oom: replace PF_OOM_ORIGIN with toggling oom_score_adj

There's a kernel-wide shortage of per-process flags, so it's always
helpful to trim one when possible without incurring a significant penalty.
 It's even more important when you're planning on adding a per- process
flag yourself, which I plan to do shortly for transparent hugepages.

PF_OOM_ORIGIN is used by ksm and swapoff to prefer current since it has a
tendency to allocate large amounts of memory and should be preferred for
killing over other tasks.  We'd rather immediately kill the task making
the errant syscall rather than penalizing an innocent task.

This patch removes PF_OOM_ORIGIN since its behavior is equivalent to
setting the process's oom_score_adj to OOM_SCORE_ADJ_MAX.

The process's old oom_score_adj is stored and then set to
OOM_SCORE_ADJ_MAX during the time it used to have PF_OOM_ORIGIN.  The old
value is then reinstated when the process should no longer be considered a
high priority for oom killing.

Signed-off-by: David Rientjes <rientjes@google.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Izik Eidus <ieidus@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 38 insertions, 14 deletions

diff --git a/include/linux/oom.h b/include/linux/oom.h
index 5e3aa83..4952fb8 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -40,6 +40,8 @@ enum oom_constraint {
 	CONSTRAINT_MEMCG,
 };
 
+extern int test_set_oom_score_adj(int new_val);
+
 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);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index aaf71e0..44b8faa 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1753,7 +1753,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define PF_FROZEN	0x00010000	/* frozen for system suspend */
 #define PF_FSTRANS	0x00020000	/* inside a filesystem transaction */
 #define PF_KSWAPD	0x00040000	/* I am kswapd */
-#define PF_OOM_ORIGIN	0x00080000	/* Allocating much memory to others */
 #define PF_LESS_THROTTLE 0x00100000	/* Throttle me less: I clean memory */
 #define PF_KTHREAD	0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE	0x00400000	/* randomize virtual address space */
diff --git a/mm/ksm.c b/mm/ksm.c
index 942dfc7..d708b3e 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -35,6 +35,7 @@
 #include <linux/ksm.h>
 #include <linux/hash.h>
 #include <linux/freezer.h>
+#include <linux/oom.h>
 
 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -1894,9 +1895,11 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (ksm_run != flags) {
 		ksm_run = flags;
 		if (flags & KSM_RUN_UNMERGE) {
-			current->flags |= PF_OOM_ORIGIN;
+			int oom_score_adj;
+
+			oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
 			err = unmerge_and_remove_all_rmap_items();
-			current->flags &= ~PF_OOM_ORIGIN;
+			test_set_oom_score_adj(oom_score_adj);
 			if (err) {
 				ksm_run = KSM_RUN_STOP;
 				count = err;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index f52e85c..e4b0991 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -38,6 +38,33 @@ int sysctl_oom_kill_allocating_task;
 int sysctl_oom_dump_tasks = 1;
 static DEFINE_SPINLOCK(zone_scan_lock);
 
+/**
+ * test_set_oom_score_adj() - set current's oom_score_adj and return old value
+ * @new_val: new oom_score_adj value
+ *
+ * Sets the oom_score_adj value for current to @new_val with proper
+ * synchronization and returns the old value.  Usually used to temporarily
+ * set a value, save the old value in the caller, and then reinstate it later.
+ */
+int test_set_oom_score_adj(int new_val)
+{
+	struct sighand_struct *sighand = current->sighand;
+	int old_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;
+	}
+	spin_unlock_irq(&sighand->siglock);
+
+	return old_val;
+}
+
 #ifdef CONFIG_NUMA
 /**
  * has_intersects_mems_allowed() - check task eligiblity for kill
@@ -155,15 +182,6 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 	}
 
 	/*
-	 * When the PF_OOM_ORIGIN bit is set, it indicates the task should have
-	 * priority for oom killing.
-	 */
-	if (p->flags & PF_OOM_ORIGIN) {
-		task_unlock(p);
-		return 1000;
-	}
-
-	/*
 	 * The memory controller may have a limit of 0 bytes, so avoid a divide
 	 * by zero, if necessary.
 	 */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 8c6b3ce..d537d29 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -31,6 +31,7 @@
 #include <linux/syscalls.h>
 #include <linux/memcontrol.h>
 #include <linux/poll.h>
+#include <linux/oom.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -1555,6 +1556,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	struct address_space *mapping;
 	struct inode *inode;
 	char *pathname;
+	int oom_score_adj;
 	int i, type, prev;
 	int err;
 
@@ -1613,9 +1615,9 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	p->flags &= ~SWP_WRITEOK;
 	spin_unlock(&swap_lock);
 
-	current->flags |= PF_OOM_ORIGIN;
+	oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
 	err = try_to_unuse(type);
-	current->flags &= ~PF_OOM_ORIGIN;
+	test_set_oom_score_adj(oom_score_adj);
 
 	if (err) {
 		/*