summaryrefslogtreecommitdiff
path: root/fs/proc/base.c
diff options
context:
space:
mode:
authorDavid Rientjes <rientjes@google.com>2009-06-16 15:32:56 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2009-06-16 19:47:43 -0700
commit2ff05b2b4eac2e63d345fc731ea151a060247f53 (patch)
tree1840bc2d3b381eca5d39869499339b0fcc6eabbf /fs/proc/base.c
parentc9e444103b5e7a5a3519f9913f59767f92e33baf (diff)
oom: move oom_adj value from task_struct to mm_struct
The per-task oom_adj value is a characteristic of its mm more than the task itself since it's not possible to oom kill any thread that shares the mm. If a task were to be killed while attached to an mm that could not be freed because another thread were set to OOM_DISABLE, it would have needlessly been terminated since there is no potential for future memory freeing. This patch moves oomkilladj (now more appropriately named oom_adj) from struct task_struct to struct mm_struct. This requires task_lock() on a task to check its oom_adj value to protect against exec, but it's already necessary to take the lock when dereferencing the mm to find the total VM size for the badness heuristic. This fixes a livelock if the oom killer chooses a task and another thread sharing the same memory has an oom_adj value of OOM_DISABLE. This occurs because oom_kill_task() repeatedly returns 1 and refuses to kill the chosen task while select_bad_process() will repeatedly choose the same task during the next retry. Taking task_lock() in select_bad_process() to check for OOM_DISABLE and in oom_kill_task() to check for threads sharing the same memory will be removed in the next patch in this series where it will no longer be necessary. Writing to /proc/pid/oom_adj for a kthread will now return -EINVAL since these threads are immune from oom killing already. They simply report an oom_adj value of OOM_DISABLE. Cc: Nick Piggin <npiggin@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/proc/base.c')
-rw-r--r--fs/proc/base.c19
1 files changed, 16 insertions, 3 deletions
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 1539e630c47d..3ce5ae9e3d2d 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1006,7 +1006,12 @@ static ssize_t oom_adjust_read(struct file *file, char __user *buf,
if (!task)
return -ESRCH;
- oom_adjust = task->oomkilladj;
+ task_lock(task);
+ if (task->mm)
+ oom_adjust = task->mm->oom_adj;
+ else
+ oom_adjust = OOM_DISABLE;
+ task_unlock(task);
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust);
@@ -1035,11 +1040,19 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
task = get_proc_task(file->f_path.dentry->d_inode);
if (!task)
return -ESRCH;
- if (oom_adjust < task->oomkilladj && !capable(CAP_SYS_RESOURCE)) {
+ task_lock(task);
+ if (!task->mm) {
+ task_unlock(task);
+ put_task_struct(task);
+ return -EINVAL;
+ }
+ if (oom_adjust < task->mm->oom_adj && !capable(CAP_SYS_RESOURCE)) {
+ task_unlock(task);
put_task_struct(task);
return -EACCES;
}
- task->oomkilladj = oom_adjust;
+ task->mm->oom_adj = oom_adjust;
+ task_unlock(task);
put_task_struct(task);
if (end - buffer == 0)
return -EIO;