From 45eacc692771bd2b1ea3d384e6345cab3da10861 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 15 May 2013 22:16:32 +0200 Subject: [PATCH 1/4] vtime: Use consistent clocks among nohz accounting While computing the cputime delta of dynticks CPUs, we are mixing up clocks of differents natures: * local_clock() which takes care of unstable clock sources and fix these if needed. * sched_clock() which is the weaker version of local_clock(). It doesn't compute any fixup in case of unstable source. If the clock source is stable, those two clocks are the same and we can safely compute the difference against two random points. Otherwise it results in random deltas as sched_clock() can randomly drift away, back or forward, from local_clock(). As a consequence, some strange behaviour with unstable tsc has been observed such as non progressing constant zero cputime. (The 'top' command showing no load). Fix this by only using local_clock(), or its irq safe/remote equivalent, in vtime code. Reported-by: Mike Galbraith Suggested-by: Mike Galbraith Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- include/linux/vtime.h | 4 ++-- kernel/sched/core.c | 2 +- kernel/sched/cputime.c | 6 +++--- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 71a5782d8c59..b1dd2db80076 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -34,7 +34,7 @@ static inline void vtime_user_exit(struct task_struct *tsk) } extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); -extern void vtime_init_idle(struct task_struct *tsk); +extern void vtime_init_idle(struct task_struct *tsk, int cpu); #else static inline void vtime_account_irq_exit(struct task_struct *tsk) { @@ -45,7 +45,7 @@ static inline void vtime_user_enter(struct task_struct *tsk) { } static inline void vtime_user_exit(struct task_struct *tsk) { } static inline void vtime_guest_enter(struct task_struct *tsk) { } static inline void vtime_guest_exit(struct task_struct *tsk) { } -static inline void vtime_init_idle(struct task_struct *tsk) { } +static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { } #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 58453b8272fd..e1a27f918723 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4745,7 +4745,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) */ idle->sched_class = &idle_sched_class; ftrace_graph_init_idle_task(idle, cpu); - vtime_init_idle(idle); + vtime_init_idle(idle, cpu); #if defined(CONFIG_SMP) sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); #endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index cc2dc3eea8a3..b5ccba22603b 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -747,17 +747,17 @@ void arch_vtime_task_switch(struct task_struct *prev) write_seqlock(¤t->vtime_seqlock); current->vtime_snap_whence = VTIME_SYS; - current->vtime_snap = sched_clock(); + current->vtime_snap = sched_clock_cpu(smp_processor_id()); write_sequnlock(¤t->vtime_seqlock); } -void vtime_init_idle(struct task_struct *t) +void vtime_init_idle(struct task_struct *t, int cpu) { unsigned long flags; write_seqlock_irqsave(&t->vtime_seqlock, flags); t->vtime_snap_whence = VTIME_SYS; - t->vtime_snap = sched_clock(); + t->vtime_snap = sched_clock_cpu(cpu); write_sequnlock_irqrestore(&t->vtime_seqlock, flags); } From 521921bad1192fb1b8f9b6a5aa673635848b8b5f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 16 May 2013 01:21:38 +0200 Subject: [PATCH 2/4] kvm: Move guest entry/exit APIs to context_tracking The kvm_host.h header file doesn't handle well inclusion when archs don't support KVM. This results in build crashes for such archs when they want to implement context tracking because this subsystem includes kvm_host.h in order to implement the guest_enter/exit APIs but it doesn't handle KVM off case. To fix this, move the guest_enter()/guest_exit() declarations and generic implementation to the context tracking headers. These generic APIs actually belong to this subsystem, besides other domains boundary tracking like user_enter() et al. KVM now properly becomes a user of this library, not the other buggy way around. Reported-by: Kevin Hilman Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Kevin Hilman Cc: Marcelo Tosatti Cc: Gleb Natapov Signed-off-by: Ingo Molnar --- include/linux/context_tracking.h | 35 ++++++++++++++++++++++++++++++ include/linux/kvm_host.h | 37 +------------------------------- kernel/context_tracking.c | 1 - 3 files changed, 36 insertions(+), 37 deletions(-) diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 365f4a61bf04..fc09d7b0dacf 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -3,6 +3,7 @@ #include #include +#include #include struct context_tracking { @@ -19,6 +20,26 @@ struct context_tracking { } state; }; +static inline void __guest_enter(void) +{ + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags |= PF_VCPU; +} + +static inline void __guest_exit(void) +{ + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags &= ~PF_VCPU; +} + #ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); @@ -35,6 +56,9 @@ static inline bool context_tracking_active(void) extern void user_enter(void); extern void user_exit(void); +extern void guest_enter(void); +extern void guest_exit(void); + static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; @@ -57,6 +81,17 @@ extern void context_tracking_task_switch(struct task_struct *prev, static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } + +static inline void guest_enter(void) +{ + __guest_enter(); +} + +static inline void guest_exit(void) +{ + __guest_exit(); +} + static inline enum ctx_state exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline void context_tracking_task_switch(struct task_struct *prev, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f0eea07d2c2b..8db53cfaccdb 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -760,42 +761,6 @@ static inline int kvm_iommu_unmap_guest(struct kvm *kvm) } #endif -static inline void __guest_enter(void) -{ - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system(current); - current->flags |= PF_VCPU; -} - -static inline void __guest_exit(void) -{ - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system(current); - current->flags &= ~PF_VCPU; -} - -#ifdef CONFIG_CONTEXT_TRACKING -extern void guest_enter(void); -extern void guest_exit(void); - -#else /* !CONFIG_CONTEXT_TRACKING */ -static inline void guest_enter(void) -{ - __guest_enter(); -} - -static inline void guest_exit(void) -{ - __guest_exit(); -} -#endif /* !CONFIG_CONTEXT_TRACKING */ - static inline void kvm_guest_enter(void) { unsigned long flags; diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 65349f07b878..85bdde1137eb 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -15,7 +15,6 @@ */ #include -#include #include #include #include From 1a7f829f094dd7951e7d46c571a18080e455a436 Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Fri, 17 May 2013 16:44:04 +0800 Subject: [PATCH 3/4] nohz: Fix notifier return val that enforce timekeeping In tick_nohz_cpu_down_callback() if the cpu is the one handling timekeeping, we must return something that stops the CPU_DOWN_PREPARE notifiers and then start notify CPU_DOWN_FAILED on the already called notifier call backs. However traditional errno values are not handled by the notifier unless these are encapsulated using errno_to_notifier(). Hence the current -EINVAL is misinterpreted and converted to junk after notifier_to_errno(), leaving the notifier subsystem to random behaviour such as eventually allowing the cpu to go down. Fix this by using the standard NOTIFY_BAD instead. Signed-off-by: Li Zhong Reviewed-by: Srivatsa S. Bhat Acked-by: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- kernel/time/tick-sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index f4208138fbf4..0cf1c1453181 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -306,7 +306,7 @@ static int __cpuinit tick_nohz_cpu_down_callback(struct notifier_block *nfb, * we can't safely shutdown that CPU. */ if (have_nohz_full_mask && tick_do_timer_cpu == cpu) - return -EINVAL; + return NOTIFY_BAD; break; } return NOTIFY_OK; From f5d00c1f9adb350c24c5301600f7bf2da99b66de Mon Sep 17 00:00:00 2001 From: Jiri Bohac Date: Tue, 28 May 2013 15:29:03 +0200 Subject: [PATCH 4/4] tick: Remove useless timekeeping duty attribution to broadcast source Since 7300711e ("clockevents: broadcast fixup possible waiters"), the timekeeping duty is assigned to the CPU that handles the tick broadcast clock device by the time it is set in one shot mode. This is an issue in full dynticks mode where the timekeeping duty must stay handled by the boot CPU for now. Otherwise it prevents secondary CPUs from offlining and this breaks suspend/shutdown/reboot/... As it appears there is no reason for this timekeeping duty to be moved to the broadcast CPU, besides nothing prevent it from being later re-assigned to another target, let's simply remove it. Signed-off-by: Jiri Bohac Reported-by: Steven Rostedt Acked-by: Thomas Gleixner Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Borislav Petkov Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- kernel/time/tick-broadcast.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 0c739423b0f9..b4c245580b79 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -698,10 +698,6 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) bc->event_handler = tick_handle_oneshot_broadcast; - /* Take the do_timer update */ - if (!tick_nohz_full_cpu(cpu)) - tick_do_timer_cpu = cpu; - /* * We must be careful here. There might be other CPUs * waiting for periodic broadcast. We need to set the