- rel 3; v2 version of the patch

[packages/kernel.git] / kernel-small_fixes.patch

From: Shaohua Li <shli@fb.com>

Basically this is a copy of commit 001e4a8775f6(ext4: implement cgroup
writeback support). Tested with a fio test, verified writeback is
throttled against cgroup io.max write bandwidth, also verified moving
the fio test to another cgroup and the writeback is throttled against
new cgroup setting.

Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 fs/xfs/xfs_aops.c  | 2 ++
 fs/xfs/xfs_super.c | 1 +
 2 files changed, 3 insertions(+)

--- linux-4.19/fs/xfs/xfs_aops.c.org	2018-11-21 10:31:12.348955352 +0100
+++ linux-4.19/fs/xfs/xfs_aops.c	2018-11-21 10:34:35.241764742 +0100
@@ -613,8 +613,10 @@ xfs_add_to_ioend(
 			list_add(&wpc->ioend->io_list, iolist);
 		wpc->ioend = xfs_alloc_ioend(inode, wpc->io_type, offset,
 				bdev, sector);
+		wbc_init_bio(wbc, wpc->ioend->io_bio);
 	}
 
+	wbc_account_io(wbc, page, len);
 	if (!__bio_try_merge_page(wpc->ioend->io_bio, page, len, poff)) {
 		if (iop)
 			atomic_inc(&iop->write_count);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 584cf2d..aea3bc2 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1634,6 +1634,7 @@ xfs_fs_fill_super(
 	sb->s_max_links = XFS_MAXLINK;
 	sb->s_time_gran = 1;
 	set_posix_acl_flag(sb);
+	sb->s_iflags |= SB_I_CGROUPWB;
 
 	/* version 5 superblocks support inode version counters. */
 	if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
From e820d55cb99dd93ac2dc949cf486bb187e5cd70d Mon Sep 17 00:00:00 2001
From: Guoqing Jiang <gqjiang@suse.com>
Date: Wed, 19 Dec 2018 14:19:25 +0800
Subject: md: fix raid10 hang issue caused by barrier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When both regular IO and resync IO happen at the same time,
and if we also need to split regular. Then we can see tasks
hang due to barrier.

1. resync thread
[ 1463.757205] INFO: task md1_resync:5215 blocked for more than 480 seconds.
[ 1463.757207]       Not tainted 4.19.5-1-default #1
[ 1463.757209] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 1463.757212] md1_resync      D    0  5215      2 0x80000000
[ 1463.757216] Call Trace:
[ 1463.757223]  ? __schedule+0x29a/0x880
[ 1463.757231]  ? raise_barrier+0x8d/0x140 [raid10]
[ 1463.757236]  schedule+0x78/0x110
[ 1463.757243]  raise_barrier+0x8d/0x140 [raid10]
[ 1463.757248]  ? wait_woken+0x80/0x80
[ 1463.757257]  raid10_sync_request+0x1f6/0x1e30 [raid10]
[ 1463.757265]  ? _raw_spin_unlock_irq+0x22/0x40
[ 1463.757284]  ? is_mddev_idle+0x125/0x137 [md_mod]
[ 1463.757302]  md_do_sync.cold.78+0x404/0x969 [md_mod]
[ 1463.757311]  ? wait_woken+0x80/0x80
[ 1463.757336]  ? md_rdev_init+0xb0/0xb0 [md_mod]
[ 1463.757351]  md_thread+0xe9/0x140 [md_mod]
[ 1463.757358]  ? _raw_spin_unlock_irqrestore+0x2e/0x60
[ 1463.757364]  ? __kthread_parkme+0x4c/0x70
[ 1463.757369]  kthread+0x112/0x130
[ 1463.757374]  ? kthread_create_worker_on_cpu+0x40/0x40
[ 1463.757380]  ret_from_fork+0x3a/0x50

2. regular IO
[ 1463.760679] INFO: task kworker/0:8:5367 blocked for more than 480 seconds.
[ 1463.760683]       Not tainted 4.19.5-1-default #1
[ 1463.760684] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 1463.760687] kworker/0:8     D    0  5367      2 0x80000000
[ 1463.760718] Workqueue: md submit_flushes [md_mod]
[ 1463.760721] Call Trace:
[ 1463.760731]  ? __schedule+0x29a/0x880
[ 1463.760741]  ? wait_barrier+0xdd/0x170 [raid10]
[ 1463.760746]  schedule+0x78/0x110
[ 1463.760753]  wait_barrier+0xdd/0x170 [raid10]
[ 1463.760761]  ? wait_woken+0x80/0x80
[ 1463.760768]  raid10_write_request+0xf2/0x900 [raid10]
[ 1463.760774]  ? wait_woken+0x80/0x80
[ 1463.760778]  ? mempool_alloc+0x55/0x160
[ 1463.760795]  ? md_write_start+0xa9/0x270 [md_mod]
[ 1463.760801]  ? try_to_wake_up+0x44/0x470
[ 1463.760810]  raid10_make_request+0xc1/0x120 [raid10]
[ 1463.760816]  ? wait_woken+0x80/0x80
[ 1463.760831]  md_handle_request+0x121/0x190 [md_mod]
[ 1463.760851]  md_make_request+0x78/0x190 [md_mod]
[ 1463.760860]  generic_make_request+0x1c6/0x470
[ 1463.760870]  raid10_write_request+0x77a/0x900 [raid10]
[ 1463.760875]  ? wait_woken+0x80/0x80
[ 1463.760879]  ? mempool_alloc+0x55/0x160
[ 1463.760895]  ? md_write_start+0xa9/0x270 [md_mod]
[ 1463.760904]  raid10_make_request+0xc1/0x120 [raid10]
[ 1463.760910]  ? wait_woken+0x80/0x80
[ 1463.760926]  md_handle_request+0x121/0x190 [md_mod]
[ 1463.760931]  ? _raw_spin_unlock_irq+0x22/0x40
[ 1463.760936]  ? finish_task_switch+0x74/0x260
[ 1463.760954]  submit_flushes+0x21/0x40 [md_mod]

So resync io is waiting for regular write io to complete to
decrease nr_pending (conf->barrier++ is called before waiting).
The regular write io splits another bio after call wait_barrier
which call nr_pending++, then the splitted bio would continue
with raid10_write_request -> wait_barrier, so the splitted bio
has to wait for barrier to be zero, then deadlock happens as
follows.

	resync io		regular io

	raise_barrier
				wait_barrier
				generic_make_request
				wait_barrier

To resolve the issue, we need to call allow_barrier to decrease
nr_pending before generic_make_request since regular IO is not
issued to underlying devices, and wait_barrier is called again
to ensure no internal IO happening.

Fixes: fc9977dd069e ("md/raid10: simplify the splitting of requests.")
Reported-and-tested-by: Siniša Bandin <sinisa@4net.rs>
Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/raid10.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 76c92e31afc0..abb5d382f64d 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1209,7 +1209,9 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 		struct bio *split = bio_split(bio, max_sectors,
 					      gfp, &conf->bio_split);
 		bio_chain(split, bio);
+		allow_barrier(conf);
 		generic_make_request(bio);
+		wait_barrier(conf);
 		bio = split;
 		r10_bio->master_bio = bio;
 		r10_bio->sectors = max_sectors;
@@ -1492,7 +1494,9 @@ retry_write:
 		struct bio *split = bio_split(bio, r10_bio->sectors,
 					      GFP_NOIO, &conf->bio_split);
 		bio_chain(split, bio);
+		allow_barrier(conf);
 		generic_make_request(bio);
+		wait_barrier(conf);
 		bio = split;
 		r10_bio->master_bio = bio;
 	}
-- 
cgit 1.2-0.3.lf.el7


From 9c9e935fc038342c48461aabca666f1b544e32b1 Mon Sep 17 00:00:00 2001\r
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>\r
Date: Sat, 26 Jan 2019 21:57:25 +0900\r
Subject: [PATCH v2] oom, oom_reaper: do not enqueue same task twice\r
\r
Arkadiusz reported that enabling memcg's group oom killing causes\r
strange memcg statistics where there is no task in a memcg despite\r
the number of tasks in that memcg is not 0. It turned out that there\r
is a bug in wake_oom_reaper() which allows enqueuing same task twice\r
which makes impossible to decrease the number of tasks in that memcg\r
due to a refcount leak.\r
\r
This bug existed since the OOM reaper became invokable from\r
task_will_free_mem(current) path in out_of_memory() in Linux 4.7,\r
but memcg's group oom killing made it easier to trigger this bug by\r
calling wake_oom_reaper() on the same task from one out_of_memory()\r
request.\r
\r
Fix this bug using an approach used by commit 855b018325737f76\r
("oom, oom_reaper: disable oom_reaper for oom_kill_allocating_task").\r
As a side effect of this patch, this patch also avoids enqueuing\r
multiple threads sharing memory via task_will_free_mem(current) path.\r
\r
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>\r
Reported-by: Arkadiusz Miśkiewicz <arekm@maven.pl>\r
Tested-by: Arkadiusz Miśkiewicz <arekm@maven.pl>\r
Fixes: af8e15cc85a25315 ("oom, oom_reaper: do not enqueue task if it is on the oom_reaper_list head")\r
---\r
 mm/oom_kill.c | 17 +++++++----------\r
 1 file changed, 7 insertions(+), 10 deletions(-)\r
\r
diff --git a/mm/oom_kill.c b/mm/oom_kill.c\r
index f0e8cd9..057bfee 100644\r
--- a/mm/oom_kill.c\r
+++ b/mm/oom_kill.c\r
@@ -505,14 +505,6 @@ bool __oom_reap_task_mm(struct mm_struct *mm)\r
 	struct vm_area_struct *vma;\r
 	bool ret = true;\r
 \r
-	/*\r
-	 * Tell all users of get_user/copy_from_user etc... that the content\r
-	 * is no longer stable. No barriers really needed because unmapping\r
-	 * should imply barriers already and the reader would hit a page fault\r
-	 * if it stumbled over a reaped memory.\r
-	 */\r
-	set_bit(MMF_UNSTABLE, &mm->flags);\r
-\r
 	for (vma = mm->mmap ; vma; vma = vma->vm_next) {\r
 		if (!can_madv_dontneed_vma(vma))\r
 			continue;\r
@@ -647,8 +639,13 @@ static int oom_reaper(void *unused)\r
 \r
 static void wake_oom_reaper(struct task_struct *tsk)\r
 {\r
-	/* tsk is already queued? */\r
-	if (tsk == oom_reaper_list || tsk->oom_reaper_list)\r
+	/*\r
+	 * Tell all users of get_user/copy_from_user etc... that the content\r
+	 * is no longer stable. No barriers really needed because unmapping\r
+	 * should imply barriers already and the reader would hit a page fault\r
+	 * if it stumbled over a reaped memory.\r
+	 */\r
+	if (test_and_set_bit(MMF_UNSTABLE, &tsk->signal->oom_mm->flags))\r
 		return;\r
 \r
 	get_task_struct(tsk);\r
-- \r
1.8.3.1\r
\r