Commit d0ac06ae53be for kernel
commit d0ac06ae53be0cdb61f5fe6b62d25d3317c51657
Author: Mikulas Patocka <mpatocka@redhat.com>
Date: Mon Oct 20 14:48:13 2025 +0200
dm-bufio: align write boundary on physical block size
There may be devices with physical block size larger than 4k.
If dm-bufio sends I/O that is not aligned on physical block size,
performance is degraded.
The 4k minimum alignment limit is there because some SSDs report logical
and physical block size 512 despite having 4k internally - so dm-bufio
shouldn't send I/Os not aligned on 4k boundary, because they perform
badly (the SSD does read-modify-write for them).
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Reported-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: stable@vger.kernel.org
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index e6d28be11c5c..5235f3e4924b 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1374,7 +1374,7 @@ static void submit_io(struct dm_buffer *b, enum req_op op, unsigned short ioprio
{
unsigned int n_sectors;
sector_t sector;
- unsigned int offset, end;
+ unsigned int offset, end, align;
b->end_io = end_io;
@@ -1388,9 +1388,11 @@ static void submit_io(struct dm_buffer *b, enum req_op op, unsigned short ioprio
b->c->write_callback(b);
offset = b->write_start;
end = b->write_end;
- offset &= -DM_BUFIO_WRITE_ALIGN;
- end += DM_BUFIO_WRITE_ALIGN - 1;
- end &= -DM_BUFIO_WRITE_ALIGN;
+ align = max(DM_BUFIO_WRITE_ALIGN,
+ bdev_physical_block_size(b->c->bdev));
+ offset &= -align;
+ end += align - 1;
+ end &= -align;
if (unlikely(end > b->c->block_size))
end = b->c->block_size;