summaryrefslogtreecommitdiffstats
path: root/mm/memcontrol.c
diff options
context:
space:
mode:
authorBalbir Singh <balbir@linux.vnet.ibm.com>2008-09-28 23:09:31 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2008-09-29 08:41:47 -0700
commit31a78f23bac0069004e69f98808b6988baccb6b6 (patch)
treeedca8cffb4682de6be2e79b0b8d381dbb1b70964 /mm/memcontrol.c
parentbf5cb66447e7d9f7f111c1d0ebb6d7c90ec24b4d (diff)
downloadlinux-31a78f23bac0069004e69f98808b6988baccb6b6.tar.gz
linux-31a78f23bac0069004e69f98808b6988baccb6b6.tar.bz2
linux-31a78f23bac0069004e69f98808b6988baccb6b6.zip
mm owner: fix race between swapoff and exit
There's a race between mm->owner assignment and swapoff, more easily seen when task slab poisoning is turned on. The condition occurs when try_to_unuse() runs in parallel with an exiting task. A similar race can occur with callers of get_task_mm(), such as /proc/<pid>/<mmstats> or ptrace or page migration. CPU0 CPU1 try_to_unuse looks at mm = task0->mm increments mm->mm_users task 0 exits mm->owner needs to be updated, but no new owner is found (mm_users > 1, but no other task has task->mm = task0->mm) mm_update_next_owner() leaves mmput(mm) decrements mm->mm_users task0 freed dereferencing mm->owner fails The fix is to notify the subsystem via mm_owner_changed callback(), if no new owner is found, by specifying the new task as NULL. Jiri Slaby: mm->owner was set to NULL prior to calling cgroup_mm_owner_callbacks(), but must be set after that, so as not to pass NULL as old owner causing oops. Daisuke Nishimura: mm_update_next_owner() may set mm->owner to NULL, but mem_cgroup_from_task() and its callers need to take account of this situation to avoid oops. Hugh Dickins: Lockdep warning and hang below exec_mmap() when testing these patches. exit_mm() up_reads mmap_sem before calling mm_update_next_owner(), so exec_mmap() now needs to do the same. And with that repositioning, there's now no point in mm_need_new_owner() allowing for NULL mm. Reported-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Jiri Slaby <jirislaby@gmail.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Paul Menage <menage@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/memcontrol.c')
-rw-r--r--mm/memcontrol.c17
1 files changed, 17 insertions, 0 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c0500e4d3a2f..36896f3eb7f5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -250,6 +250,14 @@ static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
+ /*
+ * mm_update_next_owner() may clear mm->owner to NULL
+ * if it races with swapoff, page migration, etc.
+ * So this can be called with p == NULL.
+ */
+ if (unlikely(!p))
+ return NULL;
+
return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
struct mem_cgroup, css);
}
@@ -549,6 +557,11 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
if (likely(!memcg)) {
rcu_read_lock();
mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+ if (unlikely(!mem)) {
+ rcu_read_unlock();
+ kmem_cache_free(page_cgroup_cache, pc);
+ return 0;
+ }
/*
* For every charge from the cgroup, increment reference count
*/
@@ -801,6 +814,10 @@ int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
rcu_read_lock();
mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+ if (unlikely(!mem)) {
+ rcu_read_unlock();
+ return 0;
+ }
css_get(&mem->css);
rcu_read_unlock();