The patch titled
Subject: proc, oom: drop bogus sighand lock
has been added to the -mm tree. Its filename is
proc-oom-drop-bogus-sighand-lock.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/proc-oom-drop-bogus-sighand-lock.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/proc-oom-drop-bogus-sighand-lock.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 ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Michal Hocko <mhocko@xxxxxxxx>
Subject: proc, oom: drop bogus sighand lock
Oleg has pointed out that can simplify both oom_adj_{read,write} and
oom_score_adj_{read,write} even further and drop the sighand lock. The
main purpose of the lock was to protect p->signal from going away but this
will not happen since ea6d290ca34c ("signals: make task_struct->signal
immutable/refcountable").
The other role of the lock was to synchronize different writers,
especially those with CAP_SYS_RESOURCE. Introduce a mutex for this
purpose. Later patches will need this lock anyway.
Suggested-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/1466426628-15074-3-git-send-email-mhocko@xxxxxxxxxx
Signed-off-by: Michal Hocko <mhocko@xxxxxxxx>
Acked-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/proc/base.c | 51 +++++++++++++++--------------------------------
1 file changed, 17 insertions(+), 34 deletions(-)
diff -puN fs/proc/base.c~proc-oom-drop-bogus-sighand-lock fs/proc/base.c
--- a/fs/proc/base.c~proc-oom-drop-bogus-sighand-lock
+++ a/fs/proc/base.c
@@ -1024,23 +1024,21 @@ static ssize_t oom_adj_read(struct file
char buffer[PROC_NUMBUF];
int oom_adj = OOM_ADJUST_MIN;
size_t len;
- unsigned long flags;
if (!task)
return -ESRCH;
- if (lock_task_sighand(task, &flags)) {
- if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
- oom_adj = OOM_ADJUST_MAX;
- else
- oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
- OOM_SCORE_ADJ_MAX;
- unlock_task_sighand(task, &flags);
- }
+ if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
+ oom_adj = OOM_ADJUST_MAX;
+ else
+ oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
+ OOM_SCORE_ADJ_MAX;
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
+static DEFINE_MUTEX(oom_adj_mutex);
+
/*
* /proc/pid/oom_adj exists solely for backwards compatibility with previous
* kernels. The effective policy is defined by oom_score_adj, which has a
@@ -1057,7 +1055,6 @@ static ssize_t oom_adj_write(struct file
struct task_struct *task;
char buffer[PROC_NUMBUF];
int oom_adj;
- unsigned long flags;
int err;
memset(buffer, 0, sizeof(buffer));
@@ -1083,11 +1080,6 @@ static ssize_t oom_adj_write(struct file
goto out;
}
- if (!lock_task_sighand(task, &flags)) {
- err = -ESRCH;
- goto err_put_task;
- }
-
/*
* Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
* value is always attainable.
@@ -1097,10 +1089,11 @@ static ssize_t oom_adj_write(struct file
else
oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
+ mutex_lock(&oom_adj_mutex);
if (oom_adj < task->signal->oom_score_adj &&
!capable(CAP_SYS_RESOURCE)) {
err = -EACCES;
- goto err_sighand;
+ goto err_unlock;
}
/*
@@ -1113,9 +1106,8 @@ static ssize_t oom_adj_write(struct file
task->signal->oom_score_adj = oom_adj;
trace_oom_score_adj_update(task);
-err_sighand:
- unlock_task_sighand(task, &flags);
-err_put_task:
+err_unlock:
+ mutex_unlock(&oom_adj_mutex);
put_task_struct(task);
out:
return err < 0 ? err : count;
@@ -1133,15 +1125,11 @@ static ssize_t oom_score_adj_read(struct
struct task_struct *task = get_proc_task(file_inode(file));
char buffer[PROC_NUMBUF];
short 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);
- }
+ oom_score_adj = task->signal->oom_score_adj;
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj);
return simple_read_from_buffer(buf, count, ppos, buffer, len);
@@ -1152,7 +1140,6 @@ static ssize_t oom_score_adj_write(struc
{
struct task_struct *task;
char buffer[PROC_NUMBUF];
- unsigned long flags;
int oom_score_adj;
int err;
@@ -1179,25 +1166,21 @@ static ssize_t oom_score_adj_write(struc
goto out;
}
- if (!lock_task_sighand(task, &flags)) {
- err = -ESRCH;
- goto err_put_task;
- }
-
+ mutex_lock(&oom_adj_mutex);
if ((short)oom_score_adj < task->signal->oom_score_adj_min &&
!capable(CAP_SYS_RESOURCE)) {
err = -EACCES;
- goto err_sighand;
+ goto err_unlock;
}
task->signal->oom_score_adj = (short)oom_score_adj;
if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
task->signal->oom_score_adj_min = (short)oom_score_adj;
+
trace_oom_score_adj_update(task);
-err_sighand:
- unlock_task_sighand(task, &flags);
-err_put_task:
+err_unlock:
+ mutex_unlock(&oom_adj_mutex);
put_task_struct(task);
out:
return err < 0 ? err : count;
_
Patches currently in -mm which might be from mhocko@xxxxxxxx are
tree-wide-get-rid-of-__gfp_repeat-for-order-0-allocations-part-i.patch
x86-get-rid-of-superfluous-__gfp_repeat.patch
x86-efi-get-rid-of-superfluous-__gfp_repeat.patch
arm64-get-rid-of-superfluous-__gfp_repeat.patch
arc-get-rid-of-superfluous-__gfp_repeat.patch
mips-get-rid-of-superfluous-__gfp_repeat.patch
nios2-get-rid-of-superfluous-__gfp_repeat.patch
parisc-get-rid-of-superfluous-__gfp_repeat.patch
score-get-rid-of-superfluous-__gfp_repeat.patch
powerpc-get-rid-of-superfluous-__gfp_repeat.patch
sparc-get-rid-of-superfluous-__gfp_repeat.patch
s390-get-rid-of-superfluous-__gfp_repeat.patch
sh-get-rid-of-superfluous-__gfp_repeat.patch
tile-get-rid-of-superfluous-__gfp_repeat.patch
unicore32-get-rid-of-superfluous-__gfp_repeat.patch
jbd2-get-rid-of-superfluous-__gfp_repeat.patch
arm-get-rid-of-superfluous-__gfp_repeat.patch
slab-make-gfp_slab_bug_mask-information-more-human-readable.patch
slab-do-not-panic-on-invalid-gfp_mask.patch
mm-oom_reaper-make-sure-that-mmput_async-is-called-only-when-memory-was-reaped.patch
mm-memcg-use-consistent-gfp-flags-during-readahead.patch
mm-memcg-use-consistent-gfp-flags-during-readahead-fix.patch
proc-oom-drop-bogus-task_lock-and-mm-check.patch
proc-oom-drop-bogus-sighand-lock.patch
proc-oom_adj-extract-oom_score_adj-setting-into-a-helper.patch
mm-oom_adj-make-sure-processes-sharing-mm-have-same-view-of-oom_score_adj.patch
mm-oom-skip-vforked-tasks-from-being-selected.patch
mm-oom-kill-all-tasks-sharing-the-mm.patch
mm-oom-fortify-task_will_free_mem.patch
mm-oom-task_will_free_mem-should-skip-oom_reaped-tasks.patch
mm-oom_reaper-do-not-attempt-to-reap-a-task-more-than-twice.patch
mm-oom-hide-mm-which-is-shared-with-kthread-or-global-init.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
