From 40bea039593dfc7f3f9814dab844f6db43ae580b Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 13 Aug 2014 18:50:16 +0200 Subject: nohz: Restore NMI safe local irq work for local nohz kick The local nohz kick is currently used by perf which needs it to be NMI-safe. Recent commit though (7d1311b93e58ed55f3a31cc8f94c4b8fe988a2b9) changed its implementation to fire the local kick using the remote kick API. It was convenient to make the code more generic but the remote kick isn't NMI-safe. As a result: WARNING: CPU: 3 PID: 18062 at kernel/irq_work.c:72 irq_work_queue_on+0x11e/0x140() CPU: 3 PID: 18062 Comm: trinity-subchil Not tainted 3.16.0+ #34 0000000000000009 00000000903774d1 ffff880244e06c00 ffffffff9a7f1e37 0000000000000000 ffff880244e06c38 ffffffff9a0791dd ffff880244fce180 0000000000000003 ffff880244e06d58 ffff880244e06ef8 0000000000000000 Call Trace: [] dump_stack+0x4e/0x7a [] warn_slowpath_common+0x7d/0xa0 [] warn_slowpath_null+0x1a/0x20 [] irq_work_queue_on+0x11e/0x140 [] tick_nohz_full_kick_cpu+0x57/0x90 [] __perf_event_overflow+0x275/0x350 [] ? perf_event_task_disable+0xa0/0xa0 [] ? x86_perf_event_set_period+0xbf/0x150 [] perf_event_overflow+0x14/0x20 [] intel_pmu_handle_irq+0x206/0x410 [] ? arch_vtime_task_switch+0x63/0x130 [] perf_event_nmi_handler+0x2b/0x50 [] nmi_handle+0xd2/0x390 [] ? nmi_handle+0x5/0x390 [] ? lock_release+0xab/0x330 [] default_do_nmi+0x72/0x1c0 [] ? cpuacct_account_field+0xcf/0x200 [] do_nmi+0xb8/0x100 Lets fix this by restoring the use of local irq work for the nohz local kick. Reported-by: Catalin Iacob Reported-and-tested-by: Dave Jones Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Frederic Weisbecker --- include/linux/tick.h | 7 +------ kernel/time/tick-sched.c | 14 ++++++++++++++ 2 files changed, 15 insertions(+), 6 deletions(-) diff --git a/include/linux/tick.h b/include/linux/tick.h index 059052306831..9a82c7dc3fdd 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -183,13 +183,8 @@ static inline bool tick_nohz_full_cpu(int cpu) extern void tick_nohz_init(void); extern void __tick_nohz_full_check(void); +extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_cpu(int cpu); - -static inline void tick_nohz_full_kick(void) -{ - tick_nohz_full_kick_cpu(smp_processor_id()); -} - extern void tick_nohz_full_kick_all(void); extern void __tick_nohz_task_switch(struct task_struct *tsk); #else diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 99aa6ee3908f..f654a8a298fa 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -224,6 +224,20 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { .func = nohz_full_kick_work_func, }; +/* + * Kick this CPU if it's full dynticks in order to force it to + * re-evaluate its dependency on the tick and restart it if necessary. + * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(), + * is NMI safe. + */ +void tick_nohz_full_kick(void) +{ + if (!tick_nohz_full_cpu(smp_processor_id())) + return; + + irq_work_queue(&__get_cpu_var(nohz_full_kick_work)); +} + /* * Kick the CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. -- cgit v1.2.3 From 849151dd5481bc8acb1d287a299b5d6a4ca9f1c3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 6 Sep 2014 12:18:07 +0200 Subject: compat: nanosleep: Clarify error handling The error handling in compat_sys_nanosleep() is correct, but completely non obvious. Document it and restrict it to the -ERESTART_RESTARTBLOCK return value for clarity. Reported-by: Kees Cook Signed-off-by: Thomas Gleixner --- kernel/compat.c | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git a/kernel/compat.c b/kernel/compat.c index 633394f442f8..ebb3c369d03d 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -226,7 +226,7 @@ static long compat_nanosleep_restart(struct restart_block *restart) ret = hrtimer_nanosleep_restart(restart); set_fs(oldfs); - if (ret) { + if (ret == -ERESTART_RESTARTBLOCK) { rmtp = restart->nanosleep.compat_rmtp; if (rmtp && compat_put_timespec(&rmt, rmtp)) @@ -256,7 +256,26 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC); set_fs(oldfs); - if (ret) { + /* + * hrtimer_nanosleep() can only return 0 or + * -ERESTART_RESTARTBLOCK here because: + * + * - we call it with HRTIMER_MODE_REL and therefor exclude the + * -ERESTARTNOHAND return path. + * + * - we supply the rmtp argument from the task stack (due to + * the necessary compat conversion. So the update cannot + * fail, which excludes the -EFAULT return path as well. If + * it fails nevertheless we have a bigger problem and wont + * reach this place anymore. + * + * - if the return value is 0, we do not have to update rmtp + * because there is no remaining time. + * + * We check for -ERESTART_RESTARTBLOCK nevertheless if the + * core implementation decides to return random nonsense. + */ + if (ret == -ERESTART_RESTARTBLOCK) { struct restart_block *restart = ¤t_thread_info()->restart_block; @@ -266,7 +285,6 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, if (rmtp && compat_put_timespec(&rmt, rmtp)) return -EFAULT; } - return ret; } -- cgit v1.2.3 From 9bf2419fa7bffa16ce58a4d5c20399eff8c970c9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 6 Sep 2014 12:24:49 +0200 Subject: timekeeping: Update timekeeper before updating vsyscall and pvclock The update_walltime() code works on the shadow timekeeper to make the seqcount protected region as short as possible. But that update to the shadow timekeeper does not update all timekeeper fields because it's sufficient to do that once before it becomes life. One of these fields is tkr.base_mono. That stays stale in the shadow timekeeper unless an operation happens which copies the real timekeeper to the shadow. The update function is called after the update calls to vsyscall and pvclock. While not correct, it did not cause any problems because none of the invoked update functions used base_mono. commit cbcf2dd3b3d4 (x86: kvm: Make kvm_get_time_and_clockread() nanoseconds based) changed that in the kvm pvclock update function, so the stale mono_base value got used and caused kvm-clock to malfunction. Put the update where it belongs and fix the issue. Reported-by: Chris J Arges Reported-by: Paolo Bonzini Cc: Gleb Natapov Cc: John Stultz Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1409050000570.3333@nanos Signed-off-by: Thomas Gleixner --- kernel/time/timekeeping.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index fb4a9c2cf8d9..ec1791fae965 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -442,11 +442,12 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) tk->ntp_error = 0; ntp_clear(); } - update_vsyscall(tk); - update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); tk_update_ktime_data(tk); + update_vsyscall(tk); + update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); + if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); -- cgit v1.2.3