diff options
Diffstat (limited to 'kernel')
42 files changed, 672 insertions, 300 deletions
diff --git a/kernel/async.c b/kernel/async.c index 608b32b4281..f565891f2c9 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -54,6 +54,7 @@ asynchronous and synchronous parts of the kernel. #include <linux/sched.h> #include <linux/init.h> #include <linux/kthread.h> +#include <linux/delay.h> #include <asm/atomic.h> static async_cookie_t next_cookie = 1; @@ -132,21 +133,23 @@ static void run_one_entry(void) entry = list_first_entry(&async_pending, struct async_entry, list); /* 2) move it to the running queue */ - list_del(&entry->list); - list_add_tail(&entry->list, &async_running); + list_move_tail(&entry->list, entry->running); spin_unlock_irqrestore(&async_lock, flags); /* 3) run it (and print duration)*/ if (initcall_debug && system_state == SYSTEM_BOOTING) { - printk("calling %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current)); + printk("calling %lli_%pF @ %i\n", (long long)entry->cookie, + entry->func, task_pid_nr(current)); calltime = ktime_get(); } entry->func(entry->data, entry->cookie); if (initcall_debug && system_state == SYSTEM_BOOTING) { rettime = ktime_get(); delta = ktime_sub(rettime, calltime); - printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie, - entry->func, ktime_to_ns(delta) >> 10); + printk("initcall %lli_%pF returned 0 after %lld usecs\n", + (long long)entry->cookie, + entry->func, + (long long)ktime_to_ns(delta) >> 10); } /* 4) remove it from the running queue */ @@ -205,18 +208,44 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct l return newcookie; } +/** + * async_schedule - schedule a function for asynchronous execution + * @ptr: function to execute asynchronously + * @data: data pointer to pass to the function + * + * Returns an async_cookie_t that may be used for checkpointing later. + * Note: This function may be called from atomic or non-atomic contexts. + */ async_cookie_t async_schedule(async_func_ptr *ptr, void *data) { - return __async_schedule(ptr, data, &async_pending); + return __async_schedule(ptr, data, &async_running); } EXPORT_SYMBOL_GPL(async_schedule); -async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running) +/** + * async_schedule_domain - schedule a function for asynchronous execution within a certain domain + * @ptr: function to execute asynchronously + * @data: data pointer to pass to the function + * @running: running list for the domain + * + * Returns an async_cookie_t that may be used for checkpointing later. + * @running may be used in the async_synchronize_*_domain() functions + * to wait within a certain synchronization domain rather than globally. + * A synchronization domain is specified via the running queue @running to use. + * Note: This function may be called from atomic or non-atomic contexts. + */ +async_cookie_t async_schedule_domain(async_func_ptr *ptr, void *data, + struct list_head *running) { return __async_schedule(ptr, data, running); } -EXPORT_SYMBOL_GPL(async_schedule_special); +EXPORT_SYMBOL_GPL(async_schedule_domain); +/** + * async_synchronize_full - synchronize all asynchronous function calls + * + * This function waits until all asynchronous function calls have been done. + */ void async_synchronize_full(void) { do { @@ -225,13 +254,30 @@ void async_synchronize_full(void) } EXPORT_SYMBOL_GPL(async_synchronize_full); -void async_synchronize_full_special(struct list_head *list) +/** + * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain + * @list: running list to synchronize on + * + * This function waits until all asynchronous function calls for the + * synchronization domain specified by the running list @list have been done. + */ +void async_synchronize_full_domain(struct list_head *list) { - async_synchronize_cookie_special(next_cookie, list); + async_synchronize_cookie_domain(next_cookie, list); } -EXPORT_SYMBOL_GPL(async_synchronize_full_special); +EXPORT_SYMBOL_GPL(async_synchronize_full_domain); -void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running) +/** + * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing + * @cookie: async_cookie_t to use as checkpoint + * @running: running list to synchronize on + * + * This function waits until all asynchronous function calls for the + * synchronization domain specified by the running list @list submitted + * prior to @cookie have been done. + */ +void async_synchronize_cookie_domain(async_cookie_t cookie, + struct list_head *running) { ktime_t starttime, delta, endtime; @@ -247,14 +293,22 @@ void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *r delta = ktime_sub(endtime, starttime); printk("async_continuing @ %i after %lli usec\n", - task_pid_nr(current), ktime_to_ns(delta) >> 10); + task_pid_nr(current), + (long long)ktime_to_ns(delta) >> 10); } } -EXPORT_SYMBOL_GPL(async_synchronize_cookie_special); +EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain); +/** + * async_synchronize_cookie - synchronize asynchronous function calls with cookie checkpointing + * @cookie: async_cookie_t to use as checkpoint + * + * This function waits until all asynchronous function calls prior to @cookie + * have been done. + */ void async_synchronize_cookie(async_cookie_t cookie) { - async_synchronize_cookie_special(cookie, &async_running); + async_synchronize_cookie_domain(cookie, &async_running); } EXPORT_SYMBOL_GPL(async_synchronize_cookie); @@ -315,7 +369,11 @@ static int async_manager_thread(void *unused) ec = atomic_read(&entry_count); while (tc < ec && tc < MAX_THREADS) { - kthread_run(async_thread, NULL, "async/%i", tc); + if (IS_ERR(kthread_run(async_thread, NULL, "async/%i", + tc))) { + msleep(100); + continue; + } atomic_inc(&thread_count); tc++; } @@ -330,7 +388,9 @@ static int async_manager_thread(void *unused) static int __init async_init(void) { if (async_enabled) - kthread_run(async_manager_thread, NULL, "async/mgr"); + if (IS_ERR(kthread_run(async_manager_thread, NULL, + "async/mgr"))) + async_enabled = 0; return 0; } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c29831076e7..e14db9c089b 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); @@ -2349,7 +2351,7 @@ static void cgroup_lock_hierarchy(struct cgroupfs_root *root) for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; if (ss->root == root) - mutex_lock_nested(&ss->hierarchy_mutex, i); + mutex_lock(&ss->hierarchy_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) { @@ -2630,6 +2637,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) BUG_ON(!list_empty(&init_task.tasks)); mutex_init(&ss->hierarchy_mutex); + lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key); ss->active = 1; } @@ -2991,20 +2999,21 @@ 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 +3052,7 @@ 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 +3078,7 @@ 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/cpuset.c b/kernel/cpuset.c index a85678865c5..f76db9dcaa0 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 038707404b7..962a3b574f2 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 f80dec3f187..efd30ccf385 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -118,6 +118,8 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ + sig->utime = cputime_add(sig->utime, task_utime(tsk)); + sig->stime = cputime_add(sig->stime, task_stime(tsk)); sig->gtime = cputime_add(sig->gtime, task_gtime(tsk)); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; @@ -126,6 +128,7 @@ static void __exit_signal(struct task_struct *tsk) sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); + sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig = NULL; /* Marker for below. */ } diff --git a/kernel/fork.c b/kernel/fork.c index bf0cef8bbdf..a66fbde2071 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -817,17 +817,17 @@ 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; @@ -851,21 +851,20 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->tty_old_pgrp = NULL; sig->tty = NULL; - sig->cutime = sig->cstime = cputime_zero; + sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; sig->gtime = cputime_zero; sig->cgtime = cputime_zero; sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; task_io_accounting_init(&sig->ioac); + sig->sum_sched_runtime = 0; taskstats_tgid_init(sig); task_lock(current->group_leader); 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); @@ -1007,6 +1006,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ + retval = -EAGAIN; if (nr_threads >= max_threads) goto bad_fork_cleanup_count; @@ -1095,7 +1095,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif - if (unlikely(ptrace_reparented(current))) + if (unlikely(current->ptrace)) ptrace_fork(p, clone_flags); /* Perform scheduler related setup. Assign this task to a CPU. */ diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 2dc30c59c5f..f394d2a42ca 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/irq/chip.c b/kernel/irq/chip.c index 9a7fbb84f56..03d0bed2b8d 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -78,6 +78,7 @@ void dynamic_irq_cleanup(unsigned int irq) desc->handle_irq = handle_bad_irq; desc->chip = &no_irq_chip; desc->name = NULL; + clear_kstat_irqs(desc); spin_unlock_irqrestore(&desc->lock, flags); } @@ -384,6 +385,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc) out_unlock: spin_unlock(&desc->lock); } +EXPORT_SYMBOL_GPL(handle_level_irq); /** * handle_fasteoi_irq - irq handler for transparent controllers @@ -595,6 +597,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, } spin_unlock_irqrestore(&desc->lock, flags); } +EXPORT_SYMBOL_GPL(__set_irq_handler); void set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip, diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index c20db0be917..759b8b04d29 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -39,6 +39,18 @@ 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 @@ -71,19 +83,21 @@ static struct irq_desc irq_desc_init = { void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr) { - unsigned long bytes; - char *ptr; int node; - - /* Compute how many bytes we need per irq and allocate them */ - bytes = nr * sizeof(unsigned int); + void *ptr; node = cpu_to_node(cpu); - ptr = kzalloc_node(bytes, GFP_ATOMIC, node); - printk(KERN_DEBUG " alloc kstat_irqs on cpu %d node %d\n", cpu, node); + ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs), GFP_ATOMIC, node); - if (ptr) - desc->kstat_irqs = (unsigned int *)ptr; + /* + * don't overwite if can not get new one + * init_copy_kstat_irqs() could still use old one + */ + if (ptr) { + printk(KERN_DEBUG " alloc kstat_irqs on cpu %d node %d\n", + cpu, node); + desc->kstat_irqs = ptr; + } } static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) @@ -134,6 +148,8 @@ int __init early_irq_init(void) int legacy_count; int i; + init_irq_default_affinity(); + desc = irq_desc_legacy; legacy_count = ARRAY_SIZE(irq_desc_legacy); @@ -213,17 +229,22 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { } }; +static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS]; int __init early_irq_init(void) { struct irq_desc *desc; int count; int i; + init_irq_default_affinity(); + desc = irq_desc; count = ARRAY_SIZE(irq_desc); - for (i = 0; i < count; i++) + for (i = 0; i < count; i++) { desc[i].irq = i; + desc[i].kstat_irqs = kstat_irqs_all[i]; + } return arch_early_irq_init(); } @@ -239,6 +260,11 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) } #endif /* !CONFIG_SPARSE_IRQ */ +void clear_kstat_irqs(struct irq_desc *desc) +{ + memset(desc->kstat_irqs, 0, nr_cpu_ids * sizeof(*(desc->kstat_irqs))); +} + /* * What should we do if we get a hw irq event on an illegal vector? * Each architecture has to answer this themself. @@ -451,12 +477,10 @@ void early_init_irq_lock_class(void) } } -#ifdef CONFIG_SPARSE_IRQ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { struct irq_desc *desc = irq_to_desc(irq); return desc ? desc->kstat_irqs[cpu] : 0; } -#endif EXPORT_SYMBOL(kstat_irqs_cpu); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index e6d0a43cc12..b60950bf5a1 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -15,6 +15,7 @@ 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 void clear_kstat_irqs(struct irq_desc *desc); extern spinlock_t sparse_irq_lock; extern struct irq_desc *irq_desc_ptrs[NR_IRQS]; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 1c505506917..cbc3828faf5 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 @@ -117,7 +109,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) /* * Generic version of the affinity autoselector. */ -int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc) +static int setup_affinity(unsigned int irq, struct irq_desc *desc) { if (!irq_can_set_affinity(irq)) return 0; @@ -141,7 +133,7 @@ set_affinity: return 0; } #else -static inline int do_irq_select_affinity(unsigned int irq, struct irq_desc *d) +static inline int setup_affinity(unsigned int irq, struct irq_desc *d) { return irq_select_affinity(irq); } @@ -157,14 +149,14 @@ int irq_select_affinity_usr(unsigned int irq) int ret; spin_lock_irqsave(&desc->lock, flags); - ret = do_irq_select_affinity(irq, desc); + ret = setup_affinity(irq, desc); spin_unlock_irqrestore(&desc->lock, flags); return ret; } #else -static inline int do_irq_select_affinity(int irq, struct irq_desc *desc) +static inline int setup_affinity(unsigned int irq, struct irq_desc *desc) { return 0; } @@ -496,7 +488,7 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new) desc->status |= IRQ_NO_BALANCING; /* Set default affinity mask once everything is setup */ - do_irq_select_affinity(irq, desc); + setup_affinity(irq, desc); } else if ((new->flags & IRQF_TRIGGER_MASK) && (new->flags & IRQF_TRIGGER_MASK) diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c index ecf765c6a77..aef18ab6b75 100644 --- a/kernel/irq/numa_migrate.c +++ b/kernel/irq/numa_migrate.c @@ -17,16 +17,11 @@ static void init_copy_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc, int cpu, int nr) { - unsigned long bytes; - init_kstat_irqs(desc, cpu, nr); - if (desc->kstat_irqs != old_desc->kstat_irqs) { - /* Compute how many bytes we need per irq and allocate them */ - bytes = nr * sizeof(unsigned int); - - memcpy(desc->kstat_irqs, old_desc->kstat_irqs, bytes); - } + if (desc->kstat_irqs != old_desc->kstat_irqs) + memcpy(desc->kstat_irqs, old_desc->kstat_irqs, + nr * sizeof(*desc->kstat_irqs)); } static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc) @@ -71,7 +66,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, desc = irq_desc_ptrs[irq]; if (desc && old_desc != desc) - goto out_unlock; + goto out_unlock; node = cpu_to_node(cpu); desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node); @@ -84,10 +79,15 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, init_copy_one_irq_desc(irq, old_desc, desc, cpu); irq_desc_ptrs[irq] = desc; + spin_unlock_irqrestore(&sparse_irq_lock, flags); /* free the old one */ free_one_irq_desc(old_desc, desc); + spin_unlock(&old_desc->lock); kfree(old_desc); + spin_lock(&desc->lock); + + return desc; out_unlock: spin_unlock_irqrestore(&sparse_irq_lock, flags); diff --git a/kernel/itimer.c b/kernel/itimer.c index 6a5fe93dd8b..58762f7077e 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -62,7 +62,7 @@ int do_getitimer(int which, struct itimerval *value) struct task_cputime cputime; cputime_t utime; - thread_group_cputime(tsk, &cputime); + thread_group_cputimer(tsk, &cputime); utime = cputime.utime; if (cputime_le(cval, utime)) { /* about to fire */ cval = jiffies_to_cputime(1); @@ -82,7 +82,7 @@ int do_getitimer(int which, struct itimerval *value) struct task_cputime times; cputime_t ptime; - thread_group_cputime(tsk, ×); + thread_group_cputimer(tsk, ×); ptime = cputime_add(times.utime, times.stime); if (cputime_le(cval, ptime)) { /* about to fire */ cval = jiffies_to_cputime(1); diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index e694afa0eb8..7b8b0f21a5b 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/kprobes.c b/kernel/kprobes.c index 1b9cbdc0127..7ba8cd9845c 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -123,7 +123,7 @@ static int collect_garbage_slots(void); static int __kprobes check_safety(void) { int ret = 0; -#if defined(CONFIG_PREEMPT) && defined(CONFIG_PM) +#if defined(CONFIG_PREEMPT) && defined(CONFIG_FREEZER) ret = freeze_processes(); if (ret == 0) { struct task_struct *p, *q; diff --git a/kernel/module.c b/kernel/module.c index e8b51d41dd7..ba22484a987 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/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 157de3a4783..2313a4cc14e 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) @@ -300,6 +230,71 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, return 0; } +void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) +{ + struct sighand_struct *sighand; + struct signal_struct *sig; + struct task_struct *t; + + *times = INIT_CPUTIME; + + rcu_read_lock(); + sighand = rcu_dereference(tsk->sighand); + if (!sighand) + goto out; + + sig = tsk->signal; + + t = tsk; + do { + times->utime = cputime_add(times->utime, t->utime); + times->stime = cputime_add(times->stime, t->stime); + times->sum_exec_runtime += t->se.sum_exec_runtime; + + t = next_thread(t); + } while (t != tsk); + + times->utime = cputime_add(times->utime, sig->utime); + times->stime = cputime_add(times->stime, sig->stime); + times->sum_exec_runtime += sig->sum_sched_runtime; +out: + rcu_read_unlock(); +} + +static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b) +{ + if (cputime_gt(b->utime, a->utime)) + a->utime = b->utime; + + if (cputime_gt(b->stime, a->stime)) + a->stime = b->stime; + + if (b->sum_exec_runtime > a->sum_exec_runtime) + a->sum_exec_runtime = b->sum_exec_runtime; +} + +void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct task_cputime sum; + unsigned long flags; + + spin_lock_irqsave(&cputimer->lock, flags); + if (!cputimer->running) { + cputimer->running = 1; + /* + * The POSIX timer interface allows for absolute time expiry + * values through the TIMER_ABSTIME flag, therefore we have + * to synchronize the timer to the clock every time we start + * it. + */ + thread_group_cputime(tsk, &sum); + update_gt_cputime(&cputimer->cputime, &sum); + } + *times = cputimer->cputime; + spin_unlock_irqrestore(&cputimer->lock, flags); +} + /* * Sample a process (thread group) clock for the given group_leader task. * Must be called with tasklist_lock held for reading. @@ -527,7 +522,7 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk) { struct task_cputime cputime; - thread_group_cputime(tsk, &cputime); + thread_group_cputimer(tsk, &cputime); cleanup_timers(tsk->signal->cpu_timers, cputime.utime, cputime.stime, cputime.sum_exec_runtime); } @@ -1034,6 +1029,19 @@ static void check_thread_timers(struct task_struct *tsk, } } +static void stop_process_timers(struct task_struct *tsk) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + unsigned long flags; + + if (!cputimer->running) + return; + + spin_lock_irqsave(&cputimer->lock, flags); + cputimer->running = 0; + spin_unlock_irqrestore(&cputimer->lock, flags); +} + /* * Check for any per-thread CPU timers that have fired and move them * off the tsk->*_timers list onto the firing list. Per-thread timers @@ -1057,13 +1065,15 @@ static void check_process_timers(struct task_struct *tsk, sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY && list_empty(&timers[CPUCLOCK_VIRT]) && cputime_eq(sig->it_virt_expires, cputime_zero) && - list_empty(&timers[CPUCLOCK_SCHED])) + list_empty(&timers[CPUCLOCK_SCHED])) { + stop_process_timers(tsk); return; + } /* * Collect the current process totals. */ - thread_group_cputime(tsk, &cputime); + thread_group_cputimer(tsk, &cputime); utime = cputime.utime; ptime = cputime_add(utime, cputime.stime); sum_sched_runtime = cputime.sum_exec_runtime; @@ -1329,7 +1339,7 @@ static inline int fastpath_timer_check(struct task_struct *tsk) if (!task_cputime_zero(&sig->cputime_expires)) { struct task_cputime group_sample; - thread_group_cputime(tsk, &group_sample); + thread_group_cputimer(tsk, &group_sample); if (task_cputime_expired(&group_sample, &sig->cputime_expires)) return 1; } @@ -1399,6 +1409,33 @@ void run_posix_cpu_timers(struct task_struct *tsk) } /* + * Sample a process (thread group) timer for the given group_leader task. + * Must be called with tasklist_lock held for reading. + */ +static int cpu_timer_sample_group(const clockid_t which_clock, + struct task_struct *p, + union cpu_time_count *cpu) +{ + struct task_cputime cputime; + + thread_group_cputimer(p, &cputime); + switch (CPUCLOCK_WHICH(which_clock)) { + default: + return -EINVAL; + case CPUCLOCK_PROF: + cpu->cpu = cputime_add(cputime.utime, cputime.stime); + break; + case CPUCLOCK_VIRT: + cpu->cpu = cputime.utime; + break; + case CPUCLOCK_SCHED: + cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p); + break; + } + return 0; +} + +/* * Set one of the process-wide special case CPU timers. * The tsk->sighand->siglock must be held by the caller. * The *newval argument is relative and we update it to be absolute, *oldval @@ -1411,7 +1448,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, struct list_head *head; BUG_ON(clock_idx == CPUCLOCK_SCHED); - cpu_clock_sample_group(clock_idx, tsk, &now); + cpu_timer_sample_group(clock_idx, tsk, &now); if (oldval) { if (!cputime_eq(*oldval, cputime_zero)) { diff --git a/kernel/power/Makefile b/kernel/power/Makefile index 597823b5b70..d7a10167a25 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -4,7 +4,8 @@ EXTRA_CFLAGS += -DDEBUG endif obj-y := main.o -obj-$(CONFIG_PM_SLEEP) += process.o console.o +obj-$(CONFIG_PM_SLEEP) += console.o +obj-$(CONFIG_FREEZER) += process.o obj-$(CONFIG_HIBERNATION) += swsusp.o disk.o snapshot.o swap.o user.o obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 45e8541ab7e..432ee575c9e 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 23998887397..b4d219016b6 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/profile.c b/kernel/profile.c index 784933acf5b..7724e0409ba 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -114,12 +114,15 @@ int __ref profile_init(void) if (!slab_is_available()) { prof_buffer = alloc_bootmem(buffer_bytes); alloc_bootmem_cpumask_var(&prof_cpu_mask); + cpumask_copy(prof_cpu_mask, cpu_possible_mask); return 0; } if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL)) return -ENOMEM; + cpumask_copy(prof_cpu_mask, cpu_possible_mask); + prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL); if (prof_buffer) return 0; diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c index 490934fc7ac..bd5a9003497 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 f2d8638e6c6..b2fd602a6f6 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 09ac2008f77..9d79b7854fa 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(); diff --git a/kernel/sched.c b/kernel/sched.c index 52bbf1c842a..c1d0ed36008 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3880,19 +3880,24 @@ int select_nohz_load_balancer(int stop_tick) int cpu = smp_processor_id(); if (stop_tick) { - cpumask_set_cpu(cpu, nohz.cpu_mask); cpu_rq(cpu)->in_nohz_recently = 1; - /* - * If we are going offline and still the leader, give up! - */ - if (!cpu_active(cpu) && - atomic_read(&nohz.load_balancer) == cpu) { + if (!cpu_active(cpu)) { + if (atomic_read(&nohz.load_balancer) != cpu) + return 0; + + /* + * If we are going offline and still the leader, + * give up! + */ if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) BUG(); + return 0; } + cpumask_set_cpu(cpu, nohz.cpu_mask); + /* time for ilb owner also to sleep */ if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { if (atomic_read(&nohz.load_balancer) == cpu) @@ -4687,8 +4692,8 @@ EXPORT_SYMBOL(default_wake_function); * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns * zero in this (rare) case, and we handle it by continuing to scan the queue. */ -static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, - int nr_exclusive, int sync, void *key) +void __wake_up_common(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, int sync, void *key) { wait_queue_t *curr, *next; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 5cc1c162044..0566f2a03c4 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 @@ -1452,6 +1464,11 @@ 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_rt.c b/kernel/sched_rt.c index 954e1a81b79..bac1061cea2 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -968,8 +968,8 @@ static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask) if ((this_cpu != -1) && cpu_isset(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; diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index f2773b5d122..a8f93dd374e 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -296,20 +296,21 @@ 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 signal_struct *sig; + struct thread_group_cputimer *cputimer; /* tsk == current, ensure it is safe to use ->signal */ if (unlikely(tsk->exit_state)) return; - sig = tsk->signal; - if (sig->cputime.totals) { - struct task_cputime *times; + cputimer = &tsk->signal->cputimer; - times = per_cpu_ptr(sig->cputime.totals, get_cpu()); - times->utime = cputime_add(times->utime, cputime); - put_cpu_no_resched(); - } + if (!cputimer->running) + return; + + spin_lock(&cputimer->lock); + cputimer->cputime.utime = + cputime_add(cputimer->cputime.utime, cputime); + spin_unlock(&cputimer->lock); } /** @@ -325,20 +326,21 @@ 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 signal_struct *sig; + struct thread_group_cputimer *cputimer; /* tsk == current, ensure it is safe to use ->signal */ if (unlikely(tsk->exit_state)) return; - sig = tsk->signal; - if (sig->cputime.totals) { - struct task_cputime *times; + cputimer = &tsk->signal->cputimer; - times = per_cpu_ptr(sig->cputime.totals, get_cpu()); - times->stime = cputime_add(times->stime, cputime); - put_cpu_no_resched(); - } + if (!cputimer->running) + return; + + spin_lock(&cputimer->lock); + cputimer->cputime.stime = + cputime_add(cputimer->cputime.stime, cputime); + spin_unlock(&cputimer->lock); } /** @@ -354,6 +356,7 @@ 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 thread_group_cputimer *cputimer; struct signal_struct *sig; sig = tsk->signal; @@ -362,11 +365,12 @@ static inline void account_group_exec_runtime(struct task_struct *tsk, if (unlikely(!sig)) return; - if (sig->cputime.totals) { - struct task_cputime *times; + cputimer = &sig->cputimer; - times = per_cpu_ptr(sig->cputime.totals, get_cpu()); - times->sum_exec_runtime += ns; - put_cpu_no_resched(); - } + if (!cputimer->running) + return; + + spin_lock(&cputimer->lock); + cputimer->cputime.sum_exec_runtime += ns; + spin_unlock(&cputimer->lock); } diff --git a/kernel/signal.c b/kernel/signal.c index e73759783dc..2a74fe87c0d 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) @@ -1365,7 +1367,6 @@ int do_notify_parent(struct task_struct *tsk, int sig) struct siginfo info; unsigned long flags; struct sighand_struct *psig; - struct task_cputime cputime; int ret = sig; BUG_ON(sig == -1); @@ -1395,9 +1396,10 @@ int do_notify_parent(struct task_struct *tsk, int sig) info.si_uid = __task_cred(tsk)->uid; rcu_read_unlock(); - thread_group_cputime(tsk, &cputime); - info.si_utime = cputime_to_jiffies(cputime.utime); - info.si_stime = cputime_to_jiffies(cputime.stime); + info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime, + tsk->signal->utime)); + info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime, + tsk->signal->stime)); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) diff --git a/kernel/smp.c b/kernel/smp.c index 5cfa0e5e3e8..bbedbb7efe3 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/softlockup.c b/kernel/softlockup.c index d9188c66278..85d5a245510 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: diff --git a/kernel/sys.c b/kernel/sys.c index e7dc0e10a48..f145c415bc1 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1525,22 +1525,14 @@ SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim) return -EINVAL; if (copy_from_user(&new_rlim, rlim, sizeof(*rlim))) return -EFAULT; + if (new_rlim.rlim_cur > new_rlim.rlim_max) + return -EINVAL; old_rlim = current->signal->rlim + resource; if ((new_rlim.rlim_max > old_rlim->rlim_max) && !capable(CAP_SYS_RESOURCE)) return -EPERM; - - if (resource == RLIMIT_NOFILE) { - if (new_rlim.rlim_max == RLIM_INFINITY) - new_rlim.rlim_max = sysctl_nr_open; - if (new_rlim.rlim_cur == RLIM_INFINITY) - new_rlim.rlim_cur = sysctl_nr_open; - if (new_rlim.rlim_max > sysctl_nr_open) - return -EPERM; - } - - if (new_rlim.rlim_cur > new_rlim.rlim_max) - return -EINVAL; + if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open) + return -EPERM; retval = security_task_setrlimit(resource, &new_rlim); if (retval) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 368d1638ee7..c5ef44ff850 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -101,6 +101,7 @@ static int two = 2; static int zero; static int one = 1; +static unsigned long one_ul = 1; static int one_hundred = 100; /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ @@ -809,7 +810,7 @@ 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, @@ -974,7 +975,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &dirty_background_bytes_handler, .strategy = &sysctl_intvec, - .extra1 = &one, + .extra1 = &one_ul, }, { .ctl_name = VM_DIRTY_RATIO, @@ -995,7 +996,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &dirty_bytes_handler, .strategy = &sysctl_intvec, - .extra1 = &one, + .extra1 = &one_ul, }, { .procname = "dirty_writeback_centisecs", diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 63e05d423a0..21a5ca84951 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 1b6c05bd0d0..d3f1ef4d5cb 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/ftrace.c b/kernel/trace/ftrace.c index 2f32969c09d..9a236ffe2aa 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> @@ -1736,9 +1737,12 @@ static void clear_ftrace_pid(struct pid *pid) { struct task_struct *p; + rcu_read_lock(); do_each_pid_task(pid, PIDTYPE_PID, p) { clear_tsk_trace_trace(p); } while_each_pid_task(pid, PIDTYPE_PID, p); + rcu_read_unlock(); + put_pid(pid); } @@ -1746,9 +1750,11 @@ static void set_ftrace_pid(struct pid *pid) { struct task_struct *p; + rcu_read_lock(); do_each_pid_task(pid, PIDTYPE_PID, p) { set_tsk_trace_trace(p); } while_each_pid_task(pid, PIDTYPE_PID, p); + rcu_read_unlock(); } static void clear_ftrace_pid_task(struct pid **pid) @@ -1965,6 +1971,7 @@ 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 +2050,27 @@ 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 +2078,9 @@ 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 +2106,7 @@ 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/ring_buffer.c b/kernel/trace/ring_buffer.c index 8b0daf0662e..bd38c5cfd8a 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -246,7 +246,7 @@ 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. @@ -1025,12 +1025,8 @@ __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 +1101,10 @@ __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; @@ -2174,6 +2174,9 @@ 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; } /** diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c580233add9..17bb88d86ac 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -40,7 +40,7 @@ #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; /* @@ -3736,7 +3736,7 @@ 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 +3770,7 @@ void ftrace_dump(void) dump_ran = 1; /* No turning back! */ + tracing_off(); ftrace_kill(); for_each_tracing_cpu(cpu) { diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 7c2e326bbc8..62a78d94353 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_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 43586b689e3..42ae1e77b6b 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -333,6 +333,7 @@ static void stop_wakeup_tracer(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; diff --git a/kernel/wait.c b/kernel/wait.c index cd87131f2fc..42a2dbc181c 100644 --- a/kernel/wait.c +++ b/kernel/wait.c @@ -91,6 +91,15 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state) } EXPORT_SYMBOL(prepare_to_wait_exclusive); +/* + * finish_wait - clean up after waiting in a queue + * @q: waitqueue waited on + * @wait: wait descriptor + * + * Sets current thread back to running state and removes + * the wait descriptor from the given waitqueue if still + * queued. + */ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait) { unsigned long flags; @@ -117,6 +126,39 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait) } EXPORT_SYMBOL(finish_wait); +/* + * abort_exclusive_wait - abort exclusive waiting in a queue + * @q: waitqueue waited on + * @wait: wait descriptor + * @state: runstate of the waiter to be woken + * @key: key to identify a wait bit queue or %NULL + * + * Sets current thread back to running state and removes + * the wait descriptor from the given waitqueue if still + * queued. + * + * Wakes up the next waiter if the caller is concurrently + * woken up through the queue. + * + * This prevents waiter starvation where an exclusive waiter + * aborts and is woken up concurrently and noone wakes up + * the next waiter. + */ +void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, + unsigned int mode, void *key) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + spin_lock_irqsave(&q->lock, flags); + if (!list_empty(&wait->task_list)) + list_del_init(&wait->task_list); + else if (waitqueue_active(q)) + __wake_up_common(q, mode, 1, 0, key); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(abort_exclusive_wait); + int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) { int ret = default_wake_function(wait, mode, sync, key); @@ -177,17 +219,20 @@ int __sched __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, int (*action)(void *), unsigned mode) { - int ret = 0; - do { + int ret; + prepare_to_wait_exclusive(wq, &q->wait, mode); - if (test_bit(q->key.bit_nr, q->key.flags)) { - if ((ret = (*action)(q->key.flags))) - break; - } + if (!test_bit(q->key.bit_nr, q->key.flags)) + continue; + ret = action(q->key.flags); + if (!ret) + continue; + abort_exclusive_wait(wq, &q->wait, mode, &q->key); + return ret; } while (test_and_set_bit(q->key.bit_nr, q->key.flags)); finish_wait(wq, &q->wait); - return ret; + return 0; } EXPORT_SYMBOL(__wait_on_bit_lock); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2f445833ae3..1f0c509b40d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -971,6 +971,8 @@ 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 +993,8 @@ 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 +1003,8 @@ 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 +1021,8 @@ 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 } |