From abb0ea1923a68ec8f45a7615ebad1fc87ea06da6 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 7 Feb 2025 09:32:44 -0500 Subject: [PATCH 01/10] iomap: factor out iomap length helper In preparation to support more granular iomap iter advancing, factor the pos/len values as parameters to length calculation. Signed-off-by: Brian Foster Link: https://lore.kernel.org/r/20250207143253.314068-2-bfoster@redhat.com Reviewed-by: Christoph Hellwig Reviewed-by: "Darrick J. Wong" Signed-off-by: Christian Brauner --- include/linux/iomap.h | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 022d7f338c68..feb748eb6294 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -237,6 +237,25 @@ struct iomap_iter { int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); +/** + * iomap_length_trim - trimmed length of the current iomap iteration + * @iter: iteration structure + * @pos: File position to trim from. + * @len: Length of the mapping to trim to. + * + * Returns a trimmed length that the operation applies to for the current + * iteration. + */ +static inline u64 iomap_length_trim(const struct iomap_iter *iter, loff_t pos, + u64 len) +{ + u64 end = iter->iomap.offset + iter->iomap.length; + + if (iter->srcmap.type != IOMAP_HOLE) + end = min(end, iter->srcmap.offset + iter->srcmap.length); + return min(len, end - pos); +} + /** * iomap_length - length of the current iomap iteration * @iter: iteration structure @@ -245,11 +264,7 @@ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); */ static inline u64 iomap_length(const struct iomap_iter *iter) { - u64 end = iter->iomap.offset + iter->iomap.length; - - if (iter->srcmap.type != IOMAP_HOLE) - end = min(end, iter->srcmap.offset + iter->srcmap.length); - return min(iter->len, end - iter->pos); + return iomap_length_trim(iter, iter->pos, iter->len); } /** From 2e4b0b6cf5333f3a8e36d211dd81dd1074ff66c2 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 7 Feb 2025 09:32:45 -0500 Subject: [PATCH 02/10] iomap: split out iomap check and reset logic from iter advance In preparation for more granular iomap_iter advancing, break out some of the logic associated with higher level iteration from iomap_advance_iter(). Specifically, factor the iomap reset code into a separate helper and lift the iomap.length check into the calling code, similar to how ->iomap_end() calls are handled. Signed-off-by: Brian Foster Link: https://lore.kernel.org/r/20250207143253.314068-3-bfoster@redhat.com Reviewed-by: Christoph Hellwig Reviewed-by: "Darrick J. Wong" Signed-off-by: Christian Brauner --- fs/iomap/iter.c | 49 ++++++++++++++++++++++++++----------------------- 1 file changed, 26 insertions(+), 23 deletions(-) diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c index 3790918646af..731ea7267f27 100644 --- a/fs/iomap/iter.c +++ b/fs/iomap/iter.c @@ -7,6 +7,13 @@ #include #include "trace.h" +static inline void iomap_iter_reset_iomap(struct iomap_iter *iter) +{ + iter->processed = 0; + memset(&iter->iomap, 0, sizeof(iter->iomap)); + memset(&iter->srcmap, 0, sizeof(iter->srcmap)); +} + /* * Advance to the next range we need to map. * @@ -14,32 +21,24 @@ * processed - it was aborted because the extent the iomap spanned may have been * changed during the operation. In this case, the iteration behaviour is to * remap the unprocessed range of the iter, and that means we may need to remap - * even when we've made no progress (i.e. iter->processed = 0). Hence the - * "finished iterating" case needs to distinguish between - * (processed = 0) meaning we are done and (processed = 0 && stale) meaning we - * need to remap the entire remaining range. + * even when we've made no progress (i.e. count = 0). Hence the "finished + * iterating" case needs to distinguish between (count = 0) meaning we are done + * and (count = 0 && stale) meaning we need to remap the entire remaining range. */ -static inline int iomap_iter_advance(struct iomap_iter *iter) +static inline int iomap_iter_advance(struct iomap_iter *iter, s64 count) { bool stale = iter->iomap.flags & IOMAP_F_STALE; int ret = 1; - /* handle the previous iteration (if any) */ - if (iter->iomap.length) { - if (iter->processed < 0) - return iter->processed; - if (WARN_ON_ONCE(iter->processed > iomap_length(iter))) - return -EIO; - iter->pos += iter->processed; - iter->len -= iter->processed; - if (!iter->len || (!iter->processed && !stale)) - ret = 0; - } + if (count < 0) + return count; + if (WARN_ON_ONCE(count > iomap_length(iter))) + return -EIO; + iter->pos += count; + iter->len -= count; + if (!iter->len || (!count && !stale)) + ret = 0; - /* clear the per iteration state */ - iter->processed = 0; - memset(&iter->iomap, 0, sizeof(iter->iomap)); - memset(&iter->srcmap, 0, sizeof(iter->srcmap)); return ret; } @@ -82,10 +81,14 @@ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) return ret; } + /* advance and clear state from the previous iteration */ trace_iomap_iter(iter, ops, _RET_IP_); - ret = iomap_iter_advance(iter); - if (ret <= 0) - return ret; + if (iter->iomap.length) { + ret = iomap_iter_advance(iter, iter->processed); + iomap_iter_reset_iomap(iter); + if (ret <= 0) + return ret; + } ret = ops->iomap_begin(iter->inode, iter->pos, iter->len, iter->flags, &iter->iomap, &iter->srcmap); From f4799838662340b3e53da8ff6bcabac743d80f17 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 7 Feb 2025 09:32:46 -0500 Subject: [PATCH 03/10] iomap: refactor iomap_iter() length check and tracepoint iomap_iter() checks iomap.length to skip individual code blocks not appropriate for the initial case where there is no mapping in the iter. To prepare for upcoming changes, refactor the code to jump straight to the ->iomap_begin() handler in the initial case and move the tracepoint to the top of the function so it always executes. Signed-off-by: Brian Foster Link: https://lore.kernel.org/r/20250207143253.314068-4-bfoster@redhat.com Reviewed-by: Christoph Hellwig Reviewed-by: "Darrick J. Wong" Signed-off-by: Christian Brauner --- fs/iomap/iter.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c index 731ea7267f27..a2ae99fe6431 100644 --- a/fs/iomap/iter.c +++ b/fs/iomap/iter.c @@ -73,7 +73,12 @@ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) { int ret; - if (iter->iomap.length && ops->iomap_end) { + trace_iomap_iter(iter, ops, _RET_IP_); + + if (!iter->iomap.length) + goto begin; + + if (ops->iomap_end) { ret = ops->iomap_end(iter->inode, iter->pos, iomap_length(iter), iter->processed > 0 ? iter->processed : 0, iter->flags, &iter->iomap); @@ -82,14 +87,12 @@ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) } /* advance and clear state from the previous iteration */ - trace_iomap_iter(iter, ops, _RET_IP_); - if (iter->iomap.length) { - ret = iomap_iter_advance(iter, iter->processed); - iomap_iter_reset_iomap(iter); - if (ret <= 0) - return ret; - } + ret = iomap_iter_advance(iter, iter->processed); + iomap_iter_reset_iomap(iter); + if (ret <= 0) + return ret; +begin: ret = ops->iomap_begin(iter->inode, iter->pos, iter->len, iter->flags, &iter->iomap, &iter->srcmap); if (ret < 0) From 9183b2a0e439ffa7ba2e176416efc4ffa21406d8 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 7 Feb 2025 09:32:47 -0500 Subject: [PATCH 04/10] iomap: lift error code check out of iomap_iter_advance() The error code is only used to check whether iomap_iter() should terminate due to an error returned in iter.processed. Lift the check out of iomap_iter_advance() in preparation to make it more generic. Signed-off-by: Brian Foster Link: https://lore.kernel.org/r/20250207143253.314068-5-bfoster@redhat.com Reviewed-by: Christoph Hellwig Reviewed-by: "Darrick J. Wong" Signed-off-by: Christian Brauner --- fs/iomap/iter.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c index a2ae99fe6431..1db16be7b9f0 100644 --- a/fs/iomap/iter.c +++ b/fs/iomap/iter.c @@ -30,8 +30,6 @@ static inline int iomap_iter_advance(struct iomap_iter *iter, s64 count) bool stale = iter->iomap.flags & IOMAP_F_STALE; int ret = 1; - if (count < 0) - return count; if (WARN_ON_ONCE(count > iomap_length(iter))) return -EIO; iter->pos += count; @@ -71,6 +69,7 @@ static inline void iomap_iter_done(struct iomap_iter *iter) */ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) { + s64 processed; int ret; trace_iomap_iter(iter, ops, _RET_IP_); @@ -86,8 +85,14 @@ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) return ret; } + processed = iter->processed; + if (processed < 0) { + iomap_iter_reset_iomap(iter); + return processed; + } + /* advance and clear state from the previous iteration */ - ret = iomap_iter_advance(iter, iter->processed); + ret = iomap_iter_advance(iter, processed); iomap_iter_reset_iomap(iter); if (ret <= 0) return ret; From b26f2ea1cd068b0b902e3bb735d05398d8c05aba Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 7 Feb 2025 09:32:48 -0500 Subject: [PATCH 05/10] iomap: lift iter termination logic from iomap_iter_advance() The iter termination logic in iomap_iter_advance() is only needed by iomap_iter() to determine whether to proceed with the next mapping for an ongoing operation. The old logic sets ret to 1 and then terminates if the operation is complete (iter->len == 0) or the previous iteration performed no work and the mapping has not been marked stale. The stale check exists to allow operations to retry the current mapping if an inconsistency has been detected. To further genericize iomap_iter_advance(), lift the termination logic into iomap_iter() and update the former to return success (0) or an error code. iomap_iter() continues on successful advance and non-zero iter->len or otherwise terminates in the no progress (and not stale) or error cases. Signed-off-by: Brian Foster Link: https://lore.kernel.org/r/20250207143253.314068-6-bfoster@redhat.com Reviewed-by: Christoph Hellwig Reviewed-by: "Darrick J. Wong" Signed-off-by: Christian Brauner --- fs/iomap/iter.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c index 1db16be7b9f0..8e0746ad80bd 100644 --- a/fs/iomap/iter.c +++ b/fs/iomap/iter.c @@ -27,17 +27,11 @@ static inline void iomap_iter_reset_iomap(struct iomap_iter *iter) */ static inline int iomap_iter_advance(struct iomap_iter *iter, s64 count) { - bool stale = iter->iomap.flags & IOMAP_F_STALE; - int ret = 1; - if (WARN_ON_ONCE(count > iomap_length(iter))) return -EIO; iter->pos += count; iter->len -= count; - if (!iter->len || (!count && !stale)) - ret = 0; - - return ret; + return 0; } static inline void iomap_iter_done(struct iomap_iter *iter) @@ -69,6 +63,7 @@ static inline void iomap_iter_done(struct iomap_iter *iter) */ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) { + bool stale = iter->iomap.flags & IOMAP_F_STALE; s64 processed; int ret; @@ -91,8 +86,18 @@ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) return processed; } - /* advance and clear state from the previous iteration */ + /* + * Advance the iter and clear state from the previous iteration. Use + * iter->len to determine whether to continue onto the next mapping. + * Explicitly terminate in the case where the current iter has not + * advanced at all (i.e. no work was done for some reason) unless the + * mapping has been marked stale and needs to be reprocessed. + */ ret = iomap_iter_advance(iter, processed); + if (!ret && iter->len > 0) + ret = 1; + if (ret > 0 && !iter->processed && !stale) + ret = 0; iomap_iter_reset_iomap(iter); if (ret <= 0) return ret; From b51d30ff51f9c325b65c8cd66ff6590530b14041 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 7 Feb 2025 09:32:49 -0500 Subject: [PATCH 06/10] iomap: export iomap_iter_advance() and return remaining length As a final step for generic iter advance, export the helper and update it to return the remaining length of the current iteration after the advance. This will usually be 0 in the iomap_iter() case, but will be useful for the various operations that iterate on their own and will be updated to advance as they progress. Signed-off-by: Brian Foster Link: https://lore.kernel.org/r/20250207143253.314068-7-bfoster@redhat.com Reviewed-by: Christoph Hellwig Reviewed-by: "Darrick J. Wong" Signed-off-by: Christian Brauner --- fs/iomap/iter.c | 22 ++++++++-------------- include/linux/iomap.h | 1 + 2 files changed, 9 insertions(+), 14 deletions(-) diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c index 8e0746ad80bd..544cd7a5a16b 100644 --- a/fs/iomap/iter.c +++ b/fs/iomap/iter.c @@ -15,22 +15,16 @@ static inline void iomap_iter_reset_iomap(struct iomap_iter *iter) } /* - * Advance to the next range we need to map. - * - * If the iomap is marked IOMAP_F_STALE, it means the existing map was not fully - * processed - it was aborted because the extent the iomap spanned may have been - * changed during the operation. In this case, the iteration behaviour is to - * remap the unprocessed range of the iter, and that means we may need to remap - * even when we've made no progress (i.e. count = 0). Hence the "finished - * iterating" case needs to distinguish between (count = 0) meaning we are done - * and (count = 0 && stale) meaning we need to remap the entire remaining range. + * Advance the current iterator position and output the length remaining for the + * current mapping. */ -static inline int iomap_iter_advance(struct iomap_iter *iter, s64 count) +int iomap_iter_advance(struct iomap_iter *iter, u64 *count) { - if (WARN_ON_ONCE(count > iomap_length(iter))) + if (WARN_ON_ONCE(*count > iomap_length(iter))) return -EIO; - iter->pos += count; - iter->len -= count; + iter->pos += *count; + iter->len -= *count; + *count = iomap_length(iter); return 0; } @@ -93,7 +87,7 @@ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) * advanced at all (i.e. no work was done for some reason) unless the * mapping has been marked stale and needs to be reprocessed. */ - ret = iomap_iter_advance(iter, processed); + ret = iomap_iter_advance(iter, &processed); if (!ret && iter->len > 0) ret = 1; if (ret > 0 && !iter->processed && !stale) diff --git a/include/linux/iomap.h b/include/linux/iomap.h index feb748eb6294..eed06ffdcfbd 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -236,6 +236,7 @@ struct iomap_iter { }; int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); +int iomap_iter_advance(struct iomap_iter *iter, u64 *count); /** * iomap_length_trim - trimmed length of the current iomap iteration From bc264fea0f6f230e56f876cc4266b1982d20f35d Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 7 Feb 2025 09:32:50 -0500 Subject: [PATCH 07/10] iomap: support incremental iomap_iter advances The current iomap_iter iteration model reads the mapping from the filesystem, processes the subrange of the operation associated with the current mapping, and returns the number of bytes processed back to the iteration code. The latter advances the position and remaining length of the iter in preparation for the next iteration. At the _iter() handler level, this tends to produce a processing loop where the local code pulls the current position and remaining length out of the iter, iterates it locally based on file offset, and then breaks out when the associated range has been fully processed. This works well enough for current handlers, but upcoming enhancements require a bit more flexibility in certain situations. Enhancements for zero range will lead to a situation where the processing loop is no longer a pure ascending offset walk, but rather dictated by pagecache state and folio lookup. Since folio lookup and write preparation occur at different levels, it is more difficult to manage position and length outside of the iter. To provide more flexibility to certain iomap operations, introduce support for incremental iomap_iter advances from within the operation itself. This allows more granular advances for operations that might not use the typical file offset based walk. Note that the semantics for operations that use incremental advances is slightly different than traditional operations. Operations that advance the iter directly are expected to return success or failure (i.e. 0 or negative error code) in iter.processed rather than the number of bytes processed. Signed-off-by: Brian Foster Link: https://lore.kernel.org/r/20250207143253.314068-8-bfoster@redhat.com Reviewed-by: Christoph Hellwig Reviewed-by: "Darrick J. Wong" Signed-off-by: Christian Brauner --- fs/iomap/iter.c | 32 +++++++++++++++++++++++++------- include/linux/iomap.h | 8 ++++++-- 2 files changed, 31 insertions(+), 9 deletions(-) diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c index 544cd7a5a16b..0ebcabc7df52 100644 --- a/fs/iomap/iter.c +++ b/fs/iomap/iter.c @@ -35,6 +35,8 @@ static inline void iomap_iter_done(struct iomap_iter *iter) WARN_ON_ONCE(iter->iomap.offset + iter->iomap.length <= iter->pos); WARN_ON_ONCE(iter->iomap.flags & IOMAP_F_STALE); + iter->iter_start_pos = iter->pos; + trace_iomap_iter_dstmap(iter->inode, &iter->iomap); if (iter->srcmap.type != IOMAP_HOLE) trace_iomap_iter_srcmap(iter->inode, &iter->srcmap); @@ -58,6 +60,8 @@ static inline void iomap_iter_done(struct iomap_iter *iter) int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) { bool stale = iter->iomap.flags & IOMAP_F_STALE; + ssize_t advanced = iter->processed > 0 ? iter->processed : 0; + u64 olen = iter->len; s64 processed; int ret; @@ -66,11 +70,22 @@ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) if (!iter->iomap.length) goto begin; + /* + * If iter.processed is zero, the op may still have advanced the iter + * itself. Calculate the advanced and original length bytes based on how + * far pos has advanced for ->iomap_end(). + */ + if (!advanced) { + advanced = iter->pos - iter->iter_start_pos; + olen += advanced; + } + if (ops->iomap_end) { - ret = ops->iomap_end(iter->inode, iter->pos, iomap_length(iter), - iter->processed > 0 ? iter->processed : 0, - iter->flags, &iter->iomap); - if (ret < 0 && !iter->processed) + ret = ops->iomap_end(iter->inode, iter->iter_start_pos, + iomap_length_trim(iter, iter->iter_start_pos, + olen), + advanced, iter->flags, &iter->iomap); + if (ret < 0 && !advanced) return ret; } @@ -81,8 +96,11 @@ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) } /* - * Advance the iter and clear state from the previous iteration. Use - * iter->len to determine whether to continue onto the next mapping. + * Advance the iter and clear state from the previous iteration. This + * passes iter->processed because that reflects the bytes processed but + * not yet advanced by the iter handler. + * + * Use iter->len to determine whether to continue onto the next mapping. * Explicitly terminate in the case where the current iter has not * advanced at all (i.e. no work was done for some reason) unless the * mapping has been marked stale and needs to be reprocessed. @@ -90,7 +108,7 @@ int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) ret = iomap_iter_advance(iter, &processed); if (!ret && iter->len > 0) ret = 1; - if (ret > 0 && !iter->processed && !stale) + if (ret > 0 && !advanced && !stale) ret = 0; iomap_iter_reset_iomap(iter); if (ret <= 0) diff --git a/include/linux/iomap.h b/include/linux/iomap.h index eed06ffdcfbd..e180dacf434c 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -218,8 +218,11 @@ struct iomap_ops { * calls to iomap_iter(). Treat as read-only in the body. * @len: The remaining length of the file segment we're operating on. * It is updated at the same time as @pos. - * @processed: The number of bytes processed by the body in the most recent - * iteration, or a negative errno. 0 causes the iteration to stop. + * @iter_start_pos: The original start pos for the current iomap. Used for + * incremental iter advance. + * @processed: The number of bytes the most recent iteration needs iomap_iter() + * to advance the iter, zero if the iter was already advanced, or a + * negative errno for an error during the operation. * @flags: Zero or more of the iomap_begin flags above. * @iomap: Map describing the I/O iteration * @srcmap: Source map for COW operations @@ -228,6 +231,7 @@ struct iomap_iter { struct inode *inode; loff_t pos; u64 len; + loff_t iter_start_pos; s64 processed; unsigned flags; struct iomap iomap; From 1a1a3b574b979912882f19d655ddac73f5cbc159 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 7 Feb 2025 09:32:51 -0500 Subject: [PATCH 08/10] iomap: advance the iter directly on buffered writes Modify the buffered write path to advance the iter directly. Replace the local pos and length calculations with direct advances and loop based on iter state instead. Also remove the -EAGAIN return hack as it is no longer necessary now that separate return channels exist for processing progress and error returns. For example, the existing write handler must return either a count of bytes written or error if the write is interrupted, but presumably wants to return -EAGAIN directly in order to break the higher level iomap_iter() loop. Since the current iteration may have made some progress, it unwinds the iter on the way out to return the error while ensuring that portion of the write can be retried. If -EAGAIN occurs at any point beyond the first iteration, iomap_file_buffered_write() will then observe progress based on iter->pos to return a short write. With incremental advances on the iomap_iter, iomap_write_iter() can simply return the error. iomap_iter() completes whatever progress was made based on iomap_iter position and still breaks out of the iter loop based on the error code in iter.processed. The end result of the write is similar in terms of being a short write if progress was made or error return otherwise. Signed-off-by: Brian Foster Link: https://lore.kernel.org/r/20250207143253.314068-9-bfoster@redhat.com Reviewed-by: Christoph Hellwig Reviewed-by: "Darrick J. Wong" Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 3458f97d1b1e..93a7e8bdd15b 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -905,8 +905,6 @@ static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) { - loff_t length = iomap_length(iter); - loff_t pos = iter->pos; ssize_t total_written = 0; long status = 0; struct address_space *mapping = iter->inode->i_mapping; @@ -919,7 +917,8 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) size_t offset; /* Offset into folio */ size_t bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ - size_t written; /* Bytes have been written */ + u64 written; /* Bytes have been written */ + loff_t pos = iter->pos; bytes = iov_iter_count(i); retry: @@ -930,8 +929,8 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) if (unlikely(status)) break; - if (bytes > length) - bytes = length; + if (bytes > iomap_length(iter)) + bytes = iomap_length(iter); /* * Bring in the user page that we'll copy from _first_. @@ -1002,17 +1001,12 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) goto retry; } } else { - pos += written; total_written += written; - length -= written; + iomap_iter_advance(iter, &written); } - } while (iov_iter_count(i) && length); + } while (iov_iter_count(i) && iomap_length(iter)); - if (status == -EAGAIN) { - iov_iter_revert(i, total_written); - return -EAGAIN; - } - return total_written ? total_written : status; + return total_written ? 0 : status; } ssize_t From e60837da4d9daa8abadd9fafd9b1941fa1dba037 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 7 Feb 2025 09:32:52 -0500 Subject: [PATCH 09/10] iomap: advance the iter directly on unshare range Modify unshare range to advance the iter directly. Replace the local pos and length calculations with direct advances and loop based on iter state instead. Signed-off-by: Brian Foster Link: https://lore.kernel.org/r/20250207143253.314068-10-bfoster@redhat.com Reviewed-by: Christoph Hellwig Reviewed-by: "Darrick J. Wong" Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 93a7e8bdd15b..61e541f0364a 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1263,20 +1263,19 @@ EXPORT_SYMBOL_GPL(iomap_write_delalloc_release); static loff_t iomap_unshare_iter(struct iomap_iter *iter) { struct iomap *iomap = &iter->iomap; - loff_t pos = iter->pos; - loff_t length = iomap_length(iter); - loff_t written = 0; + u64 bytes = iomap_length(iter); + int status; if (!iomap_want_unshare_iter(iter)) - return length; + return iomap_iter_advance(iter, &bytes); do { struct folio *folio; - int status; size_t offset; - size_t bytes = min_t(u64, SIZE_MAX, length); + loff_t pos = iter->pos; bool ret; + bytes = min_t(u64, SIZE_MAX, bytes); status = iomap_write_begin(iter, pos, bytes, &folio); if (unlikely(status)) return status; @@ -1294,14 +1293,14 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) cond_resched(); - pos += bytes; - written += bytes; - length -= bytes; - balance_dirty_pages_ratelimited(iter->inode->i_mapping); - } while (length > 0); - return written; + status = iomap_iter_advance(iter, &bytes); + if (status) + break; + } while (bytes > 0); + + return status; } int From cbad829cef3ba7318a2380a0eadc5059770f004a Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 7 Feb 2025 09:32:53 -0500 Subject: [PATCH 10/10] iomap: advance the iter directly on zero range Modify zero range to advance the iter directly. Replace the local pos and length calculations with direct advances and loop based on iter state instead. Signed-off-by: Brian Foster Link: https://lore.kernel.org/r/20250207143253.314068-11-bfoster@redhat.com Reviewed-by: Christoph Hellwig Reviewed-by: "Darrick J. Wong" Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 61e541f0364a..8368a4ae716f 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1341,17 +1341,16 @@ static inline int iomap_zero_iter_flush_and_stale(struct iomap_iter *i) static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) { - loff_t pos = iter->pos; - loff_t length = iomap_length(iter); - loff_t written = 0; + u64 bytes = iomap_length(iter); + int status; do { struct folio *folio; - int status; size_t offset; - size_t bytes = min_t(u64, SIZE_MAX, length); + loff_t pos = iter->pos; bool ret; + bytes = min_t(u64, SIZE_MAX, bytes); status = iomap_write_begin(iter, pos, bytes, &folio); if (status) return status; @@ -1372,14 +1371,14 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) if (WARN_ON_ONCE(!ret)) return -EIO; - pos += bytes; - length -= bytes; - written += bytes; - } while (length > 0); + status = iomap_iter_advance(iter, &bytes); + if (status) + break; + } while (bytes > 0); if (did_zero) *did_zero = true; - return written; + return status; } int @@ -1433,11 +1432,14 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) { - loff_t proc = iomap_length(&iter); + s64 proc; if (range_dirty) { range_dirty = false; proc = iomap_zero_iter_flush_and_stale(&iter); + } else { + u64 length = iomap_length(&iter); + proc = iomap_iter_advance(&iter, &length); } iter.processed = proc; continue;