mm: memcg: handle non-error OOM situations more gracefully

Commit 3812c8c8f395 ("mm: memcg: do not trap chargers with full
callstack on OOM") assumed that only a few places that can trigger a
memcg OOM situation do not return VM_FAULT_OOM, like optional page cache
readahead.  But there are many more and it's impractical to annotate
them all.

First of all, we don't want to invoke the OOM killer when the failed
allocation is gracefully handled, so defer the actual kill to the end of
the fault handling as well.  This simplifies the code quite a bit for
added bonus.

Second, since a failed allocation might not be the abrupt end of the
fault, the memcg OOM handler needs to be re-entrant until the fault
finishes for subsequent allocation attempts.  If an allocation is
attempted after the task already OOMed, allow it to bypass the limit so
that it can quickly finish the fault and invoke the OOM killer.

Reported-by: azurIt <azurit@pobox.sk>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 14 insertions, 43 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ecc82b37c4c..b3e7a667e03 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -137,47 +137,24 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
 extern void mem_cgroup_replace_page_cache(struct page *oldpage,
 					struct page *newpage);
 
-/**
- * mem_cgroup_toggle_oom - toggle the memcg OOM killer for the current task
- * @new: true to enable, false to disable
- *
- * Toggle whether a failed memcg charge should invoke the OOM killer
- * or just return -ENOMEM.  Returns the previous toggle state.
- *
- * NOTE: Any path that enables the OOM killer before charging must
- *       call mem_cgroup_oom_synchronize() afterward to finalize the
- *       OOM handling and clean up.
- */
-static inline bool mem_cgroup_toggle_oom(bool new)
+static inline void mem_cgroup_oom_enable(void)
 {
-	bool old;
-
-	old = current->memcg_oom.may_oom;
-	current->memcg_oom.may_oom = new;
-
-	return old;
+	WARN_ON(current->memcg_oom.may_oom);
+	current->memcg_oom.may_oom = 1;
 }
 
-static inline void mem_cgroup_enable_oom(void)
+static inline void mem_cgroup_oom_disable(void)
 {
-	bool old = mem_cgroup_toggle_oom(true);
-
-	WARN_ON(old == true);
-}
-
-static inline void mem_cgroup_disable_oom(void)
-{
-	bool old = mem_cgroup_toggle_oom(false);
-
-	WARN_ON(old == false);
+	WARN_ON(!current->memcg_oom.may_oom);
+	current->memcg_oom.may_oom = 0;
 }
 
 static inline bool task_in_memcg_oom(struct task_struct *p)
 {
-	return p->memcg_oom.in_memcg_oom;
+	return p->memcg_oom.memcg;
 }
 
-bool mem_cgroup_oom_synchronize(void);
+bool mem_cgroup_oom_synchronize(bool wait);
 
 #ifdef CONFIG_MEMCG_SWAP
 extern int do_swap_account;
@@ -402,16 +379,11 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page,
 {
 }
 
-static inline bool mem_cgroup_toggle_oom(bool new)
-{
-	return false;
-}
-
-static inline void mem_cgroup_enable_oom(void)
+static inline void mem_cgroup_oom_enable(void)
 {
 }
 
-static inline void mem_cgroup_disable_oom(void)
+static inline void mem_cgroup_oom_disable(void)
 {
 }
 
@@ -420,7 +392,7 @@ static inline bool task_in_memcg_oom(struct task_struct *p)
 	return false;
 }
 
-static inline bool mem_cgroup_oom_synchronize(void)
+static inline bool mem_cgroup_oom_synchronize(bool wait)
 {
 	return false;
 }
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6682da36b29..e27baeeda3f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1394,11 +1394,10 @@ struct task_struct {
 	} memcg_batch;
 	unsigned int memcg_kmem_skip_account;
 	struct memcg_oom_info {
+		struct mem_cgroup *memcg;
+		gfp_t gfp_mask;
+		int order;
 		unsigned int may_oom:1;
-		unsigned int in_memcg_oom:1;
-		unsigned int oom_locked:1;
-		int wakeups;
-		struct mem_cgroup *wait_on_memcg;
 	} memcg_oom;
 #endif
 #ifdef CONFIG_UPROBES