sched_exec: remove select_fallback_rq() logic
PATCH 4/6 sched_exec: remove select_fallback_rq() logic
sched_exec()->select_task_rq() reads/updates ->cpus_allowed lockless. This can race with other CPUs updating our ->cpus_allowed, and this looks meaningless to me.
The task is current and running, it must have online cpus in ->cpus_allowed, the fallback mode is bogus. And, if ->sched_class returns the "wrong" cpu, this likely means we raced with set_cpus_allowed() which was called for reason, why should sched_exec() retry and call ->select_task_rq() again?
Change the code to call sched_class->select_task_rq() directly and do nothing if the returned cpu is wrong after re-checking under rq->lock.
Quoted 1 line
From now
task_struct->cpus_allowedis always stable underTASK_WAKING,
select_fallback_rq() is always called under rq-lock or the caller or the caller owns TASK_WAKING (select_task_rq).
---
kernel/sched.c | 25 ++++++++----------------- 1 file changed, 8 insertions(+), 17 deletions(-)
kernel/sched.c renamed from kernel/sched.c~3_SCHED_EXEC_DONT_FALLBACK +8 -17
@@ -2272,6 +2272,9 @@ void task_oncpu_function_call(struct tas }#ifdef CONFIG_SMP +/* +* ->cpus_allowed is protected by either TASK_WAKING or rq->lock held. +*/ static int select_fallback_rq (int cpu,struct task_struct *p) {int dest_cpu;
@@ -2308,12 +2311,7 @@ static int select_fallback_rq(int cpu, s }/* -* Gets called from 3 sites (exec, fork, wakeup), since it is called without -* holding rq->lock we need to ensure ->cpus_allowed is stable, this is done -* by: -* -* exec: is unstable, retry loop -* fork & wake-up: serialize ->cpus_allowed against TASK_WAKING +* The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable. */ static inline int select_task_rq (struct task_struct *p,int sd_flags,int wake_flags)
@@ -3123,9 +3121,8 @@ void sched_exec(void)unsigned long flags;struct rq *rq; -again: this_cpu =get_cpu (); - dest_cpu =select_task_rq (p,SD_BALANCE_EXEC ,0 ); + dest_cpu = p->sched_class->select_task_rq (p,SD_BALANCE_EXEC ,0 );if (dest_cpu == this_cpu) {put_cpu ();return ;
@@ -3133,18 +3130,12 @@ again: rq =task_rq_lock (p, &flags);put_cpu (); -/* * select_task_rq() can race against ->cpus_allowed */ -if (!cpumask_test_cpu (dest_cpu, &p->cpus_allowed) - ||unlikely (!cpu_active (dest_cpu))) { -task_rq_unlock (rq, &flags); - goto again; - } - -/* force the process onto the specified CPU */ -if (migrate_task (p, dest_cpu, &req)) { +if (cpumask_test_cpu (dest_cpu, &p->cpus_allowed) && +likely (cpu_active (dest_cpu)) && +migrate_task (p, dest_cpu, &req)) {/* Need to wait for migration thread (might exit: take ref). */ struct task_struct *mt = rq->migration_thread;
[tip:sched/core] sched: sched_exec(): Remove the select_fallback_rq() logic
Commit-ID: 30da688ef6b76e01969b00608202fff1eed2accc Gitweb: http://git.kernel.org/tip/30da688ef6b76e01969b00608202fff1eed2accc Author: Oleg Nesterov <[email protected]> AuthorDate: Mon, 15 Mar 2010 10:10:19 +0100 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 2 Apr 2010 20:12:02 +0200
sched: sched_exec(): Remove the select_fallback_rq() logic
sched_exec()->select_task_rq() reads/updates ->cpus_allowed lockless. This can race with other CPUs updating our ->cpus_allowed, and this looks meaningless to me.
The task is current and running, it must have online cpus in ->cpus_allowed, the fallback mode is bogus. And, if ->sched_class returns the "wrong" cpu, this likely means we raced with set_cpus_allowed() which was called for reason, why should sched_exec() retry and call ->select_task_rq() again?
Change the code to call sched_class->select_task_rq() directly and do nothing if the returned cpu is wrong after re-checking under rq->lock.
Quoted 1 line
From now
task_struct->cpus_allowedis always stable underTASK_WAKING,
select_fallback_rq() is always called under rq-lock or the caller or the caller owns TASK_WAKING (select_task_rq).
LKML-Reference: <[email protected]>
--- kernel/sched.c | 25 ++++++++----------------- 1 files changed, 8 insertions(+), 17 deletions(-)
kernel/sched.c +8 -17
@@ -2280,6 +2280,9 @@ void task_oncpu_function_call(struct task_struct *p, }#ifdef CONFIG_SMP +/* +* ->cpus_allowed is protected by either TASK_WAKING or rq->lock held. +*/ static int select_fallback_rq (int cpu,struct task_struct *p) {int dest_cpu;
@@ -2316,12 +2319,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) }/* -* Gets called from 3 sites (exec, fork, wakeup), since it is called without -* holding rq->lock we need to ensure ->cpus_allowed is stable, this is done -* by: -* -* exec: is unstable, retry loop -* fork & wake-up: serialize ->cpus_allowed against TASK_WAKING +* The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable. */ static inline int select_task_rq (struct task_struct *p,int sd_flags,int wake_flags)
@@ -3076,9 +3074,8 @@ void sched_exec(void)unsigned long flags;struct rq *rq; -again: this_cpu =get_cpu (); - dest_cpu =select_task_rq (p,SD_BALANCE_EXEC ,0 ); + dest_cpu = p->sched_class->select_task_rq (p,SD_BALANCE_EXEC ,0 );if (dest_cpu == this_cpu) {put_cpu ();return ;
@@ -3086,18 +3083,12 @@ again: rq =task_rq_lock (p, &flags);put_cpu (); -/* * select_task_rq() can race against ->cpus_allowed */ -if (!cpumask_test_cpu (dest_cpu, &p->cpus_allowed) - ||unlikely (!cpu_active (dest_cpu))) { -task_rq_unlock (rq, &flags); - goto again; - } - -/* force the process onto the specified CPU */ -if (migrate_task (p, dest_cpu, &req)) { +if (cpumask_test_cpu (dest_cpu, &p->cpus_allowed) && +likely (cpu_active (dest_cpu)) && +migrate_task (p, dest_cpu, &req)) {/* Need to wait for migration thread (might exit: take ref). */ struct task_struct *mt = rq->migration_thread;