don't build bios/contexts over multiple iomaps v3
Subsystems (7)
Hi all,
this patch changes how iomap submits bios for reads. The old behavior to build up bios across iomap was already considered problematic for a while, but we now ran into a erofs bug because of it, so it's time to finally fix it.
It would be great to get the fix into 7.2 as the fixed bug can be triggered by users.
Changes since v2:
- drop an unused argument
- make sure we submit for the same iteration to not leave a landmine for future changes
Changes since v1:
- don't submit fuse context after each iteration
- consolidate some code to support the above
- fix a bug in the fs PI support found while doing the above
PATCH 1/2 iomap: consolidate bio submission
Add a iomap_bio_submit_read_endio helper factored out of iomap_bio_submit_read to that all ->submit_read implementations for iomap_read_ops that use iomap_bio_read_folio_range can shared the logic.
Right now that logic is mostly trivial, but already has a bug for XFS because the XFS version is too trivial: file system integrity validation needs a workqueue context and thus can't happen from the default iomap bi_end_io I/O handler. Unfortunately the iomap refactoring just before fs integrity landed moved code around here and the call go misplaced, meaning it never got called. The PI information still is verified by the block layer, but the offloading is less efficient (and the future userspace interface can't get at it).
--- fs/exfat/iomap.c | 5 +---- fs/iomap/bio.c | 13 ++++++++++--- fs/ntfs/aops.c | 6 ++---- fs/ntfs3/inode.c | 5 +---- fs/xfs/xfs_aops.c | 3 +-- include/linux/iomap.h | 2 ++ 6 files changed, 17 insertions(+), 17 deletions(-)
fs/exfat/iomap.c +1 -4
@@ -253,10 +253,7 @@ static void exfat_iomap_read_end_io(struct bio *bio)static void exfat_iomap_bio_submit_read (const struct iomap_iter *iter,struct iomap_read_folio_ctx *ctx) { -struct bio *bio = ctx->read_ctx; - - bio->bi_end_io = exfat_iomap_read_end_io; -submit_bio (bio); +iomap_bio_submit_read_endio (iter, ctx, exfat_iomap_read_end_io); }const struct iomap_read_ops exfat_iomap_bio_read_ops = {
fs/iomap/bio.c +10 -3
@@ -78,15 +78,23 @@ u32 iomap_finish_ioend_buffered_read(struct iomap_ioend *ioend)return __iomap_read_end_io (&ioend->io_bio, ioend->io_error); } -static void iomap_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +void iomap_bio_submit_read_endio (const struct iomap_iter *iter, +struct iomap_read_folio_ctx *ctx,bio_end_io_t end_io) {struct bio *bio = ctx->read_ctx; + bio->bi_end_io = end_io;if (iter->iomap.flags &IOMAP_F_INTEGRITY )fs_bio_integrity_alloc (bio);submit_bio (bio); } +EXPORT_SYMBOL_GPL (iomap_bio_submit_read_endio); + +static void iomap_bio_submit_read (const struct iomap_iter *iter, +struct iomap_read_folio_ctx *ctx) +{ +return iomap_bio_submit_read_endio (iter, ctx, iomap_read_end_io); +}static struct bio_set *iomap_read_bio_set (struct iomap_read_folio_ctx *ctx) {
@@ -127,7 +135,6 @@ static void iomap_read_alloc_bio(const struct iomap_iter *iter,if (ctx->rac) bio->bi_opf |=REQ_RAHEAD ; bio->bi_iter.bi_sector =iomap_sector (iomap, iter->pos); - bio->bi_end_io = iomap_read_end_io;bio_add_folio_nofail (bio, folio, plen,offset_in_folio (folio, iter->pos)); ctx->read_ctx = bio;
fs/ntfs/aops.c +2 -4
@@ -38,11 +38,9 @@ static void ntfs_iomap_read_end_io(struct bio *bio) }static void ntfs_iomap_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx) { -struct bio *bio = ctx->read_ctx; - bio->bi_end_io = ntfs_iomap_read_end_io; -submit_bio (bio); +iomap_bio_submit_read_endio (iter, ctx, ntfs_iomap_read_end_io); }static const struct iomap_read_ops ntfs_iomap_bio_read_ops = {
fs/ntfs3/inode.c +1 -4
@@ -609,10 +609,7 @@ static void ntfs_iomap_read_end_io(struct bio *bio)static void ntfs_iomap_bio_submit_read (const struct iomap_iter *iter,struct iomap_read_folio_ctx *ctx) { -struct bio *bio = ctx->read_ctx; - - bio->bi_end_io = ntfs_iomap_read_end_io; -submit_bio (bio); +iomap_bio_submit_read_endio (iter, ctx, ntfs_iomap_read_end_io); }static const struct iomap_read_ops ntfs_iomap_bio_read_ops = {
fs/xfs/xfs_aops.c +1 -2
@@ -764,8 +764,7 @@ xfs_bio_submit_read(/* defer read completions to the ioend workqueue */ iomap_init_ioend (iter->inode, bio, ctx->read_ctx_file_offset,0 ); - bio->bi_end_io = xfs_end_bio; -submit_bio (bio); +iomap_bio_submit_read_endio (iter, ctx, xfs_end_bio); }static const struct iomap_read_ops xfs_iomap_read_ops = {
include/linux/iomap.h +2 -0
@@ -622,6 +622,8 @@ extern struct bio_set iomap_ioend_bioset;#ifdef CONFIG_BLOCK int iomap_bio_read_folio_range (const struct iomap_iter *iter,struct iomap_read_folio_ctx *ctx,size_t plen); +void iomap_bio_submit_read_endio (const struct iomap_iter *iter, +struct iomap_read_folio_ctx *ctx,bio_end_io_t end_io);extern const struct iomap_read_ops iomap_bio_read_ops;
Signature · 1 line
2.53.0
Re: [PATCH 1/2] iomap: consolidate bio submission
Quoted 49 lines · Christoph Hellwig
Add a
iomap_bio_submit_read_endiohelper factored out ofiomap_bio_submit_readto that all ->submit_read implementations foriomap_read_opsthat useiomap_bio_read_folio_rangecan shared the logic.Right now that logic is mostly trivial, but already has a bug for XFS because the XFS version is too trivial: file system integrity validation needs a workqueue context and thus can't happen from the default iomap
bi_end_ioI/O handler. Unfortunately the iomap refactoring just before fs integrity landed moved code around here and the call go misplaced, meaning it never got called. The PI information still is verified by the block layer, but the offloading is less efficient (and the future userspace interface can't get at it).Fixes 0b10a370529c ("iomap: support T10 protection information")Signed-off-by Christoph Hellwig <[email protected]>--- fs/exfat/iomap.c | 5 +---- fs/iomap/bio.c | 13 ++++++++++--- fs/ntfs/aops.c | 6 ++---- fs/ntfs3/inode.c | 5 +---- fs/xfs/xfs_aops.c | 3 +-- include/linux/iomap.h | 2 ++ 6 files changed, 17 insertions(+), 17 deletions(-)fs/exfat/iomap.c +1
-4@@ -253,10 +253,7 @@ static void exfat_iomap_read_end_io(struct bio *bio)static void exfat_iomap_bio_submit_read (const struct iomap_iter *iter,struct iomap_read_folio_ctx *ctx) { -struct bio *bio = ctx->read_ctx; - - bio->bi_end_io = exfat_iomap_read_end_io; -submit_bio (bio); +iomap_bio_submit_read_endio (iter, ctx, exfat_iomap_read_end_io); }const struct iomap_read_ops exfat_iomap_bio_read_ops = {fs/iomap/bio.c +0
-0@@ -78,15 +78,23 @@ u32 iomap_finish_ioend_buffered_read(struct iomap_ioend *ioend)return __iomap_read_end_io (&ioend->io_bio, ioend->io_error); }
fs/iomap/bio.c u32 iomap_finish_ioend_buffered_read(struct iomap_ioend *ioend) · line 88
Quoted 10 lines
fs/iomap/bio.c +3
-2-static void iomap_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +void iomap_bio_submit_read_endio (const struct iomap_iter *iter, +struct iomap_read_folio_ctx *ctx,bio_end_io_t end_io) {struct bio *bio = ctx->read_ctx; + bio->bi_end_io = end_io;if (iter->iomap.flags &IOMAP_F_INTEGRITY )fs_bio_integrity_alloc (bio);
Ah, so the bug here is that all the pagecache readers should have been allocating integrity information for the bio before submitting it? And because it doesn't, iomap_finish_ioend won't do the read verification? So the block layer does it for us, and that's why we don't use the ioend chaining? And (I guess) the future userspace interface won't have any means to get at the integrity data?
If the answers to all four questions is "yes" then I've understood this fix well enough to declare
--D
Quoted 85 lines
fs/iomap/bio.c +7
-1submit_bio (bio); } +EXPORT_SYMBOL_GPL (iomap_bio_submit_read_endio); + +static void iomap_bio_submit_read (const struct iomap_iter *iter, +struct iomap_read_folio_ctx *ctx) +{ +return iomap_bio_submit_read_endio (iter, ctx, iomap_read_end_io); +}static struct bio_set *iomap_read_bio_set (struct iomap_read_folio_ctx *ctx) {@@ -127,7 +135,6 @@ static void iomap_read_alloc_bio(const struct iomap_iter *iter,if (ctx->rac) bio->bi_opf |=REQ_RAHEAD ; bio->bi_iter.bi_sector =iomap_sector (iomap, iter->pos); - bio->bi_end_io = iomap_read_end_io;bio_add_folio_nofail (bio, folio, plen,offset_in_folio (folio, iter->pos)); ctx->read_ctx = bio;fs/ntfs/aops.c +2
-4@@ -38,11 +38,9 @@ static void ntfs_iomap_read_end_io(struct bio *bio) }static void ntfs_iomap_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx) { -struct bio *bio = ctx->read_ctx; - bio->bi_end_io = ntfs_iomap_read_end_io; -submit_bio (bio); +iomap_bio_submit_read_endio (iter, ctx, ntfs_iomap_read_end_io); }static const struct iomap_read_ops ntfs_iomap_bio_read_ops = {fs/ntfs3/inode.c +1
-4@@ -609,10 +609,7 @@ static void ntfs_iomap_read_end_io(struct bio *bio)static void ntfs_iomap_bio_submit_read (const struct iomap_iter *iter,struct iomap_read_folio_ctx *ctx) { -struct bio *bio = ctx->read_ctx; - - bio->bi_end_io = ntfs_iomap_read_end_io; -submit_bio (bio); +iomap_bio_submit_read_endio (iter, ctx, ntfs_iomap_read_end_io); }static const struct iomap_read_ops ntfs_iomap_bio_read_ops = {fs/xfs/xfs_aops.c +1
-2@@ -764,8 +764,7 @@ xfs_bio_submit_read(/* defer read completions to the ioend workqueue */ iomap_init_ioend (iter->inode, bio, ctx->read_ctx_file_offset,0 ); - bio->bi_end_io = xfs_end_bio; -submit_bio (bio); +iomap_bio_submit_read_endio (iter, ctx, xfs_end_bio); }static const struct iomap_read_ops xfs_iomap_read_ops = {include/linux/iomap.h +2
-0@@ -622,6 +622,8 @@ extern struct bio_set iomap_ioend_bioset;#ifdef CONFIG_BLOCK int iomap_bio_read_folio_range (const struct iomap_iter *iter,struct iomap_read_folio_ctx *ctx,size_t plen); +void iomap_bio_submit_read_endio (const struct iomap_iter *iter, +struct iomap_read_folio_ctx *ctx,bio_end_io_t end_io);extern const struct iomap_read_ops iomap_bio_read_ops;Signature · 1 line
2.53.0
Re: [PATCH 1/2] iomap: consolidate bio submission
Quoted 7 lines · Darrick J. Wong
fs/iomap/bio.c u32 iomap_finish_ioend_buffered_read(struct iomap_ioend *ioend) · line 88
Quoted 4 lines
fs/iomap/bio.c +1
-0+ bio->bi_end_io = end_io;if (iter->iomap.flags &IOMAP_F_INTEGRITY )fs_bio_integrity_alloc (bio);Ah, so the bug here is that all the pagecache readers should have been allocating integrity information for the bio before submitting it?
Well, all the ones that set IOMAP_F_INTEGRITY, which really is just XFS at the momen. And because if the iomap refactoring for fuse XFS is now using it's own submit callback and does not get it..
Quoted 2 lines
And
because it doesn't,iomap_finish_ioendwon't do the read verification?
Yeah.
Quoted 3 lines
So the block layer does it for us, and that's why we don't use the ioend chaining? And (I guess) the future userspace interface won't have any means to get at the integrity data?
Yeah.
PATCH 2/2 iomap: submit read bio after each extent
In reply to Christoph HellwigCurrently the iomap buffered read path tries to build up read context (i.e. bios for the typical block based case) over multiple iomaps as long as the sector matches. This does not take into account files that can map to multiple different devices. While this could be fixed by a bdev check in iomap_bio_read_folio_range, the building up of I/O over iomaps actually was a problem for the not yet merged ext2 iomap port, as that does want to send out I/O at the end of an indirect block mapped range.
So instead of adding more checks move over to a model where a bio only spans a single iomap. Change ->submit_read to be called after each iteration, and pass a force argument to indicate that the bio must be submitted set on the last iteration. Switch the bio based users to always submit, while keeping the single submit for fuse.
--- fs/exfat/iomap.c | 2 +- fs/fuse/file.c | 6 +++++- fs/iomap/bio.c | 6 ++++-- fs/iomap/buffered-io.c | 21 +++++++++++++-------- fs/ntfs/aops.c | 2 +- fs/ntfs3/inode.c | 2 +- fs/xfs/xfs_aops.c | 3 ++- include/linux/iomap.h | 2 +- 8 files changed, 28 insertions(+), 16 deletions(-)
fs/exfat/iomap.c +1 -1
@@ -251,7 +251,7 @@ static void exfat_iomap_read_end_io(struct bio *bio) }static void exfat_iomap_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx,bool force) {iomap_bio_submit_read_endio (iter, ctx, exfat_iomap_read_end_io); }
fs/fuse/file.c +5 -1
@@ -982,13 +982,17 @@ static int fuse_iomap_read_folio_range_async(const struct iomap_iter *iter, }static void fuse_iomap_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx,bool force) {struct fuse_fill_read_data *data = ctx->read_ctx; +if (!force) +return ; +if (data->ia)fuse_send_readpages (data->ia, data->file, data->nr_bytes, data->fc->async_read); + ctx->read_ctx =NULL ; }static const struct iomap_read_ops fuse_iomap_read_ops = {
fs/iomap/bio.c +4 -2
@@ -87,11 +87,13 @@ void iomap_bio_submit_read_endio(const struct iomap_iter *iter,if (iter->iomap.flags &IOMAP_F_INTEGRITY )fs_bio_integrity_alloc (bio);submit_bio (bio); + + ctx->read_ctx =NULL ; }EXPORT_SYMBOL_GPL (iomap_bio_submit_read_endio);static void iomap_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx,bool force) {return iomap_bio_submit_read_endio (iter, ctx, iomap_read_end_io); }
@@ -116,7 +118,7 @@ static void iomap_read_alloc_bio(const struct iomap_iter *iter,/* Submit the existing range if there was one. */ if (ctx->read_ctx) - ctx->ops->submit_read (iter, ctx); + ctx->ops->submit_read (iter, ctx, true);/* Same as readahead_gfp_mask: */ if (ctx->rac)
fs/iomap/buffered-io.c +13 -8
@@ -524,6 +524,13 @@ static void iomap_read_end(struct folio *folio, size_t bytes_submitted) } } +static void iomap_submit_read (struct iomap_iter *iter, +struct iomap_read_folio_ctx *ctx,bool force) +{ +if (ctx->read_ctx && ctx->ops->submit_read) + ctx->ops->submit_read (iter, ctx, force); +} +static int iomap_read_folio_iter (struct iomap_iter *iter,struct iomap_read_folio_ctx *ctx,size_t *bytes_submitted) {
@@ -642,12 +649,11 @@ void iomap_read_folio(const struct iomap_ops *ops,fsverity_readahead (ctx->vi, folio->index,folio_nr_pages (folio)); -while ((ret =iomap_iter (&iter, ops)) >0 ) +while ((ret =iomap_iter (&iter, ops)) >0 ) { iter.status =iomap_read_folio_iter (&iter, ctx, &bytes_submitted); - -if (ctx->read_ctx && ctx->ops->submit_read) - ctx->ops->submit_read (&iter, ctx); +iomap_submit_read (&iter, ctx, !iter.iomap.length); + }if (ctx->cur_folio)iomap_read_end (ctx->cur_folio, bytes_submitted);
@@ -718,12 +724,11 @@ void iomap_readahead(const struct iomap_ops *ops,fsverity_readahead (ctx->vi,readahead_index (rac),readahead_count (rac)); -while (iomap_iter (&iter, ops) >0 ) +while (iomap_iter (&iter, ops) >0 ) { iter.status =iomap_readahead_iter (&iter, ctx, &cur_bytes_submitted); - -if (ctx->read_ctx && ctx->ops->submit_read) - ctx->ops->submit_read (&iter, ctx); +iomap_submit_read (&iter, ctx, !iter.iomap.length); + }if (ctx->cur_folio)iomap_read_end (ctx->cur_folio, cur_bytes_submitted);
fs/ntfs/aops.c +1 -1
@@ -38,7 +38,7 @@ static void ntfs_iomap_read_end_io(struct bio *bio) }static void ntfs_iomap_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx,bool force) {iomap_bio_submit_read_endio (iter, ctx, ntfs_iomap_read_end_io); }
fs/ntfs3/inode.c +1 -1
@@ -607,7 +607,7 @@ static void ntfs_iomap_read_end_io(struct bio *bio) }static void ntfs_iomap_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx,bool force) {iomap_bio_submit_read_endio (iter, ctx, ntfs_iomap_read_end_io); }
fs/xfs/xfs_aops.c +2 -1
@@ -758,7 +758,8 @@ xfs_vm_bmap(static void xfs_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx, +bool force) {struct bio *bio = ctx->read_ctx;
include/linux/iomap.h +1 -1
@@ -528,7 +528,7 @@ struct iomap_read_ops {* This is optional. */ void (*submit_read)(const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx); +struct iomap_read_folio_ctx *ctx,bool force);/* * Optional, allows filesystem to specify own bio_set, so new bio's
Signature · 1 line
2.53.0
Re: [PATCH 2/2] iomap: submit read bio after each extent
Quoted 8 lines · Christoph Hellwig
Currently the iomap buffered read path tries to build up read context (i.e. bios for the typical block based case) over multiple iomaps as long as the sector matches. This does not take into account files that can map to multiple different devices. While this could be fixed by a bdev check in
iomap_bio_read_folio_range, the building up of I/O over iomaps actually was a problem for the not yet merged ext2 iomap port, as that does want to send out I/O at the end of an indirect block mapped range.
This really puts the onus on block-mapped filesystems (e.g. ext2) to merge adjacent maps into extents. Granted they *probably* already have been doing that.
Quoted 5 lines
So instead of adding more checks move over to a model where a bio only spans a single iomap. Change ->submit_read to be called after each iteration, and pass a force argument to indicate that the bio must be submitted set on the last iteration. Switch the bio based users to always submit, while keeping the single submit for fuse.
Is fuse the sole reason for the "force" parameter to exist? I wonder if fuse could drop its submit_read function and call fuse_send_readpages after the iomap_read{ahead,folio} function returns?
--D
Quoted 187 lines
Fixes dfeab2e95a75 ("erofs: add multiple device support")Reported-by Kelu Ye <[email protected]>Reported-by Yifan Zhao <[email protected]>Signed-off-by Christoph Hellwig <[email protected]>Tested-by Yifan Zhao <[email protected]>--- fs/exfat/iomap.c | 2 +- fs/fuse/file.c | 6 +++++- fs/iomap/bio.c | 6 ++++-- fs/iomap/buffered-io.c | 21 +++++++++++++-------- fs/ntfs/aops.c | 2 +- fs/ntfs3/inode.c | 2 +- fs/xfs/xfs_aops.c | 3 ++- include/linux/iomap.h | 2 +- 8 files changed, 28 insertions(+), 16 deletions(-)fs/exfat/iomap.c +1
-1@@ -251,7 +251,7 @@ static void exfat_iomap_read_end_io(struct bio *bio) }static void exfat_iomap_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx,bool force) {iomap_bio_submit_read_endio (iter, ctx, exfat_iomap_read_end_io); }fs/fuse/file.c +5
-1@@ -982,13 +982,17 @@ static int fuse_iomap_read_folio_range_async(const struct iomap_iter *iter, }static void fuse_iomap_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx,bool force) {struct fuse_fill_read_data *data = ctx->read_ctx; +if (!force) +return ; +if (data->ia)fuse_send_readpages (data->ia, data->file, data->nr_bytes, data->fc->async_read); + ctx->read_ctx =NULL ; }static const struct iomap_read_ops fuse_iomap_read_ops = {fs/iomap/bio.c +4
-2@@ -87,11 +87,13 @@ void iomap_bio_submit_read_endio(const struct iomap_iter *iter,if (iter->iomap.flags &IOMAP_F_INTEGRITY )fs_bio_integrity_alloc (bio);submit_bio (bio); + + ctx->read_ctx =NULL ; }EXPORT_SYMBOL_GPL (iomap_bio_submit_read_endio);static void iomap_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx,bool force) {return iomap_bio_submit_read_endio (iter, ctx, iomap_read_end_io); }@@ -116,7 +118,7 @@ static void iomap_read_alloc_bio(const struct iomap_iter *iter,/* Submit the existing range if there was one. */ if (ctx->read_ctx) - ctx->ops->submit_read (iter, ctx); + ctx->ops->submit_read (iter, ctx, true);/* Same as readahead_gfp_mask: */ if (ctx->rac)fs/iomap/buffered-io.c +13
-8@@ -524,6 +524,13 @@ static void iomap_read_end(struct folio *folio, size_t bytes_submitted) } } +static void iomap_submit_read (struct iomap_iter *iter, +struct iomap_read_folio_ctx *ctx,bool force) +{ +if (ctx->read_ctx && ctx->ops->submit_read) + ctx->ops->submit_read (iter, ctx, force); +} +static int iomap_read_folio_iter (struct iomap_iter *iter,struct iomap_read_folio_ctx *ctx,size_t *bytes_submitted) {@@ -642,12 +649,11 @@ void iomap_read_folio(const struct iomap_ops *ops,fsverity_readahead (ctx->vi, folio->index,folio_nr_pages (folio)); -while ((ret =iomap_iter (&iter, ops)) >0 ) +while ((ret =iomap_iter (&iter, ops)) >0 ) { iter.status =iomap_read_folio_iter (&iter, ctx, &bytes_submitted); - -if (ctx->read_ctx && ctx->ops->submit_read) - ctx->ops->submit_read (&iter, ctx); +iomap_submit_read (&iter, ctx, !iter.iomap.length); + }if (ctx->cur_folio)iomap_read_end (ctx->cur_folio, bytes_submitted);@@ -718,12 +724,11 @@ void iomap_readahead(const struct iomap_ops *ops,fsverity_readahead (ctx->vi,readahead_index (rac),readahead_count (rac)); -while (iomap_iter (&iter, ops) >0 ) +while (iomap_iter (&iter, ops) >0 ) { iter.status =iomap_readahead_iter (&iter, ctx, &cur_bytes_submitted); - -if (ctx->read_ctx && ctx->ops->submit_read) - ctx->ops->submit_read (&iter, ctx); +iomap_submit_read (&iter, ctx, !iter.iomap.length); + }if (ctx->cur_folio)iomap_read_end (ctx->cur_folio, cur_bytes_submitted);fs/ntfs/aops.c +1
-1@@ -38,7 +38,7 @@ static void ntfs_iomap_read_end_io(struct bio *bio) }static void ntfs_iomap_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx,bool force) {iomap_bio_submit_read_endio (iter, ctx, ntfs_iomap_read_end_io); }fs/ntfs3/inode.c +1
-1@@ -607,7 +607,7 @@ static void ntfs_iomap_read_end_io(struct bio *bio) }static void ntfs_iomap_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx,bool force) {iomap_bio_submit_read_endio (iter, ctx, ntfs_iomap_read_end_io); }fs/xfs/xfs_aops.c +2
-1@@ -758,7 +758,8 @@ xfs_vm_bmap(static void xfs_bio_submit_read (const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx) +struct iomap_read_folio_ctx *ctx, +bool force) {struct bio *bio = ctx->read_ctx;include/linux/iomap.h +1
-1@@ -528,7 +528,7 @@ struct iomap_read_ops {* This is optional. */ void (*submit_read)(const struct iomap_iter *iter, -struct iomap_read_folio_ctx *ctx); +struct iomap_read_folio_ctx *ctx,bool force);/* * Optional, allows filesystem to specify own bio_set, so new bio's Signature · 1 line
2.53.0
Re: [PATCH 2/2] iomap: submit read bio after each extent
Quoted 9 lines · Darrick J. Wong
Quoted 5 lines · Christoph Hellwig
So instead of adding more checks move over to a model where a bio only spans a single iomap. Change ->submit_read to be called after each iteration, and pass a force argument to indicate that the bio must be submitted set on the last iteration. Switch the bio based users to always submit, while keeping the single submit for fuse.
Quoted 4 lines
Is fuse the sole reason for the "force" parameter to exist? I wonder if fuse could drop its
submit_readfunction and callfuse_send_readpagesafter the iomap_read{ahead,folio} function returns?
Yes, that works. I think that's a good idea. fuse only needs submit_read logic for readahead. The change would just be:
fs/fuse/file.c +0 -0
@@ -953,19 +953,8 @@ static int
fuse_iomap_read_folio_range_async(const struct iomap_iter *iter,
return ret;
}
-static void fuse_iomap_submit_read(const struct iomap_iter *iter,
- struct iomap_read_folio_ctx *ctx)
-{
- struct fuse_fill_read_data *data = ctx->read_ctx;
-
- if (data->ia)
- fuse_send_readpages(data->ia, data->file, data->nr_bytes,
- data->fc->async_read);
-}
-
static const struct iomap_read_ops fuse_iomap_read_ops = {
.read_folio_range = fuse_iomap_read_folio_range_async,
- .submit_read = fuse_iomap_submit_read,
};
static int fuse_read_folio(struct file *file, struct folio *folio)
@@ -1089,6 +1078,9 @@ static void fuse_readahead(struct readahead_control *rac)
return;
iomap_readahead(&fuse_iomap_ops, &ctx, NULL);+ if (data.ia)
+ fuse_send_readpages(data.ia, data.file, data.nr_bytes,
+ fc->async_read);
}
If this fix needs to go into 7.2 though, maybe it makes sense to land the v1 implementation [1] + the xfs integrity fix now and do the fuse change later?
Thanks,
Joanne
[1] https://lore.kernel.org/linux-fsdevel/[email protected]/
Re: [PATCH 2/2] iomap: submit read bio after each extent
Quoted 2 lines · Joanne Koong
Yes, that works. I think that's a good idea. fuse only needs
submit_readlogic for readahead. The change would just be:
A nice, I'll fold that in.
Quoted 3 lines
If this fix needs to go into 7.2 though, maybe it makes sense to land the v1 implementation [1] + the xfs integrity fix now and do the fuse change later?
In a way this is actually simpler as it doesn't require the prototype change. And it'll avoid both a temporary fuse performance regression and a bit of churn.
Re: [PATCH 2/2] iomap: submit read bio after each extent
Quoted 5 lines · Christoph Hellwig
Quoted 2 lines · Joanne Koong
Yes, that works. I think that's a good idea. fuse only needs
submit_readlogic for readahead. The change would just be:A nice, I'll fold that in.
Btw, can I get a signoff from you for this? It looks like splitting this into a separate patch actually works better. If you have a preferred commit log I'd take that as well instead of mine.
This is what I'm currently testing:
https://git.infradead.org/?p=users/hch/misc.git;a=shortlog;h=refs/heads/iomap-read-submit-bio
Darrick J. Wong
Reviewed-byRe: [PATCH 2/2] iomap: submit read bio after each extent
Quoted 7 lines · Christoph Hellwig
Quoted 5 lines · Christoph Hellwig
Quoted 2 lines · Joanne Koong
Yes, that works. I think that's a good idea. fuse only needs
submit_readlogic for readahead. The change would just be:A nice, I'll fold that in.
Quoted 7 lines
Btw, can I get a signoff from you for this? It looks like splitting this into a separate patch actually works better. If you have a preferred commit log I'd take that as well instead of mine.
This is what I'm currently testing:
https://git.infradead.org/?p=users/hch/misc.git;a=shortlog;h=refs/heads/iomap-read-submit-bio
For both of the patches at the end of the branch,
--D
Re: [PATCH 2/2] iomap: submit read bio after each extent
In reply to Christoph HellwigQuoted 8 lines · Christoph Hellwig
Quoted 5 lines · Christoph Hellwig
Quoted 2 lines · Joanne Koong
Yes, that works. I think that's a good idea. fuse only needs
submit_readlogic for readahead. The change would just be:A nice, I'll fold that in.
Quoted 7 lines
Btw, can I get a signoff from you for this? It looks like splitting this into a separate patch actually works better. If you have a preferred commit log I'd take that as well instead of mine.
This is what I'm currently testing:
https://git.infradead.org/?p=users/hch/misc.git;a=shortlog;h=refs/heads/iomap-read-submit-bio
The submit_read logic is only needed for readahead. We can remove the
+ if (data.ia)
+ fuse_send_readpages(data.ia, data.file, data.nr_bytes,
+ data.fc->async_read);
change to fuse_read_folio().
Thanks,
Joanne
Re: [PATCH 2/2] iomap: submit read bio after each extent
In reply to Darrick J. WongQuoted 10 lines · Darrick J. Wong
Quoted 8 lines · Christoph Hellwig
Currently the iomap buffered read path tries to build up read context (i.e. bios for the typical block based case) over multiple iomaps as long as the sector matches. This does not take into account files that can map to multiple different devices. While this could be fixed by a bdev check in
iomap_bio_read_folio_range, the building up of I/O over iomaps actually was a problem for the not yet merged ext2 iomap port, as that does want to send out I/O at the end of an indirect block mapped range.
Quoted 3 lines
This really puts the onus on block-mapped filesystems (e.g. ext2) to merge adjacent maps into extents. Granted they *probably* already have been doing that.
Yes. In fact the ext2 conversion was the first ask for this change, because they do not want unlimited merging but kick off I/O at the indirect block boundary.
Quoted 9 lines
Quoted 5 lines
So instead of adding more checks move over to a model where a bio only spans a single iomap. Change ->submit_read to be called after each iteration, and pass a force argument to indicate that the bio must be submitted set on the last iteration. Switch the bio based users to always submit, while keeping the single submit for fuse.
Is fuse the sole reason for the "force" parameter to exist? I wonder if fuse could drop its
submit_readfunction and callfuse_send_readpagesafter the iomap_read{ahead,folio} function returns?
Probably..