From 2a6e1a8f4cf39cd3d10c52fca639a7d6f30b7004 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 15 Feb 2024 07:36:37 +0100 Subject: writeback: remove a duplicate prototype for tag_pages_for_writeback [hch@lst.de: split from a larger patch] Link: https://lkml.kernel.org/r/20240215063649.2164017-3-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Brian Foster Reviewed-by: Jan Kara Acked-by: Dave Chinner Cc: Christian Brauner Cc: David Howells Signed-off-by: Andrew Morton --- include/linux/writeback.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/writeback.h') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 453736fd1d23..4b8cf9e4810b 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -363,8 +363,6 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb); typedef int (*writepage_t)(struct folio *folio, struct writeback_control *wbc, void *data); -void tag_pages_for_writeback(struct address_space *mapping, - pgoff_t start, pgoff_t end); int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data); -- cgit v1.2.3 From 751e0d559c62a87dc828af22c3c58dc078c734e3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 15 Feb 2024 07:36:43 +0100 Subject: writeback: factor writeback_get_batch() out of write_cache_pages() This simple helper will be the basis of the writeback iterator. To make this work, we need to remember the current index and end positions in writeback_control. [hch@lst.de: heavily rebased, add helpers to get the tag and end index, don't keep the end index in struct writeback_control] Link: https://lkml.kernel.org/r/20240215063649.2164017-9-hch@lst.de Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Reviewed-by: Jan Kara Acked-by: Dave Chinner Cc: Christian Brauner Cc: David Howells Signed-off-by: Andrew Morton --- include/linux/writeback.h | 6 +++++ mm/page-writeback.c | 60 ++++++++++++++++++++++++++++++----------------- 2 files changed, 44 insertions(+), 22 deletions(-) (limited to 'include/linux/writeback.h') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 4b8cf9e4810b..f67b3ea866a0 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -11,6 +11,7 @@ #include #include #include +#include struct bio; @@ -40,6 +41,7 @@ enum writeback_sync_modes { * in a manner such that unspecified fields are set to zero. */ struct writeback_control { + /* public fields that can be set and/or consumed by the caller: */ long nr_to_write; /* Write this many pages, and decrement this for each page written */ long pages_skipped; /* Pages which were not written */ @@ -77,6 +79,10 @@ struct writeback_control { */ struct swap_iocb **swap_plug; + /* internal fields used by the ->writepages implementation: */ + struct folio_batch fbatch; + pgoff_t index; + #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 4bc55ce9597d..5b8dbbef7137 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2392,6 +2392,29 @@ static bool folio_prepare_writeback(struct address_space *mapping, return true; } +static xa_mark_t wbc_to_tag(struct writeback_control *wbc) +{ + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) + return PAGECACHE_TAG_TOWRITE; + return PAGECACHE_TAG_DIRTY; +} + +static pgoff_t wbc_end(struct writeback_control *wbc) +{ + if (wbc->range_cyclic) + return -1; + return wbc->range_end >> PAGE_SHIFT; +} + +static void writeback_get_batch(struct address_space *mapping, + struct writeback_control *wbc) +{ + folio_batch_release(&wbc->fbatch); + cond_resched(); + filemap_get_folios_tag(mapping, &wbc->index, wbc_end(wbc), + wbc_to_tag(wbc), &wbc->fbatch); +} + /** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. * @mapping: address space structure to write @@ -2429,38 +2452,32 @@ int write_cache_pages(struct address_space *mapping, { int ret = 0; int error; - struct folio_batch fbatch; struct folio *folio; - int nr_folios; - pgoff_t index; pgoff_t end; /* Inclusive */ - xa_mark_t tag; - folio_batch_init(&fbatch); if (wbc->range_cyclic) { - index = mapping->writeback_index; /* prev offset */ + wbc->index = mapping->writeback_index; /* prev offset */ end = -1; } else { - index = wbc->range_start >> PAGE_SHIFT; + wbc->index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; } - if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) { - tag_pages_for_writeback(mapping, index, end); - tag = PAGECACHE_TAG_TOWRITE; - } else { - tag = PAGECACHE_TAG_DIRTY; - } - while (index <= end) { + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) + tag_pages_for_writeback(mapping, wbc->index, end); + + folio_batch_init(&wbc->fbatch); + + while (wbc->index <= end) { int i; - nr_folios = filemap_get_folios_tag(mapping, &index, end, - tag, &fbatch); + writeback_get_batch(mapping, wbc); - if (nr_folios == 0) + if (wbc->fbatch.nr == 0) break; - for (i = 0; i < nr_folios; i++) { - folio = fbatch.folios[i]; + for (i = 0; i < wbc->fbatch.nr; i++) { + folio = wbc->fbatch.folios[i]; + folio_lock(folio); if (!folio_prepare_writeback(mapping, wbc, folio)) { folio_unlock(folio); @@ -2498,8 +2515,6 @@ int write_cache_pages(struct address_space *mapping, goto done; } } - folio_batch_release(&fbatch); - cond_resched(); } /* @@ -2512,6 +2527,7 @@ int write_cache_pages(struct address_space *mapping, * of the file if we are called again, which can only happen due to * -ENOMEM from the file system. */ + folio_batch_release(&wbc->fbatch); if (wbc->range_cyclic) mapping->writeback_index = 0; return ret; @@ -2519,7 +2535,7 @@ int write_cache_pages(struct address_space *mapping, done: if (wbc->range_cyclic) mapping->writeback_index = folio->index + folio_nr_pages(folio); - folio_batch_release(&fbatch); + folio_batch_release(&wbc->fbatch); return error; } EXPORT_SYMBOL(write_cache_pages); -- cgit v1.2.3 From cdc150b575cf1176472791cfbe7738708812ea0d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Feb 2024 07:36:48 +0100 Subject: writeback: add a writeback iterator Refactor the code left in write_cache_pages into an iterator that the file system can call to get the next folio for a writeback operation: struct folio *folio = NULL; while ((folio = writeback_iter(mapping, wbc, folio, &error))) { error = ; } The twist here is that the error value is passed by reference, so that the iterator can restore it when breaking out of the loop. Handling of the magic AOP_WRITEPAGE_ACTIVATE value stays outside the iterator and needs is just kept in the write_cache_pages legacy wrapper. in preparation for eventually killing it off. Heavily based on a for_each* based iterator from Matthew Wilcox. Link: https://lkml.kernel.org/r/20240215063649.2164017-14-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Reviewed-by: Jan Kara Cc: Christian Brauner Cc: Dave Chinner Cc: David Howells Cc: "Matthew Wilcox (Oracle)" Signed-off-by: Andrew Morton --- include/linux/writeback.h | 4 + mm/page-writeback.c | 192 +++++++++++++++++++++++++++------------------- 2 files changed, 118 insertions(+), 78 deletions(-) (limited to 'include/linux/writeback.h') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index f67b3ea866a0..9845cb62e40b 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -82,6 +82,7 @@ struct writeback_control { /* internal fields used by the ->writepages implementation: */ struct folio_batch fbatch; pgoff_t index; + int saved_err; #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ @@ -366,6 +367,9 @@ int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, bool wb_over_bg_thresh(struct bdi_writeback *wb); +struct folio *writeback_iter(struct address_space *mapping, + struct writeback_control *wbc, struct folio *folio, int *error); + typedef int (*writepage_t)(struct folio *folio, struct writeback_control *wbc, void *data); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index fc421402f818..3da4345f08a3 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2325,18 +2325,18 @@ void __init page_writeback_init(void) } /** - * tag_pages_for_writeback - tag pages to be written by write_cache_pages + * tag_pages_for_writeback - tag pages to be written by writeback * @mapping: address space structure to write * @start: starting page index * @end: ending page index (inclusive) * * This function scans the page range from @start to @end (inclusive) and tags - * all pages that have DIRTY tag set with a special TOWRITE tag. The idea is - * that write_cache_pages (or whoever calls this function) will then use - * TOWRITE tag to identify pages eligible for writeback. This mechanism is - * used to avoid livelocking of writeback by a process steadily creating new - * dirty pages in the file (thus it is important for this function to be quick - * so that it can tag pages faster than a dirtying process can create them). + * all pages that have DIRTY tag set with a special TOWRITE tag. The caller + * can then use the TOWRITE tag to identify pages eligible for writeback. + * This mechanism is used to avoid livelocking of writeback by a process + * steadily creating new dirty pages in the file (thus it is important for this + * function to be quick so that it can tag pages faster than a dirtying process + * can create them). */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) @@ -2434,69 +2434,68 @@ retry: } /** - * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. + * writeback_iter - iterate folio of a mapping for writeback * @mapping: address space structure to write - * @wbc: subtract the number of written pages from *@wbc->nr_to_write - * @writepage: function called for each page - * @data: data passed to writepage function + * @wbc: writeback context + * @folio: previously iterated folio (%NULL to start) + * @error: in-out pointer for writeback errors (see below) * - * If a page is already under I/O, write_cache_pages() skips it, even - * if it's dirty. This is desirable behaviour for memory-cleaning writeback, - * but it is INCORRECT for data-integrity system calls such as fsync(). fsync() - * and msync() need to guarantee that all the data which was dirty at the time - * the call was made get new I/O started against them. If wbc->sync_mode is - * WB_SYNC_ALL then we were called for data integrity and we must wait for - * existing IO to complete. - * - * To avoid livelocks (when other process dirties new pages), we first tag - * pages which should be written back with TOWRITE tag and only then start - * writing them. For data-integrity sync we have to be careful so that we do - * not miss some pages (e.g., because some other process has cleared TOWRITE - * tag we set). The rule we follow is that TOWRITE tag can be cleared only - * by the process clearing the DIRTY tag (and submitting the page for IO). - * - * To avoid deadlocks between range_cyclic writeback and callers that hold - * pages in PageWriteback to aggregate IO until write_cache_pages() returns, - * we do not loop back to the start of the file. Doing so causes a page - * lock/page writeback access order inversion - we should only ever lock - * multiple pages in ascending page->index order, and looping back to the start - * of the file violates that rule and causes deadlocks. + * This function returns the next folio for the writeback operation described by + * @wbc on @mapping and should be called in a while loop in the ->writepages + * implementation. * - * Return: %0 on success, negative error code otherwise + * To start the writeback operation, %NULL is passed in the @folio argument, and + * for every subsequent iteration the folio returned previously should be passed + * back in. + * + * If there was an error in the per-folio writeback inside the writeback_iter() + * loop, @error should be set to the error value. + * + * Once the writeback described in @wbc has finished, this function will return + * %NULL and if there was an error in any iteration restore it to @error. + * + * Note: callers should not manually break out of the loop using break or goto + * but must keep calling writeback_iter() until it returns %NULL. + * + * Return: the folio to write or %NULL if the loop is done. */ -int write_cache_pages(struct address_space *mapping, - struct writeback_control *wbc, writepage_t writepage, - void *data) +struct folio *writeback_iter(struct address_space *mapping, + struct writeback_control *wbc, struct folio *folio, int *error) { - int ret = 0; - int error; - struct folio *folio; - pgoff_t end; /* Inclusive */ - - if (wbc->range_cyclic) { - wbc->index = mapping->writeback_index; /* prev offset */ - end = -1; - } else { - wbc->index = wbc->range_start >> PAGE_SHIFT; - end = wbc->range_end >> PAGE_SHIFT; - } - if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) - tag_pages_for_writeback(mapping, wbc->index, end); - - folio_batch_init(&wbc->fbatch); + if (!folio) { + folio_batch_init(&wbc->fbatch); + wbc->saved_err = *error = 0; - for (;;) { - folio = writeback_get_folio(mapping, wbc); - if (!folio) - break; + /* + * For range cyclic writeback we remember where we stopped so + * that we can continue where we stopped. + * + * For non-cyclic writeback we always start at the beginning of + * the passed in range. + */ + if (wbc->range_cyclic) + wbc->index = mapping->writeback_index; + else + wbc->index = wbc->range_start >> PAGE_SHIFT; - error = writepage(folio, wbc, data); + /* + * To avoid livelocks when other processes dirty new pages, we + * first tag pages which should be written back and only then + * start writing them. + * + * For data-integrity writeback we have to be careful so that we + * do not miss some pages (e.g., because some other process has + * cleared the TOWRITE tag we set). The rule we follow is that + * TOWRITE tag can be cleared only by the process clearing the + * DIRTY tag (and submitting the page for I/O). + */ + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) + tag_pages_for_writeback(mapping, wbc->index, + wbc_end(wbc)); + } else { wbc->nr_to_write -= folio_nr_pages(folio); - if (error == AOP_WRITEPAGE_ACTIVATE) { - folio_unlock(folio); - error = 0; - } + WARN_ON_ONCE(*error > 0); /* * For integrity writeback we have to keep going until we have @@ -2510,33 +2509,70 @@ int write_cache_pages(struct address_space *mapping, * wbc->nr_to_write or encounter the first error. */ if (wbc->sync_mode == WB_SYNC_ALL) { - if (error && !ret) - ret = error; + if (*error && !wbc->saved_err) + wbc->saved_err = *error; } else { - if (error || wbc->nr_to_write <= 0) + if (*error || wbc->nr_to_write <= 0) goto done; } } - /* - * For range cyclic writeback we need to remember where we stopped so - * that we can continue there next time we are called. If we hit the - * last page and there is more work to be done, wrap back to the start - * of the file. - * - * For non-cyclic writeback we always start looking up at the beginning - * of the file if we are called again, which can only happen due to - * -ENOMEM from the file system. - */ - folio_batch_release(&wbc->fbatch); - if (wbc->range_cyclic) - mapping->writeback_index = 0; - return ret; + folio = writeback_get_folio(mapping, wbc); + if (!folio) { + /* + * To avoid deadlocks between range_cyclic writeback and callers + * that hold pages in PageWriteback to aggregate I/O until + * the writeback iteration finishes, we do not loop back to the + * start of the file. Doing so causes a page lock/page + * writeback access order inversion - we should only ever lock + * multiple pages in ascending page->index order, and looping + * back to the start of the file violates that rule and causes + * deadlocks. + */ + if (wbc->range_cyclic) + mapping->writeback_index = 0; + + /* + * Return the first error we encountered (if there was any) to + * the caller. + */ + *error = wbc->saved_err; + } + return folio; done: if (wbc->range_cyclic) mapping->writeback_index = folio->index + folio_nr_pages(folio); folio_batch_release(&wbc->fbatch); + return NULL; +} + +/** + * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. + * @mapping: address space structure to write + * @wbc: subtract the number of written pages from *@wbc->nr_to_write + * @writepage: function called for each page + * @data: data passed to writepage function + * + * Return: %0 on success, negative error code otherwise + * + * Note: please use writeback_iter() instead. + */ +int write_cache_pages(struct address_space *mapping, + struct writeback_control *wbc, writepage_t writepage, + void *data) +{ + struct folio *folio = NULL; + int error; + + while ((folio = writeback_iter(mapping, wbc, folio, &error))) { + error = writepage(folio, wbc, data); + if (error == AOP_WRITEPAGE_ACTIVATE) { + folio_unlock(folio); + error = 0; + } + } + return error; } EXPORT_SYMBOL(write_cache_pages); -- cgit v1.2.3