--- /dev/null
+From 39fbc78c4408f38f779e9f41fe563bfa3828e5f2 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 5 Dec 2024 19:41:53 +0800
+Subject: dm array: fix cursor index when skipping across block boundaries
+
+From: Ming-Hung Tsai <mtsai@redhat.com>
+
+[ Upstream commit 0bb1968da2737ba68fd63857d1af2b301a18d3bf ]
+
+dm_array_cursor_skip() seeks to the target position by loading array
+blocks iteratively until the specified number of entries to skip is
+reached. When seeking across block boundaries, it uses
+dm_array_cursor_next() to step into the next block.
+dm_array_cursor_skip() must first move the cursor index to the end
+of the current block; otherwise, the cursor position could incorrectly
+remain in the same block, causing the actual number of skipped entries
+to be much smaller than expected.
+
+This bug affects cache resizing in v2 metadata and could lead to data
+loss if the fast device is shrunk during the first-time resume. For
+example:
+
+1. create a cache metadata consists of 32768 blocks, with a dirty block
+ assigned to the second bitmap block. cache_restore v1.0 is required.
+
+cat <<EOF >> cmeta.xml
+<superblock uuid="" block_size="64" nr_cache_blocks="32768" \
+policy="smq" hint_width="4">
+ <mappings>
+ <mapping cache_block="32767" origin_block="0" dirty="true"/>
+ </mappings>
+</superblock>
+EOF
+dmsetup create cmeta --table "0 8192 linear /dev/sdc 0"
+cache_restore -i cmeta.xml -o /dev/mapper/cmeta --metadata-version=2
+
+2. bring up the cache while attempt to discard all the blocks belonging
+ to the second bitmap block (block# 32576 to 32767). The last command
+ is expected to fail, but it actually succeeds.
+
+dmsetup create cdata --table "0 2084864 linear /dev/sdc 8192"
+dmsetup create corig --table "0 65536 linear /dev/sdc 2105344"
+dmsetup create cache --table "0 65536 cache /dev/mapper/cmeta \
+/dev/mapper/cdata /dev/mapper/corig 64 2 metadata2 writeback smq \
+2 migration_threshold 0"
+
+In addition to the reproducer described above, this fix can be
+verified using the "array_cursor/skip" tests in dm-unit:
+ dm-unit run /pdata/array_cursor/skip/ --kernel-dir <KERNEL_DIR>
+
+Signed-off-by: Ming-Hung Tsai <mtsai@redhat.com>
+Fixes: 9b696229aa7d ("dm persistent data: add cursor skip functions to the cursor APIs")
+Reviewed-by: Joe Thornber <thornber@redhat.com>
+Signed-off-by: Mike Snitzer <snitzer@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/md/persistent-data/dm-array.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c
+index f97de343a398..4d434d89eadd 100644
+--- a/drivers/md/persistent-data/dm-array.c
++++ b/drivers/md/persistent-data/dm-array.c
+@@ -993,6 +993,7 @@ int dm_array_cursor_skip(struct dm_array_cursor *c, uint32_t count)
+ }
+
+ count -= remaining;
++ c->index += (remaining - 1);
+ r = dm_array_cursor_next(c);
+
+ } while (!r);
+--
+2.39.5
+
--- /dev/null
+From 03c4e91e877cc281a6c5f58f42a38a94f554e4be Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 5 Dec 2024 19:41:51 +0800
+Subject: dm array: fix releasing a faulty array block twice in
+ dm_array_cursor_end
+
+From: Ming-Hung Tsai <mtsai@redhat.com>
+
+[ Upstream commit f2893c0804d86230ffb8f1c8703fdbb18648abc8 ]
+
+When dm_bm_read_lock() fails due to locking or checksum errors, it
+releases the faulty block implicitly while leaving an invalid output
+pointer behind. The caller of dm_bm_read_lock() should not operate on
+this invalid dm_block pointer, or it will lead to undefined result.
+For example, the dm_array_cursor incorrectly caches the invalid pointer
+on reading a faulty array block, causing a double release in
+dm_array_cursor_end(), then hitting the BUG_ON in dm-bufio cache_put().
+
+Reproduce steps:
+
+1. initialize a cache device
+
+dmsetup create cmeta --table "0 8192 linear /dev/sdc 0"
+dmsetup create cdata --table "0 65536 linear /dev/sdc 8192"
+dmsetup create corig --table "0 524288 linear /dev/sdc $262144"
+dd if=/dev/zero of=/dev/mapper/cmeta bs=4k count=1
+dmsetup create cache --table "0 524288 cache /dev/mapper/cmeta \
+/dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 writethrough smq 0"
+
+2. wipe the second array block offline
+
+dmsteup remove cache cmeta cdata corig
+mapping_root=$(dd if=/dev/sdc bs=1c count=8 skip=192 \
+2>/dev/null | hexdump -e '1/8 "%u\n"')
+ablock=$(dd if=/dev/sdc bs=1c count=8 skip=$((4096*mapping_root+2056)) \
+2>/dev/null | hexdump -e '1/8 "%u\n"')
+dd if=/dev/zero of=/dev/sdc bs=4k count=1 seek=$ablock
+
+3. try reopen the cache device
+
+dmsetup create cmeta --table "0 8192 linear /dev/sdc 0"
+dmsetup create cdata --table "0 65536 linear /dev/sdc 8192"
+dmsetup create corig --table "0 524288 linear /dev/sdc $262144"
+dmsetup create cache --table "0 524288 cache /dev/mapper/cmeta \
+/dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 writethrough smq 0"
+
+Kernel logs:
+
+(snip)
+device-mapper: array: array_block_check failed: blocknr 0 != wanted 10
+device-mapper: block manager: array validator check failed for block 10
+device-mapper: array: get_ablock failed
+device-mapper: cache metadata: dm_array_cursor_next for mapping failed
+------------[ cut here ]------------
+kernel BUG at drivers/md/dm-bufio.c:638!
+
+Fix by setting the cached block pointer to NULL on errors.
+
+In addition to the reproducer described above, this fix can be
+verified using the "array_cursor/damaged" test in dm-unit:
+ dm-unit run /pdata/array_cursor/damaged --kernel-dir <KERNEL_DIR>
+
+Signed-off-by: Ming-Hung Tsai <mtsai@redhat.com>
+Fixes: fdd1315aa5f0 ("dm array: introduce cursor api")
+Reviewed-by: Joe Thornber <thornber@redhat.com>
+Signed-off-by: Mike Snitzer <snitzer@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/md/persistent-data/dm-array.c | 12 ++++++++----
+ 1 file changed, 8 insertions(+), 4 deletions(-)
+
+diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c
+index 185dc60360b5..849eb1b97c43 100644
+--- a/drivers/md/persistent-data/dm-array.c
++++ b/drivers/md/persistent-data/dm-array.c
+@@ -907,23 +907,27 @@ static int load_ablock(struct dm_array_cursor *c)
+ if (c->block)
+ unlock_ablock(c->info, c->block);
+
+- c->block = NULL;
+- c->ab = NULL;
+ c->index = 0;
+
+ r = dm_btree_cursor_get_value(&c->cursor, &key, &value_le);
+ if (r) {
+ DMERR("dm_btree_cursor_get_value failed");
+- dm_btree_cursor_end(&c->cursor);
++ goto out;
+
+ } else {
+ r = get_ablock(c->info, le64_to_cpu(value_le), &c->block, &c->ab);
+ if (r) {
+ DMERR("get_ablock failed");
+- dm_btree_cursor_end(&c->cursor);
++ goto out;
+ }
+ }
+
++ return 0;
++
++out:
++ dm_btree_cursor_end(&c->cursor);
++ c->block = NULL;
++ c->ab = NULL;
+ return r;
+ }
+
+--
+2.39.5
+
--- /dev/null
+From 75e8bf9f21a1d7ff331f53cf34f069987f117d38 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 5 Dec 2024 19:41:52 +0800
+Subject: dm array: fix unreleased btree blocks on closing a faulty array
+ cursor
+
+From: Ming-Hung Tsai <mtsai@redhat.com>
+
+[ Upstream commit 626f128ee9c4133b1cfce4be2b34a1508949370e ]
+
+The cached block pointer in dm_array_cursor might be NULL if it reaches
+an unreadable array block, or the array is empty. Therefore,
+dm_array_cursor_end() should call dm_btree_cursor_end() unconditionally,
+to prevent leaving unreleased btree blocks.
+
+This fix can be verified using the "array_cursor/iterate/empty" test
+in dm-unit:
+ dm-unit run /pdata/array_cursor/iterate/empty --kernel-dir <KERNEL_DIR>
+
+Signed-off-by: Ming-Hung Tsai <mtsai@redhat.com>
+Fixes: fdd1315aa5f0 ("dm array: introduce cursor api")
+Reviewed-by: Joe Thornber <thornber@redhat.com>
+Signed-off-by: Mike Snitzer <snitzer@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/md/persistent-data/dm-array.c | 6 +++---
+ 1 file changed, 3 insertions(+), 3 deletions(-)
+
+diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c
+index 849eb1b97c43..f97de343a398 100644
+--- a/drivers/md/persistent-data/dm-array.c
++++ b/drivers/md/persistent-data/dm-array.c
+@@ -950,10 +950,10 @@ EXPORT_SYMBOL_GPL(dm_array_cursor_begin);
+
+ void dm_array_cursor_end(struct dm_array_cursor *c)
+ {
+- if (c->block) {
++ if (c->block)
+ unlock_ablock(c->info, c->block);
+- dm_btree_cursor_end(&c->cursor);
+- }
++
++ dm_btree_cursor_end(&c->cursor);
+ }
+ EXPORT_SYMBOL_GPL(dm_array_cursor_end);
+
+--
+2.39.5
+
--- /dev/null
+From 34a3c2adace3aa74f0541a2a9fff68a539354ab2 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 3 Dec 2024 09:44:07 +0800
+Subject: jbd2: flush filesystem device before updating tail sequence
+
+From: Zhang Yi <yi.zhang@huawei.com>
+
+[ Upstream commit a0851ea9cd555c333795b85ddd908898b937c4e1 ]
+
+When committing transaction in jbd2_journal_commit_transaction(), the
+disk caches for the filesystem device should be flushed before updating
+the journal tail sequence. However, this step is missed if the journal
+is not located on the filesystem device. As a result, the filesystem may
+become inconsistent following a power failure or system crash. Fix it by
+ensuring that the filesystem device is flushed appropriately.
+
+Fixes: 3339578f0578 ("jbd2: cleanup journal tail after transaction commit")
+Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
+Link: https://lore.kernel.org/r/20241203014407.805916-3-yi.zhang@huaweicloud.com
+Reviewed-by: Jan Kara <jack@suse.cz>
+Signed-off-by: Christian Brauner <brauner@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ fs/jbd2/commit.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
+index 255026497b8c..8c435c11664d 100644
+--- a/fs/jbd2/commit.c
++++ b/fs/jbd2/commit.c
+@@ -770,9 +770,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
+ /*
+ * If the journal is not located on the file system device,
+ * then we must flush the file system device before we issue
+- * the commit record
++ * the commit record and update the journal tail sequence.
+ */
+- if (commit_transaction->t_need_data_flush &&
++ if ((commit_transaction->t_need_data_flush || update_tail) &&
+ (journal->j_fs_dev != journal->j_dev) &&
+ (journal->j_flags & JBD2_BARRIER))
+ blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS, NULL);
+--
+2.39.5
+
--- /dev/null
+jbd2-flush-filesystem-device-before-updating-tail-se.patch
+dm-array-fix-releasing-a-faulty-array-block-twice-in.patch
+dm-array-fix-unreleased-btree-blocks-on-closing-a-fa.patch
+dm-array-fix-cursor-index-when-skipping-across-block.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
