diff options
Diffstat (limited to 'kernel')
63 files changed, 4528 insertions, 938 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 5068e2a4e75f..7bd0598bfe6a 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -199,4 +199,4 @@ config INLINE_WRITE_UNLOCK_IRQRESTORE def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE config MUTEX_SPIN_ON_OWNER - def_bool SMP && !DEBUG_MUTEXES + def_bool SMP && !DEBUG_MUTEXES && !PREEMPT_RT_FULL diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 24e7cb0ba26a..d0e93725d891 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -1,3 +1,10 @@ +config PREEMPT + bool + select PREEMPT_COUNT + +config PREEMPT_RT_BASE + bool + select PREEMPT choice prompt "Preemption Model" @@ -33,9 +40,9 @@ config PREEMPT_VOLUNTARY Select this if you are building a kernel for a desktop system. -config PREEMPT +config PREEMPT__LL bool "Preemptible Kernel (Low-Latency Desktop)" - select PREEMPT_COUNT + select PREEMPT help This option reduces the latency of the kernel by making all kernel code (that is not executing in a critical section) @@ -51,6 +58,21 @@ config PREEMPT embedded system with latency requirements in the milliseconds range. +config PREEMPT_RTB + bool "Preemptible Kernel (Basic RT)" + select PREEMPT_RT_BASE + help + This option is basically the same as (Low-Latency Desktop) but + enables changes which are preliminary for the full preemptiple + RT kernel. + +config PREEMPT_RT_FULL + bool "Fully Preemptible Kernel (RT)" + depends on IRQ_FORCED_THREADING + select PREEMPT_RT_BASE + help + All and everything + endchoice config PREEMPT_COUNT diff --git a/kernel/Makefile b/kernel/Makefile index e898c5b9d02c..ae86e48cdaff 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -7,10 +7,10 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o \ rcupdate.o extable.o params.o posix-timers.o \ - kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ - hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ + kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o \ + hrtimer.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o sched_clock.o cred.o \ - async.o range.o + async.o range.o wait-simple.o obj-y += groups.o ifdef CONFIG_FUNCTION_TRACER @@ -29,7 +29,11 @@ obj-$(CONFIG_PROFILING) += profile.o obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ +ifneq ($(CONFIG_PREEMPT_RT_FULL),y) +obj-y += mutex.o obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o +obj-y += rwsem.o +endif obj-$(CONFIG_LOCKDEP) += lockdep.o ifeq ($(CONFIG_PROC_FS),y) obj-$(CONFIG_LOCKDEP) += lockdep_proc.o @@ -41,6 +45,7 @@ endif obj-$(CONFIG_RT_MUTEXES) += rtmutex.o obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o +obj-$(CONFIG_PREEMPT_RT_FULL) += rt.o obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += smp.o ifneq ($(CONFIG_SMP),y) diff --git a/kernel/cpu.c b/kernel/cpu.c index 563f13609470..fa4083478d75 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -58,6 +58,104 @@ static struct { .refcount = 0, }; +struct hotplug_pcp { + struct task_struct *unplug; + int refcount; + struct completion synced; +}; + +static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp); + +/** + * pin_current_cpu - Prevent the current cpu from being unplugged + * + * Lightweight version of get_online_cpus() to prevent cpu from being + * unplugged when code runs in a migration disabled region. + * + * Must be called with preemption disabled (preempt_count = 1)! + */ +void pin_current_cpu(void) +{ + struct hotplug_pcp *hp; + +retry: + hp = &__get_cpu_var(hotplug_pcp); + + if (!hp->unplug || hp->refcount || preempt_count() > 1 || + hp->unplug == current || (current->flags & PF_STOMPER)) { + hp->refcount++; + return; + } + preempt_enable(); + mutex_lock(&cpu_hotplug.lock); + mutex_unlock(&cpu_hotplug.lock); + preempt_disable(); + goto retry; +} + +/** + * unpin_current_cpu - Allow unplug of current cpu + * + * Must be called with preemption or interrupts disabled! + */ +void unpin_current_cpu(void) +{ + struct hotplug_pcp *hp = &__get_cpu_var(hotplug_pcp); + + WARN_ON(hp->refcount <= 0); + + /* This is safe. sync_unplug_thread is pinned to this cpu */ + if (!--hp->refcount && hp->unplug && hp->unplug != current && + !(current->flags & PF_STOMPER)) + wake_up_process(hp->unplug); +} + +/* + * FIXME: Is this really correct under all circumstances ? + */ +static int sync_unplug_thread(void *data) +{ + struct hotplug_pcp *hp = data; + + preempt_disable(); + hp->unplug = current; + set_current_state(TASK_UNINTERRUPTIBLE); + while (hp->refcount) { + schedule_preempt_disabled(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + set_current_state(TASK_RUNNING); + preempt_enable(); + complete(&hp->synced); + return 0; +} + +/* + * Start the sync_unplug_thread on the target cpu and wait for it to + * complete. + */ +static int cpu_unplug_begin(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + struct task_struct *tsk; + + init_completion(&hp->synced); + tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); + if (IS_ERR(tsk)) + return (PTR_ERR(tsk)); + kthread_bind(tsk, cpu); + wake_up_process(tsk); + wait_for_completion(&hp->synced); + return 0; +} + +static void cpu_unplug_done(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + hp->unplug = NULL; +} + void get_online_cpus(void) { might_sleep(); @@ -211,13 +309,14 @@ static int __ref take_cpu_down(void *_param) /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) { - int err, nr_calls = 0; + int mycpu, err, nr_calls = 0; void *hcpu = (void *)(long)cpu; unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; struct take_cpu_down_param tcd_param = { .mod = mod, .hcpu = hcpu, }; + cpumask_var_t cpumask; if (num_online_cpus() == 1) return -EBUSY; @@ -225,7 +324,26 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) if (!cpu_online(cpu)) return -EINVAL; + /* Move the downtaker off the unplug cpu */ + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) + return -ENOMEM; + cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu)); + set_cpus_allowed_ptr(current, cpumask); + free_cpumask_var(cpumask); + migrate_disable(); + mycpu = smp_processor_id(); + if (mycpu == cpu) { + printk(KERN_ERR "Yuck! Still on unplug CPU\n!"); + migrate_enable(); + return -EBUSY; + } + cpu_hotplug_begin(); + err = cpu_unplug_begin(cpu); + if (err) { + printk("cpu_unplug_begin(%d) failed\n", cpu); + goto out_cancel; + } err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); if (err) { @@ -264,6 +382,9 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) check_for_tasks(cpu); out_release: + cpu_unplug_done(cpu); +out_cancel: + migrate_enable(); cpu_hotplug_done(); if (!err) cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); diff --git a/kernel/cred.c b/kernel/cred.c index 5791612a4045..944761380c37 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -35,7 +35,7 @@ static struct kmem_cache *cred_jar; static struct thread_group_cred init_tgcred = { .usage = ATOMIC_INIT(2), .tgid = 0, - .lock = __SPIN_LOCK_UNLOCKED(init_cred.tgcred.lock), + .lock = __SPIN_LOCK_UNLOCKED(init_tgcred.lock), }; #endif diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 4802eb5840e1..5b7455fada1e 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -553,7 +553,6 @@ int vkdb_printf(const char *fmt, va_list ap) int diag; int linecount; int logging, saved_loglevel = 0; - int saved_trap_printk; int got_printf_lock = 0; int retlen = 0; int fnd, len; @@ -564,8 +563,6 @@ int vkdb_printf(const char *fmt, va_list ap) unsigned long uninitialized_var(flags); preempt_disable(); - saved_trap_printk = kdb_trap_printk; - kdb_trap_printk = 0; /* Serialize kdb_printf if multiple cpus try to write at once. * But if any cpu goes recursive in kdb, just print the output, @@ -821,7 +818,6 @@ kdb_print_out: } else { __release(kdb_printf_lock); } - kdb_trap_printk = saved_trap_printk; preempt_enable(); return retlen; } @@ -831,9 +827,11 @@ int kdb_printf(const char *fmt, ...) va_list ap; int r; + kdb_trap_printk++; va_start(ap, fmt); r = vkdb_printf(fmt, ap); va_end(ap); + kdb_trap_printk--; return r; } diff --git a/kernel/exit.c b/kernel/exit.c index e6e01b959a0e..90757807b27b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -141,7 +141,7 @@ static void __exit_signal(struct task_struct *tsk) * Do this under ->siglock, we can race with another thread * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. */ - flush_sigqueue(&tsk->pending); + flush_task_sigqueue(tsk); tsk->sighand = NULL; spin_unlock(&sighand->siglock); diff --git a/kernel/fork.c b/kernel/fork.c index da4a6a10d088..d713d9682101 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -86,7 +86,7 @@ int max_threads; /* tunable limit on nr_threads */ DEFINE_PER_CPU(unsigned long, process_counts) = 0; -__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ +DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) @@ -196,7 +196,18 @@ void __put_task_struct(struct task_struct *tsk) if (!profile_handoff_task(tsk)) free_task(tsk); } +#ifndef CONFIG_PREEMPT_RT_BASE EXPORT_SYMBOL_GPL(__put_task_struct); +#else +void __put_task_struct_cb(struct rcu_head *rhp) +{ + struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu); + + __put_task_struct(tsk); + +} +EXPORT_SYMBOL_GPL(__put_task_struct_cb); +#endif /* * macro override instead of weak attribute alias, to workaround @@ -541,6 +552,19 @@ void __mmdrop(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(__mmdrop); +#ifdef CONFIG_PREEMPT_RT_BASE +/* + * RCU callback for delayed mm drop. Not strictly rcu, but we don't + * want another facility to make this work. + */ +void __mmdrop_delayed(struct rcu_head *rhp) +{ + struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); + + __mmdrop(mm); +} +#endif + /* * Decrement the use count and release all resources for an mm. */ @@ -1023,6 +1047,9 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p) */ static void posix_cpu_timers_init(struct task_struct *tsk) { +#ifdef CONFIG_PREEMPT_RT_BASE + tsk->posix_timer_list = NULL; +#endif tsk->cputime_expires.prof_exp = cputime_zero; tsk->cputime_expires.virt_exp = cputime_zero; tsk->cputime_expires.sched_exp = 0; @@ -1131,6 +1158,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); + p->sigqueue_cache = NULL; p->utime = cputime_zero; p->stime = cputime_zero; @@ -1192,6 +1220,9 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->hardirq_context = 0; p->softirq_context = 0; #endif +#ifdef CONFIG_PREEMPT_RT_FULL + p->pagefault_disabled = 0; +#endif #ifdef CONFIG_LOCKDEP p->lockdep_depth = 0; /* no locks held yet */ p->curr_chain_key = 0; diff --git a/kernel/futex.c b/kernel/futex.c index 1614be20173d..2d311cdad5a6 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1422,6 +1422,16 @@ retry_private: requeue_pi_wake_futex(this, &key2, hb2); drop_count++; continue; + } else if (ret == -EAGAIN) { + /* + * Waiter was woken by timeout or + * signal and has set pi_blocked_on to + * PI_WAKEUP_INPROGRESS before we + * tried to enqueue it on the rtmutex. + */ + this->pi_state = NULL; + free_pi_state(pi_state); + continue; } else if (ret) { /* -EDEADLK */ this->pi_state = NULL; @@ -2266,7 +2276,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, struct hrtimer_sleeper timeout, *to = NULL; struct rt_mutex_waiter rt_waiter; struct rt_mutex *pi_mutex = NULL; - struct futex_hash_bucket *hb; + struct futex_hash_bucket *hb, *hb2; union futex_key key2 = FUTEX_KEY_INIT; struct futex_q q = futex_q_init; int res, ret; @@ -2288,8 +2298,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * The waiter is allocated on our stack, manipulated by the requeue * code while we sleep on uaddr. */ - debug_rt_mutex_init_waiter(&rt_waiter); - rt_waiter.task = NULL; + rt_mutex_init_waiter(&rt_waiter, false); ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); if (unlikely(ret != 0)) @@ -2310,20 +2319,55 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, /* Queue the futex_q, drop the hb lock, wait for wakeup. */ futex_wait_queue_me(hb, &q, to); - spin_lock(&hb->lock); - ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); - spin_unlock(&hb->lock); - if (ret) - goto out_put_keys; + /* + * On RT we must avoid races with requeue and trying to block + * on two mutexes (hb->lock and uaddr2's rtmutex) by + * serializing access to pi_blocked_on with pi_lock. + */ + raw_spin_lock_irq(¤t->pi_lock); + if (current->pi_blocked_on) { + /* + * We have been requeued or are in the process of + * being requeued. + */ + raw_spin_unlock_irq(¤t->pi_lock); + } else { + /* + * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS + * prevents a concurrent requeue from moving us to the + * uaddr2 rtmutex. After that we can safely acquire + * (and possibly block on) hb->lock. + */ + current->pi_blocked_on = PI_WAKEUP_INPROGRESS; + raw_spin_unlock_irq(¤t->pi_lock); + + spin_lock(&hb->lock); + + /* + * Clean up pi_blocked_on. We might leak it otherwise + * when we succeeded with the hb->lock in the fast + * path. + */ + raw_spin_lock_irq(¤t->pi_lock); + current->pi_blocked_on = NULL; + raw_spin_unlock_irq(¤t->pi_lock); + + ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); + spin_unlock(&hb->lock); + if (ret) + goto out_put_keys; + } /* - * In order for us to be here, we know our q.key == key2, and since - * we took the hb->lock above, we also know that futex_requeue() has - * completed and we no longer have to concern ourselves with a wakeup - * race with the atomic proxy lock acquisition by the requeue code. The - * futex_requeue dropped our key1 reference and incremented our key2 - * reference count. + * In order to be here, we have either been requeued, are in + * the process of being requeued, or requeue successfully + * acquired uaddr2 on our behalf. If pi_blocked_on was + * non-null above, we may be racing with a requeue. Do not + * rely on q->lock_ptr to be hb2->lock until after blocking on + * hb->lock or hb2->lock. The futex_requeue dropped our key1 + * reference and incremented our key2 reference count. */ + hb2 = hash_futex(&key2); /* Check if the requeue code acquired the second futex for us. */ if (!q.rt_waiter) { @@ -2332,9 +2376,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * did a lock-steal - fix up the PI-state in that case. */ if (q.pi_state && (q.pi_state->owner != current)) { - spin_lock(q.lock_ptr); + spin_lock(&hb2->lock); + BUG_ON(&hb2->lock != q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); - spin_unlock(q.lock_ptr); + spin_unlock(&hb2->lock); } } else { /* @@ -2347,7 +2392,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1); debug_rt_mutex_free_waiter(&rt_waiter); - spin_lock(q.lock_ptr); + spin_lock(&hb2->lock); + BUG_ON(&hb2->lock != q.lock_ptr); /* * Fixup the pi_state owner and possibly acquire the lock if we * haven't already. diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index ae34bf51682b..3991464c3066 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -49,6 +49,7 @@ #include <asm/uaccess.h> #include <trace/events/timer.h> +#include <trace/events/hist.h> /* * The timer bases: @@ -588,8 +589,7 @@ static int hrtimer_reprogram(struct hrtimer *timer, * When the callback is running, we do not reprogram the clock event * device. The timer callback is either running on a different CPU or * the callback is executed in the hrtimer_interrupt context. The - * reprogramming is handled either by the softirq, which called the - * callback or at the end of the hrtimer_interrupt. + * reprogramming is handled at the end of the hrtimer_interrupt. */ if (hrtimer_callback_running(timer)) return 0; @@ -624,6 +624,9 @@ static int hrtimer_reprogram(struct hrtimer *timer, return res; } +static void __run_hrtimer(struct hrtimer *timer, ktime_t *now); +static int hrtimer_rt_defer(struct hrtimer *timer); + /* * Initialize the high resolution related parts of cpu_base */ @@ -644,14 +647,23 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, int wakeup) { if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) { - if (wakeup) { - raw_spin_unlock(&base->cpu_base->lock); - raise_softirq_irqoff(HRTIMER_SOFTIRQ); - raw_spin_lock(&base->cpu_base->lock); - } else - __raise_softirq_irqoff(HRTIMER_SOFTIRQ); + if (!wakeup) + return -ETIME; - return 1; +#ifdef CONFIG_PREEMPT_RT_BASE + /* + * Move softirq based timers away from the rbtree in + * case it expired already. Otherwise we would have a + * stale base->first entry until the softirq runs. + */ + if (!hrtimer_rt_defer(timer)) + return -ETIME; +#endif + raw_spin_unlock(&base->cpu_base->lock); + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + raw_spin_lock(&base->cpu_base->lock); + + return 0; } return 0; @@ -732,6 +744,11 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, } static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { } static inline void retrigger_next_event(void *arg) { } +static inline int hrtimer_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base) +{ + return 0; +} #endif /* CONFIG_HIGH_RES_TIMERS */ @@ -846,6 +863,32 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) } EXPORT_SYMBOL_GPL(hrtimer_forward); +#ifdef CONFIG_PREEMPT_RT_BASE +# define wake_up_timer_waiters(b) wake_up(&(b)->wait) + +/** + * hrtimer_wait_for_timer - Wait for a running timer + * + * @timer: timer to wait for + * + * The function waits in case the timers callback function is + * currently executed on the waitqueue of the timer base. The + * waitqueue is woken up after the timer callback function has + * finished execution. + */ +void hrtimer_wait_for_timer(const struct hrtimer *timer) +{ + struct hrtimer_clock_base *base = timer->base; + + if (base && base->cpu_base && !timer->irqsafe) + wait_event(base->cpu_base->wait, + !(timer->state & HRTIMER_STATE_CALLBACK)); +} + +#else +# define wake_up_timer_waiters(b) do { } while (0) +#endif + /* * enqueue_hrtimer - internal function to (re)start a timer * @@ -889,6 +932,11 @@ static void __remove_hrtimer(struct hrtimer *timer, if (!(timer->state & HRTIMER_STATE_ENQUEUED)) goto out; + if (unlikely(!list_empty(&timer->cb_entry))) { + list_del_init(&timer->cb_entry); + goto out; + } + next_timer = timerqueue_getnext(&base->active); timerqueue_del(&base->active, &timer->node); if (&timer->node == next_timer) { @@ -985,8 +1033,20 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, * * XXX send_remote_softirq() ? */ - if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)) - hrtimer_enqueue_reprogram(timer, new_base, wakeup); + if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)) { + ret = hrtimer_enqueue_reprogram(timer, new_base, wakeup); + if (ret) { + /* + * In case we failed to reprogram the timer (mostly + * because out current timer is already elapsed), + * remove it again and report a failure. This avoids + * stale base->first entries. + */ + debug_deactivate(timer); + __remove_hrtimer(timer, new_base, + timer->state & HRTIMER_STATE_CALLBACK, 0); + } + } unlock_hrtimer_base(timer, &flags); @@ -1072,7 +1132,7 @@ int hrtimer_cancel(struct hrtimer *timer) if (ret >= 0) return ret; - cpu_relax(); + hrtimer_wait_for_timer(timer); } } EXPORT_SYMBOL_GPL(hrtimer_cancel); @@ -1151,6 +1211,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, base = hrtimer_clockid_to_base(clock_id); timer->base = &cpu_base->clock_base[base]; + INIT_LIST_HEAD(&timer->cb_entry); timerqueue_init(&timer->node); #ifdef CONFIG_TIMER_STATS @@ -1234,6 +1295,122 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now) timer->state &= ~HRTIMER_STATE_CALLBACK; } +static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer); + +#ifdef CONFIG_PREEMPT_RT_BASE +static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer, + struct hrtimer_clock_base *base) +{ + /* + * Note, we clear the callback flag before we requeue the + * timer otherwise we trigger the callback_running() check + * in hrtimer_reprogram(). + */ + timer->state &= ~HRTIMER_STATE_CALLBACK; + + if (restart != HRTIMER_NORESTART) { + BUG_ON(hrtimer_active(timer)); + /* + * Enqueue the timer, if it's the leftmost timer then + * we need to reprogram it. + */ + if (!enqueue_hrtimer(timer, base)) + return; + +#ifndef CONFIG_HIGH_RES_TIMERS + } +#else + if (base->cpu_base->hres_active && + hrtimer_reprogram(timer, base)) + goto requeue; + + } else if (hrtimer_active(timer)) { + /* + * If the timer was rearmed on another CPU, reprogram + * the event device. + */ + if (&timer->node == base->active.next && + base->cpu_base->hres_active && + hrtimer_reprogram(timer, base)) + goto requeue; + } + return; + +requeue: + /* + * Timer is expired. Thus move it from tree to pending list + * again. + */ + __remove_hrtimer(timer, base, timer->state, 0); + list_add_tail(&timer->cb_entry, &base->expired); +#endif +} + +/* + * The changes in mainline which removed the callback modes from + * hrtimer are not yet working with -rt. The non wakeup_process() + * based callbacks which involve sleeping locks need to be treated + * seperately. + */ +static void hrtimer_rt_run_pending(void) +{ + enum hrtimer_restart (*fn)(struct hrtimer *); + struct hrtimer_cpu_base *cpu_base; + struct hrtimer_clock_base *base; + struct hrtimer *timer; + int index, restart; + + local_irq_disable(); + cpu_base = &per_cpu(hrtimer_bases, smp_processor_id()); + + raw_spin_lock(&cpu_base->lock); + + for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) { + base = &cpu_base->clock_base[index]; + + while (!list_empty(&base->expired)) { + timer = list_first_entry(&base->expired, + struct hrtimer, cb_entry); + + /* + * Same as the above __run_hrtimer function + * just we run with interrupts enabled. + */ + debug_hrtimer_deactivate(timer); + __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0); + timer_stats_account_hrtimer(timer); + fn = timer->function; + + raw_spin_unlock_irq(&cpu_base->lock); + restart = fn(timer); + raw_spin_lock_irq(&cpu_base->lock); + + hrtimer_rt_reprogram(restart, timer, base); + } + } + + raw_spin_unlock_irq(&cpu_base->lock); + + wake_up_timer_waiters(cpu_base); +} + +static int hrtimer_rt_defer(struct hrtimer *timer) +{ + if (timer->irqsafe) + return 0; + + __remove_hrtimer(timer, timer->base, timer->state, 0); + list_add_tail(&timer->cb_entry, &timer->base->expired); + return 1; +} + +#else + +static inline void hrtimer_rt_run_pending(void) { } +static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; } + +#endif + #ifdef CONFIG_HIGH_RES_TIMERS /* @@ -1244,7 +1421,7 @@ void hrtimer_interrupt(struct clock_event_device *dev) { struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); ktime_t expires_next, now, entry_time, delta; - int i, retries = 0; + int i, retries = 0, raise = 0; BUG_ON(!cpu_base->hres_active); cpu_base->nr_events++; @@ -1280,6 +1457,14 @@ retry: timer = container_of(node, struct hrtimer, node); + trace_hrtimer_interrupt(raw_smp_processor_id(), + ktime_to_ns(ktime_sub( + hrtimer_get_expires(timer), basenow)), + current, + timer->function == hrtimer_wakeup ? + container_of(timer, struct hrtimer_sleeper, + timer)->task : NULL); + /* * The immediate goal for using the softexpires is * minimizing wakeups, not running timers at the @@ -1303,7 +1488,10 @@ retry: break; } - __run_hrtimer(timer, &basenow); + if (!hrtimer_rt_defer(timer)) + __run_hrtimer(timer, &basenow); + else + raise = 1; } } @@ -1318,6 +1506,10 @@ retry: if (expires_next.tv64 == KTIME_MAX || !tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; + + if (raise) + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + return; } @@ -1393,17 +1585,17 @@ void hrtimer_peek_ahead_timers(void) local_irq_restore(flags); } -static void run_hrtimer_softirq(struct softirq_action *h) -{ - hrtimer_peek_ahead_timers(); -} - #else /* CONFIG_HIGH_RES_TIMERS */ static inline void __hrtimer_peek_ahead_timers(void) { } #endif /* !CONFIG_HIGH_RES_TIMERS */ +static void run_hrtimer_softirq(struct softirq_action *h) +{ + hrtimer_rt_run_pending(); +} + /* * Called from timer softirq every jiffy, expire hrtimers: * @@ -1436,7 +1628,7 @@ void hrtimer_run_queues(void) struct timerqueue_node *node; struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); struct hrtimer_clock_base *base; - int index, gettime = 1; + int index, gettime = 1, raise = 0; if (hrtimer_hres_active()) return; @@ -1461,10 +1653,16 @@ void hrtimer_run_queues(void) hrtimer_get_expires_tv64(timer)) break; - __run_hrtimer(timer, &base->softirq_time); + if (!hrtimer_rt_defer(timer)) + __run_hrtimer(timer, &base->softirq_time); + else + raise = 1; } raw_spin_unlock(&cpu_base->lock); } + + if (raise) + raise_softirq_irqoff(HRTIMER_SOFTIRQ); } /* @@ -1486,6 +1684,7 @@ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) { sl->timer.function = hrtimer_wakeup; + sl->timer.irqsafe = 1; sl->task = task; } EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); @@ -1624,9 +1823,13 @@ static void __cpuinit init_hrtimers_cpu(int cpu) for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { cpu_base->clock_base[i].cpu_base = cpu_base; timerqueue_init_head(&cpu_base->clock_base[i].active); + INIT_LIST_HEAD(&cpu_base->clock_base[i].expired); } hrtimer_init_hres(cpu_base); +#ifdef CONFIG_PREEMPT_RT_BASE + init_waitqueue_head(&cpu_base->wait); +#endif } #ifdef CONFIG_HOTPLUG_CPU @@ -1739,9 +1942,7 @@ void __init hrtimers_init(void) hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, (void *)(long)smp_processor_id()); register_cpu_notifier(&hrtimers_nb); -#ifdef CONFIG_HIGH_RES_TIMERS open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq); -#endif } /** diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 470d08c82bbe..634620c1b291 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -156,8 +156,11 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) action = action->next; } while (action); +#ifndef CONFIG_PREEMPT_RT_FULL + /* FIXME: Can we unbreak that ? */ if (random & IRQF_SAMPLE_RANDOM) add_interrupt_randomness(irq); +#endif if (!noirqdebug) note_interrupt(irq, desc, retval); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 1da999f5e746..a39b40c53606 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -18,6 +18,7 @@ #include "internals.h" #ifdef CONFIG_IRQ_FORCED_THREADING +# ifndef CONFIG_PREEMPT_RT_BASE __read_mostly bool force_irqthreads; static int __init setup_forced_irqthreads(char *arg) @@ -26,6 +27,7 @@ static int __init setup_forced_irqthreads(char *arg) return 0; } early_param("threadirqs", setup_forced_irqthreads); +# endif #endif /** diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index dc813a948be2..d09e0f51d182 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -341,6 +341,11 @@ MODULE_PARM_DESC(noirqdebug, "Disable irq lockup detection when true"); static int __init irqfixup_setup(char *str) { +#ifdef CONFIG_PREEMPT_RT_BASE + printk(KERN_WARNING "irqfixup boot option not supported " + "w/ CONFIG_PREEMPT_RT\n"); + return 1; +#endif irqfixup = 1; printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); printk(KERN_WARNING "This may impact system performance.\n"); @@ -353,6 +358,11 @@ module_param(irqfixup, int, 0644); static int __init irqpoll_setup(char *str) { +#ifdef CONFIG_PREEMPT_RT_BASE + printk(KERN_WARNING "irqpoll boot option not supported " + "w/ CONFIG_PREEMPT_RT\n"); + return 1; +#endif irqfixup = 2; printk(KERN_WARNING "Misrouted IRQ fixup and polling support " "enabled\n"); diff --git a/kernel/irq_work.c b/kernel/irq_work.c index c3c46c72046e..727ba59e38f9 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -105,8 +105,10 @@ void irq_work_run(void) if (llist_empty(this_list)) return; +#ifndef CONFIG_PREEMPT_RT_FULL BUG_ON(!in_irq()); BUG_ON(!irqs_disabled()); +#endif llnode = llist_del_all(this_list); while (llnode != NULL) { diff --git a/kernel/itimer.c b/kernel/itimer.c index d802883153da..2c582fc41579 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -214,6 +214,7 @@ again: /* We are sharing ->siglock with it_real_fn() */ if (hrtimer_try_to_cancel(timer) < 0) { spin_unlock_irq(&tsk->sighand->siglock); + hrtimer_wait_for_timer(&tsk->signal->real_timer); goto again; } expires = timeval_to_ktime(value->it_value); diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 4e316e1acf58..a546d3303a2c 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -133,6 +133,15 @@ KERNEL_ATTR_RO(vmcoreinfo); #endif /* CONFIG_KEXEC */ +#if defined(CONFIG_PREEMPT_RT_FULL) +static ssize_t realtime_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", 1); +} +KERNEL_ATTR_RO(realtime); +#endif + /* whether file capabilities are enabled */ static ssize_t fscaps_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -182,6 +191,9 @@ static struct attribute * kernel_attrs[] = { &kexec_crash_size_attr.attr, &vmcoreinfo_attr.attr, #endif +#ifdef CONFIG_PREEMPT_RT_FULL + &realtime_attr.attr, +#endif NULL }; diff --git a/kernel/lockdep.c b/kernel/lockdep.c index b2e08c932d91..334d3c037b34 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -3494,6 +3494,7 @@ static void check_flags(unsigned long flags) } } +#ifndef CONFIG_PREEMPT_RT_FULL /* * We dont accurately track softirq state in e.g. * hardirq contexts (such as on 4KSTACKS), so only @@ -3508,6 +3509,7 @@ static void check_flags(unsigned long flags) DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); } } +#endif if (!debug_locks) print_irqtrace_events(current); diff --git a/kernel/mutex.c b/kernel/mutex.c index 89096dd8786f..a307cc9c9526 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -240,9 +240,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, /* didn't get the lock, go to sleep: */ spin_unlock_mutex(&lock->wait_lock, flags); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); spin_lock_mutex(&lock->wait_lock, flags); } diff --git a/kernel/panic.c b/kernel/panic.c index b26593604214..d102b5703164 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -334,9 +334,11 @@ static u64 oops_id; static int init_oops_id(void) { +#ifndef CONFIG_PREEMPT_RT_FULL if (!oops_id) get_random_bytes(&oops_id, sizeof(oops_id)); else +#endif oops_id++; return 0; diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index e7cb76dc18f5..1d4c6096395a 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -701,7 +701,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, /* * Disarm any old timer after extracting its expiry time. */ - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); ret = 0; old_incr = timer->it.cpu.incr; @@ -1223,7 +1223,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) /* * Now re-arm for the new expiry time. */ - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); arm_timer(timer); spin_unlock(&p->sighand->siglock); @@ -1290,10 +1290,11 @@ static inline int fastpath_timer_check(struct task_struct *tsk) sig = tsk->signal; if (sig->cputimer.running) { struct task_cputime group_sample; + unsigned long flags; - raw_spin_lock(&sig->cputimer.lock); + raw_spin_lock_irqsave(&sig->cputimer.lock, flags); group_sample = sig->cputimer.cputime; - raw_spin_unlock(&sig->cputimer.lock); + raw_spin_unlock_irqrestore(&sig->cputimer.lock, flags); if (task_cputime_expired(&group_sample, &sig->cputime_expires)) return 1; @@ -1307,13 +1308,13 @@ static inline int fastpath_timer_check(struct task_struct *tsk) * already updated our counts. We need to check if any timers fire now. * Interrupts are disabled. */ -void run_posix_cpu_timers(struct task_struct *tsk) +static void __run_posix_cpu_timers(struct task_struct *tsk) { LIST_HEAD(firing); struct k_itimer *timer, *next; unsigned long flags; - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); /* * The fast path checks that there are no expired thread or thread @@ -1371,6 +1372,190 @@ void run_posix_cpu_timers(struct task_struct *tsk) } } +#ifdef CONFIG_PREEMPT_RT_BASE +#include <linux/kthread.h> +#include <linux/cpu.h> +DEFINE_PER_CPU(struct task_struct *, posix_timer_task); +DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist); + +static int posix_cpu_timers_thread(void *data) +{ + int cpu = (long)data; + + BUG_ON(per_cpu(posix_timer_task,cpu) != current); + + while (!kthread_should_stop()) { + struct task_struct *tsk = NULL; + struct task_struct *next = NULL; + + if (cpu_is_offline(cpu)) + goto wait_to_die; + + /* grab task list */ + raw_local_irq_disable(); + tsk = per_cpu(posix_timer_tasklist, cpu); + per_cpu(posix_timer_tasklist, cpu) = NULL; + raw_local_irq_enable(); + + /* its possible the list is empty, just return */ + if (!tsk) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + __set_current_state(TASK_RUNNING); + continue; + } + + /* Process task list */ + while (1) { + /* save next */ + next = tsk->posix_timer_list; + + /* run the task timers, clear its ptr and + * unreference it + */ + __run_posix_cpu_timers(tsk); + tsk->posix_timer_list = NULL; + put_task_struct(tsk); + + /* check if this is the last on the list */ + if (next == tsk) + break; + tsk = next; + } + } + return 0; + +wait_to_die: + /* Wait for kthread_stop */ + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +static inline int __fastpath_timer_check(struct task_struct *tsk) +{ + /* tsk == current, ensure it is safe to use ->signal/sighand */ + if (unlikely(tsk->exit_state)) + return 0; + + if (!task_cputime_zero(&tsk->cputime_expires)) + return 1; + + if (!task_cputime_zero(&tsk->signal->cputime_expires)) + return 1; + + return 0; +} + +void run_posix_cpu_timers(struct task_struct *tsk) +{ + unsigned long cpu = smp_processor_id(); + struct task_struct *tasklist; + + BUG_ON(!irqs_disabled()); + if(!per_cpu(posix_timer_task, cpu)) + return; + /* get per-cpu references */ + tasklist = per_cpu(posix_timer_tasklist, cpu); + + /* check to see if we're already queued */ + if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) { + get_task_struct(tsk); + if (tasklist) { + tsk->posix_timer_list = tasklist; + } else { + /* + * The list is terminated by a self-pointing + * task_struct + */ + tsk->posix_timer_list = tsk; + } + per_cpu(posix_timer_tasklist, cpu) = tsk; + + wake_up_process(per_cpu(posix_timer_task, cpu)); + } +} + +/* + * posix_cpu_thread_call - callback that gets triggered when a CPU is added. + * Here we can start up the necessary migration thread for the new CPU. + */ +static int posix_cpu_thread_call(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + struct task_struct *p; + struct sched_param param; + + switch (action) { + case CPU_UP_PREPARE: + p = kthread_create(posix_cpu_timers_thread, hcpu, + "posixcputmr/%d",cpu); + if (IS_ERR(p)) + return NOTIFY_BAD; + p->flags |= PF_NOFREEZE; + kthread_bind(p, cpu); + /* Must be high prio to avoid getting starved */ + param.sched_priority = MAX_RT_PRIO-1; + sched_setscheduler(p, SCHED_FIFO, ¶m); + per_cpu(posix_timer_task,cpu) = p; + break; + case CPU_ONLINE: + /* Strictly unneccessary, as first user will wake it. */ + wake_up_process(per_cpu(posix_timer_task,cpu)); + break; +#ifdef CONFIG_HOTPLUG_CPU + case CPU_UP_CANCELED: + /* Unbind it from offline cpu so it can run. Fall thru. */ + kthread_bind(per_cpu(posix_timer_task,cpu), + any_online_cpu(cpu_online_map)); + kthread_stop(per_cpu(posix_timer_task,cpu)); + per_cpu(posix_timer_task,cpu) = NULL; + break; + case CPU_DEAD: + kthread_stop(per_cpu(posix_timer_task,cpu)); + per_cpu(posix_timer_task,cpu) = NULL; + break; +#endif + } + return NOTIFY_OK; +} + +/* Register at highest priority so that task migration (migrate_all_tasks) + * happens before everything else. + */ +static struct notifier_block __devinitdata posix_cpu_thread_notifier = { + .notifier_call = posix_cpu_thread_call, + .priority = 10 +}; + +static int __init posix_cpu_thread_init(void) +{ + void *hcpu = (void *)(long)smp_processor_id(); + /* Start one for boot CPU. */ + unsigned long cpu; + + /* init the per-cpu posix_timer_tasklets */ + for_each_cpu_mask(cpu, cpu_possible_map) + per_cpu(posix_timer_tasklist, cpu) = NULL; + + posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, hcpu); + posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, hcpu); + register_cpu_notifier(&posix_cpu_thread_notifier); + return 0; +} +early_initcall(posix_cpu_thread_init); +#else /* CONFIG_PREEMPT_RT_BASE */ +void run_posix_cpu_timers(struct task_struct *tsk) +{ + __run_posix_cpu_timers(tsk); +} +#endif /* CONFIG_PREEMPT_RT_BASE */ + /* * Set one of the process-wide special case CPU timers or RLIMIT_CPU. * The tsk->sighand->siglock must be held by the caller. diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 69185ae6b701..6a74800a6f66 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -439,6 +439,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) static struct pid *good_sigevent(sigevent_t * event) { struct task_struct *rtn = current->group_leader; + int sig = event->sigev_signo; if ((event->sigev_notify & SIGEV_THREAD_ID ) && (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) || @@ -447,7 +448,8 @@ static struct pid *good_sigevent(sigevent_t * event) return NULL; if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) && - ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX))) + (sig <= 0 || sig > SIGRTMAX || sig_kernel_only(sig) || + sig_kernel_coredump(sig))) return NULL; return task_pid(rtn); @@ -764,6 +766,20 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) return overrun; } +/* + * Protected by RCU! + */ +static void timer_wait_for_callback(struct k_clock *kc, struct k_itimer *timr) +{ +#ifdef CONFIG_PREEMPT_RT_FULL + if (kc->timer_set == common_timer_set) + hrtimer_wait_for_timer(&timr->it.real.timer); + else + /* FIXME: Whacky hack for posix-cpu-timers */ + schedule_timeout(1); +#endif +} + /* Set a POSIX.1b interval timer. */ /* timr->it_lock is taken. */ static int @@ -841,6 +857,7 @@ retry: if (!timr) return -EINVAL; + rcu_read_lock(); kc = clockid_to_kclock(timr->it_clock); if (WARN_ON_ONCE(!kc || !kc->timer_set)) error = -EINVAL; @@ -849,9 +866,12 @@ retry: unlock_timer(timr, flag); if (error == TIMER_RETRY) { + timer_wait_for_callback(kc, timr); rtn = NULL; // We already got the old time... + rcu_read_unlock(); goto retry; } + rcu_read_unlock(); if (old_setting && !error && copy_to_user(old_setting, &old_spec, sizeof (old_spec))) @@ -889,10 +909,15 @@ retry_delete: if (!timer) return -EINVAL; + rcu_read_lock(); if (timer_delete_hook(timer) == TIMER_RETRY) { unlock_timer(timer, flags); + timer_wait_for_callback(clockid_to_kclock(timer->it_clock), + timer); + rcu_read_unlock(); goto retry_delete; } + rcu_read_unlock(); spin_lock(¤t->sighand->siglock); list_del(&timer->list); @@ -918,8 +943,18 @@ static void itimer_delete(struct k_itimer *timer) retry_delete: spin_lock_irqsave(&timer->it_lock, flags); + /* On RT we can race with a deletion */ + if (!timer->it_signal) { + unlock_timer(timer, flags); + return; + } + if (timer_delete_hook(timer) == TIMER_RETRY) { + rcu_read_lock(); unlock_timer(timer, flags); + timer_wait_for_callback(clockid_to_kclock(timer->it_clock), + timer); + rcu_read_unlock(); goto retry_delete; } list_del(&timer->list); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index a6b0503574ee..5c6ce10b305b 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -284,6 +284,8 @@ static int create_image(int platform_mode) local_irq_disable(); + system_state = SYSTEM_SUSPEND; + error = syscore_suspend(); if (error) { printk(KERN_ERR "PM: Some system devices failed to power down, " @@ -311,6 +313,7 @@ static int create_image(int platform_mode) syscore_resume(); Enable_irqs: + system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: @@ -437,6 +440,7 @@ static int resume_target_kernel(bool platform_mode) goto Enable_cpus; local_irq_disable(); + system_state = SYSTEM_SUSPEND; error = syscore_suspend(); if (error) @@ -470,6 +474,7 @@ static int resume_target_kernel(bool platform_mode) syscore_resume(); Enable_irqs: + system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: @@ -549,6 +554,7 @@ int hibernation_platform_enter(void) goto Platform_finish; local_irq_disable(); + system_state = SYSTEM_SUSPEND; syscore_suspend(); if (pm_wakeup_pending()) { error = -EAGAIN; @@ -561,6 +567,7 @@ int hibernation_platform_enter(void) Power_up: syscore_resume(); + system_state = SYSTEM_RUNNING; local_irq_enable(); enable_nonboot_cpus(); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 4953dc054c53..691f46e148f4 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -171,6 +171,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) arch_suspend_disable_irqs(); BUG_ON(!irqs_disabled()); + system_state = SYSTEM_SUSPEND; + error = syscore_suspend(); if (!error) { *wakeup = pm_wakeup_pending(); @@ -181,6 +183,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) syscore_resume(); } + system_state = SYSTEM_RUNNING; + arch_suspend_enable_irqs(); BUG_ON(irqs_disabled()); diff --git a/kernel/printk.c b/kernel/printk.c index 7982a0a841ea..9eabbbbae463 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -21,6 +21,7 @@ #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/console.h> +#include <linux/sysrq.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/nmi.h> @@ -44,13 +45,6 @@ #include <asm/uaccess.h> -/* - * Architectures can override it: - */ -void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...) -{ -} - #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) /* printk's without a loglevel use this.. */ @@ -511,6 +505,7 @@ static void __call_console_drivers(unsigned start, unsigned end) { struct console *con; + migrate_disable(); for_each_console(con) { if (exclusive_console && con != exclusive_console) continue; @@ -519,7 +514,61 @@ static void __call_console_drivers(unsigned start, unsigned end) (con->flags & CON_ANYTIME))) con->write(con, &LOG_BUF(start), end - start); } + migrate_enable(); +} + +#ifdef CONFIG_EARLY_PRINTK +struct console *early_console; + +static void early_vprintk(const char *fmt, va_list ap) +{ + char buf[512]; + int n = vscnprintf(buf, sizeof(buf), fmt, ap); + if (early_console) + early_console->write(early_console, buf, n); +} + +asmlinkage void early_printk(const char *fmt, ...) +{ + va_list ap; + va_start(ap, fmt); + early_vprintk(fmt, ap); + va_end(ap); +} + +/* + * This is independent of any log levels - a global + * kill switch that turns off all of printk. + * + * Used by the NMI watchdog if early-printk is enabled. + */ +static int __read_mostly printk_killswitch; + +static int __init force_early_printk_setup(char *str) +{ + printk_killswitch = 1; + return 0; +} +early_param("force_early_printk", force_early_printk_setup); + +void printk_kill(void) +{ + printk_killswitch = 1; +} + +static int forced_early_printk(const char *fmt, va_list ap) +{ + if (!printk_killswitch) + return 0; + early_vprintk(fmt, ap); + return 1; +} +#else +static inline int forced_early_printk(const char *fmt, va_list ap) +{ + return 0; } +#endif static int __read_mostly ignore_loglevel; @@ -781,12 +830,18 @@ static inline int can_use_console(unsigned int cpu) * interrupts disabled. It should return with 'lockbuf_lock' * released but interrupts still disabled. */ -static int console_trylock_for_printk(unsigned int cpu) +static int console_trylock_for_printk(unsigned int cpu, unsigned long flags) __releases(&logbuf_lock) { int retval = 0, wake = 0; +#ifdef CONFIG_PREEMPT_RT_FULL + int lock = (!early_boot_irqs_disabled && !irqs_disabled_flags(flags) && + !preempt_count()) || sysrq_in_progress; +#else + int lock = 1; +#endif - if (console_trylock()) { + if (lock && console_trylock()) { retval = 1; /* @@ -837,10 +892,17 @@ asmlinkage int vprintk(const char *fmt, va_list args) size_t plen; char special; + /* + * Fall back to early_printk if a debugging subsystem has + * killed printk output + */ + if (unlikely(forced_early_printk(fmt, args))) + return 1; + boot_delay_msec(); printk_delay(); - preempt_disable(); + migrate_disable(); /* This stops the holder of console_sem just where we want him */ raw_local_irq_save(flags); this_cpu = smp_processor_id(); @@ -957,14 +1019,21 @@ asmlinkage int vprintk(const char *fmt, va_list args) * will release 'logbuf_lock' regardless of whether it * actually gets the semaphore or not. */ - if (console_trylock_for_printk(this_cpu)) + if (console_trylock_for_printk(this_cpu, flags)) { +#ifndef CONFIG_PREEMPT_RT_FULL console_unlock(); +#else + raw_local_irq_restore(flags); + console_unlock(); + raw_local_irq_save(flags); +#endif + } lockdep_on(); out_restore_irqs: raw_local_irq_restore(flags); - preempt_enable(); + migrate_enable(); return printed_len; } EXPORT_SYMBOL(printk); @@ -1221,8 +1290,8 @@ void printk_tick(void) int printk_needs_cpu(int cpu) { - if (cpu_is_offline(cpu)) - printk_tick(); + if (unlikely(cpu_is_offline(cpu))) + __this_cpu_write(printk_pending, 0); return __this_cpu_read(printk_pending); } @@ -1268,11 +1337,16 @@ again: _con_start = con_start; _log_end = log_end; con_start = log_end; /* Flush */ +#ifndef CONFIG_PREEMPT_RT_FULL raw_spin_unlock(&logbuf_lock); stop_critical_timings(); /* don't trace print latency */ call_console_drivers(_con_start, _log_end); start_critical_timings(); local_irq_restore(flags); +#else + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + call_console_drivers(_con_start, _log_end); +#endif } console_locked = 0; diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index c5b98e565aee..24dcc713bd00 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -77,6 +77,7 @@ int debug_lockdep_rcu_enabled(void) } EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled); +#ifndef CONFIG_PREEMPT_RT_FULL /** * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? * @@ -96,6 +97,7 @@ int rcu_read_lock_bh_held(void) return in_softirq() || irqs_disabled(); } EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); +#endif #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 636af6d9c6e5..6689097c45ec 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -243,6 +243,7 @@ void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) } EXPORT_SYMBOL_GPL(call_rcu_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /* * Post an RCU bottom-half callback to be invoked after any subsequent * quiescent state. @@ -252,3 +253,4 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) __call_rcu(head, func, &rcu_bh_ctrlblk); } EXPORT_SYMBOL_GPL(call_rcu_bh); +#endif diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 6b76d812740c..8c26a499ff99 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -170,6 +170,14 @@ void rcu_sched_qs(int cpu) rdp->passed_quiesce = 1; } +#ifdef CONFIG_PREEMPT_RT_FULL +static void rcu_preempt_qs(int cpu); + +void rcu_bh_qs(int cpu) +{ + rcu_preempt_qs(cpu); +} +#else void rcu_bh_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); @@ -180,6 +188,7 @@ void rcu_bh_qs(int cpu) trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs"); rdp->passed_quiesce = 1; } +#endif /* * Note a context switch. This is a quiescent state for RCU-sched, @@ -225,6 +234,7 @@ long rcu_batches_completed_sched(void) } EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /* * Return the number of RCU BH batches processed thus far for debug & stats. */ @@ -242,6 +252,7 @@ void rcu_bh_force_quiescent_state(void) force_quiescent_state(&rcu_bh_state, 0); } EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); +#endif /* * Record the number of times rcutorture tests have been initiated and @@ -1221,7 +1232,7 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) else raw_spin_unlock_irqrestore(&rnp->lock, flags); if (need_report & RCU_OFL_TASKS_EXP_GP) - rcu_report_exp_rnp(rsp, rnp); + rcu_report_exp_rnp(rsp, rnp, true); rcu_node_kthread_setaffinity(rnp, -1); } @@ -1667,6 +1678,7 @@ void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) } EXPORT_SYMBOL_GPL(call_rcu_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /* * Queue an RCU for invocation after a quicker grace period. */ @@ -1675,6 +1687,7 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) __call_rcu(head, func, &rcu_bh_state); } EXPORT_SYMBOL_GPL(call_rcu_bh); +#endif /** * synchronize_sched - wait until an rcu-sched grace period has elapsed. @@ -1707,6 +1720,7 @@ void synchronize_sched(void) } EXPORT_SYMBOL_GPL(synchronize_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /** * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. * @@ -1723,6 +1737,7 @@ void synchronize_rcu_bh(void) wait_rcu_gp(call_rcu_bh); } EXPORT_SYMBOL_GPL(synchronize_rcu_bh); +#endif /* * Check to see if there is any immediate RCU-related work to be done @@ -1877,6 +1892,7 @@ static void _rcu_barrier(struct rcu_state *rsp, mutex_unlock(&rcu_barrier_mutex); } +#ifndef CONFIG_PREEMPT_RT_FULL /** * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. */ @@ -1885,6 +1901,7 @@ void rcu_barrier_bh(void) _rcu_barrier(&rcu_bh_state, call_rcu_bh); } EXPORT_SYMBOL_GPL(rcu_barrier_bh); +#endif /** * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 849ce9ec51fe..dca495d81304 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -451,7 +451,8 @@ static void rcu_preempt_check_callbacks(int cpu); static void rcu_preempt_process_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp); +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake); #endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */ static int rcu_preempt_pending(int cpu); static int rcu_preempt_needs_cpu(int cpu); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 4b9b9f8a4184..936441dc5cac 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -336,7 +336,7 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) } /* Hardware IRQ handlers cannot block. */ - if (in_irq() || in_serving_softirq()) { + if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { local_irq_restore(flags); return; } @@ -407,7 +407,7 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) * then we need to report up the rcu_node hierarchy. */ if (!empty_exp && !rcu_preempted_readers_exp(rnp)) - rcu_report_exp_rnp(&rcu_preempt_state, rnp); + rcu_report_exp_rnp(&rcu_preempt_state, rnp, true); } else { local_irq_restore(flags); } @@ -731,7 +731,8 @@ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) * * Caller must hold sync_rcu_preempt_exp_mutex. */ -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake) { unsigned long flags; unsigned long mask; @@ -744,7 +745,8 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) } if (rnp->parent == NULL) { raw_spin_unlock_irqrestore(&rnp->lock, flags); - wake_up(&sync_rcu_preempt_exp_wq); + if (wake) + wake_up(&sync_rcu_preempt_exp_wq); break; } mask = rnp->grpmask; @@ -777,7 +779,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) must_wait = 1; } if (!must_wait) - rcu_report_exp_rnp(rsp, rnp); + rcu_report_exp_rnp(rsp, rnp, false); } /* @@ -1069,9 +1071,9 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); * report on tasks preempted in RCU read-side critical sections during * expedited RCU grace periods. */ -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake) { - return; } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ @@ -1931,7 +1933,7 @@ EXPORT_SYMBOL_GPL(synchronize_sched_expedited); #endif /* #else #ifndef CONFIG_SMP */ -#if !defined(CONFIG_RCU_FAST_NO_HZ) +#if 1 /* !defined(CONFIG_RCU_FAST_NO_HZ) */ /* * Check to see if any future RCU-related work will need to be done diff --git a/kernel/relay.c b/kernel/relay.c index 226fade4d727..d5aeaa8bb9ee 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -336,6 +336,10 @@ static void wakeup_readers(unsigned long data) { struct rchan_buf *buf = (struct rchan_buf *)data; wake_up_interruptible(&buf->read_wait); + /* + * Stupid polling for now: + */ + mod_timer(&buf->timer, jiffies + 1); } /** @@ -353,6 +357,7 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init) init_waitqueue_head(&buf->read_wait); kref_init(&buf->kref); setup_timer(&buf->timer, wakeup_readers, (unsigned long)buf); + mod_timer(&buf->timer, jiffies + 1); } else del_timer_sync(&buf->timer); @@ -733,15 +738,6 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) else buf->early_bytes += buf->chan->subbuf_size - buf->padding[old_subbuf]; - smp_mb(); - if (waitqueue_active(&buf->read_wait)) - /* - * Calling wake_up_interruptible() from here - * will deadlock if we happen to be logging - * from the scheduler (trying to re-grab - * rq->lock), so defer it. - */ - mod_timer(&buf->timer, jiffies + 1); } old = buf->data; diff --git a/kernel/res_counter.c b/kernel/res_counter.c index 34683efa2cce..21e9ec4a96cf 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -43,7 +43,7 @@ int res_counter_charge(struct res_counter *counter, unsigned long val, struct res_counter *c, *u; *limit_fail_at = NULL; - local_irq_save(flags); + local_irq_save_nort(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); ret = res_counter_charge_locked(c, val); @@ -62,7 +62,7 @@ undo: spin_unlock(&u->lock); } done: - local_irq_restore(flags); + local_irq_restore_nort(flags); return ret; } @@ -79,13 +79,13 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val) unsigned long flags; struct res_counter *c; - local_irq_save(flags); + local_irq_save_nort(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); res_counter_uncharge_locked(c, val); spin_unlock(&c->lock); } - local_irq_restore(flags); + local_irq_restore_nort(flags); } diff --git a/kernel/rt.c b/kernel/rt.c new file mode 100644 index 000000000000..092d6b356d59 --- /dev/null +++ b/kernel/rt.c @@ -0,0 +1,442 @@ +/* + * kernel/rt.c + * + * Real-Time Preemption Support + * + * started by Ingo Molnar: + * + * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com> + * + * historic credit for proving that Linux spinlocks can be implemented via + * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow + * and others) who prototyped it on 2.4 and did lots of comparative + * research and analysis; TimeSys, for proving that you can implement a + * fully preemptible kernel via the use of IRQ threading and mutexes; + * Bill Huey for persuasively arguing on lkml that the mutex model is the + * right one; and to MontaVista, who ported pmutexes to 2.6. + * + * This code is a from-scratch implementation and is not based on pmutexes, + * but the idea of converting spinlocks to mutexes is used here too. + * + * lock debugging, locking tree, deadlock detection: + * + * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey + * Released under the General Public License (GPL). + * + * Includes portions of the generic R/W semaphore implementation from: + * + * Copyright (c) 2001 David Howells (dhowells@redhat.com). + * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de> + * - Derived also from comments by Linus + * + * Pending ownership of locks and ownership stealing: + * + * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt + * + * (also by Steven Rostedt) + * - Converted single pi_lock to individual task locks. + * + * By Esben Nielsen: + * Doing priority inheritance with help of the scheduler. + * + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com> + * - major rework based on Esben Nielsens initial patch + * - replaced thread_info references by task_struct refs + * - removed task->pending_owner dependency + * - BKL drop/reacquire for semaphore style locks to avoid deadlocks + * in the scheduler return path as discussed with Steven Rostedt + * + * Copyright (C) 2006, Kihon Technologies Inc. + * Steven Rostedt <rostedt@goodmis.org> + * - debugged and patched Thomas Gleixner's rework. + * - added back the cmpxchg to the rework. + * - turned atomic require back on for SMP. + */ + +#include <linux/spinlock.h> +#include <linux/rtmutex.h> +#include <linux/sched.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/syscalls.h> +#include <linux/interrupt.h> +#include <linux/plist.h> +#include <linux/fs.h> +#include <linux/futex.h> +#include <linux/hrtimer.h> + +#include "rtmutex_common.h" + +/* + * struct mutex functions + */ +void __mutex_do_init(struct mutex *mutex, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); + lockdep_init_map(&mutex->dep_map, name, key, 0); +#endif + mutex->lock.save_state = 0; +} +EXPORT_SYMBOL(__mutex_do_init); + +void __lockfunc _mutex_lock(struct mutex *lock) +{ + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + rt_mutex_lock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_lock); + +int __lockfunc _mutex_lock_interruptible(struct mutex *lock) +{ + int ret; + + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_lock_interruptible(&lock->lock, 0); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_interruptible); + +int __lockfunc _mutex_lock_killable(struct mutex *lock) +{ + int ret; + + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_lock_killable(&lock->lock, 0); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_killable); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass) +{ + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); + rt_mutex_lock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_lock_nested); + +void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) +{ + mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_); + rt_mutex_lock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_lock_nest_lock); + +int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass) +{ + int ret; + + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); + ret = rt_mutex_lock_interruptible(&lock->lock, 0); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_interruptible_nested); + +int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass) +{ + int ret; + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + ret = rt_mutex_lock_killable(&lock->lock, 0); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_killable_nested); +#endif + +int __lockfunc _mutex_trylock(struct mutex *lock) +{ + int ret = rt_mutex_trylock(&lock->lock); + + if (ret) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + + return ret; +} +EXPORT_SYMBOL(_mutex_trylock); + +void __lockfunc _mutex_unlock(struct mutex *lock) +{ + mutex_release(&lock->dep_map, 1, _RET_IP_); + rt_mutex_unlock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_unlock); + +/* + * rwlock_t functions + */ +int __lockfunc rt_write_trylock(rwlock_t *rwlock) +{ + int ret = rt_mutex_trylock(&rwlock->lock); + + migrate_disable(); + if (ret) + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); + else + migrate_enable(); + + return ret; +} +EXPORT_SYMBOL(rt_write_trylock); + +int __lockfunc rt_write_trylock_irqsave(rwlock_t *rwlock, unsigned long *flags) +{ + int ret; + + *flags = 0; + migrate_disable(); + ret = rt_write_trylock(rwlock); + if (!ret) + migrate_enable(); + return ret; +} +EXPORT_SYMBOL(rt_write_trylock_irqsave); + +int __lockfunc rt_read_trylock(rwlock_t *rwlock) +{ + struct rt_mutex *lock = &rwlock->lock; + int ret = 1; + + /* + * recursive read locks succeed when current owns the lock, + * but not when read_depth == 0 which means that the lock is + * write locked. + */ + migrate_disable(); + if (rt_mutex_owner(lock) != current) + ret = rt_mutex_trylock(lock); + else if (!rwlock->read_depth) + ret = 0; + + if (ret) { + rwlock->read_depth++; + rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_); + } else + migrate_enable(); + + return ret; +} +EXPORT_SYMBOL(rt_read_trylock); + +void __lockfunc rt_write_lock(rwlock_t *rwlock) +{ + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + __rt_spin_lock(&rwlock->lock); +} +EXPORT_SYMBOL(rt_write_lock); + +void __lockfunc rt_read_lock(rwlock_t *rwlock) +{ + struct rt_mutex *lock = &rwlock->lock; + + rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); + + /* + * recursive read locks succeed when current owns the lock + */ + if (rt_mutex_owner(lock) != current) + __rt_spin_lock(lock); + rwlock->read_depth++; +} + +EXPORT_SYMBOL(rt_read_lock); + +void __lockfunc rt_write_unlock(rwlock_t *rwlock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + __rt_spin_unlock(&rwlock->lock); +} +EXPORT_SYMBOL(rt_write_unlock); + +void __lockfunc rt_read_unlock(rwlock_t *rwlock) +{ + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + + /* Release the lock only when read_depth is down to 0 */ + if (--rwlock->read_depth == 0) + __rt_spin_unlock(&rwlock->lock); +} +EXPORT_SYMBOL(rt_read_unlock); + +unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock) +{ + rt_write_lock(rwlock); + + return 0; +} +EXPORT_SYMBOL(rt_write_lock_irqsave); + +unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock) +{ + rt_read_lock(rwlock); + + return 0; +} +EXPORT_SYMBOL(rt_read_lock_irqsave); + +void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock)); + lockdep_init_map(&rwlock->dep_map, name, key, 0); +#endif + rwlock->lock.save_state = 1; + rwlock->read_depth = 0; +} +EXPORT_SYMBOL(__rt_rwlock_init); + +/* + * rw_semaphores + */ + +void rt_up_write(struct rw_semaphore *rwsem) +{ + rwsem_release(&rwsem->dep_map, 1, _RET_IP_); + rt_mutex_unlock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_up_write); + +void rt_up_read(struct rw_semaphore *rwsem) +{ + rwsem_release(&rwsem->dep_map, 1, _RET_IP_); + if (--rwsem->read_depth == 0) + rt_mutex_unlock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_up_read); + +/* + * downgrade a write lock into a read lock + * - just wake up any readers at the front of the queue + */ +void rt_downgrade_write(struct rw_semaphore *rwsem) +{ + BUG_ON(rt_mutex_owner(&rwsem->lock) != current); + rwsem->read_depth = 1; +} +EXPORT_SYMBOL(rt_downgrade_write); + +int rt_down_write_trylock(struct rw_semaphore *rwsem) +{ + int ret = rt_mutex_trylock(&rwsem->lock); + + if (ret) + rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(rt_down_write_trylock); + +void rt_down_write(struct rw_semaphore *rwsem) +{ + rwsem_acquire(&rwsem->dep_map, 0, 0, _RET_IP_); + rt_mutex_lock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_down_write); + +void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass) +{ + rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_); + rt_mutex_lock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_down_write_nested); + +int rt_down_read_trylock(struct rw_semaphore *rwsem) +{ + struct rt_mutex *lock = &rwsem->lock; + int ret = 1; + + /* + * recursive read locks succeed when current owns the rwsem, + * but not when read_depth == 0 which means that the rwsem is + * write locked. + */ + if (rt_mutex_owner(lock) != current) + ret = rt_mutex_trylock(&rwsem->lock); + else if (!rwsem->read_depth) + ret = 0; + + if (ret) { + rwsem->read_depth++; + rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); + } + return ret; +} +EXPORT_SYMBOL(rt_down_read_trylock); + +static void __rt_down_read(struct rw_semaphore *rwsem, int subclass) +{ + struct rt_mutex *lock = &rwsem->lock; + + rwsem_acquire_read(&rwsem->dep_map, subclass, 0, _RET_IP_); + + if (rt_mutex_owner(lock) != current) + rt_mutex_lock(&rwsem->lock); + rwsem->read_depth++; +} + +void rt_down_read(struct rw_semaphore *rwsem) +{ + __rt_down_read(rwsem, 0); +} +EXPORT_SYMBOL(rt_down_read); + +void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass) +{ + __rt_down_read(rwsem, subclass); +} +EXPORT_SYMBOL(rt_down_read_nested); + +void __rt_rwsem_init(struct rw_semaphore *rwsem, char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)rwsem, sizeof(*rwsem)); + lockdep_init_map(&rwsem->dep_map, name, key, 0); +#endif + rwsem->read_depth = 0; + rwsem->lock.save_state = 0; +} +EXPORT_SYMBOL(__rt_rwsem_init); + +/** + * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 + * @cnt: the atomic which we are to dec + * @lock: the mutex to return holding if we dec to 0 + * + * return true and hold lock if we dec to 0, return false otherwise + */ +int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) +{ + /* dec if we can't possibly hit 0 */ + if (atomic_add_unless(cnt, -1, 1)) + return 0; + /* we might hit 0, so take the lock */ + mutex_lock(lock); + if (!atomic_dec_and_test(cnt)) { + /* when we actually did the dec, we didn't hit 0 */ + mutex_unlock(lock); + return 0; + } + /* we hit 0, and we hold the lock */ + return 1; +} +EXPORT_SYMBOL(atomic_dec_and_mutex_lock); diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index f9d8482dd487..9850dc02f1db 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -8,6 +8,12 @@ * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt * Copyright (C) 2006 Esben Nielsen * + * Adaptive Spinlocks: + * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich, + * and Peter Morreale, + * Adaptive Spinlocks simplification: + * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt <srostedt@redhat.com> + * * See Documentation/rt-mutex-design.txt for details. */ #include <linux/spinlock.h> @@ -67,6 +73,12 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock) clear_rt_mutex_waiters(lock); } +static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) +{ + return waiter && waiter != PI_WAKEUP_INPROGRESS && + waiter != PI_REQUEUE_INPROGRESS; +} + /* * We can speed up the acquire/release, if the architecture * supports cmpxchg and if there's no debugging state to be set up @@ -90,6 +102,12 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) } #endif +static inline void init_lists(struct rt_mutex *lock) +{ + if (unlikely(!lock->wait_list.node_list.prev)) + plist_head_init(&lock->wait_list); +} + /* * Calculate task priority from the waiter list priority * @@ -136,6 +154,14 @@ static void rt_mutex_adjust_prio(struct task_struct *task) raw_spin_unlock_irqrestore(&task->pi_lock, flags); } +static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter) +{ + if (waiter->savestate) + wake_up_lock_sleeper(waiter->task); + else + wake_up_process(waiter->task); +} + /* * Max number of times we'll walk the boosting chain: */ @@ -196,7 +222,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * reached or the state of the chain has changed while we * dropped the locks. */ - if (!waiter) + if (!rt_mutex_real_waiter(waiter)) goto out_unlock_pi; /* @@ -247,13 +273,15 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, /* Release the task */ raw_spin_unlock_irqrestore(&task->pi_lock, flags); if (!rt_mutex_owner(lock)) { + struct rt_mutex_waiter *lock_top_waiter; + /* * If the requeue above changed the top waiter, then we need * to wake the new top waiter up to try to get the lock. */ - - if (top_waiter != rt_mutex_top_waiter(lock)) - wake_up_process(rt_mutex_top_waiter(lock)->task); + lock_top_waiter = rt_mutex_top_waiter(lock); + if (top_waiter != lock_top_waiter) + rt_mutex_wake_waiter(lock_top_waiter); raw_spin_unlock(&lock->wait_lock); goto out_put_task; } @@ -298,6 +326,25 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, return ret; } + +#define STEAL_NORMAL 0 +#define STEAL_LATERAL 1 + +/* + * Note that RT tasks are excluded from lateral-steals to prevent the + * introduction of an unbounded latency + */ +static inline int lock_is_stealable(struct task_struct *task, + struct task_struct *pendowner, int mode) +{ + if (mode == STEAL_NORMAL || rt_task(task)) { + if (task->prio >= pendowner->prio) + return 0; + } else if (task->prio > pendowner->prio) + return 0; + return 1; +} + /* * Try to take an rt-mutex * @@ -307,8 +354,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * @task: the task which wants to acquire the lock * @waiter: the waiter that is queued to the lock's wait list. (could be NULL) */ -static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, - struct rt_mutex_waiter *waiter) +static int +__try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + struct rt_mutex_waiter *waiter, int mode) { /* * We have to be careful here if the atomic speedups are @@ -341,12 +389,14 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, * 3) it is top waiter */ if (rt_mutex_has_waiters(lock)) { - if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) { - if (!waiter || waiter != rt_mutex_top_waiter(lock)) - return 0; - } + struct task_struct *pown = rt_mutex_top_waiter(lock)->task; + + if (task != pown && !lock_is_stealable(task, pown, mode)) + return 0; } + /* We got the lock. */ + if (waiter || rt_mutex_has_waiters(lock)) { unsigned long flags; struct rt_mutex_waiter *top; @@ -371,7 +421,6 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, raw_spin_unlock_irqrestore(&task->pi_lock, flags); } - /* We got the lock. */ debug_rt_mutex_lock(lock); rt_mutex_set_owner(lock, task); @@ -381,6 +430,13 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, return 1; } +static inline int +try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + struct rt_mutex_waiter *waiter) +{ + return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL); +} + /* * Task blocks on lock. * @@ -399,6 +455,23 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, int chain_walk = 0, res; raw_spin_lock_irqsave(&task->pi_lock, flags); + + /* + * In the case of futex requeue PI, this will be a proxy + * lock. The task will wake unaware that it is enqueueed on + * this lock. Avoid blocking on two locks and corrupting + * pi_blocked_on via the PI_WAKEUP_INPROGRESS + * flag. futex_wait_requeue_pi() sets this when it wakes up + * before requeue (due to a signal or timeout). Do not enqueue + * the task if PI_WAKEUP_INPROGRESS is set. + */ + if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return -EAGAIN; + } + + BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); + __rt_mutex_adjust_prio(task); waiter->task = task; waiter->lock = lock; @@ -423,7 +496,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, plist_add(&waiter->pi_list_entry, &owner->pi_waiters); __rt_mutex_adjust_prio(owner); - if (owner->pi_blocked_on) + if (rt_mutex_real_waiter(owner->pi_blocked_on)) chain_walk = 1; raw_spin_unlock_irqrestore(&owner->pi_lock, flags); } @@ -478,7 +551,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock) raw_spin_unlock_irqrestore(¤t->pi_lock, flags); - wake_up_process(waiter->task); + rt_mutex_wake_waiter(waiter); } /* @@ -517,7 +590,7 @@ static void remove_waiter(struct rt_mutex *lock, } __rt_mutex_adjust_prio(owner); - if (owner->pi_blocked_on) + if (rt_mutex_real_waiter(owner->pi_blocked_on)) chain_walk = 1; raw_spin_unlock_irqrestore(&owner->pi_lock, flags); @@ -551,23 +624,316 @@ void rt_mutex_adjust_pi(struct task_struct *task) raw_spin_lock_irqsave(&task->pi_lock, flags); waiter = task->pi_blocked_on; - if (!waiter || waiter->list_entry.prio == task->prio) { + if (!rt_mutex_real_waiter(waiter) || + waiter->list_entry.prio == task->prio) { raw_spin_unlock_irqrestore(&task->pi_lock, flags); return; } - raw_spin_unlock_irqrestore(&task->pi_lock, flags); - /* gets dropped in rt_mutex_adjust_prio_chain()! */ get_task_struct(task); + raw_spin_unlock_irqrestore(&task->pi_lock, flags); rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task); } +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * preemptible spin_lock functions: + */ +static inline void rt_spin_lock_fastlock(struct rt_mutex *lock, + void (*slowfn)(struct rt_mutex *lock)) +{ + might_sleep(); + + if (likely(rt_mutex_cmpxchg(lock, NULL, current))) + rt_mutex_deadlock_account_lock(lock, current); + else + slowfn(lock); +} + +static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock, + void (*slowfn)(struct rt_mutex *lock)) +{ + if (likely(rt_mutex_cmpxchg(lock, current, NULL))) + rt_mutex_deadlock_account_unlock(current); + else + slowfn(lock); +} + +#ifdef CONFIG_SMP +/* + * Note that owner is a speculative pointer and dereferencing relies + * on rcu_read_lock() and the check against the lock owner. + */ +static int adaptive_wait(struct rt_mutex *lock, + struct task_struct *owner) +{ + int res = 0; + + rcu_read_lock(); + for (;;) { + if (owner != rt_mutex_owner(lock)) + break; + /* + * Ensure that owner->on_cpu is dereferenced _after_ + * checking the above to be valid. + */ + barrier(); + if (!owner->on_cpu) { + res = 1; + break; + } + cpu_relax(); + } + rcu_read_unlock(); + return res; +} +#else +static int adaptive_wait(struct rt_mutex *lock, + struct task_struct *orig_owner) +{ + return 1; +} +#endif + +# define pi_lock(lock) raw_spin_lock_irq(lock) +# define pi_unlock(lock) raw_spin_unlock_irq(lock) + +/* + * Slow path lock function spin_lock style: this variant is very + * careful not to miss any non-lock wakeups. + * + * We store the current state under p->pi_lock in p->saved_state and + * the try_to_wake_up() code handles this accordingly. + */ +static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock) +{ + struct task_struct *lock_owner, *self = current; + struct rt_mutex_waiter waiter, *top_waiter; + int ret; + + rt_mutex_init_waiter(&waiter, true); + + raw_spin_lock(&lock->wait_lock); + init_lists(lock); + + if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) { + raw_spin_unlock(&lock->wait_lock); + return; + } + + BUG_ON(rt_mutex_owner(lock) == self); + + /* + * We save whatever state the task is in and we'll restore it + * after acquiring the lock taking real wakeups into account + * as well. We are serialized via pi_lock against wakeups. See + * try_to_wake_up(). + */ + pi_lock(&self->pi_lock); + self->saved_state = self->state; + __set_current_state(TASK_UNINTERRUPTIBLE); + pi_unlock(&self->pi_lock); + + ret = task_blocks_on_rt_mutex(lock, &waiter, self, 0); + BUG_ON(ret); + + for (;;) { + /* Try to acquire the lock again. */ + if (__try_to_take_rt_mutex(lock, self, &waiter, STEAL_LATERAL)) + break; + + top_waiter = rt_mutex_top_waiter(lock); + lock_owner = rt_mutex_owner(lock); + + raw_spin_unlock(&lock->wait_lock); + + debug_rt_mutex_print_deadlock(&waiter); + + if (top_waiter != &waiter || adaptive_wait(lock, lock_owner)) + schedule_rt_mutex(lock); + + raw_spin_lock(&lock->wait_lock); + + pi_lock(&self->pi_lock); + __set_current_state(TASK_UNINTERRUPTIBLE); + pi_unlock(&self->pi_lock); + } + + /* + * Restore the task state to current->saved_state. We set it + * to the original state above and the try_to_wake_up() code + * has possibly updated it when a real (non-rtmutex) wakeup + * happened while we were blocked. Clear saved_state so + * try_to_wakeup() does not get confused. + */ + pi_lock(&self->pi_lock); + __set_current_state(self->saved_state); + self->saved_state = TASK_RUNNING; + pi_unlock(&self->pi_lock); + + /* + * try_to_take_rt_mutex() sets the waiter bit + * unconditionally. We might have to fix that up: + */ + fixup_rt_mutex_waiters(lock); + + BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock)); + BUG_ON(!plist_node_empty(&waiter.list_entry)); + + raw_spin_unlock(&lock->wait_lock); + + debug_rt_mutex_free_waiter(&waiter); +} + +/* + * Slow path to release a rt_mutex spin_lock style + */ +static void noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) +{ + raw_spin_lock(&lock->wait_lock); + + debug_rt_mutex_unlock(lock); + + rt_mutex_deadlock_account_unlock(current); + + if (!rt_mutex_has_waiters(lock)) { + lock->owner = NULL; + raw_spin_unlock(&lock->wait_lock); + return; + } + + wakeup_next_waiter(lock); + + raw_spin_unlock(&lock->wait_lock); + + /* Undo pi boosting.when necessary */ + rt_mutex_adjust_prio(current); +} + +void __lockfunc rt_spin_lock(spinlock_t *lock) +{ + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); +} +EXPORT_SYMBOL(rt_spin_lock); + +void __lockfunc __rt_spin_lock(struct rt_mutex *lock) +{ + rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock); +} +EXPORT_SYMBOL(__rt_spin_lock); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) +{ + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); +} +EXPORT_SYMBOL(rt_spin_lock_nested); +#endif + +void __lockfunc rt_spin_unlock(spinlock_t *lock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(rt_spin_unlock); + +void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) +{ + rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(__rt_spin_unlock); + +/* + * Wait for the lock to get unlocked: instead of polling for an unlock + * (like raw spinlocks do), we lock and unlock, to force the kernel to + * schedule if there's contention: + */ +void __lockfunc rt_spin_unlock_wait(spinlock_t *lock) +{ + spin_lock(lock); + spin_unlock(lock); +} +EXPORT_SYMBOL(rt_spin_unlock_wait); + +int __lockfunc rt_spin_trylock(spinlock_t *lock) +{ + int ret = rt_mutex_trylock(&lock->lock); + + if (ret) + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock); + +int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) +{ + int ret; + + local_bh_disable(); + ret = rt_mutex_trylock(&lock->lock); + if (ret) { + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } else + local_bh_enable(); + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock_bh); + +int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) +{ + int ret; + + *flags = 0; + migrate_disable(); + ret = rt_mutex_trylock(&lock->lock); + if (ret) + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + else + migrate_enable(); + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock_irqsave); + +int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock) +{ + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + if (atomic_add_unless(atomic, -1, 1)) + return 0; + migrate_disable(); + rt_spin_lock(lock); + if (atomic_dec_and_test(atomic)) + return 1; + rt_spin_unlock(lock); + migrate_enable(); + return 0; +} +EXPORT_SYMBOL(atomic_dec_and_spin_lock); + +void +__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif +} +EXPORT_SYMBOL(__rt_spin_lock_init); + +#endif /* PREEMPT_RT_FULL */ + /** * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop * @lock: the rt_mutex to take * @state: the state the task should block in (TASK_INTERRUPTIBLE - * or TASK_UNINTERRUPTIBLE) + * or TASK_UNINTERRUPTIBLE) * @timeout: the pre-initialized and started timer, or NULL for none * @waiter: the pre-initialized rt_mutex_waiter * @@ -631,9 +997,10 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, struct rt_mutex_waiter waiter; int ret = 0; - debug_rt_mutex_init_waiter(&waiter); + rt_mutex_init_waiter(&waiter, false); raw_spin_lock(&lock->wait_lock); + init_lists(lock); /* Try to acquire the lock again: */ if (try_to_take_rt_mutex(lock, current, NULL)) { @@ -686,6 +1053,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock) int ret = 0; raw_spin_lock(&lock->wait_lock); + init_lists(lock); if (likely(rt_mutex_owner(lock) != current)) { @@ -799,12 +1167,12 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock); /** * rt_mutex_lock_interruptible - lock a rt_mutex interruptible * - * @lock: the rt_mutex to be locked + * @lock: the rt_mutex to be locked * @detect_deadlock: deadlock detection on/off * * Returns: - * 0 on success - * -EINTR when interrupted by a signal + * 0 on success + * -EINTR when interrupted by a signal * -EDEADLK when the lock would deadlock (when deadlock detection is on) */ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock, @@ -818,17 +1186,38 @@ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock, EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); /** + * rt_mutex_lock_killable - lock a rt_mutex killable + * + * @lock: the rt_mutex to be locked + * @detect_deadlock: deadlock detection on/off + * + * Returns: + * 0 on success + * -EINTR when interrupted by a signal + * -EDEADLK when the lock would deadlock (when deadlock detection is on) + */ +int __sched rt_mutex_lock_killable(struct rt_mutex *lock, + int detect_deadlock) +{ + might_sleep(); + + return rt_mutex_fastlock(lock, TASK_KILLABLE, + detect_deadlock, rt_mutex_slowlock); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); + +/** * rt_mutex_timed_lock - lock a rt_mutex interruptible * the timeout structure is provided * by the caller * - * @lock: the rt_mutex to be locked + * @lock: the rt_mutex to be locked * @timeout: timeout structure or NULL (no timeout) * @detect_deadlock: deadlock detection on/off * * Returns: - * 0 on success - * -EINTR when interrupted by a signal + * 0 on success + * -EINTR when interrupted by a signal * -ETIMEDOUT when the timeout expired * -EDEADLK when the lock would deadlock (when deadlock detection is on) */ @@ -897,7 +1286,6 @@ EXPORT_SYMBOL_GPL(rt_mutex_destroy); void __rt_mutex_init(struct rt_mutex *lock, const char *name) { lock->owner = NULL; - raw_spin_lock_init(&lock->wait_lock); plist_head_init(&lock->wait_list); debug_rt_mutex_init(lock, name); @@ -917,7 +1305,7 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init); void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner) { - __rt_mutex_init(lock, NULL); + rt_mutex_init(lock); debug_rt_mutex_proxy_lock(lock, proxy_owner); rt_mutex_set_owner(lock, proxy_owner); rt_mutex_deadlock_account_lock(lock, proxy_owner); @@ -966,6 +1354,35 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, return 1; } +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * In PREEMPT_RT there's an added race. + * If the task, that we are about to requeue, times out, + * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue + * to skip this task. But right after the task sets + * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then + * block on the spin_lock(&hb->lock), which in RT is an rtmutex. + * This will replace the PI_WAKEUP_INPROGRESS with the actual + * lock that it blocks on. We *must not* place this task + * on this proxy lock in that case. + * + * To prevent this race, we first take the task's pi_lock + * and check if it has updated its pi_blocked_on. If it has, + * we assume that it woke up and we return -EAGAIN. + * Otherwise, we set the task's pi_blocked_on to + * PI_REQUEUE_INPROGRESS, so that if the task is waking up + * it will know that we are in the process of requeuing it. + */ + raw_spin_lock(&task->pi_lock); + if (task->pi_blocked_on) { + raw_spin_unlock(&task->pi_lock); + raw_spin_unlock(&lock->wait_lock); + return -EAGAIN; + } + task->pi_blocked_on = PI_REQUEUE_INPROGRESS; + raw_spin_unlock(&task->pi_lock); +#endif + ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock); if (ret && !rt_mutex_owner(lock)) { diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h index 53a66c85261b..6ec3dc1eab10 100644 --- a/kernel/rtmutex_common.h +++ b/kernel/rtmutex_common.h @@ -49,6 +49,7 @@ struct rt_mutex_waiter { struct plist_node pi_list_entry; struct task_struct *task; struct rt_mutex *lock; + bool savestate; #ifdef CONFIG_DEBUG_RT_MUTEXES unsigned long ip; struct pid *deadlock_task_pid; @@ -103,6 +104,9 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) /* * PI-futex support (proxy locking functions, etc.): */ +#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) +#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner); @@ -123,4 +127,12 @@ extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, # include "rtmutex.h" #endif +static inline void +rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate) +{ + debug_rt_mutex_init_waiter(waiter); + waiter->task = NULL; + waiter->savestate = savestate; +} + #endif diff --git a/kernel/sched.c b/kernel/sched.c index d6b149ccf925..81b340df601e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -189,6 +189,7 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rt_b->rt_period_timer.irqsafe = 1; rt_b->rt_period_timer.function = sched_rt_period_timer; } @@ -941,7 +942,11 @@ late_initcall(sched_init_debug); * Number of tasks to iterate in a single balance run. * Limited because this is done with IRQs disabled. */ +#ifndef CONFIG_PREEMPT_RT_FULL const_debug unsigned int sysctl_sched_nr_migrate = 32; +#else +const_debug unsigned int sysctl_sched_nr_migrate = 8; +#endif /* * period over which we average the RT time consumption, measured @@ -1277,6 +1282,7 @@ static void init_rq_hrtick(struct rq *rq) hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); rq->hrtick_timer.function = hrtick; + rq->hrtick_timer.irqsafe = 1; } #else /* CONFIG_SCHED_HRTICK */ static inline void hrtick_clear(struct rq *rq) @@ -2564,7 +2570,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p) printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n", task_pid_nr(p), p->comm, cpu); } - + /* + * Clear PF_THREAD_BOUND, otherwise we wreckage + * migrate_disable/enable. See optimization for + * PF_THREAD_BOUND tasks there. + */ + p->flags &= ~PF_THREAD_BOUND; return dest_cpu; } @@ -2644,10 +2655,6 @@ static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) { activate_task(rq, p, en_flags); p->on_rq = 1; - - /* if a worker is waking up, notify workqueue */ - if (p->flags & PF_WQ_WORKER) - wq_worker_waking_up(p, cpu_of(rq)); } /* @@ -2825,8 +2832,27 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) smp_wmb(); raw_spin_lock_irqsave(&p->pi_lock, flags); - if (!(p->state & state)) + if (!(p->state & state)) { + /* + * The task might be running due to a spinlock sleeper + * wakeup. Check the saved state and set it to running + * if the wakeup condition is true. + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) { + if (p->saved_state & state) { + p->saved_state = TASK_RUNNING; + success = 1; + } + } goto out; + } + + /* + * If this is a regular wakeup, then we can unconditionally + * clear the saved state of a "lock sleeper". + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) + p->saved_state = TASK_RUNNING; success = 1; /* we're going to change ->state */ cpu = task_cpu(p); @@ -2882,40 +2908,6 @@ out: } /** - * try_to_wake_up_local - try to wake up a local task with rq lock held - * @p: the thread to be awakened - * - * Put @p on the run-queue if it's not already there. The caller must - * ensure that this_rq() is locked, @p is bound to this_rq() and not - * the current task. - */ -static void try_to_wake_up_local(struct task_struct *p) -{ - struct rq *rq = task_rq(p); - - BUG_ON(rq != this_rq()); - BUG_ON(p == current); - lockdep_assert_held(&rq->lock); - - if (!raw_spin_trylock(&p->pi_lock)) { - raw_spin_unlock(&rq->lock); - raw_spin_lock(&p->pi_lock); - raw_spin_lock(&rq->lock); - } - - if (!(p->state & TASK_NORMAL)) - goto out; - - if (!p->on_rq) - ttwu_activate(rq, p, ENQUEUE_WAKEUP); - - ttwu_do_wakeup(rq, p, 0); - ttwu_stat(p, smp_processor_id(), 0); -out: - raw_spin_unlock(&p->pi_lock); -} - -/** * wake_up_process - Wake up a specific process * @p: The process to be woken up. * @@ -2932,6 +2924,18 @@ int wake_up_process(struct task_struct *p) } EXPORT_SYMBOL(wake_up_process); +/** + * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock" + * @p: The process to be woken up. + * + * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate + * the nature of the wakeup. + */ +int wake_up_lock_sleeper(struct task_struct *p) +{ + return try_to_wake_up(p, TASK_ALL, WF_LOCK_SLEEPER); +} + int wake_up_state(struct task_struct *p, unsigned int state) { return try_to_wake_up(p, state, 0); @@ -3206,8 +3210,12 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) finish_lock_switch(rq, prev); fire_sched_in_preempt_notifiers(current); + /* + * We use mmdrop_delayed() here so we don't have to do the + * full __mmdrop() when we are the last user. + */ if (mm) - mmdrop(mm); + mmdrop_delayed(mm); if (unlikely(prev_state == TASK_DEAD)) { /* * Remove function-return probe instances associated with this @@ -4354,6 +4362,126 @@ static inline void schedule_debug(struct task_struct *prev) schedstat_inc(this_rq(), sched_count); } +#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_SMP) +#define MIGRATE_DISABLE_SET_AFFIN (1<<30) /* Can't make a negative */ +#define migrate_disabled_updated(p) ((p)->migrate_disable & MIGRATE_DISABLE_SET_AFFIN) +#define migrate_disable_count(p) ((p)->migrate_disable & ~MIGRATE_DISABLE_SET_AFFIN) + +static inline void update_migrate_disable(struct task_struct *p) +{ + const struct cpumask *mask; + + if (likely(!p->migrate_disable)) + return; + + /* Did we already update affinity? */ + if (unlikely(migrate_disabled_updated(p))) + return; + + /* + * Since this is always current we can get away with only locking + * rq->lock, the ->cpus_allowed value can normally only be changed + * while holding both p->pi_lock and rq->lock, but seeing that this + * is current, we cannot actually be waking up, so all code that + * relies on serialization against p->pi_lock is out of scope. + * + * Having rq->lock serializes us against things like + * set_cpus_allowed_ptr() that can still happen concurrently. + */ + mask = tsk_cpus_allowed(p); + + if (p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, mask); + p->rt.nr_cpus_allowed = cpumask_weight(mask); + + /* Let migrate_enable know to fix things back up */ + p->migrate_disable |= MIGRATE_DISABLE_SET_AFFIN; +} + +void migrate_disable(void) +{ + struct task_struct *p = current; + + if (in_atomic() || p->flags & PF_THREAD_BOUND) { +#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic++; +#endif + return; + } + +#ifdef CONFIG_SCHED_DEBUG + WARN_ON_ONCE(p->migrate_disable_atomic); +#endif + + preempt_disable(); + if (p->migrate_disable) { + p->migrate_disable++; + preempt_enable(); + return; + } + + pin_current_cpu(); + p->migrate_disable = 1; + preempt_enable(); +} +EXPORT_SYMBOL_GPL(migrate_disable); + +void migrate_enable(void) +{ + struct task_struct *p = current; + const struct cpumask *mask; + unsigned long flags; + struct rq *rq; + + if (in_atomic() || p->flags & PF_THREAD_BOUND) { +#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic--; +#endif + return; + } + +#ifdef CONFIG_SCHED_DEBUG + WARN_ON_ONCE(p->migrate_disable_atomic); +#endif + WARN_ON_ONCE(p->migrate_disable <= 0); + + preempt_disable(); + if (migrate_disable_count(p) > 1) { + p->migrate_disable--; + preempt_enable(); + return; + } + + if (unlikely(migrate_disabled_updated(p))) { + /* + * Undo whatever update_migrate_disable() did, also see there + * about locking. + */ + rq = this_rq(); + raw_spin_lock_irqsave(&rq->lock, flags); + + /* + * Clearing migrate_disable causes tsk_cpus_allowed to + * show the tasks original cpu affinity. + */ + p->migrate_disable = 0; + mask = tsk_cpus_allowed(p); + if (p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, mask); + p->rt.nr_cpus_allowed = cpumask_weight(mask); + raw_spin_unlock_irqrestore(&rq->lock, flags); + } else + p->migrate_disable = 0; + + unpin_current_cpu(); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(migrate_enable); +#else +static inline void update_migrate_disable(struct task_struct *p) { } +#define migrate_disabled_updated(p) 0 +#endif + static void put_prev_task(struct rq *rq, struct task_struct *prev) { if (prev->on_rq || rq->skip_clock_update < 0) @@ -4413,6 +4541,8 @@ need_resched: raw_spin_lock_irq(&rq->lock); + update_migrate_disable(prev); + switch_count = &prev->nivcsw; if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { if (unlikely(signal_pending_state(prev->state, prev))) { @@ -4420,19 +4550,6 @@ need_resched: } else { deactivate_task(rq, prev, DEQUEUE_SLEEP); prev->on_rq = 0; - - /* - * If a worker went to sleep, notify and ask workqueue - * whether it wants to wake up a task to maintain - * concurrency. - */ - if (prev->flags & PF_WQ_WORKER) { - struct task_struct *to_wakeup; - - to_wakeup = wq_worker_sleeping(prev, cpu); - if (to_wakeup) - try_to_wake_up_local(to_wakeup); - } } switch_count = &prev->nvcsw; } @@ -4466,15 +4583,23 @@ need_resched: post_schedule(rq); - preempt_enable_no_resched(); + __preempt_enable_no_resched(); if (need_resched()) goto need_resched; } static inline void sched_submit_work(struct task_struct *tsk) { - if (!tsk->state) + if (!tsk->state || tsk_is_pi_blocked(tsk)) return; + + /* + * If a worker went to sleep, notify and ask workqueue whether + * it wants to wake up a task to maintain concurrency. + */ + if (tsk->flags & PF_WQ_WORKER) + wq_worker_sleeping(tsk); + /* * If we are going to sleep and we have plugged IO queued, * make sure to submit it to avoid deadlocks. @@ -4483,15 +4608,37 @@ static inline void sched_submit_work(struct task_struct *tsk) blk_schedule_flush_plug(tsk); } +static inline void sched_update_worker(struct task_struct *tsk) +{ + if (tsk_is_pi_blocked(tsk)) + return; + + if (tsk->flags & PF_WQ_WORKER) + wq_worker_running(tsk); +} + asmlinkage void __sched schedule(void) { struct task_struct *tsk = current; sched_submit_work(tsk); __schedule(); + sched_update_worker(tsk); } EXPORT_SYMBOL(schedule); +/** + * schedule_preempt_disabled - called with preemption disabled + * + * Returns with preemption disabled. Note: preempt_count must be 1 + */ +void __sched schedule_preempt_disabled(void) +{ + __preempt_enable_no_resched(); + schedule(); + preempt_disable(); +} + #ifdef CONFIG_MUTEX_SPIN_ON_OWNER static inline bool owner_running(struct mutex *lock, struct task_struct *owner) @@ -4556,7 +4703,16 @@ asmlinkage void __sched notrace preempt_schedule(void) do { add_preempt_count_notrace(PREEMPT_ACTIVE); + /* + * The add/subtract must not be traced by the function + * tracer. But we still want to account for the + * preempt off latency tracer. Since the _notrace versions + * of add/subtract skip the accounting for latency tracer + * we must force it manually. + */ + start_critical_timings(); __schedule(); + stop_critical_timings(); sub_preempt_count_notrace(PREEMPT_ACTIVE); /* @@ -4652,9 +4808,9 @@ EXPORT_SYMBOL(__wake_up); /* * Same as __wake_up but called with the spinlock in wait_queue_head_t held. */ -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr) { - __wake_up_common(q, mode, 1, 0, NULL); + __wake_up_common(q, mode, nr, 0, NULL); } EXPORT_SYMBOL_GPL(__wake_up_locked); @@ -5013,6 +5169,24 @@ void rt_mutex_setprio(struct task_struct *p, int prio) rq = __task_rq_lock(p); + /* + * Idle task boosting is a nono in general. There is one + * exception, when PREEMPT_RT and NOHZ is active: + * + * The idle task calls get_next_timer_interrupt() and holds + * the timer wheel base->lock on the CPU and another CPU wants + * to access the timer (probably to cancel it). We can safely + * ignore the boosting request, as the idle CPU runs this code + * with interrupts disabled and will complete the lock + * protected section without being interrupted. So there is no + * real need to boost. + */ + if (unlikely(p == rq->idle)) { + WARN_ON(p != rq->curr); + WARN_ON(p->pi_blocked_on); + goto out_unlock; + } + trace_sched_pi_setprio(p, prio); oldprio = p->prio; prev_class = p->sched_class; @@ -5036,11 +5210,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio) enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); check_class_changed(rq, p, prev_class, oldprio); +out_unlock: __task_rq_unlock(rq); } - #endif - void set_user_nice(struct task_struct *p, long nice) { int old_prio, delta, on_rq; @@ -5720,7 +5893,7 @@ SYSCALL_DEFINE0(sched_yield) __release(rq->lock); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); do_raw_spin_unlock(&rq->lock); - preempt_enable_no_resched(); + __preempt_enable_no_resched(); schedule(); @@ -5734,9 +5907,17 @@ static inline int should_resched(void) static void __cond_resched(void) { - add_preempt_count(PREEMPT_ACTIVE); - __schedule(); - sub_preempt_count(PREEMPT_ACTIVE); + do { + add_preempt_count(PREEMPT_ACTIVE); + __schedule(); + sub_preempt_count(PREEMPT_ACTIVE); + /* + * Check again in case we missed a preemption + * opportunity between schedule and now. + */ + barrier(); + + } while (need_resched()); } int __sched _cond_resched(void) @@ -5777,6 +5958,7 @@ int __cond_resched_lock(spinlock_t *lock) } EXPORT_SYMBOL(__cond_resched_lock); +#ifndef CONFIG_PREEMPT_RT_FULL int __sched __cond_resched_softirq(void) { BUG_ON(!in_softirq()); @@ -5790,6 +5972,7 @@ int __sched __cond_resched_softirq(void) return 0; } EXPORT_SYMBOL(__cond_resched_softirq); +#endif /** * yield - yield the current processor to other threads. @@ -6168,11 +6351,12 @@ static inline void sched_init_granularity(void) #ifdef CONFIG_SMP void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { - if (p->sched_class && p->sched_class->set_cpus_allowed) - p->sched_class->set_cpus_allowed(p, new_mask); - + if (!migrate_disabled_updated(p)) { + if (p->sched_class && p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, new_mask); + p->rt.nr_cpus_allowed = cpumask_weight(new_mask); + } cpumask_copy(&p->cpus_allowed, new_mask); - p->rt.nr_cpus_allowed = cpumask_weight(new_mask); } /* @@ -6223,7 +6407,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) do_set_cpus_allowed(p, new_mask); /* Can the task run on the task's current CPU? If so, we're done */ - if (cpumask_test_cpu(task_cpu(p), new_mask)) + if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) goto out; dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); @@ -6312,6 +6496,8 @@ static int migration_cpu_stop(void *data) #ifdef CONFIG_HOTPLUG_CPU +static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm); + /* * Ensures that the idle task is using init_mm right before its cpu goes * offline. @@ -6324,7 +6510,12 @@ void idle_task_exit(void) if (mm != &init_mm) switch_mm(mm, &init_mm, current); - mmdrop(mm); + + /* + * Defer the cleanup to an alive cpu. On RT we can neither + * call mmdrop() nor mmdrop_delayed() from here. + */ + per_cpu(idle_last_mm, smp_processor_id()) = mm; } /* @@ -6669,6 +6860,12 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) migrate_nr_uninterruptible(rq); calc_global_load_remove(rq); break; + case CPU_DEAD: + if (per_cpu(idle_last_mm, cpu)) { + mmdrop(per_cpu(idle_last_mm, cpu)); + per_cpu(idle_last_mm, cpu) = NULL; + } + break; #endif } @@ -8375,7 +8572,8 @@ void __init sched_init(void) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP static inline int preempt_count_equals(int preempt_offset) { - int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); + int nested = (preempt_count() & ~PREEMPT_ACTIVE) + + sched_rcu_preempt_depth(); return (nested == preempt_offset); } diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index a6710a112b4f..528032b18655 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -235,6 +235,9 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) P(rt_throttled); PN(rt_time); PN(rt_runtime); +#ifdef CONFIG_SMP + P(rt_nr_migratory); +#endif #undef PN #undef P @@ -484,6 +487,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) P(se.load.weight); P(policy); P(prio); +#ifdef CONFIG_PREEMPT_RT_FULL + P(migrate_disable); +#endif + P(rt.nr_cpus_allowed); #undef PN #undef __PN #undef P diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 8a39fa3e3c6c..3747e53ee6a5 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -2899,6 +2899,10 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, */ if (idle == CPU_NEWLY_IDLE) break; + + if (raw_spin_is_contended(&this_rq->lock) || + raw_spin_is_contended(&busiest->lock)) + break; #endif /* @@ -3039,6 +3043,20 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, rem_load_move -= moved_load; if (rem_load_move < 0) break; + +#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; + + if (raw_spin_is_contended(&this_rq->lock) || + raw_spin_is_contended(&busiest->lock)) + break; +#endif } rcu_read_unlock(); diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 84802245abd2..0007001f995e 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -60,11 +60,15 @@ SCHED_FEAT(OWNER_SPIN, 1) */ SCHED_FEAT(NONTASK_POWER, 1) +#ifndef CONFIG_PREEMPT_RT_FULL /* * Queue remote wakeups on the target CPU and process them * using the scheduler IPI. Reduces rq->lock contention/bounces. */ SCHED_FEAT(TTWU_QUEUE, 1) +#else +SCHED_FEAT(TTWU_QUEUE, 0) +#endif SCHED_FEAT(FORCE_SD_OVERLAP, 0) SCHED_FEAT(RT_RUNTIME_SHARE, 1) diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 583a1368afe6..c27c5ff3203b 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -580,12 +580,9 @@ static inline int balance_runtime(struct rt_rq *rt_rq) static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) { - int i, idle = 1; + int i, idle = 1, throttled = 0; const struct cpumask *span; - if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) - return 1; - span = sched_rt_period_mask(); for_each_cpu(i, span) { int enqueue = 0; @@ -620,12 +617,17 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) if (!rt_rq_throttled(rt_rq)) enqueue = 1; } + if (rt_rq->rt_throttled) + throttled = 1; if (enqueue) sched_rt_rq_enqueue(rt_rq); raw_spin_unlock(&rq->lock); } + if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)) + return 1; + return idle; } @@ -657,8 +659,24 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) return 0; if (rt_rq->rt_time > runtime) { - rt_rq->rt_throttled = 1; - printk_once(KERN_WARNING "sched: RT throttling activated\n"); + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + /* + * Don't actually throttle groups that have no runtime assigned + * but accrue some time due to boosting. + */ + if (likely(rt_b->rt_runtime)) { + rt_rq->rt_throttled = 1; + printk_once(KERN_WARNING "sched: RT throttling activated\n"); + } else { + /* + * In case we did anyway, make it go away, + * replenishment is a joke, since it will replenish us + * with exactly 0 ns. + */ + rt_rq->rt_time = 0; + } + if (rt_rq_throttled(rt_rq)) { sched_rt_rq_dequeue(rt_rq); return 1; @@ -686,7 +704,8 @@ static void update_curr_rt(struct rq *rq) if (unlikely((s64)delta_exec < 0)) delta_exec = 0; - schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec)); + schedstat_set(curr->se.statistics.exec_max, + max(curr->se.statistics.exec_max, delta_exec)); curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); diff --git a/kernel/signal.c b/kernel/signal.c index 206551563cce..194c3667faae 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -344,13 +344,45 @@ static bool task_participate_group_stop(struct task_struct *task) return false; } +#ifdef __HAVE_ARCH_CMPXCHG +static inline struct sigqueue *get_task_cache(struct task_struct *t) +{ + struct sigqueue *q = t->sigqueue_cache; + + if (cmpxchg(&t->sigqueue_cache, q, NULL) != q) + return NULL; + return q; +} + +static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) +{ + if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL) + return 0; + return 1; +} + +#else + +static inline struct sigqueue *get_task_cache(struct task_struct *t) +{ + return NULL; +} + +static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) +{ + return 1; +} + +#endif + /* * allocate a new signal queue record * - this may be called without locks if and only if t == current, otherwise an * appropriate lock must be held to stop the target task from exiting */ static struct sigqueue * -__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit) +__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags, + int override_rlimit, int fromslab) { struct sigqueue *q = NULL; struct user_struct *user; @@ -367,7 +399,10 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi if (override_rlimit || atomic_read(&user->sigpending) <= task_rlimit(t, RLIMIT_SIGPENDING)) { - q = kmem_cache_alloc(sigqueue_cachep, flags); + if (!fromslab) + q = get_task_cache(t); + if (!q) + q = kmem_cache_alloc(sigqueue_cachep, flags); } else { print_dropped_signal(sig); } @@ -384,6 +419,13 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi return q; } +static struct sigqueue * +__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, + int override_rlimit) +{ + return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0); +} + static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) @@ -393,6 +435,21 @@ static void __sigqueue_free(struct sigqueue *q) kmem_cache_free(sigqueue_cachep, q); } +static void sigqueue_free_current(struct sigqueue *q) +{ + struct user_struct *up; + + if (q->flags & SIGQUEUE_PREALLOC) + return; + + up = q->user; + if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) { + atomic_dec(&up->sigpending); + free_uid(up); + } else + __sigqueue_free(q); +} + void flush_sigqueue(struct sigpending *queue) { struct sigqueue *q; @@ -406,6 +463,21 @@ void flush_sigqueue(struct sigpending *queue) } /* + * Called from __exit_signal. Flush tsk->pending and + * tsk->sigqueue_cache + */ +void flush_task_sigqueue(struct task_struct *tsk) +{ + struct sigqueue *q; + + flush_sigqueue(&tsk->pending); + + q = get_task_cache(tsk); + if (q) + kmem_cache_free(sigqueue_cachep, q); +} + +/* * Flush all pending signals for a task. */ void __flush_signals(struct task_struct *t) @@ -554,7 +626,7 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); - __sigqueue_free(first); + sigqueue_free_current(first); } else { /* * Ok, it wasn't in the queue. This must be @@ -600,6 +672,8 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) { int signr; + WARN_ON_ONCE(tsk != current); + /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ @@ -682,6 +756,9 @@ void signal_wake_up(struct task_struct *t, int resume) set_tsk_thread_flag(t, TIF_SIGPENDING); + if (unlikely(t == current)) + return; + /* * For SIGKILL, we want to wake it up in the stopped/traced/killable * case. We don't check t->state here because there is a race with it @@ -1252,12 +1329,12 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, struct sighand_struct *sighand; for (;;) { - local_irq_save(*flags); + local_irq_save_nort(*flags); rcu_read_lock(); sighand = rcu_dereference(tsk->sighand); if (unlikely(sighand == NULL)) { rcu_read_unlock(); - local_irq_restore(*flags); + local_irq_restore_nort(*flags); break; } @@ -1268,7 +1345,7 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, } spin_unlock(&sighand->siglock); rcu_read_unlock(); - local_irq_restore(*flags); + local_irq_restore_nort(*flags); } return sighand; @@ -1515,7 +1592,8 @@ EXPORT_SYMBOL(kill_pid); */ struct sigqueue *sigqueue_alloc(void) { - struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0); + /* Preallocated sigqueue objects always from the slabcache ! */ + struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1); if (q) q->flags |= SIGQUEUE_PREALLOC; @@ -1857,15 +1935,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) if (gstop_done && ptrace_reparented(current)) do_notify_parent_cldstop(current, false, why); - /* - * Don't want to allow preemption here, because - * sys_ptrace() needs this task to be inactive. - * - * XXX: implement read_unlock_no_resched(). - */ - preempt_disable(); read_unlock(&tasklist_lock); - preempt_enable_no_resched(); schedule(); } else { /* diff --git a/kernel/softirq.c b/kernel/softirq.c index 2c71d91efff0..85bcdc534d16 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -21,9 +21,11 @@ #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/rcupdate.h> +#include <linux/delay.h> #include <linux/ftrace.h> #include <linux/smp.h> #include <linux/tick.h> +#include <linux/locallock.h> #define CREATE_TRACE_POINTS #include <trace/events/irq.h> @@ -61,6 +63,67 @@ char *softirq_to_name[NR_SOFTIRQS] = { "TASKLET", "SCHED", "HRTIMER", "RCU" }; +#ifdef CONFIG_NO_HZ +# ifdef CONFIG_PREEMPT_RT_FULL +/* + * On preempt-rt a softirq might be blocked on a lock. There might be + * no other runnable task on this CPU because the lock owner runs on + * some other CPU. So we have to go into idle with the pending bit + * set. Therefor we need to check this otherwise we warn about false + * positives which confuses users and defeats the whole purpose of + * this test. + * + * This code is called with interrupts disabled. + */ +void softirq_check_pending_idle(void) +{ + static int rate_limit; + u32 warnpending = 0, pending = local_softirq_pending(); + + if (rate_limit >= 10) + return; + + if (pending) { + struct task_struct *tsk; + + tsk = __get_cpu_var(ksoftirqd); + /* + * The wakeup code in rtmutex.c wakes up the task + * _before_ it sets pi_blocked_on to NULL under + * tsk->pi_lock. So we need to check for both: state + * and pi_blocked_on. + */ + raw_spin_lock(&tsk->pi_lock); + + if (!tsk->pi_blocked_on && !(tsk->state == TASK_RUNNING)) + warnpending = 1; + + raw_spin_unlock(&tsk->pi_lock); + } + + if (warnpending) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + pending); + rate_limit++; + } +} +# else +/* + * On !PREEMPT_RT we just printk rate limited: + */ +void softirq_check_pending_idle(void) +{ + static int rate_limit; + + if (rate_limit < 10) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + local_softirq_pending()); + rate_limit++; + } +} +# endif +#endif + /* * we cannot loop indefinitely here to avoid userspace starvation, * but we also don't want to introduce a worst case 1/HZ latency @@ -76,6 +139,36 @@ static void wakeup_softirqd(void) wake_up_process(tsk); } +static void handle_pending_softirqs(u32 pending, int cpu, int need_rcu_bh_qs) +{ + struct softirq_action *h = softirq_vec; + unsigned int prev_count = preempt_count(); + + local_irq_enable(); + for ( ; pending; h++, pending >>= 1) { + unsigned int vec_nr = h - softirq_vec; + + if (!(pending & 1)) + continue; + + kstat_incr_softirqs_this_cpu(vec_nr); + trace_softirq_entry(vec_nr); + h->action(h); + trace_softirq_exit(vec_nr); + if (unlikely(prev_count != preempt_count())) { + printk(KERN_ERR + "huh, entered softirq %u %s %p with preempt_count %08x exited with %08x?\n", + vec_nr, softirq_to_name[vec_nr], h->action, + prev_count, (unsigned int) preempt_count()); + preempt_count() = prev_count; + } + if (need_rcu_bh_qs) + rcu_bh_qs(cpu); + } + local_irq_disable(); +} + +#ifndef CONFIG_PREEMPT_RT_FULL /* * preempt_count and SOFTIRQ_OFFSET usage: * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving @@ -206,7 +299,6 @@ EXPORT_SYMBOL(local_bh_enable_ip); asmlinkage void __do_softirq(void) { - struct softirq_action *h; __u32 pending; int max_restart = MAX_SOFTIRQ_RESTART; int cpu; @@ -215,7 +307,7 @@ asmlinkage void __do_softirq(void) account_system_vtime(current); __local_bh_disable((unsigned long)__builtin_return_address(0), - SOFTIRQ_OFFSET); + SOFTIRQ_OFFSET); lockdep_softirq_enter(); cpu = smp_processor_id(); @@ -223,36 +315,7 @@ restart: /* Reset the pending bitmask before enabling irqs */ set_softirq_pending(0); - local_irq_enable(); - - h = softirq_vec; - - do { - if (pending & 1) { - unsigned int vec_nr = h - softirq_vec; - int prev_count = preempt_count(); - - kstat_incr_softirqs_this_cpu(vec_nr); - - trace_softirq_entry(vec_nr); - h->action(h); - trace_softirq_exit(vec_nr); - if (unlikely(prev_count != preempt_count())) { - printk(KERN_ERR "huh, entered softirq %u %s %p" - "with preempt_count %08x," - " exited with %08x?\n", vec_nr, - softirq_to_name[vec_nr], h->action, - prev_count, preempt_count()); - preempt_count() = prev_count; - } - - rcu_bh_qs(cpu); - } - h++; - pending >>= 1; - } while (pending); - - local_irq_disable(); + handle_pending_softirqs(pending, cpu, 1); pending = local_softirq_pending(); if (pending && --max_restart) @@ -267,6 +330,26 @@ restart: __local_bh_enable(SOFTIRQ_OFFSET); } +/* + * Called with preemption disabled from run_ksoftirqd() + */ +static int ksoftirqd_do_softirq(int cpu) +{ + /* + * Preempt disable stops cpu going offline. + * If already offline, we'll be on wrong CPU: + * don't process. + */ + if (cpu_is_offline(cpu)) + return -1; + + local_irq_disable(); + if (local_softirq_pending()) + __do_softirq(); + local_irq_enable(); + return 0; +} + #ifndef __ARCH_HAS_DO_SOFTIRQ asmlinkage void do_softirq(void) @@ -289,6 +372,184 @@ asmlinkage void do_softirq(void) #endif +static inline void local_bh_disable_nort(void) { local_bh_disable(); } +static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } +static inline void ksoftirqd_set_sched_params(void) { } +static inline void ksoftirqd_clr_sched_params(void) { } + +#else /* !PREEMPT_RT_FULL */ + +/* + * On RT we serialize softirq execution with a cpu local lock + */ +static DEFINE_LOCAL_IRQ_LOCK(local_softirq_lock); +static DEFINE_PER_CPU(struct task_struct *, local_softirq_runner); + +static void __do_softirq_common(int need_rcu_bh_qs); + +void __do_softirq(void) +{ + __do_softirq_common(0); +} + +void __init softirq_early_init(void) +{ + local_irq_lock_init(local_softirq_lock); +} + +void local_bh_disable(void) +{ + migrate_disable(); + current->softirq_nestcnt++; +} +EXPORT_SYMBOL(local_bh_disable); + +void local_bh_enable(void) +{ + if (WARN_ON(current->softirq_nestcnt == 0)) + return; + + if ((current->softirq_nestcnt == 1) && + local_softirq_pending() && + local_trylock(local_softirq_lock)) { + + local_irq_disable(); + if (local_softirq_pending()) + __do_softirq(); + local_irq_enable(); + local_unlock(local_softirq_lock); + WARN_ON(current->softirq_nestcnt != 1); + } + current->softirq_nestcnt--; + migrate_enable(); +} +EXPORT_SYMBOL(local_bh_enable); + +void local_bh_enable_ip(unsigned long ip) +{ + local_bh_enable(); +} +EXPORT_SYMBOL(local_bh_enable_ip); + +/* For tracing */ +int notrace __in_softirq(void) +{ + if (__get_cpu_var(local_softirq_lock).owner == current) + return __get_cpu_var(local_softirq_lock).nestcnt; + return 0; +} + +int in_serving_softirq(void) +{ + int res; + + preempt_disable(); + res = __get_cpu_var(local_softirq_runner) == current; + preempt_enable(); + return res; +} +EXPORT_SYMBOL(in_serving_softirq); + +/* + * Called with bh and local interrupts disabled. For full RT cpu must + * be pinned. + */ +static void __do_softirq_common(int need_rcu_bh_qs) +{ + u32 pending = local_softirq_pending(); + int cpu = smp_processor_id(); + + current->softirq_nestcnt++; + + /* Reset the pending bitmask before enabling irqs */ + set_softirq_pending(0); + + __get_cpu_var(local_softirq_runner) = current; + + lockdep_softirq_enter(); + + handle_pending_softirqs(pending, cpu, need_rcu_bh_qs); + + pending = local_softirq_pending(); + if (pending) + wakeup_softirqd(); + + lockdep_softirq_exit(); + __get_cpu_var(local_softirq_runner) = NULL; + + current->softirq_nestcnt--; +} + +static int __thread_do_softirq(int cpu) +{ + /* + * Prevent the current cpu from going offline. + * pin_current_cpu() can reenable preemption and block on the + * hotplug mutex. When it returns, the current cpu is + * pinned. It might be the wrong one, but the offline check + * below catches that. + */ + pin_current_cpu(); + /* + * If called from ksoftirqd (cpu >= 0) we need to check + * whether we are on the wrong cpu due to cpu offlining. If + * called via thread_do_softirq() no action required. + */ + if (cpu >= 0 && cpu_is_offline(cpu)) { + unpin_current_cpu(); + return -1; + } + preempt_enable(); + local_lock(local_softirq_lock); + local_irq_disable(); + /* + * We cannot switch stacks on RT as we want to be able to + * schedule! + */ + if (local_softirq_pending()) + __do_softirq_common(cpu >= 0); + local_unlock(local_softirq_lock); + unpin_current_cpu(); + preempt_disable(); + local_irq_enable(); + return 0; +} + +/* + * Called from netif_rx_ni(). Preemption enabled. + */ +void thread_do_softirq(void) +{ + if (!in_serving_softirq()) { + preempt_disable(); + __thread_do_softirq(-1); + preempt_enable(); + } +} + +static int ksoftirqd_do_softirq(int cpu) +{ + return __thread_do_softirq(cpu); +} + +static inline void local_bh_disable_nort(void) { } +static inline void _local_bh_enable_nort(void) { } + +static inline void ksoftirqd_set_sched_params(void) +{ + struct sched_param param = { .sched_priority = 1 }; + + sched_setscheduler(current, SCHED_FIFO, ¶m); +} + +static inline void ksoftirqd_clr_sched_params(void) +{ + struct sched_param param = { .sched_priority = 0 }; + + sched_setscheduler(current, SCHED_NORMAL, ¶m); +} + +#endif /* PREEMPT_RT_FULL */ /* * Enter an interrupt context. */ @@ -302,9 +563,9 @@ void irq_enter(void) * Prevent raise_softirq from needlessly waking up ksoftirqd * here, as softirq will be serviced on return from interrupt. */ - local_bh_disable(); + local_bh_disable_nort(); tick_check_idle(cpu); - _local_bh_enable(); + _local_bh_enable_nort(); } __irq_enter(); @@ -313,6 +574,7 @@ void irq_enter(void) #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED static inline void invoke_softirq(void) { +#ifndef CONFIG_PREEMPT_RT_FULL if (!force_irqthreads) __do_softirq(); else { @@ -321,10 +583,14 @@ static inline void invoke_softirq(void) wakeup_softirqd(); __local_bh_enable(SOFTIRQ_OFFSET); } +#else + wakeup_softirqd(); +#endif } #else static inline void invoke_softirq(void) { +#ifndef CONFIG_PREEMPT_RT_FULL if (!force_irqthreads) do_softirq(); else { @@ -333,6 +599,9 @@ static inline void invoke_softirq(void) wakeup_softirqd(); __local_bh_enable(SOFTIRQ_OFFSET); } +#else + wakeup_softirqd(); +#endif } #endif @@ -353,7 +622,7 @@ void irq_exit(void) if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched()) tick_nohz_stop_sched_tick(0); #endif - preempt_enable_no_resched(); + __preempt_enable_no_resched(); } /* @@ -402,15 +671,45 @@ struct tasklet_head static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec); static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec); +static void inline +__tasklet_common_schedule(struct tasklet_struct *t, struct tasklet_head *head, unsigned int nr) +{ + if (tasklet_trylock(t)) { +again: + /* We may have been preempted before tasklet_trylock + * and __tasklet_action may have already run. + * So double check the sched bit while the takslet + * is locked before adding it to the list. + */ + if (test_bit(TASKLET_STATE_SCHED, &t->state)) { + t->next = NULL; + *head->tail = t; + head->tail = &(t->next); + raise_softirq_irqoff(nr); + tasklet_unlock(t); + } else { + /* This is subtle. If we hit the corner case above + * It is possible that we get preempted right here, + * and another task has successfully called + * tasklet_schedule(), then this function, and + * failed on the trylock. Thus we must be sure + * before releasing the tasklet lock, that the + * SCHED_BIT is clear. Otherwise the tasklet + * may get its SCHED_BIT set, but not added to the + * list + */ + if (!tasklet_tryunlock(t)) + goto again; + } + } +} + void __tasklet_schedule(struct tasklet_struct *t) { unsigned long flags; local_irq_save(flags); - t->next = NULL; - *__this_cpu_read(tasklet_vec.tail) = t; - __this_cpu_write(tasklet_vec.tail, &(t->next)); - raise_softirq_irqoff(TASKLET_SOFTIRQ); + __tasklet_common_schedule(t, &__get_cpu_var(tasklet_vec), TASKLET_SOFTIRQ); local_irq_restore(flags); } @@ -421,10 +720,7 @@ void __tasklet_hi_schedule(struct tasklet_struct *t) unsigned long flags; local_irq_save(flags); - t->next = NULL; - *__this_cpu_read(tasklet_hi_vec.tail) = t; - __this_cpu_write(tasklet_hi_vec.tail, &(t->next)); - raise_softirq_irqoff(HI_SOFTIRQ); + __tasklet_common_schedule(t, &__get_cpu_var(tasklet_hi_vec), HI_SOFTIRQ); local_irq_restore(flags); } @@ -432,50 +728,119 @@ EXPORT_SYMBOL(__tasklet_hi_schedule); void __tasklet_hi_schedule_first(struct tasklet_struct *t) { - BUG_ON(!irqs_disabled()); - - t->next = __this_cpu_read(tasklet_hi_vec.head); - __this_cpu_write(tasklet_hi_vec.head, t); - __raise_softirq_irqoff(HI_SOFTIRQ); + __tasklet_hi_schedule(t); } EXPORT_SYMBOL(__tasklet_hi_schedule_first); -static void tasklet_action(struct softirq_action *a) +void tasklet_enable(struct tasklet_struct *t) { - struct tasklet_struct *list; + if (!atomic_dec_and_test(&t->count)) + return; + if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) + tasklet_schedule(t); +} - local_irq_disable(); - list = __this_cpu_read(tasklet_vec.head); - __this_cpu_write(tasklet_vec.head, NULL); - __this_cpu_write(tasklet_vec.tail, &__get_cpu_var(tasklet_vec).head); - local_irq_enable(); +EXPORT_SYMBOL(tasklet_enable); + +void tasklet_hi_enable(struct tasklet_struct *t) +{ + if (!atomic_dec_and_test(&t->count)) + return; + if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) + tasklet_hi_schedule(t); +} + +EXPORT_SYMBOL(tasklet_hi_enable); + +static void +__tasklet_action(struct softirq_action *a, struct tasklet_struct *list) +{ + int loops = 1000000; while (list) { struct tasklet_struct *t = list; list = list->next; - if (tasklet_trylock(t)) { - if (!atomic_read(&t->count)) { - if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) - BUG(); - t->func(t->data); - tasklet_unlock(t); - continue; - } - tasklet_unlock(t); + /* + * Should always succeed - after a tasklist got on the + * list (after getting the SCHED bit set from 0 to 1), + * nothing but the tasklet softirq it got queued to can + * lock it: + */ + if (!tasklet_trylock(t)) { + WARN_ON(1); + continue; } - local_irq_disable(); t->next = NULL; - *__this_cpu_read(tasklet_vec.tail) = t; - __this_cpu_write(tasklet_vec.tail, &(t->next)); - __raise_softirq_irqoff(TASKLET_SOFTIRQ); - local_irq_enable(); + + /* + * If we cannot handle the tasklet because it's disabled, + * mark it as pending. tasklet_enable() will later + * re-schedule the tasklet. + */ + if (unlikely(atomic_read(&t->count))) { +out_disabled: + /* implicit unlock: */ + wmb(); + t->state = TASKLET_STATEF_PENDING; + continue; + } + + /* + * After this point on the tasklet might be rescheduled + * on another CPU, but it can only be added to another + * CPU's tasklet list if we unlock the tasklet (which we + * dont do yet). + */ + if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) + WARN_ON(1); + +again: + t->func(t->data); + + /* + * Try to unlock the tasklet. We must use cmpxchg, because + * another CPU might have scheduled or disabled the tasklet. + * We only allow the STATE_RUN -> 0 transition here. + */ + while (!tasklet_tryunlock(t)) { + /* + * If it got disabled meanwhile, bail out: + */ + if (atomic_read(&t->count)) + goto out_disabled; + /* + * If it got scheduled meanwhile, re-execute + * the tasklet function: + */ + if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) + goto again; + if (!--loops) { + printk("hm, tasklet state: %08lx\n", t->state); + WARN_ON(1); + tasklet_unlock(t); + break; + } + } } } +static void tasklet_action(struct softirq_action *a) +{ + struct tasklet_struct *list; + + local_irq_disable(); + list = __get_cpu_var(tasklet_vec).head; + __get_cpu_var(tasklet_vec).head = NULL; + __get_cpu_var(tasklet_vec).tail = &__get_cpu_var(tasklet_vec).head; + local_irq_enable(); + + __tasklet_action(a, list); +} + static void tasklet_hi_action(struct softirq_action *a) { struct tasklet_struct *list; @@ -486,29 +851,7 @@ static void tasklet_hi_action(struct softirq_action *a) __this_cpu_write(tasklet_hi_vec.tail, &__get_cpu_var(tasklet_hi_vec).head); local_irq_enable(); - while (list) { - struct tasklet_struct *t = list; - - list = list->next; - - if (tasklet_trylock(t)) { - if (!atomic_read(&t->count)) { - if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) - BUG(); - t->func(t->data); - tasklet_unlock(t); - continue; - } - tasklet_unlock(t); - } - - local_irq_disable(); - t->next = NULL; - *__this_cpu_read(tasklet_hi_vec.tail) = t; - __this_cpu_write(tasklet_hi_vec.tail, &(t->next)); - __raise_softirq_irqoff(HI_SOFTIRQ); - local_irq_enable(); - } + __tasklet_action(a, list); } @@ -531,7 +874,7 @@ void tasklet_kill(struct tasklet_struct *t) while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { do { - yield(); + msleep(1); } while (test_bit(TASKLET_STATE_SCHED, &t->state)); } tasklet_unlock_wait(t); @@ -737,31 +1080,40 @@ void __init softirq_init(void) open_softirq(HI_SOFTIRQ, tasklet_hi_action); } +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) +void tasklet_unlock_wait(struct tasklet_struct *t) +{ + while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { + /* + * Hack for now to avoid this busy-loop: + */ +#ifdef CONFIG_PREEMPT_RT_FULL + msleep(1); +#else + barrier(); +#endif + } +} +EXPORT_SYMBOL(tasklet_unlock_wait); +#endif + static int run_ksoftirqd(void * __bind_cpu) { + ksoftirqd_set_sched_params(); + set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { preempt_disable(); - if (!local_softirq_pending()) { - preempt_enable_no_resched(); - schedule(); - preempt_disable(); - } + if (!local_softirq_pending()) + schedule_preempt_disabled(); __set_current_state(TASK_RUNNING); while (local_softirq_pending()) { - /* Preempt disable stops cpu going offline. - If already offline, we'll be on wrong CPU: - don't process */ - if (cpu_is_offline((long)__bind_cpu)) + if (ksoftirqd_do_softirq((long) __bind_cpu)) goto wait_to_die; - local_irq_disable(); - if (local_softirq_pending()) - __do_softirq(); - local_irq_enable(); - preempt_enable_no_resched(); + __preempt_enable_no_resched(); cond_resched(); preempt_disable(); rcu_note_context_switch((long)__bind_cpu); @@ -774,6 +1126,7 @@ static int run_ksoftirqd(void * __bind_cpu) wait_to_die: preempt_enable(); + ksoftirqd_clr_sched_params(); /* Wait for kthread_stop */ set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { @@ -850,9 +1203,8 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb, int hotcpu = (unsigned long)hcpu; struct task_struct *p; - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: p = kthread_create_on_node(run_ksoftirqd, hcpu, cpu_to_node(hotcpu), @@ -865,19 +1217,16 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb, per_cpu(ksoftirqd, hotcpu) = p; break; case CPU_ONLINE: - case CPU_ONLINE_FROZEN: wake_up_process(per_cpu(ksoftirqd, hotcpu)); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: if (!per_cpu(ksoftirqd, hotcpu)) break; /* Unbind so it can run. Fall thru. */ kthread_bind(per_cpu(ksoftirqd, hotcpu), cpumask_any(cpu_online_mask)); - case CPU_DEAD: - case CPU_DEAD_FROZEN: { + case CPU_POST_DEAD: { static const struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; diff --git a/kernel/spinlock.c b/kernel/spinlock.c index 84c7d96918bf..47fd3cf03a8e 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -110,8 +110,11 @@ void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock) \ * __[spin|read|write]_lock_bh() */ BUILD_LOCK_OPS(spin, raw_spinlock); + +#ifndef CONFIG_PREEMPT_RT_FULL BUILD_LOCK_OPS(read, rwlock); BUILD_LOCK_OPS(write, rwlock); +#endif #endif @@ -195,6 +198,8 @@ void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock) EXPORT_SYMBOL(_raw_spin_unlock_bh); #endif +#ifndef CONFIG_PREEMPT_RT_FULL + #ifndef CONFIG_INLINE_READ_TRYLOCK int __lockfunc _raw_read_trylock(rwlock_t *lock) { @@ -339,6 +344,8 @@ void __lockfunc _raw_write_unlock_bh(rwlock_t *lock) EXPORT_SYMBOL(_raw_write_unlock_bh); #endif +#endif /* !PREEMPT_RT_FULL */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 2f194e965715..561ba3a7b8cf 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -29,12 +29,12 @@ struct cpu_stop_done { atomic_t nr_todo; /* nr left to execute */ bool executed; /* actually executed? */ int ret; /* collected return value */ - struct completion completion; /* fired if nr_todo reaches 0 */ + struct task_struct *waiter; /* woken when nr_todo reaches 0 */ }; /* the actual stopper, one per every possible cpu, enabled on online cpus */ struct cpu_stopper { - spinlock_t lock; + raw_spinlock_t lock; bool enabled; /* is this stopper enabled? */ struct list_head works; /* list of pending works */ struct task_struct *thread; /* stopper thread */ @@ -47,7 +47,7 @@ static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo) { memset(done, 0, sizeof(*done)); atomic_set(&done->nr_todo, nr_todo); - init_completion(&done->completion); + done->waiter = current; } /* signal completion unless @done is NULL */ @@ -56,8 +56,10 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed) if (done) { if (executed) done->executed = true; - if (atomic_dec_and_test(&done->nr_todo)) - complete(&done->completion); + if (atomic_dec_and_test(&done->nr_todo)) { + wake_up_process(done->waiter); + done->waiter = NULL; + } } } @@ -67,7 +69,7 @@ static void cpu_stop_queue_work(struct cpu_stopper *stopper, { unsigned long flags; - spin_lock_irqsave(&stopper->lock, flags); + raw_spin_lock_irqsave(&stopper->lock, flags); if (stopper->enabled) { list_add_tail(&work->list, &stopper->works); @@ -75,7 +77,23 @@ static void cpu_stop_queue_work(struct cpu_stopper *stopper, } else cpu_stop_signal_done(work->done, false); - spin_unlock_irqrestore(&stopper->lock, flags); + raw_spin_unlock_irqrestore(&stopper->lock, flags); +} + +static void wait_for_stop_done(struct cpu_stop_done *done) +{ + set_current_state(TASK_UNINTERRUPTIBLE); + while (atomic_read(&done->nr_todo)) { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + /* + * We need to wait until cpu_stop_signal_done() has cleared + * done->waiter. + */ + while (done->waiter) + cpu_relax(); + set_current_state(TASK_RUNNING); } /** @@ -109,7 +127,7 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg) cpu_stop_init_done(&done, 1); cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), &work); - wait_for_completion(&done.completion); + wait_for_stop_done(&done); return done.executed ? done.ret : -ENOENT; } @@ -135,6 +153,7 @@ void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, /* static data for stop_cpus */ static DEFINE_MUTEX(stop_cpus_mutex); +static DEFINE_MUTEX(stopper_lock); static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work); static void queue_stop_cpus_work(const struct cpumask *cpumask, @@ -153,15 +172,14 @@ static void queue_stop_cpus_work(const struct cpumask *cpumask, } /* - * Disable preemption while queueing to avoid getting - * preempted by a stopper which might wait for other stoppers - * to enter @fn which can lead to deadlock. + * Make sure that all work is queued on all cpus before we + * any of the cpus can execute it. */ - preempt_disable(); + mutex_lock(&stopper_lock); for_each_cpu(cpu, cpumask) cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), &per_cpu(stop_cpus_work, cpu)); - preempt_enable(); + mutex_unlock(&stopper_lock); } static int __stop_cpus(const struct cpumask *cpumask, @@ -171,7 +189,7 @@ static int __stop_cpus(const struct cpumask *cpumask, cpu_stop_init_done(&done, cpumask_weight(cpumask)); queue_stop_cpus_work(cpumask, fn, arg, &done); - wait_for_completion(&done.completion); + wait_for_stop_done(&done); return done.executed ? done.ret : -ENOENT; } @@ -259,13 +277,13 @@ repeat: } work = NULL; - spin_lock_irq(&stopper->lock); + raw_spin_lock_irq(&stopper->lock); if (!list_empty(&stopper->works)) { work = list_first_entry(&stopper->works, struct cpu_stop_work, list); list_del_init(&work->list); } - spin_unlock_irq(&stopper->lock); + raw_spin_unlock_irq(&stopper->lock); if (work) { cpu_stop_fn_t fn = work->fn; @@ -275,6 +293,16 @@ repeat: __set_current_state(TASK_RUNNING); + /* + * Wait until the stopper finished scheduling on all + * cpus + */ + mutex_lock(&stopper_lock); + /* + * Let other cpu threads continue as well + */ + mutex_unlock(&stopper_lock); + /* cpu stop callbacks are not allowed to sleep */ preempt_disable(); @@ -289,7 +317,13 @@ repeat: kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL, ksym_buf), arg); + /* + * Make sure that the wakeup and setting done->waiter + * to NULL is atomic. + */ + local_irq_disable(); cpu_stop_signal_done(done, true); + local_irq_enable(); } else schedule(); @@ -317,6 +351,7 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb, if (IS_ERR(p)) return notifier_from_errno(PTR_ERR(p)); get_task_struct(p); + p->flags |= PF_STOMPER; kthread_bind(p, cpu); sched_set_stop_task(cpu, p); stopper->thread = p; @@ -326,9 +361,9 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb, /* strictly unnecessary, as first user will wake it */ wake_up_process(stopper->thread); /* mark enabled */ - spin_lock_irq(&stopper->lock); + raw_spin_lock_irq(&stopper->lock); stopper->enabled = true; - spin_unlock_irq(&stopper->lock); + raw_spin_unlock_irq(&stopper->lock); break; #ifdef CONFIG_HOTPLUG_CPU @@ -341,11 +376,11 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb, /* kill the stopper */ kthread_stop(stopper->thread); /* drain remaining works */ - spin_lock_irq(&stopper->lock); + raw_spin_lock_irq(&stopper->lock); list_for_each_entry(work, &stopper->works, list) cpu_stop_signal_done(work->done, false); stopper->enabled = false; - spin_unlock_irq(&stopper->lock); + raw_spin_unlock_irq(&stopper->lock); /* release the stopper */ put_task_struct(stopper->thread); stopper->thread = NULL; @@ -376,7 +411,7 @@ static int __init cpu_stop_init(void) for_each_possible_cpu(cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); - spin_lock_init(&stopper->lock); + raw_spin_lock_init(&stopper->lock); INIT_LIST_HEAD(&stopper->works); } @@ -570,7 +605,7 @@ int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data, ret = stop_machine_cpu_stop(&smdata); /* Busy wait for completion. */ - while (!completion_done(&done.completion)) + while (atomic_read(&done.nr_todo)) cpu_relax(); mutex_unlock(&stop_cpus_mutex); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index f6117a4c7cb8..b510ba954fe1 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -358,7 +358,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) { enum hrtimer_restart res = HRTIMER_NORESTART; - write_seqlock(&xtime_lock); + raw_write_seqlock(&xtime_lock); switch (time_state) { case TIME_OK: @@ -388,7 +388,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) break; } - write_sequnlock(&xtime_lock); + raw_write_sequnlock(&xtime_lock); return res; } @@ -663,7 +663,7 @@ int do_adjtimex(struct timex *txc) getnstimeofday(&ts); - write_seqlock_irq(&xtime_lock); + raw_write_seqlock_irq(&xtime_lock); if (txc->modes & ADJ_ADJTIME) { long save_adjust = time_adjust; @@ -705,7 +705,7 @@ int do_adjtimex(struct timex *txc) /* fill PPS status fields */ pps_fill_timex(txc); - write_sequnlock_irq(&xtime_lock); + raw_write_sequnlock_irq(&xtime_lock); txc->time.tv_sec = ts.tv_sec; txc->time.tv_usec = ts.tv_nsec; @@ -903,7 +903,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) pts_norm = pps_normalize_ts(*phase_ts); - write_seqlock_irqsave(&xtime_lock, flags); + raw_write_seqlock_irqsave(&xtime_lock, flags); /* clear the error bits, they will be set again if needed */ time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR); @@ -916,7 +916,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) * just start the frequency interval */ if (unlikely(pps_fbase.tv_sec == 0)) { pps_fbase = *raw_ts; - write_sequnlock_irqrestore(&xtime_lock, flags); + raw_write_sequnlock_irqrestore(&xtime_lock, flags); return; } @@ -931,7 +931,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) time_status |= STA_PPSJITTER; /* restart the frequency calibration interval */ pps_fbase = *raw_ts; - write_sequnlock_irqrestore(&xtime_lock, flags); + raw_write_sequnlock_irqrestore(&xtime_lock, flags); pr_err("hardpps: PPSJITTER: bad pulse\n"); return; } @@ -948,7 +948,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) hardpps_update_phase(pts_norm.nsec); - write_sequnlock_irqrestore(&xtime_lock, flags); + raw_write_sequnlock_irqrestore(&xtime_lock, flags); } EXPORT_SYMBOL(hardpps); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index da6c9ecad4e4..c443a8fb87dc 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -63,13 +63,13 @@ int tick_is_oneshot_available(void) static void tick_periodic(int cpu) { if (tick_do_timer_cpu == cpu) { - write_seqlock(&xtime_lock); + raw_write_seqlock(&xtime_lock); /* Keep track of the next tick event */ tick_next_period = ktime_add(tick_next_period, tick_period); do_timer(1); - write_sequnlock(&xtime_lock); + raw_write_sequnlock(&xtime_lock); } update_process_times(user_mode(get_irq_regs())); diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 4e265b901fed..ea6b7ae2a893 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -141,4 +141,4 @@ static inline int tick_device_is_functional(struct clock_event_device *dev) #endif extern void do_timer(unsigned long ticks); -extern seqlock_t xtime_lock; +extern raw_seqlock_t xtime_lock; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 40420644d0ba..57315c5780be 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -56,7 +56,7 @@ static void tick_do_update_jiffies64(ktime_t now) return; /* Reevalute with xtime_lock held */ - write_seqlock(&xtime_lock); + raw_write_seqlock(&xtime_lock); delta = ktime_sub(now, last_jiffies_update); if (delta.tv64 >= tick_period.tv64) { @@ -79,7 +79,7 @@ static void tick_do_update_jiffies64(ktime_t now) /* Keep the tick_next_period variable up to date */ tick_next_period = ktime_add(last_jiffies_update, tick_period); } - write_sequnlock(&xtime_lock); + raw_write_sequnlock(&xtime_lock); } /* @@ -89,12 +89,12 @@ static ktime_t tick_init_jiffy_update(void) { ktime_t period; - write_seqlock(&xtime_lock); + raw_write_seqlock(&xtime_lock); /* Did we start the jiffies update yet ? */ if (last_jiffies_update.tv64 == 0) last_jiffies_update = tick_next_period; period = last_jiffies_update; - write_sequnlock(&xtime_lock); + raw_write_sequnlock(&xtime_lock); return period; } @@ -332,13 +332,7 @@ void tick_nohz_stop_sched_tick(int inidle) goto end; if (unlikely(local_softirq_pending() && cpu_online(cpu))) { - static int ratelimit; - - if (ratelimit < 10) { - printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", - (unsigned int) local_softirq_pending()); - ratelimit++; - } + softirq_check_pending_idle(); goto end; } @@ -798,6 +792,7 @@ void tick_setup_sched_timer(void) * Emulate tick processing via per-CPU hrtimers: */ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + ts->sched_timer.irqsafe = 1; ts->sched_timer.function = tick_sched_timer; /* Get the next period (per cpu) */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 237841378c03..22fd69e211eb 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -139,8 +139,7 @@ static inline s64 timekeeping_get_ns_raw(void) * This read-write spinlock protects us from races in SMP while * playing with xtime. */ -__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); - +__cacheline_aligned_in_smp DEFINE_RAW_SEQLOCK(xtime_lock); /* * The current time @@ -365,7 +364,7 @@ int do_settimeofday(const struct timespec *tv) if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) return -EINVAL; - write_seqlock_irqsave(&xtime_lock, flags); + raw_write_seqlock_irqsave(&xtime_lock, flags); timekeeping_forward_now(); @@ -381,7 +380,7 @@ int do_settimeofday(const struct timespec *tv) update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, timekeeper.mult); - write_sequnlock_irqrestore(&xtime_lock, flags); + raw_write_sequnlock_irqrestore(&xtime_lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -405,7 +404,7 @@ int timekeeping_inject_offset(struct timespec *ts) if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; - write_seqlock_irqsave(&xtime_lock, flags); + raw_write_seqlock_irqsave(&xtime_lock, flags); timekeeping_forward_now(); @@ -418,7 +417,7 @@ int timekeeping_inject_offset(struct timespec *ts) update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, timekeeper.mult); - write_sequnlock_irqrestore(&xtime_lock, flags); + raw_write_sequnlock_irqrestore(&xtime_lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -572,7 +571,7 @@ void __init timekeeping_init(void) read_persistent_clock(&now); read_boot_clock(&boot); - write_seqlock_irqsave(&xtime_lock, flags); + raw_write_seqlock_irqsave(&xtime_lock, flags); ntp_init(); @@ -593,7 +592,7 @@ void __init timekeeping_init(void) -boot.tv_sec, -boot.tv_nsec); total_sleep_time.tv_sec = 0; total_sleep_time.tv_nsec = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); + raw_write_sequnlock_irqrestore(&xtime_lock, flags); } /* time in seconds when suspend began */ @@ -640,7 +639,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta) if (!(ts.tv_sec == 0 && ts.tv_nsec == 0)) return; - write_seqlock_irqsave(&xtime_lock, flags); + raw_write_seqlock_irqsave(&xtime_lock, flags); timekeeping_forward_now(); __timekeeping_inject_sleeptime(delta); @@ -650,7 +649,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta) update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, timekeeper.mult); - write_sequnlock_irqrestore(&xtime_lock, flags); + raw_write_sequnlock_irqrestore(&xtime_lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -673,7 +672,7 @@ static void timekeeping_resume(void) clocksource_resume(); - write_seqlock_irqsave(&xtime_lock, flags); + raw_write_seqlock_irqsave(&xtime_lock, flags); if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) { ts = timespec_sub(ts, timekeeping_suspend_time); @@ -683,7 +682,7 @@ static void timekeeping_resume(void) timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock); timekeeper.ntp_error = 0; timekeeping_suspended = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); + raw_write_sequnlock_irqrestore(&xtime_lock, flags); touch_softlockup_watchdog(); @@ -701,7 +700,7 @@ static int timekeeping_suspend(void) read_persistent_clock(&timekeeping_suspend_time); - write_seqlock_irqsave(&xtime_lock, flags); + raw_write_seqlock_irqsave(&xtime_lock, flags); timekeeping_forward_now(); timekeeping_suspended = 1; @@ -724,7 +723,7 @@ static int timekeeping_suspend(void) timekeeping_suspend_time = timespec_add(timekeeping_suspend_time, delta_delta); } - write_sequnlock_irqrestore(&xtime_lock, flags); + raw_write_sequnlock_irqrestore(&xtime_lock, flags); clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); clocksource_suspend(); @@ -1239,7 +1238,7 @@ ktime_t ktime_get_monotonic_offset(void) */ void xtime_update(unsigned long ticks) { - write_seqlock(&xtime_lock); + raw_write_seqlock(&xtime_lock); do_timer(ticks); - write_sequnlock(&xtime_lock); + raw_write_sequnlock(&xtime_lock); } diff --git a/kernel/timer.c b/kernel/timer.c index 9c3c62b0c4bc..a791a43799b0 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -75,6 +75,7 @@ struct tvec_root { struct tvec_base { spinlock_t lock; struct timer_list *running_timer; + wait_queue_head_t wait_for_running_timer; unsigned long timer_jiffies; unsigned long next_timer; struct tvec_root tv1; @@ -653,6 +654,36 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer, } } +#ifndef CONFIG_PREEMPT_RT_FULL +static inline struct tvec_base *switch_timer_base(struct timer_list *timer, + struct tvec_base *old, + struct tvec_base *new) +{ + /* See the comment in lock_timer_base() */ + timer_set_base(timer, NULL); + spin_unlock(&old->lock); + spin_lock(&new->lock); + timer_set_base(timer, new); + return new; +} +#else +static inline struct tvec_base *switch_timer_base(struct timer_list *timer, + struct tvec_base *old, + struct tvec_base *new) +{ + /* + * We cannot do the above because we might be preempted and + * then the preempter would see NULL and loop forever. + */ + if (spin_trylock(&new->lock)) { + timer_set_base(timer, new); + spin_unlock(&old->lock); + return new; + } + return old; +} +#endif + static inline int __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only, int pinned) @@ -679,12 +710,15 @@ __mod_timer(struct timer_list *timer, unsigned long expires, debug_activate(timer, expires); + preempt_disable_rt(); cpu = smp_processor_id(); #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) cpu = get_nohz_timer_target(); #endif + preempt_enable_rt(); + new_base = per_cpu(tvec_bases, cpu); if (base != new_base) { @@ -695,14 +729,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, * handler yet has not finished. This also guarantees that * the timer is serialized wrt itself. */ - if (likely(base->running_timer != timer)) { - /* See the comment in lock_timer_base() */ - timer_set_base(timer, NULL); - spin_unlock(&base->lock); - base = new_base; - spin_lock(&base->lock); - timer_set_base(timer, base); - } + if (likely(base->running_timer != timer)) + base = switch_timer_base(timer, base, new_base); } timer->expires = expires; @@ -885,6 +913,29 @@ void add_timer_on(struct timer_list *timer, int cpu) } EXPORT_SYMBOL_GPL(add_timer_on); +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * Wait for a running timer + */ +static void wait_for_running_timer(struct timer_list *timer) +{ + struct tvec_base *base = timer->base; + + if (base->running_timer == timer) + wait_event(base->wait_for_running_timer, + base->running_timer != timer); +} + +# define wakeup_timer_waiters(b) wake_up(&(b)->wait_for_tunning_timer) +#else +static inline void wait_for_running_timer(struct timer_list *timer) +{ + cpu_relax(); +} + +# define wakeup_timer_waiters(b) do { } while (0) +#endif + /** * del_timer - deactive a timer. * @timer: the timer to be deactivated @@ -953,7 +1004,7 @@ out: } EXPORT_SYMBOL(try_to_del_timer_sync); -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) /** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated @@ -1013,7 +1064,7 @@ int del_timer_sync(struct timer_list *timer) int ret = try_to_del_timer_sync(timer); if (ret >= 0) return ret; - cpu_relax(); + wait_for_running_timer(timer); } } EXPORT_SYMBOL(del_timer_sync); @@ -1124,10 +1175,11 @@ static inline void __run_timers(struct tvec_base *base) spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, data); + base->running_timer = NULL; spin_lock_irq(&base->lock); } } - base->running_timer = NULL; + wake_up(&base->wait_for_running_timer); spin_unlock_irq(&base->lock); } @@ -1266,6 +1318,23 @@ unsigned long get_next_timer_interrupt(unsigned long now) */ if (cpu_is_offline(smp_processor_id())) return now + NEXT_TIMER_MAX_DELTA; + +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * On PREEMPT_RT we cannot sleep here. If the trylock does not + * succeed then we return the worst-case 'expires in 1 tick' + * value. We use the rt functions here directly to avoid a + * migrate_disable() call. + */ + if (spin_do_trylock(&base->lock)) { + if (time_before_eq(base->next_timer, base->timer_jiffies)) + base->next_timer = __next_timer_interrupt(base); + expires = base->next_timer; + rt_spin_unlock(&base->lock); + } else { + expires = now + 1; + } +#else spin_lock(&base->lock); if (time_before_eq(base->next_timer, base->timer_jiffies)) base->next_timer = __next_timer_interrupt(base); @@ -1274,7 +1343,7 @@ unsigned long get_next_timer_interrupt(unsigned long now) if (time_before_eq(expires, now)) return now; - +#endif return cmp_next_hrtimer_event(now, expires); } #endif @@ -1290,14 +1359,13 @@ void update_process_times(int user_tick) /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); + scheduler_tick(); run_local_timers(); rcu_check_callbacks(cpu, user_tick); - printk_tick(); -#ifdef CONFIG_IRQ_WORK +#if defined(CONFIG_IRQ_WORK) && !defined(CONFIG_PREEMPT_RT_FULL) if (in_irq()) irq_work_run(); #endif - scheduler_tick(); run_posix_cpu_timers(p); } @@ -1308,6 +1376,11 @@ static void run_timer_softirq(struct softirq_action *h) { struct tvec_base *base = __this_cpu_read(tvec_bases); +#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) + irq_work_run(); +#endif + + printk_tick(); hrtimer_run_pending(); if (time_after_eq(jiffies, base->timer_jiffies)) @@ -1634,6 +1707,7 @@ static int __cpuinit init_timers_cpu(int cpu) } spin_lock_init(&base->lock); + init_waitqueue_head(&base->wait_for_running_timer); for (j = 0; j < TVN_SIZE; j++) { INIT_LIST_HEAD(base->tv5.vec + j); @@ -1669,6 +1743,7 @@ static void __cpuinit migrate_timers(int cpu) { struct tvec_base *old_base; struct tvec_base *new_base; + unsigned long flags; int i; BUG_ON(cpu_online(cpu)); @@ -1678,8 +1753,11 @@ static void __cpuinit migrate_timers(int cpu) * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ - spin_lock_irq(&new_base->lock); - spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); + local_irq_save(flags); + while (!spin_trylock(&new_base->lock)) + cpu_relax(); + while (!spin_trylock(&old_base->lock)) + cpu_relax(); BUG_ON(old_base->running_timer); @@ -1693,7 +1771,9 @@ static void __cpuinit migrate_timers(int cpu) } spin_unlock(&old_base->lock); - spin_unlock_irq(&new_base->lock); + spin_unlock(&new_base->lock); + local_irq_restore(flags); + put_cpu_var(tvec_bases); } #endif /* CONFIG_HOTPLUG_CPU */ diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index cd3134510f3d..2685322ab69b 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -192,6 +192,24 @@ config IRQSOFF_TRACER enabled. This option and the preempt-off timing option can be used together or separately.) +config INTERRUPT_OFF_HIST + bool "Interrupts-off Latency Histogram" + depends on IRQSOFF_TRACER + help + This option generates continuously updated histograms (one per cpu) + of the duration of time periods with interrupts disabled. The + histograms are disabled by default. To enable them, write a non-zero + number to + + /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff + + If PREEMPT_OFF_HIST is also selected, additional histograms (one + per cpu) are generated that accumulate the duration of time periods + when both interrupts and preemption are disabled. The histogram data + will be located in the debug file system at + + /sys/kernel/debug/tracing/latency_hist/irqsoff + config PREEMPT_TRACER bool "Preemption-off Latency Tracer" default n @@ -214,6 +232,24 @@ config PREEMPT_TRACER enabled. This option and the irqs-off timing option can be used together or separately.) +config PREEMPT_OFF_HIST + bool "Preemption-off Latency Histogram" + depends on PREEMPT_TRACER + help + This option generates continuously updated histograms (one per cpu) + of the duration of time periods with preemption disabled. The + histograms are disabled by default. To enable them, write a non-zero + number to + + /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff + + If INTERRUPT_OFF_HIST is also selected, additional histograms (one + per cpu) are generated that accumulate the duration of time periods + when both interrupts and preemption are disabled. The histogram data + will be located in the debug file system at + + /sys/kernel/debug/tracing/latency_hist/preemptoff + config SCHED_TRACER bool "Scheduling Latency Tracer" select GENERIC_TRACER @@ -223,6 +259,74 @@ config SCHED_TRACER This tracer tracks the latency of the highest priority task to be scheduled in, starting from the point it has woken up. +config WAKEUP_LATENCY_HIST + bool "Scheduling Latency Histogram" + depends on SCHED_TRACER + help + This option generates continuously updated histograms (one per cpu) + of the scheduling latency of the highest priority task. + The histograms are disabled by default. To enable them, write a + non-zero number to + + /sys/kernel/debug/tracing/latency_hist/enable/wakeup + + Two different algorithms are used, one to determine the latency of + processes that exclusively use the highest priority of the system and + another one to determine the latency of processes that share the + highest system priority with other processes. The former is used to + improve hardware and system software, the latter to optimize the + priority design of a given system. The histogram data will be + located in the debug file system at + + /sys/kernel/debug/tracing/latency_hist/wakeup + + and + + /sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio + + If both Scheduling Latency Histogram and Missed Timer Offsets + Histogram are selected, additional histogram data will be collected + that contain, in addition to the wakeup latency, the timer latency, in + case the wakeup was triggered by an expired timer. These histograms + are available in the + + /sys/kernel/debug/tracing/latency_hist/timerandwakeup + + directory. They reflect the apparent interrupt and scheduling latency + and are best suitable to determine the worst-case latency of a given + system. To enable these histograms, write a non-zero number to + + /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup + +config MISSED_TIMER_OFFSETS_HIST + depends on HIGH_RES_TIMERS + select GENERIC_TRACER + bool "Missed Timer Offsets Histogram" + help + Generate a histogram of missed timer offsets in microseconds. The + histograms are disabled by default. To enable them, write a non-zero + number to + + /sys/kernel/debug/tracing/latency_hist/enable/missed_timer_offsets + + The histogram data will be located in the debug file system at + + /sys/kernel/debug/tracing/latency_hist/missed_timer_offsets + + If both Scheduling Latency Histogram and Missed Timer Offsets + Histogram are selected, additional histogram data will be collected + that contain, in addition to the wakeup latency, the timer latency, in + case the wakeup was triggered by an expired timer. These histograms + are available in the + + /sys/kernel/debug/tracing/latency_hist/timerandwakeup + + directory. They reflect the apparent interrupt and scheduling latency + and are best suitable to determine the worst-case latency of a given + system. To enable these histograms, write a non-zero number to + + /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup + config ENABLE_DEFAULT_TRACERS bool "Trace process context switches and events" depends on !GENERIC_TRACER diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 5f39a07fe5ea..108a387e1459 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -36,6 +36,10 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o +obj-$(CONFIG_INTERRUPT_OFF_HIST) += latency_hist.o +obj-$(CONFIG_PREEMPT_OFF_HIST) += latency_hist.o +obj-$(CONFIG_WAKEUP_LATENCY_HIST) += latency_hist.o +obj-$(CONFIG_MISSED_TIMER_OFFSETS_HIST) += latency_hist.o obj-$(CONFIG_NOP_TRACER) += trace_nop.o obj-$(CONFIG_STACK_TRACER) += trace_stack.o obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o diff --git a/kernel/trace/latency_hist.c b/kernel/trace/latency_hist.c new file mode 100644 index 000000000000..9d49fcb8962f --- /dev/null +++ b/kernel/trace/latency_hist.c @@ -0,0 +1,1170 @@ +/* + * kernel/trace/latency_hist.c + * + * Add support for histograms of preemption-off latency and + * interrupt-off latency and wakeup latency, it depends on + * Real-Time Preemption Support. + * + * Copyright (C) 2005 MontaVista Software, Inc. + * Yi Yang <yyang@ch.mvista.com> + * + * Converted to work with the new latency tracer. + * Copyright (C) 2008 Red Hat, Inc. + * Steven Rostedt <srostedt@redhat.com> + * + */ +#include <linux/module.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> +#include <linux/percpu.h> +#include <linux/kallsyms.h> +#include <linux/uaccess.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <asm/atomic.h> +#include <asm/div64.h> + +#include "trace.h" +#include <trace/events/sched.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/hist.h> + +enum { + IRQSOFF_LATENCY = 0, + PREEMPTOFF_LATENCY, + PREEMPTIRQSOFF_LATENCY, + WAKEUP_LATENCY, + WAKEUP_LATENCY_SHAREDPRIO, + MISSED_TIMER_OFFSETS, + TIMERANDWAKEUP_LATENCY, + MAX_LATENCY_TYPE, +}; + +#define MAX_ENTRY_NUM 10240 + +struct hist_data { + atomic_t hist_mode; /* 0 log, 1 don't log */ + long offset; /* set it to MAX_ENTRY_NUM/2 for a bipolar scale */ + unsigned long min_lat; + unsigned long max_lat; + unsigned long long below_hist_bound_samples; + unsigned long long above_hist_bound_samples; + unsigned long long accumulate_lat; + unsigned long long total_samples; + unsigned long long hist_array[MAX_ENTRY_NUM]; +}; + +struct enable_data { + int latency_type; + int enabled; +}; + +static char *latency_hist_dir_root = "latency_hist"; + +#ifdef CONFIG_INTERRUPT_OFF_HIST +static DEFINE_PER_CPU(struct hist_data, irqsoff_hist); +static char *irqsoff_hist_dir = "irqsoff"; +static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start); +static DEFINE_PER_CPU(int, hist_irqsoff_counting); +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST +static DEFINE_PER_CPU(struct hist_data, preemptoff_hist); +static char *preemptoff_hist_dir = "preemptoff"; +static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start); +static DEFINE_PER_CPU(int, hist_preemptoff_counting); +#endif + +#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) +static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist); +static char *preemptirqsoff_hist_dir = "preemptirqsoff"; +static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start); +static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting); +#endif + +#if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST) +static notrace void probe_preemptirqsoff_hist(void *v, int reason, int start); +static struct enable_data preemptirqsoff_enabled_data = { + .latency_type = PREEMPTIRQSOFF_LATENCY, + .enabled = 0, +}; +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +struct maxlatproc_data { + char comm[FIELD_SIZEOF(struct task_struct, comm)]; + char current_comm[FIELD_SIZEOF(struct task_struct, comm)]; + int pid; + int current_pid; + int prio; + int current_prio; + long latency; + long timeroffset; + cycle_t timestamp; +}; +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST +static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist); +static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio); +static char *wakeup_latency_hist_dir = "wakeup"; +static char *wakeup_latency_hist_dir_sharedprio = "sharedprio"; +static notrace void probe_wakeup_latency_hist_start(void *v, + struct task_struct *p, int success); +static notrace void probe_wakeup_latency_hist_stop(void *v, + struct task_struct *prev, struct task_struct *next); +static notrace void probe_sched_migrate_task(void *, + struct task_struct *task, int cpu); +static struct enable_data wakeup_latency_enabled_data = { + .latency_type = WAKEUP_LATENCY, + .enabled = 0, +}; +static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc); +static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc_sharedprio); +static DEFINE_PER_CPU(struct task_struct *, wakeup_task); +static DEFINE_PER_CPU(int, wakeup_sharedprio); +static unsigned long wakeup_pid; +#endif + +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST +static DEFINE_PER_CPU(struct hist_data, missed_timer_offsets); +static char *missed_timer_offsets_dir = "missed_timer_offsets"; +static notrace void probe_hrtimer_interrupt(void *v, int cpu, + long long offset, struct task_struct *curr, struct task_struct *task); +static struct enable_data missed_timer_offsets_enabled_data = { + .latency_type = MISSED_TIMER_OFFSETS, + .enabled = 0, +}; +static DEFINE_PER_CPU(struct maxlatproc_data, missed_timer_offsets_maxlatproc); +static unsigned long missed_timer_offsets_pid; +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static DEFINE_PER_CPU(struct hist_data, timerandwakeup_latency_hist); +static char *timerandwakeup_latency_hist_dir = "timerandwakeup"; +static struct enable_data timerandwakeup_enabled_data = { + .latency_type = TIMERANDWAKEUP_LATENCY, + .enabled = 0, +}; +static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc); +#endif + +void notrace latency_hist(int latency_type, int cpu, unsigned long latency, + unsigned long timeroffset, cycle_t stop, + struct task_struct *p) +{ + struct hist_data *my_hist; +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + struct maxlatproc_data *mp = NULL; +#endif + + if (cpu < 0 || cpu >= NR_CPUS || latency_type < 0 || + latency_type >= MAX_LATENCY_TYPE) + return; + + switch (latency_type) { +#ifdef CONFIG_INTERRUPT_OFF_HIST + case IRQSOFF_LATENCY: + my_hist = &per_cpu(irqsoff_hist, cpu); + break; +#endif +#ifdef CONFIG_PREEMPT_OFF_HIST + case PREEMPTOFF_LATENCY: + my_hist = &per_cpu(preemptoff_hist, cpu); + break; +#endif +#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + my_hist = &per_cpu(preemptirqsoff_hist, cpu); + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + my_hist = &per_cpu(wakeup_latency_hist, cpu); + mp = &per_cpu(wakeup_maxlatproc, cpu); + break; + case WAKEUP_LATENCY_SHAREDPRIO: + my_hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); + mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + my_hist = &per_cpu(missed_timer_offsets, cpu); + mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); + break; +#endif +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + case TIMERANDWAKEUP_LATENCY: + my_hist = &per_cpu(timerandwakeup_latency_hist, cpu); + mp = &per_cpu(timerandwakeup_maxlatproc, cpu); + break; +#endif + + default: + return; + } + + latency += my_hist->offset; + + if (atomic_read(&my_hist->hist_mode) == 0) + return; + + if (latency < 0 || latency >= MAX_ENTRY_NUM) { + if (latency < 0) + my_hist->below_hist_bound_samples++; + else + my_hist->above_hist_bound_samples++; + } else + my_hist->hist_array[latency]++; + + if (unlikely(latency > my_hist->max_lat || + my_hist->min_lat == ULONG_MAX)) { +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + if (latency_type == WAKEUP_LATENCY || + latency_type == WAKEUP_LATENCY_SHAREDPRIO || + latency_type == MISSED_TIMER_OFFSETS || + latency_type == TIMERANDWAKEUP_LATENCY) { + strncpy(mp->comm, p->comm, sizeof(mp->comm)); + strncpy(mp->current_comm, current->comm, + sizeof(mp->current_comm)); + mp->pid = task_pid_nr(p); + mp->current_pid = task_pid_nr(current); + mp->prio = p->prio; + mp->current_prio = current->prio; + mp->latency = latency; + mp->timeroffset = timeroffset; + mp->timestamp = stop; + } +#endif + my_hist->max_lat = latency; + } + if (unlikely(latency < my_hist->min_lat)) + my_hist->min_lat = latency; + my_hist->total_samples++; + my_hist->accumulate_lat += latency; +} + +static void *l_start(struct seq_file *m, loff_t *pos) +{ + loff_t *index_ptr = NULL; + loff_t index = *pos; + struct hist_data *my_hist = m->private; + + if (index == 0) { + char minstr[32], avgstr[32], maxstr[32]; + + atomic_dec(&my_hist->hist_mode); + + if (likely(my_hist->total_samples)) { + unsigned long avg = (unsigned long) + div64_u64(my_hist->accumulate_lat, + my_hist->total_samples); + snprintf(minstr, sizeof(minstr), "%ld", + (long) my_hist->min_lat - my_hist->offset); + snprintf(avgstr, sizeof(avgstr), "%ld", + (long) avg - my_hist->offset); + snprintf(maxstr, sizeof(maxstr), "%ld", + (long) my_hist->max_lat - my_hist->offset); + } else { + strcpy(minstr, "<undef>"); + strcpy(avgstr, minstr); + strcpy(maxstr, minstr); + } + + seq_printf(m, "#Minimum latency: %s microseconds\n" + "#Average latency: %s microseconds\n" + "#Maximum latency: %s microseconds\n" + "#Total samples: %llu\n" + "#There are %llu samples lower than %ld" + " microseconds.\n" + "#There are %llu samples greater or equal" + " than %ld microseconds.\n" + "#usecs\t%16s\n", + minstr, avgstr, maxstr, + my_hist->total_samples, + my_hist->below_hist_bound_samples, + -my_hist->offset, + my_hist->above_hist_bound_samples, + MAX_ENTRY_NUM - my_hist->offset, + "samples"); + } + if (index < MAX_ENTRY_NUM) { + index_ptr = kmalloc(sizeof(loff_t), GFP_KERNEL); + if (index_ptr) + *index_ptr = index; + } + + return index_ptr; +} + +static void *l_next(struct seq_file *m, void *p, loff_t *pos) +{ + loff_t *index_ptr = p; + struct hist_data *my_hist = m->private; + + if (++*pos >= MAX_ENTRY_NUM) { + atomic_inc(&my_hist->hist_mode); + return NULL; + } + *index_ptr = *pos; + return index_ptr; +} + +static void l_stop(struct seq_file *m, void *p) +{ + kfree(p); +} + +static int l_show(struct seq_file *m, void *p) +{ + int index = *(loff_t *) p; + struct hist_data *my_hist = m->private; + + seq_printf(m, "%6ld\t%16llu\n", index - my_hist->offset, + my_hist->hist_array[index]); + return 0; +} + +static struct seq_operations latency_hist_seq_op = { + .start = l_start, + .next = l_next, + .stop = l_stop, + .show = l_show +}; + +static int latency_hist_open(struct inode *inode, struct file *file) +{ + int ret; + + ret = seq_open(file, &latency_hist_seq_op); + if (!ret) { + struct seq_file *seq = file->private_data; + seq->private = inode->i_private; + } + return ret; +} + +static struct file_operations latency_hist_fops = { + .open = latency_hist_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static void clear_maxlatprocdata(struct maxlatproc_data *mp) +{ + mp->comm[0] = mp->current_comm[0] = '\0'; + mp->prio = mp->current_prio = mp->pid = mp->current_pid = + mp->latency = mp->timeroffset = -1; + mp->timestamp = 0; +} +#endif + +static void hist_reset(struct hist_data *hist) +{ + atomic_dec(&hist->hist_mode); + + memset(hist->hist_array, 0, sizeof(hist->hist_array)); + hist->below_hist_bound_samples = 0ULL; + hist->above_hist_bound_samples = 0ULL; + hist->min_lat = ULONG_MAX; + hist->max_lat = 0UL; + hist->total_samples = 0ULL; + hist->accumulate_lat = 0ULL; + + atomic_inc(&hist->hist_mode); +} + +static ssize_t +latency_hist_reset(struct file *file, const char __user *a, + size_t size, loff_t *off) +{ + int cpu; + struct hist_data *hist = NULL; +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + struct maxlatproc_data *mp = NULL; +#endif + off_t latency_type = (off_t) file->private_data; + + for_each_online_cpu(cpu) { + + switch (latency_type) { +#ifdef CONFIG_PREEMPT_OFF_HIST + case PREEMPTOFF_LATENCY: + hist = &per_cpu(preemptoff_hist, cpu); + break; +#endif +#ifdef CONFIG_INTERRUPT_OFF_HIST + case IRQSOFF_LATENCY: + hist = &per_cpu(irqsoff_hist, cpu); + break; +#endif +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + hist = &per_cpu(preemptirqsoff_hist, cpu); + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + hist = &per_cpu(wakeup_latency_hist, cpu); + mp = &per_cpu(wakeup_maxlatproc, cpu); + break; + case WAKEUP_LATENCY_SHAREDPRIO: + hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); + mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + hist = &per_cpu(missed_timer_offsets, cpu); + mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); + break; +#endif +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + case TIMERANDWAKEUP_LATENCY: + hist = &per_cpu(timerandwakeup_latency_hist, cpu); + mp = &per_cpu(timerandwakeup_maxlatproc, cpu); + break; +#endif + } + + hist_reset(hist); +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + if (latency_type == WAKEUP_LATENCY || + latency_type == WAKEUP_LATENCY_SHAREDPRIO || + latency_type == MISSED_TIMER_OFFSETS || + latency_type == TIMERANDWAKEUP_LATENCY) + clear_maxlatprocdata(mp); +#endif + } + + return size; +} + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static ssize_t +show_pid(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + char buf[64]; + int r; + unsigned long *this_pid = file->private_data; + + r = snprintf(buf, sizeof(buf), "%lu\n", *this_pid); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t do_pid(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + unsigned long pid; + unsigned long *this_pid = file->private_data; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = '\0'; + + if (strict_strtoul(buf, 10, &pid)) + return(-EINVAL); + + *this_pid = pid; + + return cnt; +} +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static ssize_t +show_maxlatproc(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + int r; + struct maxlatproc_data *mp = file->private_data; + int strmaxlen = (TASK_COMM_LEN * 2) + (8 * 8); + unsigned long long t; + unsigned long usecs, secs; + char *buf; + + if (mp->pid == -1 || mp->current_pid == -1) { + buf = "(none)\n"; + return simple_read_from_buffer(ubuf, cnt, ppos, buf, + strlen(buf)); + } + + buf = kmalloc(strmaxlen, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + t = ns2usecs(mp->timestamp); + usecs = do_div(t, USEC_PER_SEC); + secs = (unsigned long) t; + r = snprintf(buf, strmaxlen, + "%d %d %ld (%ld) %s <- %d %d %s %lu.%06lu\n", mp->pid, + MAX_RT_PRIO-1 - mp->prio, mp->latency, mp->timeroffset, mp->comm, + mp->current_pid, MAX_RT_PRIO-1 - mp->current_prio, mp->current_comm, + secs, usecs); + r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + kfree(buf); + return r; +} +#endif + +static ssize_t +show_enable(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + char buf[64]; + struct enable_data *ed = file->private_data; + int r; + + r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +do_enable(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) +{ + char buf[64]; + long enable; + struct enable_data *ed = file->private_data; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + if (strict_strtol(buf, 10, &enable)) + return(-EINVAL); + + if ((enable && ed->enabled) || (!enable && !ed->enabled)) + return cnt; + + if (enable) { + int ret; + + switch (ed->latency_type) { +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + ret = register_trace_preemptirqsoff_hist( + probe_preemptirqsoff_hist, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_preemptirqsoff_hist " + "to trace_preemptirqsoff_hist\n"); + return ret; + } + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + ret = register_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_start " + "to trace_sched_wakeup\n"); + return ret; + } + ret = register_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_start " + "to trace_sched_wakeup_new\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + return ret; + } + ret = register_trace_sched_switch( + probe_wakeup_latency_hist_stop, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_stop " + "to trace_sched_switch\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + return ret; + } + ret = register_trace_sched_migrate_task( + probe_sched_migrate_task, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_sched_migrate_task " + "to trace_sched_migrate_task\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_switch( + probe_wakeup_latency_hist_stop, NULL); + return ret; + } + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + ret = register_trace_hrtimer_interrupt( + probe_hrtimer_interrupt, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_hrtimer_interrupt " + "to trace_hrtimer_interrupt\n"); + return ret; + } + break; +#endif +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + case TIMERANDWAKEUP_LATENCY: + if (!wakeup_latency_enabled_data.enabled || + !missed_timer_offsets_enabled_data.enabled) + return -EINVAL; + break; +#endif + default: + break; + } + } else { + switch (ed->latency_type) { +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + { + int cpu; + + unregister_trace_preemptirqsoff_hist( + probe_preemptirqsoff_hist, NULL); + for_each_online_cpu(cpu) { +#ifdef CONFIG_INTERRUPT_OFF_HIST + per_cpu(hist_irqsoff_counting, + cpu) = 0; +#endif +#ifdef CONFIG_PREEMPT_OFF_HIST + per_cpu(hist_preemptoff_counting, + cpu) = 0; +#endif +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + per_cpu(hist_preemptirqsoff_counting, + cpu) = 0; +#endif + } + } + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + { + int cpu; + + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_switch( + probe_wakeup_latency_hist_stop, NULL); + unregister_trace_sched_migrate_task( + probe_sched_migrate_task, NULL); + + for_each_online_cpu(cpu) { + per_cpu(wakeup_task, cpu) = NULL; + per_cpu(wakeup_sharedprio, cpu) = 0; + } + } +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + timerandwakeup_enabled_data.enabled = 0; +#endif + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + unregister_trace_hrtimer_interrupt( + probe_hrtimer_interrupt, NULL); +#ifdef CONFIG_WAKEUP_LATENCY_HIST + timerandwakeup_enabled_data.enabled = 0; +#endif + break; +#endif + default: + break; + } + } + ed->enabled = enable; + return cnt; +} + +static const struct file_operations latency_hist_reset_fops = { + .open = tracing_open_generic, + .write = latency_hist_reset, +}; + +static const struct file_operations enable_fops = { + .open = tracing_open_generic, + .read = show_enable, + .write = do_enable, +}; + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static const struct file_operations pid_fops = { + .open = tracing_open_generic, + .read = show_pid, + .write = do_pid, +}; + +static const struct file_operations maxlatproc_fops = { + .open = tracing_open_generic, + .read = show_maxlatproc, +}; +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) +static notrace void probe_preemptirqsoff_hist(void *v, int reason, + int starthist) +{ + int cpu = raw_smp_processor_id(); + int time_set = 0; + + if (starthist) { + cycle_t uninitialized_var(start); + + if (!preempt_count() && !irqs_disabled()) + return; + +#ifdef CONFIG_INTERRUPT_OFF_HIST + if ((reason == IRQS_OFF || reason == TRACE_START) && + !per_cpu(hist_irqsoff_counting, cpu)) { + per_cpu(hist_irqsoff_counting, cpu) = 1; + start = ftrace_now(cpu); + time_set++; + per_cpu(hist_irqsoff_start, cpu) = start; + } +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + if ((reason == PREEMPT_OFF || reason == TRACE_START) && + !per_cpu(hist_preemptoff_counting, cpu)) { + per_cpu(hist_preemptoff_counting, cpu) = 1; + if (!(time_set++)) + start = ftrace_now(cpu); + per_cpu(hist_preemptoff_start, cpu) = start; + } +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + if (per_cpu(hist_irqsoff_counting, cpu) && + per_cpu(hist_preemptoff_counting, cpu) && + !per_cpu(hist_preemptirqsoff_counting, cpu)) { + per_cpu(hist_preemptirqsoff_counting, cpu) = 1; + if (!time_set) + start = ftrace_now(cpu); + per_cpu(hist_preemptirqsoff_start, cpu) = start; + } +#endif + } else { + cycle_t uninitialized_var(stop); + +#ifdef CONFIG_INTERRUPT_OFF_HIST + if ((reason == IRQS_ON || reason == TRACE_STOP) && + per_cpu(hist_irqsoff_counting, cpu)) { + cycle_t start = per_cpu(hist_irqsoff_start, cpu); + + stop = ftrace_now(cpu); + time_set++; + if (start && stop >= start) { + unsigned long latency = + nsecs_to_usecs(stop - start); + + latency_hist(IRQSOFF_LATENCY, cpu, latency, 0, + stop, NULL); + } + per_cpu(hist_irqsoff_counting, cpu) = 0; + } +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + if ((reason == PREEMPT_ON || reason == TRACE_STOP) && + per_cpu(hist_preemptoff_counting, cpu)) { + cycle_t start = per_cpu(hist_preemptoff_start, cpu); + + if (!(time_set++)) + stop = ftrace_now(cpu); + if (start && stop >= start) { + unsigned long latency = + nsecs_to_usecs(stop - start); + + latency_hist(PREEMPTOFF_LATENCY, cpu, latency, + 0, stop, NULL); + } + per_cpu(hist_preemptoff_counting, cpu) = 0; + } +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + if ((!per_cpu(hist_irqsoff_counting, cpu) || + !per_cpu(hist_preemptoff_counting, cpu)) && + per_cpu(hist_preemptirqsoff_counting, cpu)) { + cycle_t start = per_cpu(hist_preemptirqsoff_start, cpu); + + if (!time_set) + stop = ftrace_now(cpu); + if (start && stop >= start) { + unsigned long latency = + nsecs_to_usecs(stop - start); + latency_hist(PREEMPTIRQSOFF_LATENCY, cpu, + latency, 0, stop, NULL); + } + per_cpu(hist_preemptirqsoff_counting, cpu) = 0; + } +#endif + } +} +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST +static DEFINE_RAW_SPINLOCK(wakeup_lock); +static notrace void probe_sched_migrate_task(void *v, struct task_struct *task, + int cpu) +{ + int old_cpu = task_cpu(task); + + if (cpu != old_cpu) { + unsigned long flags; + struct task_struct *cpu_wakeup_task; + + raw_spin_lock_irqsave(&wakeup_lock, flags); + + cpu_wakeup_task = per_cpu(wakeup_task, old_cpu); + if (task == cpu_wakeup_task) { + put_task_struct(cpu_wakeup_task); + per_cpu(wakeup_task, old_cpu) = NULL; + cpu_wakeup_task = per_cpu(wakeup_task, cpu) = task; + get_task_struct(cpu_wakeup_task); + } + + raw_spin_unlock_irqrestore(&wakeup_lock, flags); + } +} + +static notrace void probe_wakeup_latency_hist_start(void *v, + struct task_struct *p, int success) +{ + unsigned long flags; + struct task_struct *curr = current; + int cpu = task_cpu(p); + struct task_struct *cpu_wakeup_task; + + raw_spin_lock_irqsave(&wakeup_lock, flags); + + cpu_wakeup_task = per_cpu(wakeup_task, cpu); + + if (wakeup_pid) { + if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || + p->prio == curr->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + if (likely(wakeup_pid != task_pid_nr(p))) + goto out; + } else { + if (likely(!rt_task(p)) || + (cpu_wakeup_task && p->prio > cpu_wakeup_task->prio) || + p->prio > curr->prio) + goto out; + if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || + p->prio == curr->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + } + + if (cpu_wakeup_task) + put_task_struct(cpu_wakeup_task); + cpu_wakeup_task = per_cpu(wakeup_task, cpu) = p; + get_task_struct(cpu_wakeup_task); + cpu_wakeup_task->preempt_timestamp_hist = + ftrace_now(raw_smp_processor_id()); +out: + raw_spin_unlock_irqrestore(&wakeup_lock, flags); +} + +static notrace void probe_wakeup_latency_hist_stop(void *v, + struct task_struct *prev, struct task_struct *next) +{ + unsigned long flags; + int cpu = task_cpu(next); + unsigned long latency; + cycle_t stop; + struct task_struct *cpu_wakeup_task; + + raw_spin_lock_irqsave(&wakeup_lock, flags); + + cpu_wakeup_task = per_cpu(wakeup_task, cpu); + + if (cpu_wakeup_task == NULL) + goto out; + + /* Already running? */ + if (unlikely(current == cpu_wakeup_task)) + goto out_reset; + + if (next != cpu_wakeup_task) { + if (next->prio < cpu_wakeup_task->prio) + goto out_reset; + + if (next->prio == cpu_wakeup_task->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + + goto out; + } + + /* + * The task we are waiting for is about to be switched to. + * Calculate latency and store it in histogram. + */ + stop = ftrace_now(raw_smp_processor_id()); + + latency = nsecs_to_usecs(stop - next->preempt_timestamp_hist); + + if (per_cpu(wakeup_sharedprio, cpu)) { + latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop, + next); + per_cpu(wakeup_sharedprio, cpu) = 0; + } else { + latency_hist(WAKEUP_LATENCY, cpu, latency, 0, stop, next); +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + if (timerandwakeup_enabled_data.enabled) { + latency_hist(TIMERANDWAKEUP_LATENCY, cpu, + next->timer_offset + latency, next->timer_offset, + stop, next); + } +#endif + } + +out_reset: +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + next->timer_offset = 0; +#endif + put_task_struct(cpu_wakeup_task); + per_cpu(wakeup_task, cpu) = NULL; +out: + raw_spin_unlock_irqrestore(&wakeup_lock, flags); +} +#endif + +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST +static notrace void probe_hrtimer_interrupt(void *v, int cpu, + long long latency_ns, struct task_struct *curr, struct task_struct *task) +{ + if (latency_ns <= 0 && task != NULL && rt_task(task) && + (task->prio < curr->prio || + (task->prio == curr->prio && + !cpumask_test_cpu(cpu, &task->cpus_allowed)))) { + unsigned long latency; + cycle_t now; + + if (missed_timer_offsets_pid) { + if (likely(missed_timer_offsets_pid != + task_pid_nr(task))) + return; + } + + now = ftrace_now(cpu); + latency = (unsigned long) div_s64(-latency_ns, 1000); + latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now, + task); +#ifdef CONFIG_WAKEUP_LATENCY_HIST + task->timer_offset = latency; +#endif + } +} +#endif + +static __init int latency_hist_init(void) +{ + struct dentry *latency_hist_root = NULL; + struct dentry *dentry; +#ifdef CONFIG_WAKEUP_LATENCY_HIST + struct dentry *dentry_sharedprio; +#endif + struct dentry *entry; + struct dentry *enable_root; + int i = 0; + struct hist_data *my_hist; + char name[64]; + char *cpufmt = "CPU%d"; +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + char *cpufmt_maxlatproc = "max_latency-CPU%d"; + struct maxlatproc_data *mp = NULL; +#endif + + dentry = tracing_init_dentry(); + latency_hist_root = debugfs_create_dir(latency_hist_dir_root, dentry); + enable_root = debugfs_create_dir("enable", latency_hist_root); + +#ifdef CONFIG_INTERRUPT_OFF_HIST + dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(irqsoff_hist, i), &latency_hist_fops); + my_hist = &per_cpu(irqsoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = 0xFFFFFFFFUL; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops); +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + dentry = debugfs_create_dir(preemptoff_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(preemptoff_hist, i), &latency_hist_fops); + my_hist = &per_cpu(preemptoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = 0xFFFFFFFFUL; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops); +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + dentry = debugfs_create_dir(preemptirqsoff_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops); + my_hist = &per_cpu(preemptirqsoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = 0xFFFFFFFFUL; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops); +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + entry = debugfs_create_file("preemptirqsoff", 0644, + enable_root, (void *)&preemptirqsoff_enabled_data, + &enable_fops); +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST + dentry = debugfs_create_dir(wakeup_latency_hist_dir, + latency_hist_root); + dentry_sharedprio = debugfs_create_dir( + wakeup_latency_hist_dir_sharedprio, dentry); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(wakeup_latency_hist, i), + &latency_hist_fops); + my_hist = &per_cpu(wakeup_latency_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = 0xFFFFFFFFUL; + + entry = debugfs_create_file(name, 0444, dentry_sharedprio, + &per_cpu(wakeup_latency_hist_sharedprio, i), + &latency_hist_fops); + my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = 0xFFFFFFFFUL; + + sprintf(name, cpufmt_maxlatproc, i); + + mp = &per_cpu(wakeup_maxlatproc, i); + entry = debugfs_create_file(name, 0444, dentry, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + + mp = &per_cpu(wakeup_maxlatproc_sharedprio, i); + entry = debugfs_create_file(name, 0444, dentry_sharedprio, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + } + entry = debugfs_create_file("pid", 0644, dentry, + (void *)&wakeup_pid, &pid_fops); + entry = debugfs_create_file("reset", 0644, dentry, + (void *)WAKEUP_LATENCY, &latency_hist_reset_fops); + entry = debugfs_create_file("reset", 0644, dentry_sharedprio, + (void *)WAKEUP_LATENCY_SHAREDPRIO, &latency_hist_reset_fops); + entry = debugfs_create_file("wakeup", 0644, + enable_root, (void *)&wakeup_latency_enabled_data, + &enable_fops); +#endif + +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + dentry = debugfs_create_dir(missed_timer_offsets_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(missed_timer_offsets, i), &latency_hist_fops); + my_hist = &per_cpu(missed_timer_offsets, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = 0xFFFFFFFFUL; + + sprintf(name, cpufmt_maxlatproc, i); + mp = &per_cpu(missed_timer_offsets_maxlatproc, i); + entry = debugfs_create_file(name, 0444, dentry, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + } + entry = debugfs_create_file("pid", 0644, dentry, + (void *)&missed_timer_offsets_pid, &pid_fops); + entry = debugfs_create_file("reset", 0644, dentry, + (void *)MISSED_TIMER_OFFSETS, &latency_hist_reset_fops); + entry = debugfs_create_file("missed_timer_offsets", 0644, + enable_root, (void *)&missed_timer_offsets_enabled_data, + &enable_fops); +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + dentry = debugfs_create_dir(timerandwakeup_latency_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(timerandwakeup_latency_hist, i), + &latency_hist_fops); + my_hist = &per_cpu(timerandwakeup_latency_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = 0xFFFFFFFFUL; + + sprintf(name, cpufmt_maxlatproc, i); + mp = &per_cpu(timerandwakeup_maxlatproc, i); + entry = debugfs_create_file(name, 0444, dentry, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)TIMERANDWAKEUP_LATENCY, &latency_hist_reset_fops); + entry = debugfs_create_file("timerandwakeup", 0644, + enable_root, (void *)&timerandwakeup_enabled_data, + &enable_fops); +#endif + return 0; +} + +__initcall(latency_hist_init); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f5b7b5c1195b..354017f455e5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -478,7 +478,7 @@ struct ring_buffer_per_cpu { int cpu; atomic_t record_disabled; struct ring_buffer *buffer; - raw_spinlock_t reader_lock; /* serialize readers */ + spinlock_t reader_lock; /* serialize readers */ arch_spinlock_t lock; struct lock_class_key lock_key; struct list_head *pages; @@ -1049,6 +1049,44 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, return -ENOMEM; } +static inline int ok_to_lock(void) +{ + if (in_nmi()) + return 0; +#ifdef CONFIG_PREEMPT_RT_FULL + if (in_atomic()) + return 0; +#endif + return 1; +} + +static int +read_buffer_lock(struct ring_buffer_per_cpu *cpu_buffer, + unsigned long *flags) +{ + /* + * If an NMI die dumps out the content of the ring buffer + * do not grab locks. We also permanently disable the ring + * buffer too. A one time deal is all you get from reading + * the ring buffer from an NMI. + */ + if (!ok_to_lock()) { + if (spin_trylock_irqsave(&cpu_buffer->reader_lock, *flags)) + return 1; + tracing_off_permanent(); + return 0; + } + spin_lock_irqsave(&cpu_buffer->reader_lock, *flags); + return 1; +} + +static void +read_buffer_unlock(struct ring_buffer_per_cpu *cpu_buffer, + unsigned long flags, int locked) +{ + if (locked) + spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); +} static struct ring_buffer_per_cpu * rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) { @@ -1064,7 +1102,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) cpu_buffer->cpu = cpu; cpu_buffer->buffer = buffer; - raw_spin_lock_init(&cpu_buffer->reader_lock); + spin_lock_init(&cpu_buffer->reader_lock); lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key); cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; @@ -1259,9 +1297,11 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) { struct buffer_page *bpage; struct list_head *p; + unsigned long flags; unsigned i; + int locked; - raw_spin_lock_irq(&cpu_buffer->reader_lock); + locked = read_buffer_lock(cpu_buffer, &flags); rb_head_page_deactivate(cpu_buffer); for (i = 0; i < nr_pages; i++) { @@ -1279,7 +1319,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) rb_check_pages(cpu_buffer); out: - raw_spin_unlock_irq(&cpu_buffer->reader_lock); + read_buffer_unlock(cpu_buffer, flags, locked); } static void @@ -1288,9 +1328,11 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer, { struct buffer_page *bpage; struct list_head *p; + unsigned long flags; unsigned i; + int locked; - raw_spin_lock_irq(&cpu_buffer->reader_lock); + locked = read_buffer_lock(cpu_buffer, &flags); rb_head_page_deactivate(cpu_buffer); for (i = 0; i < nr_pages; i++) { @@ -1305,7 +1347,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer, rb_check_pages(cpu_buffer); out: - raw_spin_unlock_irq(&cpu_buffer->reader_lock); + read_buffer_unlock(cpu_buffer, flags, locked); } /** @@ -2689,7 +2731,7 @@ unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu) return 0; cpu_buffer = buffer->buffers[cpu]; - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + spin_lock_irqsave(&cpu_buffer->reader_lock, flags); /* * if the tail is on reader_page, oldest time stamp is on the reader * page @@ -2699,7 +2741,7 @@ unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu) else bpage = rb_set_head_page(cpu_buffer); ret = bpage->page->time_stamp; - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); return ret; } @@ -2863,15 +2905,16 @@ void ring_buffer_iter_reset(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; + int locked; if (!iter) return; cpu_buffer = iter->cpu_buffer; - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + locked = read_buffer_lock(cpu_buffer, &flags); rb_iter_reset(iter); - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + read_buffer_unlock(cpu_buffer, flags, locked); } EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); @@ -3289,21 +3332,6 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) } EXPORT_SYMBOL_GPL(ring_buffer_iter_peek); -static inline int rb_ok_to_lock(void) -{ - /* - * If an NMI die dumps out the content of the ring buffer - * do not grab locks. We also permanently disable the ring - * buffer too. A one time deal is all you get from reading - * the ring buffer from an NMI. - */ - if (likely(!in_nmi())) - return 1; - - tracing_off_permanent(); - return 0; -} - /** * ring_buffer_peek - peek at the next event to be read * @buffer: The ring buffer to read @@ -3321,22 +3349,17 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts, struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct ring_buffer_event *event; unsigned long flags; - int dolock; + int locked; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; - dolock = rb_ok_to_lock(); again: - local_irq_save(flags); - if (dolock) - raw_spin_lock(&cpu_buffer->reader_lock); + locked = read_buffer_lock(cpu_buffer, &flags); event = rb_buffer_peek(cpu_buffer, ts, lost_events); if (event && event->type_len == RINGBUF_TYPE_PADDING) rb_advance_reader(cpu_buffer); - if (dolock) - raw_spin_unlock(&cpu_buffer->reader_lock); - local_irq_restore(flags); + read_buffer_unlock(cpu_buffer, flags, locked); if (event && event->type_len == RINGBUF_TYPE_PADDING) goto again; @@ -3358,11 +3381,12 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; struct ring_buffer_event *event; unsigned long flags; + int locked; again: - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + locked = read_buffer_lock(cpu_buffer, &flags); event = rb_iter_peek(iter, ts); - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + read_buffer_unlock(cpu_buffer, flags, locked); if (event && event->type_len == RINGBUF_TYPE_PADDING) goto again; @@ -3388,9 +3412,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts, struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event = NULL; unsigned long flags; - int dolock; - - dolock = rb_ok_to_lock(); + int locked; again: /* might be called in atomic */ @@ -3400,9 +3422,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts, goto out; cpu_buffer = buffer->buffers[cpu]; - local_irq_save(flags); - if (dolock) - raw_spin_lock(&cpu_buffer->reader_lock); + locked = read_buffer_lock(cpu_buffer, &flags); event = rb_buffer_peek(cpu_buffer, ts, lost_events); if (event) { @@ -3410,9 +3430,8 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts, rb_advance_reader(cpu_buffer); } - if (dolock) - raw_spin_unlock(&cpu_buffer->reader_lock); - local_irq_restore(flags); + read_buffer_unlock(cpu_buffer, flags, locked); + out: preempt_enable(); @@ -3497,17 +3516,18 @@ ring_buffer_read_start(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; + int locked; if (!iter) return; cpu_buffer = iter->cpu_buffer; - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + locked = read_buffer_lock(cpu_buffer, &flags); arch_spin_lock(&cpu_buffer->lock); rb_iter_reset(iter); arch_spin_unlock(&cpu_buffer->lock); - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + read_buffer_unlock(cpu_buffer, flags, locked); } EXPORT_SYMBOL_GPL(ring_buffer_read_start); @@ -3541,8 +3561,9 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_event *event; struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; unsigned long flags; + int locked; - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + locked = read_buffer_lock(cpu_buffer, &flags); again: event = rb_iter_peek(iter, ts); if (!event) @@ -3553,7 +3574,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) rb_advance_iter(iter); out: - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + read_buffer_unlock(cpu_buffer, flags, locked); return event; } @@ -3618,13 +3639,14 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; unsigned long flags; + int locked; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; atomic_inc(&cpu_buffer->record_disabled); - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + locked = read_buffer_lock(cpu_buffer, &flags); if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing))) goto out; @@ -3636,7 +3658,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) arch_spin_unlock(&cpu_buffer->lock); out: - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + read_buffer_unlock(cpu_buffer, flags, locked); atomic_dec(&cpu_buffer->record_disabled); } @@ -3663,22 +3685,16 @@ int ring_buffer_empty(struct ring_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; - int dolock; + int locked; int cpu; int ret; - dolock = rb_ok_to_lock(); - /* yes this is racy, but if you don't like the race, lock the buffer */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; - local_irq_save(flags); - if (dolock) - raw_spin_lock(&cpu_buffer->reader_lock); + locked = read_buffer_lock(cpu_buffer, &flags); ret = rb_per_cpu_empty(cpu_buffer); - if (dolock) - raw_spin_unlock(&cpu_buffer->reader_lock); - local_irq_restore(flags); + read_buffer_unlock(cpu_buffer, flags, locked); if (!ret) return 0; @@ -3697,22 +3713,16 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; - int dolock; + int locked; int ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 1; - dolock = rb_ok_to_lock(); - cpu_buffer = buffer->buffers[cpu]; - local_irq_save(flags); - if (dolock) - raw_spin_lock(&cpu_buffer->reader_lock); + locked = read_buffer_lock(cpu_buffer, &flags); ret = rb_per_cpu_empty(cpu_buffer); - if (dolock) - raw_spin_unlock(&cpu_buffer->reader_lock); - local_irq_restore(flags); + read_buffer_unlock(cpu_buffer, flags, locked); return ret; } @@ -3887,6 +3897,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer, unsigned int commit; unsigned int read; u64 save_timestamp; + int locked; int ret = -1; if (!cpumask_test_cpu(cpu, buffer->cpumask)) @@ -3908,7 +3919,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer, if (!bpage) goto out; - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + locked = read_buffer_lock(cpu_buffer, &flags); reader = rb_get_reader_page(cpu_buffer); if (!reader) @@ -4032,7 +4043,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer, memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit); out_unlock: - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + read_buffer_unlock(cpu_buffer, flags, locked); out: return ret; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f2bd275bb60f..9b2e20893033 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -359,11 +359,13 @@ static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler); */ void trace_wake_up(void) { +#ifndef CONFIG_PREEMPT_RT_FULL const unsigned long delay = msecs_to_jiffies(2); if (trace_flags & TRACE_ITER_BLOCK) return; schedule_delayed_work(&wakeup_work, delay); +#endif } static int __init set_buf_size(char *str) @@ -719,6 +721,12 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) } #endif /* CONFIG_TRACER_MAX_TRACE */ +#ifndef CONFIG_PREEMPT_RT_FULL +static void default_wait_pipe(struct trace_iterator *iter); +#else +#define default_wait_pipe poll_wait_pipe +#endif + /** * register_tracer - register a tracer with the ftrace system. * @type - the plugin for the tracer @@ -1123,6 +1131,8 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); + + entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; } EXPORT_SYMBOL_GPL(tracing_generic_entry_update); @@ -1850,9 +1860,10 @@ static void print_lat_help_header(struct seq_file *m) seq_puts(m, "# | / _----=> need-resched \n"); seq_puts(m, "# || / _---=> hardirq/softirq \n"); seq_puts(m, "# ||| / _--=> preempt-depth \n"); - seq_puts(m, "# |||| / delay \n"); - seq_puts(m, "# cmd pid ||||| time | caller \n"); - seq_puts(m, "# \\ / ||||| \\ | / \n"); + seq_puts(m, "# |||| / _--=> migrate-disable\n"); + seq_puts(m, "# ||||| / delay \n"); + seq_puts(m, "# cmd pid |||||| time | caller \n"); + seq_puts(m, "# \\ / ||||| \\ | / \n"); } static void print_func_help_header(struct seq_file *m) @@ -3189,6 +3200,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) return 0; } +#ifndef CONFIG_PREEMPT_RT_FULL static unsigned int tracing_poll_pipe(struct file *filp, poll_table *poll_table) { @@ -3210,8 +3222,7 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table) } } - -void default_wait_pipe(struct trace_iterator *iter) +static void default_wait_pipe(struct trace_iterator *iter) { DEFINE_WAIT(wait); @@ -3222,6 +3233,20 @@ void default_wait_pipe(struct trace_iterator *iter) finish_wait(&trace_wait, &wait); } +#else +static unsigned int +tracing_poll_pipe(struct file *filp, poll_table *poll_table) +{ + struct trace_iterator *iter = filp->private_data; + + if ((trace_flags & TRACE_ITER_BLOCK) || !trace_empty(iter)) + return POLLIN | POLLRDNORM; + poll_wait_pipe(iter); + if (!trace_empty(iter)) + return POLLIN | POLLRDNORM; + return 0; +} +#endif /* * This is a make-shift waitqueue. diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 092e1f8d18dc..69b87009854c 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -345,7 +345,6 @@ void trace_init_global_iter(struct trace_iterator *iter); void tracing_iter_reset(struct trace_iterator *iter, int cpu); -void default_wait_pipe(struct trace_iterator *iter); void poll_wait_pipe(struct trace_iterator *iter); void ftrace(struct trace_array *tr, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index c212a7f934ec..69cc90808ed5 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -116,7 +116,8 @@ static int trace_define_common_fields(void) __common_field(unsigned char, flags); __common_field(unsigned char, preempt_count); __common_field(int, pid); - __common_field(int, padding); + __common_field(unsigned short, migrate_disable); + __common_field(unsigned short, padding); return ret; } diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 20dad0d7a163..1e6c33ea78b4 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -17,6 +17,7 @@ #include <linux/fs.h> #include "trace.h" +#include <trace/events/hist.h> static struct trace_array *irqsoff_trace __read_mostly; static int tracer_enabled __read_mostly; @@ -426,11 +427,13 @@ void start_critical_timings(void) { if (preempt_trace() || irq_trace()) start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + trace_preemptirqsoff_hist(TRACE_START, 1); } EXPORT_SYMBOL_GPL(start_critical_timings); void stop_critical_timings(void) { + trace_preemptirqsoff_hist(TRACE_STOP, 0); if (preempt_trace() || irq_trace()) stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } @@ -440,6 +443,7 @@ EXPORT_SYMBOL_GPL(stop_critical_timings); #ifdef CONFIG_PROVE_LOCKING void time_hardirqs_on(unsigned long a0, unsigned long a1) { + trace_preemptirqsoff_hist(IRQS_ON, 0); if (!preempt_trace() && irq_trace()) stop_critical_timing(a0, a1); } @@ -448,6 +452,7 @@ void time_hardirqs_off(unsigned long a0, unsigned long a1) { if (!preempt_trace() && irq_trace()) start_critical_timing(a0, a1); + trace_preemptirqsoff_hist(IRQS_OFF, 1); } #else /* !CONFIG_PROVE_LOCKING */ @@ -473,6 +478,7 @@ inline void print_irqtrace_events(struct task_struct *curr) */ void trace_hardirqs_on(void) { + trace_preemptirqsoff_hist(IRQS_ON, 0); if (!preempt_trace() && irq_trace()) stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } @@ -482,11 +488,13 @@ void trace_hardirqs_off(void) { if (!preempt_trace() && irq_trace()) start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + trace_preemptirqsoff_hist(IRQS_OFF, 1); } EXPORT_SYMBOL(trace_hardirqs_off); void trace_hardirqs_on_caller(unsigned long caller_addr) { + trace_preemptirqsoff_hist(IRQS_ON, 0); if (!preempt_trace() && irq_trace()) stop_critical_timing(CALLER_ADDR0, caller_addr); } @@ -496,6 +504,7 @@ void trace_hardirqs_off_caller(unsigned long caller_addr) { if (!preempt_trace() && irq_trace()) start_critical_timing(CALLER_ADDR0, caller_addr); + trace_preemptirqsoff_hist(IRQS_OFF, 1); } EXPORT_SYMBOL(trace_hardirqs_off_caller); @@ -505,12 +514,14 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller); #ifdef CONFIG_PREEMPT_TRACER void trace_preempt_on(unsigned long a0, unsigned long a1) { + trace_preemptirqsoff_hist(PREEMPT_ON, 0); if (preempt_trace() && !irq_trace()) stop_critical_timing(a0, a1); } void trace_preempt_off(unsigned long a0, unsigned long a1) { + trace_preemptirqsoff_hist(PREEMPT_ON, 1); if (preempt_trace() && !irq_trace()) start_critical_timing(a0, a1); } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 51999309a6cf..c93de84fb8eb 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -591,6 +591,11 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) else ret = trace_seq_putc(s, '.'); + if (entry->migrate_disable) + ret = trace_seq_printf(s, "%x", entry->migrate_disable); + else + ret = trace_seq_putc(s, '.'); + return ret; } diff --git a/kernel/user.c b/kernel/user.c index 71dd2363ab0f..b831e51c3489 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -129,11 +129,11 @@ void free_uid(struct user_struct *up) if (!up) return; - local_irq_save(flags); + local_irq_save_nort(flags); if (atomic_dec_and_lock(&up->__count, &uidhash_lock)) free_user(up, flags); else - local_irq_restore(flags); + local_irq_restore_nort(flags); } struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) diff --git a/kernel/wait-simple.c b/kernel/wait-simple.c new file mode 100644 index 000000000000..9e53eaaa4b68 --- /dev/null +++ b/kernel/wait-simple.c @@ -0,0 +1,63 @@ +/* + * Simple waitqueues without fancy flags and callbacks + * + * (C) 2011 Thomas Gleixner <tglx@linutronix.de> + * + * Based on kernel/wait.c + * + * For licencing details see kernel-base/COPYING + */ +#include <linux/init.h> +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/wait-simple.h> + +void __init_swait_head(struct swait_head *head, struct lock_class_key *key) +{ + raw_spin_lock_init(&head->lock); + lockdep_set_class(&head->lock, key); + INIT_LIST_HEAD(&head->list); +} +EXPORT_SYMBOL_GPL(__init_swait_head); + +void swait_prepare(struct swait_head *head, struct swaiter *w, int state) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&head->lock, flags); + w->task = current; + __swait_enqueue(head, w); + set_current_state(state); + raw_spin_unlock_irqrestore(&head->lock, flags); +} +EXPORT_SYMBOL_GPL(swait_prepare); + +void swait_finish(struct swait_head *head, struct swaiter *w) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + if (w->task) { + raw_spin_lock_irqsave(&head->lock, flags); + __swait_dequeue(w); + raw_spin_unlock_irqrestore(&head->lock, flags); + } +} +EXPORT_SYMBOL_GPL(swait_finish); + +void __swait_wake(struct swait_head *head, unsigned int state) +{ + struct swaiter *curr, *next; + unsigned long flags; + + raw_spin_lock_irqsave(&head->lock, flags); + + list_for_each_entry_safe(curr, next, &head->list, node) { + if (wake_up_state(curr->task, state)) { + __swait_dequeue(curr); + curr->task = NULL; + } + } + + raw_spin_unlock_irqrestore(&head->lock, flags); +} diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 1d7bca7f4f52..c0c47d71f844 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -201,6 +201,8 @@ static int is_softlockup(unsigned long touch_ts) #ifdef CONFIG_HARDLOCKUP_DETECTOR +static DEFINE_RAW_SPINLOCK(watchdog_output_lock); + static struct perf_event_attr wd_hw_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, @@ -235,10 +237,19 @@ static void watchdog_overflow_callback(struct perf_event *event, if (__this_cpu_read(hard_watchdog_warn) == true) return; - if (hardlockup_panic) + /* + * If early-printk is enabled then make sure we do not + * lock up in printk() and kill console logging: + */ + printk_kill(); + + if (hardlockup_panic) { panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu); - else + } else { + raw_spin_lock(&watchdog_output_lock); WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu); + raw_spin_unlock(&watchdog_output_lock); + } __this_cpu_write(hard_watchdog_warn, true); return; @@ -425,6 +436,7 @@ static void watchdog_prepare_cpu(int cpu) WARN_ON(per_cpu(softlockup_watchdog, cpu)); hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; + hrtimer->irqsafe = 1; } static int watchdog_enable(int cpu) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 42fa9ad0a810..e7f3e79184dd 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -41,6 +41,7 @@ #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> +#include <linux/delay.h> #include "workqueue_sched.h" @@ -57,20 +58,10 @@ enum { WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ - WORKER_ROGUE = 1 << 4, /* not bound to any cpu */ - WORKER_REBIND = 1 << 5, /* mom is home, come back */ - WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ - WORKER_UNBOUND = 1 << 7, /* worker is unbound */ + WORKER_CPU_INTENSIVE = 1 << 4, /* cpu intensive */ + WORKER_UNBOUND = 1 << 5, /* worker is unbound */ - WORKER_NOT_RUNNING = WORKER_PREP | WORKER_ROGUE | WORKER_REBIND | - WORKER_CPU_INTENSIVE | WORKER_UNBOUND, - - /* gcwq->trustee_state */ - TRUSTEE_START = 0, /* start */ - TRUSTEE_IN_CHARGE = 1, /* trustee in charge of gcwq */ - TRUSTEE_BUTCHER = 2, /* butcher workers */ - TRUSTEE_RELEASE = 3, /* release workers */ - TRUSTEE_DONE = 4, /* trustee is done */ + WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND, BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ BUSY_WORKER_HASH_SIZE = 1 << BUSY_WORKER_HASH_ORDER, @@ -84,7 +75,6 @@ enum { (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ - TRUSTEE_COOLDOWN = HZ / 10, /* for trustee draining */ /* * Rescue workers are used only on emergencies and shared by @@ -136,7 +126,7 @@ struct worker { unsigned long last_active; /* L: last active timestamp */ unsigned int flags; /* X: flags */ int id; /* I: worker id */ - struct work_struct rebind_work; /* L: rebind worker to cpu */ + int sleeping; /* None */ }; /* @@ -163,10 +153,8 @@ struct global_cwq { struct ida worker_ida; /* L: for worker IDs */ - struct task_struct *trustee; /* L: for gcwq shutdown */ - unsigned int trustee_state; /* L: trustee state */ - wait_queue_head_t trustee_wait; /* trustee wait */ struct worker *first_idle; /* L: first idle worker */ + wait_queue_head_t idle_wait; } ____cacheline_aligned_in_smp; /* @@ -658,66 +646,58 @@ static void wake_up_worker(struct global_cwq *gcwq) } /** - * wq_worker_waking_up - a worker is waking up - * @task: task waking up - * @cpu: CPU @task is waking up to - * - * This function is called during try_to_wake_up() when a worker is - * being awoken. + * wq_worker_running - a worker is running again + * @task: task returning from sleep * - * CONTEXT: - * spin_lock_irq(rq->lock) + * This function is called when a worker returns from schedule() */ -void wq_worker_waking_up(struct task_struct *task, unsigned int cpu) +void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); + if (!worker->sleeping) + return; if (!(worker->flags & WORKER_NOT_RUNNING)) - atomic_inc(get_gcwq_nr_running(cpu)); + atomic_inc(get_gcwq_nr_running(smp_processor_id())); + worker->sleeping = 0; } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep - * @cpu: CPU in question, must be the current CPU number - * - * This function is called during schedule() when a busy worker is - * going to sleep. Worker on the same cpu can be woken up by - * returning pointer to its task. * - * CONTEXT: - * spin_lock_irq(rq->lock) - * - * RETURNS: - * Worker task on @cpu to wake up, %NULL if none. + * This function is called from schedule() when a busy worker is + * going to sleep. */ -struct task_struct *wq_worker_sleeping(struct task_struct *task, - unsigned int cpu) +void wq_worker_sleeping(struct task_struct *task) { - struct worker *worker = kthread_data(task), *to_wakeup = NULL; - struct global_cwq *gcwq = get_gcwq(cpu); - atomic_t *nr_running = get_gcwq_nr_running(cpu); + struct worker *worker = kthread_data(task); + struct global_cwq *gcwq; + int cpu; if (worker->flags & WORKER_NOT_RUNNING) - return NULL; + return; - /* this can only happen on the local cpu */ - BUG_ON(cpu != raw_smp_processor_id()); + if (WARN_ON_ONCE(worker->sleeping)) + return; + + worker->sleeping = 1; + cpu = smp_processor_id(); + gcwq = get_gcwq(cpu); + spin_lock_irq(&gcwq->lock); /* * The counterpart of the following dec_and_test, implied mb, * worklist not empty test sequence is in insert_work(). * Please read comment there. - * - * NOT_RUNNING is clear. This means that trustee is not in - * charge and we're running on the local cpu w/ rq lock held - * and preemption disabled, which in turn means that none else - * could be manipulating idle_list, so dereferencing idle_list - * without gcwq lock is safe. */ - if (atomic_dec_and_test(nr_running) && !list_empty(&gcwq->worklist)) - to_wakeup = first_worker(gcwq); - return to_wakeup ? to_wakeup->task : NULL; + if (atomic_dec_and_test(get_gcwq_nr_running(cpu)) && + !list_empty(&gcwq->worklist)) { + worker = first_worker(gcwq); + if (worker) + wake_up_process(worker->task); + } + spin_unlock_irq(&gcwq->lock); } /** @@ -979,13 +959,38 @@ static bool is_chained_work(struct workqueue_struct *wq) return false; } -static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, - struct work_struct *work) +static void ___queue_work(struct workqueue_struct *wq, struct global_cwq *gcwq, + struct work_struct *work) { - struct global_cwq *gcwq; struct cpu_workqueue_struct *cwq; struct list_head *worklist; unsigned int work_flags; + + /* gcwq determined, get cwq and queue */ + cwq = get_cwq(gcwq->cpu, wq); + trace_workqueue_queue_work(gcwq->cpu, cwq, work); + + BUG_ON(!list_empty(&work->entry)); + + cwq->nr_in_flight[cwq->work_color]++; + work_flags = work_color_to_flags(cwq->work_color); + + if (likely(cwq->nr_active < cwq->max_active)) { + trace_workqueue_activate_work(work); + cwq->nr_active++; + worklist = gcwq_determine_ins_pos(gcwq, cwq); + } else { + work_flags |= WORK_STRUCT_DELAYED; + worklist = &cwq->delayed_works; + } + + insert_work(cwq, work, worklist, work_flags); +} + +static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, + struct work_struct *work) +{ + struct global_cwq *gcwq; unsigned long flags; debug_work_activate(work); @@ -1031,27 +1036,32 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, spin_lock_irqsave(&gcwq->lock, flags); } - /* gcwq determined, get cwq and queue */ - cwq = get_cwq(gcwq->cpu, wq); - trace_workqueue_queue_work(cpu, cwq, work); + ___queue_work(wq, gcwq, work); - BUG_ON(!list_empty(&work->entry)); + spin_unlock_irqrestore(&gcwq->lock, flags); +} - cwq->nr_in_flight[cwq->work_color]++; - work_flags = work_color_to_flags(cwq->work_color); +/** + * queue_work_on - queue work on specific cpu + * @cpu: CPU number to execute work on + * @wq: workqueue to use + * @work: work to queue + * + * Returns 0 if @work was already on a queue, non-zero otherwise. + * + * We queue the work to a specific CPU, the caller must ensure it + * can't go away. + */ +static int +__queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) +{ + int ret = 0; - if (likely(cwq->nr_active < cwq->max_active)) { - trace_workqueue_activate_work(work); - cwq->nr_active++; - worklist = gcwq_determine_ins_pos(gcwq, cwq); - } else { - work_flags |= WORK_STRUCT_DELAYED; - worklist = &cwq->delayed_works; + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_work(cpu, wq, work); + ret = 1; } - - insert_work(cwq, work, worklist, work_flags); - - spin_unlock_irqrestore(&gcwq->lock, flags); + return ret; } /** @@ -1068,34 +1078,19 @@ int queue_work(struct workqueue_struct *wq, struct work_struct *work) { int ret; - ret = queue_work_on(get_cpu(), wq, work); - put_cpu(); + ret = __queue_work_on(get_cpu_light(), wq, work); + put_cpu_light(); return ret; } EXPORT_SYMBOL_GPL(queue_work); -/** - * queue_work_on - queue work on specific cpu - * @cpu: CPU number to execute work on - * @wq: workqueue to use - * @work: work to queue - * - * Returns 0 if @work was already on a queue, non-zero otherwise. - * - * We queue the work to a specific CPU, the caller must ensure it - * can't go away. - */ int queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { - int ret = 0; + WARN_ON(wq->flags & WQ_NON_AFFINE); - if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { - __queue_work(cpu, wq, work); - ret = 1; - } - return ret; + return __queue_work_on(cpu, wq, work); } EXPORT_SYMBOL_GPL(queue_work_on); @@ -1141,6 +1136,8 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; + WARN_ON((wq->flags & WQ_NON_AFFINE) && cpu != -1); + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { unsigned int lcpu; @@ -1206,12 +1203,13 @@ static void worker_enter_idle(struct worker *worker) /* idle_list is LIFO */ list_add(&worker->entry, &gcwq->idle_list); - if (likely(!(worker->flags & WORKER_ROGUE))) { - if (too_many_workers(gcwq) && !timer_pending(&gcwq->idle_timer)) - mod_timer(&gcwq->idle_timer, - jiffies + IDLE_WORKER_TIMEOUT); - } else - wake_up_all(&gcwq->trustee_wait); + if (gcwq->nr_idle == gcwq->nr_workers) + wake_up_all(&gcwq->idle_wait); + + if (too_many_workers(gcwq) && !timer_pending(&gcwq->idle_timer)) { + mod_timer(&gcwq->idle_timer, + jiffies + IDLE_WORKER_TIMEOUT); + } /* sanity check nr_running */ WARN_ON_ONCE(gcwq->nr_workers == gcwq->nr_idle && @@ -1288,8 +1286,14 @@ __acquires(&gcwq->lock) return false; if (task_cpu(task) == gcwq->cpu && cpumask_equal(¤t->cpus_allowed, - get_cpu_mask(gcwq->cpu))) + get_cpu_mask(gcwq->cpu))) { + /* + * Since we're binding to a particular cpu and need to + * stay there for correctness, mark us PF_THREAD_BOUND. + */ + task->flags |= PF_THREAD_BOUND; return true; + } spin_unlock_irq(&gcwq->lock); /* @@ -1303,20 +1307,15 @@ __acquires(&gcwq->lock) } } -/* - * Function for worker->rebind_work used to rebind rogue busy workers - * to the associated cpu which is coming back online. This is - * scheduled by cpu up but can race with other cpu hotplug operations - * and may be executed twice without intervening cpu down. - */ -static void worker_rebind_fn(struct work_struct *work) +static void worker_unbind_and_unlock(struct worker *worker) { - struct worker *worker = container_of(work, struct worker, rebind_work); struct global_cwq *gcwq = worker->gcwq; + struct task_struct *task = worker->task; - if (worker_maybe_bind_and_lock(worker)) - worker_clr_flags(worker, WORKER_REBIND); - + /* + * Its no longer required we're PF_THREAD_BOUND, the work is done. + */ + task->flags &= ~PF_THREAD_BOUND; spin_unlock_irq(&gcwq->lock); } @@ -1328,7 +1327,6 @@ static struct worker *alloc_worker(void) if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); - INIT_WORK(&worker->rebind_work, worker_rebind_fn); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } @@ -1383,15 +1381,9 @@ static struct worker *create_worker(struct global_cwq *gcwq, bool bind) if (IS_ERR(worker->task)) goto fail; - /* - * A rogue worker will become a regular one if CPU comes - * online later on. Make sure every worker has - * PF_THREAD_BOUND set. - */ if (bind && !on_unbound_cpu) kthread_bind(worker->task, gcwq->cpu); else { - worker->task->flags |= PF_THREAD_BOUND; if (on_unbound_cpu) worker->flags |= WORKER_UNBOUND; } @@ -1668,13 +1660,6 @@ static bool manage_workers(struct worker *worker) gcwq->flags &= ~GCWQ_MANAGING_WORKERS; - /* - * The trustee might be waiting to take over the manager - * position, tell it we're done. - */ - if (unlikely(gcwq->trustee)) - wake_up_all(&gcwq->trustee_wait); - return ret; } @@ -2075,7 +2060,7 @@ repeat: if (keep_working(gcwq)) wake_up_worker(gcwq); - spin_unlock_irq(&gcwq->lock); + worker_unbind_and_unlock(rescuer); } schedule(); @@ -3024,7 +3009,6 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, if (IS_ERR(rescuer->task)) goto err; - rescuer->task->flags |= PF_THREAD_BOUND; wake_up_process(rescuer->task); } @@ -3214,171 +3198,76 @@ EXPORT_SYMBOL_GPL(work_busy); * gcwqs serve mix of short, long and very long running works making * blocked draining impractical. * - * This is solved by allowing a gcwq to be detached from CPU, running - * it with unbound (rogue) workers and allowing it to be reattached - * later if the cpu comes back online. A separate thread is created - * to govern a gcwq in such state and is called the trustee of the - * gcwq. - * - * Trustee states and their descriptions. - * - * START Command state used on startup. On CPU_DOWN_PREPARE, a - * new trustee is started with this state. - * - * IN_CHARGE Once started, trustee will enter this state after - * assuming the manager role and making all existing - * workers rogue. DOWN_PREPARE waits for trustee to - * enter this state. After reaching IN_CHARGE, trustee - * tries to execute the pending worklist until it's empty - * and the state is set to BUTCHER, or the state is set - * to RELEASE. - * - * BUTCHER Command state which is set by the cpu callback after - * the cpu has went down. Once this state is set trustee - * knows that there will be no new works on the worklist - * and once the worklist is empty it can proceed to - * killing idle workers. - * - * RELEASE Command state which is set by the cpu callback if the - * cpu down has been canceled or it has come online - * again. After recognizing this state, trustee stops - * trying to drain or butcher and clears ROGUE, rebinds - * all remaining workers back to the cpu and releases - * manager role. - * - * DONE Trustee will enter this state after BUTCHER or RELEASE - * is complete. - * - * trustee CPU draining - * took over down complete - * START -----------> IN_CHARGE -----------> BUTCHER -----------> DONE - * | | ^ - * | CPU is back online v return workers | - * ----------------> RELEASE -------------- */ -/** - * trustee_wait_event_timeout - timed event wait for trustee - * @cond: condition to wait for - * @timeout: timeout in jiffies - * - * wait_event_timeout() for trustee to use. Handles locking and - * checks for RELEASE request. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed - * multiple times. To be used by trustee. - * - * RETURNS: - * Positive indicating left time if @cond is satisfied, 0 if timed - * out, -1 if canceled. - */ -#define trustee_wait_event_timeout(cond, timeout) ({ \ - long __ret = (timeout); \ - while (!((cond) || (gcwq->trustee_state == TRUSTEE_RELEASE)) && \ - __ret) { \ - spin_unlock_irq(&gcwq->lock); \ - __wait_event_timeout(gcwq->trustee_wait, (cond) || \ - (gcwq->trustee_state == TRUSTEE_RELEASE), \ - __ret); \ - spin_lock_irq(&gcwq->lock); \ - } \ - gcwq->trustee_state == TRUSTEE_RELEASE ? -1 : (__ret); \ -}) +static int __devinit workqueue_cpu_up_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + struct global_cwq *gcwq = get_gcwq(cpu); + struct worker *uninitialized_var(new_worker); + unsigned long flags; -/** - * trustee_wait_event - event wait for trustee - * @cond: condition to wait for - * - * wait_event() for trustee to use. Automatically handles locking and - * checks for CANCEL request. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed - * multiple times. To be used by trustee. - * - * RETURNS: - * 0 if @cond is satisfied, -1 if canceled. - */ -#define trustee_wait_event(cond) ({ \ - long __ret1; \ - __ret1 = trustee_wait_event_timeout(cond, MAX_SCHEDULE_TIMEOUT);\ - __ret1 < 0 ? -1 : 0; \ -}) + action &= ~CPU_TASKS_FROZEN; -static int __cpuinit trustee_thread(void *__gcwq) -{ - struct global_cwq *gcwq = __gcwq; - struct worker *worker; - struct work_struct *work; - struct hlist_node *pos; - long rc; - int i; + switch (action) { + case CPU_UP_PREPARE: + BUG_ON(gcwq->first_idle); + new_worker = create_worker(gcwq, false); + if (!new_worker) + return NOTIFY_BAD; + case CPU_UP_CANCELED: + case CPU_ONLINE: + break; + default: + return notifier_from_errno(0); + } - BUG_ON(gcwq->cpu != smp_processor_id()); + /* some are called w/ irq disabled, don't disturb irq status */ + spin_lock_irqsave(&gcwq->lock, flags); - spin_lock_irq(&gcwq->lock); - /* - * Claim the manager position and make all workers rogue. - * Trustee must be bound to the target cpu and can't be - * cancelled. - */ - BUG_ON(gcwq->cpu != smp_processor_id()); - rc = trustee_wait_event(!(gcwq->flags & GCWQ_MANAGING_WORKERS)); - BUG_ON(rc < 0); + switch (action) { + case CPU_UP_PREPARE: + BUG_ON(gcwq->first_idle); + gcwq->first_idle = new_worker; + break; - gcwq->flags |= GCWQ_MANAGING_WORKERS; + case CPU_UP_CANCELED: + destroy_worker(gcwq->first_idle); + gcwq->first_idle = NULL; + break; - list_for_each_entry(worker, &gcwq->idle_list, entry) - worker->flags |= WORKER_ROGUE; + case CPU_ONLINE: + spin_unlock_irq(&gcwq->lock); + kthread_bind(gcwq->first_idle->task, cpu); + spin_lock_irq(&gcwq->lock); + gcwq->flags |= GCWQ_MANAGE_WORKERS; + start_worker(gcwq->first_idle); + gcwq->first_idle = NULL; + break; + } - for_each_busy_worker(worker, i, pos, gcwq) - worker->flags |= WORKER_ROGUE; + spin_unlock_irqrestore(&gcwq->lock, flags); - /* - * Call schedule() so that we cross rq->lock and thus can - * guarantee sched callbacks see the rogue flag. This is - * necessary as scheduler callbacks may be invoked from other - * cpus. - */ - spin_unlock_irq(&gcwq->lock); - schedule(); - spin_lock_irq(&gcwq->lock); + return notifier_from_errno(0); +} - /* - * Sched callbacks are disabled now. Zap nr_running. After - * this, nr_running stays zero and need_more_worker() and - * keep_working() are always true as long as the worklist is - * not empty. - */ - atomic_set(get_gcwq_nr_running(gcwq->cpu), 0); +static void flush_gcwq(struct global_cwq *gcwq) +{ + struct work_struct *work, *nw; + struct worker *worker, *n; + LIST_HEAD(non_affine_works); - spin_unlock_irq(&gcwq->lock); - del_timer_sync(&gcwq->idle_timer); spin_lock_irq(&gcwq->lock); + list_for_each_entry_safe(work, nw, &gcwq->worklist, entry) { + struct workqueue_struct *wq = get_work_cwq(work)->wq; - /* - * We're now in charge. Notify and proceed to drain. We need - * to keep the gcwq running during the whole CPU down - * procedure as other cpu hotunplug callbacks may need to - * flush currently running tasks. - */ - gcwq->trustee_state = TRUSTEE_IN_CHARGE; - wake_up_all(&gcwq->trustee_wait); + if (wq->flags & WQ_NON_AFFINE) + list_move(&work->entry, &non_affine_works); + } - /* - * The original cpu is in the process of dying and may go away - * anytime now. When that happens, we and all workers would - * be migrated to other cpus. Try draining any left work. We - * want to get it over with ASAP - spam rescuers, wake up as - * many idlers as necessary and create new ones till the - * worklist is empty. Note that if the gcwq is frozen, there - * may be frozen works in freezable cwqs. Don't declare - * completion while frozen. - */ - while (gcwq->nr_workers != gcwq->nr_idle || - gcwq->flags & GCWQ_FREEZING || - gcwq->trustee_state == TRUSTEE_IN_CHARGE) { + while (!list_empty(&gcwq->worklist)) { int nr_works = 0; list_for_each_entry(work, &gcwq->worklist, entry) { @@ -3392,189 +3281,54 @@ static int __cpuinit trustee_thread(void *__gcwq) wake_up_process(worker->task); } + spin_unlock_irq(&gcwq->lock); + if (need_to_create_worker(gcwq)) { - spin_unlock_irq(&gcwq->lock); - worker = create_worker(gcwq, false); - spin_lock_irq(&gcwq->lock); - if (worker) { - worker->flags |= WORKER_ROGUE; + worker = create_worker(gcwq, true); + if (worker) start_worker(worker); - } } - /* give a breather */ - if (trustee_wait_event_timeout(false, TRUSTEE_COOLDOWN) < 0) - break; - } - - /* - * Either all works have been scheduled and cpu is down, or - * cpu down has already been canceled. Wait for and butcher - * all workers till we're canceled. - */ - do { - rc = trustee_wait_event(!list_empty(&gcwq->idle_list)); - while (!list_empty(&gcwq->idle_list)) - destroy_worker(list_first_entry(&gcwq->idle_list, - struct worker, entry)); - } while (gcwq->nr_workers && rc >= 0); + wait_event_timeout(gcwq->idle_wait, + gcwq->nr_idle == gcwq->nr_workers, HZ/10); - /* - * At this point, either draining has completed and no worker - * is left, or cpu down has been canceled or the cpu is being - * brought back up. There shouldn't be any idle one left. - * Tell the remaining busy ones to rebind once it finishes the - * currently scheduled works by scheduling the rebind_work. - */ - WARN_ON(!list_empty(&gcwq->idle_list)); - - for_each_busy_worker(worker, i, pos, gcwq) { - struct work_struct *rebind_work = &worker->rebind_work; - - /* - * Rebind_work may race with future cpu hotplug - * operations. Use a separate flag to mark that - * rebinding is scheduled. - */ - worker->flags |= WORKER_REBIND; - worker->flags &= ~WORKER_ROGUE; + spin_lock_irq(&gcwq->lock); + } - /* queue rebind_work, wq doesn't matter, use the default one */ - if (test_and_set_bit(WORK_STRUCT_PENDING_BIT, - work_data_bits(rebind_work))) - continue; + WARN_ON(gcwq->nr_workers != gcwq->nr_idle); - debug_work_activate(rebind_work); - insert_work(get_cwq(gcwq->cpu, system_wq), rebind_work, - worker->scheduled.next, - work_color_to_flags(WORK_NO_COLOR)); - } + list_for_each_entry_safe(worker, n, &gcwq->idle_list, entry) + destroy_worker(worker); - /* relinquish manager role */ - gcwq->flags &= ~GCWQ_MANAGING_WORKERS; + WARN_ON(gcwq->nr_workers || gcwq->nr_idle); - /* notify completion */ - gcwq->trustee = NULL; - gcwq->trustee_state = TRUSTEE_DONE; - wake_up_all(&gcwq->trustee_wait); spin_unlock_irq(&gcwq->lock); - return 0; -} -/** - * wait_trustee_state - wait for trustee to enter the specified state - * @gcwq: gcwq the trustee of interest belongs to - * @state: target state to wait for - * - * Wait for the trustee to reach @state. DONE is already matched. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed - * multiple times. To be used by cpu_callback. - */ -static void __cpuinit wait_trustee_state(struct global_cwq *gcwq, int state) -__releases(&gcwq->lock) -__acquires(&gcwq->lock) -{ - if (!(gcwq->trustee_state == state || - gcwq->trustee_state == TRUSTEE_DONE)) { - spin_unlock_irq(&gcwq->lock); - __wait_event(gcwq->trustee_wait, - gcwq->trustee_state == state || - gcwq->trustee_state == TRUSTEE_DONE); - spin_lock_irq(&gcwq->lock); + gcwq = get_gcwq(get_cpu_light()); + spin_lock_irq(&gcwq->lock); + list_for_each_entry_safe(work, nw, &non_affine_works, entry) { + list_del_init(&work->entry); + ___queue_work(get_work_cwq(work)->wq, gcwq, work); } + spin_unlock_irq(&gcwq->lock); + put_cpu_light(); } -static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, +static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; struct global_cwq *gcwq = get_gcwq(cpu); - struct task_struct *new_trustee = NULL; - struct worker *uninitialized_var(new_worker); - unsigned long flags; action &= ~CPU_TASKS_FROZEN; - switch (action) { - case CPU_DOWN_PREPARE: - new_trustee = kthread_create(trustee_thread, gcwq, - "workqueue_trustee/%d\n", cpu); - if (IS_ERR(new_trustee)) - return notifier_from_errno(PTR_ERR(new_trustee)); - kthread_bind(new_trustee, cpu); - /* fall through */ - case CPU_UP_PREPARE: - BUG_ON(gcwq->first_idle); - new_worker = create_worker(gcwq, false); - if (!new_worker) { - if (new_trustee) - kthread_stop(new_trustee); - return NOTIFY_BAD; - } - } + switch (action) { + case CPU_DOWN_PREPARE: + flush_gcwq(gcwq); + break; + } - /* some are called w/ irq disabled, don't disturb irq status */ - spin_lock_irqsave(&gcwq->lock, flags); - - switch (action) { - case CPU_DOWN_PREPARE: - /* initialize trustee and tell it to acquire the gcwq */ - BUG_ON(gcwq->trustee || gcwq->trustee_state != TRUSTEE_DONE); - gcwq->trustee = new_trustee; - gcwq->trustee_state = TRUSTEE_START; - wake_up_process(gcwq->trustee); - wait_trustee_state(gcwq, TRUSTEE_IN_CHARGE); - /* fall through */ - case CPU_UP_PREPARE: - BUG_ON(gcwq->first_idle); - gcwq->first_idle = new_worker; - break; - - case CPU_DYING: - /* - * Before this, the trustee and all workers except for - * the ones which are still executing works from - * before the last CPU down must be on the cpu. After - * this, they'll all be diasporas. - */ - gcwq->flags |= GCWQ_DISASSOCIATED; - break; - - case CPU_POST_DEAD: - gcwq->trustee_state = TRUSTEE_BUTCHER; - /* fall through */ - case CPU_UP_CANCELED: - destroy_worker(gcwq->first_idle); - gcwq->first_idle = NULL; - break; - - case CPU_DOWN_FAILED: - case CPU_ONLINE: - gcwq->flags &= ~GCWQ_DISASSOCIATED; - if (gcwq->trustee_state != TRUSTEE_DONE) { - gcwq->trustee_state = TRUSTEE_RELEASE; - wake_up_process(gcwq->trustee); - wait_trustee_state(gcwq, TRUSTEE_DONE); - } - - /* - * Trustee is done and there might be no worker left. - * Put the first_idle in and request a real manager to - * take a look. - */ - spin_unlock_irq(&gcwq->lock); - kthread_bind(gcwq->first_idle->task, cpu); - spin_lock_irq(&gcwq->lock); - gcwq->flags |= GCWQ_MANAGE_WORKERS; - start_worker(gcwq->first_idle); - gcwq->first_idle = NULL; - break; - } - - spin_unlock_irqrestore(&gcwq->lock, flags); return notifier_from_errno(0); } @@ -3772,7 +3526,8 @@ static int __init init_workqueues(void) unsigned int cpu; int i; - cpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE); + cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_ACTIVE); + hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_INACTIVE); /* initialize gcwqs */ for_each_gcwq_cpu(cpu) { @@ -3795,9 +3550,7 @@ static int __init init_workqueues(void) (unsigned long)gcwq); ida_init(&gcwq->worker_ida); - - gcwq->trustee_state = TRUSTEE_DONE; - init_waitqueue_head(&gcwq->trustee_wait); + init_waitqueue_head(&gcwq->idle_wait); } /* create the initial worker */ diff --git a/kernel/workqueue_sched.h b/kernel/workqueue_sched.h index 2d10fc98dc79..3bf73e24e1ea 100644 --- a/kernel/workqueue_sched.h +++ b/kernel/workqueue_sched.h @@ -4,6 +4,5 @@ * Scheduler hooks for concurrency managed workqueue. Only to be * included from sched.c and workqueue.c. */ -void wq_worker_waking_up(struct task_struct *task, unsigned int cpu); -struct task_struct *wq_worker_sleeping(struct task_struct *task, - unsigned int cpu); +void wq_worker_running(struct task_struct *task); +void wq_worker_sleeping(struct task_struct *task); |