diff options
Diffstat (limited to 'kernel')
67 files changed, 5815 insertions, 821 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index d2b32ac..8bb92eb 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -222,4 +222,4 @@ endif config MUTEX_SPIN_ON_OWNER def_bool y - depends on SMP && !DEBUG_MUTEXES + depends on SMP && !DEBUG_MUTEXES && !PREEMPT_RT_FULL diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 3f9c974..11dbe26 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -1,3 +1,16 @@ +config PREEMPT + bool + select PREEMPT_COUNT + +config PREEMPT_RT_BASE + bool + select PREEMPT + +config HAVE_PREEMPT_LAZY + bool + +config PREEMPT_LAZY + def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL choice prompt "Preemption Model" @@ -33,9 +46,9 @@ 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 select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK help This option reduces the latency of the kernel by making @@ -52,6 +65,22 @@ 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 preemptible + RT kernel. + +config PREEMPT_RT_FULL + bool "Fully Preemptible Kernel (RT)" + depends on IRQ_FORCED_THREADING + select PREEMPT_RT_BASE + select PREEMPT_RCU + help + All and everything + endchoice config PREEMPT_COUNT diff --git a/kernel/Makefile b/kernel/Makefile index 1ce4755..b3ff0a8 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -7,10 +7,10 @@ obj-y = fork.o exec_domain.o panic.o \ sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o task_work.o \ rcupdate.o extable.o params.o posix-timers.o \ - kthread.o wait.o sys_ni.o posix-cpu-timers.o mutex.o \ - hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ + kthread.o wait.o sys_ni.o posix-cpu-timers.o \ + hrtimer.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o cred.o reboot.o \ - async.o range.o groups.o lglock.o smpboot.o + async.o range.o groups.o lglock.o smpboot.o wait-simple.o ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files @@ -33,7 +33,11 @@ obj-$(CONFIG_FREEZER) += freezer.o obj-$(CONFIG_PROFILING) += profile.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 @@ -45,6 +49,7 @@ 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 d7f07a2..ba7416b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -63,6 +63,290 @@ static struct { .refcount = 0, }; +/** + * hotplug_pcp - per cpu hotplug descriptor + * @unplug: set when pin_current_cpu() needs to sync tasks + * @sync_tsk: the task that waits for tasks to finish pinned sections + * @refcount: counter of tasks in pinned sections + * @grab_lock: set when the tasks entering pinned sections should wait + * @synced: notifier for @sync_tsk to tell cpu_down it's finished + * @mutex: the mutex to make tasks wait (used when @grab_lock is true) + * @mutex_init: zero if the mutex hasn't been initialized yet. + * + * Although @unplug and @sync_tsk may point to the same task, the @unplug + * is used as a flag and still exists after @sync_tsk has exited and + * @sync_tsk set to NULL. + */ +struct hotplug_pcp { + struct task_struct *unplug; + struct task_struct *sync_tsk; + int refcount; + int grab_lock; + struct completion synced; + struct completion unplug_wait; +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * Note, on PREEMPT_RT, the hotplug lock must save the state of + * the task, otherwise the mutex will cause the task to fail + * to sleep when required. (Because it's called from migrate_disable()) + * + * The spinlock_t on PREEMPT_RT is a mutex that saves the task's + * state. + */ + spinlock_t lock; +#else + struct mutex mutex; +#endif + int mutex_init; +}; + +#ifdef CONFIG_PREEMPT_RT_FULL +# define hotplug_lock(hp) rt_spin_lock(&(hp)->lock) +# define hotplug_unlock(hp) rt_spin_unlock(&(hp)->lock) +#else +# define hotplug_lock(hp) mutex_lock(&(hp)->mutex) +# define hotplug_unlock(hp) mutex_unlock(&(hp)->mutex) +#endif + +static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp); + +/** + * pin_current_cpu - Prevent the current cpu from being unplugged + * + * Lightweight version of get_online_cpus() to prevent cpu from being + * unplugged when code runs in a migration disabled region. + * + * Must be called with preemption disabled (preempt_count = 1)! + */ +void pin_current_cpu(void) +{ + struct hotplug_pcp *hp; + int force = 0; + +retry: + hp = &__get_cpu_var(hotplug_pcp); + + if (!hp->unplug || hp->refcount || force || preempt_count() > 1 || + hp->unplug == current) { + hp->refcount++; + return; + } + if (hp->grab_lock) { + preempt_enable(); + hotplug_lock(hp); + hotplug_unlock(hp); + } else { + preempt_enable(); + /* + * Try to push this task off of this CPU. + */ + if (!migrate_me()) { + preempt_disable(); + hp = &__get_cpu_var(hotplug_pcp); + if (!hp->grab_lock) { + /* + * Just let it continue it's already pinned + * or about to sleep. + */ + force = 1; + goto retry; + } + preempt_enable(); + } + } + preempt_disable(); + goto retry; +} + +/** + * unpin_current_cpu - Allow unplug of current cpu + * + * Must be called with preemption or interrupts disabled! + */ +void unpin_current_cpu(void) +{ + struct hotplug_pcp *hp = &__get_cpu_var(hotplug_pcp); + + WARN_ON(hp->refcount <= 0); + + /* This is safe. sync_unplug_thread is pinned to this cpu */ + if (!--hp->refcount && hp->unplug && hp->unplug != current) + wake_up_process(hp->unplug); +} + +static void wait_for_pinned_cpus(struct hotplug_pcp *hp) +{ + set_current_state(TASK_UNINTERRUPTIBLE); + while (hp->refcount) { + schedule_preempt_disabled(); + set_current_state(TASK_UNINTERRUPTIBLE); + } +} + +static int sync_unplug_thread(void *data) +{ + struct hotplug_pcp *hp = data; + + wait_for_completion(&hp->unplug_wait); + preempt_disable(); + hp->unplug = current; + wait_for_pinned_cpus(hp); + + /* + * This thread will synchronize the cpu_down() with threads + * that have pinned the CPU. When the pinned CPU count reaches + * zero, we inform the cpu_down code to continue to the next step. + */ + set_current_state(TASK_UNINTERRUPTIBLE); + preempt_enable(); + complete(&hp->synced); + + /* + * If all succeeds, the next step will need tasks to wait till + * the CPU is offline before continuing. To do this, the grab_lock + * is set and tasks going into pin_current_cpu() will block on the + * mutex. But we still need to wait for those that are already in + * pinned CPU sections. If the cpu_down() failed, the kthread_should_stop() + * will kick this thread out. + */ + while (!hp->grab_lock && !kthread_should_stop()) { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + + /* Make sure grab_lock is seen before we see a stale completion */ + smp_mb(); + + /* + * Now just before cpu_down() enters stop machine, we need to make + * sure all tasks that are in pinned CPU sections are out, and new + * tasks will now grab the lock, keeping them from entering pinned + * CPU sections. + */ + if (!kthread_should_stop()) { + preempt_disable(); + wait_for_pinned_cpus(hp); + preempt_enable(); + complete(&hp->synced); + } + + set_current_state(TASK_UNINTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + set_current_state(TASK_RUNNING); + + /* + * Force this thread off this CPU as it's going down and + * we don't want any more work on this CPU. + */ + current->flags &= ~PF_NO_SETAFFINITY; + do_set_cpus_allowed(current, cpu_present_mask); + migrate_me(); + return 0; +} + +static void __cpu_unplug_sync(struct hotplug_pcp *hp) +{ + wake_up_process(hp->sync_tsk); + wait_for_completion(&hp->synced); +} + +static void __cpu_unplug_wait(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + complete(&hp->unplug_wait); + wait_for_completion(&hp->synced); +} + +/* + * Start the sync_unplug_thread on the target cpu and wait for it to + * complete. + */ +static int cpu_unplug_begin(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + int err; + + /* Protected by cpu_hotplug.lock */ + if (!hp->mutex_init) { +#ifdef CONFIG_PREEMPT_RT_FULL + spin_lock_init(&hp->lock); +#else + mutex_init(&hp->mutex); +#endif + hp->mutex_init = 1; + } + + /* Inform the scheduler to migrate tasks off this CPU */ + tell_sched_cpu_down_begin(cpu); + + init_completion(&hp->synced); + init_completion(&hp->unplug_wait); + + hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); + if (IS_ERR(hp->sync_tsk)) { + err = PTR_ERR(hp->sync_tsk); + hp->sync_tsk = NULL; + return err; + } + kthread_bind(hp->sync_tsk, cpu); + + /* + * Wait for tasks to get out of the pinned sections, + * it's still OK if new tasks enter. Some CPU notifiers will + * wait for tasks that are going to enter these sections and + * we must not have them block. + */ + wake_up_process(hp->sync_tsk); + return 0; +} + +static void cpu_unplug_sync(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + init_completion(&hp->synced); + /* The completion needs to be initialzied before setting grab_lock */ + smp_wmb(); + + /* Grab the mutex before setting grab_lock */ + hotplug_lock(hp); + hp->grab_lock = 1; + + /* + * The CPU notifiers have been completed. + * Wait for tasks to get out of pinned CPU sections and have new + * tasks block until the CPU is completely down. + */ + __cpu_unplug_sync(hp); + + /* All done with the sync thread */ + kthread_stop(hp->sync_tsk); + hp->sync_tsk = NULL; +} + +static void cpu_unplug_done(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + hp->unplug = NULL; + /* Let all tasks know cpu unplug is finished before cleaning up */ + smp_wmb(); + + if (hp->sync_tsk) + kthread_stop(hp->sync_tsk); + + if (hp->grab_lock) { + hotplug_unlock(hp); + /* protected by cpu_hotplug.lock */ + hp->grab_lock = 0; + } + tell_sched_cpu_down_done(cpu); +} + void get_online_cpus(void) { might_sleep(); @@ -79,15 +363,14 @@ void put_online_cpus(void) { if (cpu_hotplug.active_writer == current) return; - mutex_lock(&cpu_hotplug.lock); + mutex_lock(&cpu_hotplug.lock); if (WARN_ON(!cpu_hotplug.refcount)) cpu_hotplug.refcount++; /* try to fix things up */ if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer)) wake_up_process(cpu_hotplug.active_writer); mutex_unlock(&cpu_hotplug.lock); - } EXPORT_SYMBOL_GPL(put_online_cpus); @@ -282,13 +565,15 @@ 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; + cpumask_var_t cpumask_org; if (num_online_cpus() == 1) return -EBUSY; @@ -296,7 +581,34 @@ 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; + if (!alloc_cpumask_var(&cpumask_org, GFP_KERNEL)) { + free_cpumask_var(cpumask); + return -ENOMEM; + } + + cpumask_copy(cpumask_org, tsk_cpus_allowed(current)); + cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu)); + set_cpus_allowed_ptr(current, cpumask); + free_cpumask_var(cpumask); + migrate_disable(); + mycpu = smp_processor_id(); + if (mycpu == cpu) { + printk(KERN_ERR "Yuck! Still on unplug CPU\n!"); + migrate_enable(); + err = -EBUSY; + goto restore_cpus; + } + migrate_enable(); + cpu_hotplug_begin(); + err = cpu_unplug_begin(cpu); + if (err) { + printk("cpu_unplug_begin(%d) failed\n", cpu); + goto out_cancel; + } err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); if (err) { @@ -306,8 +618,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) __func__, cpu); goto out_release; } + + __cpu_unplug_wait(cpu); smpboot_park_threads(cpu); + /* Notifiers are done. Don't let any more tasks pin this CPU. */ + cpu_unplug_sync(cpu); + err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); if (err) { /* CPU didn't die: tell everyone. Can't complain. */ @@ -336,9 +653,14 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) check_for_tasks(cpu); out_release: + cpu_unplug_done(cpu); +out_cancel: cpu_hotplug_done(); if (!err) cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); +restore_cpus: + set_cpus_allowed_ptr(current, cpumask_org); + free_cpumask_var(cpumask_org); return err; } diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 14ff484..399dba6 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -554,7 +554,6 @@ int vkdb_printf(const char *fmt, va_list ap) int linecount; int colcount; int logging, saved_loglevel = 0; - int saved_trap_printk; int got_printf_lock = 0; int retlen = 0; int fnd, len; @@ -565,8 +564,6 @@ 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, @@ -833,7 +830,6 @@ kdb_print_out: } else { __release(kdb_printf_lock); } - kdb_trap_printk = saved_trap_printk; preempt_enable(); return retlen; } @@ -843,9 +839,11 @@ 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/events/core.c b/kernel/events/core.c index 6dde811..40c3397 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6033,6 +6033,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event) hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hwc->hrtimer.function = perf_swevent_hrtimer; + hwc->hrtimer.irqsafe = 1; /* * Since hrtimers have a fixed rate, we can do a static freq->period diff --git a/kernel/exit.c b/kernel/exit.c index a949819..7493b32 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -145,7 +145,7 @@ 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 458953c..ae9a1a4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -94,7 +94,7 @@ 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) @@ -230,7 +230,9 @@ static inline void put_signal_struct(struct signal_struct *sig) if (atomic_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } - +#ifdef CONFIG_PREEMPT_RT_BASE +static +#endif void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); @@ -245,7 +247,18 @@ 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 void __init __weak arch_task_cache_init(void) { } @@ -598,6 +611,19 @@ 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. */ @@ -1107,6 +1133,9 @@ 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 = 0; tsk->cputime_expires.virt_exp = 0; tsk->cputime_expires.sched_exp = 0; @@ -1235,6 +1264,7 @@ 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 = p->stime = p->gtime = 0; p->utimescaled = p->stimescaled = 0; @@ -1242,7 +1272,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->prev_cputime.utime = p->prev_cputime.stime = 0; #endif #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqlock_init(&p->vtime_seqlock); + raw_spin_lock_init(&p->vtime_lock); + seqcount_init(&p->vtime_seq); p->vtime_snap = 0; p->vtime_snap_whence = VTIME_SLEEPING; #endif @@ -1295,6 +1326,9 @@ 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; @@ -1656,7 +1690,7 @@ SYSCALL_DEFINE0(fork) #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, 0, NULL, NULL); } #endif diff --git a/kernel/futex.c b/kernel/futex.c index 2317548..3b85a95 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -573,7 +573,9 @@ void exit_pi_state_list(struct task_struct *curr) * task still owns the PI-state: */ if (head->next != next) { + raw_spin_unlock_irq(&curr->pi_lock); spin_unlock(&hb->lock); + raw_spin_lock_irq(&curr->pi_lock); continue; } @@ -1447,6 +1449,16 @@ 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; @@ -2290,7 +2302,7 @@ 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; @@ -2315,8 +2327,7 @@ 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)) @@ -2337,20 +2348,55 @@ 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) { @@ -2359,9 +2405,10 @@ 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 { /* @@ -2374,7 +2421,8 @@ 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 383319b..c19183d 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -47,11 +47,13 @@ #include <linux/sched/sysctl.h> #include <linux/sched/rt.h> #include <linux/timer.h> +#include <linux/kthread.h> #include <linux/freezer.h> #include <asm/uaccess.h> #include <trace/events/timer.h> +#include <trace/events/hist.h> /* * The timer bases: @@ -607,8 +609,7 @@ 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; @@ -643,6 +644,9 @@ 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 */ @@ -659,9 +663,18 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) * and expiry check is done in the hrtimer_interrupt or in the softirq. */ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base) + struct hrtimer_clock_base *base, + int wakeup) { - return base->cpu_base->hres_active && hrtimer_reprogram(timer, base); + if (!(base->cpu_base->hres_active && hrtimer_reprogram(timer, base))) + return 0; + if (!wakeup) + return -ETIME; +#ifdef CONFIG_PREEMPT_RT_BASE + if (!hrtimer_rt_defer(timer)) + return -ETIME; +#endif + return 1; } static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) @@ -729,6 +742,44 @@ static void clock_was_set_work(struct work_struct *work) static DECLARE_WORK(hrtimer_work, clock_was_set_work); +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * RT can not call schedule_work from real interrupt context. + * Need to make a thread to do the real work. + */ +static struct task_struct *clock_set_delay_thread; +static bool do_clock_set_delay; + +static int run_clock_set_delay(void *ignore) +{ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + if (do_clock_set_delay) { + do_clock_set_delay = false; + schedule_work(&hrtimer_work); + } + schedule(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +void clock_was_set_delayed(void) +{ + do_clock_set_delay = true; + /* Make visible before waking up process */ + smp_wmb(); + wake_up_process(clock_set_delay_thread); +} + +static __init int create_clock_set_delay_thread(void) +{ + clock_set_delay_thread = kthread_run(run_clock_set_delay, NULL, "kclksetdelayd"); + BUG_ON(!clock_set_delay_thread); + return 0; +} +early_initcall(create_clock_set_delay_thread); +#else /* PREEMPT_RT_FULL */ /* * Called from timekeeping and resume code to reprogramm the hrtimer * interrupt device on all cpus. @@ -737,6 +788,7 @@ void clock_was_set_delayed(void) { schedule_work(&hrtimer_work); } +#endif #else @@ -746,12 +798,18 @@ static inline int hrtimer_switch_to_hres(void) { return 0; } static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base) + struct hrtimer_clock_base *base, + int wakeup) { return 0; } 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 */ @@ -870,6 +928,32 @@ 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 * @@ -913,6 +997,11 @@ 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) { @@ -997,6 +1086,17 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, #endif } +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + { + ktime_t now = new_base->get_time(); + + if (ktime_to_ns(tim) < ktime_to_ns(now)) + timer->praecox = now; + else + timer->praecox = ktime_set(0, 0); + } +#endif + hrtimer_set_expires_range_ns(timer, tim, delta_ns); timer_stats_hrtimer_set_start_info(timer); @@ -1009,9 +1109,19 @@ 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)) { - if (wakeup) { + if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)) { + ret = hrtimer_enqueue_reprogram(timer, new_base, wakeup); + if (ret < 0) { + /* + * In case we failed to reprogram the timer (mostly + * because out current timer is already elapsed), + * remove it again and report a failure. This avoids + * stale base->first entries. + */ + debug_deactivate(timer); + __remove_hrtimer(timer, new_base, + timer->state & HRTIMER_STATE_CALLBACK, 0); + } else if (ret > 0) { /* * We need to drop cpu_base->lock to avoid a * lock ordering issue vs. rq->lock. @@ -1019,9 +1129,7 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, raw_spin_unlock(&new_base->cpu_base->lock); raise_softirq_irqoff(HRTIMER_SOFTIRQ); local_irq_restore(flags); - return ret; - } else { - __raise_softirq_irqoff(HRTIMER_SOFTIRQ); + return 0; } } @@ -1111,7 +1219,7 @@ int hrtimer_cancel(struct hrtimer *timer) if (ret >= 0) return ret; - cpu_relax(); + hrtimer_wait_for_timer(timer); } } EXPORT_SYMBOL_GPL(hrtimer_cancel); @@ -1190,6 +1298,7 @@ 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 @@ -1273,6 +1382,126 @@ 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) +{ + hrtimer_peek_ahead_timers(); +} + +static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; } + +#endif + #ifdef CONFIG_HIGH_RES_TIMERS /* @@ -1283,7 +1512,7 @@ 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++; @@ -1318,6 +1547,15 @@ retry: timer = container_of(node, struct hrtimer, node); + trace_hrtimer_interrupt(raw_smp_processor_id(), + ktime_to_ns(ktime_sub(ktime_to_ns(timer->praecox) ? + timer->praecox : hrtimer_get_expires(timer), + basenow)), + current, + timer->function == hrtimer_wakeup ? + container_of(timer, struct hrtimer_sleeper, + timer)->task : NULL); + /* * The immediate goal for using the softexpires is * minimizing wakeups, not running timers at the @@ -1343,7 +1581,10 @@ retry: break; } - __run_hrtimer(timer, &basenow); + if (!hrtimer_rt_defer(timer)) + __run_hrtimer(timer, &basenow); + else + raise = 1; } } @@ -1358,7 +1599,7 @@ retry: if (expires_next.tv64 == KTIME_MAX || !tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; - return; + goto out; } /* @@ -1402,6 +1643,9 @@ retry: tick_program_event(expires_next, 1); printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); +out: + if (raise) + raise_softirq_irqoff(HRTIMER_SOFTIRQ); } /* @@ -1437,40 +1681,16 @@ void hrtimer_peek_ahead_timers(void) __hrtimer_peek_ahead_timers(); local_irq_restore(flags); } - -static void run_hrtimer_softirq(struct softirq_action *h) -{ - hrtimer_peek_ahead_timers(); -} - #else /* CONFIG_HIGH_RES_TIMERS */ static inline void __hrtimer_peek_ahead_timers(void) { } #endif /* !CONFIG_HIGH_RES_TIMERS */ -/* - * Called from timer softirq every jiffy, expire hrtimers: - * - * For HRT its the fall back code to run the softirq in the timer - * softirq context in case the hrtimer initialization failed or has - * not been done yet. - */ -void hrtimer_run_pending(void) -{ - if (hrtimer_hres_active()) - return; - /* - * This _is_ ugly: We have to check in the softirq context, - * whether we can switch to highres and / or nohz mode. The - * clocksource switch happens in the timer interrupt with - * xtime_lock held. Notification from there only sets the - * check bit in the tick_oneshot code, otherwise we might - * deadlock vs. xtime_lock. - */ - if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) - hrtimer_switch_to_hres(); +static void run_hrtimer_softirq(struct softirq_action *h) +{ + hrtimer_rt_run_pending(); } /* @@ -1481,11 +1701,18 @@ 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; + /* + * Check whether we can switch to highres mode. + */ + if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()) + && hrtimer_switch_to_hres()) + return; + for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) { base = &cpu_base->clock_base[index]; if (!timerqueue_getnext(&base->active)) @@ -1506,10 +1733,16 @@ 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); } /* @@ -1531,16 +1764,18 @@ 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); -static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) +static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode, + unsigned long state) { hrtimer_init_sleeper(t, current); do { - set_current_state(TASK_INTERRUPTIBLE); + set_current_state(state); hrtimer_start_expires(&t->timer, mode); if (!hrtimer_active(&t->timer)) t->task = NULL; @@ -1584,7 +1819,8 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart) HRTIMER_MODE_ABS); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); - if (do_nanosleep(&t, HRTIMER_MODE_ABS)) + /* cpu_chill() does not care about restart state. */ + if (do_nanosleep(&t, HRTIMER_MODE_ABS, TASK_INTERRUPTIBLE)) goto out; rmtp = restart->nanosleep.rmtp; @@ -1601,8 +1837,10 @@ out: return ret; } -long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, - const enum hrtimer_mode mode, const clockid_t clockid) +static long +__hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, + const enum hrtimer_mode mode, const clockid_t clockid, + unsigned long state) { struct restart_block *restart; struct hrtimer_sleeper t; @@ -1615,7 +1853,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, hrtimer_init_on_stack(&t.timer, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack); - if (do_nanosleep(&t, mode)) + if (do_nanosleep(&t, mode, state)) goto out; /* Absolute timers do not update the rmtp value and restart: */ @@ -1642,6 +1880,12 @@ out: return ret; } +long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, + const enum hrtimer_mode mode, const clockid_t clockid) +{ + return __hrtimer_nanosleep(rqtp, rmtp, mode, clockid, TASK_INTERRUPTIBLE); +} + SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp, struct timespec __user *, rmtp) { @@ -1656,6 +1900,26 @@ SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp, return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC); } +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * Sleep for 1 ms in hope whoever holds what we want will let it go. + */ +void cpu_chill(void) +{ + struct timespec tu = { + .tv_nsec = NSEC_PER_MSEC, + }; + unsigned int freeze_flag = current->flags & PF_NOFREEZE; + + current->flags |= PF_NOFREEZE; + __hrtimer_nanosleep(&tu, NULL, HRTIMER_MODE_REL, CLOCK_MONOTONIC, + TASK_UNINTERRUPTIBLE); + if (!freeze_flag) + current->flags &= ~PF_NOFREEZE; +} +EXPORT_SYMBOL(cpu_chill); +#endif + /* * Functions related to boot-time initialization: */ @@ -1667,9 +1931,13 @@ static void 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 @@ -1782,9 +2050,7 @@ 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 131ca17..7f50c55 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -132,6 +132,8 @@ static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action) irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) { + struct pt_regs *regs = get_irq_regs(); + u64 ip = regs ? instruction_pointer(regs) : 0; irqreturn_t retval = IRQ_NONE; unsigned int flags = 0, irq = desc->irq_data.irq; @@ -172,7 +174,11 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) action = action->next; } while (action); - add_interrupt_randomness(irq, flags); +#ifndef CONFIG_PREEMPT_RT_FULL + add_interrupt_randomness(irq, flags, ip); +#else + desc->random_ip = ip; +#endif if (!noirqdebug) note_interrupt(irq, desc, retval); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 4c84746..252bf10 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -22,6 +22,7 @@ #include "internals.h" #ifdef CONFIG_IRQ_FORCED_THREADING +# ifndef CONFIG_PREEMPT_RT_BASE __read_mostly bool force_irqthreads; static int __init setup_forced_irqthreads(char *arg) @@ -30,6 +31,7 @@ static int __init setup_forced_irqthreads(char *arg) return 0; } early_param("threadirqs", setup_forced_irqthreads); +# endif #endif /** @@ -162,6 +164,62 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, return ret; } +#ifdef CONFIG_PREEMPT_RT_FULL +static void _irq_affinity_notify(struct irq_affinity_notify *notify); +static struct task_struct *set_affinity_helper; +static LIST_HEAD(affinity_list); +static DEFINE_RAW_SPINLOCK(affinity_list_lock); + +static int set_affinity_thread(void *unused) +{ + while (1) { + struct irq_affinity_notify *notify; + int empty; + + set_current_state(TASK_INTERRUPTIBLE); + + raw_spin_lock_irq(&affinity_list_lock); + empty = list_empty(&affinity_list); + raw_spin_unlock_irq(&affinity_list_lock); + + if (empty) + schedule(); + if (kthread_should_stop()) + break; + set_current_state(TASK_RUNNING); +try_next: + notify = NULL; + + raw_spin_lock_irq(&affinity_list_lock); + if (!list_empty(&affinity_list)) { + notify = list_first_entry(&affinity_list, + struct irq_affinity_notify, list); + list_del_init(¬ify->list); + } + raw_spin_unlock_irq(&affinity_list_lock); + + if (!notify) + continue; + _irq_affinity_notify(notify); + goto try_next; + } + return 0; +} + +static void init_helper_thread(void) +{ + if (set_affinity_helper) + return; + set_affinity_helper = kthread_run(set_affinity_thread, NULL, + "affinity-cb"); + WARN_ON(IS_ERR(set_affinity_helper)); +} +#else + +static inline void init_helper_thread(void) { } + +#endif + int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask) { struct irq_chip *chip = irq_data_get_irq_chip(data); @@ -180,7 +238,17 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask) if (desc->affinity_notify) { kref_get(&desc->affinity_notify->kref); + +#ifdef CONFIG_PREEMPT_RT_FULL + raw_spin_lock(&affinity_list_lock); + if (list_empty(&desc->affinity_notify->list)) + list_add_tail(&affinity_list, + &desc->affinity_notify->list); + raw_spin_unlock(&affinity_list_lock); + wake_up_process(set_affinity_helper); +#else schedule_work(&desc->affinity_notify->work); +#endif } irqd_set(data, IRQD_AFFINITY_SET); @@ -221,10 +289,8 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) } EXPORT_SYMBOL_GPL(irq_set_affinity_hint); -static void irq_affinity_notify(struct work_struct *work) +static void _irq_affinity_notify(struct irq_affinity_notify *notify) { - struct irq_affinity_notify *notify = - container_of(work, struct irq_affinity_notify, work); struct irq_desc *desc = irq_to_desc(notify->irq); cpumask_var_t cpumask; unsigned long flags; @@ -246,6 +312,13 @@ out: kref_put(¬ify->kref, notify->release); } +static void irq_affinity_notify(struct work_struct *work) +{ + struct irq_affinity_notify *notify = + container_of(work, struct irq_affinity_notify, work); + _irq_affinity_notify(notify); +} + /** * irq_set_affinity_notifier - control notification of IRQ affinity changes * @irq: Interrupt for which to enable/disable notification @@ -275,6 +348,8 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) notify->irq = irq; kref_init(¬ify->kref); INIT_WORK(¬ify->work, irq_affinity_notify); + INIT_LIST_HEAD(¬ify->list); + init_helper_thread(); } raw_spin_lock_irqsave(&desc->lock, flags); @@ -781,7 +856,15 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) local_bh_disable(); ret = action->thread_fn(action->irq, action->dev_id); irq_finalize_oneshot(desc, action); - local_bh_enable(); + /* + * Interrupts which have real time requirements can be set up + * to avoid softirq processing in the thread handler. This is + * safe as these interrupts do not raise soft interrupts. + */ + if (irq_settings_no_softirq_call(desc)) + _local_bh_enable(); + else + local_bh_enable(); return ret; } @@ -864,6 +947,12 @@ static int irq_thread(void *data) if (!noirqdebug) note_interrupt(action->irq, desc, action_ret); +#ifdef CONFIG_PREEMPT_RT_FULL + migrate_disable(); + add_interrupt_randomness(action->irq, 0, + desc->random_ip ^ (unsigned long) action); + migrate_enable(); +#endif wake_threads_waitq(desc); } @@ -1126,6 +1215,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irqd_set(&desc->irq_data, IRQD_NO_BALANCING); } + if (new->flags & IRQF_NO_SOFTIRQ_CALL) + irq_settings_set_no_softirq_call(desc); + /* Set default affinity mask once everything is setup */ setup_affinity(irq, desc, mask); diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h index 1162f10..0d2c381 100644 --- a/kernel/irq/settings.h +++ b/kernel/irq/settings.h @@ -14,6 +14,7 @@ enum { _IRQ_NO_BALANCING = IRQ_NO_BALANCING, _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, + _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL, _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, }; @@ -26,6 +27,7 @@ enum { #define IRQ_NOAUTOEN GOT_YOU_MORON #define IRQ_NESTED_THREAD GOT_YOU_MORON #define IRQ_PER_CPU_DEVID GOT_YOU_MORON +#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON #undef IRQF_MODIFY_MASK #define IRQF_MODIFY_MASK GOT_YOU_MORON @@ -36,6 +38,16 @@ irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set) desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); } +static inline bool irq_settings_no_softirq_call(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL; +} + +static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL; +} + static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_PER_CPU; diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 7b5f012..e5a309a 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -340,6 +340,10 @@ MODULE_PARM_DESC(noirqdebug, "Disable irq lockup detection when true"); static int __init irqfixup_setup(char *str) { +#ifdef CONFIG_PREEMPT_RT_BASE + pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); + return 1; +#endif irqfixup = 1; printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); printk(KERN_WARNING "This may impact system performance.\n"); @@ -352,6 +356,10 @@ module_param(irqfixup, int, 0644); static int __init irqpoll_setup(char *str) { +#ifdef CONFIG_PREEMPT_RT_BASE + pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); + return 1; +#endif irqfixup = 2; printk(KERN_WARNING "Misrouted IRQ fixup and polling support " "enabled\n"); diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 55fcce6..35d21f9 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -20,6 +20,9 @@ static DEFINE_PER_CPU(struct llist_head, irq_work_list); +#ifdef CONFIG_PREEMPT_RT_FULL +static DEFINE_PER_CPU(struct llist_head, hirq_work_list); +#endif static DEFINE_PER_CPU(int, irq_work_raised); /* @@ -48,7 +51,11 @@ static bool irq_work_claim(struct irq_work *work) return true; } +#ifdef CONFIG_PREEMPT_RT_FULL +void arch_irq_work_raise(void) +#else void __weak arch_irq_work_raise(void) +#endif { /* * Lame architectures will get the timer tick callback @@ -70,8 +77,12 @@ void irq_work_queue(struct irq_work *work) /* Queue the entry and raise the IPI if needed. */ preempt_disable(); - llist_add(&work->llnode, &__get_cpu_var(irq_work_list)); - +#ifdef CONFIG_PREEMPT_RT_FULL + if (work->flags & IRQ_WORK_HARD_IRQ) + llist_add(&work->llnode, &__get_cpu_var(hirq_work_list)); + else +#endif + llist_add(&work->llnode, &__get_cpu_var(irq_work_list)); /* * If the work is not "lazy" or the tick is stopped, raise the irq * work interrupt (if supported by the arch), otherwise, just wait @@ -115,12 +126,18 @@ static void __irq_work_run(void) __this_cpu_write(irq_work_raised, 0); barrier(); - this_list = &__get_cpu_var(irq_work_list); +#ifdef CONFIG_PREEMPT_RT_FULL + if (in_irq()) + this_list = &__get_cpu_var(hirq_work_list); + else +#endif + this_list = &__get_cpu_var(irq_work_list); if (llist_empty(this_list)) return; +#ifndef CONFIG_PREEMPT_RT_FULL BUG_ON(!irqs_disabled()); - +#endif llnode = llist_del_all(this_list); while (llnode != NULL) { work = llist_entry(llnode, struct irq_work, llnode); @@ -152,7 +169,9 @@ static void __irq_work_run(void) */ void irq_work_run(void) { +#ifndef CONFIG_PREEMPT_RT_FULL BUG_ON(!in_irq()); +#endif __irq_work_run(); } EXPORT_SYMBOL_GPL(irq_work_run); diff --git a/kernel/itimer.c b/kernel/itimer.c index 8d262b4..d051390 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -213,6 +213,7 @@ 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 9659d38..b66ab9e 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -132,6 +132,15 @@ 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) @@ -197,6 +206,9 @@ static struct attribute * kernel_attrs[] = { &vmcoreinfo_attr.attr, #endif &rcu_expedited_attr.attr, +#ifdef CONFIG_PREEMPT_RT_FULL + &realtime_attr.attr, +#endif NULL }; diff --git a/kernel/lglock.c b/kernel/lglock.c index 86ae2ae..f2356df 100644 --- a/kernel/lglock.c +++ b/kernel/lglock.c @@ -4,6 +4,15 @@ #include <linux/cpu.h> #include <linux/string.h> +#ifndef CONFIG_PREEMPT_RT_FULL +# define lg_lock_ptr arch_spinlock_t +# define lg_do_lock(l) arch_spin_lock(l) +# define lg_do_unlock(l) arch_spin_unlock(l) +#else +# define lg_lock_ptr struct rt_mutex +# define lg_do_lock(l) __rt_spin_lock(l) +# define lg_do_unlock(l) __rt_spin_unlock(l) +#endif /* * Note there is no uninit, so lglocks cannot be defined in * modules (but it's fine to use them from there) @@ -12,51 +21,60 @@ void lg_lock_init(struct lglock *lg, char *name) { +#ifdef CONFIG_PREEMPT_RT_FULL + int i; + + for_each_possible_cpu(i) { + struct rt_mutex *lock = per_cpu_ptr(lg->lock, i); + + rt_mutex_init(lock); + } +#endif LOCKDEP_INIT_MAP(&lg->lock_dep_map, name, &lg->lock_key, 0); } EXPORT_SYMBOL(lg_lock_init); void lg_local_lock(struct lglock *lg) { - arch_spinlock_t *lock; + lg_lock_ptr *lock; - preempt_disable(); + migrate_disable(); lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); lock = this_cpu_ptr(lg->lock); - arch_spin_lock(lock); + lg_do_lock(lock); } EXPORT_SYMBOL(lg_local_lock); void lg_local_unlock(struct lglock *lg) { - arch_spinlock_t *lock; + lg_lock_ptr *lock; lock_release(&lg->lock_dep_map, 1, _RET_IP_); lock = this_cpu_ptr(lg->lock); - arch_spin_unlock(lock); - preempt_enable(); + lg_do_unlock(lock); + migrate_enable(); } EXPORT_SYMBOL(lg_local_unlock); void lg_local_lock_cpu(struct lglock *lg, int cpu) { - arch_spinlock_t *lock; + lg_lock_ptr *lock; - preempt_disable(); + preempt_disable_nort(); lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); lock = per_cpu_ptr(lg->lock, cpu); - arch_spin_lock(lock); + lg_do_lock(lock); } EXPORT_SYMBOL(lg_local_lock_cpu); void lg_local_unlock_cpu(struct lglock *lg, int cpu) { - arch_spinlock_t *lock; + lg_lock_ptr *lock; lock_release(&lg->lock_dep_map, 1, _RET_IP_); lock = per_cpu_ptr(lg->lock, cpu); - arch_spin_unlock(lock); - preempt_enable(); + lg_do_unlock(lock); + preempt_enable_nort(); } EXPORT_SYMBOL(lg_local_unlock_cpu); @@ -64,12 +82,12 @@ void lg_global_lock(struct lglock *lg) { int i; - preempt_disable(); + preempt_disable_nort(); lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); for_each_possible_cpu(i) { - arch_spinlock_t *lock; + lg_lock_ptr *lock; lock = per_cpu_ptr(lg->lock, i); - arch_spin_lock(lock); + lg_do_lock(lock); } } EXPORT_SYMBOL(lg_global_lock); @@ -80,10 +98,10 @@ void lg_global_unlock(struct lglock *lg) lock_release(&lg->lock_dep_map, 1, _RET_IP_); for_each_possible_cpu(i) { - arch_spinlock_t *lock; + lg_lock_ptr *lock; lock = per_cpu_ptr(lg->lock, i); - arch_spin_unlock(lock); + lg_do_unlock(lock); } - preempt_enable(); + preempt_enable_nort(); } EXPORT_SYMBOL(lg_global_unlock); diff --git a/kernel/lockdep.c b/kernel/lockdep.c index e16c45b..b74f7a5 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -3541,6 +3541,7 @@ 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 @@ -3555,6 +3556,7 @@ 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/panic.c b/kernel/panic.c index b6c482c..936d00f 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -368,9 +368,11 @@ 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 c7f31aa..4bf82f8 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -3,6 +3,7 @@ */ #include <linux/sched.h> +#include <linux/sched/rt.h> #include <linux/posix-timers.h> #include <linux/errno.h> #include <linux/math64.h> @@ -663,7 +664,7 @@ 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; @@ -1110,7 +1111,7 @@ 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); @@ -1177,10 +1178,11 @@ 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; @@ -1194,13 +1196,13 @@ 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 @@ -1265,6 +1267,190 @@ void run_posix_cpu_timers(struct task_struct *tsk) posix_cpu_timer_kick_nohz(); } +#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), + cpumask_any(cpu_online_mask)); + kthread_stop(per_cpu(posix_timer_task,cpu)); + per_cpu(posix_timer_task,cpu) = NULL; + break; + case CPU_DEAD: + kthread_stop(per_cpu(posix_timer_task,cpu)); + per_cpu(posix_timer_task,cpu) = NULL; + break; +#endif + } + return NOTIFY_OK; +} + +/* Register at highest priority so that task migration (migrate_all_tasks) + * happens before everything else. + */ +static struct notifier_block posix_cpu_thread_notifier = { + .notifier_call = posix_cpu_thread_call, + .priority = 10 +}; + +static int __init posix_cpu_thread_init(void) +{ + void *hcpu = (void *)(long)smp_processor_id(); + /* Start one for boot CPU. */ + unsigned long cpu; + + /* init the per-cpu posix_timer_tasklets */ + for_each_possible_cpu(cpu) + per_cpu(posix_timer_tasklist, cpu) = NULL; + + posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, hcpu); + posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, hcpu); + register_cpu_notifier(&posix_cpu_thread_notifier); + return 0; +} +early_initcall(posix_cpu_thread_init); +#else /* CONFIG_PREEMPT_RT_BASE */ +void run_posix_cpu_timers(struct task_struct *tsk) +{ + __run_posix_cpu_timers(tsk); +} +#endif /* CONFIG_PREEMPT_RT_BASE */ + /* * Set one of the process-wide special case CPU timers or RLIMIT_CPU. * The tsk->sighand->siglock must be held by the caller. diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 424c2d4..a22b931 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -497,6 +497,7 @@ 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)) || @@ -505,7 +506,8 @@ 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); @@ -816,6 +818,20 @@ 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 @@ -893,6 +909,7 @@ 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; @@ -901,9 +918,12 @@ 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))) @@ -941,10 +961,15 @@ 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); @@ -970,8 +995,18 @@ 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 0121dab..d26958b 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -275,6 +275,8 @@ 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, " @@ -302,6 +304,7 @@ static int create_image(int platform_mode) syscore_resume(); Enable_irqs: + system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: @@ -427,6 +430,7 @@ static int resume_target_kernel(bool platform_mode) goto Enable_cpus; local_irq_disable(); + system_state = SYSTEM_SUSPEND; error = syscore_suspend(); if (error) @@ -460,6 +464,7 @@ static int resume_target_kernel(bool platform_mode) syscore_resume(); Enable_irqs: + system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: @@ -542,6 +547,7 @@ int hibernation_platform_enter(void) goto Platform_finish; local_irq_disable(); + system_state = SYSTEM_SUSPEND; syscore_suspend(); if (pm_wakeup_pending()) { error = -EAGAIN; @@ -554,6 +560,7 @@ 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 62ee437..e6703bb 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -218,6 +218,8 @@ 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(); @@ -228,6 +230,8 @@ 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/printk.c b/kernel/printk/printk.c index c59896c..981ff61 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1029,6 +1029,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) { char *text; int len = 0; + int attempts = 0; text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); if (!text) @@ -1040,7 +1041,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear) u64 seq; u32 idx; enum log_flags prev; - + int num_msg; +try_again: + attempts++; + if (attempts > 10) { + len = -EBUSY; + goto out; + } + num_msg = 0; if (clear_seq < log_first_seq) { /* messages are gone, move to first available one */ clear_seq = log_first_seq; @@ -1061,6 +1069,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear) prev = msg->flags; idx = log_next(idx); seq++; + num_msg++; + if (num_msg > 5) { + num_msg = 0; + raw_spin_unlock_irq(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); + if (clear_seq < log_first_seq) + goto try_again; + } } /* move first record forward until length fits into the buffer */ @@ -1074,6 +1090,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear) prev = msg->flags; idx = log_next(idx); seq++; + num_msg++; + if (num_msg > 5) { + num_msg = 0; + raw_spin_unlock_irq(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); + if (clear_seq < log_first_seq) + goto try_again; + } } /* last message fitting into this dump */ @@ -1114,6 +1138,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) clear_seq = log_next_seq; clear_idx = log_next_idx; } +out: raw_spin_unlock_irq(&logbuf_lock); kfree(text); @@ -1271,6 +1296,7 @@ static void call_console_drivers(int level, const char *text, size_t len) if (!console_drivers) return; + migrate_disable(); for_each_console(con) { if (exclusive_console && con != exclusive_console) continue; @@ -1283,6 +1309,7 @@ static void call_console_drivers(int level, const char *text, size_t len) continue; con->write(con, text, len); } + migrate_enable(); } /* @@ -1342,12 +1369,18 @@ 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() <= 1); +#else + int lock = 1; +#endif - if (console_trylock()) { + if (lock && console_trylock()) { retval = 1; /* @@ -1487,6 +1520,62 @@ static size_t cont_print_text(char *text, size_t size) return textlen; } +#ifdef CONFIG_EARLY_PRINTK +struct console *early_console; + +void early_vprintk(const char *fmt, va_list ap) +{ + if (early_console) { + char buf[512]; + int n = vscnprintf(buf, sizeof(buf), fmt, ap); + + early_console->write(early_console, buf, n); + } +} + +asmlinkage void early_printk(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + early_vprintk(fmt, ap); + va_end(ap); +} + +/* + * This is independent of any log levels - a global + * kill switch that turns off all of printk. + * + * Used by the NMI watchdog if early-printk is enabled. + */ +static bool __read_mostly printk_killswitch; + +static int __init force_early_printk_setup(char *str) +{ + printk_killswitch = true; + return 0; +} +early_param("force_early_printk", force_early_printk_setup); + +void printk_kill(void) +{ + printk_killswitch = true; +} + +static int forced_early_printk(const char *fmt, va_list ap) +{ + if (!printk_killswitch) + return 0; + early_vprintk(fmt, ap); + return 1; +} +#else +static inline int forced_early_printk(const char *fmt, va_list ap) +{ + return 0; +} +#endif + asmlinkage int vprintk_emit(int facility, int level, const char *dict, size_t dictlen, const char *fmt, va_list args) @@ -1500,6 +1589,13 @@ asmlinkage int vprintk_emit(int facility, int level, int this_cpu; int printed_len = 0; + /* + * 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(level); printk_delay(); @@ -1619,8 +1715,15 @@ asmlinkage int vprintk_emit(int facility, int level, * The console_trylock_for_printk() function will release 'logbuf_lock' * regardless of whether it actually gets the console 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: @@ -1722,29 +1825,6 @@ static size_t cont_print_text(char *text, size_t size) { return 0; } #endif /* CONFIG_PRINTK */ -#ifdef CONFIG_EARLY_PRINTK -struct console *early_console; - -void early_vprintk(const char *fmt, va_list ap) -{ - if (early_console) { - char buf[512]; - int n = vscnprintf(buf, sizeof(buf), fmt, ap); - - early_console->write(early_console, buf, n); - } -} - -asmlinkage void early_printk(const char *fmt, ...) -{ - va_list ap; - - va_start(ap, fmt); - early_vprintk(fmt, ap); - va_end(ap); -} -#endif - static int __add_preferred_console(char *name, int idx, char *options, char *brl_options) { @@ -1985,11 +2065,16 @@ static void console_cont_flush(char *text, size_t size) goto out; len = cont_print_text(text, size); +#ifndef CONFIG_PREEMPT_RT_FULL raw_spin_unlock(&logbuf_lock); stop_critical_timings(); call_console_drivers(cont.level, text, len); start_critical_timings(); local_irq_restore(flags); +#else + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + call_console_drivers(cont.level, text, len); +#endif return; out: raw_spin_unlock_irqrestore(&logbuf_lock, flags); @@ -2072,12 +2157,17 @@ skip: console_idx = log_next(console_idx); console_seq++; console_prev = msg->flags; - raw_spin_unlock(&logbuf_lock); +#ifndef CONFIG_PREEMPT_RT_FULL + raw_spin_unlock(&logbuf_lock); stop_critical_timings(); /* don't trace print latency */ call_console_drivers(level, text, len); start_critical_timings(); local_irq_restore(flags); +#else + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + call_console_drivers(level, text, len); +#endif } console_locked = 0; mutex_release(&console_lock_dep_map, 1, _RET_IP_); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 1f4bcb3..fddaf65 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -135,7 +135,12 @@ static bool ptrace_freeze_traced(struct task_struct *task) spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !__fatal_signal_pending(task)) { - task->state = __TASK_TRACED; + raw_spin_lock_irq(&task->pi_lock); + if (task->state & __TASK_TRACED) + task->state = __TASK_TRACED; + else + task->saved_state = __TASK_TRACED; + raw_spin_unlock_irq(&task->pi_lock); ret = true; } spin_unlock_irq(&task->sighand->siglock); diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index b02a339..7e1dd3e 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -129,6 +129,7 @@ int notrace 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? * @@ -155,6 +156,7 @@ 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 9ed6075..f202b26 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -369,6 +369,7 @@ 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. @@ -378,6 +379,7 @@ 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 void rcu_init(void) { diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 32618b3..507fab1 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -55,6 +55,11 @@ #include <linux/random.h> #include <linux/ftrace_event.h> #include <linux/suspend.h> +#include <linux/delay.h> +#include <linux/gfp.h> +#include <linux/oom.h> +#include <linux/smpboot.h> +#include "time/tick-internal.h" #include "rcutree.h" #include <trace/events/rcu.h> @@ -145,8 +150,6 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active); */ static int rcu_scheduler_fully_active __read_mostly; -#ifdef CONFIG_RCU_BOOST - /* * Control variables for per-CPU and per-rcu_node kthreads. These * handle all flavors of RCU. @@ -156,8 +159,6 @@ DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); DEFINE_PER_CPU(char, rcu_cpu_has_work); -#endif /* #ifdef CONFIG_RCU_BOOST */ - static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); static void invoke_rcu_core(void); static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); @@ -199,6 +200,19 @@ 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) +{ + unsigned long flags; + + /* Callers to this function, rcu_preempt_qs(), must disable irqs. */ + local_irq_save(flags); + rcu_preempt_qs(cpu); + local_irq_restore(flags); +} +#else void rcu_bh_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); @@ -207,6 +221,7 @@ void rcu_bh_qs(int cpu) trace_rcu_grace_period(TPS("rcu_bh"), rdp->gpnum, TPS("cpuqs")); rdp->passed_quiesce = 1; } +#endif /* * Note a context switch. This is a quiescent state for RCU-sched, @@ -263,6 +278,7 @@ 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. */ @@ -280,6 +296,7 @@ void rcu_bh_force_quiescent_state(void) force_quiescent_state(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); +#endif /* * Record the number of times rcutorture tests have been initiated and @@ -1471,7 +1488,7 @@ static int __noreturn rcu_gp_kthread(void *arg) /* Handle grace-period start. */ for (;;) { - wait_event_interruptible(rsp->gp_wq, + swait_event_interruptible(rsp->gp_wq, rsp->gp_flags & RCU_GP_FLAG_INIT); if ((rsp->gp_flags & RCU_GP_FLAG_INIT) && @@ -1490,7 +1507,7 @@ static int __noreturn rcu_gp_kthread(void *arg) } for (;;) { rsp->jiffies_force_qs = jiffies + j; - ret = wait_event_interruptible_timeout(rsp->gp_wq, + ret = swait_event_interruptible_timeout(rsp->gp_wq, (rsp->gp_flags & RCU_GP_FLAG_FQS) || (!ACCESS_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp)), @@ -1528,7 +1545,7 @@ static void rsp_wakeup(struct irq_work *work) struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work); /* Wake up rcu_gp_kthread() to start the grace period. */ - wake_up(&rsp->gp_wq); + swait_wake(&rsp->gp_wq); } /* @@ -1602,7 +1619,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + swait_wake(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ } /* @@ -2172,7 +2189,8 @@ static void force_quiescent_state(struct rcu_state *rsp) } rsp->gp_flags |= RCU_GP_FLAG_FQS; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + /* Memory barrier implied by wake_up() path. */ + swait_wake(&rsp->gp_wq); } /* @@ -2209,16 +2227,14 @@ __rcu_process_callbacks(struct rcu_state *rsp) /* * Do RCU core processing for the current CPU. */ -static void rcu_process_callbacks(struct softirq_action *unused) +static void rcu_process_callbacks(void) { struct rcu_state *rsp; if (cpu_is_offline(smp_processor_id())) return; - trace_rcu_utilization(TPS("Start RCU core")); for_each_rcu_flavor(rsp) __rcu_process_callbacks(rsp); - trace_rcu_utilization(TPS("End RCU core")); } /* @@ -2232,18 +2248,105 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) { if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active))) return; - if (likely(!rsp->boost)) { - rcu_do_batch(rsp, rdp); + rcu_do_batch(rsp, rdp); +} + +static void rcu_wake_cond(struct task_struct *t, int status) +{ + /* + * If the thread is yielding, only wake it when this + * is invoked from idle + */ + if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current))) + wake_up_process(t); +} + +/* + * Wake up this CPU's rcuc kthread to do RCU core processing. + */ +static void invoke_rcu_core(void) +{ + unsigned long flags; + struct task_struct *t; + + if (!cpu_online(smp_processor_id())) return; + local_irq_save(flags); + __this_cpu_write(rcu_cpu_has_work, 1); + t = __this_cpu_read(rcu_cpu_kthread_task); + if (t != NULL && current != t) + rcu_wake_cond(t, __this_cpu_read(rcu_cpu_kthread_status)); + local_irq_restore(flags); +} + +static void rcu_cpu_kthread_park(unsigned int cpu) +{ + per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; +} + +static int rcu_cpu_kthread_should_run(unsigned int cpu) +{ + return __this_cpu_read(rcu_cpu_has_work); +} + +/* + * Per-CPU kernel thread that invokes RCU callbacks. This replaces the + * RCU softirq used in flavors and configurations of RCU that do not + * support RCU priority boosting. + */ +static void rcu_cpu_kthread(unsigned int cpu) +{ + unsigned int *statusp = &__get_cpu_var(rcu_cpu_kthread_status); + char work, *workp = &__get_cpu_var(rcu_cpu_has_work); + int spincnt; + + for (spincnt = 0; spincnt < 10; spincnt++) { + trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); + local_bh_disable(); + *statusp = RCU_KTHREAD_RUNNING; + this_cpu_inc(rcu_cpu_kthread_loops); + local_irq_disable(); + work = *workp; + *workp = 0; + local_irq_enable(); + if (work) + rcu_process_callbacks(); + local_bh_enable(); + if (*workp == 0) { + trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); + *statusp = RCU_KTHREAD_WAITING; + return; + } } - invoke_rcu_callbacks_kthread(); + *statusp = RCU_KTHREAD_YIELDING; + trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); + schedule_timeout_interruptible(2); + trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); + *statusp = RCU_KTHREAD_WAITING; } -static void invoke_rcu_core(void) +static struct smp_hotplug_thread rcu_cpu_thread_spec = { + .store = &rcu_cpu_kthread_task, + .thread_should_run = rcu_cpu_kthread_should_run, + .thread_fn = rcu_cpu_kthread, + .thread_comm = "rcuc/%u", + .setup = rcu_cpu_kthread_setup, + .park = rcu_cpu_kthread_park, +}; + +/* + * Spawn per-CPU RCU core processing kthreads. + */ +static int __init rcu_spawn_core_kthreads(void) { - if (cpu_online(smp_processor_id())) - raise_softirq(RCU_SOFTIRQ); + int cpu; + + for_each_possible_cpu(cpu) + per_cpu(rcu_cpu_has_work, cpu) = 0; + BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); + return 0; } +early_initcall(rcu_spawn_core_kthreads); /* * Handle any core-RCU processing required by a call_rcu() invocation. @@ -2373,6 +2476,7 @@ 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 callback for invocation after a quicker grace period. */ @@ -2381,6 +2485,7 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) __call_rcu(head, func, &rcu_bh_state, -1, 0); } EXPORT_SYMBOL_GPL(call_rcu_bh); +#endif /* * Because a context switch is a grace period for RCU-sched and RCU-bh, @@ -2458,6 +2563,7 @@ 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. * @@ -2484,6 +2590,7 @@ void synchronize_rcu_bh(void) wait_rcu_gp(call_rcu_bh); } EXPORT_SYMBOL_GPL(synchronize_rcu_bh); +#endif static int synchronize_sched_expedited_cpu_stop(void *data) { @@ -2658,6 +2765,10 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) /* Check for CPU stalls, if enabled. */ check_cpu_stall(rsp, rdp); + /* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */ + if (rcu_nohz_full_cpu(rsp)) + return 0; + /* Is the RCU core waiting for a quiescent state from this CPU? */ if (rcu_scheduler_fully_active && rdp->qs_pending && !rdp->passed_quiesce) { @@ -2891,6 +3002,7 @@ static void _rcu_barrier(struct rcu_state *rsp) mutex_unlock(&rsp->barrier_mutex); } +#ifndef CONFIG_PREEMPT_RT_FULL /** * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. */ @@ -2899,6 +3011,7 @@ void rcu_barrier_bh(void) _rcu_barrier(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_barrier_bh); +#endif /** * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. @@ -3202,7 +3315,7 @@ static void __init rcu_init_one(struct rcu_state *rsp, } rsp->rda = rda; - init_waitqueue_head(&rsp->gp_wq); + init_swait_head(&rsp->gp_wq); init_irq_work(&rsp->wakeup_work, rsp_wakeup); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { @@ -3298,7 +3411,6 @@ void __init rcu_init(void) rcu_init_one(&rcu_sched_state, &rcu_sched_data); rcu_init_one(&rcu_bh_state, &rcu_bh_data); __rcu_init_preempt(); - open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); /* * We don't need protection against CPU-hotplug here because diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 52be957..1df8d9e 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -28,6 +28,7 @@ #include <linux/cpumask.h> #include <linux/seqlock.h> #include <linux/irq_work.h> +#include <linux/wait-simple.h> /* * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and @@ -200,7 +201,7 @@ struct rcu_node { /* This can happen due to race conditions. */ #endif /* #ifdef CONFIG_RCU_BOOST */ #ifdef CONFIG_RCU_NOCB_CPU - wait_queue_head_t nocb_gp_wq[2]; + struct swait_head nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ int need_future_gp[2]; @@ -333,7 +334,7 @@ struct rcu_data { atomic_long_t nocb_q_count_lazy; /* (approximate). */ int nocb_p_count; /* # CBs being invoked by kthread */ int nocb_p_count_lazy; /* (approximate). */ - wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */ + struct swait_head nocb_wq; /* For nocb kthreads to sleep on. */ struct task_struct *nocb_kthread; #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ @@ -403,7 +404,7 @@ struct rcu_state { unsigned long gpnum; /* Current gp number. */ unsigned long completed; /* # of last completed gp. */ struct task_struct *gp_kthread; /* Task for grace periods. */ - wait_queue_head_t gp_wq; /* Where GP task waits. */ + struct swait_head gp_wq; /* Where GP task waits. */ int gp_flags; /* Commands for GP task. */ /* End of fields guarded by root rcu_node's lock. */ @@ -527,10 +528,9 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, static void __init __rcu_init_preempt(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); -static void invoke_rcu_callbacks_kthread(void); static bool rcu_is_callbacks_kthread(void); +static void rcu_cpu_kthread_setup(unsigned int cpu); #ifdef CONFIG_RCU_BOOST -static void rcu_preempt_do_callbacks(void); static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, struct rcu_node *rnp); #endif /* #ifdef CONFIG_RCU_BOOST */ @@ -564,6 +564,7 @@ static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, unsigned long maxj); static void rcu_bind_gp_kthread(void); static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp); +static bool rcu_nohz_full_cpu(struct rcu_state *rsp); #endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 511e6b4..c849bd4 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -24,12 +24,6 @@ * Paul E. McKenney <paulmck@linux.vnet.ibm.com> */ -#include <linux/delay.h> -#include <linux/gfp.h> -#include <linux/oom.h> -#include <linux/smpboot.h> -#include "time/tick-internal.h" - #define RCU_KTHREAD_PRIO 1 #ifdef CONFIG_RCU_BOOST @@ -359,7 +353,7 @@ 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; } @@ -656,15 +650,6 @@ static void rcu_preempt_check_callbacks(int cpu) t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; } -#ifdef CONFIG_RCU_BOOST - -static void rcu_preempt_do_callbacks(void) -{ - rcu_do_batch(&rcu_preempt_state, &__get_cpu_var(rcu_preempt_data)); -} - -#endif /* #ifdef CONFIG_RCU_BOOST */ - /* * Queue a preemptible-RCU callback for invocation after a grace period. */ @@ -1126,6 +1111,19 @@ void exit_rcu(void) #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ +/* + * If boosting, set rcuc kthreads to realtime priority. + */ +static void rcu_cpu_kthread_setup(unsigned int cpu) +{ +#ifdef CONFIG_RCU_BOOST + struct sched_param sp; + + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); +#endif /* #ifdef CONFIG_RCU_BOOST */ +} + #ifdef CONFIG_RCU_BOOST #include "rtmutex_common.h" @@ -1157,16 +1155,6 @@ static void rcu_initiate_boost_trace(struct rcu_node *rnp) #endif /* #else #ifdef CONFIG_RCU_TRACE */ -static void rcu_wake_cond(struct task_struct *t, int status) -{ - /* - * If the thread is yielding, only wake it when this - * is invoked from idle - */ - if (status != RCU_KTHREAD_YIELDING || is_idle_task(current)) - wake_up_process(t); -} - /* * Carry out RCU priority boosting on the task indicated by ->exp_tasks * or ->boost_tasks, advancing the pointer to the next task in the @@ -1310,23 +1298,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) } /* - * Wake up the per-CPU kthread to invoke RCU callbacks. - */ -static void invoke_rcu_callbacks_kthread(void) -{ - unsigned long flags; - - local_irq_save(flags); - __this_cpu_write(rcu_cpu_has_work, 1); - if (__this_cpu_read(rcu_cpu_kthread_task) != NULL && - current != __this_cpu_read(rcu_cpu_kthread_task)) { - rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task), - __this_cpu_read(rcu_cpu_kthread_status)); - } - local_irq_restore(flags); -} - -/* * Is the current CPU running the RCU-callbacks kthread? * Caller must have preemption disabled. */ @@ -1380,67 +1351,6 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, return 0; } -static void rcu_kthread_do_work(void) -{ - rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data)); - rcu_do_batch(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); - rcu_preempt_do_callbacks(); -} - -static void rcu_cpu_kthread_setup(unsigned int cpu) -{ - struct sched_param sp; - - sp.sched_priority = RCU_KTHREAD_PRIO; - sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); -} - -static void rcu_cpu_kthread_park(unsigned int cpu) -{ - per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; -} - -static int rcu_cpu_kthread_should_run(unsigned int cpu) -{ - return __get_cpu_var(rcu_cpu_has_work); -} - -/* - * Per-CPU kernel thread that invokes RCU callbacks. This replaces the - * RCU softirq used in flavors and configurations of RCU that do not - * support RCU priority boosting. - */ -static void rcu_cpu_kthread(unsigned int cpu) -{ - unsigned int *statusp = &__get_cpu_var(rcu_cpu_kthread_status); - char work, *workp = &__get_cpu_var(rcu_cpu_has_work); - int spincnt; - - for (spincnt = 0; spincnt < 10; spincnt++) { - trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); - local_bh_disable(); - *statusp = RCU_KTHREAD_RUNNING; - this_cpu_inc(rcu_cpu_kthread_loops); - local_irq_disable(); - work = *workp; - *workp = 0; - local_irq_enable(); - if (work) - rcu_kthread_do_work(); - local_bh_enable(); - if (*workp == 0) { - trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); - *statusp = RCU_KTHREAD_WAITING; - return; - } - } - *statusp = RCU_KTHREAD_YIELDING; - trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); - schedule_timeout_interruptible(2); - trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); - *statusp = RCU_KTHREAD_WAITING; -} - /* * Set the per-rcu_node kthread's affinity to cover all CPUs that are * served by the rcu_node in question. The CPU hotplug lock is still @@ -1474,27 +1384,14 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) free_cpumask_var(cm); } -static struct smp_hotplug_thread rcu_cpu_thread_spec = { - .store = &rcu_cpu_kthread_task, - .thread_should_run = rcu_cpu_kthread_should_run, - .thread_fn = rcu_cpu_kthread, - .thread_comm = "rcuc/%u", - .setup = rcu_cpu_kthread_setup, - .park = rcu_cpu_kthread_park, -}; - /* * Spawn all kthreads -- called as soon as the scheduler is running. */ static int __init rcu_spawn_kthreads(void) { struct rcu_node *rnp; - int cpu; rcu_scheduler_fully_active = 1; - for_each_possible_cpu(cpu) - per_cpu(rcu_cpu_has_work, cpu) = 0; - BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); rnp = rcu_get_root(rcu_state); (void)rcu_spawn_one_boost_kthread(rcu_state, rnp); if (NUM_RCU_NODES > 1) { @@ -1522,11 +1419,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) raw_spin_unlock_irqrestore(&rnp->lock, flags); } -static void invoke_rcu_callbacks_kthread(void) -{ - WARN_ON_ONCE(1); -} - static bool rcu_is_callbacks_kthread(void) { return false; @@ -1553,7 +1445,7 @@ static void rcu_prepare_kthreads(int cpu) #endif /* #else #ifdef CONFIG_RCU_BOOST */ -#if !defined(CONFIG_RCU_FAST_NO_HZ) +#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) /* * Check to see if any future RCU-related work will need to be done @@ -1569,6 +1461,9 @@ int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) *delta_jiffies = ULONG_MAX; return rcu_cpu_has_callbacks(cpu, NULL); } +#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */ + +#if !defined(CONFIG_RCU_FAST_NO_HZ) /* * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up @@ -1666,6 +1561,8 @@ static bool rcu_try_advance_all_cbs(void) return cbs_ready; } +#ifndef CONFIG_PREEMPT_RT_FULL + /* * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready * to invoke. If the CPU has callbacks, try to advance them. Tell the @@ -1704,6 +1601,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj) } return 0; } +#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */ /* * Prepare a CPU for idle from an RCU perspective. The first major task @@ -2061,7 +1959,7 @@ static int rcu_nocb_needs_gp(struct rcu_state *rsp) */ static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) { - wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); + swait_wake_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); } /* @@ -2079,8 +1977,8 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) static void rcu_init_one_nocb(struct rcu_node *rnp) { - init_waitqueue_head(&rnp->nocb_gp_wq[0]); - init_waitqueue_head(&rnp->nocb_gp_wq[1]); + init_swait_head(&rnp->nocb_gp_wq[0]); + init_swait_head(&rnp->nocb_gp_wq[1]); } /* Is the specified CPU a no-CPUs CPU? */ @@ -2120,7 +2018,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, return; len = atomic_long_read(&rdp->nocb_q_count); if (old_rhpp == &rdp->nocb_head) { - wake_up(&rdp->nocb_wq); /* ... only if queue was empty ... */ + swait_wake(&rdp->nocb_wq); /* ... only if queue was empty ... */ rdp->qlen_last_fqs_check = 0; } else if (len > rdp->qlen_last_fqs_check + qhimark) { wake_up_process(t); /* ... or if many callbacks queued. */ @@ -2210,7 +2108,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) */ trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait")); for (;;) { - wait_event_interruptible( + swait_event_interruptible( rnp->nocb_gp_wq[c & 0x1], (d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c))); if (likely(d)) @@ -2238,7 +2136,7 @@ static int rcu_nocb_kthread(void *arg) for (;;) { /* If not polling, wait for next batch of callbacks. */ if (!rcu_nocb_poll) - wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head); + swait_event_interruptible(rdp->nocb_wq, rdp->nocb_head); list = ACCESS_ONCE(rdp->nocb_head); if (!list) { schedule_timeout_interruptible(1); @@ -2288,7 +2186,7 @@ static int rcu_nocb_kthread(void *arg) static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { rdp->nocb_tail = &rdp->nocb_head; - init_waitqueue_head(&rdp->nocb_wq); + init_swait_head(&rdp->nocb_wq); } /* Create a kthread for each RCU flavor for each no-CBs CPU. */ @@ -2803,3 +2701,23 @@ static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) } #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ + +/* + * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the + * grace-period kthread will do force_quiescent_state() processing? + * The idea is to avoid waking up RCU core processing on such a + * CPU unless the grace period has extended for too long. + * + * This code relies on the fact that all NO_HZ_FULL CPUs are also + * CONFIG_RCU_NOCB_CPUs. + */ +static bool rcu_nohz_full_cpu(struct rcu_state *rsp) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_cpu(smp_processor_id()) && + (!rcu_gp_in_progress(rsp) || + ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ))) + return 1; +#endif /* #ifdef CONFIG_NO_HZ_FULL */ + return 0; +} diff --git a/kernel/relay.c b/kernel/relay.c index 5001c98..b915513 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -339,6 +339,10 @@ 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); } /** @@ -356,6 +360,7 @@ 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); @@ -739,15 +744,6 @@ 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 4aa8a30..3fbcb0d 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -49,7 +49,7 @@ static int __res_counter_charge(struct res_counter *counter, unsigned long val, r = ret = 0; *limit_fail_at = NULL; - local_irq_save(flags); + local_irq_save_nort(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); r = res_counter_charge_locked(c, val, force); @@ -69,7 +69,7 @@ static int __res_counter_charge(struct res_counter *counter, unsigned long val, spin_unlock(&u->lock); } } - local_irq_restore(flags); + local_irq_restore_nort(flags); return ret; } @@ -103,7 +103,7 @@ u64 res_counter_uncharge_until(struct res_counter *counter, struct res_counter *c; u64 ret = 0; - local_irq_save(flags); + local_irq_save_nort(flags); for (c = counter; c != top; c = c->parent) { u64 r; spin_lock(&c->lock); @@ -112,7 +112,7 @@ u64 res_counter_uncharge_until(struct res_counter *counter, ret = r; spin_unlock(&c->lock); } - local_irq_restore(flags); + local_irq_restore_nort(flags); return ret; } diff --git a/kernel/rt.c b/kernel/rt.c new file mode 100644 index 0000000..5d17727 --- /dev/null +++ b/kernel/rt.c @@ -0,0 +1,452 @@ +/* + * 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); + + if (ret) { + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); + migrate_disable(); + } + + return ret; +} +EXPORT_SYMBOL(rt_write_trylock); + +int __lockfunc rt_write_trylock_irqsave(rwlock_t *rwlock, unsigned long *flags) +{ + int ret; + + *flags = 0; + ret = rt_write_trylock(rwlock); + return ret; +} +EXPORT_SYMBOL(rt_write_trylock_irqsave); + +int __lockfunc rt_read_trylock(rwlock_t *rwlock) +{ + struct rt_mutex *lock = &rwlock->lock; + int ret = 1; + + /* + * recursive read locks succeed when current owns the lock, + * but not when read_depth == 0 which means that the lock is + * write locked. + */ + if (rt_mutex_owner(lock) != current) { + ret = rt_mutex_trylock(lock); + if (ret) { + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); + migrate_disable(); + } + } else if (!rwlock->read_depth) { + ret = 0; + } + + if (ret) + rwlock->read_depth++; + + return ret; +} +EXPORT_SYMBOL(rt_read_trylock); + +void __lockfunc rt_write_lock(rwlock_t *rwlock) +{ + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + migrate_disable(); + __rt_spin_lock(&rwlock->lock); +} +EXPORT_SYMBOL(rt_write_lock); + +void __lockfunc rt_read_lock(rwlock_t *rwlock) +{ + struct rt_mutex *lock = &rwlock->lock; + + /* + * recursive read locks succeed when current owns the lock + */ + if (rt_mutex_owner(lock) != current) { + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + __rt_spin_lock(lock); + migrate_disable(); + } + rwlock->read_depth++; +} + +EXPORT_SYMBOL(rt_read_lock); + +void __lockfunc rt_write_unlock(rwlock_t *rwlock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + __rt_spin_unlock(&rwlock->lock); + migrate_enable(); +} +EXPORT_SYMBOL(rt_write_unlock); + +void __lockfunc rt_read_unlock(rwlock_t *rwlock) +{ + /* Release the lock only when read_depth is down to 0 */ + if (--rwlock->read_depth == 0) { + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + __rt_spin_unlock(&rwlock->lock); + migrate_enable(); + } +} +EXPORT_SYMBOL(rt_read_unlock); + +unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock) +{ + rt_write_lock(rwlock); + + return 0; +} +EXPORT_SYMBOL(rt_write_lock_irqsave); + +unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock) +{ + rt_read_lock(rwlock); + + return 0; +} +EXPORT_SYMBOL(rt_read_lock_irqsave); + +void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock)); + lockdep_init_map(&rwlock->dep_map, name, key, 0); +#endif + rwlock->lock.save_state = 1; + rwlock->read_depth = 0; +} +EXPORT_SYMBOL(__rt_rwlock_init); + +/* + * rw_semaphores + */ + +void rt_up_write(struct rw_semaphore *rwsem) +{ + rwsem_release(&rwsem->dep_map, 1, _RET_IP_); + rt_mutex_unlock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_up_write); + +void rt_up_read(struct rw_semaphore *rwsem) +{ + if (--rwsem->read_depth == 0) { + rwsem_release(&rwsem->dep_map, 1, _RET_IP_); + rt_mutex_unlock(&rwsem->lock); + } +} +EXPORT_SYMBOL(rt_up_read); + +/* + * downgrade a write lock into a read lock + * - just wake up any readers at the front of the queue + */ +void rt_downgrade_write(struct rw_semaphore *rwsem) +{ + BUG_ON(rt_mutex_owner(&rwsem->lock) != current); + 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); + +void rt_down_write_nested_lock(struct rw_semaphore *rwsem, + struct lockdep_map *nest) +{ + rwsem_acquire_nest(&rwsem->dep_map, 0, 0, nest, _RET_IP_); + rt_mutex_lock(&rwsem->lock); +} + +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); + if (ret) + rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); + } else if (!rwsem->read_depth) { + ret = 0; + } + + if (ret) + rwsem->read_depth++; + 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; + + if (rt_mutex_owner(lock) != current) { + rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_); + 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, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)rwsem, sizeof(*rwsem)); + lockdep_init_map(&rwsem->dep_map, name, key, 0); +#endif + rwsem->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 0dd6aec..4057bc6 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> @@ -15,6 +21,7 @@ #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/timer.h> +#include <linux/ww_mutex.h> #include "rtmutex_common.h" @@ -68,6 +75,12 @@ 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 @@ -91,6 +104,12 @@ 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 * @@ -107,6 +126,18 @@ int rt_mutex_getprio(struct task_struct *task) } /* + * Called by sched_setscheduler() to check whether the priority change + * is overruled by a possible priority boosting. + */ +int rt_mutex_check_prio(struct task_struct *task, int newprio) +{ + if (!task_has_pi_waiters(task)) + return 0; + + return task_top_pi_waiter(task)->pi_list_entry.prio <= newprio; +} + +/* * Adjust the priority of a task, after its pi_waiters got modified. * * This can be both boosting and unboosting. task->pi_lock must be held. @@ -137,6 +168,14 @@ 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: */ @@ -210,7 +249,7 @@ 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; /* @@ -261,13 +300,15 @@ 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; } @@ -312,6 +353,25 @@ 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 * @@ -321,8 +381,9 @@ 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 @@ -355,12 +416,14 @@ 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; @@ -385,7 +448,6 @@ 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); @@ -395,6 +457,13 @@ 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. * @@ -413,6 +482,23 @@ 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; @@ -437,7 +523,7 @@ 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); } @@ -492,7 +578,7 @@ 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); } /* @@ -531,7 +617,7 @@ 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); @@ -565,23 +651,371 @@ 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 __sched __rt_spin_lock_slowunlock(struct rt_mutex *lock) +{ + debug_rt_mutex_unlock(lock); + + rt_mutex_deadlock_account_unlock(current); + + if (!rt_mutex_has_waiters(lock)) { + lock->owner = NULL; + raw_spin_unlock(&lock->wait_lock); + return; + } + + wakeup_next_waiter(lock); + + raw_spin_unlock(&lock->wait_lock); + + /* Undo pi boosting.when necessary */ + rt_mutex_adjust_prio(current); +} + +static void noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) +{ + raw_spin_lock(&lock->wait_lock); + __rt_spin_lock_slowunlock(lock); +} + +static void noinline __sched rt_spin_lock_slowunlock_hirq(struct rt_mutex *lock) +{ + int ret; + + do { + ret = raw_spin_trylock(&lock->wait_lock); + } while (!ret); + + __rt_spin_lock_slowunlock(lock); +} + +void __lockfunc rt_spin_lock(spinlock_t *lock) +{ + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); +} +EXPORT_SYMBOL(rt_spin_lock); + +void __lockfunc __rt_spin_lock(struct rt_mutex *lock) +{ + rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock); +} +EXPORT_SYMBOL(__rt_spin_lock); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) +{ + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); +} +EXPORT_SYMBOL(rt_spin_lock_nested); +#endif + +void __lockfunc rt_spin_unlock(spinlock_t *lock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(rt_spin_unlock); + +void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock_hirq); +} + +void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) +{ + rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(__rt_spin_unlock); + +/* + * Wait for the lock to get unlocked: instead of polling for an unlock + * (like raw spinlocks do), we lock and unlock, to force the kernel to + * schedule if there's contention: + */ +void __lockfunc rt_spin_unlock_wait(spinlock_t *lock) +{ + spin_lock(lock); + spin_unlock(lock); +} +EXPORT_SYMBOL(rt_spin_unlock_wait); + +int __lockfunc rt_spin_trylock(spinlock_t *lock) +{ + int ret = rt_mutex_trylock(&lock->lock); + + if (ret) + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock); + +int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) +{ + int ret; + + local_bh_disable(); + ret = rt_mutex_trylock(&lock->lock); + if (ret) { + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } else + local_bh_enable(); + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock_bh); + +int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) +{ + int ret; + + *flags = 0; + ret = rt_mutex_trylock(&lock->lock); + if (ret) { + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock_irqsave); + +int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock) +{ + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + if (atomic_add_unless(atomic, -1, 1)) + return 0; + rt_spin_lock(lock); + if (atomic_dec_and_test(atomic)){ + migrate_disable(); + return 1; + } + rt_spin_unlock(lock); + return 0; +} +EXPORT_SYMBOL(atomic_dec_and_spin_lock); + +void +__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif +} +EXPORT_SYMBOL(__rt_spin_lock_init); + +#endif /* PREEMPT_RT_FULL */ + +#ifdef CONFIG_PREEMPT_RT_FULL +static inline int __sched +__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) +{ + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); + struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx); + + if (!hold_ctx) + return 0; + + if (unlikely(ctx == hold_ctx)) + return -EALREADY; + + if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && + (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(ctx->contending_lock); + ctx->contending_lock = ww; +#endif + return -EDEADLK; + } + + return 0; +} +#else +static inline int __sched +__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) +{ + BUG(); + return 0; +} + +#endif + /** * __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 * @@ -590,7 +1024,8 @@ void rt_mutex_adjust_pi(struct task_struct *task) static int __sched __rt_mutex_slowlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - struct rt_mutex_waiter *waiter) + struct rt_mutex_waiter *waiter, + struct ww_acquire_ctx *ww_ctx) { int ret = 0; @@ -613,6 +1048,12 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, break; } + if (ww_ctx && ww_ctx->acquired > 0) { + ret = __mutex_lock_check_stamp(lock, ww_ctx); + if (ret) + break; + } + raw_spin_unlock(&lock->wait_lock); debug_rt_mutex_print_deadlock(waiter); @@ -626,23 +1067,102 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, return ret; } +static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, + struct ww_acquire_ctx *ww_ctx) +{ +#ifdef CONFIG_DEBUG_MUTEXES + /* + * If this WARN_ON triggers, you used ww_mutex_lock to acquire, + * but released with a normal mutex_unlock in this call. + * + * This should never happen, always use ww_mutex_unlock. + */ + DEBUG_LOCKS_WARN_ON(ww->ctx); + + /* + * Not quite done after calling ww_acquire_done() ? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); + + if (ww_ctx->contending_lock) { + /* + * After -EDEADLK you tried to + * acquire a different ww_mutex? Bad! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); + + /* + * You called ww_mutex_lock after receiving -EDEADLK, + * but 'forgot' to unlock everything else first? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); + ww_ctx->contending_lock = NULL; + } + + /* + * Naughty, using a different class will lead to undefined behavior! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); +#endif + ww_ctx->acquired++; +} + +#ifdef CONFIG_PREEMPT_RT_FULL +static void ww_mutex_account_lock(struct rt_mutex *lock, + struct ww_acquire_ctx *ww_ctx) +{ + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); + struct rt_mutex_waiter *waiter; + + /* + * This branch gets optimized out for the common case, + * and is only important for ww_mutex_lock. + */ + ww_mutex_lock_acquired(ww, ww_ctx); + ww->ctx = ww_ctx; + + /* + * Give any possible sleeping processes the chance to wake up, + * so they can recheck if they have to back off. + */ + plist_for_each_entry(waiter, &lock->wait_list, list_entry) { + + /* XXX debug rt mutex waiter wakeup */ + + BUG_ON(waiter->lock != lock); + rt_mutex_wake_waiter(waiter); + } +} + +#else + +static void ww_mutex_account_lock(struct rt_mutex *lock, + struct ww_acquire_ctx *ww_ctx) +{ + BUG(); +} +#endif + /* * Slow path lock function: */ static int __sched rt_mutex_slowlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - int detect_deadlock) + int detect_deadlock, struct ww_acquire_ctx *ww_ctx) { 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)) { + if (ww_ctx) + ww_mutex_account_lock(lock, ww_ctx); raw_spin_unlock(&lock->wait_lock); return 0; } @@ -659,12 +1179,14 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock); if (likely(!ret)) - ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); + ret = __rt_mutex_slowlock(lock, state, timeout, &waiter, ww_ctx); set_current_state(TASK_RUNNING); if (unlikely(ret)) remove_waiter(lock, &waiter); + else if (ww_ctx) + ww_mutex_account_lock(lock, ww_ctx); /* * try_to_take_rt_mutex() sets the waiter bit @@ -691,7 +1213,9 @@ rt_mutex_slowtrylock(struct rt_mutex *lock) { int ret = 0; - raw_spin_lock(&lock->wait_lock); + if (!raw_spin_trylock(&lock->wait_lock)) + return ret; + init_lists(lock); if (likely(rt_mutex_owner(lock) != current)) { @@ -742,30 +1266,33 @@ rt_mutex_slowunlock(struct rt_mutex *lock) */ static inline int rt_mutex_fastlock(struct rt_mutex *lock, int state, - int detect_deadlock, + int detect_deadlock, struct ww_acquire_ctx *ww_ctx, int (*slowfn)(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - int detect_deadlock)) + int detect_deadlock, + struct ww_acquire_ctx *ww_ctx)) { if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 0; } else - return slowfn(lock, state, NULL, detect_deadlock); + return slowfn(lock, state, NULL, detect_deadlock, ww_ctx); } static inline int rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, int detect_deadlock, + struct ww_acquire_ctx *ww_ctx, int (*slowfn)(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - int detect_deadlock)) + int detect_deadlock, + struct ww_acquire_ctx *ww_ctx)) { if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 0; } else - return slowfn(lock, state, timeout, detect_deadlock); + return slowfn(lock, state, timeout, detect_deadlock, ww_ctx); } static inline int @@ -798,19 +1325,19 @@ void __sched rt_mutex_lock(struct rt_mutex *lock) { might_sleep(); - rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, 0, rt_mutex_slowlock); + rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, 0, NULL, rt_mutex_slowlock); } 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, @@ -819,22 +1346,43 @@ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock, might_sleep(); return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, - detect_deadlock, rt_mutex_slowlock); + detect_deadlock, NULL, rt_mutex_slowlock); } 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, NULL, rt_mutex_slowlock); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); + +/** * rt_mutex_timed_lock - lock a rt_mutex interruptible * the timeout structure is provided * by the caller * - * @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) */ @@ -845,7 +1393,7 @@ rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout, might_sleep(); return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, - detect_deadlock, rt_mutex_slowlock); + detect_deadlock, NULL, rt_mutex_slowlock); } EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); @@ -903,12 +1451,11 @@ 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); } -EXPORT_SYMBOL_GPL(__rt_mutex_init); +EXPORT_SYMBOL(__rt_mutex_init); /** * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a @@ -923,7 +1470,7 @@ 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); @@ -972,6 +1519,35 @@ 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_irq(&task->pi_lock); + if (task->pi_blocked_on) { + raw_spin_unlock_irq(&task->pi_lock); + raw_spin_unlock(&lock->wait_lock); + return -EAGAIN; + } + task->pi_blocked_on = PI_REQUEUE_INPROGRESS; + raw_spin_unlock_irq(&task->pi_lock); +#endif + ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock); if (ret && !rt_mutex_owner(lock)) { @@ -1041,7 +1617,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, set_current_state(TASK_INTERRUPTIBLE); - ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); + ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL); set_current_state(TASK_RUNNING); @@ -1058,3 +1634,88 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, return ret; } + +static inline int +ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH + unsigned tmp; + + if (ctx->deadlock_inject_countdown-- == 0) { + tmp = ctx->deadlock_inject_interval; + if (tmp > UINT_MAX/4) + tmp = UINT_MAX; + else + tmp = tmp*2 + tmp + tmp/2; + + ctx->deadlock_inject_interval = tmp; + ctx->deadlock_inject_countdown = tmp; + ctx->contending_lock = lock; + + ww_mutex_unlock(lock); + + return -EDEADLK; + } +#endif + + return 0; +} + +#ifdef CONFIG_PREEMPT_RT_FULL +int __sched +__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) +{ + int ret; + + might_sleep(); + + mutex_acquire(&lock->base.dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ww_ctx); + if (ret) + mutex_release(&lock->base.dep_map, 1, _RET_IP_); + else if (!ret && ww_ctx->acquired > 1) + return ww_mutex_deadlock_injection(lock, ww_ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); + +int __sched +__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) +{ + int ret; + + might_sleep(); + + mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, + _RET_IP_); + ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ww_ctx); + if (ret) + mutex_release(&lock->base.dep_map, 1, _RET_IP_); + else if (!ret && ww_ctx->acquired > 1) + return ww_mutex_deadlock_injection(lock, ww_ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(__ww_mutex_lock); + +void __sched ww_mutex_unlock(struct ww_mutex *lock) +{ + /* + * The unlocking fastpath is the 0->1 transition from 'locked' + * into 'unlocked' state: + */ + if (lock->ctx) { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); +#endif + if (lock->ctx->acquired > 0) + lock->ctx->acquired--; + lock->ctx = NULL; + } + + mutex_release(&lock->base.dep_map, 1, _RET_IP_); + rt_mutex_unlock(&lock->base.lock); +} +EXPORT_SYMBOL(ww_mutex_unlock); +#endif diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h index 53a66c8..6ec3dc1 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/core.c b/kernel/sched/core.c index a494ace..8749d20 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -272,7 +272,11 @@ 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 @@ -491,6 +495,7 @@ 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) @@ -535,6 +540,37 @@ void resched_task(struct task_struct *p) smp_send_reschedule(cpu); } +#ifdef CONFIG_PREEMPT_LAZY +void resched_task_lazy(struct task_struct *p) +{ + int cpu; + + if (!sched_feat(PREEMPT_LAZY)) { + resched_task(p); + return; + } + + assert_raw_spin_locked(&task_rq(p)->lock); + + if (test_tsk_need_resched(p)) + return; + + if (test_tsk_need_resched_lazy(p)) + return; + + set_tsk_need_resched_lazy(p); + + cpu = task_cpu(p); + if (cpu == smp_processor_id()) + return; + + /* NEED_RESCHED_LAZY must be visible before we test polling */ + smp_mb(); + if (!tsk_is_polling(p)) + smp_send_reschedule(cpu); +} +#endif + void resched_cpu(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -699,6 +735,17 @@ void resched_task(struct task_struct *p) assert_raw_spin_locked(&task_rq(p)->lock); set_tsk_need_resched(p); } +#ifdef CONFIG_PREEMPT_LAZY +void resched_task_lazy(struct task_struct *p) +{ + if (!sched_feat(PREEMPT_LAZY)) { + resched_task(p); + return; + } + assert_raw_spin_locked(&task_rq(p)->lock); + set_tsk_need_resched_lazy(p); +} +#endif #endif /* CONFIG_SMP */ #if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \ @@ -1024,6 +1071,18 @@ struct migration_arg { static int migration_cpu_stop(void *data); +static bool check_task_state(struct task_struct *p, long match_state) +{ + bool match = false; + + raw_spin_lock_irq(&p->pi_lock); + if (p->state == match_state || p->saved_state == match_state) + match = true; + raw_spin_unlock_irq(&p->pi_lock); + + return match; +} + /* * wait_task_inactive - wait for a thread to unschedule. * @@ -1068,7 +1127,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * is actually now running somewhere else! */ while (task_running(rq, p)) { - if (match_state && unlikely(p->state != match_state)) + if (match_state && !check_task_state(p, match_state)) return 0; cpu_relax(); } @@ -1083,7 +1142,8 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) running = task_running(rq, p); on_rq = p->on_rq; ncsw = 0; - if (!match_state || p->state == match_state) + if (!match_state || p->state == match_state + || p->saved_state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ task_rq_unlock(rq, p, &flags); @@ -1229,6 +1289,12 @@ out: } } + /* + * Clear PF_NO_SETAFFINITY, otherwise we wreckage + * migrate_disable/enable. See optimization for + * PF_NO_SETAFFINITY tasks there. + */ + p->flags &= ~PF_NO_SETAFFINITY; return dest_cpu; } @@ -1308,10 +1374,6 @@ 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)); } /* @@ -1486,8 +1548,27 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) */ smp_mb__before_spinlock(); raw_spin_lock_irqsave(&p->pi_lock, flags); - if (!(p->state & state)) + if (!(p->state & state)) { + /* + * The task might be running due to a spinlock sleeper + * wakeup. Check the saved state and set it to running + * if the wakeup condition is true. + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) { + if (p->saved_state & state) { + p->saved_state = TASK_RUNNING; + success = 1; + } + } goto out; + } + + /* + * If this is a regular wakeup, then we can unconditionally + * clear the saved state of a "lock sleeper". + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) + p->saved_state = TASK_RUNNING; success = 1; /* we're going to change ->state */ cpu = task_cpu(p); @@ -1530,42 +1611,6 @@ 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); - - if (WARN_ON_ONCE(rq != this_rq()) || - WARN_ON_ONCE(p == current)) - return; - - lockdep_assert_held(&rq->lock); - - if (!raw_spin_trylock(&p->pi_lock)) { - raw_spin_unlock(&rq->lock); - raw_spin_lock(&p->pi_lock); - raw_spin_lock(&rq->lock); - } - - if (!(p->state & TASK_NORMAL)) - goto out; - - if (!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. * @@ -1579,11 +1624,23 @@ out: */ int wake_up_process(struct task_struct *p) { - WARN_ON(task_is_stopped_or_traced(p)); + WARN_ON(__task_is_stopped_or_traced(p)); return try_to_wake_up(p, TASK_NORMAL, 0); } EXPORT_SYMBOL(wake_up_process); +/** + * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock" + * @p: The process to be woken up. + * + * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate + * the nature of the wakeup. + */ +int wake_up_lock_sleeper(struct task_struct *p) +{ + return try_to_wake_up(p, TASK_ALL, WF_LOCK_SLEEPER); +} + int wake_up_state(struct task_struct *p, unsigned int state) { return try_to_wake_up(p, state, 0); @@ -1721,6 +1778,9 @@ void sched_fork(struct task_struct *p) /* Want to start with kernel preemption disabled. */ task_thread_info(p)->preempt_count = 1; #endif +#ifdef CONFIG_HAVE_PREEMPT_LAZY + task_thread_info(p)->preempt_lazy_count = 0; +#endif #ifdef CONFIG_SMP plist_node_init(&p->pushable_tasks, MAX_PRIO); #endif @@ -1887,8 +1947,12 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) finish_arch_post_lock_switch(); fire_sched_in_preempt_notifiers(current); + /* + * We use mmdrop_delayed() here so we don't have to do the + * full __mmdrop() when we are the last user. + */ if (mm) - mmdrop(mm); + mmdrop_delayed(mm); if (unlikely(prev_state == TASK_DEAD)) { /* * Remove function-return probe instances associated with this @@ -2232,8 +2296,13 @@ void __kprobes add_preempt_count(int val) DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK - 10); #endif - if (preempt_count() == val) - trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + if (preempt_count() == val) { + unsigned long ip = get_parent_ip(CALLER_ADDR1); +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; +#endif + trace_preempt_off(CALLER_ADDR0, ip); + } } EXPORT_SYMBOL(add_preempt_count); @@ -2276,6 +2345,13 @@ static noinline void __schedule_bug(struct task_struct *prev) print_modules(); if (irqs_disabled()) print_irqtrace_events(prev); +#ifdef CONFIG_DEBUG_PREEMPT + if (in_atomic_preempt_off()) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif dump_stack(); add_taint(TAINT_WARN, LOCKDEP_STILL_OK); } @@ -2299,6 +2375,133 @@ 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); + /* mask==cpumask_of(task_cpu(p)) which has a cpumask_weight==1 */ + p->nr_cpus_allowed = 1; + + /* Let migrate_enable know to fix things back up */ + p->migrate_disable |= MIGRATE_DISABLE_SET_AFFIN; +} + +void migrate_disable(void) +{ + struct task_struct *p = current; + + if (in_atomic()) { +#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic++; +#endif + return; + } + +#ifdef CONFIG_SCHED_DEBUG + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } +#endif + + if (p->migrate_disable) { + p->migrate_disable++; + return; + } + + preempt_disable(); + preempt_lazy_disable(); + pin_current_cpu(); + p->migrate_disable = 1; + preempt_enable(); +} +EXPORT_SYMBOL(migrate_disable); + +void migrate_enable(void) +{ + struct task_struct *p = current; + const struct cpumask *mask; + unsigned long flags; + struct rq *rq; + + if (in_atomic()) { +#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic--; +#endif + return; + } + +#ifdef CONFIG_SCHED_DEBUG + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } +#endif + WARN_ON_ONCE(p->migrate_disable <= 0); + + if (migrate_disable_count(p) > 1) { + p->migrate_disable--; + return; + } + + preempt_disable(); + if (unlikely(migrate_disabled_updated(p))) { + /* + * Undo whatever update_migrate_disable() did, also see there + * about locking. + */ + rq = this_rq(); + raw_spin_lock_irqsave(&rq->lock, flags); + + /* + * Clearing migrate_disable causes tsk_cpus_allowed to + * show the tasks original cpu affinity. + */ + p->migrate_disable = 0; + mask = tsk_cpus_allowed(p); + if (p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, mask); + p->nr_cpus_allowed = cpumask_weight(mask); + raw_spin_unlock_irqrestore(&rq->lock, flags); + } else + p->migrate_disable = 0; + + unpin_current_cpu(); + preempt_enable(); + preempt_lazy_enable(); +} +EXPORT_SYMBOL(migrate_enable); +#else +static inline void update_migrate_disable(struct task_struct *p) { } +#define migrate_disabled_updated(p) 0 +#endif + static void put_prev_task(struct rq *rq, struct task_struct *prev) { if (prev->on_rq || rq->skip_clock_update < 0) @@ -2398,6 +2601,8 @@ need_resched: smp_mb__before_spinlock(); raw_spin_lock_irq(&rq->lock); + update_migrate_disable(prev); + switch_count = &prev->nivcsw; if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { if (unlikely(signal_pending_state(prev->state, prev))) { @@ -2405,19 +2610,6 @@ 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; } @@ -2430,6 +2622,7 @@ need_resched: put_prev_task(rq, prev); next = pick_next_task(rq); clear_tsk_need_resched(prev); + clear_tsk_need_resched_lazy(prev); rq->skip_clock_update = 0; if (likely(prev != next)) { @@ -2460,6 +2653,14 @@ static inline void sched_submit_work(struct task_struct *tsk) { 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. @@ -2468,12 +2669,19 @@ 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->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); @@ -2519,9 +2727,26 @@ asmlinkage void __sched notrace preempt_schedule(void) if (likely(!preemptible())) return; +#ifdef CONFIG_PREEMPT_LAZY + /* + * Check for lazy preemption + */ + if (current_thread_info()->preempt_lazy_count && + !test_thread_flag(TIF_NEED_RESCHED)) + return; +#endif do { 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); /* @@ -2694,10 +2919,10 @@ void complete(struct completion *x) { unsigned long flags; - spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); x->done++; - __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL); - spin_unlock_irqrestore(&x->wait.lock, flags); + __swait_wake_locked(&x->wait, TASK_NORMAL, 1); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); } EXPORT_SYMBOL(complete); @@ -2714,10 +2939,10 @@ void complete_all(struct completion *x) { unsigned long flags; - spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); x->done += UINT_MAX/2; - __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL); - spin_unlock_irqrestore(&x->wait.lock, flags); + __swait_wake_locked(&x->wait, TASK_NORMAL, 0); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); } EXPORT_SYMBOL(complete_all); @@ -2726,20 +2951,20 @@ do_wait_for_common(struct completion *x, long (*action)(long), long timeout, int state) { if (!x->done) { - DECLARE_WAITQUEUE(wait, current); + DEFINE_SWAITER(wait); - __add_wait_queue_tail_exclusive(&x->wait, &wait); + swait_prepare_locked(&x->wait, &wait); do { if (signal_pending_state(state, current)) { timeout = -ERESTARTSYS; break; } __set_current_state(state); - spin_unlock_irq(&x->wait.lock); + raw_spin_unlock_irq(&x->wait.lock); timeout = action(timeout); - spin_lock_irq(&x->wait.lock); + raw_spin_lock_irq(&x->wait.lock); } while (!x->done && timeout); - __remove_wait_queue(&x->wait, &wait); + swait_finish_locked(&x->wait, &wait); if (!x->done) return timeout; } @@ -2753,9 +2978,9 @@ __wait_for_common(struct completion *x, { might_sleep(); - spin_lock_irq(&x->wait.lock); + raw_spin_lock_irq(&x->wait.lock); timeout = do_wait_for_common(x, action, timeout, state); - spin_unlock_irq(&x->wait.lock); + raw_spin_unlock_irq(&x->wait.lock); return timeout; } @@ -2931,12 +3156,12 @@ bool try_wait_for_completion(struct completion *x) unsigned long flags; int ret = 1; - spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = 0; else x->done--; - spin_unlock_irqrestore(&x->wait.lock, flags); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); return ret; } EXPORT_SYMBOL(try_wait_for_completion); @@ -2954,10 +3179,10 @@ bool completion_done(struct completion *x) unsigned long flags; int ret = 1; - spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = 0; - spin_unlock_irqrestore(&x->wait.lock, flags); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); return ret; } EXPORT_SYMBOL(completion_done); @@ -3018,7 +3243,8 @@ EXPORT_SYMBOL(sleep_on_timeout); * This function changes the 'effective' priority of a task. It does * not touch ->normal_prio like __setscheduler(). * - * Used by the rt_mutex code to implement priority inheritance logic. + * Used by the rt_mutex code to implement priority inheritance + * logic. Call site only calls if the priority of the task changed. */ void rt_mutex_setprio(struct task_struct *p, int prio) { @@ -3249,20 +3475,25 @@ static struct task_struct *find_process_by_pid(pid_t pid) return pid ? find_task_by_vpid(pid) : current; } -/* Actually do priority change: must hold rq lock. */ -static void -__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) +static void __setscheduler_params(struct task_struct *p, int policy, int prio) { p->policy = policy; p->rt_priority = prio; p->normal_prio = normal_prio(p); + set_load_weight(p); +} + +/* Actually do priority change: must hold rq lock. */ +static void +__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) +{ + __setscheduler_params(p, policy, prio); /* we are holding p->pi_lock already */ p->prio = rt_mutex_getprio(p); if (rt_prio(p->prio)) p->sched_class = &rt_sched_class; else p->sched_class = &fair_sched_class; - set_load_weight(p); } /* @@ -3284,6 +3515,7 @@ static bool check_same_owner(struct task_struct *p) static int __sched_setscheduler(struct task_struct *p, int policy, const struct sched_param *param, bool user) { + int newprio = MAX_RT_PRIO - 1 - param->sched_priority; int retval, oldprio, oldpolicy = -1, on_rq, running; unsigned long flags; const struct sched_class *prev_class; @@ -3379,10 +3611,13 @@ recheck: } /* - * If not changing anything there's no need to proceed further: + * If not changing anything there's no need to proceed + * further, but store a possible modification of + * reset_on_fork. */ if (unlikely(policy == p->policy && (!rt_policy(policy) || param->sched_priority == p->rt_priority))) { + p->sched_reset_on_fork = reset_on_fork; task_rq_unlock(rq, p, &flags); return 0; } @@ -3408,6 +3643,25 @@ recheck: task_rq_unlock(rq, p, &flags); goto recheck; } + + p->sched_reset_on_fork = reset_on_fork; + oldprio = p->prio; + + /* + * Special case for priority boosted tasks. + * + * If the new priority is lower or equal (user space view) + * than the current (boosted) priority, we just store the new + * normal parameters and do not touch the scheduler class and + * the runqueue. This will be done when the task deboost + * itself. + */ + if (rt_mutex_check_prio(p, newprio)) { + __setscheduler_params(p, policy, param->sched_priority); + task_rq_unlock(rq, p, &flags); + return 0; + } + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) @@ -3415,17 +3669,18 @@ recheck: if (running) p->sched_class->put_prev_task(rq, p); - p->sched_reset_on_fork = reset_on_fork; - - oldprio = p->prio; prev_class = p->sched_class; __setscheduler(rq, p, policy, param->sched_priority); if (running) p->sched_class->set_curr_task(rq); - if (on_rq) - enqueue_task(rq, p, 0); - + if (on_rq) { + /* + * We enqueue to tail when the priority of a task is + * increased (user space view). + */ + enqueue_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0); + } check_class_changed(rq, p, prev_class, oldprio); task_rq_unlock(rq, p, &flags); @@ -3801,9 +4056,17 @@ 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) @@ -3844,6 +4107,7 @@ 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()); @@ -3857,6 +4121,7 @@ int __sched __cond_resched_softirq(void) return 0; } EXPORT_SYMBOL(__cond_resched_softirq); +#endif /** * yield - yield the current processor to other threads. @@ -4206,6 +4471,7 @@ void init_idle(struct task_struct *idle, int cpu) rcu_read_unlock(); rq->curr = rq->idle = idle; + idle->on_rq = 1; #if defined(CONFIG_SMP) idle->on_cpu = 1; #endif @@ -4213,7 +4479,9 @@ void init_idle(struct task_struct *idle, int cpu) /* Set the preempt count _outside_ the spinlocks! */ task_thread_info(idle)->preempt_count = 0; - +#ifdef CONFIG_HAVE_PREEMPT_LAZY + task_thread_info(idle)->preempt_lazy_count = 0; +#endif /* * The idle tasks have their own, simple scheduling class: */ @@ -4228,11 +4496,90 @@ void init_idle(struct task_struct *idle, int cpu) #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->nr_cpus_allowed = cpumask_weight(new_mask); + } cpumask_copy(&p->cpus_allowed, new_mask); - p->nr_cpus_allowed = cpumask_weight(new_mask); +} + +static DEFINE_PER_CPU(struct cpumask, sched_cpumasks); +static DEFINE_MUTEX(sched_down_mutex); +static cpumask_t sched_down_cpumask; + +void tell_sched_cpu_down_begin(int cpu) +{ + mutex_lock(&sched_down_mutex); + cpumask_set_cpu(cpu, &sched_down_cpumask); + mutex_unlock(&sched_down_mutex); +} + +void tell_sched_cpu_down_done(int cpu) +{ + mutex_lock(&sched_down_mutex); + cpumask_clear_cpu(cpu, &sched_down_cpumask); + mutex_unlock(&sched_down_mutex); +} + +/** + * migrate_me - try to move the current task off this cpu + * + * Used by the pin_current_cpu() code to try to get tasks + * to move off the current CPU as it is going down. + * It will only move the task if the task isn't pinned to + * the CPU (with migrate_disable, affinity or NO_SETAFFINITY) + * and the task has to be in a RUNNING state. Otherwise the + * movement of the task will wake it up (change its state + * to running) when the task did not expect it. + * + * Returns 1 if it succeeded in moving the current task + * 0 otherwise. + */ +int migrate_me(void) +{ + struct task_struct *p = current; + struct migration_arg arg; + struct cpumask *cpumask; + struct cpumask *mask; + unsigned long flags; + unsigned int dest_cpu; + struct rq *rq; + + /* + * We can not migrate tasks bounded to a CPU or tasks not + * running. The movement of the task will wake it up. + */ + if (p->flags & PF_NO_SETAFFINITY || p->state) + return 0; + + mutex_lock(&sched_down_mutex); + rq = task_rq_lock(p, &flags); + + cpumask = &__get_cpu_var(sched_cpumasks); + mask = &p->cpus_allowed; + + cpumask_andnot(cpumask, mask, &sched_down_cpumask); + + if (!cpumask_weight(cpumask)) { + /* It's only on this CPU? */ + task_rq_unlock(rq, p, &flags); + mutex_unlock(&sched_down_mutex); + return 0; + } + + dest_cpu = cpumask_any_and(cpu_active_mask, cpumask); + + arg.task = p; + arg.dest_cpu = dest_cpu; + + task_rq_unlock(rq, p, &flags); + + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); + tlb_migrate_finish(p->mm); + mutex_unlock(&sched_down_mutex); + + return 1; } /* @@ -4278,7 +4625,7 @@ 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); @@ -4367,6 +4714,8 @@ 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. @@ -4379,7 +4728,12 @@ 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; } /* @@ -4703,6 +5057,10 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_DEAD: calc_load_migrate(rq); + if (per_cpu(idle_last_mm, cpu)) { + mmdrop(per_cpu(idle_last_mm, cpu)); + per_cpu(idle_last_mm, cpu) = NULL; + } break; #endif } @@ -6575,7 +6933,8 @@ 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); } @@ -6585,7 +6944,8 @@ void __might_sleep(const char *file, int line, int preempt_offset) static unsigned long prev_jiffy; /* ratelimiting */ rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ - if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || + if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && + !is_idle_task(current)) || system_state != SYSTEM_RUNNING || oops_in_progress) return; if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) @@ -6603,6 +6963,13 @@ void __might_sleep(const char *file, int line, int preempt_offset) debug_show_held_locks(current); if (irqs_disabled()) print_irqtrace_events(current); +#ifdef CONFIG_DEBUG_PREEMPT + if (!preempt_count_equals(preempt_offset)) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif dump_stack(); } EXPORT_SYMBOL(__might_sleep); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 9994791..1681f49 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -655,37 +655,45 @@ static void __vtime_account_system(struct task_struct *tsk) void vtime_account_system(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); __vtime_account_system(tsk); - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); } void vtime_gen_account_irq_exit(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); __vtime_account_system(tsk); if (context_tracking_in_user()) tsk->vtime_snap_whence = VTIME_USER; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); } void vtime_account_user(struct task_struct *tsk) { cputime_t delta_cpu; - write_seqlock(&tsk->vtime_seqlock); + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); delta_cpu = get_vtime_delta(tsk); tsk->vtime_snap_whence = VTIME_SYS; account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); } void vtime_user_enter(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); __vtime_account_system(tsk); tsk->vtime_snap_whence = VTIME_USER; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); } void vtime_guest_enter(struct task_struct *tsk) @@ -697,19 +705,23 @@ void vtime_guest_enter(struct task_struct *tsk) * synchronization against the reader (task_gtime()) * that can thus safely catch up with a tickless delta. */ - write_seqlock(&tsk->vtime_seqlock); + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); __vtime_account_system(tsk); current->flags |= PF_VCPU; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); } EXPORT_SYMBOL_GPL(vtime_guest_enter); void vtime_guest_exit(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); __vtime_account_system(tsk); current->flags &= ~PF_VCPU; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); } EXPORT_SYMBOL_GPL(vtime_guest_exit); @@ -722,24 +734,30 @@ void vtime_account_idle(struct task_struct *tsk) void arch_vtime_task_switch(struct task_struct *prev) { - write_seqlock(&prev->vtime_seqlock); + raw_spin_lock(&prev->vtime_lock); + write_seqcount_begin(&prev->vtime_seq); prev->vtime_snap_whence = VTIME_SLEEPING; - write_sequnlock(&prev->vtime_seqlock); + write_seqcount_end(&prev->vtime_seq); + raw_spin_unlock(&prev->vtime_lock); - write_seqlock(¤t->vtime_seqlock); + raw_spin_lock(¤t->vtime_lock); + write_seqcount_begin(¤t->vtime_seq); current->vtime_snap_whence = VTIME_SYS; current->vtime_snap = sched_clock_cpu(smp_processor_id()); - write_sequnlock(¤t->vtime_seqlock); + write_seqcount_end(¤t->vtime_seq); + raw_spin_unlock(¤t->vtime_lock); } void vtime_init_idle(struct task_struct *t, int cpu) { unsigned long flags; - write_seqlock_irqsave(&t->vtime_seqlock, flags); + raw_spin_lock_irqsave(&t->vtime_lock, flags); + write_seqcount_begin(&t->vtime_seq); t->vtime_snap_whence = VTIME_SYS; t->vtime_snap = sched_clock_cpu(cpu); - write_sequnlock_irqrestore(&t->vtime_seqlock, flags); + write_seqcount_end(&t->vtime_seq); + raw_spin_unlock_irqrestore(&t->vtime_lock, flags); } cputime_t task_gtime(struct task_struct *t) @@ -748,13 +766,13 @@ cputime_t task_gtime(struct task_struct *t) cputime_t gtime; do { - seq = read_seqbegin(&t->vtime_seqlock); + seq = read_seqcount_begin(&t->vtime_seq); gtime = t->gtime; if (t->flags & PF_VCPU) gtime += vtime_delta(t); - } while (read_seqretry(&t->vtime_seqlock, seq)); + } while (read_seqcount_retry(&t->vtime_seq, seq)); return gtime; } @@ -777,7 +795,7 @@ fetch_task_cputime(struct task_struct *t, *udelta = 0; *sdelta = 0; - seq = read_seqbegin(&t->vtime_seqlock); + seq = read_seqcount_begin(&t->vtime_seq); if (u_dst) *u_dst = *u_src; @@ -801,7 +819,7 @@ fetch_task_cputime(struct task_struct *t, if (t->vtime_snap_whence == VTIME_SYS) *sdelta = delta; } - } while (read_seqretry(&t->vtime_seqlock, seq)); + } while (read_seqcount_retry(&t->vtime_seq, seq)); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index fd9ca1d..70812af 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -256,6 +256,9 @@ 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 @@ -585,6 +588,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) #endif P(policy); P(prio); +#ifdef CONFIG_PREEMPT_RT_FULL + P(migrate_disable); +#endif + P(nr_cpus_allowed); #undef PN #undef __PN #undef P diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 790e2fc..0af1448 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1902,7 +1902,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) ideal_runtime = sched_slice(cfs_rq, curr); delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; if (delta_exec > ideal_runtime) { - resched_task(rq_of(cfs_rq)->curr); + resched_task_lazy(rq_of(cfs_rq)->curr); /* * The current task ran long enough, ensure it doesn't get * re-elected due to buddy favours. @@ -1926,7 +1926,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) return; if (delta > ideal_runtime) - resched_task(rq_of(cfs_rq)->curr); + resched_task_lazy(rq_of(cfs_rq)->curr); } static void @@ -2047,7 +2047,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) * validating it and just reschedule. */ if (queued) { - resched_task(rq_of(cfs_rq)->curr); + resched_task_lazy(rq_of(cfs_rq)->curr); return; } /* @@ -2237,7 +2237,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, * hierarchy can be throttled */ if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) - resched_task(rq_of(cfs_rq)->curr); + resched_task_lazy(rq_of(cfs_rq)->curr); } static __always_inline @@ -2837,7 +2837,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) if (delta < 0) { if (rq->curr == p) - resched_task(p); + resched_task_lazy(p); return; } @@ -3704,7 +3704,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; preempt: - resched_task(curr); + resched_task_lazy(curr); /* * Only set the backward buddy when the current task is still * on the rq. This can happen when a wakeup gets interleaved @@ -5979,7 +5979,7 @@ static void task_fork_fair(struct task_struct *p) * 'current' within the tree based on its new key value. */ swap(curr->vruntime, se->vruntime); - resched_task(rq->curr); + resched_task_lazy(rq->curr); } se->vruntime -= cfs_rq->min_vruntime; @@ -6004,7 +6004,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) */ if (rq->curr == p) { if (p->prio > oldprio) - resched_task(rq->curr); + resched_task_lazy(rq->curr); } else check_preempt_curr(rq, p, 0); } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 99399f8..4594051 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -50,11 +50,18 @@ SCHED_FEAT(LB_BIAS, true) */ SCHED_FEAT(NONTASK_POWER, true) +#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, true) +#else +SCHED_FEAT(TTWU_QUEUE, false) +# ifdef CONFIG_PREEMPT_LAZY +SCHED_FEAT(PREEMPT_LAZY, true) +# endif +#endif SCHED_FEAT(FORCE_SD_OVERLAP, false) SCHED_FEAT(RT_RUNTIME_SHARE, true) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index ff04e1a..240fc60 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -43,6 +43,7 @@ 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; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 4f31059..2843303 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -898,6 +898,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) #define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ #define WF_FORK 0x02 /* child wakeup after fork */ #define WF_MIGRATED 0x4 /* internal use, task got migrated */ +#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */ /* * To aid in avoiding the subversion of "niceness" due to uneven distribution @@ -1045,6 +1046,15 @@ extern void init_sched_fair_class(void); extern void resched_task(struct task_struct *p); extern void resched_cpu(int cpu); +#ifdef CONFIG_PREEMPT_LAZY +extern void resched_task_lazy(struct task_struct *tsk); +#else +static inline void resched_task_lazy(struct task_struct *tsk) +{ + resched_task(tsk); +} +#endif + extern struct rt_bandwidth def_rt_bandwidth; extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); diff --git a/kernel/signal.c b/kernel/signal.c index ded28b9..3d32f54 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -14,6 +14,7 @@ #include <linux/export.h> #include <linux/init.h> #include <linux/sched.h> +#include <linux/sched/rt.h> #include <linux/fs.h> #include <linux/tty.h> #include <linux/binfmts.h> @@ -349,13 +350,45 @@ 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; @@ -372,7 +405,10 @@ __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); } @@ -389,6 +425,13 @@ __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) @@ -398,6 +441,21 @@ 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; @@ -411,6 +469,21 @@ 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) @@ -562,7 +635,7 @@ 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 @@ -608,6 +681,8 @@ 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 */ @@ -1230,8 +1305,8 @@ int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, * We don't want to have recursive SIGSEGV's etc, for example, * that is why we also clear SIGNAL_UNKILLABLE. */ -int -force_sig_info(int sig, struct siginfo *info, struct task_struct *t) +static int +do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t) { unsigned long int flags; int ret, blocked, ignored; @@ -1256,6 +1331,39 @@ force_sig_info(int sig, struct siginfo *info, struct task_struct *t) return ret; } +int force_sig_info(int sig, struct siginfo *info, struct task_struct *t) +{ +/* + * On some archs, PREEMPT_RT has to delay sending a signal from a trap + * since it can not enable preemption, and the signal code's spin_locks + * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will + * send the signal on exit of the trap. + */ +#ifdef ARCH_RT_DELAYS_SIGNAL_SEND + if (in_atomic()) { + if (WARN_ON_ONCE(t != current)) + return 0; + if (WARN_ON_ONCE(t->forced_info.si_signo)) + return 0; + + if (is_si_special(info)) { + WARN_ON_ONCE(info != SEND_SIG_PRIV); + t->forced_info.si_signo = sig; + t->forced_info.si_errno = 0; + t->forced_info.si_code = SI_KERNEL; + t->forced_info.si_pid = 0; + t->forced_info.si_uid = 0; + } else { + t->forced_info = *info; + } + + set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); + return 0; + } +#endif + return do_force_sig_info(sig, info, t); +} + /* * Nuke all other threads in the group. */ @@ -1286,12 +1394,12 @@ 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; } @@ -1302,7 +1410,7 @@ 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; @@ -1547,7 +1655,8 @@ 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; @@ -1908,15 +2017,7 @@ 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(); freezable_schedule(); } else { /* diff --git a/kernel/softirq.c b/kernel/softirq.c index d7d498d..15ad603 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -21,10 +21,12 @@ #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/smpboot.h> #include <linux/tick.h> +#include <linux/locallock.h> #define CREATE_TRACE_POINTS #include <trace/events/irq.h> @@ -62,6 +64,98 @@ char *softirq_to_name[NR_SOFTIRQS] = { "TASKLET", "SCHED", "HRTIMER", "RCU" }; +#ifdef CONFIG_NO_HZ_COMMON +# ifdef CONFIG_PREEMPT_RT_FULL + +struct softirq_runner { + struct task_struct *runner[NR_SOFTIRQS]; +}; + +static DEFINE_PER_CPU(struct softirq_runner, softirq_runners); + +static inline void softirq_set_runner(unsigned int sirq) +{ + struct softirq_runner *sr = &__get_cpu_var(softirq_runners); + + sr->runner[sirq] = current; +} + +static inline void softirq_clr_runner(unsigned int sirq) +{ + struct softirq_runner *sr = &__get_cpu_var(softirq_runners); + + sr->runner[sirq] = NULL; +} + +/* + * On preempt-rt a softirq running context might be blocked on a + * lock. There might be no other runnable task on this CPU because the + * lock owner runs on some other CPU. So we have to go into idle with + * the pending bit set. Therefor we need to check this otherwise we + * warn about false positives which confuses users and defeats the + * whole purpose of this test. + * + * This code is called with interrupts disabled. + */ +void softirq_check_pending_idle(void) +{ + static int rate_limit; + struct softirq_runner *sr = &__get_cpu_var(softirq_runners); + u32 warnpending; + int i; + + if (rate_limit >= 10) + return; + + warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK; + for (i = 0; i < NR_SOFTIRQS; i++) { + struct task_struct *tsk = sr->runner[i]; + + /* + * The wakeup code in rtmutex.c wakes up the task + * _before_ it sets pi_blocked_on to NULL under + * tsk->pi_lock. So we need to check for both: state + * and pi_blocked_on. + */ + if (tsk) { + raw_spin_lock(&tsk->pi_lock); + if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { + /* Clear all bits pending in that task */ + warnpending &= ~(tsk->softirqs_raised); + warnpending &= ~(1 << i); + } + raw_spin_unlock(&tsk->pi_lock); + } + } + + if (warnpending) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + warnpending); + rate_limit++; + } +} +# else +/* + * On !PREEMPT_RT we just printk rate limited: + */ +void softirq_check_pending_idle(void) +{ + static int rate_limit; + + if (rate_limit < 10 && + (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + local_softirq_pending()); + rate_limit++; + } +} +# endif + +#else /* !CONFIG_NO_HZ_COMMON */ +static inline void softirq_set_runner(unsigned int sirq) { } +static inline void softirq_clr_runner(unsigned int sirq) { } +#endif + /* * we cannot loop indefinitely here to avoid userspace starvation, * but we also don't want to introduce a worst case 1/HZ latency @@ -77,6 +171,57 @@ static void wakeup_softirqd(void) wake_up_process(tsk); } +static void handle_softirq(unsigned int vec_nr, int cpu, int need_rcu_bh_qs) +{ + struct softirq_action *h = softirq_vec + vec_nr; + unsigned 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())) { + pr_err("softirq %u %s %p preempt count leak: %08x -> %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); +} + +#ifndef CONFIG_PREEMPT_RT_FULL +static inline int ksoftirqd_softirq_pending(void) +{ + return local_softirq_pending(); +} + +static void handle_pending_softirqs(u32 pending, int cpu, int need_rcu_bh_qs) +{ + unsigned int vec_nr; + + local_irq_enable(); + for (vec_nr = 0; pending; vec_nr++, pending >>= 1) { + if (pending & 1) + handle_softirq(vec_nr, cpu, need_rcu_bh_qs); + } + local_irq_disable(); +} + +static void run_ksoftirqd(unsigned int cpu) +{ + local_irq_disable(); + if (ksoftirqd_softirq_pending()) { + __do_softirq(); + rcu_note_context_switch(cpu); + local_irq_enable(); + cond_resched(); + return; + } + local_irq_enable(); +} + /* * preempt_count and SOFTIRQ_OFFSET usage: * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving @@ -209,14 +354,51 @@ EXPORT_SYMBOL(local_bh_enable_ip); #define MAX_SOFTIRQ_TIME msecs_to_jiffies(2) #define MAX_SOFTIRQ_RESTART 10 +#ifdef CONFIG_TRACE_IRQFLAGS +/* + * Convoluted means of passing __do_softirq() a message through the various + * architecture execute_on_stack() bits. + * + * When we run softirqs from irq_exit() and thus on the hardirq stack we need + * to keep the lockdep irq context tracking as tight as possible in order to + * not miss-qualify lock contexts and miss possible deadlocks. + */ +static DEFINE_PER_CPU(int, softirq_from_hardirq); + +static inline void lockdep_softirq_from_hardirq(void) +{ + this_cpu_write(softirq_from_hardirq, 1); +} + +static inline void lockdep_softirq_start(void) +{ + if (this_cpu_read(softirq_from_hardirq)) + trace_hardirq_exit(); + lockdep_softirq_enter(); +} + +static inline void lockdep_softirq_end(void) +{ + lockdep_softirq_exit(); + if (this_cpu_read(softirq_from_hardirq)) { + this_cpu_write(softirq_from_hardirq, 0); + trace_hardirq_enter(); + } +} + +#else +static inline void lockdep_softirq_from_hardirq(void) { } +static inline void lockdep_softirq_start(void) { } +static inline void lockdep_softirq_end(void) { } +#endif + asmlinkage void __do_softirq(void) { - struct softirq_action *h; - __u32 pending; unsigned long end = jiffies + MAX_SOFTIRQ_TIME; - int cpu; unsigned long old_flags = current->flags; int max_restart = MAX_SOFTIRQ_RESTART; + __u32 pending; + int cpu; /* * Mask out PF_MEMALLOC s current task context is borrowed for the @@ -229,43 +411,14 @@ asmlinkage void __do_softirq(void) account_irq_enter_time(current); __local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET); - lockdep_softirq_enter(); + lockdep_softirq_start(); cpu = smp_processor_id(); 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) { @@ -276,8 +429,7 @@ restart: wakeup_softirqd(); } - lockdep_softirq_exit(); - + lockdep_softirq_end(); account_irq_exit_time(current); __local_bh_enable(SOFTIRQ_OFFSET); tsk_restore_flags(current, old_flags, PF_MEMALLOC); @@ -306,6 +458,261 @@ asmlinkage void do_softirq(void) #endif /* + * This function must run with irqs disabled! + */ +void raise_softirq_irqoff(unsigned int nr) +{ + __raise_softirq_irqoff(nr); + + /* + * If we're in an interrupt or softirq, we're done + * (this also catches softirq-disabled code). We will + * actually run the softirq once we return from + * the irq or softirq. + * + * Otherwise we wake up ksoftirqd to make sure we + * schedule the softirq soon. + */ + if (!in_interrupt()) + wakeup_softirqd(); +} + +void __raise_softirq_irqoff(unsigned int nr) +{ + trace_softirq_raise(nr); + or_softirq_pending(1UL << nr); +} + +static inline void local_bh_disable_nort(void) { local_bh_disable(); } +static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } +static void ksoftirqd_set_sched_params(unsigned int cpu) { } +static void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) { } + +#else /* !PREEMPT_RT_FULL */ + +/* + * On RT we serialize softirq execution with a cpu local lock per softirq + */ +static DEFINE_PER_CPU(struct local_irq_lock [NR_SOFTIRQS], local_softirq_locks); + +void __init softirq_early_init(void) +{ + int i; + + for (i = 0; i < NR_SOFTIRQS; i++) + local_irq_lock_init(local_softirq_locks[i]); +} + +static void lock_softirq(int which) +{ + local_lock(local_softirq_locks[which]); +} + +static void unlock_softirq(int which) +{ + local_unlock(local_softirq_locks[which]); +} + +static void do_single_softirq(int which, int need_rcu_bh_qs) +{ + unsigned long old_flags = current->flags; + + current->flags &= ~PF_MEMALLOC; + vtime_account_irq_enter(current); + current->flags |= PF_IN_SOFTIRQ; + lockdep_softirq_enter(); + local_irq_enable(); + handle_softirq(which, smp_processor_id(), need_rcu_bh_qs); + local_irq_disable(); + lockdep_softirq_exit(); + current->flags &= ~PF_IN_SOFTIRQ; + vtime_account_irq_enter(current); + tsk_restore_flags(current, old_flags, PF_MEMALLOC); +} + +/* + * Called with interrupts disabled. Process softirqs which were raised + * in current context (or on behalf of ksoftirqd). + */ +static void do_current_softirqs(int need_rcu_bh_qs) +{ + while (current->softirqs_raised) { + int i = __ffs(current->softirqs_raised); + unsigned int pending, mask = (1U << i); + + current->softirqs_raised &= ~mask; + local_irq_enable(); + + /* + * If the lock is contended, we boost the owner to + * process the softirq or leave the critical section + * now. + */ + lock_softirq(i); + local_irq_disable(); + softirq_set_runner(i); + /* + * Check with the local_softirq_pending() bits, + * whether we need to process this still or if someone + * else took care of it. + */ + pending = local_softirq_pending(); + if (pending & mask) { + set_softirq_pending(pending & ~mask); + do_single_softirq(i, need_rcu_bh_qs); + } + softirq_clr_runner(i); + unlock_softirq(i); + WARN_ON(current->softirq_nestcnt != 1); + } +} + +void local_bh_disable(void) +{ + if (++current->softirq_nestcnt == 1) + migrate_disable(); +} +EXPORT_SYMBOL(local_bh_disable); + +void local_bh_enable(void) +{ + if (WARN_ON(current->softirq_nestcnt == 0)) + return; + + local_irq_disable(); + if (current->softirq_nestcnt == 1 && current->softirqs_raised) + do_current_softirqs(1); + local_irq_enable(); + + if (--current->softirq_nestcnt == 0) + migrate_enable(); +} +EXPORT_SYMBOL(local_bh_enable); + +void local_bh_enable_ip(unsigned long ip) +{ + local_bh_enable(); +} +EXPORT_SYMBOL(local_bh_enable_ip); + +void _local_bh_enable(void) +{ + if (WARN_ON(current->softirq_nestcnt == 0)) + return; + if (--current->softirq_nestcnt == 0) + migrate_enable(); +} +EXPORT_SYMBOL(_local_bh_enable); + +int in_serving_softirq(void) +{ + return current->flags & PF_IN_SOFTIRQ; +} +EXPORT_SYMBOL(in_serving_softirq); + +/* Called with preemption disabled */ +static void run_ksoftirqd(unsigned int cpu) +{ + local_irq_disable(); + current->softirq_nestcnt++; + do_current_softirqs(1); + current->softirq_nestcnt--; + rcu_note_context_switch(cpu); + local_irq_enable(); +} + +/* + * Called from netif_rx_ni(). Preemption enabled, but migration + * disabled. So the cpu can't go away under us. + */ +void thread_do_softirq(void) +{ + if (!in_serving_softirq() && current->softirqs_raised) { + current->softirq_nestcnt++; + do_current_softirqs(0); + current->softirq_nestcnt--; + } +} + +static void do_raise_softirq_irqoff(unsigned int nr) +{ + trace_softirq_raise(nr); + or_softirq_pending(1UL << nr); + + /* + * If we are not in a hard interrupt and inside a bh disabled + * region, we simply raise the flag on current. local_bh_enable() + * will make sure that the softirq is executed. Otherwise we + * delegate it to ksoftirqd. + */ + if (!in_irq() && current->softirq_nestcnt) + current->softirqs_raised |= (1U << nr); + else if (__this_cpu_read(ksoftirqd)) + __this_cpu_read(ksoftirqd)->softirqs_raised |= (1U << nr); +} + +void __raise_softirq_irqoff(unsigned int nr) +{ + do_raise_softirq_irqoff(nr); + if (!in_irq() && !current->softirq_nestcnt) + wakeup_softirqd(); +} + +/* + * This function must run with irqs disabled! + */ +void raise_softirq_irqoff(unsigned int nr) +{ + do_raise_softirq_irqoff(nr); + + /* + * If we're in an hard interrupt we let irq return code deal + * with the wakeup of ksoftirqd. + */ + if (in_irq()) + return; + + /* + * If we are in thread context but outside of a bh disabled + * region, we need to wake ksoftirqd as well. + * + * CHECKME: Some of the places which do that could be wrapped + * into local_bh_disable/enable pairs. Though it's unclear + * whether this is worth the effort. To find those places just + * raise a WARN() if the condition is met. + */ + if (!current->softirq_nestcnt) + wakeup_softirqd(); +} + +static inline int ksoftirqd_softirq_pending(void) +{ + return current->softirqs_raised; +} + +static inline void local_bh_disable_nort(void) { } +static inline void _local_bh_enable_nort(void) { } + +static inline void ksoftirqd_set_sched_params(unsigned int cpu) +{ + struct sched_param param = { .sched_priority = 1 }; + + sched_setscheduler(current, SCHED_FIFO, ¶m); + /* Take over all pending softirqs when starting */ + local_irq_disable(); + current->softirqs_raised = local_softirq_pending(); + local_irq_enable(); +} + +static inline void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) +{ + struct sched_param param = { .sched_priority = 0 }; + + sched_setscheduler(current, SCHED_NORMAL, ¶m); +} + +#endif /* PREEMPT_RT_FULL */ +/* * Enter an interrupt context. */ void irq_enter(void) @@ -318,9 +725,9 @@ 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(); @@ -328,7 +735,9 @@ void irq_enter(void) static inline void invoke_softirq(void) { +#ifndef CONFIG_PREEMPT_RT_FULL if (!force_irqthreads) { + lockdep_softirq_from_hardirq(); /* * We can safely execute softirq on the current stack if * it is the irq stack, because it should be near empty @@ -341,6 +750,15 @@ static inline void invoke_softirq(void) } else { wakeup_softirqd(); } +#else /* PREEMPT_RT_FULL */ + unsigned long flags; + + local_irq_save(flags); + if (__this_cpu_read(ksoftirqd) && + __this_cpu_read(ksoftirqd)->softirqs_raised) + wakeup_softirqd(); + local_irq_restore(flags); +#endif } static inline void tick_irq_exit(void) @@ -368,33 +786,13 @@ void irq_exit(void) #endif account_irq_exit_time(current); - trace_hardirq_exit(); sub_preempt_count(HARDIRQ_OFFSET); if (!in_interrupt() && local_softirq_pending()) invoke_softirq(); tick_irq_exit(); rcu_irq_exit(); -} - -/* - * This function must run with irqs disabled! - */ -inline void raise_softirq_irqoff(unsigned int nr) -{ - __raise_softirq_irqoff(nr); - - /* - * If we're in an interrupt or softirq, we're done - * (this also catches softirq-disabled code). We will - * actually run the softirq once we return from - * the irq or softirq. - * - * Otherwise we wake up ksoftirqd to make sure we - * schedule the softirq soon. - */ - if (!in_interrupt()) - wakeup_softirqd(); + trace_hardirq_exit(); /* must be last! */ } void raise_softirq(unsigned int nr) @@ -406,12 +804,6 @@ void raise_softirq(unsigned int nr) local_irq_restore(flags); } -void __raise_softirq_irqoff(unsigned int nr) -{ - trace_softirq_raise(nr); - or_softirq_pending(1UL << nr); -} - void open_softirq(int nr, void (*action)(struct softirq_action *)) { softirq_vec[nr].action = action; @@ -429,15 +821,45 @@ 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); } @@ -448,10 +870,7 @@ 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); } @@ -459,50 +878,119 @@ 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; @@ -513,29 +1001,7 @@ 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); } @@ -558,7 +1024,7 @@ 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); @@ -762,22 +1228,26 @@ void __init softirq_init(void) open_softirq(HI_SOFTIRQ, tasklet_hi_action); } -static int ksoftirqd_should_run(unsigned int cpu) +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) +void tasklet_unlock_wait(struct tasklet_struct *t) { - return local_softirq_pending(); + 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 void run_ksoftirqd(unsigned int cpu) +static int ksoftirqd_should_run(unsigned int cpu) { - local_irq_disable(); - if (local_softirq_pending()) { - __do_softirq(); - rcu_note_context_switch(cpu); - local_irq_enable(); - cond_resched(); - return; - } - local_irq_enable(); + return ksoftirqd_softirq_pending(); } #ifdef CONFIG_HOTPLUG_CPU @@ -860,6 +1330,8 @@ static struct notifier_block cpu_nfb = { static struct smp_hotplug_thread softirq_threads = { .store = &ksoftirqd, + .setup = ksoftirqd_set_sched_params, + .cleanup = ksoftirqd_clr_sched_params, .thread_should_run = ksoftirqd_should_run, .thread_fn = run_ksoftirqd, .thread_comm = "ksoftirqd/%u", diff --git a/kernel/spinlock.c b/kernel/spinlock.c index 4b082b5..5c76166 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -124,8 +124,11 @@ 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 @@ -209,6 +212,8 @@ 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) { @@ -353,6 +358,8 @@ 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 c09f295..5f02a3f 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 */ }; @@ -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; + } } } @@ -69,7 +71,7 @@ static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) 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); @@ -77,7 +79,23 @@ static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) } 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); } /** @@ -111,7 +129,7 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg) cpu_stop_init_done(&done, 1); cpu_stop_queue_work(cpu, &work); - wait_for_completion(&done.completion); + wait_for_stop_done(&done); return done.executed ? done.ret : -ENOENT; } @@ -137,11 +155,12 @@ 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, cpu_stop_fn_t fn, void *arg, - struct cpu_stop_done *done) + struct cpu_stop_done *done, bool inactive) { struct cpu_stop_work *work; unsigned int cpu; @@ -155,14 +174,18 @@ 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(); + if (!inactive) { + mutex_lock(&stopper_lock); + } else { + while (!mutex_trylock(&stopper_lock)) + cpu_relax(); + } for_each_cpu(cpu, cpumask) cpu_stop_queue_work(cpu, &per_cpu(stop_cpus_work, cpu)); - preempt_enable(); + mutex_unlock(&stopper_lock); } static int __stop_cpus(const struct cpumask *cpumask, @@ -171,8 +194,8 @@ static int __stop_cpus(const struct cpumask *cpumask, struct cpu_stop_done done; cpu_stop_init_done(&done, cpumask_weight(cpumask)); - queue_stop_cpus_work(cpumask, fn, arg, &done); - wait_for_completion(&done.completion); + queue_stop_cpus_work(cpumask, fn, arg, &done, false); + wait_for_stop_done(&done); return done.executed ? done.ret : -ENOENT; } @@ -251,9 +274,9 @@ static int cpu_stop_should_run(unsigned int cpu) unsigned long flags; int run; - spin_lock_irqsave(&stopper->lock, flags); + raw_spin_lock_irqsave(&stopper->lock, flags); run = !list_empty(&stopper->works); - spin_unlock_irqrestore(&stopper->lock, flags); + raw_spin_unlock_irqrestore(&stopper->lock, flags); return run; } @@ -265,13 +288,13 @@ static void cpu_stopper_thread(unsigned int cpu) 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; @@ -279,6 +302,16 @@ repeat: struct cpu_stop_done *done = work->done; char ksym_buf[KSYM_NAME_LEN] __maybe_unused; + /* + * 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(); @@ -293,7 +326,13 @@ 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(); goto repeat; } } @@ -312,20 +351,20 @@ static void cpu_stop_park(unsigned int cpu) unsigned long flags; /* drain remaining works */ - spin_lock_irqsave(&stopper->lock, flags); + raw_spin_lock_irqsave(&stopper->lock, flags); list_for_each_entry(work, &stopper->works, list) cpu_stop_signal_done(work->done, false); stopper->enabled = false; - spin_unlock_irqrestore(&stopper->lock, flags); + raw_spin_unlock_irqrestore(&stopper->lock, flags); } static void cpu_stop_unpark(unsigned int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); - spin_lock_irq(&stopper->lock); + raw_spin_lock_irq(&stopper->lock); stopper->enabled = true; - spin_unlock_irq(&stopper->lock); + raw_spin_unlock_irq(&stopper->lock); } static struct smp_hotplug_thread cpu_stop_threads = { @@ -347,7 +386,7 @@ 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); } @@ -530,11 +569,11 @@ int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data, set_state(&smdata, STOPMACHINE_PREPARE); cpu_stop_init_done(&done, num_active_cpus()); queue_stop_cpus_work(cpu_active_mask, stop_machine_cpu_stop, &smdata, - &done); + &done, true); 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/jiffies.c b/kernel/time/jiffies.c index a6a5bf5..23d7203 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -73,7 +73,8 @@ static struct clocksource clocksource_jiffies = { .shift = JIFFIES_SHIFT, }; -__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); +__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock); +__cacheline_aligned_in_smp seqcount_t jiffies_seq; #if (BITS_PER_LONG < 64) u64 get_jiffies_64(void) @@ -82,9 +83,9 @@ u64 get_jiffies_64(void) u64 ret; do { - seq = read_seqbegin(&jiffies_lock); + seq = read_seqcount_begin(&jiffies_seq); ret = jiffies_64; - } while (read_seqretry(&jiffies_lock, seq)); + } while (read_seqcount_retry(&jiffies_seq, seq)); return ret; } EXPORT_SYMBOL(get_jiffies_64); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index af8d1d4..d6132cd 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -10,6 +10,7 @@ #include <linux/workqueue.h> #include <linux/hrtimer.h> #include <linux/jiffies.h> +#include <linux/kthread.h> #include <linux/math64.h> #include <linux/timex.h> #include <linux/time.h> @@ -517,10 +518,49 @@ static void sync_cmos_clock(struct work_struct *work) schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next)); } +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * RT can not call schedule_delayed_work from real interrupt context. + * Need to make a thread to do the real work. + */ +static struct task_struct *cmos_delay_thread; +static bool do_cmos_delay; + +static int run_cmos_delay(void *ignore) +{ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + if (do_cmos_delay) { + do_cmos_delay = false; + schedule_delayed_work(&sync_cmos_work, 0); + } + schedule(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +void ntp_notify_cmos_timer(void) +{ + do_cmos_delay = true; + /* Make visible before waking up process */ + smp_wmb(); + wake_up_process(cmos_delay_thread); +} + +static __init int create_cmos_delay_thread(void) +{ + cmos_delay_thread = kthread_run(run_cmos_delay, NULL, "kcmosdelayd"); + BUG_ON(!cmos_delay_thread); + return 0; +} +early_initcall(create_cmos_delay_thread); +#else void ntp_notify_cmos_timer(void) { schedule_delayed_work(&sync_cmos_work, 0); } +#endif /* CONFIG_PREEMPT_RT_FULL */ #else void ntp_notify_cmos_timer(void) { } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 64522ec..1b80eb0 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -63,13 +63,15 @@ int tick_is_oneshot_available(void) static void tick_periodic(int cpu) { if (tick_do_timer_cpu == cpu) { - write_seqlock(&jiffies_lock); + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); /* Keep track of the next tick event */ tick_next_period = ktime_add(tick_next_period, tick_period); do_timer(1); - write_sequnlock(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); } update_process_times(user_mode(get_irq_regs())); @@ -130,9 +132,9 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) ktime_t next; do { - seq = read_seqbegin(&jiffies_lock); + seq = read_seqcount_begin(&jiffies_seq); next = tick_next_period; - } while (read_seqretry(&jiffies_lock, seq)); + } while (read_seqcount_retry(&jiffies_seq, seq)); clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index bc906ca..7e5e7f8 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -4,7 +4,8 @@ #include <linux/hrtimer.h> #include <linux/tick.h> -extern seqlock_t jiffies_lock; +extern raw_spinlock_t jiffies_lock; +extern seqcount_t jiffies_seq; #define CS_NAME_LEN 32 diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index ea20f7d..3740f28 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -62,7 +62,8 @@ static void tick_do_update_jiffies64(ktime_t now) return; /* Reevalute with jiffies_lock held */ - write_seqlock(&jiffies_lock); + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); delta = ktime_sub(now, last_jiffies_update); if (delta.tv64 >= tick_period.tv64) { @@ -85,7 +86,8 @@ 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(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); } /* @@ -95,12 +97,14 @@ static ktime_t tick_init_jiffy_update(void) { ktime_t period; - write_seqlock(&jiffies_lock); + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); /* Did we start the jiffies update yet ? */ if (last_jiffies_update.tv64 == 0) last_jiffies_update = tick_next_period; period = last_jiffies_update; - write_sequnlock(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); return period; } @@ -217,6 +221,7 @@ static void nohz_full_kick_work_func(struct irq_work *work) static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { .func = nohz_full_kick_work_func, + .flags = IRQ_WORK_HARD_IRQ, }; /* @@ -538,11 +543,11 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, /* Read jiffies and the time when jiffies were updated last */ do { - seq = read_seqbegin(&jiffies_lock); + seq = read_seqcount_begin(&jiffies_seq); last_update = last_jiffies_update; last_jiffies = jiffies; time_delta = timekeeping_max_deferment(); - } while (read_seqretry(&jiffies_lock, seq)); + } while (read_seqcount_retry(&jiffies_seq, seq)); if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || arch_needs_cpu(cpu) || irq_work_needs_cpu()) { @@ -720,14 +725,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; if (unlikely(local_softirq_pending() && cpu_online(cpu))) { - static int ratelimit; - - if (ratelimit < 10 && - (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { - pr_warn("NOHZ: local_softirq_pending %02x\n", - (unsigned int) local_softirq_pending()); - ratelimit++; - } + softirq_check_pending_idle(); return false; } @@ -1112,6 +1110,7 @@ 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 bfca770..d3150a7 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1754,7 +1754,9 @@ EXPORT_SYMBOL(hardpps); */ void xtime_update(unsigned long ticks) { - write_seqlock(&jiffies_lock); + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); do_timer(ticks); - write_sequnlock(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); } diff --git a/kernel/timer.c b/kernel/timer.c index 4296d13..cc34e42 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -78,6 +78,9 @@ struct tvec_root { struct tvec_base { spinlock_t lock; struct timer_list *running_timer; +#ifdef CONFIG_PREEMPT_RT_FULL + wait_queue_head_t wait_for_running_timer; +#endif unsigned long timer_jiffies; unsigned long next_timer; unsigned long active_timers; @@ -720,6 +723,36 @@ 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) @@ -739,12 +772,15 @@ __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_COMMON) && 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) { @@ -755,14 +791,8 @@ __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; @@ -945,6 +975,29 @@ 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_running_timer) +#else +static inline void wait_for_running_timer(struct timer_list *timer) +{ + cpu_relax(); +} + +# define wakeup_timer_waiters(b) do { } while (0) +#endif + /** * del_timer - deactive a timer. * @timer: the timer to be deactivated @@ -1002,7 +1055,7 @@ int try_to_del_timer_sync(struct timer_list *timer) } 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 @@ -1062,7 +1115,7 @@ 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); @@ -1179,15 +1232,17 @@ static inline void __run_timers(struct tvec_base *base) if (irqsafe) { spin_unlock(&base->lock); call_timer_fn(timer, fn, data); + base->running_timer = NULL; spin_lock(&base->lock); } else { spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, data); + base->running_timer = NULL; spin_lock_irq(&base->lock); } } } - base->running_timer = NULL; + wakeup_timer_waiters(base); spin_unlock_irq(&base->lock); } @@ -1327,17 +1382,31 @@ unsigned long get_next_timer_interrupt(unsigned long now) if (cpu_is_offline(smp_processor_id())) return expires; +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * On PREEMPT_RT we cannot sleep here. If the trylock does not + * succeed then we return the worst-case 'expires in 1 tick' + * value. We use the rt functions here directly to avoid a + * migrate_disable() call. + */ + if (!spin_do_trylock(&base->lock)) + return now + 1; +#else spin_lock(&base->lock); +#endif if (base->active_timers) { if (time_before_eq(base->next_timer, base->timer_jiffies)) base->next_timer = __next_timer_interrupt(base); expires = base->next_timer; } +#ifdef CONFIG_PREEMPT_RT_FULL + rt_spin_unlock_after_trylock_in_irq(&base->lock); +#else spin_unlock(&base->lock); +#endif if (time_before_eq(expires, now)) return now; - return cmp_next_hrtimer_event(now, expires); } #endif @@ -1353,13 +1422,13 @@ 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); -#ifdef CONFIG_IRQ_WORK +#if defined(CONFIG_IRQ_WORK) if (in_irq()) irq_work_run(); #endif - scheduler_tick(); run_posix_cpu_timers(p); } @@ -1370,7 +1439,9 @@ static void run_timer_softirq(struct softirq_action *h) { struct tvec_base *base = __this_cpu_read(tvec_bases); - hrtimer_run_pending(); +#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) + irq_work_run(); +#endif if (time_after_eq(jiffies, base->timer_jiffies)) __run_timers(base); @@ -1381,8 +1452,39 @@ static void run_timer_softirq(struct softirq_action *h) */ void run_local_timers(void) { + struct tvec_base *base = __this_cpu_read(tvec_bases); + hrtimer_run_queues(); - raise_softirq(TIMER_SOFTIRQ); + /* + * We can access this lockless as we are in the timer + * interrupt. If there are no timers queued, nothing to do in + * the timer softirq. + */ +#ifdef CONFIG_PREEMPT_RT_FULL + /* On RT, irq work runs from softirq */ + if (irq_work_needs_cpu()) { + raise_softirq(TIMER_SOFTIRQ); + return; + } + + if (!spin_do_trylock(&base->lock)) { + raise_softirq(TIMER_SOFTIRQ); + return; + } +#endif + + if (!base->active_timers) + goto out; + + /* Check whether the next pending timer has expired */ + if (time_before_eq(base->next_timer, jiffies)) + raise_softirq(TIMER_SOFTIRQ); +out: +#ifdef CONFIG_PREEMPT_RT_FULL + rt_spin_unlock_after_trylock_in_irq(&base->lock); +#endif + /* The ; ensures that gcc won't complain in the !RT case */ + ; } #ifdef __ARCH_WANT_SYS_ALARM @@ -1547,6 +1649,9 @@ static int init_timers_cpu(int cpu) base = per_cpu(tvec_bases, cpu); } +#ifdef CONFIG_PREEMPT_RT_FULL + init_waitqueue_head(&base->wait_for_running_timer); +#endif for (j = 0; j < TVN_SIZE; j++) { INIT_LIST_HEAD(base->tv5.vec + j); @@ -1585,7 +1690,7 @@ static void migrate_timers(int cpu) BUG_ON(cpu_online(cpu)); old_base = per_cpu(tvec_bases, cpu); - new_base = get_cpu_var(tvec_bases); + new_base = get_local_var(tvec_bases); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. @@ -1606,7 +1711,7 @@ static void migrate_timers(int cpu) spin_unlock(&old_base->lock); spin_unlock_irq(&new_base->lock); - put_cpu_var(tvec_bases); + put_local_var(tvec_bases); } #endif /* CONFIG_HOTPLUG_CPU */ diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 015f85a..bbe95b9 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 @@ -216,6 +234,24 @@ 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 @@ -226,6 +262,74 @@ 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 d7e2068..f5e0243 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -34,6 +34,10 @@ 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 0000000..66a69eb --- /dev/null +++ b/kernel/trace/latency_hist.c @@ -0,0 +1,1178 @@ +/* + * kernel/trace/latency_hist.c + * + * Add support for histograms of preemption-off latency and + * interrupt-off latency and wakeup latency, it depends on + * Real-Time Preemption Support. + * + * Copyright (C) 2005 MontaVista Software, Inc. + * Yi Yang <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/sched/rt.h> +#include <linux/slab.h> +#include <linux/atomic.h> +#include <asm/div64.h> + +#include "trace.h" +#include <trace/events/sched.h> + +#define NSECS_PER_USECS 1000L + +#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 */ + long min_lat; + long max_lat; + unsigned long long below_hist_bound_samples; + unsigned long long above_hist_bound_samples; + long long accumulate_lat; + unsigned long long total_samples; + unsigned long long hist_array[MAX_ENTRY_NUM]; +}; + +struct enable_data { + int latency_type; + int enabled; +}; + +static char *latency_hist_dir_root = "latency_hist"; + +#ifdef CONFIG_INTERRUPT_OFF_HIST +static DEFINE_PER_CPU(struct hist_data, irqsoff_hist); +static char *irqsoff_hist_dir = "irqsoff"; +static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start); +static DEFINE_PER_CPU(int, hist_irqsoff_counting); +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST +static DEFINE_PER_CPU(struct hist_data, preemptoff_hist); +static char *preemptoff_hist_dir = "preemptoff"; +static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start); +static DEFINE_PER_CPU(int, hist_preemptoff_counting); +#endif + +#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) +static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist); +static char *preemptirqsoff_hist_dir = "preemptirqsoff"; +static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start); +static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting); +#endif + +#if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST) +static notrace void probe_preemptirqsoff_hist(void *v, int reason, int start); +static struct enable_data preemptirqsoff_enabled_data = { + .latency_type = PREEMPTIRQSOFF_LATENCY, + .enabled = 0, +}; +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +struct maxlatproc_data { + char comm[FIELD_SIZEOF(struct task_struct, comm)]; + char current_comm[FIELD_SIZEOF(struct task_struct, comm)]; + int pid; + int current_pid; + int prio; + int current_prio; + long latency; + long timeroffset; + cycle_t timestamp; +}; +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST +static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist); +static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio); +static char *wakeup_latency_hist_dir = "wakeup"; +static char *wakeup_latency_hist_dir_sharedprio = "sharedprio"; +static notrace void probe_wakeup_latency_hist_start(void *v, + struct task_struct *p, int success); +static notrace void probe_wakeup_latency_hist_stop(void *v, + struct task_struct *prev, struct task_struct *next); +static notrace void probe_sched_migrate_task(void *, + struct task_struct *task, int cpu); +static struct enable_data wakeup_latency_enabled_data = { + .latency_type = WAKEUP_LATENCY, + .enabled = 0, +}; +static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc); +static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc_sharedprio); +static DEFINE_PER_CPU(struct task_struct *, wakeup_task); +static DEFINE_PER_CPU(int, wakeup_sharedprio); +static unsigned long wakeup_pid; +#endif + +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST +static DEFINE_PER_CPU(struct hist_data, missed_timer_offsets); +static char *missed_timer_offsets_dir = "missed_timer_offsets"; +static notrace void probe_hrtimer_interrupt(void *v, int cpu, + long long offset, struct task_struct *curr, struct task_struct *task); +static struct enable_data missed_timer_offsets_enabled_data = { + .latency_type = MISSED_TIMER_OFFSETS, + .enabled = 0, +}; +static DEFINE_PER_CPU(struct maxlatproc_data, missed_timer_offsets_maxlatproc); +static unsigned long missed_timer_offsets_pid; +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static DEFINE_PER_CPU(struct hist_data, timerandwakeup_latency_hist); +static char *timerandwakeup_latency_hist_dir = "timerandwakeup"; +static struct enable_data timerandwakeup_enabled_data = { + .latency_type = TIMERANDWAKEUP_LATENCY, + .enabled = 0, +}; +static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc); +#endif + +void notrace latency_hist(int latency_type, int cpu, long latency, + long timeroffset, cycle_t stop, + struct task_struct *p) +{ + struct hist_data *my_hist; +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + struct maxlatproc_data *mp = NULL; +#endif + + if (!cpu_possible(cpu) || latency_type < 0 || + latency_type >= MAX_LATENCY_TYPE) + return; + + switch (latency_type) { +#ifdef CONFIG_INTERRUPT_OFF_HIST + case IRQSOFF_LATENCY: + my_hist = &per_cpu(irqsoff_hist, cpu); + break; +#endif +#ifdef CONFIG_PREEMPT_OFF_HIST + case PREEMPTOFF_LATENCY: + my_hist = &per_cpu(preemptoff_hist, cpu); + break; +#endif +#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + my_hist = &per_cpu(preemptirqsoff_hist, cpu); + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + my_hist = &per_cpu(wakeup_latency_hist, cpu); + mp = &per_cpu(wakeup_maxlatproc, cpu); + break; + case WAKEUP_LATENCY_SHAREDPRIO: + my_hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); + mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + my_hist = &per_cpu(missed_timer_offsets, cpu); + mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); + break; +#endif +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + case TIMERANDWAKEUP_LATENCY: + my_hist = &per_cpu(timerandwakeup_latency_hist, cpu); + mp = &per_cpu(timerandwakeup_maxlatproc, cpu); + break; +#endif + + default: + return; + } + + latency += my_hist->offset; + + if (atomic_read(&my_hist->hist_mode) == 0) + return; + + if (latency < 0 || latency >= MAX_ENTRY_NUM) { + if (latency < 0) + my_hist->below_hist_bound_samples++; + else + my_hist->above_hist_bound_samples++; + } else + my_hist->hist_array[latency]++; + + if (unlikely(latency > my_hist->max_lat || + my_hist->min_lat == LONG_MAX)) { +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + if (latency_type == WAKEUP_LATENCY || + latency_type == WAKEUP_LATENCY_SHAREDPRIO || + latency_type == MISSED_TIMER_OFFSETS || + latency_type == TIMERANDWAKEUP_LATENCY) { + strncpy(mp->comm, p->comm, sizeof(mp->comm)); + strncpy(mp->current_comm, current->comm, + sizeof(mp->current_comm)); + mp->pid = task_pid_nr(p); + mp->current_pid = task_pid_nr(current); + mp->prio = p->prio; + mp->current_prio = current->prio; + mp->latency = latency; + mp->timeroffset = timeroffset; + mp->timestamp = stop; + } +#endif + my_hist->max_lat = latency; + } + if (unlikely(latency < my_hist->min_lat)) + my_hist->min_lat = latency; + my_hist->total_samples++; + my_hist->accumulate_lat += latency; +} + +static void *l_start(struct seq_file *m, loff_t *pos) +{ + loff_t *index_ptr = NULL; + loff_t index = *pos; + struct hist_data *my_hist = m->private; + + if (index == 0) { + char minstr[32], avgstr[32], maxstr[32]; + + atomic_dec(&my_hist->hist_mode); + + if (likely(my_hist->total_samples)) { + long avg = (long) div64_s64(my_hist->accumulate_lat, + my_hist->total_samples); + snprintf(minstr, sizeof(minstr), "%ld", + my_hist->min_lat - my_hist->offset); + snprintf(avgstr, sizeof(avgstr), "%ld", + avg - my_hist->offset); + snprintf(maxstr, sizeof(maxstr), "%ld", + my_hist->max_lat - my_hist->offset); + } else { + strcpy(minstr, "<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 const struct seq_operations latency_hist_seq_op = { + .start = l_start, + .next = l_next, + .stop = l_stop, + .show = l_show +}; + +static int latency_hist_open(struct inode *inode, struct file *file) +{ + int ret; + + ret = seq_open(file, &latency_hist_seq_op); + if (!ret) { + struct seq_file *seq = file->private_data; + seq->private = inode->i_private; + } + return ret; +} + +static const struct file_operations latency_hist_fops = { + .open = latency_hist_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static void clear_maxlatprocdata(struct maxlatproc_data *mp) +{ + mp->comm[0] = mp->current_comm[0] = '\0'; + mp->prio = mp->current_prio = mp->pid = mp->current_pid = + mp->latency = mp->timeroffset = -1; + mp->timestamp = 0; +} +#endif + +static void hist_reset(struct hist_data *hist) +{ + atomic_dec(&hist->hist_mode); + + memset(hist->hist_array, 0, sizeof(hist->hist_array)); + hist->below_hist_bound_samples = 0ULL; + hist->above_hist_bound_samples = 0ULL; + hist->min_lat = LONG_MAX; + hist->max_lat = LONG_MIN; + hist->total_samples = 0ULL; + hist->accumulate_lat = 0LL; + + atomic_inc(&hist->hist_mode); +} + +static ssize_t +latency_hist_reset(struct file *file, const char __user *a, + size_t size, loff_t *off) +{ + int cpu; + struct hist_data *hist = NULL; +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + struct maxlatproc_data *mp = NULL; +#endif + off_t latency_type = (off_t) file->private_data; + + for_each_online_cpu(cpu) { + + switch (latency_type) { +#ifdef CONFIG_PREEMPT_OFF_HIST + case PREEMPTOFF_LATENCY: + hist = &per_cpu(preemptoff_hist, cpu); + break; +#endif +#ifdef CONFIG_INTERRUPT_OFF_HIST + case IRQSOFF_LATENCY: + hist = &per_cpu(irqsoff_hist, cpu); + break; +#endif +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + hist = &per_cpu(preemptirqsoff_hist, cpu); + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + hist = &per_cpu(wakeup_latency_hist, cpu); + mp = &per_cpu(wakeup_maxlatproc, cpu); + break; + case WAKEUP_LATENCY_SHAREDPRIO: + hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); + mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + hist = &per_cpu(missed_timer_offsets, cpu); + mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); + break; +#endif +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + case TIMERANDWAKEUP_LATENCY: + hist = &per_cpu(timerandwakeup_latency_hist, cpu); + mp = &per_cpu(timerandwakeup_maxlatproc, cpu); + break; +#endif + } + + hist_reset(hist); +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + if (latency_type == WAKEUP_LATENCY || + latency_type == WAKEUP_LATENCY_SHAREDPRIO || + latency_type == MISSED_TIMER_OFFSETS || + latency_type == TIMERANDWAKEUP_LATENCY) + clear_maxlatprocdata(mp); +#endif + } + + return size; +} + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static ssize_t +show_pid(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + char buf[64]; + int r; + unsigned long *this_pid = file->private_data; + + r = snprintf(buf, sizeof(buf), "%lu\n", *this_pid); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t do_pid(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + unsigned long pid; + unsigned long *this_pid = file->private_data; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = '\0'; + + if (kstrtoul(buf, 10, &pid)) + return -EINVAL; + + *this_pid = pid; + + return cnt; +} +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static ssize_t +show_maxlatproc(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + int r; + struct maxlatproc_data *mp = file->private_data; + int strmaxlen = (TASK_COMM_LEN * 2) + (8 * 8); + unsigned long long t; + unsigned long usecs, secs; + char *buf; + + if (mp->pid == -1 || mp->current_pid == -1) { + buf = "(none)\n"; + return simple_read_from_buffer(ubuf, cnt, ppos, buf, + strlen(buf)); + } + + buf = kmalloc(strmaxlen, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + t = ns2usecs(mp->timestamp); + usecs = do_div(t, USEC_PER_SEC); + secs = (unsigned long) t; + r = snprintf(buf, strmaxlen, + "%d %d %ld (%ld) %s <- %d %d %s %lu.%06lu\n", mp->pid, + MAX_RT_PRIO-1 - mp->prio, mp->latency, mp->timeroffset, mp->comm, + mp->current_pid, MAX_RT_PRIO-1 - mp->current_prio, mp->current_comm, + secs, usecs); + r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + kfree(buf); + return r; +} +#endif + +static ssize_t +show_enable(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + char buf[64]; + struct enable_data *ed = file->private_data; + int r; + + r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +do_enable(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) +{ + char buf[64]; + long enable; + struct enable_data *ed = file->private_data; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + if (kstrtoul(buf, 10, &enable)) + return -EINVAL; + + if ((enable && ed->enabled) || (!enable && !ed->enabled)) + return cnt; + + if (enable) { + int ret; + + switch (ed->latency_type) { +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + ret = register_trace_preemptirqsoff_hist( + probe_preemptirqsoff_hist, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_preemptirqsoff_hist " + "to trace_preemptirqsoff_hist\n"); + return ret; + } + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + ret = register_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_start " + "to trace_sched_wakeup\n"); + return ret; + } + ret = register_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_start " + "to trace_sched_wakeup_new\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + return ret; + } + ret = register_trace_sched_switch( + probe_wakeup_latency_hist_stop, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_stop " + "to trace_sched_switch\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + return ret; + } + ret = register_trace_sched_migrate_task( + probe_sched_migrate_task, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_sched_migrate_task " + "to trace_sched_migrate_task\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_switch( + probe_wakeup_latency_hist_stop, NULL); + return ret; + } + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + ret = register_trace_hrtimer_interrupt( + probe_hrtimer_interrupt, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_hrtimer_interrupt " + "to trace_hrtimer_interrupt\n"); + return ret; + } + break; +#endif +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + case TIMERANDWAKEUP_LATENCY: + if (!wakeup_latency_enabled_data.enabled || + !missed_timer_offsets_enabled_data.enabled) + return -EINVAL; + break; +#endif + default: + break; + } + } else { + switch (ed->latency_type) { +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + { + int cpu; + + unregister_trace_preemptirqsoff_hist( + probe_preemptirqsoff_hist, NULL); + for_each_online_cpu(cpu) { +#ifdef CONFIG_INTERRUPT_OFF_HIST + per_cpu(hist_irqsoff_counting, + cpu) = 0; +#endif +#ifdef CONFIG_PREEMPT_OFF_HIST + per_cpu(hist_preemptoff_counting, + cpu) = 0; +#endif +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + per_cpu(hist_preemptirqsoff_counting, + cpu) = 0; +#endif + } + } + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + { + int cpu; + + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_switch( + probe_wakeup_latency_hist_stop, NULL); + unregister_trace_sched_migrate_task( + probe_sched_migrate_task, NULL); + + for_each_online_cpu(cpu) { + per_cpu(wakeup_task, cpu) = NULL; + per_cpu(wakeup_sharedprio, cpu) = 0; + } + } +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + timerandwakeup_enabled_data.enabled = 0; +#endif + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + unregister_trace_hrtimer_interrupt( + probe_hrtimer_interrupt, NULL); +#ifdef CONFIG_WAKEUP_LATENCY_HIST + timerandwakeup_enabled_data.enabled = 0; +#endif + break; +#endif + default: + break; + } + } + ed->enabled = enable; + return cnt; +} + +static const struct file_operations latency_hist_reset_fops = { + .open = tracing_open_generic, + .write = latency_hist_reset, +}; + +static const struct file_operations enable_fops = { + .open = tracing_open_generic, + .read = show_enable, + .write = do_enable, +}; + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static const struct file_operations pid_fops = { + .open = tracing_open_generic, + .read = show_pid, + .write = do_pid, +}; + +static const struct file_operations maxlatproc_fops = { + .open = tracing_open_generic, + .read = show_maxlatproc, +}; +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) +static notrace void probe_preemptirqsoff_hist(void *v, int reason, + int starthist) +{ + int cpu = raw_smp_processor_id(); + int time_set = 0; + + if (starthist) { + cycle_t uninitialized_var(start); + + if (!preempt_count() && !irqs_disabled()) + return; + +#ifdef CONFIG_INTERRUPT_OFF_HIST + if ((reason == IRQS_OFF || reason == TRACE_START) && + !per_cpu(hist_irqsoff_counting, cpu)) { + per_cpu(hist_irqsoff_counting, cpu) = 1; + start = ftrace_now(cpu); + time_set++; + per_cpu(hist_irqsoff_start, cpu) = start; + } +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + if ((reason == PREEMPT_OFF || reason == TRACE_START) && + !per_cpu(hist_preemptoff_counting, cpu)) { + per_cpu(hist_preemptoff_counting, cpu) = 1; + if (!(time_set++)) + start = ftrace_now(cpu); + per_cpu(hist_preemptoff_start, cpu) = start; + } +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + if (per_cpu(hist_irqsoff_counting, cpu) && + per_cpu(hist_preemptoff_counting, cpu) && + !per_cpu(hist_preemptirqsoff_counting, cpu)) { + per_cpu(hist_preemptirqsoff_counting, cpu) = 1; + if (!time_set) + start = ftrace_now(cpu); + per_cpu(hist_preemptirqsoff_start, cpu) = start; + } +#endif + } else { + cycle_t uninitialized_var(stop); + +#ifdef CONFIG_INTERRUPT_OFF_HIST + if ((reason == IRQS_ON || reason == TRACE_STOP) && + per_cpu(hist_irqsoff_counting, cpu)) { + cycle_t start = per_cpu(hist_irqsoff_start, cpu); + + stop = ftrace_now(cpu); + time_set++; + if (start) { + long latency = ((long) (stop - start)) / + NSECS_PER_USECS; + + latency_hist(IRQSOFF_LATENCY, cpu, latency, 0, + stop, NULL); + } + per_cpu(hist_irqsoff_counting, cpu) = 0; + } +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + if ((reason == PREEMPT_ON || reason == TRACE_STOP) && + per_cpu(hist_preemptoff_counting, cpu)) { + cycle_t start = per_cpu(hist_preemptoff_start, cpu); + + if (!(time_set++)) + stop = ftrace_now(cpu); + if (start) { + long latency = ((long) (stop - start)) / + NSECS_PER_USECS; + + latency_hist(PREEMPTOFF_LATENCY, cpu, latency, + 0, stop, NULL); + } + per_cpu(hist_preemptoff_counting, cpu) = 0; + } +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + if ((!per_cpu(hist_irqsoff_counting, cpu) || + !per_cpu(hist_preemptoff_counting, cpu)) && + per_cpu(hist_preemptirqsoff_counting, cpu)) { + cycle_t start = per_cpu(hist_preemptirqsoff_start, cpu); + + if (!time_set) + stop = ftrace_now(cpu); + if (start) { + long latency = ((long) (stop - start)) / + NSECS_PER_USECS; + + latency_hist(PREEMPTIRQSOFF_LATENCY, cpu, + latency, 0, stop, NULL); + } + per_cpu(hist_preemptirqsoff_counting, cpu) = 0; + } +#endif + } +} +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST +static DEFINE_RAW_SPINLOCK(wakeup_lock); +static notrace void probe_sched_migrate_task(void *v, struct task_struct *task, + int cpu) +{ + int old_cpu = task_cpu(task); + + if (cpu != old_cpu) { + unsigned long flags; + struct task_struct *cpu_wakeup_task; + + raw_spin_lock_irqsave(&wakeup_lock, flags); + + cpu_wakeup_task = per_cpu(wakeup_task, old_cpu); + if (task == cpu_wakeup_task) { + put_task_struct(cpu_wakeup_task); + per_cpu(wakeup_task, old_cpu) = NULL; + cpu_wakeup_task = per_cpu(wakeup_task, cpu) = task; + get_task_struct(cpu_wakeup_task); + } + + raw_spin_unlock_irqrestore(&wakeup_lock, flags); + } +} + +static notrace void probe_wakeup_latency_hist_start(void *v, + struct task_struct *p, int success) +{ + unsigned long flags; + struct task_struct *curr = current; + int cpu = task_cpu(p); + struct task_struct *cpu_wakeup_task; + + raw_spin_lock_irqsave(&wakeup_lock, flags); + + cpu_wakeup_task = per_cpu(wakeup_task, cpu); + + if (wakeup_pid) { + if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || + p->prio == curr->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + if (likely(wakeup_pid != task_pid_nr(p))) + goto out; + } else { + if (likely(!rt_task(p)) || + (cpu_wakeup_task && p->prio > cpu_wakeup_task->prio) || + p->prio > curr->prio) + goto out; + if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || + p->prio == curr->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + } + + if (cpu_wakeup_task) + put_task_struct(cpu_wakeup_task); + cpu_wakeup_task = per_cpu(wakeup_task, cpu) = p; + get_task_struct(cpu_wakeup_task); + cpu_wakeup_task->preempt_timestamp_hist = + ftrace_now(raw_smp_processor_id()); +out: + raw_spin_unlock_irqrestore(&wakeup_lock, flags); +} + +static notrace void probe_wakeup_latency_hist_stop(void *v, + struct task_struct *prev, struct task_struct *next) +{ + unsigned long flags; + int cpu = task_cpu(next); + long latency; + cycle_t stop; + struct task_struct *cpu_wakeup_task; + + raw_spin_lock_irqsave(&wakeup_lock, flags); + + cpu_wakeup_task = per_cpu(wakeup_task, cpu); + + if (cpu_wakeup_task == NULL) + goto out; + + /* Already running? */ + if (unlikely(current == cpu_wakeup_task)) + goto out_reset; + + if (next != cpu_wakeup_task) { + if (next->prio < cpu_wakeup_task->prio) + goto out_reset; + + if (next->prio == cpu_wakeup_task->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + + goto out; + } + + if (current->prio == cpu_wakeup_task->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + + /* + * The task we are waiting for is about to be switched to. + * Calculate latency and store it in histogram. + */ + stop = ftrace_now(raw_smp_processor_id()); + + latency = ((long) (stop - next->preempt_timestamp_hist)) / + NSECS_PER_USECS; + + if (per_cpu(wakeup_sharedprio, cpu)) { + latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop, + next); + per_cpu(wakeup_sharedprio, cpu) = 0; + } else { + latency_hist(WAKEUP_LATENCY, cpu, latency, 0, stop, next); +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + if (timerandwakeup_enabled_data.enabled) { + latency_hist(TIMERANDWAKEUP_LATENCY, cpu, + next->timer_offset + latency, next->timer_offset, + stop, next); + } +#endif + } + +out_reset: +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + next->timer_offset = 0; +#endif + put_task_struct(cpu_wakeup_task); + per_cpu(wakeup_task, cpu) = NULL; +out: + raw_spin_unlock_irqrestore(&wakeup_lock, flags); +} +#endif + +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST +static notrace void probe_hrtimer_interrupt(void *v, int cpu, + long long latency_ns, struct task_struct *curr, + struct task_struct *task) +{ + if (latency_ns <= 0 && task != NULL && rt_task(task) && + (task->prio < curr->prio || + (task->prio == curr->prio && + !cpumask_test_cpu(cpu, &task->cpus_allowed)))) { + long latency; + cycle_t now; + + if (missed_timer_offsets_pid) { + if (likely(missed_timer_offsets_pid != + task_pid_nr(task))) + return; + } + + now = ftrace_now(cpu); + latency = (long) div_s64(-latency_ns, NSECS_PER_USECS); + latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now, + task); +#ifdef CONFIG_WAKEUP_LATENCY_HIST + task->timer_offset = latency; +#endif + } +} +#endif + +static __init int latency_hist_init(void) +{ + struct dentry *latency_hist_root = NULL; + struct dentry *dentry; +#ifdef CONFIG_WAKEUP_LATENCY_HIST + struct dentry *dentry_sharedprio; +#endif + struct dentry *entry; + struct dentry *enable_root; + int i = 0; + struct hist_data *my_hist; + char name[64]; + char *cpufmt = "CPU%d"; +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + char *cpufmt_maxlatproc = "max_latency-CPU%d"; + struct maxlatproc_data *mp = NULL; +#endif + + dentry = tracing_init_dentry(); + latency_hist_root = debugfs_create_dir(latency_hist_dir_root, dentry); + enable_root = debugfs_create_dir("enable", latency_hist_root); + +#ifdef CONFIG_INTERRUPT_OFF_HIST + dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(irqsoff_hist, i), &latency_hist_fops); + my_hist = &per_cpu(irqsoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops); +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + dentry = debugfs_create_dir(preemptoff_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(preemptoff_hist, i), &latency_hist_fops); + my_hist = &per_cpu(preemptoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops); +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + dentry = debugfs_create_dir(preemptirqsoff_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops); + my_hist = &per_cpu(preemptirqsoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops); +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + entry = debugfs_create_file("preemptirqsoff", 0644, + enable_root, (void *)&preemptirqsoff_enabled_data, + &enable_fops); +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST + dentry = debugfs_create_dir(wakeup_latency_hist_dir, + latency_hist_root); + dentry_sharedprio = debugfs_create_dir( + wakeup_latency_hist_dir_sharedprio, dentry); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(wakeup_latency_hist, i), + &latency_hist_fops); + my_hist = &per_cpu(wakeup_latency_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + + entry = debugfs_create_file(name, 0444, dentry_sharedprio, + &per_cpu(wakeup_latency_hist_sharedprio, i), + &latency_hist_fops); + my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + + sprintf(name, cpufmt_maxlatproc, i); + + mp = &per_cpu(wakeup_maxlatproc, i); + entry = debugfs_create_file(name, 0444, dentry, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + + mp = &per_cpu(wakeup_maxlatproc_sharedprio, i); + entry = debugfs_create_file(name, 0444, dentry_sharedprio, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + } + entry = debugfs_create_file("pid", 0644, dentry, + (void *)&wakeup_pid, &pid_fops); + entry = debugfs_create_file("reset", 0644, dentry, + (void *)WAKEUP_LATENCY, &latency_hist_reset_fops); + entry = debugfs_create_file("reset", 0644, dentry_sharedprio, + (void *)WAKEUP_LATENCY_SHAREDPRIO, &latency_hist_reset_fops); + entry = debugfs_create_file("wakeup", 0644, + enable_root, (void *)&wakeup_latency_enabled_data, + &enable_fops); +#endif + +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + dentry = debugfs_create_dir(missed_timer_offsets_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(missed_timer_offsets, i), &latency_hist_fops); + my_hist = &per_cpu(missed_timer_offsets, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + + sprintf(name, cpufmt_maxlatproc, i); + mp = &per_cpu(missed_timer_offsets_maxlatproc, i); + entry = debugfs_create_file(name, 0444, dentry, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + } + entry = debugfs_create_file("pid", 0644, dentry, + (void *)&missed_timer_offsets_pid, &pid_fops); + entry = debugfs_create_file("reset", 0644, dentry, + (void *)MISSED_TIMER_OFFSETS, &latency_hist_reset_fops); + entry = debugfs_create_file("missed_timer_offsets", 0644, + enable_root, (void *)&missed_timer_offsets_enabled_data, + &enable_fops); +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + dentry = debugfs_create_dir(timerandwakeup_latency_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(timerandwakeup_latency_hist, i), + &latency_hist_fops); + my_hist = &per_cpu(timerandwakeup_latency_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + + sprintf(name, cpufmt_maxlatproc, i); + mp = &per_cpu(timerandwakeup_maxlatproc, i); + entry = debugfs_create_file(name, 0444, dentry, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)TIMERANDWAKEUP_LATENCY, &latency_hist_reset_fops); + entry = debugfs_create_file("timerandwakeup", 0644, + enable_root, (void *)&timerandwakeup_enabled_data, + &enable_fops); +#endif + return 0; +} + +device_initcall(latency_hist_init); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 138077b..f9401ed 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -442,7 +442,7 @@ int __trace_puts(unsigned long ip, const char *str, int size) local_save_flags(irq_flags); buffer = global_trace.trace_buffer.buffer; - event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, + event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, irq_flags, preempt_count()); if (!event) return 0; @@ -1509,6 +1509,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, struct task_struct *tsk = current; entry->preempt_count = pc & 0xff; + entry->preempt_lazy_count = preempt_lazy_count(); entry->pid = (tsk) ? tsk->pid : 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT @@ -1518,7 +1519,10 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, #endif ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | - (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); + (need_resched_now() ? TRACE_FLAG_NEED_RESCHED : 0) | + (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0); + + entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; } EXPORT_SYMBOL_GPL(tracing_generic_entry_update); @@ -2408,14 +2412,17 @@ get_total_entries(struct trace_buffer *buf, static void print_lat_help_header(struct seq_file *m) { - seq_puts(m, "# _------=> CPU# \n"); - seq_puts(m, "# / _-----=> irqs-off \n"); - seq_puts(m, "# | / _----=> need-resched \n"); - seq_puts(m, "# || / _---=> hardirq/softirq \n"); - seq_puts(m, "# ||| / _--=> preempt-depth \n"); - seq_puts(m, "# |||| / delay \n"); - seq_puts(m, "# cmd pid ||||| time | caller \n"); - seq_puts(m, "# \\ / ||||| \\ | / \n"); + seq_puts(m, "# _--------=> CPU# \n"); + seq_puts(m, "# / _-------=> irqs-off \n"); + seq_puts(m, "# | / _------=> need-resched \n"); + seq_puts(m, "# || / _-----=> need-resched_lazy \n"); + seq_puts(m, "# ||| / _----=> hardirq/softirq \n"); + seq_puts(m, "# |||| / _---=> preempt-depth \n"); + seq_puts(m, "# ||||| / _--=> preempt-lazy-depth\n"); + seq_puts(m, "# |||||| / _-=> migrate-disable \n"); + seq_puts(m, "# ||||||| / delay \n"); + seq_puts(m, "# cmd pid |||||||| time | caller \n"); + seq_puts(m, "# \\ / |||||||| \\ | / \n"); } static void print_event_info(struct trace_buffer *buf, struct seq_file *m) @@ -2439,13 +2446,16 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m) static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m) { print_event_info(buf, m); - seq_puts(m, "# _-----=> irqs-off\n"); - seq_puts(m, "# / _----=> need-resched\n"); - seq_puts(m, "# | / _---=> hardirq/softirq\n"); - seq_puts(m, "# || / _--=> preempt-depth\n"); - seq_puts(m, "# ||| / delay\n"); - seq_puts(m, "# TASK-PID CPU# |||| TIMESTAMP FUNCTION\n"); - seq_puts(m, "# | | | |||| | |\n"); + seq_puts(m, "# _-------=> irqs-off \n"); + seq_puts(m, "# / _------=> need-resched \n"); + seq_puts(m, "# |/ _-----=> need-resched_lazy \n"); + seq_puts(m, "# ||/ _----=> hardirq/softirq \n"); + seq_puts(m, "# |||/ _---=> preempt-depth \n"); + seq_puts(m, "# ||||/ _--=> preempt-lazy-depth\n"); + seq_puts(m, "# ||||| / _-=> migrate-disable \n"); + seq_puts(m, "# |||||| / delay\n"); + seq_puts(m, "# TASK-PID CPU# |||||| TIMESTAMP FUNCTION\n"); + seq_puts(m, "# | | | |||||| | |\n"); } void diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 10c86fb..109291a 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -117,6 +117,7 @@ struct kretprobe_trace_entry_head { * NEED_RESCHED - reschedule is requested * HARDIRQ - inside an interrupt handler * SOFTIRQ - inside a softirq handler + * NEED_RESCHED_LAZY - lazy reschedule is requested */ enum trace_flag_type { TRACE_FLAG_IRQS_OFF = 0x01, @@ -124,6 +125,7 @@ enum trace_flag_type { TRACE_FLAG_NEED_RESCHED = 0x04, TRACE_FLAG_HARDIRQ = 0x08, TRACE_FLAG_SOFTIRQ = 0x10, + TRACE_FLAG_NEED_RESCHED_LAZY = 0x20, }; #define TRACE_BUF_SIZE 1024 diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index bc1bd20..9e49f3f 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -160,6 +160,8 @@ static int trace_define_common_fields(void) __common_field(unsigned char, flags); __common_field(unsigned char, preempt_count); __common_field(int, pid); + __common_field(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 2aefbee..2f4eb37 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; @@ -439,11 +440,13 @@ 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); } @@ -453,6 +456,7 @@ 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); } @@ -461,6 +465,7 @@ 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 */ @@ -486,6 +491,7 @@ 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); } @@ -495,11 +501,13 @@ 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); } @@ -509,6 +517,7 @@ 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); @@ -518,12 +527,14 @@ 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 34e7cba..46b6467 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -606,6 +606,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) { char hardsoft_irq; char need_resched; + char need_resched_lazy; char irqs_off; int hardirq; int softirq; @@ -620,14 +621,17 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) '.'; need_resched = (entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.'; + need_resched_lazy = + (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; hardsoft_irq = (hardirq && softirq) ? 'H' : hardirq ? 'h' : softirq ? 's' : '.'; - if (!trace_seq_printf(s, "%c%c%c", - irqs_off, need_resched, hardsoft_irq)) + if (!trace_seq_printf(s, "%c%c%c%c", + irqs_off, need_resched, need_resched_lazy, + hardsoft_irq)) return 0; if (entry->preempt_count) @@ -635,6 +639,16 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) else ret = trace_seq_putc(s, '.'); + if (entry->preempt_lazy_count) + ret = trace_seq_printf(s, "%x", entry->preempt_lazy_count); + else + ret = trace_seq_putc(s, '.'); + + if (entry->migrate_disable) + ret = trace_seq_printf(s, "%x", entry->migrate_disable); + else + ret = trace_seq_putc(s, '.'); + return ret; } diff --git a/kernel/user.c b/kernel/user.c index 5bbb919..2800008 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -154,11 +154,11 @@ 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(kuid_t uid) diff --git a/kernel/wait-simple.c b/kernel/wait-simple.c new file mode 100644 index 0000000..7dfa86d --- /dev/null +++ b/kernel/wait-simple.c @@ -0,0 +1,115 @@ +/* + * 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> + +/* Adds w to head->list. Must be called with head->lock locked. */ +static inline void __swait_enqueue(struct swait_head *head, struct swaiter *w) +{ + list_add(&w->node, &head->list); + /* We can't let the condition leak before the setting of head */ + smp_mb(); +} + +/* Removes w from head->list. Must be called with head->lock locked. */ +static inline void __swait_dequeue(struct swaiter *w) +{ + list_del_init(&w->node); +} + +void __init_swait_head(struct swait_head *head, struct lock_class_key *key) +{ + raw_spin_lock_init(&head->lock); + lockdep_set_class(&head->lock, key); + INIT_LIST_HEAD(&head->list); +} +EXPORT_SYMBOL(__init_swait_head); + +void swait_prepare_locked(struct swait_head *head, struct swaiter *w) +{ + w->task = current; + if (list_empty(&w->node)) + __swait_enqueue(head, w); +} + +void swait_prepare(struct swait_head *head, struct swaiter *w, int state) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&head->lock, flags); + swait_prepare_locked(head, w); + __set_current_state(state); + raw_spin_unlock_irqrestore(&head->lock, flags); +} +EXPORT_SYMBOL(swait_prepare); + +void swait_finish_locked(struct swait_head *head, struct swaiter *w) +{ + __set_current_state(TASK_RUNNING); + if (w->task) + __swait_dequeue(w); +} + +void swait_finish(struct swait_head *head, struct swaiter *w) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + if (w->task) { + raw_spin_lock_irqsave(&head->lock, flags); + __swait_dequeue(w); + raw_spin_unlock_irqrestore(&head->lock, flags); + } +} +EXPORT_SYMBOL(swait_finish); + +unsigned int +__swait_wake_locked(struct swait_head *head, unsigned int state, unsigned int num) +{ + struct swaiter *curr, *next; + int woken = 0; + + list_for_each_entry_safe(curr, next, &head->list, node) { + if (wake_up_state(curr->task, state)) { + __swait_dequeue(curr); + /* + * The waiting task can free the waiter as + * soon as curr->task = NULL is written, + * without taking any locks. A memory barrier + * is required here to prevent the following + * store to curr->task from getting ahead of + * the dequeue operation. + */ + smp_wmb(); + curr->task = NULL; + if (++woken == num) + break; + } + } + return woken; +} + +unsigned int +__swait_wake(struct swait_head *head, unsigned int state, unsigned int num) +{ + unsigned long flags; + int woken; + + if (!swaitqueue_active(head)) + return 0; + + raw_spin_lock_irqsave(&head->lock, flags); + woken = __swait_wake_locked(head, state, num); + raw_spin_unlock_irqrestore(&head->lock, flags); + return woken; +} +EXPORT_SYMBOL(__swait_wake); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 4431610..870b748 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -205,6 +205,8 @@ 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, @@ -239,10 +241,19 @@ 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; @@ -346,6 +357,7 @@ static void watchdog_enable(unsigned int cpu) /* kick off the timer for the hardlockup detector */ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; + hrtimer->irqsafe = 1; /* Enable the perf event */ watchdog_nmi_enable(cpu); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 60fee69..9efb7ce 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -48,6 +48,8 @@ #include <linux/nodemask.h> #include <linux/moduleparam.h> #include <linux/uaccess.h> +#include <linux/locallock.h> +#include <linux/delay.h> #include "workqueue_internal.h" @@ -129,11 +131,11 @@ enum { * * PL: wq_pool_mutex protected. * - * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads. + * PR: wq_pool_mutex protected for writes. RCU protected for reads. * * WQ: wq->mutex protected. * - * WR: wq->mutex protected for writes. Sched-RCU protected for reads. + * WR: wq->mutex protected for writes. RCU protected for reads. * * MD: wq_mayday_lock protected. */ @@ -178,7 +180,7 @@ struct worker_pool { atomic_t nr_running ____cacheline_aligned_in_smp; /* - * Destruction of pool is sched-RCU protected to allow dereferences + * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; @@ -207,7 +209,7 @@ struct pool_workqueue { /* * Release of unbound pwq is punted to system_wq. See put_pwq() * and pwq_unbound_release_workfn() for details. pool_workqueue - * itself is also sched-RCU protected so that the first pwq can be + * itself is also RCU protected so that the first pwq can be * determined without grabbing wq->mutex. */ struct work_struct unbound_release_work; @@ -323,6 +325,8 @@ EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); +static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock); + static int worker_thread(void *__worker); static void copy_workqueue_attrs(struct workqueue_attrs *to, const struct workqueue_attrs *from); @@ -331,14 +335,14 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, #include <trace/events/workqueue.h> #define assert_rcu_or_pool_mutex() \ - rcu_lockdep_assert(rcu_read_lock_sched_held() || \ + rcu_lockdep_assert(rcu_read_lock_held() || \ lockdep_is_held(&wq_pool_mutex), \ - "sched RCU or wq_pool_mutex should be held") + "RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex(wq) \ - rcu_lockdep_assert(rcu_read_lock_sched_held() || \ + rcu_lockdep_assert(rcu_read_lock_held() || \ lockdep_is_held(&wq->mutex), \ - "sched RCU or wq->mutex should be held") + "RCU or wq->mutex should be held") #ifdef CONFIG_LOCKDEP #define assert_manager_or_pool_lock(pool) \ @@ -360,7 +364,7 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, * @pool: iteration cursor * @pi: integer used for iteration * - * This must be called either with wq_pool_mutex held or sched RCU read + * This must be called either with wq_pool_mutex held or RCU read * locked. If the pool needs to be used beyond the locking in effect, the * caller is responsible for guaranteeing that the pool stays online. * @@ -393,7 +397,7 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, * @pwq: iteration cursor * @wq: the target workqueue * - * This must be called either with wq->mutex held or sched RCU read locked. + * This must be called either with wq->mutex held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * @@ -541,7 +545,7 @@ static int worker_pool_assign_id(struct worker_pool *pool) * @wq: the target workqueue * @node: the node ID * - * This must be called either with pwq_lock held or sched RCU read locked. + * This must be called either with pwq_lock held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * @@ -645,8 +649,8 @@ static struct pool_workqueue *get_work_pwq(struct work_struct *work) * @work: the work item of interest * * Pools are created and destroyed under wq_pool_mutex, and allows read - * access under sched-RCU read lock. As such, this function should be - * called under wq_pool_mutex or with preemption disabled. + * access under RCU read lock. As such, this function should be + * called under wq_pool_mutex or inside of a rcu_read_lock() region. * * All fields of the returned pool are accessible as long as the above * mentioned locking is in effect. If the returned pool needs to be used @@ -804,44 +808,31 @@ static void wake_up_worker(struct worker_pool *pool) } /** - * wq_worker_waking_up - a worker is waking up - * @task: task waking up - * @cpu: CPU @task is waking up to - * - * This function is called during try_to_wake_up() when a worker is - * being awoken. + * wq_worker_running - a worker is running again + * @task: task returning from sleep * - * CONTEXT: - * spin_lock_irq(rq->lock) + * This function is called when a worker returns from schedule() */ -void wq_worker_waking_up(struct task_struct *task, int cpu) +void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); - if (!(worker->flags & WORKER_NOT_RUNNING)) { - WARN_ON_ONCE(worker->pool->cpu != cpu); + if (!worker->sleeping) + return; + if (!(worker->flags & WORKER_NOT_RUNNING)) atomic_inc(&worker->pool->nr_running); - } + worker->sleeping = 0; } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep - * @cpu: CPU in question, must be the current CPU number - * - * This function is called during schedule() when a busy worker is - * going to sleep. Worker on the same cpu can be woken up by - * returning pointer to its task. - * - * CONTEXT: - * spin_lock_irq(rq->lock) - * - * Return: - * Worker task on @cpu to wake up, %NULL if none. + * This function is called from schedule() when a busy worker is + * going to sleep. */ -struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) +void wq_worker_sleeping(struct task_struct *task) { - struct worker *worker = kthread_data(task), *to_wakeup = NULL; + struct worker *next, *worker = kthread_data(task); struct worker_pool *pool; /* @@ -850,14 +841,15 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) - return NULL; + return; pool = worker->pool; - /* this can only happen on the local cpu */ - if (WARN_ON_ONCE(cpu != raw_smp_processor_id())) - return NULL; + if (WARN_ON_ONCE(worker->sleeping)) + return; + worker->sleeping = 1; + spin_lock_irq(&pool->lock); /* * The counterpart of the following dec_and_test, implied mb, * worklist not empty test sequence is in insert_work(). @@ -870,9 +862,12 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) * lock is safe. */ if (atomic_dec_and_test(&pool->nr_running) && - !list_empty(&pool->worklist)) - to_wakeup = first_worker(pool); - return to_wakeup ? to_wakeup->task : NULL; + !list_empty(&pool->worklist)) { + next = first_worker(pool); + if (next) + wake_up_process(next->task); + } + spin_unlock_irq(&pool->lock); } /** @@ -1079,12 +1074,12 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq) { if (pwq) { /* - * As both pwqs and pools are sched-RCU protected, the + * As both pwqs and pools are RCU protected, the * following lock operations are safe. */ - spin_lock_irq(&pwq->pool->lock); + local_spin_lock_irq(pendingb_lock, &pwq->pool->lock); put_pwq(pwq); - spin_unlock_irq(&pwq->pool->lock); + local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock); } } @@ -1186,7 +1181,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, struct worker_pool *pool; struct pool_workqueue *pwq; - local_irq_save(*flags); + local_lock_irqsave(pendingb_lock, *flags); /* try to steal the timer if it exists */ if (is_dwork) { @@ -1205,6 +1200,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; + rcu_read_lock(); /* * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. @@ -1243,14 +1239,16 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, set_work_pool_and_keep_pending(work, pool->id); spin_unlock(&pool->lock); + rcu_read_unlock(); return 1; } spin_unlock(&pool->lock); fail: - local_irq_restore(*flags); + rcu_read_unlock(); + local_unlock_irqrestore(pendingb_lock, *flags); if (work_is_canceling(work)) return -ENOENT; - cpu_relax(); + cpu_chill(); return -EAGAIN; } @@ -1319,7 +1317,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, * queued or lose PENDING. Grabbing PENDING and queueing should * happen with IRQ disabled. */ - WARN_ON_ONCE(!irqs_disabled()); + WARN_ON_ONCE_NONRT(!irqs_disabled()); debug_work_activate(work); @@ -1327,6 +1325,8 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, if (unlikely(wq->flags & __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq))) return; + + rcu_read_lock(); retry: if (req_cpu == WORK_CPU_UNBOUND) cpu = raw_smp_processor_id(); @@ -1383,10 +1383,8 @@ retry: /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); - if (WARN_ON(!list_empty(&work->entry))) { - spin_unlock(&pwq->pool->lock); - return; - } + if (WARN_ON(!list_empty(&work->entry))) + goto out; pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); @@ -1402,7 +1400,9 @@ retry: insert_work(pwq, work, worklist, work_flags); +out: spin_unlock(&pwq->pool->lock); + rcu_read_unlock(); } /** @@ -1422,14 +1422,14 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, bool ret = false; unsigned long flags; - local_irq_save(flags); + local_lock_irqsave(pendingb_lock,flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_work(cpu, wq, work); ret = true; } - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); return ret; } EXPORT_SYMBOL(queue_work_on); @@ -1496,14 +1496,14 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, unsigned long flags; /* read the comment in __queue_work() */ - local_irq_save(flags); + local_lock_irqsave(pendingb_lock, flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); @@ -1538,7 +1538,7 @@ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, if (likely(ret >= 0)) { __queue_delayed_work(cpu, wq, dwork, delay); - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); } /* -ENOENT from try_to_grab_pending() becomes %true */ @@ -2809,14 +2809,14 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr) might_sleep(); - local_irq_disable(); + rcu_read_lock(); pool = get_work_pool(work); if (!pool) { - local_irq_enable(); + rcu_read_unlock(); return false; } - spin_lock(&pool->lock); + spin_lock_irq(&pool->lock); /* see the comment in try_to_grab_pending() with the same code */ pwq = get_work_pwq(work); if (pwq) { @@ -2843,10 +2843,11 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr) else lock_map_acquire_read(&pwq->wq->lockdep_map); lock_map_release(&pwq->wq->lockdep_map); - + rcu_read_unlock(); return true; already_gone: spin_unlock_irq(&pool->lock); + rcu_read_unlock(); return false; } @@ -2900,7 +2901,7 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) /* tell other tasks trying to grab @work to back off */ mark_work_canceling(work); - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); flush_work(work); clear_work_data(work); @@ -2945,10 +2946,10 @@ EXPORT_SYMBOL_GPL(cancel_work_sync); */ bool flush_delayed_work(struct delayed_work *dwork) { - local_irq_disable(); + local_lock_irq(pendingb_lock); if (del_timer_sync(&dwork->timer)) __queue_work(dwork->cpu, dwork->wq, &dwork->work); - local_irq_enable(); + local_unlock_irq(pendingb_lock); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); @@ -2983,7 +2984,7 @@ bool cancel_delayed_work(struct delayed_work *dwork) set_work_pool_and_clear_pending(&dwork->work, get_work_pool_id(&dwork->work)); - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); return ret; } EXPORT_SYMBOL(cancel_delayed_work); @@ -3169,7 +3170,8 @@ static ssize_t wq_pool_ids_show(struct device *dev, const char *delim = ""; int node, written = 0; - rcu_read_lock_sched(); + get_online_cpus(); + rcu_read_lock(); for_each_node(node) { written += scnprintf(buf + written, PAGE_SIZE - written, "%s%d:%d", delim, node, @@ -3177,7 +3179,8 @@ static ssize_t wq_pool_ids_show(struct device *dev, delim = " "; } written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); - rcu_read_unlock_sched(); + rcu_read_unlock(); + put_online_cpus(); return written; } @@ -3543,7 +3546,7 @@ static void rcu_free_pool(struct rcu_head *rcu) * put_unbound_pool - put a worker_pool * @pool: worker_pool to put * - * Put @pool. If its refcnt reaches zero, it gets destroyed in sched-RCU + * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU * safe manner. get_unbound_pool() calls this function on its failure path * and this function should be able to release pools which went through, * successfully or not, init_worker_pool(). @@ -3590,8 +3593,8 @@ static void put_unbound_pool(struct worker_pool *pool) del_timer_sync(&pool->idle_timer); del_timer_sync(&pool->mayday_timer); - /* sched-RCU protected to allow dereferences from get_work_pool() */ - call_rcu_sched(&pool->rcu, rcu_free_pool); + /* RCU protected to allow dereferences from get_work_pool() */ + call_rcu(&pool->rcu, rcu_free_pool); } /** @@ -3704,7 +3707,7 @@ static void pwq_unbound_release_workfn(struct work_struct *work) put_unbound_pool(pool); mutex_unlock(&wq_pool_mutex); - call_rcu_sched(&pwq->rcu, rcu_free_pwq); + call_rcu(&pwq->rcu, rcu_free_pwq); /* * If we're the last pwq going away, @wq is already dead and no one @@ -4417,7 +4420,8 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) struct pool_workqueue *pwq; bool ret; - rcu_read_lock_sched(); + rcu_read_lock(); + preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); @@ -4428,7 +4432,8 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); ret = !list_empty(&pwq->delayed_works); - rcu_read_unlock_sched(); + preempt_enable(); + rcu_read_unlock(); return ret; } @@ -4454,16 +4459,15 @@ unsigned int work_busy(struct work_struct *work) if (work_pending(work)) ret |= WORK_BUSY_PENDING; - local_irq_save(flags); + rcu_read_lock(); pool = get_work_pool(work); if (pool) { - spin_lock(&pool->lock); + spin_lock_irqsave(&pool->lock, flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; - spin_unlock(&pool->lock); + spin_unlock_irqrestore(&pool->lock, flags); } - local_irq_restore(flags); - + rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_busy); @@ -4916,16 +4920,16 @@ bool freeze_workqueues_busy(void) * nr_active is monotonically decreasing. It's safe * to peek without lock. */ - rcu_read_lock_sched(); + rcu_read_lock(); for_each_pwq(pwq, wq) { WARN_ON_ONCE(pwq->nr_active < 0); if (pwq->nr_active) { busy = true; - rcu_read_unlock_sched(); + rcu_read_unlock(); goto out_unlock; } } - rcu_read_unlock_sched(); + rcu_read_unlock(); } out_unlock: mutex_unlock(&wq_pool_mutex); diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 7e2204d..2bb5b5a 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -41,6 +41,7 @@ struct worker { unsigned long last_active; /* L: last active timestamp */ unsigned int flags; /* X: flags */ int id; /* I: worker id */ + int sleeping; /* None */ /* * Opaque string set with work_set_desc(). Printed out with task @@ -66,7 +67,7 @@ static inline struct worker *current_wq_worker(void) * Scheduler hooks for concurrency managed workqueue. Only to be used from * sched/core.c and workqueue.c. */ -void wq_worker_waking_up(struct task_struct *task, int cpu); -struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu); +void wq_worker_running(struct task_struct *task); +void wq_worker_sleeping(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ |