diff options
Diffstat (limited to 'kernel')
72 files changed, 4816 insertions, 1724 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 170a9213c1b6..57babbbc65ee 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -73,6 +73,7 @@ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o +obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o obj-$(CONFIG_GENERIC_HARDIRQS) += irq/ obj-$(CONFIG_SECCOMP) += seccomp.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o @@ -92,6 +93,7 @@ obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o +obj-$(CONFIG_SLOW_WORK) += slow-work.o ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c29831076e7a..5a54ff42874e 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1115,8 +1115,10 @@ static void cgroup_kill_sb(struct super_block *sb) { } write_unlock(&css_set_lock); - list_del(&root->root_list); - root_count--; + if (!list_empty(&root->root_list)) { + list_del(&root->root_list); + root_count--; + } mutex_unlock(&cgroup_mutex); @@ -2434,7 +2436,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, err_remove: + cgroup_lock_hierarchy(root); list_del(&cgrp->sibling); + cgroup_unlock_hierarchy(root); root->number_of_cgroups--; err_destroy: @@ -2507,7 +2511,7 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp) for_each_subsys(cgrp->root, ss) { struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; int refcnt; - do { + while (1) { /* We can only remove a CSS with a refcnt==1 */ refcnt = atomic_read(&css->refcnt); if (refcnt > 1) { @@ -2521,7 +2525,10 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp) * css_tryget() to spin until we set the * CSS_REMOVED bits or abort */ - } while (atomic_cmpxchg(&css->refcnt, refcnt, 0) != refcnt); + if (atomic_cmpxchg(&css->refcnt, refcnt, 0) == refcnt) + break; + cpu_relax(); + } } done: for_each_subsys(cgrp->root, ss) { @@ -2991,20 +2998,21 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, mutex_unlock(&cgroup_mutex); return 0; } - task_lock(tsk); - cg = tsk->cgroups; - parent = task_cgroup(tsk, subsys->subsys_id); /* Pin the hierarchy */ - if (!atomic_inc_not_zero(&parent->root->sb->s_active)) { + if (!atomic_inc_not_zero(&root->sb->s_active)) { /* We race with the final deactivate_super() */ mutex_unlock(&cgroup_mutex); return 0; } /* Keep the cgroup alive */ + task_lock(tsk); + parent = task_cgroup(tsk, subsys->subsys_id); + cg = tsk->cgroups; get_css_set(cg); task_unlock(tsk); + mutex_unlock(&cgroup_mutex); /* Now do the VFS work to create a cgroup */ @@ -3043,7 +3051,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, mutex_unlock(&inode->i_mutex); put_css_set(cg); - deactivate_super(parent->root->sb); + deactivate_super(root->sb); /* The cgroup is still accessible in the VFS, but * we're not going to try to rmdir() it at this * point. */ @@ -3069,7 +3077,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, mutex_lock(&cgroup_mutex); put_css_set(cg); mutex_unlock(&cgroup_mutex); - deactivate_super(parent->root->sb); + deactivate_super(root->sb); return ret; } diff --git a/kernel/cpu.c b/kernel/cpu.c index 79e40f00dcb8..a9033184bfff 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -499,69 +499,65 @@ const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; EXPORT_SYMBOL(cpu_all_bits); #ifdef CONFIG_INIT_ALL_POSSIBLE -static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly +DECLARE_BITMAP(__cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly = CPU_BITS_ALL; #else -static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly; +DECLARE_BITMAP(__cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly; #endif -const struct cpumask *const cpu_possible_mask = to_cpumask(cpu_possible_bits); -EXPORT_SYMBOL(cpu_possible_mask); +EXPORT_SYMBOL(__cpu_possible_bits); -static DECLARE_BITMAP(cpu_online_bits, CONFIG_NR_CPUS) __read_mostly; -const struct cpumask *const cpu_online_mask = to_cpumask(cpu_online_bits); -EXPORT_SYMBOL(cpu_online_mask); +DECLARE_BITMAP(__cpu_online_bits, CONFIG_NR_CPUS) __read_mostly; +EXPORT_SYMBOL(__cpu_online_bits); -static DECLARE_BITMAP(cpu_present_bits, CONFIG_NR_CPUS) __read_mostly; -const struct cpumask *const cpu_present_mask = to_cpumask(cpu_present_bits); -EXPORT_SYMBOL(cpu_present_mask); +DECLARE_BITMAP(__cpu_present_bits, CONFIG_NR_CPUS) __read_mostly; +EXPORT_SYMBOL(__cpu_present_bits); -static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly; -const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits); -EXPORT_SYMBOL(cpu_active_mask); +DECLARE_BITMAP(__cpu_active_bits, CONFIG_NR_CPUS) __read_mostly; +EXPORT_SYMBOL(__cpu_active_bits); void set_cpu_possible(unsigned int cpu, bool possible) { if (possible) - cpumask_set_cpu(cpu, to_cpumask(cpu_possible_bits)); + cpumask_set_cpu(cpu, to_cpumask(__cpu_possible_bits)); else - cpumask_clear_cpu(cpu, to_cpumask(cpu_possible_bits)); + cpumask_clear_cpu(cpu, to_cpumask(__cpu_possible_bits)); } void set_cpu_present(unsigned int cpu, bool present) { if (present) - cpumask_set_cpu(cpu, to_cpumask(cpu_present_bits)); + cpumask_set_cpu(cpu, to_cpumask(__cpu_present_bits)); else - cpumask_clear_cpu(cpu, to_cpumask(cpu_present_bits)); + cpumask_clear_cpu(cpu, to_cpumask(__cpu_present_bits)); } void set_cpu_online(unsigned int cpu, bool online) { if (online) - cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits)); + cpumask_set_cpu(cpu, to_cpumask(__cpu_online_bits)); else - cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits)); + cpumask_clear_cpu(cpu, to_cpumask(__cpu_online_bits)); } void set_cpu_active(unsigned int cpu, bool active) { if (active) - cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits)); + cpumask_set_cpu(cpu, to_cpumask(__cpu_active_bits)); else - cpumask_clear_cpu(cpu, to_cpumask(cpu_active_bits)); + cpumask_clear_cpu(cpu, to_cpumask(__cpu_active_bits)); } void init_cpu_present(const struct cpumask *src) { - cpumask_copy(to_cpumask(cpu_present_bits), src); + cpumask_copy(to_cpumask(__cpu_present_bits), src); } void init_cpu_possible(const struct cpumask *src) { - cpumask_copy(to_cpumask(cpu_possible_bits), src); + cpumask_copy(to_cpumask(__cpu_possible_bits), src); } void init_cpu_online(const struct cpumask *src) { - cpumask_copy(to_cpumask(cpu_online_bits), src); + cpumask_copy(to_cpumask(__cpu_online_bits), src); } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index a85678865c5e..f76db9dcaa05 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -61,6 +61,14 @@ #include <linux/cgroup.h> /* + * Workqueue for cpuset related tasks. + * + * Using kevent workqueue may cause deadlock when memory_migrate + * is set. So we create a separate workqueue thread for cpuset. + */ +static struct workqueue_struct *cpuset_wq; + +/* * Tracks how many cpusets are currently defined in system. * When there is only one cpuset (the root cpuset) we can * short circuit some hooks. @@ -831,7 +839,7 @@ static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains); */ static void async_rebuild_sched_domains(void) { - schedule_work(&rebuild_sched_domains_work); + queue_work(cpuset_wq, &rebuild_sched_domains_work); } /* @@ -2111,6 +2119,9 @@ void __init cpuset_init_smp(void) hotcpu_notifier(cpuset_track_online_cpus, 0); hotplug_memory_notifier(cpuset_track_online_nodes, 10); + + cpuset_wq = create_singlethread_workqueue("cpuset"); + BUG_ON(!cpuset_wq); } /** diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c index 038707404b76..962a3b574f21 100644 --- a/kernel/dma-coherent.c +++ b/kernel/dma-coherent.c @@ -98,7 +98,7 @@ EXPORT_SYMBOL(dma_mark_declared_memory_occupied); * @size: size of requested memory area * @dma_handle: This will be filled with the correct dma handle * @ret: This pointer will be filled with the virtual address - * to allocated area. + * to allocated area. * * This function should be only called from per-arch dma_alloc_coherent() * to support allocation from per-device coherent memory pools. @@ -118,31 +118,32 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size, mem = dev->dma_mem; if (!mem) return 0; - if (unlikely(size > mem->size)) - return 0; + + *ret = NULL; + + if (unlikely(size > (mem->size << PAGE_SHIFT))) + goto err; pageno = bitmap_find_free_region(mem->bitmap, mem->size, order); - if (pageno >= 0) { - /* - * Memory was found in the per-device arena. - */ - *dma_handle = mem->device_base + (pageno << PAGE_SHIFT); - *ret = mem->virt_base + (pageno << PAGE_SHIFT); - memset(*ret, 0, size); - } else if (mem->flags & DMA_MEMORY_EXCLUSIVE) { - /* - * The per-device arena is exhausted and we are not - * permitted to fall back to generic memory. - */ - *ret = NULL; - } else { - /* - * The per-device arena is exhausted and we are - * permitted to fall back to generic memory. - */ - return 0; - } + if (unlikely(pageno < 0)) + goto err; + + /* + * Memory was found in the per-device area. + */ + *dma_handle = mem->device_base + (pageno << PAGE_SHIFT); + *ret = mem->virt_base + (pageno << PAGE_SHIFT); + memset(*ret, 0, size); + return 1; + +err: + /* + * In the case where the allocation can not be satisfied from the + * per-device area, try to fall back to generic memory if the + * constraints allow it. + */ + return mem->flags & DMA_MEMORY_EXCLUSIVE; } EXPORT_SYMBOL(dma_alloc_from_coherent); diff --git a/kernel/exit.c b/kernel/exit.c index f80dec3f1875..70612c19ac96 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -977,12 +977,9 @@ static void check_stack_usage(void) { static DEFINE_SPINLOCK(low_water_lock); static int lowest_to_date = THREAD_SIZE; - unsigned long *n = end_of_stack(current); unsigned long free; - while (*n == 0) - n++; - free = (unsigned long)n - (unsigned long)end_of_stack(current); + free = stack_not_used(current); if (free >= lowest_to_date) return; diff --git a/kernel/fork.c b/kernel/fork.c index bf0cef8bbdf2..28d7669f8965 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -61,6 +61,7 @@ #include <linux/proc_fs.h> #include <linux/blkdev.h> #include <trace/sched.h> +#include <linux/magic.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -176,7 +177,7 @@ void __init fork_init(unsigned long mempages) /* create a slab on which task_structs can be allocated */ task_struct_cachep = kmem_cache_create("task_struct", sizeof(struct task_struct), - ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL); + ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL); #endif /* do the arch specific task caches init */ @@ -212,6 +213,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) { struct task_struct *tsk; struct thread_info *ti; + unsigned long *stackend; + int err; prepare_to_copy(orig); @@ -237,6 +240,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) goto out; setup_thread_stack(tsk, orig); + stackend = end_of_stack(tsk); + *stackend = STACK_END_MAGIC; /* for overflow detection */ #ifdef CONFIG_CC_STACKPROTECTOR tsk->stack_canary = get_random_int(); @@ -817,17 +822,17 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig) static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; - int ret; if (clone_flags & CLONE_THREAD) { - ret = thread_group_cputime_clone_thread(current); - if (likely(!ret)) { - atomic_inc(¤t->signal->count); - atomic_inc(¤t->signal->live); - } - return ret; + atomic_inc(¤t->signal->count); + atomic_inc(¤t->signal->live); + return 0; } sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL); + + if (sig) + posix_cpu_timers_init_group(sig); + tsk->signal = sig; if (!sig) return -ENOMEM; @@ -864,8 +869,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); - posix_cpu_timers_init_group(sig); - acct_init_pacct(&sig->pacct); tty_audit_fork(sig); @@ -1041,7 +1044,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->default_timer_slack_ns = current->timer_slack_ns; -#ifdef CONFIG_DETECT_SOFTLOCKUP +#ifdef CONFIG_DETECT_HUNG_TASK p->last_switch_count = 0; p->last_switch_timestamp = 0; #endif @@ -1470,20 +1473,20 @@ void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU, - sighand_ctor); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU| + SLAB_NOTRACK, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); mmap_init(); } diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 2dc30c59c5fd..f394d2a42ca3 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -501,6 +501,13 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base) continue; timer = rb_entry(base->first, struct hrtimer, node); expires = ktime_sub(hrtimer_get_expires(timer), base->offset); + /* + * clock_was_set() has changed base->offset so the + * result might be negative. Fix it up to prevent a + * false positive in clockevents_program_event() + */ + if (expires.tv64 < 0) + expires.tv64 = 0; if (expires.tv64 < cpu_base->expires_next.tv64) cpu_base->expires_next = expires; } @@ -614,7 +621,9 @@ void clock_was_set(void) */ void hres_timers_resume(void) { - /* Retrigger the CPU local events: */ + WARN_ONCE(!irqs_disabled(), + KERN_INFO "hres_timers_resume() called with IRQs enabled!"); + retrigger_next_event(NULL); } @@ -1156,6 +1165,29 @@ static void __run_hrtimer(struct hrtimer *timer) #ifdef CONFIG_HIGH_RES_TIMERS +static int force_clock_reprogram; + +/* + * After 5 iteration's attempts, we consider that hrtimer_interrupt() + * is hanging, which could happen with something that slows the interrupt + * such as the tracing. Then we force the clock reprogramming for each future + * hrtimer interrupts to avoid infinite loops and use the min_delta_ns + * threshold that we will overwrite. + * The next tick event will be scheduled to 3 times we currently spend on + * hrtimer_interrupt(). This gives a good compromise, the cpus will spend + * 1/4 of their time to process the hrtimer interrupts. This is enough to + * let it running without serious starvation. + */ + +static inline void +hrtimer_interrupt_hanging(struct clock_event_device *dev, + ktime_t try_time) +{ + force_clock_reprogram = 1; + dev->min_delta_ns = (unsigned long)try_time.tv64 * 3; + printk(KERN_WARNING "hrtimer: interrupt too slow, " + "forcing clock min delta to %lu ns\n", dev->min_delta_ns); +} /* * High resolution timer interrupt * Called with interrupts disabled @@ -1165,6 +1197,7 @@ void hrtimer_interrupt(struct clock_event_device *dev) struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); struct hrtimer_clock_base *base; ktime_t expires_next, now; + int nr_retries = 0; int i; BUG_ON(!cpu_base->hres_active); @@ -1172,6 +1205,10 @@ void hrtimer_interrupt(struct clock_event_device *dev) dev->next_event.tv64 = KTIME_MAX; retry: + /* 5 retries is enough to notice a hang */ + if (!(++nr_retries % 5)) + hrtimer_interrupt_hanging(dev, ktime_sub(ktime_get(), now)); + now = ktime_get(); expires_next.tv64 = KTIME_MAX; @@ -1224,7 +1261,7 @@ void hrtimer_interrupt(struct clock_event_device *dev) /* Reprogramming necessary ? */ if (expires_next.tv64 != KTIME_MAX) { - if (tick_program_event(expires_next, 0)) + if (tick_program_event(expires_next, force_clock_reprogram)) goto retry; } } @@ -1578,6 +1615,10 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self, break; #ifdef CONFIG_HOTPLUG_CPU + case CPU_DYING: + case CPU_DYING_FROZEN: + clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu); + break; case CPU_DEAD: case CPU_DEAD_FROZEN: { diff --git a/kernel/hung_task.c b/kernel/hung_task.c new file mode 100644 index 000000000000..ba8ccd432963 --- /dev/null +++ b/kernel/hung_task.c @@ -0,0 +1,206 @@ +/* + * Detect Hung Task + * + * kernel/hung_task.c - kernel thread for detecting tasks stuck in D state + * + */ + +#include <linux/mm.h> +#include <linux/cpu.h> +#include <linux/nmi.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/freezer.h> +#include <linux/kthread.h> +#include <linux/lockdep.h> +#include <linux/module.h> +#include <linux/sysctl.h> + +/* + * Have a reasonable limit on the number of tasks checked: + */ +unsigned long __read_mostly sysctl_hung_task_check_count = 1024; + +/* + * Zero means infinite timeout - no checking done: + */ +unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120; +static unsigned long __read_mostly hung_task_poll_jiffies; + +unsigned long __read_mostly sysctl_hung_task_warnings = 10; + +static int __read_mostly did_panic; + +static struct task_struct *watchdog_task; + +/* + * Should we panic (and reboot, if panic_timeout= is set) when a + * hung task is detected: + */ +unsigned int __read_mostly sysctl_hung_task_panic = + CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE; + +static int __init hung_task_panic_setup(char *str) +{ + sysctl_hung_task_panic = simple_strtoul(str, NULL, 0); + + return 1; +} +__setup("hung_task_panic=", hung_task_panic_setup); + +static int +hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr) +{ + did_panic = 1; + + return NOTIFY_DONE; +} + +static struct notifier_block panic_block = { + .notifier_call = hung_task_panic, +}; + +/* + * Returns seconds, approximately. We don't need nanosecond + * resolution, and we don't need to waste time with a big divide when + * 2^30ns == 1.074s. + */ +static unsigned long get_timestamp(void) +{ + int this_cpu = raw_smp_processor_id(); + + return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */ +} + +static void check_hung_task(struct task_struct *t, unsigned long now, + unsigned long timeout) +{ + unsigned long switch_count = t->nvcsw + t->nivcsw; + + if (t->flags & PF_FROZEN) + return; + + if (switch_count != t->last_switch_count || !t->last_switch_timestamp) { + t->last_switch_count = switch_count; + t->last_switch_timestamp = now; + return; + } + if ((long)(now - t->last_switch_timestamp) < timeout) + return; + if (!sysctl_hung_task_warnings) + return; + sysctl_hung_task_warnings--; + + /* + * Ok, the task did not get scheduled for more than 2 minutes, + * complain: + */ + printk(KERN_ERR "INFO: task %s:%d blocked for more than " + "%ld seconds.\n", t->comm, t->pid, timeout); + printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\"" + " disables this message.\n"); + sched_show_task(t); + __debug_show_held_locks(t); + + t->last_switch_timestamp = now; + touch_nmi_watchdog(); + + if (sysctl_hung_task_panic) + panic("hung_task: blocked tasks"); +} + +/* + * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for + * a really long time (120 seconds). If that happens, print out + * a warning. + */ +static void check_hung_uninterruptible_tasks(unsigned long timeout) +{ + int max_count = sysctl_hung_task_check_count; + unsigned long now = get_timestamp(); + struct task_struct *g, *t; + + /* + * If the system crashed already then all bets are off, + * do not report extra hung tasks: + */ + if (test_taint(TAINT_DIE) || did_panic) + return; + + read_lock(&tasklist_lock); + do_each_thread(g, t) { + if (!--max_count) + goto unlock; + /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */ + if (t->state == TASK_UNINTERRUPTIBLE) + check_hung_task(t, now, timeout); + } while_each_thread(g, t); + unlock: + read_unlock(&tasklist_lock); +} + +static void update_poll_jiffies(void) +{ + /* timeout of 0 will disable the watchdog */ + if (sysctl_hung_task_timeout_secs == 0) + hung_task_poll_jiffies = MAX_SCHEDULE_TIMEOUT; + else + hung_task_poll_jiffies = sysctl_hung_task_timeout_secs * HZ / 2; +} + +/* + * Process updating of timeout sysctl + */ +int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + + if (ret || !write) + goto out; + + update_poll_jiffies(); + + wake_up_process(watchdog_task); + + out: + return ret; +} + +/* + * kthread which checks for tasks stuck in D state + */ +static int watchdog(void *dummy) +{ + set_user_nice(current, 0); + update_poll_jiffies(); + + for ( ; ; ) { + unsigned long timeout; + + while (schedule_timeout_interruptible(hung_task_poll_jiffies)); + + /* + * Need to cache timeout here to avoid timeout being set + * to 0 via sysctl while inside check_hung_*_tasks(). + */ + timeout = sysctl_hung_task_timeout_secs; + if (timeout) + check_hung_uninterruptible_tasks(timeout); + } + + return 0; +} + +static int __init hung_task_init(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, &panic_block); + watchdog_task = kthread_run(watchdog, NULL, "khungtaskd"); + + return 0; +} + +module_init(hung_task_init); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 7de11bd64dfe..e89adf3e69cf 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -46,7 +46,10 @@ void dynamic_irq_init(unsigned int irq) desc->irq_count = 0; desc->irqs_unhandled = 0; #ifdef CONFIG_SMP - cpumask_setall(&desc->affinity); + cpumask_setall(desc->affinity); +#ifdef CONFIG_GENERIC_PENDING_IRQ + cpumask_clear(desc->pending_mask); +#endif #endif spin_unlock_irqrestore(&desc->lock, flags); } @@ -290,7 +293,8 @@ static inline void mask_ack_irq(struct irq_desc *desc, int irq) desc->chip->mask_ack(irq); else { desc->chip->mask(irq); - desc->chip->ack(irq); + if (desc->chip->ack) + desc->chip->ack(irq); } } @@ -476,7 +480,8 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc) kstat_incr_irqs_this_cpu(irq, desc); /* Start handling the irq */ - desc->chip->ack(irq); + if (desc->chip->ack) + desc->chip->ack(irq); desc = irq_remap_to_desc(irq, desc); /* Mark the IRQ currently in progress.*/ diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 48299a8a22f8..8b70e5ef71a4 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -17,6 +17,7 @@ #include <linux/kernel_stat.h> #include <linux/rculist.h> #include <linux/hash.h> +#include <linux/bootmem.h> #include "internals.h" @@ -39,6 +40,18 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc) ack_bad_irq(irq); } +#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS) +static void __init init_irq_default_affinity(void) +{ + alloc_bootmem_cpumask_var(&irq_default_affinity); + cpumask_setall(irq_default_affinity); +} +#else +static void __init init_irq_default_affinity(void) +{ +} +#endif + /* * Linux has a controller-independent interrupt architecture. * Every controller has a 'controller-template', that is used @@ -57,6 +70,7 @@ int nr_irqs = NR_IRQS; EXPORT_SYMBOL_GPL(nr_irqs); #ifdef CONFIG_SPARSE_IRQ + static struct irq_desc irq_desc_init = { .irq = -1, .status = IRQ_DISABLED, @@ -64,9 +78,6 @@ static struct irq_desc irq_desc_init = { .handle_irq = handle_bad_irq, .depth = 1, .lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock), -#ifdef CONFIG_SMP - .affinity = CPU_MASK_ALL -#endif }; void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr) @@ -101,6 +112,10 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) printk(KERN_ERR "can not alloc kstat_irqs\n"); BUG_ON(1); } + if (!init_alloc_desc_masks(desc, cpu, false)) { + printk(KERN_ERR "can not alloc irq_desc cpumasks\n"); + BUG_ON(1); + } arch_init_chip_data(desc, cpu); } @@ -109,7 +124,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) */ DEFINE_SPINLOCK(sparse_irq_lock); -struct irq_desc *irq_desc_ptrs[NR_IRQS] __read_mostly; +struct irq_desc **irq_desc_ptrs __read_mostly; static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = { [0 ... NR_IRQS_LEGACY-1] = { @@ -119,14 +134,10 @@ static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_sm .handle_irq = handle_bad_irq, .depth = 1, .lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock), -#ifdef CONFIG_SMP - .affinity = CPU_MASK_ALL -#endif } }; -/* FIXME: use bootmem alloc ...*/ -static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS]; +static unsigned int *kstat_irqs_legacy; int __init early_irq_init(void) { @@ -134,18 +145,32 @@ int __init early_irq_init(void) int legacy_count; int i; + init_irq_default_affinity(); + + /* initialize nr_irqs based on nr_cpu_ids */ + arch_probe_nr_irqs(); + printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs); + desc = irq_desc_legacy; legacy_count = ARRAY_SIZE(irq_desc_legacy); + /* allocate irq_desc_ptrs array based on nr_irqs */ + irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *)); + + /* allocate based on nr_cpu_ids */ + /* FIXME: invert kstat_irgs, and it'd be a per_cpu_alloc'd thing */ + kstat_irqs_legacy = alloc_bootmem(NR_IRQS_LEGACY * nr_cpu_ids * + sizeof(int)); + for (i = 0; i < legacy_count; i++) { desc[i].irq = i; - desc[i].kstat_irqs = kstat_irqs_legacy[i]; + desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids; lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); - + init_alloc_desc_masks(&desc[i], 0, true); irq_desc_ptrs[i] = desc + i; } - for (i = legacy_count; i < NR_IRQS; i++) + for (i = legacy_count; i < nr_irqs; i++) irq_desc_ptrs[i] = NULL; return arch_early_irq_init(); @@ -153,7 +178,10 @@ int __init early_irq_init(void) struct irq_desc *irq_to_desc(unsigned int irq) { - return (irq < NR_IRQS) ? irq_desc_ptrs[irq] : NULL; + if (irq_desc_ptrs && irq < nr_irqs) + return irq_desc_ptrs[irq]; + + return NULL; } struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) @@ -162,10 +190,9 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) unsigned long flags; int node; - if (irq >= NR_IRQS) { - printk(KERN_WARNING "irq >= NR_IRQS in irq_to_desc_alloc: %d %d\n", - irq, NR_IRQS); - WARN_ON(1); + if (irq >= nr_irqs) { + WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n", + irq, nr_irqs); return NULL; } @@ -207,9 +234,6 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { .handle_irq = handle_bad_irq, .depth = 1, .lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock), -#ifdef CONFIG_SMP - .affinity = CPU_MASK_ALL -#endif } }; @@ -220,12 +244,17 @@ int __init early_irq_init(void) int count; int i; + init_irq_default_affinity(); + + printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS); + desc = irq_desc; count = ARRAY_SIZE(irq_desc); for (i = 0; i < count; i++) { desc[i].irq = i; desc[i].kstat_irqs = kstat_irqs_all[i]; + init_alloc_desc_masks(&desc[i], 0, true); } return arch_early_irq_init(); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index e6d0a43cc125..40416a81a0f5 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -16,7 +16,14 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, extern struct lock_class_key irq_desc_lock_class; extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr); extern spinlock_t sparse_irq_lock; + +#ifdef CONFIG_SPARSE_IRQ +/* irq_desc_ptrs allocated at boot time */ +extern struct irq_desc **irq_desc_ptrs; +#else +/* irq_desc_ptrs is a fixed size array */ extern struct irq_desc *irq_desc_ptrs[NR_IRQS]; +#endif #ifdef CONFIG_PROC_FS extern void register_irq_proc(unsigned int irq, struct irq_desc *desc); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index cd0cd8dcb345..a3a5dc9ef346 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -15,17 +15,9 @@ #include "internals.h" -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS) cpumask_var_t irq_default_affinity; -static int init_irq_default_affinity(void) -{ - alloc_cpumask_var(&irq_default_affinity, GFP_KERNEL); - cpumask_setall(irq_default_affinity); - return 0; -} -core_initcall(init_irq_default_affinity); - /** * synchronize_irq - wait for pending IRQ handlers (on other CPUs) * @irq: interrupt number to wait for @@ -98,14 +90,14 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) #ifdef CONFIG_GENERIC_PENDING_IRQ if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) { - cpumask_copy(&desc->affinity, cpumask); + cpumask_copy(desc->affinity, cpumask); desc->chip->set_affinity(irq, cpumask); } else { desc->status |= IRQ_MOVE_PENDING; - cpumask_copy(&desc->pending_mask, cpumask); + cpumask_copy(desc->pending_mask, cpumask); } #else - cpumask_copy(&desc->affinity, cpumask); + cpumask_copy(desc->affinity, cpumask); desc->chip->set_affinity(irq, cpumask); #endif desc->status |= IRQ_AFFINITY_SET; @@ -127,16 +119,16 @@ int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc) * one of the targets is online. */ if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) { - if (cpumask_any_and(&desc->affinity, cpu_online_mask) + if (cpumask_any_and(desc->affinity, cpu_online_mask) < nr_cpu_ids) goto set_affinity; else desc->status &= ~IRQ_AFFINITY_SET; } - cpumask_and(&desc->affinity, cpu_online_mask, irq_default_affinity); + cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity); set_affinity: - desc->chip->set_affinity(irq, &desc->affinity); + desc->chip->set_affinity(irq, desc->affinity); return 0; } diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index bd72329e630c..e05ad9be43b7 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -18,7 +18,7 @@ void move_masked_irq(int irq) desc->status &= ~IRQ_MOVE_PENDING; - if (unlikely(cpumask_empty(&desc->pending_mask))) + if (unlikely(cpumask_empty(desc->pending_mask))) return; if (!desc->chip->set_affinity) @@ -38,13 +38,13 @@ void move_masked_irq(int irq) * For correct operation this depends on the caller * masking the irqs. */ - if (likely(cpumask_any_and(&desc->pending_mask, cpu_online_mask) + if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)) { - cpumask_and(&desc->affinity, - &desc->pending_mask, cpu_online_mask); - desc->chip->set_affinity(irq, &desc->affinity); + cpumask_and(desc->affinity, + desc->pending_mask, cpu_online_mask); + desc->chip->set_affinity(irq, desc->affinity); } - cpumask_clear(&desc->pending_mask); + cpumask_clear(desc->pending_mask); } void move_native_irq(int irq) diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c index ecf765c6a77a..666260e4c065 100644 --- a/kernel/irq/numa_migrate.c +++ b/kernel/irq/numa_migrate.c @@ -38,15 +38,22 @@ static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc) old_desc->kstat_irqs = NULL; } -static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc, +static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc, struct irq_desc *desc, int cpu) { memcpy(desc, old_desc, sizeof(struct irq_desc)); + if (!init_alloc_desc_masks(desc, cpu, false)) { + printk(KERN_ERR "irq %d: can not get new irq_desc cpumask " + "for migration.\n", irq); + return false; + } spin_lock_init(&desc->lock); desc->cpu = cpu; lockdep_set_class(&desc->lock, &irq_desc_lock_class); init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids); + init_copy_desc_masks(old_desc, desc); arch_init_copy_chip_data(old_desc, desc, cpu); + return true; } static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc) @@ -76,12 +83,18 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, node = cpu_to_node(cpu); desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node); if (!desc) { - printk(KERN_ERR "irq %d: can not get new irq_desc for migration.\n", irq); + printk(KERN_ERR "irq %d: can not get new irq_desc " + "for migration.\n", irq); + /* still use old one */ + desc = old_desc; + goto out_unlock; + } + if (!init_copy_one_irq_desc(irq, old_desc, desc, cpu)) { /* still use old one */ + kfree(desc); desc = old_desc; goto out_unlock; } - init_copy_one_irq_desc(irq, old_desc, desc, cpu); irq_desc_ptrs[irq] = desc; diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index aae3f742bcec..692363dd591f 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -20,11 +20,11 @@ static struct proc_dir_entry *root_irq_dir; static int irq_affinity_proc_show(struct seq_file *m, void *v) { struct irq_desc *desc = irq_to_desc((long)m->private); - const struct cpumask *mask = &desc->affinity; + const struct cpumask *mask = desc->affinity; #ifdef CONFIG_GENERIC_PENDING_IRQ if (desc->status & IRQ_MOVE_PENDING) - mask = &desc->pending_mask; + mask = desc->pending_mask; #endif seq_cpumask(m, mask); seq_putc(m, '\n'); diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index dd364c11e56e..4d568294de3e 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -104,7 +104,7 @@ static int misrouted_irq(int irq) return ok; } -static void poll_spurious_irqs(unsigned long dummy) +static void poll_all_shared_irqs(void) { struct irq_desc *desc; int i; @@ -123,11 +123,23 @@ static void poll_spurious_irqs(unsigned long dummy) try_one_irq(i, desc); } +} + +static void poll_spurious_irqs(unsigned long dummy) +{ + poll_all_shared_irqs(); mod_timer(&poll_spurious_irq_timer, jiffies + POLL_SPURIOUS_IRQ_INTERVAL); } +#ifdef CONFIG_DEBUG_SHIRQ +void debug_poll_all_shared_irqs(void) +{ + poll_all_shared_irqs(); +} +#endif + /* * If 99,900 of the previous 100,000 interrupts have not been handled * then assume that the IRQ is stuck in some manner. Drop a diagnostic diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index e694afa0eb8c..7b8b0f21a5b1 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -30,19 +30,20 @@ #define all_var 0 #endif -extern const unsigned long kallsyms_addresses[]; -extern const u8 kallsyms_names[]; +/* These will be re-linked against their real values during the second link stage */ +extern const unsigned long kallsyms_addresses[] __attribute__((weak)); +extern const u8 kallsyms_names[] __attribute__((weak)); /* tell the compiler that the count isn't in the small data section if the arch * has one (eg: FRV) */ extern const unsigned long kallsyms_num_syms - __attribute__((__section__(".rodata"))); +__attribute__((weak, section(".rodata"))); -extern const u8 kallsyms_token_table[]; -extern const u16 kallsyms_token_index[]; +extern const u8 kallsyms_token_table[] __attribute__((weak)); +extern const u16 kallsyms_token_index[] __attribute__((weak)); -extern const unsigned long kallsyms_markers[]; +extern const unsigned long kallsyms_markers[] __attribute__((weak)); static inline int is_kernel_inittext(unsigned long addr) { @@ -167,6 +168,9 @@ static unsigned long get_symbol_pos(unsigned long addr, unsigned long symbol_start = 0, symbol_end = 0; unsigned long i, low, high, mid; + /* This kernel should never had been booted. */ + BUG_ON(!kallsyms_addresses); + /* do a binary search on the sorted kallsyms_addresses array */ low = 0; high = kallsyms_num_syms; diff --git a/kernel/kgdb.c b/kernel/kgdb.c index e4dcfb2272a4..b5ea4650f2ea 100644 --- a/kernel/kgdb.c +++ b/kernel/kgdb.c @@ -363,7 +363,7 @@ static void put_packet(char *buffer) * Convert the memory pointed to by mem into hex, placing result in buf. * Return a pointer to the last char put in buf (null). May return an error. */ -int kgdb_mem2hex(char *mem, char *buf, int count) +int __weak kgdb_mem2hex(char *mem, char *buf, int count) { char *tmp; int err; @@ -393,7 +393,7 @@ int kgdb_mem2hex(char *mem, char *buf, int count) * 0x7d escaped with 0x7d. Return a pointer to the character after * the last byte written. */ -static int kgdb_ebin2mem(char *buf, char *mem, int count) +int __weak kgdb_ebin2mem(char *buf, char *mem, int count) { int err = 0; char c; @@ -418,7 +418,7 @@ static int kgdb_ebin2mem(char *buf, char *mem, int count) * Return a pointer to the character AFTER the last byte written. * May return an error. */ -int kgdb_hex2mem(char *buf, char *mem, int count) +int __weak kgdb_hex2mem(char *buf, char *mem, int count) { char *tmp_raw; char *tmp_hex; diff --git a/kernel/kthread.c b/kernel/kthread.c index 4fbc456f393d..fd765f9f1b2a 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -76,6 +76,7 @@ static int kthread(void *_create) /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); + create->result = current; complete(&create->started); schedule(); @@ -101,9 +102,6 @@ static void create_kthread(struct kthread_create_info *create) } else { struct sched_param param = { .sched_priority = 0 }; wait_for_completion(&create->started); - read_lock(&tasklist_lock); - create->result = find_task_by_pid_ns(pid, &init_pid_ns); - read_unlock(&tasklist_lock); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. diff --git a/kernel/module.c b/kernel/module.c index e8b51d41dd72..ba22484a987e 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -573,13 +573,13 @@ static char last_unloaded_module[MODULE_NAME_LEN+1]; /* Init the unload section of the module. */ static void module_unload_init(struct module *mod) { - unsigned int i; + int cpu; INIT_LIST_HEAD(&mod->modules_which_use_me); - for (i = 0; i < NR_CPUS; i++) - local_set(&mod->ref[i].count, 0); + for_each_possible_cpu(cpu) + local_set(__module_ref_addr(mod, cpu), 0); /* Hold reference count during initialization. */ - local_set(&mod->ref[raw_smp_processor_id()].count, 1); + local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1); /* Backwards compatibility macros put refcount during init. */ mod->waiter = current; } @@ -717,10 +717,11 @@ static int try_stop_module(struct module *mod, int flags, int *forced) unsigned int module_refcount(struct module *mod) { - unsigned int i, total = 0; + unsigned int total = 0; + int cpu; - for (i = 0; i < NR_CPUS; i++) - total += local_read(&mod->ref[i].count); + for_each_possible_cpu(cpu) + total += local_read(__module_ref_addr(mod, cpu)); return total; } EXPORT_SYMBOL(module_refcount); @@ -894,7 +895,7 @@ void module_put(struct module *module) { if (module) { unsigned int cpu = get_cpu(); - local_dec(&module->ref[cpu].count); + local_dec(__module_ref_addr(module, cpu)); /* Maybe they're waiting for us to drop reference? */ if (unlikely(!module_is_live(module))) wake_up_process(module->waiter); @@ -1464,7 +1465,10 @@ static void free_module(struct module *mod) kfree(mod->args); if (mod->percpu) percpu_modfree(mod->percpu); - +#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) + if (mod->refptr) + percpu_modfree(mod->refptr); +#endif /* Free lock-classes: */ lockdep_free_key_range(mod->module_core, mod->core_size); @@ -2011,6 +2015,14 @@ static noinline struct module *load_module(void __user *umod, if (err < 0) goto free_mod; +#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) + mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t), + mod->name); + if (!mod->refptr) { + err = -ENOMEM; + goto free_mod; + } +#endif if (pcpuindex) { /* We have a special allocation for this section. */ percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size, @@ -2018,7 +2030,7 @@ static noinline struct module *load_module(void __user *umod, mod->name); if (!percpu) { err = -ENOMEM; - goto free_mod; + goto free_percpu; } sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC; mod->percpu = percpu; @@ -2282,6 +2294,9 @@ static noinline struct module *load_module(void __user *umod, free_percpu: if (percpu) percpu_modfree(percpu); +#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) + percpu_modfree(mod->refptr); +#endif free_mod: kfree(args); free_hdr: diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c index 1d94160eb532..50d022e5a560 100644 --- a/kernel/mutex-debug.c +++ b/kernel/mutex-debug.c @@ -26,11 +26,6 @@ /* * Must be called with lock->wait_lock held. */ -void debug_mutex_set_owner(struct mutex *lock, struct thread_info *new_owner) -{ - lock->owner = new_owner; -} - void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter) { memset(waiter, MUTEX_DEBUG_INIT, sizeof(*waiter)); @@ -59,7 +54,6 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, /* Mark the current thread as blocked on the lock: */ ti->task->blocked_on = waiter; - waiter->lock = lock; } void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, @@ -82,7 +76,7 @@ void debug_mutex_unlock(struct mutex *lock) DEBUG_LOCKS_WARN_ON(lock->magic != lock); DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); - DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); + mutex_clear_owner(lock); } void debug_mutex_init(struct mutex *lock, const char *name, @@ -95,7 +89,6 @@ void debug_mutex_init(struct mutex *lock, const char *name, debug_check_no_locks_freed((void *)lock, sizeof(*lock)); lockdep_init_map(&lock->dep_map, name, key, 0); #endif - lock->owner = NULL; lock->magic = lock; } diff --git a/kernel/mutex-debug.h b/kernel/mutex-debug.h index babfbdfc534b..6b2d735846a5 100644 --- a/kernel/mutex-debug.h +++ b/kernel/mutex-debug.h @@ -13,14 +13,6 @@ /* * This must be called with lock->wait_lock held. */ -extern void -debug_mutex_set_owner(struct mutex *lock, struct thread_info *new_owner); - -static inline void debug_mutex_clear_owner(struct mutex *lock) -{ - lock->owner = NULL; -} - extern void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter); extern void debug_mutex_wake_waiter(struct mutex *lock, @@ -35,6 +27,16 @@ extern void debug_mutex_unlock(struct mutex *lock); extern void debug_mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key); +static inline void mutex_set_owner(struct mutex *lock) +{ + lock->owner = current_thread_info(); +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ + lock->owner = NULL; +} + #define spin_lock_mutex(lock, flags) \ do { \ struct mutex *l = container_of(lock, struct mutex, wait_lock); \ diff --git a/kernel/mutex.c b/kernel/mutex.c index 4f45d4b658ef..5d79781394a3 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -10,6 +10,11 @@ * Many thanks to Arjan van de Ven, Thomas Gleixner, Steven Rostedt and * David Howells for suggestions and improvements. * + * - Adaptive spinning for mutexes by Peter Zijlstra. (Ported to mainline + * from the -rt tree, where it was originally implemented for rtmutexes + * by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale + * and Sven Dietrich. + * * Also see Documentation/mutex-design.txt. */ #include <linux/mutex.h> @@ -46,6 +51,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) atomic_set(&lock->count, 1); spin_lock_init(&lock->wait_lock); INIT_LIST_HEAD(&lock->wait_list); + mutex_clear_owner(lock); debug_mutex_init(lock, name, key); } @@ -91,6 +97,7 @@ void inline __sched mutex_lock(struct mutex *lock) * 'unlocked' into 'locked' state. */ __mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath); + mutex_set_owner(lock); } EXPORT_SYMBOL(mutex_lock); @@ -115,6 +122,14 @@ void __sched mutex_unlock(struct mutex *lock) * The unlocking fastpath is the 0->1 transition from 'locked' * into 'unlocked' state: */ +#ifndef CONFIG_DEBUG_MUTEXES + /* + * When debugging is enabled we must not clear the owner before time, + * the slow path will always be taken, and that clears the owner field + * after verifying that it was indeed current. + */ + mutex_clear_owner(lock); +#endif __mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath); } @@ -129,21 +144,75 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, { struct task_struct *task = current; struct mutex_waiter waiter; - unsigned int old_val; unsigned long flags; + preempt_disable(); + mutex_acquire(&lock->dep_map, subclass, 0, ip); +#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES) + /* + * Optimistic spinning. + * + * We try to spin for acquisition when we find that there are no + * pending waiters and the lock owner is currently running on a + * (different) CPU. + * + * The rationale is that if the lock owner is running, it is likely to + * release the lock soon. + * + * Since this needs the lock owner, and this mutex implementation + * doesn't track the owner atomically in the lock field, we need to + * track it non-atomically. + * + * We can't do this for DEBUG_MUTEXES because that relies on wait_lock + * to serialize everything. + */ + + for (;;) { + struct thread_info *owner; + + /* + * If there's an owner, wait for it to either + * release the lock or go to sleep. + */ + owner = ACCESS_ONCE(lock->owner); + if (owner && !mutex_spin_on_owner(lock, owner)) + break; + + if (atomic_cmpxchg(&lock->count, 1, 0) == 1) { + lock_acquired(&lock->dep_map, ip); + mutex_set_owner(lock); + preempt_enable(); + return 0; + } + + /* + * When there's no owner, we might have preempted between the + * owner acquiring the lock and setting the owner field. If + * we're an RT task that will live-lock because we won't let + * the owner complete. + */ + if (!owner && (need_resched() || rt_task(task))) + break; + + /* + * The cpu_relax() call is a compiler barrier which forces + * everything in this loop to be re-loaded. We don't need + * memory barriers as we'll eventually observe the right + * values at the cost of a few extra spins. + */ + cpu_relax(); + } +#endif spin_lock_mutex(&lock->wait_lock, flags); debug_mutex_lock_common(lock, &waiter); - mutex_acquire(&lock->dep_map, subclass, 0, ip); debug_mutex_add_waiter(lock, &waiter, task_thread_info(task)); /* add waiting tasks to the end of the waitqueue (FIFO): */ list_add_tail(&waiter.list, &lock->wait_list); waiter.task = task; - old_val = atomic_xchg(&lock->count, -1); - if (old_val == 1) + if (atomic_xchg(&lock->count, -1) == 1) goto done; lock_contended(&lock->dep_map, ip); @@ -158,8 +227,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * that when we release the lock, we properly wake up the * other waiters: */ - old_val = atomic_xchg(&lock->count, -1); - if (old_val == 1) + if (atomic_xchg(&lock->count, -1) == 1) break; /* @@ -173,21 +241,22 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, spin_unlock_mutex(&lock->wait_lock, flags); debug_mutex_free_waiter(&waiter); + preempt_enable(); return -EINTR; } __set_task_state(task, state); /* didnt get the lock, go to sleep: */ spin_unlock_mutex(&lock->wait_lock, flags); - schedule(); + __schedule(); spin_lock_mutex(&lock->wait_lock, flags); } done: lock_acquired(&lock->dep_map, ip); /* got the lock - rejoice! */ - mutex_remove_waiter(lock, &waiter, task_thread_info(task)); - debug_mutex_set_owner(lock, task_thread_info(task)); + mutex_remove_waiter(lock, &waiter, current_thread_info()); + mutex_set_owner(lock); /* set it to 0 if there are no waiters left: */ if (likely(list_empty(&lock->wait_list))) @@ -196,6 +265,7 @@ done: spin_unlock_mutex(&lock->wait_lock, flags); debug_mutex_free_waiter(&waiter); + preempt_enable(); return 0; } @@ -222,7 +292,8 @@ int __sched mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); - return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, subclass, _RET_IP_); + return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, + subclass, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); @@ -260,8 +331,6 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) wake_up_process(waiter->task); } - debug_mutex_clear_owner(lock); - spin_unlock_mutex(&lock->wait_lock, flags); } @@ -298,18 +367,30 @@ __mutex_lock_interruptible_slowpath(atomic_t *lock_count); */ int __sched mutex_lock_interruptible(struct mutex *lock) { + int ret; + might_sleep(); - return __mutex_fastpath_lock_retval + ret = __mutex_fastpath_lock_retval (&lock->count, __mutex_lock_interruptible_slowpath); + if (!ret) + mutex_set_owner(lock); + + return ret; } EXPORT_SYMBOL(mutex_lock_interruptible); int __sched mutex_lock_killable(struct mutex *lock) { + int ret; + might_sleep(); - return __mutex_fastpath_lock_retval + ret = __mutex_fastpath_lock_retval (&lock->count, __mutex_lock_killable_slowpath); + if (!ret) + mutex_set_owner(lock); + + return ret; } EXPORT_SYMBOL(mutex_lock_killable); @@ -352,9 +433,10 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) prev = atomic_xchg(&lock->count, -1); if (likely(prev == 1)) { - debug_mutex_set_owner(lock, current_thread_info()); + mutex_set_owner(lock); mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); } + /* Set it back to 0 if there are no waiters: */ if (likely(list_empty(&lock->wait_list))) atomic_set(&lock->count, 0); @@ -380,8 +462,13 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) */ int __sched mutex_trylock(struct mutex *lock) { - return __mutex_fastpath_trylock(&lock->count, - __mutex_trylock_slowpath); + int ret; + + ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath); + if (ret) + mutex_set_owner(lock); + + return ret; } EXPORT_SYMBOL(mutex_trylock); diff --git a/kernel/mutex.h b/kernel/mutex.h index a075dafbb290..67578ca48f94 100644 --- a/kernel/mutex.h +++ b/kernel/mutex.h @@ -16,8 +16,26 @@ #define mutex_remove_waiter(lock, waiter, ti) \ __list_del((waiter)->list.prev, (waiter)->list.next) -#define debug_mutex_set_owner(lock, new_owner) do { } while (0) -#define debug_mutex_clear_owner(lock) do { } while (0) +#ifdef CONFIG_SMP +static inline void mutex_set_owner(struct mutex *lock) +{ + lock->owner = current_thread_info(); +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ + lock->owner = NULL; +} +#else +static inline void mutex_set_owner(struct mutex *lock) +{ +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ +} +#endif + #define debug_mutex_wake_waiter(lock, waiter) do { } while (0) #define debug_mutex_free_waiter(waiter) do { } while (0) #define debug_mutex_add_waiter(lock, waiter, ti) do { } while (0) diff --git a/kernel/panic.c b/kernel/panic.c index 2a2ff36ff44d..33cab3de1763 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -74,6 +74,9 @@ NORET_TYPE void panic(const char * fmt, ...) vsnprintf(buf, sizeof(buf), fmt, args); va_end(args); printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf); +#ifdef CONFIG_DEBUG_BUGVERBOSE + dump_stack(); +#endif bust_spinlocks(0); /* @@ -355,15 +358,22 @@ EXPORT_SYMBOL(warn_slowpath); #endif #ifdef CONFIG_CC_STACKPROTECTOR + +#ifndef GCC_HAS_SP +#warning You have selected the CONFIG_CC_STACKPROTECTOR option, but the gcc used does not support this. +#endif + /* * Called when gcc's -fstack-protector feature is used, and * gcc detects corruption of the on-stack canary value */ void __stack_chk_fail(void) { - panic("stack-protector: Kernel stack is corrupted"); + panic("stack-protector: Kernel stack is corrupted in: %p\n", + __builtin_return_address(0)); } EXPORT_SYMBOL(__stack_chk_fail); + #endif core_param(panic, panic_timeout, int, 0644); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 157de3a47832..fa07da94d7be 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -10,76 +10,6 @@ #include <linux/kernel_stat.h> /* - * Allocate the thread_group_cputime structure appropriately and fill in the - * current values of the fields. Called from copy_signal() via - * thread_group_cputime_clone_thread() when adding a second or subsequent - * thread to a thread group. Assumes interrupts are enabled when called. - */ -int thread_group_cputime_alloc(struct task_struct *tsk) -{ - struct signal_struct *sig = tsk->signal; - struct task_cputime *cputime; - - /* - * If we have multiple threads and we don't already have a - * per-CPU task_cputime struct (checked in the caller), allocate - * one and fill it in with the times accumulated so far. We may - * race with another thread so recheck after we pick up the sighand - * lock. - */ - cputime = alloc_percpu(struct task_cputime); - if (cputime == NULL) - return -ENOMEM; - spin_lock_irq(&tsk->sighand->siglock); - if (sig->cputime.totals) { - spin_unlock_irq(&tsk->sighand->siglock); - free_percpu(cputime); - return 0; - } - sig->cputime.totals = cputime; - cputime = per_cpu_ptr(sig->cputime.totals, smp_processor_id()); - cputime->utime = tsk->utime; - cputime->stime = tsk->stime; - cputime->sum_exec_runtime = tsk->se.sum_exec_runtime; - spin_unlock_irq(&tsk->sighand->siglock); - return 0; -} - -/** - * thread_group_cputime - Sum the thread group time fields across all CPUs. - * - * @tsk: The task we use to identify the thread group. - * @times: task_cputime structure in which we return the summed fields. - * - * Walk the list of CPUs to sum the per-CPU time fields in the thread group - * time structure. - */ -void thread_group_cputime( - struct task_struct *tsk, - struct task_cputime *times) -{ - struct task_cputime *totals, *tot; - int i; - - totals = tsk->signal->cputime.totals; - if (!totals) { - times->utime = tsk->utime; - times->stime = tsk->stime; - times->sum_exec_runtime = tsk->se.sum_exec_runtime; - return; - } - - times->stime = times->utime = cputime_zero; - times->sum_exec_runtime = 0; - for_each_possible_cpu(i) { - tot = per_cpu_ptr(totals, i); - times->utime = cputime_add(times->utime, tot->utime); - times->stime = cputime_add(times->stime, tot->stime); - times->sum_exec_runtime += tot->sum_exec_runtime; - } -} - -/* * Called after updating RLIMIT_CPU to set timer expiration if necessary. */ void update_rlimit_cpu(unsigned long rlim_new) diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 45e8541ab7e3..432ee575c9ee 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -71,6 +71,14 @@ void hibernation_set_ops(struct platform_hibernation_ops *ops) mutex_unlock(&pm_mutex); } +static bool entering_platform_hibernation; + +bool system_entering_hibernation(void) +{ + return entering_platform_hibernation; +} +EXPORT_SYMBOL(system_entering_hibernation); + #ifdef CONFIG_PM_DEBUG static void hibernation_debug_sleep(void) { @@ -411,6 +419,7 @@ int hibernation_platform_enter(void) if (error) goto Close; + entering_platform_hibernation = true; suspend_console(); error = device_suspend(PMSG_HIBERNATE); if (error) { @@ -445,6 +454,7 @@ int hibernation_platform_enter(void) Finish: hibernation_ops->finish(); Resume_devices: + entering_platform_hibernation = false; device_resume(PMSG_RESTORE); resume_console(); Close: diff --git a/kernel/power/main.c b/kernel/power/main.c index 239988873971..b4d219016b6c 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -57,16 +57,6 @@ int pm_notifier_call_chain(unsigned long val) #ifdef CONFIG_PM_DEBUG int pm_test_level = TEST_NONE; -static int suspend_test(int level) -{ - if (pm_test_level == level) { - printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n"); - mdelay(5000); - return 1; - } - return 0; -} - static const char * const pm_tests[__TEST_AFTER_LAST] = { [TEST_NONE] = "none", [TEST_CORE] = "core", @@ -125,14 +115,24 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr, } power_attr(pm_test); -#else /* !CONFIG_PM_DEBUG */ -static inline int suspend_test(int level) { return 0; } -#endif /* !CONFIG_PM_DEBUG */ +#endif /* CONFIG_PM_DEBUG */ #endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_SUSPEND +static int suspend_test(int level) +{ +#ifdef CONFIG_PM_DEBUG + if (pm_test_level == level) { + printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n"); + mdelay(5000); + return 1; + } +#endif /* !CONFIG_PM_DEBUG */ + return 0; +} + #ifdef CONFIG_PM_TEST_SUSPEND /* diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c index 490934fc7ac3..bd5a9003497c 100644 --- a/kernel/rcuclassic.c +++ b/kernel/rcuclassic.c @@ -716,7 +716,7 @@ void rcu_check_callbacks(int cpu, int user) raise_rcu_softirq(); } -static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp, +static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp, struct rcu_data *rdp) { unsigned long flags; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index f2d8638e6c60..b2fd602a6f6f 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1314,7 +1314,7 @@ int rcu_needs_cpu(int cpu) * access due to the fact that this CPU cannot possibly have any RCU * callbacks in flight yet. */ -static void +static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_state *rsp) { unsigned long flags; diff --git a/kernel/relay.c b/kernel/relay.c index 09ac2008f77b..edc0ba6d8160 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -663,8 +663,10 @@ int relay_late_setup_files(struct rchan *chan, mutex_lock(&relay_channels_mutex); /* Is chan already set up? */ - if (unlikely(chan->has_base_filename)) + if (unlikely(chan->has_base_filename)) { + mutex_unlock(&relay_channels_mutex); return -EEXIST; + } chan->has_base_filename = 1; chan->parent = parent; curr_cpu = get_cpu(); @@ -675,9 +677,7 @@ int relay_late_setup_files(struct rchan *chan, */ for_each_online_cpu(i) { if (unlikely(!chan->buf[i])) { - printk(KERN_ERR "relay_late_setup_files: CPU %u " - "has no buffer, it must have!\n", i); - BUG(); + WARN_ONCE(1, KERN_ERR "CPU has no buffer!\n"); err = -EINVAL; break; } diff --git a/kernel/sched.c b/kernel/sched.c index 52bbf1c842a8..3a4763257395 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -467,11 +467,17 @@ struct rt_rq { struct rt_prio_array active; unsigned long rt_nr_running; #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED - int highest_prio; /* highest queued rt task prio */ + struct { + int curr; /* highest queued rt task prio */ +#ifdef CONFIG_SMP + int next; /* next highest */ +#endif + } highest_prio; #endif #ifdef CONFIG_SMP unsigned long rt_nr_migratory; int overloaded; + struct plist_head pushable_tasks; #endif int rt_throttled; u64 rt_time; @@ -1610,21 +1616,42 @@ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd) #endif +#ifdef CONFIG_PREEMPT + /* - * double_lock_balance - lock the busiest runqueue, this_rq is locked already. + * fair double_lock_balance: Safely acquires both rq->locks in a fair + * way at the expense of forcing extra atomic operations in all + * invocations. This assures that the double_lock is acquired using the + * same underlying policy as the spinlock_t on this architecture, which + * reduces latency compared to the unfair variant below. However, it + * also adds more overhead and therefore may reduce throughput. */ -static int double_lock_balance(struct rq *this_rq, struct rq *busiest) +static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) + __releases(this_rq->lock) + __acquires(busiest->lock) + __acquires(this_rq->lock) +{ + spin_unlock(&this_rq->lock); + double_rq_lock(this_rq, busiest); + + return 1; +} + +#else +/* + * Unfair double_lock_balance: Optimizes throughput at the expense of + * latency by eliminating extra atomic operations when the locks are + * already in proper order on entry. This favors lower cpu-ids and will + * grant the double lock to lower cpus over higher ids under contention, + * regardless of entry order into the function. + */ +static int _double_lock_balance(struct rq *this_rq, struct rq *busiest) __releases(this_rq->lock) __acquires(busiest->lock) __acquires(this_rq->lock) { int ret = 0; - if (unlikely(!irqs_disabled())) { - /* printk() doesn't work good under rq->lock */ - spin_unlock(&this_rq->lock); - BUG_ON(1); - } if (unlikely(!spin_trylock(&busiest->lock))) { if (busiest < this_rq) { spin_unlock(&this_rq->lock); @@ -1637,6 +1664,22 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest) return ret; } +#endif /* CONFIG_PREEMPT */ + +/* + * double_lock_balance - lock the busiest runqueue, this_rq is locked already. + */ +static int double_lock_balance(struct rq *this_rq, struct rq *busiest) +{ + if (unlikely(!irqs_disabled())) { + /* printk() doesn't work good under rq->lock */ + spin_unlock(&this_rq->lock); + BUG_ON(1); + } + + return _double_lock_balance(this_rq, busiest); +} + static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) __releases(busiest->lock) { @@ -1705,6 +1748,9 @@ static void update_avg(u64 *avg, u64 sample) static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup) { + if (wakeup) + p->se.start_runtime = p->se.sum_exec_runtime; + sched_info_queued(p); p->sched_class->enqueue_task(rq, p, wakeup); p->se.on_rq = 1; @@ -1712,10 +1758,15 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup) static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) { - if (sleep && p->se.last_wakeup) { - update_avg(&p->se.avg_overlap, - p->se.sum_exec_runtime - p->se.last_wakeup); - p->se.last_wakeup = 0; + if (sleep) { + if (p->se.last_wakeup) { + update_avg(&p->se.avg_overlap, + p->se.sum_exec_runtime - p->se.last_wakeup); + p->se.last_wakeup = 0; + } else { + update_avg(&p->se.avg_wakeup, + sysctl_sched_wakeup_granularity); + } } sched_info_dequeued(p); @@ -2266,6 +2317,16 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) if (!sched_feat(SYNC_WAKEUPS)) sync = 0; + if (!sync) { + if (current->se.avg_overlap < sysctl_sched_migration_cost && + p->se.avg_overlap < sysctl_sched_migration_cost) + sync = 1; + } else { + if (current->se.avg_overlap >= sysctl_sched_migration_cost || + p->se.avg_overlap >= sysctl_sched_migration_cost) + sync = 0; + } + #ifdef CONFIG_SMP if (sched_feat(LB_WAKEUP_UPDATE)) { struct sched_domain *sd; @@ -2345,6 +2406,22 @@ out_activate: activate_task(rq, p, 1); success = 1; + /* + * Only attribute actual wakeups done by this task. + */ + if (!in_interrupt()) { + struct sched_entity *se = ¤t->se; + u64 sample = se->sum_exec_runtime; + + if (se->last_wakeup) + sample -= se->last_wakeup; + else + sample -= se->start_runtime; + update_avg(&se->avg_wakeup, sample); + + se->last_wakeup = se->sum_exec_runtime; + } + out_running: trace_sched_wakeup(rq, p, success); check_preempt_curr(rq, p, sync); @@ -2355,8 +2432,6 @@ out_running: p->sched_class->task_wake_up(rq, p); #endif out: - current->se.last_wakeup = current->se.sum_exec_runtime; - task_rq_unlock(rq, &flags); return success; @@ -2386,6 +2461,8 @@ static void __sched_fork(struct task_struct *p) p->se.prev_sum_exec_runtime = 0; p->se.last_wakeup = 0; p->se.avg_overlap = 0; + p->se.start_runtime = 0; + p->se.avg_wakeup = sysctl_sched_wakeup_granularity; #ifdef CONFIG_SCHEDSTATS p->se.wait_start = 0; @@ -2448,6 +2525,8 @@ void sched_fork(struct task_struct *p, int clone_flags) /* Want to start with kernel preemption disabled. */ task_thread_info(p)->preempt_count = 1; #endif + plist_node_init(&p->pushable_tasks, MAX_PRIO); + put_cpu(); } @@ -2588,6 +2667,12 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) { struct mm_struct *mm = rq->prev_mm; long prev_state; +#ifdef CONFIG_SMP + int post_schedule = 0; + + if (current->sched_class->needs_post_schedule) + post_schedule = current->sched_class->needs_post_schedule(rq); +#endif rq->prev_mm = NULL; @@ -2606,7 +2691,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) finish_arch_switch(prev); finish_lock_switch(rq, prev); #ifdef CONFIG_SMP - if (current->sched_class->post_schedule) + if (post_schedule) current->sched_class->post_schedule(rq); #endif @@ -2987,6 +3072,16 @@ next: pulled++; rem_load_move -= p->se.load.weight; +#ifdef CONFIG_PREEMPT + /* + * NEWIDLE balancing is a source of latency, so preemptible kernels + * will stop after the first task is pulled to minimize the critical + * section. + */ + if (idle == CPU_NEWLY_IDLE) + goto out; +#endif + /* * We only want to steal up to the prescribed amount of weighted load. */ @@ -3033,9 +3128,15 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, sd, idle, all_pinned, &this_best_prio); class = class->next; +#ifdef CONFIG_PREEMPT + /* + * NEWIDLE balancing is a source of latency, so preemptible + * kernels will stop after the first task is pulled to minimize + * the critical section. + */ if (idle == CPU_NEWLY_IDLE && this_rq->nr_running) break; - +#endif } while (class && max_load_move > total_load_moved); return total_load_moved > 0; @@ -4538,15 +4639,13 @@ pick_next_task(struct rq *rq, struct task_struct *prev) /* * schedule() is the main scheduler function. */ -asmlinkage void __sched schedule(void) +asmlinkage void __sched __schedule(void) { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; -need_resched: - preempt_disable(); cpu = smp_processor_id(); rq = cpu_rq(cpu); rcu_qsctr_inc(cpu); @@ -4603,13 +4702,80 @@ need_resched_nonpreemptible: if (unlikely(reacquire_kernel_lock(current) < 0)) goto need_resched_nonpreemptible; +} +asmlinkage void __sched schedule(void) +{ +need_resched: + preempt_disable(); + __schedule(); preempt_enable_no_resched(); if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) goto need_resched; } EXPORT_SYMBOL(schedule); +#ifdef CONFIG_SMP +/* + * Look out! "owner" is an entirely speculative pointer + * access and not reliable. + */ +int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) +{ + unsigned int cpu; + struct rq *rq; + + if (!sched_feat(OWNER_SPIN)) + return 0; + +#ifdef CONFIG_DEBUG_PAGEALLOC + /* + * Need to access the cpu field knowing that + * DEBUG_PAGEALLOC could have unmapped it if + * the mutex owner just released it and exited. + */ + if (probe_kernel_address(&owner->cpu, cpu)) + goto out; +#else + cpu = owner->cpu; +#endif + + /* + * Even if the access succeeded (likely case), + * the cpu field may no longer be valid. + */ + if (cpu >= nr_cpumask_bits) + goto out; + + /* + * We need to validate that we can do a + * get_cpu() and that we have the percpu area. + */ + if (!cpu_online(cpu)) + goto out; + + rq = cpu_rq(cpu); + + for (;;) { + /* + * Owner changed, break to re-assess state. + */ + if (lock->owner != owner) + break; + + /* + * Is that owner really running on that cpu? + */ + if (task_thread_info(rq->curr) != owner || need_resched()) + return 0; + + cpu_relax(); + } +out: + return 1; +} +#endif + #ifdef CONFIG_PREEMPT /* * this is the entry point to schedule() from in-kernel preemption @@ -5939,12 +6105,7 @@ void sched_show_task(struct task_struct *p) printk(KERN_CONT " %016lx ", thread_saved_pc(p)); #endif #ifdef CONFIG_DEBUG_STACK_USAGE - { - unsigned long *n = end_of_stack(p); - while (!*n) - n++; - free = (unsigned long)n - (unsigned long)end_of_stack(p); - } + free = stack_not_used(p); #endif printk(KERN_CONT "%5lu %5d %6d\n", free, task_pid_nr(p), task_pid_nr(p->real_parent)); @@ -8204,11 +8365,15 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) __set_bit(MAX_RT_PRIO, array->bitmap); #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED - rt_rq->highest_prio = MAX_RT_PRIO; + rt_rq->highest_prio.curr = MAX_RT_PRIO; +#ifdef CONFIG_SMP + rt_rq->highest_prio.next = MAX_RT_PRIO; +#endif #endif #ifdef CONFIG_SMP rt_rq->rt_nr_migratory = 0; rt_rq->overloaded = 0; + plist_head_init(&rq->rt.pushable_tasks, &rq->lock); #endif rt_rq->rt_time = 0; diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c index 1e00bfacf9b8..cdd3c89574cd 100644 --- a/kernel/sched_cpupri.c +++ b/kernel/sched_cpupri.c @@ -55,7 +55,7 @@ static int convert_prio(int prio) * cpupri_find - find the best (lowest-pri) CPU in the system * @cp: The cpupri context * @p: The task - * @lowest_mask: A mask to fill in with selected CPUs + * @lowest_mask: A mask to fill in with selected CPUs (or NULL) * * Note: This function returns the recommended CPUs as calculated during the * current invokation. By the time the call returns, the CPUs may have in @@ -81,7 +81,8 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) continue; - cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); + if (lowest_mask) + cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); return 1; } diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 16eeba4e4169..2b1260f0e800 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -397,6 +397,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) PN(se.vruntime); PN(se.sum_exec_runtime); PN(se.avg_overlap); + PN(se.avg_wakeup); nr_switches = p->nvcsw + p->nivcsw; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 5cc1c162044f..bc1563e7a248 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -719,7 +719,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup) __enqueue_entity(cfs_rq, se); } -static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) +static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) { if (cfs_rq->last == se) cfs_rq->last = NULL; @@ -728,6 +728,12 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) cfs_rq->next = NULL; } +static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + for_each_sched_entity(se) + __clear_buddies(cfs_rq_of(se), se); +} + static void dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep) { @@ -768,8 +774,14 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) ideal_runtime = sched_slice(cfs_rq, curr); delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; - if (delta_exec > ideal_runtime) + if (delta_exec > ideal_runtime) { resched_task(rq_of(cfs_rq)->curr); + /* + * The current task ran long enough, ensure it doesn't get + * re-elected due to buddy favours. + */ + clear_buddies(cfs_rq, curr); + } } static void @@ -1179,20 +1191,15 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq, int idx, unsigned long load, unsigned long this_load, unsigned int imbalance) { - struct task_struct *curr = this_rq->curr; - struct task_group *tg; unsigned long tl = this_load; unsigned long tl_per_task; + struct task_group *tg; unsigned long weight; int balanced; if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS)) return 0; - if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost || - p->se.avg_overlap > sysctl_sched_migration_cost)) - sync = 0; - /* * If sync wakeup then subtract the (maximum possible) * effect of the currently running task from the load @@ -1302,16 +1309,63 @@ out: } #endif /* CONFIG_SMP */ -static unsigned long wakeup_gran(struct sched_entity *se) +/* + * Adaptive granularity + * + * se->avg_wakeup gives the average time a task runs until it does a wakeup, + * with the limit of wakeup_gran -- when it never does a wakeup. + * + * So the smaller avg_wakeup is the faster we want this task to preempt, + * but we don't want to treat the preemptee unfairly and therefore allow it + * to run for at least the amount of time we'd like to run. + * + * NOTE: we use 2*avg_wakeup to increase the probability of actually doing one + * + * NOTE: we use *nr_running to scale with load, this nicely matches the + * degrading latency on load. + */ +static unsigned long +adaptive_gran(struct sched_entity *curr, struct sched_entity *se) +{ + u64 this_run = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; + u64 expected_wakeup = 2*se->avg_wakeup * cfs_rq_of(se)->nr_running; + u64 gran = 0; + + if (this_run < expected_wakeup) + gran = expected_wakeup - this_run; + + return min_t(s64, gran, sysctl_sched_wakeup_granularity); +} + +static unsigned long +wakeup_gran(struct sched_entity *curr, struct sched_entity *se) { unsigned long gran = sysctl_sched_wakeup_granularity; + if (cfs_rq_of(curr)->curr && sched_feat(ADAPTIVE_GRAN)) + gran = adaptive_gran(curr, se); + /* - * More easily preempt - nice tasks, while not making it harder for - * + nice tasks. + * Since its curr running now, convert the gran from real-time + * to virtual-time in his units. */ - if (!sched_feat(ASYM_GRAN) || se->load.weight > NICE_0_LOAD) - gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se); + if (sched_feat(ASYM_GRAN)) { + /* + * By using 'se' instead of 'curr' we penalize light tasks, so + * they get preempted easier. That is, if 'se' < 'curr' then + * the resulting gran will be larger, therefore penalizing the + * lighter, if otoh 'se' > 'curr' then the resulting gran will + * be smaller, again penalizing the lighter task. + * + * This is especially important for buddies when the leftmost + * task is higher priority than the buddy. + */ + if (unlikely(se->load.weight != NICE_0_LOAD)) + gran = calc_delta_fair(gran, se); + } else { + if (unlikely(curr->load.weight != NICE_0_LOAD)) + gran = calc_delta_fair(gran, curr); + } return gran; } @@ -1338,7 +1392,7 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se) if (vdiff <= 0) return -1; - gran = wakeup_gran(curr); + gran = wakeup_gran(curr, se); if (vdiff > gran) return 1; @@ -1419,9 +1473,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync) if (!sched_feat(WAKEUP_PREEMPT)) return; - if (sched_feat(WAKEUP_OVERLAP) && (sync || - (se->avg_overlap < sysctl_sched_migration_cost && - pse->avg_overlap < sysctl_sched_migration_cost))) { + if (sched_feat(WAKEUP_OVERLAP) && sync) { resched_task(curr); return; } @@ -1452,6 +1504,11 @@ static struct task_struct *pick_next_task_fair(struct rq *rq) do { se = pick_next_entity(cfs_rq); + /* + * If se was a buddy, clear it so that it will have to earn + * the favour again. + */ + __clear_buddies(cfs_rq, se); set_next_entity(cfs_rq, se); cfs_rq = group_cfs_rq(se); } while (cfs_rq); diff --git a/kernel/sched_features.h b/kernel/sched_features.h index da5d93b5d2c6..4569bfa7df9b 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -1,5 +1,6 @@ SCHED_FEAT(NEW_FAIR_SLEEPERS, 1) -SCHED_FEAT(NORMALIZED_SLEEPER, 1) +SCHED_FEAT(NORMALIZED_SLEEPER, 0) +SCHED_FEAT(ADAPTIVE_GRAN, 1) SCHED_FEAT(WAKEUP_PREEMPT, 1) SCHED_FEAT(START_DEBIT, 1) SCHED_FEAT(AFFINE_WAKEUPS, 1) @@ -13,3 +14,4 @@ SCHED_FEAT(LB_WAKEUP_UPDATE, 1) SCHED_FEAT(ASYM_EFF_LOAD, 1) SCHED_FEAT(WAKEUP_OVERLAP, 0) SCHED_FEAT(LAST_BUDDY, 1) +SCHED_FEAT(OWNER_SPIN, 1) diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 954e1a81b796..f2c66f8f9712 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -3,6 +3,40 @@ * policies) */ +static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se) +{ + return container_of(rt_se, struct task_struct, rt); +} + +#ifdef CONFIG_RT_GROUP_SCHED + +static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) +{ + return rt_rq->rq; +} + +static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) +{ + return rt_se->rt_rq; +} + +#else /* CONFIG_RT_GROUP_SCHED */ + +static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) +{ + return container_of(rt_rq, struct rq, rt); +} + +static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) +{ + struct task_struct *p = rt_task_of(rt_se); + struct rq *rq = task_rq(p); + + return &rq->rt; +} + +#endif /* CONFIG_RT_GROUP_SCHED */ + #ifdef CONFIG_SMP static inline int rt_overloaded(struct rq *rq) @@ -37,25 +71,69 @@ static inline void rt_clear_overload(struct rq *rq) cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask); } -static void update_rt_migration(struct rq *rq) +static void update_rt_migration(struct rt_rq *rt_rq) { - if (rq->rt.rt_nr_migratory && (rq->rt.rt_nr_running > 1)) { - if (!rq->rt.overloaded) { - rt_set_overload(rq); - rq->rt.overloaded = 1; + if (rt_rq->rt_nr_migratory && (rt_rq->rt_nr_running > 1)) { + if (!rt_rq->overloaded) { + rt_set_overload(rq_of_rt_rq(rt_rq)); + rt_rq->overloaded = 1; } - } else if (rq->rt.overloaded) { - rt_clear_overload(rq); - rq->rt.overloaded = 0; + } else if (rt_rq->overloaded) { + rt_clear_overload(rq_of_rt_rq(rt_rq)); + rt_rq->overloaded = 0; } } -#endif /* CONFIG_SMP */ -static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se) +static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { - return container_of(rt_se, struct task_struct, rt); + if (rt_se->nr_cpus_allowed > 1) + rt_rq->rt_nr_migratory++; + + update_rt_migration(rt_rq); +} + +static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + if (rt_se->nr_cpus_allowed > 1) + rt_rq->rt_nr_migratory--; + + update_rt_migration(rt_rq); +} + +static void enqueue_pushable_task(struct rq *rq, struct task_struct *p) +{ + plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks); + plist_node_init(&p->pushable_tasks, p->prio); + plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks); } +static void dequeue_pushable_task(struct rq *rq, struct task_struct *p) +{ + plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks); +} + +#else + +static inline void enqueue_pushable_task(struct rq *rq, struct task_struct *p) +{ +} + +static inline void dequeue_pushable_task(struct rq *rq, struct task_struct *p) +{ +} + +static inline +void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ +} + +static inline +void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ +} + +#endif /* CONFIG_SMP */ + static inline int on_rt_rq(struct sched_rt_entity *rt_se) { return !list_empty(&rt_se->run_list); @@ -79,16 +157,6 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq) #define for_each_leaf_rt_rq(rt_rq, rq) \ list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list) -static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) -{ - return rt_rq->rq; -} - -static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) -{ - return rt_se->rt_rq; -} - #define for_each_sched_rt_entity(rt_se) \ for (; rt_se; rt_se = rt_se->parent) @@ -108,7 +176,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) if (rt_rq->rt_nr_running) { if (rt_se && !on_rt_rq(rt_se)) enqueue_rt_entity(rt_se); - if (rt_rq->highest_prio < curr->prio) + if (rt_rq->highest_prio.curr < curr->prio) resched_task(curr); } } @@ -176,19 +244,6 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq) #define for_each_leaf_rt_rq(rt_rq, rq) \ for (rt_rq = &rq->rt; rt_rq; rt_rq = NULL) -static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) -{ - return container_of(rt_rq, struct rq, rt); -} - -static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) -{ - struct task_struct *p = rt_task_of(rt_se); - struct rq *rq = task_rq(p); - - return &rq->rt; -} - #define for_each_sched_rt_entity(rt_se) \ for (; rt_se; rt_se = NULL) @@ -473,7 +528,7 @@ static inline int rt_se_prio(struct sched_rt_entity *rt_se) struct rt_rq *rt_rq = group_rt_rq(rt_se); if (rt_rq) - return rt_rq->highest_prio; + return rt_rq->highest_prio.curr; #endif return rt_task_of(rt_se)->prio; @@ -547,91 +602,174 @@ static void update_curr_rt(struct rq *rq) } } -static inline -void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +#if defined CONFIG_SMP + +static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu); + +static inline int next_prio(struct rq *rq) { - WARN_ON(!rt_prio(rt_se_prio(rt_se))); - rt_rq->rt_nr_running++; -#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED - if (rt_se_prio(rt_se) < rt_rq->highest_prio) { -#ifdef CONFIG_SMP - struct rq *rq = rq_of_rt_rq(rt_rq); -#endif + struct task_struct *next = pick_next_highest_task_rt(rq, rq->cpu); + + if (next && rt_prio(next->prio)) + return next->prio; + else + return MAX_RT_PRIO; +} + +static void +inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + if (prio < prev_prio) { + + /* + * If the new task is higher in priority than anything on the + * run-queue, we know that the previous high becomes our + * next-highest. + */ + rt_rq->highest_prio.next = prev_prio; - rt_rq->highest_prio = rt_se_prio(rt_se); -#ifdef CONFIG_SMP if (rq->online) - cpupri_set(&rq->rd->cpupri, rq->cpu, - rt_se_prio(rt_se)); -#endif - } -#endif -#ifdef CONFIG_SMP - if (rt_se->nr_cpus_allowed > 1) { - struct rq *rq = rq_of_rt_rq(rt_rq); + cpupri_set(&rq->rd->cpupri, rq->cpu, prio); - rq->rt.rt_nr_migratory++; - } + } else if (prio == rt_rq->highest_prio.curr) + /* + * If the next task is equal in priority to the highest on + * the run-queue, then we implicitly know that the next highest + * task cannot be any lower than current + */ + rt_rq->highest_prio.next = prio; + else if (prio < rt_rq->highest_prio.next) + /* + * Otherwise, we need to recompute next-highest + */ + rt_rq->highest_prio.next = next_prio(rq); +} - update_rt_migration(rq_of_rt_rq(rt_rq)); -#endif -#ifdef CONFIG_RT_GROUP_SCHED - if (rt_se_boosted(rt_se)) - rt_rq->rt_nr_boosted++; +static void +dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); - if (rt_rq->tg) - start_rt_bandwidth(&rt_rq->tg->rt_bandwidth); -#else - start_rt_bandwidth(&def_rt_bandwidth); -#endif + if (rt_rq->rt_nr_running && (prio <= rt_rq->highest_prio.next)) + rt_rq->highest_prio.next = next_prio(rq); + + if (rq->online && rt_rq->highest_prio.curr != prev_prio) + cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr); } +#else /* CONFIG_SMP */ + static inline -void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) -{ -#ifdef CONFIG_SMP - int highest_prio = rt_rq->highest_prio; -#endif +void inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {} +static inline +void dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {} + +#endif /* CONFIG_SMP */ - WARN_ON(!rt_prio(rt_se_prio(rt_se))); - WARN_ON(!rt_rq->rt_nr_running); - rt_rq->rt_nr_running--; #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED +static void +inc_rt_prio(struct rt_rq *rt_rq, int prio) +{ + int prev_prio = rt_rq->highest_prio.curr; + + if (prio < prev_prio) + rt_rq->highest_prio.curr = prio; + + inc_rt_prio_smp(rt_rq, prio, prev_prio); +} + +static void +dec_rt_prio(struct rt_rq *rt_rq, int prio) +{ + int prev_prio = rt_rq->highest_prio.curr; + if (rt_rq->rt_nr_running) { - struct rt_prio_array *array; - WARN_ON(rt_se_prio(rt_se) < rt_rq->highest_prio); - if (rt_se_prio(rt_se) == rt_rq->highest_prio) { - /* recalculate */ - array = &rt_rq->active; - rt_rq->highest_prio = + WARN_ON(prio < prev_prio); + + /* + * This may have been our highest task, and therefore + * we may have some recomputation to do + */ + if (prio == prev_prio) { + struct rt_prio_array *array = &rt_rq->active; + + rt_rq->highest_prio.curr = sched_find_first_bit(array->bitmap); - } /* otherwise leave rq->highest prio alone */ + } + } else - rt_rq->highest_prio = MAX_RT_PRIO; -#endif -#ifdef CONFIG_SMP - if (rt_se->nr_cpus_allowed > 1) { - struct rq *rq = rq_of_rt_rq(rt_rq); - rq->rt.rt_nr_migratory--; - } + rt_rq->highest_prio.curr = MAX_RT_PRIO; - if (rt_rq->highest_prio != highest_prio) { - struct rq *rq = rq_of_rt_rq(rt_rq); + dec_rt_prio_smp(rt_rq, prio, prev_prio); +} - if (rq->online) - cpupri_set(&rq->rd->cpupri, rq->cpu, - rt_rq->highest_prio); - } +#else + +static inline void inc_rt_prio(struct rt_rq *rt_rq, int prio) {} +static inline void dec_rt_prio(struct rt_rq *rt_rq, int prio) {} + +#endif /* CONFIG_SMP || CONFIG_RT_GROUP_SCHED */ - update_rt_migration(rq_of_rt_rq(rt_rq)); -#endif /* CONFIG_SMP */ #ifdef CONFIG_RT_GROUP_SCHED + +static void +inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + if (rt_se_boosted(rt_se)) + rt_rq->rt_nr_boosted++; + + if (rt_rq->tg) + start_rt_bandwidth(&rt_rq->tg->rt_bandwidth); +} + +static void +dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ if (rt_se_boosted(rt_se)) rt_rq->rt_nr_boosted--; WARN_ON(!rt_rq->rt_nr_running && rt_rq->rt_nr_boosted); -#endif +} + +#else /* CONFIG_RT_GROUP_SCHED */ + +static void +inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + start_rt_bandwidth(&def_rt_bandwidth); +} + +static inline +void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {} + +#endif /* CONFIG_RT_GROUP_SCHED */ + +static inline +void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + int prio = rt_se_prio(rt_se); + + WARN_ON(!rt_prio(prio)); + rt_rq->rt_nr_running++; + + inc_rt_prio(rt_rq, prio); + inc_rt_migration(rt_se, rt_rq); + inc_rt_group(rt_se, rt_rq); +} + +static inline +void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + WARN_ON(!rt_prio(rt_se_prio(rt_se))); + WARN_ON(!rt_rq->rt_nr_running); + rt_rq->rt_nr_running--; + + dec_rt_prio(rt_rq, rt_se_prio(rt_se)); + dec_rt_migration(rt_se, rt_rq); + dec_rt_group(rt_se, rt_rq); } static void __enqueue_rt_entity(struct sched_rt_entity *rt_se) @@ -718,6 +856,9 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup) enqueue_rt_entity(rt_se); + if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1) + enqueue_pushable_task(rq, p); + inc_cpu_load(rq, p->se.load.weight); } @@ -728,6 +869,8 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep) update_curr_rt(rq); dequeue_rt_entity(rt_se); + dequeue_pushable_task(rq, p); + dec_cpu_load(rq, p->se.load.weight); } @@ -805,20 +948,15 @@ static int select_task_rq_rt(struct task_struct *p, int sync) static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) { - cpumask_var_t mask; - if (rq->curr->rt.nr_cpus_allowed == 1) return; - if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) - return; - if (p->rt.nr_cpus_allowed != 1 - && cpupri_find(&rq->rd->cpupri, p, mask)) - goto free; + && cpupri_find(&rq->rd->cpupri, p, NULL)) + return; - if (!cpupri_find(&rq->rd->cpupri, rq->curr, mask)) - goto free; + if (!cpupri_find(&rq->rd->cpupri, rq->curr, NULL)) + return; /* * There appears to be other cpus that can accept @@ -827,8 +965,6 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) */ requeue_task_rt(rq, p, 1); resched_task(rq->curr); -free: - free_cpumask_var(mask); } #endif /* CONFIG_SMP */ @@ -878,7 +1014,7 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, return next; } -static struct task_struct *pick_next_task_rt(struct rq *rq) +static struct task_struct *_pick_next_task_rt(struct rq *rq) { struct sched_rt_entity *rt_se; struct task_struct *p; @@ -900,6 +1036,18 @@ static struct task_struct *pick_next_task_rt(struct rq *rq) p = rt_task_of(rt_se); p->se.exec_start = rq->clock; + + return p; +} + +static struct task_struct *pick_next_task_rt(struct rq *rq) +{ + struct task_struct *p = _pick_next_task_rt(rq); + + /* The running task is never eligible for pushing */ + if (p) + dequeue_pushable_task(rq, p); + return p; } @@ -907,6 +1055,13 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) { update_curr_rt(rq); p->se.exec_start = 0; + + /* + * The previous task needs to be made eligible for pushing + * if it is still active + */ + if (p->se.on_rq && p->rt.nr_cpus_allowed > 1) + enqueue_pushable_task(rq, p); } #ifdef CONFIG_SMP @@ -960,16 +1115,17 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu) static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask); -static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask) +static inline int pick_optimal_cpu(int this_cpu, + const struct cpumask *mask) { int first; /* "this_cpu" is cheaper to preempt than a remote processor */ - if ((this_cpu != -1) && cpu_isset(this_cpu, *mask)) + if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask)) return this_cpu; - first = first_cpu(*mask); - if (first != NR_CPUS) + first = cpumask_first(mask); + if (first < nr_cpu_ids) return first; return -1; @@ -981,6 +1137,7 @@ static int find_lowest_rq(struct task_struct *task) struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask); int this_cpu = smp_processor_id(); int cpu = task_cpu(task); + cpumask_var_t domain_mask; if (task->rt.nr_cpus_allowed == 1) return -1; /* No other targets possible */ @@ -1013,19 +1170,25 @@ static int find_lowest_rq(struct task_struct *task) if (this_cpu == cpu) this_cpu = -1; /* Skip this_cpu opt if the same */ - for_each_domain(cpu, sd) { - if (sd->flags & SD_WAKE_AFFINE) { - cpumask_t domain_mask; - int best_cpu; + if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) { + for_each_domain(cpu, sd) { + if (sd->flags & SD_WAKE_AFFINE) { + int best_cpu; - cpumask_and(&domain_mask, sched_domain_span(sd), - lowest_mask); + cpumask_and(domain_mask, + sched_domain_span(sd), + lowest_mask); - best_cpu = pick_optimal_cpu(this_cpu, - &domain_mask); - if (best_cpu != -1) - return best_cpu; + best_cpu = pick_optimal_cpu(this_cpu, + domain_mask); + + if (best_cpu != -1) { + free_cpumask_var(domain_mask); + return best_cpu; + } + } } + free_cpumask_var(domain_mask); } /* @@ -1072,7 +1235,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) } /* If this rq is still suitable use it. */ - if (lowest_rq->rt.highest_prio > task->prio) + if (lowest_rq->rt.highest_prio.curr > task->prio) break; /* try again */ @@ -1083,6 +1246,31 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) return lowest_rq; } +static inline int has_pushable_tasks(struct rq *rq) +{ + return !plist_head_empty(&rq->rt.pushable_tasks); +} + +static struct task_struct *pick_next_pushable_task(struct rq *rq) +{ + struct task_struct *p; + + if (!has_pushable_tasks(rq)) + return NULL; + + p = plist_first_entry(&rq->rt.pushable_tasks, + struct task_struct, pushable_tasks); + + BUG_ON(rq->cpu != task_cpu(p)); + BUG_ON(task_current(rq, p)); + BUG_ON(p->rt.nr_cpus_allowed <= 1); + + BUG_ON(!p->se.on_rq); + BUG_ON(!rt_task(p)); + + return p; +} + /* * If the current CPU has more than one RT task, see if the non * running task can migrate over to a CPU that is running a task @@ -1092,13 +1280,11 @@ static int push_rt_task(struct rq *rq) { struct task_struct *next_task; struct rq *lowest_rq; - int ret = 0; - int paranoid = RT_MAX_TRIES; if (!rq->rt.overloaded) return 0; - next_task = pick_next_highest_task_rt(rq, -1); + next_task = pick_next_pushable_task(rq); if (!next_task) return 0; @@ -1127,16 +1313,34 @@ static int push_rt_task(struct rq *rq) struct task_struct *task; /* * find lock_lowest_rq releases rq->lock - * so it is possible that next_task has changed. - * If it has, then try again. + * so it is possible that next_task has migrated. + * + * We need to make sure that the task is still on the same + * run-queue and is also still the next task eligible for + * pushing. */ - task = pick_next_highest_task_rt(rq, -1); - if (unlikely(task != next_task) && task && paranoid--) { - put_task_struct(next_task); - next_task = task; - goto retry; + task = pick_next_pushable_task(rq); + if (task_cpu(next_task) == rq->cpu && task == next_task) { + /* + * If we get here, the task hasnt moved at all, but + * it has failed to push. We will not try again, + * since the other cpus will pull from us when they + * are ready. + */ + dequeue_pushable_task(rq, next_task); + goto out; } - goto out; + + if (!task) + /* No more tasks, just exit */ + goto out; + + /* + * Something has shifted, try again. + */ + put_task_struct(next_task); + next_task = task; + goto retry; } deactivate_task(rq, next_task, 0); @@ -1147,23 +1351,12 @@ static int push_rt_task(struct rq *rq) double_unlock_balance(rq, lowest_rq); - ret = 1; out: put_task_struct(next_task); - return ret; + return 1; } -/* - * TODO: Currently we just use the second highest prio task on - * the queue, and stop when it can't migrate (or there's - * no more RT tasks). There may be a case where a lower - * priority RT task has a different affinity than the - * higher RT task. In this case the lower RT task could - * possibly be able to migrate where as the higher priority - * RT task could not. We currently ignore this issue. - * Enhancements are welcome! - */ static void push_rt_tasks(struct rq *rq) { /* push_rt_task will return true if it moved an RT */ @@ -1174,33 +1367,35 @@ static void push_rt_tasks(struct rq *rq) static int pull_rt_task(struct rq *this_rq) { int this_cpu = this_rq->cpu, ret = 0, cpu; - struct task_struct *p, *next; + struct task_struct *p; struct rq *src_rq; if (likely(!rt_overloaded(this_rq))) return 0; - next = pick_next_task_rt(this_rq); - for_each_cpu(cpu, this_rq->rd->rto_mask) { if (this_cpu == cpu) continue; src_rq = cpu_rq(cpu); + + /* + * Don't bother taking the src_rq->lock if the next highest + * task is known to be lower-priority than our current task. + * This may look racy, but if this value is about to go + * logically higher, the src_rq will push this task away. + * And if its going logically lower, we do not care + */ + if (src_rq->rt.highest_prio.next >= + this_rq->rt.highest_prio.curr) + continue; + /* * We can potentially drop this_rq's lock in * double_lock_balance, and another CPU could - * steal our next task - hence we must cause - * the caller to recalculate the next task - * in that case: + * alter this_rq */ - if (double_lock_balance(this_rq, src_rq)) { - struct task_struct *old_next = next; - - next = pick_next_task_rt(this_rq); - if (next != old_next) - ret = 1; - } + double_lock_balance(this_rq, src_rq); /* * Are there still pullable RT tasks? @@ -1214,7 +1409,7 @@ static int pull_rt_task(struct rq *this_rq) * Do we have an RT task that preempts * the to-be-scheduled task? */ - if (p && (!next || (p->prio < next->prio))) { + if (p && (p->prio < this_rq->rt.highest_prio.curr)) { WARN_ON(p == src_rq->curr); WARN_ON(!p->se.on_rq); @@ -1224,12 +1419,9 @@ static int pull_rt_task(struct rq *this_rq) * This is just that p is wakeing up and hasn't * had a chance to schedule. We only pull * p if it is lower in priority than the - * current task on the run queue or - * this_rq next task is lower in prio than - * the current task on that rq. + * current task on the run queue */ - if (p->prio < src_rq->curr->prio || - (next && next->prio < src_rq->curr->prio)) + if (p->prio < src_rq->curr->prio) goto skip; ret = 1; @@ -1242,13 +1434,7 @@ static int pull_rt_task(struct rq *this_rq) * case there's an even higher prio task * in another runqueue. (low likelyhood * but possible) - * - * Update next so that we won't pick a task - * on another cpu with a priority lower (or equal) - * than the one we just picked. */ - next = p; - } skip: double_unlock_balance(this_rq, src_rq); @@ -1260,24 +1446,27 @@ static int pull_rt_task(struct rq *this_rq) static void pre_schedule_rt(struct rq *rq, struct task_struct *prev) { /* Try to pull RT tasks here if we lower this rq's prio */ - if (unlikely(rt_task(prev)) && rq->rt.highest_prio > prev->prio) + if (unlikely(rt_task(prev)) && rq->rt.highest_prio.curr > prev->prio) pull_rt_task(rq); } +/* + * assumes rq->lock is held + */ +static int needs_post_schedule_rt(struct rq *rq) +{ + return has_pushable_tasks(rq); +} + static void post_schedule_rt(struct rq *rq) { /* - * If we have more than one rt_task queued, then - * see if we can push the other rt_tasks off to other CPUS. - * Note we may release the rq lock, and since - * the lock was owned by prev, we need to release it - * first via finish_lock_switch and then reaquire it here. + * This is only called if needs_post_schedule_rt() indicates that + * we need to push tasks away */ - if (unlikely(rq->rt.overloaded)) { - spin_lock_irq(&rq->lock); - push_rt_tasks(rq); - spin_unlock_irq(&rq->lock); - } + spin_lock_irq(&rq->lock); + push_rt_tasks(rq); + spin_unlock_irq(&rq->lock); } /* @@ -1288,7 +1477,8 @@ static void task_wake_up_rt(struct rq *rq, struct task_struct *p) { if (!task_running(rq, p) && !test_tsk_need_resched(rq->curr) && - rq->rt.overloaded) + has_pushable_tasks(rq) && + p->rt.nr_cpus_allowed > 1) push_rt_tasks(rq); } @@ -1324,6 +1514,24 @@ static void set_cpus_allowed_rt(struct task_struct *p, if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) { struct rq *rq = task_rq(p); + if (!task_current(rq, p)) { + /* + * Make sure we dequeue this task from the pushable list + * before going further. It will either remain off of + * the list because we are no longer pushable, or it + * will be requeued. + */ + if (p->rt.nr_cpus_allowed > 1) + dequeue_pushable_task(rq, p); + + /* + * Requeue if our weight is changing and still > 1 + */ + if (weight > 1) + enqueue_pushable_task(rq, p); + + } + if ((p->rt.nr_cpus_allowed <= 1) && (weight > 1)) { rq->rt.rt_nr_migratory++; } else if ((p->rt.nr_cpus_allowed > 1) && (weight <= 1)) { @@ -1331,7 +1539,7 @@ static void set_cpus_allowed_rt(struct task_struct *p, rq->rt.rt_nr_migratory--; } - update_rt_migration(rq); + update_rt_migration(&rq->rt); } cpumask_copy(&p->cpus_allowed, new_mask); @@ -1346,7 +1554,7 @@ static void rq_online_rt(struct rq *rq) __enable_runtime(rq); - cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio); + cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr); } /* Assumes rq->lock is held */ @@ -1438,7 +1646,7 @@ static void prio_changed_rt(struct rq *rq, struct task_struct *p, * can release the rq lock and p could migrate. * Only reschedule if p is still on the same runqueue. */ - if (p->prio > rq->rt.highest_prio && rq->curr == p) + if (p->prio > rq->rt.highest_prio.curr && rq->curr == p) resched_task(p); #else /* For UP simply resched on drop of prio */ @@ -1509,6 +1717,9 @@ static void set_curr_task_rt(struct rq *rq) struct task_struct *p = rq->curr; p->se.exec_start = rq->clock; + + /* The running task is never eligible for pushing */ + dequeue_pushable_task(rq, p); } static const struct sched_class rt_sched_class = { @@ -1531,6 +1742,7 @@ static const struct sched_class rt_sched_class = { .rq_online = rq_online_rt, .rq_offline = rq_offline_rt, .pre_schedule = pre_schedule_rt, + .needs_post_schedule = needs_post_schedule_rt, .post_schedule = post_schedule_rt, .task_wake_up = task_wake_up_rt, .switched_from = switched_from_rt, diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index f2773b5d1226..8ab0cef8ecab 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -296,6 +296,7 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) static inline void account_group_user_time(struct task_struct *tsk, cputime_t cputime) { + struct task_cputime *times; struct signal_struct *sig; /* tsk == current, ensure it is safe to use ->signal */ @@ -303,13 +304,11 @@ static inline void account_group_user_time(struct task_struct *tsk, return; sig = tsk->signal; - if (sig->cputime.totals) { - struct task_cputime *times; + times = &sig->cputime.totals; - times = per_cpu_ptr(sig->cputime.totals, get_cpu()); - times->utime = cputime_add(times->utime, cputime); - put_cpu_no_resched(); - } + spin_lock(×->lock); + times->utime = cputime_add(times->utime, cputime); + spin_unlock(×->lock); } /** @@ -325,6 +324,7 @@ static inline void account_group_user_time(struct task_struct *tsk, static inline void account_group_system_time(struct task_struct *tsk, cputime_t cputime) { + struct task_cputime *times; struct signal_struct *sig; /* tsk == current, ensure it is safe to use ->signal */ @@ -332,13 +332,11 @@ static inline void account_group_system_time(struct task_struct *tsk, return; sig = tsk->signal; - if (sig->cputime.totals) { - struct task_cputime *times; + times = &sig->cputime.totals; - times = per_cpu_ptr(sig->cputime.totals, get_cpu()); - times->stime = cputime_add(times->stime, cputime); - put_cpu_no_resched(); - } + spin_lock(×->lock); + times->stime = cputime_add(times->stime, cputime); + spin_unlock(×->lock); } /** @@ -354,6 +352,7 @@ static inline void account_group_system_time(struct task_struct *tsk, static inline void account_group_exec_runtime(struct task_struct *tsk, unsigned long long ns) { + struct task_cputime *times; struct signal_struct *sig; sig = tsk->signal; @@ -362,11 +361,9 @@ static inline void account_group_exec_runtime(struct task_struct *tsk, if (unlikely(!sig)) return; - if (sig->cputime.totals) { - struct task_cputime *times; + times = &sig->cputime.totals; - times = per_cpu_ptr(sig->cputime.totals, get_cpu()); - times->sum_exec_runtime += ns; - put_cpu_no_resched(); - } + spin_lock(×->lock); + times->sum_exec_runtime += ns; + spin_unlock(×->lock); } diff --git a/kernel/signal.c b/kernel/signal.c index e73759783dc8..b6b36768b758 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -909,7 +909,9 @@ static void print_fatal_signal(struct pt_regs *regs, int signr) } #endif printk("\n"); + preempt_disable(); show_regs(regs); + preempt_enable(); } static int __init setup_print_fatal_signals(char *str) diff --git a/kernel/slow-work.c b/kernel/slow-work.c new file mode 100644 index 000000000000..cf2bc01186ef --- /dev/null +++ b/kernel/slow-work.c @@ -0,0 +1,640 @@ +/* Worker thread pool for slow items, such as filesystem lookups or mkdirs + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + * + * See Documentation/slow-work.txt + */ + +#include <linux/module.h> +#include <linux/slow-work.h> +#include <linux/kthread.h> +#include <linux/freezer.h> +#include <linux/wait.h> + +#define SLOW_WORK_CULL_TIMEOUT (5 * HZ) /* cull threads 5s after running out of + * things to do */ +#define SLOW_WORK_OOM_TIMEOUT (5 * HZ) /* can't start new threads for 5s after + * OOM */ + +static void slow_work_cull_timeout(unsigned long); +static void slow_work_oom_timeout(unsigned long); + +#ifdef CONFIG_SYSCTL +static int slow_work_min_threads_sysctl(struct ctl_table *, int, struct file *, + void __user *, size_t *, loff_t *); + +static int slow_work_max_threads_sysctl(struct ctl_table *, int , struct file *, + void __user *, size_t *, loff_t *); +#endif + +/* + * The pool of threads has at least min threads in it as long as someone is + * using the facility, and may have as many as max. + * + * A portion of the pool may be processing very slow operations. + */ +static unsigned slow_work_min_threads = 2; +static unsigned slow_work_max_threads = 4; +static unsigned vslow_work_proportion = 50; /* % of threads that may process + * very slow work */ + +#ifdef CONFIG_SYSCTL +static const int slow_work_min_min_threads = 2; +static int slow_work_max_max_threads = 255; +static const int slow_work_min_vslow = 1; +static const int slow_work_max_vslow = 99; + +ctl_table slow_work_sysctls[] = { + { + .ctl_name = CTL_UNNUMBERED, + .procname = "min-threads", + .data = &slow_work_min_threads, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = slow_work_min_threads_sysctl, + .extra1 = (void *) &slow_work_min_min_threads, + .extra2 = &slow_work_max_threads, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "max-threads", + .data = &slow_work_max_threads, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = slow_work_max_threads_sysctl, + .extra1 = &slow_work_min_threads, + .extra2 = (void *) &slow_work_max_max_threads, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "vslow-percentage", + .data = &vslow_work_proportion, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .extra1 = (void *) &slow_work_min_vslow, + .extra2 = (void *) &slow_work_max_vslow, + }, + { .ctl_name = 0 } +}; +#endif + +/* + * The active state of the thread pool + */ +static atomic_t slow_work_thread_count; +static atomic_t vslow_work_executing_count; + +static bool slow_work_may_not_start_new_thread; +static bool slow_work_cull; /* cull a thread due to lack of activity */ +static DEFINE_TIMER(slow_work_cull_timer, slow_work_cull_timeout, 0, 0); +static DEFINE_TIMER(slow_work_oom_timer, slow_work_oom_timeout, 0, 0); +static struct slow_work slow_work_new_thread; /* new thread starter */ + +/* + * The queues of work items and the lock governing access to them. These are + * shared between all the CPUs. It doesn't make sense to have per-CPU queues + * as the number of threads bears no relation to the number of CPUs. + * + * There are two queues of work items: one for slow work items, and one for + * very slow work items. + */ +static LIST_HEAD(slow_work_queue); +static LIST_HEAD(vslow_work_queue); +static DEFINE_SPINLOCK(slow_work_queue_lock); + +/* + * The thread controls. A variable used to signal to the threads that they + * should exit when the queue is empty, a waitqueue used by the threads to wait + * for signals, and a completion set by the last thread to exit. + */ +static bool slow_work_threads_should_exit; +static DECLARE_WAIT_QUEUE_HEAD(slow_work_thread_wq); +static DECLARE_COMPLETION(slow_work_last_thread_exited); + +/* + * The number of users of the thread pool and its lock. Whilst this is zero we + * have no threads hanging around, and when this reaches zero, we wait for all + * active or queued work items to complete and kill all the threads we do have. + */ +static int slow_work_user_count; +static DEFINE_MUTEX(slow_work_user_lock); + +/* + * Calculate the maximum number of active threads in the pool that are + * permitted to process very slow work items. + * + * The answer is rounded up to at least 1, but may not equal or exceed the + * maximum number of the threads in the pool. This means we always have at + * least one thread that can process slow work items, and we always have at + * least one thread that won't get tied up doing so. + */ +static unsigned slow_work_calc_vsmax(void) +{ + unsigned vsmax; + + vsmax = atomic_read(&slow_work_thread_count) * vslow_work_proportion; + vsmax /= 100; + vsmax = max(vsmax, 1U); + return min(vsmax, slow_work_max_threads - 1); +} + +/* + * Attempt to execute stuff queued on a slow thread. Return true if we managed + * it, false if there was nothing to do. + */ +static bool slow_work_execute(void) +{ + struct slow_work *work = NULL; + unsigned vsmax; + bool very_slow; + + vsmax = slow_work_calc_vsmax(); + + /* see if we can schedule a new thread to be started if we're not + * keeping up with the work */ + if (!waitqueue_active(&slow_work_thread_wq) && + (!list_empty(&slow_work_queue) || !list_empty(&vslow_work_queue)) && + atomic_read(&slow_work_thread_count) < slow_work_max_threads && + !slow_work_may_not_start_new_thread) + slow_work_enqueue(&slow_work_new_thread); + + /* find something to execute */ + spin_lock_irq(&slow_work_queue_lock); + if (!list_empty(&vslow_work_queue) && + atomic_read(&vslow_work_executing_count) < vsmax) { + work = list_entry(vslow_work_queue.next, + struct slow_work, link); + if (test_and_set_bit_lock(SLOW_WORK_EXECUTING, &work->flags)) + BUG(); + list_del_init(&work->link); + atomic_inc(&vslow_work_executing_count); + very_slow = true; + } else if (!list_empty(&slow_work_queue)) { + work = list_entry(slow_work_queue.next, + struct slow_work, link); + if (test_and_set_bit_lock(SLOW_WORK_EXECUTING, &work->flags)) + BUG(); + list_del_init(&work->link); + very_slow = false; + } else { + very_slow = false; /* avoid the compiler warning */ + } + spin_unlock_irq(&slow_work_queue_lock); + + if (!work) + return false; + + if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags)) + BUG(); + + work->ops->execute(work); + + if (very_slow) + atomic_dec(&vslow_work_executing_count); + clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags); + + /* if someone tried to enqueue the item whilst we were executing it, + * then it'll be left unenqueued to avoid multiple threads trying to + * execute it simultaneously + * + * there is, however, a race between us testing the pending flag and + * getting the spinlock, and between the enqueuer setting the pending + * flag and getting the spinlock, so we use a deferral bit to tell us + * if the enqueuer got there first + */ + if (test_bit(SLOW_WORK_PENDING, &work->flags)) { + spin_lock_irq(&slow_work_queue_lock); + + if (!test_bit(SLOW_WORK_EXECUTING, &work->flags) && + test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags)) + goto auto_requeue; + + spin_unlock_irq(&slow_work_queue_lock); + } + + work->ops->put_ref(work); + return true; + +auto_requeue: + /* we must complete the enqueue operation + * - we transfer our ref on the item back to the appropriate queue + * - don't wake another thread up as we're awake already + */ + if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) + list_add_tail(&work->link, &vslow_work_queue); + else + list_add_tail(&work->link, &slow_work_queue); + spin_unlock_irq(&slow_work_queue_lock); + return true; +} + +/** + * slow_work_enqueue - Schedule a slow work item for processing + * @work: The work item to queue + * + * Schedule a slow work item for processing. If the item is already undergoing + * execution, this guarantees not to re-enter the execution routine until the + * first execution finishes. + * + * The item is pinned by this function as it retains a reference to it, managed + * through the item operations. The item is unpinned once it has been + * executed. + * + * An item may hog the thread that is running it for a relatively large amount + * of time, sufficient, for example, to perform several lookup, mkdir, create + * and setxattr operations. It may sleep on I/O and may sleep to obtain locks. + * + * Conversely, if a number of items are awaiting processing, it may take some + * time before any given item is given attention. The number of threads in the + * pool may be increased to deal with demand, but only up to a limit. + * + * If SLOW_WORK_VERY_SLOW is set on the work item, then it will be placed in + * the very slow queue, from which only a portion of the threads will be + * allowed to pick items to execute. This ensures that very slow items won't + * overly block ones that are just ordinarily slow. + * + * Returns 0 if successful, -EAGAIN if not. + */ +int slow_work_enqueue(struct slow_work *work) +{ + unsigned long flags; + + BUG_ON(slow_work_user_count <= 0); + BUG_ON(!work); + BUG_ON(!work->ops); + BUG_ON(!work->ops->get_ref); + + /* when honouring an enqueue request, we only promise that we will run + * the work function in the future; we do not promise to run it once + * per enqueue request + * + * we use the PENDING bit to merge together repeat requests without + * having to disable IRQs and take the spinlock, whilst still + * maintaining our promise + */ + if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) { + spin_lock_irqsave(&slow_work_queue_lock, flags); + + /* we promise that we will not attempt to execute the work + * function in more than one thread simultaneously + * + * this, however, leaves us with a problem if we're asked to + * enqueue the work whilst someone is executing the work + * function as simply queueing the work immediately means that + * another thread may try executing it whilst it is already + * under execution + * + * to deal with this, we set the ENQ_DEFERRED bit instead of + * enqueueing, and the thread currently executing the work + * function will enqueue the work item when the work function + * returns and it has cleared the EXECUTING bit + */ + if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) { + set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags); + } else { + if (work->ops->get_ref(work) < 0) + goto cant_get_ref; + if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) + list_add_tail(&work->link, &vslow_work_queue); + else + list_add_tail(&work->link, &slow_work_queue); + wake_up(&slow_work_thread_wq); + } + + spin_unlock_irqrestore(&slow_work_queue_lock, flags); + } + return 0; + +cant_get_ref: + spin_unlock_irqrestore(&slow_work_queue_lock, flags); + return -EAGAIN; +} +EXPORT_SYMBOL(slow_work_enqueue); + +/* + * Worker thread culling algorithm + */ +static bool slow_work_cull_thread(void) +{ + unsigned long flags; + bool do_cull = false; + + spin_lock_irqsave(&slow_work_queue_lock, flags); + + if (slow_work_cull) { + slow_work_cull = false; + + if (list_empty(&slow_work_queue) && + list_empty(&vslow_work_queue) && + atomic_read(&slow_work_thread_count) > + slow_work_min_threads) { + mod_timer(&slow_work_cull_timer, + jiffies + SLOW_WORK_CULL_TIMEOUT); + do_cull = true; + } + } + + spin_unlock_irqrestore(&slow_work_queue_lock, flags); + return do_cull; +} + +/* + * Determine if there is slow work available for dispatch + */ +static inline bool slow_work_available(int vsmax) +{ + return !list_empty(&slow_work_queue) || + (!list_empty(&vslow_work_queue) && + atomic_read(&vslow_work_executing_count) < vsmax); +} + +/* + * Worker thread dispatcher + */ +static int slow_work_thread(void *_data) +{ + int vsmax; + + DEFINE_WAIT(wait); + + set_freezable(); + set_user_nice(current, -5); + + for (;;) { + vsmax = vslow_work_proportion; + vsmax *= atomic_read(&slow_work_thread_count); + vsmax /= 100; + + prepare_to_wait(&slow_work_thread_wq, &wait, + TASK_INTERRUPTIBLE); + if (!freezing(current) && + !slow_work_threads_should_exit && + !slow_work_available(vsmax) && + !slow_work_cull) + schedule(); + finish_wait(&slow_work_thread_wq, &wait); + + try_to_freeze(); + + vsmax = vslow_work_proportion; + vsmax *= atomic_read(&slow_work_thread_count); + vsmax /= 100; + + if (slow_work_available(vsmax) && slow_work_execute()) { + cond_resched(); + if (list_empty(&slow_work_queue) && + list_empty(&vslow_work_queue) && + atomic_read(&slow_work_thread_count) > + slow_work_min_threads) + mod_timer(&slow_work_cull_timer, + jiffies + SLOW_WORK_CULL_TIMEOUT); + continue; + } + + if (slow_work_threads_should_exit) + break; + + if (slow_work_cull && slow_work_cull_thread()) + break; + } + + if (atomic_dec_and_test(&slow_work_thread_count)) + complete_and_exit(&slow_work_last_thread_exited, 0); + return 0; +} + +/* + * Handle thread cull timer expiration + */ +static void slow_work_cull_timeout(unsigned long data) +{ + slow_work_cull = true; + wake_up(&slow_work_thread_wq); +} + +/* + * Get a reference on slow work thread starter + */ +static int slow_work_new_thread_get_ref(struct slow_work *work) +{ + return 0; +} + +/* + * Drop a reference on slow work thread starter + */ +static void slow_work_new_thread_put_ref(struct slow_work *work) +{ +} + +/* + * Start a new slow work thread + */ +static void slow_work_new_thread_execute(struct slow_work *work) +{ + struct task_struct *p; + + if (slow_work_threads_should_exit) + return; + + if (atomic_read(&slow_work_thread_count) >= slow_work_max_threads) + return; + + if (!mutex_trylock(&slow_work_user_lock)) + return; + + slow_work_may_not_start_new_thread = true; + atomic_inc(&slow_work_thread_count); + p = kthread_run(slow_work_thread, NULL, "kslowd"); + if (IS_ERR(p)) { + printk(KERN_DEBUG "Slow work thread pool: OOM\n"); + if (atomic_dec_and_test(&slow_work_thread_count)) + BUG(); /* we're running on a slow work thread... */ + mod_timer(&slow_work_oom_timer, + jiffies + SLOW_WORK_OOM_TIMEOUT); + } else { + /* ratelimit the starting of new threads */ + mod_timer(&slow_work_oom_timer, jiffies + 1); + } + + mutex_unlock(&slow_work_user_lock); +} + +static const struct slow_work_ops slow_work_new_thread_ops = { + .get_ref = slow_work_new_thread_get_ref, + .put_ref = slow_work_new_thread_put_ref, + .execute = slow_work_new_thread_execute, +}; + +/* + * post-OOM new thread start suppression expiration + */ +static void slow_work_oom_timeout(unsigned long data) +{ + slow_work_may_not_start_new_thread = false; +} + +#ifdef CONFIG_SYSCTL +/* + * Handle adjustment of the minimum number of threads + */ +static int slow_work_min_threads_sysctl(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int n; + + if (ret == 0) { + mutex_lock(&slow_work_user_lock); + if (slow_work_user_count > 0) { + /* see if we need to start or stop threads */ + n = atomic_read(&slow_work_thread_count) - + slow_work_min_threads; + + if (n < 0 && !slow_work_may_not_start_new_thread) + slow_work_enqueue(&slow_work_new_thread); + else if (n > 0) + mod_timer(&slow_work_cull_timer, + jiffies + SLOW_WORK_CULL_TIMEOUT); + } + mutex_unlock(&slow_work_user_lock); + } + + return ret; +} + +/* + * Handle adjustment of the maximum number of threads + */ +static int slow_work_max_threads_sysctl(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int n; + + if (ret == 0) { + mutex_lock(&slow_work_user_lock); + if (slow_work_user_count > 0) { + /* see if we need to stop threads */ + n = slow_work_max_threads - + atomic_read(&slow_work_thread_count); + + if (n < 0) + mod_timer(&slow_work_cull_timer, + jiffies + SLOW_WORK_CULL_TIMEOUT); + } + mutex_unlock(&slow_work_user_lock); + } + + return ret; +} +#endif /* CONFIG_SYSCTL */ + +/** + * slow_work_register_user - Register a user of the facility + * + * Register a user of the facility, starting up the initial threads if there + * aren't any other users at this point. This will return 0 if successful, or + * an error if not. + */ +int slow_work_register_user(void) +{ + struct task_struct *p; + int loop; + + mutex_lock(&slow_work_user_lock); + + if (slow_work_user_count == 0) { + printk(KERN_NOTICE "Slow work thread pool: Starting up\n"); + init_completion(&slow_work_last_thread_exited); + + slow_work_threads_should_exit = false; + slow_work_init(&slow_work_new_thread, + &slow_work_new_thread_ops); + slow_work_may_not_start_new_thread = false; + slow_work_cull = false; + + /* start the minimum number of threads */ + for (loop = 0; loop < slow_work_min_threads; loop++) { + atomic_inc(&slow_work_thread_count); + p = kthread_run(slow_work_thread, NULL, "kslowd"); + if (IS_ERR(p)) + goto error; + } + printk(KERN_NOTICE "Slow work thread pool: Ready\n"); + } + + slow_work_user_count++; + mutex_unlock(&slow_work_user_lock); + return 0; + +error: + if (atomic_dec_and_test(&slow_work_thread_count)) + complete(&slow_work_last_thread_exited); + if (loop > 0) { + printk(KERN_ERR "Slow work thread pool:" + " Aborting startup on ENOMEM\n"); + slow_work_threads_should_exit = true; + wake_up_all(&slow_work_thread_wq); + wait_for_completion(&slow_work_last_thread_exited); + printk(KERN_ERR "Slow work thread pool: Aborted\n"); + } + mutex_unlock(&slow_work_user_lock); + return PTR_ERR(p); +} +EXPORT_SYMBOL(slow_work_register_user); + +/** + * slow_work_unregister_user - Unregister a user of the facility + * + * Unregister a user of the facility, killing all the threads if this was the + * last one. + */ +void slow_work_unregister_user(void) +{ + mutex_lock(&slow_work_user_lock); + + BUG_ON(slow_work_user_count <= 0); + + slow_work_user_count--; + if (slow_work_user_count == 0) { + printk(KERN_NOTICE "Slow work thread pool: Shutting down\n"); + slow_work_threads_should_exit = true; + wake_up_all(&slow_work_thread_wq); + wait_for_completion(&slow_work_last_thread_exited); + printk(KERN_NOTICE "Slow work thread pool:" + " Shut down complete\n"); + } + + del_timer_sync(&slow_work_cull_timer); + + mutex_unlock(&slow_work_user_lock); +} +EXPORT_SYMBOL(slow_work_unregister_user); + +/* + * Initialise the slow work facility + */ +static int __init init_slow_work(void) +{ + unsigned nr_cpus = num_possible_cpus(); + + if (slow_work_max_threads < nr_cpus) + slow_work_max_threads = nr_cpus; +#ifdef CONFIG_SYSCTL + if (slow_work_max_max_threads < nr_cpus * 2) + slow_work_max_max_threads = nr_cpus * 2; +#endif + return 0; +} + +subsys_initcall(init_slow_work); diff --git a/kernel/smp.c b/kernel/smp.c index 5cfa0e5e3e88..bbedbb7efe32 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -18,6 +18,7 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(call_function_lock); enum { CSD_FLAG_WAIT = 0x01, CSD_FLAG_ALLOC = 0x02, + CSD_FLAG_LOCK = 0x04, }; struct call_function_data { @@ -186,6 +187,9 @@ void generic_smp_call_function_single_interrupt(void) if (data_flags & CSD_FLAG_WAIT) { smp_wmb(); data->flags &= ~CSD_FLAG_WAIT; + } else if (data_flags & CSD_FLAG_LOCK) { + smp_wmb(); + data->flags &= ~CSD_FLAG_LOCK; } else if (data_flags & CSD_FLAG_ALLOC) kfree(data); } @@ -196,6 +200,8 @@ void generic_smp_call_function_single_interrupt(void) } } +static DEFINE_PER_CPU(struct call_single_data, csd_data); + /* * smp_call_function_single - Run a function on a specific CPU * @func: The function to run. This must be fast and non-blocking. @@ -224,14 +230,38 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, func(info); local_irq_restore(flags); } else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) { - struct call_single_data *data = NULL; + struct call_single_data *data; if (!wait) { + /* + * We are calling a function on a single CPU + * and we are not going to wait for it to finish. + * We first try to allocate the data, but if we + * fail, we fall back to use a per cpu data to pass + * the information to that CPU. Since all callers + * of this code will use the same data, we must + * synchronize the callers to prevent a new caller + * from corrupting the data before the callee + * can access it. + * + * The CSD_FLAG_LOCK is used to let us know when + * the IPI handler is done with the data. + * The first caller will set it, and the callee + * will clear it. The next caller must wait for + * it to clear before we set it again. This + * will make sure the callee is done with the + * data before a new caller will use it. + */ data = kmalloc(sizeof(*data), GFP_ATOMIC); if (data) data->flags = CSD_FLAG_ALLOC; - } - if (!data) { + else { + data = &per_cpu(csd_data, me); + while (data->flags & CSD_FLAG_LOCK) + cpu_relax(); + data->flags = CSD_FLAG_LOCK; + } + } else { data = &d; data->flags = CSD_FLAG_WAIT; } diff --git a/kernel/softirq.c b/kernel/softirq.c index bdbe9de9cd8d..7e93870cf3ea 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -361,6 +361,17 @@ void __tasklet_hi_schedule(struct tasklet_struct *t) EXPORT_SYMBOL(__tasklet_hi_schedule); +void __tasklet_hi_schedule_first(struct tasklet_struct *t) +{ + BUG_ON(!irqs_disabled()); + + t->next = __get_cpu_var(tasklet_hi_vec).head; + __get_cpu_var(tasklet_hi_vec).head = t; + __raise_softirq_irqoff(HI_SOFTIRQ); +} + +EXPORT_SYMBOL(__tasklet_hi_schedule_first); + static void tasklet_action(struct softirq_action *a) { struct tasklet_struct *list; @@ -795,6 +806,11 @@ int __init __weak early_irq_init(void) return 0; } +int __init __weak arch_probe_nr_irqs(void) +{ + return 0; +} + int __init __weak arch_early_irq_init(void) { return 0; diff --git a/kernel/softlockup.c b/kernel/softlockup.c index d9188c66278a..88796c330838 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -16,6 +16,7 @@ #include <linux/lockdep.h> #include <linux/notifier.h> #include <linux/module.h> +#include <linux/sysctl.h> #include <asm/irq_regs.h> @@ -88,6 +89,14 @@ void touch_all_softlockup_watchdogs(void) } EXPORT_SYMBOL(touch_all_softlockup_watchdogs); +int proc_dosoftlockup_thresh(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + touch_all_softlockup_watchdogs(); + return proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); +} + /* * This callback runs from the timer interrupt, and checks * whether the watchdog thread has hung or not: @@ -157,97 +166,11 @@ void softlockup_tick(void) } /* - * Have a reasonable limit on the number of tasks checked: - */ -unsigned long __read_mostly sysctl_hung_task_check_count = 1024; - -/* - * Zero means infinite timeout - no checking done: - */ -unsigned long __read_mostly sysctl_hung_task_timeout_secs = 480; - -unsigned long __read_mostly sysctl_hung_task_warnings = 10; - -/* - * Only do the hung-tasks check on one CPU: - */ -static int check_cpu __read_mostly = -1; - -static void check_hung_task(struct task_struct *t, unsigned long now) -{ - unsigned long switch_count = t->nvcsw + t->nivcsw; - - if (t->flags & PF_FROZEN) - return; - - if (switch_count != t->last_switch_count || !t->last_switch_timestamp) { - t->last_switch_count = switch_count; - t->last_switch_timestamp = now; - return; - } - if ((long)(now - t->last_switch_timestamp) < - sysctl_hung_task_timeout_secs) - return; - if (!sysctl_hung_task_warnings) - return; - sysctl_hung_task_warnings--; - - /* - * Ok, the task did not get scheduled for more than 2 minutes, - * complain: - */ - printk(KERN_ERR "INFO: task %s:%d blocked for more than " - "%ld seconds.\n", t->comm, t->pid, - sysctl_hung_task_timeout_secs); - printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\"" - " disables this message.\n"); - sched_show_task(t); - __debug_show_held_locks(t); - - t->last_switch_timestamp = now; - touch_nmi_watchdog(); - - if (softlockup_panic) - panic("softlockup: blocked tasks"); -} - -/* - * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for - * a really long time (120 seconds). If that happens, print out - * a warning. - */ -static void check_hung_uninterruptible_tasks(int this_cpu) -{ - int max_count = sysctl_hung_task_check_count; - unsigned long now = get_timestamp(this_cpu); - struct task_struct *g, *t; - - /* - * If the system crashed already then all bets are off, - * do not report extra hung tasks: - */ - if (test_taint(TAINT_DIE) || did_panic) - return; - - read_lock(&tasklist_lock); - do_each_thread(g, t) { - if (!--max_count) - goto unlock; - /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */ - if (t->state == TASK_UNINTERRUPTIBLE) - check_hung_task(t, now); - } while_each_thread(g, t); - unlock: - read_unlock(&tasklist_lock); -} - -/* * The watchdog thread - runs every second and touches the timestamp. */ static int watchdog(void *__bind_cpu) { struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; - int this_cpu = (long)__bind_cpu; sched_setscheduler(current, SCHED_FIFO, ¶m); @@ -267,11 +190,6 @@ static int watchdog(void *__bind_cpu) if (kthread_should_stop()) break; - if (this_cpu == check_cpu) { - if (sysctl_hung_task_timeout_secs) - check_hung_uninterruptible_tasks(this_cpu); - } - set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); @@ -303,18 +221,9 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; case CPU_ONLINE: case CPU_ONLINE_FROZEN: - check_cpu = cpumask_any(cpu_online_mask); wake_up_process(per_cpu(watchdog_task, hotcpu)); break; #ifdef CONFIG_HOTPLUG_CPU - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - if (hotcpu == check_cpu) { - /* Pick any other online cpu. */ - check_cpu = cpumask_any_but(cpu_online_mask, hotcpu); - } - break; - case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: if (!per_cpu(watchdog_task, hotcpu)) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 368d1638ee78..d99d2e86cbe2 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -27,6 +27,7 @@ #include <linux/security.h> #include <linux/ctype.h> #include <linux/utsname.h> +#include <linux/kmemcheck.h> #include <linux/smp_lock.h> #include <linux/fs.h> #include <linux/init.h> @@ -48,6 +49,7 @@ #include <linux/acpi.h> #include <linux/reboot.h> #include <linux/ftrace.h> +#include <linux/slow-work.h> #include <asm/uaccess.h> #include <asm/processor.h> @@ -809,11 +811,24 @@ static struct ctl_table kern_table[] = { .data = &softlockup_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = &proc_dosoftlockup_thresh, .strategy = &sysctl_intvec, .extra1 = &neg_one, .extra2 = &sixty, }, +#endif +#ifdef CONFIG_DETECT_HUNG_TASK + { + .ctl_name = CTL_UNNUMBERED, + .procname = "hung_task_panic", + .data = &sysctl_hung_task_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &one, + }, { .ctl_name = CTL_UNNUMBERED, .procname = "hung_task_check_count", @@ -829,7 +844,7 @@ static struct ctl_table kern_table[] = { .data = &sysctl_hung_task_timeout_secs, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = &proc_dohung_task_timeout_secs, .strategy = &sysctl_intvec, }, { @@ -889,6 +904,16 @@ static struct ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif +#ifdef CONFIG_KMEMCHECK + { + .ctl_name = CTL_UNNUMBERED, + .procname = "kmemcheck", + .data = &kmemcheck_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif #ifdef CONFIG_UNEVICTABLE_LRU { .ctl_name = CTL_UNNUMBERED, @@ -899,6 +924,14 @@ static struct ctl_table kern_table[] = { .proc_handler = &scan_unevictable_handler, }, #endif +#ifdef CONFIG_SLOW_WORK + { + .ctl_name = CTL_UNNUMBERED, + .procname = "slow-work", + .mode = 0555, + .child = slow_work_sysctls, + }, +#endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index fafeb48f27c0..b38423ca711a 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -219,6 +219,7 @@ static const struct trans_ctl_table trans_net_ipv4_conf_vars_table[] = { { NET_IPV4_CONF_ARP_IGNORE, "arp_ignore" }, { NET_IPV4_CONF_PROMOTE_SECONDARIES, "promote_secondaries" }, { NET_IPV4_CONF_ARP_ACCEPT, "arp_accept" }, + { NET_IPV4_CONF_ARP_NOTIFY, "arp_notify" }, {} }; diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index ea2f48af83cf..d13be216a790 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -68,6 +68,17 @@ void clockevents_set_mode(struct clock_event_device *dev, if (dev->mode != mode) { dev->set_mode(mode, dev); dev->mode = mode; + + /* + * A nsec2cyc multiplicator of 0 is invalid and we'd crash + * on it, so fix it up and emit a warning: + */ + if (mode == CLOCK_EVT_MODE_ONESHOT) { + if (unlikely(!dev->mult)) { + dev->mult = 1; + WARN_ON(1); + } + } } } @@ -168,15 +179,6 @@ void clockevents_register_device(struct clock_event_device *dev) BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); BUG_ON(!dev->cpumask); - /* - * A nsec2cyc multiplicator of 0 is invalid and we'd crash - * on it, so fix it up and emit a warning: - */ - if (unlikely(!dev->mult)) { - dev->mult = 1; - WARN_ON(1); - } - spin_lock(&clockevents_lock); list_add(&dev->list, &clockevent_devices); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 63e05d423a09..21a5ca849514 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -274,6 +274,21 @@ out_bc: } /* + * Transfer the do_timer job away from a dying cpu. + * + * Called with interrupts disabled. + */ +static void tick_handover_do_timer(int *cpup) +{ + if (*cpup == tick_do_timer_cpu) { + int cpu = cpumask_first(cpu_online_mask); + + tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu : + TICK_DO_TIMER_NONE; + } +} + +/* * Shutdown an event device on a given cpu: * * This is called on a life CPU, when a CPU is dead. So we cannot @@ -297,13 +312,6 @@ static void tick_shutdown(unsigned int *cpup) clockevents_exchange_device(dev, NULL); td->evtdev = NULL; } - /* Transfer the do_timer job away from this cpu */ - if (*cpup == tick_do_timer_cpu) { - int cpu = cpumask_first(cpu_online_mask); - - tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu : - TICK_DO_TIMER_NONE; - } spin_unlock_irqrestore(&tick_device_lock, flags); } @@ -357,6 +365,10 @@ static int tick_notify(struct notifier_block *nb, unsigned long reason, tick_broadcast_oneshot_control(reason); break; + case CLOCK_EVT_NOTIFY_CPU_DYING: + tick_handover_do_timer(dev); + break; + case CLOCK_EVT_NOTIFY_CPU_DEAD: tick_shutdown_broadcast_oneshot(dev); tick_shutdown_broadcast(dev); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 1b6c05bd0d0a..d3f1ef4d5cbe 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -134,7 +134,7 @@ __setup("nohz=", setup_tick_nohz); * value. We do this unconditionally on any cpu, as we don't know whether the * cpu, which has the update task assigned is in a long sleep. */ -void tick_nohz_update_jiffies(void) +static void tick_nohz_update_jiffies(void) { int cpu = smp_processor_id(); struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index e2a4ff6fc3a6..dde1d46f77e5 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -264,6 +264,38 @@ config HW_BRANCH_TRACER This tracer records all branches on the system in a circular buffer giving access to the last N branches for each cpu. +config KMEMTRACE + bool "Trace SLAB allocations" + select TRACING + help + kmemtrace provides tracing for slab allocator functions, such as + kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected + data is then fed to the userspace application in order to analyse + allocation hotspots, internal fragmentation and so on, making it + possible to see how well an allocator performs, as well as debug + and profile kernel code. + + This requires an userspace application to use. See + Documentation/vm/kmemtrace.txt for more information. + + Saying Y will make the kernel somewhat larger and slower. However, + if you disable kmemtrace at run-time or boot-time, the performance + impact is minimal (depending on the arch the kernel is built for). + + If unsure, say N. + +config WORKQUEUE_TRACER + bool "Trace workqueues" + select TRACING + help + The workqueue tracer provides some statistical informations + about each cpu workqueue thread such as the number of the + works inserted and executed since their creation. It can help + to evaluate the amount of work each of them have to perform. + For example it can help a developer to decide whether he should + choose a per cpu workqueue instead of a singlethreaded one. + + config DYNAMIC_FTRACE bool "enable/disable ftrace tracepoints dynamically" depends on FUNCTION_TRACER @@ -302,4 +334,27 @@ config FTRACE_STARTUP_TEST functioning properly. It will do tests on all the configured tracers of ftrace. +config MMIOTRACE + bool "Memory mapped IO tracing" + depends on HAVE_MMIOTRACE_SUPPORT && DEBUG_KERNEL && PCI + select TRACING + help + Mmiotrace traces Memory Mapped I/O access and is meant for + debugging and reverse engineering. It is called from the ioremap + implementation and works via page faults. Tracing is disabled by + default and can be enabled at run-time. + + See Documentation/tracers/mmiotrace.txt. + If you are not helping to develop drivers, say N. + +config MMIOTRACE_TEST + tristate "Test module for mmiotrace" + depends on MMIOTRACE && m + help + This is a dumb module for testing mmiotrace. It is very dangerous + as it will write garbage to IO memory starting at a given address. + However, it should be safe to use on e.g. unused portion of VRAM. + + Say N, unless you absolutely know what you are doing. + endmenu diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 349d5a93653f..f76d48f3527d 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -19,6 +19,8 @@ obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o obj-$(CONFIG_RING_BUFFER) += ring_buffer.o obj-$(CONFIG_TRACING) += trace.o +obj-$(CONFIG_TRACING) += trace_output.o +obj-$(CONFIG_TRACING) += trace_stat.o obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o @@ -33,5 +35,7 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o obj-$(CONFIG_POWER_TRACER) += trace_power.o +obj-$(CONFIG_KMEMTRACE) += kmemtrace.o +obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o libftrace-y := ftrace.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 2f32969c09df..7e9a20b69939 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -17,6 +17,7 @@ #include <linux/clocksource.h> #include <linux/kallsyms.h> #include <linux/seq_file.h> +#include <linux/suspend.h> #include <linux/debugfs.h> #include <linux/hardirq.h> #include <linux/kthread.h> @@ -263,14 +264,6 @@ static void ftrace_update_pid_func(void) # error Dynamic ftrace depends on MCOUNT_RECORD #endif -/* - * Since MCOUNT_ADDR may point to mcount itself, we do not want - * to get it confused by reading a reference in the code as we - * are parsing on objcopy output of text. Use a variable for - * it instead. - */ -static unsigned long mcount_addr = MCOUNT_ADDR; - enum { FTRACE_ENABLE_CALLS = (1 << 0), FTRACE_DISABLE_CALLS = (1 << 1), @@ -289,7 +282,7 @@ static DEFINE_MUTEX(ftrace_regex_lock); struct ftrace_page { struct ftrace_page *next; - unsigned long index; + int index; struct dyn_ftrace records[]; }; @@ -463,7 +456,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) unsigned long ip, fl; unsigned long ftrace_addr; - ftrace_addr = (unsigned long)ftrace_caller; + ftrace_addr = (unsigned long)FTRACE_ADDR; ip = rec->ip; @@ -575,7 +568,7 @@ ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) ip = rec->ip; - ret = ftrace_make_nop(mod, rec, mcount_addr); + ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR); if (ret) { ftrace_bug(ret, ip); rec->flags |= FTRACE_FL_FAILED; @@ -786,7 +779,7 @@ enum { struct ftrace_iterator { struct ftrace_page *pg; - unsigned idx; + int idx; unsigned flags; unsigned char buffer[FTRACE_BUFF_MAX+1]; unsigned buffer_idx; @@ -1902,7 +1895,7 @@ int register_ftrace_function(struct ftrace_ops *ops) } /** - * unregister_ftrace_function - unresgister a function for profiling. + * unregister_ftrace_function - unregister a function for profiling. * @ops - ops structure that holds the function to unregister * * Unregister a function that was added to be called by ftrace profiling. @@ -1965,6 +1958,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, #ifdef CONFIG_FUNCTION_GRAPH_TRACER static atomic_t ftrace_graph_active; +static struct notifier_block ftrace_suspend_notifier; int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace) { @@ -2043,6 +2037,27 @@ static int start_graph_tracing(void) return ret; } +/* + * Hibernation protection. + * The state of the current task is too much unstable during + * suspend/restore to disk. We want to protect against that. + */ +static int +ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state, + void *unused) +{ + switch (state) { + case PM_HIBERNATION_PREPARE: + pause_graph_tracing(); + break; + + case PM_POST_HIBERNATION: + unpause_graph_tracing(); + break; + } + return NOTIFY_DONE; +} + int register_ftrace_graph(trace_func_graph_ret_t retfunc, trace_func_graph_ent_t entryfunc) { @@ -2050,6 +2065,9 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc, mutex_lock(&ftrace_sysctl_lock); + ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call; + register_pm_notifier(&ftrace_suspend_notifier); + atomic_inc(&ftrace_graph_active); ret = start_graph_tracing(); if (ret) { @@ -2075,6 +2093,7 @@ void unregister_ftrace_graph(void) ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub; ftrace_graph_entry = ftrace_graph_entry_stub; ftrace_shutdown(FTRACE_STOP_FUNC_RET); + unregister_pm_notifier(&ftrace_suspend_notifier); mutex_unlock(&ftrace_sysctl_lock); } diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c new file mode 100644 index 000000000000..7ebc58cee3bd --- /dev/null +++ b/kernel/trace/kmemtrace.c @@ -0,0 +1,350 @@ +/* + * Memory allocator tracing + * + * Copyright (C) 2008 Eduard - Gabriel Munteanu + * Copyright (C) 2008 Pekka Enberg <penberg@cs.helsinki.fi> + * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com> + */ + +#include <linux/dcache.h> +#include <linux/debugfs.h> +#include <linux/fs.h> +#include <linux/seq_file.h> +#include <trace/kmemtrace.h> + +#include "trace.h" +#include "trace_output.h" + +/* Select an alternative, minimalistic output than the original one */ +#define TRACE_KMEM_OPT_MINIMAL 0x1 + +static struct tracer_opt kmem_opts[] = { + /* Default disable the minimalistic output */ + { TRACER_OPT(kmem_minimalistic, TRACE_KMEM_OPT_MINIMAL) }, + { } +}; + +static struct tracer_flags kmem_tracer_flags = { + .val = 0, + .opts = kmem_opts +}; + + +static bool kmem_tracing_enabled __read_mostly; +static struct trace_array *kmemtrace_array; + +static int kmem_trace_init(struct trace_array *tr) +{ + int cpu; + kmemtrace_array = tr; + + for_each_cpu_mask(cpu, cpu_possible_map) + tracing_reset(tr, cpu); + + kmem_tracing_enabled = true; + + return 0; +} + +static void kmem_trace_reset(struct trace_array *tr) +{ + kmem_tracing_enabled = false; +} + +static void kmemtrace_headers(struct seq_file *s) +{ + /* Don't need headers for the original kmemtrace output */ + if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)) + return; + + seq_printf(s, "#\n"); + seq_printf(s, "# ALLOC TYPE REQ GIVEN FLAGS " + " POINTER NODE CALLER\n"); + seq_printf(s, "# FREE | | | | " + " | | | |\n"); + seq_printf(s, "# |\n\n"); +} + +/* + * The two following functions give the original output from kmemtrace, + * or something close to....perhaps they need some missing things + */ +static enum print_line_t +kmemtrace_print_alloc_original(struct trace_iterator *iter, + struct kmemtrace_alloc_entry *entry) +{ + struct trace_seq *s = &iter->seq; + int ret; + + /* Taken from the old linux/kmemtrace.h */ + ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu " + "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n", + entry->type_id, entry->call_site, (unsigned long) entry->ptr, + (unsigned long) entry->bytes_req, (unsigned long) entry->bytes_alloc, + (unsigned long) entry->gfp_flags, entry->node); + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t +kmemtrace_print_free_original(struct trace_iterator *iter, + struct kmemtrace_free_entry *entry) +{ + struct trace_seq *s = &iter->seq; + int ret; + + /* Taken from the old linux/kmemtrace.h */ + ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu\n", + entry->type_id, entry->call_site, (unsigned long) entry->ptr); + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + + +/* The two other following provide a more minimalistic output */ +static enum print_line_t +kmemtrace_print_alloc_compress(struct trace_iterator *iter, + struct kmemtrace_alloc_entry *entry) +{ + struct trace_seq *s = &iter->seq; + int ret; + + /* Alloc entry */ + ret = trace_seq_printf(s, " + "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Type */ + switch (entry->type_id) { + case KMEMTRACE_TYPE_KMALLOC: + ret = trace_seq_printf(s, "K "); + break; + case KMEMTRACE_TYPE_CACHE: + ret = trace_seq_printf(s, "C "); + break; + case KMEMTRACE_TYPE_PAGES: + ret = trace_seq_printf(s, "P "); + break; + default: + ret = trace_seq_printf(s, "? "); + } + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Requested */ + ret = trace_seq_printf(s, "%4ld ", entry->bytes_req); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Allocated */ + ret = trace_seq_printf(s, "%4ld ", entry->bytes_alloc); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Flags + * TODO: would be better to see the name of the GFP flag names + */ + ret = trace_seq_printf(s, "%08x ", entry->gfp_flags); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Pointer to allocated */ + ret = trace_seq_printf(s, "0x%tx ", (ptrdiff_t)entry->ptr); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Node */ + ret = trace_seq_printf(s, "%4d ", entry->node); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Call site */ + ret = seq_print_ip_sym(s, entry->call_site, 0); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + if (!trace_seq_printf(s, "\n")) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t +kmemtrace_print_free_compress(struct trace_iterator *iter, + struct kmemtrace_free_entry *entry) +{ + struct trace_seq *s = &iter->seq; + int ret; + + /* Free entry */ + ret = trace_seq_printf(s, " - "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Type */ + switch (entry->type_id) { + case KMEMTRACE_TYPE_KMALLOC: + ret = trace_seq_printf(s, "K "); + break; + case KMEMTRACE_TYPE_CACHE: + ret = trace_seq_printf(s, "C "); + break; + case KMEMTRACE_TYPE_PAGES: + ret = trace_seq_printf(s, "P "); + break; + default: + ret = trace_seq_printf(s, "? "); + } + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Skip requested/allocated/flags */ + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Pointer to allocated */ + ret = trace_seq_printf(s, "0x%tx ", (ptrdiff_t)entry->ptr); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Skip node */ + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Call site */ + ret = seq_print_ip_sym(s, entry->call_site, 0); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + if (!trace_seq_printf(s, "\n")) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter) +{ + struct trace_entry *entry = iter->ent; + + switch (entry->type) { + case TRACE_KMEM_ALLOC: { + struct kmemtrace_alloc_entry *field; + trace_assign_type(field, entry); + if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL) + return kmemtrace_print_alloc_compress(iter, field); + else + return kmemtrace_print_alloc_original(iter, field); + } + + case TRACE_KMEM_FREE: { + struct kmemtrace_free_entry *field; + trace_assign_type(field, entry); + if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL) + return kmemtrace_print_free_compress(iter, field); + else + return kmemtrace_print_free_original(iter, field); + } + + default: + return TRACE_TYPE_UNHANDLED; + } +} + +/* Trace allocations */ +void kmemtrace_mark_alloc_node(enum kmemtrace_type_id type_id, + unsigned long call_site, + const void *ptr, + size_t bytes_req, + size_t bytes_alloc, + gfp_t gfp_flags, + int node) +{ + struct ring_buffer_event *event; + struct kmemtrace_alloc_entry *entry; + struct trace_array *tr = kmemtrace_array; + unsigned long irq_flags; + + if (!kmem_tracing_enabled) + return; + + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + return; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, 0, 0); + + entry->ent.type = TRACE_KMEM_ALLOC; + entry->call_site = call_site; + entry->ptr = ptr; + entry->bytes_req = bytes_req; + entry->bytes_alloc = bytes_alloc; + entry->gfp_flags = gfp_flags; + entry->node = node; + + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + + trace_wake_up(); +} +EXPORT_SYMBOL(kmemtrace_mark_alloc_node); + +void kmemtrace_mark_free(enum kmemtrace_type_id type_id, + unsigned long call_site, + const void *ptr) +{ + struct ring_buffer_event *event; + struct kmemtrace_free_entry *entry; + struct trace_array *tr = kmemtrace_array; + unsigned long irq_flags; + + if (!kmem_tracing_enabled) + return; + + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + return; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, 0, 0); + + entry->ent.type = TRACE_KMEM_FREE; + entry->type_id = type_id; + entry->call_site = call_site; + entry->ptr = ptr; + + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + + trace_wake_up(); +} +EXPORT_SYMBOL(kmemtrace_mark_free); + +static struct tracer kmem_tracer __read_mostly = { + .name = "kmemtrace", + .init = kmem_trace_init, + .reset = kmem_trace_reset, + .print_line = kmemtrace_print_line, + .print_header = kmemtrace_headers, + .flags = &kmem_tracer_flags +}; + +void kmemtrace_init(void) +{ + /* earliest opportunity to start kmem tracing */ +} + +static int __init init_kmem_tracer(void) +{ + return register_tracer(&kmem_tracer); +} + +device_initcall(init_kmem_tracer); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 8b0daf0662ef..b36d7374ceef 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -123,8 +123,7 @@ void ring_buffer_normalize_time_stamp(int cpu, u64 *ts) EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp); #define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event)) -#define RB_ALIGNMENT_SHIFT 2 -#define RB_ALIGNMENT (1 << RB_ALIGNMENT_SHIFT) +#define RB_ALIGNMENT 4U #define RB_MAX_SMALL_DATA 28 enum { @@ -133,7 +132,7 @@ enum { }; /* inline for ring buffer fast paths */ -static inline unsigned +static unsigned rb_event_length(struct ring_buffer_event *event) { unsigned length; @@ -151,7 +150,7 @@ rb_event_length(struct ring_buffer_event *event) case RINGBUF_TYPE_DATA: if (event->len) - length = event->len << RB_ALIGNMENT_SHIFT; + length = event->len * RB_ALIGNMENT; else length = event->array[0]; return length + RB_EVNT_HDR_SIZE; @@ -179,7 +178,7 @@ unsigned ring_buffer_event_length(struct ring_buffer_event *event) EXPORT_SYMBOL_GPL(ring_buffer_event_length); /* inline for ring buffer fast paths */ -static inline void * +static void * rb_event_data(struct ring_buffer_event *event) { BUG_ON(event->type != RINGBUF_TYPE_DATA); @@ -229,10 +228,9 @@ static void rb_init_page(struct buffer_data_page *bpage) * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing * this issue out. */ -static inline void free_buffer_page(struct buffer_page *bpage) +static void free_buffer_page(struct buffer_page *bpage) { - if (bpage->page) - free_page((unsigned long)bpage->page); + free_page((unsigned long)bpage->page); kfree(bpage); } @@ -246,7 +244,7 @@ static inline int test_time_stamp(u64 delta) return 0; } -#define BUF_PAGE_SIZE (PAGE_SIZE - sizeof(struct buffer_data_page)) +#define BUF_PAGE_SIZE (PAGE_SIZE - offsetof(struct buffer_data_page, data)) /* * head_page == tail_page && head == tail then buffer is empty. @@ -811,7 +809,7 @@ rb_event_index(struct ring_buffer_event *event) return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE); } -static inline int +static int rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { @@ -825,7 +823,7 @@ rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer, rb_commit_index(cpu_buffer) == index; } -static inline void +static void rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { @@ -850,7 +848,7 @@ rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer, local_set(&cpu_buffer->commit_page->page->commit, index); } -static inline void +static void rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) { /* @@ -896,7 +894,7 @@ static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read = 0; } -static inline void rb_inc_iter(struct ring_buffer_iter *iter) +static void rb_inc_iter(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; @@ -926,7 +924,7 @@ static inline void rb_inc_iter(struct ring_buffer_iter *iter) * and with this, we can determine what to place into the * data field. */ -static inline void +static void rb_update_event(struct ring_buffer_event *event, unsigned type, unsigned length) { @@ -938,15 +936,11 @@ rb_update_event(struct ring_buffer_event *event, break; case RINGBUF_TYPE_TIME_EXTEND: - event->len = - (RB_LEN_TIME_EXTEND + (RB_ALIGNMENT-1)) - >> RB_ALIGNMENT_SHIFT; + event->len = DIV_ROUND_UP(RB_LEN_TIME_EXTEND, RB_ALIGNMENT); break; case RINGBUF_TYPE_TIME_STAMP: - event->len = - (RB_LEN_TIME_STAMP + (RB_ALIGNMENT-1)) - >> RB_ALIGNMENT_SHIFT; + event->len = DIV_ROUND_UP(RB_LEN_TIME_STAMP, RB_ALIGNMENT); break; case RINGBUF_TYPE_DATA: @@ -955,16 +949,14 @@ rb_update_event(struct ring_buffer_event *event, event->len = 0; event->array[0] = length; } else - event->len = - (length + (RB_ALIGNMENT-1)) - >> RB_ALIGNMENT_SHIFT; + event->len = DIV_ROUND_UP(length, RB_ALIGNMENT); break; default: BUG(); } } -static inline unsigned rb_calculate_event_length(unsigned length) +static unsigned rb_calculate_event_length(unsigned length) { struct ring_buffer_event event; /* Used only for sizeof array */ @@ -1025,12 +1017,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, } if (next_page == head_page) { - if (!(buffer->flags & RB_FL_OVERWRITE)) { - /* reset write */ - if (tail <= BUF_PAGE_SIZE) - local_set(&tail_page->write, tail); + if (!(buffer->flags & RB_FL_OVERWRITE)) goto out_unlock; - } /* tail_page has not moved yet? */ if (tail_page == cpu_buffer->tail_page) { @@ -1105,6 +1093,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, return event; out_unlock: + /* reset write */ + if (tail <= BUF_PAGE_SIZE) + local_set(&tail_page->write, tail); + __raw_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); return NULL; @@ -1438,7 +1430,7 @@ int ring_buffer_write(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_write); -static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) +static int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *reader = cpu_buffer->reader_page; struct buffer_page *head = cpu_buffer->head_page; @@ -2174,6 +2166,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->overrun = 0; cpu_buffer->entries = 0; + + cpu_buffer->write_stamp = 0; + cpu_buffer->read_stamp = 0; } /** @@ -2274,9 +2269,24 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, if (buffer_a->pages != buffer_b->pages) return -EINVAL; + if (ring_buffer_flags != RB_BUFFERS_ON) + return -EAGAIN; + + if (atomic_read(&buffer_a->record_disabled)) + return -EAGAIN; + + if (atomic_read(&buffer_b->record_disabled)) + return -EAGAIN; + cpu_buffer_a = buffer_a->buffers[cpu]; cpu_buffer_b = buffer_b->buffers[cpu]; + if (atomic_read(&cpu_buffer_a->record_disabled)) + return -EAGAIN; + + if (atomic_read(&cpu_buffer_b->record_disabled)) + return -EAGAIN; + /* * We can't do a synchronize_sched here because this * function can be called in atomic context. diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c580233add95..757ae6f7e648 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -37,10 +37,11 @@ #include <linux/irqflags.h> #include "trace.h" +#include "trace_output.h" #define TRACE_BUFFER_FLAGS (RB_FL_OVERWRITE) -unsigned long __read_mostly tracing_max_latency = (cycle_t)ULONG_MAX; +unsigned long __read_mostly tracing_max_latency; unsigned long __read_mostly tracing_thresh; /* @@ -186,9 +187,6 @@ int tracing_is_enabled(void) return tracer_enabled; } -/* function tracing enabled */ -int ftrace_function_enabled; - /* * trace_buf_size is the size in bytes that is allocated * for a buffer. Note, the number of bytes is always rounded @@ -329,132 +327,6 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) tracing_record_cmdline(current); } -/** - * trace_seq_printf - sequence printing of trace information - * @s: trace sequence descriptor - * @fmt: printf format string - * - * The tracer may use either sequence operations or its own - * copy to user routines. To simplify formating of a trace - * trace_seq_printf is used to store strings into a special - * buffer (@s). Then the output may be either used by - * the sequencer or pulled into another buffer. - */ -int -trace_seq_printf(struct trace_seq *s, const char *fmt, ...) -{ - int len = (PAGE_SIZE - 1) - s->len; - va_list ap; - int ret; - - if (!len) - return 0; - - va_start(ap, fmt); - ret = vsnprintf(s->buffer + s->len, len, fmt, ap); - va_end(ap); - - /* If we can't write it all, don't bother writing anything */ - if (ret >= len) - return 0; - - s->len += ret; - - return len; -} - -/** - * trace_seq_puts - trace sequence printing of simple string - * @s: trace sequence descriptor - * @str: simple string to record - * - * The tracer may use either the sequence operations or its own - * copy to user routines. This function records a simple string - * into a special buffer (@s) for later retrieval by a sequencer - * or other mechanism. - */ -static int -trace_seq_puts(struct trace_seq *s, const char *str) -{ - int len = strlen(str); - - if (len > ((PAGE_SIZE - 1) - s->len)) - return 0; - - memcpy(s->buffer + s->len, str, len); - s->len += len; - - return len; -} - -static int -trace_seq_putc(struct trace_seq *s, unsigned char c) -{ - if (s->len >= (PAGE_SIZE - 1)) - return 0; - - s->buffer[s->len++] = c; - - return 1; -} - -static int -trace_seq_putmem(struct trace_seq *s, void *mem, size_t len) -{ - if (len > ((PAGE_SIZE - 1) - s->len)) - return 0; - - memcpy(s->buffer + s->len, mem, len); - s->len += len; - - return len; -} - -#define MAX_MEMHEX_BYTES 8 -#define HEX_CHARS (MAX_MEMHEX_BYTES*2 + 1) - -static int -trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len) -{ - unsigned char hex[HEX_CHARS]; - unsigned char *data = mem; - int i, j; - -#ifdef __BIG_ENDIAN - for (i = 0, j = 0; i < len; i++) { -#else - for (i = len-1, j = 0; i >= 0; i--) { -#endif - hex[j++] = hex_asc_hi(data[i]); - hex[j++] = hex_asc_lo(data[i]); - } - hex[j++] = ' '; - - return trace_seq_putmem(s, hex, j); -} - -static int -trace_seq_path(struct trace_seq *s, struct path *path) -{ - unsigned char *p; - - if (s->len >= (PAGE_SIZE - 1)) - return 0; - p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len); - if (!IS_ERR(p)) { - p = mangle_path(s->buffer + s->len, p, "\n"); - if (p) { - s->len = p - s->buffer; - return 1; - } - } else { - s->buffer[s->len++] = '?'; - return 1; - } - - return 0; -} - static void trace_seq_reset(struct trace_seq *s) { @@ -543,7 +415,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) ftrace_enable_cpu(); - WARN_ON_ONCE(ret); + WARN_ON_ONCE(ret && ret != -EAGAIN); __update_max_tr(tr, tsk, cpu); __raw_spin_unlock(&ftrace_max_lock); @@ -960,10 +832,10 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data, trace_function(tr, data, ip, parent_ip, flags, pc); } -static void ftrace_trace_stack(struct trace_array *tr, - struct trace_array_cpu *data, - unsigned long flags, - int skip, int pc) +static void __ftrace_trace_stack(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long flags, + int skip, int pc) { #ifdef CONFIG_STACKTRACE struct ring_buffer_event *event; @@ -971,9 +843,6 @@ static void ftrace_trace_stack(struct trace_array *tr, struct stack_trace trace; unsigned long irq_flags; - if (!(trace_flags & TRACE_ITER_STACKTRACE)) - return; - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), &irq_flags); if (!event) @@ -994,12 +863,23 @@ static void ftrace_trace_stack(struct trace_array *tr, #endif } +static void ftrace_trace_stack(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long flags, + int skip, int pc) +{ + if (!(trace_flags & TRACE_ITER_STACKTRACE)) + return; + + __ftrace_trace_stack(tr, data, flags, skip, pc); +} + void __trace_stack(struct trace_array *tr, struct trace_array_cpu *data, unsigned long flags, - int skip) + int skip, int pc) { - ftrace_trace_stack(tr, data, flags, skip, preempt_count()); + __ftrace_trace_stack(tr, data, flags, skip, pc); } static void ftrace_trace_userstack(struct trace_array *tr, @@ -1163,65 +1043,6 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) local_irq_restore(flags); } -#ifdef CONFIG_FUNCTION_TRACER -static void -function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) -{ - struct trace_array *tr = &global_trace; - struct trace_array_cpu *data; - unsigned long flags; - long disabled; - int cpu, resched; - int pc; - - if (unlikely(!ftrace_function_enabled)) - return; - - pc = preempt_count(); - resched = ftrace_preempt_disable(); - local_save_flags(flags); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - disabled = atomic_inc_return(&data->disabled); - - if (likely(disabled == 1)) - trace_function(tr, data, ip, parent_ip, flags, pc); - - atomic_dec(&data->disabled); - ftrace_preempt_enable(resched); -} - -static void -function_trace_call(unsigned long ip, unsigned long parent_ip) -{ - struct trace_array *tr = &global_trace; - struct trace_array_cpu *data; - unsigned long flags; - long disabled; - int cpu; - int pc; - - if (unlikely(!ftrace_function_enabled)) - return; - - /* - * Need to use raw, since this must be called before the - * recursive protection is performed. - */ - local_irq_save(flags); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - disabled = atomic_inc_return(&data->disabled); - - if (likely(disabled == 1)) { - pc = preempt_count(); - trace_function(tr, data, ip, parent_ip, flags, pc); - } - - atomic_dec(&data->disabled); - local_irq_restore(flags); -} - #ifdef CONFIG_FUNCTION_GRAPH_TRACER int trace_graph_entry(struct ftrace_graph_ent *trace) { @@ -1279,31 +1100,6 @@ void trace_graph_return(struct ftrace_graph_ret *trace) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -static struct ftrace_ops trace_ops __read_mostly = -{ - .func = function_trace_call, -}; - -void tracing_start_function_trace(void) -{ - ftrace_function_enabled = 0; - - if (trace_flags & TRACE_ITER_PREEMPTONLY) - trace_ops.func = function_trace_call_preempt_only; - else - trace_ops.func = function_trace_call; - - register_ftrace_function(&trace_ops); - ftrace_function_enabled = 1; -} - -void tracing_stop_function_trace(void) -{ - ftrace_function_enabled = 0; - unregister_ftrace_function(&trace_ops); -} -#endif - enum trace_file_type { TRACE_FILE_LAT_FMT = 1, TRACE_FILE_ANNOTATE = 2, @@ -1472,154 +1268,6 @@ static void s_stop(struct seq_file *m, void *p) mutex_unlock(&trace_types_lock); } -#ifdef CONFIG_KRETPROBES -static inline const char *kretprobed(const char *name) -{ - static const char tramp_name[] = "kretprobe_trampoline"; - int size = sizeof(tramp_name); - - if (strncmp(tramp_name, name, size) == 0) - return "[unknown/kretprobe'd]"; - return name; -} -#else -static inline const char *kretprobed(const char *name) -{ - return name; -} -#endif /* CONFIG_KRETPROBES */ - -static int -seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address) -{ -#ifdef CONFIG_KALLSYMS - char str[KSYM_SYMBOL_LEN]; - const char *name; - - kallsyms_lookup(address, NULL, NULL, NULL, str); - - name = kretprobed(str); - - return trace_seq_printf(s, fmt, name); -#endif - return 1; -} - -static int -seq_print_sym_offset(struct trace_seq *s, const char *fmt, - unsigned long address) -{ -#ifdef CONFIG_KALLSYMS - char str[KSYM_SYMBOL_LEN]; - const char *name; - - sprint_symbol(str, address); - name = kretprobed(str); - - return trace_seq_printf(s, fmt, name); -#endif - return 1; -} - -#ifndef CONFIG_64BIT -# define IP_FMT "%08lx" -#else -# define IP_FMT "%016lx" -#endif - -int -seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) -{ - int ret; - - if (!ip) - return trace_seq_printf(s, "0"); - - if (sym_flags & TRACE_ITER_SYM_OFFSET) - ret = seq_print_sym_offset(s, "%s", ip); - else - ret = seq_print_sym_short(s, "%s", ip); - - if (!ret) - return 0; - - if (sym_flags & TRACE_ITER_SYM_ADDR) - ret = trace_seq_printf(s, " <" IP_FMT ">", ip); - return ret; -} - -static inline int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm, - unsigned long ip, unsigned long sym_flags) -{ - struct file *file = NULL; - unsigned long vmstart = 0; - int ret = 1; - - if (mm) { - const struct vm_area_struct *vma; - - down_read(&mm->mmap_sem); - vma = find_vma(mm, ip); - if (vma) { - file = vma->vm_file; - vmstart = vma->vm_start; - } - if (file) { - ret = trace_seq_path(s, &file->f_path); - if (ret) - ret = trace_seq_printf(s, "[+0x%lx]", ip - vmstart); - } - up_read(&mm->mmap_sem); - } - if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file)) - ret = trace_seq_printf(s, " <" IP_FMT ">", ip); - return ret; -} - -static int -seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s, - unsigned long sym_flags) -{ - struct mm_struct *mm = NULL; - int ret = 1; - unsigned int i; - - if (trace_flags & TRACE_ITER_SYM_USEROBJ) { - struct task_struct *task; - /* - * we do the lookup on the thread group leader, - * since individual threads might have already quit! - */ - rcu_read_lock(); - task = find_task_by_vpid(entry->ent.tgid); - if (task) - mm = get_task_mm(task); - rcu_read_unlock(); - } - - for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { - unsigned long ip = entry->caller[i]; - - if (ip == ULONG_MAX || !ret) - break; - if (i && ret) - ret = trace_seq_puts(s, " <- "); - if (!ip) { - if (ret) - ret = trace_seq_puts(s, "??"); - continue; - } - if (!ret) - break; - if (ret) - ret = seq_print_user_ip(s, mm, ip, sym_flags); - } - - if (mm) - mmput(mm); - return ret; -} - static void print_lat_help_header(struct seq_file *m) { seq_puts(m, "# _------=> CPU# \n"); @@ -1755,52 +1403,6 @@ lat_print_timestamp(struct trace_seq *s, u64 abs_usecs, trace_seq_puts(s, " : "); } -static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; - -static int task_state_char(unsigned long state) -{ - int bit = state ? __ffs(state) + 1 : 0; - - return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; -} - -/* - * The message is supposed to contain an ending newline. - * If the printing stops prematurely, try to add a newline of our own. - */ -void trace_seq_print_cont(struct trace_seq *s, struct trace_iterator *iter) -{ - struct trace_entry *ent; - struct trace_field_cont *cont; - bool ok = true; - - ent = peek_next_entry(iter, iter->cpu, NULL); - if (!ent || ent->type != TRACE_CONT) { - trace_seq_putc(s, '\n'); - return; - } - - do { - cont = (struct trace_field_cont *)ent; - if (ok) - ok = (trace_seq_printf(s, "%s", cont->buf) > 0); - - ftrace_disable_cpu(); - - if (iter->buffer_iter[iter->cpu]) - ring_buffer_read(iter->buffer_iter[iter->cpu], NULL); - else - ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL); - - ftrace_enable_cpu(); - - ent = peek_next_entry(iter, iter->cpu, NULL); - } while (ent && ent->type == TRACE_CONT); - - if (!ok) - trace_seq_putc(s, '\n'); -} - static void test_cpu_buff_start(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; @@ -1824,17 +1426,14 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) struct trace_seq *s = &iter->seq; unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); struct trace_entry *next_entry; + struct trace_event *event; unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE); struct trace_entry *entry = iter->ent; unsigned long abs_usecs; unsigned long rel_usecs; u64 next_ts; char *comm; - int S, T; - int i; - - if (entry->type == TRACE_CONT) - return TRACE_TYPE_HANDLED; + int ret; test_cpu_buff_start(iter); @@ -1859,96 +1458,16 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) lat_print_generic(s, entry, cpu); lat_print_timestamp(s, abs_usecs, rel_usecs); } - switch (entry->type) { - case TRACE_FN: { - struct ftrace_entry *field; - trace_assign_type(field, entry); - - seq_print_ip_sym(s, field->ip, sym_flags); - trace_seq_puts(s, " ("); - seq_print_ip_sym(s, field->parent_ip, sym_flags); - trace_seq_puts(s, ")\n"); - break; - } - case TRACE_CTX: - case TRACE_WAKE: { - struct ctx_switch_entry *field; - - trace_assign_type(field, entry); - - T = task_state_char(field->next_state); - S = task_state_char(field->prev_state); - comm = trace_find_cmdline(field->next_pid); - trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", - field->prev_pid, - field->prev_prio, - S, entry->type == TRACE_CTX ? "==>" : " +", - field->next_cpu, - field->next_pid, - field->next_prio, - T, comm); - break; - } - case TRACE_SPECIAL: { - struct special_entry *field; - - trace_assign_type(field, entry); - - trace_seq_printf(s, "# %ld %ld %ld\n", - field->arg1, - field->arg2, - field->arg3); - break; - } - case TRACE_STACK: { - struct stack_entry *field; - - trace_assign_type(field, entry); - - for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { - if (i) - trace_seq_puts(s, " <= "); - seq_print_ip_sym(s, field->caller[i], sym_flags); - } - trace_seq_puts(s, "\n"); - break; - } - case TRACE_PRINT: { - struct print_entry *field; - - trace_assign_type(field, entry); - - seq_print_ip_sym(s, field->ip, sym_flags); - trace_seq_printf(s, ": %s", field->buf); - if (entry->flags & TRACE_FLAG_CONT) - trace_seq_print_cont(s, iter); - break; - } - case TRACE_BRANCH: { - struct trace_branch *field; - - trace_assign_type(field, entry); - - trace_seq_printf(s, "[%s] %s:%s:%d\n", - field->correct ? " ok " : " MISS ", - field->func, - field->file, - field->line); - break; + event = ftrace_find_event(entry->type); + if (event && event->latency_trace) { + ret = event->latency_trace(s, entry, sym_flags); + if (ret) + return ret; + return TRACE_TYPE_HANDLED; } - case TRACE_USER_STACK: { - struct userstack_entry *field; - trace_assign_type(field, entry); - - seq_print_userip_objs(field, s, sym_flags); - trace_seq_putc(s, '\n'); - break; - } - default: - trace_seq_printf(s, "Unknown type %d\n", entry->type); - } + trace_seq_printf(s, "Unknown type %d\n", entry->type); return TRACE_TYPE_HANDLED; } @@ -1957,19 +1476,15 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) struct trace_seq *s = &iter->seq; unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); struct trace_entry *entry; + struct trace_event *event; unsigned long usec_rem; unsigned long long t; unsigned long secs; char *comm; int ret; - int S, T; - int i; entry = iter->ent; - if (entry->type == TRACE_CONT) - return TRACE_TYPE_HANDLED; - test_cpu_buff_start(iter); comm = trace_find_cmdline(iter->ent->pid); @@ -1988,129 +1503,17 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) if (!ret) return TRACE_TYPE_PARTIAL_LINE; - switch (entry->type) { - case TRACE_FN: { - struct ftrace_entry *field; - - trace_assign_type(field, entry); - - ret = seq_print_ip_sym(s, field->ip, sym_flags); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - if ((sym_flags & TRACE_ITER_PRINT_PARENT) && - field->parent_ip) { - ret = trace_seq_printf(s, " <-"); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - ret = seq_print_ip_sym(s, - field->parent_ip, - sym_flags); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } - ret = trace_seq_printf(s, "\n"); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - case TRACE_CTX: - case TRACE_WAKE: { - struct ctx_switch_entry *field; - - trace_assign_type(field, entry); - - T = task_state_char(field->next_state); - S = task_state_char(field->prev_state); - ret = trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c\n", - field->prev_pid, - field->prev_prio, - S, - entry->type == TRACE_CTX ? "==>" : " +", - field->next_cpu, - field->next_pid, - field->next_prio, - T); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - case TRACE_SPECIAL: { - struct special_entry *field; - - trace_assign_type(field, entry); - - ret = trace_seq_printf(s, "# %ld %ld %ld\n", - field->arg1, - field->arg2, - field->arg3); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - case TRACE_STACK: { - struct stack_entry *field; - - trace_assign_type(field, entry); - - for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { - if (i) { - ret = trace_seq_puts(s, " <= "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } - ret = seq_print_ip_sym(s, field->caller[i], - sym_flags); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } - ret = trace_seq_puts(s, "\n"); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - case TRACE_PRINT: { - struct print_entry *field; - - trace_assign_type(field, entry); - - seq_print_ip_sym(s, field->ip, sym_flags); - trace_seq_printf(s, ": %s", field->buf); - if (entry->flags & TRACE_FLAG_CONT) - trace_seq_print_cont(s, iter); - break; - } - case TRACE_GRAPH_RET: { - return print_graph_function(iter); - } - case TRACE_GRAPH_ENT: { - return print_graph_function(iter); - } - case TRACE_BRANCH: { - struct trace_branch *field; - - trace_assign_type(field, entry); - - trace_seq_printf(s, "[%s] %s:%s:%d\n", - field->correct ? " ok " : " MISS ", - field->func, - field->file, - field->line); - break; + event = ftrace_find_event(entry->type); + if (event && event->trace) { + ret = event->trace(s, entry, sym_flags); + if (ret) + return ret; + return TRACE_TYPE_HANDLED; } - case TRACE_USER_STACK: { - struct userstack_entry *field; - - trace_assign_type(field, entry); + ret = trace_seq_printf(s, "Unknown type %d\n", entry->type); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; - ret = seq_print_userip_objs(field, s, sym_flags); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_putc(s, '\n'); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - } return TRACE_TYPE_HANDLED; } @@ -2118,152 +1521,47 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct trace_entry *entry; + struct trace_event *event; int ret; - int S, T; entry = iter->ent; - if (entry->type == TRACE_CONT) - return TRACE_TYPE_HANDLED; - ret = trace_seq_printf(s, "%d %d %llu ", entry->pid, iter->cpu, iter->ts); if (!ret) return TRACE_TYPE_PARTIAL_LINE; - switch (entry->type) { - case TRACE_FN: { - struct ftrace_entry *field; - - trace_assign_type(field, entry); - - ret = trace_seq_printf(s, "%x %x\n", - field->ip, - field->parent_ip); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - case TRACE_CTX: - case TRACE_WAKE: { - struct ctx_switch_entry *field; - - trace_assign_type(field, entry); - - T = task_state_char(field->next_state); - S = entry->type == TRACE_WAKE ? '+' : - task_state_char(field->prev_state); - ret = trace_seq_printf(s, "%d %d %c %d %d %d %c\n", - field->prev_pid, - field->prev_prio, - S, - field->next_cpu, - field->next_pid, - field->next_prio, - T); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - case TRACE_SPECIAL: - case TRACE_USER_STACK: - case TRACE_STACK: { - struct special_entry *field; - - trace_assign_type(field, entry); - - ret = trace_seq_printf(s, "# %ld %ld %ld\n", - field->arg1, - field->arg2, - field->arg3); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; + event = ftrace_find_event(entry->type); + if (event && event->raw) { + ret = event->raw(s, entry, 0); + if (ret) + return ret; + return TRACE_TYPE_HANDLED; } - case TRACE_PRINT: { - struct print_entry *field; - - trace_assign_type(field, entry); + ret = trace_seq_printf(s, "%d ?\n", entry->type); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; - trace_seq_printf(s, "# %lx %s", field->ip, field->buf); - if (entry->flags & TRACE_FLAG_CONT) - trace_seq_print_cont(s, iter); - break; - } - } return TRACE_TYPE_HANDLED; } -#define SEQ_PUT_FIELD_RET(s, x) \ -do { \ - if (!trace_seq_putmem(s, &(x), sizeof(x))) \ - return 0; \ -} while (0) - -#define SEQ_PUT_HEX_FIELD_RET(s, x) \ -do { \ - BUILD_BUG_ON(sizeof(x) > MAX_MEMHEX_BYTES); \ - if (!trace_seq_putmem_hex(s, &(x), sizeof(x))) \ - return 0; \ -} while (0) - static enum print_line_t print_hex_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; unsigned char newline = '\n'; struct trace_entry *entry; - int S, T; + struct trace_event *event; entry = iter->ent; - if (entry->type == TRACE_CONT) - return TRACE_TYPE_HANDLED; - SEQ_PUT_HEX_FIELD_RET(s, entry->pid); SEQ_PUT_HEX_FIELD_RET(s, iter->cpu); SEQ_PUT_HEX_FIELD_RET(s, iter->ts); - switch (entry->type) { - case TRACE_FN: { - struct ftrace_entry *field; - - trace_assign_type(field, entry); - - SEQ_PUT_HEX_FIELD_RET(s, field->ip); - SEQ_PUT_HEX_FIELD_RET(s, field->parent_ip); - break; - } - case TRACE_CTX: - case TRACE_WAKE: { - struct ctx_switch_entry *field; - - trace_assign_type(field, entry); - - T = task_state_char(field->next_state); - S = entry->type == TRACE_WAKE ? '+' : - task_state_char(field->prev_state); - SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid); - SEQ_PUT_HEX_FIELD_RET(s, field->prev_prio); - SEQ_PUT_HEX_FIELD_RET(s, S); - SEQ_PUT_HEX_FIELD_RET(s, field->next_cpu); - SEQ_PUT_HEX_FIELD_RET(s, field->next_pid); - SEQ_PUT_HEX_FIELD_RET(s, field->next_prio); - SEQ_PUT_HEX_FIELD_RET(s, T); - break; - } - case TRACE_SPECIAL: - case TRACE_USER_STACK: - case TRACE_STACK: { - struct special_entry *field; - - trace_assign_type(field, entry); + event = ftrace_find_event(entry->type); + if (event && event->hex) + event->hex(s, entry, 0); - SEQ_PUT_HEX_FIELD_RET(s, field->arg1); - SEQ_PUT_HEX_FIELD_RET(s, field->arg2); - SEQ_PUT_HEX_FIELD_RET(s, field->arg3); - break; - } - } SEQ_PUT_FIELD_RET(s, newline); return TRACE_TYPE_HANDLED; @@ -2282,9 +1580,6 @@ static enum print_line_t print_printk_msg_only(struct trace_iterator *iter) if (!ret) return TRACE_TYPE_PARTIAL_LINE; - if (entry->flags & TRACE_FLAG_CONT) - trace_seq_print_cont(s, iter); - return TRACE_TYPE_HANDLED; } @@ -2292,53 +1587,19 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct trace_entry *entry; + struct trace_event *event; entry = iter->ent; - if (entry->type == TRACE_CONT) - return TRACE_TYPE_HANDLED; - SEQ_PUT_FIELD_RET(s, entry->pid); SEQ_PUT_FIELD_RET(s, entry->cpu); SEQ_PUT_FIELD_RET(s, iter->ts); - switch (entry->type) { - case TRACE_FN: { - struct ftrace_entry *field; - - trace_assign_type(field, entry); - - SEQ_PUT_FIELD_RET(s, field->ip); - SEQ_PUT_FIELD_RET(s, field->parent_ip); - break; - } - case TRACE_CTX: { - struct ctx_switch_entry *field; - - trace_assign_type(field, entry); + event = ftrace_find_event(entry->type); + if (event && event->binary) + event->binary(s, entry, 0); - SEQ_PUT_FIELD_RET(s, field->prev_pid); - SEQ_PUT_FIELD_RET(s, field->prev_prio); - SEQ_PUT_FIELD_RET(s, field->prev_state); - SEQ_PUT_FIELD_RET(s, field->next_pid); - SEQ_PUT_FIELD_RET(s, field->next_prio); - SEQ_PUT_FIELD_RET(s, field->next_state); - break; - } - case TRACE_SPECIAL: - case TRACE_USER_STACK: - case TRACE_STACK: { - struct special_entry *field; - - trace_assign_type(field, entry); - - SEQ_PUT_FIELD_RET(s, field->arg1); - SEQ_PUT_FIELD_RET(s, field->arg2); - SEQ_PUT_FIELD_RET(s, field->arg3); - break; - } - } - return 1; + return TRACE_TYPE_HANDLED; } static int trace_empty(struct trace_iterator *iter) @@ -3736,7 +2997,7 @@ static struct notifier_block trace_die_notifier = { * it if we decide to change what log level the ftrace dump * should be at. */ -#define KERN_TRACE KERN_INFO +#define KERN_TRACE KERN_EMERG static void trace_printk_seq(struct trace_seq *s) @@ -3770,6 +3031,7 @@ void ftrace_dump(void) dump_ran = 1; /* No turning back! */ + tracing_off(); ftrace_kill(); for_each_tracing_cpu(cpu) { @@ -3877,7 +3139,6 @@ __init static int tracer_alloc_buffers(void) #else current_trace = &nop_trace; #endif - /* All seems OK, enable tracing */ tracing_disabled = 0; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 4d3d381bfd95..b96037d970df 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -9,6 +9,7 @@ #include <linux/mmiotrace.h> #include <linux/ftrace.h> #include <trace/boot.h> +#include <trace/kmemtrace.h> enum trace_type { __TRACE_FIRST_TYPE = 0, @@ -16,7 +17,6 @@ enum trace_type { TRACE_FN, TRACE_CTX, TRACE_WAKE, - TRACE_CONT, TRACE_STACK, TRACE_PRINT, TRACE_SPECIAL, @@ -29,9 +29,11 @@ enum trace_type { TRACE_GRAPH_ENT, TRACE_USER_STACK, TRACE_HW_BRANCHES, + TRACE_KMEM_ALLOC, + TRACE_KMEM_FREE, TRACE_POWER, - __TRACE_LAST_TYPE + __TRACE_LAST_TYPE, }; /* @@ -170,6 +172,24 @@ struct trace_power { struct power_trace state_data; }; +struct kmemtrace_alloc_entry { + struct trace_entry ent; + enum kmemtrace_type_id type_id; + unsigned long call_site; + const void *ptr; + size_t bytes_req; + size_t bytes_alloc; + gfp_t gfp_flags; + int node; +}; + +struct kmemtrace_free_entry { + struct trace_entry ent; + enum kmemtrace_type_id type_id; + unsigned long call_site; + const void *ptr; +}; + /* * trace_flag_type is an enumeration that holds different * states when a trace occurs. These are: @@ -178,7 +198,6 @@ struct trace_power { * NEED_RESCED - reschedule is requested * HARDIRQ - inside an interrupt handler * SOFTIRQ - inside a softirq handler - * CONT - multiple entries hold the trace item */ enum trace_flag_type { TRACE_FLAG_IRQS_OFF = 0x01, @@ -186,7 +205,6 @@ enum trace_flag_type { TRACE_FLAG_NEED_RESCHED = 0x04, TRACE_FLAG_HARDIRQ = 0x08, TRACE_FLAG_SOFTIRQ = 0x10, - TRACE_FLAG_CONT = 0x20, }; #define TRACE_BUF_SIZE 1024 @@ -262,7 +280,6 @@ extern void __ftrace_bad_type(void); do { \ IF_ASSIGN(var, ent, struct ftrace_entry, TRACE_FN); \ IF_ASSIGN(var, ent, struct ctx_switch_entry, 0); \ - IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \ IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK); \ IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\ IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \ @@ -280,6 +297,10 @@ extern void __ftrace_bad_type(void); TRACE_GRAPH_RET); \ IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\ IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \ + IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry, \ + TRACE_KMEM_ALLOC); \ + IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \ + TRACE_KMEM_FREE); \ __ftrace_bad_type(); \ } while (0) @@ -313,6 +334,7 @@ struct tracer_flags { /* Makes more easy to define a tracer opt */ #define TRACER_OPT(s, b) .name = #s, .bit = b + /* * A specific tracer, represented by methods that operate on a trace array: */ @@ -340,6 +362,7 @@ struct tracer { struct tracer *next; int print_max; struct tracer_flags *flags; + struct tracer_stat *stats; }; struct trace_seq { @@ -415,7 +438,6 @@ void trace_function(struct trace_array *tr, void trace_graph_return(struct ftrace_graph_ret *trace); int trace_graph_entry(struct ftrace_graph_ent *trace); -void trace_hw_branch(struct trace_array *tr, u64 from, u64 to); void tracing_start_cmdline_record(void); void tracing_stop_cmdline_record(void); @@ -434,15 +456,12 @@ void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu); void update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu); -extern cycle_t ftrace_now(int cpu); +void __trace_stack(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long flags, + int skip, int pc); -#ifdef CONFIG_FUNCTION_TRACER -void tracing_start_function_trace(void); -void tracing_stop_function_trace(void); -#else -# define tracing_start_function_trace() do { } while (0) -# define tracing_stop_function_trace() do { } while (0) -#endif +extern cycle_t ftrace_now(int cpu); #ifdef CONFIG_CONTEXT_SWITCH_TRACER typedef void @@ -456,10 +475,10 @@ struct tracer_switch_ops { void *private; struct tracer_switch_ops *next; }; - -char *trace_find_cmdline(int pid); #endif /* CONFIG_CONTEXT_SWITCH_TRACER */ +extern char *trace_find_cmdline(int pid); + #ifdef CONFIG_DYNAMIC_FTRACE extern unsigned long ftrace_update_tot_cnt; #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func @@ -488,15 +507,6 @@ extern int trace_selftest_startup_branch(struct tracer *trace, #endif /* CONFIG_FTRACE_STARTUP_TEST */ extern void *head_page(struct trace_array_cpu *data); -extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...); -extern void trace_seq_print_cont(struct trace_seq *s, - struct trace_iterator *iter); - -extern int -seq_print_ip_sym(struct trace_seq *s, unsigned long ip, - unsigned long sym_flags); -extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, - size_t cnt); extern long ns2usecs(cycle_t nsec); extern int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args); diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index 366c8c333e13..0e94b3d091f7 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -11,6 +11,7 @@ #include <linux/kallsyms.h> #include "trace.h" +#include "trace_output.h" static struct trace_array *boot_trace; static bool pre_initcalls_finished; diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 6c00feb3bac7..ca017e0a9a27 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -14,12 +14,17 @@ #include <linux/hash.h> #include <linux/fs.h> #include <asm/local.h> + #include "trace.h" +#include "trace_stat.h" +#include "trace_output.h" #ifdef CONFIG_BRANCH_TRACER +static struct tracer branch_trace; static int branch_tracing_enabled __read_mostly; static DEFINE_MUTEX(branch_tracing_mutex); + static struct trace_array *branch_tracer; static void @@ -142,22 +147,74 @@ static void branch_trace_reset(struct trace_array *tr) stop_branch_trace(tr); } -struct tracer branch_trace __read_mostly = +static int +trace_print_print(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct print_entry *field; + + trace_assign_type(field, entry); + + if (seq_print_ip_sym(s, field->ip, flags)) + goto partial; + + if (trace_seq_printf(s, ": %s", field->buf)) + goto partial; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static int +trace_branch_print(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct trace_branch *field; + + trace_assign_type(field, entry); + + if (trace_seq_printf(s, "[%s] %s:%s:%d\n", + field->correct ? " ok " : " MISS ", + field->func, + field->file, + field->line)) + return TRACE_TYPE_PARTIAL_LINE; + + return 0; +} + + +static struct trace_event trace_branch_event = { + .type = TRACE_BRANCH, + .trace = trace_branch_print, + .latency_trace = trace_branch_print, + .raw = trace_nop_print, + .hex = trace_nop_print, + .binary = trace_nop_print, +}; + +static struct tracer branch_trace __read_mostly = { .name = "branch", .init = branch_trace_init, .reset = branch_trace_reset, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_branch, -#endif +#endif /* CONFIG_FTRACE_SELFTEST */ }; -__init static int init_branch_trace(void) +__init static int init_branch_tracer(void) { + int ret; + + ret = register_ftrace_event(&trace_branch_event); + if (!ret) { + printk(KERN_WARNING "Warning: could not register " + "branch events\n"); + return 1; + } return register_tracer(&branch_trace); } +device_initcall(init_branch_tracer); -device_initcall(init_branch_trace); #else static inline void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect) @@ -183,66 +240,39 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect) } EXPORT_SYMBOL(ftrace_likely_update); -struct ftrace_pointer { - void *start; - void *stop; - int hit; -}; +extern unsigned long __start_annotated_branch_profile[]; +extern unsigned long __stop_annotated_branch_profile[]; -static void * -t_next(struct seq_file *m, void *v, loff_t *pos) +static int annotated_branch_stat_headers(struct seq_file *m) { - const struct ftrace_pointer *f = m->private; - struct ftrace_branch_data *p = v; - - (*pos)++; - - if (v == (void *)1) - return f->start; - - ++p; - - if ((void *)p >= (void *)f->stop) - return NULL; - - return p; + seq_printf(m, " correct incorrect %% "); + seq_printf(m, " Function " + " File Line\n" + " ------- --------- - " + " -------- " + " ---- ----\n"); + return 0; } -static void *t_start(struct seq_file *m, loff_t *pos) +static inline long get_incorrect_percent(struct ftrace_branch_data *p) { - void *t = (void *)1; - loff_t l = 0; - - for (; t && l < *pos; t = t_next(m, t, &l)) - ; + long percent; - return t; -} + if (p->correct) { + percent = p->incorrect * 100; + percent /= p->correct + p->incorrect; + } else + percent = p->incorrect ? 100 : -1; -static void t_stop(struct seq_file *m, void *p) -{ + return percent; } -static int t_show(struct seq_file *m, void *v) +static int branch_stat_show(struct seq_file *m, void *v) { - const struct ftrace_pointer *fp = m->private; struct ftrace_branch_data *p = v; const char *f; long percent; - if (v == (void *)1) { - if (fp->hit) - seq_printf(m, " miss hit %% "); - else - seq_printf(m, " correct incorrect %% "); - seq_printf(m, " Function " - " File Line\n" - " ------- --------- - " - " -------- " - " ---- ----\n"); - return 0; - } - /* Only print the file, not the path */ f = p->file + strlen(p->file); while (f >= p->file && *f != '/') @@ -252,11 +282,7 @@ static int t_show(struct seq_file *m, void *v) /* * The miss is overlayed on correct, and hit on incorrect. */ - if (p->correct) { - percent = p->incorrect * 100; - percent /= p->correct + p->incorrect; - } else - percent = p->incorrect ? 100 : -1; + percent = get_incorrect_percent(p); seq_printf(m, "%8lu %8lu ", p->correct, p->incorrect); if (percent < 0) @@ -267,76 +293,118 @@ static int t_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations tracing_likely_seq_ops = { - .start = t_start, - .next = t_next, - .stop = t_stop, - .show = t_show, +static void *annotated_branch_stat_start(void) +{ + return __start_annotated_branch_profile; +} + +static void * +annotated_branch_stat_next(void *v, int idx) +{ + struct ftrace_branch_data *p = v; + + ++p; + + if ((void *)p >= (void *)__stop_annotated_branch_profile) + return NULL; + + return p; +} + +static int annotated_branch_stat_cmp(void *p1, void *p2) +{ + struct ftrace_branch_data *a = p1; + struct ftrace_branch_data *b = p2; + + long percent_a, percent_b; + + percent_a = get_incorrect_percent(a); + percent_b = get_incorrect_percent(b); + + if (percent_a < percent_b) + return -1; + if (percent_a > percent_b) + return 1; + else + return 0; +} + +static struct tracer_stat annotated_branch_stats = { + .name = "branch_annotated", + .stat_start = annotated_branch_stat_start, + .stat_next = annotated_branch_stat_next, + .stat_cmp = annotated_branch_stat_cmp, + .stat_headers = annotated_branch_stat_headers, + .stat_show = branch_stat_show }; -static int tracing_branch_open(struct inode *inode, struct file *file) +__init static int init_annotated_branch_stats(void) { int ret; - ret = seq_open(file, &tracing_likely_seq_ops); + ret = register_stat_tracer(&annotated_branch_stats); if (!ret) { - struct seq_file *m = file->private_data; - m->private = (void *)inode->i_private; + printk(KERN_WARNING "Warning: could not register " + "annotated branches stats\n"); + return 1; } - - return ret; + return 0; } - -static const struct file_operations tracing_branch_fops = { - .open = tracing_branch_open, - .read = seq_read, - .llseek = seq_lseek, -}; +fs_initcall(init_annotated_branch_stats); #ifdef CONFIG_PROFILE_ALL_BRANCHES + extern unsigned long __start_branch_profile[]; extern unsigned long __stop_branch_profile[]; -static const struct ftrace_pointer ftrace_branch_pos = { - .start = __start_branch_profile, - .stop = __stop_branch_profile, - .hit = 1, -}; +static int all_branch_stat_headers(struct seq_file *m) +{ + seq_printf(m, " miss hit %% "); + seq_printf(m, " Function " + " File Line\n" + " ------- --------- - " + " -------- " + " ---- ----\n"); + return 0; +} -#endif /* CONFIG_PROFILE_ALL_BRANCHES */ +static void *all_branch_stat_start(void) +{ + return __start_branch_profile; +} -extern unsigned long __start_annotated_branch_profile[]; -extern unsigned long __stop_annotated_branch_profile[]; +static void * +all_branch_stat_next(void *v, int idx) +{ + struct ftrace_branch_data *p = v; -static const struct ftrace_pointer ftrace_annotated_branch_pos = { - .start = __start_annotated_branch_profile, - .stop = __stop_annotated_branch_profile, -}; + ++p; -static __init int ftrace_branch_init(void) -{ - struct dentry *d_tracer; - struct dentry *entry; + if ((void *)p >= (void *)__stop_branch_profile) + return NULL; - d_tracer = tracing_init_dentry(); + return p; +} - entry = debugfs_create_file("profile_annotated_branch", 0444, d_tracer, - (void *)&ftrace_annotated_branch_pos, - &tracing_branch_fops); - if (!entry) - pr_warning("Could not create debugfs " - "'profile_annotatet_branch' entry\n"); +static struct tracer_stat all_branch_stats = { + .name = "branch_all", + .stat_start = all_branch_stat_start, + .stat_next = all_branch_stat_next, + .stat_headers = all_branch_stat_headers, + .stat_show = branch_stat_show +}; -#ifdef CONFIG_PROFILE_ALL_BRANCHES - entry = debugfs_create_file("profile_branch", 0444, d_tracer, - (void *)&ftrace_branch_pos, - &tracing_branch_fops); - if (!entry) - pr_warning("Could not create debugfs" - " 'profile_branch' entry\n"); -#endif +__init static int all_annotated_branch_stats(void) +{ + int ret; + ret = register_stat_tracer(&all_branch_stats); + if (!ret) { + printk(KERN_WARNING "Warning: could not register " + "all branches stats\n"); + return 1; + } return 0; } - -device_initcall(ftrace_branch_init); +fs_initcall(all_annotated_branch_stats); +#endif /* CONFIG_PROFILE_ALL_BRANCHES */ diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 9236d7e25a16..b3a320f8aba7 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -16,8 +16,17 @@ #include "trace.h" +/* function tracing enabled */ +static int ftrace_function_enabled; + +static struct trace_array *func_trace; + +static void tracing_start_function_trace(void); +static void tracing_stop_function_trace(void); + static void start_function_trace(struct trace_array *tr) { + func_trace = tr; tr->cpu = get_cpu(); tracing_reset_online_cpus(tr); put_cpu(); @@ -48,14 +57,188 @@ static void function_trace_start(struct trace_array *tr) tracing_reset_online_cpus(tr); } +static void +function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) +{ + struct trace_array *tr = func_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu, resched; + int pc; + + if (unlikely(!ftrace_function_enabled)) + return; + + pc = preempt_count(); + resched = ftrace_preempt_disable(); + local_save_flags(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) + trace_function(tr, data, ip, parent_ip, flags, pc); + + atomic_dec(&data->disabled); + ftrace_preempt_enable(resched); +} + +static void +function_trace_call(unsigned long ip, unsigned long parent_ip) +{ + struct trace_array *tr = func_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + int pc; + + if (unlikely(!ftrace_function_enabled)) + return; + + /* + * Need to use raw, since this must be called before the + * recursive protection is performed. + */ + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) { + pc = preempt_count(); + trace_function(tr, data, ip, parent_ip, flags, pc); + } + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +static void +function_stack_trace_call(unsigned long ip, unsigned long parent_ip) +{ + struct trace_array *tr = func_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + int pc; + + if (unlikely(!ftrace_function_enabled)) + return; + + /* + * Need to use raw, since this must be called before the + * recursive protection is performed. + */ + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) { + pc = preempt_count(); + trace_function(tr, data, ip, parent_ip, flags, pc); + /* + * skip over 5 funcs: + * __ftrace_trace_stack, + * __trace_stack, + * function_stack_trace_call + * ftrace_list_func + * ftrace_call + */ + __trace_stack(tr, data, flags, 5, pc); + } + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + + +static struct ftrace_ops trace_ops __read_mostly = +{ + .func = function_trace_call, +}; + +static struct ftrace_ops trace_stack_ops __read_mostly = +{ + .func = function_stack_trace_call, +}; + +/* Our two options */ +enum { + TRACE_FUNC_OPT_STACK = 0x1, +}; + +static struct tracer_opt func_opts[] = { +#ifdef CONFIG_STACKTRACE + { TRACER_OPT(func_stack_trace, TRACE_FUNC_OPT_STACK) }, +#endif + { } /* Always set a last empty entry */ +}; + +static struct tracer_flags func_flags = { + .val = 0, /* By default: all flags disabled */ + .opts = func_opts +}; + +static void tracing_start_function_trace(void) +{ + ftrace_function_enabled = 0; + + if (trace_flags & TRACE_ITER_PREEMPTONLY) + trace_ops.func = function_trace_call_preempt_only; + else + trace_ops.func = function_trace_call; + + if (func_flags.val & TRACE_FUNC_OPT_STACK) + register_ftrace_function(&trace_stack_ops); + else + register_ftrace_function(&trace_ops); + + ftrace_function_enabled = 1; +} + +static void tracing_stop_function_trace(void) +{ + ftrace_function_enabled = 0; + /* OK if they are not registered */ + unregister_ftrace_function(&trace_stack_ops); + unregister_ftrace_function(&trace_ops); +} + +static int func_set_flag(u32 old_flags, u32 bit, int set) +{ + if (bit == TRACE_FUNC_OPT_STACK) { + /* do nothing if already set */ + if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK)) + return 0; + + if (set) { + unregister_ftrace_function(&trace_ops); + register_ftrace_function(&trace_stack_ops); + } else { + unregister_ftrace_function(&trace_stack_ops); + register_ftrace_function(&trace_ops); + } + + return 0; + } + + return -EINVAL; +} + static struct tracer function_trace __read_mostly = { - .name = "function", - .init = function_trace_init, - .reset = function_trace_reset, - .start = function_trace_start, + .name = "function", + .init = function_trace_init, + .reset = function_trace_reset, + .start = function_trace_start, + .flags = &func_flags, + .set_flag = func_set_flag, #ifdef CONFIG_FTRACE_SELFTEST - .selftest = trace_selftest_startup_function, + .selftest = trace_selftest_startup_function, #endif }; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 930c08e5b38e..3c545984816f 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -12,6 +12,7 @@ #include <linux/fs.h> #include "trace.h" +#include "trace_output.h" #define TRACE_GRAPH_INDENT 2 @@ -589,8 +590,11 @@ print_graph_comment(struct print_entry *trace, struct trace_seq *s, if (!ret) return TRACE_TYPE_PARTIAL_LINE; - if (ent->flags & TRACE_FLAG_CONT) - trace_seq_print_cont(s, iter); + /* Strip ending newline */ + if (s->buffer[s->len - 1] == '\n') { + s->buffer[s->len - 1] = '\0'; + s->len--; + } ret = trace_seq_printf(s, " */\n"); if (!ret) diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c index 649df22d435f..fff3545fc866 100644 --- a/kernel/trace/trace_hw_branches.c +++ b/kernel/trace/trace_hw_branches.c @@ -1,7 +1,8 @@ /* * h/w branch tracer for x86 based on bts * - * Copyright (C) 2008 Markus Metzger <markus.t.metzger@gmail.com> + * Copyright (C) 2008-2009 Intel Corporation. + * Markus Metzger <markus.t.metzger@gmail.com>, 2008-2009 * */ @@ -10,21 +11,44 @@ #include <linux/debugfs.h> #include <linux/ftrace.h> #include <linux/kallsyms.h> +#include <linux/mutex.h> +#include <linux/cpu.h> +#include <linux/smp.h> #include <asm/ds.h> #include "trace.h" +#include "trace_output.h" #define SIZEOF_BTS (1 << 13) +/* The tracer mutex protects the below per-cpu tracer array. + It needs to be held to: + - start tracing on all cpus + - stop tracing on all cpus + - start tracing on a single hotplug cpu + - stop tracing on a single hotplug cpu + - read the trace from all cpus + - read the trace from a single cpu +*/ +static DEFINE_MUTEX(bts_tracer_mutex); static DEFINE_PER_CPU(struct bts_tracer *, tracer); static DEFINE_PER_CPU(unsigned char[SIZEOF_BTS], buffer); #define this_tracer per_cpu(tracer, smp_processor_id()) #define this_buffer per_cpu(buffer, smp_processor_id()) +static int __read_mostly trace_hw_branches_enabled; +static struct trace_array *hw_branch_trace __read_mostly; + +/* + * Start tracing on the current cpu. + * The argument is ignored. + * + * pre: bts_tracer_mutex must be locked. + */ static void bts_trace_start_cpu(void *arg) { if (this_tracer) @@ -42,14 +66,20 @@ static void bts_trace_start_cpu(void *arg) static void bts_trace_start(struct trace_array *tr) { - int cpu; + mutex_lock(&bts_tracer_mutex); - tracing_reset_online_cpus(tr); + on_each_cpu(bts_trace_start_cpu, NULL, 1); + trace_hw_branches_enabled = 1; - for_each_cpu(cpu, cpu_possible_mask) - smp_call_function_single(cpu, bts_trace_start_cpu, NULL, 1); + mutex_unlock(&bts_tracer_mutex); } +/* + * Start tracing on the current cpu. + * The argument is ignored. + * + * pre: bts_tracer_mutex must be locked. + */ static void bts_trace_stop_cpu(void *arg) { if (this_tracer) { @@ -60,26 +90,63 @@ static void bts_trace_stop_cpu(void *arg) static void bts_trace_stop(struct trace_array *tr) { - int cpu; + mutex_lock(&bts_tracer_mutex); + + trace_hw_branches_enabled = 0; + on_each_cpu(bts_trace_stop_cpu, NULL, 1); - for_each_cpu(cpu, cpu_possible_mask) + mutex_unlock(&bts_tracer_mutex); +} + +static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + + mutex_lock(&bts_tracer_mutex); + + if (!trace_hw_branches_enabled) + goto out; + + switch (action) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + smp_call_function_single(cpu, bts_trace_start_cpu, NULL, 1); + break; + case CPU_DOWN_PREPARE: smp_call_function_single(cpu, bts_trace_stop_cpu, NULL, 1); + break; + } + + out: + mutex_unlock(&bts_tracer_mutex); + return NOTIFY_DONE; } +static struct notifier_block bts_hotcpu_notifier __cpuinitdata = { + .notifier_call = bts_hotcpu_handler +}; + static int bts_trace_init(struct trace_array *tr) { + hw_branch_trace = tr; + + register_hotcpu_notifier(&bts_hotcpu_notifier); tracing_reset_online_cpus(tr); bts_trace_start(tr); return 0; } +static void bts_trace_reset(struct trace_array *tr) +{ + bts_trace_stop(tr); + unregister_hotcpu_notifier(&bts_hotcpu_notifier); +} + static void bts_trace_print_header(struct seq_file *m) { - seq_puts(m, - "# CPU# FROM TO FUNCTION\n"); - seq_puts(m, - "# | | | |\n"); + seq_puts(m, "# CPU# TO <- FROM\n"); } static enum print_line_t bts_trace_print_line(struct trace_iterator *iter) @@ -87,15 +154,15 @@ static enum print_line_t bts_trace_print_line(struct trace_iterator *iter) struct trace_entry *entry = iter->ent; struct trace_seq *seq = &iter->seq; struct hw_branch_entry *it; + unsigned long symflags = TRACE_ITER_SYM_OFFSET; trace_assign_type(it, entry); if (entry->type == TRACE_HW_BRANCHES) { if (trace_seq_printf(seq, "%4d ", entry->cpu) && - trace_seq_printf(seq, "0x%016llx -> 0x%016llx ", - it->from, it->to) && - (!it->from || - seq_print_ip_sym(seq, it->from, /* sym_flags = */ 0)) && + seq_print_ip_sym(seq, it->to, symflags) && + trace_seq_printf(seq, "\t <- ") && + seq_print_ip_sym(seq, it->from, symflags) && trace_seq_printf(seq, "\n")) return TRACE_TYPE_HANDLED; return TRACE_TYPE_PARTIAL_LINE;; @@ -103,26 +170,42 @@ static enum print_line_t bts_trace_print_line(struct trace_iterator *iter) return TRACE_TYPE_UNHANDLED; } -void trace_hw_branch(struct trace_array *tr, u64 from, u64 to) +void trace_hw_branch(u64 from, u64 to) { + struct trace_array *tr = hw_branch_trace; struct ring_buffer_event *event; struct hw_branch_entry *entry; - unsigned long irq; + unsigned long irq1, irq2; + int cpu; - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), &irq); - if (!event) + if (unlikely(!tr)) return; + + if (unlikely(!trace_hw_branches_enabled)) + return; + + local_irq_save(irq1); + cpu = raw_smp_processor_id(); + if (atomic_inc_return(&tr->data[cpu]->disabled) != 1) + goto out; + + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), &irq2); + if (!event) + goto out; entry = ring_buffer_event_data(event); tracing_generic_entry_update(&entry->ent, 0, from); entry->ent.type = TRACE_HW_BRANCHES; - entry->ent.cpu = smp_processor_id(); + entry->ent.cpu = cpu; entry->from = from; entry->to = to; - ring_buffer_unlock_commit(tr->buffer, event, irq); + ring_buffer_unlock_commit(tr->buffer, event, irq2); + + out: + atomic_dec(&tr->data[cpu]->disabled); + local_irq_restore(irq1); } -static void trace_bts_at(struct trace_array *tr, - const struct bts_trace *trace, void *at) +static void trace_bts_at(const struct bts_trace *trace, void *at) { struct bts_struct bts; int err = 0; @@ -137,18 +220,29 @@ static void trace_bts_at(struct trace_array *tr, switch (bts.qualifier) { case BTS_BRANCH: - trace_hw_branch(tr, bts.variant.lbr.from, bts.variant.lbr.to); + trace_hw_branch(bts.variant.lbr.from, bts.variant.lbr.to); break; } } +/* + * Collect the trace on the current cpu and write it into the ftrace buffer. + * + * pre: bts_tracer_mutex must be locked + */ static void trace_bts_cpu(void *arg) { struct trace_array *tr = (struct trace_array *) arg; const struct bts_trace *trace; unsigned char *at; - if (!this_tracer) + if (unlikely(!tr)) + return; + + if (unlikely(atomic_read(&tr->data[raw_smp_processor_id()]->disabled))) + return; + + if (unlikely(!this_tracer)) return; ds_suspend_bts(this_tracer); @@ -158,11 +252,11 @@ static void trace_bts_cpu(void *arg) for (at = trace->ds.top; (void *)at < trace->ds.end; at += trace->ds.size) - trace_bts_at(tr, trace, at); + trace_bts_at(trace, at); for (at = trace->ds.begin; (void *)at < trace->ds.top; at += trace->ds.size) - trace_bts_at(tr, trace, at); + trace_bts_at(trace, at); out: ds_resume_bts(this_tracer); @@ -170,22 +264,38 @@ out: static void trace_bts_prepare(struct trace_iterator *iter) { - int cpu; + mutex_lock(&bts_tracer_mutex); + + on_each_cpu(trace_bts_cpu, iter->tr, 1); + + mutex_unlock(&bts_tracer_mutex); +} + +static void trace_bts_close(struct trace_iterator *iter) +{ + tracing_reset_online_cpus(iter->tr); +} + +void trace_hw_branch_oops(void) +{ + mutex_lock(&bts_tracer_mutex); + + trace_bts_cpu(hw_branch_trace); - for_each_cpu(cpu, cpu_possible_mask) - smp_call_function_single(cpu, trace_bts_cpu, iter->tr, 1); + mutex_unlock(&bts_tracer_mutex); } struct tracer bts_tracer __read_mostly = { .name = "hw-branch-tracer", .init = bts_trace_init, - .reset = bts_trace_stop, + .reset = bts_trace_reset, .print_header = bts_trace_print_header, .print_line = bts_trace_print_line, .start = bts_trace_start, .stop = bts_trace_stop, - .open = trace_bts_prepare + .open = trace_bts_prepare, + .close = trace_bts_close }; __init static int init_bts_trace(void) diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 7c2e326bbc8b..62a78d943534 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -380,6 +380,7 @@ static void stop_irqsoff_tracer(struct trace_array *tr) static void __irqsoff_tracer_init(struct trace_array *tr) { + tracing_max_latency = 0; irqsoff_trace = tr; /* make sure that the tracer is visible */ smp_wmb(); diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index fffcb069f1dc..ec78e244242e 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -9,8 +9,10 @@ #include <linux/kernel.h> #include <linux/mmiotrace.h> #include <linux/pci.h> +#include <asm/atomic.h> #include "trace.h" +#include "trace_output.h" struct header_iter { struct pci_dev *dev; @@ -19,6 +21,7 @@ struct header_iter { static struct trace_array *mmio_trace_array; static bool overrun_detected; static unsigned long prev_overruns; +static atomic_t dropped_count; static void mmio_reset_data(struct trace_array *tr) { @@ -121,11 +124,11 @@ static void mmio_close(struct trace_iterator *iter) static unsigned long count_overruns(struct trace_iterator *iter) { - unsigned long cnt = 0; + unsigned long cnt = atomic_xchg(&dropped_count, 0); unsigned long over = ring_buffer_overruns(iter->tr->buffer); if (over > prev_overruns) - cnt = over - prev_overruns; + cnt += over - prev_overruns; prev_overruns = over; return cnt; } @@ -181,21 +184,22 @@ static enum print_line_t mmio_print_rw(struct trace_iterator *iter) switch (rw->opcode) { case MMIO_READ: ret = trace_seq_printf(s, - "R %d %lu.%06lu %d 0x%llx 0x%lx 0x%lx %d\n", + "R %d %u.%06lu %d 0x%llx 0x%lx 0x%lx %d\n", rw->width, secs, usec_rem, rw->map_id, (unsigned long long)rw->phys, rw->value, rw->pc, 0); break; case MMIO_WRITE: ret = trace_seq_printf(s, - "W %d %lu.%06lu %d 0x%llx 0x%lx 0x%lx %d\n", + "W %d %u.%06lu %d 0x%llx 0x%lx 0x%lx %d\n", rw->width, secs, usec_rem, rw->map_id, (unsigned long long)rw->phys, rw->value, rw->pc, 0); break; case MMIO_UNKNOWN_OP: ret = trace_seq_printf(s, - "UNKNOWN %lu.%06lu %d 0x%llx %02x,%02x,%02x 0x%lx %d\n", + "UNKNOWN %u.%06lu %d 0x%llx %02lx,%02lx," + "%02lx 0x%lx %d\n", secs, usec_rem, rw->map_id, (unsigned long long)rw->phys, (rw->value >> 16) & 0xff, (rw->value >> 8) & 0xff, @@ -227,14 +231,14 @@ static enum print_line_t mmio_print_map(struct trace_iterator *iter) switch (m->opcode) { case MMIO_PROBE: ret = trace_seq_printf(s, - "MAP %lu.%06lu %d 0x%llx 0x%lx 0x%lx 0x%lx %d\n", + "MAP %u.%06lu %d 0x%llx 0x%lx 0x%lx 0x%lx %d\n", secs, usec_rem, m->map_id, (unsigned long long)m->phys, m->virt, m->len, 0UL, 0); break; case MMIO_UNPROBE: ret = trace_seq_printf(s, - "UNMAP %lu.%06lu %d 0x%lx %d\n", + "UNMAP %u.%06lu %d 0x%lx %d\n", secs, usec_rem, m->map_id, 0UL, 0); break; default: @@ -258,13 +262,10 @@ static enum print_line_t mmio_print_mark(struct trace_iterator *iter) int ret; /* The trailing newline must be in the message. */ - ret = trace_seq_printf(s, "MARK %lu.%06lu %s", secs, usec_rem, msg); + ret = trace_seq_printf(s, "MARK %u.%06lu %s", secs, usec_rem, msg); if (!ret) return TRACE_TYPE_PARTIAL_LINE; - if (entry->flags & TRACE_FLAG_CONT) - trace_seq_print_cont(s, iter); - return TRACE_TYPE_HANDLED; } @@ -310,8 +311,10 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), &irq_flags); - if (!event) + if (!event) { + atomic_inc(&dropped_count); return; + } entry = ring_buffer_event_data(event); tracing_generic_entry_update(&entry->ent, 0, preempt_count()); entry->ent.type = TRACE_MMIO_RW; @@ -338,8 +341,10 @@ static void __trace_mmiotrace_map(struct trace_array *tr, event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), &irq_flags); - if (!event) + if (!event) { + atomic_inc(&dropped_count); return; + } entry = ring_buffer_event_data(event); tracing_generic_entry_update(&entry->ent, 0, preempt_count()); entry->ent.type = TRACE_MMIO_MAP; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c new file mode 100644 index 000000000000..1a4e144a9f8f --- /dev/null +++ b/kernel/trace/trace_output.c @@ -0,0 +1,829 @@ +/* + * trace_output.c + * + * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ + +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/ftrace.h> + +#include "trace_output.h" + +/* must be a power of 2 */ +#define EVENT_HASHSIZE 128 + +static DEFINE_MUTEX(trace_event_mutex); +static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly; + +static int next_event_type = __TRACE_LAST_TYPE + 1; + +/** + * trace_seq_printf - sequence printing of trace information + * @s: trace sequence descriptor + * @fmt: printf format string + * + * The tracer may use either sequence operations or its own + * copy to user routines. To simplify formating of a trace + * trace_seq_printf is used to store strings into a special + * buffer (@s). Then the output may be either used by + * the sequencer or pulled into another buffer. + */ +int +trace_seq_printf(struct trace_seq *s, const char *fmt, ...) +{ + int len = (PAGE_SIZE - 1) - s->len; + va_list ap; + int ret; + + if (!len) + return 0; + + va_start(ap, fmt); + ret = vsnprintf(s->buffer + s->len, len, fmt, ap); + va_end(ap); + + /* If we can't write it all, don't bother writing anything */ + if (ret >= len) + return 0; + + s->len += ret; + + return len; +} + +/** + * trace_seq_puts - trace sequence printing of simple string + * @s: trace sequence descriptor + * @str: simple string to record + * + * The tracer may use either the sequence operations or its own + * copy to user routines. This function records a simple string + * into a special buffer (@s) for later retrieval by a sequencer + * or other mechanism. + */ +int trace_seq_puts(struct trace_seq *s, const char *str) +{ + int len = strlen(str); + + if (len > ((PAGE_SIZE - 1) - s->len)) + return 0; + + memcpy(s->buffer + s->len, str, len); + s->len += len; + + return len; +} + +int trace_seq_putc(struct trace_seq *s, unsigned char c) +{ + if (s->len >= (PAGE_SIZE - 1)) + return 0; + + s->buffer[s->len++] = c; + + return 1; +} + +int trace_seq_putmem(struct trace_seq *s, void *mem, size_t len) +{ + if (len > ((PAGE_SIZE - 1) - s->len)) + return 0; + + memcpy(s->buffer + s->len, mem, len); + s->len += len; + + return len; +} + +int trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len) +{ + unsigned char hex[HEX_CHARS]; + unsigned char *data = mem; + int i, j; + +#ifdef __BIG_ENDIAN + for (i = 0, j = 0; i < len; i++) { +#else + for (i = len-1, j = 0; i >= 0; i--) { +#endif + hex[j++] = hex_asc_hi(data[i]); + hex[j++] = hex_asc_lo(data[i]); + } + hex[j++] = ' '; + + return trace_seq_putmem(s, hex, j); +} + +int trace_seq_path(struct trace_seq *s, struct path *path) +{ + unsigned char *p; + + if (s->len >= (PAGE_SIZE - 1)) + return 0; + p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len); + if (!IS_ERR(p)) { + p = mangle_path(s->buffer + s->len, p, "\n"); + if (p) { + s->len = p - s->buffer; + return 1; + } + } else { + s->buffer[s->len++] = '?'; + return 1; + } + + return 0; +} + +#ifdef CONFIG_KRETPROBES +static inline const char *kretprobed(const char *name) +{ + static const char tramp_name[] = "kretprobe_trampoline"; + int size = sizeof(tramp_name); + + if (strncmp(tramp_name, name, size) == 0) + return "[unknown/kretprobe'd]"; + return name; +} +#else +static inline const char *kretprobed(const char *name) +{ + return name; +} +#endif /* CONFIG_KRETPROBES */ + +static int +seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address) +{ +#ifdef CONFIG_KALLSYMS + char str[KSYM_SYMBOL_LEN]; + const char *name; + + kallsyms_lookup(address, NULL, NULL, NULL, str); + + name = kretprobed(str); + + return trace_seq_printf(s, fmt, name); +#endif + return 1; +} + +static int +seq_print_sym_offset(struct trace_seq *s, const char *fmt, + unsigned long address) +{ +#ifdef CONFIG_KALLSYMS + char str[KSYM_SYMBOL_LEN]; + const char *name; + + sprint_symbol(str, address); + name = kretprobed(str); + + return trace_seq_printf(s, fmt, name); +#endif + return 1; +} + +#ifndef CONFIG_64BIT +# define IP_FMT "%08lx" +#else +# define IP_FMT "%016lx" +#endif + +int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm, + unsigned long ip, unsigned long sym_flags) +{ + struct file *file = NULL; + unsigned long vmstart = 0; + int ret = 1; + + if (mm) { + const struct vm_area_struct *vma; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, ip); + if (vma) { + file = vma->vm_file; + vmstart = vma->vm_start; + } + if (file) { + ret = trace_seq_path(s, &file->f_path); + if (ret) + ret = trace_seq_printf(s, "[+0x%lx]", + ip - vmstart); + } + up_read(&mm->mmap_sem); + } + if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file)) + ret = trace_seq_printf(s, " <" IP_FMT ">", ip); + return ret; +} + +int +seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s, + unsigned long sym_flags) +{ + struct mm_struct *mm = NULL; + int ret = 1; + unsigned int i; + + if (trace_flags & TRACE_ITER_SYM_USEROBJ) { + struct task_struct *task; + /* + * we do the lookup on the thread group leader, + * since individual threads might have already quit! + */ + rcu_read_lock(); + task = find_task_by_vpid(entry->ent.tgid); + if (task) + mm = get_task_mm(task); + rcu_read_unlock(); + } + + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { + unsigned long ip = entry->caller[i]; + + if (ip == ULONG_MAX || !ret) + break; + if (i && ret) + ret = trace_seq_puts(s, " <- "); + if (!ip) { + if (ret) + ret = trace_seq_puts(s, "??"); + continue; + } + if (!ret) + break; + if (ret) + ret = seq_print_user_ip(s, mm, ip, sym_flags); + } + + if (mm) + mmput(mm); + return ret; +} + +int +seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) +{ + int ret; + + if (!ip) + return trace_seq_printf(s, "0"); + + if (sym_flags & TRACE_ITER_SYM_OFFSET) + ret = seq_print_sym_offset(s, "%s", ip); + else + ret = seq_print_sym_short(s, "%s", ip); + + if (!ret) + return 0; + + if (sym_flags & TRACE_ITER_SYM_ADDR) + ret = trace_seq_printf(s, " <" IP_FMT ">", ip); + return ret; +} + +static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; + +static int task_state_char(unsigned long state) +{ + int bit = state ? __ffs(state) + 1 : 0; + + return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; +} + +/** + * ftrace_find_event - find a registered event + * @type: the type of event to look for + * + * Returns an event of type @type otherwise NULL + */ +struct trace_event *ftrace_find_event(int type) +{ + struct trace_event *event; + struct hlist_node *n; + unsigned key; + + key = type & (EVENT_HASHSIZE - 1); + + hlist_for_each_entry_rcu(event, n, &event_hash[key], node) { + if (event->type == type) + return event; + } + + return NULL; +} + +/** + * register_ftrace_event - register output for an event type + * @event: the event type to register + * + * Event types are stored in a hash and this hash is used to + * find a way to print an event. If the @event->type is set + * then it will use that type, otherwise it will assign a + * type to use. + * + * If you assign your own type, please make sure it is added + * to the trace_type enum in trace.h, to avoid collisions + * with the dynamic types. + * + * Returns the event type number or zero on error. + */ +int register_ftrace_event(struct trace_event *event) +{ + unsigned key; + int ret = 0; + + mutex_lock(&trace_event_mutex); + + if (!event->type) + event->type = next_event_type++; + else if (event->type > __TRACE_LAST_TYPE) { + printk(KERN_WARNING "Need to add type to trace.h\n"); + WARN_ON(1); + } + + if (ftrace_find_event(event->type)) + goto out; + + key = event->type & (EVENT_HASHSIZE - 1); + + hlist_add_head_rcu(&event->node, &event_hash[key]); + + ret = event->type; + out: + mutex_unlock(&trace_event_mutex); + + return ret; +} + +/** + * unregister_ftrace_event - remove a no longer used event + * @event: the event to remove + */ +int unregister_ftrace_event(struct trace_event *event) +{ + mutex_lock(&trace_event_mutex); + hlist_del(&event->node); + mutex_unlock(&trace_event_mutex); + + return 0; +} + +/* + * Standard events + */ + +int +trace_nop_print(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + return 0; +} + +/* TRACE_FN */ +static int +trace_fn_latency(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct ftrace_entry *field; + + trace_assign_type(field, entry); + + if (!seq_print_ip_sym(s, field->ip, flags)) + goto partial; + if (!trace_seq_puts(s, " (")) + goto partial; + if (!seq_print_ip_sym(s, field->parent_ip, flags)) + goto partial; + if (!trace_seq_puts(s, ")\n")) + goto partial; + + return 0; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static int +trace_fn_trace(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct ftrace_entry *field; + + trace_assign_type(field, entry); + + if (!seq_print_ip_sym(s, field->ip, flags)) + goto partial; + + if ((flags & TRACE_ITER_PRINT_PARENT) && field->parent_ip) { + if (!trace_seq_printf(s, " <-")) + goto partial; + if (!seq_print_ip_sym(s, + field->parent_ip, + flags)) + goto partial; + } + if (!trace_seq_printf(s, "\n")) + goto partial; + + return 0; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static int +trace_fn_raw(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct ftrace_entry *field; + + trace_assign_type(field, entry); + + if (!trace_seq_printf(s, "%lx %lx\n", + field->ip, + field->parent_ip)) + return TRACE_TYPE_PARTIAL_LINE; + + return 0; +} + +static int +trace_fn_hex(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct ftrace_entry *field; + + trace_assign_type(field, entry); + + SEQ_PUT_HEX_FIELD_RET(s, field->ip); + SEQ_PUT_HEX_FIELD_RET(s, field->parent_ip); + + return 0; +} + +static int +trace_fn_bin(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct ftrace_entry *field; + + trace_assign_type(field, entry); + + SEQ_PUT_FIELD_RET(s, field->ip); + SEQ_PUT_FIELD_RET(s, field->parent_ip); + + return 0; +} + +static struct trace_event trace_fn_event = { + .type = TRACE_FN, + .trace = trace_fn_trace, + .latency_trace = trace_fn_latency, + .raw = trace_fn_raw, + .hex = trace_fn_hex, + .binary = trace_fn_bin, +}; + +/* TRACE_CTX an TRACE_WAKE */ +static int +trace_ctxwake_print(struct trace_seq *s, struct trace_entry *entry, int flags, + char *delim) +{ + struct ctx_switch_entry *field; + char *comm; + int S, T; + + trace_assign_type(field, entry); + + T = task_state_char(field->next_state); + S = task_state_char(field->prev_state); + comm = trace_find_cmdline(field->next_pid); + if (!trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", + field->prev_pid, + field->prev_prio, + S, delim, + field->next_cpu, + field->next_pid, + field->next_prio, + T, comm)) + return TRACE_TYPE_PARTIAL_LINE; + + return 0; +} + +static int +trace_ctx_print(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + return trace_ctxwake_print(s, entry, flags, "==>"); +} + +static int +trace_wake_print(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + return trace_ctxwake_print(s, entry, flags, " +"); +} + +static int +trace_ctxwake_raw(struct trace_seq *s, struct trace_entry *entry, int flags, + char S) +{ + struct ctx_switch_entry *field; + int T; + + trace_assign_type(field, entry); + + if (!S) + task_state_char(field->prev_state); + T = task_state_char(field->next_state); + if (!trace_seq_printf(s, "%d %d %c %d %d %d %c\n", + field->prev_pid, + field->prev_prio, + S, + field->next_cpu, + field->next_pid, + field->next_prio, + T)) + return TRACE_TYPE_PARTIAL_LINE; + + return 0; +} + +static int +trace_ctx_raw(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + return trace_ctxwake_raw(s, entry, flags, 0); +} + +static int +trace_wake_raw(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + return trace_ctxwake_raw(s, entry, flags, '+'); +} + + +static int +trace_ctxwake_hex(struct trace_seq *s, struct trace_entry *entry, int flags, + char S) +{ + struct ctx_switch_entry *field; + int T; + + trace_assign_type(field, entry); + + if (!S) + task_state_char(field->prev_state); + T = task_state_char(field->next_state); + + SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid); + SEQ_PUT_HEX_FIELD_RET(s, field->prev_prio); + SEQ_PUT_HEX_FIELD_RET(s, S); + SEQ_PUT_HEX_FIELD_RET(s, field->next_cpu); + SEQ_PUT_HEX_FIELD_RET(s, field->next_pid); + SEQ_PUT_HEX_FIELD_RET(s, field->next_prio); + SEQ_PUT_HEX_FIELD_RET(s, T); + + return 0; +} + +static int +trace_ctx_hex(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + return trace_ctxwake_hex(s, entry, flags, 0); +} + +static int +trace_wake_hex(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + return trace_ctxwake_hex(s, entry, flags, '+'); +} + +static int +trace_ctxwake_bin(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct ctx_switch_entry *field; + + trace_assign_type(field, entry); + + SEQ_PUT_FIELD_RET(s, field->prev_pid); + SEQ_PUT_FIELD_RET(s, field->prev_prio); + SEQ_PUT_FIELD_RET(s, field->prev_state); + SEQ_PUT_FIELD_RET(s, field->next_pid); + SEQ_PUT_FIELD_RET(s, field->next_prio); + SEQ_PUT_FIELD_RET(s, field->next_state); + + return 0; +} + +static struct trace_event trace_ctx_event = { + .type = TRACE_CTX, + .trace = trace_ctx_print, + .latency_trace = trace_ctx_print, + .raw = trace_ctx_raw, + .hex = trace_ctx_hex, + .binary = trace_ctxwake_bin, +}; + +static struct trace_event trace_wake_event = { + .type = TRACE_WAKE, + .trace = trace_wake_print, + .latency_trace = trace_wake_print, + .raw = trace_wake_raw, + .hex = trace_wake_hex, + .binary = trace_ctxwake_bin, +}; + +/* TRACE_SPECIAL */ +static int +trace_special_print(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct special_entry *field; + + trace_assign_type(field, entry); + + if (!trace_seq_printf(s, "# %ld %ld %ld\n", + field->arg1, + field->arg2, + field->arg3)) + return TRACE_TYPE_PARTIAL_LINE; + + return 0; +} + +static int +trace_special_hex(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct special_entry *field; + + trace_assign_type(field, entry); + + SEQ_PUT_HEX_FIELD_RET(s, field->arg1); + SEQ_PUT_HEX_FIELD_RET(s, field->arg2); + SEQ_PUT_HEX_FIELD_RET(s, field->arg3); + + return 0; +} + +static int +trace_special_bin(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct special_entry *field; + + trace_assign_type(field, entry); + + SEQ_PUT_FIELD_RET(s, field->arg1); + SEQ_PUT_FIELD_RET(s, field->arg2); + SEQ_PUT_FIELD_RET(s, field->arg3); + + return 0; +} + +static struct trace_event trace_special_event = { + .type = TRACE_SPECIAL, + .trace = trace_special_print, + .latency_trace = trace_special_print, + .raw = trace_special_print, + .hex = trace_special_hex, + .binary = trace_special_bin, +}; + +/* TRACE_STACK */ + +static int +trace_stack_print(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct stack_entry *field; + int i; + + trace_assign_type(field, entry); + + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { + if (i) { + if (!trace_seq_puts(s, " <= ")) + goto partial; + + if (!seq_print_ip_sym(s, field->caller[i], flags)) + goto partial; + } + if (!trace_seq_puts(s, "\n")) + goto partial; + } + + return 0; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static struct trace_event trace_stack_event = { + .type = TRACE_STACK, + .trace = trace_stack_print, + .latency_trace = trace_stack_print, + .raw = trace_special_print, + .hex = trace_special_hex, + .binary = trace_special_bin, +}; + +/* TRACE_USER_STACK */ +static int +trace_user_stack_print(struct trace_seq *s, struct trace_entry *entry, + int flags) +{ + struct userstack_entry *field; + + trace_assign_type(field, entry); + + if (!seq_print_userip_objs(field, s, flags)) + goto partial; + + if (!trace_seq_putc(s, '\n')) + goto partial; + + return 0; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static struct trace_event trace_user_stack_event = { + .type = TRACE_USER_STACK, + .trace = trace_user_stack_print, + .latency_trace = trace_user_stack_print, + .raw = trace_special_print, + .hex = trace_special_hex, + .binary = trace_special_bin, +}; + +/* TRACE_PRINT */ +static int +trace_print_print(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct print_entry *field; + + trace_assign_type(field, entry); + + if (!seq_print_ip_sym(s, field->ip, flags)) + goto partial; + + if (!trace_seq_printf(s, ": %s", field->buf)) + goto partial; + + return 0; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static int +trace_print_raw(struct trace_seq *s, struct trace_entry *entry, int flags) +{ + struct print_entry *field; + + trace_assign_type(field, entry); + + if (!trace_seq_printf(s, "# %lx %s", field->ip, field->buf)) + goto partial; + + return 0; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static struct trace_event trace_print_event = { + .type = TRACE_PRINT, + .trace = trace_print_print, + .latency_trace = trace_print_print, + .raw = trace_print_raw, + .hex = trace_nop_print, + .binary = trace_nop_print, +}; + +static struct trace_event *events[] __initdata = { + &trace_fn_event, + &trace_ctx_event, + &trace_wake_event, + &trace_special_event, + &trace_stack_event, + &trace_user_stack_event, + &trace_print_event, + NULL +}; + +__init static int init_events(void) +{ + struct trace_event *event; + int i, ret; + + for (i = 0; events[i]; i++) { + event = events[i]; + + ret = register_ftrace_event(event); + if (!ret) { + printk(KERN_WARNING "event %d failed to register\n", + event->type); + WARN_ON_ONCE(1); + } + } + + return 0; +} +device_initcall(init_events); diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h new file mode 100644 index 000000000000..1cbab5e3dc99 --- /dev/null +++ b/kernel/trace/trace_output.h @@ -0,0 +1,60 @@ +#ifndef __TRACE_EVENTS_H +#define __TRACE_EVENTS_H + +#include "trace.h" + +typedef int (*trace_print_func)(struct trace_seq *s, struct trace_entry *entry, + int flags); + +struct trace_event { + struct hlist_node node; + int type; + trace_print_func trace; + trace_print_func latency_trace; + trace_print_func raw; + trace_print_func hex; + trace_print_func binary; +}; + +extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...) + __attribute__ ((format (printf, 2, 3))); +extern int +seq_print_ip_sym(struct trace_seq *s, unsigned long ip, + unsigned long sym_flags); +extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, + size_t cnt); +int trace_seq_puts(struct trace_seq *s, const char *str); +int trace_seq_putc(struct trace_seq *s, unsigned char c); +int trace_seq_putmem(struct trace_seq *s, void *mem, size_t len); +int trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len); +int trace_seq_path(struct trace_seq *s, struct path *path); +int seq_print_userip_objs(const struct userstack_entry *entry, + struct trace_seq *s, unsigned long sym_flags); +int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm, + unsigned long ip, unsigned long sym_flags); + +struct trace_event *ftrace_find_event(int type); +int register_ftrace_event(struct trace_event *event); +int unregister_ftrace_event(struct trace_event *event); + +int +trace_nop_print(struct trace_seq *s, struct trace_entry *entry, int flags); + +#define MAX_MEMHEX_BYTES 8 +#define HEX_CHARS (MAX_MEMHEX_BYTES*2 + 1) + +#define SEQ_PUT_FIELD_RET(s, x) \ +do { \ + if (!trace_seq_putmem(s, &(x), sizeof(x))) \ + return TRACE_TYPE_PARTIAL_LINE; \ +} while (0) + +#define SEQ_PUT_HEX_FIELD_RET(s, x) \ +do { \ + BUILD_BUG_ON(sizeof(x) > MAX_MEMHEX_BYTES); \ + if (!trace_seq_putmem_hex(s, &(x), sizeof(x))) \ + return TRACE_TYPE_PARTIAL_LINE; \ +} while (0) + +#endif + diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c index 7bda248daf55..faa6ab7a1f5c 100644 --- a/kernel/trace/trace_power.c +++ b/kernel/trace/trace_power.c @@ -16,6 +16,7 @@ #include <linux/module.h> #include "trace.h" +#include "trace_output.h" static struct trace_array *power_trace; static int __read_mostly trace_power_enabled; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 43586b689e31..93cecda650b2 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -25,6 +25,7 @@ static int __read_mostly tracer_enabled; static struct task_struct *wakeup_task; static int wakeup_cpu; static unsigned wakeup_prio = -1; +static int wakeup_rt; static raw_spinlock_t wakeup_lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; @@ -152,6 +153,7 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev, goto out_unlock; trace_function(wakeup_trace, data, CALLER_ADDR1, CALLER_ADDR2, flags, pc); + tracing_sched_switch_trace(wakeup_trace, data, prev, next, flags, pc); /* * usecs conversion is slow so we try to delay the conversion @@ -213,6 +215,7 @@ static void wakeup_reset(struct trace_array *tr) static void probe_wakeup(struct rq *rq, struct task_struct *p, int success) { + struct trace_array_cpu *data; int cpu = smp_processor_id(); unsigned long flags; long disabled; @@ -224,7 +227,7 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success) tracing_record_cmdline(p); tracing_record_cmdline(current); - if (likely(!rt_task(p)) || + if ((wakeup_rt && !rt_task(p)) || p->prio >= wakeup_prio || p->prio >= current->prio) return; @@ -252,9 +255,12 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success) local_save_flags(flags); - wakeup_trace->data[wakeup_cpu]->preempt_timestamp = ftrace_now(cpu); - trace_function(wakeup_trace, wakeup_trace->data[wakeup_cpu], - CALLER_ADDR1, CALLER_ADDR2, flags, pc); + data = wakeup_trace->data[wakeup_cpu]; + data->preempt_timestamp = ftrace_now(cpu); + tracing_sched_wakeup_trace(wakeup_trace, data, p, current, + flags, pc); + trace_function(wakeup_trace, data, CALLER_ADDR1, CALLER_ADDR2, + flags, pc); out_locked: __raw_spin_unlock(&wakeup_lock); @@ -262,12 +268,6 @@ out: atomic_dec(&wakeup_trace->data[cpu]->disabled); } -/* - * save_tracer_enabled is used to save the state of the tracer_enabled - * variable when we disable it when we open a trace output file. - */ -static int save_tracer_enabled; - static void start_wakeup_tracer(struct trace_array *tr) { int ret; @@ -306,13 +306,10 @@ static void start_wakeup_tracer(struct trace_array *tr) register_ftrace_function(&trace_ops); - if (tracing_is_enabled()) { + if (tracing_is_enabled()) tracer_enabled = 1; - save_tracer_enabled = 1; - } else { + else tracer_enabled = 0; - save_tracer_enabled = 0; - } return; fail_deprobe_wake_new: @@ -324,20 +321,32 @@ fail_deprobe: static void stop_wakeup_tracer(struct trace_array *tr) { tracer_enabled = 0; - save_tracer_enabled = 0; unregister_ftrace_function(&trace_ops); unregister_trace_sched_switch(probe_wakeup_sched_switch); unregister_trace_sched_wakeup_new(probe_wakeup); unregister_trace_sched_wakeup(probe_wakeup); } -static int wakeup_tracer_init(struct trace_array *tr) +static int __wakeup_tracer_init(struct trace_array *tr) { + tracing_max_latency = 0; wakeup_trace = tr; start_wakeup_tracer(tr); return 0; } +static int wakeup_tracer_init(struct trace_array *tr) +{ + wakeup_rt = 0; + return __wakeup_tracer_init(tr); +} + +static int wakeup_rt_tracer_init(struct trace_array *tr) +{ + wakeup_rt = 1; + return __wakeup_tracer_init(tr); +} + static void wakeup_tracer_reset(struct trace_array *tr) { stop_wakeup_tracer(tr); @@ -349,28 +358,11 @@ static void wakeup_tracer_start(struct trace_array *tr) { wakeup_reset(tr); tracer_enabled = 1; - save_tracer_enabled = 1; } static void wakeup_tracer_stop(struct trace_array *tr) { tracer_enabled = 0; - save_tracer_enabled = 0; -} - -static void wakeup_tracer_open(struct trace_iterator *iter) -{ - /* stop the trace while dumping */ - tracer_enabled = 0; -} - -static void wakeup_tracer_close(struct trace_iterator *iter) -{ - /* forget about any processes we were recording */ - if (save_tracer_enabled) { - wakeup_reset(iter->tr); - tracer_enabled = 1; - } } static struct tracer wakeup_tracer __read_mostly = @@ -380,8 +372,19 @@ static struct tracer wakeup_tracer __read_mostly = .reset = wakeup_tracer_reset, .start = wakeup_tracer_start, .stop = wakeup_tracer_stop, - .open = wakeup_tracer_open, - .close = wakeup_tracer_close, + .print_max = 1, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_wakeup, +#endif +}; + +static struct tracer wakeup_rt_tracer __read_mostly = +{ + .name = "wakeup_rt", + .init = wakeup_rt_tracer_init, + .reset = wakeup_tracer_reset, + .start = wakeup_tracer_start, + .stop = wakeup_tracer_stop, .print_max = 1, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, @@ -396,6 +399,10 @@ __init static int init_wakeup_tracer(void) if (ret) return ret; + ret = register_tracer(&wakeup_rt_tracer); + if (ret) + return ret; + return 0; } device_initcall(init_wakeup_tracer); diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 88c8eb70f54a..5013812578b1 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -9,7 +9,6 @@ static inline int trace_valid_entry(struct trace_entry *entry) case TRACE_FN: case TRACE_CTX: case TRACE_WAKE: - case TRACE_CONT: case TRACE_STACK: case TRACE_PRINT: case TRACE_SPECIAL: diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c new file mode 100644 index 000000000000..eae9cef39291 --- /dev/null +++ b/kernel/trace/trace_stat.c @@ -0,0 +1,319 @@ +/* + * Infrastructure for statistic tracing (histogram output). + * + * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com> + * + * Based on the code from trace_branch.c which is + * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com> + * + */ + + +#include <linux/list.h> +#include <linux/debugfs.h> +#include "trace_stat.h" +#include "trace.h" + + +/* List of stat entries from a tracer */ +struct trace_stat_list { + struct list_head list; + void *stat; +}; + +/* A stat session is the stats output in one file */ +struct tracer_stat_session { + struct list_head session_list; + struct tracer_stat *ts; + struct list_head stat_list; + struct mutex stat_mutex; + struct dentry *file; +}; + +/* All of the sessions currently in use. Each stat file embeed one session */ +static LIST_HEAD(all_stat_sessions); +static DEFINE_MUTEX(all_stat_sessions_mutex); + +/* The root directory for all stat files */ +static struct dentry *stat_dir; + + +static void reset_stat_session(struct tracer_stat_session *session) +{ + struct trace_stat_list *node, *next; + + list_for_each_entry_safe(node, next, &session->stat_list, list) + kfree(node); + + INIT_LIST_HEAD(&session->stat_list); +} + +static void destroy_session(struct tracer_stat_session *session) +{ + debugfs_remove(session->file); + reset_stat_session(session); + mutex_destroy(&session->stat_mutex); + kfree(session); +} + +/* + * For tracers that don't provide a stat_cmp callback. + * This one will force an immediate insertion on tail of + * the list. + */ +static int dummy_cmp(void *p1, void *p2) +{ + return 1; +} + +/* + * Initialize the stat list at each trace_stat file opening. + * All of these copies and sorting are required on all opening + * since the stats could have changed between two file sessions. + */ +static int stat_seq_init(struct tracer_stat_session *session) +{ + struct trace_stat_list *iter_entry, *new_entry; + struct tracer_stat *ts = session->ts; + void *prev_stat; + int ret = 0; + int i; + + mutex_lock(&session->stat_mutex); + reset_stat_session(session); + + if (!ts->stat_cmp) + ts->stat_cmp = dummy_cmp; + + /* + * The first entry. Actually this is the second, but the first + * one (the stat_list head) is pointless. + */ + new_entry = kmalloc(sizeof(struct trace_stat_list), GFP_KERNEL); + if (!new_entry) { + ret = -ENOMEM; + goto exit; + } + + INIT_LIST_HEAD(&new_entry->list); + + list_add(&new_entry->list, &session->stat_list); + + new_entry->stat = ts->stat_start(); + prev_stat = new_entry->stat; + + /* + * Iterate over the tracer stat entries and store them in a sorted + * list. + */ + for (i = 1; ; i++) { + new_entry = kmalloc(sizeof(struct trace_stat_list), GFP_KERNEL); + if (!new_entry) { + ret = -ENOMEM; + goto exit_free_list; + } + + INIT_LIST_HEAD(&new_entry->list); + new_entry->stat = ts->stat_next(prev_stat, i); + + /* End of insertion */ + if (!new_entry->stat) + break; + + list_for_each_entry(iter_entry, &session->stat_list, list) { + + /* Insertion with a descendent sorting */ + if (ts->stat_cmp(new_entry->stat, + iter_entry->stat) > 0) { + + list_add_tail(&new_entry->list, + &iter_entry->list); + break; + + /* The current smaller value */ + } else if (list_is_last(&iter_entry->list, + &session->stat_list)) { + list_add(&new_entry->list, &iter_entry->list); + break; + } + } + + prev_stat = new_entry->stat; + } +exit: + mutex_unlock(&session->stat_mutex); + return ret; + +exit_free_list: + reset_stat_session(session); + mutex_unlock(&session->stat_mutex); + return ret; +} + + +static void *stat_seq_start(struct seq_file *s, loff_t *pos) +{ + struct tracer_stat_session *session = s->private; + + /* Prevent from tracer switch or stat_list modification */ + mutex_lock(&session->stat_mutex); + + /* If we are in the beginning of the file, print the headers */ + if (!*pos && session->ts->stat_headers) + session->ts->stat_headers(s); + + return seq_list_start(&session->stat_list, *pos); +} + +static void *stat_seq_next(struct seq_file *s, void *p, loff_t *pos) +{ + struct tracer_stat_session *session = s->private; + + return seq_list_next(p, &session->stat_list, pos); +} + +static void stat_seq_stop(struct seq_file *s, void *p) +{ + struct tracer_stat_session *session = s->private; + mutex_unlock(&session->stat_mutex); +} + +static int stat_seq_show(struct seq_file *s, void *v) +{ + struct tracer_stat_session *session = s->private; + struct trace_stat_list *l = list_entry(v, struct trace_stat_list, list); + + return session->ts->stat_show(s, l->stat); +} + +static const struct seq_operations trace_stat_seq_ops = { + .start = stat_seq_start, + .next = stat_seq_next, + .stop = stat_seq_stop, + .show = stat_seq_show +}; + +/* The session stat is refilled and resorted at each stat file opening */ +static int tracing_stat_open(struct inode *inode, struct file *file) +{ + int ret; + + struct tracer_stat_session *session = inode->i_private; + + ret = seq_open(file, &trace_stat_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = session; + ret = stat_seq_init(session); + } + + return ret; +} + +/* + * Avoid consuming memory with our now useless list. + */ +static int tracing_stat_release(struct inode *i, struct file *f) +{ + struct tracer_stat_session *session = i->i_private; + + mutex_lock(&session->stat_mutex); + reset_stat_session(session); + mutex_unlock(&session->stat_mutex); + + return 0; +} + +static const struct file_operations tracing_stat_fops = { + .open = tracing_stat_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tracing_stat_release +}; + +static int tracing_stat_init(void) +{ + struct dentry *d_tracing; + + d_tracing = tracing_init_dentry(); + + stat_dir = debugfs_create_dir("trace_stat", d_tracing); + if (!stat_dir) + pr_warning("Could not create debugfs " + "'trace_stat' entry\n"); + return 0; +} + +static int init_stat_file(struct tracer_stat_session *session) +{ + if (!stat_dir && tracing_stat_init()) + return -ENODEV; + + session->file = debugfs_create_file(session->ts->name, 0644, + stat_dir, + session, &tracing_stat_fops); + if (!session->file) + return -ENOMEM; + return 0; +} + +int register_stat_tracer(struct tracer_stat *trace) +{ + struct tracer_stat_session *session, *node, *tmp; + int ret; + + if (!trace) + return -EINVAL; + + if (!trace->stat_start || !trace->stat_next || !trace->stat_show) + return -EINVAL; + + /* Already registered? */ + mutex_lock(&all_stat_sessions_mutex); + list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) { + if (node->ts == trace) { + mutex_unlock(&all_stat_sessions_mutex); + return -EINVAL; + } + } + mutex_unlock(&all_stat_sessions_mutex); + + /* Init the session */ + session = kmalloc(sizeof(struct tracer_stat_session), GFP_KERNEL); + if (!session) + return -ENOMEM; + + session->ts = trace; + INIT_LIST_HEAD(&session->session_list); + INIT_LIST_HEAD(&session->stat_list); + mutex_init(&session->stat_mutex); + session->file = NULL; + + ret = init_stat_file(session); + if (ret) { + destroy_session(session); + return ret; + } + + /* Register */ + mutex_lock(&all_stat_sessions_mutex); + list_add_tail(&session->session_list, &all_stat_sessions); + mutex_unlock(&all_stat_sessions_mutex); + + return 0; +} + +void unregister_stat_tracer(struct tracer_stat *trace) +{ + struct tracer_stat_session *node, *tmp; + + mutex_lock(&all_stat_sessions_mutex); + list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) { + if (node->ts == trace) { + list_del(&node->session_list); + destroy_session(node); + break; + } + } + mutex_unlock(&all_stat_sessions_mutex); +} diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h new file mode 100644 index 000000000000..202274cf7f3d --- /dev/null +++ b/kernel/trace/trace_stat.h @@ -0,0 +1,31 @@ +#ifndef __TRACE_STAT_H +#define __TRACE_STAT_H + +#include <linux/seq_file.h> + +/* + * If you want to provide a stat file (one-shot statistics), fill + * an iterator with stat_start/stat_next and a stat_show callbacks. + * The others callbacks are optional. + */ +struct tracer_stat { + /* The name of your stat file */ + const char *name; + /* Iteration over statistic entries */ + void *(*stat_start)(void); + void *(*stat_next)(void *prev, int idx); + /* Compare two entries for stats sorting */ + int (*stat_cmp)(void *p1, void *p2); + /* Print a stat entry */ + int (*stat_show)(struct seq_file *s, void *p); + /* Print the headers of your stat entries */ + int (*stat_headers)(struct seq_file *s); +}; + +/* + * Destroy or create a stat file + */ +extern int register_stat_tracer(struct tracer_stat *trace); +extern void unregister_stat_tracer(struct tracer_stat *trace); + +#endif /* __TRACE_STAT_H */ diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c new file mode 100644 index 000000000000..4664990fe9c5 --- /dev/null +++ b/kernel/trace/trace_workqueue.c @@ -0,0 +1,281 @@ +/* + * Workqueue statistical tracer. + * + * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com> + * + */ + + +#include <trace/workqueue.h> +#include <linux/list.h> +#include <linux/percpu.h> +#include "trace_stat.h" +#include "trace.h" + + +/* A cpu workqueue thread */ +struct cpu_workqueue_stats { + struct list_head list; +/* Useful to know if we print the cpu headers */ + bool first_entry; + int cpu; + pid_t pid; +/* Can be inserted from interrupt or user context, need to be atomic */ + atomic_t inserted; +/* + * Don't need to be atomic, works are serialized in a single workqueue thread + * on a single CPU. + */ + unsigned int executed; +}; + +/* List of workqueue threads on one cpu */ +struct workqueue_global_stats { + struct list_head list; + spinlock_t lock; +}; + +/* Don't need a global lock because allocated before the workqueues, and + * never freed. + */ +static DEFINE_PER_CPU(struct workqueue_global_stats, all_workqueue_stat); +#define workqueue_cpu_stat(cpu) (&per_cpu(all_workqueue_stat, cpu)) + +/* Insertion of a work */ +static void +probe_workqueue_insertion(struct task_struct *wq_thread, + struct work_struct *work) +{ + int cpu = cpumask_first(&wq_thread->cpus_allowed); + struct cpu_workqueue_stats *node, *next; + unsigned long flags; + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list, + list) { + if (node->pid == wq_thread->pid) { + atomic_inc(&node->inserted); + goto found; + } + } + pr_debug("trace_workqueue: entry not found\n"); +found: + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); +} + +/* Execution of a work */ +static void +probe_workqueue_execution(struct task_struct *wq_thread, + struct work_struct *work) +{ + int cpu = cpumask_first(&wq_thread->cpus_allowed); + struct cpu_workqueue_stats *node, *next; + unsigned long flags; + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list, + list) { + if (node->pid == wq_thread->pid) { + node->executed++; + goto found; + } + } + pr_debug("trace_workqueue: entry not found\n"); +found: + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); +} + +/* Creation of a cpu workqueue thread */ +static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu) +{ + struct cpu_workqueue_stats *cws; + unsigned long flags; + + WARN_ON(cpu < 0 || cpu >= num_possible_cpus()); + + /* Workqueues are sometimes created in atomic context */ + cws = kzalloc(sizeof(struct cpu_workqueue_stats), GFP_ATOMIC); + if (!cws) { + pr_warning("trace_workqueue: not enough memory\n"); + return; + } + tracing_record_cmdline(wq_thread); + + INIT_LIST_HEAD(&cws->list); + cws->cpu = cpu; + + cws->pid = wq_thread->pid; + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + if (list_empty(&workqueue_cpu_stat(cpu)->list)) + cws->first_entry = true; + list_add_tail(&cws->list, &workqueue_cpu_stat(cpu)->list); + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); +} + +/* Destruction of a cpu workqueue thread */ +static void probe_workqueue_destruction(struct task_struct *wq_thread) +{ + /* Workqueue only execute on one cpu */ + int cpu = cpumask_first(&wq_thread->cpus_allowed); + struct cpu_workqueue_stats *node, *next; + unsigned long flags; + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list, + list) { + if (node->pid == wq_thread->pid) { + list_del(&node->list); + kfree(node); + goto found; + } + } + + pr_debug("trace_workqueue: don't find workqueue to destroy\n"); +found: + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); + +} + +static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu) +{ + unsigned long flags; + struct cpu_workqueue_stats *ret = NULL; + + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + + if (!list_empty(&workqueue_cpu_stat(cpu)->list)) + ret = list_entry(workqueue_cpu_stat(cpu)->list.next, + struct cpu_workqueue_stats, list); + + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); + + return ret; +} + +static void *workqueue_stat_start(void) +{ + int cpu; + void *ret = NULL; + + for_each_possible_cpu(cpu) { + ret = workqueue_stat_start_cpu(cpu); + if (ret) + return ret; + } + return NULL; +} + +static void *workqueue_stat_next(void *prev, int idx) +{ + struct cpu_workqueue_stats *prev_cws = prev; + int cpu = prev_cws->cpu; + unsigned long flags; + void *ret = NULL; + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + if (list_is_last(&prev_cws->list, &workqueue_cpu_stat(cpu)->list)) { + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); + for (++cpu ; cpu < num_possible_cpus(); cpu++) { + ret = workqueue_stat_start_cpu(cpu); + if (ret) + return ret; + } + return NULL; + } + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); + + return list_entry(prev_cws->list.next, struct cpu_workqueue_stats, + list); +} + +static int workqueue_stat_show(struct seq_file *s, void *p) +{ + struct cpu_workqueue_stats *cws = p; + unsigned long flags; + int cpu = cws->cpu; + + seq_printf(s, "%3d %6d %6u %s\n", cws->cpu, + atomic_read(&cws->inserted), + cws->executed, + trace_find_cmdline(cws->pid)); + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + if (&cws->list == workqueue_cpu_stat(cpu)->list.next) + seq_printf(s, "\n"); + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); + + return 0; +} + +static int workqueue_stat_headers(struct seq_file *s) +{ + seq_printf(s, "# CPU INSERTED EXECUTED NAME\n"); + seq_printf(s, "# | | | |\n\n"); + return 0; +} + +struct tracer_stat workqueue_stats __read_mostly = { + .name = "workqueues", + .stat_start = workqueue_stat_start, + .stat_next = workqueue_stat_next, + .stat_show = workqueue_stat_show, + .stat_headers = workqueue_stat_headers +}; + + +int __init stat_workqueue_init(void) +{ + if (register_stat_tracer(&workqueue_stats)) { + pr_warning("Unable to register workqueue stat tracer\n"); + return 1; + } + + return 0; +} +fs_initcall(stat_workqueue_init); + +/* + * Workqueues are created very early, just after pre-smp initcalls. + * So we must register our tracepoints at this stage. + */ +int __init trace_workqueue_early_init(void) +{ + int ret, cpu; + + ret = register_trace_workqueue_insertion(probe_workqueue_insertion); + if (ret) + goto out; + + ret = register_trace_workqueue_execution(probe_workqueue_execution); + if (ret) + goto no_insertion; + + ret = register_trace_workqueue_creation(probe_workqueue_creation); + if (ret) + goto no_execution; + + ret = register_trace_workqueue_destruction(probe_workqueue_destruction); + if (ret) + goto no_creation; + + for_each_possible_cpu(cpu) { + spin_lock_init(&workqueue_cpu_stat(cpu)->lock); + INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list); + } + + return 0; + +no_creation: + unregister_trace_workqueue_creation(probe_workqueue_creation); +no_execution: + unregister_trace_workqueue_execution(probe_workqueue_execution); +no_insertion: + unregister_trace_workqueue_insertion(probe_workqueue_insertion); +out: + pr_warning("trace_workqueue: unable to trace workqueues\n"); + + return 1; +} +early_initcall(trace_workqueue_early_init); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2f445833ae37..e53ee18ef431 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -33,6 +33,7 @@ #include <linux/kallsyms.h> #include <linux/debug_locks.h> #include <linux/lockdep.h> +#include <trace/workqueue.h> /* * The per-CPU workqueue (if single thread, we always use the first @@ -125,9 +126,13 @@ struct cpu_workqueue_struct *get_wq_data(struct work_struct *work) return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK); } +DEFINE_TRACE(workqueue_insertion); + static void insert_work(struct cpu_workqueue_struct *cwq, struct work_struct *work, struct list_head *head) { + trace_workqueue_insertion(cwq->thread, work); + set_wq_data(work, cwq); /* * Ensure that we get the right work->data if we see the @@ -259,6 +264,8 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, } EXPORT_SYMBOL_GPL(queue_delayed_work_on); +DEFINE_TRACE(workqueue_execution); + static void run_workqueue(struct cpu_workqueue_struct *cwq) { spin_lock_irq(&cwq->lock); @@ -284,7 +291,7 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq) */ struct lockdep_map lockdep_map = work->lockdep_map; #endif - + trace_workqueue_execution(cwq->thread, work); cwq->current_work = work; list_del_init(cwq->worklist.next); spin_unlock_irq(&cwq->lock); @@ -765,6 +772,8 @@ init_cpu_workqueue(struct workqueue_struct *wq, int cpu) return cwq; } +DEFINE_TRACE(workqueue_creation); + static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) { struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; @@ -787,6 +796,8 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); cwq->thread = p; + trace_workqueue_creation(cwq->thread, cpu); + return 0; } @@ -868,6 +879,8 @@ struct workqueue_struct *__create_workqueue_key(const char *name, } EXPORT_SYMBOL_GPL(__create_workqueue_key); +DEFINE_TRACE(workqueue_destruction); + static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq) { /* @@ -891,6 +904,7 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq) * checks list_empty(), and a "normal" queue_work() can't use * a dead CPU. */ + trace_workqueue_destruction(cwq->thread); kthread_stop(cwq->thread); cwq->thread = NULL; } @@ -971,6 +985,8 @@ undo: } #ifdef CONFIG_SMP +static struct workqueue_struct *work_on_cpu_wq __read_mostly; + struct work_for_cpu { struct work_struct work; long (*fn)(void *); @@ -991,8 +1007,8 @@ static void do_work_for_cpu(struct work_struct *w) * @fn: the function to run * @arg: the function arg * - * This will return -EINVAL in the cpu is not online, or the return value - * of @fn otherwise. + * This will return the value @fn returns. + * It is up to the caller to ensure that the cpu doesn't go offline. */ long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) { @@ -1001,14 +1017,8 @@ long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) INIT_WORK(&wfc.work, do_work_for_cpu); wfc.fn = fn; wfc.arg = arg; - get_online_cpus(); - if (unlikely(!cpu_online(cpu))) - wfc.ret = -EINVAL; - else { - schedule_work_on(cpu, &wfc.work); - flush_work(&wfc.work); - } - put_online_cpus(); + queue_work_on(cpu, work_on_cpu_wq, &wfc.work); + flush_work(&wfc.work); return wfc.ret; } @@ -1025,4 +1035,8 @@ void __init init_workqueues(void) hotcpu_notifier(workqueue_cpu_callback, 0); keventd_wq = create_workqueue("events"); BUG_ON(!keventd_wq); +#ifdef CONFIG_SMP + work_on_cpu_wq = create_workqueue("work_on_cpu"); + BUG_ON(!work_on_cpu_wq); +#endif } |