[PATCH 4.14 1/3] Revert "Btrfs: fix scrub to repair raid6 corruption"

[PATCH 4.14 1/3] Revert "Btrfs: fix scrub to repair raid6 corruption"

[Sasha Levin]

This reverts commit d91bb7c6988bd6450284c762b33f2e1ea3fe7c97.

This commit used an incorrect log message.

Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
---
 fs/btrfs/raid56.c  | 18 ++++--------------
 fs/btrfs/volumes.c |  9 +--------
 2 files changed, 5 insertions(+), 22 deletions(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 2e995e565633..d1bda68a3386 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -2172,21 +2172,11 @@ int raid56_parity_recover(struct btrfs_fs_info *fs_info, struct bio *bio,
 	}
 
 	/*
-	 * Loop retry:
-	 * for 'mirror == 2', reconstruct from all other stripes.
-	 * for 'mirror_num > 2', select a stripe to fail on every retry.
+	 * reconstruct from the q stripe if they are
+	 * asking for mirror 3
 	 */
-	if (mirror_num > 2) {
-		/*
-		 * 'mirror == 3' is to fail the p stripe and
-		 * reconstruct from the q stripe.  'mirror > 3' is to
-		 * fail a data stripe and reconstruct from p+q stripe.
-		 */
-		rbio->failb = rbio->real_stripes - (mirror_num - 1);
-		ASSERT(rbio->failb > 0);
-		if (rbio->failb <= rbio->faila)
-			rbio->failb--;
-	}
+	if (mirror_num == 3)
+		rbio->failb = rbio->real_stripes - 2;
 
 	ret = lock_stripe_add(rbio);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 08afafb6ecf7..69bc37a87c5a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5110,14 +5110,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 	else if (map->type & BTRFS_BLOCK_GROUP_RAID5)
 		ret = 2;
 	else if (map->type & BTRFS_BLOCK_GROUP_RAID6)
-		/*
-		 * There could be two corrupted data stripes, we need
-		 * to loop retry in order to rebuild the correct data.
-		 *
-		 * Fail a stripe at a time on every retry except the
-		 * stripe under reconstruction.
-		 */
-		ret = map->num_stripes;
+		ret = 3;
 	else
 		ret = 1;
 	free_extent_map(em);
-- 
2.17.1

[PATCH 4.14 2/3] Btrfs: fix scrub to repair raid6 corruption

[Sasha Levin]

From: Liu Bo <bo.li.liu@oracle.com>

[ Upstream commit 762221f095e3932669093466aaf4b85ed9ad2ac1 ]

The raid6 corruption is that,
suppose that all disks can be read without problems and if the content
that was read out doesn't match its checksum, currently for raid6
btrfs at most retries twice,

- the 1st retry is to rebuild with all other stripes, it'll eventually
  be a raid5 xor rebuild,
- if the 1st fails, the 2nd retry will deliberately fail parity p so
  that it will do raid6 style rebuild,

however, the chances are that another non-parity stripe content also
has something corrupted, so that the above retries are not able to
return correct content.

We've fixed normal reads to rebuild raid6 correctly with more retries
in Patch "Btrfs: make raid6 rebuild retry more"[1], this is to fix
scrub to do the exactly same rebuild process.

[1]: https://patchwork.kernel.org/patch/10091755/

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
---
 fs/btrfs/scrub.c | 44 ++++++++++++++++++++++++++++++++------------
 1 file changed, 32 insertions(+), 12 deletions(-)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index e3f6c49e5c4d..24613b4e224c 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -301,6 +301,11 @@ static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_put_ctx(struct scrub_ctx *sctx);
 
+static inline int scrub_is_page_on_raid56(struct scrub_page *page)
+{
+	return page->recover &&
+	       (page->recover->bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK);
+}
 
 static void scrub_pending_bio_inc(struct scrub_ctx *sctx)
 {
@@ -1323,15 +1328,34 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 	 * could happen otherwise that a correct page would be
 	 * overwritten by a bad one).
 	 */
-	for (mirror_index = 0;
-	     mirror_index < BTRFS_MAX_MIRRORS &&
-	     sblocks_for_recheck[mirror_index].page_count > 0;
-	     mirror_index++) {
+	for (mirror_index = 0; ;mirror_index++) {
 		struct scrub_block *sblock_other;
 
 		if (mirror_index == failed_mirror_index)
 			continue;
-		sblock_other = sblocks_for_recheck + mirror_index;
+
+		/* raid56's mirror can be more than BTRFS_MAX_MIRRORS */
+		if (!scrub_is_page_on_raid56(sblock_bad->pagev[0])) {
+			if (mirror_index >= BTRFS_MAX_MIRRORS)
+				break;
+			if (!sblocks_for_recheck[mirror_index].page_count)
+				break;
+
+			sblock_other = sblocks_for_recheck + mirror_index;
+		} else {
+			struct scrub_recover *r = sblock_bad->pagev[0]->recover;
+			int max_allowed = r->bbio->num_stripes -
+						r->bbio->num_tgtdevs;
+
+			if (mirror_index >= max_allowed)
+				break;
+			if (!sblocks_for_recheck[1].page_count)
+				break;
+
+			ASSERT(failed_mirror_index == 0);
+			sblock_other = sblocks_for_recheck + 1;
+			sblock_other->pagev[0]->mirror_num = 1 + mirror_index;
+		}
 
 		/* build and submit the bios, check checksums */
 		scrub_recheck_block(fs_info, sblock_other, 0);
@@ -1679,18 +1703,13 @@ static void scrub_bio_wait_endio(struct bio *bio)
 	complete(&ret->event);
 }
 
-static inline int scrub_is_page_on_raid56(struct scrub_page *page)
-{
-	return page->recover &&
-	       (page->recover->bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK);
-}
-
 static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
 					struct bio *bio,
 					struct scrub_page *page)
 {
 	struct scrub_bio_ret done;
 	int ret;
+	int mirror_num;
 
 	init_completion(&done.event);
 	done.status = 0;
@@ -1698,9 +1717,10 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
 	bio->bi_private = &done;
 	bio->bi_end_io = scrub_bio_wait_endio;
 
+	mirror_num = page->sblock->pagev[0]->mirror_num;
 	ret = raid56_parity_recover(fs_info, bio, page->recover->bbio,
 				    page->recover->map_length,
-				    page->mirror_num, 0);
+				    mirror_num, 0);
 	if (ret)
 		return ret;
 
-- 
2.17.1

[PATCH 4.14 3/3] Btrfs: make raid6 rebuild retry more

[Sasha Levin]

From: Liu Bo <bo.li.liu@oracle.com>

[ Upstream commit 8810f7517a3bc4ca2d41d022446d3f5fd6b77c09 ]

There is a scenario that can end up with rebuild process failing to
return good content, i.e.
suppose that all disks can be read without problems and if the content
that was read out doesn't match its checksum, currently for raid6
btrfs at most retries twice,

- the 1st retry is to rebuild with all other stripes, it'll eventually
  be a raid5 xor rebuild,
- if the 1st fails, the 2nd retry will deliberately fail parity p so
  that it will do raid6 style rebuild,

however, the chances are that another non-parity stripe content also
has something corrupted, so that the above retries are not able to
return correct content, and users will think of this as data loss.
More seriouly, if the loss happens on some important internal btree
roots, it could refuse to mount.

This extends btrfs to do more retries and each retry fails only one
stripe.  Since raid6 can tolerate 2 disk failures, if there is one
more failure besides the failure on which we're recovering, this can
always work.

The worst case is to retry as many times as the number of raid6 disks,
but given the fact that such a scenario is really rare in practice,
it's still acceptable.

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
---
 fs/btrfs/raid56.c  | 18 ++++++++++++++----
 fs/btrfs/volumes.c |  9 ++++++++-
 2 files changed, 22 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index d1bda68a3386..2e995e565633 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -2172,11 +2172,21 @@ int raid56_parity_recover(struct btrfs_fs_info *fs_info, struct bio *bio,
 	}
 
 	/*
-	 * reconstruct from the q stripe if they are
-	 * asking for mirror 3
+	 * Loop retry:
+	 * for 'mirror == 2', reconstruct from all other stripes.
+	 * for 'mirror_num > 2', select a stripe to fail on every retry.
 	 */
-	if (mirror_num == 3)
-		rbio->failb = rbio->real_stripes - 2;
+	if (mirror_num > 2) {
+		/*
+		 * 'mirror == 3' is to fail the p stripe and
+		 * reconstruct from the q stripe.  'mirror > 3' is to
+		 * fail a data stripe and reconstruct from p+q stripe.
+		 */
+		rbio->failb = rbio->real_stripes - (mirror_num - 1);
+		ASSERT(rbio->failb > 0);
+		if (rbio->failb <= rbio->faila)
+			rbio->failb--;
+	}
 
 	ret = lock_stripe_add(rbio);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 69bc37a87c5a..cb2643ca8411 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5110,7 +5110,14 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 	else if (map->type & BTRFS_BLOCK_GROUP_RAID5)
 		ret = 2;
 	else if (map->type & BTRFS_BLOCK_GROUP_RAID6)
-		ret = 3;
+		/*
+		 * There could be two corrupted data stripes, we need
+		 * to loop retry in order to rebuild the correct data.
+		 * 
+		 * Fail a stripe at a time on every retry except the
+		 * stripe under reconstruction.
+		 */
+		ret = map->num_stripes;
 	else
 		ret = 1;
 	free_extent_map(em);
-- 
2.17.1

[PATCH 4.14 2/3] Btrfs: fix scrub to repair raid6 corruption

[Sasha Levin]

From: Liu Bo <bo.li.liu@oracle.com>

[ Upstream commit 762221f095e3932669093466aaf4b85ed9ad2ac1 ]

The raid6 corruption is that,
suppose that all disks can be read without problems and if the content
that was read out doesn't match its checksum, currently for raid6
btrfs at most retries twice,

- the 1st retry is to rebuild with all other stripes, it'll eventually
  be a raid5 xor rebuild,
- if the 1st fails, the 2nd retry will deliberately fail parity p so
  that it will do raid6 style rebuild,

however, the chances are that another non-parity stripe content also
has something corrupted, so that the above retries are not able to
return correct content.

We've fixed normal reads to rebuild raid6 correctly with more retries
in Patch "Btrfs: make raid6 rebuild retry more"[1], this is to fix
scrub to do the exactly same rebuild process.

[1]: https://patchwork.kernel.org/patch/10091755/

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
---
 fs/btrfs/scrub.c | 44 ++++++++++++++++++++++++++++++++------------
 1 file changed, 32 insertions(+), 12 deletions(-)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index e3f6c49e5c4d..24613b4e224c 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -301,6 +301,11 @@ static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_put_ctx(struct scrub_ctx *sctx);
 
+static inline int scrub_is_page_on_raid56(struct scrub_page *page)
+{
+	return page->recover &&
+	       (page->recover->bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK);
+}
 
 static void scrub_pending_bio_inc(struct scrub_ctx *sctx)
 {
@@ -1323,15 +1328,34 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 	 * could happen otherwise that a correct page would be
 	 * overwritten by a bad one).
 	 */
-	for (mirror_index = 0;
-	     mirror_index < BTRFS_MAX_MIRRORS &&
-	     sblocks_for_recheck[mirror_index].page_count > 0;
-	     mirror_index++) {
+	for (mirror_index = 0; ;mirror_index++) {
 		struct scrub_block *sblock_other;
 
 		if (mirror_index == failed_mirror_index)
 			continue;
-		sblock_other = sblocks_for_recheck + mirror_index;
+
+		/* raid56's mirror can be more than BTRFS_MAX_MIRRORS */
+		if (!scrub_is_page_on_raid56(sblock_bad->pagev[0])) {
+			if (mirror_index >= BTRFS_MAX_MIRRORS)
+				break;
+			if (!sblocks_for_recheck[mirror_index].page_count)
+				break;
+
+			sblock_other = sblocks_for_recheck + mirror_index;
+		} else {
+			struct scrub_recover *r = sblock_bad->pagev[0]->recover;
+			int max_allowed = r->bbio->num_stripes -
+						r->bbio->num_tgtdevs;
+
+			if (mirror_index >= max_allowed)
+				break;
+			if (!sblocks_for_recheck[1].page_count)
+				break;
+
+			ASSERT(failed_mirror_index == 0);
+			sblock_other = sblocks_for_recheck + 1;
+			sblock_other->pagev[0]->mirror_num = 1 + mirror_index;
+		}
 
 		/* build and submit the bios, check checksums */
 		scrub_recheck_block(fs_info, sblock_other, 0);
@@ -1679,18 +1703,13 @@ static void scrub_bio_wait_endio(struct bio *bio)
 	complete(&ret->event);
 }
 
-static inline int scrub_is_page_on_raid56(struct scrub_page *page)
-{
-	return page->recover &&
-	       (page->recover->bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK);
-}
-
 static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
 					struct bio *bio,
 					struct scrub_page *page)
 {
 	struct scrub_bio_ret done;
 	int ret;
+	int mirror_num;
 
 	init_completion(&done.event);
 	done.status = 0;
@@ -1698,9 +1717,10 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
 	bio->bi_private = &done;
 	bio->bi_end_io = scrub_bio_wait_endio;
 
+	mirror_num = page->sblock->pagev[0]->mirror_num;
 	ret = raid56_parity_recover(fs_info, bio, page->recover->bbio,
 				    page->recover->map_length,
-				    page->mirror_num, 0);
+				    mirror_num, 0);
 	if (ret)
 		return ret;
 
-- 
2.17.1