1 files changed, 42 insertions, 47 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 7dcca55ede7c..83fb72c108b7 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -31,6 +31,7 @@
 #include <linux/memcontrol.h>
 #include <linux/mempolicy.h>
 #include <linux/security.h>
+#include <linux/ptrace.h>
 
 int sysctl_panic_on_oom;
 int sysctl_oom_kill_allocating_task;
@@ -83,24 +84,6 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
 #endif /* CONFIG_NUMA */
 
 /*
- * If this is a system OOM (not a memcg OOM) and the task selected to be
- * killed is not already running at high (RT) priorities, speed up the
- * recovery by boosting the dying task to the lowest FIFO priority.
- * That helps with the recovery and avoids interfering with RT tasks.
- */
-static void boost_dying_task_prio(struct task_struct *p,
-                                  struct mem_cgroup *mem)
-{
-        struct sched_param param = { .sched_priority = 1 };
-
-        if (mem)
-                return;
-
-        if (!rt_task(p))
-                sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
-}
-
-/*
  * The process p may have detached its own ->mm while exiting or through
  * use_mm(), but one or more of its subthreads may still have a valid
  * pointer.  Return p, or any of its subthreads with a valid ->mm, with
@@ -292,13 +275,15 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
                 unsigned long totalpages, struct mem_cgroup *mem,
                 const nodemask_t *nodemask)
 {
-        struct task_struct *p;
+        struct task_struct *g, *p;
         struct task_struct *chosen = NULL;
         *ppoints = 0;
 
-        for_each_process(p) {
+        do_each_thread(g, p) {
                 unsigned int points;
 
+                if (!p->mm)
+                        continue;
                 if (oom_unkillable_task(p, mem, nodemask))
                         continue;
 
@@ -314,22 +299,29 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
                 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.
-                 *
-                 * However, if p is the current task, we allow the 'kill' to
-                 * 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 easy OOM deadlock.
-                 */
-                if (thread_group_empty(p) && (p->flags & PF_EXITING) && p->mm) {
-                        if (p != current)
-                                return ERR_PTR(-1UL);
-
-                        chosen = p;
-                        *ppoints = 1000;
+                if (p->flags & PF_EXITING) {
+                        /*
+                         * If p is the current task and is in the process of
+                         * releasing memory, we allow the "kill" to set
+                         * TIF_MEMDIE, which will allow it to gain access to
+                         * memory reserves.  Otherwise, it may stall forever.
+                         *
+                         * The loop isn't broken here, however, in case other
+                         * threads are found to have already been oom killed.
+                         */
+                        if (p == current) {
+                                chosen = p;
+                                *ppoints = 1000;
+                        } else {
+                                /*
+                                 * If this task is not being ptraced on exit,
+                                 * then wait for it to finish before killing
+                                 * some other task unnecessarily.
+                                 */
+                                if (!(task_ptrace(p->group_leader) &
+                                                        PT_TRACE_EXIT))
+                                        return ERR_PTR(-1UL);
+                        }
                 }
 
                 points = oom_badness(p, mem, nodemask, totalpages);
@@ -337,7 +329,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
                         chosen = p;
                         *ppoints = points;
                 }
-        }
+        } while_each_thread(g, p);
 
         return chosen;
 }
@@ -396,7 +388,7 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
         task_unlock(current);
         dump_stack();
         mem_cgroup_print_oom_info(mem, p);
-        show_mem();
+        show_mem(SHOW_MEM_FILTER_NODES);
         if (sysctl_oom_dump_tasks)
                 dump_tasks(mem, nodemask);
 }
@@ -442,13 +434,6 @@ static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem)
         set_tsk_thread_flag(p, TIF_MEMDIE);
         force_sig(SIGKILL, p);
 
-        /*
-         * We give our sacrificial lamb high priority and access to
-         * all the memory it needs. That way it should be able to
-         * exit() and clear out its resources quickly...
-         */
-        boost_dying_task_prio(p, mem);
-
         return 0;
 }
 #undef K
@@ -472,7 +457,6 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
          */
         if (p->flags & PF_EXITING) {
                 set_tsk_thread_flag(p, TIF_MEMDIE);
-                boost_dying_task_prio(p, mem);
                 return 0;
         }
 
@@ -491,6 +475,8 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
                 list_for_each_entry(child, &t->children, sibling) {
                         unsigned int child_points;
 
+                        if (child->mm == p->mm)
+                                continue;
                         /*
                          * oom_badness() returns 0 if the thread is unkillable
                          */
@@ -537,6 +523,16 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask)
         unsigned int points = 0;
         struct task_struct *p;
 
+        /*
+         * If current has a pending SIGKILL, then automatically select it.  The
+         * goal is to allow it to allocate so that it may quickly exit and free
+         * its memory.
+         */
+        if (fatal_signal_pending(current)) {
+                set_thread_flag(TIF_MEMDIE);
+                return;
+        }
+
         check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0, NULL);
         limit = mem_cgroup_get_limit(mem) >> PAGE_SHIFT;
         read_lock(&tasklist_lock);
@@ -689,7 +685,6 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
          */
         if (fatal_signal_pending(current)) {
                 set_thread_flag(TIF_MEMDIE);
-                boost_dying_task_prio(current, NULL);
                 return;
         }