From 73459e2a1ada09a68c02cc5b73f3116fc8194b3d Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 23 Apr 2015 13:20:18 +0200 Subject: x86: pvclock: Really remove the sched notifier for cross-cpu migrations This reverts commits 0a4e6be9ca17c54817cf814b4b5aa60478c6df27 and 80f7fdb1c7f0f9266421f823964fd1962681f6ce. The task migration notifier was originally introduced in order to support the pvclock vsyscall with non-synchronized TSC, but KVM only supports it with synchronized TSC. Hence, on KVM the race condition is only needed due to a bad implementation on the host side, and even then it's so rare that it's mostly theoretical. As far as KVM is concerned it's possible to fix the host, avoiding the additional complexity in the vDSO and the (re)introduction of the task migration notifier. Xen, on the other hand, hasn't yet implemented vsyscall support at all, so we do not care about its plans for non-synchronized TSC. Reported-by: Peter Zijlstra Suggested-by: Marcelo Tosatti Signed-off-by: Paolo Bonzini --- kernel/sched/core.c | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f9123a82cbb6..fe22f7510bce 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1016,13 +1016,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) rq_clock_skip_update(rq, true); } -static ATOMIC_NOTIFIER_HEAD(task_migration_notifier); - -void register_task_migration_notifier(struct notifier_block *n) -{ - atomic_notifier_chain_register(&task_migration_notifier, n); -} - #ifdef CONFIG_SMP void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { @@ -1053,18 +1046,10 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) trace_sched_migrate_task(p, new_cpu); if (task_cpu(p) != new_cpu) { - struct task_migration_notifier tmn; - if (p->sched_class->migrate_task_rq) p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); - - tmn.task = p; - tmn.from_cpu = task_cpu(p); - tmn.to_cpu = new_cpu; - - atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn); } __set_task_cpu(p, new_cpu); -- cgit From df8d9eeadd0f7a216f2476351d5aee43c6550bf0 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 29 Apr 2015 15:19:21 +0200 Subject: cpuidle: Run tick_broadcast_exit() with disabled interrupts Commit 335f49196fd6 (sched/idle: Use explicit broadcast oneshot control function) replaced clockevents_notify() invocations in cpuidle_idle_call() with direct calls to tick_broadcast_enter() and tick_broadcast_exit(), but it overlooked the fact that interrupts were already enabled before calling the latter which led to functional breakage on systems using idle states with the CPUIDLE_FLAG_TIMER_STOP flag set. Fix that by moving the invocations of tick_broadcast_enter() and tick_broadcast_exit() down into cpuidle_enter_state() where interrupts are still disabled when tick_broadcast_exit() is called. Also ensure that interrupts will be disabled before running tick_broadcast_exit() even if they have been enabled by the idle state's ->enter callback. Trigger a WARN_ON_ONCE() in that case, as we generally don't want that to happen for states with CPUIDLE_FLAG_TIMER_STOP set. Fixes: 335f49196fd6 (sched/idle: Use explicit broadcast oneshot control function) Reported-and-tested-by: Linus Walleij Acked-by: Peter Zijlstra (Intel) Acked-by: Daniel Lezcano Reported-and-tested-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/cpuidle.c | 16 ++++++++++++++++ kernel/sched/idle.c | 16 ++-------------- 2 files changed, 18 insertions(+), 14 deletions(-) (limited to 'kernel/sched') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 7a73a279e179..61c417b9e53f 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -158,9 +158,18 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, int entered_state; struct cpuidle_state *target_state = &drv->states[index]; + bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP); ktime_t time_start, time_end; s64 diff; + /* + * Tell the time framework to switch to a broadcast timer because our + * local timer will be shut down. If a local timer is used from another + * CPU as a broadcast timer, this call may fail if it is not available. + */ + if (broadcast && tick_broadcast_enter()) + return -EBUSY; + trace_cpu_idle_rcuidle(index, dev->cpu); time_start = ktime_get(); @@ -169,6 +178,13 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, time_end = ktime_get(); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); + if (broadcast) { + if (WARN_ON_ONCE(!irqs_disabled())) + local_irq_disable(); + + tick_broadcast_exit(); + } + if (!cpuidle_state_is_coupled(dev, drv, entered_state)) local_irq_enable(); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index deef1caa94c6..fefcb1fa5160 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -81,7 +81,6 @@ static void cpuidle_idle_call(void) struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); int next_state, entered_state; - unsigned int broadcast; bool reflect; /* @@ -150,17 +149,6 @@ static void cpuidle_idle_call(void) goto exit_idle; } - broadcast = drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP; - - /* - * Tell the time framework to switch to a broadcast timer - * because our local timer will be shutdown. If a local timer - * is used from another cpu as a broadcast timer, this call may - * fail if it is not available - */ - if (broadcast && tick_broadcast_enter()) - goto use_default; - /* Take note of the planned idle state. */ idle_set_state(this_rq(), &drv->states[next_state]); @@ -174,8 +162,8 @@ static void cpuidle_idle_call(void) /* The cpu is no longer idle or about to enter idle. */ idle_set_state(this_rq(), NULL); - if (broadcast) - tick_broadcast_exit(); + if (entered_state == -EBUSY) + goto use_default; /* * Give the governor an opportunity to reflect on the outcome -- cgit