From ae5535efd8c445ad6033ac0d5da0197897b148ea Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 7 Dec 2023 08:27:05 +0100 Subject: iomap: don't chain bios Back in the days when a single bio could only be filled to the hardware limits, and we scheduled a work item for each bio completion, chaining multiple bios for a single ioend made a lot of sense to reduce the number of completions. But these days bios can be filled until we reach the number of vectors or total size limit, which means we can always fit at least 1 megabyte worth of data in the worst case, but usually a lot more due to large folios. The only thing bio chaining is buying us now is to reduce the size of the allocation from an ioend with an embedded bio into a plain bio, which is a 52 bytes differences on 64-bit systems. This is not worth the added complexity, so remove the bio chaining and only use the bio embedded into the ioend. This will help to simplify further changes to the iomap writeback code. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20231207072710.176093-10-hch@lst.de Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- fs/xfs/xfs_aops.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs/xfs/xfs_aops.c') diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 813f85156b0c..4fb244bb884d 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -112,7 +112,7 @@ xfs_end_ioend( * longer dirty. If we don't remove delalloc blocks here, they become * stale and can corrupt free space accounting on unmount. */ - error = blk_status_to_errno(ioend->io_bio->bi_status); + error = blk_status_to_errno(ioend->io_bio.bi_status); if (unlikely(error)) { if (ioend->io_flags & IOMAP_F_SHARED) { xfs_reflink_cancel_cow_range(ip, offset, size, true); @@ -179,7 +179,7 @@ STATIC void xfs_end_bio( struct bio *bio) { - struct iomap_ioend *ioend = bio->bi_private; + struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); struct xfs_inode *ip = XFS_I(ioend->io_inode); unsigned long flags; @@ -444,7 +444,7 @@ xfs_prepare_ioend( /* send ioends that might require a transaction to the completion wq */ if (xfs_ioend_is_append(ioend) || ioend->io_type == IOMAP_UNWRITTEN || (ioend->io_flags & IOMAP_F_SHARED)) - ioend->io_bio->bi_end_io = xfs_end_bio; + ioend->io_bio.bi_end_io = xfs_end_bio; return status; } -- cgit v1.2.3 From 19871b5c7a003946d3cd4209a348ab7c0df5dbad Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 7 Dec 2023 08:27:10 +0100 Subject: iomap: pass the length of the dirty region to ->map_blocks Let the file system know how much dirty data exists at the passed in offset. This allows file systems to allocate the right amount of space that actually is written back if they can't eagerly convert (e.g. because they don't support unwritten extents). Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20231207072710.176093-15-hch@lst.de Signed-off-by: Christian Brauner --- block/fops.c | 2 +- fs/gfs2/bmap.c | 2 +- fs/iomap/buffered-io.c | 2 +- fs/xfs/xfs_aops.c | 3 ++- fs/zonefs/file.c | 3 ++- include/linux/iomap.h | 2 +- 6 files changed, 8 insertions(+), 6 deletions(-) (limited to 'fs/xfs/xfs_aops.c') diff --git a/block/fops.c b/block/fops.c index 0cf8cf72cdfa..93bae17ce660 100644 --- a/block/fops.c +++ b/block/fops.c @@ -482,7 +482,7 @@ static void blkdev_readahead(struct readahead_control *rac) } static int blkdev_map_blocks(struct iomap_writepage_ctx *wpc, - struct inode *inode, loff_t offset) + struct inode *inode, loff_t offset, unsigned int len) { loff_t isize = i_size_read(inode); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index d9ccfd27e4f1..789af5c8fade 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -2465,7 +2465,7 @@ out: } static int gfs2_map_blocks(struct iomap_writepage_ctx *wpc, struct inode *inode, - loff_t offset) + loff_t offset, unsigned int len) { int ret; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 3dab060aed6d..2ad0e287c704 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1773,7 +1773,7 @@ static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, do { unsigned map_len; - error = wpc->ops->map_blocks(wpc, inode, pos); + error = wpc->ops->map_blocks(wpc, inode, pos, dirty_len); if (error) break; trace_iomap_writepage_map(inode, &wpc->iomap); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 4fb244bb884d..1698507d1ac7 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -276,7 +276,8 @@ static int xfs_map_blocks( struct iomap_writepage_ctx *wpc, struct inode *inode, - loff_t offset) + loff_t offset, + unsigned int len) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index 6ab2318a9c8e..8dab4c2ad300 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -125,7 +125,8 @@ static void zonefs_readahead(struct readahead_control *rac) * which implies that the page range can only be within the fixed inode size. */ static int zonefs_write_map_blocks(struct iomap_writepage_ctx *wpc, - struct inode *inode, loff_t offset) + struct inode *inode, loff_t offset, + unsigned int len) { struct zonefs_zone *z = zonefs_inode_zone(inode); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 49d93f538785..6fc1c858013d 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -318,7 +318,7 @@ struct iomap_writeback_ops { * by the file system if it is still valid. */ int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode, - loff_t offset); + loff_t offset, unsigned len); /* * Optional, allows the file systems to perform actions just before -- cgit v1.2.3