Skip to contentSkip to conversation

sched: Fix TASK_WAKING vs fork deadlock

tip:sched/core tip-bot for Peter Zijlstra 1 participant 1 message Apr 2, 2010 Scheduler

lore
Share & tools
lore
#0 lore raw
Commit-ID:  0017d735092844118bef006696a750a0e4ef6ebd
Gitweb:     http://git.kernel.org/tip/0017d735092844118bef006696a750a0e4ef6ebd
Author:     Peter Zijlstra <[email protected]>
AuthorDate: Wed, 24 Mar 2010 18:34:10 +0100
Committer:  Ingo Molnar <[email protected]>
CommitDate: Fri, 2 Apr 2010 20:12:03 +0200

sched: Fix TASK_WAKING vs fork deadlock

Oleg noticed a few races with the TASK_WAKING usage on fork.

- since TASK_WAKING is basically a spinlock, it should be IRQ safe
- since we set TASK_WAKING (*) without holding rq->lock it could be there still is a rq->lock holder, thereby not actually providing full serialization.

(*) in fact we clear PF_STARTING, which in effect enables TASK_WAKING.

Cure the second issue by not setting TASK_WAKING in sched_fork(), but only temporarily in wake_up_new_task() while calling select_task_rq().

Cure the first by holding rq->lock around the select_task_rq() call, this will disable IRQs, this however requires that we push down the rq->lock release into select_task_rq_fair()'s cgroup stuff.

Because select_task_rq_fair() still needs to drop the rq->lock we cannot fully get rid of TASK_WAKING.

LKML-Reference: <new-submission>

---
 include/linux/sched.h   |    3 +-
 kernel/sched.c          |   65 +++++++++++++++++-----------------------------
 kernel/sched_fair.c     |    8 ++++-
 kernel/sched_idletask.c |    3 +-
 kernel/sched_rt.c       |    5 +--
 5 files changed, 36 insertions(+), 48 deletions(-)
include/linux/sched.h +2 -1
index 8bea407..fb6c188 100644
@@ -1046,7 +1046,8 @@ struct sched_class {
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
-	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
+	int  (*select_task_rq)(struct rq *rq, struct task_struct *p,
+			       int sd_flag, int flags);
 
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
 	void (*post_schedule) (struct rq *this_rq);
kernel/sched.c +24 -41

128 lines not on this page · raw message

kernel/sched_fair.c +6 -2
index 49ad993..8a5e763 100644
@@ -1423,7 +1423,8 @@ select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
  *
  * preempt must be disabled.
  */
-static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
+static int
+select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags)
 {
 	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
 	int cpu = smp_processor_id();
@@ -1521,8 +1522,11 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 				  cpumask_weight(sched_domain_span(sd))))
 			tmp = affine_sd;
 
-		if (tmp)
+		if (tmp) {
+			raw_spin_unlock(&rq->lock);
 			update_shares(tmp);
+			raw_spin_lock(&rq->lock);
+		}
 	}
 #endif
 
kernel/sched_idletask.c +2 -1
index a8a6d8a..5af709f 100644
@@ -6,7 +6,8 @@
  */
 
 #ifdef CONFIG_SMP
-static int select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
+static int
+select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
kernel/sched_rt.c +2 -3
index 012d69b..fde895f 100644
@@ -948,10 +948,9 @@ static void yield_task_rt(struct rq *rq)
 #ifdef CONFIG_SMP
 static int find_lowest_rq(struct task_struct *task);
 
-static int select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
+static int
+select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 {
-	struct rq *rq = task_rq(p);
-
 	if (sd_flag != SD_BALANCE_WAKE)
 		return smp_processor_id();