From 67fd9615a782b11cd0c62823d722a815c9e1eb75 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 10 Jul 2025 15:33:26 +0200 Subject: iomap: pass more arguments using the iomap writeback context Add inode and wpc fields to pass the inode and writeback context that are needed in the entire writeback call chain, and let the callers initialize all fields in the writeback context before calling iomap_writepages to simplify the argument passing. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/20250710133343.399917-3-hch@lst.de Reviewed-by: Brian Foster Reviewed-by: Joanne Koong Reviewed-by: Johannes Thumshirn Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- include/linux/iomap.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 522644d62f30..00179c9387c5 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -448,6 +448,8 @@ struct iomap_writeback_ops { struct iomap_writepage_ctx { struct iomap iomap; + struct inode *inode; + struct writeback_control *wbc; struct iomap_ioend *ioend; const struct iomap_writeback_ops *ops; u32 nr_folios; /* folios added to the ioend */ @@ -461,9 +463,7 @@ void iomap_finish_ioends(struct iomap_ioend *ioend, int error); void iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends); void iomap_sort_ioends(struct list_head *ioend_list); -int iomap_writepages(struct address_space *mapping, - struct writeback_control *wbc, struct iomap_writepage_ctx *wpc, - const struct iomap_writeback_ops *ops); +int iomap_writepages(struct iomap_writepage_ctx *wpc); /* * Flags for direct I/O ->end_io: -- cgit v1.2.3 From fb7399cf2d0b33825b8039f95c45395c7deba25c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 10 Jul 2025 15:33:28 +0200 Subject: iomap: refactor the writeback interface Replace ->map_blocks with a new ->writeback_range, which differs in the following ways: - it must also queue up the I/O for writeback, that is called into the slightly refactored and extended in scope iomap_add_to_ioend for each region - can handle only a part of the requested region, that is the retry loop for partial mappings moves to the caller - handles cleanup on failures as well, and thus also replaces the discard_folio method only implemented by XFS. This will allow to use the iomap writeback code also for file systems that are not block based like fuse. Co-developed-by: Joanne Koong Signed-off-by: Joanne Koong Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/20250710133343.399917-5-hch@lst.de Acked-by: Damien Le Moal # zonefs Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- include/linux/iomap.h | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 00179c9387c5..625d7911a2b5 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -416,18 +416,20 @@ static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio) struct iomap_writeback_ops { /* - * Required, maps the blocks so that writeback can be performed on - * the range starting at offset. + * Required, performs writeback on the passed in range * - * Can return arbitrarily large regions, but we need to call into it at + * Can map arbitrarily large regions, but we need to call into it at * least once per folio to allow the file systems to synchronize with * the write path that could be invalidating mappings. * * An existing mapping from a previous call to this method can be reused * by the file system if it is still valid. + * + * Returns the number of bytes processed or a negative errno. */ - int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode, - loff_t offset, unsigned len); + ssize_t (*writeback_range)(struct iomap_writepage_ctx *wpc, + struct folio *folio, u64 pos, unsigned int len, + u64 end_pos); /* * Optional, allows the file systems to hook into bio submission, @@ -438,12 +440,6 @@ struct iomap_writeback_ops { * the bio could not be submitted. */ int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status); - - /* - * Optional, allows the file system to discard state on a page where - * we failed to submit any I/O. - */ - void (*discard_folio)(struct folio *folio, loff_t pos); }; struct iomap_writepage_ctx { @@ -463,6 +459,9 @@ void iomap_finish_ioends(struct iomap_ioend *ioend, int error); void iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends); void iomap_sort_ioends(struct list_head *ioend_list); +ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio, + loff_t pos, loff_t end_pos, unsigned int dirty_len); + int iomap_writepages(struct iomap_writepage_ctx *wpc); /* -- cgit v1.2.3 From f4fa7981fa26c664cc540cbce9bcb7ffe02a8912 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 10 Jul 2025 15:33:29 +0200 Subject: iomap: hide ioends from the generic writeback code Replace the ioend pointer in iomap_writeback_ctx with a void *wb_ctx one to facilitate non-block, non-ioend writeback for use. Rename the submit_ioend method to writeback_submit and make it mandatory so that the generic writeback code stops seeing ioends and bios. Co-developed-by: Joanne Koong Signed-off-by: Joanne Koong Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/20250710133343.399917-6-hch@lst.de Acked-by: Damien Le Moal Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- include/linux/iomap.h | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 625d7911a2b5..9f32dd8dc075 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -391,8 +391,7 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno, /* * Structure for writeback I/O completions. * - * File systems implementing ->submit_ioend (for buffered I/O) or ->submit_io - * for direct I/O) can split a bio generated by iomap. In that case the parent + * File systems can split a bio generated by iomap. In that case the parent * ioend it was split from is recorded in ioend->io_parent. */ struct iomap_ioend { @@ -416,7 +415,7 @@ static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio) struct iomap_writeback_ops { /* - * Required, performs writeback on the passed in range + * Performs writeback on the passed in range * * Can map arbitrarily large regions, but we need to call into it at * least once per folio to allow the file systems to synchronize with @@ -432,23 +431,22 @@ struct iomap_writeback_ops { u64 end_pos); /* - * Optional, allows the file systems to hook into bio submission, - * including overriding the bi_end_io handler. + * Submit a writeback context previously build up by ->writeback_range. * - * Returns 0 if the bio was successfully submitted, or a negative - * error code if status was non-zero or another error happened and - * the bio could not be submitted. + * Returns 0 if the context was successfully submitted, or a negative + * error code if not. If @error is non-zero a failure occurred, and + * the writeback context should be completed with an error. */ - int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status); + int (*writeback_submit)(struct iomap_writepage_ctx *wpc, int error); }; struct iomap_writepage_ctx { struct iomap iomap; struct inode *inode; struct writeback_control *wbc; - struct iomap_ioend *ioend; const struct iomap_writeback_ops *ops; u32 nr_folios; /* folios added to the ioend */ + void *wb_ctx; /* pending writeback context */ }; struct iomap_ioend *iomap_init_ioend(struct inode *inode, struct bio *bio, @@ -461,6 +459,7 @@ void iomap_ioend_try_merge(struct iomap_ioend *ioend, void iomap_sort_ioends(struct list_head *ioend_list); ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio, loff_t pos, loff_t end_pos, unsigned int dirty_len); +int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error); int iomap_writepages(struct iomap_writepage_ctx *wpc); -- cgit v1.2.3 From 9caf1ea80cedf7d35d9371c44fbe5f84b0da667a Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Thu, 10 Jul 2025 15:33:30 +0200 Subject: iomap: add public helpers for uptodate state manipulation Add a new iomap_start_folio_write helper to abstract away the write_bytes_pending handling, and export it and the existing iomap_finish_folio_write for non-iomap writeback in fuse. Signed-off-by: Joanne Koong [hch: split from a larger patch] Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/20250710133343.399917-7-hch@lst.de Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- include/linux/iomap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 9f32dd8dc075..cbf9d299a616 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -461,6 +461,11 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio, loff_t pos, loff_t end_pos, unsigned int dirty_len); int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error); +void iomap_start_folio_write(struct inode *inode, struct folio *folio, + size_t len); +void iomap_finish_folio_write(struct inode *inode, struct folio *folio, + size_t len); + int iomap_writepages(struct iomap_writepage_ctx *wpc); /* -- cgit v1.2.3 From 8b217cf779cba2b10112f6845dcbbb7e6f4b3d75 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 10 Jul 2025 15:33:34 +0200 Subject: iomap: export iomap_writeback_folio Allow fuse to use iomap_writeback_folio for folio laundering. Note that the caller needs to manually submit the pending writeback context. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/20250710133343.399917-11-hch@lst.de Reviewed-by: Joanne Koong Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- include/linux/iomap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index cbf9d299a616..b65d3f063bb0 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -466,6 +466,7 @@ void iomap_start_folio_write(struct inode *inode, struct folio *folio, void iomap_finish_folio_write(struct inode *inode, struct folio *folio, size_t len); +int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio); int iomap_writepages(struct iomap_writepage_ctx *wpc); /* -- cgit v1.2.3 From 2a5574fc57d13031f869c409181bdeadd75770e1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 10 Jul 2025 15:33:35 +0200 Subject: iomap: replace iomap_folio_ops with iomap_write_ops The iomap_folio_ops are only used for buffered writes, including the zero and unshare variants. Rename them to iomap_write_ops to better describe the usage, and pass them through the call chain like the other operation specific methods instead of through the iomap. xfs_iomap_valid grows a IOMAP_HOLE check to keep the existing behavior that never attached the folio_ops to a iomap representing a hole. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/20250710133343.399917-12-hch@lst.de Acked-by: Damien Le Moal Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- include/linux/iomap.h | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index b65d3f063bb0..80f543cc4fe8 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -101,8 +101,6 @@ struct vm_fault; */ #define IOMAP_NULL_ADDR -1ULL /* addr is not valid */ -struct iomap_folio_ops; - struct iomap { u64 addr; /* disk offset of mapping, bytes */ loff_t offset; /* file offset of mapping, bytes */ @@ -113,7 +111,6 @@ struct iomap { struct dax_device *dax_dev; /* dax_dev for dax operations */ void *inline_data; void *private; /* filesystem private */ - const struct iomap_folio_ops *folio_ops; u64 validity_cookie; /* used with .iomap_valid() */ }; @@ -143,16 +140,11 @@ static inline bool iomap_inline_data_valid(const struct iomap *iomap) } /* - * When a filesystem sets folio_ops in an iomap mapping it returns, get_folio - * and put_folio will be called for each folio written to. This only applies - * to buffered writes as unbuffered writes will not typically have folios - * associated with them. - * * When get_folio succeeds, put_folio will always be called to do any * cleanup work necessary. put_folio is responsible for unlocking and putting * @folio. */ -struct iomap_folio_ops { +struct iomap_write_ops { struct folio *(*get_folio)(struct iomap_iter *iter, loff_t pos, unsigned len); void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied, @@ -335,7 +327,8 @@ static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter) } ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, - const struct iomap_ops *ops, void *private); + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops, void *private); int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); @@ -344,11 +337,14 @@ bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags); void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio); int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, - const struct iomap_ops *ops); + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, - bool *did_zero, const struct iomap_ops *ops, void *private); + bool *did_zero, const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops, void *private); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, - const struct iomap_ops *ops, void *private); + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops, void *private); vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops, void *private); typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, -- cgit v1.2.3 From c5690dd0197809bc5305f474a71b2e71e7eac0ff Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 10 Jul 2025 15:33:37 +0200 Subject: iomap: add read_folio_range() handler for buffered writes Add a read_folio_range() handler for buffered writes that filesystems may pass in if they wish to provide a custom handler for synchronously reading in the contents of a folio. Signed-off-by: Joanne Koong [hch: renamed to read_folio_range, pass less arguments] Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/20250710133343.399917-14-hch@lst.de Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- include/linux/iomap.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 80f543cc4fe8..73dceabc21c8 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -166,6 +166,16 @@ struct iomap_write_ops { * locked by the iomap code. */ bool (*iomap_valid)(struct inode *inode, const struct iomap *iomap); + + /* + * Optional if the filesystem wishes to provide a custom handler for + * reading in the contents of a folio, otherwise iomap will default to + * submitting a bio read request. + * + * The read must be done synchronously. + */ + int (*read_folio_range)(const struct iomap_iter *iter, + struct folio *folio, loff_t pos, size_t len); }; /* -- cgit v1.2.3