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>

1 files changed, 90 insertions, 4 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 5949d0ac30f2..f923b728388a 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -63,6 +63,7 @@
 #include <linux/namei.h>
 #include <linux/mnt_namespace.h>
 #include <linux/mm.h>
+#include <linux/swap.h>
 #include <linux/rcupdate.h>
 #include <linux/kallsyms.h>
 #include <linux/stacktrace.h>
@@ -430,12 +431,11 @@ static const struct file_operations proc_lstats_operations = {
 static int proc_oom_score(struct task_struct *task, char *buffer)
 {
 	unsigned long points = 0;
-	struct timespec uptime;
 
-	do_posix_clock_monotonic_gettime(&uptime);
 	read_lock(&tasklist_lock);
 	if (pid_alive(task))
-		points = badness(task, NULL, NULL, uptime.tv_sec);
+		points = oom_badness(task, NULL, NULL,
+					totalram_pages + total_swap_pages);
 	read_unlock(&tasklist_lock);
 	return sprintf(buffer, "%lu\n", points);
 }
@@ -1038,7 +1038,15 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
 	}
 
 	task->signal->oom_adj = oom_adjust;
-
+	/*
+	 * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
+	 * value is always attainable.
+	 */
+	if (task->signal->oom_adj == OOM_ADJUST_MAX)
+		task->signal->oom_score_adj = OOM_SCORE_ADJ_MAX;
+	else
+		task->signal->oom_score_adj = (oom_adjust * OOM_SCORE_ADJ_MAX) /
+								-OOM_DISABLE;
 	unlock_task_sighand(task, &flags);
 	put_task_struct(task);
 
@@ -1051,6 +1059,82 @@ static const struct file_operations proc_oom_adjust_operations = {
 	.llseek		= generic_file_llseek,
 };
 
+static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+	char buffer[PROC_NUMBUF];
+	int oom_score_adj = OOM_SCORE_ADJ_MIN;
+	unsigned long flags;
+	size_t len;
+
+	if (!task)
+		return -ESRCH;
+	if (lock_task_sighand(task, &flags)) {
+		oom_score_adj = task->signal->oom_score_adj;
+		unlock_task_sighand(task, &flags);
+	}
+	put_task_struct(task);
+	len = snprintf(buffer, sizeof(buffer), "%d\n", oom_score_adj);
+	return simple_read_from_buffer(buf, count, ppos, buffer, len);
+}
+
+static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	char buffer[PROC_NUMBUF];
+	unsigned long flags;
+	long oom_score_adj;
+	int err;
+
+	memset(buffer, 0, sizeof(buffer));
+	if (count > sizeof(buffer) - 1)
+		count = sizeof(buffer) - 1;
+	if (copy_from_user(buffer, buf, count))
+		return -EFAULT;
+
+	err = strict_strtol(strstrip(buffer), 0, &oom_score_adj);
+	if (err)
+		return -EINVAL;
+	if (oom_score_adj < OOM_SCORE_ADJ_MIN ||
+			oom_score_adj > OOM_SCORE_ADJ_MAX)
+		return -EINVAL;
+
+	task = get_proc_task(file->f_path.dentry->d_inode);
+	if (!task)
+		return -ESRCH;
+	if (!lock_task_sighand(task, &flags)) {
+		put_task_struct(task);
+		return -ESRCH;
+	}
+	if (oom_score_adj < task->signal->oom_score_adj &&
+			!capable(CAP_SYS_RESOURCE)) {
+		unlock_task_sighand(task, &flags);
+		put_task_struct(task);
+		return -EACCES;
+	}
+
+	task->signal->oom_score_adj = oom_score_adj;
+	/*
+	 * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is
+	 * always attainable.
+	 */
+	if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+		task->signal->oom_adj = OOM_DISABLE;
+	else
+		task->signal->oom_adj = (oom_score_adj * OOM_ADJUST_MAX) /
+							OOM_SCORE_ADJ_MAX;
+	unlock_task_sighand(task, &flags);
+	put_task_struct(task);
+	return count;
+}
+
+static const struct file_operations proc_oom_score_adj_operations = {
+	.read		= oom_score_adj_read,
+	.write		= oom_score_adj_write,
+};
+
 #ifdef CONFIG_AUDITSYSCALL
 #define TMPBUFLEN 21
 static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
@@ -2623,6 +2707,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #endif
 	INF("oom_score",  S_IRUGO, proc_oom_score),
 	REG("oom_adj",    S_IRUGO|S_IWUSR, proc_oom_adjust_operations),
+	REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
 	REG("loginuid",   S_IWUSR|S_IRUGO, proc_loginuid_operations),
 	REG("sessionid",  S_IRUGO, proc_sessionid_operations),
@@ -2957,6 +3042,7 @@ static const struct pid_entry tid_base_stuff[] = {
 #endif
 	INF("oom_score", S_IRUGO, proc_oom_score),
 	REG("oom_adj",   S_IRUGO|S_IWUSR, proc_oom_adjust_operations),
+	REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
 	REG("loginuid",  S_IWUSR|S_IRUGO, proc_loginuid_operations),
 	REG("sessionid",  S_IRUSR, proc_sessionid_operations),