linux-stable.git/drivers/md/dm-writecache.c, branch linux-5.12.y

dm writecache: write at least 4k when committing

2021-07-19T08:01:27+00:00

commit 867de40c4c23e6d7f89f9ce4272a5d1b1484c122 upstream.

SSDs perform badly with sub-4k writes (because they perfrorm
read-modify-write internally), so make sure writecache writes at least
4k when committing.

Fixes: 991bd8d7bc78 ("dm writecache: commit just one block, not a full page")
Signed-off-by: Mikulas Patocka 
Signed-off-by: Mike Snitzer 
Signed-off-by: Greg Kroah-Hartman

dm writecache: flush origin device when writing and cache is full

2021-07-19T08:01:25+00:00

commit ee55b92a7391bf871939330f662651b54be51b73 upstream.

Commit d53f1fafec9d086f1c5166436abefdaef30e0363 ("dm writecache: do
direct write if the cache is full") changed dm-writecache, so that it
writes directly to the origin device if the cache is full.
Unfortunately, it doesn't forward flush requests to the origin device,
so that there is a bug where flushes are being ignored.

Fix this by adding missing flush forwarding.

For PMEM mode, we fix this bug by disabling direct writes to the origin
device, because it performs better.

Signed-off-by: Mikulas Patocka 
Fixes: d53f1fafec9d ("dm writecache: do direct write if the cache is full")
Cc: stable@vger.kernel.org # v5.7+
Signed-off-by: Mike Snitzer 
Signed-off-by: Greg Kroah-Hartman

dm writecache: commit just one block, not a full page

2021-07-19T08:00:59+00:00

[ Upstream commit 991bd8d7bc78966b4dc427b53a144f276bffcd52 ]

Some architectures have pages larger than 4k and committing a full
page causes needless overhead.

Fix this by writing a single block when committing the superblock.

Signed-off-by: Mikulas Patocka 
Signed-off-by: Mike Snitzer 
Signed-off-by: Sasha Levin

dm writecache: don't split bios when overwriting contiguous cache content

2021-07-19T08:00:53+00:00

[ Upstream commit ee50cc19d80e9b9a8283d1fb517a778faf2f6899 ]

If dm-writecache overwrites existing cached data, it splits the
incoming bio into many block-sized bios. The I/O scheduler does merge
these bios into one large request but this needless splitting and
merging causes performance degradation.

Fix this by avoiding bio splitting if the cache target area that is
being overwritten is contiguous.

Signed-off-by: Mikulas Patocka 
Signed-off-by: Mike Snitzer 
Signed-off-by: Sasha Levin

block: rename BIO_MAX_PAGES to BIO_MAX_VECS

2021-03-11T14:47:48+00:00

Ever since the addition of multipage bio_vecs BIO_MAX_PAGES has been
horribly confusingly misnamed.  Rename it to BIO_MAX_VECS to stop
confusing users of the bio API.

Signed-off-by: Christoph Hellwig 
Reviewed-by: Matthew Wilcox (Oracle) 
Reviewed-by: Martin K. Petersen 
Link: https://lore.kernel.org/r/20210311110137.1132391-2-hch@lst.de
Signed-off-by: Jens Axboe

dm writecache: use bdev_nr_sectors() instead of open-coded equivalent

2021-02-09T22:09:02+00:00

Signed-off-by: Mike Snitzer

dm writecache: fix writing beyond end of underlying device when shrinking

2021-02-09T22:09:02+00:00

Do not attempt to write any data beyond the end of the underlying data
device while shrinking it.

The DM writecache device must be suspended when the underlying data
device is shrunk.

Signed-off-by: Mikulas Patocka 
Cc: stable@vger.kernel.org
Signed-off-by: Mike Snitzer

dm writecache: return the exact table values that were set

2021-02-08T16:32:54+00:00

LVM doesn't like it when the target returns different values from what
was set in the constructor. Fix dm-writecache so that the returned
table values are exactly the same as requested values.

Signed-off-by: Mikulas Patocka 
Cc: stable@vger.kernel.org # v4.18+
Signed-off-by: Mike Snitzer

dm writecache: fix unnecessary NULL check warnings

2021-02-03T15:10:05+00:00

Remove NULL checks before vfree() to fix these warnings:
./drivers/md/dm-writecache.c:2008:2-7: WARNING: NULL check before some
freeing functions is not needed.
./drivers/md/dm-writecache.c:2024:2-7: WARNING: NULL check before some
freeing functions is not needed.

Signed-off-by: Tian Tao 
Signed-off-by: Mike Snitzer

dm writecache: fix performance degradation in ssd mode

2021-02-03T15:10:05+00:00

Fix a thinko in ssd_commit_superblock. region.count is in sectors, not
bytes. This bug doesn't corrupt data, but it causes performance
degradation.

Signed-off-by: Mikulas Patocka 
Fixes: dc8a01ae1dbd ("dm writecache: optimize superblock write")
Cc: stable@vger.kernel.org # v5.7+
Reported-by: J. Bruce Fields 
Signed-off-by: Mike Snitzer