oom: badness heuristic rewrite

This a complete rewrite of the oom killer's badness() heuristic which is
used to determine which task to kill in oom conditions.  The goal is to
make it as simple and predictable as possible so the results are better
understood and we end up killing the task which will lead to the most
memory freeing while still respecting the fine-tuning from userspace.

Instead of basing the heuristic on mm->total_vm for each task, the task's
rss and swap space is used instead.  This is a better indication of the
amount of memory that will be freeable if the oom killed task is chosen
and subsequently exits.  This helps specifically in cases where KDE or
GNOME is chosen for oom kill on desktop systems instead of a memory
hogging task.

The baseline for the heuristic is a proportion of memory that each task is
currently using in memory plus swap compared to the amount of "allowable"
memory.  "Allowable," in this sense, means the system-wide resources for
unconstrained oom conditions, the set of mempolicy nodes, the mems
attached to current's cpuset, or a memory controller's limit.  The
proportion is given on a scale of 0 (never kill) to 1000 (always kill),
roughly meaning that if a task has a badness() score of 500 that the task
consumes approximately 50% of allowable memory resident in RAM or in swap
space.

The proportion is always relative to the amount of "allowable" memory and
not the total amount of RAM systemwide so that mempolicies and cpusets may
operate in isolation; they shall not need to know the true size of the
machine on which they are running if they are bound to a specific set of
nodes or mems, respectively.

Root tasks are given 3% extra memory just like __vm_enough_memory()
provides in LSMs.  In the event of two tasks consuming similar amounts of
memory, it is generally better to save root's task.

Because of the change in the badness() heuristic's baseline, it is also
necessary to introduce a new user interface to tune it.  It's not possible
to redefine the meaning of /proc/pid/oom_adj with a new scale since the
ABI cannot be changed for backward compatability.  Instead, a new tunable,
/proc/pid/oom_score_adj, is added that ranges from -1000 to +1000.  It may
be used to polarize the heuristic such that certain tasks are never
considered for oom kill while others may always be considered.  The value
is added directly into the badness() score so a value of -500, for
example, means to discount 50% of its memory consumption in comparison to
other tasks either on the system, bound to the mempolicy, in the cpuset,
or sharing the same memory controller.

/proc/pid/oom_adj is changed so that its meaning is rescaled into the
units used by /proc/pid/oom_score_adj, and vice versa.  Changing one of
these per-task tunables will rescale the value of the other to an
equivalent meaning.  Although /proc/pid/oom_adj was originally defined as
a bitshift on the badness score, it now shares the same linear growth as
/proc/pid/oom_score_adj but with different granularity.  This is required
so the ABI is not broken with userspace applications and allows oom_adj to
be deprecated for future removal.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 23 insertions, 2 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 9f1afd36158..73564cac38c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -125,6 +125,8 @@ void mem_cgroup_update_file_mapped(struct page *page, int val);
 unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 						gfp_t gfp_mask, int nid,
 						int zid);
+u64 mem_cgroup_get_limit(struct mem_cgroup *mem);
+
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
 struct mem_cgroup;
 
@@ -304,6 +306,12 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 	return 0;
 }
 
+static inline
+u64 mem_cgroup_get_limit(struct mem_cgroup *mem)
+{
+	return 0;
+}
+
 #endif /* CONFIG_CGROUP_MEM_CONT */
 
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 40e5e3a6bc2..73b8d7b6dd1 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -1,14 +1,24 @@
 #ifndef __INCLUDE_LINUX_OOM_H
 #define __INCLUDE_LINUX_OOM_H
 
-/* /proc/<pid>/oom_adj set to -17 protects from the oom-killer */
+/*
+ * /proc/<pid>/oom_adj set to -17 protects from the oom-killer
+ */
 #define OOM_DISABLE (-17)
 /* inclusive */
 #define OOM_ADJUST_MIN (-16)
 #define OOM_ADJUST_MAX 15
 
+/*
+ * /proc/<pid>/oom_score_adj set to OOM_SCORE_ADJ_MIN disables oom killing for
+ * pid.
+ */
+#define OOM_SCORE_ADJ_MIN	(-1000)
+#define OOM_SCORE_ADJ_MAX	1000
+
 #ifdef __KERNEL__
 
+#include <linux/sched.h>
 #include <linux/types.h>
 #include <linux/nodemask.h>
 
@@ -27,6 +37,8 @@ enum oom_constraint {
 	CONSTRAINT_MEMCG,
 };
 
+extern unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
+			const nodemask_t *nodemask, unsigned long totalpages);
 extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9591907c4f7..ce160d68f5e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -621,7 +621,8 @@ struct signal_struct {
 	struct tty_audit_buf *tty_audit_buf;
 #endif
 
-	int oom_adj;	/* OOM kill score adjustment (bit shift) */
+	int oom_adj;		/* OOM kill score adjustment (bit shift) */
+	int oom_score_adj;	/* OOM kill score adjustment */
 };
 
 /* Context switch must be unlocked if interrupts are to be enabled */