summaryrefslogtreecommitdiffstats
path: root/kernel/cpuset.c
diff options
context:
space:
mode:
authorPaul Jackson <pj@sgi.com>2006-02-15 15:17:38 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2006-02-15 15:32:21 -0800
commit06fed33849c13af637c4d09e9ba27828fac9edd5 (patch)
tree0dd2fa91503250edc94ec58b23fbb3e9ad6100f4 /kernel/cpuset.c
parent651c29a17f7ea0204dacbc2a5042d57b1c9e2e37 (diff)
downloadlinux-stable-06fed33849c13af637c4d09e9ba27828fac9edd5.tar.gz
linux-stable-06fed33849c13af637c4d09e9ba27828fac9edd5.tar.bz2
linux-stable-06fed33849c13af637c4d09e9ba27828fac9edd5.zip
[PATCH] cpuset: oops in exit on null cpuset fix
Fix a latent bug in cpuset_exit() handling. If a task tried to allocate memory after calling cpuset_exit(), it oops'd in cpuset_update_task_memory_state() on a NULL cpuset pointer. So set the exiting tasks cpuset to the root cpuset instead of to NULL. A distro kernel hit this with an added kernel package that had just such a hook (allocating memory) in the exit code path. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'kernel/cpuset.c')
-rw-r--r--kernel/cpuset.c35
1 files changed, 34 insertions, 1 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index ba42b0a76961..12815d3f1a05 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1977,6 +1977,39 @@ void cpuset_fork(struct task_struct *child)
* We don't need to task_lock() this reference to tsk->cpuset,
* because tsk is already marked PF_EXITING, so attach_task() won't
* mess with it, or task is a failed fork, never visible to attach_task.
+ *
+ * Hack:
+ *
+ * Set the exiting tasks cpuset to the root cpuset (top_cpuset).
+ *
+ * Don't leave a task unable to allocate memory, as that is an
+ * accident waiting to happen should someone add a callout in
+ * do_exit() after the cpuset_exit() call that might allocate.
+ * If a task tries to allocate memory with an invalid cpuset,
+ * it will oops in cpuset_update_task_memory_state().
+ *
+ * We call cpuset_exit() while the task is still competent to
+ * handle notify_on_release(), then leave the task attached to
+ * the root cpuset (top_cpuset) for the remainder of its exit.
+ *
+ * To do this properly, we would increment the reference count on
+ * top_cpuset, and near the very end of the kernel/exit.c do_exit()
+ * code we would add a second cpuset function call, to drop that
+ * reference. This would just create an unnecessary hot spot on
+ * the top_cpuset reference count, to no avail.
+ *
+ * Normally, holding a reference to a cpuset without bumping its
+ * count is unsafe. The cpuset could go away, or someone could
+ * attach us to a different cpuset, decrementing the count on
+ * the first cpuset that we never incremented. But in this case,
+ * top_cpuset isn't going away, and either task has PF_EXITING set,
+ * which wards off any attach_task() attempts, or task is a failed
+ * fork, never visible to attach_task.
+ *
+ * Another way to do this would be to set the cpuset pointer
+ * to NULL here, and check in cpuset_update_task_memory_state()
+ * for a NULL pointer. This hack avoids that NULL check, for no
+ * cost (other than this way too long comment ;).
**/
void cpuset_exit(struct task_struct *tsk)
@@ -1984,7 +2017,7 @@ void cpuset_exit(struct task_struct *tsk)
struct cpuset *cs;
cs = tsk->cpuset;
- tsk->cpuset = NULL;
+ tsk->cpuset = &top_cpuset; /* Hack - see comment above */
if (notify_on_release(cs)) {
char *pathbuf = NULL;