[PATCH] oom: don't kill current when another OOM in progress

A previous patch to allow an exiting task to OOM kill itself (and thereby
avoid a little deadlock) introduced a problem.  We don't want the
PF_EXITING task, even if it is 'current', to access mem reserves if there
is already a TIF_MEMDIE process in the system sucking up reserves.

Also make the commenting a little bit clearer, and note that our current
scheme of effectively single threading the OOM killer is not itself
perfect.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index a5493a3b4851282b879590f653ed9aae1b36b08a..20f41b082e16484a8c52aa04272bf4f30359593c 100644 (file)
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -215,6 +215,18 @@ static struct task_struct *select_bad_process(unsigned long *ppoints)
                if (is_init(p))
                        continue;
 
+               /*
+                * This task already has access to memory reserves and is
+                * being killed. Don't allow any other task access to the
+                * memory reserve.
+                *
+                * Note: this may have a chance of deadlock if it gets
+                * blocked waiting for another task which itself is waiting
+                * for memory. Is there a better alternative?
+                */
+               if (test_tsk_thread_flag(p, TIF_MEMDIE))
+                       return ERR_PTR(-1UL);
+
                /*
                 * This is in the process of releasing memory so wait for it
                 * to finish before killing some other task by mistake.
@@ -223,16 +235,15 @@ static struct task_struct *select_bad_process(unsigned long *ppoints)
                 * go ahead if it is exiting: this will simply set TIF_MEMDIE,
                 * which will allow it to gain access to memory reserves in
                 * the process of exiting and releasing its resources.
-                * Otherwise we could get an OOM deadlock.
+                * Otherwise we could get an easy OOM deadlock.
                 */
-               if ((p->flags & PF_EXITING) && p == current) {
+               if (p->flags & PF_EXITING) {
+                       if (p != current)
+                               return ERR_PTR(-1UL);
+
                        chosen = p;
                        *ppoints = ULONG_MAX;
-                       break;
                }
-               if ((p->flags & PF_EXITING) ||
-                               test_tsk_thread_flag(p, TIF_MEMDIE))
-                       return ERR_PTR(-1UL);
 
                if (p->oomkilladj == OOM_DISABLE)
                        continue;