From 1cc4fff0b360aeffeedb7d6db5089d88dd861700 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 22 Dec 2008 02:24:48 +0100 Subject: [PATCH 01/11] hrtimers: increase clock min delta threshold while interrupt hanging Impact: avoid timer IRQ hanging slow systems While using the function graph tracer on a virtualized system, the hrtimer_interrupt can hang the system on an infinite loop. This can be caused in several situations: - the hardware is very slow and HZ is set too high - something intrusive is slowing the system down (tracing under emulation) ... and the next clock events to program are always before the current time. This patch implements a reasonable compromise: if such a situation is detected, we share the CPUs time in 1/4 to process the hrtimer interrupts. This is enough to let the system running without serious starvation. It has been successfully tested under VirtualBox with 1000 HZ and 100 HZ with function graph tracer launched. On both cases, the clock events were increased until about 25 ms periodic ticks, which means 40 HZ. So we change a hard to debug hang into a warning message and a system that still manages to limp along. Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- kernel/hrtimer.c | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index bda9cb924276..c2a69b89ac61 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1171,6 +1171,29 @@ static void __run_hrtimer(struct hrtimer *timer) #ifdef CONFIG_HIGH_RES_TIMERS +static int force_clock_reprogram; + +/* + * After 5 iteration's attempts, we consider that hrtimer_interrupt() + * is hanging, which could happen with something that slows the interrupt + * such as the tracing. Then we force the clock reprogramming for each future + * hrtimer interrupts to avoid infinite loops and use the min_delta_ns + * threshold that we will overwrite. + * The next tick event will be scheduled to 3 times we currently spend on + * hrtimer_interrupt(). This gives a good compromise, the cpus will spend + * 1/4 of their time to process the hrtimer interrupts. This is enough to + * let it running without serious starvation. + */ + +static inline void +hrtimer_interrupt_hanging(struct clock_event_device *dev, + ktime_t try_time) +{ + force_clock_reprogram = 1; + dev->min_delta_ns = (unsigned long)try_time.tv64 * 3; + printk(KERN_WARNING "hrtimer: interrupt too slow, " + "forcing clock min delta to %lu ns\n", dev->min_delta_ns); +} /* * High resolution timer interrupt * Called with interrupts disabled @@ -1180,6 +1203,7 @@ void hrtimer_interrupt(struct clock_event_device *dev) struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); struct hrtimer_clock_base *base; ktime_t expires_next, now; + int nr_retries = 0; int i; BUG_ON(!cpu_base->hres_active); @@ -1187,6 +1211,10 @@ void hrtimer_interrupt(struct clock_event_device *dev) dev->next_event.tv64 = KTIME_MAX; retry: + /* 5 retries is enough to notice a hang */ + if (!(++nr_retries % 5)) + hrtimer_interrupt_hanging(dev, ktime_sub(ktime_get(), now)); + now = ktime_get(); expires_next.tv64 = KTIME_MAX; @@ -1239,7 +1267,7 @@ void hrtimer_interrupt(struct clock_event_device *dev) /* Reprogramming necessary ? */ if (expires_next.tv64 != KTIME_MAX) { - if (tick_program_event(expires_next, 0)) + if (tick_program_event(expires_next, force_clock_reprogram)) goto retry; } } From 5762ba1873b0bb9faa631aaa02f533c2b9837f82 Mon Sep 17 00:00:00 2001 From: Sebastien Dugue Date: Mon, 1 Dec 2008 14:09:07 +0100 Subject: [PATCH 02/11] hrtimers: allow the hot-unplugging of all cpus Impact: fix CPU hotplug hang on Power6 testbox On architectures that support offlining all cpus (at least powerpc/pseries), hot-unpluging the tick_do_timer_cpu can result in a system hang. This comes from the fact that if the cpu going down happens to be the cpu doing the tick, then as the tick_do_timer_cpu handover happens after the cpu is dead (via the CPU_DEAD notification), we're left without ticks, jiffies are frozen and any task relying on timers (msleep, ...) is stuck. That's particularly the case for the cpu looping in __cpu_die() waiting for the dying cpu to be dead. This patch addresses this by having the tick_do_timer_cpu handover happen earlier during the CPU_DYING notification. For this, a new clockevent notification type is introduced (CLOCK_EVT_NOTIFY_CPU_DYING) which is triggered in hrtimer_cpu_notify(). Signed-off-by: Sebastien Dugue Cc: Signed-off-by: Ingo Molnar --- include/linux/clockchips.h | 1 + kernel/hrtimer.c | 4 ++++ kernel/time/tick-common.c | 26 +++++++++++++++++++------- 3 files changed, 24 insertions(+), 7 deletions(-) diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index ed3a5d473e52..c6de413c5dd1 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -36,6 +36,7 @@ enum clock_event_nofitiers { CLOCK_EVT_NOTIFY_BROADCAST_EXIT, CLOCK_EVT_NOTIFY_SUSPEND, CLOCK_EVT_NOTIFY_RESUME, + CLOCK_EVT_NOTIFY_CPU_DYING, CLOCK_EVT_NOTIFY_CPU_DEAD, }; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index c2a69b89ac61..61cb933395ba 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1609,6 +1609,10 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self, break; #ifdef CONFIG_HOTPLUG_CPU + case CPU_DYING: + case CPU_DYING_FROZEN: + clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu); + break; case CPU_DEAD: case CPU_DEAD_FROZEN: { diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index df12434b43ca..457d281258ee 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -273,6 +273,21 @@ static int tick_check_new_device(struct clock_event_device *newdev) return ret; } +/* + * Transfer the do_timer job away from a dying cpu. + * + * Called with interrupts disabled. + */ +static void tick_handover_do_timer(int *cpup) +{ + if (*cpup == tick_do_timer_cpu) { + int cpu = first_cpu(cpu_online_map); + + tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu : + TICK_DO_TIMER_NONE; + } +} + /* * Shutdown an event device on a given cpu: * @@ -297,13 +312,6 @@ static void tick_shutdown(unsigned int *cpup) clockevents_exchange_device(dev, NULL); td->evtdev = NULL; } - /* Transfer the do_timer job away from this cpu */ - if (*cpup == tick_do_timer_cpu) { - int cpu = first_cpu(cpu_online_map); - - tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu : - TICK_DO_TIMER_NONE; - } spin_unlock_irqrestore(&tick_device_lock, flags); } @@ -357,6 +365,10 @@ static int tick_notify(struct notifier_block *nb, unsigned long reason, tick_broadcast_oneshot_control(reason); break; + case CLOCK_EVT_NOTIFY_CPU_DYING: + tick_handover_do_timer(dev); + break; + case CLOCK_EVT_NOTIFY_CPU_DEAD: tick_shutdown_broadcast_oneshot(dev); tick_shutdown_broadcast(dev); From 42bb8cc5e81028e217105299001070d57eb84ad7 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 9 Jan 2009 12:17:40 -0800 Subject: [PATCH 03/11] x86: hpet: allow force enable on ICH10 HPET Intel "Smackover" x58 BIOS don't have HPET enabled in the BIOS, so allow to force enable it at least. The register layout is the same as in other recent ICHs, so all the code can be reused. Using numerical PCI-ID because it's unlikely the PCI-ID will be used anywhere else. Signed-off-by: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- arch/x86/kernel/quirks.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 309949e9e1c1..697d1b78cfbf 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -172,7 +172,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH8_4, ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH9_7, ich_force_enable_hpet); - +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x3a16, /* ICH10 */ + ich_force_enable_hpet); static struct pci_dev *cached_dev; From 2d68259db26ad57fd9643f1c69b5181ec9836ca9 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Fri, 16 Jan 2009 17:14:38 +0900 Subject: [PATCH 04/11] clockevents: let set_mode() setup delta information Allow the set_mode() clockevent callback to decide and fill in delta details such as shift, mult, max_delta_ns and min_delta_ns. With this change the clockevent can be registered without delta details which allows us to keep the parent clock disabled until the clockevent gets setup using set_mode(). Letting set_mode() fill in or update delta details allows us to save power by disabling the parent clock while the clockevent is unused. This may however make the parent clock rate change, so next time the clockevent gets enabled we need let set_mode() to update the detla details accordingly. Doing it at registration time is not enough. Furthermore, the delta details seem unused in the case of periodic-only clockevent drivers, so this change also allows registration of such drivers without the delta details filled in. Signed-off-by: Magnus Damm Signed-off-by: Thomas Gleixner --- kernel/time/clockevents.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index ea2f48af83cf..d13be216a790 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -68,6 +68,17 @@ void clockevents_set_mode(struct clock_event_device *dev, if (dev->mode != mode) { dev->set_mode(mode, dev); dev->mode = mode; + + /* + * A nsec2cyc multiplicator of 0 is invalid and we'd crash + * on it, so fix it up and emit a warning: + */ + if (mode == CLOCK_EVT_MODE_ONESHOT) { + if (unlikely(!dev->mult)) { + dev->mult = 1; + WARN_ON(1); + } + } } } @@ -168,15 +179,6 @@ void clockevents_register_device(struct clock_event_device *dev) BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); BUG_ON(!dev->cpumask); - /* - * A nsec2cyc multiplicator of 0 is invalid and we'd crash - * on it, so fix it up and emit a warning: - */ - if (unlikely(!dev->mult)) { - dev->mult = 1; - WARN_ON(1); - } - spin_lock(&clockevents_lock); list_add(&dev->list, &clockevent_devices); From 6626bff24578753808c8b5bd4f1619e14e980f0f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Jan 2009 11:31:36 +0100 Subject: [PATCH 05/11] hrtimer: prevent negative expiry value after clock_was_set() Impact: prevent false positive WARN_ON() in clockevents_program_event() clock_was_set() changes the base->offset of CLOCK_REALTIME and enforces the reprogramming of the clockevent device to expire timers which are based on CLOCK_REALTIME. If the clock change is large enough then the subtraction of the timer expiry value and base->offset can become negative which triggers the warning in clockevents_program_event(). Check the subtraction result and set a negative value to 0. Signed-off-by: Thomas Gleixner --- kernel/hrtimer.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 2c40ee8f44bd..d71cef25954b 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -501,6 +501,13 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base) continue; timer = rb_entry(base->first, struct hrtimer, node); expires = ktime_sub(hrtimer_get_expires(timer), base->offset); + /* + * clock_was_set() has changed base->offset so the + * result might be negative. Fix it up to prevent a + * false positive in clockevents_program_event() + */ + if (expires.tv64 < 0) + expires.tv64 = 0; if (expires.tv64 < cpu_base->expires_next.tv64) cpu_base->expires_next = expires; } From 483b4ee60edbefdfbff0dd538fb81f368d9e7c0d Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Wed, 4 Feb 2009 11:59:44 -0800 Subject: [PATCH 06/11] sched: fix nohz load balancer on cpu offline Christian Borntraeger reports: > After a logical cpu offline, even on a complete idle system, there > is one cpu with full ticks. It turns out that nohz.cpu_mask has the > the offlined cpu still set. > > In select_nohz_load_balancer() we check if the system is completely > idle to turn of load balancing. We compare cpu_online_map with > nohz.cpu_mask. Since cpu_online_map is updated on cpu unplug, > but nohz.cpu_mask is not, the check fails and the scheduler believes > that we need an "idle load balancer" even on a fully idle system. > Since the ilb cpu does not deactivate the timer tick this breaks NOHZ. Fix the select_nohz_load_balancer() to not set the nohz.cpu_mask while a cpu is going offline. Reported-by: Christian Borntraeger Signed-off-by: Suresh Siddha Tested-by: Christian Borntraeger Signed-off-by: Ingo Molnar --- kernel/sched.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 242d0d47a70d..e1fc67d0674c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3890,19 +3890,24 @@ int select_nohz_load_balancer(int stop_tick) int cpu = smp_processor_id(); if (stop_tick) { - cpumask_set_cpu(cpu, nohz.cpu_mask); cpu_rq(cpu)->in_nohz_recently = 1; - /* - * If we are going offline and still the leader, give up! - */ - if (!cpu_active(cpu) && - atomic_read(&nohz.load_balancer) == cpu) { + if (!cpu_active(cpu)) { + if (atomic_read(&nohz.load_balancer) != cpu) + return 0; + + /* + * If we are going offline and still the leader, + * give up! + */ if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) BUG(); + return 0; } + cpumask_set_cpu(cpu, nohz.cpu_mask); + /* time for ilb owner also to sleep */ if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { if (atomic_read(&nohz.load_balancer) == cpu) From a6a95406c676ffe4f9dee708eb404a17c69f7fdd Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 4 Feb 2009 13:40:31 +0300 Subject: [PATCH 07/11] x86: fix hpet timer reinit for x86_64 There's a small problem with hpet_rtc_reinit function - it checks for the: hpet_readl(HPET_COUNTER) - hpet_t1_cmp > 0 to continue increasing both the HPET_T1_CMP (register) and the hpet_t1_cmp (variable). But since the HPET_COUNTER is always 32-bit, if the hpet_t1_cmp is 64-bit this condition will always be FALSE once the latter hits the 32-bit boundary, and we can have a situation, when we don't increase the HPET_T1_CMP register high enough. The result - timer stops ticking, since HPET_T1_CMP becomes less, than the COUNTER and never increased again. The solution is (based on Linus's suggestion) to not compare 64-bits (on 64-bit x86), but to do the comparison on 32-bit signed integers. Reported-by: Kirill Korotaev Signed-off-by: Pavel Emelyanov Signed-off-by: Ingo Molnar --- arch/x86/kernel/hpet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 64d5ad0b8add..c761f914430a 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1075,7 +1075,7 @@ static void hpet_rtc_timer_reinit(void) hpet_t1_cmp += delta; hpet_writel(hpet_t1_cmp, HPET_T1_CMP); lost_ints++; - } while ((long)(hpet_readl(HPET_COUNTER) - hpet_t1_cmp) > 0); + } while ((s32)(hpet_readl(HPET_COUNTER) - hpet_t1_cmp) > 0); if (lost_ints) { if (hpet_rtc_flags & RTC_PIE) From 32bd671d6cbeda60dc73be77fa2b9037d9a9bfa0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 5 Feb 2009 12:24:15 +0100 Subject: [PATCH 08/11] signal: re-add dead task accumulation stats. We're going to split the process wide cpu accounting into two parts: - clocks; which can take all the time they want since they run from user context. - timers; which need constant time tracing but can affort the overhead because they're default off -- and rare. The clock readout will go back to a full sum of the thread group, for this we need to re-add the exit stats that were removed in the initial itimer rework (f06febc9: timers: fix itimer/many thread hang). Furthermore, since that full sum can be rather slow for large thread groups and we have the complete dead task stats, revert the do_notify_parent time computation. Signed-off-by: Peter Zijlstra Reviewed-by: Ingo Molnar Signed-off-by: Ingo Molnar --- include/linux/sched.h | 10 +++++++++- kernel/exit.c | 3 +++ kernel/fork.c | 3 ++- kernel/signal.c | 8 ++++---- 4 files changed, 18 insertions(+), 6 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 2127e959e0f4..2e0646a30314 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -559,7 +559,7 @@ struct signal_struct { * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ - cputime_t cutime, cstime; + cputime_t utime, stime, cutime, cstime; cputime_t gtime; cputime_t cgtime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; @@ -567,6 +567,14 @@ struct signal_struct { unsigned long inblock, oublock, cinblock, coublock; struct task_io_accounting ioac; + /* + * Cumulative ns of schedule CPU time fo dead threads in the + * group, not including a zombie group leader, (This only differs + * from jiffies_to_ns(utime + stime) if sched_clock uses something + * other than jiffies.) + */ + unsigned long long sum_sched_runtime; + /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs diff --git a/kernel/exit.c b/kernel/exit.c index f80dec3f1875..efd30ccf3858 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -118,6 +118,8 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ + sig->utime = cputime_add(sig->utime, task_utime(tsk)); + sig->stime = cputime_add(sig->stime, task_stime(tsk)); sig->gtime = cputime_add(sig->gtime, task_gtime(tsk)); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; @@ -126,6 +128,7 @@ static void __exit_signal(struct task_struct *tsk) sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); + sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig = NULL; /* Marker for below. */ } diff --git a/kernel/fork.c b/kernel/fork.c index 242a706e7721..e8e854a04ad2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -851,13 +851,14 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->tty_old_pgrp = NULL; sig->tty = NULL; - sig->cutime = sig->cstime = cputime_zero; + sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; sig->gtime = cputime_zero; sig->cgtime = cputime_zero; sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; task_io_accounting_init(&sig->ioac); + sig->sum_sched_runtime = 0; taskstats_tgid_init(sig); task_lock(current->group_leader); diff --git a/kernel/signal.c b/kernel/signal.c index b6b36768b758..2a74fe87c0dd 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1367,7 +1367,6 @@ int do_notify_parent(struct task_struct *tsk, int sig) struct siginfo info; unsigned long flags; struct sighand_struct *psig; - struct task_cputime cputime; int ret = sig; BUG_ON(sig == -1); @@ -1397,9 +1396,10 @@ int do_notify_parent(struct task_struct *tsk, int sig) info.si_uid = __task_cred(tsk)->uid; rcu_read_unlock(); - thread_group_cputime(tsk, &cputime); - info.si_utime = cputime_to_jiffies(cputime.utime); - info.si_stime = cputime_to_jiffies(cputime.stime); + info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime, + tsk->signal->utime)); + info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime, + tsk->signal->stime)); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) From 4cd4c1b40d40447fb5e7ba80746c6d7ba91d7a53 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 5 Feb 2009 12:24:16 +0100 Subject: [PATCH 09/11] timers: split process wide cpu clocks/timers Change the process wide cpu timers/clocks so that we: 1) don't mess up the kernel with too many threads, 2) don't have a per-cpu allocation for each process, 3) have no impact when not used. In order to accomplish this we're going to split it into two parts: - clocks; which can take all the time they want since they run from user context -- ie. sys_clock_gettime(CLOCK_PROCESS_CPUTIME_ID) - timers; which need constant time sampling but since they're explicity used, the user can pay the overhead. The clock readout will go back to a full sum of the thread group, while the timers will run of a global 'clock' that only runs when needed, so only programs that make use of the facility pay the price. Signed-off-by: Peter Zijlstra Reviewed-by: Ingo Molnar Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 11 +++-- include/linux/sched.h | 54 ++++++++++++---------- kernel/itimer.c | 4 +- kernel/posix-cpu-timers.c | 95 +++++++++++++++++++++++++++++++++++++-- kernel/sched_stats.h | 45 +++++++++++-------- 5 files changed, 155 insertions(+), 54 deletions(-) diff --git a/include/linux/init_task.h b/include/linux/init_task.h index ea0ea1a4c36f..e752d973fa21 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -48,12 +48,11 @@ extern struct fs_struct init_fs; .posix_timers = LIST_HEAD_INIT(sig.posix_timers), \ .cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \ .rlim = INIT_RLIMITS, \ - .cputime = { .totals = { \ - .utime = cputime_zero, \ - .stime = cputime_zero, \ - .sum_exec_runtime = 0, \ - .lock = __SPIN_LOCK_UNLOCKED(sig.cputime.totals.lock), \ - }, }, \ + .cputimer = { \ + .cputime = INIT_CPUTIME, \ + .running = 0, \ + .lock = __SPIN_LOCK_UNLOCKED(sig.cputimer.lock), \ + }, \ } extern struct nsproxy init_nsproxy; diff --git a/include/linux/sched.h b/include/linux/sched.h index 2e0646a30314..082d7619b3a1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -443,7 +443,6 @@ struct pacct_struct { * @utime: time spent in user mode, in &cputime_t units * @stime: time spent in kernel mode, in &cputime_t units * @sum_exec_runtime: total time spent on the CPU, in nanoseconds - * @lock: lock for fields in this struct * * This structure groups together three kinds of CPU time that are * tracked for threads and thread groups. Most things considering @@ -454,23 +453,33 @@ struct task_cputime { cputime_t utime; cputime_t stime; unsigned long long sum_exec_runtime; - spinlock_t lock; }; /* Alternate field names when used to cache expirations. */ #define prof_exp stime #define virt_exp utime #define sched_exp sum_exec_runtime +#define INIT_CPUTIME \ + (struct task_cputime) { \ + .utime = cputime_zero, \ + .stime = cputime_zero, \ + .sum_exec_runtime = 0, \ + } + /** - * struct thread_group_cputime - thread group interval timer counts - * @totals: thread group interval timers; substructure for - * uniprocessor kernel, per-cpu for SMP kernel. + * struct thread_group_cputimer - thread group interval timer counts + * @cputime: thread group interval timers. + * @running: non-zero when there are timers running and + * @cputime receives updates. + * @lock: lock for fields in this struct. * * This structure contains the version of task_cputime, above, that is - * used for thread group CPU clock calculations. + * used for thread group CPU timer calculations. */ -struct thread_group_cputime { - struct task_cputime totals; +struct thread_group_cputimer { + struct task_cputime cputime; + int running; + spinlock_t lock; }; /* @@ -519,10 +528,10 @@ struct signal_struct { cputime_t it_prof_incr, it_virt_incr; /* - * Thread group totals for process CPU clocks. - * See thread_group_cputime(), et al, for details. + * Thread group totals for process CPU timers. + * See thread_group_cputimer(), et al, for details. */ - struct thread_group_cputime cputime; + struct thread_group_cputimer cputimer; /* Earliest-expiration cache. */ struct task_cputime cputime_expires; @@ -2191,27 +2200,26 @@ static inline int spin_needbreak(spinlock_t *lock) /* * Thread group CPU time accounting. */ +void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times); static inline -void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) +void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) { - struct task_cputime *totals = &tsk->signal->cputime.totals; + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; unsigned long flags; - spin_lock_irqsave(&totals->lock, flags); - *times = *totals; - spin_unlock_irqrestore(&totals->lock, flags); + WARN_ON(!cputimer->running); + + spin_lock_irqsave(&cputimer->lock, flags); + *times = cputimer->cputime; + spin_unlock_irqrestore(&cputimer->lock, flags); } static inline void thread_group_cputime_init(struct signal_struct *sig) { - sig->cputime.totals = (struct task_cputime){ - .utime = cputime_zero, - .stime = cputime_zero, - .sum_exec_runtime = 0, - }; - - spin_lock_init(&sig->cputime.totals.lock); + sig->cputimer.cputime = INIT_CPUTIME; + spin_lock_init(&sig->cputimer.lock); + sig->cputimer.running = 0; } static inline void thread_group_cputime_free(struct signal_struct *sig) diff --git a/kernel/itimer.c b/kernel/itimer.c index 6a5fe93dd8bd..58762f7077ec 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -62,7 +62,7 @@ int do_getitimer(int which, struct itimerval *value) struct task_cputime cputime; cputime_t utime; - thread_group_cputime(tsk, &cputime); + thread_group_cputimer(tsk, &cputime); utime = cputime.utime; if (cputime_le(cval, utime)) { /* about to fire */ cval = jiffies_to_cputime(1); @@ -82,7 +82,7 @@ int do_getitimer(int which, struct itimerval *value) struct task_cputime times; cputime_t ptime; - thread_group_cputime(tsk, ×); + thread_group_cputimer(tsk, ×); ptime = cputime_add(times.utime, times.stime); if (cputime_le(cval, ptime)) { /* about to fire */ cval = jiffies_to_cputime(1); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index fa07da94d7be..db107c9bbc05 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -230,6 +230,37 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, return 0; } +void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) +{ + struct sighand_struct *sighand; + struct signal_struct *sig; + struct task_struct *t; + + *times = INIT_CPUTIME; + + rcu_read_lock(); + sighand = rcu_dereference(tsk->sighand); + if (!sighand) + goto out; + + sig = tsk->signal; + + t = tsk; + do { + times->utime = cputime_add(times->utime, t->utime); + times->stime = cputime_add(times->stime, t->stime); + times->sum_exec_runtime += t->se.sum_exec_runtime; + + t = next_thread(t); + } while (t != tsk); + + times->utime = cputime_add(times->utime, sig->utime); + times->stime = cputime_add(times->stime, sig->stime); + times->sum_exec_runtime += sig->sum_sched_runtime; +out: + rcu_read_unlock(); +} + /* * Sample a process (thread group) clock for the given group_leader task. * Must be called with tasklist_lock held for reading. @@ -475,6 +506,29 @@ static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now) now); } +/* + * Enable the process wide cpu timer accounting. + * + * serialized using ->sighand->siglock + */ +static void start_process_timers(struct task_struct *tsk) +{ + tsk->signal->cputimer.running = 1; + barrier(); +} + +/* + * Release the process wide timer accounting -- timer stops ticking when + * nobody cares about it. + * + * serialized using ->sighand->siglock + */ +static void stop_process_timers(struct task_struct *tsk) +{ + tsk->signal->cputimer.running = 0; + barrier(); +} + /* * Insert the timer on the appropriate list before any timers that * expire later. This must be called with the tasklist_lock held @@ -495,6 +549,9 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) BUG_ON(!irqs_disabled()); spin_lock(&p->sighand->siglock); + if (!CPUCLOCK_PERTHREAD(timer->it_clock)) + start_process_timers(p); + listpos = head; if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) { list_for_each_entry(next, head, entry) { @@ -987,13 +1044,15 @@ static void check_process_timers(struct task_struct *tsk, sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY && list_empty(&timers[CPUCLOCK_VIRT]) && cputime_eq(sig->it_virt_expires, cputime_zero) && - list_empty(&timers[CPUCLOCK_SCHED])) + list_empty(&timers[CPUCLOCK_SCHED])) { + stop_process_timers(tsk); return; + } /* * Collect the current process totals. */ - thread_group_cputime(tsk, &cputime); + thread_group_cputimer(tsk, &cputime); utime = cputime.utime; ptime = cputime_add(utime, cputime.stime); sum_sched_runtime = cputime.sum_exec_runtime; @@ -1259,7 +1318,7 @@ static inline int fastpath_timer_check(struct task_struct *tsk) if (!task_cputime_zero(&sig->cputime_expires)) { struct task_cputime group_sample; - thread_group_cputime(tsk, &group_sample); + thread_group_cputimer(tsk, &group_sample); if (task_cputime_expired(&group_sample, &sig->cputime_expires)) return 1; } @@ -1328,6 +1387,33 @@ void run_posix_cpu_timers(struct task_struct *tsk) } } +/* + * Sample a process (thread group) timer for the given group_leader task. + * Must be called with tasklist_lock held for reading. + */ +static int cpu_timer_sample_group(const clockid_t which_clock, + struct task_struct *p, + union cpu_time_count *cpu) +{ + struct task_cputime cputime; + + thread_group_cputimer(p, &cputime); + switch (CPUCLOCK_WHICH(which_clock)) { + default: + return -EINVAL; + case CPUCLOCK_PROF: + cpu->cpu = cputime_add(cputime.utime, cputime.stime); + break; + case CPUCLOCK_VIRT: + cpu->cpu = cputime.utime; + break; + case CPUCLOCK_SCHED: + cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p); + break; + } + return 0; +} + /* * Set one of the process-wide special case CPU timers. * The tsk->sighand->siglock must be held by the caller. @@ -1341,7 +1427,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, struct list_head *head; BUG_ON(clock_idx == CPUCLOCK_SCHED); - cpu_clock_sample_group(clock_idx, tsk, &now); + start_process_timers(tsk); + cpu_timer_sample_group(clock_idx, tsk, &now); if (oldval) { if (!cputime_eq(*oldval, cputime_zero)) { diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 8ab0cef8ecab..a8f93dd374e1 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -296,19 +296,21 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) static inline void account_group_user_time(struct task_struct *tsk, cputime_t cputime) { - struct task_cputime *times; - struct signal_struct *sig; + struct thread_group_cputimer *cputimer; /* tsk == current, ensure it is safe to use ->signal */ if (unlikely(tsk->exit_state)) return; - sig = tsk->signal; - times = &sig->cputime.totals; + cputimer = &tsk->signal->cputimer; - spin_lock(×->lock); - times->utime = cputime_add(times->utime, cputime); - spin_unlock(×->lock); + if (!cputimer->running) + return; + + spin_lock(&cputimer->lock); + cputimer->cputime.utime = + cputime_add(cputimer->cputime.utime, cputime); + spin_unlock(&cputimer->lock); } /** @@ -324,19 +326,21 @@ static inline void account_group_user_time(struct task_struct *tsk, static inline void account_group_system_time(struct task_struct *tsk, cputime_t cputime) { - struct task_cputime *times; - struct signal_struct *sig; + struct thread_group_cputimer *cputimer; /* tsk == current, ensure it is safe to use ->signal */ if (unlikely(tsk->exit_state)) return; - sig = tsk->signal; - times = &sig->cputime.totals; + cputimer = &tsk->signal->cputimer; - spin_lock(×->lock); - times->stime = cputime_add(times->stime, cputime); - spin_unlock(×->lock); + if (!cputimer->running) + return; + + spin_lock(&cputimer->lock); + cputimer->cputime.stime = + cputime_add(cputimer->cputime.stime, cputime); + spin_unlock(&cputimer->lock); } /** @@ -352,7 +356,7 @@ static inline void account_group_system_time(struct task_struct *tsk, static inline void account_group_exec_runtime(struct task_struct *tsk, unsigned long long ns) { - struct task_cputime *times; + struct thread_group_cputimer *cputimer; struct signal_struct *sig; sig = tsk->signal; @@ -361,9 +365,12 @@ static inline void account_group_exec_runtime(struct task_struct *tsk, if (unlikely(!sig)) return; - times = &sig->cputime.totals; + cputimer = &sig->cputimer; - spin_lock(×->lock); - times->sum_exec_runtime += ns; - spin_unlock(×->lock); + if (!cputimer->running) + return; + + spin_lock(&cputimer->lock); + cputimer->cputime.sum_exec_runtime += ns; + spin_unlock(&cputimer->lock); } From 7d8e23df69820e6be42bcc41d441f4860e8c76f7 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 6 Feb 2009 14:57:51 +0100 Subject: [PATCH 10/11] timers: split process wide cpu clocks/timers, remove spurious warning Mike Galbraith reported that the new warning in thread_group_cputimer() triggers en masse with Amarok running. Oleg Nesterov observed: Can't fastpath_timer_check()->thread_group_cputimer() have the false warning too? Suppose we had the timer, then posix_cpu_timer_del() removes this timer, but task_cputime_zero(&sig->cputime_expires) still not true. Remove the spurious debug warning. Reported-by: Mike Galbraith Explained-by: Oleg Nesterov Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 082d7619b3a1..79392916d6c9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2208,8 +2208,6 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; unsigned long flags; - WARN_ON(!cputimer->running); - spin_lock_irqsave(&cputimer->lock, flags); *times = cputimer->cputime; spin_unlock_irqrestore(&cputimer->lock, flags); From ff08f76d738d0ec0f334b187f61e160caa321d54 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 4 Feb 2009 13:40:31 +0300 Subject: [PATCH 11/11] x86: clean up hpet timer reinit Implement Linus's suggestion: introduce the hpet_cnt_ahead() helper function to compare hpet time values - like other wrapping counter comparisons are abstracted away elsewhere. (jiffies, ktime_t, etc.) Reported-by: Kirill Korotaev Signed-off-by: Pavel Emelyanov Signed-off-by: Ingo Molnar --- arch/x86/kernel/hpet.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index c761f914430a..388254f69a2a 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -897,13 +897,21 @@ static unsigned long hpet_rtc_flags; static int hpet_prev_update_sec; static struct rtc_time hpet_alarm_time; static unsigned long hpet_pie_count; -static unsigned long hpet_t1_cmp; +static u32 hpet_t1_cmp; static unsigned long hpet_default_delta; static unsigned long hpet_pie_delta; static unsigned long hpet_pie_limit; static rtc_irq_handler irq_handler; +/* + * Check that the hpet counter c1 is ahead of the c2 + */ +static inline int hpet_cnt_ahead(u32 c1, u32 c2) +{ + return (s32)(c2 - c1) < 0; +} + /* * Registers a IRQ handler. */ @@ -1075,7 +1083,7 @@ static void hpet_rtc_timer_reinit(void) hpet_t1_cmp += delta; hpet_writel(hpet_t1_cmp, HPET_T1_CMP); lost_ints++; - } while ((s32)(hpet_readl(HPET_COUNTER) - hpet_t1_cmp) > 0); + } while (!hpet_cnt_ahead(hpet_t1_cmp, hpet_readl(HPET_COUNTER))); if (lost_ints) { if (hpet_rtc_flags & RTC_PIE)