mirrors/linux
2
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-08-31 08:15:07 -04:00
Code Issues Packages Projects Releases Wiki Activity

zloop: set dma_alignment from the backing files for direct I/O

Browse Source 
Direct I/O request's use pages handed to the backing files unchanged, so
the backing's DMA alignment requirement applies. Track dio_mem_align and
advertise it as the device's dma_alignment so we communicate proper
limits and misaligned I/O is rejected here instead of reaching the
backend.

Reviewed-by: Hannes Reinecke <hare@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://patch.msgid.link/20260720201057.1862857-5-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Keith Busch
2026-07-20 13:10:56 -07:00
committed by Jens Axboe
parent 6c8dec275c
commit c5059c1af2
1 changed files with 26 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
drivers/block/zloop.c
View File

@@ -144,6 +144,7 @@ struct zloop_device {
unsigned int nr_conv_zones;
unsigned int max_open_zones;
unsigned int block_size;
unsigned int dio_mem_align;
spinlock_t open_zones_lock;
struct list_head open_zones_lru_list;
@@ -1037,20 +1038,30 @@ static int zloop_get_block_size(struct zloop_device *zlo,
struct kstat st;
/*
* If the FS block size is lower than or equal to 4K, use that as the
* device block size. Otherwise, fallback to the FS direct IO alignment
* constraint if that is provided, and to the FS underlying device
* physical block size if the direct IO alignment is unknown.
* Use the dio alignment of the file system if provided. The incoming
* request's bio_vec is forwarded to the backing file unchanged, so its
* required memory alignment becomes the device's dma_alignment when
* used for direct-io.
*/
if (!vfs_getattr(&zone->file->f_path, &st, STATX_DIOALIGN, 0) &&
(st.result_mask & STATX_DIOALIGN)) {
zlo->block_size = st.dio_offset_align;
zlo->dio_mem_align = st.dio_mem_align - 1;
} else if (sb_bdev) {
zlo->block_size = bdev_physical_block_size(sb_bdev);
zlo->dio_mem_align = bdev_dma_alignment(sb_bdev);
} else {
zlo->block_size = SECTOR_SIZE;
zlo->dio_mem_align = SECTOR_SIZE - 1;
}
/*
* Prefer the FS block size for the device block size when it is no
* larger than 4K; otherwise keep the direct I/O / physical block size
* selected above.
*/
if (file_inode(zone->file)->i_sb->s_blocksize <= SZ_4K)
zlo->block_size = file_inode(zone->file)->i_sb->s_blocksize;
else if (!vfs_getattr(&zone->file->f_path, &st, STATX_DIOALIGN, 0) &&
(st.result_mask & STATX_DIOALIGN))
zlo->block_size = st.dio_offset_align;
else if (sb_bdev)
zlo->block_size = bdev_physical_block_size(sb_bdev);
else
zlo->block_size = SECTOR_SIZE;
if (zlo->zone_capacity & ((zlo->block_size >> SECTOR_SHIFT) - 1)) {
pr_err("Zone capacity is not aligned to block size %u\n",
@@ -1279,6 +1290,10 @@ static int zloop_ctl_add(struct zloop_options *opts)
lim.physical_block_size = zlo->block_size;
lim.logical_block_size = zlo->block_size;
/* Direct I/O forwards the request pages to the backing files as-is. */
if (!opts->buffered_io)
lim.dma_alignment = max_t(unsigned int, zlo->dio_mem_align,
SECTOR_SIZE - 1);
if (zlo->zone_append)
lim.max_hw_zone_append_sectors = lim.max_hw_sectors;
lim.max_open_zones = zlo->max_open_zones;