From 091d71e023557136e96f0e54f301497a3fc95dc3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 17 Jan 2009 00:10:45 +0100 Subject: PM: Fix compilation warning in kernel/power/main.c Reorder the code in kernel/power/main.c to fix compilation warning triggered by unsetting CONFIG_SUSPEND. Signed-off-by: Rafael J. Wysocki Signed-off-by: Len Brown --- kernel/power/main.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/power/main.c b/kernel/power/main.c index 239988873971..b4d219016b6c 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -57,16 +57,6 @@ int pm_notifier_call_chain(unsigned long val) #ifdef CONFIG_PM_DEBUG int pm_test_level = TEST_NONE; -static int suspend_test(int level) -{ - if (pm_test_level == level) { - printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n"); - mdelay(5000); - return 1; - } - return 0; -} - static const char * const pm_tests[__TEST_AFTER_LAST] = { [TEST_NONE] = "none", [TEST_CORE] = "core", @@ -125,14 +115,24 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr, } power_attr(pm_test); -#else /* !CONFIG_PM_DEBUG */ -static inline int suspend_test(int level) { return 0; } -#endif /* !CONFIG_PM_DEBUG */ +#endif /* CONFIG_PM_DEBUG */ #endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_SUSPEND +static int suspend_test(int level) +{ +#ifdef CONFIG_PM_DEBUG + if (pm_test_level == level) { + printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n"); + mdelay(5000); + return 1; + } +#endif /* !CONFIG_PM_DEBUG */ + return 0; +} + #ifdef CONFIG_PM_TEST_SUSPEND /* -- cgit v1.2.3 From 10b888d6cec2688e65e9e128b14bf98ecd199da2 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sat, 31 Jan 2009 14:50:07 -0800 Subject: irq, x86: fix lock status with numa_migrate_irq_desc Eric Paris reported: > I have an hp dl785g5 which is unable to successfully run > 2.6.29-0.66.rc3.fc11.x86_64 or 2.6.29-rc2-next-20090126. During bootup > (early in userspace daemons starting) I get the below BUG, which quickly > renders the machine dead. I assume it is because sparse_irq_lock never > gets released when the BUG kills that task. Adjust lock sequence when migrating a descriptor with CONFIG_NUMA_MIGRATE_IRQ_DESC enabled. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- kernel/irq/numa_migrate.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c index ecf765c6a77a..acd88356ac76 100644 --- a/kernel/irq/numa_migrate.c +++ b/kernel/irq/numa_migrate.c @@ -71,7 +71,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, desc = irq_desc_ptrs[irq]; if (desc && old_desc != desc) - goto out_unlock; + goto out_unlock; node = cpu_to_node(cpu); desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node); @@ -84,10 +84,15 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, init_copy_one_irq_desc(irq, old_desc, desc, cpu); irq_desc_ptrs[irq] = desc; + spin_unlock_irqrestore(&sparse_irq_lock, flags); /* free the old one */ free_one_irq_desc(old_desc, desc); + spin_unlock(&old_desc->lock); kfree(old_desc); + spin_lock(&desc->lock); + + return desc; out_unlock: spin_unlock_irqrestore(&sparse_irq_lock, flags); -- cgit v1.2.3 From 229c4ef8ae56d69f8dec64533bf1c7f8070c1a4a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 3 Feb 2009 20:39:04 +0100 Subject: ftrace: do_each_pid_task() needs rcu lock "ftrace: use struct pid" commit 978f3a45d9499c7a447ca7615455cefb63d44165 converted ftrace_pid_trace to "struct pid*". But we can't use do_each_pid_task() without rcu_read_lock() even if we know the pid itself can't go away (it was pinned in ftrace_pid_write). The exiting task can detach itself from this pid at any moment. Signed-off-by: Oleg Nesterov Signed-off-by: Ingo Molnar --- kernel/trace/ftrace.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 7dcf6e9f2b04..9a236ffe2aa4 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1737,9 +1737,12 @@ static void clear_ftrace_pid(struct pid *pid) { struct task_struct *p; + rcu_read_lock(); do_each_pid_task(pid, PIDTYPE_PID, p) { clear_tsk_trace_trace(p); } while_each_pid_task(pid, PIDTYPE_PID, p); + rcu_read_unlock(); + put_pid(pid); } @@ -1747,9 +1750,11 @@ static void set_ftrace_pid(struct pid *pid) { struct task_struct *p; + rcu_read_lock(); do_each_pid_task(pid, PIDTYPE_PID, p) { set_tsk_trace_trace(p); } while_each_pid_task(pid, PIDTYPE_PID, p); + rcu_read_unlock(); } static void clear_ftrace_pid_task(struct pid **pid) -- cgit v1.2.3 From 483b4ee60edbefdfbff0dd538fb81f368d9e7c0d Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Wed, 4 Feb 2009 11:59:44 -0800 Subject: 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(-) (limited to 'kernel') 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) -- cgit v1.2.3 From 32bd671d6cbeda60dc73be77fa2b9037d9a9bfa0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 5 Feb 2009 12:24:15 +0100 Subject: 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 --- kernel/exit.c | 3 +++ kernel/fork.c | 3 ++- kernel/signal.c | 8 ++++---- 3 files changed, 9 insertions(+), 5 deletions(-) (limited to 'kernel') 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) -- cgit v1.2.3 From 4cd4c1b40d40447fb5e7ba80746c6d7ba91d7a53 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 5 Feb 2009 12:24:16 +0100 Subject: 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 --- kernel/itimer.c | 4 +- kernel/posix-cpu-timers.c | 95 +++++++++++++++++++++++++++++++++++++++++++++-- kernel/sched_stats.h | 45 ++++++++++++---------- 3 files changed, 119 insertions(+), 25 deletions(-) (limited to 'kernel') 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; + + if (!cputimer->running) + return; - spin_lock(×->lock); - times->stime = cputime_add(times->stime, cputime); - spin_unlock(×->lock); + 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; + + if (!cputimer->running) + return; - spin_lock(×->lock); - times->sum_exec_runtime += ns; - spin_unlock(×->lock); + spin_lock(&cputimer->lock); + cputimer->cputime.sum_exec_runtime += ns; + spin_unlock(&cputimer->lock); } -- cgit v1.2.3 From 58763a297405024d23d8f1d0bba3e6603660c4b6 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 4 Feb 2009 15:11:58 -0800 Subject: kernel/async.c: fix printk warnings alpha: kernel/async.c: In function 'run_one_entry': kernel/async.c:141: warning: format '%lli' expects type 'long long int', but argument 2 has type 'async_cookie_t' kernel/async.c:149: warning: format '%lli' expects type 'long long int', but argument 2 has type 'async_cookie_t' kernel/async.c:149: warning: format '%lld' expects type 'long long int', but argument 4 has type 's64' kernel/async.c: In function 'async_synchronize_cookie_special': kernel/async.c:250: warning: format '%lli' expects type 'long long int', but argument 3 has type 's64' Cc: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/async.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/async.c b/kernel/async.c index 608b32b42812..67a2be71f517 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -138,15 +138,18 @@ static void run_one_entry(void) /* 3) run it (and print duration)*/ if (initcall_debug && system_state == SYSTEM_BOOTING) { - printk("calling %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current)); + printk("calling %lli_%pF @ %i\n", (long long)entry->cookie, + entry->func, task_pid_nr(current)); calltime = ktime_get(); } entry->func(entry->data, entry->cookie); if (initcall_debug && system_state == SYSTEM_BOOTING) { rettime = ktime_get(); delta = ktime_sub(rettime, calltime); - printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie, - entry->func, ktime_to_ns(delta) >> 10); + printk("initcall %lli_%pF returned 0 after %lld usecs\n", + (long long)entry->cookie, + entry->func, + (long long)ktime_to_ns(delta) >> 10); } /* 4) remove it from the running queue */ @@ -247,7 +250,8 @@ void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *r delta = ktime_sub(endtime, starttime); printk("async_continuing @ %i after %lli usec\n", - task_pid_nr(current), ktime_to_ns(delta) >> 10); + task_pid_nr(current), + (long long)ktime_to_ns(delta) >> 10); } } EXPORT_SYMBOL_GPL(async_synchronize_cookie_special); -- cgit v1.2.3 From 60fd760fb9ff7034360bab7137c917c0330628c2 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 4 Feb 2009 15:12:06 -0800 Subject: revert "rlimit: permit setting RLIMIT_NOFILE to RLIM_INFINITY" Revert commit 0c2d64fb6cae9aae480f6a46cfe79f8d7d48b59f because it causes (arguably poorly designed) existing userspace to spend interminable periods closing billions of not-open file descriptors. We could bring this back, with some sort of opt-in tunable in /proc, which defaults to "off". Peter's alanysis follows: : I spent several hours trying to get to the bottom of a serious : performance issue that appeared on one of our servers after upgrading to : 2.6.28. In the end it's what could be considered a userspace bug that : was triggered by a change in 2.6.28. Since this might also affect other : people I figured I'd at least document what I found here, and maybe we : can even do something about it: : : : So, I upgraded some of debian.org's machines to 2.6.28.1 and immediately : the team maintaining our ftp archive complained that one of their : scripts that previously ran in a few minutes still hadn't even come : close to being done after an hour or so. Downgrading to 2.6.27 fixed : that. : : Turns out that script is forking a lot and something in it or python or : whereever closes all the file descriptors it doesn't want to pass on. : That is, it starts at zero and goes up to ulimit -n/RLIMIT_NOFILE and : closes them all with a few exceptions. : : Turns out that takes a long time when your limit -n is now 2^20 (1048576). : : With 2.6.27.* the ulimit -n was the standard 1024, but with 2.6.28 it is : now a thousand times that. : : 2.6.28 included a patch titled "rlimit: permit setting RLIMIT_NOFILE to : RLIM_INFINITY" (0c2d64fb6cae9aae480f6a46cfe79f8d7d48b59f)[1] that : allows, as the title implies, to set the limit for number of files to : infinity. : : Closer investigation showed that the broken default ulimit did not apply : to "system" processes (like stuff started from init). In the end I : could establish that all processes that passed through pam_limit at one : point had the bad resource limit. : : Apparently the pam library in Debian etch (4.0) initializes the limits : to some default values when it doesn't have any settings in limit.conf : to override them. Turns out that for nofiles this is RLIM_INFINITY. : Commenting out "case RLIMIT_NOFILE" in pam_limit.c:267 of our pam : package version 0.79-5 fixes that - tho I'm not sure what side effects : that has. : : Debian lenny (the upcoming 5.0 version) doesn't have this issue as it : uses a different pam (version). Reported-by: Peter Palfrader Cc: Adam Tkac Cc: Michael Kerrisk Cc: [2.6.28.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index e7dc0e10a485..f145c415bc16 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1525,22 +1525,14 @@ SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim) return -EINVAL; if (copy_from_user(&new_rlim, rlim, sizeof(*rlim))) return -EFAULT; + if (new_rlim.rlim_cur > new_rlim.rlim_max) + return -EINVAL; old_rlim = current->signal->rlim + resource; if ((new_rlim.rlim_max > old_rlim->rlim_max) && !capable(CAP_SYS_RESOURCE)) return -EPERM; - - if (resource == RLIMIT_NOFILE) { - if (new_rlim.rlim_max == RLIM_INFINITY) - new_rlim.rlim_max = sysctl_nr_open; - if (new_rlim.rlim_cur == RLIM_INFINITY) - new_rlim.rlim_cur = sysctl_nr_open; - if (new_rlim.rlim_max > sysctl_nr_open) - return -EPERM; - } - - if (new_rlim.rlim_cur > new_rlim.rlim_max) - return -EINVAL; + if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open) + return -EPERM; retval = security_task_setrlimit(resource, &new_rlim); if (retval) -- cgit v1.2.3 From 777c6c5f1f6e757ae49ecca2ed72d6b1f523c007 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 4 Feb 2009 15:12:14 -0800 Subject: wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason Signed-off-by: Johannes Weiner Mentored-by: Oleg Nesterov Cc: Peter Zijlstra Cc: Matthew Wilcox Cc: Chuck Lever Cc: Nick Piggin Cc: Ingo Molnar Cc: ["after some testing"] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched.c | 4 ++-- kernel/wait.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++++------- 2 files changed, 54 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 242d0d47a70d..8ee437a5ec1d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4697,8 +4697,8 @@ EXPORT_SYMBOL(default_wake_function); * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns * zero in this (rare) case, and we handle it by continuing to scan the queue. */ -static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, - int nr_exclusive, int sync, void *key) +void __wake_up_common(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, int sync, void *key) { wait_queue_t *curr, *next; diff --git a/kernel/wait.c b/kernel/wait.c index cd87131f2fc2..42a2dbc181c8 100644 --- a/kernel/wait.c +++ b/kernel/wait.c @@ -91,6 +91,15 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state) } EXPORT_SYMBOL(prepare_to_wait_exclusive); +/* + * finish_wait - clean up after waiting in a queue + * @q: waitqueue waited on + * @wait: wait descriptor + * + * Sets current thread back to running state and removes + * the wait descriptor from the given waitqueue if still + * queued. + */ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait) { unsigned long flags; @@ -117,6 +126,39 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait) } EXPORT_SYMBOL(finish_wait); +/* + * abort_exclusive_wait - abort exclusive waiting in a queue + * @q: waitqueue waited on + * @wait: wait descriptor + * @state: runstate of the waiter to be woken + * @key: key to identify a wait bit queue or %NULL + * + * Sets current thread back to running state and removes + * the wait descriptor from the given waitqueue if still + * queued. + * + * Wakes up the next waiter if the caller is concurrently + * woken up through the queue. + * + * This prevents waiter starvation where an exclusive waiter + * aborts and is woken up concurrently and noone wakes up + * the next waiter. + */ +void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, + unsigned int mode, void *key) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + spin_lock_irqsave(&q->lock, flags); + if (!list_empty(&wait->task_list)) + list_del_init(&wait->task_list); + else if (waitqueue_active(q)) + __wake_up_common(q, mode, 1, 0, key); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(abort_exclusive_wait); + int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) { int ret = default_wake_function(wait, mode, sync, key); @@ -177,17 +219,20 @@ int __sched __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, int (*action)(void *), unsigned mode) { - int ret = 0; - do { + int ret; + prepare_to_wait_exclusive(wq, &q->wait, mode); - if (test_bit(q->key.bit_nr, q->key.flags)) { - if ((ret = (*action)(q->key.flags))) - break; - } + if (!test_bit(q->key.bit_nr, q->key.flags)) + continue; + ret = action(q->key.flags); + if (!ret) + continue; + abort_exclusive_wait(wq, &q->wait, mode, &q->key); + return ret; } while (test_and_set_bit(q->key.bit_nr, q->key.flags)); finish_wait(wq, &q->wait); - return ret; + return 0; } EXPORT_SYMBOL(__wait_on_bit_lock); -- cgit v1.2.3 From 04ec93fe9bc98e3bd8560f79f56fed66dfae40d5 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 6 Feb 2009 08:17:19 +0000 Subject: fork.c: fix NULL pointer dereference when nr_threads == threads-max I happened to forked lots of processes, and hit NULL pointer dereference. It is because in copy_process() after checking max_threads, 0 is returned but not -EAGAIN. The bug is introduced by "CRED: Detach the credentials from task_struct" (commit f1752eec6145c97163dbce62d17cf5d928e28a27). Signed-off-by: Li Zefan Signed-off-by: David Howells Acked-by: James Morris Signed-off-by: Linus Torvalds --- kernel/fork.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 242a706e7721..6d5dbb7a13e2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1005,6 +1005,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ + retval = -EAGAIN; if (nr_threads >= max_threads) goto bad_fork_cleanup_count; -- cgit v1.2.3 From 7a89bbc74937cd74a6bcf109cfc7c032109639be Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Mon, 19 Jan 2009 13:45:28 +0100 Subject: async: Fix running list handling. async_schedule() should pass in async_running as the running list, and run_one_entry() should put the entry to be run on the provided running list instead of always on the generic one. Reported-by: Jonathan Corbet Signed-off-by: Cornelia Huck Signed-off-by: Arjan van de Ven --- kernel/async.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/async.c b/kernel/async.c index 67a2be71f517..0c90d500ab68 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -133,7 +133,7 @@ static void run_one_entry(void) /* 2) move it to the running queue */ list_del(&entry->list); - list_add_tail(&entry->list, &async_running); + list_add_tail(&entry->list, entry->running); spin_unlock_irqrestore(&async_lock, flags); /* 3) run it (and print duration)*/ @@ -210,7 +210,7 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct l async_cookie_t async_schedule(async_func_ptr *ptr, void *data) { - return __async_schedule(ptr, data, &async_pending); + return __async_schedule(ptr, data, &async_running); } EXPORT_SYMBOL_GPL(async_schedule); -- cgit v1.2.3 From 86532d8b167e71e24da8b564348b52977b76d15f Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Mon, 19 Jan 2009 13:45:31 +0100 Subject: async: Handle kthread_run() return codes. If we fail to create the manager thread, fall back to non-fastboot. If we fail to create an async thread, try again after waiting for a bit. Signed-off-by: Cornelia Huck Signed-off-by: Arjan van de Ven --- kernel/async.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/async.c b/kernel/async.c index 0c90d500ab68..078d5ed150d1 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -54,6 +54,7 @@ asynchronous and synchronous parts of the kernel. #include #include #include +#include #include static async_cookie_t next_cookie = 1; @@ -319,7 +320,11 @@ static int async_manager_thread(void *unused) ec = atomic_read(&entry_count); while (tc < ec && tc < MAX_THREADS) { - kthread_run(async_thread, NULL, "async/%i", tc); + if (IS_ERR(kthread_run(async_thread, NULL, "async/%i", + tc))) { + msleep(100); + continue; + } atomic_inc(&thread_count); tc++; } @@ -334,7 +339,9 @@ static int async_manager_thread(void *unused) static int __init async_init(void) { if (async_enabled) - kthread_run(async_manager_thread, NULL, "async/mgr"); + if (IS_ERR(kthread_run(async_manager_thread, NULL, + "async/mgr"))) + async_enabled = 0; return 0; } -- cgit v1.2.3 From f30d5b307c694e03368ab55f2f96b0ca4131e775 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Mon, 19 Jan 2009 13:45:33 +0100 Subject: async: Add some documentation. Add some kerneldoc to the async interface. Signed-off-by: Cornelia Huck Signed-off-by: Arjan van de Ven --- kernel/async.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'kernel') diff --git a/kernel/async.c b/kernel/async.c index 078d5ed150d1..b5f0d4b94937 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -209,18 +209,43 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct l return newcookie; } +/** + * async_schedule - schedule a function for asynchronous execution + * @ptr: function to execute asynchronously + * @data: data pointer to pass to the function + * + * Returns an async_cookie_t that may be used for checkpointing later. + * Note: This function may be called from atomic or non-atomic contexts. + */ async_cookie_t async_schedule(async_func_ptr *ptr, void *data) { return __async_schedule(ptr, data, &async_running); } EXPORT_SYMBOL_GPL(async_schedule); +/** + * async_schedule_special - schedule a function for asynchronous execution with a special running queue + * @ptr: function to execute asynchronously + * @data: data pointer to pass to the function + * @running: list head to add to while running + * + * Returns an async_cookie_t that may be used for checkpointing later. + * @running may be used in the async_synchronize_*_special() functions + * to wait on a special running queue rather than on the global running + * queue. + * Note: This function may be called from atomic or non-atomic contexts. + */ async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running) { return __async_schedule(ptr, data, running); } EXPORT_SYMBOL_GPL(async_schedule_special); +/** + * async_synchronize_full - synchronize all asynchronous function calls + * + * This function waits until all asynchronous function calls have been done. + */ void async_synchronize_full(void) { do { @@ -229,12 +254,27 @@ void async_synchronize_full(void) } EXPORT_SYMBOL_GPL(async_synchronize_full); +/** + * async_synchronize_full_special - synchronize all asynchronous function calls for a running list + * @list: running list to synchronize on + * + * This function waits until all asynchronous function calls for the running + * list @list have been done. + */ void async_synchronize_full_special(struct list_head *list) { async_synchronize_cookie_special(next_cookie, list); } EXPORT_SYMBOL_GPL(async_synchronize_full_special); +/** + * async_synchronize_cookie_special - synchronize asynchronous function calls on a running list with cookie checkpointing + * @cookie: async_cookie_t to use as checkpoint + * @running: running list to synchronize on + * + * This function waits until all asynchronous function calls for the running + * list @list submitted prior to @cookie have been done. + */ void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running) { ktime_t starttime, delta, endtime; @@ -257,6 +297,13 @@ void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *r } EXPORT_SYMBOL_GPL(async_synchronize_cookie_special); +/** + * async_synchronize_cookie - synchronize asynchronous function calls with cookie checkpointing + * @cookie: async_cookie_t to use as checkpoint + * + * This function waits until all asynchronous function calls prior to @cookie + * have been done. + */ void async_synchronize_cookie(async_cookie_t cookie) { async_synchronize_cookie_special(cookie, &async_running); -- cgit v1.2.3 From 766ccb9ed406c230d13c145def08ebea1b932982 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Tue, 20 Jan 2009 15:31:31 +0100 Subject: async: Rename _special -> _domain for clarity. Rename the async_*_special() functions to async_*_domain(), which describes the purpose of these functions much better. [Broke up long lines to silence checkpatch] Signed-off-by: Cornelia Huck Signed-off-by: Arjan van de Ven --- kernel/async.c | 41 ++++++++++++++++++++++------------------- 1 file changed, 22 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/kernel/async.c b/kernel/async.c index b5f0d4b94937..e23399d88bac 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -224,22 +224,23 @@ async_cookie_t async_schedule(async_func_ptr *ptr, void *data) EXPORT_SYMBOL_GPL(async_schedule); /** - * async_schedule_special - schedule a function for asynchronous execution with a special running queue + * async_schedule_domain - schedule a function for asynchronous execution within a certain domain * @ptr: function to execute asynchronously * @data: data pointer to pass to the function - * @running: list head to add to while running + * @running: running list for the domain * * Returns an async_cookie_t that may be used for checkpointing later. - * @running may be used in the async_synchronize_*_special() functions - * to wait on a special running queue rather than on the global running - * queue. + * @running may be used in the async_synchronize_*_domain() functions + * to wait within a certain synchronization domain rather than globally. + * A synchronization domain is specified via the running queue @running to use. * Note: This function may be called from atomic or non-atomic contexts. */ -async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running) +async_cookie_t async_schedule_domain(async_func_ptr *ptr, void *data, + struct list_head *running) { return __async_schedule(ptr, data, running); } -EXPORT_SYMBOL_GPL(async_schedule_special); +EXPORT_SYMBOL_GPL(async_schedule_domain); /** * async_synchronize_full - synchronize all asynchronous function calls @@ -255,27 +256,29 @@ void async_synchronize_full(void) EXPORT_SYMBOL_GPL(async_synchronize_full); /** - * async_synchronize_full_special - synchronize all asynchronous function calls for a running list + * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain * @list: running list to synchronize on * - * This function waits until all asynchronous function calls for the running - * list @list have been done. + * This function waits until all asynchronous function calls for the + * synchronization domain specified by the running list @list have been done. */ -void async_synchronize_full_special(struct list_head *list) +void async_synchronize_full_domain(struct list_head *list) { - async_synchronize_cookie_special(next_cookie, list); + async_synchronize_cookie_domain(next_cookie, list); } -EXPORT_SYMBOL_GPL(async_synchronize_full_special); +EXPORT_SYMBOL_GPL(async_synchronize_full_domain); /** - * async_synchronize_cookie_special - synchronize asynchronous function calls on a running list with cookie checkpointing + * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing * @cookie: async_cookie_t to use as checkpoint * @running: running list to synchronize on * - * This function waits until all asynchronous function calls for the running - * list @list submitted prior to @cookie have been done. + * This function waits until all asynchronous function calls for the + * synchronization domain specified by the running list @list submitted + * prior to @cookie have been done. */ -void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running) +void async_synchronize_cookie_domain(async_cookie_t cookie, + struct list_head *running) { ktime_t starttime, delta, endtime; @@ -295,7 +298,7 @@ void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *r (long long)ktime_to_ns(delta) >> 10); } } -EXPORT_SYMBOL_GPL(async_synchronize_cookie_special); +EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain); /** * async_synchronize_cookie - synchronize asynchronous function calls with cookie checkpointing @@ -306,7 +309,7 @@ EXPORT_SYMBOL_GPL(async_synchronize_cookie_special); */ void async_synchronize_cookie(async_cookie_t cookie) { - async_synchronize_cookie_special(cookie, &async_running); + async_synchronize_cookie_domain(cookie, &async_running); } EXPORT_SYMBOL_GPL(async_synchronize_cookie); -- cgit v1.2.3 From f7de7621f07495ad14fb23a812003bcf8f6af65a Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Mon, 2 Feb 2009 13:24:34 +0100 Subject: async: use list_move_tail list.h provides a dedicated primitive for "list_del followed by list_add_tail"... list_move_tail. Signed-off-by: Arjan van de Ven Signed-off-by: Stefan Richter --- kernel/async.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/async.c b/kernel/async.c index e23399d88bac..f565891f2c9b 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -133,8 +133,7 @@ static void run_one_entry(void) entry = list_first_entry(&async_pending, struct async_entry, list); /* 2) move it to the running queue */ - list_del(&entry->list); - list_add_tail(&entry->list, entry->running); + list_move_tail(&entry->list, entry->running); spin_unlock_irqrestore(&async_lock, flags); /* 3) run it (and print duration)*/ -- cgit v1.2.3 From acd895795d35d7c6405f20301a846d16998795ec Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 9 Feb 2009 19:20:50 +0000 Subject: profiling: fix broken profiling regression Impact: fix broken /proc/profile on UP machines Commit c309b917cab55799ea489d7b5f1b77025d9f8462 "cpumask: convert kernel/profile.c" broke profiling. prof_cpu_mask was previously initialized to CPU_MASK_ALL, but left uninitialized in that commit. We need to copy cpu_possible_mask (cpu_online_mask is not enough). Signed-off-by: Hugh Dickins Signed-off-by: Ingo Molnar --- kernel/profile.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/profile.c b/kernel/profile.c index 784933acf5b8..7724e0409bae 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -114,12 +114,15 @@ int __ref profile_init(void) if (!slab_is_available()) { prof_buffer = alloc_bootmem(buffer_bytes); alloc_bootmem_cpumask_var(&prof_cpu_mask); + cpumask_copy(prof_cpu_mask, cpu_possible_mask); return 0; } if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL)) return -ENOMEM; + cpumask_copy(prof_cpu_mask, cpu_possible_mask); + prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL); if (prof_buffer) return 0; -- cgit v1.2.3 From 06eb23b1ba39c61ee5d5faeb42a097635693e370 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 9 Feb 2009 02:02:33 +0100 Subject: ptrace, x86: fix the usage of ptrace_fork() I noticed by pure accident we have ptrace_fork() and friends. This was added by "x86, bts: add fork and exit handling", commit bf53de907dfdaac178c92d774aae7370d7b97d20. I can't test this, ds_request_bts() returns -EOPNOTSUPP, but I strongly believe this needs the fix. I think something like this program int main(void) { int pid = fork(); if (!pid) { ptrace(PTRACE_TRACEME, 0, NULL, NULL); kill(getpid(), SIGSTOP); fork(); } else { struct ptrace_bts_config bts = { .flags = PTRACE_BTS_O_ALLOC, .size = 4 * 4096, }; wait(NULL); ptrace(PTRACE_SETOPTIONS, pid, NULL, PTRACE_O_TRACEFORK); ptrace(PTRACE_BTS_CONFIG, pid, &bts, sizeof(bts)); ptrace(PTRACE_CONT, pid, NULL, NULL); sleep(1); } return 0; } should crash the kernel. If the task is traced by its natural parent ptrace_reparented() returns 0 but we should clear ->btsxxx anyway. Signed-off-by: Oleg Nesterov Acked-by: Markus Metzger Signed-off-by: Ingo Molnar --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 242a706e7721..43c039d55e95 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1093,7 +1093,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif - if (unlikely(ptrace_reparented(current))) + if (unlikely(current->ptrace)) ptrace_fork(p, clone_flags); /* Perform scheduler related setup. Assign this task to a CPU. */ -- cgit v1.2.3 From 3fccfd67df79c6351a156eb25a7a514e5f39c4d9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 10 Feb 2009 16:37:31 +0100 Subject: timers: split process wide cpu clocks/timers, fix To decrease the chance of a missed enable, always enable the timer when we sample it, we'll always disable it when we find that there are no active timers in the jiffy tick. This fixes a flood of warnings reported by Mike Galbraith. Reported-by: Mike Galbraith Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/posix-cpu-timers.c | 42 ++++++++++++++---------------------------- 1 file changed, 14 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index db107c9bbc05..e5d7bfdfa7d4 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -488,7 +488,7 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk) { struct task_cputime cputime; - thread_group_cputime(tsk, &cputime); + thread_group_cputimer(tsk, &cputime); cleanup_timers(tsk->signal->cpu_timers, cputime.utime, cputime.stime, cputime.sum_exec_runtime); } @@ -506,29 +506,6 @@ 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 @@ -549,9 +526,6 @@ 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) { @@ -1021,6 +995,19 @@ static void check_thread_timers(struct task_struct *tsk, } } +static void stop_process_timers(struct task_struct *tsk) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + unsigned long flags; + + if (!cputimer->running) + return; + + spin_lock_irqsave(&cputimer->lock, flags); + cputimer->running = 0; + spin_unlock_irqrestore(&cputimer->lock, flags); +} + /* * Check for any per-thread CPU timers that have fired and move them * off the tsk->*_timers list onto the firing list. Per-thread timers @@ -1427,7 +1414,6 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, struct list_head *head; BUG_ON(clock_idx == CPUCLOCK_SCHED); - start_process_timers(tsk); cpu_timer_sample_group(clock_idx, tsk, &now); if (oldval) { -- cgit v1.2.3 From 4da94d49b2ecb0a26e716a8811c3ecc542c2a65d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 11 Feb 2009 11:30:27 +0100 Subject: timers: fix TIMER_ABSTIME for process wide cpu timers The POSIX timer interface allows for absolute time expiry values through the TIMER_ABSTIME flag, therefore we have to synchronize the timer to the clock every time we start it. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/posix-cpu-timers.c | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'kernel') diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index e5d7bfdfa7d4..2313a4cc14ea 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -261,6 +261,40 @@ out: rcu_read_unlock(); } +static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b) +{ + if (cputime_gt(b->utime, a->utime)) + a->utime = b->utime; + + if (cputime_gt(b->stime, a->stime)) + a->stime = b->stime; + + if (b->sum_exec_runtime > a->sum_exec_runtime) + a->sum_exec_runtime = b->sum_exec_runtime; +} + +void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct task_cputime sum; + unsigned long flags; + + spin_lock_irqsave(&cputimer->lock, flags); + if (!cputimer->running) { + cputimer->running = 1; + /* + * The POSIX timer interface allows for absolute time expiry + * values through the TIMER_ABSTIME flag, therefore we have + * to synchronize the timer to the clock every time we start + * it. + */ + thread_group_cputime(tsk, &sum); + update_gt_cputime(&cputimer->cputime, &sum); + } + *times = cputimer->cputime; + spin_unlock_irqrestore(&cputimer->lock, flags); +} + /* * Sample a process (thread group) clock for the given group_leader task. * Must be called with tasklist_lock held for reading. -- cgit v1.2.3 From fc631c82e1734d718ff0832558f64c8f5d185f26 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 11 Feb 2009 14:27:17 +0100 Subject: sched: revert recent sync wakeup changes Intel reported a 10% regression (mysql+sysbench) on a 16-way machine with these patches: 1596e29: sched: symmetric sync vs avg_overlap d942fb6: sched: fix sync wakeups Revert them. Reported-by: "Zhang, Yanmin" Bisected-by: Lin Ming Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 10 ---------- kernel/sched_fair.c | 11 +++++++++-- 2 files changed, 9 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index e1fc67d0674c..f11c02b86c73 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2266,16 +2266,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) if (!sched_feat(SYNC_WAKEUPS)) sync = 0; - if (!sync) { - if (current->se.avg_overlap < sysctl_sched_migration_cost && - p->se.avg_overlap < sysctl_sched_migration_cost) - sync = 1; - } else { - if (current->se.avg_overlap >= sysctl_sched_migration_cost || - p->se.avg_overlap >= sysctl_sched_migration_cost) - sync = 0; - } - #ifdef CONFIG_SMP if (sched_feat(LB_WAKEUP_UPDATE)) { struct sched_domain *sd; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index a7e50ba185ac..0566f2a03c42 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1191,15 +1191,20 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq, int idx, unsigned long load, unsigned long this_load, unsigned int imbalance) { + struct task_struct *curr = this_rq->curr; + struct task_group *tg; unsigned long tl = this_load; unsigned long tl_per_task; - struct task_group *tg; unsigned long weight; int balanced; if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS)) return 0; + if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost || + p->se.avg_overlap > sysctl_sched_migration_cost)) + sync = 0; + /* * If sync wakeup then subtract the (maximum possible) * effect of the currently running task from the load @@ -1426,7 +1431,9 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync) if (!sched_feat(WAKEUP_PREEMPT)) return; - if (sched_feat(WAKEUP_OVERLAP) && sync) { + if (sched_feat(WAKEUP_OVERLAP) && (sync || + (se->avg_overlap < sysctl_sched_migration_cost && + pse->avg_overlap < sysctl_sched_migration_cost))) { resched_task(curr); return; } -- cgit v1.2.3 From fc3501d411d34823fb9be248a95a0c44f945866f Mon Sep 17 00:00:00 2001 From: Sven Wegener Date: Wed, 11 Feb 2009 13:04:23 -0800 Subject: mm: fix dirty_bytes/dirty_background_bytes sysctls on 64bit arches We need to pass an unsigned long as the minimum, because it gets casted to an unsigned long in the sysctl handler. If we pass an int, we'll access four more bytes on 64bit arches, resulting in a random minimum value. [rientjes@google.com: fix type of `old_bytes'] Signed-off-by: Sven Wegener Cc: Peter Zijlstra Cc: Dave Chinner Cc: Christoph Lameter Cc: David Rientjes Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 790f9d785663..c5ef44ff850f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -101,6 +101,7 @@ static int two = 2; static int zero; static int one = 1; +static unsigned long one_ul = 1; static int one_hundred = 100; /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ @@ -974,7 +975,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &dirty_background_bytes_handler, .strategy = &sysctl_intvec, - .extra1 = &one, + .extra1 = &one_ul, }, { .ctl_name = VM_DIRTY_RATIO, @@ -995,7 +996,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &dirty_bytes_handler, .strategy = &sysctl_intvec, - .extra1 = &one, + .extra1 = &one_ul, }, { .procname = "dirty_writeback_centisecs", -- cgit v1.2.3 From cfebe563bd0a3ff97e1bc167123120d59c7a84db Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 11 Feb 2009 13:04:36 -0800 Subject: cgroups: fix lockdep subclasses overflow I enabled all cgroup subsystems when compiling kernel, and then: # mount -t cgroup -o net_cls xxx /mnt # mkdir /mnt/0 This showed up immediately: BUG: MAX_LOCKDEP_SUBCLASSES too low! turning off the locking correctness validator. It's caused by the cgroup hierarchy lock: for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; if (ss->root == root) mutex_lock_nested(&ss->hierarchy_mutex, i); } Now we have 9 cgroup subsystems, and the above 'i' for net_cls is 8, but MAX_LOCKDEP_SUBCLASSES is 8. This patch uses different lockdep keys for different subsystems. Signed-off-by: Li Zefan Acked-by: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 5a54ff42874e..e14db9c089b9 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2351,7 +2351,7 @@ static void cgroup_lock_hierarchy(struct cgroupfs_root *root) for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; if (ss->root == root) - mutex_lock_nested(&ss->hierarchy_mutex, i); + mutex_lock(&ss->hierarchy_mutex); } } @@ -2637,6 +2637,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) BUG_ON(!list_empty(&init_task.tasks)); mutex_init(&ss->hierarchy_mutex); + lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key); ss->active = 1; } -- cgit v1.2.3 From fb5ae64fdde29236e1a15e0366946df7060f41f2 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Fri, 13 Feb 2009 14:04:21 +0000 Subject: User namespaces: Only put the userns when we unhash the uid uids in namespaces other than init don't get a sysfs entry. For those in the init namespace, while we're waiting to remove the sysfs entry for the uid the uid is still hashed, and alloc_uid() may re-grab that uid without getting a new reference to the user_ns, which we've already put in free_user before scheduling remove_user_sysfs_dir(). Reported-and-tested-by: KOSAKI Motohiro Signed-off-by: Serge E. Hallyn Acked-by: David Howells Tested-by: Ingo Molnar Signed-off-by: Linus Torvalds --- kernel/user.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/user.c b/kernel/user.c index 477b6660f447..3551ac742395 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -72,6 +72,7 @@ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent) static void uid_hash_remove(struct user_struct *up) { hlist_del_init(&up->uidhash_node); + put_user_ns(up->user_ns); } static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent) @@ -334,7 +335,6 @@ static void free_user(struct user_struct *up, unsigned long flags) atomic_inc(&up->__count); spin_unlock_irqrestore(&uidhash_lock, flags); - put_user_ns(up->user_ns); INIT_WORK(&up->work, remove_user_sysfs_dir); schedule_work(&up->work); } @@ -357,7 +357,6 @@ static void free_user(struct user_struct *up, unsigned long flags) sched_destroy_user(up); key_put(up->uid_keyring); key_put(up->session_keyring); - put_user_ns(up->user_ns); kmem_cache_free(uid_cachep, up); } -- cgit v1.2.3