From 9b4d1cbef8f41aff2b3e4ca31f566c071fe601de Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 22 Sep 2009 16:45:34 -0700
Subject: [PATCH] proc_flush_task: flush /proc/tid/task/pid when a sub-thread
 exits

The exiting sub-thread flushes /proc/pid only, but this doesn't buy too
much: ps and friends mostly use /proc/tid/task/pid.

Remove "if (thread_group_leader())" checks from proc_flush_task() path,
this means we always remove /proc/tid/task/pid dentry on exit, and this
actually matches the comment above proc_flush_task().

The test-case:

	static void* tfunc(void *arg)
	{
		char name[256];

		sprintf(name, "/proc/%d/task/%ld/status", getpid(), gettid());
		close(open(name, O_RDONLY));

		return NULL;
	}

	int main(void)
	{
		pthread_t t;

		for (;;) {
			if (!pthread_create(&t, NULL, &tfunc, NULL))
				pthread_join(t, NULL);
		}
	}

slabtop shows that pid/proc_inode_cache/etc grow quickly and
"indefinitely" until the task is killed or shrink_slab() is called, not
good.  And the main thread needs a lot of time to exit.

The same can happen if something like "ps -efL" runs continuously, while
some application spawns short-living threads.

Reported-by: "James M. Leddy" <jleddy@redhat.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Dominic Duval <dduval@redhat.com>
Cc: Frank Hirtz <fhirtz@redhat.com>
Cc: "Fuller, Johnray" <Johnray.Fuller@gs.com>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Paul Batkowski <pbatkowski@redhat.com>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/base.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 69bb703..5bc5870 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2604,9 +2604,6 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
 		dput(dentry);
 	}
 
-	if (tgid == 0)
-		goto out;
-
 	name.name = buf;
 	name.len = snprintf(buf, sizeof(buf), "%d", tgid);
 	leader = d_hash_and_lookup(mnt->mnt_root, &name);
@@ -2663,17 +2660,16 @@ out:
 void proc_flush_task(struct task_struct *task)
 {
 	int i;
-	struct pid *pid, *tgid = NULL;
+	struct pid *pid, *tgid;
 	struct upid *upid;
 
 	pid = task_pid(task);
-	if (thread_group_leader(task))
-		tgid = task_tgid(task);
+	tgid = task_tgid(task);
 
 	for (i = 0; i <= pid->level; i++) {
 		upid = &pid->numbers[i];
 		proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr,
-			tgid ? tgid->numbers[i].nr : 0);
+					tgid->numbers[i].nr);
 	}
 
 	upid = &pid->numbers[pid->level];
-- 
2.7.4