + int hash, cnt; + + if (newsize <= conf->pool_size) + return 0; /* never bother to shrink */ + + err = md_allow_write(conf->mddev); + if (err) + return err; + + /* Step 1 */ + sc = kmem_cache_create(conf->cache_name[1-conf->active_name], + sizeof(struct stripe_head)+(newsize-1)*sizeof(struct r5dev), + 0, 0, NULL); + if (!sc) + return -ENOMEM; + + for (i = conf->max_nr_stripes; i; i--) { + nsh = kmem_cache_zalloc(sc, GFP_KERNEL); + if (!nsh) + break; + + nsh->raid_conf = conf; + spin_lock_init(&nsh->stripe_lock); + + list_add(&nsh->lru, &newstripes); + } + if (i) { + /* didn't get enough, give up */ + while (!list_empty(&newstripes)) { + nsh = list_entry(newstripes.next, struct stripe_head, lru); + list_del(&nsh->lru); + kmem_cache_free(sc, nsh); + } + kmem_cache_destroy(sc); + return -ENOMEM; + } + /* Step 2 - Must use GFP_NOIO now. + * OK, we have enough stripes, start collecting inactive + * stripes and copying them over + */ + hash = 0; + cnt = 0; + list_for_each_entry(nsh, &newstripes, lru) { + lock_device_hash_lock(conf, hash); + wait_event_cmd(conf->wait_for_stripe, + !list_empty(conf->inactive_list + hash), + unlock_device_hash_lock(conf, hash), + lock_device_hash_lock(conf, hash)); + osh = get_free_stripe(conf, hash); + unlock_device_hash_lock(conf, hash); + atomic_set(&nsh->count, 1); + for(i=0; ipool_size; i++) { + nsh->dev[i].page = osh->dev[i].page; + nsh->dev[i].orig_page = osh->dev[i].page; + } + for( ; idev[i].page = NULL; + nsh->hash_lock_index = hash; + kmem_cache_free(conf->slab_cache, osh); + cnt++; + if (cnt >= conf->max_nr_stripes / NR_STRIPE_HASH_LOCKS + + !!((conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS) > hash)) { + hash++; + cnt = 0; + } + } + kmem_cache_destroy(conf->slab_cache); + + /* Step 3. + * At this point, we are holding all the stripes so the array + * is completely stalled, so now is a good time to resize + * conf->disks and the scribble region + */ + ndisks = kzalloc(newsize * sizeof(struct disk_info), GFP_NOIO); + if (ndisks) { + for (i=0; iraid_disks; i++) + ndisks[i] = conf->disks[i]; + kfree(conf->disks); + conf->disks = ndisks; + } else + err = -ENOMEM; + + get_online_cpus(); + conf->scribble_len = scribble_len(newsize); + for_each_present_cpu(cpu) { + struct raid5_percpu *percpu; + void *scribble; + + percpu = per_cpu_ptr(conf->percpu, cpu); + scribble = kmalloc(conf->scribble_len, GFP_NOIO); + + if (scribble) { + kfree(percpu->scribble); + percpu->scribble = scribble; + } else { + err = -ENOMEM; + break; + } + } + put_online_cpus(); + + /* Step 4, return new stripes to service */ + while(!list_empty(&newstripes)) { + nsh = list_entry(newstripes.next, struct stripe_head, lru); + list_del_init(&nsh->lru); + + for (i=conf->raid_disks; i < newsize; i++) + if (nsh->dev[i].page == NULL) { + struct page *p = alloc_page(GFP_NOIO); + nsh->dev[i].page = p; + nsh->dev[i].orig_page = p; + if (!p) + err = -ENOMEM; + } + release_stripe(nsh); + } + /* critical section pass, GFP_NOIO no longer needed */ + + conf->slab_cache = sc; + conf->active_name = 1-conf->active_name; + conf->pool_size = newsize; + return err; +} + +static int drop_one_stripe(struct r5conf *conf, int hash) +{ + struct stripe_head *sh; + + spin_lock_irq(conf->hash_locks + hash); + sh = get_free_stripe(conf, hash); + spin_unlock_irq(conf->hash_locks + hash); + if (!sh) + return 0; + BUG_ON(atomic_read(&sh->count)); + shrink_buffers(sh); + kmem_cache_free(conf->slab_cache, sh); + atomic_dec(&conf->active_stripes); + return 1; +} + +static void shrink_stripes(struct r5conf *conf) +{ + int hash; + for (hash = 0; hash < NR_STRIPE_HASH_LOCKS; hash++) + while (drop_one_stripe(conf, hash)) + ; + + if (conf->slab_cache) + kmem_cache_destroy(conf->slab_cache); + conf->slab_cache = NULL; +} + +static void raid5_end_read_request(struct bio * bi, int error) +{ + struct stripe_head *sh = bi->bi_private; + struct r5conf *conf = sh->raid_conf; + int disks = sh->disks, i; + int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags); + char b[BDEVNAME_SIZE]; + struct md_rdev *rdev = NULL; + sector_t s; + + for (i=0 ; idev[i].req) + break; + + pr_debug("end_read_request %llu/%d, count: %d, uptodate %d.\n", + (unsigned long long)sh->sector, i, atomic_read(&sh->count), + uptodate); + if (i == disks) { + BUG(); + return; + } + if (test_bit(R5_ReadRepl, &sh->dev[i].flags)) + /* If replacement finished while this request was outstanding, + * 'replacement' might be NULL already. + * In that case it moved down to 'rdev'. + * rdev is not removed until all requests are finished. + */ + rdev = conf->disks[i].replacement; + if (!rdev) + rdev = conf->disks[i].rdev; + + if (use_new_offset(conf, sh)) + s = sh->sector + rdev->new_data_offset; + else + s = sh->sector + rdev->data_offset; + if (uptodate) { + set_bit(R5_UPTODATE, &sh->dev[i].flags); + if (test_bit(R5_ReadError, &sh->dev[i].flags)) { + /* Note that this cannot happen on a + * replacement device. We just fail those on + * any error + */ + printk_ratelimited( + KERN_INFO + "md/raid:%s: read error corrected" + " (%lu sectors at %llu on %s)\n", + mdname(conf->mddev), STRIPE_SECTORS, + (unsigned long long)s, + bdevname(rdev->bdev, b)); + atomic_add(STRIPE_SECTORS, &rdev->corrected_errors); + clear_bit(R5_ReadError, &sh->dev[i].flags); + clear_bit(R5_ReWrite, &sh->dev[i].flags); + } else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) + clear_bit(R5_ReadNoMerge, &sh->dev[i].flags); + + if (atomic_read(&rdev->read_errors)) + atomic_set(&rdev->read_errors, 0); + } else { + const char *bdn = bdevname(rdev->bdev, b); + int retry = 0; + int set_bad = 0; + + clear_bit(R5_UPTODATE, &sh->dev[i].flags); + atomic_inc(&rdev->read_errors); + if (test_bit(R5_ReadRepl, &sh->dev[i].flags)) + printk_ratelimited( + KERN_WARNING + "md/raid:%s: read error on replacement device " + "(sector %llu on %s).\n", + mdname(conf->mddev), + (unsigned long long)s, + bdn); + else if (conf->mddev->degraded >= conf->max_degraded) { + set_bad = 1; + printk_ratelimited( + KERN_WARNING + "md/raid:%s: read error not correctable " + "(sector %llu on %s).\n", + mdname(conf->mddev), + (unsigned long long)s, + bdn); + } else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) { + /* Oh, no!!! */ + set_bad = 1; + printk_ratelimited( + KERN_WARNING + "md/raid:%s: read error NOT corrected!! " + "(sector %llu on %s).\n", + mdname(conf->mddev), + (unsigned long long)s, + bdn); + } else if (atomic_read(&rdev->read_errors) + > conf->max_nr_stripes) + printk(KERN_WARNING + "md/raid:%s: Too many read errors, failing device %s.\n", + mdname(conf->mddev), bdn); + else + retry = 1; + if (set_bad && test_bit(In_sync, &rdev->flags) + && !test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) + retry = 1; + if (retry) + if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) { + set_bit(R5_ReadError, &sh->dev[i].flags); + clear_bit(R5_ReadNoMerge, &sh->dev[i].flags); + } else + set_bit(R5_ReadNoMerge, &sh->dev[i].flags); + else { + clear_bit(R5_ReadError, &sh->dev[i].flags); + clear_bit(R5_ReWrite, &sh->dev[i].flags); + if (!(set_bad + && test_bit(In_sync, &rdev->flags) + && rdev_set_badblocks( + rdev, sh->sector, STRIPE_SECTORS, 0))) + md_error(conf->mddev, rdev); + } + } + rdev_dec_pending(rdev, conf->mddev); + clear_bit(R5_LOCKED, &sh->dev[i].flags); + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); +} + +static void raid5_end_write_request(struct bio *bi, int error) +{ + struct stripe_head *sh = bi->bi_private; + struct r5conf *conf = sh->raid_conf; + int disks = sh->disks, i; + struct md_rdev *uninitialized_var(rdev); + int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags); + sector_t first_bad; + int bad_sectors; + int replacement = 0; + + for (i = 0 ; i < disks; i++) { + if (bi == &sh->dev[i].req) { + rdev = conf->disks[i].rdev; + break; + } + if (bi == &sh->dev[i].rreq) { + rdev = conf->disks[i].replacement; + if (rdev) + replacement = 1; + else + /* rdev was removed and 'replacement' + * replaced it. rdev is not removed + * until all requests are finished. + */ + rdev = conf->disks[i].rdev; + break; + } + } + pr_debug("end_write_request %llu/%d, count %d, uptodate: %d.\n", + (unsigned long long)sh->sector, i, atomic_read(&sh->count), + uptodate); + if (i == disks) { + BUG(); + return; + } + + if (replacement) { + if (!uptodate) + md_error(conf->mddev, rdev); + else if (is_badblock(rdev, sh->sector, + STRIPE_SECTORS, + &first_bad, &bad_sectors)) + set_bit(R5_MadeGoodRepl, &sh->dev[i].flags); + } else { + if (!uptodate) { + set_bit(STRIPE_DEGRADED, &sh->state); + set_bit(WriteErrorSeen, &rdev->flags); + set_bit(R5_WriteError, &sh->dev[i].flags); + if (!test_and_set_bit(WantReplacement, &rdev->flags)) + set_bit(MD_RECOVERY_NEEDED, + &rdev->mddev->recovery); + } else if (is_badblock(rdev, sh->sector, + STRIPE_SECTORS, + &first_bad, &bad_sectors)) { + set_bit(R5_MadeGood, &sh->dev[i].flags); + if (test_bit(R5_ReadError, &sh->dev[i].flags)) + /* That was a successful write so make + * sure it looks like we already did + * a re-write. + */ + set_bit(R5_ReWrite, &sh->dev[i].flags); + } + } + rdev_dec_pending(rdev, conf->mddev); + + if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags)) + clear_bit(R5_LOCKED, &sh->dev[i].flags); + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); +} + +static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous); + +static void raid5_build_block(struct stripe_head *sh, int i, int previous) +{ + struct r5dev *dev = &sh->dev[i]; + + bio_init(&dev->req); + dev->req.bi_io_vec = &dev->vec; + dev->req.bi_max_vecs = 1; + dev->req.bi_private = sh; + + bio_init(&dev->rreq); + dev->rreq.bi_io_vec = &dev->rvec; + dev->rreq.bi_max_vecs = 1; + dev->rreq.bi_private = sh; + + dev->flags = 0; + dev->sector = compute_blocknr(sh, i, previous); +} + +static void error(struct mddev *mddev, struct md_rdev *rdev) +{ + char b[BDEVNAME_SIZE]; + struct r5conf *conf = mddev->private; + unsigned long flags; + pr_debug("raid456: error called\n"); + + spin_lock_irqsave(&conf->device_lock, flags); + clear_bit(In_sync, &rdev->flags); + mddev->degraded = calc_degraded(conf); + spin_unlock_irqrestore(&conf->device_lock, flags); + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + + set_bit(Blocked, &rdev->flags); + set_bit(Faulty, &rdev->flags); + set_bit(MD_CHANGE_DEVS, &mddev->flags); + printk(KERN_ALERT + "md/raid:%s: Disk failure on %s, disabling device.\n" + "md/raid:%s: Operation continuing on %d devices.\n", + mdname(mddev), + bdevname(rdev->bdev, b), + mdname(mddev), + conf->raid_disks - mddev->degraded); +} + +/* + * Input: a 'big' sector number, + * Output: index of the data and parity disk, and the sector # in them. + */ +static sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector, + int previous, int *dd_idx, + struct stripe_head *sh) +{ + sector_t stripe, stripe2; + sector_t chunk_number; + unsigned int chunk_offset; + int pd_idx, qd_idx; + int ddf_layout = 0; + sector_t new_sector; + int algorithm = previous ? conf->prev_algo + : conf->algorithm; + int sectors_per_chunk = previous ? conf->prev_chunk_sectors + : conf->chunk_sectors; + int raid_disks = previous ? conf->previous_raid_disks + : conf->raid_disks; + int data_disks = raid_disks - conf->max_degraded; + + /* First compute the information on this sector */ + + /* + * Compute the chunk number and the sector offset inside the chunk + */ + chunk_offset = sector_div(r_sector, sectors_per_chunk); + chunk_number = r_sector; + + /* + * Compute the stripe number + */ + stripe = chunk_number; + *dd_idx = sector_div(stripe, data_disks); + stripe2 = stripe; + /* + * Select the parity disk based on the user selected algorithm. + */ + pd_idx = qd_idx = -1; + switch(conf->level) { + case 4: + pd_idx = data_disks; + break; + case 5: + switch (algorithm) { + case ALGORITHM_LEFT_ASYMMETRIC: + pd_idx = data_disks - sector_div(stripe2, raid_disks); + if (*dd_idx >= pd_idx) + (*dd_idx)++; + break; + case ALGORITHM_RIGHT_ASYMMETRIC: + pd_idx = sector_div(stripe2, raid_disks); + if (*dd_idx >= pd_idx) + (*dd_idx)++; + break; + case ALGORITHM_LEFT_SYMMETRIC: + pd_idx = data_disks - sector_div(stripe2, raid_disks); + *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks; + break; + case ALGORITHM_RIGHT_SYMMETRIC: + pd_idx = sector_div(stripe2, raid_disks); + *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks; + break; + case ALGORITHM_PARITY_0: + pd_idx = 0; + (*dd_idx)++; + break; + case ALGORITHM_PARITY_N: + pd_idx = data_disks; + break; + default: + BUG(); + } + break; + case 6: + + switch (algorithm) { + case ALGORITHM_LEFT_ASYMMETRIC: + pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks); + qd_idx = pd_idx + 1; + if (pd_idx == raid_disks-1) { + (*dd_idx)++; /* Q D D D P */ + qd_idx = 0; + } else if (*dd_idx >= pd_idx) + (*dd_idx) += 2; /* D D P Q D */ + break; + case ALGORITHM_RIGHT_ASYMMETRIC: + pd_idx = sector_div(stripe2, raid_disks); + qd_idx = pd_idx + 1; + if (pd_idx == raid_disks-1) { + (*dd_idx)++; /* Q D D D P */ + qd_idx = 0; + } else if (*dd_idx >= pd_idx) + (*dd_idx) += 2; /* D D P Q D */ + break; + case ALGORITHM_LEFT_SYMMETRIC: + pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks); + qd_idx = (pd_idx + 1) % raid_disks; + *dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks; + break; + case ALGORITHM_RIGHT_SYMMETRIC: + pd_idx = sector_div(stripe2, raid_disks); + qd_idx = (pd_idx + 1) % raid_disks; + *dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks; + break; + + case ALGORITHM_PARITY_0: + pd_idx = 0; + qd_idx = 1; + (*dd_idx) += 2; + break; + case ALGORITHM_PARITY_N: + pd_idx = data_disks; + qd_idx = data_disks + 1; + break; + + case ALGORITHM_ROTATING_ZERO_RESTART: + /* Exactly the same as RIGHT_ASYMMETRIC, but or + * of blocks for computing Q is different. + */ + pd_idx = sector_div(stripe2, raid_disks); + qd_idx = pd_idx + 1; + if (pd_idx == raid_disks-1) { + (*dd_idx)++; /* Q D D D P */ + qd_idx = 0; + } else if (*dd_idx >= pd_idx) + (*dd_idx) += 2; /* D D P Q D */ + ddf_layout = 1; + break; + + case ALGORITHM_ROTATING_N_RESTART: + /* Same a left_asymmetric, by first stripe is + * D D D P Q rather than + * Q D D D P + */ + stripe2 += 1; + pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks); + qd_idx = pd_idx + 1; + if (pd_idx == raid_disks-1) { + (*dd_idx)++; /* Q D D D P */ + qd_idx = 0; + } else if (*dd_idx >= pd_idx) + (*dd_idx) += 2; /* D D P Q D */ + ddf_layout = 1; + break; + + case ALGORITHM_ROTATING_N_CONTINUE: + /* Same as left_symmetric but Q is before P */ + pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks); + qd_idx = (pd_idx + raid_disks - 1) % raid_disks; + *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks; + ddf_layout = 1; + break; + + case ALGORITHM_LEFT_ASYMMETRIC_6: + /* RAID5 left_asymmetric, with Q on last device */ + pd_idx = data_disks - sector_div(stripe2, raid_disks-1); + if (*dd_idx >= pd_idx) + (*dd_idx)++; + qd_idx = raid_disks - 1; + break; + + case ALGORITHM_RIGHT_ASYMMETRIC_6: + pd_idx = sector_div(stripe2, raid_disks-1); + if (*dd_idx >= pd_idx) + (*dd_idx)++; + qd_idx = raid_disks - 1; + break; + + case ALGORITHM_LEFT_SYMMETRIC_6: + pd_idx = data_disks - sector_div(stripe2, raid_disks-1); + *dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1); + qd_idx = raid_disks - 1; + break; + + case ALGORITHM_RIGHT_SYMMETRIC_6: + pd_idx = sector_div(stripe2, raid_disks-1); + *dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1); + qd_idx = raid_disks - 1; + break; + + case ALGORITHM_PARITY_0_6: + pd_idx = 0; + (*dd_idx)++; + qd_idx = raid_disks - 1; + break; + + default: + BUG(); + } + break; + } + + if (sh) { + sh->pd_idx = pd_idx; + sh->qd_idx = qd_idx; + sh->ddf_layout = ddf_layout; + } + /* + * Finally, compute the new sector number + */ + new_sector = (sector_t)stripe * sectors_per_chunk + chunk_offset; + return new_sector; +} + +static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous) +{ + struct r5conf *conf = sh->raid_conf; + int raid_disks = sh->disks; + int data_disks = raid_disks - conf->max_degraded; + sector_t new_sector = sh->sector, check; + int sectors_per_chunk = previous ? conf->prev_chunk_sectors + : conf->chunk_sectors; + int algorithm = previous ? conf->prev_algo + : conf->algorithm; + sector_t stripe; + int chunk_offset; + sector_t chunk_number; + int dummy1, dd_idx = i; + sector_t r_sector; + struct stripe_head sh2; + + chunk_offset = sector_div(new_sector, sectors_per_chunk); + stripe = new_sector; + + if (i == sh->pd_idx) + return 0; + switch(conf->level) { + case 4: break; + case 5: + switch (algorithm) { + case ALGORITHM_LEFT_ASYMMETRIC: + case ALGORITHM_RIGHT_ASYMMETRIC: + if (i > sh->pd_idx) + i--; + break; + case ALGORITHM_LEFT_SYMMETRIC: + case ALGORITHM_RIGHT_SYMMETRIC: + if (i < sh->pd_idx) + i += raid_disks; + i -= (sh->pd_idx + 1); + break; + case ALGORITHM_PARITY_0: + i -= 1; + break; + case ALGORITHM_PARITY_N: + break; + default: + BUG(); + } + break; + case 6: + if (i == sh->qd_idx) + return 0; /* It is the Q disk */ + switch (algorithm) { + case ALGORITHM_LEFT_ASYMMETRIC: + case ALGORITHM_RIGHT_ASYMMETRIC: + case ALGORITHM_ROTATING_ZERO_RESTART: + case ALGORITHM_ROTATING_N_RESTART: + if (sh->pd_idx == raid_disks-1) + i--; /* Q D D D P */ + else if (i > sh->pd_idx) + i -= 2; /* D D P Q D */ + break; + case ALGORITHM_LEFT_SYMMETRIC: + case ALGORITHM_RIGHT_SYMMETRIC: + if (sh->pd_idx == raid_disks-1) + i--; /* Q D D D P */ + else { + /* D D P Q D */ + if (i < sh->pd_idx) + i += raid_disks; + i -= (sh->pd_idx + 2); + } + break; + case ALGORITHM_PARITY_0: + i -= 2; + break; + case ALGORITHM_PARITY_N: + break; + case ALGORITHM_ROTATING_N_CONTINUE: + /* Like left_symmetric, but P is before Q */ + if (sh->pd_idx == 0) + i--; /* P D D D Q */ + else { + /* D D Q P D */ + if (i < sh->pd_idx) + i += raid_disks; + i -= (sh->pd_idx + 1); + } + break; + case ALGORITHM_LEFT_ASYMMETRIC_6: + case ALGORITHM_RIGHT_ASYMMETRIC_6: + if (i > sh->pd_idx) + i--; + break; + case ALGORITHM_LEFT_SYMMETRIC_6: + case ALGORITHM_RIGHT_SYMMETRIC_6: + if (i < sh->pd_idx) + i += data_disks + 1; + i -= (sh->pd_idx + 1); + break; + case ALGORITHM_PARITY_0_6: + i -= 1; + break; + default: + BUG(); + } + break; + } + + chunk_number = stripe * data_disks + i; + r_sector = chunk_number * sectors_per_chunk + chunk_offset; + + check = raid5_compute_sector(conf, r_sector, + previous, &dummy1, &sh2); + if (check != sh->sector || dummy1 != dd_idx || sh2.pd_idx != sh->pd_idx + || sh2.qd_idx != sh->qd_idx) { + printk(KERN_ERR "md/raid:%s: compute_blocknr: map not correct\n", + mdname(conf->mddev)); + return 0; + } + return r_sector; +} + +static void +schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, + int rcw, int expand) +{ + int i, pd_idx = sh->pd_idx, disks = sh->disks; + struct r5conf *conf = sh->raid_conf; + int level = conf->level; + + if (rcw) { + + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + + if (dev->towrite) { + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantdrain, &dev->flags); + if (!expand) + clear_bit(R5_UPTODATE, &dev->flags); + s->locked++; + } + } + /* if we are not expanding this is a proper write request, and + * there will be bios with new data to be drained into the + * stripe cache + */ + if (!expand) { + if (!s->locked) + /* False alarm, nothing to do */ + return; + sh->reconstruct_state = reconstruct_state_drain_run; + set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); + } else + sh->reconstruct_state = reconstruct_state_run; + + set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request); + + if (s->locked + conf->max_degraded == disks) + if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state)) + atomic_inc(&conf->pending_full_writes); + } else { + BUG_ON(level == 6); + BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) || + test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags))); + + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (i == pd_idx) + continue; + + if (dev->towrite && + (test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Wantcompute, &dev->flags))) { + set_bit(R5_Wantdrain, &dev->flags); + set_bit(R5_LOCKED, &dev->flags); + clear_bit(R5_UPTODATE, &dev->flags); + s->locked++; + } + } + if (!s->locked) + /* False alarm - nothing to do */ + return; + sh->reconstruct_state = reconstruct_state_prexor_drain_run; + set_bit(STRIPE_OP_PREXOR, &s->ops_request); + set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); + set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request); + } + + /* keep the parity disk(s) locked while asynchronous operations + * are in flight + */ + set_bit(R5_LOCKED, &sh->dev[pd_idx].flags); + clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags); + s->locked++; + + if (level == 6) { + int qd_idx = sh->qd_idx; + struct r5dev *dev = &sh->dev[qd_idx]; + + set_bit(R5_LOCKED, &dev->flags); + clear_bit(R5_UPTODATE, &dev->flags); + s->locked++; + } + + pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n", + __func__, (unsigned long long)sh->sector, + s->locked, s->ops_request); +} + +/* + * Each stripe/dev can have one or more bion attached. + * toread/towrite point to the first in a chain. + * The bi_next chain must be in order. + */ +static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, int forwrite) +{ + struct bio **bip; + struct r5conf *conf = sh->raid_conf; + int firstwrite=0; + + pr_debug("adding bi b#%llu to stripe s#%llu\n", + (unsigned long long)bi->bi_iter.bi_sector, + (unsigned long long)sh->sector); + + /* + * If several bio share a stripe. The bio bi_phys_segments acts as a + * reference count to avoid race. The reference count should already be + * increased before this function is called (for example, in + * make_request()), so other bio sharing this stripe will not free the + * stripe. If a stripe is owned by one stripe, the stripe lock will + * protect it. + */ + spin_lock_irq(&sh->stripe_lock); + if (forwrite) { + bip = &sh->dev[dd_idx].towrite; + if (*bip == NULL) + firstwrite = 1; + } else + bip = &sh->dev[dd_idx].toread; + while (*bip && (*bip)->bi_iter.bi_sector < bi->bi_iter.bi_sector) { + if (bio_end_sector(*bip) > bi->bi_iter.bi_sector) + goto overlap; + bip = & (*bip)->bi_next; + } + if (*bip && (*bip)->bi_iter.bi_sector < bio_end_sector(bi)) + goto overlap; + + BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next); + if (*bip) + bi->bi_next = *bip; + *bip = bi; + raid5_inc_bi_active_stripes(bi); + + if (forwrite) { + /* check if page is covered */ + sector_t sector = sh->dev[dd_idx].sector; + for (bi=sh->dev[dd_idx].towrite; + sector < sh->dev[dd_idx].sector + STRIPE_SECTORS && + bi && bi->bi_iter.bi_sector <= sector; + bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) { + if (bio_end_sector(bi) >= sector) + sector = bio_end_sector(bi); + } + if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS) + set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags); + } + + pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n", + (unsigned long long)(*bip)->bi_iter.bi_sector, + (unsigned long long)sh->sector, dd_idx); + spin_unlock_irq(&sh->stripe_lock); + + if (conf->mddev->bitmap && firstwrite) { + bitmap_startwrite(conf->mddev->bitmap, sh->sector, + STRIPE_SECTORS, 0); + sh->bm_seq = conf->seq_flush+1; + set_bit(STRIPE_BIT_DELAY, &sh->state); + } + return 1; + + overlap: + set_bit(R5_Overlap, &sh->dev[dd_idx].flags); + spin_unlock_irq(&sh->stripe_lock); + return 0; +} + +static void end_reshape(struct r5conf *conf); + +static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous, + struct stripe_head *sh) +{ + int sectors_per_chunk = + previous ? conf->prev_chunk_sectors : conf->chunk_sectors; + int dd_idx; + int chunk_offset = sector_div(stripe, sectors_per_chunk); + int disks = previous ? conf->previous_raid_disks : conf->raid_disks; + + raid5_compute_sector(conf, + stripe * (disks - conf->max_degraded) + *sectors_per_chunk + chunk_offset, + previous, + &dd_idx, sh); +} + +static void +handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, + struct stripe_head_state *s, int disks, + struct bio **return_bi) +{ + int i; + for (i = disks; i--; ) { + struct bio *bi; + int bitmap_end = 0; + + if (test_bit(R5_ReadError, &sh->dev[i].flags)) { + struct md_rdev *rdev; + rcu_read_lock(); + rdev = rcu_dereference(conf->disks[i].rdev); + if (rdev && test_bit(In_sync, &rdev->flags)) + atomic_inc(&rdev->nr_pending); + else + rdev = NULL; + rcu_read_unlock(); + if (rdev) { + if (!rdev_set_badblocks( + rdev, + sh->sector, + STRIPE_SECTORS, 0)) + md_error(conf->mddev, rdev); + rdev_dec_pending(rdev, conf->mddev); + } + } + spin_lock_irq(&sh->stripe_lock); + /* fail all writes first */ + bi = sh->dev[i].towrite; + sh->dev[i].towrite = NULL; + spin_unlock_irq(&sh->stripe_lock); + if (bi) + bitmap_end = 1; + + if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) + wake_up(&conf->wait_for_overlap); + + while (bi && bi->bi_iter.bi_sector < + sh->dev[i].sector + STRIPE_SECTORS) { + struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector); + clear_bit(BIO_UPTODATE, &bi->bi_flags); + if (!raid5_dec_bi_active_stripes(bi)) { + md_write_end(conf->mddev); + bi->bi_next = *return_bi; + *return_bi = bi; + } + bi = nextbi; + } + if (bitmap_end) + bitmap_endwrite(conf->mddev->bitmap, sh->sector, + STRIPE_SECTORS, 0, 0); + bitmap_end = 0; + /* and fail all 'written' */ + bi = sh->dev[i].written; + sh->dev[i].written = NULL; + if (test_and_clear_bit(R5_SkipCopy, &sh->dev[i].flags)) { + WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags)); + sh->dev[i].page = sh->dev[i].orig_page; + } + + if (bi) bitmap_end = 1; + while (bi && bi->bi_iter.bi_sector < + sh->dev[i].sector + STRIPE_SECTORS) { + struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector); + clear_bit(BIO_UPTODATE, &bi->bi_flags); + if (!raid5_dec_bi_active_stripes(bi)) { + md_write_end(conf->mddev); + bi->bi_next = *return_bi; + *return_bi = bi; + } + bi = bi2; + } + + /* fail any reads if this device is non-operational and + * the data has not reached the cache yet. + */ + if (!test_bit(R5_Wantfill, &sh->dev[i].flags) && + (!test_bit(R5_Insync, &sh->dev[i].flags) || + test_bit(R5_ReadError, &sh->dev[i].flags))) { + spin_lock_irq(&sh->stripe_lock); + bi = sh->dev[i].toread; + sh->dev[i].toread = NULL; + spin_unlock_irq(&sh->stripe_lock); + if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) + wake_up(&conf->wait_for_overlap); + while (bi && bi->bi_iter.bi_sector < + sh->dev[i].sector + STRIPE_SECTORS) { + struct bio *nextbi = + r5_next_bio(bi, sh->dev[i].sector); + clear_bit(BIO_UPTODATE, &bi->bi_flags); + if (!raid5_dec_bi_active_stripes(bi)) { + bi->bi_next = *return_bi; + *return_bi = bi; + } + bi = nextbi; + } + } + if (bitmap_end) + bitmap_endwrite(conf->mddev->bitmap, sh->sector, + STRIPE_SECTORS, 0, 0); + /* If we were in the middle of a write the parity block might + * still be locked - so just clear all R5_LOCKED flags + */ + clear_bit(R5_LOCKED, &sh->dev[i].flags); + } + + if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state)) + if (atomic_dec_and_test(&conf->pending_full_writes)) + md_wakeup_thread(conf->mddev->thread); +} + +static void +handle_failed_sync(struct r5conf *conf, struct stripe_head *sh, + struct stripe_head_state *s) +{ + int abort = 0; + int i; + + clear_bit(STRIPE_SYNCING, &sh->state); + if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags)) + wake_up(&conf->wait_for_overlap); + s->syncing = 0; + s->replacing = 0; + /* There is nothing more to do for sync/check/repair. + * Don't even need to abort as that is handled elsewhere + * if needed, and not always wanted e.g. if there is a known + * bad block here. + * For recover/replace we need to record a bad block on all + * non-sync devices, or abort the recovery + */ + if (test_bit(MD_RECOVERY_RECOVER, &conf->mddev->recovery)) { + /* During recovery devices cannot be removed, so + * locking and refcounting of rdevs is not needed + */ + for (i = 0; i < conf->raid_disks; i++) { + struct md_rdev *rdev = conf->disks[i].rdev; + if (rdev + && !test_bit(Faulty, &rdev->flags) + && !test_bit(In_sync, &rdev->flags) + && !rdev_set_badblocks(rdev, sh->sector, + STRIPE_SECTORS, 0)) + abort = 1; + rdev = conf->disks[i].replacement; + if (rdev + && !test_bit(Faulty, &rdev->flags) + && !test_bit(In_sync, &rdev->flags) + && !rdev_set_badblocks(rdev, sh->sector, + STRIPE_SECTORS, 0)) + abort = 1; + } + if (abort) + conf->recovery_disabled = + conf->mddev->recovery_disabled; + } + md_done_sync(conf->mddev, STRIPE_SECTORS, !abort); +} + +static int want_replace(struct stripe_head *sh, int disk_idx) +{ + struct md_rdev *rdev; + int rv = 0; + /* Doing recovery so rcu locking not required */ + rdev = sh->raid_conf->disks[disk_idx].replacement; + if (rdev + && !test_bit(Faulty, &rdev->flags) + && !test_bit(In_sync, &rdev->flags) + && (rdev->recovery_offset <= sh->sector + || rdev->mddev->recovery_cp <= sh->sector)) + rv = 1; + + return rv; +} + +/* fetch_block - checks the given member device to see if its data needs + * to be read or computed to satisfy a request. + * + * Returns 1 when no more member devices need to be checked, otherwise returns + * 0 to tell the loop in handle_stripe_fill to continue + */ +static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s, + int disk_idx, int disks) +{ + struct r5dev *dev = &sh->dev[disk_idx]; + struct r5dev *fdev[2] = { &sh->dev[s->failed_num[0]], + &sh->dev[s->failed_num[1]] }; + + /* is the data in this block needed, and can we get it? */ + if (!test_bit(R5_LOCKED, &dev->flags) && + !test_bit(R5_UPTODATE, &dev->flags) && + (dev->toread || + (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) || + s->syncing || s->expanding || + (s->replacing && want_replace(sh, disk_idx)) || + (s->failed >= 1 && fdev[0]->toread) || + (s->failed >= 2 && fdev[1]->toread) || + (sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite && + (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) && + !test_bit(R5_OVERWRITE, &fdev[0]->flags)) || + ((sh->raid_conf->level == 6 || + sh->sector >= sh->raid_conf->mddev->recovery_cp) + && s->failed && s->to_write && + (s->to_write - s->non_overwrite < + sh->raid_conf->raid_disks - sh->raid_conf->max_degraded) && + (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))))) { + /* we would like to get this block, possibly by computing it, + * otherwise read it if the backing disk is insync + */ + BUG_ON(test_bit(R5_Wantcompute, &dev->flags)); + BUG_ON(test_bit(R5_Wantread, &dev->flags)); + if ((s->uptodate == disks - 1) && + (s->failed && (disk_idx == s->failed_num[0] || + disk_idx == s->failed_num[1]))) { + /* have disk failed, and we're requested to fetch it; + * do compute it + */ + pr_debug("Computing stripe %llu block %d\n", + (unsigned long long)sh->sector, disk_idx); + set_bit(STRIPE_COMPUTE_RUN, &sh->state); + set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request); + set_bit(R5_Wantcompute, &dev->flags); + sh->ops.target = disk_idx; + sh->ops.target2 = -1; /* no 2nd target */ + s->req_compute = 1; + /* Careful: from this point on 'uptodate' is in the eye + * of raid_run_ops which services 'compute' operations + * before writes. R5_Wantcompute flags a block that will + * be R5_UPTODATE by the time it is needed for a + * subsequent operation. + */ + s->uptodate++; + return 1; + } else if (s->uptodate == disks-2 && s->failed >= 2) { + /* Computing 2-failure is *very* expensive; only + * do it if failed >= 2 + */ + int other; + for (other = disks; other--; ) { + if (other == disk_idx) + continue; + if (!test_bit(R5_UPTODATE, + &sh->dev[other].flags)) + break; + } + BUG_ON(other < 0); + pr_debug("Computing stripe %llu blocks %d,%d\n", + (unsigned long long)sh->sector, + disk_idx, other); + set_bit(STRIPE_COMPUTE_RUN, &sh->state); + set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request); + set_bit(R5_Wantcompute, &sh->dev[disk_idx].flags); + set_bit(R5_Wantcompute, &sh->dev[other].flags); + sh->ops.target = disk_idx; + sh->ops.target2 = other; + s->uptodate += 2; + s->req_compute = 1; + return 1; + } else if (test_bit(R5_Insync, &dev->flags)) { + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantread, &dev->flags); + s->locked++; + pr_debug("Reading block %d (sync=%d)\n", + disk_idx, s->syncing); + } + } + + return 0; +} + +/** + * handle_stripe_fill - read or compute data to satisfy pending requests. + */ +static void handle_stripe_fill(struct stripe_head *sh, + struct stripe_head_state *s, + int disks) +{ + int i; + + /* look for blocks to read/compute, skip this if a compute + * is already in flight, or if the stripe contents are in the + * midst of changing due to a write + */ + if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state && + !sh->reconstruct_state) + for (i = disks; i--; ) + if (fetch_block(sh, s, i, disks)) + break; + set_bit(STRIPE_HANDLE, &sh->state); +} + +/* handle_stripe_clean_event + * any written block on an uptodate or failed drive can be returned. + * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but + * never LOCKED, so we don't need to test 'failed' directly. + */ +static void handle_stripe_clean_event(struct r5conf *conf, + struct stripe_head *sh, int disks, struct bio **return_bi) +{ + int i; + struct r5dev *dev; + int discard_pending = 0; + + for (i = disks; i--; ) + if (sh->dev[i].written) { + dev = &sh->dev[i]; + if (!test_bit(R5_LOCKED, &dev->flags) && + (test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Discard, &dev->flags) || + test_bit(R5_SkipCopy, &dev->flags))) { + /* We can return any write requests */ + struct bio *wbi, *wbi2; + pr_debug("Return write for disc %d\n", i); + if (test_and_clear_bit(R5_Discard, &dev->flags)) + clear_bit(R5_UPTODATE, &dev->flags); + if (test_and_clear_bit(R5_SkipCopy, &dev->flags)) { + WARN_ON(test_bit(R5_UPTODATE, &dev->flags)); + dev->page = dev->orig_page; + } + wbi = dev->written; + dev->written = NULL; + while (wbi && wbi->bi_iter.bi_sector < + dev->sector + STRIPE_SECTORS) { + wbi2 = r5_next_bio(wbi, dev->sector); + if (!raid5_dec_bi_active_stripes(wbi)) { + md_write_end(conf->mddev); + wbi->bi_next = *return_bi; + *return_bi = wbi; + } + wbi = wbi2; + } + bitmap_endwrite(conf->mddev->bitmap, sh->sector, + STRIPE_SECTORS, + !test_bit(STRIPE_DEGRADED, &sh->state), + 0); + } else if (test_bit(R5_Discard, &dev->flags)) + discard_pending = 1; + WARN_ON(test_bit(R5_SkipCopy, &dev->flags)); + WARN_ON(dev->page != dev->orig_page); + } + if (!discard_pending && + test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) { + clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags); + clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags); + if (sh->qd_idx >= 0) { + clear_bit(R5_Discard, &sh->dev[sh->qd_idx].flags); + clear_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags); + } + /* now that discard is done we can proceed with any sync */ + clear_bit(STRIPE_DISCARD, &sh->state); + /* + * SCSI discard will change some bio fields and the stripe has + * no updated data, so remove it from hash list and the stripe + * will be reinitialized + */ + spin_lock_irq(&conf->device_lock); + remove_hash(sh); + spin_unlock_irq(&conf->device_lock); + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) + set_bit(STRIPE_HANDLE, &sh->state); + + } + + if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state)) + if (atomic_dec_and_test(&conf->pending_full_writes)) + md_wakeup_thread(conf->mddev->thread); +} + +static void handle_stripe_dirtying(struct r5conf *conf, + struct stripe_head *sh, + struct stripe_head_state *s, + int disks) +{ + int rmw = 0, rcw = 0, i; + sector_t recovery_cp = conf->mddev->recovery_cp; + + /* RAID6 requires 'rcw' in current implementation. + * Otherwise, check whether resync is now happening or should start. + * If yes, then the array is dirty (after unclean shutdown or + * initial creation), so parity in some stripes might be inconsistent. + * In this case, we need to always do reconstruct-write, to ensure + * that in case of drive failure or read-error correction, we + * generate correct data from the parity. + */ + if (conf->max_degraded == 2 || + (recovery_cp < MaxSector && sh->sector >= recovery_cp && + s->failed == 0)) { + /* Calculate the real rcw later - for now make it + * look like rcw is cheaper + */ + rcw = 1; rmw = 2; + pr_debug("force RCW max_degraded=%u, recovery_cp=%llu sh->sector=%llu\n", + conf->max_degraded, (unsigned long long)recovery_cp, + (unsigned long long)sh->sector); + } else for (i = disks; i--; ) { + /* would I have to read this buffer for read_modify_write */ + struct r5dev *dev = &sh->dev[i]; + if ((dev->towrite || i == sh->pd_idx) && + !test_bit(R5_LOCKED, &dev->flags) && + !(test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Wantcompute, &dev->flags))) { + if (test_bit(R5_Insync, &dev->flags)) + rmw++; + else + rmw += 2*disks; /* cannot read it */ + } + /* Would I have to read this buffer for reconstruct_write */ + if (!test_bit(R5_OVERWRITE, &dev->flags) && i != sh->pd_idx && + !test_bit(R5_LOCKED, &dev->flags) && + !(test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Wantcompute, &dev->flags))) { + if (test_bit(R5_Insync, &dev->flags)) + rcw++; + else + rcw += 2*disks; + } + } + pr_debug("for sector %llu, rmw=%d rcw=%d\n", + (unsigned long long)sh->sector, rmw, rcw); + set_bit(STRIPE_HANDLE, &sh->state); + if (rmw < rcw && rmw > 0) { + /* prefer read-modify-write, but need to get some data */ + if (conf->mddev->queue) + blk_add_trace_msg(conf->mddev->queue, + "raid5 rmw %llu %d", + (unsigned long long)sh->sector, rmw); + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if ((dev->towrite || i == sh->pd_idx) && + !test_bit(R5_LOCKED, &dev->flags) && + !(test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Wantcompute, &dev->flags)) && + test_bit(R5_Insync, &dev->flags)) { + if (test_bit(STRIPE_PREREAD_ACTIVE, + &sh->state)) { + pr_debug("Read_old block %d for r-m-w\n", + i); + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantread, &dev->flags); + s->locked++; + } else { + set_bit(STRIPE_DELAYED, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + } + } + } + } + if (rcw <= rmw && rcw > 0) { + /* want reconstruct write, but need to get some data */ + int qread =0; + rcw = 0; + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (!test_bit(R5_OVERWRITE, &dev->flags) && + i != sh->pd_idx && i != sh->qd_idx && + !test_bit(R5_LOCKED, &dev->flags) && + !(test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Wantcompute, &dev->flags))) { + rcw++; + if (test_bit(R5_Insync, &dev->flags) && + test_bit(STRIPE_PREREAD_ACTIVE, + &sh->state)) { + pr_debug("Read_old block " + "%d for Reconstruct\n", i); + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantread, &dev->flags); + s->locked++; + qread++; + } else { + set_bit(STRIPE_DELAYED, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + } + } + } + if (rcw && conf->mddev->queue) + blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d", + (unsigned long long)sh->sector, + rcw, qread, test_bit(STRIPE_DELAYED, &sh->state)); + } + + if (rcw > disks && rmw > disks && + !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + set_bit(STRIPE_DELAYED, &sh->state); + + /* now if nothing is locked, and if we have enough data, + * we can start a write request + */ + /* since handle_stripe can be called at any time we need to handle the + * case where a compute block operation has been submitted and then a + * subsequent call wants to start a write request. raid_run_ops only + * handles the case where compute block and reconstruct are requested + * simultaneously. If this is not the case then new writes need to be + * held off until the compute completes. + */ + if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) && + (s->locked == 0 && (rcw == 0 || rmw == 0) && + !test_bit(STRIPE_BIT_DELAY, &sh->state))) + schedule_reconstruction(sh, s, rcw == 0, 0); +} + +static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh, + struct stripe_head_state *s, int disks) +{ + struct r5dev *dev = NULL; + + set_bit(STRIPE_HANDLE, &sh->state); + + switch (sh->check_state) { + case check_state_idle: + /* start a new check operation if there are no failures */ + if (s->failed == 0) { + BUG_ON(s->uptodate != disks); + sh->check_state = check_state_run; + set_bit(STRIPE_OP_CHECK, &s->ops_request); + clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags); + s->uptodate--; + break; + } + dev = &sh->dev[s->failed_num[0]]; + /* fall through */ + case check_state_compute_result: + sh->check_state = check_state_idle; + if (!dev) + dev = &sh->dev[sh->pd_idx]; + + /* check that a write has not made the stripe insync */ + if (test_bit(STRIPE_INSYNC, &sh->state)) + break; + + /* either failed parity check, or recovery is happening */ + BUG_ON(!test_bit(R5_UPTODATE, &dev->flags)); + BUG_ON(s->uptodate != disks); + + set_bit(R5_LOCKED, &dev->flags); + s->locked++; + set_bit(R5_Wantwrite, &dev->flags); + + clear_bit(STRIPE_DEGRADED, &sh->state); + set_bit(STRIPE_INSYNC, &sh->state); + break; + case check_state_run: + break; /* we will be called again upon completion */ + case check_state_check_result: + sh->check_state = check_state_idle; + + /* if a failure occurred during the check operation, leave + * STRIPE_INSYNC not set and let the stripe be handled again + */ + if (s->failed) + break; + + /* handle a successful check operation, if parity is correct + * we are done. Otherwise update the mismatch count and repair + * parity if !MD_RECOVERY_CHECK + */ + if ((sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) == 0) + /* parity is correct (on disc, + * not in buffer any more) + */ + set_bit(STRIPE_INSYNC, &sh->state); + else { + atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches); + if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) + /* don't try to repair!! */ + set_bit(STRIPE_INSYNC, &sh->state); + else { + sh->check_state = check_state_compute_run; + set_bit(STRIPE_COMPUTE_RUN, &sh->state); + set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request); + set_bit(R5_Wantcompute, + &sh->dev[sh->pd_idx].flags); + sh->ops.target = sh->pd_idx; + sh->ops.target2 = -1; + s->uptodate++; + } + } + break; + case check_state_compute_run: + break; + default: + printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n", + __func__, sh->check_state, + (unsigned long long) sh->sector); + BUG(); + } +} + +static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, + struct stripe_head_state *s, + int disks) +{ + int pd_idx = sh->pd_idx; + int qd_idx = sh->qd_idx; + struct r5dev *dev; + + set_bit(STRIPE_HANDLE, &sh->state); + + BUG_ON(s->failed > 2); + + /* Want to check and possibly repair P and Q. + * However there could be one 'failed' device, in which + * case we can only check one of them, possibly using the + * other to generate missing data + */ + + switch (sh->check_state) { + case check_state_idle: + /* start a new check operation if there are < 2 failures */ + if (s->failed == s->q_failed) { + /* The only possible failed device holds Q, so it + * makes sense to check P (If anything else were failed, + * we would have used P to recreate it). + */ + sh->check_state = check_state_run; + } + if (!s->q_failed && s->failed < 2) { + /* Q is not failed, and we didn't use it to generate + * anything, so it makes sense to check it + */ + if (sh->check_state == check_state_run) + sh->check_state = check_state_run_pq; + else + sh->check_state = check_state_run_q; + } + + /* discard potentially stale zero_sum_result */ + sh->ops.zero_sum_result = 0; + + if (sh->check_state == check_state_run) { + /* async_xor_zero_sum destroys the contents of P */ + clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags); + s->uptodate--; + } + if (sh->check_state >= check_state_run && + sh->check_state <= check_state_run_pq) { + /* async_syndrome_zero_sum preserves P and Q, so + * no need to mark them !uptodate here + */ + set_bit(STRIPE_OP_CHECK, &s->ops_request); + break; + } + + /* we have 2-disk failure */ + BUG_ON(s->failed != 2); + /* fall through */ + case check_state_compute_result: + sh->check_state = check_state_idle; + + /* check that a write has not made the stripe insync */ + if (test_bit(STRIPE_INSYNC, &sh->state)) + break; + + /* now write out any block on a failed drive, + * or P or Q if they were recomputed + */ + BUG_ON(s->uptodate < disks - 1); /* We don't need Q to recover */ + if (s->failed == 2) { + dev = &sh->dev[s->failed_num[1]]; + s->locked++; + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantwrite, &dev->flags); + } + if (s->failed >= 1) { + dev = &sh->dev[s->failed_num[0]]; + s->locked++; + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantwrite, &dev->flags); + } + if (sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) { + dev = &sh->dev[pd_idx]; + s->locked++; + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantwrite, &dev->flags); + } + if (sh->ops.zero_sum_result & SUM_CHECK_Q_RESULT) { + dev = &sh->dev[qd_idx]; + s->locked++; + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantwrite, &dev->flags); + } + clear_bit(STRIPE_DEGRADED, &sh->state); + + set_bit(STRIPE_INSYNC, &sh->state); + break; + case check_state_run: + case check_state_run_q: + case check_state_run_pq: + break; /* we will be called again upon completion */ + case check_state_check_result: + sh->check_state = check_state_idle; + + /* handle a successful check operation, if parity is correct + * we are done. Otherwise update the mismatch count and repair + * parity if !MD_RECOVERY_CHECK + */ + if (sh->ops.zero_sum_result == 0) { + /* both parities are correct */ + if (!s->failed) + set_bit(STRIPE_INSYNC, &sh->state); + else { + /* in contrast to the raid5 case we can validate + * parity, but still have a failure to write + * back + */ + sh->check_state = check_state_compute_result; + /* Returning at this point means that we may go + * off and bring p and/or q uptodate again so + * we make sure to check zero_sum_result again + * to verify if p or q need writeback + */ + } + } else { + atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches); + if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) + /* don't try to repair!! */ + set_bit(STRIPE_INSYNC, &sh->state); + else { + int *target = &sh->ops.target; + + sh->ops.target = -1; + sh->ops.target2 = -1; + sh->check_state = check_state_compute_run; + set_bit(STRIPE_COMPUTE_RUN, &sh->state); + set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request); + if (sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) { + set_bit(R5_Wantcompute, + &sh->dev[pd_idx].flags); + *target = pd_idx; + target = &sh->ops.target2; + s->uptodate++; + } + if (sh->ops.zero_sum_result & SUM_CHECK_Q_RESULT) { + set_bit(R5_Wantcompute, + &sh->dev[qd_idx].flags); + *target = qd_idx; + s->uptodate++; + } + } + } + break; + case check_state_compute_run: + break; + default: + printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n", + __func__, sh->check_state, + (unsigned long long) sh->sector); + BUG(); + } +} + +static void handle_stripe_expansion(struct r5conf *conf, struct stripe_head *sh) +{ + int i; + + /* We have read all the blocks in this stripe and now we need to + * copy some of them into a target stripe for expand. + */ + struct dma_async_tx_descriptor *tx = NULL; + clear_bit(STRIPE_EXPAND_SOURCE, &sh->state); + for (i = 0; i < sh->disks; i++) + if (i != sh->pd_idx && i != sh->qd_idx) { + int dd_idx, j; + struct stripe_head *sh2; + struct async_submit_ctl submit; + + sector_t bn = compute_blocknr(sh, i, 1); + sector_t s = raid5_compute_sector(conf, bn, 0, + &dd_idx, NULL); + sh2 = get_active_stripe(conf, s, 0, 1, 1); + if (sh2 == NULL) + /* so far only the early blocks of this stripe + * have been requested. When later blocks + * get requested, we will try again + */ + continue; + if (!test_bit(STRIPE_EXPANDING, &sh2->state) || + test_bit(R5_Expanded, &sh2->dev[dd_idx].flags)) { + /* must have already done this block */ + release_stripe(sh2); + continue; + } + + /* place all the copies on one channel */ + init_async_submit(&submit, 0, tx, NULL, NULL, NULL); + tx = async_memcpy(sh2->dev[dd_idx].page, + sh->dev[i].page, 0, 0, STRIPE_SIZE, + &submit); + + set_bit(R5_Expanded, &sh2->dev[dd_idx].flags); + set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags); + for (j = 0; j < conf->raid_disks; j++) + if (j != sh2->pd_idx && + j != sh2->qd_idx && + !test_bit(R5_Expanded, &sh2->dev[j].flags)) + break; + if (j == conf->raid_disks) { + set_bit(STRIPE_EXPAND_READY, &sh2->state); + set_bit(STRIPE_HANDLE, &sh2->state); + } + release_stripe(sh2); + + } + /* done submitting copies, wait for them to complete */ + async_tx_quiesce(&tx); +} + +/* + * handle_stripe - do things to a stripe. + * + * We lock the stripe by setting STRIPE_ACTIVE and then examine the + * state of various bits to see what needs to be done. + * Possible results: + * return some read requests which now have data + * return some write requests which are safely on storage + * schedule a read on some buffers + * schedule a write of some buffers + * return confirmation of parity correctness + * + */ + +static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) +{ + struct r5conf *conf = sh->raid_conf; + int disks = sh->disks; + struct r5dev *dev; + int i; + int do_recovery = 0; + + memset(s, 0, sizeof(*s)); + + s->expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state); + s->expanded = test_bit(STRIPE_EXPAND_READY, &sh->state); + s->failed_num[0] = -1; + s->failed_num[1] = -1; + + /* Now to look around and see what can be done */ + rcu_read_lock(); + for (i=disks; i--; ) { + struct md_rdev *rdev; + sector_t first_bad; + int bad_sectors; + int is_bad = 0; + + dev = &sh->dev[i]; + + pr_debug("check %d: state 0x%lx read %p write %p written %p\n", + i, dev->flags, + dev->toread, dev->towrite, dev->written); + /* maybe we can reply to a read + * + * new wantfill requests are only permitted while + * ops_complete_biofill is guaranteed to be inactive + */ + if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread && + !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) + set_bit(R5_Wantfill, &dev->flags); + + /* now count some things */ + if (test_bit(R5_LOCKED, &dev->flags)) + s->locked++; + if (test_bit(R5_UPTODATE, &dev->flags)) + s->uptodate++; + if (test_bit(R5_Wantcompute, &dev->flags)) { + s->compute++; + BUG_ON(s->compute > 2); + } + + if (test_bit(R5_Wantfill, &dev->flags)) + s->to_fill++; + else if (dev->toread) + s->to_read++; + if (dev->towrite) { + s->to_write++; + if (!test_bit(R5_OVERWRITE, &dev->flags)) + s->non_overwrite++; + } + if (dev->written) + s->written++; + /* Prefer to use the replacement for reads, but only + * if it is recovered enough and has no bad blocks. + */ + rdev = rcu_dereference(conf->disks[i].replacement); + if (rdev && !test_bit(Faulty, &rdev->flags) && + rdev->recovery_offset >= sh->sector + STRIPE_SECTORS && + !is_badblock(rdev, sh->sector, STRIPE_SECTORS, + &first_bad, &bad_sectors)) + set_bit(R5_ReadRepl, &dev->flags); + else { + if (rdev) + set_bit(R5_NeedReplace, &dev->flags); + rdev = rcu_dereference(conf->disks[i].rdev); + clear_bit(R5_ReadRepl, &dev->flags); + } + if (rdev && test_bit(Faulty, &rdev->flags)) + rdev = NULL; + if (rdev) { + is_bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS, + &first_bad, &bad_sectors); + if (s->blocked_rdev == NULL + && (test_bit(Blocked, &rdev->flags) + || is_bad < 0)) { + if (is_bad < 0) + set_bit(BlockedBadBlocks, + &rdev->flags); + s->blocked_rdev = rdev; + atomic_inc(&rdev->nr_pending); + } + } + clear_bit(R5_Insync, &dev->flags); + if (!rdev) + /* Not in-sync */; + else if (is_bad) { + /* also not in-sync */ + if (!test_bit(WriteErrorSeen, &rdev->flags) && + test_bit(R5_UPTODATE, &dev->flags)) { + /* treat as in-sync, but with a read error + * which we can now try to correct + */ + set_bit(R5_Insync, &dev->flags); + set_bit(R5_ReadError, &dev->flags); + } + } else if (test_bit(In_sync, &rdev->flags)) + set_bit(R5_Insync, &dev->flags); + else if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset) + /* in sync if before recovery_offset */ + set_bit(R5_Insync, &dev->flags); + else if (test_bit(R5_UPTODATE, &dev->flags) && + test_bit(R5_Expanded, &dev->flags)) + /* If we've reshaped into here, we assume it is Insync. + * We will shortly update recovery_offset to make + * it official. + */ + set_bit(R5_Insync, &dev->flags); + + if (test_bit(R5_WriteError, &dev->flags)) { + /* This flag does not apply to '.replacement' + * only to .rdev, so make sure to check that*/ + struct md_rdev *rdev2 = rcu_dereference( + conf->disks[i].rdev); + if (rdev2 == rdev) + clear_bit(R5_Insync, &dev->flags); + if (rdev2 && !test_bit(Faulty, &rdev2->flags)) { + s->handle_bad_blocks = 1; + atomic_inc(&rdev2->nr_pending); + } else + clear_bit(R5_WriteError, &dev->flags); + } + if (test_bit(R5_MadeGood, &dev->flags)) { + /* This flag does not apply to '.replacement' + * only to .rdev, so make sure to check that*/ + struct md_rdev *rdev2 = rcu_dereference( + conf->disks[i].rdev); + if (rdev2 && !test_bit(Faulty, &rdev2->flags)) { + s->handle_bad_blocks = 1; + atomic_inc(&rdev2->nr_pending); + } else + clear_bit(R5_MadeGood, &dev->flags); + } + if (test_bit(R5_MadeGoodRepl, &dev->flags)) { + struct md_rdev *rdev2 = rcu_dereference( + conf->disks[i].replacement); + if (rdev2 && !test_bit(Faulty, &rdev2->flags)) { + s->handle_bad_blocks = 1; + atomic_inc(&rdev2->nr_pending); + } else + clear_bit(R5_MadeGoodRepl, &dev->flags); + } + if (!test_bit(R5_Insync, &dev->flags)) { + /* The ReadError flag will just be confusing now */ + clear_bit(R5_ReadError, &dev->flags); + clear_bit(R5_ReWrite, &dev->flags); + } + if (test_bit(R5_ReadError, &dev->flags)) + clear_bit(R5_Insync, &dev->flags); + if (!test_bit(R5_Insync, &dev->flags)) { + if (s->failed < 2) + s->failed_num[s->failed] = i; + s->failed++; + if (rdev && !test_bit(Faulty, &rdev->flags)) + do_recovery = 1; + } + } + if (test_bit(STRIPE_SYNCING, &sh->state)) { + /* If there is a failed device being replaced, + * we must be recovering. + * else if we are after recovery_cp, we must be syncing + * else if MD_RECOVERY_REQUESTED is set, we also are syncing. + * else we can only be replacing + * sync and recovery both need to read all devices, and so + * use the same flag. + */ + if (do_recovery || + sh->sector >= conf->mddev->recovery_cp || + test_bit(MD_RECOVERY_REQUESTED, &(conf->mddev->recovery))) + s->syncing = 1; + else + s->replacing = 1; + } + rcu_read_unlock(); +} + +static void handle_stripe(struct stripe_head *sh) +{ + struct stripe_head_state s; + struct r5conf *conf = sh->raid_conf; + int i; + int prexor; + int disks = sh->disks; + struct r5dev *pdev, *qdev; + + clear_bit(STRIPE_HANDLE, &sh->state); + if (test_and_set_bit_lock(STRIPE_ACTIVE, &sh->state)) { + /* already being handled, ensure it gets handled + * again when current action finishes */ + set_bit(STRIPE_HANDLE, &sh->state); + return; + } + + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) { + spin_lock(&sh->stripe_lock); + /* Cannot process 'sync' concurrently with 'discard' */ + if (!test_bit(STRIPE_DISCARD, &sh->state) && + test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) { + set_bit(STRIPE_SYNCING, &sh->state); + clear_bit(STRIPE_INSYNC, &sh->state); + clear_bit(STRIPE_REPLACED, &sh->state); + } + spin_unlock(&sh->stripe_lock); + } + clear_bit(STRIPE_DELAYED, &sh->state); + + pr_debug("handling stripe %llu, state=%#lx cnt=%d, " + "pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n", + (unsigned long long)sh->sector, sh->state, + atomic_read(&sh->count), sh->pd_idx, sh->qd_idx, + sh->check_state, sh->reconstruct_state); + + analyse_stripe(sh, &s); + + if (s.handle_bad_blocks) { + set_bit(STRIPE_HANDLE, &sh->state); + goto finish; + } + + if (unlikely(s.blocked_rdev)) { + if (s.syncing || s.expanding || s.expanded || + s.replacing || s.to_write || s.written) { + set_bit(STRIPE_HANDLE, &sh->state); + goto finish; + } + /* There is nothing for the blocked_rdev to block */ + rdev_dec_pending(s.blocked_rdev, conf->mddev); + s.blocked_rdev = NULL; + } + + if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) { + set_bit(STRIPE_OP_BIOFILL, &s.ops_request); + set_bit(STRIPE_BIOFILL_RUN, &sh->state); + } + + pr_debug("locked=%d uptodate=%d to_read=%d" + " to_write=%d failed=%d failed_num=%d,%d\n", + s.locked, s.uptodate, s.to_read, s.to_write, s.failed, + s.failed_num[0], s.failed_num[1]); + /* check if the array has lost more than max_degraded devices and, + * if so, some requests might need to be failed. + */ + if (s.failed > conf->max_degraded) { + sh->check_state = 0; + sh->reconstruct_state = 0; + if (s.to_read+s.to_write+s.written) + handle_failed_stripe(conf, sh, &s, disks, &s.return_bi); + if (s.syncing + s.replacing) + handle_failed_sync(conf, sh, &s); + } + + /* Now we check to see if any write operations have recently + * completed + */ + prexor = 0; + if (sh->reconstruct_state == reconstruct_state_prexor_drain_result) + prexor = 1; + if (sh->reconstruct_state == reconstruct_state_drain_result || + sh->reconstruct_state == reconstruct_state_prexor_drain_result) { + sh->reconstruct_state = reconstruct_state_idle; + + /* All the 'written' buffers and the parity block are ready to + * be written back to disk + */ + BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags) && + !test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)); + BUG_ON(sh->qd_idx >= 0 && + !test_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags) && + !test_bit(R5_Discard, &sh->dev[sh->qd_idx].flags)); + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (test_bit(R5_LOCKED, &dev->flags) && + (i == sh->pd_idx || i == sh->qd_idx || + dev->written)) { + pr_debug("Writing block %d\n", i); + set_bit(R5_Wantwrite, &dev->flags); + if (prexor) + continue; + if (s.failed > 1) + continue; + if (!test_bit(R5_Insync, &dev->flags) || + ((i == sh->pd_idx || i == sh->qd_idx) && + s.failed == 0)) + set_bit(STRIPE_INSYNC, &sh->state); + } + } + if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + s.dec_preread_active = 1; + } + + /* + * might be able to return some write requests if the parity blocks + * are safe, or on a failed drive + */ + pdev = &sh->dev[sh->pd_idx]; + s.p_failed = (s.failed >= 1 && s.failed_num[0] == sh->pd_idx) + || (s.failed >= 2 && s.failed_num[1] == sh->pd_idx); + qdev = &sh->dev[sh->qd_idx]; + s.q_failed = (s.failed >= 1 && s.failed_num[0] == sh->qd_idx) + || (s.failed >= 2 && s.failed_num[1] == sh->qd_idx) + || conf->level < 6; + + if (s.written && + (s.p_failed || ((test_bit(R5_Insync, &pdev->flags) + && !test_bit(R5_LOCKED, &pdev->flags) + && (test_bit(R5_UPTODATE, &pdev->flags) || + test_bit(R5_Discard, &pdev->flags))))) && + (s.q_failed || ((test_bit(R5_Insync, &qdev->flags) + && !test_bit(R5_LOCKED, &qdev->flags) + && (test_bit(R5_UPTODATE, &qdev->flags) || + test_bit(R5_Discard, &qdev->flags)))))) + handle_stripe_clean_event(conf, sh, disks, &s.return_bi); + + /* Now we might consider reading some blocks, either to check/generate + * parity, or to satisfy requests + * or to load a block that is being partially written. + */ + if (s.to_read || s.non_overwrite + || (conf->level == 6 && s.to_write && s.failed) + || (s.syncing && (s.uptodate + s.compute < disks)) + || s.replacing + || s.expanding) + handle_stripe_fill(sh, &s, disks); + + /* Now to consider new write requests and what else, if anything + * should be read. We do not handle new writes when: + * 1/ A 'write' operation (copy+xor) is already in flight. + * 2/ A 'check' operation is in flight, as it may clobber the parity + * block. + */ + if (s.to_write && !sh->reconstruct_state && !sh->check_state) + handle_stripe_dirtying(conf, sh, &s, disks); + + /* maybe we need to check and possibly fix the parity for this stripe + * Any reads will already have been scheduled, so we just see if enough + * data is available. The parity check is held off while parity + * dependent operations are in flight. + */ + if (sh->check_state || + (s.syncing && s.locked == 0 && + !test_bit(STRIPE_COMPUTE_RUN, &sh->state) && + !test_bit(STRIPE_INSYNC, &sh->state))) { + if (conf->level == 6) + handle_parity_checks6(conf, sh, &s, disks); + else + handle_parity_checks5(conf, sh, &s, disks); + } + + if ((s.replacing || s.syncing) && s.locked == 0 + && !test_bit(STRIPE_COMPUTE_RUN, &sh->state) + && !test_bit(STRIPE_REPLACED, &sh->state)) { + /* Write out to replacement devices where possible */ + for (i = 0; i < conf->raid_disks; i++) + if (test_bit(R5_NeedReplace, &sh->dev[i].flags)) { + WARN_ON(!test_bit(R5_UPTODATE, &sh->dev[i].flags)); + set_bit(R5_WantReplace, &sh->dev[i].flags); + set_bit(R5_LOCKED, &sh->dev[i].flags); + s.locked++; + } + if (s.replacing) + set_bit(STRIPE_INSYNC, &sh->state); + set_bit(STRIPE_REPLACED, &sh->state); + } + if ((s.syncing || s.replacing) && s.locked == 0 && + !test_bit(STRIPE_COMPUTE_RUN, &sh->state) && + test_bit(STRIPE_INSYNC, &sh->state)) { + md_done_sync(conf->mddev, STRIPE_SECTORS, 1); + clear_bit(STRIPE_SYNCING, &sh->state); + if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags)) + wake_up(&conf->wait_for_overlap); + } + + /* If the failed drives are just a ReadError, then we might need + * to progress the repair/check process + */ + if (s.failed <= conf->max_degraded && !conf->mddev->ro) + for (i = 0; i < s.failed; i++) { + struct r5dev *dev = &sh->dev[s.failed_num[i]]; + if (test_bit(R5_ReadError, &dev->flags) + && !test_bit(R5_LOCKED, &dev->flags) + && test_bit(R5_UPTODATE, &dev->flags) + ) { + if (!test_bit(R5_ReWrite, &dev->flags)) { + set_bit(R5_Wantwrite, &dev->flags); + set_bit(R5_ReWrite, &dev->flags); + set_bit(R5_LOCKED, &dev->flags); + s.locked++; + } else { + /* let's read it back */ + set_bit(R5_Wantread, &dev->flags); + set_bit(R5_LOCKED, &dev->flags); + s.locked++; + } + } + } + + /* Finish reconstruct operations initiated by the expansion process */ + if (sh->reconstruct_state == reconstruct_state_result) { + struct stripe_head *sh_src + = get_active_stripe(conf, sh->sector, 1, 1, 1); + if (sh_src && test_bit(STRIPE_EXPAND_SOURCE, &sh_src->state)) { + /* sh cannot be written until sh_src has been read. + * so arrange for sh to be delayed a little + */ + set_bit(STRIPE_DELAYED, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, + &sh_src->state)) + atomic_inc(&conf->preread_active_stripes); + release_stripe(sh_src); + goto finish; + } + if (sh_src) + release_stripe(sh_src); + + sh->reconstruct_state = reconstruct_state_idle; + clear_bit(STRIPE_EXPANDING, &sh->state); + for (i = conf->raid_disks; i--; ) { + set_bit(R5_Wantwrite, &sh->dev[i].flags); + set_bit(R5_LOCKED, &sh->dev[i].flags); + s.locked++; + } + } + + if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) && + !sh->reconstruct_state) { + /* Need to write out all blocks after computing parity */ + sh->disks = conf->raid_disks; + stripe_set_idx(sh->sector, conf, 0, sh); + schedule_reconstruction(sh, &s, 1, 1); + } else if (s.expanded && !sh->reconstruct_state && s.locked == 0) { + clear_bit(STRIPE_EXPAND_READY, &sh->state); + atomic_dec(&conf->reshape_stripes); + wake_up(&conf->wait_for_overlap); + md_done_sync(conf->mddev, STRIPE_SECTORS, 1); + } + + if (s.expanding && s.locked == 0 && + !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) + handle_stripe_expansion(conf, sh); + +finish: + /* wait for this device to become unblocked */ + if (unlikely(s.blocked_rdev)) { + if (conf->mddev->external) + md_wait_for_blocked_rdev(s.blocked_rdev, + conf->mddev); + else + /* Internal metadata will immediately + * be written by raid5d, so we don't + * need to wait here. + */ + rdev_dec_pending(s.blocked_rdev, + conf->mddev); + } + + if (s.handle_bad_blocks) + for (i = disks; i--; ) { + struct md_rdev *rdev; + struct r5dev *dev = &sh->dev[i]; + if (test_and_clear_bit(R5_WriteError, &dev->flags)) { + /* We own a safe reference to the rdev */ + rdev = conf->disks[i].rdev; + if (!rdev_set_badblocks(rdev, sh->sector, + STRIPE_SECTORS, 0)) + md_error(conf->mddev, rdev); + rdev_dec_pending(rdev, conf->mddev); + } + if (test_and_clear_bit(R5_MadeGood, &dev->flags)) { + rdev = conf->disks[i].rdev; + rdev_clear_badblocks(rdev, sh->sector, + STRIPE_SECTORS, 0); + rdev_dec_pending(rdev, conf->mddev); + } + if (test_and_clear_bit(R5_MadeGoodRepl, &dev->flags)) { + rdev = conf->disks[i].replacement; + if (!rdev) + /* rdev have been moved down */ + rdev = conf->disks[i].rdev; + rdev_clear_badblocks(rdev, sh->sector, + STRIPE_SECTORS, 0); + rdev_dec_pending(rdev, conf->mddev); + } + } + + if (s.ops_request) + raid_run_ops(sh, s.ops_request); + + ops_run_io(sh, &s); + + if (s.dec_preread_active) { + /* We delay this until after ops_run_io so that if make_request + * is waiting on a flush, it won't continue until the writes + * have actually been submitted. + */ + atomic_dec(&conf->preread_active_stripes); + if (atomic_read(&conf->preread_active_stripes) < + IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + } + + return_io(s.return_bi); + + clear_bit_unlock(STRIPE_ACTIVE, &sh->state); +} + +static void raid5_activate_delayed(struct r5conf *conf) +{ + if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) { + while (!list_empty(&conf->delayed_list)) { + struct list_head *l = conf->delayed_list.next; + struct stripe_head *sh; + sh = list_entry(l, struct stripe_head, lru); + list_del_init(l); + clear_bit(STRIPE_DELAYED, &sh->state); + if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + atomic_inc(&conf->preread_active_stripes); + list_add_tail(&sh->lru, &conf->hold_list); + raid5_wakeup_stripe_thread(sh); + } + } +} + +static void activate_bit_delay(struct r5conf *conf, + struct list_head *temp_inactive_list) +{ + /* device_lock is held */ + struct list_head head; + list_add(&head, &conf->bitmap_list); + list_del_init(&conf->bitmap_list); + while (!list_empty(&head)) { + struct stripe_head *sh = list_entry(head.next, struct stripe_head, lru); + int hash; + list_del_init(&sh->lru); + atomic_inc(&sh->count); + hash = sh->hash_lock_index; + __release_stripe(conf, sh, &temp_inactive_list[hash]); + } +} + +int md_raid5_congested(struct mddev *mddev, int bits) +{ + struct r5conf *conf = mddev->private; + + /* No difference between reads and writes. Just check + * how busy the stripe_cache is + */ + + if (conf->inactive_blocked) + return 1; + if (conf->quiesce) + return 1; + if (atomic_read(&conf->empty_inactive_list_nr)) + return 1; + + return 0; +} +EXPORT_SYMBOL_GPL(md_raid5_congested); + +static int raid5_congested(void *data, int bits) +{ + struct mddev *mddev = data; + + return mddev_congested(mddev, bits) || + md_raid5_congested(mddev, bits); +} + +/* We want read requests to align with chunks where possible, + * but write requests don't need to. + */ +static int raid5_mergeable_bvec(struct request_queue *q, + struct bvec_merge_data *bvm, + struct bio_vec *biovec) +{ + struct mddev *mddev = q->queuedata; + sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev); + int max; + unsigned int chunk_sectors = mddev->chunk_sectors; + unsigned int bio_sectors = bvm->bi_size >> 9; + + if ((bvm->bi_rw & 1) == WRITE) + return biovec->bv_len; /* always allow writes to be mergeable */ + + if (mddev->new_chunk_sectors < mddev->chunk_sectors) + chunk_sectors = mddev->new_chunk_sectors; + max = (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9; + if (max < 0) max = 0; + if (max <= biovec->bv_len && bio_sectors == 0) + return biovec->bv_len; + else + return max; +} + +static int in_chunk_boundary(struct mddev *mddev, struct bio *bio) +{ + sector_t sector = bio->bi_iter.bi_sector + get_start_sect(bio->bi_bdev); + unsigned int chunk_sectors = mddev->chunk_sectors; + unsigned int bio_sectors = bio_sectors(bio); + + if (mddev->new_chunk_sectors < mddev->chunk_sectors) + chunk_sectors = mddev->new_chunk_sectors; + return chunk_sectors >= + ((sector & (chunk_sectors - 1)) + bio_sectors); +} + +/* + * add bio to the retry LIFO ( in O(1) ... we are in interrupt ) + * later sampled by raid5d. + */ +static void add_bio_to_retry(struct bio *bi,struct r5conf *conf) +{ + unsigned long flags; + + spin_lock_irqsave(&conf->device_lock, flags); + + bi->bi_next = conf->retry_read_aligned_list; + conf->retry_read_aligned_list = bi; + + spin_unlock_irqrestore(&conf->device_lock, flags); + md_wakeup_thread(conf->mddev->thread); +} + +static struct bio *remove_bio_from_retry(struct r5conf *conf) +{ + struct bio *bi; + + bi = conf->retry_read_aligned; + if (bi) { + conf->retry_read_aligned = NULL; + return bi; + } + bi = conf->retry_read_aligned_list; + if(bi) { + conf->retry_read_aligned_list = bi->bi_next; + bi->bi_next = NULL; + /* + * this sets the active strip count to 1 and the processed + * strip count to zero (upper 8 bits) + */ + raid5_set_bi_stripes(bi, 1); /* biased count of active stripes */ + } + + return bi; +} + +/* + * The "raid5_align_endio" should check if the read succeeded and if it + * did, call bio_endio on the original bio (having bio_put the new bio + * first). + * If the read failed.. + */ +static void raid5_align_endio(struct bio *bi, int error) +{ + struct bio* raid_bi = bi->bi_private; + struct mddev *mddev; + struct r5conf *conf; + int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags); + struct md_rdev *rdev; + + bio_put(bi); + + rdev = (void*)raid_bi->bi_next; + raid_bi->bi_next = NULL; + mddev = rdev->mddev; + conf = mddev->private; + + rdev_dec_pending(rdev, conf->mddev); + + if (!error && uptodate) { + trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev), + raid_bi, 0); + bio_endio(raid_bi, 0); + if (atomic_dec_and_test(&conf->active_aligned_reads)) + wake_up(&conf->wait_for_stripe); + return; + } + + pr_debug("raid5_align_endio : io error...handing IO for a retry\n"); + + add_bio_to_retry(raid_bi, conf); +} + +static int bio_fits_rdev(struct bio *bi) +{ + struct request_queue *q = bdev_get_queue(bi->bi_bdev); + + if (bio_sectors(bi) > queue_max_sectors(q)) + return 0; + blk_recount_segments(q, bi); + if (bi->bi_phys_segments > queue_max_segments(q)) + return 0; + + if (q->merge_bvec_fn) + /* it's too hard to apply the merge_bvec_fn at this stage, + * just just give up + */ + return 0; + + return 1; +} + +static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) +{ + struct r5conf *conf = mddev->private; + int dd_idx; + struct bio* align_bi; + struct md_rdev *rdev; + sector_t end_sector; + + if (!in_chunk_boundary(mddev, raid_bio)) { + pr_debug("chunk_aligned_read : non aligned\n"); + return 0; + } + /* + * use bio_clone_mddev to make a copy of the bio + */ + align_bi = bio_clone_mddev(raid_bio, GFP_NOIO, mddev); + if (!align_bi) + return 0; + /* + * set bi_end_io to a new function, and set bi_private to the + * original bio. + */ + align_bi->bi_end_io = raid5_align_endio; + align_bi->bi_private = raid_bio; + /* + * compute position + */ + align_bi->bi_iter.bi_sector = + raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector, + 0, &dd_idx, NULL); + + end_sector = bio_end_sector(align_bi); + rcu_read_lock(); + rdev = rcu_dereference(conf->disks[dd_idx].replacement); + if (!rdev || test_bit(Faulty, &rdev->flags) || + rdev->recovery_offset < end_sector) { + rdev = rcu_dereference(conf->disks[dd_idx].rdev); + if (rdev && + (test_bit(Faulty, &rdev->flags) || + !(test_bit(In_sync, &rdev->flags) || + rdev->recovery_offset >= end_sector))) + rdev = NULL; + } + if (rdev) { + sector_t first_bad; + int bad_sectors; + + atomic_inc(&rdev->nr_pending); + rcu_read_unlock(); + raid_bio->bi_next = (void*)rdev; + align_bi->bi_bdev = rdev->bdev; + __clear_bit(BIO_SEG_VALID, &align_bi->bi_flags); + + if (!bio_fits_rdev(align_bi) || + is_badblock(rdev, align_bi->bi_iter.bi_sector, + bio_sectors(align_bi), + &first_bad, &bad_sectors)) { + /* too big in some way, or has a known bad block */ + bio_put(align_bi); + rdev_dec_pending(rdev, mddev); + return 0; + } + + /* No reshape active, so we can trust rdev->data_offset */ + align_bi->bi_iter.bi_sector += rdev->data_offset; + + spin_lock_irq(&conf->device_lock); + wait_event_lock_irq(conf->wait_for_stripe, + conf->quiesce == 0, + conf->device_lock); + atomic_inc(&conf->active_aligned_reads); + spin_unlock_irq(&conf->device_lock); + + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev), + align_bi, disk_devt(mddev->gendisk), + raid_bio->bi_iter.bi_sector); + generic_make_request(align_bi); + return 1; + } else { + rcu_read_unlock(); + bio_put(align_bi); + return 0; + } +} + +/* __get_priority_stripe - get the next stripe to process + * + * Full stripe writes are allowed to pass preread active stripes up until + * the bypass_threshold is exceeded. In general the bypass_count + * increments when the handle_list is handled before the hold_list; however, it + * will not be incremented when STRIPE_IO_STARTED is sampled set signifying a + * stripe with in flight i/o. The bypass_count will be reset when the + * head of the hold_list has changed, i.e. the head was promoted to the + * handle_list. + */ +static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group) +{ + struct stripe_head *sh = NULL, *tmp; + struct list_head *handle_list = NULL; + struct r5worker_group *wg = NULL; + + if (conf->worker_cnt_per_group == 0) { + handle_list = &conf->handle_list; + } else if (group != ANY_GROUP) { + handle_list = &conf->worker_groups[group].handle_list; + wg = &conf->worker_groups[group]; + } else { + int i; + for (i = 0; i < conf->group_cnt; i++) { + handle_list = &conf->worker_groups[i].handle_list; + wg = &conf->worker_groups[i]; + if (!list_empty(handle_list)) + break; + } + } + + pr_debug("%s: handle: %s hold: %s full_writes: %d bypass_count: %d\n", + __func__, + list_empty(handle_list) ? "empty" : "busy", + list_empty(&conf->hold_list) ? "empty" : "busy", + atomic_read(&conf->pending_full_writes), conf->bypass_count); + + if (!list_empty(handle_list)) { + sh = list_entry(handle_list->next, typeof(*sh), lru); + + if (list_empty(&conf->hold_list)) + conf->bypass_count = 0; + else if (!test_bit(STRIPE_IO_STARTED, &sh->state)) { + if (conf->hold_list.next == conf->last_hold) + conf->bypass_count++; + else { + conf->last_hold = conf->hold_list.next; + conf->bypass_count -= conf->bypass_threshold; + if (conf->bypass_count < 0) + conf->bypass_count = 0; + } + } + } else if (!list_empty(&conf->hold_list) && + ((conf->bypass_threshold && + conf->bypass_count > conf->bypass_threshold) || + atomic_read(&conf->pending_full_writes) == 0)) { + + list_for_each_entry(tmp, &conf->hold_list, lru) { + if (conf->worker_cnt_per_group == 0 || + group == ANY_GROUP || + !cpu_online(tmp->cpu) || + cpu_to_group(tmp->cpu) == group) { + sh = tmp; + break; + } + } + + if (sh) { + conf->bypass_count -= conf->bypass_threshold; + if (conf->bypass_count < 0) + conf->bypass_count = 0; + } + wg = NULL; + } + + if (!sh) + return NULL; + + if (wg) { + wg->stripes_cnt--; + sh->group = NULL; + } + list_del_init(&sh->lru); + BUG_ON(atomic_inc_return(&sh->count) != 1); + return sh; +} + +struct raid5_plug_cb { + struct blk_plug_cb cb; + struct list_head list; + struct list_head temp_inactive_list[NR_STRIPE_HASH_LOCKS]; +}; + +static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule) +{ + struct raid5_plug_cb *cb = container_of( + blk_cb, struct raid5_plug_cb, cb); + struct stripe_head *sh; + struct mddev *mddev = cb->cb.data; + struct r5conf *conf = mddev->private; + int cnt = 0; + int hash; + + if (cb->list.next && !list_empty(&cb->list)) { + spin_lock_irq(&conf->device_lock); + while (!list_empty(&cb->list)) { + sh = list_first_entry(&cb->list, struct stripe_head, lru); + list_del_init(&sh->lru); + /* + * avoid race release_stripe_plug() sees + * STRIPE_ON_UNPLUG_LIST clear but the stripe + * is still in our list + */ + smp_mb__before_atomic(); + clear_bit(STRIPE_ON_UNPLUG_LIST, &sh->state); + /* + * STRIPE_ON_RELEASE_LIST could be set here. In that + * case, the count is always > 1 here + */ + hash = sh->hash_lock_index; + __release_stripe(conf, sh, &cb->temp_inactive_list[hash]); + cnt++; + } + spin_unlock_irq(&conf->device_lock); + } + release_inactive_stripe_list(conf, cb->temp_inactive_list, + NR_STRIPE_HASH_LOCKS); + if (mddev->queue) + trace_block_unplug(mddev->queue, cnt, !from_schedule); + kfree(cb); +} + +static void release_stripe_plug(struct mddev *mddev, + struct stripe_head *sh) +{ + struct blk_plug_cb *blk_cb = blk_check_plugged( + raid5_unplug, mddev, + sizeof(struct raid5_plug_cb)); + struct raid5_plug_cb *cb; + + if (!blk_cb) { + release_stripe(sh); + return; + } + + cb = container_of(blk_cb, struct raid5_plug_cb, cb); + + if (cb->list.next == NULL) { + int i; + INIT_LIST_HEAD(&cb->list); + for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) + INIT_LIST_HEAD(cb->temp_inactive_list + i); + } + + if (!test_and_set_bit(STRIPE_ON_UNPLUG_LIST, &sh->state)) + list_add_tail(&sh->lru, &cb->list); + else + release_stripe(sh); +} + +static void make_discard_request(struct mddev *mddev, struct bio *bi) +{ + struct r5conf *conf = mddev->private; + sector_t logical_sector, last_sector; + struct stripe_head *sh; + int remaining; + int stripe_sectors; + + if (mddev->reshape_position != MaxSector) + /* Skip discard while reshape is happening */ + return; + + logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1); + last_sector = bi->bi_iter.bi_sector + (bi->bi_iter.bi_size>>9); + + bi->bi_next = NULL; + bi->bi_phys_segments = 1; /* over-loaded to count active stripes */ + + stripe_sectors = conf->chunk_sectors * + (conf->raid_disks - conf->max_degraded); + logical_sector = DIV_ROUND_UP_SECTOR_T(logical_sector, + stripe_sectors); + sector_div(last_sector, stripe_sectors); + + logical_sector *= conf->chunk_sectors; + last_sector *= conf->chunk_sectors; + + for (; logical_sector < last_sector; + logical_sector += STRIPE_SECTORS) { + DEFINE_WAIT(w); + int d; + again: + sh = get_active_stripe(conf, logical_sector, 0, 0, 0); + prepare_to_wait(&conf->wait_for_overlap, &w, + TASK_UNINTERRUPTIBLE); + set_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags); + if (test_bit(STRIPE_SYNCING, &sh->state)) { + release_stripe(sh); + schedule(); + goto again; + } + clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags); + spin_lock_irq(&sh->stripe_lock); + for (d = 0; d < conf->raid_disks; d++) { + if (d == sh->pd_idx || d == sh->qd_idx) + continue; + if (sh->dev[d].towrite || sh->dev[d].toread) { + set_bit(R5_Overlap, &sh->dev[d].flags); + spin_unlock_irq(&sh->stripe_lock); + release_stripe(sh); + schedule(); + goto again; + } + } + set_bit(STRIPE_DISCARD, &sh->state); + finish_wait(&conf->wait_for_overlap, &w); + for (d = 0; d < conf->raid_disks; d++) { + if (d == sh->pd_idx || d == sh->qd_idx) + continue; + sh->dev[d].towrite = bi; + set_bit(R5_OVERWRITE, &sh->dev[d].flags); + raid5_inc_bi_active_stripes(bi); + } + spin_unlock_irq(&sh->stripe_lock); + if (conf->mddev->bitmap) { + for (d = 0; + d < conf->raid_disks - conf->max_degraded; + d++) + bitmap_startwrite(mddev->bitmap, + sh->sector, + STRIPE_SECTORS, + 0); + sh->bm_seq = conf->seq_flush + 1; + set_bit(STRIPE_BIT_DELAY, &sh->state); + } + + set_bit(STRIPE_HANDLE, &sh->state); + clear_bit(STRIPE_DELAYED, &sh->state); + if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + atomic_inc(&conf->preread_active_stripes); + release_stripe_plug(mddev, sh); + } + + remaining = raid5_dec_bi_active_stripes(bi); + if (remaining == 0) { + md_write_end(mddev); + bio_endio(bi, 0); + } +} + +static void make_request(struct mddev *mddev, struct bio * bi) +{ + struct r5conf *conf = mddev->private; + int dd_idx; + sector_t new_sector; + sector_t logical_sector, last_sector; + struct stripe_head *sh; + const int rw = bio_data_dir(bi); + int remaining; + DEFINE_WAIT(w); + bool do_prepare; + + if (unlikely(bi->bi_rw & REQ_FLUSH)) { + md_flush_request(mddev, bi); + return; + } + + md_write_start(mddev, bi); + + if (rw == READ && + mddev->reshape_position == MaxSector && + chunk_aligned_read(mddev,bi)) + return; + + if (unlikely(bi->bi_rw & REQ_DISCARD)) { + make_discard_request(mddev, bi); + return; + } + + logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1); + last_sector = bio_end_sector(bi); + bi->bi_next = NULL; + bi->bi_phys_segments = 1; /* over-loaded to count active stripes */ + + prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE); + for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) { + int previous; + int seq; + + do_prepare = false; + retry: + seq = read_seqcount_begin(&conf->gen_lock); + previous = 0; + if (do_prepare) + prepare_to_wait(&conf->wait_for_overlap, &w, + TASK_UNINTERRUPTIBLE); + if (unlikely(conf->reshape_progress != MaxSector)) { + /* spinlock is needed as reshape_progress may be + * 64bit on a 32bit platform, and so it might be + * possible to see a half-updated value + * Of course reshape_progress could change after + * the lock is dropped, so once we get a reference + * to the stripe that we think it is, we will have + * to check again. + */ + spin_lock_irq(&conf->device_lock); + if (mddev->reshape_backwards + ? logical_sector < conf->reshape_progress + : logical_sector >= conf->reshape_progress) { + previous = 1; + } else { + if (mddev->reshape_backwards + ? logical_sector < conf->reshape_safe + : logical_sector >= conf->reshape_safe) { + spin_unlock_irq(&conf->device_lock); + schedule(); + do_prepare = true; + goto retry; + } + } + spin_unlock_irq(&conf->device_lock); + } + + new_sector = raid5_compute_sector(conf, logical_sector, + previous, + &dd_idx, NULL); + pr_debug("raid456: make_request, sector %llu logical %llu\n", + (unsigned long long)new_sector, + (unsigned long long)logical_sector); + + sh = get_active_stripe(conf, new_sector, previous, + (bi->bi_rw&RWA_MASK), 0); + if (sh) { + if (unlikely(previous)) { + /* expansion might have moved on while waiting for a + * stripe, so we must do the range check again. + * Expansion could still move past after this + * test, but as we are holding a reference to + * 'sh', we know that if that happens, + * STRIPE_EXPANDING will get set and the expansion + * won't proceed until we finish with the stripe. + */ + int must_retry = 0; + spin_lock_irq(&conf->device_lock); + if (mddev->reshape_backwards + ? logical_sector >= conf->reshape_progress + : logical_sector < conf->reshape_progress) + /* mismatch, need to try again */ + must_retry = 1; + spin_unlock_irq(&conf->device_lock); + if (must_retry) { + release_stripe(sh); + schedule(); + do_prepare = true; + goto retry; + } + } + if (read_seqcount_retry(&conf->gen_lock, seq)) { + /* Might have got the wrong stripe_head + * by accident + */ + release_stripe(sh); + goto retry; + } + + if (rw == WRITE && + logical_sector >= mddev->suspend_lo && + logical_sector < mddev->suspend_hi) { + release_stripe(sh); + /* As the suspend_* range is controlled by + * userspace, we want an interruptible + * wait. + */ + flush_signals(current); + prepare_to_wait(&conf->wait_for_overlap, + &w, TASK_INTERRUPTIBLE); + if (logical_sector >= mddev->suspend_lo && + logical_sector < mddev->suspend_hi) { + schedule(); + do_prepare = true; + } + goto retry; + } + + if (test_bit(STRIPE_EXPANDING, &sh->state) || + !add_stripe_bio(sh, bi, dd_idx, rw)) { + /* Stripe is busy expanding or + * add failed due to overlap. Flush everything + * and wait a while + */ + md_wakeup_thread(mddev->thread); + release_stripe(sh); + schedule(); + do_prepare = true; + goto retry; + } + set_bit(STRIPE_HANDLE, &sh->state); + clear_bit(STRIPE_DELAYED, &sh->state); + if ((bi->bi_rw & REQ_SYNC) && + !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + atomic_inc(&conf->preread_active_stripes); + release_stripe_plug(mddev, sh); + } else { + /* cannot get stripe for read-ahead, just give-up */ + clear_bit(BIO_UPTODATE, &bi->bi_flags); + break; + } + } + finish_wait(&conf->wait_for_overlap, &w); + + remaining = raid5_dec_bi_active_stripes(bi); + if (remaining == 0) { + + if ( rw == WRITE ) + md_write_end(mddev); + + trace_block_bio_complete(bdev_get_queue(bi->bi_bdev), + bi, 0); + bio_endio(bi, 0); + } +} + +static sector_t raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks); + +static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *skipped) +{ + /* reshaping is quite different to recovery/resync so it is + * handled quite separately ... here. + * + * On each call to sync_request, we gather one chunk worth of + * destination stripes and flag them as expanding. + * Then we find all the source stripes and request reads. + * As the reads complete, handle_stripe will copy the data + * into the destination stripe and release that stripe. + */ + struct r5conf *conf = mddev->private; + struct stripe_head *sh; + sector_t first_sector, last_sector; + int raid_disks = conf->previous_raid_disks; + int data_disks = raid_disks - conf->max_degraded; + int new_data_disks = conf->raid_disks - conf->max_degraded; + int i; + int dd_idx; + sector_t writepos, readpos, safepos; + sector_t stripe_addr; + int reshape_sectors; + struct list_head stripes; + + if (sector_nr == 0) { + /* If restarting in the middle, skip the initial sectors */ + if (mddev->reshape_backwards && + conf->reshape_progress < raid5_size(mddev, 0, 0)) { + sector_nr = raid5_size(mddev, 0, 0) + - conf->reshape_progress; + } else if (!mddev->reshape_backwards && + conf->reshape_progress > 0) + sector_nr = conf->reshape_progress; + sector_div(sector_nr, new_data_disks); + if (sector_nr) { + mddev->curr_resync_completed = sector_nr; + sysfs_notify(&mddev->kobj, NULL, "sync_completed"); + *skipped = 1; + return sector_nr; + } + } + + /* We need to process a full chunk at a time. + * If old and new chunk sizes differ, we need to process the + * largest of these + */ + if (mddev->new_chunk_sectors > mddev->chunk_sectors) + reshape_sectors = mddev->new_chunk_sectors; + else + reshape_sectors = mddev->chunk_sectors; + + /* We update the metadata at least every 10 seconds, or when + * the data about to be copied would over-write the source of + * the data at the front of the range. i.e. one new_stripe + * along from reshape_progress new_maps to after where + * reshape_safe old_maps to + */ + writepos = conf->reshape_progress; + sector_div(writepos, new_data_disks); + readpos = conf->reshape_progress; + sector_div(readpos, data_disks); + safepos = conf->reshape_safe; + sector_div(safepos, data_disks); + if (mddev->reshape_backwards) { + writepos -= min_t(sector_t, reshape_sectors, writepos); + readpos += reshape_sectors; + safepos += reshape_sectors; + } else { + writepos += reshape_sectors; + readpos -= min_t(sector_t, reshape_sectors, readpos); + safepos -= min_t(sector_t, reshape_sectors, safepos); + } + + /* Having calculated the 'writepos' possibly use it + * to set 'stripe_addr' which is where we will write to. + */ + if (mddev->reshape_backwards) { + BUG_ON(conf->reshape_progress == 0); + stripe_addr = writepos; + BUG_ON((mddev->dev_sectors & + ~((sector_t)reshape_sectors - 1)) + - reshape_sectors - stripe_addr + != sector_nr); + } else { + BUG_ON(writepos != sector_nr + reshape_sectors); + stripe_addr = sector_nr; + } + + /* 'writepos' is the most advanced device address we might write. + * 'readpos' is the least advanced device address we might read. + * 'safepos' is the least address recorded in the metadata as having + * been reshaped. + * If there is a min_offset_diff, these are adjusted either by + * increasing the safepos/readpos if diff is negative, or + * increasing writepos if diff is positive. + * If 'readpos' is then behind 'writepos', there is no way that we can + * ensure safety in the face of a crash - that must be done by userspace + * making a backup of the data. So in that case there is no particular + * rush to update metadata. + * Otherwise if 'safepos' is behind 'writepos', then we really need to + * update the metadata to advance 'safepos' to match 'readpos' so that + * we can be safe in the event of a crash. + * So we insist on updating metadata if safepos is behind writepos and + * readpos is beyond writepos. + * In any case, update the metadata every 10 seconds. + * Maybe that number should be configurable, but I'm not sure it is + * worth it.... maybe it could be a multiple of safemode_delay??? + */ + if (conf->min_offset_diff < 0) { + safepos += -conf->min_offset_diff; + readpos += -conf->min_offset_diff; + } else + writepos += conf->min_offset_diff; + + if ((mddev->reshape_backwards + ? (safepos > writepos && readpos < writepos) + : (safepos < writepos && readpos > writepos)) || + time_after(jiffies, conf->reshape_checkpoint + 10*HZ)) { + /* Cannot proceed until we've updated the superblock... */ + wait_event(conf->wait_for_overlap, + atomic_read(&conf->reshape_stripes)==0 + || test_bit(MD_RECOVERY_INTR, &mddev->recovery)); + if (atomic_read(&conf->reshape_stripes) != 0) + return 0; + mddev->reshape_position = conf->reshape_progress; + mddev->curr_resync_completed = sector_nr; + conf->reshape_checkpoint = jiffies; + set_bit(MD_CHANGE_DEVS, &mddev->flags); + md_wakeup_thread(mddev->thread); + wait_event(mddev->sb_wait, mddev->flags == 0 || + test_bit(MD_RECOVERY_INTR, &mddev->recovery)); + if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) + return 0; + spin_lock_irq(&conf->device_lock); + conf->reshape_safe = mddev->reshape_position; + spin_unlock_irq(&conf->device_lock); + wake_up(&conf->wait_for_overlap); + sysfs_notify(&mddev->kobj, NULL, "sync_completed"); + } + + INIT_LIST_HEAD(&stripes); + for (i = 0; i < reshape_sectors; i += STRIPE_SECTORS) { + int j; + int skipped_disk = 0; + sh = get_active_stripe(conf, stripe_addr+i, 0, 0, 1); + set_bit(STRIPE_EXPANDING, &sh->state); + atomic_inc(&conf->reshape_stripes); + /* If any of this stripe is beyond the end of the old + * array, then we need to zero those blocks + */ + for (j=sh->disks; j--;) { + sector_t s; + if (j == sh->pd_idx) + continue; + if (conf->level == 6 && + j == sh->qd_idx) + continue; + s = compute_blocknr(sh, j, 0); + if (s < raid5_size(mddev, 0, 0)) { + skipped_disk = 1; + continue; + } + memset(page_address(sh->dev[j].page), 0, STRIPE_SIZE); + set_bit(R5_Expanded, &sh->dev[j].flags); + set_bit(R5_UPTODATE, &sh->dev[j].flags); + } + if (!skipped_disk) { + set_bit(STRIPE_EXPAND_READY, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + } + list_add(&sh->lru, &stripes); + } + spin_lock_irq(&conf->device_lock); + if (mddev->reshape_backwards) + conf->reshape_progress -= reshape_sectors * new_data_disks; + else + conf->reshape_progress += reshape_sectors * new_data_disks; + spin_unlock_irq(&conf->device_lock); + /* Ok, those stripe are ready. We can start scheduling + * reads on the source stripes. + * The source stripes are determined by mapping the first and last + * block on the destination stripes. + */ + first_sector = + raid5_compute_sector(conf, stripe_addr*(new_data_disks), + 1, &dd_idx, NULL); + last_sector = + raid5_compute_sector(conf, ((stripe_addr+reshape_sectors) + * new_data_disks - 1), + 1, &dd_idx, NULL); + if (last_sector >= mddev->dev_sectors) + last_sector = mddev->dev_sectors - 1; + while (first_sector <= last_sector) { + sh = get_active_stripe(conf, first_sector, 1, 0, 1); + set_bit(STRIPE_EXPAND_SOURCE, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); + first_sector += STRIPE_SECTORS; + } + /* Now that the sources are clearly marked, we can release + * the destination stripes + */ + while (!list_empty(&stripes)) { + sh = list_entry(stripes.next, struct stripe_head, lru); + list_del_init(&sh->lru); + release_stripe(sh); + } + /* If this takes us to the resync_max point where we have to pause, + * then we need to write out the superblock. + */ + sector_nr += reshape_sectors; + if ((sector_nr - mddev->curr_resync_completed) * 2 + >= mddev->resync_max - mddev->curr_resync_completed) { + /* Cannot proceed until we've updated the superblock... */ + wait_event(conf->wait_for_overlap, + atomic_read(&conf->reshape_stripes) == 0 + || test_bit(MD_RECOVERY_INTR, &mddev->recovery)); + if (atomic_read(&conf->reshape_stripes) != 0) + goto ret; + mddev->reshape_position = conf->reshape_progress; + mddev->curr_resync_completed = sector_nr; + conf->reshape_checkpoint = jiffies; + set_bit(MD_CHANGE_DEVS, &mddev->flags); + md_wakeup_thread(mddev->thread); + wait_event(mddev->sb_wait, + !test_bit(MD_CHANGE_DEVS, &mddev->flags) + || test_bit(MD_RECOVERY_INTR, &mddev->recovery)); + if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) + goto ret; + spin_lock_irq(&conf->device_lock); + conf->reshape_safe = mddev->reshape_position; + spin_unlock_irq(&conf->device_lock); + wake_up(&conf->wait_for_overlap); + sysfs_notify(&mddev->kobj, NULL, "sync_completed"); + } +ret: + return reshape_sectors; +} + +/* FIXME go_faster isn't used */ +static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster) +{ + struct r5conf *conf = mddev->private; + struct stripe_head *sh; + sector_t max_sector = mddev->dev_sectors; + sector_t sync_blocks; + int still_degraded = 0; + int i; + + if (sector_nr >= max_sector) { + /* just being told to finish up .. nothing much to do */ + + if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) { + end_reshape(conf); + return 0; + } + + if (mddev->curr_resync < max_sector) /* aborted */ + bitmap_end_sync(mddev->bitmap, mddev->curr_resync, + &sync_blocks, 1); + else /* completed sync */ + conf->fullsync = 0; + bitmap_close_sync(mddev->bitmap); + + return 0; + } + + /* Allow raid5_quiesce to complete */ + wait_event(conf->wait_for_overlap, conf->quiesce != 2); + + if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) + return reshape_request(mddev, sector_nr, skipped); + + /* No need to check resync_max as we never do more than one + * stripe, and as resync_max will always be on a chunk boundary, + * if the check in md_do_sync didn't fire, there is no chance + * of overstepping resync_max here + */ + + /* if there is too many failed drives and we are trying + * to resync, then assert that we are finished, because there is + * nothing we can do. + */ + if (mddev->degraded >= conf->max_degraded && + test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) { + sector_t rv = mddev->dev_sectors - sector_nr; + *skipped = 1; + return rv; + } + if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && + !conf->fullsync && + !bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) && + sync_blocks >= STRIPE_SECTORS) { + /* we can skip this block, and probably more */ + sync_blocks /= STRIPE_SECTORS; + *skipped = 1; + return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */ + } + + bitmap_cond_end_sync(mddev->bitmap, sector_nr); + + sh = get_active_stripe(conf, sector_nr, 0, 1, 0); + if (sh == NULL) { + sh = get_active_stripe(conf, sector_nr, 0, 0, 0); + /* make sure we don't swamp the stripe cache if someone else + * is trying to get access + */ + schedule_timeout_uninterruptible(1); + } + /* Need to check if array will still be degraded after recovery/resync + * We don't need to check the 'failed' flag as when that gets set, + * recovery aborts. + */ + for (i = 0; i < conf->raid_disks; i++) + if (conf->disks[i].rdev == NULL) + still_degraded = 1; + + bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded); + + set_bit(STRIPE_SYNC_REQUESTED, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + + release_stripe(sh); + + return STRIPE_SECTORS; +} + +static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio) +{ + /* We may not be able to submit a whole bio at once as there + * may not be enough stripe_heads available. + * We cannot pre-allocate enough stripe_heads as we may need + * more than exist in the cache (if we allow ever large chunks). + * So we do one stripe head at a time and record in + * ->bi_hw_segments how many have been done. + * + * We *know* that this entire raid_bio is in one chunk, so + * it will be only one 'dd_idx' and only need one call to raid5_compute_sector. + */ + struct stripe_head *sh; + int dd_idx; + sector_t sector, logical_sector, last_sector; + int scnt = 0; + int remaining; + int handled = 0; + + logical_sector = raid_bio->bi_iter.bi_sector & + ~((sector_t)STRIPE_SECTORS-1); + sector = raid5_compute_sector(conf, logical_sector, + 0, &dd_idx, NULL); + last_sector = bio_end_sector(raid_bio); + + for (; logical_sector < last_sector; + logical_sector += STRIPE_SECTORS, + sector += STRIPE_SECTORS, + scnt++) { + + if (scnt < raid5_bi_processed_stripes(raid_bio)) + /* already done this stripe */ + continue; + + sh = get_active_stripe(conf, sector, 0, 1, 1); + + if (!sh) { + /* failed to get a stripe - must wait */ + raid5_set_bi_processed_stripes(raid_bio, scnt); + conf->retry_read_aligned = raid_bio; + return handled; + } + + if (!add_stripe_bio(sh, raid_bio, dd_idx, 0)) { + release_stripe(sh); + raid5_set_bi_processed_stripes(raid_bio, scnt); + conf->retry_read_aligned = raid_bio; + return handled; + } + + set_bit(R5_ReadNoMerge, &sh->dev[dd_idx].flags); + handle_stripe(sh); + release_stripe(sh); + handled++; + } + remaining = raid5_dec_bi_active_stripes(raid_bio); + if (remaining == 0) { + trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev), + raid_bio, 0); + bio_endio(raid_bio, 0); + } + if (atomic_dec_and_test(&conf->active_aligned_reads)) + wake_up(&conf->wait_for_stripe); + return handled; +} + +static int handle_active_stripes(struct r5conf *conf, int group, + struct r5worker *worker, + struct list_head *temp_inactive_list) +{ + struct stripe_head *batch[MAX_STRIPE_BATCH], *sh; + int i, batch_size = 0, hash; + bool release_inactive = false; + + while (batch_size < MAX_STRIPE_BATCH && + (sh = __get_priority_stripe(conf, group)) != NULL) + batch[batch_size++] = sh; + + if (batch_size == 0) { + for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) + if (!list_empty(temp_inactive_list + i)) + break; + if (i == NR_STRIPE_HASH_LOCKS) + return batch_size; + release_inactive = true; + } + spin_unlock_irq(&conf->device_lock); + + release_inactive_stripe_list(conf, temp_inactive_list, + NR_STRIPE_HASH_LOCKS); + + if (release_inactive) { + spin_lock_irq(&conf->device_lock); + return 0; + } + + for (i = 0; i < batch_size; i++) + handle_stripe(batch[i]); + + cond_resched(); + + spin_lock_irq(&conf->device_lock); + for (i = 0; i < batch_size; i++) { + hash = batch[i]->hash_lock_index; + __release_stripe(conf, batch[i], &temp_inactive_list[hash]); + } + return batch_size; +} + +static void raid5_do_work(struct work_struct *work) +{ + struct r5worker *worker = container_of(work, struct r5worker, work); + struct r5worker_group *group = worker->group; + struct r5conf *conf = group->conf; + int group_id = group - conf->worker_groups; + int handled; + struct blk_plug plug; + + pr_debug("+++ raid5worker active\n"); + + blk_start_plug(&plug); + handled = 0; + spin_lock_irq(&conf->device_lock); + while (1) { + int batch_size, released; + + released = release_stripe_list(conf, worker->temp_inactive_list); + + batch_size = handle_active_stripes(conf, group_id, worker, + worker->temp_inactive_list); + worker->working = false; + if (!batch_size && !released) + break; + handled += batch_size; + } + pr_debug("%d stripes handled\n", handled); + + spin_unlock_irq(&conf->device_lock); + blk_finish_plug(&plug); + + pr_debug("--- raid5worker inactive\n"); +} + +/* + * This is our raid5 kernel thread. + * + * We scan the hash table for stripes which can be handled now. + * During the scan, completed stripes are saved for us by the interrupt + * handler, so that they will not have to wait for our next wakeup. + */ +static void raid5d(struct md_thread *thread) +{ + struct mddev *mddev = thread->mddev; + struct r5conf *conf = mddev->private; + int handled; + struct blk_plug plug; + + pr_debug("+++ raid5d active\n"); + + md_check_recovery(mddev); + + blk_start_plug(&plug); + handled = 0; + spin_lock_irq(&conf->device_lock); + while (1) { + struct bio *bio; + int batch_size, released; + + released = release_stripe_list(conf, conf->temp_inactive_list); + + if ( + !list_empty(&conf->bitmap_list)) { + /* Now is a good time to flush some bitmap updates */ + conf->seq_flush++; + spin_unlock_irq(&conf->device_lock); + bitmap_unplug(mddev->bitmap); + spin_lock_irq(&conf->device_lock); + conf->seq_write = conf->seq_flush; + activate_bit_delay(conf, conf->temp_inactive_list); + } + raid5_activate_delayed(conf); + + while ((bio = remove_bio_from_retry(conf))) { + int ok; + spin_unlock_irq(&conf->device_lock); + ok = retry_aligned_read(conf, bio); + spin_lock_irq(&conf->device_lock); + if (!ok) + break; + handled++; + } + + batch_size = handle_active_stripes(conf, ANY_GROUP, NULL, + conf->temp_inactive_list); + if (!batch_size && !released) + break; + handled += batch_size; + + if (mddev->flags & ~(1<device_lock); + md_check_recovery(mddev); + spin_lock_irq(&conf->device_lock); + } + } + pr_debug("%d stripes handled\n", handled); + + spin_unlock_irq(&conf->device_lock); + + async_tx_issue_pending_all(); + blk_finish_plug(&plug); + + pr_debug("--- raid5d inactive\n"); +} + +static ssize_t +raid5_show_stripe_cache_size(struct mddev *mddev, char *page) +{ + struct r5conf *conf = mddev->private; + if (conf) + return sprintf(page, "%d\n", conf->max_nr_stripes); + else + return 0; +} + +int +raid5_set_cache_size(struct mddev *mddev, int size) +{ + struct r5conf *conf = mddev->private; + int err; + int hash; + + if (size <= 16 || size > 32768) + return -EINVAL; + hash = (conf->max_nr_stripes - 1) % NR_STRIPE_HASH_LOCKS; + while (size < conf->max_nr_stripes) { + if (drop_one_stripe(conf, hash)) + conf->max_nr_stripes--; + else + break; + hash--; + if (hash < 0) + hash = NR_STRIPE_HASH_LOCKS - 1; + } + err = md_allow_write(mddev); + if (err) + return err; + hash = conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS; + while (size > conf->max_nr_stripes) { + if (grow_one_stripe(conf, hash)) + conf->max_nr_stripes++; + else break; + hash = (hash + 1) % NR_STRIPE_HASH_LOCKS; + } + return 0; +} +EXPORT_SYMBOL(raid5_set_cache_size); + +static ssize_t +raid5_store_stripe_cache_size(struct mddev *mddev, const char *page, size_t len) +{ + struct r5conf *conf = mddev->private; + unsigned long new; + int err; + + if (len >= PAGE_SIZE) + return -EINVAL; + if (!conf) + return -ENODEV; + + if (kstrtoul(page, 10, &new)) + return -EINVAL; + err = raid5_set_cache_size(mddev, new); + if (err) + return err; + return len; +} + +static struct md_sysfs_entry +raid5_stripecache_size = __ATTR(stripe_cache_size, S_IRUGO | S_IWUSR, + raid5_show_stripe_cache_size, + raid5_store_stripe_cache_size); + +static ssize_t +raid5_show_preread_threshold(struct mddev *mddev, char *page) +{ + struct r5conf *conf = mddev->private; + if (conf) + return sprintf(page, "%d\n", conf->bypass_threshold); + else + return 0; +} + +static ssize_t +raid5_store_preread_threshold(struct mddev *mddev, const char *page, size_t len) +{ + struct r5conf *conf = mddev->private; + unsigned long new; + if (len >= PAGE_SIZE) + return -EINVAL; + if (!conf) + return -ENODEV; + + if (kstrtoul(page, 10, &new)) + return -EINVAL; + if (new > conf->max_nr_stripes) + return -EINVAL; + conf->bypass_threshold = new; + return len; +} + +static struct md_sysfs_entry +raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold, + S_IRUGO | S_IWUSR, + raid5_show_preread_threshold, + raid5_store_preread_threshold); + +static ssize_t +raid5_show_skip_copy(struct mddev *mddev, char *page) +{ + struct r5conf *conf = mddev->private; + if (conf) + return sprintf(page, "%d\n", conf->skip_copy); + else + return 0; +} + +static ssize_t +raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len) +{ + struct r5conf *conf = mddev->private; + unsigned long new; + if (len >= PAGE_SIZE) + return -EINVAL; + if (!conf) + return -ENODEV; + + if (kstrtoul(page, 10, &new)) + return -EINVAL; + new = !!new; + if (new == conf->skip_copy) + return len; + + mddev_suspend(mddev); + conf->skip_copy = new; + if (new) + mddev->queue->backing_dev_info.capabilities |= + BDI_CAP_STABLE_WRITES; + else + mddev->queue->backing_dev_info.capabilities &= + ~BDI_CAP_STABLE_WRITES; + mddev_resume(mddev); + return len; +} + +static struct md_sysfs_entry +raid5_skip_copy = __ATTR(skip_copy, S_IRUGO | S_IWUSR, + raid5_show_skip_copy, + raid5_store_skip_copy); + +static ssize_t +stripe_cache_active_show(struct mddev *mddev, char *page) +{ + struct r5conf *conf = mddev->private; + if (conf) + return sprintf(page, "%d\n", atomic_read(&conf->active_stripes)); + else + return 0; +} + +static struct md_sysfs_entry +raid5_stripecache_active = __ATTR_RO(stripe_cache_active); + +static ssize_t +raid5_show_group_thread_cnt(struct mddev *mddev, char *page) +{ + struct r5conf *conf = mddev->private; + if (conf) + return sprintf(page, "%d\n", conf->worker_cnt_per_group); + else + return 0; +} + +static int alloc_thread_groups(struct r5conf *conf, int cnt, + int *group_cnt, + int *worker_cnt_per_group, + struct r5worker_group **worker_groups); +static ssize_t +raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) +{ + struct r5conf *conf = mddev->private; + unsigned long new; + int err; + struct r5worker_group *new_groups, *old_groups; + int group_cnt, worker_cnt_per_group; + + if (len >= PAGE_SIZE) + return -EINVAL; + if (!conf) + return -ENODEV; + + if (kstrtoul(page, 10, &new)) + return -EINVAL; + + if (new == conf->worker_cnt_per_group) + return len; + + mddev_suspend(mddev); + + old_groups = conf->worker_groups; + if (old_groups) + flush_workqueue(raid5_wq); + + err = alloc_thread_groups(conf, new, + &group_cnt, &worker_cnt_per_group, + &new_groups); + if (!err) { + spin_lock_irq(&conf->device_lock); + conf->group_cnt = group_cnt; + conf->worker_cnt_per_group = worker_cnt_per_group; + conf->worker_groups = new_groups; + spin_unlock_irq(&conf->device_lock); + + if (old_groups) + kfree(old_groups[0].workers); + kfree(old_groups); + } + + mddev_resume(mddev); + + if (err) + return err; + return len; +} + +static struct md_sysfs_entry +raid5_group_thread_cnt = __ATTR(group_thread_cnt, S_IRUGO | S_IWUSR, + raid5_show_group_thread_cnt, + raid5_store_group_thread_cnt); + +static struct attribute *raid5_attrs[] = { + &raid5_stripecache_size.attr, + &raid5_stripecache_active.attr, + &raid5_preread_bypass_threshold.attr, + &raid5_group_thread_cnt.attr, + &raid5_skip_copy.attr, + NULL, +}; +static struct attribute_group raid5_attrs_group = { + .name = NULL, + .attrs = raid5_attrs, +}; + +static int alloc_thread_groups(struct r5conf *conf, int cnt, + int *group_cnt, + int *worker_cnt_per_group, + struct r5worker_group **worker_groups) +{ + int i, j, k; + ssize_t size; + struct r5worker *workers; + + *worker_cnt_per_group = cnt; + if (cnt == 0) { + *group_cnt = 0; + *worker_groups = NULL; + return 0; + } + *group_cnt = num_possible_nodes(); + size = sizeof(struct r5worker) * cnt; + workers = kzalloc(size * *group_cnt, GFP_NOIO); + *worker_groups = kzalloc(sizeof(struct r5worker_group) * + *group_cnt, GFP_NOIO); + if (!*worker_groups || !workers) { + kfree(workers); + kfree(*worker_groups); + return -ENOMEM; + } + + for (i = 0; i < *group_cnt; i++) { + struct r5worker_group *group; + + group = &(*worker_groups)[i]; + INIT_LIST_HEAD(&group->handle_list); + group->conf = conf; + group->workers = workers + i * cnt; + + for (j = 0; j < cnt; j++) { + struct r5worker *worker = group->workers + j; + worker->group = group; + INIT_WORK(&worker->work, raid5_do_work); + + for (k = 0; k < NR_STRIPE_HASH_LOCKS; k++) + INIT_LIST_HEAD(worker->temp_inactive_list + k); + } + } + + return 0; +} + +static void free_thread_groups(struct r5conf *conf) +{ + if (conf->worker_groups) + kfree(conf->worker_groups[0].workers); + kfree(conf->worker_groups); + conf->worker_groups = NULL; +} + +static sector_t +raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks) +{ + struct r5conf *conf = mddev->private; + + if (!sectors) + sectors = mddev->dev_sectors; + if (!raid_disks) + /* size is defined by the smallest of previous and new size */ + raid_disks = min(conf->raid_disks, conf->previous_raid_disks); + + sectors &= ~((sector_t)mddev->chunk_sectors - 1); + sectors &= ~((sector_t)mddev->new_chunk_sectors - 1); + return sectors * (raid_disks - conf->max_degraded); +} + +static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu) +{ + safe_put_page(percpu->spare_page); + kfree(percpu->scribble); + percpu->spare_page = NULL; + percpu->scribble = NULL; +} + +static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu) +{ + if (conf->level == 6 && !percpu->spare_page) + percpu->spare_page = alloc_page(GFP_KERNEL); + if (!percpu->scribble) + percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL); + + if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) { + free_scratch_buffer(conf, percpu); + return -ENOMEM; + } + + return 0; +} + +static void raid5_free_percpu(struct r5conf *conf) +{ + unsigned long cpu; + + if (!conf->percpu) + return; + +#ifdef CONFIG_HOTPLUG_CPU + unregister_cpu_notifier(&conf->cpu_notify); +#endif + + get_online_cpus(); + for_each_possible_cpu(cpu) + free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); + put_online_cpus(); + + free_percpu(conf->percpu); +} + +static void free_conf(struct r5conf *conf) +{ + free_thread_groups(conf); + shrink_stripes(conf); + raid5_free_percpu(conf); + kfree(conf->disks); + kfree(conf->stripe_hashtbl); + kfree(conf); +} + +#ifdef CONFIG_HOTPLUG_CPU +static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, + void *hcpu) +{ + struct r5conf *conf = container_of(nfb, struct r5conf, cpu_notify); + long cpu = (long)hcpu; + struct raid5_percpu *percpu = per_cpu_ptr(conf->percpu, cpu); + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + if (alloc_scratch_buffer(conf, percpu)) { + pr_err("%s: failed memory allocation for cpu%ld\n", + __func__, cpu); + return notifier_from_errno(-ENOMEM); + } + break; + case CPU_DEAD: + case CPU_DEAD_FROZEN: + free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); + break; + default: + break; + } + return NOTIFY_OK; +} +#endif + +static int raid5_alloc_percpu(struct r5conf *conf) +{ + unsigned long cpu; + int err = 0; + + conf->percpu = alloc_percpu(struct raid5_percpu); + if (!conf->percpu) + return -ENOMEM; + +#ifdef CONFIG_HOTPLUG_CPU + conf->cpu_notify.notifier_call = raid456_cpu_notify; + conf->cpu_notify.priority = 0; + err = register_cpu_notifier(&conf->cpu_notify); + if (err) + return err; +#endif + + get_online_cpus(); + for_each_present_cpu(cpu) { + err = alloc_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); + if (err) { + pr_err("%s: failed memory allocation for cpu%ld\n", + __func__, cpu); + break; + } + } + put_online_cpus(); + + return err; +} + +static struct r5conf *setup_conf(struct mddev *mddev) +{ + struct r5conf *conf; + int raid_disk, memory, max_disks; + struct md_rdev *rdev; + struct disk_info *disk; + char pers_name[6]; + int i; + int group_cnt, worker_cnt_per_group; + struct r5worker_group *new_group; + + if (mddev->new_level != 5 + && mddev->new_level != 4 + && mddev->new_level != 6) { + printk(KERN_ERR "md/raid:%s: raid level not set to 4/5/6 (%d)\n", + mdname(mddev), mddev->new_level); + return ERR_PTR(-EIO); + } + if ((mddev->new_level == 5 + && !algorithm_valid_raid5(mddev->new_layout)) || + (mddev->new_level == 6 + && !algorithm_valid_raid6(mddev->new_layout))) { + printk(KERN_ERR "md/raid:%s: layout %d not supported\n", + mdname(mddev), mddev->new_layout); + return ERR_PTR(-EIO); + } + if (mddev->new_level == 6 && mddev->raid_disks < 4) { + printk(KERN_ERR "md/raid:%s: not enough configured devices (%d, minimum 4)\n", + mdname(mddev), mddev->raid_disks); + return ERR_PTR(-EINVAL); + } + + if (!mddev->new_chunk_sectors || + (mddev->new_chunk_sectors << 9) % PAGE_SIZE || + !is_power_of_2(mddev->new_chunk_sectors)) { + printk(KERN_ERR "md/raid:%s: invalid chunk size %d\n", + mdname(mddev), mddev->new_chunk_sectors << 9); + return ERR_PTR(-EINVAL); + } + + conf = kzalloc(sizeof(struct r5conf), GFP_KERNEL); + if (conf == NULL) + goto abort; + /* Don't enable multi-threading by default*/ + if (!alloc_thread_groups(conf, 0, &group_cnt, &worker_cnt_per_group, + &new_group)) { + conf->group_cnt = group_cnt; + conf->worker_cnt_per_group = worker_cnt_per_group; + conf->worker_groups = new_group; + } else + goto abort; + spin_lock_init(&conf->device_lock); + seqcount_init(&conf->gen_lock); + init_waitqueue_head(&conf->wait_for_stripe); + init_waitqueue_head(&conf->wait_for_overlap); + INIT_LIST_HEAD(&conf->handle_list); + INIT_LIST_HEAD(&conf->hold_list); + INIT_LIST_HEAD(&conf->delayed_list); + INIT_LIST_HEAD(&conf->bitmap_list); + init_llist_head(&conf->released_stripes); + atomic_set(&conf->active_stripes, 0); + atomic_set(&conf->preread_active_stripes, 0); + atomic_set(&conf->active_aligned_reads, 0); + conf->bypass_threshold = BYPASS_THRESHOLD; + conf->recovery_disabled = mddev->recovery_disabled - 1; + + conf->raid_disks = mddev->raid_disks; + if (mddev->reshape_position == MaxSector) + conf->previous_raid_disks = mddev->raid_disks; + else + conf->previous_raid_disks = mddev->raid_disks - mddev->delta_disks; + max_disks = max(conf->raid_disks, conf->previous_raid_disks); + conf->scribble_len = scribble_len(max_disks); + + conf->disks = kzalloc(max_disks * sizeof(struct disk_info), + GFP_KERNEL); + if (!conf->disks) + goto abort; + + conf->mddev = mddev; + + if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL) + goto abort; + + /* We init hash_locks[0] separately to that it can be used + * as the reference lock in the spin_lock_nest_lock() call + * in lock_all_device_hash_locks_irq in order to convince + * lockdep that we know what we are doing. + */ + spin_lock_init(conf->hash_locks); + for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++) + spin_lock_init(conf->hash_locks + i); + + for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) + INIT_LIST_HEAD(conf->inactive_list + i); + + for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) + INIT_LIST_HEAD(conf->temp_inactive_list + i); + + conf->level = mddev->new_level; + if (raid5_alloc_percpu(conf) != 0) + goto abort; + + pr_debug("raid456: run(%s) called.\n", mdname(mddev)); + + rdev_for_each(rdev, mddev) { + raid_disk = rdev->raid_disk; + if (raid_disk >= max_disks + || raid_disk < 0) + continue; + disk = conf->disks + raid_disk; + + if (test_bit(Replacement, &rdev->flags)) { + if (disk->replacement) + goto abort; + disk->replacement = rdev; + } else { + if (disk->rdev) + goto abort; + disk->rdev = rdev; + } + + if (test_bit(In_sync, &rdev->flags)) { + char b[BDEVNAME_SIZE]; + printk(KERN_INFO "md/raid:%s: device %s operational as raid" + " disk %d\n", + mdname(mddev), bdevname(rdev->bdev, b), raid_disk); + } else if (rdev->saved_raid_disk != raid_disk) + /* Cannot rely on bitmap to complete recovery */ + conf->fullsync = 1; + } + + conf->chunk_sectors = mddev->new_chunk_sectors; + conf->level = mddev->new_level; + if (conf->level == 6) + conf->max_degraded = 2; + else + conf->max_degraded = 1; + conf->algorithm = mddev->new_layout; + conf->reshape_progress = mddev->reshape_position; + if (conf->reshape_progress != MaxSector) { + conf->prev_chunk_sectors = mddev->chunk_sectors; + conf->prev_algo = mddev->layout; + } + + memory = conf->max_nr_stripes * (sizeof(struct stripe_head) + + max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024; + atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS); + if (grow_stripes(conf, NR_STRIPES)) { + printk(KERN_ERR + "md/raid:%s: couldn't allocate %dkB for buffers\n", + mdname(mddev), memory); + goto abort; + } else + printk(KERN_INFO "md/raid:%s: allocated %dkB\n", + mdname(mddev), memory); + + sprintf(pers_name, "raid%d", mddev->new_level); + conf->thread = md_register_thread(raid5d, mddev, pers_name); + if (!conf->thread) { + printk(KERN_ERR + "md/raid:%s: couldn't allocate thread.\n", + mdname(mddev)); + goto abort; + } + + return conf; + + abort: + if (conf) { + free_conf(conf); + return ERR_PTR(-EIO); + } else + return ERR_PTR(-ENOMEM); +} + +static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded) +{ + switch (algo) { + case ALGORITHM_PARITY_0: + if (raid_disk < max_degraded) + return 1; + break; + case ALGORITHM_PARITY_N: + if (raid_disk >= raid_disks - max_degraded) + return 1; + break; + case ALGORITHM_PARITY_0_6: + if (raid_disk == 0 || + raid_disk == raid_disks - 1) + return 1; + break; + case ALGORITHM_LEFT_ASYMMETRIC_6: + case ALGORITHM_RIGHT_ASYMMETRIC_6: + case ALGORITHM_LEFT_SYMMETRIC_6: + case ALGORITHM_RIGHT_SYMMETRIC_6: + if (raid_disk == raid_disks - 1) + return 1; + } + return 0; +} + +static int run(struct mddev *mddev) +{ + struct r5conf *conf; + int working_disks = 0; + int dirty_parity_disks = 0; + struct md_rdev *rdev; + sector_t reshape_offset = 0; + int i; + long long min_offset_diff = 0; + int first = 1; + + if (mddev->recovery_cp != MaxSector) + printk(KERN_NOTICE "md/raid:%s: not clean" + " -- starting background reconstruction\n", + mdname(mddev)); + + rdev_for_each(rdev, mddev) { + long long diff; + if (rdev->raid_disk < 0) + continue; + diff = (rdev->new_data_offset - rdev->data_offset); + if (first) { + min_offset_diff = diff; + first = 0; + } else if (mddev->reshape_backwards && + diff < min_offset_diff) + min_offset_diff = diff; + else if (!mddev->reshape_backwards && + diff > min_offset_diff) + min_offset_diff = diff; + } + + if (mddev->reshape_position != MaxSector) { + /* Check that we can continue the reshape. + * Difficulties arise if the stripe we would write to + * next is at or after the stripe we would read from next. + * For a reshape that changes the number of devices, this + * is only possible for a very short time, and mdadm makes + * sure that time appears to have past before assembling + * the array. So we fail if that time hasn't passed. + * For a reshape that keeps the number of devices the same + * mdadm must be monitoring the reshape can keeping the + * critical areas read-only and backed up. It will start + * the array in read-only mode, so we check for that. + */ + sector_t here_new, here_old; + int old_disks; + int max_degraded = (mddev->level == 6 ? 2 : 1); + + if (mddev->new_level != mddev->level) { + printk(KERN_ERR "md/raid:%s: unsupported reshape " + "required - aborting.\n", + mdname(mddev)); + return -EINVAL; + } + old_disks = mddev->raid_disks - mddev->delta_disks; + /* reshape_position must be on a new-stripe boundary, and one + * further up in new geometry must map after here in old + * geometry. + */ + here_new = mddev->reshape_position; + if (sector_div(here_new, mddev->new_chunk_sectors * + (mddev->raid_disks - max_degraded))) { + printk(KERN_ERR "md/raid:%s: reshape_position not " + "on a stripe boundary\n", mdname(mddev)); + return -EINVAL; + } + reshape_offset = here_new * mddev->new_chunk_sectors; + /* here_new is the stripe we will write to */ + here_old = mddev->reshape_position; + sector_div(here_old, mddev->chunk_sectors * + (old_disks-max_degraded)); + /* here_old is the first stripe that we might need to read + * from */ + if (mddev->delta_disks == 0) { + if ((here_new * mddev->new_chunk_sectors != + here_old * mddev->chunk_sectors)) { + printk(KERN_ERR "md/raid:%s: reshape position is" + " confused - aborting\n", mdname(mddev)); + return -EINVAL; + } + /* We cannot be sure it is safe to start an in-place + * reshape. It is only safe if user-space is monitoring + * and taking constant backups. + * mdadm always starts a situation like this in + * readonly mode so it can take control before + * allowing any writes. So just check for that. + */ + if (abs(min_offset_diff) >= mddev->chunk_sectors && + abs(min_offset_diff) >= mddev->new_chunk_sectors) + /* not really in-place - so OK */; + else if (mddev->ro == 0) { + printk(KERN_ERR "md/raid:%s: in-place reshape " + "must be started in read-only mode " + "- aborting\n", + mdname(mddev)); + return -EINVAL; + } + } else if (mddev->reshape_backwards + ? (here_new * mddev->new_chunk_sectors + min_offset_diff <= + here_old * mddev->chunk_sectors) + : (here_new * mddev->new_chunk_sectors >= + here_old * mddev->chunk_sectors + (-min_offset_diff))) { + /* Reading from the same stripe as writing to - bad */ + printk(KERN_ERR "md/raid:%s: reshape_position too early for " + "auto-recovery - aborting.\n", + mdname(mddev)); + return -EINVAL; + } + printk(KERN_INFO "md/raid:%s: reshape will continue\n", + mdname(mddev)); + /* OK, we should be able to continue; */ + } else { + BUG_ON(mddev->level != mddev->new_level); + BUG_ON(mddev->layout != mddev->new_layout); + BUG_ON(mddev->chunk_sectors != mddev->new_chunk_sectors); + BUG_ON(mddev->delta_disks != 0); + } + + if (mddev->private == NULL) + conf = setup_conf(mddev); + else + conf = mddev->private; + + if (IS_ERR(conf)) + return PTR_ERR(conf); + + conf->min_offset_diff = min_offset_diff; + mddev->thread = conf->thread; + conf->thread = NULL; + mddev->private = conf; + + for (i = 0; i < conf->raid_disks && conf->previous_raid_disks; + i++) { + rdev = conf->disks[i].rdev; + if (!rdev && conf->disks[i].replacement) { + /* The replacement is all we have yet */ + rdev = conf->disks[i].replacement; + conf->disks[i].replacement = NULL; + clear_bit(Replacement, &rdev->flags); + conf->disks[i].rdev = rdev; + } + if (!rdev) + continue; + if (conf->disks[i].replacement && + conf->reshape_progress != MaxSector) { + /* replacements and reshape simply do not mix. */ + printk(KERN_ERR "md: cannot handle concurrent " + "replacement and reshape.\n"); + goto abort; + } + if (test_bit(In_sync, &rdev->flags)) { + working_disks++; + continue; + } + /* This disc is not fully in-sync. However if it + * just stored parity (beyond the recovery_offset), + * when we don't need to be concerned about the + * array being dirty. + * When reshape goes 'backwards', we never have + * partially completed devices, so we only need + * to worry about reshape going forwards. + */ + /* Hack because v0.91 doesn't store recovery_offset properly. */ + if (mddev->major_version == 0 && + mddev->minor_version > 90) + rdev->recovery_offset = reshape_offset; + + if (rdev->recovery_offset < reshape_offset) { + /* We need to check old and new layout */ + if (!only_parity(rdev->raid_disk, + conf->algorithm, + conf->raid_disks, + conf->max_degraded)) + continue; + } + if (!only_parity(rdev->raid_disk, + conf->prev_algo, + conf->previous_raid_disks, + conf->max_degraded)) + continue; + dirty_parity_disks++; + } + + /* + * 0 for a fully functional array, 1 or 2 for a degraded array. + */ + mddev->degraded = calc_degraded(conf); + + if (has_failed(conf)) { + printk(KERN_ERR "md/raid:%s: not enough operational devices" + " (%d/%d failed)\n", + mdname(mddev), mddev->degraded, conf->raid_disks); + goto abort; + } + + /* device size must be a multiple of chunk size */ + mddev->dev_sectors &= ~(mddev->chunk_sectors - 1); + mddev->resync_max_sectors = mddev->dev_sectors; + + if (mddev->degraded > dirty_parity_disks && + mddev->recovery_cp != MaxSector) { + if (mddev->ok_start_degraded) + printk(KERN_WARNING + "md/raid:%s: starting dirty degraded array" + " - data corruption possible.\n", + mdname(mddev)); + else { + printk(KERN_ERR + "md/raid:%s: cannot start dirty degraded array.\n", + mdname(mddev)); + goto abort; + } + } + + if (mddev->degraded == 0) + printk(KERN_INFO "md/raid:%s: raid level %d active with %d out of %d" + " devices, algorithm %d\n", mdname(mddev), conf->level, + mddev->raid_disks-mddev->degraded, mddev->raid_disks, + mddev->new_layout); + else + printk(KERN_ALERT "md/raid:%s: raid level %d active with %d" + " out of %d devices, algorithm %d\n", + mdname(mddev), conf->level, + mddev->raid_disks - mddev->degraded, + mddev->raid_disks, mddev->new_layout); + + print_raid5_conf(conf); + + if (conf->reshape_progress != MaxSector) { + conf->reshape_safe = conf->reshape_progress; + atomic_set(&conf->reshape_stripes, 0); + clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); + clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); + set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); + set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); + mddev->sync_thread = md_register_thread(md_do_sync, mddev, + "reshape"); + } + + /* Ok, everything is just fine now */ + if (mddev->to_remove == &raid5_attrs_group) + mddev->to_remove = NULL; + else if (mddev->kobj.sd && + sysfs_create_group(&mddev->kobj, &raid5_attrs_group)) + printk(KERN_WARNING + "raid5: failed to create sysfs attributes for %s\n", + mdname(mddev)); + md_set_array_sectors(mddev, raid5_size(mddev, 0, 0)); + + if (mddev->queue) { + int chunk_size; + bool discard_supported = true; + /* read-ahead size must cover two whole stripes, which + * is 2 * (datadisks) * chunksize where 'n' is the + * number of raid devices + */ + int data_disks = conf->previous_raid_disks - conf->max_degraded; + int stripe = data_disks * + ((mddev->chunk_sectors << 9) / PAGE_SIZE); + if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe) + mddev->queue->backing_dev_info.ra_pages = 2 * stripe; + + blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec); + + mddev->queue->backing_dev_info.congested_data = mddev; + mddev->queue->backing_dev_info.congested_fn = raid5_congested; + + chunk_size = mddev->chunk_sectors << 9; + blk_queue_io_min(mddev->queue, chunk_size); + blk_queue_io_opt(mddev->queue, chunk_size * + (conf->raid_disks - conf->max_degraded)); + mddev->queue->limits.raid_partial_stripes_expensive = 1; + /* + * We can only discard a whole stripe. It doesn't make sense to + * discard data disk but write parity disk + */ + stripe = stripe * PAGE_SIZE; + /* Round up to power of 2, as discard handling + * currently assumes that */ + while ((stripe-1) & stripe) + stripe = (stripe | (stripe-1)) + 1; + mddev->queue->limits.discard_alignment = stripe; + mddev->queue->limits.discard_granularity = stripe; + /* + * unaligned part of discard request will be ignored, so can't + * guarantee discard_zeroes_data + */ + mddev->queue->limits.discard_zeroes_data = 0; + + blk_queue_max_write_same_sectors(mddev->queue, 0); + + rdev_for_each(rdev, mddev) { + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->new_data_offset << 9); + /* + * discard_zeroes_data is required, otherwise data + * could be lost. Consider a scenario: discard a stripe + * (the stripe could be inconsistent if + * discard_zeroes_data is 0); write one disk of the + * stripe (the stripe could be inconsistent again + * depending on which disks are used to calculate + * parity); the disk is broken; The stripe data of this + * disk is lost. + */ + if (!blk_queue_discard(bdev_get_queue(rdev->bdev)) || + !bdev_get_queue(rdev->bdev)-> + limits.discard_zeroes_data) + discard_supported = false; + /* Unfortunately, discard_zeroes_data is not currently + * a guarantee - just a hint. So we only allow DISCARD + * if the sysadmin has confirmed that only safe devices + * are in use by setting a module parameter. + */ + if (!devices_handle_discard_safely) { + if (discard_supported) { + pr_info("md/raid456: discard support disabled due to uncertainty.\n"); + pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n"); + } + discard_supported = false; + } + } + + if (discard_supported && + mddev->queue->limits.max_discard_sectors >= stripe && + mddev->queue->limits.discard_granularity >= stripe) + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, + mddev->queue); + else + queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, + mddev->queue); + } + + return 0; +abort: + md_unregister_thread(&mddev->thread); + print_raid5_conf(conf); + free_conf(conf); + mddev->private = NULL; + printk(KERN_ALERT "md/raid:%s: failed to run raid set.\n", mdname(mddev)); + return -EIO; +} + +static int stop(struct mddev *mddev) +{ + struct r5conf *conf = mddev->private; + + md_unregister_thread(&mddev->thread); + if (mddev->queue) + mddev->queue->backing_dev_info.congested_fn = NULL; + free_conf(conf); + mddev->private = NULL; + mddev->to_remove = &raid5_attrs_group; + return 0; +} + +static void status(struct seq_file *seq, struct mddev *mddev) +{ + struct r5conf *conf = mddev->private; + int i; + + seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level, + mddev->chunk_sectors / 2, mddev->layout); + seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded); + for (i = 0; i < conf->raid_disks; i++) + seq_printf (seq, "%s", + conf->disks[i].rdev && + test_bit(In_sync, &conf->disks[i].rdev->flags) ? "U" : "_"); + seq_printf (seq, "]"); +} + +static void print_raid5_conf (struct r5conf *conf) +{ + int i; + struct disk_info *tmp; + + printk(KERN_DEBUG "RAID conf printout:\n"); + if (!conf) { + printk("(conf==NULL)\n"); + return; + } + printk(KERN_DEBUG " --- level:%d rd:%d wd:%d\n", conf->level, + conf->raid_disks, + conf->raid_disks - conf->mddev->degraded); + + for (i = 0; i < conf->raid_disks; i++) { + char b[BDEVNAME_SIZE]; + tmp = conf->disks + i; + if (tmp->rdev) + printk(KERN_DEBUG " disk %d, o:%d, dev:%s\n", + i, !test_bit(Faulty, &tmp->rdev->flags), + bdevname(tmp->rdev->bdev, b)); + } +} + +static int raid5_spare_active(struct mddev *mddev) +{ + int i; + struct r5conf *conf = mddev->private; + struct disk_info *tmp; + int count = 0; + unsigned long flags; + + for (i = 0; i < conf->raid_disks; i++) { + tmp = conf->disks + i; + if (tmp->replacement + && tmp->replacement->recovery_offset == MaxSector + && !test_bit(Faulty, &tmp->replacement->flags) + && !test_and_set_bit(In_sync, &tmp->replacement->flags)) { + /* Replacement has just become active. */ + if (!tmp->rdev + || !test_and_clear_bit(In_sync, &tmp->rdev->flags)) + count++; + if (tmp->rdev) { + /* Replaced device not technically faulty, + * but we need to be sure it gets removed + * and never re-added. + */ + set_bit(Faulty, &tmp->rdev->flags); + sysfs_notify_dirent_safe( + tmp->rdev->sysfs_state); + } + sysfs_notify_dirent_safe(tmp->replacement->sysfs_state); + } else if (tmp->rdev + && tmp->rdev->recovery_offset == MaxSector + && !test_bit(Faulty, &tmp->rdev->flags) + && !test_and_set_bit(In_sync, &tmp->rdev->flags)) { + count++; + sysfs_notify_dirent_safe(tmp->rdev->sysfs_state); + } + } + spin_lock_irqsave(&conf->device_lock, flags); + mddev->degraded = calc_degraded(conf); + spin_unlock_irqrestore(&conf->device_lock, flags); + print_raid5_conf(conf); + return count; +} + +static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev) +{ + struct r5conf *conf = mddev->private; + int err = 0; + int number = rdev->raid_disk; + struct md_rdev **rdevp; + struct disk_info *p = conf->disks + number; + + print_raid5_conf(conf); + if (rdev == p->rdev) + rdevp = &p->rdev; + else if (rdev == p->replacement) + rdevp = &p->replacement; + else + return 0; + + if (number >= conf->raid_disks && + conf->reshape_progress == MaxSector) + clear_bit(In_sync, &rdev->flags); + + if (test_bit(In_sync, &rdev->flags) || + atomic_read(&rdev->nr_pending)) { + err = -EBUSY; + goto abort; + } + /* Only remove non-faulty devices if recovery + * isn't possible. + */ + if (!test_bit(Faulty, &rdev->flags) && + mddev->recovery_disabled != conf->recovery_disabled && + !has_failed(conf) && + (!p->replacement || p->replacement == rdev) && + number < conf->raid_disks) { + err = -EBUSY; + goto abort; + } + *rdevp = NULL; + synchronize_rcu(); + if (atomic_read(&rdev->nr_pending)) { + /* lost the race, try later */ + err = -EBUSY; + *rdevp = rdev; + } else if (p->replacement) { + /* We must have just cleared 'rdev' */ + p->rdev = p->replacement; + clear_bit(Replacement, &p->replacement->flags); + smp_mb(); /* Make sure other CPUs may see both as identical + * but will never see neither - if they are careful + */ + p->replacement = NULL; + clear_bit(WantReplacement, &rdev->flags); + } else + /* We might have just removed the Replacement as faulty- + * clear the bit just in case + */ + clear_bit(WantReplacement, &rdev->flags); +abort: + + print_raid5_conf(conf); + return err; +} + +static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) +{ + struct r5conf *conf = mddev->private; + int err = -EEXIST; + int disk; + struct disk_info *p; + int first = 0; + int last = conf->raid_disks - 1; + + if (mddev->recovery_disabled == conf->recovery_disabled) + return -EBUSY; + + if (rdev->saved_raid_disk < 0 && has_failed(conf)) + /* no point adding a device */ + return -EINVAL; + + if (rdev->raid_disk >= 0) + first = last = rdev->raid_disk; + + /* + * find the disk ... but prefer rdev->saved_raid_disk + * if possible. + */ + if (rdev->saved_raid_disk >= 0 && + rdev->saved_raid_disk >= first && + conf->disks[rdev->saved_raid_disk].rdev == NULL) + first = rdev->saved_raid_disk; + + for (disk = first; disk <= last; disk++) { + p = conf->disks + disk; + if (p->rdev == NULL) { + clear_bit(In_sync, &rdev->flags); + rdev->raid_disk = disk; + err = 0; + if (rdev->saved_raid_disk != disk) + conf->fullsync = 1; + rcu_assign_pointer(p->rdev, rdev); + goto out; + } + } + for (disk = first; disk <= last; disk++) { + p = conf->disks + disk; + if (test_bit(WantReplacement, &p->rdev->flags) && + p->replacement == NULL) { + clear_bit(In_sync, &rdev->flags); + set_bit(Replacement, &rdev->flags); + rdev->raid_disk = disk; + err = 0; + conf->fullsync = 1; + rcu_assign_pointer(p->replacement, rdev); + break; + } + } +out: + print_raid5_conf(conf); + return err; +} + +static int raid5_resize(struct mddev *mddev, sector_t sectors) +{ + /* no resync is happening, and there is enough space + * on all devices, so we can resize. + * We need to make sure resync covers any new space. + * If the array is shrinking we should possibly wait until + * any io in the removed space completes, but it hardly seems + * worth it. + */ + sector_t newsize; + sectors &= ~((sector_t)mddev->chunk_sectors - 1); + newsize = raid5_size(mddev, sectors, mddev->raid_disks); + if (mddev->external_size && + mddev->array_sectors > newsize) + return -EINVAL; + if (mddev->bitmap) { + int ret = bitmap_resize(mddev->bitmap, sectors, 0, 0); + if (ret) + return ret; + } + md_set_array_sectors(mddev, newsize); + set_capacity(mddev->gendisk, mddev->array_sectors); + revalidate_disk(mddev->gendisk); + if (sectors > mddev->dev_sectors && + mddev->recovery_cp > mddev->dev_sectors) { + mddev->recovery_cp = mddev->dev_sectors; + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + } + mddev->dev_sectors = sectors; + mddev->resync_max_sectors = sectors; + return 0; +} + +static int check_stripe_cache(struct mddev *mddev) +{ + /* Can only proceed if there are plenty of stripe_heads. + * We need a minimum of one full stripe,, and for sensible progress + * it is best to have about 4 times that. + * If we require 4 times, then the default 256 4K stripe_heads will + * allow for chunk sizes up to 256K, which is probably OK. + * If the chunk size is greater, user-space should request more + * stripe_heads first. + */ + struct r5conf *conf = mddev->private; + if (((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4 + > conf->max_nr_stripes || + ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4 + > conf->max_nr_stripes) { + printk(KERN_WARNING "md/raid:%s: reshape: not enough stripes. Needed %lu\n", + mdname(mddev), + ((max(mddev->chunk_sectors, mddev->new_chunk_sectors) << 9) + / STRIPE_SIZE)*4); + return 0; + } + return 1; +} + +static int check_reshape(struct mddev *mddev) +{ + struct r5conf *conf = mddev->private; + + if (mddev->delta_disks == 0 && + mddev->new_layout == mddev->layout && + mddev->new_chunk_sectors == mddev->chunk_sectors) + return 0; /* nothing to do */ + if (has_failed(conf)) + return -EINVAL; + if (mddev->delta_disks < 0 && mddev->reshape_position == MaxSector) { + /* We might be able to shrink, but the devices must + * be made bigger first. + * For raid6, 4 is the minimum size. + * Otherwise 2 is the minimum + */ + int min = 2; + if (mddev->level == 6) + min = 4; + if (mddev->raid_disks + mddev->delta_disks < min) + return -EINVAL; + } + + if (!check_stripe_cache(mddev)) + return -ENOSPC; + + return resize_stripes(conf, (conf->previous_raid_disks + + mddev->delta_disks)); +} + +static int raid5_start_reshape(struct mddev *mddev) +{ + struct r5conf *conf = mddev->private; + struct md_rdev *rdev; + int spares = 0; + unsigned long flags; + + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + return -EBUSY; + + if (!check_stripe_cache(mddev)) + return -ENOSPC; + + if (has_failed(conf)) + return -EINVAL; + + rdev_for_each(rdev, mddev) { + if (!test_bit(In_sync, &rdev->flags) + && !test_bit(Faulty, &rdev->flags)) + spares++; + } + + if (spares - mddev->degraded < mddev->delta_disks - conf->max_degraded) + /* Not enough devices even to make a degraded array + * of that size + */ + return -EINVAL; + + /* Refuse to reduce size of the array. Any reductions in + * array size must be through explicit setting of array_size + * attribute. + */ + if (raid5_size(mddev, 0, conf->raid_disks + mddev->delta_disks) + < mddev->array_sectors) { + printk(KERN_ERR "md/raid:%s: array size must be reduced " + "before number of disks\n", mdname(mddev)); + return -EINVAL; + } + + atomic_set(&conf->reshape_stripes, 0); + spin_lock_irq(&conf->device_lock); + write_seqcount_begin(&conf->gen_lock); + conf->previous_raid_disks = conf->raid_disks; + conf->raid_disks += mddev->delta_disks; + conf->prev_chunk_sectors = conf->chunk_sectors; + conf->chunk_sectors = mddev->new_chunk_sectors; + conf->prev_algo = conf->algorithm; + conf->algorithm = mddev->new_layout; + conf->generation++; + /* Code that selects data_offset needs to see the generation update + * if reshape_progress has been set - so a memory barrier needed. + */ + smp_mb(); + if (mddev->reshape_backwards) + conf->reshape_progress = raid5_size(mddev, 0, 0); + else + conf->reshape_progress = 0; + conf->reshape_safe = conf->reshape_progress; + write_seqcount_end(&conf->gen_lock); + spin_unlock_irq(&conf->device_lock); + + /* Now make sure any requests that proceeded on the assumption + * the reshape wasn't running - like Discard or Read - have + * completed. + */ + mddev_suspend(mddev); + mddev_resume(mddev); + + /* Add some new drives, as many as will fit. + * We know there are enough to make the newly sized array work. + * Don't add devices if we are reducing the number of + * devices in the array. This is because it is not possible + * to correctly record the "partially reconstructed" state of + * such devices during the reshape and confusion could result. + */ + if (mddev->delta_disks >= 0) { + rdev_for_each(rdev, mddev) + if (rdev->raid_disk < 0 && + !test_bit(Faulty, &rdev->flags)) { + if (raid5_add_disk(mddev, rdev) == 0) { + if (rdev->raid_disk + >= conf->previous_raid_disks) + set_bit(In_sync, &rdev->flags); + else + rdev->recovery_offset = 0; + + if (sysfs_link_rdev(mddev, rdev)) + /* Failure here is OK */; + } + } else if (rdev->raid_disk >= conf->previous_raid_disks + && !test_bit(Faulty, &rdev->flags)) { + /* This is a spare that was manually added */ + set_bit(In_sync, &rdev->flags); + } + + /* When a reshape changes the number of devices, + * ->degraded is measured against the larger of the + * pre and post number of devices. + */ + spin_lock_irqsave(&conf->device_lock, flags); + mddev->degraded = calc_degraded(conf); + spin_unlock_irqrestore(&conf->device_lock, flags); + } + mddev->raid_disks = conf->raid_disks; + mddev->reshape_position = conf->reshape_progress; + set_bit(MD_CHANGE_DEVS, &mddev->flags); + + clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); + clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); + set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); + set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); + mddev->sync_thread = md_register_thread(md_do_sync, mddev, + "reshape"); + if (!mddev->sync_thread) { + mddev->recovery = 0; + spin_lock_irq(&conf->device_lock); + write_seqcount_begin(&conf->gen_lock); + mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks; + mddev->new_chunk_sectors = + conf->chunk_sectors = conf->prev_chunk_sectors; + mddev->new_layout = conf->algorithm = conf->prev_algo; + rdev_for_each(rdev, mddev) + rdev->new_data_offset = rdev->data_offset; + smp_wmb(); + conf->generation --; + conf->reshape_progress = MaxSector; + mddev->reshape_position = MaxSector; + write_seqcount_end(&conf->gen_lock); + spin_unlock_irq(&conf->device_lock); + return -EAGAIN; + } + conf->reshape_checkpoint = jiffies; + md_wakeup_thread(mddev->sync_thread); + md_new_event(mddev); + return 0; +} + +/* This is called from the reshape thread and should make any + * changes needed in 'conf' + */ +static void end_reshape(struct r5conf *conf) +{ + + if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) { + struct md_rdev *rdev; + + spin_lock_irq(&conf->device_lock); + conf->previous_raid_disks = conf->raid_disks; + rdev_for_each(rdev, conf->mddev) + rdev->data_offset = rdev->new_data_offset; + smp_wmb(); + conf->reshape_progress = MaxSector; + spin_unlock_irq(&conf->device_lock); + wake_up(&conf->wait_for_overlap); + + /* read-ahead size must cover two whole stripes, which is + * 2 * (datadisks) * chunksize where 'n' is the number of raid devices + */ + if (conf->mddev->queue) { + int data_disks = conf->raid_disks - conf->max_degraded; + int stripe = data_disks * ((conf->chunk_sectors << 9) + / PAGE_SIZE); + if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe) + conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe; + } + } +} + +/* This is called from the raid5d thread with mddev_lock held. + * It makes config changes to the device. + */ +static void raid5_finish_reshape(struct mddev *mddev) +{ + struct r5conf *conf = mddev->private; + + if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { + + if (mddev->delta_disks > 0) { + md_set_array_sectors(mddev, raid5_size(mddev, 0, 0)); + set_capacity(mddev->gendisk, mddev->array_sectors); + revalidate_disk(mddev->gendisk); + } else { + int d; + spin_lock_irq(&conf->device_lock); + mddev->degraded = calc_degraded(conf); + spin_unlock_irq(&conf->device_lock); + for (d = conf->raid_disks ; + d < conf->raid_disks - mddev->delta_disks; + d++) { + struct md_rdev *rdev = conf->disks[d].rdev; + if (rdev) + clear_bit(In_sync, &rdev->flags); + rdev = conf->disks[d].replacement; + if (rdev) + clear_bit(In_sync, &rdev->flags); + } + } + mddev->layout = conf->algorithm; + mddev->chunk_sectors = conf->chunk_sectors; + mddev->reshape_position = MaxSector; + mddev->delta_disks = 0; + mddev->reshape_backwards = 0; + } +} + +static void raid5_quiesce(struct mddev *mddev, int state) +{ + struct r5conf *conf = mddev->private; + + switch(state) { + case 2: /* resume for a suspend */ + wake_up(&conf->wait_for_overlap); + break; + + case 1: /* stop all writes */ + lock_all_device_hash_locks_irq(conf); + /* '2' tells resync/reshape to pause so that all + * active stripes can drain + */ + conf->quiesce = 2; + wait_event_cmd(conf->wait_for_stripe, + atomic_read(&conf->active_stripes) == 0 && + atomic_read(&conf->active_aligned_reads) == 0, + unlock_all_device_hash_locks_irq(conf), + lock_all_device_hash_locks_irq(conf)); + conf->quiesce = 1; + unlock_all_device_hash_locks_irq(conf); + /* allow reshape to continue */ + wake_up(&conf->wait_for_overlap); + break; + + case 0: /* re-enable writes */ + lock_all_device_hash_locks_irq(conf); + conf->quiesce = 0; + wake_up(&conf->wait_for_stripe); + wake_up(&conf->wait_for_overlap); + unlock_all_device_hash_locks_irq(conf); + break; + } +} + +static void *raid45_takeover_raid0(struct mddev *mddev, int level) +{ + struct r0conf *raid0_conf = mddev->private; + sector_t sectors; + + /* for raid0 takeover only one zone is supported */ + if (raid0_conf->nr_strip_zones > 1) { + printk(KERN_ERR "md/raid:%s: cannot takeover raid0 with more than one zone.\n", + mdname(mddev)); + return ERR_PTR(-EINVAL); + } + + sectors = raid0_conf->strip_zone[0].zone_end; + sector_div(sectors, raid0_conf->strip_zone[0].nb_dev); + mddev->dev_sectors = sectors; + mddev->new_level = level; + mddev->new_layout = ALGORITHM_PARITY_N; + mddev->new_chunk_sectors = mddev->chunk_sectors; + mddev->raid_disks += 1; + mddev->delta_disks = 1; + /* make sure it will be not marked as dirty */ + mddev->recovery_cp = MaxSector; + + return setup_conf(mddev); +} + +static void *raid5_takeover_raid1(struct mddev *mddev) +{ + int chunksect; + + if (mddev->raid_disks != 2 || + mddev->degraded > 1) + return ERR_PTR(-EINVAL); + + /* Should check if there are write-behind devices? */ + + chunksect = 64*2; /* 64K by default */ + + /* The array must be an exact multiple of chunksize */ + while (chunksect && (mddev->array_sectors & (chunksect-1))) + chunksect >>= 1; + + if ((chunksect<<9) < STRIPE_SIZE) + /* array size does not allow a suitable chunk size */ + return ERR_PTR(-EINVAL); + + mddev->new_level = 5; + mddev->new_layout = ALGORITHM_LEFT_SYMMETRIC; + mddev->new_chunk_sectors = chunksect; + + return setup_conf(mddev); +} + +static void *raid5_takeover_raid6(struct mddev *mddev) +{ + int new_layout; + + switch (mddev->layout) { + case ALGORITHM_LEFT_ASYMMETRIC_6: + new_layout = ALGORITHM_LEFT_ASYMMETRIC; + break; + case ALGORITHM_RIGHT_ASYMMETRIC_6: + new_layout = ALGORITHM_RIGHT_ASYMMETRIC; + break; + case ALGORITHM_LEFT_SYMMETRIC_6: + new_layout = ALGORITHM_LEFT_SYMMETRIC; + break; + case ALGORITHM_RIGHT_SYMMETRIC_6: + new_layout = ALGORITHM_RIGHT_SYMMETRIC; + break; + case ALGORITHM_PARITY_0_6: + new_layout = ALGORITHM_PARITY_0; + break; + case ALGORITHM_PARITY_N: + new_layout = ALGORITHM_PARITY_N; + break; + default: + return ERR_PTR(-EINVAL); + } + mddev->new_level = 5; + mddev->new_layout = new_layout; + mddev->delta_disks = -1; + mddev->raid_disks -= 1; + return setup_conf(mddev); +} + +static int raid5_check_reshape(struct mddev *mddev) +{ + /* For a 2-drive array, the layout and chunk size can be changed + * immediately as not restriping is needed. + * For larger arrays we record the new value - after validation + * to be used by a reshape pass. + */ + struct r5conf *conf = mddev->private; + int new_chunk = mddev->new_chunk_sectors; + + if (mddev->new_layout >= 0 && !algorithm_valid_raid5(mddev->new_layout)) + return -EINVAL; + if (new_chunk > 0) { + if (!is_power_of_2(new_chunk)) + return -EINVAL; + if (new_chunk < (PAGE_SIZE>>9)) + return -EINVAL; + if (mddev->array_sectors & (new_chunk-1)) + /* not factor of array size */ + return -EINVAL; + } + + /* They look valid */ + + if (mddev->raid_disks == 2) { + /* can make the change immediately */ + if (mddev->new_layout >= 0) { + conf->algorithm = mddev->new_layout; + mddev->layout = mddev->new_layout; + } + if (new_chunk > 0) { + conf->chunk_sectors = new_chunk ; + mddev->chunk_sectors = new_chunk; + } + set_bit(MD_CHANGE_DEVS, &mddev->flags); + md_wakeup_thread(mddev->thread); + } + return check_reshape(mddev); +} + +static int raid6_check_reshape(struct mddev *mddev) +{ + int new_chunk = mddev->new_chunk_sectors; + + if (mddev->new_layout >= 0 && !algorithm_valid_raid6(mddev->new_layout)) + return -EINVAL; + if (new_chunk > 0) { + if (!is_power_of_2(new_chunk)) + return -EINVAL; + if (new_chunk < (PAGE_SIZE >> 9)) + return -EINVAL; + if (mddev->array_sectors & (new_chunk-1)) + /* not factor of array size */ + return -EINVAL; + } + + /* They look valid */ + return check_reshape(mddev); +} + +static void *raid5_takeover(struct mddev *mddev) +{ + /* raid5 can take over: + * raid0 - if there is only one strip zone - make it a raid4 layout + * raid1 - if there are two drives. We need to know the chunk size + * raid4 - trivial - just use a raid4 layout. + * raid6 - Providing it is a *_6 layout + */ + if (mddev->level == 0) + return raid45_takeover_raid0(mddev, 5); + if (mddev->level == 1) + return raid5_takeover_raid1(mddev); + if (mddev->level == 4) { + mddev->new_layout = ALGORITHM_PARITY_N; + mddev->new_level = 5; + return setup_conf(mddev); + } + if (mddev->level == 6) + return raid5_takeover_raid6(mddev); + + return ERR_PTR(-EINVAL); +} + +static void *raid4_takeover(struct mddev *mddev) +{ + /* raid4 can take over: + * raid0 - if there is only one strip zone + * raid5 - if layout is right + */ + if (mddev->level == 0) + return raid45_takeover_raid0(mddev, 4); + if (mddev->level == 5 && + mddev->layout == ALGORITHM_PARITY_N) { + mddev->new_layout = 0; + mddev->new_level = 4; + return setup_conf(mddev); + } + return ERR_PTR(-EINVAL); +} + +static struct md_personality raid5_personality; + +static void *raid6_takeover(struct mddev *mddev) +{ + /* Currently can only take over a raid5. We map the + * personality to an equivalent raid6 personality + * with the Q block at the end. + */ + int new_layout; + + if (mddev->pers != &raid5_personality) + return ERR_PTR(-EINVAL); + if (mddev->degraded > 1) + return ERR_PTR(-EINVAL); + if (mddev->raid_disks > 253) + return ERR_PTR(-EINVAL); + if (mddev->raid_disks < 3) + return ERR_PTR(-EINVAL); + + switch (mddev->layout) { + case ALGORITHM_LEFT_ASYMMETRIC: + new_layout = ALGORITHM_LEFT_ASYMMETRIC_6; + break; + case ALGORITHM_RIGHT_ASYMMETRIC: + new_layout = ALGORITHM_RIGHT_ASYMMETRIC_6; + break; + case ALGORITHM_LEFT_SYMMETRIC: + new_layout = ALGORITHM_LEFT_SYMMETRIC_6; + break; + case ALGORITHM_RIGHT_SYMMETRIC: + new_layout = ALGORITHM_RIGHT_SYMMETRIC_6; + break; + case ALGORITHM_PARITY_0: + new_layout = ALGORITHM_PARITY_0_6; + break; + case ALGORITHM_PARITY_N: + new_layout = ALGORITHM_PARITY_N; + break; + default: + return ERR_PTR(-EINVAL); + } + mddev->new_level = 6; + mddev->new_layout = new_layout; + mddev->delta_disks = 1; + mddev->raid_disks += 1; + return setup_conf(mddev); +} + +static struct md_personality raid6_personality = +{ + .name = "raid6", + .level = 6, + .owner = THIS_MODULE, + .make_request = make_request, + .run = run, + .stop = stop, + .status = status, + .error_handler = error, + .hot_add_disk = raid5_add_disk, + .hot_remove_disk= raid5_remove_disk, + .spare_active = raid5_spare_active, + .sync_request = sync_request, + .resize = raid5_resize, + .size = raid5_size, + .check_reshape = raid6_check_reshape, + .start_reshape = raid5_start_reshape, + .finish_reshape = raid5_finish_reshape, + .quiesce = raid5_quiesce, + .takeover = raid6_takeover, +}; +static struct md_personality raid5_personality = +{ + .name = "raid5", + .level = 5, + .owner = THIS_MODULE, + .make_request = make_request, + .run = run, + .stop = stop, + .status = status, + .error_handler = error, + .hot_add_disk = raid5_add_disk, + .hot_remove_disk= raid5_remove_disk, + .spare_active = raid5_spare_active, + .sync_request = sync_request, + .resize = raid5_resize, + .size = raid5_size, + .check_reshape = raid5_check_reshape, + .start_reshape = raid5_start_reshape, + .finish_reshape = raid5_finish_reshape, + .quiesce = raid5_quiesce, + .takeover = raid5_takeover, +}; + +static struct md_personality raid4_personality = +{ + .name = "raid4", + .level = 4, + .owner = THIS_MODULE, + .make_request = make_request, + .run = run, + .stop = stop, + .status = status, + .error_handler = error, + .hot_add_disk = raid5_add_disk, + .hot_remove_disk= raid5_remove_disk, + .spare_active = raid5_spare_active, + .sync_request = sync_request, + .resize = raid5_resize, + .size = raid5_size, + .check_reshape = raid5_check_reshape, + .start_reshape = raid5_start_reshape, + .finish_reshape = raid5_finish_reshape, + .quiesce = raid5_quiesce, + .takeover = raid4_takeover, +}; + +static int __init raid5_init(void) +{ + raid5_wq = alloc_workqueue("raid5wq", + WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE|WQ_SYSFS, 0); + if (!raid5_wq) + return -ENOMEM; + register_md_personality(&raid6_personality); + register_md_personality(&raid5_personality); + register_md_personality(&raid4_personality); + return 0; +} + +static void raid5_exit(void) +{ + unregister_md_personality(&raid6_personality); + unregister_md_personality(&raid5_personality); + unregister_md_personality(&raid4_personality); + destroy_workqueue(raid5_wq); +} + +module_init(raid5_init); +module_exit(raid5_exit); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("RAID4/5/6 (striping with parity) personality for MD"); +MODULE_ALIAS("md-personality-4"); /* RAID5 */ +MODULE_ALIAS("md-raid5"); +MODULE_ALIAS("md-raid4"); +MODULE_ALIAS("md-level-5"); +MODULE_ALIAS("md-level-4"); +MODULE_ALIAS("md-personality-8"); /* RAID6 */ +MODULE_ALIAS("md-raid6"); +MODULE_ALIAS("md-level-6"); + +/* This used to be two separate modules, they were: */ +MODULE_ALIAS("raid5"); +MODULE_ALIAS("raid6"); diff -Nur linux-3.18.9.orig/drivers/md/raid5.h linux-3.18.9/drivers/md/raid5.h --- linux-3.18.9.orig/drivers/md/raid5.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/md/raid5.h 2015-03-15 16:03:03.724094875 -0500 @@ -457,6 +457,7 @@ 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 */ void *scribble; /* space for constructing buffer * lists and performing address diff -Nur linux-3.18.9.orig/drivers/misc/hwlat_detector.c linux-3.18.9/drivers/misc/hwlat_detector.c --- linux-3.18.9.orig/drivers/misc/hwlat_detector.c 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/drivers/misc/hwlat_detector.c 2015-03-15 16:03:03.724094875 -0500 @@ -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-3.18.9.orig/drivers/misc/Kconfig linux-3.18.9/drivers/misc/Kconfig --- linux-3.18.9.orig/drivers/misc/Kconfig 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/misc/Kconfig 2015-03-15 16:03:03.724094875 -0500 @@ -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-3.18.9.orig/drivers/misc/Makefile linux-3.18.9/drivers/misc/Makefile --- linux-3.18.9.orig/drivers/misc/Makefile 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/misc/Makefile 2015-03-15 16:03:03.724094875 -0500 @@ -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-3.18.9.orig/drivers/mmc/host/mmci.c linux-3.18.9/drivers/mmc/host/mmci.c --- linux-3.18.9.orig/drivers/mmc/host/mmci.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/mmc/host/mmci.c 2015-03-15 16:03:03.732094876 -0500 @@ -1153,15 +1153,12 @@ 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; @@ -1201,8 +1198,6 @@ 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-3.18.9.orig/drivers/net/ethernet/3com/3c59x.c linux-3.18.9/drivers/net/ethernet/3com/3c59x.c --- linux-3.18.9.orig/drivers/net/ethernet/3com/3c59x.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/net/ethernet/3com/3c59x.c 2015-03-15 16:03:03.732094876 -0500 @@ -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-3.18.9.orig/drivers/net/ethernet/atheros/atl1c/atl1c_main.c linux-3.18.9/drivers/net/ethernet/atheros/atl1c/atl1c_main.c --- linux-3.18.9.orig/drivers/net/ethernet/atheros/atl1c/atl1c_main.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/net/ethernet/atheros/atl1c/atl1c_main.c 2015-03-15 16:03:03.732094876 -0500 @@ -2213,11 +2213,7 @@ } 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-3.18.9.orig/drivers/net/ethernet/atheros/atl1e/atl1e_main.c linux-3.18.9/drivers/net/ethernet/atheros/atl1e/atl1e_main.c --- linux-3.18.9.orig/drivers/net/ethernet/atheros/atl1e/atl1e_main.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/net/ethernet/atheros/atl1e/atl1e_main.c 2015-03-15 16:03:03.732094876 -0500 @@ -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-3.18.9.orig/drivers/net/ethernet/chelsio/cxgb/sge.c linux-3.18.9/drivers/net/ethernet/chelsio/cxgb/sge.c --- linux-3.18.9.orig/drivers/net/ethernet/chelsio/cxgb/sge.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/net/ethernet/chelsio/cxgb/sge.c 2015-03-15 16:03:03.732094876 -0500 @@ -1663,8 +1663,7 @@ 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-3.18.9.orig/drivers/net/ethernet/freescale/gianfar.c linux-3.18.9/drivers/net/ethernet/freescale/gianfar.c --- linux-3.18.9.orig/drivers/net/ethernet/freescale/gianfar.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/net/ethernet/freescale/gianfar.c 2015-03-15 16:03:03.732094876 -0500 @@ -1483,7 +1483,7 @@ if (netif_running(ndev)) { - local_irq_save(flags); + local_irq_save_nort(flags); lock_tx_qs(priv); gfar_halt_nodisable(priv); @@ -1499,7 +1499,7 @@ gfar_write(®s->maccfg1, tempval); unlock_tx_qs(priv); - local_irq_restore(flags); + local_irq_restore_nort(flags); disable_napi(priv); @@ -1541,7 +1541,7 @@ /* 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); @@ -1551,7 +1551,7 @@ gfar_start(priv); unlock_tx_qs(priv); - local_irq_restore(flags); + local_irq_restore_nort(flags); netif_device_attach(ndev); @@ -3307,14 +3307,14 @@ 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-3.18.9.orig/drivers/net/ethernet/neterion/s2io.c linux-3.18.9/drivers/net/ethernet/neterion/s2io.c --- linux-3.18.9.orig/drivers/net/ethernet/neterion/s2io.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/net/ethernet/neterion/s2io.c 2015-03-15 16:03:03.736094876 -0500 @@ -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-3.18.9.orig/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c linux-3.18.9/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c --- linux-3.18.9.orig/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c 2015-03-15 16:03:03.736094876 -0500 @@ -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-3.18.9.orig/drivers/net/ethernet/realtek/8139too.c linux-3.18.9/drivers/net/ethernet/realtek/8139too.c --- linux-3.18.9.orig/drivers/net/ethernet/realtek/8139too.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/net/ethernet/realtek/8139too.c 2015-03-15 16:03:03.736094876 -0500 @@ -2215,7 +2215,7 @@ 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-3.18.9.orig/drivers/net/ethernet/tehuti/tehuti.c linux-3.18.9/drivers/net/ethernet/tehuti/tehuti.c --- linux-3.18.9.orig/drivers/net/ethernet/tehuti/tehuti.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/net/ethernet/tehuti/tehuti.c 2015-03-15 16:03:03.744094876 -0500 @@ -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-3.18.9.orig/drivers/net/rionet.c linux-3.18.9/drivers/net/rionet.c --- linux-3.18.9.orig/drivers/net/rionet.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/net/rionet.c 2015-03-15 16:03:03.744094876 -0500 @@ -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-3.18.9.orig/drivers/net/wireless/orinoco/orinoco_usb.c linux-3.18.9/drivers/net/wireless/orinoco/orinoco_usb.c --- linux-3.18.9.orig/drivers/net/wireless/orinoco/orinoco_usb.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/net/wireless/orinoco/orinoco_usb.c 2015-03-15 16:03:03.744094876 -0500 @@ -699,7 +699,7 @@ 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-3.18.9.orig/drivers/pci/access.c linux-3.18.9/drivers/pci/access.c --- linux-3.18.9.orig/drivers/pci/access.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/pci/access.c 2015-03-15 16:03:03.744094876 -0500 @@ -434,7 +434,7 @@ 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-3.18.9.orig/drivers/scsi/fcoe/fcoe.c linux-3.18.9/drivers/scsi/fcoe/fcoe.c --- linux-3.18.9.orig/drivers/scsi/fcoe/fcoe.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/scsi/fcoe/fcoe.c 2015-03-15 16:03:03.744094876 -0500 @@ -1286,7 +1286,7 @@ 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); @@ -1342,7 +1342,7 @@ 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 @@ -1566,11 +1566,11 @@ 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; } @@ -1768,11 +1768,11 @@ 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; } @@ -1848,13 +1848,13 @@ 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-3.18.9.orig/drivers/scsi/fcoe/fcoe_ctlr.c linux-3.18.9/drivers/scsi/fcoe/fcoe_ctlr.c --- linux-3.18.9.orig/drivers/scsi/fcoe/fcoe_ctlr.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/scsi/fcoe/fcoe_ctlr.c 2015-03-15 16:03:03.744094876 -0500 @@ -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-3.18.9.orig/drivers/scsi/libfc/fc_exch.c linux-3.18.9/drivers/scsi/libfc/fc_exch.c --- linux-3.18.9.orig/drivers/scsi/libfc/fc_exch.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/scsi/libfc/fc_exch.c 2015-03-15 16:03:03.744094876 -0500 @@ -816,10 +816,10 @@ } 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-3.18.9.orig/drivers/scsi/libsas/sas_ata.c linux-3.18.9/drivers/scsi/libsas/sas_ata.c --- linux-3.18.9.orig/drivers/scsi/libsas/sas_ata.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/scsi/libsas/sas_ata.c 2015-03-15 16:03:03.744094876 -0500 @@ -191,7 +191,7 @@ /* 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 */ @@ -261,7 +261,7 @@ out: spin_lock(ap->lock); - local_irq_restore(flags); + local_irq_restore_nort(flags); return ret; } diff -Nur linux-3.18.9.orig/drivers/scsi/qla2xxx/qla_inline.h linux-3.18.9/drivers/scsi/qla2xxx/qla_inline.h --- linux-3.18.9.orig/drivers/scsi/qla2xxx/qla_inline.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/scsi/qla2xxx/qla_inline.h 2015-03-15 16:03:03.744094876 -0500 @@ -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-3.18.9.orig/drivers/tty/serial/8250/8250_core.c linux-3.18.9/drivers/tty/serial/8250/8250_core.c --- linux-3.18.9.orig/drivers/tty/serial/8250/8250_core.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/tty/serial/8250/8250_core.c 2015-03-15 16:03:03.784094876 -0500 @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #ifdef CONFIG_SPARC @@ -81,7 +82,16 @@ #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) @@ -3198,7 +3208,7 @@ serial8250_rpm_get(up); - if (port->sysrq || oops_in_progress) + if (port->sysrq || oops_in_progress || in_kdb_printk()) locked = spin_trylock_irqsave(&port->lock, flags); else spin_lock_irqsave(&port->lock, flags); diff -Nur linux-3.18.9.orig/drivers/tty/serial/amba-pl011.c linux-3.18.9/drivers/tty/serial/amba-pl011.c --- linux-3.18.9.orig/drivers/tty/serial/amba-pl011.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/tty/serial/amba-pl011.c 2015-03-15 16:03:03.784094876 -0500 @@ -1935,13 +1935,19 @@ 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 @@ -1963,8 +1969,7 @@ 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-3.18.9.orig/drivers/tty/serial/omap-serial.c linux-3.18.9/drivers/tty/serial/omap-serial.c --- linux-3.18.9.orig/drivers/tty/serial/omap-serial.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/tty/serial/omap-serial.c 2015-03-15 16:03:03.784094876 -0500 @@ -1270,13 +1270,10 @@ 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 @@ -1305,8 +1302,7 @@ 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-3.18.9.orig/drivers/usb/core/hcd.c linux-3.18.9/drivers/usb/core/hcd.c --- linux-3.18.9.orig/drivers/usb/core/hcd.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/usb/core/hcd.c 2015-03-15 16:03:03.784094876 -0500 @@ -1681,9 +1681,9 @@ * 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-3.18.9.orig/drivers/usb/gadget/function/f_fs.c linux-3.18.9/drivers/usb/gadget/function/f_fs.c --- linux-3.18.9.orig/drivers/usb/gadget/function/f_fs.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/usb/gadget/function/f_fs.c 2015-03-15 16:03:03.784094876 -0500 @@ -1428,7 +1428,7 @@ 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-3.18.9.orig/drivers/usb/gadget/legacy/inode.c linux-3.18.9/drivers/usb/gadget/legacy/inode.c --- linux-3.18.9.orig/drivers/usb/gadget/legacy/inode.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/drivers/usb/gadget/legacy/inode.c 2015-03-15 16:03:03.784094876 -0500 @@ -339,7 +339,7 @@ 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)) { @@ -348,7 +348,7 @@ 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-3.18.9.orig/fs/aio.c linux-3.18.9/fs/aio.c --- linux-3.18.9.orig/fs/aio.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/fs/aio.c 2015-03-15 16:03:03.788094876 -0500 @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -110,7 +111,7 @@ 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 @@ -226,6 +227,7 @@ .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."); @@ -505,9 +507,9 @@ return cancel(kiocb); } -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); @@ -526,8 +528,8 @@ if (ctx->requests_done) complete(ctx->requests_done); - INIT_WORK(&ctx->free_work, free_ioctx); - schedule_work(&ctx->free_work); + INIT_SWORK(&ctx->free_work, free_ioctx); + swork_queue(&ctx->free_work); } /* @@ -535,9 +537,9 @@ * 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 kiocb *req; spin_lock_irq(&ctx->ctx_lock); @@ -556,6 +558,14 @@ 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-3.18.9.orig/fs/autofs4/autofs_i.h linux-3.18.9/fs/autofs4/autofs_i.h --- linux-3.18.9.orig/fs/autofs4/autofs_i.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/fs/autofs4/autofs_i.h 2015-03-15 16:03:03.788094876 -0500 @@ -34,6 +34,7 @@ #include #include #include +#include #include #include diff -Nur linux-3.18.9.orig/fs/autofs4/expire.c linux-3.18.9/fs/autofs4/expire.c --- linux-3.18.9.orig/fs/autofs4/expire.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/fs/autofs4/expire.c 2015-03-15 16:03:03.788094876 -0500 @@ -151,7 +151,7 @@ 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-3.18.9.orig/fs/buffer.c linux-3.18.9/fs/buffer.c --- linux-3.18.9.orig/fs/buffer.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/fs/buffer.c 2015-03-15 16:03:03.788094876 -0500 @@ -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-3.18.9.orig/fs/dcache.c linux-3.18.9/fs/dcache.c --- linux-3.18.9.orig/fs/dcache.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/fs/dcache.c 2015-03-15 16:03:03.788094876 -0500 @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -552,7 +553,7 @@ failed: spin_unlock(&dentry->d_lock); - cpu_relax(); + cpu_chill(); return dentry; /* try again with same dentry */ } @@ -2285,7 +2286,7 @@ 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-3.18.9.orig/fs/eventpoll.c linux-3.18.9/fs/eventpoll.c --- linux-3.18.9.orig/fs/eventpoll.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/fs/eventpoll.c 2015-03-15 16:03:03.788094876 -0500 @@ -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-3.18.9.orig/fs/exec.c linux-3.18.9/fs/exec.c --- linux-3.18.9.orig/fs/exec.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/fs/exec.c 2015-03-15 16:03:03.788094876 -0500 @@ -841,12 +841,14 @@ } } 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-3.18.9.orig/fs/jbd/checkpoint.c linux-3.18.9/fs/jbd/checkpoint.c --- linux-3.18.9.orig/fs/jbd/checkpoint.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/fs/jbd/checkpoint.c 2015-03-15 16:03:03.788094876 -0500 @@ -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-3.18.9.orig/fs/jbd2/checkpoint.c linux-3.18.9/fs/jbd2/checkpoint.c --- linux-3.18.9.orig/fs/jbd2/checkpoint.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/fs/jbd2/checkpoint.c 2015-03-15 16:03:03.788094876 -0500 @@ -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-3.18.9.orig/fs/namespace.c linux-3.18.9/fs/namespace.c --- linux-3.18.9.orig/fs/namespace.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/fs/namespace.c 2015-03-15 16:03:03.788094876 -0500 @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include /* init_rootfs */ @@ -344,8 +345,11 @@ * 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-3.18.9.orig/fs/ntfs/aops.c linux-3.18.9/fs/ntfs/aops.c --- linux-3.18.9.orig/fs/ntfs/aops.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/fs/ntfs/aops.c 2015-03-15 16:03:03.788094876 -0500 @@ -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-3.18.9.orig/fs/timerfd.c linux-3.18.9/fs/timerfd.c --- linux-3.18.9.orig/fs/timerfd.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/fs/timerfd.c 2015-03-15 16:03:03.788094876 -0500 @@ -449,7 +449,10 @@ 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-3.18.9.orig/include/acpi/platform/aclinux.h linux-3.18.9/include/acpi/platform/aclinux.h --- linux-3.18.9.orig/include/acpi/platform/aclinux.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/acpi/platform/aclinux.h 2015-03-15 16:03:03.788094876 -0500 @@ -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-3.18.9.orig/include/asm-generic/bug.h linux-3.18.9/include/asm-generic/bug.h --- linux-3.18.9.orig/include/asm-generic/bug.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/asm-generic/bug.h 2015-03-15 16:03:03.792094875 -0500 @@ -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-3.18.9.orig/include/linux/blkdev.h linux-3.18.9/include/linux/blkdev.h --- linux-3.18.9.orig/include/linux/blkdev.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/blkdev.h 2015-03-15 16:03:03.792094875 -0500 @@ -101,6 +101,7 @@ struct list_head queuelist; union { struct call_single_data csd; + struct work_struct work; unsigned long fifo_time; }; @@ -478,7 +479,7 @@ 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-3.18.9.orig/include/linux/blk-mq.h linux-3.18.9/include/linux/blk-mq.h --- linux-3.18.9.orig/include/linux/blk-mq.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/blk-mq.h 2015-03-15 16:03:03.792094875 -0500 @@ -169,6 +169,7 @@ 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); void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, int error); diff -Nur linux-3.18.9.orig/include/linux/bottom_half.h linux-3.18.9/include/linux/bottom_half.h --- linux-3.18.9.orig/include/linux/bottom_half.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/bottom_half.h 2015-03-15 16:03:03.792094875 -0500 @@ -4,6 +4,17 @@ #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); +extern void local_bh_enable_ip(unsigned long ip); +extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); +extern void __local_bh_enable_ip(unsigned long ip, unsigned int cnt); + +#else + #ifdef CONFIG_TRACE_IRQFLAGS extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); #else @@ -31,5 +42,6 @@ { __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); } +#endif #endif /* _LINUX_BH_H */ diff -Nur linux-3.18.9.orig/include/linux/buffer_head.h linux-3.18.9/include/linux/buffer_head.h --- linux-3.18.9.orig/include/linux/buffer_head.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/buffer_head.h 2015-03-15 16:03:03.792094875 -0500 @@ -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-3.18.9.orig/include/linux/cgroup.h linux-3.18.9/include/linux/cgroup.h --- linux-3.18.9.orig/include/linux/cgroup.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/cgroup.h 2015-03-15 16:03:03.792094875 -0500 @@ -22,6 +22,7 @@ #include #include #include +#include #ifdef CONFIG_CGROUPS @@ -91,6 +92,7 @@ /* percpu_ref killing and RCU release */ struct rcu_head rcu_head; struct work_struct destroy_work; + struct swork_event destroy_swork; }; /* bits in struct cgroup_subsys_state flags field */ diff -Nur linux-3.18.9.orig/include/linux/completion.h linux-3.18.9/include/linux/completion.h --- linux-3.18.9.orig/include/linux/completion.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/completion.h 2015-03-15 16:03:03.792094875 -0500 @@ -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-3.18.9.orig/include/linux/cpu.h linux-3.18.9/include/linux/cpu.h --- linux-3.18.9.orig/include/linux/cpu.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/cpu.h 2015-03-15 16:03:03.792094875 -0500 @@ -217,6 +217,8 @@ 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) @@ -235,6 +237,8 @@ #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-3.18.9.orig/include/linux/delay.h linux-3.18.9/include/linux/delay.h --- linux-3.18.9.orig/include/linux/delay.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/delay.h 2015-03-15 16:03:03.792094875 -0500 @@ -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-3.18.9.orig/include/linux/ftrace_event.h linux-3.18.9/include/linux/ftrace_event.h --- linux-3.18.9.orig/include/linux/ftrace_event.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/ftrace_event.h 2015-03-15 16:03:03.804094874 -0500 @@ -61,6 +61,9 @@ 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-3.18.9.orig/include/linux/highmem.h linux-3.18.9/include/linux/highmem.h --- linux-3.18.9.orig/include/linux/highmem.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/highmem.h 2015-03-15 16:03:03.804094874 -0500 @@ -7,6 +7,7 @@ #include #include #include +#include #include @@ -85,32 +86,51 @@ #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-3.18.9.orig/include/linux/hrtimer.h linux-3.18.9/include/linux/hrtimer.h --- linux-3.18.9.orig/include/linux/hrtimer.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/hrtimer.h 2015-03-15 16:03:03.804094874 -0500 @@ -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; @@ -192,6 +198,9 @@ 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]; }; @@ -379,6 +388,13 @@ 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-3.18.9.orig/include/linux/idr.h linux-3.18.9/include/linux/idr.h --- linux-3.18.9.orig/include/linux/idr.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/idr.h 2015-03-15 16:03:03.804094874 -0500 @@ -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-3.18.9.orig/include/linux/init_task.h linux-3.18.9/include/linux/init_task.h --- linux-3.18.9.orig/include/linux/init_task.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/init_task.h 2015-03-15 16:03:03.804094874 -0500 @@ -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 @@ -219,6 +226,7 @@ .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-3.18.9.orig/include/linux/interrupt.h linux-3.18.9/include/linux/interrupt.h --- linux-3.18.9.orig/include/linux/interrupt.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/interrupt.h 2015-03-15 16:03:03.804094874 -0500 @@ -57,6 +57,7 @@ * IRQF_NO_THREAD - Interrupt cannot be threaded * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device * resume time. + * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT) */ #define IRQF_DISABLED 0x00000020 #define IRQF_SHARED 0x00000080 @@ -70,6 +71,7 @@ #define IRQF_FORCE_RESUME 0x00008000 #define IRQF_NO_THREAD 0x00010000 #define IRQF_EARLY_RESUME 0x00020000 +#define IRQF_NO_SOFTIRQ_CALL 0x00080000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) @@ -180,7 +182,7 @@ #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); @@ -210,6 +212,7 @@ 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); }; @@ -358,9 +361,13 @@ #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 @@ -416,9 +423,10 @@ 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 @@ -427,6 +435,9 @@ __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); @@ -434,6 +445,7 @@ 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); @@ -455,8 +467,9 @@ 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. @@ -481,27 +494,36 @@ 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 @@ -550,17 +572,8 @@ smp_mb(); } -static inline void tasklet_enable(struct tasklet_struct *t) -{ - smp_mb__before_atomic(); - atomic_dec(&t->count); -} - -static inline void tasklet_hi_enable(struct tasklet_struct *t) -{ - smp_mb__before_atomic(); - atomic_dec(&t->count); -} +extern void tasklet_enable(struct tasklet_struct *t); +extern void tasklet_hi_enable(struct tasklet_struct *t); extern void tasklet_kill(struct tasklet_struct *t); extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); @@ -592,6 +605,12 @@ 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-3.18.9.orig/include/linux/irqdesc.h linux-3.18.9/include/linux/irqdesc.h --- linux-3.18.9.orig/include/linux/irqdesc.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/irqdesc.h 2015-03-15 16:03:03.804094874 -0500 @@ -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-3.18.9.orig/include/linux/irqflags.h linux-3.18.9/include/linux/irqflags.h --- linux-3.18.9.orig/include/linux/irqflags.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/irqflags.h 2015-03-15 16:03:03.804094874 -0500 @@ -25,8 +25,6 @@ # define trace_softirqs_enabled(p) ((p)->softirqs_enabled) # define trace_hardirq_enter() do { current->hardirq_context++; } while (0) # define trace_hardirq_exit() do { current->hardirq_context--; } while (0) -# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) -# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1, #else # define trace_hardirqs_on() do { } while (0) @@ -39,9 +37,15 @@ # define trace_softirqs_enabled(p) 0 # define trace_hardirq_enter() do { } while (0) # define trace_hardirq_exit() do { } while (0) +# define INIT_TRACE_IRQFLAGS +#endif + +#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL) +# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) +# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) +#else # define lockdep_softirq_enter() do { } while (0) # define lockdep_softirq_exit() do { } while (0) -# define INIT_TRACE_IRQFLAGS #endif #if defined(CONFIG_IRQSOFF_TRACER) || \ @@ -147,4 +151,23 @@ #endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */ +/* + * local_irq* variants depending on RT/!RT + */ +#ifdef CONFIG_PREEMPT_RT_FULL +# define local_irq_disable_nort() do { } while (0) +# define local_irq_enable_nort() do { } while (0) +# define local_irq_save_nort(flags) 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-3.18.9.orig/include/linux/irq.h linux-3.18.9/include/linux/irq.h --- linux-3.18.9.orig/include/linux/irq.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/irq.h 2015-03-15 16:03:03.804094874 -0500 @@ -73,6 +73,7 @@ * 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, @@ -98,13 +99,14 @@ 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-3.18.9.orig/include/linux/irq_work.h linux-3.18.9/include/linux/irq_work.h --- linux-3.18.9.orig/include/linux/irq_work.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/irq_work.h 2015-03-15 16:03:03.804094874 -0500 @@ -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; diff -Nur linux-3.18.9.orig/include/linux/jbd_common.h linux-3.18.9/include/linux/jbd_common.h --- linux-3.18.9.orig/include/linux/jbd_common.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/jbd_common.h 2015-03-15 16:03:03.804094874 -0500 @@ -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-3.18.9.orig/include/linux/jump_label.h linux-3.18.9/include/linux/jump_label.h --- linux-3.18.9.orig/include/linux/jump_label.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/jump_label.h 2015-03-15 16:03:03.804094874 -0500 @@ -55,7 +55,8 @@ "%s used before call to jump_label_init", \ __func__) -#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) +#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) && \ + !defined(CONFIG_PREEMPT_BASE) struct static_key { atomic_t enabled; diff -Nur linux-3.18.9.orig/include/linux/kdb.h linux-3.18.9/include/linux/kdb.h --- linux-3.18.9.orig/include/linux/kdb.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/kdb.h 2015-03-15 16:03:03.804094874 -0500 @@ -116,7 +116,7 @@ extern __printf(1, 0) int vkdb_printf(const char *fmt, va_list args); 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 */ @@ -151,6 +151,7 @@ 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-3.18.9.orig/include/linux/kernel.h linux-3.18.9/include/linux/kernel.h --- linux-3.18.9.orig/include/linux/kernel.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/kernel.h 2015-03-15 16:03:03.804094874 -0500 @@ -451,6 +451,7 @@ SYSTEM_HALT, SYSTEM_POWER_OFF, SYSTEM_RESTART, + SYSTEM_SUSPEND, } system_state; #define TAINT_PROPRIETARY_MODULE 0 diff -Nur linux-3.18.9.orig/include/linux/lglock.h linux-3.18.9/include/linux/lglock.h --- linux-3.18.9.orig/include/linux/lglock.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/lglock.h 2015-03-15 16:03:03.804094874 -0500 @@ -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-3.18.9.orig/include/linux/list_bl.h linux-3.18.9/include/linux/list_bl.h --- linux-3.18.9.orig/include/linux/list_bl.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/list_bl.h 2015-03-15 16:03:03.808094874 -0500 @@ -2,6 +2,7 @@ #define _LINUX_LIST_BL_H #include +#include #include /* @@ -32,13 +33,22 @@ struct hlist_bl_head { struct hlist_bl_node *first; +#ifdef CONFIG_PREEMPT_RT_BASE + raw_spinlock_t lock; +#endif }; struct hlist_bl_node { struct hlist_bl_node *next, **pprev; }; -#define INIT_HLIST_BL_HEAD(ptr) \ - ((ptr)->first = NULL) + +static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h) +{ + h->first = NULL; +#ifdef CONFIG_PREEMPT_RT_BASE + raw_spin_lock_init(&h->lock); +#endif +} static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) { @@ -117,12 +127,26 @@ static inline void hlist_bl_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-3.18.9.orig/include/linux/locallock.h linux-3.18.9/include/linux/locallock.h --- linux-3.18.9.orig/include/linux/locallock.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/linux/locallock.h 2015-03-15 16:03:03.808094874 -0500 @@ -0,0 +1,270 @@ +#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) + +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(&__get_cpu_var(lvar)); \ + put_local_var(lvar); \ + } while (0) + +static inline void __local_lock_irq(struct local_irq_lock *lv) +{ + spin_lock_irqsave(&lv->lock, lv->flags); + LL_WARN(lv->owner); + LL_WARN(lv->nestcnt); + lv->owner = current; + lv->nestcnt = 1; +} + +#define local_lock_irq(lvar) \ + do { __local_lock_irq(&get_local_var(lvar)); } while (0) + +#define local_lock_irq_on(lvar, cpu) \ + do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0) + +static inline void __local_unlock_irq(struct local_irq_lock *lv) +{ + LL_WARN(!lv->nestcnt); + LL_WARN(lv->owner != current); + lv->owner = NULL; + lv->nestcnt = 0; + spin_unlock_irq(&lv->lock); +} + +#define local_unlock_irq(lvar) \ + do { \ + __local_unlock_irq(&__get_cpu_var(lvar)); \ + put_local_var(lvar); \ + } while (0) + +#define local_unlock_irq_on(lvar, cpu) \ + do { \ + __local_unlock_irq(&per_cpu(lvar, cpu)); \ + } while (0) + +static inline int __local_lock_irqsave(struct local_irq_lock *lv) +{ + if (lv->owner != current) { + __local_lock_irq(lv); + return 0; + } else { + lv->nestcnt++; + return 1; + } +} + +#define local_lock_irqsave(lvar, _flags) \ + do { \ + if (__local_lock_irqsave(&get_local_var(lvar))) \ + put_local_var(lvar); \ + _flags = __get_cpu_var(lvar).flags; \ + } while (0) + +#define local_lock_irqsave_on(lvar, _flags, cpu) \ + do { \ + __local_lock_irqsave(&per_cpu(lvar, cpu)); \ + _flags = per_cpu(lvar, cpu).flags; \ + } while (0) + +static inline int __local_unlock_irqrestore(struct local_irq_lock *lv, + unsigned long flags) +{ + LL_WARN(!lv->nestcnt); + LL_WARN(lv->owner != current); + if (--lv->nestcnt) + return 0; + + lv->owner = NULL; + spin_unlock_irqrestore(&lv->lock, lv->flags); + return 1; +} + +#define local_unlock_irqrestore(lvar, flags) \ + do { \ + if (__local_unlock_irqrestore(&__get_cpu_var(lvar), flags)) \ + put_local_var(lvar); \ + } while (0) + +#define local_unlock_irqrestore_on(lvar, flags, cpu) \ + do { \ + __local_unlock_irqrestore(&per_cpu(lvar, cpu), flags); \ + } while (0) + +#define local_spin_trylock_irq(lvar, lock) \ + ({ \ + int __locked; \ + local_lock_irq(lvar); \ + __locked = spin_trylock(lock); \ + if (!__locked) \ + local_unlock_irq(lvar); \ + __locked; \ + }) + +#define local_spin_lock_irq(lvar, lock) \ + do { \ + local_lock_irq(lvar); \ + spin_lock(lock); \ + } while (0) + +#define local_spin_unlock_irq(lvar, lock) \ + do { \ + spin_unlock(lock); \ + local_unlock_irq(lvar); \ + } while (0) + +#define local_spin_lock_irqsave(lvar, lock, flags) \ + do { \ + local_lock_irqsave(lvar, flags); \ + spin_lock(lock); \ + } while (0) + +#define local_spin_unlock_irqrestore(lvar, lock, flags) \ + do { \ + spin_unlock(lock); \ + local_unlock_irqrestore(lvar, flags); \ + } while (0) + +#define get_locked_var(lvar, var) \ + (*({ \ + local_lock(lvar); \ + &__get_cpu_var(var); \ + })) + +#define put_locked_var(lvar, var) local_unlock(lvar); + +#define local_lock_cpu(lvar) \ + ({ \ + local_lock(lvar); \ + smp_processor_id(); \ + }) + +#define local_unlock_cpu(lvar) local_unlock(lvar) + +#else /* PREEMPT_RT_BASE */ + +#define DEFINE_LOCAL_IRQ_LOCK(lvar) __typeof__(const int) lvar +#define DECLARE_LOCAL_IRQ_LOCK(lvar) extern __typeof__(const int) lvar + +static inline void local_irq_lock_init(int lvar) { } + +#define local_lock(lvar) preempt_disable() +#define local_unlock(lvar) preempt_enable() +#define local_lock_irq(lvar) local_irq_disable() +#define local_unlock_irq(lvar) local_irq_enable() +#define local_lock_irqsave(lvar, flags) local_irq_save(flags) +#define local_unlock_irqrestore(lvar, flags) local_irq_restore(flags) + +#define local_spin_trylock_irq(lvar, lock) spin_trylock_irq(lock) +#define local_spin_lock_irq(lvar, lock) spin_lock_irq(lock) +#define local_spin_unlock_irq(lvar, lock) spin_unlock_irq(lock) +#define local_spin_lock_irqsave(lvar, lock, flags) \ + spin_lock_irqsave(lock, flags) +#define local_spin_unlock_irqrestore(lvar, lock, flags) \ + spin_unlock_irqrestore(lock, flags) + +#define get_locked_var(lvar, var) get_cpu_var(var) +#define put_locked_var(lvar, var) put_cpu_var(var) + +#define local_lock_cpu(lvar) get_cpu() +#define local_unlock_cpu(lvar) put_cpu() + +#endif + +#endif diff -Nur linux-3.18.9.orig/include/linux/mm_types.h linux-3.18.9/include/linux/mm_types.h --- linux-3.18.9.orig/include/linux/mm_types.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/mm_types.h 2015-03-15 16:03:03.808094874 -0500 @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -454,6 +455,9 @@ bool tlb_flush_pending; #endif struct uprobes_state uprobes_state; +#ifdef CONFIG_PREEMPT_RT_BASE + struct rcu_head delayed_drop; +#endif }; static inline void mm_init_cpumask(struct mm_struct *mm) diff -Nur linux-3.18.9.orig/include/linux/mutex.h linux-3.18.9/include/linux/mutex.h --- linux-3.18.9.orig/include/linux/mutex.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/mutex.h 2015-03-15 16:03:03.808094874 -0500 @@ -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: * @@ -100,13 +111,6 @@ 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) \ @@ -174,6 +178,8 @@ 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-3.18.9.orig/include/linux/mutex_rt.h linux-3.18.9/include/linux/mutex_rt.h --- linux-3.18.9.orig/include/linux/mutex_rt.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/linux/mutex_rt.h 2015-03-15 16:03:03.808094874 -0500 @@ -0,0 +1,84 @@ +#ifndef __LINUX_MUTEX_RT_H +#define __LINUX_MUTEX_RT_H + +#ifndef __LINUX_MUTEX_H +#error "Please include mutex.h" +#endif + +#include + +/* FIXME: Just for __lockfunc */ +#include + +struct mutex { + struct rt_mutex lock; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define __MUTEX_INITIALIZER(mutexname) \ + { \ + .lock = __RT_MUTEX_INITIALIZER(mutexname.lock) \ + __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ + } + +#define DEFINE_MUTEX(mutexname) \ + struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) + +extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key); +extern void __lockfunc _mutex_lock(struct mutex *lock); +extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock); +extern int __lockfunc _mutex_lock_killable(struct mutex *lock); +extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass); +extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock); +extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass); +extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass); +extern int __lockfunc _mutex_trylock(struct mutex *lock); +extern void __lockfunc _mutex_unlock(struct mutex *lock); + +#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->lock) +#define mutex_lock(l) _mutex_lock(l) +#define mutex_lock_interruptible(l) _mutex_lock_interruptible(l) +#define mutex_lock_killable(l) _mutex_lock_killable(l) +#define mutex_trylock(l) _mutex_trylock(l) +#define mutex_unlock(l) _mutex_unlock(l) +#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock) + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define mutex_lock_nested(l, s) _mutex_lock_nested(l, s) +# define mutex_lock_interruptible_nested(l, s) \ + _mutex_lock_interruptible_nested(l, s) +# define mutex_lock_killable_nested(l, s) \ + _mutex_lock_killable_nested(l, s) + +# define mutex_lock_nest_lock(lock, nest_lock) \ +do { \ + typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ + _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ +} while (0) + +#else +# define mutex_lock_nested(l, s) _mutex_lock(l) +# define mutex_lock_interruptible_nested(l, s) \ + _mutex_lock_interruptible(l) +# define mutex_lock_killable_nested(l, s) \ + _mutex_lock_killable(l) +# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) +#endif + +# define mutex_init(mutex) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_init(&(mutex)->lock); \ + __mutex_do_init((mutex), #mutex, &__key); \ +} while (0) + +# define __mutex_init(mutex, name, key) \ +do { \ + rt_mutex_init(&(mutex)->lock); \ + __mutex_do_init((mutex), name, key); \ +} while (0) + +#endif diff -Nur linux-3.18.9.orig/include/linux/netdevice.h linux-3.18.9/include/linux/netdevice.h --- linux-3.18.9.orig/include/linux/netdevice.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/netdevice.h 2015-03-15 16:03:03.808094874 -0500 @@ -2345,6 +2345,7 @@ unsigned int dropped; struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + struct sk_buff_head tofree_queue; #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit __rcu *flow_limit; diff -Nur linux-3.18.9.orig/include/linux/netfilter/x_tables.h linux-3.18.9/include/linux/netfilter/x_tables.h --- linux-3.18.9.orig/include/linux/netfilter/x_tables.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/netfilter/x_tables.h 2015-03-15 16:03:03.808094874 -0500 @@ -3,6 +3,7 @@ #include +#include #include /** @@ -282,6 +283,8 @@ */ DECLARE_PER_CPU(seqcount_t, xt_recseq); +DECLARE_LOCAL_IRQ_LOCK(xt_write_lock); + /** * xt_write_recseq_begin - start of a write section * @@ -296,6 +299,9 @@ { 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(). @@ -326,6 +332,7 @@ /* 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-3.18.9.orig/include/linux/notifier.h linux-3.18.9/include/linux/notifier.h --- linux-3.18.9.orig/include/linux/notifier.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/notifier.h 2015-03-15 16:03:03.808094874 -0500 @@ -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-3.18.9.orig/include/linux/percpu.h linux-3.18.9/include/linux/percpu.h --- linux-3.18.9.orig/include/linux/percpu.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/percpu.h 2015-03-15 16:03:03.808094874 -0500 @@ -23,6 +23,35 @@ PERCPU_MODULE_RESERVE) #endif +#ifdef CONFIG_PREEMPT_RT_FULL + +#define get_local_var(var) (*({ \ + migrate_disable(); \ + &__get_cpu_var(var); })) + +#define put_local_var(var) do { \ + (void)&(var); \ + migrate_enable(); \ +} while (0) + +# define get_local_ptr(var) ({ \ + migrate_disable(); \ + this_cpu_ptr(var); }) + +# define put_local_ptr(var) do { \ + (void)(var); \ + migrate_enable(); \ +} while (0) + +#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) diff -Nur linux-3.18.9.orig/include/linux/pid.h linux-3.18.9/include/linux/pid.h --- linux-3.18.9.orig/include/linux/pid.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/pid.h 2015-03-15 16:03:03.808094874 -0500 @@ -2,6 +2,7 @@ #define _LINUX_PID_H #include +#include enum pid_type { diff -Nur linux-3.18.9.orig/include/linux/preempt.h linux-3.18.9/include/linux/preempt.h --- linux-3.18.9.orig/include/linux/preempt.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/preempt.h 2015-03-15 16:03:03.808094874 -0500 @@ -33,6 +33,20 @@ #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() \ @@ -41,13 +55,25 @@ 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() \ @@ -63,6 +89,13 @@ __preempt_schedule(); \ } while (0) +#define preempt_lazy_enable() \ +do { \ + dec_preempt_lazy_count(); \ + barrier(); \ + preempt_check_resched(); \ +} while (0) + #else #define preempt_enable() \ do { \ @@ -121,6 +154,7 @@ #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 */ @@ -140,10 +174,31 @@ } 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-3.18.9.orig/include/linux/preempt_mask.h linux-3.18.9/include/linux/preempt_mask.h --- linux-3.18.9.orig/include/linux/preempt_mask.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/preempt_mask.h 2015-03-15 16:03:03.808094874 -0500 @@ -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? diff -Nur linux-3.18.9.orig/include/linux/printk.h linux-3.18.9/include/linux/printk.h --- linux-3.18.9.orig/include/linux/printk.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/printk.h 2015-03-15 16:03:03.808094874 -0500 @@ -119,9 +119,11 @@ extern asmlinkage __printf(1, 2) void early_printk(const char *fmt, ...); void early_vprintk(const char *fmt, va_list ap); +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 #ifdef CONFIG_PRINTK @@ -155,7 +157,6 @@ #define printk_ratelimit() __printk_ratelimit(__func__) extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); - extern int printk_delay_msec; extern int dmesg_restrict; extern int kptr_restrict; diff -Nur linux-3.18.9.orig/include/linux/radix-tree.h linux-3.18.9/include/linux/radix-tree.h --- linux-3.18.9.orig/include/linux/radix-tree.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/radix-tree.h 2015-03-15 16:03:03.808094874 -0500 @@ -277,8 +277,13 @@ unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items); +#ifndef CONFIG_PREEMPT_RT_FULL int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); +#else +static inline int radix_tree_preload(gfp_t gm) { return 0; } +static inline int radix_tree_maybe_preload(gfp_t gfp_mask) { return 0; } +#endif void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag); @@ -303,7 +308,7 @@ static inline void radix_tree_preload_end(void) { - preempt_enable(); + preempt_enable_nort(); } /** diff -Nur linux-3.18.9.orig/include/linux/random.h linux-3.18.9/include/linux/random.h --- linux-3.18.9.orig/include/linux/random.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/random.h 2015-03-15 16:03:03.808094874 -0500 @@ -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-3.18.9.orig/include/linux/rcupdate.h linux-3.18.9/include/linux/rcupdate.h --- linux-3.18.9.orig/include/linux/rcupdate.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/rcupdate.h 2015-03-15 16:03:03.812094874 -0500 @@ -147,6 +147,9 @@ #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. @@ -170,6 +173,7 @@ */ 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. @@ -231,6 +235,11 @@ * 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 */ @@ -254,6 +263,8 @@ return 0; } +#define sched_rcu_preempt_depth() rcu_preempt_depth() + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* Internal to kernel */ @@ -430,7 +441,14 @@ 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? @@ -955,10 +973,14 @@ 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 } /* @@ -968,10 +990,14 @@ */ 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-3.18.9.orig/include/linux/rcutree.h linux-3.18.9/include/linux/rcutree.h --- linux-3.18.9.orig/include/linux/rcutree.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/rcutree.h 2015-03-15 16:03:03.812094874 -0500 @@ -46,7 +46,11 @@ rcu_note_context_switch(cpu); } +#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); @@ -82,12 +90,10 @@ extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; long rcu_batches_completed(void); -long rcu_batches_completed_bh(void); 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); @@ -97,4 +103,12 @@ bool rcu_is_watching(void); +#ifndef CONFIG_PREEMPT_RT_FULL +void rcu_bh_force_quiescent_state(void); +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 + #endif /* __LINUX_RCUTREE_H */ diff -Nur linux-3.18.9.orig/include/linux/rtmutex.h linux-3.18.9/include/linux/rtmutex.h --- linux-3.18.9.orig/include/linux/rtmutex.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/rtmutex.h 2015-03-15 16:03:03.812094874 -0500 @@ -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-3.18.9.orig/include/linux/rwlock_rt.h linux-3.18.9/include/linux/rwlock_rt.h --- linux-3.18.9.orig/include/linux/rwlock_rt.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/linux/rwlock_rt.h 2015-03-15 16:03:03.812094874 -0500 @@ -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-3.18.9.orig/include/linux/rwlock_types.h linux-3.18.9/include/linux/rwlock_types.h --- linux-3.18.9.orig/include/linux/rwlock_types.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/rwlock_types.h 2015-03-15 16:03:03.812094874 -0500 @@ -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-3.18.9.orig/include/linux/rwlock_types_rt.h linux-3.18.9/include/linux/rwlock_types_rt.h --- linux-3.18.9.orig/include/linux/rwlock_types_rt.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/linux/rwlock_types_rt.h 2015-03-15 16:03:03.812094874 -0500 @@ -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-3.18.9.orig/include/linux/rwsem.h linux-3.18.9/include/linux/rwsem.h --- linux-3.18.9.orig/include/linux/rwsem.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/rwsem.h 2015-03-15 16:03:03.812094874 -0500 @@ -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-3.18.9.orig/include/linux/rwsem_rt.h linux-3.18.9/include/linux/rwsem_rt.h --- linux-3.18.9.orig/include/linux/rwsem_rt.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/linux/rwsem_rt.h 2015-03-15 16:03:03.812094874 -0500 @@ -0,0 +1,133 @@ +#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; +#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_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_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-3.18.9.orig/include/linux/sched.h linux-3.18.9/include/linux/sched.h --- linux-3.18.9.orig/include/linux/sched.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/sched.h 2015-03-15 16:03:03.812094874 -0500 @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -56,6 +57,7 @@ #include #include #include +#include #include #include @@ -235,10 +237,7 @@ 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) @@ -1234,6 +1233,7 @@ 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 */ @@ -1270,6 +1270,12 @@ #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; @@ -1371,7 +1377,8 @@ 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, @@ -1387,6 +1394,9 @@ 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 *real_cred; /* objective and real subjective task @@ -1419,10 +1429,15 @@ /* 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; @@ -1460,6 +1475,9 @@ /* mutex deadlock detection */ struct mutex_waiter *blocked_on; #endif +#ifdef CONFIG_PREEMPT_RT_FULL + int pagefault_disabled; +#endif #ifdef CONFIG_TRACE_IRQFLAGS unsigned int irq_events; unsigned long hardirq_enable_ip; @@ -1644,6 +1662,12 @@ 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 /* memcg uses this to do batch job */ unsigned int memcg_kmem_skip_account; @@ -1661,11 +1685,19 @@ 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 }; -/* 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 @@ -1700,6 +1732,17 @@ } #endif +#ifdef CONFIG_PREEMPT_RT_FULL +static inline bool cur_pf_disabled(void) { return current->pagefault_disabled; } +#else +static inline bool cur_pf_disabled(void) { return false; } +#endif + +static inline bool pagefault_disabled(void) +{ + return in_atomic() || cur_pf_disabled(); +} + static inline struct pid *task_pid(struct task_struct *task) { return task->pids[PIDTYPE_PID].pid; @@ -1853,6 +1896,15 @@ 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) @@ -1860,6 +1912,7 @@ 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, @@ -1898,6 +1951,7 @@ /* * 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 */ @@ -2058,6 +2112,10 @@ 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) @@ -2070,6 +2128,9 @@ 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 @@ -2290,6 +2351,7 @@ 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); @@ -2406,12 +2468,24 @@ /* 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 */ @@ -2719,6 +2793,43 @@ 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); @@ -2750,6 +2861,51 @@ 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 @@ -2766,7 +2922,7 @@ extern int __cond_resched_lock(spinlock_t *lock); -#ifdef CONFIG_PREEMPT_COUNT +#if defined(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT_FULL) #define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET #else #define PREEMPT_LOCK_OFFSET 0 @@ -2777,12 +2933,16 @@ __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) { @@ -2949,6 +3109,26 @@ #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-3.18.9.orig/include/linux/seqlock.h linux-3.18.9/include/linux/seqlock.h --- linux-3.18.9.orig/include/linux/seqlock.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/seqlock.h 2015-03-15 16:03:03.812094874 -0500 @@ -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-3.18.9.orig/include/linux/signal.h linux-3.18.9/include/linux/signal.h --- linux-3.18.9.orig/include/linux/signal.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/signal.h 2015-03-15 16:03:03.812094874 -0500 @@ -218,6 +218,7 @@ } 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-3.18.9.orig/include/linux/skbuff.h linux-3.18.9/include/linux/skbuff.h --- linux-3.18.9.orig/include/linux/skbuff.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/skbuff.h 2015-03-15 16:03:03.816094874 -0500 @@ -172,6 +172,7 @@ __u32 qlen; spinlock_t lock; + raw_spinlock_t raw_lock; }; struct sk_buff; @@ -1327,6 +1328,12 @@ __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-3.18.9.orig/include/linux/smp.h linux-3.18.9/include/linux/smp.h --- linux-3.18.9.orig/include/linux/smp.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/smp.h 2015-03-15 16:03:03.816094874 -0500 @@ -178,6 +178,9 @@ #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-3.18.9.orig/include/linux/spinlock_api_smp.h linux-3.18.9/include/linux/spinlock_api_smp.h --- linux-3.18.9.orig/include/linux/spinlock_api_smp.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/spinlock_api_smp.h 2015-03-15 16:03:03.816094874 -0500 @@ -187,6 +187,8 @@ return 0; } -#include +#ifndef CONFIG_PREEMPT_RT_FULL +# include +#endif #endif /* __LINUX_SPINLOCK_API_SMP_H */ diff -Nur linux-3.18.9.orig/include/linux/spinlock.h linux-3.18.9/include/linux/spinlock.h --- linux-3.18.9.orig/include/linux/spinlock.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/spinlock.h 2015-03-15 16:03:03.816094874 -0500 @@ -278,7 +278,11 @@ #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: @@ -289,6 +293,10 @@ # 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 */ @@ -418,4 +426,6 @@ #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-3.18.9.orig/include/linux/spinlock_rt.h linux-3.18.9/include/linux/spinlock_rt.h --- linux-3.18.9.orig/include/linux/spinlock_rt.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/linux/spinlock_rt.h 2015-03-15 16:03:03.816094874 -0500 @@ -0,0 +1,167 @@ +#ifndef __LINUX_SPINLOCK_RT_H +#define __LINUX_SPINLOCK_RT_H + +#ifndef __LINUX_SPINLOCK_H +#error Do not include directly. Use spinlock.h +#endif + +#include + +extern void +__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key); + +#define spin_lock_init(slock) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_init(&(slock)->lock); \ + __rt_spin_lock_init(slock, #slock, &__key); \ +} while (0) + +extern void __lockfunc rt_spin_lock(spinlock_t *lock); +extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock); +extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass); +extern void __lockfunc rt_spin_unlock(spinlock_t *lock); +extern void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock); +extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock); +extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags); +extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock); +extern int __lockfunc rt_spin_trylock(spinlock_t *lock); +extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock); + +/* + * lockdep-less calls, for derived types like rwlock: + * (for trylock they can use rt_mutex_trylock() directly. + */ +extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock); +extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock); +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_irqsave_nested(lock, flags, subclass) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + migrate_disable(); \ + rt_spin_lock_nested(lock, subclass); \ + } while (0) +#else +# define spin_lock_nested(lock, subclass) spin_lock(lock) + +# define spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + spin_lock(lock); \ + } while (0) +#endif + +#define spin_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + spin_lock(lock); \ + } while (0) + +static inline unsigned long spin_lock_trace_flags(spinlock_t *lock) +{ + unsigned long flags = 0; +#ifdef CONFIG_TRACE_IRQFLAGS + flags = rt_spin_lock_trace_flags(lock); +#else + spin_lock(lock); /* lock_local */ +#endif + return flags; +} + +/* FIXME: we need rt_spin_lock_nest_lock */ +#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0) + +#define spin_unlock(lock) \ + do { \ + rt_spin_unlock(lock); \ + migrate_enable(); \ + } while (0) + +#define spin_unlock_bh(lock) \ + do { \ + rt_spin_unlock(lock); \ + migrate_enable(); \ + local_bh_enable(); \ + } while (0) + +#define spin_unlock_irq(lock) spin_unlock(lock) + +#define spin_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + (void) flags; \ + spin_unlock(lock); \ + } while (0) + +#define spin_trylock_bh(lock) __cond_lock(lock, rt_spin_trylock_bh(lock)) +#define spin_trylock_irq(lock) spin_trylock(lock) + +#define spin_trylock_irqsave(lock, flags) \ + rt_spin_trylock_irqsave(lock, &(flags)) + +#define spin_unlock_wait(lock) rt_spin_unlock_wait(lock) + +#ifdef CONFIG_GENERIC_LOCKBREAK +# define spin_is_contended(lock) ((lock)->break_lock) +#else +# define spin_is_contended(lock) (((void)(lock), 0)) +#endif + +static inline int spin_can_lock(spinlock_t *lock) +{ + return !rt_mutex_is_locked(&lock->lock); +} + +static inline int spin_is_locked(spinlock_t *lock) +{ + return rt_mutex_is_locked(&lock->lock); +} + +static inline void assert_spin_locked(spinlock_t *lock) +{ + BUG_ON(!spin_is_locked(lock)); +} + +#define atomic_dec_and_lock(atomic, lock) \ + atomic_dec_and_spin_lock(atomic, lock) + +#endif diff -Nur linux-3.18.9.orig/include/linux/spinlock_types.h linux-3.18.9/include/linux/spinlock_types.h --- linux-3.18.9.orig/include/linux/spinlock_types.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/spinlock_types.h 2015-03-15 16:03:03.816094874 -0500 @@ -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-3.18.9.orig/include/linux/spinlock_types_nort.h linux-3.18.9/include/linux/spinlock_types_nort.h --- linux-3.18.9.orig/include/linux/spinlock_types_nort.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/linux/spinlock_types_nort.h 2015-03-15 16:03:03.816094874 -0500 @@ -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-3.18.9.orig/include/linux/spinlock_types_raw.h linux-3.18.9/include/linux/spinlock_types_raw.h --- linux-3.18.9.orig/include/linux/spinlock_types_raw.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/linux/spinlock_types_raw.h 2015-03-15 16:03:03.816094874 -0500 @@ -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-3.18.9.orig/include/linux/spinlock_types_rt.h linux-3.18.9/include/linux/spinlock_types_rt.h --- linux-3.18.9.orig/include/linux/spinlock_types_rt.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/linux/spinlock_types_rt.h 2015-03-15 16:03:03.816094874 -0500 @@ -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-3.18.9.orig/include/linux/srcu.h linux-3.18.9/include/linux/srcu.h --- linux-3.18.9.orig/include/linux/srcu.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/srcu.h 2015-03-15 16:03:03.820094874 -0500 @@ -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), \ @@ -104,11 +104,12 @@ */ #define DEFINE_SRCU(name) \ static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ - struct srcu_struct name = __SRCU_STRUCT_INIT(name); + struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_array); #define DEFINE_STATIC_SRCU(name) \ static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ - static struct srcu_struct name = __SRCU_STRUCT_INIT(name); + static struct srcu_struct name = __SRCU_STRUCT_INIT(\ + name, name##_srcu_array); /** * call_srcu() - Queue a callback for invocation after an SRCU grace period diff -Nur linux-3.18.9.orig/include/linux/swap.h linux-3.18.9/include/linux/swap.h --- linux-3.18.9.orig/include/linux/swap.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/swap.h 2015-03-15 16:03:03.824094874 -0500 @@ -11,6 +11,7 @@ #include #include #include +#include #include struct notifier_block; @@ -260,7 +261,8 @@ 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) { diff -Nur linux-3.18.9.orig/include/linux/sysctl.h linux-3.18.9/include/linux/sysctl.h --- linux-3.18.9.orig/include/linux/sysctl.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/sysctl.h 2015-03-15 16:03:03.824094874 -0500 @@ -25,6 +25,7 @@ #include #include #include +#include #include /* For the /proc/sys support */ diff -Nur linux-3.18.9.orig/include/linux/thread_info.h linux-3.18.9/include/linux/thread_info.h --- linux-3.18.9.orig/include/linux/thread_info.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/thread_info.h 2015-03-15 16:03:03.824094874 -0500 @@ -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-3.18.9.orig/include/linux/timer.h linux-3.18.9/include/linux/timer.h --- linux-3.18.9.orig/include/linux/timer.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/timer.h 2015-03-15 16:03:03.824094874 -0500 @@ -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-3.18.9.orig/include/linux/uaccess.h linux-3.18.9/include/linux/uaccess.h --- linux-3.18.9.orig/include/linux/uaccess.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/uaccess.h 2015-03-15 16:03:03.824094874 -0500 @@ -6,14 +6,9 @@ /* * These routines enable/disable the pagefault handler in that - * it will not take any locks and go straight to the fixup table. - * - * They have great resemblance to the preempt_disable/enable calls - * and in fact they are identical; this is because currently there is - * no other way to make the pagefault handlers do this. So we do - * disable preemption but we don't necessarily care about that. + * it will not take any MM locks and go straight to the fixup table. */ -static inline void pagefault_disable(void) +static inline void raw_pagefault_disable(void) { preempt_count_inc(); /* @@ -23,7 +18,7 @@ barrier(); } -static inline void pagefault_enable(void) +static inline void raw_pagefault_enable(void) { #ifndef CONFIG_PREEMPT /* @@ -37,6 +32,21 @@ #endif } +#ifndef CONFIG_PREEMPT_RT_FULL +static inline void pagefault_disable(void) +{ + raw_pagefault_disable(); +} + +static inline void pagefault_enable(void) +{ + raw_pagefault_enable(); +} +#else +extern void pagefault_disable(void); +extern void pagefault_enable(void); +#endif + #ifndef ARCH_HAS_NOCACHE_UACCESS static inline unsigned long __copy_from_user_inatomic_nocache(void *to, @@ -76,9 +86,9 @@ mm_segment_t old_fs = get_fs(); \ \ set_fs(KERNEL_DS); \ - pagefault_disable(); \ + raw_pagefault_disable(); \ ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval)); \ - pagefault_enable(); \ + raw_pagefault_enable(); \ set_fs(old_fs); \ ret; \ }) diff -Nur linux-3.18.9.orig/include/linux/uprobes.h linux-3.18.9/include/linux/uprobes.h --- linux-3.18.9.orig/include/linux/uprobes.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/uprobes.h 2015-03-15 16:03:03.824094874 -0500 @@ -27,6 +27,7 @@ #include #include #include +#include struct vm_area_struct; struct mm_struct; diff -Nur linux-3.18.9.orig/include/linux/vmstat.h linux-3.18.9/include/linux/vmstat.h --- linux-3.18.9.orig/include/linux/vmstat.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/vmstat.h 2015-03-15 16:03:03.824094874 -0500 @@ -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-3.18.9.orig/include/linux/wait.h linux-3.18.9/include/linux/wait.h --- linux-3.18.9.orig/include/linux/wait.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/linux/wait.h 2015-03-15 16:03:03.824094874 -0500 @@ -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-3.18.9.orig/include/linux/wait-simple.h linux-3.18.9/include/linux/wait-simple.h --- linux-3.18.9.orig/include/linux/wait-simple.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/linux/wait-simple.h 2015-03-15 16:03:03.824094874 -0500 @@ -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-3.18.9.orig/include/linux/work-simple.h linux-3.18.9/include/linux/work-simple.h --- linux-3.18.9.orig/include/linux/work-simple.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/linux/work-simple.h 2015-03-15 16:03:03.824094874 -0500 @@ -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-3.18.9.orig/include/net/dst.h linux-3.18.9/include/net/dst.h --- linux-3.18.9.orig/include/net/dst.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/net/dst.h 2015-03-15 16:03:03.824094874 -0500 @@ -403,7 +403,7 @@ 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-3.18.9.orig/include/net/neighbour.h linux-3.18.9/include/net/neighbour.h --- linux-3.18.9.orig/include/net/neighbour.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/net/neighbour.h 2015-03-15 16:03:03.824094874 -0500 @@ -387,7 +387,7 @@ } #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; @@ -442,7 +442,7 @@ #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-3.18.9.orig/include/net/netns/ipv4.h linux-3.18.9/include/net/netns/ipv4.h --- linux-3.18.9.orig/include/net/netns/ipv4.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/include/net/netns/ipv4.h 2015-03-15 16:03:03.824094874 -0500 @@ -67,6 +67,7 @@ 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-3.18.9.orig/include/trace/events/hist.h linux-3.18.9/include/trace/events/hist.h --- linux-3.18.9.orig/include/trace/events/hist.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/trace/events/hist.h 2015-03-15 16:03:03.824094874 -0500 @@ -0,0 +1,72 @@ +#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) +#else +TRACE_EVENT(preemptirqsoff_hist, + + TP_PROTO(int reason, int starthist), + + TP_ARGS(reason, starthist), + + TP_STRUCT__entry( + __field(int, reason) + __field(int, starthist) + ), + + TP_fast_assign( + __entry->reason = reason; + __entry->starthist = starthist; + ), + + TP_printk("reason=%s starthist=%s", getaction(__entry->reason), + __entry->starthist ? "start" : "stop") +); +#endif + +#ifndef CONFIG_MISSED_TIMER_OFFSETS_HIST +#define trace_hrtimer_interrupt(a, b, c, d) +#else +TRACE_EVENT(hrtimer_interrupt, + + TP_PROTO(int cpu, long long offset, struct task_struct *curr, + struct task_struct *task), + + TP_ARGS(cpu, offset, curr, task), + + TP_STRUCT__entry( + __field(int, cpu) + __field(long long, offset) + __array(char, ccomm, TASK_COMM_LEN) + __field(int, cprio) + __array(char, tcomm, TASK_COMM_LEN) + __field(int, tprio) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->offset = offset; + memcpy(__entry->ccomm, curr->comm, TASK_COMM_LEN); + __entry->cprio = curr->prio; + memcpy(__entry->tcomm, task != NULL ? task->comm : "", + task != NULL ? TASK_COMM_LEN : 7); + __entry->tprio = task != NULL ? task->prio : -1; + ), + + TP_printk("cpu=%d offset=%lld curr=%s[%d] thread=%s[%d]", + __entry->cpu, __entry->offset, __entry->ccomm, + __entry->cprio, __entry->tcomm, __entry->tprio) +); +#endif + +#endif /* _TRACE_HIST_H */ + +/* This part must be outside protection */ +#include diff -Nur linux-3.18.9.orig/include/trace/events/latency_hist.h linux-3.18.9/include/trace/events/latency_hist.h --- linux-3.18.9.orig/include/trace/events/latency_hist.h 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/include/trace/events/latency_hist.h 2015-03-15 16:03:03.824094874 -0500 @@ -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-3.18.9.orig/init/Kconfig linux-3.18.9/init/Kconfig --- linux-3.18.9.orig/init/Kconfig 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/init/Kconfig 2015-03-15 16:03:03.824094874 -0500 @@ -635,7 +635,7 @@ 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 @@ -662,7 +662,7 @@ 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. @@ -1106,6 +1106,7 @@ 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 @@ -1677,6 +1678,7 @@ 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 @@ -1695,6 +1697,7 @@ 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 diff -Nur linux-3.18.9.orig/init/main.c linux-3.18.9/init/main.c --- linux-3.18.9.orig/init/main.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/init/main.c 2015-03-15 16:03:03.828094874 -0500 @@ -533,6 +533,7 @@ 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-3.18.9.orig/init/Makefile linux-3.18.9/init/Makefile --- linux-3.18.9.orig/init/Makefile 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/init/Makefile 2015-03-15 16:03:03.828094874 -0500 @@ -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-3.18.9.orig/ipc/mqueue.c linux-3.18.9/ipc/mqueue.c --- linux-3.18.9.orig/ipc/mqueue.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/ipc/mqueue.c 2015-03-15 16:03:03.828094874 -0500 @@ -923,12 +923,17 @@ struct msg_msg *message, struct ext_wait_queue *receiver) { + /* + * Keep them in one critical section for PREEMPT_RT: + */ + preempt_disable_rt(); receiver->msg = message; list_del(&receiver->list); receiver->state = STATE_PENDING; wake_up_process(receiver->task); smp_wmb(); receiver->state = STATE_READY; + preempt_enable_rt(); } /* pipelined_receive() - if there is task waiting in sys_mq_timedsend() @@ -942,13 +947,18 @@ wake_up_interruptible(&info->wait_q); return; } - if (msg_insert(sender->msg, info)) - return; - list_del(&sender->list); - sender->state = STATE_PENDING; - wake_up_process(sender->task); - smp_wmb(); - sender->state = STATE_READY; + /* + * Keep them in one critical section for PREEMPT_RT: + */ + preempt_disable_rt(); + if (!msg_insert(sender->msg, info)) { + list_del(&sender->list); + sender->state = STATE_PENDING; + wake_up_process(sender->task); + smp_wmb(); + sender->state = STATE_READY; + } + preempt_enable_rt(); } SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, diff -Nur linux-3.18.9.orig/ipc/msg.c linux-3.18.9/ipc/msg.c --- linux-3.18.9.orig/ipc/msg.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/ipc/msg.c 2015-03-15 16:03:03.828094874 -0500 @@ -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-3.18.9.orig/ipc/sem.c linux-3.18.9/ipc/sem.c --- linux-3.18.9.orig/ipc/sem.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/ipc/sem.c 2015-03-15 16:03:03.828094874 -0500 @@ -673,6 +673,13 @@ 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 @@ -684,6 +691,7 @@ q->pid = error; list_add_tail(&q->list, pt); +#endif } /** @@ -697,6 +705,7 @@ */ static void wake_up_sem_queue_do(struct list_head *pt) { +#ifndef CONFIG_PREEMPT_RT_BASE struct sem_queue *q, *t; int did_something; @@ -709,6 +718,7 @@ } if (did_something) preempt_enable(); +#endif } static void unlink_queue(struct sem_array *sma, struct sem_queue *q) diff -Nur linux-3.18.9.orig/kernel/cgroup.c linux-3.18.9/kernel/cgroup.c --- linux-3.18.9.orig/kernel/cgroup.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/cgroup.c 2015-03-15 16:03:03.828094874 -0500 @@ -4355,10 +4355,10 @@ 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; @@ -4395,8 +4395,8 @@ 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, @@ -4997,6 +4997,7 @@ */ 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-3.18.9.orig/kernel/cpu.c linux-3.18.9/kernel/cpu.c --- linux-3.18.9.orig/kernel/cpu.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/cpu.c 2015-03-15 16:03:03.828094874 -0500 @@ -86,6 +86,290 @@ #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 = &__get_cpu_var(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 = &__get_cpu_var(hotplug_pcp); + if (!hp->grab_lock) { + /* + * Just let it continue it's already pinned + * or about to sleep. + */ + force = 1; + goto retry; + } + preempt_enable(); + } + } + preempt_disable(); + goto retry; +} + +/** + * unpin_current_cpu - Allow unplug of current cpu + * + * Must be called with preemption or interrupts disabled! + */ +void unpin_current_cpu(void) +{ + struct hotplug_pcp *hp = &__get_cpu_var(hotplug_pcp); + + WARN_ON(hp->refcount <= 0); + + /* This is safe. sync_unplug_thread is pinned to this cpu */ + if (!--hp->refcount && hp->unplug && hp->unplug != current) + 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; + do_set_cpus_allowed(current, cpu_present_mask); + migrate_me(); + return 0; +} + +static void __cpu_unplug_sync(struct hotplug_pcp *hp) +{ + wake_up_process(hp->sync_tsk); + wait_for_completion(&hp->synced); +} + +static void __cpu_unplug_wait(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + complete(&hp->unplug_wait); + wait_for_completion(&hp->synced); +} + +/* + * Start the sync_unplug_thread on the target cpu and wait for it to + * complete. + */ +static int cpu_unplug_begin(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + int err; + + /* Protected by cpu_hotplug.lock */ + if (!hp->mutex_init) { +#ifdef CONFIG_PREEMPT_RT_FULL + spin_lock_init(&hp->lock); +#else + mutex_init(&hp->mutex); +#endif + hp->mutex_init = 1; + } + + /* Inform the scheduler to migrate tasks off this CPU */ + tell_sched_cpu_down_begin(cpu); + + init_completion(&hp->synced); + init_completion(&hp->unplug_wait); + + hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); + if (IS_ERR(hp->sync_tsk)) { + err = PTR_ERR(hp->sync_tsk); + hp->sync_tsk = NULL; + return err; + } + kthread_bind(hp->sync_tsk, cpu); + + /* + * Wait for tasks to get out of the pinned sections, + * it's still OK if new tasks enter. Some CPU notifiers will + * wait for tasks that are going to enter these sections and + * we must not have them block. + */ + wake_up_process(hp->sync_tsk); + return 0; +} + +static void cpu_unplug_sync(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + init_completion(&hp->synced); + /* The completion needs to be initialzied before setting grab_lock */ + smp_wmb(); + + /* Grab the mutex before setting grab_lock */ + hotplug_lock(hp); + hp->grab_lock = 1; + + /* + * The CPU notifiers have been completed. + * Wait for tasks to get out of pinned CPU sections and have new + * tasks block until the CPU is completely down. + */ + __cpu_unplug_sync(hp); + + /* All done with the sync thread */ + kthread_stop(hp->sync_tsk); + hp->sync_tsk = NULL; +} + +static void cpu_unplug_done(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + hp->unplug = NULL; + /* Let all tasks know cpu unplug is finished before cleaning up */ + smp_wmb(); + + if (hp->sync_tsk) + kthread_stop(hp->sync_tsk); + + if (hp->grab_lock) { + hotplug_unlock(hp); + /* protected by cpu_hotplug.lock */ + hp->grab_lock = 0; + } + tell_sched_cpu_down_done(cpu); +} + void get_online_cpus(void) { might_sleep(); @@ -102,6 +386,7 @@ { if (cpu_hotplug.active_writer == current) return true; + if (!mutex_trylock(&cpu_hotplug.lock)) return false; cpuhp_lock_acquire_tryread(); @@ -349,13 +634,15 @@ /* 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 +650,34 @@ 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 +703,12 @@ #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(). */ @@ -423,9 +741,14 @@ 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-3.18.9.orig/kernel/debug/kdb/kdb_io.c linux-3.18.9/kernel/debug/kdb/kdb_io.c --- linux-3.18.9.orig/kernel/debug/kdb/kdb_io.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/debug/kdb/kdb_io.c 2015-03-15 16:03:03.828094874 -0500 @@ -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, @@ -833,7 +830,6 @@ } else { __release(kdb_printf_lock); } - kdb_trap_printk = saved_trap_printk; preempt_enable(); return retlen; } @@ -843,9 +839,11 @@ va_list ap; int r; + kdb_trap_printk++; va_start(ap, fmt); r = vkdb_printf(fmt, ap); va_end(ap); + kdb_trap_printk--; return r; } diff -Nur linux-3.18.9.orig/kernel/events/core.c linux-3.18.9/kernel/events/core.c --- linux-3.18.9.orig/kernel/events/core.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/events/core.c 2015-03-15 16:03:03.832094874 -0500 @@ -6336,6 +6336,7 @@ 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-3.18.9.orig/kernel/exit.c linux-3.18.9/kernel/exit.c --- linux-3.18.9.orig/kernel/exit.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/exit.c 2015-03-15 16:03:03.832094874 -0500 @@ -147,7 +147,7 @@ * 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-3.18.9.orig/kernel/fork.c linux-3.18.9/kernel/fork.c --- linux-3.18.9.orig/kernel/fork.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/fork.c 2015-03-15 16:03:03.832094874 -0500 @@ -97,7 +97,7 @@ 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) @@ -233,7 +233,9 @@ 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); @@ -249,7 +251,18 @@ 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) { } @@ -643,6 +656,19 @@ } 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. */ @@ -1157,6 +1183,9 @@ */ 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; @@ -1284,6 +1313,7 @@ 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; @@ -1291,7 +1321,8 @@ 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 @@ -1342,6 +1373,9 @@ p->hardirq_context = 0; p->softirq_context = 0; #endif +#ifdef CONFIG_PREEMPT_RT_FULL + p->pagefault_disabled = 0; +#endif #ifdef CONFIG_LOCKDEP p->lockdep_depth = 0; /* no locks held yet */ p->curr_chain_key = 0; diff -Nur linux-3.18.9.orig/kernel/futex.c linux-3.18.9/kernel/futex.c --- linux-3.18.9.orig/kernel/futex.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/futex.c 2015-03-15 16:03:03.832094874 -0500 @@ -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; } @@ -1705,6 +1707,16 @@ 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; @@ -2549,7 +2561,7 @@ 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; @@ -2574,10 +2586,7 @@ * 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)) @@ -2608,20 +2617,55 @@ /* 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) { @@ -2630,9 +2674,10 @@ * did a lock-steal - fix up the PI-state in that case. */ if (q.pi_state && (q.pi_state->owner != current)) { - spin_lock(q.lock_ptr); + spin_lock(&hb2->lock); + BUG_ON(&hb2->lock != q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); - spin_unlock(q.lock_ptr); + spin_unlock(&hb2->lock); } } else { /* @@ -2645,7 +2690,8 @@ 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-3.18.9.orig/kernel/irq/handle.c linux-3.18.9/kernel/irq/handle.c --- linux-3.18.9.orig/kernel/irq/handle.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/irq/handle.c 2015-03-15 16:03:03.832094874 -0500 @@ -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-3.18.9.orig/kernel/irq/manage.c linux-3.18.9/kernel/irq/manage.c --- linux-3.18.9.orig/kernel/irq/manage.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/irq/manage.c 2015-03-15 16:03:03.832094874 -0500 @@ -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) @@ -173,6 +175,62 @@ 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) { @@ -211,7 +269,17 @@ 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); @@ -246,10 +314,8 @@ } 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; @@ -271,6 +337,13 @@ 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 @@ -300,6 +373,8 @@ 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); @@ -788,7 +863,15 @@ 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; } @@ -871,6 +954,12 @@ if (action_ret == IRQ_HANDLED) atomic_inc(&desc->threads_handled); +#ifdef CONFIG_PREEMPT_RT_FULL + migrate_disable(); + add_interrupt_randomness(action->irq, 0, + desc->random_ip ^ (unsigned long) action); + migrate_enable(); +#endif wake_threads_waitq(desc); } @@ -1184,6 +1273,9 @@ 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); diff -Nur linux-3.18.9.orig/kernel/irq/settings.h linux-3.18.9/kernel/irq/settings.h --- linux-3.18.9.orig/kernel/irq/settings.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/irq/settings.h 2015-03-15 16:03:03.836094874 -0500 @@ -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-3.18.9.orig/kernel/irq/spurious.c linux-3.18.9/kernel/irq/spurious.c --- linux-3.18.9.orig/kernel/irq/spurious.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/irq/spurious.c 2015-03-15 16:03:03.836094874 -0500 @@ -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-3.18.9.orig/kernel/irq_work.c linux-3.18.9/kernel/irq_work.c --- linux-3.18.9.orig/kernel/irq_work.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/irq_work.c 2015-03-15 16:03:03.836094874 -0500 @@ -22,7 +22,9 @@ static DEFINE_PER_CPU(struct llist_head, raised_list); static DEFINE_PER_CPU(struct llist_head, lazy_list); - +#ifdef CONFIG_PREEMPT_RT_FULL +static DEFINE_PER_CPU(struct llist_head, hirq_work_list); +#endif /* * Claim the entry so that no one else will poke at it. */ @@ -49,7 +51,11 @@ return true; } +#ifdef CONFIG_PREEMPT_RT_FULL +void arch_irq_work_raise(void) +#else void __weak arch_irq_work_raise(void) +#endif { /* * Lame architectures will get the timer tick callback @@ -93,8 +99,21 @@ /* Queue the entry and raise the IPI if needed. */ preempt_disable(); +#ifdef CONFIG_PREEMPT_RT_FULL + if (work->flags & IRQ_WORK_HARD_IRQ) { + if (llist_add(&work->llnode, this_cpu_ptr(&hirq_work_list))) { + if (work->flags & IRQ_WORK_LAZY) { + if (tick_nohz_tick_stopped()) + arch_irq_work_raise(); + } else { + arch_irq_work_raise(); + } + } /* If the work is "lazy", handle it from next tick if any */ + } else if (work->flags & IRQ_WORK_LAZY) { +#else if (work->flags & IRQ_WORK_LAZY) { +#endif if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && tick_nohz_tick_stopped()) arch_irq_work_raise(); @@ -116,7 +135,7 @@ raised = this_cpu_ptr(&raised_list); lazy = this_cpu_ptr(&lazy_list); - if (llist_empty(raised) || arch_irq_work_has_interrupt()) + if (llist_empty(raised)) if (llist_empty(lazy)) return false; @@ -132,7 +151,9 @@ struct irq_work *work; struct llist_node *llnode; +#ifndef CONFIG_PREEMPT_RT_FULL BUG_ON(!irqs_disabled()); +#endif if (llist_empty(list)) return; @@ -168,6 +189,12 @@ */ void irq_work_run(void) { +#ifdef CONFIG_PREEMPT_RT_FULL + if (in_irq()) { + irq_work_run_list(this_cpu_ptr(&hirq_work_list)); + return; + } +#endif irq_work_run_list(this_cpu_ptr(&raised_list)); irq_work_run_list(this_cpu_ptr(&lazy_list)); } @@ -175,9 +202,16 @@ void irq_work_tick(void) { - struct llist_head *raised = &__get_cpu_var(raised_list); + struct llist_head *raised; - if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) +#ifdef CONFIG_PREEMPT_RT_FULL + if (in_irq()) { + irq_work_run_list(this_cpu_ptr(&hirq_work_list)); + return; + } +#endif + raised = &__get_cpu_var(raised_list); + if (!llist_empty(raised)) irq_work_run_list(raised); irq_work_run_list(&__get_cpu_var(lazy_list)); } diff -Nur linux-3.18.9.orig/kernel/Kconfig.locks linux-3.18.9/kernel/Kconfig.locks --- linux-3.18.9.orig/kernel/Kconfig.locks 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/Kconfig.locks 2015-03-15 16:03:03.836094874 -0500 @@ -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 ARCH_USE_QUEUE_RWLOCK bool diff -Nur linux-3.18.9.orig/kernel/Kconfig.preempt linux-3.18.9/kernel/Kconfig.preempt --- linux-3.18.9.orig/kernel/Kconfig.preempt 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/Kconfig.preempt 2015-03-15 16:03:03.836094874 -0500 @@ -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-3.18.9.orig/kernel/ksysfs.c linux-3.18.9/kernel/ksysfs.c --- linux-3.18.9.orig/kernel/ksysfs.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/ksysfs.c 2015-03-15 16:03:03.836094874 -0500 @@ -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-3.18.9.orig/kernel/locking/lglock.c linux-3.18.9/kernel/locking/lglock.c --- linux-3.18.9.orig/kernel/locking/lglock.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/locking/lglock.c 2015-03-15 16:03:03.836094874 -0500 @@ -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-3.18.9.orig/kernel/locking/lockdep.c linux-3.18.9/kernel/locking/lockdep.c --- linux-3.18.9.orig/kernel/locking/lockdep.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/locking/lockdep.c 2015-03-15 16:03:03.836094874 -0500 @@ -3542,6 +3542,7 @@ } } +#ifndef CONFIG_PREEMPT_RT_FULL /* * We dont accurately track softirq state in e.g. * hardirq contexts (such as on 4KSTACKS), so only @@ -3556,6 +3557,7 @@ DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); } } +#endif if (!debug_locks) print_irqtrace_events(current); diff -Nur linux-3.18.9.orig/kernel/locking/Makefile linux-3.18.9/kernel/locking/Makefile --- linux-3.18.9.orig/kernel/locking/Makefile 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/locking/Makefile 2015-03-15 16:03:03.836094874 -0500 @@ -1,5 +1,5 @@ -obj-y += mutex.o semaphore.o rwsem.o mcs_spinlock.o +obj-y += semaphore.o mcs_spinlock.o ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_lockdep.o = -pg @@ -8,7 +8,11 @@ CFLAGS_REMOVE_rtmutex-debug.o = -pg 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 @@ -21,8 +25,11 @@ 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-3.18.9.orig/kernel/locking/percpu-rwsem.c linux-3.18.9/kernel/locking/percpu-rwsem.c --- linux-3.18.9.orig/kernel/locking/percpu-rwsem.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/locking/percpu-rwsem.c 2015-03-15 16:03:03.836094874 -0500 @@ -84,8 +84,12 @@ down_read(&brw->rw_sem); atomic_inc(&brw->slow_read_ctr); +#ifdef CONFIG_PREEMPT_RT_FULL + up_read(&brw->rw_sem); +#else /* avoid up_read()->rwsem_release() */ __up_read(&brw->rw_sem); +#endif } void percpu_up_read(struct percpu_rw_semaphore *brw) diff -Nur linux-3.18.9.orig/kernel/locking/rt.c linux-3.18.9/kernel/locking/rt.c --- linux-3.18.9.orig/kernel/locking/rt.c 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/kernel/locking/rt.c 2015-03-15 16:03:03.836094874 -0500 @@ -0,0 +1,437 @@ +/* + * 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) +{ + rwsem_release(&rwsem->dep_map, 1, _RET_IP_); + rt_mutex_unlock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_up_read); + +/* + * downgrade a write lock into a read lock + * - just wake up any readers at the front of the queue + */ +void rt_downgrade_write(struct rw_semaphore *rwsem) +{ + BUG_ON(rt_mutex_owner(&rwsem->lock) != current); +} +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) +{ + int ret; + + ret = rt_mutex_trylock(&rwsem->lock); + if (ret) + 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) +{ + rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_); + rt_mutex_lock(&rwsem->lock); +} + +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->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-3.18.9.orig/kernel/locking/rtmutex.c linux-3.18.9/kernel/locking/rtmutex.c --- linux-3.18.9.orig/kernel/locking/rtmutex.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/locking/rtmutex.c 2015-03-15 16:03:03.836094874 -0500 @@ -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 @@ -333,6 +345,14 @@ 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: */ @@ -340,7 +360,8 @@ 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; } /* @@ -477,7 +498,7 @@ * 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; /* @@ -639,13 +660,16 @@ * 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; } @@ -738,6 +762,25 @@ 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 * @@ -748,8 +791,9 @@ * @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; @@ -788,8 +832,10 @@ * 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 @@ -807,14 +853,10 @@ * 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 @@ -863,6 +905,369 @@ 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(); + + 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(TASK_UNINTERRUPTIBLE); + pi_unlock(&self->pi_lock); + + ret = task_blocks_on_rt_mutex(lock, &waiter, self, 0); + BUG_ON(ret); + + for (;;) { + /* Try to acquire the lock again. */ + if (__try_to_take_rt_mutex(lock, self, &waiter, STEAL_LATERAL)) + break; + + top_waiter = rt_mutex_top_waiter(lock); + lock_owner = rt_mutex_owner(lock); + + raw_spin_unlock(&lock->wait_lock); + + debug_rt_mutex_print_deadlock(&waiter); + + if (top_waiter != &waiter || adaptive_wait(lock, lock_owner)) + schedule_rt_mutex(lock); + + raw_spin_lock(&lock->wait_lock); + + pi_lock(&self->pi_lock); + __set_current_state(TASK_UNINTERRUPTIBLE); + pi_unlock(&self->pi_lock); + } + + /* + * Restore the task state to current->saved_state. We set it + * to the original state above and the try_to_wake_up() code + * has possibly updated it when a real (non-rtmutex) wakeup + * happened while we were blocked. Clear saved_state so + * try_to_wakeup() does not get confused. + */ + pi_lock(&self->pi_lock); + __set_current_state(self->saved_state); + self->saved_state = TASK_RUNNING; + pi_unlock(&self->pi_lock); + + /* + * try_to_take_rt_mutex() sets the waiter bit + * unconditionally. We might have to fix that up: + */ + fixup_rt_mutex_waiters(lock); + + BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock)); + BUG_ON(!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 __sched __rt_spin_lock_slowunlock(struct rt_mutex *lock) +{ + debug_rt_mutex_unlock(lock); + + rt_mutex_deadlock_account_unlock(current); + + if (!rt_mutex_has_waiters(lock)) { + lock->owner = NULL; + raw_spin_unlock(&lock->wait_lock); + return; + } + + wakeup_next_waiter(lock); + + raw_spin_unlock(&lock->wait_lock); + + /* Undo pi boosting.when necessary */ + rt_mutex_adjust_prio(current); +} + +static void noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) +{ + raw_spin_lock(&lock->wait_lock); + __rt_spin_lock_slowunlock(lock); +} + +static void noinline __sched rt_spin_lock_slowunlock_hirq(struct rt_mutex *lock) +{ + int ret; + + do { + ret = raw_spin_trylock(&lock->wait_lock); + } while (!ret); + + __rt_spin_lock_slowunlock(lock); +} + +void __lockfunc rt_spin_lock(spinlock_t *lock) +{ + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); +} +EXPORT_SYMBOL(rt_spin_lock); + +void __lockfunc __rt_spin_lock(struct rt_mutex *lock) +{ + rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock); +} +EXPORT_SYMBOL(__rt_spin_lock); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) +{ + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); +} +EXPORT_SYMBOL(rt_spin_lock_nested); +#endif + +void __lockfunc rt_spin_unlock(spinlock_t *lock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(rt_spin_unlock); + +void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock_hirq); +} + +void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) +{ + rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(__rt_spin_unlock); + +/* + * Wait for the lock to get unlocked: instead of polling for an unlock + * (like raw spinlocks do), we lock and unlock, to force the kernel to + * schedule if there's contention: + */ +void __lockfunc rt_spin_unlock_wait(spinlock_t *lock) +{ + spin_lock(lock); + spin_unlock(lock); +} +EXPORT_SYMBOL(rt_spin_unlock_wait); + +int __lockfunc __rt_spin_trylock(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. * @@ -894,6 +1299,23 @@ 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; @@ -917,7 +1339,7 @@ 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; @@ -994,7 +1416,7 @@ * 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); } /* @@ -1008,7 +1430,7 @@ { 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); @@ -1033,7 +1455,8 @@ __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); @@ -1069,17 +1492,17 @@ 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); } @@ -1097,7 +1520,8 @@ 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; @@ -1120,6 +1544,12 @@ 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); @@ -1153,25 +1583,102 @@ } } +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; } @@ -1188,13 +1695,17 @@ ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk); if (likely(!ret)) - ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); + ret = __rt_mutex_slowlock(lock, state, timeout, &waiter, + ww_ctx); set_current_state(TASK_RUNNING); if (unlikely(ret)) { - remove_waiter(lock, &waiter); + if (rt_mutex_has_waiters(lock)) + remove_waiter(lock, &waiter); rt_mutex_handle_deadlock(ret, chwalk, &waiter); + } else if (ww_ctx) { + ww_mutex_account_lock(lock, ww_ctx); } /* @@ -1233,7 +1744,8 @@ * The mutex has currently no owner. Lock the wait lock and * try to acquire the lock. */ - raw_spin_lock(&lock->wait_lock); + if (!raw_spin_trylock(&lock->wait_lock)) + return 0; ret = try_to_take_rt_mutex(lock, current, NULL); @@ -1319,31 +1831,36 @@ */ 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 @@ -1376,7 +1893,7 @@ { 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); @@ -1393,7 +1910,7 @@ { 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); @@ -1406,11 +1923,30 @@ 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 @@ -1430,6 +1966,7 @@ return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, RT_MUTEX_MIN_CHAINWALK, + NULL, rt_mutex_slowlock); } EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); @@ -1488,13 +2025,12 @@ 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 @@ -1509,7 +2045,7 @@ 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); @@ -1557,6 +2093,35 @@ 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); @@ -1626,7 +2191,7 @@ set_current_state(TASK_INTERRUPTIBLE); - ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); + ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL); set_current_state(TASK_RUNNING); @@ -1643,3 +2208,89 @@ 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, + RT_MUTEX_FULL_CHAINWALK, 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, + RT_MUTEX_FULL_CHAINWALK, 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) +{ + /* + * The unlocking fastpath is the 0->1 transition from 'locked' + * into 'unlocked' state: + */ + if (lock->ctx) { +#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, 1, _RET_IP_); + rt_mutex_unlock(&lock->base.lock); +} +EXPORT_SYMBOL(ww_mutex_unlock); +#endif diff -Nur linux-3.18.9.orig/kernel/locking/rtmutex_common.h linux-3.18.9/kernel/locking/rtmutex_common.h --- linux-3.18.9.orig/kernel/locking/rtmutex_common.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/locking/rtmutex_common.h 2015-03-15 16:03:03.836094874 -0500 @@ -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); @@ -138,4 +142,14 @@ # 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-3.18.9.orig/kernel/locking/spinlock.c linux-3.18.9/kernel/locking/spinlock.c --- linux-3.18.9.orig/kernel/locking/spinlock.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/locking/spinlock.c 2015-03-15 16:03:03.840094875 -0500 @@ -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-3.18.9.orig/kernel/locking/spinlock_debug.c linux-3.18.9/kernel/locking/spinlock_debug.c --- linux-3.18.9.orig/kernel/locking/spinlock_debug.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/locking/spinlock_debug.c 2015-03-15 16:03:03.840094875 -0500 @@ -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-3.18.9.orig/kernel/panic.c linux-3.18.9/kernel/panic.c --- linux-3.18.9.orig/kernel/panic.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/panic.c 2015-03-15 16:03:03.840094875 -0500 @@ -384,9 +384,11 @@ 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-3.18.9.orig/kernel/power/hibernate.c linux-3.18.9/kernel/power/hibernate.c --- linux-3.18.9.orig/kernel/power/hibernate.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/power/hibernate.c 2015-03-15 16:03:03.840094875 -0500 @@ -287,6 +287,8 @@ local_irq_disable(); + system_state = SYSTEM_SUSPEND; + error = syscore_suspend(); if (error) { printk(KERN_ERR "PM: Some system devices failed to power down, " @@ -316,6 +318,7 @@ syscore_resume(); Enable_irqs: + system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: @@ -439,6 +442,7 @@ goto Enable_cpus; local_irq_disable(); + system_state = SYSTEM_SUSPEND; error = syscore_suspend(); if (error) @@ -472,6 +476,7 @@ syscore_resume(); Enable_irqs: + system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: @@ -557,6 +562,7 @@ goto Platform_finish; local_irq_disable(); + system_state = SYSTEM_SUSPEND; syscore_suspend(); if (pm_wakeup_pending()) { error = -EAGAIN; @@ -569,6 +575,7 @@ Power_up: syscore_resume(); + system_state = SYSTEM_RUNNING; local_irq_enable(); enable_nonboot_cpus(); diff -Nur linux-3.18.9.orig/kernel/power/suspend.c linux-3.18.9/kernel/power/suspend.c --- linux-3.18.9.orig/kernel/power/suspend.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/power/suspend.c 2015-03-15 16:03:03.840094875 -0500 @@ -318,6 +318,8 @@ arch_suspend_disable_irqs(); BUG_ON(!irqs_disabled()); + system_state = SYSTEM_SUSPEND; + error = syscore_suspend(); if (!error) { *wakeup = pm_wakeup_pending(); @@ -332,6 +334,8 @@ syscore_resume(); } + system_state = SYSTEM_RUNNING; + arch_suspend_enable_irqs(); BUG_ON(irqs_disabled()); diff -Nur linux-3.18.9.orig/kernel/printk/printk.c linux-3.18.9/kernel/printk/printk.c --- linux-3.18.9.orig/kernel/printk/printk.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/printk/printk.c 2015-03-15 16:03:03.840094875 -0500 @@ -1165,6 +1165,7 @@ { char *text; int len = 0; + int attempts = 0; text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); if (!text) @@ -1176,7 +1177,14 @@ 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; @@ -1197,6 +1205,14 @@ 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 */ @@ -1210,6 +1226,14 @@ 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 */ @@ -1250,6 +1274,7 @@ clear_seq = log_next_seq; clear_idx = log_next_idx; } +out: raw_spin_unlock_irq(&logbuf_lock); kfree(text); @@ -1407,6 +1432,7 @@ if (!console_drivers) return; + migrate_disable(); for_each_console(con) { if (exclusive_console && con != exclusive_console) continue; @@ -1419,6 +1445,7 @@ continue; con->write(con, text, len); } + migrate_enable(); } /* @@ -1479,6 +1506,15 @@ 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; @@ -1613,6 +1649,62 @@ return textlen; } +#ifdef CONFIG_EARLY_PRINTK +struct console *early_console; + +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) @@ -1629,6 +1721,13 @@ /* cpu currently holding logbuf_lock in this function */ static volatile 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 == SCHED_MESSAGE_LOGLEVEL) { level = -1; in_sched = true; @@ -1769,8 +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 @@ -1778,7 +1876,7 @@ */ if (console_trylock_for_printk()) console_unlock(); - preempt_enable(); + migrate_enable(); lockdep_on(); } @@ -1878,29 +1976,6 @@ #endif /* CONFIG_PRINTK */ -#ifdef CONFIG_EARLY_PRINTK -struct console *early_console; - -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 __visible void early_printk(const char *fmt, ...) -{ - va_list ap; - - va_start(ap, fmt); - early_vprintk(fmt, ap); - va_end(ap); -} -#endif - static int __add_preferred_console(char *name, int idx, char *options, char *brl_options) { @@ -2140,11 +2215,16 @@ 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); @@ -2232,12 +2312,17 @@ 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 } console_locked = 0; diff -Nur linux-3.18.9.orig/kernel/ptrace.c linux-3.18.9/kernel/ptrace.c --- linux-3.18.9.orig/kernel/ptrace.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/ptrace.c 2015-03-15 16:03:03.840094875 -0500 @@ -129,7 +129,12 @@ spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !__fatal_signal_pending(task)) { - task->state = __TASK_TRACED; + raw_spin_lock_irq(&task->pi_lock); + if (task->state & __TASK_TRACED) + task->state = __TASK_TRACED; + else + task->saved_state = __TASK_TRACED; + raw_spin_unlock_irq(&task->pi_lock); ret = true; } spin_unlock_irq(&task->sighand->siglock); diff -Nur linux-3.18.9.orig/kernel/rcu/tiny.c linux-3.18.9/kernel/rcu/tiny.c --- linux-3.18.9.orig/kernel/rcu/tiny.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/rcu/tiny.c 2015-03-15 16:03:03.840094875 -0500 @@ -370,6 +370,7 @@ } EXPORT_SYMBOL_GPL(call_rcu_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /* * Post an RCU bottom-half callback to be invoked after any subsequent * quiescent state. @@ -379,6 +380,7 @@ __call_rcu(head, func, &rcu_bh_ctrlblk); } EXPORT_SYMBOL_GPL(call_rcu_bh); +#endif void rcu_init(void) { diff -Nur linux-3.18.9.orig/kernel/rcu/tree.c linux-3.18.9/kernel/rcu/tree.c --- linux-3.18.9.orig/kernel/rcu/tree.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/rcu/tree.c 2015-03-15 16:03:03.840094875 -0500 @@ -56,6 +56,11 @@ #include #include #include +#include +#include +#include +#include +#include "../time/tick-internal.h" #include "tree.h" #include "rcu.h" @@ -152,8 +157,6 @@ */ static int rcu_scheduler_fully_active __read_mostly; -#ifdef CONFIG_RCU_BOOST - /* * Control variables for per-CPU and per-rcu_node kthreads. These * handle all flavors of RCU. @@ -163,8 +166,6 @@ DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); DEFINE_PER_CPU(char, rcu_cpu_has_work); -#endif /* #ifdef CONFIG_RCU_BOOST */ - static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); static void invoke_rcu_core(void); static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); @@ -207,6 +208,19 @@ } } +#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)) { @@ -216,6 +230,7 @@ __this_cpu_write(rcu_bh_data.passed_quiesce, 1); } } +#endif static DEFINE_PER_CPU(int, rcu_sched_qs_mask); @@ -336,6 +351,7 @@ } EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /* * Return the number of RCU BH batches processed thus far for debug & stats. */ @@ -362,6 +378,7 @@ force_quiescent_state(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); +#endif /* * Show the state of the grace-period kthreads. @@ -1411,7 +1428,7 @@ !ACCESS_ONCE(rsp->gp_flags) || !rsp->gp_kthread) return; - wake_up(&rsp->gp_wq); + swait_wake(&rsp->gp_wq); } /* @@ -1793,7 +1810,7 @@ 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. */ @@ -1821,7 +1838,7 @@ 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) && @@ -2565,16 +2582,14 @@ /* * 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")); } /* @@ -2588,18 +2603,105 @@ { 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 = &__get_cpu_var(rcu_cpu_kthread_status); + char work, *workp = &__get_cpu_var(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. @@ -2734,6 +2836,7 @@ } EXPORT_SYMBOL_GPL(call_rcu_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /* * Queue an RCU callback for invocation after a quicker grace period. */ @@ -2742,6 +2845,7 @@ __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. @@ -2833,6 +2937,7 @@ } EXPORT_SYMBOL_GPL(synchronize_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /** * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. * @@ -2859,6 +2964,7 @@ wait_rcu_gp(call_rcu_bh); } EXPORT_SYMBOL_GPL(synchronize_rcu_bh); +#endif /** * get_state_synchronize_rcu - Snapshot current RCU state @@ -3341,6 +3447,7 @@ mutex_unlock(&rsp->barrier_mutex); } +#ifndef CONFIG_PREEMPT_RT_FULL /** * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. */ @@ -3349,6 +3456,7 @@ _rcu_barrier(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_barrier_bh); +#endif /** * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. @@ -3658,7 +3766,7 @@ } rsp->rda = rda; - 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) @@ -3755,7 +3863,6 @@ 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-3.18.9.orig/kernel/rcu/tree.h linux-3.18.9/kernel/rcu/tree.h --- linux-3.18.9.orig/kernel/rcu/tree.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/rcu/tree.h 2015-03-15 16:03:03.840094875 -0500 @@ -28,6 +28,7 @@ #include #include #include +#include /* * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and @@ -208,7 +209,7 @@ /* 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]; @@ -348,7 +349,7 @@ atomic_long_t nocb_follower_count_lazy; /* (approximate). */ int nocb_p_count; /* # CBs being invoked by kthread */ int nocb_p_count_lazy; /* (approximate). */ - 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. */ @@ -439,7 +440,7 @@ 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. */ @@ -570,10 +571,9 @@ 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-3.18.9.orig/kernel/rcu/tree_plugin.h linux-3.18.9/kernel/rcu/tree_plugin.h --- linux-3.18.9.orig/kernel/rcu/tree_plugin.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/rcu/tree_plugin.h 2015-03-15 16:03:03.844094875 -0500 @@ -24,12 +24,6 @@ * Paul E. McKenney */ -#include -#include -#include -#include -#include "../time/tick-internal.h" - #define RCU_KTHREAD_PRIO 1 #ifdef CONFIG_RCU_BOOST @@ -335,7 +329,7 @@ } /* Hardware IRQ handlers cannot block, complain if they get here. */ - if (WARN_ON_ONCE(in_irq() || in_serving_softirq())) { + if (WARN_ON_ONCE(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET))) { local_irq_restore(flags); return; } @@ -635,15 +629,6 @@ 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. */ @@ -1072,6 +1057,19 @@ #endif /* #else #ifdef CONFIG_TREE_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 = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); +#endif /* #ifdef CONFIG_RCU_BOOST */ +} + #ifdef CONFIG_RCU_BOOST #include "../locking/rtmutex_common.h" @@ -1103,16 +1101,6 @@ #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 @@ -1261,23 +1249,6 @@ } /* - * 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. */ @@ -1332,67 +1303,6 @@ 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 = RCU_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 @@ -1426,26 +1336,13 @@ 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)); rnp = rcu_get_root(rcu_state_p); (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); if (NUM_RCU_NODES > 1) { @@ -1472,11 +1369,6 @@ 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; @@ -1500,7 +1392,7 @@ #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 @@ -1518,7 +1410,9 @@ return rcu_cpu_has_callbacks(cpu, 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. @@ -1615,6 +1509,8 @@ 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 @@ -1655,7 +1551,7 @@ 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. @@ -2001,7 +1897,7 @@ */ 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]); } /* @@ -2019,8 +1915,8 @@ 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 @@ -2045,7 +1941,7 @@ 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); } } @@ -2238,7 +2134,7 @@ */ 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)) @@ -2266,7 +2162,7 @@ /* 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) { @@ -2347,7 +2243,7 @@ * List was empty, wake up the follower. * Memory barriers supplied by atomic_long_add(). */ - wake_up(&rdp->nocb_wq); + swait_wake(&rdp->nocb_wq); } } @@ -2368,7 +2264,7 @@ 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"! */ @@ -2539,7 +2435,7 @@ 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-3.18.9.orig/kernel/rcu/update.c linux-3.18.9/kernel/rcu/update.c --- linux-3.18.9.orig/kernel/rcu/update.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/rcu/update.c 2015-03-15 16:03:03.844094875 -0500 @@ -170,6 +170,7 @@ } 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? * @@ -196,6 +197,7 @@ return in_softirq() || irqs_disabled(); } EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); +#endif #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ diff -Nur linux-3.18.9.orig/kernel/relay.c linux-3.18.9/kernel/relay.c --- linux-3.18.9.orig/kernel/relay.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/relay.c 2015-03-15 16:03:03.844094875 -0500 @@ -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-3.18.9.orig/kernel/res_counter.c linux-3.18.9/kernel/res_counter.c --- linux-3.18.9.orig/kernel/res_counter.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/res_counter.c 2015-03-15 16:03:03.844094875 -0500 @@ -59,7 +59,7 @@ r = ret = 0; *limit_fail_at = NULL; - local_irq_save(flags); + local_irq_save_nort(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); r = res_counter_charge_locked(c, val, force); @@ -79,7 +79,7 @@ spin_unlock(&u->lock); } } - local_irq_restore(flags); + local_irq_restore_nort(flags); return ret; } @@ -104,7 +104,7 @@ struct res_counter *c; u64 ret = 0; - local_irq_save(flags); + local_irq_save_nort(flags); for (c = counter; c != top; c = c->parent) { u64 r; spin_lock(&c->lock); @@ -113,7 +113,7 @@ ret = r; spin_unlock(&c->lock); } - local_irq_restore(flags); + local_irq_restore_nort(flags); return ret; } diff -Nur linux-3.18.9.orig/kernel/sched/completion.c linux-3.18.9/kernel/sched/completion.c --- linux-3.18.9.orig/kernel/sched/completion.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/sched/completion.c 2015-03-15 16:03:03.844094875 -0500 @@ -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; } @@ -267,12 +267,12 @@ unsigned long flags; int ret = 1; - 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); @@ -290,10 +290,10 @@ unsigned long flags; int ret = 1; - spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = 0; - spin_unlock_irqrestore(&x->wait.lock, flags); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); return ret; } EXPORT_SYMBOL(completion_done); diff -Nur linux-3.18.9.orig/kernel/sched/core.c linux-3.18.9/kernel/sched/core.c --- linux-3.18.9.orig/kernel/sched/core.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/sched/core.c 2015-03-15 16:03:03.844094875 -0500 @@ -280,7 +280,11 @@ * 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 @@ -511,6 +515,7 @@ 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) @@ -622,6 +627,38 @@ 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); @@ -645,12 +682,14 @@ */ 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) { @@ -663,6 +702,8 @@ } unlock: rcu_read_unlock(); +preempt_en_rt: + preempt_enable_rt(); return cpu; } /* @@ -1193,6 +1234,18 @@ 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. * @@ -1237,7 +1290,7 @@ * 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(); } @@ -1252,7 +1305,8 @@ 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); @@ -1477,10 +1531,6 @@ { 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)); } /* @@ -1694,8 +1744,27 @@ */ 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; success = 1; /* we're going to change ->state */ cpu = task_cpu(p); @@ -1738,42 +1807,6 @@ } /** - * 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. * @@ -1787,11 +1820,23 @@ */ 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); @@ -1982,6 +2027,9 @@ 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); @@ -2265,8 +2313,12 @@ 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); @@ -2691,6 +2743,133 @@ 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()) { +#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()) { +#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: */ @@ -2794,6 +2973,8 @@ smp_mb__before_spinlock(); raw_spin_lock_irq(&rq->lock); + update_migrate_disable(prev); + switch_count = &prev->nivcsw; if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { if (unlikely(signal_pending_state(prev->state, prev))) { @@ -2801,19 +2982,6 @@ } 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; } @@ -2823,6 +2991,7 @@ next = pick_next_task(rq, prev); clear_tsk_need_resched(prev); + clear_tsk_need_resched_lazy(prev); clear_preempt_need_resched(); rq->skip_clock_update = 0; @@ -2852,9 +3021,20 @@ 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. */ @@ -2862,12 +3042,19 @@ blk_schedule_flush_plug(tsk); } +static inline void sched_update_worker(struct task_struct *tsk) +{ + if (tsk->flags & PF_WQ_WORKER) + wq_worker_running(tsk); +} + asmlinkage __visible void __sched schedule(void) { struct task_struct *tsk = current; sched_submit_work(tsk); __schedule(); + sched_update_worker(tsk); } EXPORT_SYMBOL(schedule); @@ -2917,9 +3104,26 @@ if (likely(!preemptible())) return; +#ifdef CONFIG_PREEMPT_LAZY + /* + * Check for lazy preemption + */ + if (current_thread_info()->preempt_lazy_count && + !test_thread_flag(TIF_NEED_RESCHED)) + return; +#endif do { __preempt_count_add(PREEMPT_ACTIVE); + /* + * The add/subtract must not be traced by the function + * tracer. But we still want to account for the + * preempt off latency tracer. Since the _notrace versions + * of add/subtract skip the accounting for latency tracer + * we must force it manually. + */ + start_critical_timings(); __schedule(); + stop_critical_timings(); __preempt_count_sub(PREEMPT_ACTIVE); /* @@ -4229,9 +4433,16 @@ static void __cond_resched(void) { - __preempt_count_add(PREEMPT_ACTIVE); - __schedule(); - __preempt_count_sub(PREEMPT_ACTIVE); + do { + __preempt_count_add(PREEMPT_ACTIVE); + __schedule(); + __preempt_count_sub(PREEMPT_ACTIVE); + /* + * Check again in case we missed a preemption + * opportunity between schedule and now. + */ + barrier(); + } while (need_resched()); } int __sched _cond_resched(void) @@ -4272,6 +4483,7 @@ } EXPORT_SYMBOL(__cond_resched_lock); +#ifndef CONFIG_PREEMPT_RT_FULL int __sched __cond_resched_softirq(void) { BUG_ON(!in_softirq()); @@ -4285,6 +4497,7 @@ return 0; } EXPORT_SYMBOL(__cond_resched_softirq); +#endif /** * yield - yield the current processor to other threads. @@ -4646,7 +4859,9 @@ /* 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: */ @@ -4688,11 +4903,91 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { - if (p->sched_class && p->sched_class->set_cpus_allowed) - p->sched_class->set_cpus_allowed(p, new_mask); + if (!migrate_disabled_updated(p)) { + if (p->sched_class && p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, new_mask); + p->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 = &__get_cpu_var(sched_cpumasks); + mask = &p->cpus_allowed; + + cpumask_andnot(cpumask, mask, &sched_down_cpumask); + + if (!cpumask_weight(cpumask)) { + /* It's only on this CPU? */ + task_rq_unlock(rq, p, &flags); + mutex_unlock(&sched_down_mutex); + return 0; + } + + dest_cpu = cpumask_any_and(cpu_active_mask, cpumask); + + arg.task = p; + arg.dest_cpu = dest_cpu; + + task_rq_unlock(rq, p, &flags); + + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); + tlb_migrate_finish(p->mm); + mutex_unlock(&sched_down_mutex); + + return 1; } /* @@ -4738,7 +5033,7 @@ 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); @@ -4878,6 +5173,8 @@ #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. @@ -4892,7 +5189,11 @@ 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; } /* @@ -5235,6 +5536,10 @@ 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 } @@ -7176,7 +7481,8 @@ #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-3.18.9.orig/kernel/sched/cputime.c linux-3.18.9/kernel/sched/cputime.c --- linux-3.18.9.orig/kernel/sched/cputime.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/sched/cputime.c 2015-03-15 16:03:03.848094875 -0500 @@ -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-3.18.9.orig/kernel/sched/deadline.c linux-3.18.9/kernel/sched/deadline.c --- linux-3.18.9.orig/kernel/sched/deadline.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/sched/deadline.c 2015-03-15 16:03:03.848094875 -0500 @@ -570,6 +570,7 @@ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); timer->function = dl_task_timer; + timer->irqsafe = 1; } static diff -Nur linux-3.18.9.orig/kernel/sched/debug.c linux-3.18.9/kernel/sched/debug.c --- linux-3.18.9.orig/kernel/sched/debug.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/sched/debug.c 2015-03-15 16:03:03.848094875 -0500 @@ -256,6 +256,9 @@ P(rt_throttled); PN(rt_time); PN(rt_runtime); +#ifdef CONFIG_SMP + P(rt_nr_migratory); +#endif #undef PN #undef P @@ -634,6 +637,10 @@ #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-3.18.9.orig/kernel/sched/fair.c linux-3.18.9/kernel/sched/fair.c --- linux-3.18.9.orig/kernel/sched/fair.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/sched/fair.c 2015-03-15 16:03:03.848094875 -0500 @@ -2951,7 +2951,7 @@ 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. @@ -2975,7 +2975,7 @@ return; if (delta > ideal_runtime) - resched_curr(rq_of(cfs_rq)); + resched_curr_lazy(rq_of(cfs_rq)); } static void @@ -3115,7 +3115,7 @@ * validating it and just reschedule. */ if (queued) { - resched_curr(rq_of(cfs_rq)); + resched_curr_lazy(rq_of(cfs_rq)); return; } /* @@ -3306,7 +3306,7 @@ * 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 @@ -3925,7 +3925,7 @@ if (delta < 0) { if (rq->curr == p) - resched_curr(rq); + resched_curr_lazy(rq); return; } hrtick_start(rq, delta); @@ -4792,7 +4792,7 @@ 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 @@ -7576,7 +7576,7 @@ * '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; @@ -7601,7 +7601,7 @@ */ 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-3.18.9.orig/kernel/sched/features.h linux-3.18.9/kernel/sched/features.h --- linux-3.18.9.orig/kernel/sched/features.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/sched/features.h 2015-03-15 16:03:03.848094875 -0500 @@ -50,12 +50,18 @@ */ 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 SCHED_FEAT(FORCE_SD_OVERLAP, false) SCHED_FEAT(RT_RUNTIME_SHARE, true) SCHED_FEAT(LB_MIN, false) diff -Nur linux-3.18.9.orig/kernel/sched/Makefile linux-3.18.9/kernel/sched/Makefile --- linux-3.18.9.orig/kernel/sched/Makefile 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/sched/Makefile 2015-03-15 16:03:03.848094875 -0500 @@ -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-3.18.9.orig/kernel/sched/rt.c linux-3.18.9/kernel/sched/rt.c --- linux-3.18.9.orig/kernel/sched/rt.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/sched/rt.c 2015-03-15 16:03:03.848094875 -0500 @@ -43,6 +43,7 @@ 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; } diff -Nur linux-3.18.9.orig/kernel/sched/sched.h linux-3.18.9/kernel/sched/sched.h --- linux-3.18.9.orig/kernel/sched/sched.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/sched/sched.h 2015-03-15 16:03:03.848094875 -0500 @@ -1018,6 +1018,7 @@ #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 @@ -1210,6 +1211,15 @@ 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-3.18.9.orig/kernel/sched/wait-simple.c linux-3.18.9/kernel/sched/wait-simple.c --- linux-3.18.9.orig/kernel/sched/wait-simple.c 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/kernel/sched/wait-simple.c 2015-03-15 16:03:03.848094875 -0500 @@ -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-3.18.9.orig/kernel/sched/work-simple.c linux-3.18.9/kernel/sched/work-simple.c --- linux-3.18.9.orig/kernel/sched/work-simple.c 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/kernel/sched/work-simple.c 2015-03-15 16:03:03.852094875 -0500 @@ -0,0 +1,176 @@ +/* + * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@bmw-carit.de + * + * Provides a framework for enqueuing callbacks from irq context + * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context. + */ + +#include +#include +#include +#include +#include + +#define SWORK_EVENT_PENDING (1 << 0) + +static DEFINE_MUTEX(worker_mutex); +static struct sworker *glob_worker; + +struct sworker { + struct list_head events; + struct swait_head wq; + + raw_spinlock_t lock; + + struct task_struct *task; + int refs; +}; + +static bool swork_readable(struct sworker *worker) +{ + bool r; + + if (kthread_should_stop()) + return true; + + raw_spin_lock(&worker->lock); + r = !list_empty(&worker->events); + raw_spin_unlock(&worker->lock); + + return r; +} + +static int swork_kthread(void *arg) +{ + struct sworker *worker = arg; + + pr_info("swork_kthread enter\n"); + + for (;;) { + swait_event_interruptible(worker->wq, + swork_readable(worker)); + if (kthread_should_stop()) + break; + + raw_spin_lock(&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(&worker->lock); + + WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING, + &sev->flags)); + sev->func(sev); + raw_spin_lock(&worker->lock); + } + raw_spin_unlock(&worker->lock); + } + + pr_info("swork_kthread exit\n"); + 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) +{ + if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags)) + return false; + + WARN_ON(irqs_disabled()); + + raw_spin_lock(&glob_worker->lock); + list_add_tail(&sev->item, &glob_worker->events); + raw_spin_unlock(&glob_worker->lock); + + 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-3.18.9.orig/kernel/signal.c linux-3.18.9/kernel/signal.c --- linux-3.18.9.orig/kernel/signal.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/signal.c 2015-03-15 16:03:03.852094875 -0500 @@ -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; } @@ -1283,7 +1391,7 @@ } spin_unlock(&sighand->siglock); rcu_read_unlock(); - local_irq_restore(*flags); + local_irq_restore_nort(*flags); } return sighand; @@ -1528,7 +1636,8 @@ */ 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; @@ -1889,15 +1998,7 @@ 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-3.18.9.orig/kernel/softirq.c linux-3.18.9/kernel/softirq.c --- linux-3.18.9.orig/kernel/softirq.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/softirq.c 2015-03-15 16:03:03.852094875 -0500 @@ -21,10 +21,12 @@ #include #include #include +#include #include #include #include #include +#include #include #define CREATE_TRACE_POINTS @@ -62,6 +64,98 @@ "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 = &__get_cpu_var(softirq_runners); + + sr->runner[sirq] = current; +} + +static inline void softirq_clr_runner(unsigned int sirq) +{ + struct softirq_runner *sr = &__get_cpu_var(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 = &__get_cpu_var(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 +171,70 @@ wake_up_process(tsk); } +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, int need_rcu_bh_qs) +{ + 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; + } + + if (need_rcu_bh_qs) + rcu_bh_qs(); + local_irq_disable(); +} + +static void run_ksoftirqd(unsigned int cpu) +{ + local_irq_disable(); + if (ksoftirqd_softirq_pending()) { + __do_softirq(); + rcu_note_context_switch(cpu); + local_irq_enable(); + cond_resched(); + return; + } + local_irq_enable(); +} + /* * preempt_count and SOFTIRQ_OFFSET usage: * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving @@ -228,10 +386,8 @@ 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 @@ -250,36 +406,7 @@ /* 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, 1); pending = local_softirq_pending(); if (pending) { @@ -316,6 +443,285 @@ } /* + * 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) { } +static void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) { } + +#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, int need_rcu_bh_qs) +{ + 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(int need_rcu_bh_qs) +{ + 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, need_rcu_bh_qs); + } + softirq_clr_runner(i); + unlock_softirq(i); + WARN_ON(current->softirq_nestcnt != 1); + } +} + +static void __local_bh_disable(void) +{ + if (++current->softirq_nestcnt == 1) + migrate_disable(); +} + +void local_bh_disable(void) +{ + __local_bh_disable(); +} +EXPORT_SYMBOL(local_bh_disable); + +void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) +{ + __local_bh_disable(); + if (cnt & PREEMPT_CHECK_OFFSET) + preempt_disable(); +} + +static 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(1); + local_irq_enable(); + + if (--current->softirq_nestcnt == 0) + migrate_enable(); +} + +void local_bh_enable(void) +{ + __local_bh_enable(); +} +EXPORT_SYMBOL(local_bh_enable); + +extern void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) +{ + __local_bh_enable(); + if (cnt & PREEMPT_CHECK_OFFSET) + preempt_enable(); +} + +void local_bh_enable_ip(unsigned long ip) +{ + local_bh_enable(); +} +EXPORT_SYMBOL(local_bh_enable_ip); + +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(1); + current->softirq_nestcnt--; + rcu_note_context_switch(cpu); + local_irq_enable(); +} + +/* + * 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(0); + current->softirq_nestcnt--; + } +} + +static void do_raise_softirq_irqoff(unsigned int nr) +{ + trace_softirq_raise(nr); + or_softirq_pending(1UL << nr); + + /* + * 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 |= (1U << nr); + else if (__this_cpu_read(ksoftirqd)) + __this_cpu_read(ksoftirqd)->softirqs_raised |= (1U << nr); +} + +void __raise_softirq_irqoff(unsigned int nr) +{ + do_raise_softirq_irqoff(nr); + if (!in_irq() && !current->softirq_nestcnt) + wakeup_softirqd(); +} + +/* + * 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_softirqd(); +} + +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) +{ + struct sched_param param = { .sched_priority = 1 }; + + sched_setscheduler(current, SCHED_FIFO, ¶m); + /* Take over all pending softirqs when starting */ + local_irq_disable(); + current->softirqs_raised = local_softirq_pending(); + local_irq_enable(); +} + +static inline void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) +{ + struct sched_param param = { .sched_priority = 0 }; + + sched_setscheduler(current, SCHED_NORMAL, ¶m); +} + +#endif /* PREEMPT_RT_FULL */ +/* * Enter an interrupt context. */ void irq_enter(void) @@ -326,9 +732,9 @@ * 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(); @@ -336,6 +742,7 @@ static inline void invoke_softirq(void) { +#ifndef CONFIG_PREEMPT_RT_FULL if (!force_irqthreads) { #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK /* @@ -355,6 +762,15 @@ } 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(); + local_irq_restore(flags); +#endif } static inline void tick_irq_exit(void) @@ -391,26 +807,6 @@ 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; @@ -420,12 +816,6 @@ 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; @@ -442,15 +832,45 @@ 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, &__get_cpu_var(tasklet_vec), TASKLET_SOFTIRQ); local_irq_restore(flags); } EXPORT_SYMBOL(__tasklet_schedule); @@ -460,10 +880,7 @@ 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, &__get_cpu_var(tasklet_hi_vec), HI_SOFTIRQ); local_irq_restore(flags); } EXPORT_SYMBOL(__tasklet_hi_schedule); @@ -472,48 +889,116 @@ { 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(); +void tasklet_hi_enable(struct tasklet_struct *t) +{ + if (!atomic_dec_and_test(&t->count)) + return; + if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) + tasklet_hi_schedule(t); +} +EXPORT_SYMBOL(tasklet_hi_enable); + +static void __tasklet_action(struct softirq_action *a, + struct tasklet_struct *list) +{ + int loops = 1000000; while (list) { struct tasklet_struct *t = list; list = list->next; - if (tasklet_trylock(t)) { - if (!atomic_read(&t->count)) { - if (!test_and_clear_bit(TASKLET_STATE_SCHED, - &t->state)) - BUG(); - t->func(t->data); - tasklet_unlock(t); - continue; - } - tasklet_unlock(t); + /* + * Should always succeed - after a tasklist got on the + * list (after getting the SCHED bit set from 0 to 1), + * nothing but the tasklet softirq it got queued to can + * lock it: + */ + if (!tasklet_trylock(t)) { + WARN_ON(1); + continue; } - local_irq_disable(); t->next = NULL; - *__this_cpu_read(tasklet_vec.tail) = t; - __this_cpu_write(tasklet_vec.tail, &(t->next)); - __raise_softirq_irqoff(TASKLET_SOFTIRQ); - local_irq_enable(); + + /* + * If we cannot handle the tasklet because it's disabled, + * mark it as pending. tasklet_enable() will later + * re-schedule the tasklet. + */ + if (unlikely(atomic_read(&t->count))) { +out_disabled: + /* implicit unlock: */ + wmb(); + t->state = TASKLET_STATEF_PENDING; + continue; + } + + /* + * After this point on the tasklet might be rescheduled + * on another CPU, but it can only be added to another + * CPU's tasklet list if we unlock the tasklet (which we + * dont do yet). + */ + if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) + WARN_ON(1); + +again: + t->func(t->data); + + /* + * Try to unlock the tasklet. We must use cmpxchg, because + * another CPU might have scheduled or disabled the tasklet. + * We only allow the STATE_RUN -> 0 transition here. + */ + while (!tasklet_tryunlock(t)) { + /* + * If it got disabled meanwhile, bail out: + */ + if (atomic_read(&t->count)) + goto out_disabled; + /* + * If it got scheduled meanwhile, re-execute + * the tasklet function: + */ + if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) + goto again; + if (!--loops) { + printk("hm, tasklet state: %08lx\n", t->state); + WARN_ON(1); + tasklet_unlock(t); + break; + } + } } } +static void tasklet_action(struct softirq_action *a) +{ + struct tasklet_struct *list; + + local_irq_disable(); + list = __get_cpu_var(tasklet_vec).head; + __get_cpu_var(tasklet_vec).head = NULL; + __get_cpu_var(tasklet_vec).tail = &__get_cpu_var(tasklet_vec).head; + local_irq_enable(); + + __tasklet_action(a, list); +} + static void tasklet_hi_action(struct softirq_action *a) { struct tasklet_struct *list; @@ -524,30 +1009,7 @@ __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_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, @@ -568,7 +1030,7 @@ 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); @@ -642,26 +1104,26 @@ 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(); - rcu_note_context_switch(cpu); - local_irq_enable(); - cond_resched(); - 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 @@ -743,6 +1205,8 @@ static struct smp_hotplug_thread softirq_threads = { .store = &ksoftirqd, + .setup = ksoftirqd_set_sched_params, + .cleanup = ksoftirqd_clr_sched_params, .thread_should_run = ksoftirqd_should_run, .thread_fn = run_ksoftirqd, .thread_comm = "ksoftirqd/%u", diff -Nur linux-3.18.9.orig/kernel/stop_machine.c linux-3.18.9/kernel/stop_machine.c --- linux-3.18.9.orig/kernel/stop_machine.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/stop_machine.c 2015-03-15 16:03:03.852094875 -0500 @@ -30,12 +30,12 @@ atomic_t nr_todo; /* nr left to execute */ bool executed; /* actually executed? */ int ret; /* collected return value */ - struct completion completion; /* fired if nr_todo reaches 0 */ + struct task_struct *waiter; /* woken when nr_todo reaches 0 */ }; /* the actual stopper, one per every possible cpu, enabled on online cpus */ struct cpu_stopper { - spinlock_t lock; + raw_spinlock_t lock; bool enabled; /* is this stopper enabled? */ struct list_head works; /* list of pending works */ }; @@ -56,7 +56,7 @@ { memset(done, 0, sizeof(*done)); atomic_set(&done->nr_todo, nr_todo); - init_completion(&done->completion); + done->waiter = current; } /* signal completion unless @done is NULL */ @@ -65,8 +65,10 @@ if (done) { if (executed) done->executed = true; - if (atomic_dec_and_test(&done->nr_todo)) - complete(&done->completion); + if (atomic_dec_and_test(&done->nr_todo)) { + wake_up_process(done->waiter); + done->waiter = NULL; + } } } @@ -78,7 +80,7 @@ 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 +88,23 @@ } else cpu_stop_signal_done(work->done, false); - spin_unlock_irqrestore(&stopper->lock, flags); + raw_spin_unlock_irqrestore(&stopper->lock, flags); +} + +static void wait_for_stop_done(struct cpu_stop_done *done) +{ + set_current_state(TASK_UNINTERRUPTIBLE); + while (atomic_read(&done->nr_todo)) { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + /* + * We need to wait until cpu_stop_signal_done() has cleared + * done->waiter. + */ + while (done->waiter) + cpu_relax(); + set_current_state(TASK_RUNNING); } /** @@ -120,7 +138,7 @@ cpu_stop_init_done(&done, 1); cpu_stop_queue_work(cpu, &work); - wait_for_completion(&done.completion); + wait_for_stop_done(&done); return done.executed ? done.ret : -ENOENT; } @@ -248,7 +266,7 @@ 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 +299,7 @@ * This relies on the stopper workqueues to be FIFO. */ if (!cpu_active(cpu1) || !cpu_active(cpu2)) { - preempt_enable(); + preempt_enable_nort(); return -ENOENT; } @@ -295,9 +313,9 @@ &irq_cpu_stop_queue_work, &call_args, 1); lg_local_unlock(&stop_cpus_lock); - preempt_enable(); + preempt_enable_nort(); - wait_for_completion(&done.completion); + wait_for_stop_done(&done); return done.executed ? done.ret : -ENOENT; } @@ -329,7 +347,7 @@ 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 +361,13 @@ } /* - * 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); @@ -359,8 +379,8 @@ struct cpu_stop_done done; cpu_stop_init_done(&done, cpumask_weight(cpumask)); - queue_stop_cpus_work(cpumask, fn, arg, &done); - wait_for_completion(&done.completion); + queue_stop_cpus_work(cpumask, fn, arg, &done, false); + wait_for_stop_done(&done); return done.executed ? done.ret : -ENOENT; } @@ -439,9 +459,9 @@ 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 +473,13 @@ 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 +487,16 @@ 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(); @@ -481,7 +511,13 @@ kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL, ksym_buf), arg); + /* + * Make sure that the wakeup and setting done->waiter + * to NULL is atomic. + */ + local_irq_disable(); cpu_stop_signal_done(done, true); + local_irq_enable(); goto repeat; } } @@ -500,20 +536,20 @@ 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 +571,12 @@ 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; @@ -634,11 +672,11 @@ 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. */ - while (!completion_done(&done.completion)) + while (atomic_read(&done.nr_todo)) cpu_relax(); mutex_unlock(&stop_cpus_mutex); diff -Nur linux-3.18.9.orig/kernel/time/hrtimer.c linux-3.18.9/kernel/time/hrtimer.c --- linux-3.18.9.orig/kernel/time/hrtimer.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/time/hrtimer.c 2015-03-15 16:03:03.852094875 -0500 @@ -48,11 +48,13 @@ #include #include #include +#include #include #include #include +#include #include "timekeeping.h" @@ -568,8 +570,7 @@ * 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; @@ -604,6 +605,9 @@ 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 */ @@ -613,6 +617,21 @@ 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; @@ -678,6 +697,44 @@ 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. @@ -686,6 +743,7 @@ { schedule_work(&hrtimer_work); } +#endif #else @@ -694,6 +752,13 @@ 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) { @@ -701,7 +766,6 @@ } static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { } static inline void retrigger_next_event(void *arg) { } - #endif /* CONFIG_HIGH_RES_TIMERS */ /* @@ -819,6 +883,32 @@ } 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 * @@ -862,6 +952,11 @@ 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) { @@ -949,7 +1044,16 @@ 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) { @@ -963,15 +1067,26 @@ * 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. @@ -979,9 +1094,7 @@ 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; } } @@ -1072,7 +1185,7 @@ if (ret >= 0) return ret; - cpu_relax(); + hrtimer_wait_for_timer(timer); } } EXPORT_SYMBOL_GPL(hrtimer_cancel); @@ -1151,6 +1264,7 @@ 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 @@ -1234,6 +1348,126 @@ 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 /* @@ -1244,7 +1478,7 @@ { 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++; @@ -1279,6 +1513,15 @@ 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 @@ -1304,7 +1547,10 @@ break; } - __run_hrtimer(timer, &basenow); + if (!hrtimer_rt_defer(timer)) + __run_hrtimer(timer, &basenow); + else + raise = 1; } } @@ -1319,7 +1565,7 @@ if (expires_next.tv64 == KTIME_MAX || !tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; - return; + goto out; } /* @@ -1363,6 +1609,9 @@ 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); } /* @@ -1398,18 +1647,18 @@ __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: * @@ -1442,7 +1691,7 @@ 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; @@ -1467,10 +1716,16 @@ 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); } /* @@ -1492,16 +1747,18 @@ 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; @@ -1545,7 +1802,8 @@ 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; @@ -1562,8 +1820,10 @@ 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; @@ -1576,7 +1836,7 @@ 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: */ @@ -1603,6 +1863,12 @@ 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) { @@ -1617,6 +1883,26 @@ 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: */ @@ -1628,10 +1914,14 @@ 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 @@ -1744,9 +2034,7 @@ 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-3.18.9.orig/kernel/time/itimer.c linux-3.18.9/kernel/time/itimer.c --- linux-3.18.9.orig/kernel/time/itimer.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/time/itimer.c 2015-03-15 16:03:03.852094875 -0500 @@ -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-3.18.9.orig/kernel/time/jiffies.c linux-3.18.9/kernel/time/jiffies.c --- linux-3.18.9.orig/kernel/time/jiffies.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/time/jiffies.c 2015-03-15 16:03:03.852094875 -0500 @@ -73,7 +73,8 @@ .shift = JIFFIES_SHIFT, }; -__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) @@ -82,9 +83,9 @@ 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-3.18.9.orig/kernel/time/ntp.c linux-3.18.9/kernel/time/ntp.c --- linux-3.18.9.orig/kernel/time/ntp.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/time/ntp.c 2015-03-15 16:03:03.852094875 -0500 @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -519,10 +520,52 @@ &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-3.18.9.orig/kernel/time/posix-cpu-timers.c linux-3.18.9/kernel/time/posix-cpu-timers.c --- linux-3.18.9.orig/kernel/time/posix-cpu-timers.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/time/posix-cpu-timers.c 2015-03-15 16:03:03.856094875 -0500 @@ -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; @@ -1047,7 +1048,7 @@ /* * 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); @@ -1113,10 +1114,11 @@ 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; @@ -1130,13 +1132,13 @@ * 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 @@ -1194,6 +1196,190 @@ } } +#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-3.18.9.orig/kernel/time/posix-timers.c linux-3.18.9/kernel/time/posix-timers.c --- linux-3.18.9.orig/kernel/time/posix-timers.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/time/posix-timers.c 2015-03-15 16:03:03.856094875 -0500 @@ -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-3.18.9.orig/kernel/time/tick-common.c linux-3.18.9/kernel/time/tick-common.c --- linux-3.18.9.orig/kernel/time/tick-common.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/time/tick-common.c 2015-03-15 16:03:03.856094875 -0500 @@ -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_mode(dev, CLOCK_EVT_MODE_ONESHOT); diff -Nur linux-3.18.9.orig/kernel/time/tick-internal.h linux-3.18.9/kernel/time/tick-internal.h --- linux-3.18.9.orig/kernel/time/tick-internal.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/time/tick-internal.h 2015-03-15 16:03:03.856094875 -0500 @@ -6,7 +6,8 @@ #include "timekeeping.h" -extern seqlock_t jiffies_lock; +extern raw_spinlock_t jiffies_lock; +extern seqcount_t jiffies_seq; #define CS_NAME_LEN 32 diff -Nur linux-3.18.9.orig/kernel/time/tick-sched.c linux-3.18.9/kernel/time/tick-sched.c --- linux-3.18.9.orig/kernel/time/tick-sched.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/time/tick-sched.c 2015-03-15 16:03:03.856094875 -0500 @@ -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; } @@ -222,6 +227,7 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { .func = nohz_full_kick_work_func, + .flags = IRQ_WORK_HARD_IRQ, }; /* @@ -580,10 +586,10 @@ /* 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(cpu, &rcu_delta_jiffies) || arch_needs_cpu() || irq_work_needs_cpu()) { @@ -761,14 +767,7 @@ 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; } @@ -1156,6 +1155,7 @@ * 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-3.18.9.orig/kernel/time/timekeeping.c linux-3.18.9/kernel/time/timekeeping.c --- linux-3.18.9.orig/kernel/time/timekeeping.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/time/timekeeping.c 2015-03-15 16:03:03.856094875 -0500 @@ -1814,8 +1814,10 @@ */ 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-3.18.9.orig/kernel/time/timer.c linux-3.18.9/kernel/time/timer.c --- linux-3.18.9.orig/kernel/time/timer.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/time/timer.c 2015-03-15 16:03:03.856094875 -0500 @@ -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; @@ -758,6 +761,36 @@ } } +#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) @@ -788,14 +821,8 @@ * 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; @@ -969,6 +996,29 @@ } 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(&(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 @@ -1026,7 +1076,7 @@ } EXPORT_SYMBOL(try_to_del_timer_sync); -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) /** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated @@ -1086,7 +1136,7 @@ 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); @@ -1207,15 +1257,17 @@ 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; + wakeup_timer_waiters(base); spin_unlock_irq(&base->lock); } @@ -1355,17 +1407,31 @@ if (cpu_is_offline(smp_processor_id())) return expires; +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * On PREEMPT_RT we cannot sleep here. If the trylock does not + * succeed then we return the worst-case 'expires in 1 tick' + * value. We use the rt functions here directly to avoid a + * migrate_disable() call. + */ + if (!spin_do_trylock(&base->lock)) + return now + 1; +#else spin_lock(&base->lock); +#endif if (base->active_timers) { if (time_before_eq(base->next_timer, base->timer_jiffies)) base->next_timer = __next_timer_interrupt(base); expires = base->next_timer; } +#ifdef CONFIG_PREEMPT_RT_FULL + rt_spin_unlock_after_trylock_in_irq(&base->lock); +#else spin_unlock(&base->lock); +#endif if (time_before_eq(expires, now)) return now; - return cmp_next_hrtimer_event(now, expires); } #endif @@ -1381,13 +1447,13 @@ /* 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(cpu, user_tick); #ifdef CONFIG_IRQ_WORK if (in_irq()) irq_work_tick(); #endif - scheduler_tick(); run_posix_cpu_timers(p); } @@ -1400,6 +1466,10 @@ hrtimer_run_pending(); +#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) + irq_work_tick(); +#endif + if (time_after_eq(jiffies, base->timer_jiffies)) __run_timers(base); } @@ -1574,6 +1644,9 @@ base = per_cpu(tvec_bases, cpu); } +#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); @@ -1613,7 +1686,7 @@ 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. @@ -1634,7 +1707,7 @@ spin_unlock(&old_base->lock); spin_unlock_irq(&new_base->lock); - put_cpu_var(tvec_bases); + put_local_var(tvec_bases); } #endif /* CONFIG_HOTPLUG_CPU */ diff -Nur linux-3.18.9.orig/kernel/trace/Kconfig linux-3.18.9/kernel/trace/Kconfig --- linux-3.18.9.orig/kernel/trace/Kconfig 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/trace/Kconfig 2015-03-15 16:03:03.856094875 -0500 @@ -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-3.18.9.orig/kernel/trace/latency_hist.c linux-3.18.9/kernel/trace/latency_hist.c --- linux-3.18.9.orig/kernel/trace/latency_hist.c 1969-12-31 18:00:00.000000000 -0600 +++ linux-3.18.9/kernel/trace/latency_hist.c 2015-03-15 16:03:03.860094875 -0500 @@ -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, int success); +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, int success) +{ + 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-3.18.9.orig/kernel/trace/Makefile linux-3.18.9/kernel/trace/Makefile --- linux-3.18.9.orig/kernel/trace/Makefile 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/trace/Makefile 2015-03-15 16:03:03.860094875 -0500 @@ -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-3.18.9.orig/kernel/trace/trace.c linux-3.18.9/kernel/trace/trace.c --- linux-3.18.9.orig/kernel/trace/trace.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/trace/trace.c 2015-03-15 16:03:03.860094875 -0500 @@ -1579,6 +1579,7 @@ 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 @@ -1588,8 +1589,11 @@ #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); @@ -2509,14 +2513,17 @@ static void print_lat_help_header(struct seq_file *m) { - seq_puts(m, "# _------=> CPU# \n"); - seq_puts(m, "# / _-----=> irqs-off \n"); - seq_puts(m, "# | / _----=> need-resched \n"); - seq_puts(m, "# || / _---=> hardirq/softirq \n"); - seq_puts(m, "# ||| / _--=> preempt-depth \n"); - seq_puts(m, "# |||| / delay \n"); - seq_puts(m, "# cmd pid ||||| time | caller \n"); - seq_puts(m, "# \\ / ||||| \\ | / \n"); + seq_puts(m, "# _--------=> CPU# \n"); + seq_puts(m, "# / _-------=> irqs-off \n"); + seq_puts(m, "# | / _------=> need-resched \n"); + seq_puts(m, "# || / _-----=> need-resched_lazy \n"); + seq_puts(m, "# ||| / _----=> hardirq/softirq \n"); + seq_puts(m, "# |||| / _---=> preempt-depth \n"); + seq_puts(m, "# ||||| / _--=> preempt-lazy-depth\n"); + seq_puts(m, "# |||||| / _-=> migrate-disable \n"); + seq_puts(m, "# ||||||| / delay \n"); + seq_puts(m, "# cmd pid |||||||| time | caller \n"); + seq_puts(m, "# \\ / |||||||| \\ | / \n"); } static void print_event_info(struct trace_buffer *buf, struct seq_file *m) @@ -2540,13 +2547,16 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m) { print_event_info(buf, m); - seq_puts(m, "# _-----=> irqs-off\n"); - seq_puts(m, "# / _----=> need-resched\n"); - seq_puts(m, "# | / _---=> hardirq/softirq\n"); - seq_puts(m, "# || / _--=> preempt-depth\n"); - seq_puts(m, "# ||| / delay\n"); - seq_puts(m, "# TASK-PID CPU# |||| TIMESTAMP FUNCTION\n"); - seq_puts(m, "# | | | |||| | |\n"); + seq_puts(m, "# _-------=> irqs-off \n"); + seq_puts(m, "# / _------=> need-resched \n"); + seq_puts(m, "# |/ _-----=> need-resched_lazy \n"); + seq_puts(m, "# ||/ _----=> hardirq/softirq \n"); + seq_puts(m, "# |||/ _---=> preempt-depth \n"); + seq_puts(m, "# ||||/ _--=> preempt-lazy-depth\n"); + seq_puts(m, "# ||||| / _-=> migrate-disable \n"); + seq_puts(m, "# |||||| / delay\n"); + seq_puts(m, "# TASK-PID CPU# |||||| TIMESTAMP FUNCTION\n"); + seq_puts(m, "# | | | |||||| | |\n"); } void diff -Nur linux-3.18.9.orig/kernel/trace/trace_events.c linux-3.18.9/kernel/trace/trace_events.c --- linux-3.18.9.orig/kernel/trace/trace_events.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/trace/trace_events.c 2015-03-15 16:03:03.860094875 -0500 @@ -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; } diff -Nur linux-3.18.9.orig/kernel/trace/trace.h linux-3.18.9/kernel/trace/trace.h --- linux-3.18.9.orig/kernel/trace/trace.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/trace/trace.h 2015-03-15 16:03:03.860094875 -0500 @@ -119,6 +119,7 @@ * 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, @@ -127,6 +128,7 @@ 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-3.18.9.orig/kernel/trace/trace_irqsoff.c linux-3.18.9/kernel/trace/trace_irqsoff.c --- linux-3.18.9.orig/kernel/trace/trace_irqsoff.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/trace/trace_irqsoff.c 2015-03-15 16:03:03.860094875 -0500 @@ -17,6 +17,7 @@ #include #include "trace.h" +#include static struct trace_array *irqsoff_trace __read_mostly; static int tracer_enabled __read_mostly; @@ -435,11 +436,13 @@ { if (preempt_trace() || irq_trace()) start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + trace_preemptirqsoff_hist(TRACE_START, 1); } EXPORT_SYMBOL_GPL(start_critical_timings); void stop_critical_timings(void) { + trace_preemptirqsoff_hist(TRACE_STOP, 0); if (preempt_trace() || irq_trace()) stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } @@ -449,6 +452,7 @@ #ifdef CONFIG_PROVE_LOCKING void time_hardirqs_on(unsigned long a0, unsigned long a1) { + trace_preemptirqsoff_hist(IRQS_ON, 0); if (!preempt_trace() && irq_trace()) stop_critical_timing(a0, a1); } @@ -457,6 +461,7 @@ { if (!preempt_trace() && irq_trace()) start_critical_timing(a0, a1); + trace_preemptirqsoff_hist(IRQS_OFF, 1); } #else /* !CONFIG_PROVE_LOCKING */ @@ -482,6 +487,7 @@ */ void trace_hardirqs_on(void) { + trace_preemptirqsoff_hist(IRQS_ON, 0); if (!preempt_trace() && irq_trace()) stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } @@ -491,11 +497,13 @@ { if (!preempt_trace() && irq_trace()) start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + trace_preemptirqsoff_hist(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); } @@ -505,6 +513,7 @@ { if (!preempt_trace() && irq_trace()) start_critical_timing(CALLER_ADDR0, caller_addr); + trace_preemptirqsoff_hist(IRQS_OFF, 1); } EXPORT_SYMBOL(trace_hardirqs_off_caller); @@ -514,12 +523,14 @@ #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-3.18.9.orig/kernel/trace/trace_output.c linux-3.18.9/kernel/trace/trace_output.c --- linux-3.18.9.orig/kernel/trace/trace_output.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/trace/trace_output.c 2015-03-15 16:03:03.860094875 -0500 @@ -410,6 +410,7 @@ { char hardsoft_irq; char need_resched; + char need_resched_lazy; char irqs_off; int hardirq; int softirq; @@ -438,6 +439,8 @@ need_resched = '.'; break; } + need_resched_lazy = + (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; hardsoft_irq = (hardirq && softirq) ? 'H' : @@ -445,8 +448,9 @@ softirq ? 's' : '.'; - if (!trace_seq_printf(s, "%c%c%c", - irqs_off, need_resched, hardsoft_irq)) + if (!trace_seq_printf(s, "%c%c%c%c", + irqs_off, need_resched, need_resched_lazy, + hardsoft_irq)) return 0; if (entry->preempt_count) @@ -454,6 +458,16 @@ else ret = trace_seq_putc(s, '.'); + if (entry->preempt_lazy_count) + ret = trace_seq_printf(s, "%x", entry->preempt_lazy_count); + else + ret = trace_seq_putc(s, '.'); + + if (entry->migrate_disable) + ret = trace_seq_printf(s, "%x", entry->migrate_disable); + else + ret = trace_seq_putc(s, '.'); + return ret; } diff -Nur linux-3.18.9.orig/kernel/user.c linux-3.18.9/kernel/user.c --- linux-3.18.9.orig/kernel/user.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/user.c 2015-03-15 16:03:03.860094875 -0500 @@ -158,11 +158,11 @@ 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-3.18.9.orig/kernel/watchdog.c linux-3.18.9/kernel/watchdog.c --- linux-3.18.9.orig/kernel/watchdog.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/watchdog.c 2015-03-15 16:03:03.864094875 -0500 @@ -248,6 +248,8 @@ #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, @@ -281,13 +283,21 @@ /* 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; @@ -430,6 +440,7 @@ /* 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-3.18.9.orig/kernel/workqueue.c linux-3.18.9/kernel/workqueue.c --- linux-3.18.9.orig/kernel/workqueue.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/workqueue.c 2015-03-15 16:03:03.864094875 -0500 @@ -48,6 +48,8 @@ #include #include #include +#include +#include #include "workqueue_internal.h" @@ -121,15 +123,20 @@ * 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. * * 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. */ @@ -177,7 +184,7 @@ 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; @@ -206,7 +213,7 @@ /* * 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; @@ -321,6 +328,8 @@ 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); @@ -329,14 +338,14 @@ #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 for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ @@ -348,7 +357,7 @@ * @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. * @@ -380,7 +389,7 @@ * @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. * @@ -392,6 +401,31 @@ 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; @@ -542,7 +576,7 @@ * @wq: the target workqueue * @node: the node ID * - * This must be called either with pwq_lock held or sched RCU read locked. + * This must be called either with pwq_lock 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. * @@ -646,8 +680,8 @@ * @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 @@ -784,51 +818,44 @@ */ 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; /* @@ -837,29 +864,26 @@ * 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); + } } /** @@ -1053,12 +1077,12 @@ { 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); + 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); } } @@ -1160,7 +1184,7 @@ 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) { @@ -1179,6 +1203,7 @@ 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. @@ -1217,14 +1242,16 @@ 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; } @@ -1293,7 +1320,7 @@ * 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); @@ -1301,6 +1328,8 @@ 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(); @@ -1357,10 +1386,8 @@ /* 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); @@ -1376,7 +1403,9 @@ insert_work(pwq, work, worklist, work_flags); +out: spin_unlock(&pwq->pool->lock); + rcu_read_unlock(); } /** @@ -1396,14 +1425,14 @@ 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); @@ -1470,14 +1499,14 @@ 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); @@ -1512,7 +1541,7 @@ 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 */ @@ -1545,7 +1574,9 @@ 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); @@ -1578,7 +1609,9 @@ 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) @@ -1746,7 +1779,9 @@ 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); } @@ -2641,14 +2676,14 @@ 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) { @@ -2675,10 +2710,11 @@ 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; } @@ -2727,7 +2763,7 @@ /* 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); @@ -2772,10 +2808,10 @@ */ 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); @@ -2810,7 +2846,7 @@ 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); @@ -2996,7 +3032,8 @@ 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, @@ -3004,7 +3041,8 @@ delim = " "; } written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); - rcu_read_unlock_sched(); + rcu_read_unlock(); + put_online_cpus(); return written; } @@ -3372,7 +3410,7 @@ * 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(). @@ -3426,8 +3464,8 @@ 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); } /** @@ -3532,7 +3570,7 @@ 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 @@ -4244,7 +4282,8 @@ struct pool_workqueue *pwq; bool ret; - rcu_read_lock_sched(); + rcu_read_lock(); + preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); @@ -4255,7 +4294,8 @@ 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; } @@ -4281,16 +4321,15 @@ 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; } EXPORT_SYMBOL_GPL(work_busy); @@ -4719,16 +4758,16 @@ * 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); diff -Nur linux-3.18.9.orig/kernel/workqueue_internal.h linux-3.18.9/kernel/workqueue_internal.h --- linux-3.18.9.orig/kernel/workqueue_internal.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/kernel/workqueue_internal.h 2015-03-15 16:03:03.864094875 -0500 @@ -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-3.18.9.orig/lib/debugobjects.c linux-3.18.9/lib/debugobjects.c --- linux-3.18.9.orig/lib/debugobjects.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/lib/debugobjects.c 2015-03-15 16:03:03.864094875 -0500 @@ -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-3.18.9.orig/lib/idr.c linux-3.18.9/lib/idr.c --- linux-3.18.9.orig/lib/idr.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/lib/idr.c 2015-03-15 16:03:03.868094875 -0500 @@ -31,6 +31,7 @@ #include #include #include +#include #define MAX_IDR_SHIFT (sizeof(int) * 8 - 1) #define MAX_IDR_BIT (1U << MAX_IDR_SHIFT) @@ -367,6 +368,35 @@ 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() @@ -402,7 +432,7 @@ 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 @@ -414,9 +444,9 @@ 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-3.18.9.orig/lib/Kconfig linux-3.18.9/lib/Kconfig --- linux-3.18.9.orig/lib/Kconfig 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/lib/Kconfig 2015-03-15 16:03:03.868094875 -0500 @@ -383,6 +383,7 @@ 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-3.18.9.orig/lib/Kconfig.debug linux-3.18.9/lib/Kconfig.debug --- linux-3.18.9.orig/lib/Kconfig.debug 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/lib/Kconfig.debug 2015-03-15 16:03:03.868094875 -0500 @@ -639,7 +639,7 @@ config DEBUG_SHIRQ bool "Debug shared IRQ handlers" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && !PREEMPT_RT_BASE help Enable this to generate a spurious interrupt as soon as a shared interrupt handler is registered, and just before one is deregistered. diff -Nur linux-3.18.9.orig/lib/locking-selftest.c linux-3.18.9/lib/locking-selftest.c --- linux-3.18.9.orig/lib/locking-selftest.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/lib/locking-selftest.c 2015-03-15 16:03:03.868094875 -0500 @@ -1858,6 +1858,7 @@ printk(" --------------------------------------------------------------------------\n"); +#ifndef CONFIG_PREEMPT_RT_FULL /* * irq-context testcases: */ @@ -1870,6 +1871,28 @@ 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-3.18.9.orig/lib/percpu_ida.c linux-3.18.9/lib/percpu_ida.c --- linux-3.18.9.orig/lib/percpu_ida.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/lib/percpu_ida.c 2015-03-15 16:03:03.868094875 -0500 @@ -29,6 +29,9 @@ #include #include #include +#include + +static DEFINE_LOCAL_IRQ_LOCK(irq_off_lock); struct percpu_ida_cpu { /* @@ -151,13 +154,13 @@ 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; } @@ -176,6 +179,7 @@ if (!tags->nr_free) alloc_global_tags(pool, tags); + if (!tags->nr_free) steal_tags(pool, tags); @@ -187,7 +191,7 @@ } spin_unlock(&pool->lock); - local_irq_restore(flags); + local_unlock_irqrestore(irq_off_lock, flags); if (tag >= 0 || state == TASK_RUNNING) break; @@ -199,7 +203,7 @@ schedule(); - local_irq_save(flags); + local_lock_irqsave(irq_off_lock, flags); tags = this_cpu_ptr(pool->tag_cpu); } if (state != TASK_RUNNING) @@ -224,7 +228,7 @@ 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); @@ -256,7 +260,7 @@ spin_unlock(&pool->lock); } - local_irq_restore(flags); + local_unlock_irqrestore(irq_off_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ida_free); @@ -348,7 +352,7 @@ 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); @@ -370,7 +374,7 @@ } 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-3.18.9.orig/lib/radix-tree.c linux-3.18.9/lib/radix-tree.c --- linux-3.18.9.orig/lib/radix-tree.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/lib/radix-tree.c 2015-03-15 16:03:03.868094875 -0500 @@ -195,12 +195,13 @@ * succeed in getting a node here (and never reach * kmem_cache_alloc) */ - rtp = this_cpu_ptr(&radix_tree_preloads); + rtp = &get_cpu_var(radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes[rtp->nr - 1]; rtp->nodes[rtp->nr - 1] = NULL; rtp->nr--; } + put_cpu_var(radix_tree_preloads); /* * Update the allocation stack trace as this is more useful * for debugging. @@ -240,6 +241,7 @@ call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } +#ifndef CONFIG_PREEMPT_RT_FULL /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On @@ -305,6 +307,7 @@ return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); +#endif /* * Return the maximum key which can be store into a diff -Nur linux-3.18.9.orig/lib/scatterlist.c linux-3.18.9/lib/scatterlist.c --- linux-3.18.9.orig/lib/scatterlist.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/lib/scatterlist.c 2015-03-15 16:03:03.868094875 -0500 @@ -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-3.18.9.orig/lib/smp_processor_id.c linux-3.18.9/lib/smp_processor_id.c --- linux-3.18.9.orig/lib/smp_processor_id.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/lib/smp_processor_id.c 2015-03-15 16:03:03.868094875 -0500 @@ -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-3.18.9.orig/mm/filemap.c linux-3.18.9/mm/filemap.c --- linux-3.18.9.orig/mm/filemap.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/filemap.c 2015-03-15 16:03:03.868094875 -0500 @@ -168,7 +168,9 @@ 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); } } @@ -535,9 +537,12 @@ * 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-3.18.9.orig/mm/highmem.c linux-3.18.9/mm/highmem.c --- linux-3.18.9.orig/mm/highmem.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/highmem.c 2015-03-15 16:03:03.868094875 -0500 @@ -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-3.18.9.orig/mm/Kconfig linux-3.18.9/mm/Kconfig --- linux-3.18.9.orig/mm/Kconfig 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/Kconfig 2015-03-15 16:03:03.872094875 -0500 @@ -408,7 +408,7 @@ 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-3.18.9.orig/mm/memcontrol.c linux-3.18.9/mm/memcontrol.c --- linux-3.18.9.orig/mm/memcontrol.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/memcontrol.c 2015-03-15 16:03:03.872094875 -0500 @@ -60,6 +60,8 @@ #include #include #include +#include + #include "slab.h" #include @@ -87,6 +89,7 @@ #define do_swap_account 0 #endif +static DEFINE_LOCAL_IRQ_LOCK(event_lock); static const char * const mem_cgroup_stat_names[] = { "cache", @@ -2376,14 +2379,17 @@ */ 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(); } /* @@ -2397,7 +2403,7 @@ /* 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; @@ -2414,7 +2420,7 @@ schedule_work_on(cpu, &stock->work); } } - put_cpu(); + put_cpu_light(); if (!sync) goto out; @@ -3419,12 +3425,12 @@ move_unlock_mem_cgroup(from, &flags); 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: @@ -6406,10 +6412,10 @@ 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) }; @@ -6468,14 +6474,14 @@ 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_anon + nr_file); memcg_check_events(memcg, dummy_page); - local_irq_restore(flags); + local_unlock_irqrestore(event_lock, flags); } static void uncharge_list(struct list_head *page_list) diff -Nur linux-3.18.9.orig/mm/memory.c linux-3.18.9/mm/memory.c --- linux-3.18.9.orig/mm/memory.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/memory.c 2015-03-15 16:03:03.872094875 -0500 @@ -3258,6 +3258,32 @@ return 0; } +#ifdef CONFIG_PREEMPT_RT_FULL +void pagefault_disable(void) +{ + migrate_disable(); + current->pagefault_disabled++; + /* + * make sure to have issued the store before a pagefault + * can hit. + */ + barrier(); +} +EXPORT_SYMBOL(pagefault_disable); + +void pagefault_enable(void) +{ + /* + * make sure to issue those last loads/stores before enabling + * the pagefault handler again. + */ + barrier(); + current->pagefault_disabled--; + migrate_enable(); +} +EXPORT_SYMBOL(pagefault_enable); +#endif + /* * By the time we get here, we already hold the mm semaphore * diff -Nur linux-3.18.9.orig/mm/mmu_context.c linux-3.18.9/mm/mmu_context.c --- linux-3.18.9.orig/mm/mmu_context.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/mmu_context.c 2015-03-15 16:03:03.872094875 -0500 @@ -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-3.18.9.orig/mm/page_alloc.c linux-3.18.9/mm/page_alloc.c --- linux-3.18.9.orig/mm/page_alloc.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/page_alloc.c 2015-03-15 16:03:03.872094875 -0500 @@ -59,6 +59,7 @@ #include #include #include +#include #include #include @@ -230,6 +231,18 @@ 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) @@ -654,7 +667,7 @@ } /* - * 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. * @@ -665,18 +678,51 @@ * 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; @@ -692,7 +738,7 @@ 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. */ @@ -700,21 +746,11 @@ 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, @@ -723,7 +759,9 @@ 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); @@ -733,7 +771,7 @@ 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 bool free_pages_prepare(struct page *page, unsigned int order) @@ -773,11 +811,11 @@ 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 int order) @@ -1253,16 +1291,18 @@ 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 = ACCESS_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 @@ -1281,16 +1321,21 @@ for_each_populated_zone(zone) { struct per_cpu_pageset *pset; struct per_cpu_pages *pcp; + LIST_HEAD(dst); + int count; - local_irq_save(flags); + cpu_lock_irqsave(cpu, flags); pset = per_cpu_ptr(zone->pageset, cpu); pcp = &pset->pcp; - if (pcp->count) { - free_pcppages_bulk(zone, pcp->count, pcp); + count = pcp->count; + if (count) { + isolate_pcp_pages(count, pcp, &dst); pcp->count = 0; } - local_irq_restore(flags); + cpu_unlock_irqrestore(cpu, flags); + if (count) + free_pcppages_bulk(zone, count, &dst); } } @@ -1343,7 +1388,12 @@ else cpumask_clear_cpu(cpu, &cpus_with_pcps); } +#ifndef CONFIG_PREEMPT_RT_BASE on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1); +#else + for_each_cpu(cpu, &cpus_with_pcps) + drain_pages(cpu); +#endif } #ifdef CONFIG_HIBERNATION @@ -1399,7 +1449,7 @@ 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); /* @@ -1425,12 +1475,17 @@ pcp->count++; if (pcp->count >= pcp->high) { unsigned long batch = ACCESS_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); } /* @@ -1560,7 +1615,7 @@ 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)) { @@ -1592,13 +1647,15 @@ */ 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)); @@ -1608,7 +1665,7 @@ __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); if (prep_new_page(page, order, gfp_flags)) @@ -1616,7 +1673,7 @@ return page; failed: - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); return NULL; } @@ -2327,8 +2384,8 @@ count_vm_event(COMPACTSTALL); /* Page migration frees to the PCP lists but we want merging */ - drain_pages(get_cpu()); - put_cpu(); + drain_pages(get_cpu_light()); + put_cpu_light(); page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, @@ -5567,6 +5624,7 @@ void __init page_alloc_init(void) { hotcpu_notifier(page_alloc_cpu_notify, 0); + local_irq_lock_init(pa_lock); } /* @@ -6461,7 +6519,7 @@ 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); @@ -6470,7 +6528,7 @@ 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-3.18.9.orig/mm/slab.h linux-3.18.9/mm/slab.h --- linux-3.18.9.orig/mm/slab.h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/slab.h 2015-03-15 16:03:03.872094875 -0500 @@ -315,7 +315,11 @@ * 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-3.18.9.orig/mm/slub.c linux-3.18.9/mm/slub.c --- linux-3.18.9.orig/mm/slub.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/slub.c 2015-03-15 16:03:03.876094875 -0500 @@ -1044,7 +1044,7 @@ { 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)) @@ -1091,7 +1091,7 @@ 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; } @@ -1219,6 +1219,12 @@ #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. @@ -1303,10 +1309,15 @@ struct page *page; struct kmem_cache_order_objects oo = s->oo; gfp_t alloc_gfp; + 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; @@ -1347,7 +1358,7 @@ kmemcheck_mark_unallocated_pages(page, pages); } - if (flags & __GFP_WAIT) + if (enableirqs) local_irq_disable(); if (!page) return NULL; @@ -1365,8 +1376,10 @@ void *object) { setup_object_debug(s, page, object); +#ifndef CONFIG_PREEMPT_RT_FULL if (unlikely(s->ctor)) s->ctor(object); +#endif } static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) @@ -1442,6 +1455,16 @@ 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)) @@ -1476,6 +1499,12 @@ } call_rcu(head, rcu_free_slab); + } else if (irqs_disabled()) { + struct slub_free_list *f = &__get_cpu_var(slub_free_list); + + raw_spin_lock(&f->lock); + list_add(&page->lru, &f->list); + raw_spin_unlock(&f->lock); } else __free_slab(s, page); } @@ -1589,7 +1618,7 @@ 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; @@ -1614,7 +1643,7 @@ break; } - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); return object; } @@ -1860,7 +1889,7 @@ * 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; @@ -1871,7 +1900,7 @@ * slabs from diagnostic functions will not see * any frozen slabs. */ - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); } } @@ -1906,7 +1935,7 @@ goto redo; if (lock) - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); if (m == M_FREE) { stat(s, DEACTIVATE_EMPTY); @@ -1938,10 +1967,10 @@ 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 { @@ -1970,7 +1999,7 @@ } if (n) - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); while (discard_page) { page = discard_page; @@ -2008,14 +2037,21 @@ 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 = &__get_cpu_var(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; @@ -2079,7 +2115,22 @@ 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); + } } /* @@ -2115,10 +2166,10 @@ 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 */ @@ -2255,9 +2306,11 @@ 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 @@ -2325,7 +2378,13 @@ VM_BUG_ON(!c->page->frozen); c->freelist = get_freepointer(s, freelist); c->tid = next_tid(c->tid); +out: + f = &__get_cpu_var(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: @@ -2342,8 +2401,7 @@ if (unlikely(!freelist)) { slab_out_of_memory(s, gfpflags, node); - local_irq_restore(flags); - return NULL; + goto out; } page = c->page; @@ -2358,8 +2416,7 @@ deactivate_slab(s, page, get_freepointer(s, freelist)); c->page = NULL; c->freelist = NULL; - local_irq_restore(flags); - return freelist; + goto out; } /* @@ -2444,6 +2501,10 @@ if (unlikely(gfpflags & __GFP_ZERO) && object) memset(object, 0, s->object_size); +#ifdef CONFIG_PREEMPT_RT_FULL + if (unlikely(s->ctor) && object) + s->ctor(object); +#endif slab_post_alloc_hook(s, gfpflags, object); @@ -2531,7 +2592,7 @@ do { if (unlikely(n)) { - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); n = NULL; } prior = page->freelist; @@ -2563,7 +2624,7 @@ * 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); } } @@ -2605,7 +2666,7 @@ 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: @@ -2620,7 +2681,7 @@ 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); } @@ -2816,7 +2877,7 @@ 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); @@ -3373,7 +3434,7 @@ for (i = 0; i < objects; i++) INIT_LIST_HEAD(slabs_by_inuse + i); - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); /* * Build lists indexed by the items in use in each slab. @@ -3394,7 +3455,7 @@ for (i = objects - 1; i > 0; i--) list_splice(slabs_by_inuse + i, n->partial.prev); - 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, slabs_by_inuse, lru) @@ -3567,6 +3628,12 @@ { 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; @@ -3815,7 +3882,7 @@ 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); @@ -3837,7 +3904,7 @@ 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; } @@ -4025,12 +4092,12 @@ 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-3.18.9.orig/mm/swap.c linux-3.18.9/mm/swap.c --- linux-3.18.9.orig/mm/swap.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/swap.c 2015-03-15 16:03:03.876094875 -0500 @@ -31,6 +31,7 @@ #include #include #include +#include #include "internal.h" @@ -44,6 +45,9 @@ static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs); +static DEFINE_LOCAL_IRQ_LOCK(rotate_lock); +static DEFINE_LOCAL_IRQ_LOCK(swapvec_lock); + /* * This path almost never happens for VM activity - pages are normally * freed via pagevecs. But it gets used by networking. @@ -473,11 +477,11 @@ 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)) pagevec_move_tail(pvec); - local_irq_restore(flags); + local_unlock_irqrestore(rotate_lock, flags); } } @@ -528,12 +532,13 @@ 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)) pagevec_lru_move_fn(pvec, __activate_page, NULL); - put_cpu_var(activate_page_pvecs); + put_locked_var(swapvec_lock, activate_page_pvecs); } } @@ -559,7 +564,7 @@ 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; /* @@ -581,7 +586,7 @@ } } - put_cpu_var(lru_add_pvec); + put_locked_var(swapvec_lock, lru_add_pvec); } /* @@ -620,13 +625,13 @@ 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_space(pvec)) __pagevec_lru_add(pvec); pagevec_add(pvec, page); - put_cpu_var(lru_add_pvec); + put_locked_var(swapvec_lock, lru_add_pvec); } /** @@ -806,9 +811,9 @@ unsigned long flags; /* No harm done if a racing interrupt already did this */ - local_irq_save(flags); + local_lock_irqsave(rotate_lock, flags); pagevec_move_tail(pvec); - local_irq_restore(flags); + local_unlock_irqrestore(rotate_lock, flags); } pvec = &per_cpu(lru_deactivate_pvecs, cpu); @@ -836,18 +841,19 @@ return; if (likely(get_page_unless_zero(page))) { - struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); + struct pagevec *pvec = &get_locked_var(swapvec_lock, + lru_deactivate_pvecs); if (!pagevec_add(pvec, page)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); - put_cpu_var(lru_deactivate_pvecs); + put_locked_var(swapvec_lock, lru_deactivate_pvecs); } } void lru_add_drain(void) { - lru_add_drain_cpu(get_cpu()); - put_cpu(); + lru_add_drain_cpu(local_lock_cpu(swapvec_lock)); + local_unlock_cpu(swapvec_lock); } static void lru_add_drain_per_cpu(struct work_struct *dummy) diff -Nur linux-3.18.9.orig/mm/truncate.c linux-3.18.9/mm/truncate.c --- linux-3.18.9.orig/mm/truncate.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/truncate.c 2015-03-15 16:03:03.876094875 -0500 @@ -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-3.18.9.orig/mm/vmalloc.c linux-3.18.9/mm/vmalloc.c --- linux-3.18.9.orig/mm/vmalloc.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/vmalloc.c 2015-03-15 16:03:03.876094875 -0500 @@ -798,7 +798,7 @@ struct vmap_block *vb; struct vmap_area *va; unsigned long vb_idx; - int node, err; + int node, err, cpu; node = numa_node_id(); @@ -836,11 +836,12 @@ BUG_ON(err); radix_tree_preload_end(); - vbq = &get_cpu_var(vmap_block_queue); + cpu = get_cpu_light(); + vbq = &__get_cpu_var(vmap_block_queue); spin_lock(&vbq->lock); list_add_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); - put_cpu_var(vmap_block_queue); + put_cpu_light(); return vb; } @@ -908,6 +909,7 @@ struct vmap_block *vb; unsigned long addr = 0; unsigned int order; + int cpu = 0; BUG_ON(size & ~PAGE_MASK); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); @@ -923,7 +925,8 @@ again: rcu_read_lock(); - vbq = &get_cpu_var(vmap_block_queue); + cpu = get_cpu_light(); + vbq = &__get_cpu_var(vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { int i; @@ -947,7 +950,7 @@ spin_unlock(&vb->lock); } - put_cpu_var(vmap_block_queue); + put_cpu_light(); rcu_read_unlock(); if (!addr) { diff -Nur linux-3.18.9.orig/mm/vmstat.c linux-3.18.9/mm/vmstat.c --- linux-3.18.9.orig/mm/vmstat.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/vmstat.c 2015-03-15 16:03:03.876094875 -0500 @@ -221,6 +221,7 @@ long x; long t; + preempt_disable_rt(); x = delta + __this_cpu_read(*p); t = __this_cpu_read(pcp->stat_threshold); @@ -230,6 +231,7 @@ x = 0; } __this_cpu_write(*p, x); + preempt_enable_rt(); } EXPORT_SYMBOL(__mod_zone_page_state); @@ -262,6 +264,7 @@ 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)) { @@ -270,6 +273,7 @@ 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) @@ -284,6 +288,7 @@ 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)) { @@ -292,6 +297,7 @@ 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-3.18.9.orig/mm/workingset.c linux-3.18.9/mm/workingset.c --- linux-3.18.9.orig/mm/workingset.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/mm/workingset.c 2015-03-15 16:03:03.876094875 -0500 @@ -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_count_node(&workingset_shadow_nodes, sc->nid); - local_irq_enable(); + local_lock_irq(workingset_shadow_lock); + shadow_nodes = list_lru_count_node(&__workingset_shadow_nodes, sc->nid); + local_unlock_irq(workingset_shadow_lock); pages = node_present_pages(sc->nid); /* @@ -362,9 +363,9 @@ 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; } @@ -375,10 +376,10 @@ unsigned long ret; /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ - local_irq_disable(); - ret = list_lru_walk_node(&workingset_shadow_nodes, sc->nid, + local_lock_irq(workingset_shadow_lock); + ret = list_lru_walk_node(&__workingset_shadow_nodes, sc->nid, shadow_lru_isolate, NULL, &sc->nr_to_scan); - local_irq_enable(); + local_unlock_irq(workingset_shadow_lock); return ret; } @@ -399,7 +400,7 @@ { 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); @@ -407,7 +408,7 @@ 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-3.18.9.orig/net/core/dev.c linux-3.18.9/net/core/dev.c --- linux-3.18.9.orig/net/core/dev.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/net/core/dev.c 2015-03-15 16:03:03.880094875 -0500 @@ -182,6 +182,7 @@ 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) { @@ -203,14 +204,14 @@ 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 } @@ -832,7 +833,8 @@ 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; } @@ -1101,20 +1103,17 @@ 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); @@ -1127,11 +1126,12 @@ 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); @@ -1152,7 +1152,8 @@ /* 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; @@ -1165,6 +1166,11 @@ } return err; + +outunlock: + __raw_write_seqcount_end(&devnet_rename_seq); + mutex_unlock(&devnet_rename_mutex); + return err; } /** @@ -2160,6 +2166,7 @@ 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) @@ -2241,6 +2248,7 @@ __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); @@ -3336,6 +3344,7 @@ rps_unlock(sd); local_irq_restore(flags); + preempt_check_resched_rt(); atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); @@ -3354,7 +3363,7 @@ struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; - preempt_disable(); + migrate_disable(); rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -3364,13 +3373,13 @@ 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; } @@ -3404,16 +3413,44 @@ 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); @@ -3455,7 +3492,7 @@ 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); @@ -3848,7 +3885,7 @@ 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); } } @@ -3857,10 +3894,13 @@ 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) @@ -4323,6 +4363,7 @@ } else #endif local_irq_enable(); + preempt_check_resched_rt(); } static int process_backlog(struct napi_struct *napi, int quota) @@ -4394,6 +4435,7 @@ local_irq_save(flags); ____napi_schedule(this_cpu_ptr(&softnet_data), n); local_irq_restore(flags); + preempt_check_resched_rt(); } EXPORT_SYMBOL(__napi_schedule); @@ -4516,10 +4558,17 @@ struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + 2; int budget = netdev_budget; + struct sk_buff *skb; void *have; local_irq_disable(); + while ((skb = __skb_dequeue(&sd->tofree_queue))) { + local_irq_enable(); + kfree_skb(skb); + local_irq_disable(); + } + while (!list_empty(&sd->poll_list)) { struct napi_struct *n; int work, weight; @@ -7008,6 +7057,7 @@ 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))) { @@ -7018,6 +7068,9 @@ netif_rx_internal(skb); input_queue_head_incr(oldsd); } + while ((skb = __skb_dequeue(&oldsd->tofree_queue))) { + kfree_skb(skb); + } return NOTIFY_OK; } @@ -7319,8 +7372,9 @@ 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-3.18.9.orig/net/core/skbuff.c linux-3.18.9/net/core/skbuff.c --- linux-3.18.9.orig/net/core/skbuff.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/net/core/skbuff.c 2015-03-15 16:03:03.880094875 -0500 @@ -63,6 +63,7 @@ #include #include #include +#include #include #include @@ -336,6 +337,7 @@ unsigned int pagecnt_bias; }; static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); +static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock); static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { @@ -344,7 +346,7 @@ int order; unsigned long flags; - local_irq_save(flags); + local_lock_irqsave(netdev_alloc_lock, flags); nc = this_cpu_ptr(&netdev_alloc_cache); if (unlikely(!nc->frag.page)) { refill: @@ -389,7 +391,7 @@ nc->frag.offset += fragsz; nc->pagecnt_bias--; end: - local_irq_restore(flags); + local_unlock_irqrestore(netdev_alloc_lock, flags); return data; } diff -Nur linux-3.18.9.orig/net/core/sock.c linux-3.18.9/net/core/sock.c --- linux-3.18.9.orig/net/core/sock.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/net/core/sock.c 2015-03-15 16:03:03.880094875 -0500 @@ -2326,12 +2326,11 @@ 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-3.18.9.orig/net/ipv4/icmp.c linux-3.18.9/net/ipv4/icmp.c --- linux-3.18.9.orig/net/ipv4/icmp.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/net/ipv4/icmp.c 2015-03-15 16:03:03.880094875 -0500 @@ -69,6 +69,7 @@ #include #include #include +#include #include #include #include @@ -864,6 +865,30 @@ } /* + * 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 @@ -890,6 +915,11 @@ 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); + } } } diff -Nur linux-3.18.9.orig/net/ipv4/ip_output.c linux-3.18.9/net/ipv4/ip_output.c --- linux-3.18.9.orig/net/ipv4/ip_output.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/net/ipv4/ip_output.c 2015-03-15 16:03:03.880094875 -0500 @@ -79,6 +79,7 @@ #include #include #include +#include int sysctl_ip_default_ttl __read_mostly = IPDEFTTL; EXPORT_SYMBOL(sysctl_ip_default_ttl); @@ -1507,6 +1508,7 @@ * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. */ + void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, diff -Nur linux-3.18.9.orig/net/ipv4/sysctl_net_ipv4.c linux-3.18.9/net/ipv4/sysctl_net_ipv4.c --- linux-3.18.9.orig/net/ipv4/sysctl_net_ipv4.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/net/ipv4/sysctl_net_ipv4.c 2015-03-15 16:03:03.880094875 -0500 @@ -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-3.18.9.orig/net/mac80211/rx.c linux-3.18.9/net/mac80211/rx.c --- linux-3.18.9.orig/net/mac80211/rx.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/net/mac80211/rx.c 2015-03-15 16:03:03.884094875 -0500 @@ -3356,7 +3356,7 @@ 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-3.18.9.orig/net/netfilter/core.c linux-3.18.9/net/netfilter/core.c --- linux-3.18.9.orig/net/netfilter/core.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/net/netfilter/core.c 2015-03-15 16:03:03.884094875 -0500 @@ -21,11 +21,17 @@ #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-3.18.9.orig/net/packet/af_packet.c linux-3.18.9/net/packet/af_packet.c --- linux-3.18.9.orig/net/packet/af_packet.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/net/packet/af_packet.c 2015-03-15 16:03:03.884094875 -0500 @@ -63,6 +63,7 @@ #include #include #include +#include #include #include #include @@ -692,7 +693,7 @@ if (BLOCK_NUM_PKTS(pbd)) { while (atomic_read(&pkc->blk_fill_in_prog)) { /* Waiting for skb_copy_bits to finish... */ - cpu_relax(); + cpu_chill(); } } @@ -943,7 +944,7 @@ 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-3.18.9.orig/net/rds/ib_rdma.c linux-3.18.9/net/rds/ib_rdma.c --- linux-3.18.9.orig/net/rds/ib_rdma.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/net/rds/ib_rdma.c 2015-03-15 16:03:03.884094875 -0500 @@ -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-3.18.9.orig/net/sched/sch_generic.c linux-3.18.9/net/sched/sch_generic.c --- linux-3.18.9.orig/net/sched/sch_generic.c 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/net/sched/sch_generic.c 2015-03-15 16:03:03.884094875 -0500 @@ -894,7 +894,7 @@ /* 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-3.18.9.orig/scripts/mkcompile_h linux-3.18.9/scripts/mkcompile_h --- linux-3.18.9.orig/scripts/mkcompile_h 2015-03-06 16:53:42.000000000 -0600 +++ linux-3.18.9/scripts/mkcompile_h 2015-03-15 16:03:03.884094875 -0500 @@ -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