From 2064a5ab04707c55003e099e5abbf19a0826bbac Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 3 Dec 2017 13:19:00 -0800 Subject: sched/core: Fix kernel-doc warnings after code movement Fix the following kernel-doc warnings after code restructuring: ../kernel/sched/core.c:5113: warning: No description found for parameter 't' ../kernel/sched/core.c:5113: warning: Excess function parameter 'interval' description in 'sched_rr_get_interval' get rid of set_fs()") Signed-off-by: Randy Dunlap Cc: Al Viro Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: abca5fc535a3e ("sched_rr_get_interval(): move compat to native, Link: http://lkml.kernel.org/r/995c6ded-b32e-bbe4-d9f5-4d42d121aff1@infradead.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 75554f366fd3..644fa2e3d993 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5097,17 +5097,6 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy) return ret; } -/** - * sys_sched_rr_get_interval - return the default timeslice of a process. - * @pid: pid of the process. - * @interval: userspace pointer to the timeslice value. - * - * this syscall writes the default timeslice value of a given process - * into the user-space timespec buffer. A value of '0' means infinity. - * - * Return: On success, 0 and the timeslice is in @interval. Otherwise, - * an error code. - */ static int sched_rr_get_interval(pid_t pid, struct timespec64 *t) { struct task_struct *p; @@ -5144,6 +5133,17 @@ out_unlock: return retval; } +/** + * sys_sched_rr_get_interval - return the default timeslice of a process. + * @pid: pid of the process. + * @interval: userspace pointer to the timeslice value. + * + * this syscall writes the default timeslice value of a given process + * into the user-space timespec buffer. A value of '0' means infinity. + * + * Return: On success, 0 and the timeslice is in @interval. Otherwise, + * an error code. + */ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, struct timespec __user *, interval) { -- cgit v1.2.3 From f73c52a5bcd1710994e53fbccc378c42b97a06b6 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sat, 2 Dec 2017 13:04:54 -0500 Subject: sched/rt: Do not pull from current CPU if only one CPU to pull Daniel Wagner reported a crash on the BeagleBone Black SoC. This is a single CPU architecture, and does not have a functional arch_send_call_function_single_ipi() implementation which can crash the kernel if that is called. As it only has one CPU, it shouldn't be called, but if the kernel is compiled for SMP, the push/pull RT scheduling logic now calls it for irq_work if the one CPU is overloaded, it can use that function to call itself and crash the kernel. Ideally, we should disable the SCHED_FEAT(RT_PUSH_IPI) if the system only has a single CPU. But SCHED_FEAT is a constant if sched debugging is turned off. Another fix can also be used, and this should also help with normal SMP machines. That is, do not initiate the pull code if there's only one RT overloaded CPU, and that CPU happens to be the current CPU that is scheduling in a lower priority task. Even on a system with many CPUs, if there's many RT tasks waiting to run on a single CPU, and that CPU schedules in another RT task of lower priority, it will initiate the PULL logic in case there's a higher priority RT task on another CPU that is waiting to run. But if there is no other CPU with waiting RT tasks, it will initiate the RT pull logic on itself (as it still has RT tasks waiting to run). This is a wasted effort. Not only does this help with SMP code where the current CPU is the only one with RT overloaded tasks, it should also solve the issue that Daniel encountered, because it will prevent the PULL logic from executing, as there's only one CPU on the system, and the check added here will cause it to exit the RT pull code. Reported-by: Daniel Wagner Signed-off-by: Steven Rostedt (VMware) Acked-by: Peter Zijlstra Cc: Linus Torvalds Cc: Sebastian Andrzej Siewior Cc: Thomas Gleixner Cc: linux-rt-users Cc: stable@vger.kernel.org Fixes: 4bdced5c9 ("sched/rt: Simplify the IPI based RT balancing logic") Link: http://lkml.kernel.org/r/20171202130454.4cbbfe8d@vmware.local.home Signed-off-by: Ingo Molnar --- kernel/sched/rt.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/sched') diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 4056c19ca3f0..665ace2fc558 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2034,8 +2034,9 @@ static void pull_rt_task(struct rq *this_rq) bool resched = false; struct task_struct *p; struct rq *src_rq; + int rt_overload_count = rt_overloaded(this_rq); - if (likely(!rt_overloaded(this_rq))) + if (likely(!rt_overload_count)) return; /* @@ -2044,6 +2045,11 @@ static void pull_rt_task(struct rq *this_rq) */ smp_rmb(); + /* If we are the only overloaded CPU do nothing */ + if (rt_overload_count == 1 && + cpumask_test_cpu(this_rq->cpu, this_rq->rd->rto_mask)) + return; + #ifdef HAVE_RT_PUSH_IPI if (sched_feat(RT_PUSH_IPI)) { tell_cpu_to_push(this_rq); -- cgit v1.2.3 From 466a2b42d67644447a1765276259a3ea5531ddff Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Thu, 21 Dec 2017 02:22:45 +0100 Subject: cpufreq: schedutil: Use idle_calls counter of the remote CPU Since the recent remote cpufreq callback work, its possible that a cpufreq update is triggered from a remote CPU. For single policies however, the current code uses the local CPU when trying to determine if the remote sg_cpu entered idle or is busy. This is incorrect. To remedy this, compare with the nohz tick idle_calls counter of the remote CPU. Fixes: 674e75411fc2 (sched: cpufreq: Allow remote cpufreq callbacks) Acked-by: Viresh Kumar Acked-by: Peter Zijlstra (Intel) Signed-off-by: Joel Fernandes Cc: 4.14+ # 4.14+ Signed-off-by: Rafael J. Wysocki --- include/linux/tick.h | 1 + kernel/sched/cpufreq_schedutil.c | 2 +- kernel/time/tick-sched.c | 13 +++++++++++++ 3 files changed, 15 insertions(+), 1 deletion(-) (limited to 'kernel/sched') diff --git a/include/linux/tick.h b/include/linux/tick.h index f442d1a42025..7cc35921218e 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -119,6 +119,7 @@ extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); extern ktime_t tick_nohz_get_sleep_length(void); extern unsigned long tick_nohz_get_idle_calls(void); +extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); #else /* !CONFIG_NO_HZ_COMMON */ diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 2f52ec0f1539..d6717a3331a1 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -244,7 +244,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util, #ifdef CONFIG_NO_HZ_COMMON static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { - unsigned long idle_calls = tick_nohz_get_idle_calls(); + unsigned long idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu); bool ret = idle_calls == sg_cpu->saved_idle_calls; sg_cpu->saved_idle_calls = idle_calls; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 99578f06c8d4..77555faf6fbc 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -985,6 +985,19 @@ ktime_t tick_nohz_get_sleep_length(void) return ts->sleep_length; } +/** + * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value + * for a particular CPU. + * + * Called from the schedutil frequency scaling governor in scheduler context. + */ +unsigned long tick_nohz_get_idle_calls_cpu(int cpu) +{ + struct tick_sched *ts = tick_get_tick_sched(cpu); + + return ts->idle_calls; +} + /** * tick_nohz_get_idle_calls - return the current idle calls counter value * -- cgit v1.2.3 From 541676078b52f365f53d46ee5517d305cd1b6350 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 15 Dec 2017 14:23:10 -0500 Subject: membarrier: Disable preemption when calling smp_call_function_many() smp_call_function_many() requires disabling preemption around the call. Signed-off-by: Mathieu Desnoyers Cc: # v4.14+ Cc: Andrea Parri Cc: Andrew Hunter Cc: Avi Kivity Cc: Benjamin Herrenschmidt Cc: Boqun Feng Cc: Dave Watson Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Maged Michael Cc: Michael Ellerman Cc: Paul E . McKenney Cc: Paul E. McKenney Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20171215192310.25293-1-mathieu.desnoyers@efficios.com Signed-off-by: Ingo Molnar --- kernel/sched/membarrier.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/sched') diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index dd7908743dab..9bcbacba82a8 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -89,7 +89,9 @@ static int membarrier_private_expedited(void) rcu_read_unlock(); } if (!fallback) { + preempt_disable(); smp_call_function_many(tmpmask, ipi_mb, NULL, 1); + preempt_enable(); free_cpumask_var(tmpmask); } cpus_read_unlock(); -- cgit v1.2.3