All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nick Piggin <piggin@cyberone.com.au>
To: Andrew Morton <akpm@osdl.org>,
	linux-kernel <linux-kernel@vger.kernel.org>
Subject: [PATCH 5/5] 2.6.0 sched affinity race
Date: Sun, 21 Dec 2003 02:24:26 +1100	[thread overview]
Message-ID: <3FE469AA.3010808@cyberone.com.au> (raw)
In-Reply-To: <3FE46930.1020504@cyberone.com.au>

[-- Attachment #1: Type: text/plain, Size: 171 bytes --]

Prevents a race where sys_sched_setaffinity can race with sched_migrate_task
and cause sched_migrate_task to restore an invalid cpu mask.

(race can only happen on NUMA)


[-- Attachment #2: sched-migrate-affinity-race.patch --]
[-- Type: text/plain, Size: 4366 bytes --]


Prevents a race where sys_sched_setaffinity can race with sched_migrate_task
and cause sched_migrate_task to restore an invalid cpu mask.


 linux-2.6-npiggin/kernel/sched.c |   83 +++++++++++++++++++++++++++++----------
 1 files changed, 62 insertions(+), 21 deletions(-)

diff -puN kernel/sched.c~sched-migrate-affinity-race kernel/sched.c
--- linux-2.6/kernel/sched.c~sched-migrate-affinity-race	2003-12-19 19:56:27.000000000 +1100
+++ linux-2.6-npiggin/kernel/sched.c	2003-12-19 19:57:58.000000000 +1100
@@ -947,6 +947,9 @@ static inline void double_rq_unlock(runq
 }
 
 #ifdef CONFIG_NUMA
+
+static inline int __set_cpus_allowed(task_t *p, cpumask_t new_mask, unsigned long *flags);
+
 /*
  * If dest_cpu is allowed for this process, migrate the task to it.
  * This is accomplished by forcing the cpu_allowed mask to only
@@ -955,16 +958,37 @@ static inline void double_rq_unlock(runq
  */
 static void sched_migrate_task(task_t *p, int dest_cpu)
 {
-	cpumask_t old_mask;
+	runqueue_t *rq;
+	unsigned long flags;
+	cpumask_t old_mask, new_mask = cpumask_of_cpu(dest_cpu);
 
+	rq = task_rq_lock(p, &flags);
 	old_mask = p->cpus_allowed;
-	if (!cpu_isset(dest_cpu, old_mask))
+	if (!cpu_isset(dest_cpu, old_mask)) {
+		task_rq_unlock(rq, &flags);
 		return;
+	}
+
 	/* force the process onto the specified CPU */
-	set_cpus_allowed(p, cpumask_of_cpu(dest_cpu));
+	if (__set_cpus_allowed(p, new_mask, &flags) < 0)
+		return;
 
-	/* restore the cpus allowed mask */
-	set_cpus_allowed(p, old_mask);
+	rq = task_rq_lock(p, &flags);	/* __set_cpus_allowed unlocks rq */
+	if (unlikely(p->cpus_allowed != new_mask)) {
+		/*
+		 * We have raced with another set_cpus_allowed.
+		 * old_mask is invalid and we needn't move the
+		 * task back.
+		 */
+		task_rq_unlock(rq, &flags);
+		return;
+	}
+
+	/*
+	 * restore the cpus allowed mask. old_mask must be valid because
+	 * p->cpus_allowed is a subset of old_mask.
+	 */
+	WARN_ON(__set_cpus_allowed(p, old_mask, &flags) < 0);
 }
 
 /*
@@ -2603,31 +2627,27 @@ typedef struct {
 } migration_req_t;
 
 /*
- * Change a given task's CPU affinity. Migrate the thread to a
- * proper CPU and schedule it away if the CPU it's executing on
- * is removed from the allowed bitmask.
- *
- * NOTE: the caller must have a valid reference to the task, the
- * task must not exit() & deallocate itself prematurely.  The
- * call is not atomic; no spinlocks may be held.
+ * See comment for set_cpus_allowed. calling rules are different:
+ * the task's runqueue lock must be held, and __set_cpus_allowed
+ * will return with the runqueue unlocked.
  */
-int set_cpus_allowed(task_t *p, cpumask_t new_mask)
+static inline int __set_cpus_allowed(task_t *p, cpumask_t new_mask, unsigned long *flags)
 {
-	unsigned long flags;
 	migration_req_t req;
-	runqueue_t *rq;
+	runqueue_t *rq = task_rq(p);
 
-	if (any_online_cpu(new_mask) == NR_CPUS)
+	if (any_online_cpu(new_mask) == NR_CPUS) {
+		task_rq_unlock(rq, flags);
 		return -EINVAL;
+	}
 
-	rq = task_rq_lock(p, &flags);
 	p->cpus_allowed = new_mask;
 	/*
 	 * Can the task run on the task's current CPU? If not then
 	 * migrate the thread off to a proper CPU.
 	 */
 	if (cpu_isset(task_cpu(p), new_mask)) {
-		task_rq_unlock(rq, &flags);
+		task_rq_unlock(rq, flags);
 		return 0;
 	}
 	/*
@@ -2636,18 +2656,39 @@ int set_cpus_allowed(task_t *p, cpumask_
 	 */
 	if (!p->array && !task_running(rq, p)) {
 		set_task_cpu(p, any_online_cpu(p->cpus_allowed));
-		task_rq_unlock(rq, &flags);
+		task_rq_unlock(rq, flags);
 		return 0;
 	}
+
 	init_completion(&req.done);
 	req.task = p;
 	list_add(&req.list, &rq->migration_queue);
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, flags);
 
 	wake_up_process(rq->migration_thread);
-
 	wait_for_completion(&req.done);
+
 	return 0;
+
+}
+
+/*
+ * Change a given task's CPU affinity. Migrate the thread to a
+ * proper CPU and schedule it away if the CPU it's executing on
+ * is removed from the allowed bitmask.
+ *
+ * NOTE: the caller must have a valid reference to the task, the
+ * task must not exit() & deallocate itself prematurely.  The
+ * call is not atomic; no spinlocks may be held.
+ */
+int set_cpus_allowed(task_t *p, cpumask_t new_mask)
+{
+	unsigned long flags;
+	runqueue_t *rq;
+
+	rq = task_rq_lock(p, &flags);
+
+	return __set_cpus_allowed(p, new_mask, &flags);
 }
 
 EXPORT_SYMBOL_GPL(set_cpus_allowed);

_

  reply	other threads:[~2003-12-20 15:24 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-12-20 15:19 [PATCH 1/5] 2.6.0 fix preempt ctx switch accounting Nick Piggin
2003-12-20 15:20 ` [PATCH 2/5] 2.6.0 sched fork cleanup Nick Piggin
2003-12-20 15:21   ` [PATCH 3/5] 2.6.0 sched migrate comment Nick Piggin
2003-12-20 15:22     ` [PATCH 4/5] 2.6.0 sched style fixes Nick Piggin
2003-12-20 15:24       ` Nick Piggin [this message]
2003-12-20 21:07       ` Ingo Molnar
2003-12-20 20:26     ` [PATCH 3/5] 2.6.0 sched migrate comment Ingo Molnar
2003-12-20 23:19       ` Nick Piggin
2003-12-20 19:55   ` [PATCH 2/5] 2.6.0 sched fork cleanup Ingo Molnar
2003-12-20 23:17     ` Nick Piggin
2003-12-20 19:22 ` [PATCH 1/5] 2.6.0 fix preempt ctx switch accounting Ingo Molnar
2003-12-20 19:52   ` Rob Love
2003-12-20 20:07   ` Linus Torvalds
2003-12-20 21:32     ` Ingo Molnar
2003-12-20 23:15     ` Nick Piggin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=3FE469AA.3010808@cyberone.com.au \
    --to=piggin@cyberone.com.au \
    --cc=akpm@osdl.org \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.