diff options
author | Haavard Skinnemoen <haavard.skinnemoen@atmel.com> | 2009-03-27 16:14:38 +0100 |
---|---|---|
committer | Haavard Skinnemoen <haavard.skinnemoen@atmel.com> | 2009-03-27 16:14:38 +0100 |
commit | b92efa9abffc4a634cd2e7a0f81f8aa6310d67c9 (patch) | |
tree | 9847508d9b8d4e585f90db4a453bfbc3700c997e /kernel | |
parent | a16fffdd8eb95ebab7dc22414896fe6493951e0e (diff) | |
parent | be0ea69674ed95e1e98cb3687a241badc756d228 (diff) |
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into avr32-arch
Diffstat (limited to 'kernel')
71 files changed, 2936 insertions, 1202 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 170a9213c1b..e4791b3ba55 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -51,6 +51,7 @@ obj-$(CONFIG_UID16) += uid16.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_PM) += power/ +obj-$(CONFIG_FREEZER) += power/ obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o 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..9edb5c4b79b 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1115,13 +1115,15 @@ 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); - kfree(root); kill_litter_super(sb); + kfree(root); } static struct file_system_type cgroup_fs_type = { @@ -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..4854c2c4a82 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. */ @@ -1179,10 +1179,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, #endif clear_all_latency_tracing(p); - /* Our parent execution domain becomes current domain - These must match for thread signalling to apply */ - p->parent_exec_id = p->self_exec_id; - /* ok, now we should be set up.. */ p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL); p->pdeath_signal = 0; @@ -1220,10 +1216,13 @@ static struct task_struct *copy_process(unsigned long clone_flags, set_task_cpu(p, smp_processor_id()); /* CLONE_PARENT re-uses the old parent */ - if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) + if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; - else + p->parent_exec_id = current->parent_exec_id; + } else { p->real_parent = current; + p->parent_exec_id = current->self_exec_id; + } spin_lock(¤t->sighand->siglock); diff --git a/kernel/futex.c b/kernel/futex.c index f89d373a9c6..438701adce2 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1165,6 +1165,7 @@ static int futex_wait(u32 __user *uaddr, int fshared, u32 val, ktime_t *abs_time, u32 bitset, int clockrt) { struct task_struct *curr = current; + struct restart_block *restart; DECLARE_WAITQUEUE(wait, curr); struct futex_hash_bucket *hb; struct futex_q q; @@ -1216,11 +1217,13 @@ retry: if (!ret) goto retry; - return ret; + goto out; } ret = -EWOULDBLOCK; - if (uval != val) - goto out_unlock_put_key; + if (unlikely(uval != val)) { + queue_unlock(&q, hb); + goto out_put_key; + } /* Only actually queue if *uaddr contained val. */ queue_me(&q, hb); @@ -1284,38 +1287,38 @@ retry: */ /* If we were woken (and unqueued), we succeeded, whatever. */ + ret = 0; if (!unqueue_me(&q)) - return 0; + goto out_put_key; + ret = -ETIMEDOUT; if (rem) - return -ETIMEDOUT; + goto out_put_key; /* * We expect signal_pending(current), but another thread may * have handled it for us already. */ + ret = -ERESTARTSYS; if (!abs_time) - return -ERESTARTSYS; - else { - struct restart_block *restart; - restart = ¤t_thread_info()->restart_block; - restart->fn = futex_wait_restart; - restart->futex.uaddr = (u32 *)uaddr; - restart->futex.val = val; - restart->futex.time = abs_time->tv64; - restart->futex.bitset = bitset; - restart->futex.flags = 0; - - if (fshared) - restart->futex.flags |= FLAGS_SHARED; - if (clockrt) - restart->futex.flags |= FLAGS_CLOCKRT; - return -ERESTART_RESTARTBLOCK; - } + goto out_put_key; -out_unlock_put_key: - queue_unlock(&q, hb); - put_futex_key(fshared, &q.key); + restart = ¤t_thread_info()->restart_block; + restart->fn = futex_wait_restart; + restart->futex.uaddr = (u32 *)uaddr; + restart->futex.val = val; + restart->futex.time = abs_time->tv64; + restart->futex.bitset = bitset; + restart->futex.flags = 0; + + if (fshared) + restart->futex.flags |= FLAGS_SHARED; + if (clockrt) + restart->futex.flags |= FLAGS_CLOCKRT; + ret = -ERESTART_RESTARTBLOCK; + +out_put_key: + put_futex_key(fshared, &q.key); out: return ret; } 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 f63c706d25e..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); } @@ -290,7 +291,8 @@ 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); } } @@ -383,6 +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 @@ -475,7 +478,8 @@ 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.*/ @@ -593,6 +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..f6cdda68e5c 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. @@ -312,6 +338,8 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) irqreturn_t ret, retval = IRQ_NONE; unsigned int status = 0; + WARN_ONCE(!in_irq(), "BUG: IRQ handler called from non-hardirq context!"); + if (!(action->flags & IRQF_DISABLED)) local_irq_enable_in_hardirq(); @@ -331,6 +359,11 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) } #ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ + +#ifdef CONFIG_ENABLE_WARN_DEPRECATED +# warning __do_IRQ is deprecated. Please convert to proper flow handlers +#endif + /** * __do_IRQ - original all in one highlevel IRQ handler * @irq: the interrupt number @@ -451,12 +484,10 @@ 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 cd0cd8dcb34..ea119effe09 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; } @@ -397,9 +389,9 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, * allocate special interrupts that are part of the architecture. */ static int -__setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new) +__setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) { - struct irqaction *old, **p; + struct irqaction *old, **old_ptr; const char *old_name = NULL; unsigned long flags; int shared = 0; @@ -431,8 +423,8 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new) * The following block of code has to be executed atomically */ spin_lock_irqsave(&desc->lock, flags); - p = &desc->action; - old = *p; + old_ptr = &desc->action; + old = *old_ptr; if (old) { /* * Can't share interrupts unless both agree to and are @@ -455,8 +447,8 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new) /* add new interrupt at end of irq queue */ do { - p = &old->next; - old = *p; + old_ptr = &old->next; + old = *old_ptr; } while (old); shared = 1; } @@ -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) @@ -507,7 +499,7 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new) (int)(new->flags & IRQF_TRIGGER_MASK)); } - *p = new; + *old_ptr = new; /* Reset broken irq detection when installing new handler */ desc->irq_count = 0; @@ -557,90 +549,117 @@ int setup_irq(unsigned int irq, struct irqaction *act) return __setup_irq(irq, desc, act); } +EXPORT_SYMBOL_GPL(setup_irq); -/** - * free_irq - free an interrupt - * @irq: Interrupt line to free - * @dev_id: Device identity to free - * - * Remove an interrupt handler. The handler is removed and if the - * interrupt line is no longer in use by any driver it is disabled. - * On a shared IRQ the caller must ensure the interrupt is disabled - * on the card it drives before calling this function. The function - * does not return until any executing interrupts for this IRQ - * have completed. - * - * This function must not be called from interrupt context. + /* + * Internal function to unregister an irqaction - used to free + * regular and special interrupts that are part of the architecture. */ -void free_irq(unsigned int irq, void *dev_id) +static struct irqaction *__free_irq(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); - struct irqaction **p; + struct irqaction *action, **action_ptr; unsigned long flags; - WARN_ON(in_interrupt()); + WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); if (!desc) - return; + return NULL; spin_lock_irqsave(&desc->lock, flags); - p = &desc->action; + + /* + * There can be multiple actions per IRQ descriptor, find the right + * one based on the dev_id: + */ + action_ptr = &desc->action; for (;;) { - struct irqaction *action = *p; + action = *action_ptr; - if (action) { - struct irqaction **pp = p; + if (!action) { + WARN(1, "Trying to free already-free IRQ %d\n", irq); + spin_unlock_irqrestore(&desc->lock, flags); - p = &action->next; - if (action->dev_id != dev_id) - continue; + return NULL; + } - /* Found it - now remove it from the list of entries */ - *pp = action->next; + if (action->dev_id == dev_id) + break; + action_ptr = &action->next; + } + + /* Found it - now remove it from the list of entries: */ + *action_ptr = action->next; - /* Currently used only by UML, might disappear one day.*/ + /* Currently used only by UML, might disappear one day: */ #ifdef CONFIG_IRQ_RELEASE_METHOD - if (desc->chip->release) - desc->chip->release(irq, dev_id); + if (desc->chip->release) + desc->chip->release(irq, dev_id); #endif - if (!desc->action) { - desc->status |= IRQ_DISABLED; - if (desc->chip->shutdown) - desc->chip->shutdown(irq); - else - desc->chip->disable(irq); - } - spin_unlock_irqrestore(&desc->lock, flags); - unregister_handler_proc(irq, action); + /* If this was the last handler, shut down the IRQ line: */ + if (!desc->action) { + desc->status |= IRQ_DISABLED; + if (desc->chip->shutdown) + desc->chip->shutdown(irq); + else + desc->chip->disable(irq); + } + spin_unlock_irqrestore(&desc->lock, flags); + + unregister_handler_proc(irq, action); + + /* Make sure it's not being used on another CPU: */ + synchronize_irq(irq); - /* Make sure it's not being used on another CPU */ - synchronize_irq(irq); -#ifdef CONFIG_DEBUG_SHIRQ - /* - * It's a shared IRQ -- the driver ought to be - * prepared for it to happen even now it's - * being freed, so let's make sure.... We do - * this after actually deregistering it, to - * make sure that a 'real' IRQ doesn't run in - * parallel with our fake - */ - if (action->flags & IRQF_SHARED) { - local_irq_save(flags); - action->handler(irq, dev_id); - local_irq_restore(flags); - } -#endif - kfree(action); - return; - } - printk(KERN_ERR "Trying to free already-free IRQ %d\n", irq); #ifdef CONFIG_DEBUG_SHIRQ - dump_stack(); -#endif - spin_unlock_irqrestore(&desc->lock, flags); - return; + /* + * It's a shared IRQ -- the driver ought to be prepared for an IRQ + * event to happen even now it's being freed, so let's make sure that + * is so by doing an extra call to the handler .... + * + * ( We do this after actually deregistering it, to make sure that a + * 'real' IRQ doesn't run in * parallel with our fake. ) + */ + if (action->flags & IRQF_SHARED) { + local_irq_save(flags); + action->handler(irq, dev_id); + local_irq_restore(flags); } +#endif + return action; +} + +/** + * remove_irq - free an interrupt + * @irq: Interrupt line to free + * @act: irqaction for the interrupt + * + * Used to remove interrupts statically setup by the early boot process. + */ +void remove_irq(unsigned int irq, struct irqaction *act) +{ + __free_irq(irq, act->dev_id); +} +EXPORT_SYMBOL_GPL(remove_irq); + +/** + * free_irq - free an interrupt allocated with request_irq + * @irq: Interrupt line to free + * @dev_id: Device identity to free + * + * Remove an interrupt handler. The handler is removed and if the + * interrupt line is no longer in use by any driver it is disabled. + * On a shared IRQ the caller must ensure the interrupt is disabled + * on the card it drives before calling this function. The function + * does not return until any executing interrupts for this IRQ + * have completed. + * + * This function must not be called from interrupt context. + */ +void free_irq(unsigned int irq, void *dev_id) +{ + kfree(__free_irq(irq, dev_id)); } EXPORT_SYMBOL(free_irq); @@ -687,11 +706,12 @@ int request_irq(unsigned int irq, irq_handler_t handler, * the behavior is classified as "will not fix" so we need to * start nudging drivers away from using that idiom. */ - if ((irqflags & (IRQF_SHARED|IRQF_DISABLED)) - == (IRQF_SHARED|IRQF_DISABLED)) - pr_warning("IRQ %d/%s: IRQF_DISABLED is not " - "guaranteed on shared IRQs\n", - irq, devname); + if ((irqflags & (IRQF_SHARED|IRQF_DISABLED)) == + (IRQF_SHARED|IRQF_DISABLED)) { + pr_warning( + "IRQ %d/%s: IRQF_DISABLED is not guaranteed on shared IRQs\n", + irq, devname); + } #ifdef CONFIG_LOCKDEP /* @@ -717,15 +737,13 @@ int request_irq(unsigned int irq, irq_handler_t handler, if (!handler) return -EINVAL; - action = kmalloc(sizeof(struct irqaction), GFP_ATOMIC); + action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!action) return -ENOMEM; action->handler = handler; action->flags = irqflags; - cpus_clear(action->mask); action->name = devname; - action->next = NULL; action->dev_id = dev_id; retval = __setup_irq(irq, desc, action); 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/irq/spurious.c b/kernel/irq/spurious.c index dd364c11e56..4d568294de3 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/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/kexec.c b/kernel/kexec.c index 8a6d7b08864..48389957825 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1465,6 +1465,11 @@ int kernel_kexec(void) error = device_power_down(PMSG_FREEZE); if (error) goto Enable_irqs; + + /* Suspend system devices */ + error = sysdev_suspend(PMSG_FREEZE); + if (error) + goto Power_up_devices; } else #endif { @@ -1477,6 +1482,8 @@ int kernel_kexec(void) #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { + sysdev_resume(); + Power_up_devices: device_power_up(PMSG_RESTORE); Enable_irqs: local_irq_enable(); 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/latencytop.c b/kernel/latencytop.c index 449db466bdb..ca07c5c0c91 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -9,6 +9,44 @@ * as published by the Free Software Foundation; version 2 * of the License. */ + +/* + * CONFIG_LATENCYTOP enables a kernel latency tracking infrastructure that is + * used by the "latencytop" userspace tool. The latency that is tracked is not + * the 'traditional' interrupt latency (which is primarily caused by something + * else consuming CPU), but instead, it is the latency an application encounters + * because the kernel sleeps on its behalf for various reasons. + * + * This code tracks 2 levels of statistics: + * 1) System level latency + * 2) Per process latency + * + * The latency is stored in fixed sized data structures in an accumulated form; + * if the "same" latency cause is hit twice, this will be tracked as one entry + * in the data structure. Both the count, total accumulated latency and maximum + * latency are tracked in this data structure. When the fixed size structure is + * full, no new causes are tracked until the buffer is flushed by writing to + * the /proc file; the userspace tool does this on a regular basis. + * + * A latency cause is identified by a stringified backtrace at the point that + * the scheduler gets invoked. The userland tool will use this string to + * identify the cause of the latency in human readable form. + * + * The information is exported via /proc/latency_stats and /proc/<pid>/latency. + * These files look like this: + * + * Latency Top version : v0.1 + * 70 59433 4897 i915_irq_wait drm_ioctl vfs_ioctl do_vfs_ioctl sys_ioctl + * | | | | + * | | | +----> the stringified backtrace + * | | +---------> The maximum latency for this entry in microseconds + * | +--------------> The accumulated latency for this entry (microseconds) + * +-------------------> The number of times this entry is hit + * + * (note: the average latency is the accumulated latency divided by the number + * of times) + */ + #include <linux/latencytop.h> #include <linux/kallsyms.h> #include <linux/seq_file.h> @@ -72,7 +110,7 @@ account_global_scheduler_latency(struct task_struct *tsk, struct latency_record firstnonnull = i; continue; } - for (q = 0 ; q < LT_BACKTRACEDEPTH ; q++) { + for (q = 0; q < LT_BACKTRACEDEPTH; q++) { unsigned long record = lat->backtrace[q]; if (latency_record[i].backtrace[q] != record) { @@ -101,31 +139,52 @@ account_global_scheduler_latency(struct task_struct *tsk, struct latency_record memcpy(&latency_record[i], lat, sizeof(struct latency_record)); } -static inline void store_stacktrace(struct task_struct *tsk, struct latency_record *lat) +/* + * Iterator to store a backtrace into a latency record entry + */ +static inline void store_stacktrace(struct task_struct *tsk, + struct latency_record *lat) { struct stack_trace trace; memset(&trace, 0, sizeof(trace)); trace.max_entries = LT_BACKTRACEDEPTH; trace.entries = &lat->backtrace[0]; - trace.skip = 0; save_stack_trace_tsk(tsk, &trace); } +/** + * __account_scheduler_latency - record an occured latency + * @tsk - the task struct of the task hitting the latency + * @usecs - the duration of the latency in microseconds + * @inter - 1 if the sleep was interruptible, 0 if uninterruptible + * + * This function is the main entry point for recording latency entries + * as called by the scheduler. + * + * This function has a few special cases to deal with normal 'non-latency' + * sleeps: specifically, interruptible sleep longer than 5 msec is skipped + * since this usually is caused by waiting for events via select() and co. + * + * Negative latencies (caused by time going backwards) are also explicitly + * skipped. + */ void __sched -account_scheduler_latency(struct task_struct *tsk, int usecs, int inter) +__account_scheduler_latency(struct task_struct *tsk, int usecs, int inter) { unsigned long flags; int i, q; struct latency_record lat; - if (!latencytop_enabled) - return; - /* Long interruptible waits are generally user requested... */ if (inter && usecs > 5000) return; + /* Negative sleeps are time going backwards */ + /* Zero-time sleeps are non-interesting */ + if (usecs <= 0) + return; + memset(&lat, 0, sizeof(lat)); lat.count = 1; lat.time = usecs; @@ -143,12 +202,12 @@ account_scheduler_latency(struct task_struct *tsk, int usecs, int inter) if (tsk->latency_record_count >= LT_SAVECOUNT) goto out_unlock; - for (i = 0; i < LT_SAVECOUNT ; i++) { + for (i = 0; i < LT_SAVECOUNT; i++) { struct latency_record *mylat; int same = 1; mylat = &tsk->latency_record[i]; - for (q = 0 ; q < LT_BACKTRACEDEPTH ; q++) { + for (q = 0; q < LT_BACKTRACEDEPTH; q++) { unsigned long record = lat.backtrace[q]; if (mylat->backtrace[q] != record) { @@ -186,7 +245,7 @@ static int lstats_show(struct seq_file *m, void *v) for (i = 0; i < MAXLR; i++) { if (latency_record[i].backtrace[0]) { int q; - seq_printf(m, "%i %li %li ", + seq_printf(m, "%i %lu %lu ", latency_record[i].count, latency_record[i].time, latency_record[i].max); @@ -223,7 +282,7 @@ static int lstats_open(struct inode *inode, struct file *filp) return single_open(filp, lstats_show, NULL); } -static struct file_operations lstats_fops = { +static const struct file_operations lstats_fops = { .open = lstats_open, .read = seq_read, .write = lstats_write, @@ -236,4 +295,4 @@ static int __init init_lstats_procfs(void) proc_create("latency_stats", 0644, NULL, &lstats_fops); return 0; } -__initcall(init_lstats_procfs); +device_initcall(init_lstats_procfs); diff --git a/kernel/module.c b/kernel/module.c index e8b51d41dd7..77672233387 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); @@ -821,7 +822,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, mutex_lock(&module_mutex); /* Store the name of the last unloaded module for diagnostic purposes */ strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); - unregister_dynamic_debug_module(mod->name); + ddebug_remove_module(mod->name); free_module(mod); out: @@ -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); @@ -1823,19 +1827,13 @@ static inline void add_kallsyms(struct module *mod, } #endif /* CONFIG_KALLSYMS */ -static void dynamic_printk_setup(struct mod_debug *debug, unsigned int num) +static void dynamic_debug_setup(struct _ddebug *debug, unsigned int num) { -#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG - unsigned int i; - - for (i = 0; i < num; i++) { - register_dynamic_debug_module(debug[i].modname, - debug[i].type, - debug[i].logical_modname, - debug[i].flag_names, - debug[i].hash, debug[i].hash2); - } -#endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */ +#ifdef CONFIG_DYNAMIC_DEBUG + if (ddebug_add_module(debug, num, debug->modname)) + printk(KERN_ERR "dynamic debug error adding module: %s\n", + debug->modname); +#endif } static void *module_alloc_update_bounds(unsigned long size) @@ -2070,6 +2068,14 @@ static noinline struct module *load_module(void __user *umod, /* Module has been moved. */ mod = (void *)sechdrs[modindex].sh_addr; +#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_init; + } +#endif /* Now we've moved module, initialize linked lists, etc. */ module_unload_init(mod); @@ -2201,12 +2207,13 @@ static noinline struct module *load_module(void __user *umod, add_kallsyms(mod, sechdrs, symindex, strindex, secstrings); if (!mod->taints) { - struct mod_debug *debug; + struct _ddebug *debug; unsigned int num_debug; debug = section_objs(hdr, sechdrs, secstrings, "__verbose", sizeof(*debug), &num_debug); - dynamic_printk_setup(debug, num_debug); + if (debug) + dynamic_debug_setup(debug, num_debug); } /* sechdrs[0].sh_size is always zero */ @@ -2276,9 +2283,14 @@ static noinline struct module *load_module(void __user *umod, ftrace_release(mod->module_core, mod->core_size); free_unload: module_unload_free(mod); + free_init: +#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) + percpu_modfree(mod->refptr); +#endif module_free(mod, mod->module_init); free_core: module_free(mod, mod->module_core); + /* mod will be freed with core. Don't access it beyond this line! */ free_percpu: if (percpu) percpu_modfree(percpu); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 157de3a4783..8e5d9a68b02 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); } @@ -686,6 +681,33 @@ static void cpu_timer_fire(struct k_itimer *timer) } /* + * 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; +} + +/* * Guts of sys_timer_settime for CPU timers. * This is called with the timer locked and interrupts disabled. * If we return TIMER_RETRY, it's necessary to release the timer's lock @@ -746,7 +768,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags, if (CPUCLOCK_PERTHREAD(timer->it_clock)) { cpu_clock_sample(timer->it_clock, p, &val); } else { - cpu_clock_sample_group(timer->it_clock, p, &val); + cpu_timer_sample_group(timer->it_clock, p, &val); } if (old) { @@ -894,7 +916,7 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) read_unlock(&tasklist_lock); goto dead; } else { - cpu_clock_sample_group(timer->it_clock, p, &now); + cpu_timer_sample_group(timer->it_clock, p, &now); clear_dead = (unlikely(p->exit_state) && thread_group_empty(p)); } @@ -1034,6 +1056,19 @@ 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 +1092,15 @@ 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; @@ -1234,7 +1271,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) clear_dead_task(timer, now); goto out_unlock; } - cpu_clock_sample_group(timer->it_clock, p, &now); + cpu_timer_sample_group(timer->it_clock, p, &now); bump_cpu_timer(timer, now); /* Leave the tasklist_lock locked for the call below. */ } @@ -1329,11 +1366,12 @@ 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; } - return 0; + + return sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY; } /* @@ -1411,7 +1449,7 @@ 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..720ea4f781b 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -3,8 +3,9 @@ ifeq ($(CONFIG_PM_DEBUG),y) EXTRA_CFLAGS += -DDEBUG endif -obj-y := main.o -obj-$(CONFIG_PM_SLEEP) += process.o console.o +obj-$(CONFIG_PM) += main.o +obj-$(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/console.c b/kernel/power/console.c index b8628be2a46..a3961b205de 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -78,6 +78,12 @@ void pm_restore_console(void) } set_console(orig_fgconsole); release_console_sem(); + + if (vt_waitactive(orig_fgconsole)) { + pr_debug("Resume: Can't switch VCs."); + return; + } + kmsg_redirect = orig_kmsg; } #endif diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 45e8541ab7e..4a4a206b197 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) { @@ -219,6 +227,12 @@ static int create_image(int platform_mode) "aborting hibernation\n"); goto Enable_irqs; } + sysdev_suspend(PMSG_FREEZE); + if (error) { + printk(KERN_ERR "PM: Some devices failed to power down, " + "aborting hibernation\n"); + goto Power_up_devices; + } if (hibernation_test(TEST_CORE)) goto Power_up; @@ -234,9 +248,11 @@ static int create_image(int platform_mode) if (!in_suspend) platform_leave(platform_mode); Power_up: + sysdev_resume(); /* NOTE: device_power_up() is just a resume() for devices * that suspended with irqs off ... no overall powerup. */ + Power_up_devices: device_power_up(in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); Enable_irqs: @@ -327,6 +343,7 @@ static int resume_target_kernel(void) "aborting resume\n"); goto Enable_irqs; } + sysdev_suspend(PMSG_QUIESCE); /* We'll ignore saved state, but this gets preempt count (etc) right */ save_processor_state(); error = restore_highmem(); @@ -349,6 +366,7 @@ static int resume_target_kernel(void) swsusp_free(); restore_processor_state(); touch_softlockup_watchdog(); + sysdev_resume(); device_power_up(PMSG_RECOVER); Enable_irqs: local_irq_enable(); @@ -411,6 +429,7 @@ int hibernation_platform_enter(void) if (error) goto Close; + entering_platform_hibernation = true; suspend_console(); error = device_suspend(PMSG_HIBERNATE); if (error) { @@ -431,6 +450,7 @@ int hibernation_platform_enter(void) local_irq_disable(); error = device_power_down(PMSG_HIBERNATE); if (!error) { + sysdev_suspend(PMSG_HIBERNATE); hibernation_ops->enter(); /* We should never get here */ while (1); @@ -445,6 +465,7 @@ int hibernation_platform_enter(void) Finish: hibernation_ops->finish(); Resume_devices: + entering_platform_hibernation = false; device_resume(PMSG_RESTORE); resume_console(); Close: @@ -585,6 +606,12 @@ static int software_resume(void) unsigned int flags; /* + * If the user said "noresume".. bail out early. + */ + if (noresume) + return 0; + + /* * name_to_dev_t() below takes a sysfs buffer mutex when sysfs * is configured into the kernel. Since the regular hibernate * trigger path is via sysfs which takes a buffer mutex before @@ -600,6 +627,11 @@ static int software_resume(void) mutex_unlock(&pm_mutex); return -ENOENT; } + /* + * Some device discovery might still be in progress; we need + * to wait for this to finish. + */ + wait_for_device_probe(); swsusp_resume_device = name_to_dev_t(resume_file); pr_debug("PM: Resume from partition %s\n", resume_file); } else { diff --git a/kernel/power/main.c b/kernel/power/main.c index 23998887397..c9632f841f6 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 /* @@ -298,8 +298,12 @@ static int suspend_enter(suspend_state_t state) goto Done; } - if (!suspend_test(TEST_CORE)) - error = suspend_ops->enter(state); + error = sysdev_suspend(PMSG_SUSPEND); + if (!error) { + if (!suspend_test(TEST_CORE)) + error = suspend_ops->enter(state); + sysdev_resume(); + } device_power_up(PMSG_RESUME); Done: diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 6da14358537..505f319e489 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -60,6 +60,7 @@ static struct block_device *resume_bdev; static int submit(int rw, pgoff_t page_off, struct page *page, struct bio **bio_chain) { + const int bio_rw = rw | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); struct bio *bio; bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1); @@ -80,7 +81,7 @@ static int submit(int rw, pgoff_t page_off, struct page *page, bio_get(bio); if (bio_chain == NULL) { - submit_bio(rw | (1 << BIO_RW_SYNC), bio); + submit_bio(bio_rw, bio); wait_on_page_locked(page); if (rw == READ) bio_set_pages_dirty(bio); @@ -90,7 +91,7 @@ static int submit(int rw, pgoff_t page_off, struct page *page, get_page(page); /* These pages are freed later */ bio->bi_private = *bio_chain; *bio_chain = bio; - submit_bio(rw | (1 << BIO_RW_SYNC), bio); + submit_bio(bio_rw, bio); } return 0; } diff --git a/kernel/power/user.c b/kernel/power/user.c index 005b93d839b..6c85359364f 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -95,15 +95,15 @@ static int snapshot_open(struct inode *inode, struct file *filp) data->swap = swsusp_resume_device ? swap_type_of(swsusp_resume_device, 0, NULL) : -1; data->mode = O_RDONLY; - error = pm_notifier_call_chain(PM_RESTORE_PREPARE); + error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); if (error) - pm_notifier_call_chain(PM_POST_RESTORE); + pm_notifier_call_chain(PM_POST_HIBERNATION); } else { data->swap = -1; data->mode = O_WRONLY; - error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); + error = pm_notifier_call_chain(PM_RESTORE_PREPARE); if (error) - pm_notifier_call_chain(PM_POST_HIBERNATION); + pm_notifier_call_chain(PM_POST_RESTORE); } if (error) atomic_inc(&snapshot_device_available); diff --git a/kernel/printk.c b/kernel/printk.c index 69188f226a9..e3602d0755b 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -73,7 +73,6 @@ EXPORT_SYMBOL(oops_in_progress); * driver system. */ static DECLARE_MUTEX(console_sem); -static DECLARE_MUTEX(secondary_console_sem); struct console *console_drivers; EXPORT_SYMBOL_GPL(console_drivers); @@ -891,12 +890,14 @@ void suspend_console(void) printk("Suspending console(s) (use no_console_suspend to debug)\n"); acquire_console_sem(); console_suspended = 1; + up(&console_sem); } void resume_console(void) { if (!console_suspend_enabled) return; + down(&console_sem); console_suspended = 0; release_console_sem(); } @@ -912,11 +913,9 @@ void resume_console(void) void acquire_console_sem(void) { BUG_ON(in_interrupt()); - if (console_suspended) { - down(&secondary_console_sem); - return; - } down(&console_sem); + if (console_suspended) + return; console_locked = 1; console_may_schedule = 1; } @@ -926,6 +925,10 @@ int try_acquire_console_sem(void) { if (down_trylock(&console_sem)) return -1; + if (console_suspended) { + up(&console_sem); + return -1; + } console_locked = 1; console_may_schedule = 0; return 0; @@ -979,7 +982,7 @@ void release_console_sem(void) unsigned wake_klogd = 0; if (console_suspended) { - up(&secondary_console_sem); + up(&console_sem); return; } 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..654c640a6b9 100644 --- a/kernel/rcuclassic.c +++ b/kernel/rcuclassic.c @@ -679,8 +679,8 @@ int rcu_needs_cpu(int cpu) void rcu_check_callbacks(int cpu, int user) { if (user || - (idle_cpu(cpu) && !in_softirq() && - hardirq_count() <= (1 << HARDIRQ_SHIFT))) { + (idle_cpu(cpu) && rcu_scheduler_active && + !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) { /* * Get here if this CPU took its interrupt from user @@ -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/rcupdate.c b/kernel/rcupdate.c index d92a76a881a..cae8a059cf4 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -44,6 +44,7 @@ #include <linux/cpu.h> #include <linux/mutex.h> #include <linux/module.h> +#include <linux/kernel_stat.h> enum rcu_barrier { RCU_BARRIER_STD, @@ -55,6 +56,7 @@ static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL}; static atomic_t rcu_barrier_cpu_count; static DEFINE_MUTEX(rcu_barrier_mutex); static struct completion rcu_barrier_completion; +int rcu_scheduler_active __read_mostly; /* * Awaken the corresponding synchronize_rcu() instance now that a @@ -80,6 +82,10 @@ void wakeme_after_rcu(struct rcu_head *head) void synchronize_rcu(void) { struct rcu_synchronize rcu; + + if (rcu_blocking_is_gp()) + return; + init_completion(&rcu.completion); /* Will wake me after RCU finished. */ call_rcu(&rcu.head, wakeme_after_rcu); @@ -175,3 +181,9 @@ void __init rcu_init(void) __rcu_init(); } +void rcu_scheduler_starting(void) +{ + WARN_ON(num_online_cpus() != 1); + WARN_ON(nr_context_switches() > 0); + rcu_scheduler_active = 1; +} diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c index 33cfc50781f..5d59e850fb7 100644 --- a/kernel/rcupreempt.c +++ b/kernel/rcupreempt.c @@ -1181,6 +1181,9 @@ void __synchronize_sched(void) { struct rcu_synchronize rcu; + if (num_online_cpus() == 1) + return; /* blocking is gp if only one CPU! */ + init_completion(&rcu.completion); /* Will wake me after RCU finished. */ call_rcu_sched(&rcu.head, wakeme_after_rcu); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index f2d8638e6c6..97ce31579ec 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -948,8 +948,8 @@ static void rcu_do_batch(struct rcu_data *rdp) void rcu_check_callbacks(int cpu, int user) { if (user || - (idle_cpu(cpu) && !in_softirq() && - hardirq_count() <= (1 << HARDIRQ_SHIFT))) { + (idle_cpu(cpu) && rcu_scheduler_active && + !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) { /* * Get here if this CPU took its interrupt from user @@ -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..8f2179c8056 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(); @@ -748,7 +750,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) * from the scheduler (trying to re-grab * rq->lock), so defer it. */ - __mod_timer(&buf->timer, jiffies + 1); + mod_timer(&buf->timer, jiffies + 1); } old = buf->data; diff --git a/kernel/sched.c b/kernel/sched.c index 52bbf1c842a..9f8506d68fd 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -223,7 +223,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) { ktime_t now; - if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF) + if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) return; if (hrtimer_active(&rt_b->rt_period_timer)) @@ -331,6 +331,13 @@ static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp; */ static DEFINE_SPINLOCK(task_group_lock); +#ifdef CONFIG_SMP +static int root_task_group_empty(void) +{ + return list_empty(&root_task_group.children); +} +#endif + #ifdef CONFIG_FAIR_GROUP_SCHED #ifdef CONFIG_USER_SCHED # define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD) @@ -391,6 +398,13 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu) #else +#ifdef CONFIG_SMP +static int root_task_group_empty(void) +{ + return 1; +} +#endif + static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } static inline struct task_group *task_group(struct task_struct *p) { @@ -467,11 +481,17 @@ 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; @@ -549,7 +569,6 @@ struct rq { unsigned long nr_running; #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; - unsigned char idle_at_tick; #ifdef CONFIG_NO_HZ unsigned long last_tick_seen; unsigned char in_nohz_recently; @@ -590,6 +609,7 @@ struct rq { struct root_domain *rd; struct sched_domain *sd; + unsigned char idle_at_tick; /* For active balancing */ int active_balance; int push_cpu; @@ -618,9 +638,6 @@ struct rq { /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ /* sys_sched_yield() stats */ - unsigned int yld_exp_empty; - unsigned int yld_act_empty; - unsigned int yld_both_empty; unsigned int yld_count; /* schedule() stats */ @@ -1183,10 +1200,10 @@ static void resched_task(struct task_struct *p) assert_spin_locked(&task_rq(p)->lock); - if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED))) + if (test_tsk_need_resched(p)) return; - set_tsk_thread_flag(p, TIF_NEED_RESCHED); + set_tsk_need_resched(p); cpu = task_cpu(p); if (cpu == smp_processor_id()) @@ -1242,7 +1259,7 @@ void wake_up_idle_cpu(int cpu) * lockless. The worst case is that the other CPU runs the * idle task through an additional NOOP schedule() */ - set_tsk_thread_flag(rq->idle, TIF_NEED_RESCHED); + set_tsk_need_resched(rq->idle); /* NEED_RESCHED must be visible before we test polling */ smp_mb(); @@ -1610,21 +1627,42 @@ 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 +1675,22 @@ 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 +1759,9 @@ 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 +1769,15 @@ 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); @@ -2017,7 +2079,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * it must be off the runqueue _entirely_, and not * preempted! * - * So if it wa still runnable (but just not actively + * So if it was still runnable (but just not actively * running right now), it's preempted, and we should * yield - it could be a while. */ @@ -2267,7 +2329,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) sync = 0; #ifdef CONFIG_SMP - if (sched_feat(LB_WAKEUP_UPDATE)) { + if (sched_feat(LB_WAKEUP_UPDATE) && !root_task_group_empty()) { struct sched_domain *sd; this_cpu = raw_smp_processor_id(); @@ -2345,6 +2407,22 @@ 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 +2433,6 @@ 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 +2462,8 @@ 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 +2526,8 @@ 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(); } @@ -2491,7 +2571,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) #ifdef CONFIG_PREEMPT_NOTIFIERS /** - * preempt_notifier_register - tell me when current is being being preempted & rescheduled + * preempt_notifier_register - tell me when current is being preempted & rescheduled * @notifier: notifier struct to register */ void preempt_notifier_register(struct preempt_notifier *notifier) @@ -2588,6 +2668,12 @@ 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 +2692,7 @@ 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 @@ -2913,6 +2999,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, struct sched_domain *sd, enum cpu_idle_type idle, int *all_pinned) { + int tsk_cache_hot = 0; /* * We do not migrate tasks that are: * 1) running (obviously), or @@ -2936,10 +3023,11 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, * 2) too many balance attempts have failed. */ - if (!task_hot(p, rq->clock, sd) || - sd->nr_balance_failed > sd->cache_nice_tries) { + tsk_cache_hot = task_hot(p, rq->clock, sd); + if (!tsk_cache_hot || + sd->nr_balance_failed > sd->cache_nice_tries) { #ifdef CONFIG_SCHEDSTATS - if (task_hot(p, rq->clock, sd)) { + if (tsk_cache_hot) { schedstat_inc(sd, lb_hot_gained[idle]); schedstat_inc(p, se.nr_forced_migrations); } @@ -2947,7 +3035,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, return 1; } - if (task_hot(p, rq->clock, sd)) { + if (tsk_cache_hot) { schedstat_inc(p, se.nr_failed_migrations_hot); return 0; } @@ -2987,6 +3075,16 @@ 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 +3131,15 @@ 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; @@ -3085,246 +3189,479 @@ static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, return 0; } +/********** Helpers for find_busiest_group ************************/ +/** + * sd_lb_stats - Structure to store the statistics of a sched_domain + * during load balancing. + */ +struct sd_lb_stats { + struct sched_group *busiest; /* Busiest group in this sd */ + struct sched_group *this; /* Local group in this sd */ + unsigned long total_load; /* Total load of all groups in sd */ + unsigned long total_pwr; /* Total power of all groups in sd */ + unsigned long avg_load; /* Average load across all groups in sd */ + + /** Statistics of this group */ + unsigned long this_load; + unsigned long this_load_per_task; + unsigned long this_nr_running; + + /* Statistics of the busiest group */ + unsigned long max_load; + unsigned long busiest_load_per_task; + unsigned long busiest_nr_running; + + int group_imb; /* Is there imbalance in this sd */ +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) + int power_savings_balance; /* Is powersave balance needed for this sd */ + struct sched_group *group_min; /* Least loaded group in sd */ + struct sched_group *group_leader; /* Group which relieves group_min */ + unsigned long min_load_per_task; /* load_per_task in group_min */ + unsigned long leader_nr_running; /* Nr running of group_leader */ + unsigned long min_nr_running; /* Nr running of group_min */ +#endif +}; -/* - * find_busiest_group finds and returns the busiest CPU group within the - * domain. It calculates and returns the amount of weighted load which - * should be moved to restore balance via the imbalance parameter. +/** + * sg_lb_stats - stats of a sched_group required for load_balancing + */ +struct sg_lb_stats { + unsigned long avg_load; /*Avg load across the CPUs of the group */ + unsigned long group_load; /* Total load over the CPUs of the group */ + unsigned long sum_nr_running; /* Nr tasks running in the group */ + unsigned long sum_weighted_load; /* Weighted load of group's tasks */ + unsigned long group_capacity; + int group_imb; /* Is there an imbalance in the group ? */ +}; + +/** + * group_first_cpu - Returns the first cpu in the cpumask of a sched_group. + * @group: The group whose first cpu is to be returned. */ -static struct sched_group * -find_busiest_group(struct sched_domain *sd, int this_cpu, - unsigned long *imbalance, enum cpu_idle_type idle, - int *sd_idle, const struct cpumask *cpus, int *balance) +static inline unsigned int group_first_cpu(struct sched_group *group) { - struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups; - unsigned long max_load, avg_load, total_load, this_load, total_pwr; - unsigned long max_pull; - unsigned long busiest_load_per_task, busiest_nr_running; - unsigned long this_load_per_task, this_nr_running; - int load_idx, group_imb = 0; -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - int power_savings_balance = 1; - unsigned long leader_nr_running = 0, min_load_per_task = 0; - unsigned long min_nr_running = ULONG_MAX; - struct sched_group *group_min = NULL, *group_leader = NULL; -#endif + return cpumask_first(sched_group_cpus(group)); +} - max_load = this_load = total_load = total_pwr = 0; - busiest_load_per_task = busiest_nr_running = 0; - this_load_per_task = this_nr_running = 0; +/** + * get_sd_load_idx - Obtain the load index for a given sched domain. + * @sd: The sched_domain whose load_idx is to be obtained. + * @idle: The Idle status of the CPU for whose sd load_icx is obtained. + */ +static inline int get_sd_load_idx(struct sched_domain *sd, + enum cpu_idle_type idle) +{ + int load_idx; - if (idle == CPU_NOT_IDLE) + switch (idle) { + case CPU_NOT_IDLE: load_idx = sd->busy_idx; - else if (idle == CPU_NEWLY_IDLE) + break; + + case CPU_NEWLY_IDLE: load_idx = sd->newidle_idx; - else + break; + default: load_idx = sd->idle_idx; + break; + } - do { - unsigned long load, group_capacity, max_cpu_load, min_cpu_load; - int local_group; - int i; - int __group_imb = 0; - unsigned int balance_cpu = -1, first_idle_cpu = 0; - unsigned long sum_nr_running, sum_weighted_load; - unsigned long sum_avg_load_per_task; - unsigned long avg_load_per_task; + return load_idx; +} - local_group = cpumask_test_cpu(this_cpu, - sched_group_cpus(group)); - if (local_group) - balance_cpu = cpumask_first(sched_group_cpus(group)); +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) +/** + * init_sd_power_savings_stats - Initialize power savings statistics for + * the given sched_domain, during load balancing. + * + * @sd: Sched domain whose power-savings statistics are to be initialized. + * @sds: Variable containing the statistics for sd. + * @idle: Idle status of the CPU at which we're performing load-balancing. + */ +static inline void init_sd_power_savings_stats(struct sched_domain *sd, + struct sd_lb_stats *sds, enum cpu_idle_type idle) +{ + /* + * Busy processors will not participate in power savings + * balance. + */ + if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE)) + sds->power_savings_balance = 0; + else { + sds->power_savings_balance = 1; + sds->min_nr_running = ULONG_MAX; + sds->leader_nr_running = 0; + } +} - /* Tally up the load of all CPUs in the group */ - sum_weighted_load = sum_nr_running = avg_load = 0; - sum_avg_load_per_task = avg_load_per_task = 0; +/** + * update_sd_power_savings_stats - Update the power saving stats for a + * sched_domain while performing load balancing. + * + * @group: sched_group belonging to the sched_domain under consideration. + * @sds: Variable containing the statistics of the sched_domain + * @local_group: Does group contain the CPU for which we're performing + * load balancing ? + * @sgs: Variable containing the statistics of the group. + */ +static inline void update_sd_power_savings_stats(struct sched_group *group, + struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) +{ - max_cpu_load = 0; - min_cpu_load = ~0UL; + if (!sds->power_savings_balance) + return; - for_each_cpu_and(i, sched_group_cpus(group), cpus) { - struct rq *rq = cpu_rq(i); + /* + * If the local group is idle or completely loaded + * no need to do power savings balance at this domain + */ + if (local_group && (sds->this_nr_running >= sgs->group_capacity || + !sds->this_nr_running)) + sds->power_savings_balance = 0; + + /* + * If a group is already running at full capacity or idle, + * don't include that group in power savings calculations + */ + if (!sds->power_savings_balance || + sgs->sum_nr_running >= sgs->group_capacity || + !sgs->sum_nr_running) + return; - if (*sd_idle && rq->nr_running) - *sd_idle = 0; + /* + * Calculate the group which has the least non-idle load. + * This is the group from where we need to pick up the load + * for saving power + */ + if ((sgs->sum_nr_running < sds->min_nr_running) || + (sgs->sum_nr_running == sds->min_nr_running && + group_first_cpu(group) > group_first_cpu(sds->group_min))) { + sds->group_min = group; + sds->min_nr_running = sgs->sum_nr_running; + sds->min_load_per_task = sgs->sum_weighted_load / + sgs->sum_nr_running; + } - /* Bias balancing toward cpus of our domain */ - if (local_group) { - if (idle_cpu(i) && !first_idle_cpu) { - first_idle_cpu = 1; - balance_cpu = i; - } + /* + * Calculate the group which is almost near its + * capacity but still has some space to pick up some load + * from other group and save more power + */ + if (sgs->sum_nr_running > sgs->group_capacity - 1) + return; - load = target_load(i, load_idx); - } else { - load = source_load(i, load_idx); - if (load > max_cpu_load) - max_cpu_load = load; - if (min_cpu_load > load) - min_cpu_load = load; - } + if (sgs->sum_nr_running > sds->leader_nr_running || + (sgs->sum_nr_running == sds->leader_nr_running && + group_first_cpu(group) < group_first_cpu(sds->group_leader))) { + sds->group_leader = group; + sds->leader_nr_running = sgs->sum_nr_running; + } +} - avg_load += load; - sum_nr_running += rq->nr_running; - sum_weighted_load += weighted_cpuload(i); +/** + * check_power_save_busiest_group - Check if we have potential to perform + * some power-savings balance. If yes, set the busiest group to be + * the least loaded group in the sched_domain, so that it's CPUs can + * be put to idle. + * + * @sds: Variable containing the statistics of the sched_domain + * under consideration. + * @this_cpu: Cpu at which we're currently performing load-balancing. + * @imbalance: Variable to store the imbalance. + * + * Returns 1 if there is potential to perform power-savings balance. + * Else returns 0. + */ +static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, + int this_cpu, unsigned long *imbalance) +{ + if (!sds->power_savings_balance) + return 0; - sum_avg_load_per_task += cpu_avg_load_per_task(i); - } + if (sds->this != sds->group_leader || + sds->group_leader == sds->group_min) + return 0; - /* - * First idle cpu or the first cpu(busiest) in this sched group - * is eligible for doing load balancing at this and above - * domains. In the newly idle case, we will allow all the cpu's - * to do the newly idle load balance. - */ - if (idle != CPU_NEWLY_IDLE && local_group && - balance_cpu != this_cpu && balance) { - *balance = 0; - goto ret; - } + *imbalance = sds->min_load_per_task; + sds->busiest = sds->group_min; - total_load += avg_load; - total_pwr += group->__cpu_power; + if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) { + cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu = + group_first_cpu(sds->group_leader); + } - /* Adjust by relative CPU power of the group */ - avg_load = sg_div_cpu_power(group, - avg_load * SCHED_LOAD_SCALE); + return 1; +} +#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ +static inline void init_sd_power_savings_stats(struct sched_domain *sd, + struct sd_lb_stats *sds, enum cpu_idle_type idle) +{ + return; +} - /* - * Consider the group unbalanced when the imbalance is larger - * than the average weight of two tasks. - * - * APZ: with cgroup the avg task weight can vary wildly and - * might not be a suitable number - should we keep a - * normalized nr_running number somewhere that negates - * the hierarchy? - */ - avg_load_per_task = sg_div_cpu_power(group, - sum_avg_load_per_task * SCHED_LOAD_SCALE); +static inline void update_sd_power_savings_stats(struct sched_group *group, + struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) +{ + return; +} - if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task) - __group_imb = 1; +static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, + int this_cpu, unsigned long *imbalance) +{ + return 0; +} +#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ - group_capacity = group->__cpu_power / SCHED_LOAD_SCALE; +/** + * update_sg_lb_stats - Update sched_group's statistics for load balancing. + * @group: sched_group whose statistics are to be updated. + * @this_cpu: Cpu for which load balance is currently performed. + * @idle: Idle status of this_cpu + * @load_idx: Load index of sched_domain of this_cpu for load calc. + * @sd_idle: Idle status of the sched_domain containing group. + * @local_group: Does group contain this_cpu. + * @cpus: Set of cpus considered for load balancing. + * @balance: Should we balance. + * @sgs: variable to hold the statistics for this group. + */ +static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu, + enum cpu_idle_type idle, int load_idx, int *sd_idle, + int local_group, const struct cpumask *cpus, + int *balance, struct sg_lb_stats *sgs) +{ + unsigned long load, max_cpu_load, min_cpu_load; + int i; + unsigned int balance_cpu = -1, first_idle_cpu = 0; + unsigned long sum_avg_load_per_task; + unsigned long avg_load_per_task; + + if (local_group) + balance_cpu = group_first_cpu(group); + + /* Tally up the load of all CPUs in the group */ + sum_avg_load_per_task = avg_load_per_task = 0; + max_cpu_load = 0; + min_cpu_load = ~0UL; + + for_each_cpu_and(i, sched_group_cpus(group), cpus) { + struct rq *rq = cpu_rq(i); + + if (*sd_idle && rq->nr_running) + *sd_idle = 0; + + /* Bias balancing toward cpus of our domain */ if (local_group) { - this_load = avg_load; - this = group; - this_nr_running = sum_nr_running; - this_load_per_task = sum_weighted_load; - } else if (avg_load > max_load && - (sum_nr_running > group_capacity || __group_imb)) { - max_load = avg_load; - busiest = group; - busiest_nr_running = sum_nr_running; - busiest_load_per_task = sum_weighted_load; - group_imb = __group_imb; + if (idle_cpu(i) && !first_idle_cpu) { + first_idle_cpu = 1; + balance_cpu = i; + } + + load = target_load(i, load_idx); + } else { + load = source_load(i, load_idx); + if (load > max_cpu_load) + max_cpu_load = load; + if (min_cpu_load > load) + min_cpu_load = load; } -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - /* - * Busy processors will not participate in power savings - * balance. - */ - if (idle == CPU_NOT_IDLE || - !(sd->flags & SD_POWERSAVINGS_BALANCE)) - goto group_next; + sgs->group_load += load; + sgs->sum_nr_running += rq->nr_running; + sgs->sum_weighted_load += weighted_cpuload(i); - /* - * If the local group is idle or completely loaded - * no need to do power savings balance at this domain - */ - if (local_group && (this_nr_running >= group_capacity || - !this_nr_running)) - power_savings_balance = 0; + sum_avg_load_per_task += cpu_avg_load_per_task(i); + } - /* - * If a group is already running at full capacity or idle, - * don't include that group in power savings calculations - */ - if (!power_savings_balance || sum_nr_running >= group_capacity - || !sum_nr_running) - goto group_next; + /* + * First idle cpu or the first cpu(busiest) in this sched group + * is eligible for doing load balancing at this and above + * domains. In the newly idle case, we will allow all the cpu's + * to do the newly idle load balance. + */ + if (idle != CPU_NEWLY_IDLE && local_group && + balance_cpu != this_cpu && balance) { + *balance = 0; + return; + } - /* - * Calculate the group which has the least non-idle load. - * This is the group from where we need to pick up the load - * for saving power - */ - if ((sum_nr_running < min_nr_running) || - (sum_nr_running == min_nr_running && - cpumask_first(sched_group_cpus(group)) > - cpumask_first(sched_group_cpus(group_min)))) { - group_min = group; - min_nr_running = sum_nr_running; - min_load_per_task = sum_weighted_load / - sum_nr_running; - } + /* Adjust by relative CPU power of the group */ + sgs->avg_load = sg_div_cpu_power(group, + sgs->group_load * SCHED_LOAD_SCALE); - /* - * Calculate the group which is almost near its - * capacity but still has some space to pick up some load - * from other group and save more power - */ - if (sum_nr_running <= group_capacity - 1) { - if (sum_nr_running > leader_nr_running || - (sum_nr_running == leader_nr_running && - cpumask_first(sched_group_cpus(group)) < - cpumask_first(sched_group_cpus(group_leader)))) { - group_leader = group; - leader_nr_running = sum_nr_running; - } + + /* + * Consider the group unbalanced when the imbalance is larger + * than the average weight of two tasks. + * + * APZ: with cgroup the avg task weight can vary wildly and + * might not be a suitable number - should we keep a + * normalized nr_running number somewhere that negates + * the hierarchy? + */ + avg_load_per_task = sg_div_cpu_power(group, + sum_avg_load_per_task * SCHED_LOAD_SCALE); + + if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task) + sgs->group_imb = 1; + + sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE; + +} + +/** + * update_sd_lb_stats - Update sched_group's statistics for load balancing. + * @sd: sched_domain whose statistics are to be updated. + * @this_cpu: Cpu for which load balance is currently performed. + * @idle: Idle status of this_cpu + * @sd_idle: Idle status of the sched_domain containing group. + * @cpus: Set of cpus considered for load balancing. + * @balance: Should we balance. + * @sds: variable to hold the statistics for this sched_domain. + */ +static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, + enum cpu_idle_type idle, int *sd_idle, + const struct cpumask *cpus, int *balance, + struct sd_lb_stats *sds) +{ + struct sched_group *group = sd->groups; + struct sg_lb_stats sgs; + int load_idx; + + init_sd_power_savings_stats(sd, sds, idle); + load_idx = get_sd_load_idx(sd, idle); + + do { + int local_group; + + local_group = cpumask_test_cpu(this_cpu, + sched_group_cpus(group)); + memset(&sgs, 0, sizeof(sgs)); + update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle, + local_group, cpus, balance, &sgs); + + if (local_group && balance && !(*balance)) + return; + + sds->total_load += sgs.group_load; + sds->total_pwr += group->__cpu_power; + + if (local_group) { + sds->this_load = sgs.avg_load; + sds->this = group; + sds->this_nr_running = sgs.sum_nr_running; + sds->this_load_per_task = sgs.sum_weighted_load; + } else if (sgs.avg_load > sds->max_load && + (sgs.sum_nr_running > sgs.group_capacity || + sgs.group_imb)) { + sds->max_load = sgs.avg_load; + sds->busiest = group; + sds->busiest_nr_running = sgs.sum_nr_running; + sds->busiest_load_per_task = sgs.sum_weighted_load; + sds->group_imb = sgs.group_imb; } -group_next: -#endif + + update_sd_power_savings_stats(group, sds, local_group, &sgs); group = group->next; } while (group != sd->groups); - if (!busiest || this_load >= max_load || busiest_nr_running == 0) - goto out_balanced; - - avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr; +} - if (this_load >= avg_load || - 100*max_load <= sd->imbalance_pct*this_load) - goto out_balanced; +/** + * fix_small_imbalance - Calculate the minor imbalance that exists + * amongst the groups of a sched_domain, during + * load balancing. + * @sds: Statistics of the sched_domain whose imbalance is to be calculated. + * @this_cpu: The cpu at whose sched_domain we're performing load-balance. + * @imbalance: Variable to store the imbalance. + */ +static inline void fix_small_imbalance(struct sd_lb_stats *sds, + int this_cpu, unsigned long *imbalance) +{ + unsigned long tmp, pwr_now = 0, pwr_move = 0; + unsigned int imbn = 2; + + if (sds->this_nr_running) { + sds->this_load_per_task /= sds->this_nr_running; + if (sds->busiest_load_per_task > + sds->this_load_per_task) + imbn = 1; + } else + sds->this_load_per_task = + cpu_avg_load_per_task(this_cpu); - busiest_load_per_task /= busiest_nr_running; - if (group_imb) - busiest_load_per_task = min(busiest_load_per_task, avg_load); + if (sds->max_load - sds->this_load + sds->busiest_load_per_task >= + sds->busiest_load_per_task * imbn) { + *imbalance = sds->busiest_load_per_task; + return; + } /* - * We're trying to get all the cpus to the average_load, so we don't - * want to push ourselves above the average load, nor do we wish to - * reduce the max loaded cpu below the average load, as either of these - * actions would just result in more rebalancing later, and ping-pong - * tasks around. Thus we look for the minimum possible imbalance. - * Negative imbalances (*we* are more loaded than anyone else) will - * be counted as no imbalance for these purposes -- we can't fix that - * by pulling tasks to us. Be careful of negative numbers as they'll - * appear as very large values with unsigned longs. + * OK, we don't have enough imbalance to justify moving tasks, + * however we may be able to increase total CPU power used by + * moving them. */ - if (max_load <= busiest_load_per_task) - goto out_balanced; + pwr_now += sds->busiest->__cpu_power * + min(sds->busiest_load_per_task, sds->max_load); + pwr_now += sds->this->__cpu_power * + min(sds->this_load_per_task, sds->this_load); + pwr_now /= SCHED_LOAD_SCALE; + + /* Amount of load we'd subtract */ + tmp = sg_div_cpu_power(sds->busiest, + sds->busiest_load_per_task * SCHED_LOAD_SCALE); + if (sds->max_load > tmp) + pwr_move += sds->busiest->__cpu_power * + min(sds->busiest_load_per_task, sds->max_load - tmp); + + /* Amount of load we'd add */ + if (sds->max_load * sds->busiest->__cpu_power < + sds->busiest_load_per_task * SCHED_LOAD_SCALE) + tmp = sg_div_cpu_power(sds->this, + sds->max_load * sds->busiest->__cpu_power); + else + tmp = sg_div_cpu_power(sds->this, + sds->busiest_load_per_task * SCHED_LOAD_SCALE); + pwr_move += sds->this->__cpu_power * + min(sds->this_load_per_task, sds->this_load + tmp); + pwr_move /= SCHED_LOAD_SCALE; + + /* Move if we gain throughput */ + if (pwr_move > pwr_now) + *imbalance = sds->busiest_load_per_task; +} + +/** + * calculate_imbalance - Calculate the amount of imbalance present within the + * groups of a given sched_domain during load balance. + * @sds: statistics of the sched_domain whose imbalance is to be calculated. + * @this_cpu: Cpu for which currently load balance is being performed. + * @imbalance: The variable to store the imbalance. + */ +static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, + unsigned long *imbalance) +{ + unsigned long max_pull; /* * In the presence of smp nice balancing, certain scenarios can have * max load less than avg load(as we skip the groups at or below * its cpu_power, while calculating max_load..) */ - if (max_load < avg_load) { + if (sds->max_load < sds->avg_load) { *imbalance = 0; - goto small_imbalance; + return fix_small_imbalance(sds, this_cpu, imbalance); } /* Don't want to pull so many tasks that a group would go idle */ - max_pull = min(max_load - avg_load, max_load - busiest_load_per_task); + max_pull = min(sds->max_load - sds->avg_load, + sds->max_load - sds->busiest_load_per_task); /* How much load to actually move to equalise the imbalance */ - *imbalance = min(max_pull * busiest->__cpu_power, - (avg_load - this_load) * this->__cpu_power) + *imbalance = min(max_pull * sds->busiest->__cpu_power, + (sds->avg_load - sds->this_load) * sds->this->__cpu_power) / SCHED_LOAD_SCALE; /* @@ -3333,78 +3670,110 @@ group_next: * a think about bumping its value to force at least one task to be * moved */ - if (*imbalance < busiest_load_per_task) { - unsigned long tmp, pwr_now, pwr_move; - unsigned int imbn; - -small_imbalance: - pwr_move = pwr_now = 0; - imbn = 2; - if (this_nr_running) { - this_load_per_task /= this_nr_running; - if (busiest_load_per_task > this_load_per_task) - imbn = 1; - } else - this_load_per_task = cpu_avg_load_per_task(this_cpu); + if (*imbalance < sds->busiest_load_per_task) + return fix_small_imbalance(sds, this_cpu, imbalance); - if (max_load - this_load + busiest_load_per_task >= - busiest_load_per_task * imbn) { - *imbalance = busiest_load_per_task; - return busiest; - } +} +/******* find_busiest_group() helpers end here *********************/ - /* - * OK, we don't have enough imbalance to justify moving tasks, - * however we may be able to increase total CPU power used by - * moving them. - */ +/** + * find_busiest_group - Returns the busiest group within the sched_domain + * if there is an imbalance. If there isn't an imbalance, and + * the user has opted for power-savings, it returns a group whose + * CPUs can be put to idle by rebalancing those tasks elsewhere, if + * such a group exists. + * + * Also calculates the amount of weighted load which should be moved + * to restore balance. + * + * @sd: The sched_domain whose busiest group is to be returned. + * @this_cpu: The cpu for which load balancing is currently being performed. + * @imbalance: Variable which stores amount of weighted load which should + * be moved to restore balance/put a group to idle. + * @idle: The idle status of this_cpu. + * @sd_idle: The idleness of sd + * @cpus: The set of CPUs under consideration for load-balancing. + * @balance: Pointer to a variable indicating if this_cpu + * is the appropriate cpu to perform load balancing at this_level. + * + * Returns: - the busiest group if imbalance exists. + * - If no imbalance and user has opted for power-savings balance, + * return the least loaded group whose CPUs can be + * put to idle by rebalancing its tasks onto our group. + */ +static struct sched_group * +find_busiest_group(struct sched_domain *sd, int this_cpu, + unsigned long *imbalance, enum cpu_idle_type idle, + int *sd_idle, const struct cpumask *cpus, int *balance) +{ + struct sd_lb_stats sds; - pwr_now += busiest->__cpu_power * - min(busiest_load_per_task, max_load); - pwr_now += this->__cpu_power * - min(this_load_per_task, this_load); - pwr_now /= SCHED_LOAD_SCALE; - - /* Amount of load we'd subtract */ - tmp = sg_div_cpu_power(busiest, - busiest_load_per_task * SCHED_LOAD_SCALE); - if (max_load > tmp) - pwr_move += busiest->__cpu_power * - min(busiest_load_per_task, max_load - tmp); - - /* Amount of load we'd add */ - if (max_load * busiest->__cpu_power < - busiest_load_per_task * SCHED_LOAD_SCALE) - tmp = sg_div_cpu_power(this, - max_load * busiest->__cpu_power); - else - tmp = sg_div_cpu_power(this, - busiest_load_per_task * SCHED_LOAD_SCALE); - pwr_move += this->__cpu_power * - min(this_load_per_task, this_load + tmp); - pwr_move /= SCHED_LOAD_SCALE; + memset(&sds, 0, sizeof(sds)); - /* Move if we gain throughput */ - if (pwr_move > pwr_now) - *imbalance = busiest_load_per_task; - } + /* + * Compute the various statistics relavent for load balancing at + * this level. + */ + update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus, + balance, &sds); + + /* Cases where imbalance does not exist from POV of this_cpu */ + /* 1) this_cpu is not the appropriate cpu to perform load balancing + * at this level. + * 2) There is no busy sibling group to pull from. + * 3) This group is the busiest group. + * 4) This group is more busy than the avg busieness at this + * sched_domain. + * 5) The imbalance is within the specified limit. + * 6) Any rebalance would lead to ping-pong + */ + if (balance && !(*balance)) + goto ret; - return busiest; + if (!sds.busiest || sds.busiest_nr_running == 0) + goto out_balanced; -out_balanced: -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE)) - goto ret; + if (sds.this_load >= sds.max_load) + goto out_balanced; - if (this == group_leader && group_leader != group_min) { - *imbalance = min_load_per_task; - if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) { - cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu = - cpumask_first(sched_group_cpus(group_leader)); - } - return group_min; - } -#endif + sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr; + + if (sds.this_load >= sds.avg_load) + goto out_balanced; + + if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load) + goto out_balanced; + + sds.busiest_load_per_task /= sds.busiest_nr_running; + if (sds.group_imb) + sds.busiest_load_per_task = + min(sds.busiest_load_per_task, sds.avg_load); + + /* + * We're trying to get all the cpus to the average_load, so we don't + * want to push ourselves above the average load, nor do we wish to + * reduce the max loaded cpu below the average load, as either of these + * actions would just result in more rebalancing later, and ping-pong + * tasks around. Thus we look for the minimum possible imbalance. + * Negative imbalances (*we* are more loaded than anyone else) will + * be counted as no imbalance for these purposes -- we can't fix that + * by pulling tasks to us. Be careful of negative numbers as they'll + * appear as very large values with unsigned longs. + */ + if (sds.max_load <= sds.busiest_load_per_task) + goto out_balanced; + + /* Looks like there is an imbalance. Compute it */ + calculate_imbalance(&sds, this_cpu, imbalance); + return sds.busiest; + +out_balanced: + /* + * There is no obvious imbalance. But check if we can do some balancing + * to save power. + */ + if (check_power_save_busiest_group(&sds, this_cpu, imbalance)) + return sds.busiest; ret: *imbalance = 0; return NULL; @@ -3880,19 +4249,24 @@ 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) @@ -4052,6 +4426,11 @@ static void run_rebalance_domains(struct softirq_action *h) #endif } +static inline int on_null_domain(int cpu) +{ + return !rcu_dereference(cpu_rq(cpu)->sd); +} + /* * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. * @@ -4109,7 +4488,9 @@ static inline void trigger_load_balance(struct rq *rq, int cpu) cpumask_test_cpu(cpu, nohz.cpu_mask)) return; #endif - if (time_after_eq(jiffies, rq->next_balance)) + /* Don't need to rebalance while attached to NULL domain */ + if (time_after_eq(jiffies, rq->next_balance) && + likely(!on_null_domain(cpu))) raise_softirq(SCHED_SOFTIRQ); } @@ -4503,11 +4884,33 @@ static inline void schedule_debug(struct task_struct *prev) #endif } +static void put_prev_task(struct rq *rq, struct task_struct *prev) +{ + if (prev->state == TASK_RUNNING) { + u64 runtime = prev->se.sum_exec_runtime; + + runtime -= prev->se.prev_sum_exec_runtime; + runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost); + + /* + * In order to avoid avg_overlap growing stale when we are + * indeed overlapping and hence not getting put to sleep, grow + * the avg_overlap on preemption. + * + * We use the average preemption runtime because that + * correlates to the amount of cache footprint a task can + * build up. + */ + update_avg(&prev->se.avg_overlap, runtime); + } + prev->sched_class->put_prev_task(rq, prev); +} + /* * Pick up the highest-prio task: */ static inline struct task_struct * -pick_next_task(struct rq *rq, struct task_struct *prev) +pick_next_task(struct rq *rq) { const struct sched_class *class; struct task_struct *p; @@ -4581,8 +4984,8 @@ need_resched_nonpreemptible: if (unlikely(!rq->nr_running)) idle_balance(cpu, rq); - prev->sched_class->put_prev_task(rq, prev); - next = pick_next_task(rq, prev); + put_prev_task(rq, prev); + next = pick_next_task(rq); if (likely(prev != next)) { sched_info_switch(prev, next); @@ -4637,7 +5040,7 @@ asmlinkage void __sched preempt_schedule(void) * between schedule and now. */ barrier(); - } while (unlikely(test_thread_flag(TIF_NEED_RESCHED))); + } while (need_resched()); } EXPORT_SYMBOL(preempt_schedule); @@ -4666,7 +5069,7 @@ asmlinkage void __sched preempt_schedule_irq(void) * between schedule and now. */ barrier(); - } while (unlikely(test_thread_flag(TIF_NEED_RESCHED))); + } while (need_resched()); } #endif /* CONFIG_PREEMPT */ @@ -4687,8 +5090,8 @@ 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; @@ -5140,7 +5543,7 @@ SYSCALL_DEFINE1(nice, int, increment) if (increment > 40) increment = 40; - nice = PRIO_TO_NICE(current->static_prio) + increment; + nice = TASK_NICE(current) + increment; if (nice < -20) nice = -20; if (nice > 19) @@ -6418,7 +6821,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu) if (!rq->nr_running) break; update_rq_clock(rq); - next = pick_next_task(rq, rq->curr); + next = pick_next_task(rq); if (!next) break; next->sched_class->put_prev_task(rq, next); @@ -6939,20 +7342,26 @@ static void free_rootdomain(struct root_domain *rd) static void rq_attach_root(struct rq *rq, struct root_domain *rd) { + struct root_domain *old_rd = NULL; unsigned long flags; spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { - struct root_domain *old_rd = rq->rd; + old_rd = rq->rd; if (cpumask_test_cpu(rq->cpu, old_rd->online)) set_rq_offline(rq); cpumask_clear_cpu(rq->cpu, old_rd->span); - if (atomic_dec_and_test(&old_rd->refcount)) - free_rootdomain(old_rd); + /* + * If we dont want to free the old_rt yet then + * set old_rd to NULL to skip the freeing later + * in this function: + */ + if (!atomic_dec_and_test(&old_rd->refcount)) + old_rd = NULL; } atomic_inc(&rd->refcount); @@ -6963,6 +7372,9 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) set_rq_online(rq); spin_unlock_irqrestore(&rq->lock, flags); + + if (old_rd) + free_rootdomain(old_rd); } static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem) @@ -8204,11 +8616,15 @@ 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; @@ -9210,6 +9626,16 @@ static int sched_rt_global_constraints(void) return ret; } + +int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) +{ + /* Don't accept realtime tasks when there is no way for them to run */ + if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) + return 0; + + return 1; +} + #else /* !CONFIG_RT_GROUP_SCHED */ static int sched_rt_global_constraints(void) { @@ -9303,8 +9729,7 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, struct task_struct *tsk) { #ifdef CONFIG_RT_GROUP_SCHED - /* Don't accept realtime tasks when there is no way for them to run */ - if (rt_task(tsk) && cgroup_tg(cgrp)->rt_bandwidth.rt_runtime == 0) + if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk)) return -EINVAL; #else /* We don't support RT-tasks being in separate groups */ @@ -9575,7 +10000,7 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime) struct cpuacct *ca; int cpu; - if (!cpuacct_subsys.active) + if (unlikely(!cpuacct_subsys.active)) return; cpu = task_cpu(tsk); diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index a0b0852414c..390f33234bd 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -24,11 +24,11 @@ * The clock: sched_clock_cpu() is monotonic per cpu, and should be somewhat * consistent between cpus (never more than 2 jiffies difference). */ -#include <linux/sched.h> -#include <linux/percpu.h> #include <linux/spinlock.h> -#include <linux/ktime.h> #include <linux/module.h> +#include <linux/percpu.h> +#include <linux/ktime.h> +#include <linux/sched.h> /* * Scheduler clock - returns current time in nanosec units. @@ -43,6 +43,7 @@ unsigned long long __attribute__((weak)) sched_clock(void) static __read_mostly int sched_clock_running; #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK +__read_mostly int sched_clock_stable; struct sched_clock_data { /* @@ -87,7 +88,7 @@ void sched_clock_init(void) } /* - * min,max except they take wrapping into account + * min, max except they take wrapping into account */ static inline u64 wrap_min(u64 x, u64 y) @@ -111,15 +112,13 @@ static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now) s64 delta = now - scd->tick_raw; u64 clock, min_clock, max_clock; - WARN_ON_ONCE(!irqs_disabled()); - if (unlikely(delta < 0)) delta = 0; /* * scd->clock = clamp(scd->tick_gtod + delta, - * max(scd->tick_gtod, scd->clock), - * scd->tick_gtod + TICK_NSEC); + * max(scd->tick_gtod, scd->clock), + * scd->tick_gtod + TICK_NSEC); */ clock = scd->tick_gtod + delta; @@ -148,12 +147,13 @@ static void lock_double_clock(struct sched_clock_data *data1, u64 sched_clock_cpu(int cpu) { - struct sched_clock_data *scd = cpu_sdc(cpu); u64 now, clock, this_clock, remote_clock; + struct sched_clock_data *scd; - if (unlikely(!sched_clock_running)) - return 0ull; + if (sched_clock_stable) + return sched_clock(); + scd = cpu_sdc(cpu); WARN_ON_ONCE(!irqs_disabled()); now = sched_clock(); @@ -195,14 +195,18 @@ u64 sched_clock_cpu(int cpu) void sched_clock_tick(void) { - struct sched_clock_data *scd = this_scd(); + struct sched_clock_data *scd; u64 now, now_gtod; + if (sched_clock_stable) + return; + if (unlikely(!sched_clock_running)) return; WARN_ON_ONCE(!irqs_disabled()); + scd = this_scd(); now_gtod = ktime_to_ns(ktime_get()); now = sched_clock(); @@ -250,7 +254,7 @@ u64 sched_clock_cpu(int cpu) return sched_clock(); } -#endif +#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ unsigned long long cpu_clock(int cpu) { diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 16eeba4e416..467ca72f165 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -272,7 +272,6 @@ static void print_cpu(struct seq_file *m, int cpu) P(nr_switches); P(nr_load_updates); P(nr_uninterruptible); - SEQ_printf(m, " .%-30s: %lu\n", "jiffies", jiffies); PN(next_balance); P(curr->pid); PN(clock); @@ -287,9 +286,6 @@ static void print_cpu(struct seq_file *m, int cpu) #ifdef CONFIG_SCHEDSTATS #define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); - P(yld_exp_empty); - P(yld_act_empty); - P(yld_both_empty); P(yld_count); P(sched_switch); @@ -314,7 +310,7 @@ static int sched_debug_show(struct seq_file *m, void *v) u64 now = ktime_to_ns(ktime_get()); int cpu; - SEQ_printf(m, "Sched Debug Version: v0.08, %s %.*s\n", + SEQ_printf(m, "Sched Debug Version: v0.09, %s %.*s\n", init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); @@ -325,6 +321,7 @@ static int sched_debug_show(struct seq_file *m, void *v) SEQ_printf(m, " .%-40s: %Ld\n", #x, (long long)(x)) #define PN(x) \ SEQ_printf(m, " .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x)) + P(jiffies); PN(sysctl_sched_latency); PN(sysctl_sched_min_granularity); PN(sysctl_sched_wakeup_granularity); @@ -397,6 +394,7 @@ 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 5cc1c162044..3816f217f11 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 @@ -1302,16 +1314,63 @@ 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 +1397,7 @@ 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; @@ -1452,6 +1511,11 @@ 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 da5d93b5d2c..76f61756e67 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) diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 954e1a81b79..c79dc784401 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) +{ + 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) { - return container_of(rt_se, struct task_struct, rt); } +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); } @@ -878,7 +1021,7 @@ 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 +1043,18 @@ 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 +1062,13 @@ 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 @@ -968,8 +1130,8 @@ 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; @@ -1072,7 +1234,7 @@ 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 +1245,31 @@ 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 +1279,11 @@ 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 +1312,34 @@ 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 +1350,12 @@ 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 +1366,35 @@ 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 +1408,7 @@ 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 +1418,9 @@ 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 +1433,7 @@ 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 +1445,27 @@ 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 +1476,8 @@ 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 +1513,24 @@ 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 +1538,7 @@ 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 +1553,7 @@ 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 +1645,7 @@ 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 +1716,9 @@ 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 +1741,7 @@ 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 f2773b5d122..32d2bd4061b 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -4,7 +4,7 @@ * bump this up when changing the output format or the meaning of an existing * format, so that tools can adapt (or abort) */ -#define SCHEDSTAT_VERSION 14 +#define SCHEDSTAT_VERSION 15 static int show_schedstat(struct seq_file *seq, void *v) { @@ -26,9 +26,8 @@ static int show_schedstat(struct seq_file *seq, void *v) /* runqueue-specific stats */ seq_printf(seq, - "cpu%d %u %u %u %u %u %u %u %u %u %llu %llu %lu", - cpu, rq->yld_both_empty, - rq->yld_act_empty, rq->yld_exp_empty, rq->yld_count, + "cpu%d %u %u %u %u %u %u %llu %llu %lu", + cpu, rq->yld_count, rq->sched_switch, rq->sched_count, rq->sched_goidle, rq->ttwu_count, rq->ttwu_local, rq->rq_cpu_time, @@ -296,20 +295,21 @@ 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 +325,21 @@ 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 +355,7 @@ 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 +364,12 @@ 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/seccomp.c b/kernel/seccomp.c index ad64fcb731f..57d4b13b631 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -8,6 +8,7 @@ #include <linux/seccomp.h> #include <linux/sched.h> +#include <linux/compat.h> /* #define SECCOMP_DEBUG 1 */ #define NR_SECCOMP_MODES 1 @@ -22,7 +23,7 @@ static int mode1_syscalls[] = { 0, /* null terminated */ }; -#ifdef TIF_32BIT +#ifdef CONFIG_COMPAT static int mode1_syscalls_32[] = { __NR_seccomp_read_32, __NR_seccomp_write_32, __NR_seccomp_exit_32, __NR_seccomp_sigreturn_32, 0, /* null terminated */ @@ -37,8 +38,8 @@ void __secure_computing(int this_syscall) switch (mode) { case 1: syscall = mode1_syscalls; -#ifdef TIF_32BIT - if (test_thread_flag(TIF_32BIT)) +#ifdef CONFIG_COMPAT + if (is_compat_task()) syscall = mode1_syscalls_32; #endif do { diff --git a/kernel/signal.c b/kernel/signal.c index e73759783dc..1c8814481a1 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) @@ -1573,7 +1575,15 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info) read_lock(&tasklist_lock); if (may_ptrace_stop()) { do_notify_parent_cldstop(current, CLD_TRAPPED); + /* + * Don't want to allow preemption here, because + * sys_ptrace() needs this task to be inactive. + * + * XXX: implement read_unlock_no_resched(). + */ + preempt_disable(); read_unlock(&tasklist_lock); + preempt_enable_no_resched(); schedule(); } else { /* 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/softirq.c b/kernel/softirq.c index bdbe9de9cd8..9041ea7948f 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -626,6 +626,7 @@ static int ksoftirqd(void * __bind_cpu) preempt_enable_no_resched(); cond_resched(); preempt_disable(); + rcu_qsctr_inc((long)__bind_cpu); } preempt_enable(); set_current_state(TASK_INTERRUPTIBLE); 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..37f458e6882 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -559,7 +559,7 @@ error: abort_creds(new); return retval; } - + /* * change the user struct in a credentials set to match the new UID */ @@ -571,6 +571,11 @@ static int set_user(struct cred *new) if (!new_user) return -EAGAIN; + if (!task_can_switch_user(new_user, current)) { + free_uid(new_user); + return -EINVAL; + } + if (atomic_read(&new_user->processes) >= current->signal->rlim[RLIMIT_NPROC].rlim_cur && new_user != INIT_USER) { @@ -631,10 +636,11 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) goto error; } - retval = -EAGAIN; - if (new->uid != old->uid && set_user(new) < 0) - goto error; - + if (new->uid != old->uid) { + retval = set_user(new); + if (retval < 0) + goto error; + } if (ruid != (uid_t) -1 || (euid != (uid_t) -1 && euid != old->uid)) new->suid = new->euid; @@ -680,9 +686,10 @@ SYSCALL_DEFINE1(setuid, uid_t, uid) retval = -EPERM; if (capable(CAP_SETUID)) { new->suid = new->uid = uid; - if (uid != old->uid && set_user(new) < 0) { - retval = -EAGAIN; - goto error; + if (uid != old->uid) { + retval = set_user(new); + if (retval < 0) + goto error; } } else if (uid != old->uid && uid != new->suid) { goto error; @@ -734,11 +741,13 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) goto error; } - retval = -EAGAIN; if (ruid != (uid_t) -1) { new->uid = ruid; - if (ruid != old->uid && set_user(new) < 0) - goto error; + if (ruid != old->uid) { + retval = set_user(new); + if (retval < 0) + goto error; + } } if (euid != (uid_t) -1) new->euid = euid; @@ -1525,22 +1534,14 @@ 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/sysctl_check.c b/kernel/sysctl_check.c index fafeb48f27c..b38423ca711 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/Makefile b/kernel/time/Makefile index 905b0b50792..0b0a6366c9d 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -1,4 +1,4 @@ -obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o +obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index ea2f48af83c..d13be216a79 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/clocksource.c b/kernel/time/clocksource.c index ca89e1593f0..c46c931a7fe 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -31,6 +31,82 @@ #include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */ #include <linux/tick.h> +void timecounter_init(struct timecounter *tc, + const struct cyclecounter *cc, + u64 start_tstamp) +{ + tc->cc = cc; + tc->cycle_last = cc->read(cc); + tc->nsec = start_tstamp; +} +EXPORT_SYMBOL(timecounter_init); + +/** + * timecounter_read_delta - get nanoseconds since last call of this function + * @tc: Pointer to time counter + * + * When the underlying cycle counter runs over, this will be handled + * correctly as long as it does not run over more than once between + * calls. + * + * The first call to this function for a new time counter initializes + * the time tracking and returns an undefined result. + */ +static u64 timecounter_read_delta(struct timecounter *tc) +{ + cycle_t cycle_now, cycle_delta; + u64 ns_offset; + + /* read cycle counter: */ + cycle_now = tc->cc->read(tc->cc); + + /* calculate the delta since the last timecounter_read_delta(): */ + cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask; + + /* convert to nanoseconds: */ + ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta); + + /* update time stamp of timecounter_read_delta() call: */ + tc->cycle_last = cycle_now; + + return ns_offset; +} + +u64 timecounter_read(struct timecounter *tc) +{ + u64 nsec; + + /* increment time by nanoseconds since last call */ + nsec = timecounter_read_delta(tc); + nsec += tc->nsec; + tc->nsec = nsec; + + return nsec; +} +EXPORT_SYMBOL(timecounter_read); + +u64 timecounter_cyc2time(struct timecounter *tc, + cycle_t cycle_tstamp) +{ + u64 cycle_delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask; + u64 nsec; + + /* + * Instead of always treating cycle_tstamp as more recent + * than tc->cycle_last, detect when it is too far in the + * future and treat it as old time stamp instead. + */ + if (cycle_delta > tc->cc->mask / 2) { + cycle_delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask; + nsec = tc->nsec - cyclecounter_cyc2ns(tc->cc, cycle_delta); + } else { + nsec = cyclecounter_cyc2ns(tc->cc, cycle_delta) + tc->nsec; + } + + return nsec; +} +EXPORT_SYMBOL(timecounter_cyc2time); + /* XXX - Would like a better way for initializing curr_clocksource */ extern struct clocksource clocksource_jiffies; diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index f5f793d9241..7fc64375ff4 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -1,71 +1,129 @@ /* - * linux/kernel/time/ntp.c - * * NTP state machine interfaces and logic. * * This code was mainly moved from kernel/timer.c and kernel/time.c * Please see those files for relevant copyright info and historical * changelogs. */ - -#include <linux/mm.h> -#include <linux/time.h> -#include <linux/timex.h> -#include <linux/jiffies.h> -#include <linux/hrtimer.h> #include <linux/capability.h> -#include <linux/math64.h> #include <linux/clocksource.h> #include <linux/workqueue.h> -#include <asm/timex.h> +#include <linux/hrtimer.h> +#include <linux/jiffies.h> +#include <linux/math64.h> +#include <linux/timex.h> +#include <linux/time.h> +#include <linux/mm.h> /* - * Timekeeping variables + * NTP timekeeping variables: */ -unsigned long tick_usec = TICK_USEC; /* USER_HZ period (usec) */ -unsigned long tick_nsec; /* ACTHZ period (nsec) */ -u64 tick_length; -static u64 tick_length_base; -static struct hrtimer leap_timer; +/* USER_HZ period (usecs): */ +unsigned long tick_usec = TICK_USEC; -#define MAX_TICKADJ 500 /* microsecs */ -#define MAX_TICKADJ_SCALED (((u64)(MAX_TICKADJ * NSEC_PER_USEC) << \ - NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ) +/* ACTHZ period (nsecs): */ +unsigned long tick_nsec; + +u64 tick_length; +static u64 tick_length_base; + +static struct hrtimer leap_timer; + +#define MAX_TICKADJ 500LL /* usecs */ +#define MAX_TICKADJ_SCALED \ + (((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ) /* * phase-lock loop variables */ -/* TIME_ERROR prevents overwriting the CMOS clock */ -static int time_state = TIME_OK; /* clock synchronization status */ -int time_status = STA_UNSYNC; /* clock status bits */ -static long time_tai; /* TAI offset (s) */ -static s64 time_offset; /* time adjustment (ns) */ -static long time_constant = 2; /* pll time constant */ -long time_maxerror = NTP_PHASE_LIMIT; /* maximum error (us) */ -long time_esterror = NTP_PHASE_LIMIT; /* estimated error (us) */ -static s64 time_freq; /* frequency offset (scaled ns/s)*/ -static long time_reftime; /* time at last adjustment (s) */ -long time_adjust; -static long ntp_tick_adj; +/* + * clock synchronization status + * + * (TIME_ERROR prevents overwriting the CMOS clock) + */ +static int time_state = TIME_OK; + +/* clock status bits: */ +int time_status = STA_UNSYNC; + +/* TAI offset (secs): */ +static long time_tai; + +/* time adjustment (nsecs): */ +static s64 time_offset; + +/* pll time constant: */ +static long time_constant = 2; + +/* maximum error (usecs): */ +long time_maxerror = NTP_PHASE_LIMIT; + +/* estimated error (usecs): */ +long time_esterror = NTP_PHASE_LIMIT; + +/* frequency offset (scaled nsecs/secs): */ +static s64 time_freq; + +/* time at last adjustment (secs): */ +static long time_reftime; + +long time_adjust; + +/* constant (boot-param configurable) NTP tick adjustment (upscaled) */ +static s64 ntp_tick_adj; + +/* + * NTP methods: + */ + +/* + * Update (tick_length, tick_length_base, tick_nsec), based + * on (tick_usec, ntp_tick_adj, time_freq): + */ static void ntp_update_frequency(void) { - u64 second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ) - << NTP_SCALE_SHIFT; - second_length += (s64)ntp_tick_adj << NTP_SCALE_SHIFT; - second_length += time_freq; + u64 second_length; + u64 new_base; + + second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ) + << NTP_SCALE_SHIFT; + + second_length += ntp_tick_adj; + second_length += time_freq; - tick_length_base = second_length; + tick_nsec = div_u64(second_length, HZ) >> NTP_SCALE_SHIFT; + new_base = div_u64(second_length, NTP_INTERVAL_FREQ); - tick_nsec = div_u64(second_length, HZ) >> NTP_SCALE_SHIFT; - tick_length_base = div_u64(tick_length_base, NTP_INTERVAL_FREQ); + /* + * Don't wait for the next second_overflow, apply + * the change to the tick length immediately: + */ + tick_length += new_base - tick_length_base; + tick_length_base = new_base; +} + +static inline s64 ntp_update_offset_fll(s64 offset64, long secs) +{ + time_status &= ~STA_MODE; + + if (secs < MINSEC) + return 0; + + if (!(time_status & STA_FLL) && (secs <= MAXSEC)) + return 0; + + time_status |= STA_MODE; + + return div_s64(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs); } static void ntp_update_offset(long offset) { - long mtemp; s64 freq_adj; + s64 offset64; + long secs; if (!(time_status & STA_PLL)) return; @@ -84,24 +142,23 @@ static void ntp_update_offset(long offset) * Select how the frequency is to be controlled * and in which mode (PLL or FLL). */ - if (time_status & STA_FREQHOLD || time_reftime == 0) - time_reftime = xtime.tv_sec; - mtemp = xtime.tv_sec - time_reftime; + secs = xtime.tv_sec - time_reftime; + if (unlikely(time_status & STA_FREQHOLD)) + secs = 0; + time_reftime = xtime.tv_sec; - freq_adj = (s64)offset * mtemp; - freq_adj <<= NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant); - time_status &= ~STA_MODE; - if (mtemp >= MINSEC && (time_status & STA_FLL || mtemp > MAXSEC)) { - freq_adj += div_s64((s64)offset << (NTP_SCALE_SHIFT - SHIFT_FLL), - mtemp); - time_status |= STA_MODE; - } - freq_adj += time_freq; - freq_adj = min(freq_adj, MAXFREQ_SCALED); - time_freq = max(freq_adj, -MAXFREQ_SCALED); + offset64 = offset; + freq_adj = (offset64 * secs) << + (NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant)); - time_offset = div_s64((s64)offset << NTP_SCALE_SHIFT, NTP_INTERVAL_FREQ); + freq_adj += ntp_update_offset_fll(offset64, secs); + + freq_adj = min(freq_adj + time_freq, MAXFREQ_SCALED); + + time_freq = max(freq_adj, -MAXFREQ_SCALED); + + time_offset = div_s64(offset64 << NTP_SCALE_SHIFT, NTP_INTERVAL_FREQ); } /** @@ -111,15 +168,15 @@ static void ntp_update_offset(long offset) */ void ntp_clear(void) { - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + time_adjust = 0; /* stop active adjtime() */ + time_status |= STA_UNSYNC; + time_maxerror = NTP_PHASE_LIMIT; + time_esterror = NTP_PHASE_LIMIT; ntp_update_frequency(); - tick_length = tick_length_base; - time_offset = 0; + tick_length = tick_length_base; + time_offset = 0; } /* @@ -140,8 +197,8 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) xtime.tv_sec--; wall_to_monotonic.tv_sec++; time_state = TIME_OOP; - printk(KERN_NOTICE "Clock: " - "inserting leap second 23:59:60 UTC\n"); + printk(KERN_NOTICE + "Clock: inserting leap second 23:59:60 UTC\n"); hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC); res = HRTIMER_RESTART; break; @@ -150,8 +207,8 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) time_tai--; wall_to_monotonic.tv_sec--; time_state = TIME_WAIT; - printk(KERN_NOTICE "Clock: " - "deleting leap second 23:59:59 UTC\n"); + printk(KERN_NOTICE + "Clock: deleting leap second 23:59:59 UTC\n"); break; case TIME_OOP: time_tai++; @@ -179,7 +236,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) */ void second_overflow(void) { - s64 time_adj; + s64 delta; /* Bump the maxerror field */ time_maxerror += MAXFREQ / NSEC_PER_USEC; @@ -192,24 +249,30 @@ void second_overflow(void) * Compute the phase adjustment for the next second. The offset is * reduced by a fixed factor times the time constant. */ - tick_length = tick_length_base; - time_adj = shift_right(time_offset, SHIFT_PLL + time_constant); - time_offset -= time_adj; - tick_length += time_adj; - - if (unlikely(time_adjust)) { - if (time_adjust > MAX_TICKADJ) { - time_adjust -= MAX_TICKADJ; - tick_length += MAX_TICKADJ_SCALED; - } else if (time_adjust < -MAX_TICKADJ) { - time_adjust += MAX_TICKADJ; - tick_length -= MAX_TICKADJ_SCALED; - } else { - tick_length += (s64)(time_adjust * NSEC_PER_USEC / - NTP_INTERVAL_FREQ) << NTP_SCALE_SHIFT; - time_adjust = 0; - } + tick_length = tick_length_base; + + delta = shift_right(time_offset, SHIFT_PLL + time_constant); + time_offset -= delta; + tick_length += delta; + + if (!time_adjust) + return; + + if (time_adjust > MAX_TICKADJ) { + time_adjust -= MAX_TICKADJ; + tick_length += MAX_TICKADJ_SCALED; + return; } + + if (time_adjust < -MAX_TICKADJ) { + time_adjust += MAX_TICKADJ; + tick_length -= MAX_TICKADJ_SCALED; + return; + } + + tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ) + << NTP_SCALE_SHIFT; + time_adjust = 0; } #ifdef CONFIG_GENERIC_CMOS_UPDATE @@ -233,12 +296,13 @@ static void sync_cmos_clock(struct work_struct *work) * This code is run on a timer. If the clock is set, that timer * may not expire at the correct time. Thus, we adjust... */ - if (!ntp_synced()) + if (!ntp_synced()) { /* * Not synced, exit, do not restart a timer (if one is * running, let it run out). */ return; + } getnstimeofday(&now); if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2) @@ -270,7 +334,116 @@ static void notify_cmos_timer(void) static inline void notify_cmos_timer(void) { } #endif -/* adjtimex mainly allows reading (and writing, if superuser) of +/* + * Start the leap seconds timer: + */ +static inline void ntp_start_leap_timer(struct timespec *ts) +{ + long now = ts->tv_sec; + + if (time_status & STA_INS) { + time_state = TIME_INS; + now += 86400 - now % 86400; + hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS); + + return; + } + + if (time_status & STA_DEL) { + time_state = TIME_DEL; + now += 86400 - (now + 1) % 86400; + hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS); + } +} + +/* + * Propagate a new txc->status value into the NTP state: + */ +static inline void process_adj_status(struct timex *txc, struct timespec *ts) +{ + if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { + time_state = TIME_OK; + time_status = STA_UNSYNC; + } + + /* + * If we turn on PLL adjustments then reset the + * reference time to current time. + */ + if (!(time_status & STA_PLL) && (txc->status & STA_PLL)) + time_reftime = xtime.tv_sec; + + /* only set allowed bits */ + time_status &= STA_RONLY; + time_status |= txc->status & ~STA_RONLY; + + switch (time_state) { + case TIME_OK: + ntp_start_leap_timer(ts); + break; + case TIME_INS: + case TIME_DEL: + time_state = TIME_OK; + ntp_start_leap_timer(ts); + case TIME_WAIT: + if (!(time_status & (STA_INS | STA_DEL))) + time_state = TIME_OK; + break; + case TIME_OOP: + hrtimer_restart(&leap_timer); + break; + } +} +/* + * Called with the xtime lock held, so we can access and modify + * all the global NTP state: + */ +static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts) +{ + if (txc->modes & ADJ_STATUS) + process_adj_status(txc, ts); + + if (txc->modes & ADJ_NANO) + time_status |= STA_NANO; + + if (txc->modes & ADJ_MICRO) + time_status &= ~STA_NANO; + + if (txc->modes & ADJ_FREQUENCY) { + time_freq = txc->freq * PPM_SCALE; + time_freq = min(time_freq, MAXFREQ_SCALED); + time_freq = max(time_freq, -MAXFREQ_SCALED); + } + + if (txc->modes & ADJ_MAXERROR) + time_maxerror = txc->maxerror; + + if (txc->modes & ADJ_ESTERROR) + time_esterror = txc->esterror; + + if (txc->modes & ADJ_TIMECONST) { + time_constant = txc->constant; + if (!(time_status & STA_NANO)) + time_constant += 4; + time_constant = min(time_constant, (long)MAXTC); + time_constant = max(time_constant, 0l); + } + + if (txc->modes & ADJ_TAI && txc->constant > 0) + time_tai = txc->constant; + + if (txc->modes & ADJ_OFFSET) + ntp_update_offset(txc->offset); + + if (txc->modes & ADJ_TICK) + tick_usec = txc->tick; + + if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET)) + ntp_update_frequency(); +} + +/* + * adjtimex mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. */ int do_adjtimex(struct timex *txc) @@ -291,11 +464,14 @@ int do_adjtimex(struct timex *txc) if (txc->modes && !capable(CAP_SYS_TIME)) return -EPERM; - /* if the quartz is off by more than 10% something is VERY wrong! */ + /* + * if the quartz is off by more than 10% then + * something is VERY wrong! + */ if (txc->modes & ADJ_TICK && (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) - return -EINVAL; + return -EINVAL; if (txc->modes & ADJ_STATUS && time_state != TIME_OK) hrtimer_cancel(&leap_timer); @@ -305,7 +481,6 @@ int do_adjtimex(struct timex *txc) write_seqlock_irq(&xtime_lock); - /* If there are input parameters, then process them */ if (txc->modes & ADJ_ADJTIME) { long save_adjust = time_adjust; @@ -315,98 +490,24 @@ int do_adjtimex(struct timex *txc) ntp_update_frequency(); } txc->offset = save_adjust; - goto adj_done; - } - if (txc->modes) { - long sec; - - if (txc->modes & ADJ_STATUS) { - if ((time_status & STA_PLL) && - !(txc->status & STA_PLL)) { - time_state = TIME_OK; - time_status = STA_UNSYNC; - } - /* only set allowed bits */ - time_status &= STA_RONLY; - time_status |= txc->status & ~STA_RONLY; - - switch (time_state) { - case TIME_OK: - start_timer: - sec = ts.tv_sec; - if (time_status & STA_INS) { - time_state = TIME_INS; - sec += 86400 - sec % 86400; - hrtimer_start(&leap_timer, ktime_set(sec, 0), HRTIMER_MODE_ABS); - } else if (time_status & STA_DEL) { - time_state = TIME_DEL; - sec += 86400 - (sec + 1) % 86400; - hrtimer_start(&leap_timer, ktime_set(sec, 0), HRTIMER_MODE_ABS); - } - break; - case TIME_INS: - case TIME_DEL: - time_state = TIME_OK; - goto start_timer; - break; - case TIME_WAIT: - if (!(time_status & (STA_INS | STA_DEL))) - time_state = TIME_OK; - break; - case TIME_OOP: - hrtimer_restart(&leap_timer); - break; - } - } - - if (txc->modes & ADJ_NANO) - time_status |= STA_NANO; - if (txc->modes & ADJ_MICRO) - time_status &= ~STA_NANO; - - if (txc->modes & ADJ_FREQUENCY) { - time_freq = (s64)txc->freq * PPM_SCALE; - time_freq = min(time_freq, MAXFREQ_SCALED); - time_freq = max(time_freq, -MAXFREQ_SCALED); - } - - if (txc->modes & ADJ_MAXERROR) - time_maxerror = txc->maxerror; - if (txc->modes & ADJ_ESTERROR) - time_esterror = txc->esterror; - - if (txc->modes & ADJ_TIMECONST) { - time_constant = txc->constant; - if (!(time_status & STA_NANO)) - time_constant += 4; - time_constant = min(time_constant, (long)MAXTC); - time_constant = max(time_constant, 0l); - } - - if (txc->modes & ADJ_TAI && txc->constant > 0) - time_tai = txc->constant; - - if (txc->modes & ADJ_OFFSET) - ntp_update_offset(txc->offset); - if (txc->modes & ADJ_TICK) - tick_usec = txc->tick; + } else { - if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET)) - ntp_update_frequency(); - } + /* If there are input parameters, then process them: */ + if (txc->modes) + process_adjtimex_modes(txc, &ts); - txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, + txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, NTP_SCALE_SHIFT); - if (!(time_status & STA_NANO)) - txc->offset /= NSEC_PER_USEC; + if (!(time_status & STA_NANO)) + txc->offset /= NSEC_PER_USEC; + } -adj_done: result = time_state; /* mostly `TIME_OK' */ if (time_status & (STA_UNSYNC|STA_CLOCKERR)) result = TIME_ERROR; txc->freq = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) * - (s64)PPM_SCALE_INV, NTP_SCALE_SHIFT); + PPM_SCALE_INV, NTP_SCALE_SHIFT); txc->maxerror = time_maxerror; txc->esterror = time_esterror; txc->status = time_status; @@ -425,6 +526,7 @@ adj_done: txc->calcnt = 0; txc->errcnt = 0; txc->stbcnt = 0; + write_sequnlock_irq(&xtime_lock); txc->time.tv_sec = ts.tv_sec; @@ -440,6 +542,8 @@ adj_done: static int __init ntp_tick_adj_setup(char *str) { ntp_tick_adj = simple_strtol(str, NULL, 0); + ntp_tick_adj <<= NTP_SCALE_SHIFT; + return 1; } 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/time/timecompare.c b/kernel/time/timecompare.c new file mode 100644 index 00000000000..71e7f1a1915 --- /dev/null +++ b/kernel/time/timecompare.c @@ -0,0 +1,191 @@ +/* + * Copyright (C) 2009 Intel Corporation. + * Author: Patrick Ohly <patrick.ohly@intel.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#include <linux/timecompare.h> +#include <linux/module.h> +#include <linux/math64.h> + +/* + * fixed point arithmetic scale factor for skew + * + * Usually one would measure skew in ppb (parts per billion, 1e9), but + * using a factor of 2 simplifies the math. + */ +#define TIMECOMPARE_SKEW_RESOLUTION (((s64)1)<<30) + +ktime_t timecompare_transform(struct timecompare *sync, + u64 source_tstamp) +{ + u64 nsec; + + nsec = source_tstamp + sync->offset; + nsec += (s64)(source_tstamp - sync->last_update) * sync->skew / + TIMECOMPARE_SKEW_RESOLUTION; + + return ns_to_ktime(nsec); +} +EXPORT_SYMBOL(timecompare_transform); + +int timecompare_offset(struct timecompare *sync, + s64 *offset, + u64 *source_tstamp) +{ + u64 start_source = 0, end_source = 0; + struct { + s64 offset; + s64 duration_target; + } buffer[10], sample, *samples; + int counter = 0, i; + int used; + int index; + int num_samples = sync->num_samples; + + if (num_samples > sizeof(buffer)/sizeof(buffer[0])) { + samples = kmalloc(sizeof(*samples) * num_samples, GFP_ATOMIC); + if (!samples) { + samples = buffer; + num_samples = sizeof(buffer)/sizeof(buffer[0]); + } + } else { + samples = buffer; + } + + /* run until we have enough valid samples, but do not try forever */ + i = 0; + counter = 0; + while (1) { + u64 ts; + ktime_t start, end; + + start = sync->target(); + ts = timecounter_read(sync->source); + end = sync->target(); + + if (!i) + start_source = ts; + + /* ignore negative durations */ + sample.duration_target = ktime_to_ns(ktime_sub(end, start)); + if (sample.duration_target >= 0) { + /* + * assume symetric delay to and from source: + * average target time corresponds to measured + * source time + */ + sample.offset = + ktime_to_ns(ktime_add(end, start)) / 2 - + ts; + + /* simple insertion sort based on duration */ + index = counter - 1; + while (index >= 0) { + if (samples[index].duration_target < + sample.duration_target) + break; + samples[index + 1] = samples[index]; + index--; + } + samples[index + 1] = sample; + counter++; + } + + i++; + if (counter >= num_samples || i >= 100000) { + end_source = ts; + break; + } + } + + *source_tstamp = (end_source + start_source) / 2; + + /* remove outliers by only using 75% of the samples */ + used = counter * 3 / 4; + if (!used) + used = counter; + if (used) { + /* calculate average */ + s64 off = 0; + for (index = 0; index < used; index++) + off += samples[index].offset; + *offset = div_s64(off, used); + } + + if (samples && samples != buffer) + kfree(samples); + + return used; +} +EXPORT_SYMBOL(timecompare_offset); + +void __timecompare_update(struct timecompare *sync, + u64 source_tstamp) +{ + s64 offset; + u64 average_time; + + if (!timecompare_offset(sync, &offset, &average_time)) + return; + + if (!sync->last_update) { + sync->last_update = average_time; + sync->offset = offset; + sync->skew = 0; + } else { + s64 delta_nsec = average_time - sync->last_update; + + /* avoid division by negative or small deltas */ + if (delta_nsec >= 10000) { + s64 delta_offset_nsec = offset - sync->offset; + s64 skew; /* delta_offset_nsec * + TIMECOMPARE_SKEW_RESOLUTION / + delta_nsec */ + u64 divisor; + + /* div_s64() is limited to 32 bit divisor */ + skew = delta_offset_nsec * TIMECOMPARE_SKEW_RESOLUTION; + divisor = delta_nsec; + while (unlikely(divisor >= ((s64)1) << 32)) { + /* divide both by 2; beware, right shift + of negative value has undefined + behavior and can only be used for + the positive divisor */ + skew = div_s64(skew, 2); + divisor >>= 1; + } + skew = div_s64(skew, divisor); + + /* + * Calculate new overall skew as 4/16 the + * old value and 12/16 the new one. This is + * a rather arbitrary tradeoff between + * only using the latest measurement (0/16 and + * 16/16) and even more weight on past measurements. + */ +#define TIMECOMPARE_NEW_SKEW_PER_16 12 + sync->skew = + div_s64((16 - TIMECOMPARE_NEW_SKEW_PER_16) * + sync->skew + + TIMECOMPARE_NEW_SKEW_PER_16 * skew, + 16); + sync->last_update = average_time; + sync->offset = offset; + } + } +} +EXPORT_SYMBOL(__timecompare_update); diff --git a/kernel/timer.c b/kernel/timer.c index 13dd64fe143..9b77fc9a9ac 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -589,11 +589,14 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer, } } -int __mod_timer(struct timer_list *timer, unsigned long expires) +static inline int +__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) { struct tvec_base *base, *new_base; unsigned long flags; - int ret = 0; + int ret; + + ret = 0; timer_stats_timer_set_start_info(timer); BUG_ON(!timer->function); @@ -603,6 +606,9 @@ int __mod_timer(struct timer_list *timer, unsigned long expires) if (timer_pending(timer)) { detach_timer(timer, 0); ret = 1; + } else { + if (pending_only) + goto out_unlock; } debug_timer_activate(timer); @@ -629,42 +635,28 @@ int __mod_timer(struct timer_list *timer, unsigned long expires) timer->expires = expires; internal_add_timer(base, timer); + +out_unlock: spin_unlock_irqrestore(&base->lock, flags); return ret; } -EXPORT_SYMBOL(__mod_timer); - /** - * add_timer_on - start a timer on a particular CPU - * @timer: the timer to be added - * @cpu: the CPU to start it on + * mod_timer_pending - modify a pending timer's timeout + * @timer: the pending timer to be modified + * @expires: new timeout in jiffies * - * This is not very scalable on SMP. Double adds are not possible. + * mod_timer_pending() is the same for pending timers as mod_timer(), + * but will not re-activate and modify already deleted timers. + * + * It is useful for unserialized use of timers. */ -void add_timer_on(struct timer_list *timer, int cpu) +int mod_timer_pending(struct timer_list *timer, unsigned long expires) { - struct tvec_base *base = per_cpu(tvec_bases, cpu); - unsigned long flags; - - timer_stats_timer_set_start_info(timer); - BUG_ON(timer_pending(timer) || !timer->function); - spin_lock_irqsave(&base->lock, flags); - timer_set_base(timer, base); - debug_timer_activate(timer); - internal_add_timer(base, timer); - /* - * Check whether the other CPU is idle and needs to be - * triggered to reevaluate the timer wheel when nohz is - * active. We are protected against the other CPU fiddling - * with the timer by holding the timer base lock. This also - * makes sure that a CPU on the way to idle can not evaluate - * the timer wheel. - */ - wake_up_idle_cpu(cpu); - spin_unlock_irqrestore(&base->lock, flags); + return __mod_timer(timer, expires, true); } +EXPORT_SYMBOL(mod_timer_pending); /** * mod_timer - modify a timer's timeout @@ -688,9 +680,6 @@ void add_timer_on(struct timer_list *timer, int cpu) */ int mod_timer(struct timer_list *timer, unsigned long expires) { - BUG_ON(!timer->function); - - timer_stats_timer_set_start_info(timer); /* * This is a common optimization triggered by the * networking code - if the timer is re-modified @@ -699,12 +688,62 @@ int mod_timer(struct timer_list *timer, unsigned long expires) if (timer->expires == expires && timer_pending(timer)) return 1; - return __mod_timer(timer, expires); + return __mod_timer(timer, expires, false); } - EXPORT_SYMBOL(mod_timer); /** + * add_timer - start a timer + * @timer: the timer to be added + * + * The kernel will do a ->function(->data) callback from the + * timer interrupt at the ->expires point in the future. The + * current time is 'jiffies'. + * + * The timer's ->expires, ->function (and if the handler uses it, ->data) + * fields must be set prior calling this function. + * + * Timers with an ->expires field in the past will be executed in the next + * timer tick. + */ +void add_timer(struct timer_list *timer) +{ + BUG_ON(timer_pending(timer)); + mod_timer(timer, timer->expires); +} +EXPORT_SYMBOL(add_timer); + +/** + * add_timer_on - start a timer on a particular CPU + * @timer: the timer to be added + * @cpu: the CPU to start it on + * + * This is not very scalable on SMP. Double adds are not possible. + */ +void add_timer_on(struct timer_list *timer, int cpu) +{ + struct tvec_base *base = per_cpu(tvec_bases, cpu); + unsigned long flags; + + timer_stats_timer_set_start_info(timer); + BUG_ON(timer_pending(timer) || !timer->function); + spin_lock_irqsave(&base->lock, flags); + timer_set_base(timer, base); + debug_timer_activate(timer); + internal_add_timer(base, timer); + /* + * Check whether the other CPU is idle and needs to be + * triggered to reevaluate the timer wheel when nohz is + * active. We are protected against the other CPU fiddling + * with the timer by holding the timer base lock. This also + * makes sure that a CPU on the way to idle can not evaluate + * the timer wheel. + */ + wake_up_idle_cpu(cpu); + spin_unlock_irqrestore(&base->lock, flags); +} + +/** * del_timer - deactive a timer. * @timer: the timer to be deactivated * @@ -733,7 +772,6 @@ int del_timer(struct timer_list *timer) return ret; } - EXPORT_SYMBOL(del_timer); #ifdef CONFIG_SMP @@ -767,7 +805,6 @@ out: return ret; } - EXPORT_SYMBOL(try_to_del_timer_sync); /** @@ -796,7 +833,6 @@ int del_timer_sync(struct timer_list *timer) cpu_relax(); } } - EXPORT_SYMBOL(del_timer_sync); #endif @@ -1268,7 +1304,7 @@ signed long __sched schedule_timeout(signed long timeout) expire = timeout + jiffies; setup_timer_on_stack(&timer, process_timeout, (unsigned long)current); - __mod_timer(&timer, expire); + __mod_timer(&timer, expire, false); schedule(); del_singleshot_timer_sync(&timer); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index e2a4ff6fc3a..34e707e5ab8 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -52,6 +52,7 @@ config FUNCTION_TRACER depends on HAVE_FUNCTION_TRACER depends on DEBUG_KERNEL select FRAME_POINTER + select KALLSYMS select TRACING select CONTEXT_SWITCH_TRACER help @@ -238,6 +239,7 @@ config STACK_TRACER depends on DEBUG_KERNEL select FUNCTION_TRACER select STACKTRACE + select KALLSYMS help This special tracer records the maximum stack footprint of the kernel and displays it in debugfs/tracing/stack_trace. @@ -302,4 +304,27 @@ 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/ftrace.c b/kernel/trace/ftrace.c index 2f32969c09d..fdf913dfc7e 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) { @@ -2026,7 +2033,7 @@ free: static int start_graph_tracing(void) { struct ftrace_ret_stack **ret_stack_list; - int ret; + int ret, cpu; ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE * sizeof(struct ftrace_ret_stack *), @@ -2035,6 +2042,10 @@ static int start_graph_tracing(void) if (!ret_stack_list) return -ENOMEM; + /* The cpu_boot init_task->ret_stack will never be freed */ + for_each_online_cpu(cpu) + ftrace_graph_init_task(idle_task(cpu)); + do { ret = alloc_retstack_tasklist(ret_stack_list); } while (ret == -EAGAIN); @@ -2043,6 +2054,27 @@ 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 +2082,9 @@ 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 +2110,7 @@ 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_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index fffcb069f1d..80e503ef613 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/mmiotrace.h> #include <linux/pci.h> +#include <asm/atomic.h> #include "trace.h" @@ -19,6 +20,7 @@ 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 +123,11 @@ 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; } @@ -310,8 +312,10 @@ 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 +342,10 @@ 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_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/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 88c8eb70f54..bc8e80a86bc 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -23,10 +23,20 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu) { struct ring_buffer_event *event; struct trace_entry *entry; + unsigned int loops = 0; while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) { entry = ring_buffer_event_data(event); + /* + * The ring buffer is a size of trace_buf_size, if + * we loop more than the size, there's something wrong + * with the ring buffer. + */ + if (loops++ > trace_buf_size) { + printk(KERN_CONT ".. bad ring buffer "); + goto failed; + } if (!trace_valid_entry(entry)) { printk(KERN_CONT ".. invalid entry %d ", entry->type); @@ -57,11 +67,20 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count) cnt = ring_buffer_entries(tr->buffer); + /* + * The trace_test_buffer_cpu runs a while loop to consume all data. + * If the calling tracer is broken, and is constantly filling + * the buffer, this will run forever, and hard lock the box. + * We disable the ring buffer while we do this test to prevent + * a hard lock up. + */ + tracing_off(); for_each_possible_cpu(cpu) { ret = trace_test_buffer_cpu(tr, cpu); if (ret) break; } + tracing_on(); __raw_spin_unlock(&ftrace_max_lock); local_irq_restore(flags); diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 43f891b05a4..00d59d048ed 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -122,8 +122,10 @@ void acct_update_integrals(struct task_struct *tsk) if (likely(tsk->mm)) { cputime_t time, dtime; struct timeval value; + unsigned long flags; u64 delta; + local_irq_save(flags); time = tsk->stime + tsk->utime; dtime = cputime_sub(time, tsk->acct_timexpd); jiffies_to_timeval(cputime_to_jiffies(dtime), &value); @@ -131,10 +133,12 @@ void acct_update_integrals(struct task_struct *tsk) delta = delta * USEC_PER_SEC + value.tv_usec; if (delta == 0) - return; + goto out; tsk->acct_timexpd = time; tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm); tsk->acct_vm_mem1 += delta * tsk->mm->total_vm; + out: + local_irq_restore(flags); } } diff --git a/kernel/user.c b/kernel/user.c index 477b6660f44..850e0ba41c1 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -20,7 +20,7 @@ struct user_namespace init_user_ns = { .kref = { - .refcount = ATOMIC_INIT(1), + .refcount = ATOMIC_INIT(2), }, .creator = &root_user, }; @@ -72,6 +72,7 @@ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent) static void uid_hash_remove(struct user_struct *up) { hlist_del_init(&up->uidhash_node); + put_user_ns(up->user_ns); } static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent) @@ -285,14 +286,12 @@ int __init uids_sysfs_init(void) /* work function to remove sysfs directory for a user and free up * corresponding structures. */ -static void remove_user_sysfs_dir(struct work_struct *w) +static void cleanup_user_struct(struct work_struct *w) { struct user_struct *up = container_of(w, struct user_struct, work); unsigned long flags; int remove_user = 0; - if (up->user_ns != &init_user_ns) - return; /* Make uid_hash_remove() + sysfs_remove_file() + kobject_del() * atomic. */ @@ -311,9 +310,11 @@ static void remove_user_sysfs_dir(struct work_struct *w) if (!remove_user) goto done; - kobject_uevent(&up->kobj, KOBJ_REMOVE); - kobject_del(&up->kobj); - kobject_put(&up->kobj); + if (up->user_ns == &init_user_ns) { + kobject_uevent(&up->kobj, KOBJ_REMOVE); + kobject_del(&up->kobj); + kobject_put(&up->kobj); + } sched_destroy_user(up); key_put(up->uid_keyring); @@ -334,8 +335,7 @@ static void free_user(struct user_struct *up, unsigned long flags) atomic_inc(&up->__count); spin_unlock_irqrestore(&uidhash_lock, flags); - put_user_ns(up->user_ns); - INIT_WORK(&up->work, remove_user_sysfs_dir); + INIT_WORK(&up->work, cleanup_user_struct); schedule_work(&up->work); } @@ -357,12 +357,29 @@ static void free_user(struct user_struct *up, unsigned long flags) sched_destroy_user(up); key_put(up->uid_keyring); key_put(up->session_keyring); - put_user_ns(up->user_ns); kmem_cache_free(uid_cachep, up); } #endif +#if defined(CONFIG_RT_GROUP_SCHED) && defined(CONFIG_USER_SCHED) +/* + * We need to check if a setuid can take place. This function should be called + * before successfully completing the setuid. + */ +int task_can_switch_user(struct user_struct *up, struct task_struct *tsk) +{ + + return sched_rt_can_attach(up->tg, tsk); + +} +#else +int task_can_switch_user(struct user_struct *up, struct task_struct *tsk) +{ + return 1; +} +#endif + /* * Locate the user_struct for the passed UID. If found, take a ref on it. The * caller must undo that ref with free_uid(). diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 79084311ee5..076c7c8215b 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -60,12 +60,25 @@ int create_user_ns(struct cred *new) return 0; } -void free_user_ns(struct kref *kref) +/* + * Deferred destructor for a user namespace. This is required because + * free_user_ns() may be called with uidhash_lock held, but we need to call + * back to free_uid() which will want to take the lock again. + */ +static void free_user_ns_work(struct work_struct *work) { - struct user_namespace *ns; - - ns = container_of(kref, struct user_namespace, kref); + struct user_namespace *ns = + container_of(work, struct user_namespace, destroyer); free_uid(ns->creator); kfree(ns); } + +void free_user_ns(struct kref *kref) +{ + struct user_namespace *ns = + container_of(kref, struct user_namespace, kref); + + INIT_WORK(&ns->destroyer, free_user_ns_work); + schedule_work(&ns->destroyer); +} EXPORT_SYMBOL(free_user_ns); 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 } |