Merge branch 'modsplit-Oct31_2011' of git://git.kernel.org/pub/scm/linux/kernel/git...

[pandora-kernel.git] / mm / oom_kill.c

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index fcb2fa5..471dedb 100644 (file)
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -32,12 +32,32 @@
 #include <linux/mempolicy.h>
 #include <linux/security.h>
 #include <linux/ptrace.h>
+#include <linux/freezer.h>
 
 int sysctl_panic_on_oom;
 int sysctl_oom_kill_allocating_task;
 int sysctl_oom_dump_tasks = 1;
 static DEFINE_SPINLOCK(zone_scan_lock);
 
+/*
+ * compare_swap_oom_score_adj() - compare and swap current's oom_score_adj
+ * @old_val: old oom_score_adj for compare
+ * @new_val: new oom_score_adj for swap
+ *
+ * Sets the oom_score_adj value for current to @new_val iff its present value is
+ * @old_val.  Usually used to reinstate a previous value to prevent racing with
+ * userspacing tuning the value in the interim.
+ */
+void compare_swap_oom_score_adj(int old_val, int new_val)
+{
+       struct sighand_struct *sighand = current->sighand;
+
+       spin_lock_irq(&sighand->siglock);
+       if (current->signal->oom_score_adj == old_val)
+               current->signal->oom_score_adj = new_val;
+       spin_unlock_irq(&sighand->siglock);
+}
+
 /**
  * test_set_oom_score_adj() - set current's oom_score_adj and return old value
  * @new_val: new oom_score_adj value
@@ -53,13 +73,7 @@ int test_set_oom_score_adj(int new_val)
 
        spin_lock_irq(&sighand->siglock);
        old_val = current->signal->oom_score_adj;
-       if (new_val != old_val) {
-               if (new_val == OOM_SCORE_ADJ_MIN)
-                       atomic_inc(&current->mm->oom_disable_count);
-               else if (old_val == OOM_SCORE_ADJ_MIN)
-                       atomic_dec(&current->mm->oom_disable_count);
-               current->signal->oom_score_adj = new_val;
-       }
+       current->signal->oom_score_adj = new_val;
        spin_unlock_irq(&sighand->siglock);
 
        return old_val;
@@ -171,16 +185,6 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
        if (!p)
                return 0;
 
-       /*
-        * Shortcut check for a thread sharing p->mm that is OOM_SCORE_ADJ_MIN
-        * so the entire heuristic doesn't need to be executed for something
-        * that cannot be killed.
-        */
-       if (atomic_read(&p->mm->oom_disable_count)) {
-               task_unlock(p);
-               return 0;
-       }
-
        /*
         * The memory controller may have a limit of 0 bytes, so avoid a divide
         * by zero, if necessary.
@@ -317,8 +321,11 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
                 * blocked waiting for another task which itself is waiting
                 * for memory. Is there a better alternative?
                 */
-               if (test_tsk_thread_flag(p, TIF_MEMDIE))
+               if (test_tsk_thread_flag(p, TIF_MEMDIE)) {
+                       if (unlikely(frozen(p)))
+                               thaw_process(p);
                        return ERR_PTR(-1UL);
+               }
                if (!p->mm)
                        continue;
 
@@ -435,7 +442,7 @@ static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem)
        task_unlock(p);
 
        /*
-        * Kill all processes sharing p->mm in other thread groups, if any.
+        * Kill all user processes sharing p->mm in other thread groups, if any.
         * They don't get access to memory reserves or a higher scheduler
         * priority, though, to avoid depletion of all memory or task
         * starvation.  This prevents mm->mmap_sem livelock when an oom killed
@@ -445,7 +452,11 @@ static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem)
         * signal.
         */
        for_each_process(q)
-               if (q->mm == mm && !same_thread_group(q, p)) {
+               if (q->mm == mm && !same_thread_group(q, p) &&
+                   !(q->flags & PF_KTHREAD)) {
+                       if (q->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+                               continue;
+
                        task_lock(q);   /* Protect ->comm from prctl() */
                        pr_err("Kill process %d (%s) sharing same memory\n",
                                task_pid_nr(q), q->comm);
@@ -722,7 +733,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
        read_lock(&tasklist_lock);
        if (sysctl_oom_kill_allocating_task &&
            !oom_unkillable_task(current, NULL, nodemask) &&
-           current->mm && !atomic_read(&current->mm->oom_disable_count)) {
+           current->mm) {
                /*
                 * oom_kill_process() needs tasklist_lock held.  If it returns
                 * non-zero, current could not be killed so we must fallback to