From 4d34d2f5b707ccb4ec514a66452bac74e97e2102 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 9 May 2021 16:02:30 +0200 Subject: [PATCH] 4.19-stable patches added patches: dm-raid-fix-inconclusive-reshape-layout-on-fast-raid4-5-6-table-reload-sequences.patch md-raid1-properly-indicate-failure-when-ending-a-failed-write-request.patch --- ...ast-raid4-5-6-table-reload-sequences.patch | 134 ++++++++++++++++++ ...e-when-ending-a-failed-write-request.patch | 35 +++++ queue-4.19/series | 2 + 3 files changed, 171 insertions(+) create mode 100644 queue-4.19/dm-raid-fix-inconclusive-reshape-layout-on-fast-raid4-5-6-table-reload-sequences.patch create mode 100644 queue-4.19/md-raid1-properly-indicate-failure-when-ending-a-failed-write-request.patch diff --git a/queue-4.19/dm-raid-fix-inconclusive-reshape-layout-on-fast-raid4-5-6-table-reload-sequences.patch b/queue-4.19/dm-raid-fix-inconclusive-reshape-layout-on-fast-raid4-5-6-table-reload-sequences.patch new file mode 100644 index 00000000000..1daf00a1409 --- /dev/null +++ b/queue-4.19/dm-raid-fix-inconclusive-reshape-layout-on-fast-raid4-5-6-table-reload-sequences.patch @@ -0,0 +1,134 @@ +From f99a8e4373eeacb279bc9696937a55adbff7a28a Mon Sep 17 00:00:00 2001 +From: Heinz Mauelshagen +Date: Wed, 21 Apr 2021 23:32:36 +0200 +Subject: dm raid: fix inconclusive reshape layout on fast raid4/5/6 table reload sequences + +From: Heinz Mauelshagen + +commit f99a8e4373eeacb279bc9696937a55adbff7a28a upstream. + +If fast table reloads occur during an ongoing reshape of raid4/5/6 +devices the target may race reading a superblock vs the the MD resync +thread; causing an inconclusive reshape state to be read in its +constructor. + +lvm2 test lvconvert-raid-reshape-stripes-load-reload.sh can cause +BUG_ON() to trigger in md_run(), e.g.: +"kernel BUG at drivers/md/raid5.c:7567!". + +Scenario triggering the bug: + +1. the MD sync thread calls end_reshape() from raid5_sync_request() + when done reshaping. However end_reshape() _only_ updates the + reshape position to MaxSector keeping the changed layout + configuration though (i.e. any delta disks, chunk sector or RAID + algorithm changes). That inconclusive configuration is stored in + the superblock. + +2. dm-raid constructs a mapping, loading named inconsistent superblock + as of step 1 before step 3 is able to finish resetting the reshape + state completely, and calls md_run() which leads to mentioned bug + in raid5.c. + +3. the MD RAID personality's finish_reshape() is called; which resets + the reshape information on chunk sectors, delta disks, etc. This + explains why the bug is rarely seen on multi-core machines, as MD's + finish_reshape() superblock update races with the dm-raid + constructor's superblock load in step 2. + +Fix identifies inconclusive superblock content in the dm-raid +constructor and resets it before calling md_run(), factoring out +identifying checks into rs_is_layout_change() to share in existing +rs_reshape_requested() and new rs_reset_inclonclusive_reshape(). Also +enhance a comment and remove an empty line. + +Cc: stable@vger.kernel.org +Signed-off-by: Heinz Mauelshagen +Signed-off-by: Mike Snitzer +Signed-off-by: Greg Kroah-Hartman +--- + drivers/md/dm-raid.c | 34 ++++++++++++++++++++++++++++------ + 1 file changed, 28 insertions(+), 6 deletions(-) + +--- a/drivers/md/dm-raid.c ++++ b/drivers/md/dm-raid.c +@@ -1892,6 +1892,14 @@ static bool rs_takeover_requested(struct + return rs->md.new_level != rs->md.level; + } + ++/* True if layout is set to reshape. */ ++static bool rs_is_layout_change(struct raid_set *rs, bool use_mddev) ++{ ++ return (use_mddev ? rs->md.delta_disks : rs->delta_disks) || ++ rs->md.new_layout != rs->md.layout || ++ rs->md.new_chunk_sectors != rs->md.chunk_sectors; ++} ++ + /* True if @rs is requested to reshape by ctr */ + static bool rs_reshape_requested(struct raid_set *rs) + { +@@ -1904,9 +1912,7 @@ static bool rs_reshape_requested(struct + if (rs_is_raid0(rs)) + return false; + +- change = mddev->new_layout != mddev->layout || +- mddev->new_chunk_sectors != mddev->chunk_sectors || +- rs->delta_disks; ++ change = rs_is_layout_change(rs, false); + + /* Historical case to support raid1 reshape without delta disks */ + if (rs_is_raid1(rs)) { +@@ -2843,7 +2849,7 @@ static sector_t _get_reshape_sectors(str + } + + /* +- * ++ * Reshape: + * - change raid layout + * - change chunk size + * - add disks +@@ -2953,6 +2959,20 @@ static int rs_setup_reshape(struct raid_ + } + + /* ++ * If the md resync thread has updated superblock with max reshape position ++ * at the end of a reshape but not (yet) reset the layout configuration ++ * changes -> reset the latter. ++ */ ++static void rs_reset_inconclusive_reshape(struct raid_set *rs) ++{ ++ if (!rs_is_reshaping(rs) && rs_is_layout_change(rs, true)) { ++ rs_set_cur(rs); ++ rs->md.delta_disks = 0; ++ rs->md.reshape_backwards = 0; ++ } ++} ++ ++/* + * Enable/disable discard support on RAID set depending on + * RAID level and discard properties of underlying RAID members. + */ +@@ -3221,11 +3241,14 @@ static int raid_ctr(struct dm_target *ti + if (r) + goto bad; + ++ /* Catch any inconclusive reshape superblock content. */ ++ rs_reset_inconclusive_reshape(rs); ++ + /* Start raid set read-only and assumed clean to change in raid_resume() */ + rs->md.ro = 1; + rs->md.in_sync = 1; + +- /* Keep array frozen */ ++ /* Keep array frozen until resume. */ + set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery); + + /* Has to be held on running the array */ +@@ -3239,7 +3262,6 @@ static int raid_ctr(struct dm_target *ti + } + + r = md_start(&rs->md); +- + if (r) { + ti->error = "Failed to start raid array"; + mddev_unlock(&rs->md); diff --git a/queue-4.19/md-raid1-properly-indicate-failure-when-ending-a-failed-write-request.patch b/queue-4.19/md-raid1-properly-indicate-failure-when-ending-a-failed-write-request.patch new file mode 100644 index 00000000000..b69ea2d816f --- /dev/null +++ b/queue-4.19/md-raid1-properly-indicate-failure-when-ending-a-failed-write-request.patch @@ -0,0 +1,35 @@ +From 2417b9869b81882ab90fd5ed1081a1cb2d4db1dd Mon Sep 17 00:00:00 2001 +From: Paul Clements +Date: Thu, 15 Apr 2021 17:17:57 -0400 +Subject: md/raid1: properly indicate failure when ending a failed write request + +From: Paul Clements + +commit 2417b9869b81882ab90fd5ed1081a1cb2d4db1dd upstream. + +This patch addresses a data corruption bug in raid1 arrays using bitmaps. +Without this fix, the bitmap bits for the failed I/O end up being cleared. + +Since we are in the failure leg of raid1_end_write_request, the request +either needs to be retried (R1BIO_WriteError) or failed (R1BIO_Degraded). + +Fixes: eeba6809d8d5 ("md/raid1: end bio when the device faulty") +Cc: stable@vger.kernel.org # v5.2+ +Signed-off-by: Paul Clements +Signed-off-by: Song Liu +Signed-off-by: Greg Kroah-Hartman +--- + drivers/md/raid1.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/drivers/md/raid1.c ++++ b/drivers/md/raid1.c +@@ -445,6 +445,8 @@ static void raid1_end_write_request(stru + if (!test_bit(Faulty, &rdev->flags)) + set_bit(R1BIO_WriteError, &r1_bio->state); + else { ++ /* Fail the request */ ++ set_bit(R1BIO_Degraded, &r1_bio->state); + /* Finished with this branch */ + r1_bio->bios[mirror] = NULL; + to_put = bio; diff --git a/queue-4.19/series b/queue-4.19/series index 64cb03c87a2..a24c662031f 100644 --- a/queue-4.19/series +++ b/queue-4.19/series @@ -93,3 +93,5 @@ powerpc-eeh-fix-eeh-handling-for-hugepages-in-ioremap-space.patch powerpc-fix-edeadlock-redefinition-error-in-uapi-asm-errno.h.patch intel_th-pci-add-alder-lake-m-support.patch tpm-vtpm_proxy-avoid-reading-host-log-when-using-a-virtual-device.patch +md-raid1-properly-indicate-failure-when-ending-a-failed-write-request.patch +dm-raid-fix-inconclusive-reshape-layout-on-fast-raid4-5-6-table-reload-sequences.patch -- 2.47.3