The patch titled
oom: move oom_adj value from task_struct to signal_struct
has been added to the -mm tree. Its filename is
oom-move-oom_adj-value-from-task_struct-to-signal_struct.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: oom: move oom_adj value from task_struct to signal_struct
From: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Currently, OOM logic callflow is here.
__out_of_memory()
select_bad_process() for each task
badness() calculate badness of one task
oom_kill_process() search child
oom_kill_task() kill target task and mm shared tasks with it
example, process-A have two thread, thread-A and thread-B and it have very
fat memory and each thread have following oom_adj and oom_score.
thread-A: oom_adj = OOM_DISABLE, oom_score = 0
thread-B: oom_adj = 0, oom_score = very-high
Then, select_bad_process() select thread-B, but oom_kill_task() refuse
kill the task because thread-A have OOM_DISABLE. Thus __out_of_memory()
call select_bad_process() again. but select_bad_process() select the same
task. It mean kernel fall in livelock.
The fact is, select_bad_process() must select killable task. otherwise
OOM logic go into livelock.
And root cause is, oom_adj shouldn't be per-thread value. it should be
per-process value because OOM-killer kill a process, not thread. Thus
This patch moves oomkilladj (now more appropriately named oom_adj) from
struct task_struct to struct signal_struct. it naturally prevent
select_bad_process() choose wrong task.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/proc/base.c | 24 ++++++++++++++++++++----
include/linux/sched.h | 3 ++-
kernel/fork.c | 2 ++
mm/oom_kill.c | 34 +++++++++++++++-------------------
4 files changed, 39 insertions(+), 24 deletions(-)
diff -puN fs/proc/base.c~oom-move-oom_adj-value-from-task_struct-to-signal_struct fs/proc/base.c
--- a/fs/proc/base.c~oom-move-oom_adj-value-from-task_struct-to-signal_struct
+++ a/fs/proc/base.c
@@ -999,11 +999,17 @@ static ssize_t oom_adjust_read(struct fi
struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
char buffer[PROC_NUMBUF];
size_t len;
- int oom_adjust;
+ int oom_adjust = OOM_DISABLE;
+ unsigned long flags;
if (!task)
return -ESRCH;
- oom_adjust = task->oomkilladj;
+
+ if (lock_task_sighand(task, &flags)) {
+ oom_adjust = task->signal->oom_adj;
+ unlock_task_sighand(task, &flags);
+ }
+
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust);
@@ -1017,6 +1023,7 @@ static ssize_t oom_adjust_write(struct f
struct task_struct *task;
char buffer[PROC_NUMBUF], *end;
int oom_adjust;
+ unsigned long flags;
memset(buffer, 0, sizeof(buffer));
if (count > sizeof(buffer) - 1)
@@ -1032,11 +1039,20 @@ static ssize_t oom_adjust_write(struct f
task = get_proc_task(file->f_path.dentry->d_inode);
if (!task)
return -ESRCH;
- if (oom_adjust < task->oomkilladj && !capable(CAP_SYS_RESOURCE)) {
+ if (!lock_task_sighand(task, &flags)) {
+ put_task_struct(task);
+ return -ESRCH;
+ }
+
+ if (oom_adjust < task->signal->oom_adj && !capable(CAP_SYS_RESOURCE)) {
+ unlock_task_sighand(task, &flags);
put_task_struct(task);
return -EACCES;
}
- task->oomkilladj = oom_adjust;
+
+ task->signal->oom_adj = oom_adjust;
+
+ unlock_task_sighand(task, &flags);
put_task_struct(task);
if (end - buffer == 0)
return -EIO;
diff -puN include/linux/sched.h~oom-move-oom_adj-value-from-task_struct-to-signal_struct include/linux/sched.h
--- a/include/linux/sched.h~oom-move-oom_adj-value-from-task_struct-to-signal_struct
+++ a/include/linux/sched.h
@@ -652,6 +652,8 @@ struct signal_struct {
unsigned audit_tty;
struct tty_audit_buf *tty_audit_buf;
#endif
+
+ int oom_adj; /* OOM kill score adjustment (bit shift) */
};
/* Context switch must be unlocked if interrupts are to be enabled */
@@ -1220,7 +1222,6 @@ struct task_struct {
* a short time
*/
unsigned char fpu_counter;
- s8 oomkilladj; /* OOM kill score adjustment (bit shift). */
#ifdef CONFIG_BLK_DEV_IO_TRACE
unsigned int btrace_seq;
#endif
diff -puN kernel/fork.c~oom-move-oom_adj-value-from-task_struct-to-signal_struct kernel/fork.c
--- a/kernel/fork.c~oom-move-oom_adj-value-from-task_struct-to-signal_struct
+++ a/kernel/fork.c
@@ -886,6 +886,8 @@ static int copy_signal(unsigned long clo
tty_audit_fork(sig);
+ sig->oom_adj = current->signal->oom_adj;
+
return 0;
}
diff -puN mm/oom_kill.c~oom-move-oom_adj-value-from-task_struct-to-signal_struct mm/oom_kill.c
--- a/mm/oom_kill.c~oom-move-oom_adj-value-from-task_struct-to-signal_struct
+++ a/mm/oom_kill.c
@@ -58,6 +58,10 @@ unsigned long badness(struct task_struct
unsigned long points, cpu_time, run_time;
struct mm_struct *mm;
struct task_struct *child;
+ int oom_adj = p->signal->oom_adj;
+
+ if (oom_adj == OOM_DISABLE)
+ return 0;
task_lock(p);
mm = p->mm;
@@ -148,15 +152,15 @@ unsigned long badness(struct task_struct
points /= 8;
/*
- * Adjust the score by oomkilladj.
+ * Adjust the score by oom_adj.
*/
- if (p->oomkilladj) {
- if (p->oomkilladj > 0) {
+ if (oom_adj) {
+ if (oom_adj > 0) {
if (!points)
points = 1;
- points <<= p->oomkilladj;
+ points <<= oom_adj;
} else
- points >>= -(p->oomkilladj);
+ points >>= -(oom_adj);
}
#ifdef DEBUG
@@ -251,7 +255,7 @@ static struct task_struct *select_bad_pr
*ppoints = ULONG_MAX;
}
- if (p->oomkilladj == OOM_DISABLE)
+ if (p->signal->oom_adj == OOM_DISABLE)
continue;
points = badness(p, uptime.tv_sec);
@@ -304,7 +308,7 @@ static void dump_tasks(const struct mem_
}
printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n",
p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm,
- get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj,
+ get_mm_rss(mm), (int)task_cpu(p), p->signal->oom_adj,
p->comm);
task_unlock(p);
} while_each_thread(g, p);
@@ -359,18 +363,9 @@ static int oom_kill_task(struct task_str
* change to NULL at any time since we do not hold task_lock(p).
* However, this is of no concern to us.
*/
-
- if (mm == NULL)
+ if (!mm || p->signal->oom_adj == OOM_DISABLE)
return 1;
- /*
- * Don't kill the process if any threads are set to OOM_DISABLE
- */
- do_each_thread(g, q) {
- if (q->mm == mm && q->oomkilladj == OOM_DISABLE)
- return 1;
- } while_each_thread(g, q);
-
__oom_kill_task(p, 1);
/*
@@ -394,8 +389,9 @@ static int oom_kill_process(struct task_
if (printk_ratelimit()) {
printk(KERN_WARNING "%s invoked oom-killer: "
- "gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
- current->comm, gfp_mask, order, current->oomkilladj);
+ "gfp_mask=0x%x, order=%d, oom_adj=%d\n",
+ current->comm, gfp_mask, order,
+ current->signal->oom_adj);
task_lock(current);
cpuset_print_task_mems_allowed(current);
task_unlock(current);
_
Patches currently in -mm which might be from kosaki.motohiro@xxxxxxxxxxxxxx are
origin.patch
linux-next.patch
readahead-add-blk_run_backing_dev.patch
readahead-add-blk_run_backing_dev-fix.patch
readahead-add-blk_run_backing_dev-fix-fix-2.patch
mm-clean-up-page_remove_rmap.patch
mm-show_free_areas-display-slab-pages-in-two-separate-fields.patch
mm-oom-analysis-add-per-zone-statistics-to-show_free_areas.patch
mm-oom-analysis-add-buffer-cache-information-to-show_free_areas.patch
mm-oom-analysis-show-kernel-stack-usage-in-proc-meminfo-and-oom-log-output.patch
mm-oom-analysis-add-shmem-vmstat.patch
mm-rename-pgmoved-variable-in-shrink_active_list.patch
mm-shrink_inactive_list-nr_scan-accounting-fix-fix.patch
mm-vmstat-add-isolate-pages.patch
mm-vmstat-add-isolate-pages-fix.patch
vmscan-throttle-direct-reclaim-when-too-many-pages-are-isolated-already.patch
mm-remove-__addsub_zone_page_state.patch
mm-count-only-reclaimable-lru-pages-v2.patch
vmscan-dont-attempt-to-reclaim-anon-page-in-lumpy-reclaim-when-no-swap-space-is-avilable.patch
vmscan-move-clearpageactive-from-move_active_pages-to-shrink_active_list.patch
vmscan-kill-unnecessary-page-flag-test.patch
vmscan-kill-unnecessary-prefetch.patch
mm-perform-non-atomic-test-clear-of-pg_mlocked-on-free.patch
tracing-page-allocator-add-trace-events-for-page-allocation-and-page-freeing.patch
tracing-page-allocator-add-trace-event-for-page-traffic-related-to-the-buddy-lists.patch
mm-drop-unneeded-double-negations.patch
mm-introduce-page_lru_base_type.patch
mm-introduce-page_lru_base_type-fix.patch
mm-return-boolean-from-page_is_file_cache.patch
mm-return-boolean-from-page_has_private.patch
mm-document-is_page_cache_freeable.patch
mm-vmscan-rename-zone_nr_pages-to-zone_lru_nr_pages.patch
oom-move-oom_killer_enable-oom_killer_disable-to-where-they-belong.patch
mm-do-batched-scans-for-mem_cgroup.patch
mm-vmscan-remove-page_queue_congested-comment.patch
oom-move-oom_adj-value-from-task_struct-to-signal_struct.patch
oom-make-oom_score-to-per-process-value.patch
oom-oom_kill-doesnt-kill-vfork-parentor-child.patch
oom-fix-oom_adjust_write-input-sanity-check.patch
getrusage-fill-ru_maxrss-value.patch
getrusage-fill-ru_maxrss-value-update.patch
memory-controller-soft-limit-documentation-v9.patch
memory-controller-soft-limit-interface-v9.patch
memory-controller-soft-limit-organize-cgroups-v9.patch
memory-controller-soft-limit-organize-cgroups-v9-fix.patch
memory-controller-soft-limit-refactor-reclaim-flags-v9.patch
memory-controller-soft-limit-reclaim-on-contention-v9.patch
memory-controller-soft-limit-reclaim-on-contention-v9-fix.patch
memcg-improve-resource-counter-scalability.patch
memcg-improve-resource-counter-scalability-v5.patch
fs-symlink-write_begin-allocation-context-fix-reiser4-fix.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
