Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Sasha Levin <Alexander.Levin@microsoft.com>
To:     "stable@vger.kernel.org" <stable@vger.kernel.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
CC:     Mike Snitzer <snitzer@redhat.com>,
        Sasha Levin <Alexander.Levin@microsoft.com>
Subject: [PATCH AUTOSEL for 4.9 080/293] Revert "dm mirror: use all available
 legs on multiple failures"
Thread-Topic: [PATCH AUTOSEL for 4.9 080/293] Revert "dm mirror: use all
 available legs on multiple failures"
Thread-Index: AQHTz5kMD1+1agiVSUWdZLWCnwGFRw==
Date:   Mon, 9 Apr 2018 00:23:56 +0000
Message-ID: <20180409002239.163177-80-alexander.levin@microsoft.com>
References: <20180409002239.163177-1-alexander.levin@microsoft.com>
In-Reply-To: <20180409002239.163177-1-alexander.levin@microsoft.com>
Accept-Language: en-US
Content-Language: en-US
received-spf: None (protection.outlook.com: microsoft.com does not designate
 permitted sender hosts)
spamdiagnosticoutput: 1:99
spamdiagnosticmetadata: NSPM
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: 781aecbc-8638-43ea-bb6b-08d59db0d272
X-MS-Exchange-CrossTenant-originalarrivaltime: 09 Apr 2018 00:23:56.7531
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 72f988bf-86f1-41af-91ab-2d7cd011db47
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM5PR2101MB0807
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

From: Mike Snitzer <snitzer@redhat.com>

[ Upstream commit cd15fb64ee56192760ad5c1e2ad97a65e735b18b ]

This reverts commit 12a7cf5ba6c776a2621d8972c7d42e8d3d959d20.

This commit apparently attempted to fix an issue that didn't really
exist, furthermore: this commit is the source of deadlocks and crashes
seen in multiple cases related to failing the primary mirror dev while
syncing.

Reported-by: Jonathan Brassow <jbrassow@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
---
 drivers/md/dm-raid1.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 9a8b71067c6e..7a6254d54baf 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -145,6 +145,7 @@ static void dispatch_bios(void *context, struct bio_lis=
t *bio_list)
=20
 struct dm_raid1_bio_record {
 	struct mirror *m;
+	/* if details->bi_bdev =3D=3D NULL, details were not saved */
 	struct dm_bio_details details;
 	region_t write_region;
 };
@@ -1199,6 +1200,8 @@ static int mirror_map(struct dm_target *ti, struct bi=
o *bio)
 	struct dm_raid1_bio_record *bio_record =3D
 	  dm_per_bio_data(bio, sizeof(struct dm_raid1_bio_record));
=20
+	bio_record->details.bi_bdev =3D NULL;
+
 	if (rw =3D=3D WRITE) {
 		/* Save region for mirror_end_io() handler */
 		bio_record->write_region =3D dm_rh_bio_to_region(ms->rh, bio);
@@ -1257,12 +1260,22 @@ static int mirror_end_io(struct dm_target *ti, stru=
ct bio *bio, int error)
 	}
=20
 	if (error =3D=3D -EOPNOTSUPP)
-		return error;
+		goto out;
=20
 	if ((error =3D=3D -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD))
-		return error;
+		goto out;
=20
 	if (unlikely(error)) {
+		if (!bio_record->details.bi_bdev) {
+			/*
+			 * There wasn't enough memory to record necessary
+			 * information for a retry or there was no other
+			 * mirror in-sync.
+			 */
+			DMERR_LIMIT("Mirror read failed.");
+			return -EIO;
+		}
+
 		m =3D bio_record->m;
=20
 		DMERR("Mirror read failed from %s. Trying alternative device.",
@@ -1278,6 +1291,7 @@ static int mirror_end_io(struct dm_target *ti, struct=
 bio *bio, int error)
 			bd =3D &bio_record->details;
=20
 			dm_bio_restore(bd, bio);
+			bio_record->details.bi_bdev =3D NULL;
 			bio->bi_error =3D 0;
=20
 			queue_bio(ms, bio, rw);
@@ -1286,6 +1300,9 @@ static int mirror_end_io(struct dm_target *ti, struct=
 bio *bio, int error)
 		DMERR("All replicated volumes dead, failing I/O");
 	}
=20
+out:
+	bio_record->details.bi_bdev =3D NULL;
+
 	return error;
 }
=20
--=20
2.15.1