mm, oom: fix race when specifying a thread as the oom origin

test_set_oom_score_adj() and compare_swap_oom_score_adj() are used to
specify that current should be killed first if an oom condition occurs in
between the two calls.

The usage is

	short oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
	...
	compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj);

to store the thread's oom_score_adj, temporarily change it to the maximum
score possible, and then restore the old value if it is still the same.

This happens to still be racy, however, if the user writes
OOM_SCORE_ADJ_MAX to /proc/pid/oom_score_adj in between the two calls.
The compare_swap_oom_score_adj() will then incorrectly reset the old value
prior to the write of OOM_SCORE_ADJ_MAX.

To fix this, introduce a new oom_flags_t member in struct signal_struct
that will be used for per-thread oom killer flags.  KSM and swapoff can
now use a bit in this member to specify that threads should be killed
first in oom conditions without playing around with oom_score_adj.

This also allows the correct oom_score_adj to always be shown when reading
/proc/pid/oom_score.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Cc: Anton Vorontsov <anton.vorontsov@linaro.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 19 insertions, 2 deletions

diff --git a/include/linux/oom.h b/include/linux/oom.h
index 922dab164eb0..da60007075b5 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -29,8 +29,23 @@ enum oom_scan_t {
 	OOM_SCAN_SELECT,	/* always select this thread first */
 };
 
-extern void compare_swap_oom_score_adj(short old_val, short new_val);
-extern short test_set_oom_score_adj(short new_val);
+/* Thread is the potential origin of an oom condition; kill first on oom */
+#define OOM_FLAG_ORIGIN		((__force oom_flags_t)0x1)
+
+static inline void set_current_oom_origin(void)
+{
+	current->signal->oom_flags |= OOM_FLAG_ORIGIN;
+}
+
+static inline void clear_current_oom_origin(void)
+{
+	current->signal->oom_flags &= ~OOM_FLAG_ORIGIN;
+}
+
+static inline bool oom_task_origin(const struct task_struct *p)
+{
+	return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN);
+}
 
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ed30456152da..3e387df065fc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -631,6 +631,7 @@ struct signal_struct {
 	struct rw_semaphore group_rwsem;
 #endif
 
+	oom_flags_t oom_flags;
 	short oom_score_adj;		/* OOM kill score adjustment */
 	short oom_score_adj_min;	/* OOM kill score adjustment min value.
 					 * Only settable by CAP_SYS_RESOURCE. */
diff --git a/include/linux/types.h b/include/linux/types.h
index 1cc0e4b9a048..4d118ba11349 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -156,6 +156,7 @@ typedef u32 dma_addr_t;
 #endif
 typedef unsigned __bitwise__ gfp_t;
 typedef unsigned __bitwise__ fmode_t;
+typedef unsigned __bitwise__ oom_flags_t;
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
 typedef u64 phys_addr_t;