[PATCH AUTOSEL 5.4 01/73] cgroup-v1: cgroup_pidlist_next should update position index

[PATCH AUTOSEL 5.4 01/73] cgroup-v1: cgroup_pidlist_next should update position index

[Sasha Levin]

From: Vasily Averin <vvs@virtuozzo.com>

[ Upstream commit db8dd9697238be70a6b4f9d0284cd89f59c0e070 ]

if seq_file .next fuction does not change position index,
read after some lseek can generate unexpected output.

 # mount | grep cgroup
 # dd if=/mnt/cgroup.procs bs=1  # normal output
...
1294
1295
1296
1304
1382
584+0 records in
584+0 records out
584 bytes copied

dd: /mnt/cgroup.procs: cannot skip to specified offset
83  <<< generates end of last line
1383  <<< ... and whole last line once again
0+1 records in
0+1 records out
8 bytes copied

dd: /mnt/cgroup.procs: cannot skip to specified offset
1386  <<< generates last line anyway
0+1 records in
0+1 records out
5 bytes copied

https://bugzilla.kernel.org/show_bug.cgi?id=206283
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/cgroup/cgroup-v1.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 7f83f4121d8d0..2db582706ec5c 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -473,6 +473,7 @@ static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 	 */
 	p++;
 	if (p >= end) {
+		(*pos)++;
 		return NULL;
 	} else {
 		*pos = *p;
-- 
2.20.1

[PATCH AUTOSEL 5.4 02/73] cgroup: Iterate tasks that did not finish do_exit()

[Sasha Levin]

From: Michal Koutný <mkoutny-IBi9RG/b67k@public.gmane.org>

[ Upstream commit 9c974c77246460fa6a92c18554c3311c8c83c160 ]

PF_EXITING is set earlier than actual removal from css_set when a task
is exitting. This can confuse cgroup.procs readers who see no PF_EXITING
tasks, however, rmdir is checking against css_set membership so it can
transitionally fail with EBUSY.

Fix this by listing tasks that weren't unlinked from css_set active
lists.
It may happen that other users of the task iterator (without
CSS_TASK_ITER_PROCS) spot a PF_EXITING task before cgroup_exit(). This
is equal to the state before commit c03cd7738a83 ("cgroup: Include dying
leaders with live threads in PROCS iterations") but it may be reviewed
later.

Reported-by: Suren Baghdasaryan <surenb-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Fixes: c03cd7738a83 ("cgroup: Include dying leaders with live threads in PROCS iterations")
Signed-off-by: Michal Koutný <mkoutny-IBi9RG/b67k@public.gmane.org>
Signed-off-by: Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
Signed-off-by: Sasha Levin <sashal-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
---
 include/linux/cgroup.h |  1 +
 kernel/cgroup/cgroup.c | 23 ++++++++++++++++-------
 2 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3ba3e6da13a6f..57577075d2049 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -62,6 +62,7 @@ struct css_task_iter {
 	struct list_head		*mg_tasks_head;
 	struct list_head		*dying_tasks_head;
 
+	struct list_head		*cur_tasks_head;
 	struct css_set			*cur_cset;
 	struct css_set			*cur_dcset;
 	struct task_struct		*cur_task;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 595c52d59f310..a1236b1b80383 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4461,12 +4461,16 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 		}
 	} while (!css_set_populated(cset) && list_empty(&cset->dying_tasks));
 
-	if (!list_empty(&cset->tasks))
+	if (!list_empty(&cset->tasks)) {
 		it->task_pos = cset->tasks.next;
-	else if (!list_empty(&cset->mg_tasks))
+		it->cur_tasks_head = &cset->tasks;
+	} else if (!list_empty(&cset->mg_tasks)) {
 		it->task_pos = cset->mg_tasks.next;
-	else
+		it->cur_tasks_head = &cset->mg_tasks;
+	} else {
 		it->task_pos = cset->dying_tasks.next;
+		it->cur_tasks_head = &cset->dying_tasks;
+	}
 
 	it->tasks_head = &cset->tasks;
 	it->mg_tasks_head = &cset->mg_tasks;
@@ -4524,10 +4528,14 @@ static void css_task_iter_advance(struct css_task_iter *it)
 		else
 			it->task_pos = it->task_pos->next;
 
-		if (it->task_pos == it->tasks_head)
+		if (it->task_pos == it->tasks_head) {
 			it->task_pos = it->mg_tasks_head->next;
-		if (it->task_pos == it->mg_tasks_head)
+			it->cur_tasks_head = it->mg_tasks_head;
+		}
+		if (it->task_pos == it->mg_tasks_head) {
 			it->task_pos = it->dying_tasks_head->next;
+			it->cur_tasks_head = it->dying_tasks_head;
+		}
 		if (it->task_pos == it->dying_tasks_head)
 			css_task_iter_advance_css_set(it);
 	} else {
@@ -4546,11 +4554,12 @@ static void css_task_iter_advance(struct css_task_iter *it)
 			goto repeat;
 
 		/* and dying leaders w/o live member threads */
-		if (!atomic_read(&task->signal->live))
+		if (it->cur_tasks_head == it->dying_tasks_head &&
+		    !atomic_read(&task->signal->live))
 			goto repeat;
 	} else {
 		/* skip all dying ones */
-		if (task->flags & PF_EXITING)
+		if (it->cur_tasks_head == it->dying_tasks_head)
 			goto repeat;
 	}
 }
-- 
2.20.1

[PATCH AUTOSEL 5.4 25/73] cgroup1: don't call release_agent when it is ""

[Sasha Levin]

From: Tycho Andersen <tycho@tycho.ws>

[ Upstream commit 2e5383d7904e60529136727e49629a82058a5607 ]

Older (and maybe current) versions of systemd set release_agent to "" when
shutting down, but do not set notify_on_release to 0.

Since 64e90a8acb85 ("Introduce STATIC_USERMODEHELPER to mediate
call_usermodehelper()"), we filter out such calls when the user mode helper
path is "". However, when used in conjunction with an actual (i.e. non "")
STATIC_USERMODEHELPER, the path is never "", so the real usermode helper
will be called with argv[0] == "".

Let's avoid this by not invoking the release_agent when it is "".

Signed-off-by: Tycho Andersen <tycho@tycho.ws>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/cgroup/cgroup-v1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 2db582706ec5c..f684c82efc2ea 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -784,7 +784,7 @@ void cgroup1_release_agent(struct work_struct *work)
 
 	pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
 	agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
-	if (!pathbuf || !agentbuf)
+	if (!pathbuf || !agentbuf || !strlen(agentbuf))
 		goto out;
 
 	spin_lock_irq(&css_set_lock);
-- 
2.20.1