From 84429b675bcfd2a518ae167ee4661cdf7539aa7d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 22 Aug 2024 15:50:09 +0200 Subject: [PATCH 01/22] fs: Allow fine-grained control of folio sizes We need filesystems to be able to communicate acceptable folio sizes to the pagecache for a variety of uses (e.g. large block sizes). Support a range of folio sizes between order-0 and order-31. Signed-off-by: Matthew Wilcox (Oracle) Co-developed-by: Pankaj Raghav Signed-off-by: Pankaj Raghav Link: https://lore.kernel.org/r/20240822135018.1931258-2-kernel@pankajraghav.com Tested-by: David Howells Reviewed-by: Hannes Reinecke Reviewed-by: Darrick J. Wong Reviewed-by: Daniel Gomez Signed-off-by: Christian Brauner --- include/linux/pagemap.h | 90 ++++++++++++++++++++++++++++++++++------- mm/filemap.c | 6 +-- mm/readahead.c | 4 +- 3 files changed, 80 insertions(+), 20 deletions(-) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d9c7edb6422b..c60025bb584c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -204,14 +204,21 @@ enum mapping_flags { AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, - AS_LARGE_FOLIO_SUPPORT = 6, - AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */ - AS_STABLE_WRITES, /* must wait for writeback before modifying + AS_RELEASE_ALWAYS = 6, /* Call ->release_folio(), even if no private data */ + AS_STABLE_WRITES = 7, /* must wait for writeback before modifying folio contents */ - AS_INACCESSIBLE, /* Do not attempt direct R/W access to the mapping, - including to move the mapping */ + AS_INACCESSIBLE = 8, /* Do not attempt direct R/W access to the mapping */ + /* Bits 16-25 are used for FOLIO_ORDER */ + AS_FOLIO_ORDER_BITS = 5, + AS_FOLIO_ORDER_MIN = 16, + AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS, }; +#define AS_FOLIO_ORDER_BITS_MASK ((1u << AS_FOLIO_ORDER_BITS) - 1) +#define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MIN) +#define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MAX) +#define AS_FOLIO_ORDER_MASK (AS_FOLIO_ORDER_MIN_MASK | AS_FOLIO_ORDER_MAX_MASK) + /** * mapping_set_error - record a writeback error in the address_space * @mapping: the mapping in which an error should be set @@ -367,9 +374,51 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1) #define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER) +/* + * mapping_set_folio_order_range() - Set the orders supported by a file. + * @mapping: The address space of the file. + * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive). + * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive). + * + * The filesystem should call this function in its inode constructor to + * indicate which base size (min) and maximum size (max) of folio the VFS + * can use to cache the contents of the file. This should only be used + * if the filesystem needs special handling of folio sizes (ie there is + * something the core cannot know). + * Do not tune it based on, eg, i_size. + * + * Context: This should not be called while the inode is active as it + * is non-atomic. + */ +static inline void mapping_set_folio_order_range(struct address_space *mapping, + unsigned int min, + unsigned int max) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return; + + if (min > MAX_PAGECACHE_ORDER) + min = MAX_PAGECACHE_ORDER; + + if (max > MAX_PAGECACHE_ORDER) + max = MAX_PAGECACHE_ORDER; + + if (max < min) + max = min; + + mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) | + (min << AS_FOLIO_ORDER_MIN) | (max << AS_FOLIO_ORDER_MAX); +} + +static inline void mapping_set_folio_min_order(struct address_space *mapping, + unsigned int min) +{ + mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER); +} + /** * mapping_set_large_folios() - Indicate the file supports large folios. - * @mapping: The file. + * @mapping: The address space of the file. * * The filesystem should call this function in its inode constructor to * indicate that the VFS can use large folios to cache the contents of @@ -380,7 +429,23 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) */ static inline void mapping_set_large_folios(struct address_space *mapping) { - __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); + mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER); +} + +static inline unsigned int +mapping_max_folio_order(const struct address_space *mapping) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return 0; + return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX; +} + +static inline unsigned int +mapping_min_folio_order(const struct address_space *mapping) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return 0; + return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN; } /* @@ -389,20 +454,17 @@ static inline void mapping_set_large_folios(struct address_space *mapping) */ static inline bool mapping_large_folio_support(struct address_space *mapping) { - /* AS_LARGE_FOLIO_SUPPORT is only reasonable for pagecache folios */ + /* AS_FOLIO_ORDER is only reasonable for pagecache folios */ VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON, "Anonymous mapping always supports large folio"); - return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && - test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); + return mapping_max_folio_order(mapping) > 0; } /* Return the maximum folio size for this pagecache mapping, in bytes. */ -static inline size_t mapping_max_folio_size(struct address_space *mapping) +static inline size_t mapping_max_folio_size(const struct address_space *mapping) { - if (mapping_large_folio_support(mapping)) - return PAGE_SIZE << MAX_PAGECACHE_ORDER; - return PAGE_SIZE; + return PAGE_SIZE << mapping_max_folio_order(mapping); } static inline int filemap_nr_thps(struct address_space *mapping) diff --git a/mm/filemap.c b/mm/filemap.c index d62150418b91..ad5e4a848070 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1933,10 +1933,8 @@ no_page: if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; - if (!mapping_large_folio_support(mapping)) - order = 0; - if (order > MAX_PAGECACHE_ORDER) - order = MAX_PAGECACHE_ORDER; + if (order > mapping_max_folio_order(mapping)) + order = mapping_max_folio_order(mapping); /* If we're not aligned, allocate a smaller folio */ if (index & ((1UL << order) - 1)) order = __ffs(index); diff --git a/mm/readahead.c b/mm/readahead.c index 517c0be7ce66..3e5239e9e177 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -449,10 +449,10 @@ void page_cache_ra_order(struct readahead_control *ractl, limit = min(limit, index + ra->size - 1); - if (new_order < MAX_PAGECACHE_ORDER) + if (new_order < mapping_max_folio_order(mapping)) new_order += 2; - new_order = min_t(unsigned int, MAX_PAGECACHE_ORDER, new_order); + new_order = min(mapping_max_folio_order(mapping), new_order); new_order = min_t(unsigned int, new_order, ilog2(ra->size)); /* See comment in page_cache_ra_unbounded() */ From ab95d23bab220ef845c0d422f49452a475330eaf Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Thu, 22 Aug 2024 15:50:10 +0200 Subject: [PATCH 02/22] filemap: allocate mapping_min_order folios in the page cache filemap_create_folio() and do_read_cache_folio() were always allocating folio of order 0. __filemap_get_folio was trying to allocate higher order folios when fgp_flags had higher order hint set but it will default to order 0 folio if higher order memory allocation fails. Supporting mapping_min_order implies that we guarantee each folio in the page cache has at least an order of mapping_min_order. When adding new folios to the page cache we must also ensure the index used is aligned to the mapping_min_order as the page cache requires the index to be aligned to the order of the folio. Co-developed-by: Luis Chamberlain Signed-off-by: Luis Chamberlain Signed-off-by: Pankaj Raghav Link: https://lore.kernel.org/r/20240822135018.1931258-3-kernel@pankajraghav.com Tested-by: David Howells Reviewed-by: Hannes Reinecke Reviewed-by: Darrick J. Wong Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Daniel Gomez Reviewed-by: Dave Chinner Signed-off-by: Christian Brauner --- include/linux/pagemap.h | 20 ++++++++++++++++++++ mm/filemap.c | 24 ++++++++++++++++-------- 2 files changed, 36 insertions(+), 8 deletions(-) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c60025bb584c..4cc170949e9c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -448,6 +448,26 @@ mapping_min_folio_order(const struct address_space *mapping) return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN; } +static inline unsigned long +mapping_min_folio_nrpages(struct address_space *mapping) +{ + return 1UL << mapping_min_folio_order(mapping); +} + +/** + * mapping_align_index() - Align index for this mapping. + * @mapping: The address_space. + * + * The index of a folio must be naturally aligned. If you are adding a + * new folio to the page cache and need to know what index to give it, + * call this function. + */ +static inline pgoff_t mapping_align_index(struct address_space *mapping, + pgoff_t index) +{ + return round_down(index, mapping_min_folio_nrpages(mapping)); +} + /* * Large folio support currently depends on THP. These dependencies are * being worked on but are not yet fixed. diff --git a/mm/filemap.c b/mm/filemap.c index ad5e4a848070..d27e9ac54309 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -859,6 +859,8 @@ noinline int __filemap_add_folio(struct address_space *mapping, VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); + VM_BUG_ON_FOLIO(folio_order(folio) < mapping_min_folio_order(mapping), + folio); mapping_set_update(&xas, mapping); VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); @@ -1919,8 +1921,10 @@ repeat: folio_wait_stable(folio); no_page: if (!folio && (fgp_flags & FGP_CREAT)) { - unsigned order = FGF_GET_ORDER(fgp_flags); + unsigned int min_order = mapping_min_folio_order(mapping); + unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags)); int err; + index = mapping_align_index(mapping, index); if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp |= __GFP_WRITE; @@ -1943,7 +1947,7 @@ no_page: gfp_t alloc_gfp = gfp; err = -ENOMEM; - if (order > 0) + if (order > min_order) alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN; folio = filemap_alloc_folio(alloc_gfp, order); if (!folio) @@ -1958,7 +1962,7 @@ no_page: break; folio_put(folio); folio = NULL; - } while (order-- > 0); + } while (order-- > min_order); if (err == -EEXIST) goto repeat; @@ -2447,13 +2451,15 @@ unlock_mapping: } static int filemap_create_folio(struct file *file, - struct address_space *mapping, pgoff_t index, + struct address_space *mapping, loff_t pos, struct folio_batch *fbatch) { struct folio *folio; int error; + unsigned int min_order = mapping_min_folio_order(mapping); + pgoff_t index; - folio = filemap_alloc_folio(mapping_gfp_mask(mapping), 0); + folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order); if (!folio) return -ENOMEM; @@ -2471,6 +2477,7 @@ static int filemap_create_folio(struct file *file, * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); + index = (pos >> (PAGE_SHIFT + min_order)) << min_order; error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) @@ -2531,8 +2538,7 @@ retry: if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) return -EAGAIN; - err = filemap_create_folio(filp, mapping, - iocb->ki_pos >> PAGE_SHIFT, fbatch); + err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; @@ -3748,9 +3754,11 @@ static struct folio *do_read_cache_folio(struct address_space *mapping, repeat: folio = filemap_get_folio(mapping, index); if (IS_ERR(folio)) { - folio = filemap_alloc_folio(gfp, 0); + folio = filemap_alloc_folio(gfp, + mapping_min_folio_order(mapping)); if (!folio) return ERR_PTR(-ENOMEM); + index = mapping_align_index(mapping, index); err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { folio_put(folio); From 26cfdb395eefdb2d34e51184d8466ee04a1618d5 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Thu, 22 Aug 2024 15:50:11 +0200 Subject: [PATCH 03/22] readahead: allocate folios with mapping_min_order in readahead page_cache_ra_unbounded() was allocating single pages (0 order folios) if there was no folio found in an index. Allocate mapping_min_order folios as we need to guarantee the minimum order if it is set. page_cache_ra_order() tries to allocate folio to the page cache with a higher order if the index aligns with that order. Modify it so that the order does not go below the mapping_min_order requirement of the page cache. This function will do the right thing even if the new_order passed is less than the mapping_min_order. When adding new folios to the page cache we must also ensure the index used is aligned to the mapping_min_order as the page cache requires the index to be aligned to the order of the folio. readahead_expand() is called from readahead aops to extend the range of the readahead so this function can assume ractl->_index to be aligned with min_order. Signed-off-by: Pankaj Raghav Co-developed-by: Hannes Reinecke Signed-off-by: Hannes Reinecke Link: https://lore.kernel.org/r/20240822135018.1931258-4-kernel@pankajraghav.com Tested-by: David Howells Acked-by: Darrick J. Wong Reviewed-by: Darrick J. Wong Reviewed-by: Daniel Gomez Reviewed-by: Dave Chinner Reviewed-by: Hannes Reinecke Signed-off-by: Christian Brauner --- mm/readahead.c | 79 ++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 61 insertions(+), 18 deletions(-) diff --git a/mm/readahead.c b/mm/readahead.c index 3e5239e9e177..2078c42777a6 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -206,9 +206,10 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; - unsigned long index = readahead_index(ractl); + unsigned long ra_folio_index, index = readahead_index(ractl); gfp_t gfp_mask = readahead_gfp_mask(mapping); - unsigned long i; + unsigned long mark, i = 0; + unsigned int min_nrpages = mapping_min_folio_nrpages(mapping); /* * Partway through the readahead operation, we will have added @@ -223,10 +224,24 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned int nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); + index = mapping_align_index(mapping, index); + + /* + * As iterator `i` is aligned to min_nrpages, round_up the + * difference between nr_to_read and lookahead_size to mark the + * index that only has lookahead or "async_region" to set the + * readahead flag. + */ + ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size, + min_nrpages); + mark = ra_folio_index - index; + nr_to_read += readahead_index(ractl) - index; + ractl->_index = index; + /* * Preallocate as many pages as we will need. */ - for (i = 0; i < nr_to_read; i++) { + while (i < nr_to_read) { struct folio *folio = xa_load(&mapping->i_pages, index + i); int ret; @@ -240,12 +255,13 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, * not worth getting one just for that. */ read_pages(ractl); - ractl->_index++; - i = ractl->_index + ractl->_nr_pages - index - 1; + ractl->_index += min_nrpages; + i = ractl->_index + ractl->_nr_pages - index; continue; } - folio = filemap_alloc_folio(gfp_mask, 0); + folio = filemap_alloc_folio(gfp_mask, + mapping_min_folio_order(mapping)); if (!folio) break; @@ -255,14 +271,15 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, if (ret == -ENOMEM) break; read_pages(ractl); - ractl->_index++; - i = ractl->_index + ractl->_nr_pages - index - 1; + ractl->_index += min_nrpages; + i = ractl->_index + ractl->_nr_pages - index; continue; } - if (i == nr_to_read - lookahead_size) + if (i == mark) folio_set_readahead(folio); ractl->_workingset |= folio_test_workingset(folio); - ractl->_nr_pages++; + ractl->_nr_pages += min_nrpages; + i += min_nrpages; } /* @@ -438,13 +455,19 @@ void page_cache_ra_order(struct readahead_control *ractl, struct address_space *mapping = ractl->mapping; pgoff_t start = readahead_index(ractl); pgoff_t index = start; + unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); + unsigned int min_ra_size = max(4, mapping_min_folio_nrpages(mapping)); - if (!mapping_large_folio_support(mapping) || ra->size < 4) + /* + * Fallback when size < min_nrpages as each folio should be + * at least min_nrpages anyway. + */ + if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size) goto fallback; limit = min(limit, index + ra->size - 1); @@ -454,10 +477,19 @@ void page_cache_ra_order(struct readahead_control *ractl, new_order = min(mapping_max_folio_order(mapping), new_order); new_order = min_t(unsigned int, new_order, ilog2(ra->size)); + new_order = max(new_order, min_order); /* See comment in page_cache_ra_unbounded() */ nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); + /* + * If the new_order is greater than min_order and index is + * already aligned to new_order, then this will be noop as index + * aligned to new_order should also be aligned to min_order. + */ + ractl->_index = mapping_align_index(mapping, index); + index = readahead_index(ractl); + while (index <= limit) { unsigned int order = new_order; @@ -465,7 +497,7 @@ void page_cache_ra_order(struct readahead_control *ractl, if (index & ((1UL << order) - 1)) order = __ffs(index); /* Don't allocate pages past EOF */ - while (index + (1UL << order) - 1 > limit) + while (order > min_order && index + (1UL << order) - 1 > limit) order--; err = ra_alloc_folio(ractl, index, mark, order, gfp); if (err) @@ -703,8 +735,15 @@ void readahead_expand(struct readahead_control *ractl, struct file_ra_state *ra = ractl->ra; pgoff_t new_index, new_nr_pages; gfp_t gfp_mask = readahead_gfp_mask(mapping); + unsigned long min_nrpages = mapping_min_folio_nrpages(mapping); + unsigned int min_order = mapping_min_folio_order(mapping); new_index = new_start / PAGE_SIZE; + /* + * Readahead code should have aligned the ractl->_index to + * min_nrpages before calling readahead aops. + */ + VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages)); /* Expand the leading edge downwards */ while (ractl->_index > new_index) { @@ -714,9 +753,11 @@ void readahead_expand(struct readahead_control *ractl, if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ - folio = filemap_alloc_folio(gfp_mask, 0); + folio = filemap_alloc_folio(gfp_mask, min_order); if (!folio) return; + + index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; @@ -726,7 +767,7 @@ void readahead_expand(struct readahead_control *ractl, ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } - ractl->_nr_pages++; + ractl->_nr_pages += min_nrpages; ractl->_index = folio->index; } @@ -741,9 +782,11 @@ void readahead_expand(struct readahead_control *ractl, if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ - folio = filemap_alloc_folio(gfp_mask, 0); + folio = filemap_alloc_folio(gfp_mask, min_order); if (!folio) return; + + index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; @@ -753,10 +796,10 @@ void readahead_expand(struct readahead_control *ractl, ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } - ractl->_nr_pages++; + ractl->_nr_pages += min_nrpages; if (ra) { - ra->size++; - ra->async_size++; + ra->size += min_nrpages; + ra->async_size += min_nrpages; } } } From e220917fa50774fedb27c075df2261fd664e8ca3 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 22 Aug 2024 15:50:12 +0200 Subject: [PATCH 04/22] mm: split a folio in minimum folio order chunks split_folio() and split_folio_to_list() assume order 0, to support minorder for non-anonymous folios, we must expand these to check the folio mapping order and use that. Set new_order to be at least minimum folio order if it is set in split_huge_page_to_list() so that we can maintain minimum folio order requirement in the page cache. Update the debugfs write files used for testing to ensure the order is respected as well. We simply enforce the min order when a file mapping is used. Signed-off-by: Luis Chamberlain Signed-off-by: Pankaj Raghav Link: https://lore.kernel.org/r/20240902124931.506061-2-kernel@pankajraghav.com # folded fix Link: https://lore.kernel.org/r/20240822135018.1931258-5-kernel@pankajraghav.com Tested-by: David Howells Reviewed-by: Hannes Reinecke Reviewed-by: Zi Yan Signed-off-by: Christian Brauner --- include/linux/huge_mm.h | 28 +++++++++++++++--- mm/huge_memory.c | 65 ++++++++++++++++++++++++++++++++++++++--- 2 files changed, 85 insertions(+), 8 deletions(-) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index e25d9ebfdf89..7a570e0437c9 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -96,6 +96,8 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr; #define thp_vma_allowable_order(vma, vm_flags, tva_flags, order) \ (!!thp_vma_allowable_orders(vma, vm_flags, tva_flags, BIT(order))) +#define split_folio(f) split_folio_to_list(f, NULL) + #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES #define HPAGE_PMD_SHIFT PMD_SHIFT #define HPAGE_PUD_SHIFT PUD_SHIFT @@ -317,9 +319,24 @@ unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long add bool can_split_folio(struct folio *folio, int *pextra_pins); int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order); +int min_order_for_split(struct folio *folio); +int split_folio_to_list(struct folio *folio, struct list_head *list); static inline int split_huge_page(struct page *page) { - return split_huge_page_to_list_to_order(page, NULL, 0); + struct folio *folio = page_folio(page); + int ret = min_order_for_split(folio); + + if (ret < 0) + return ret; + + /* + * split_huge_page() locks the page before splitting and + * expects the same page that has been split to be locked when + * returned. split_folio(page_folio(page)) cannot be used here + * because it converts the page to folio and passes the head + * page to be split. + */ + return split_huge_page_to_list_to_order(page, NULL, ret); } void deferred_split_folio(struct folio *folio); @@ -484,6 +501,12 @@ static inline int split_huge_page(struct page *page) { return 0; } + +static inline int split_folio_to_list(struct folio *folio, struct list_head *list) +{ + return 0; +} + static inline void deferred_split_folio(struct folio *folio) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) @@ -598,7 +621,4 @@ static inline int split_folio_to_order(struct folio *folio, int new_order) return split_folio_to_list_to_order(folio, NULL, new_order); } -#define split_folio_to_list(f, l) split_folio_to_list_to_order(f, l, 0) -#define split_folio(f) split_folio_to_order(f, 0) - #endif /* _LINUX_HUGE_MM_H */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f4be468e06a4..9931ff1d9a9d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3082,6 +3082,9 @@ bool can_split_folio(struct folio *folio, int *pextra_pins) * released, or if some unexpected race happened (e.g., anon VMA disappeared, * truncation). * + * Callers should ensure that the order respects the address space mapping + * min-order if one is set for non-anonymous folios. + * * Returns -EINVAL when trying to split to an order that is incompatible * with the folio. Splitting to order 0 is compatible with all folios. */ @@ -3163,6 +3166,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, mapping = NULL; anon_vma_lock_write(anon_vma); } else { + unsigned int min_order; gfp_t gfp; mapping = folio->mapping; @@ -3173,6 +3177,14 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, goto out; } + min_order = mapping_min_folio_order(folio->mapping); + if (new_order < min_order) { + VM_WARN_ONCE(1, "Cannot split mapped folio below min-order: %u", + min_order); + ret = -EINVAL; + goto out; + } + gfp = current_gfp_context(mapping_gfp_mask(mapping) & GFP_RECLAIM_MASK); @@ -3285,6 +3297,30 @@ out: return ret; } +int min_order_for_split(struct folio *folio) +{ + if (folio_test_anon(folio)) + return 0; + + if (!folio->mapping) { + if (folio_test_pmd_mappable(folio)) + count_vm_event(THP_SPLIT_PAGE_FAILED); + return -EBUSY; + } + + return mapping_min_folio_order(folio->mapping); +} + +int split_folio_to_list(struct folio *folio, struct list_head *list) +{ + int ret = min_order_for_split(folio); + + if (ret < 0) + return ret; + + return split_huge_page_to_list_to_order(&folio->page, list, ret); +} + void __folio_undo_large_rmappable(struct folio *folio) { struct deferred_split *ds_queue; @@ -3515,6 +3551,8 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, struct vm_area_struct *vma = vma_lookup(mm, addr); struct page *page; struct folio *folio; + struct address_space *mapping; + unsigned int target_order = new_order; if (!vma) break; @@ -3535,7 +3573,13 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, if (!is_transparent_hugepage(folio)) goto next; - if (new_order >= folio_order(folio)) + if (!folio_test_anon(folio)) { + mapping = folio->mapping; + target_order = max(new_order, + mapping_min_folio_order(mapping)); + } + + if (target_order >= folio_order(folio)) goto next; total++; @@ -3551,9 +3595,14 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, if (!folio_trylock(folio)) goto next; - if (!split_folio_to_order(folio, new_order)) + if (!folio_test_anon(folio) && folio->mapping != mapping) + goto unlock; + + if (!split_folio_to_order(folio, target_order)) split++; +unlock: + folio_unlock(folio); next: folio_put(folio); @@ -3578,6 +3627,8 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, pgoff_t index; int nr_pages = 1; unsigned long total = 0, split = 0; + unsigned int min_order; + unsigned int target_order; file = getname_kernel(file_path); if (IS_ERR(file)) @@ -3591,6 +3642,8 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, file_path, off_start, off_end); mapping = candidate->f_mapping; + min_order = mapping_min_folio_order(mapping); + target_order = max(new_order, min_order); for (index = off_start; index < off_end; index += nr_pages) { struct folio *folio = filemap_get_folio(mapping, index); @@ -3605,15 +3658,19 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, total++; nr_pages = folio_nr_pages(folio); - if (new_order >= folio_order(folio)) + if (target_order >= folio_order(folio)) goto next; if (!folio_trylock(folio)) goto next; - if (!split_folio_to_order(folio, new_order)) + if (folio->mapping != mapping) + goto unlock; + + if (!split_folio_to_order(folio, target_order)) split++; +unlock: folio_unlock(folio); next: folio_put(folio); From 743a2753a02e805347969f6f89f38b736850d808 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Thu, 22 Aug 2024 15:50:13 +0200 Subject: [PATCH 05/22] filemap: cap PTE range to be created to allowed zero fill in folio_map_range() Usually the page cache does not extend beyond the size of the inode, therefore, no PTEs are created for folios that extend beyond the size. But with LBS support, we might extend page cache beyond the size of the inode as we need to guarantee folios of minimum order. While doing a read, do_fault_around() can create PTEs for pages that lie beyond the EOF leading to incorrect error return when accessing a page beyond the mapped file. Cap the PTE range to be created for the page cache up to the end of file(EOF) in filemap_map_pages() so that return error codes are consistent with POSIX[1] for LBS configurations. generic/749 has been created to trigger this edge case. This also fixes generic/749 for tmpfs with huge=always on systems with 4k base page size. [1](from mmap(2)) SIGBUS Attempted access to a page of the buffer that lies beyond the end of the mapped file. For an explanation of the treatment of the bytes in the page that corresponds to the end of a mapped file that is not a multiple of the page size, see NOTES. Signed-off-by: Luis Chamberlain Signed-off-by: Pankaj Raghav Link: https://lore.kernel.org/r/20240822135018.1931258-6-kernel@pankajraghav.com Tested-by: David Howells Acked-by: Darrick J. Wong Reviewed-by: Hannes Reinecke Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Darrick J. Wong Reviewed-by: Daniel Gomez Reviewed-by: Dave Chinner Signed-off-by: Christian Brauner --- mm/filemap.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/mm/filemap.c b/mm/filemap.c index d27e9ac54309..d32210927453 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3608,7 +3608,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, struct vm_area_struct *vma = vmf->vma; struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; - pgoff_t last_pgoff = start_pgoff; + pgoff_t file_end, last_pgoff = start_pgoff; unsigned long addr; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct folio *folio; @@ -3634,6 +3634,10 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, goto out; } + file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; + if (end_pgoff > file_end) + end_pgoff = file_end; + folio_type = mm_counter_file(folio); do { unsigned long end; From 10553a91652d995274da63fc317470f703765081 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Thu, 22 Aug 2024 15:50:14 +0200 Subject: [PATCH 06/22] iomap: fix iomap_dio_zero() for fs bs > system page size iomap_dio_zero() will pad a fs block with zeroes if the direct IO size < fs block size. iomap_dio_zero() has an implicit assumption that fs block size < page_size. This is true for most filesystems at the moment. If the block size > page size, this will send the contents of the page next to zero page(as len > PAGE_SIZE) to the underlying block device, causing FS corruption. iomap is a generic infrastructure and it should not make any assumptions about the fs block size and the page size of the system. Signed-off-by: Pankaj Raghav Link: https://lore.kernel.org/r/20240822135018.1931258-7-kernel@pankajraghav.com Reviewed-by: Hannes Reinecke Reviewed-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Daniel Gomez Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 4 ++-- fs/iomap/direct-io.c | 45 ++++++++++++++++++++++++++++++++++++------ 2 files changed, 41 insertions(+), 8 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index f420c53d86ac..d745f718bcde 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -2007,10 +2007,10 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc, } EXPORT_SYMBOL_GPL(iomap_writepages); -static int __init iomap_init(void) +static int __init iomap_buffered_init(void) { return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE), offsetof(struct iomap_ioend, io_bio), BIOSET_NEED_BVECS); } -fs_initcall(iomap_init); +fs_initcall(iomap_buffered_init); diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index f3b43d223a46..c02b266bba52 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include "trace.h" @@ -27,6 +28,13 @@ #define IOMAP_DIO_WRITE (1U << 30) #define IOMAP_DIO_DIRTY (1U << 31) +/* + * Used for sub block zeroing in iomap_dio_zero() + */ +#define IOMAP_ZERO_PAGE_SIZE (SZ_64K) +#define IOMAP_ZERO_PAGE_ORDER (get_order(IOMAP_ZERO_PAGE_SIZE)) +static struct page *zero_page; + struct iomap_dio { struct kiocb *iocb; const struct iomap_dio_ops *dops; @@ -232,13 +240,20 @@ release_bio: } EXPORT_SYMBOL_GPL(iomap_dio_bio_end_io); -static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio, +static int iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio, loff_t pos, unsigned len) { struct inode *inode = file_inode(dio->iocb->ki_filp); - struct page *page = ZERO_PAGE(0); struct bio *bio; + if (!len) + return 0; + /* + * Max block size supported is 64k + */ + if (WARN_ON_ONCE(len > IOMAP_ZERO_PAGE_SIZE)) + return -EINVAL; + bio = iomap_dio_alloc_bio(iter, dio, 1, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE); fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits, GFP_KERNEL); @@ -246,8 +261,9 @@ static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio, bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; - __bio_add_page(bio, page, len, 0); + __bio_add_page(bio, zero_page, len, 0); iomap_dio_submit_bio(iter, dio, bio, pos); + return 0; } /* @@ -356,8 +372,10 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter, if (need_zeroout) { /* zero out from the start of the block to the write offset */ pad = pos & (fs_block_size - 1); - if (pad) - iomap_dio_zero(iter, dio, pos - pad, pad); + + ret = iomap_dio_zero(iter, dio, pos - pad, pad); + if (ret) + goto out; } /* @@ -431,7 +449,8 @@ zero_tail: /* zero out from the end of the write to the end of the block */ pad = pos & (fs_block_size - 1); if (pad) - iomap_dio_zero(iter, dio, pos, fs_block_size - pad); + ret = iomap_dio_zero(iter, dio, pos, + fs_block_size - pad); } out: /* Undo iter limitation to current extent */ @@ -753,3 +772,17 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, return iomap_dio_complete(dio); } EXPORT_SYMBOL_GPL(iomap_dio_rw); + +static int __init iomap_dio_init(void) +{ + zero_page = alloc_pages(GFP_KERNEL | __GFP_ZERO, + IOMAP_ZERO_PAGE_ORDER); + + if (!zero_page) + return -ENOMEM; + + set_memory_ro((unsigned long)page_address(zero_page), + 1U << IOMAP_ZERO_PAGE_ORDER); + return 0; +} +fs_initcall(iomap_dio_init); From de631e1a8b71017b8a12b57d07db82e4052555af Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 22 Aug 2024 15:50:15 +0200 Subject: [PATCH 07/22] xfs: use kvmalloc for xattr buffers Pankaj Raghav reported that when filesystem block size is larger than page size, the xattr code can use kmalloc() for high order allocations. This triggers a useless warning in the allocator as it is a __GFP_NOFAIL allocation here: static inline struct page *rmqueue(struct zone *preferred_zone, struct zone *zone, unsigned int order, gfp_t gfp_flags, unsigned int alloc_flags, int migratetype) { struct page *page; /* * We most definitely don't want callers attempting to * allocate greater than order-1 page units with __GFP_NOFAIL. */ >>>> WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); ... Fix this by changing all these call sites to use kvmalloc(), which will strip the NOFAIL from the kmalloc attempt and if that fails will do a __GFP_NOFAIL vmalloc(). This is not an issue that productions systems will see as filesystems with block size > page size cannot be mounted by the kernel; Pankaj is developing this functionality right now. Reported-by: Pankaj Raghav Fixes: f078d4ea8276 ("xfs: convert kmem_alloc() to kmalloc()") Signed-off-by: Dave Chinner Link: https://lore.kernel.org/r/20240822135018.1931258-8-kernel@pankajraghav.com Reviewed-by: Darrick J. Wong Reviewed-by: Pankaj Raghav Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Acked-by: Darrick J. Wong Reviewed-by: Daniel Gomez Reviewed-by: Dave Chinner Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Christian Brauner --- fs/xfs/libxfs/xfs_attr_leaf.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index b9e98950eb3d..09f4cb061a6e 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -1138,10 +1138,7 @@ xfs_attr3_leaf_to_shortform( trace_xfs_attr_leaf_to_sf(args); - tmpbuffer = kmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL); - if (!tmpbuffer) - return -ENOMEM; - + tmpbuffer = kvmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL); memcpy(tmpbuffer, bp->b_addr, args->geo->blksize); leaf = (xfs_attr_leafblock_t *)tmpbuffer; @@ -1205,7 +1202,7 @@ xfs_attr3_leaf_to_shortform( error = 0; out: - kfree(tmpbuffer); + kvfree(tmpbuffer); return error; } @@ -1613,7 +1610,7 @@ xfs_attr3_leaf_compact( trace_xfs_attr_leaf_compact(args); - tmpbuffer = kmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL); + tmpbuffer = kvmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL); memcpy(tmpbuffer, bp->b_addr, args->geo->blksize); memset(bp->b_addr, 0, args->geo->blksize); leaf_src = (xfs_attr_leafblock_t *)tmpbuffer; @@ -1651,7 +1648,7 @@ xfs_attr3_leaf_compact( */ xfs_trans_log_buf(trans, bp, 0, args->geo->blksize - 1); - kfree(tmpbuffer); + kvfree(tmpbuffer); } /* @@ -2330,7 +2327,7 @@ xfs_attr3_leaf_unbalance( struct xfs_attr_leafblock *tmp_leaf; struct xfs_attr3_icleaf_hdr tmphdr; - tmp_leaf = kzalloc(state->args->geo->blksize, + tmp_leaf = kvzalloc(state->args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL); /* @@ -2371,7 +2368,7 @@ xfs_attr3_leaf_unbalance( } memcpy(save_leaf, tmp_leaf, state->args->geo->blksize); savehdr = tmphdr; /* struct copy */ - kfree(tmp_leaf); + kvfree(tmp_leaf); } xfs_attr3_leaf_hdr_to_disk(state->args->geo, save_leaf, &savehdr); From 79012cfa00b50ca80fb9f399f3c54b2185d728be Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Thu, 22 Aug 2024 15:50:16 +0200 Subject: [PATCH 08/22] xfs: expose block size in stat For block size larger than page size, the unit of efficient IO is the block size, not the page size. Leaving stat() to report PAGE_SIZE as the block size causes test programs like fsx to issue illegal ranges for operations that require block size alignment (e.g. fallocate() insert range). Hence update the preferred IO size to reflect the block size in this case. This change is based on a patch originally from Dave Chinner.[1] [1] https://lwn.net/ml/linux-fsdevel/20181107063127.3902-16-david@fromorbit.com/ Signed-off-by: Pankaj Raghav Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20240822135018.1931258-9-kernel@pankajraghav.com Acked-by: Darrick J. Wong Reviewed-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Hannes Reinecke Reviewed-by: Daniel Gomez Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Christian Brauner --- fs/xfs/xfs_iops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 1cdc8034f54d..6483b4c4cf35 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -567,7 +567,7 @@ xfs_stat_blksize( return 1U << mp->m_allocsize_log; } - return PAGE_SIZE; + return max_t(uint32_t, PAGE_SIZE, mp->m_sb.sb_blocksize); } STATIC int From cebf9dacd5c3cec2813215a081509647f777ecc3 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Thu, 22 Aug 2024 15:50:17 +0200 Subject: [PATCH 09/22] xfs: make the calculation generic in xfs_sb_validate_fsb_count() Instead of assuming that PAGE_SHIFT is always higher than the blocklog, make the calculation generic so that page cache count can be calculated correctly for LBS. Signed-off-by: Pankaj Raghav Link: https://lore.kernel.org/r/20240822135018.1931258-10-kernel@pankajraghav.com Acked-by: Darrick J. Wong Reviewed-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Daniel Gomez Reviewed-by: Hannes Reinecke Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Christian Brauner --- fs/xfs/xfs_mount.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 09eef1721ef4..3949f720b535 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -132,11 +132,16 @@ xfs_sb_validate_fsb_count( xfs_sb_t *sbp, uint64_t nblocks) { + uint64_t max_bytes; + ASSERT(PAGE_SHIFT >= sbp->sb_blocklog); ASSERT(sbp->sb_blocklog >= BBSHIFT); + if (check_shl_overflow(nblocks, sbp->sb_blocklog, &max_bytes)) + return -EFBIG; + /* Limited by ULONG_MAX of page cache index */ - if (nblocks >> (PAGE_SHIFT - sbp->sb_blocklog) > ULONG_MAX) + if (max_bytes >> PAGE_SHIFT > ULONG_MAX) return -EFBIG; return 0; } From 7df7c204c678e24cd32d33360538670b7b90e330 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Thu, 22 Aug 2024 15:50:18 +0200 Subject: [PATCH 10/22] xfs: enable block size larger than page size support Page cache now has the ability to have a minimum order when allocating a folio which is a prerequisite to add support for block size > page size. Signed-off-by: Pankaj Raghav Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20240827-xfs-fix-wformat-bs-gt-ps-v1-1-aec6717609e0@kernel.org # fix folded Link: https://lore.kernel.org/r/20240822135018.1931258-11-kernel@pankajraghav.com Reviewed-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Christian Brauner --- fs/xfs/libxfs/xfs_ialloc.c | 5 +++++ fs/xfs/libxfs/xfs_shared.h | 3 +++ fs/xfs/xfs_icache.c | 6 ++++-- fs/xfs/xfs_mount.c | 1 - fs/xfs/xfs_super.c | 28 ++++++++++++++++++++-------- include/linux/pagemap.h | 13 +++++++++++++ 6 files changed, 45 insertions(+), 11 deletions(-) diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 0af5b7a33d05..1921b689888b 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -3033,6 +3033,11 @@ xfs_ialloc_setup_geometry( igeo->ialloc_align = mp->m_dalign; else igeo->ialloc_align = 0; + + if (mp->m_sb.sb_blocksize > PAGE_SIZE) + igeo->min_folio_order = mp->m_sb.sb_blocklog - PAGE_SHIFT; + else + igeo->min_folio_order = 0; } /* Compute the location of the root directory inode that is laid out by mkfs. */ diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index 2f7413afbf46..33b84a3a83ff 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -224,6 +224,9 @@ struct xfs_ino_geometry { /* precomputed value for di_flags2 */ uint64_t new_diflags2; + /* minimum folio order of a page cache allocation */ + unsigned int min_folio_order; + }; #endif /* __XFS_SHARED_H__ */ diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index cf629302d48e..0fcf235e5023 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -88,7 +88,8 @@ xfs_inode_alloc( /* VFS doesn't initialise i_mode! */ VFS_I(ip)->i_mode = 0; - mapping_set_large_folios(VFS_I(ip)->i_mapping); + mapping_set_folio_min_order(VFS_I(ip)->i_mapping, + M_IGEO(mp)->min_folio_order); XFS_STATS_INC(mp, vn_active); ASSERT(atomic_read(&ip->i_pincount) == 0); @@ -325,7 +326,8 @@ xfs_reinit_inode( inode->i_uid = uid; inode->i_gid = gid; inode->i_state = state; - mapping_set_large_folios(inode->i_mapping); + mapping_set_folio_min_order(inode->i_mapping, + M_IGEO(mp)->min_folio_order); return error; } diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 3949f720b535..c6933440f806 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -134,7 +134,6 @@ xfs_sb_validate_fsb_count( { uint64_t max_bytes; - ASSERT(PAGE_SHIFT >= sbp->sb_blocklog); ASSERT(sbp->sb_blocklog >= BBSHIFT); if (check_shl_overflow(nblocks, sbp->sb_blocklog, &max_bytes)) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 27e9f749c4c7..e8cc7900911e 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1638,16 +1638,28 @@ xfs_fs_fill_super( goto out_free_sb; } - /* - * Until this is fixed only page-sized or smaller data blocks work. - */ if (mp->m_sb.sb_blocksize > PAGE_SIZE) { - xfs_warn(mp, - "File system with blocksize %d bytes. " - "Only pagesize (%ld) or less will currently work.", + size_t max_folio_size = mapping_max_folio_size_supported(); + + if (!xfs_has_crc(mp)) { + xfs_warn(mp, +"V4 Filesystem with blocksize %d bytes. Only pagesize (%ld) or less is supported.", mp->m_sb.sb_blocksize, PAGE_SIZE); - error = -ENOSYS; - goto out_free_sb; + error = -ENOSYS; + goto out_free_sb; + } + + if (mp->m_sb.sb_blocksize > max_folio_size) { + xfs_warn(mp, +"block size (%u bytes) not supported; Only block size (%zu) or less is supported", + mp->m_sb.sb_blocksize, max_folio_size); + error = -ENOSYS; + goto out_free_sb; + } + + xfs_warn(mp, +"EXPERIMENTAL: V5 Filesystem with Large Block Size (%d bytes) enabled.", + mp->m_sb.sb_blocksize); } /* Ensure this filesystem fits in the page cache limits */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 4cc170949e9c..55b254d951da 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -374,6 +374,19 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1) #define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER) +/* + * mapping_max_folio_size_supported() - Check the max folio size supported + * + * The filesystem should call this function at mount time if there is a + * requirement on the folio mapping size in the page cache. + */ +static inline size_t mapping_max_folio_size_supported(void) +{ + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER); + return PAGE_SIZE; +} + /* * mapping_set_folio_order_range() - Set the orders supported by a file. * @mapping: The address space of the file. From d1dd75dcda646bed5b2add8790ae69c202f9f0b1 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Mon, 26 Aug 2024 14:26:32 -0700 Subject: [PATCH 11/22] iomap: remove set_memor_ro() on zero page Stephen reported a boot failure on ppc power8 system where set_memor_ro() on the new zero page failed [0]. Christophe Leroy further clarifies we can't use this on on linear memory on ppc, and so instead of special casing this just for PowerPC [2] remove the call as suggested by Darrick. [0] https://lore.kernel.org/all/20240826175931.1989f99e@canb.auug.org.au/T/#u [1] https://lore.kernel.org/all/b0fe75b4-c1bb-47f7-a7c3-2534b31c1780@csgroup.eu/ [2] https://lore.kernel.org/all/ZszrJkFOpiy5rCma@bombadil.infradead.org/ Reported-by: Stephen Rothwell Suggested-by: Darrick J. Wong Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20240826212632.2098685-1-mcgrof@kernel.org Tested-by: Stephen Rothwell Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- fs/iomap/direct-io.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index c02b266bba52..f637aa0706a3 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include "trace.h" @@ -781,8 +780,6 @@ static int __init iomap_dio_init(void) if (!zero_page) return -ENOMEM; - set_memory_ro((unsigned long)page_address(zero_page), - 1U << IOMAP_ZERO_PAGE_ORDER); return 0; } fs_initcall(iomap_dio_init); From 31754ea6cbbc08d5bbe1fa290320c3048d8d98a3 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 27 Aug 2024 06:51:36 -0400 Subject: [PATCH 12/22] iomap: add a private argument for iomap_file_buffered_write In order to switch fuse over to using iomap for buffered writes we need to be able to have the struct file for the original write, in case we have to read in the page to make it uptodate. Handle this by using the existing private field in the iomap_iter, and add the argument to iomap_file_buffered_write. This will allow us to pass the file in through the iomap buffered write path, and is flexible for any other file systems needs. Signed-off-by: Josef Bacik Link: https://lore.kernel.org/r/7f55c7c32275004ba00cddf862d970e6e633f750.1724755651.git.josef@toxicpanda.com Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- block/fops.c | 2 +- fs/gfs2/file.c | 2 +- fs/iomap/buffered-io.c | 3 ++- fs/xfs/xfs_file.c | 2 +- fs/zonefs/file.c | 2 +- include/linux/iomap.h | 2 +- 6 files changed, 7 insertions(+), 6 deletions(-) diff --git a/block/fops.c b/block/fops.c index 9825c1713a49..d16a6dddb12a 100644 --- a/block/fops.c +++ b/block/fops.c @@ -665,7 +665,7 @@ blkdev_direct_write(struct kiocb *iocb, struct iov_iter *from) static ssize_t blkdev_buffered_write(struct kiocb *iocb, struct iov_iter *from) { - return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops); + return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops, NULL); } /* diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 08982937b5df..f7dd64856c9b 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1057,7 +1057,7 @@ retry: } pagefault_disable(); - ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops); + ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops, NULL); pagefault_enable(); if (ret > 0) written += ret; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index d745f718bcde..e79d11701553 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1022,13 +1022,14 @@ retry: ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i, - const struct iomap_ops *ops) + const struct iomap_ops *ops, void *private) { struct iomap_iter iter = { .inode = iocb->ki_filp->f_mapping->host, .pos = iocb->ki_pos, .len = iov_iter_count(i), .flags = IOMAP_WRITE, + .private = private, }; ssize_t ret; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 4cdc54dc9686..e9c693bb20bc 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -760,7 +760,7 @@ write_retry: trace_xfs_file_buffered_write(iocb, from); ret = iomap_file_buffered_write(iocb, from, - &xfs_buffered_write_iomap_ops); + &xfs_buffered_write_iomap_ops, NULL); /* * If we hit a space limit, try to free up some lingering preallocated diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index 3b103715acc9..35166c92420c 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -563,7 +563,7 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb, if (ret <= 0) goto inode_unlock; - ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops); + ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops, NULL); if (ret == -EIO) zonefs_io_error(inode, true); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 6fc1c858013d..f792b37f7627 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -257,7 +257,7 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) } ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, - const struct iomap_ops *ops); + const struct iomap_ops *ops, void *private); int iomap_file_buffered_write_punch_delalloc(struct inode *inode, struct iomap *iomap, loff_t pos, loff_t length, ssize_t written, int (*punch)(struct inode *inode, loff_t pos, loff_t length)); From c5c810b94cfd818fc2f58c96feee58a9e5ead96d Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 30 Aug 2024 10:56:33 -0400 Subject: [PATCH 13/22] iomap: fix handling of dirty folios over unwritten extents The iomap zero range implementation doesn't properly handle dirty pagecache over unwritten mappings. It skips such mappings as if they were pre-zeroed. If some part of an unwritten mapping is dirty in pagecache from a previous write, the data in cache should be zeroed as well. Instead, the data is left in cache and creates a stale data exposure problem if writeback occurs sometime after the zero range. Most callers are unaffected by this because the higher level filesystem contexts that call zero range typically perform a filemap flush of the target range for other reasons. A couple contexts that don't otherwise need to flush are write file size extension and truncate in XFS. The former path is currently susceptible to the stale data exposure problem and the latter performs a flush specifically to work around it. This is clearly inconsistent and incomplete. As a first step toward correcting behavior, lift the XFS workaround to iomap_zero_range() and unconditionally flush the range before the zero range operation proceeds. While this appears to be a bit of a big hammer, most all users already do this from calling context save for the couple of exceptions noted above. Future patches will optimize or elide this flush while maintaining functional correctness. Fixes: ae259a9c8593 ("fs: introduce iomap infrastructure") Signed-off-by: Brian Foster Link: https://lore.kernel.org/r/20240830145634.138439-2-bfoster@redhat.com Reviewed-by: Darrick J. Wong Reviewed-by: Josef Bacik Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 10 ++++++++++ fs/xfs/xfs_iops.c | 10 ---------- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index e79d11701553..a5aab73bc89b 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1452,6 +1452,16 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, }; int ret; + /* + * Zero range wants to skip pre-zeroed (i.e. unwritten) mappings, but + * pagecache must be flushed to ensure stale data from previous + * buffered writes is not exposed. + */ + ret = filemap_write_and_wait_range(inode->i_mapping, + pos, pos + len - 1); + if (ret) + return ret; + while ((ret = iomap_iter(&iter, ops)) > 0) iter.processed = iomap_zero_iter(&iter, did_zero); return ret; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 6483b4c4cf35..ee79cf161312 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -870,16 +870,6 @@ xfs_setattr_size( error = xfs_zero_range(ip, oldsize, newsize - oldsize, &did_zeroing); } else { - /* - * iomap won't detect a dirty page over an unwritten block (or a - * cow block over a hole) and subsequently skips zeroing the - * newly post-EOF portion of the page. Flush the new EOF to - * convert the block before the pagecache truncate. - */ - error = filemap_write_and_wait_range(inode->i_mapping, newsize, - newsize); - if (error) - return error; error = xfs_truncate_page(ip, newsize, &did_zeroing); } From 7d9b474ee4cc375393d13e69d60a30f9b7b46a3a Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 30 Aug 2024 10:56:34 -0400 Subject: [PATCH 14/22] iomap: make zero range flush conditional on unwritten mappings iomap_zero_range() flushes pagecache to mitigate consistency problems with dirty pagecache and unwritten mappings. The flush is unconditional over the entire range because checking pagecache state after mapping lookup is racy with writeback and reclaim. There are ways around this using iomap's mapping revalidation mechanism, but this is not supported by all iomap based filesystems and so is not a generic solution. There is another way around this limitation that is good enough to filter the flush for most cases in practice. If we check for dirty pagecache over the target range (instead of unconditionally flush), we can keep track of whether the range was dirty before lookup and defer the flush until/unless we see a combination of dirty cache backed by an unwritten mapping. We don't necessarily know whether the dirty cache was backed by the unwritten maping or some other (written) part of the range, but the impliciation of a false positive here is a spurious flush and thus relatively harmless. Note that we also flush for hole mappings because iomap_zero_range() is used for partial folio zeroing in some cases. For example, if a folio straddles EOF on a sub-page FSB size fs, the post-eof portion is hole-backed and dirtied/written via mapped write, and then i_size increases before writeback can occur (which otherwise zeroes the post-eof portion of the EOF folio), then the folio becomes inconsistent with disk until reclaimed. A flush in this case executes partial zeroing from writeback, and iomap knows that there is otherwise no I/O to submit for hole backed mappings. Signed-off-by: Brian Foster Link: https://lore.kernel.org/r/20240830145634.138439-3-bfoster@redhat.com Reviewed-by: Darrick J. Wong Reviewed-by: Josef Bacik Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 63 ++++++++++++++++++++++++++++++++++++------ 1 file changed, 54 insertions(+), 9 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index a5aab73bc89b..de47698a029a 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1394,16 +1394,53 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, } EXPORT_SYMBOL_GPL(iomap_file_unshare); -static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) +/* + * Flush the remaining range of the iter and mark the current mapping stale. + * This is used when zero range sees an unwritten mapping that may have had + * dirty pagecache over it. + */ +static inline int iomap_zero_iter_flush_and_stale(struct iomap_iter *i) +{ + struct address_space *mapping = i->inode->i_mapping; + loff_t end = i->pos + i->len - 1; + + i->iomap.flags |= IOMAP_F_STALE; + return filemap_write_and_wait_range(mapping, i->pos, end); +} + +static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero, + bool *range_dirty) { const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); loff_t written = 0; - /* already zeroed? we're done. */ - if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) + /* + * We must zero subranges of unwritten mappings that might be dirty in + * pagecache from previous writes. We only know whether the entire range + * was clean or not, however, and dirty folios may have been written + * back or reclaimed at any point after mapping lookup. + * + * The easiest way to deal with this is to flush pagecache to trigger + * any pending unwritten conversions and then grab the updated extents + * from the fs. The flush may change the current mapping, so mark it + * stale for the iterator to remap it for the next pass to handle + * properly. + * + * Note that holes are treated the same as unwritten because zero range + * is (ab)used for partial folio zeroing in some cases. Hole backed + * post-eof ranges can be dirtied via mapped write and the flush + * triggers writeback time post-eof zeroing. + */ + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) { + if (*range_dirty) { + *range_dirty = false; + return iomap_zero_iter_flush_and_stale(iter); + } + /* range is clean and already zeroed, nothing to do */ return length; + } do { struct folio *folio; @@ -1451,19 +1488,27 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, .flags = IOMAP_ZERO, }; int ret; + bool range_dirty; /* * Zero range wants to skip pre-zeroed (i.e. unwritten) mappings, but * pagecache must be flushed to ensure stale data from previous - * buffered writes is not exposed. + * buffered writes is not exposed. A flush is only required for certain + * types of mappings, but checking pagecache after mapping lookup is + * racy with writeback and reclaim. + * + * Therefore, check the entire range first and pass along whether any + * part of it is dirty. If so and an underlying mapping warrants it, + * flush the cache at that point. This trades off the occasional false + * positive (and spurious flush, if the dirty data and mapping don't + * happen to overlap) for simplicity in handling a relatively uncommon + * situation. */ - ret = filemap_write_and_wait_range(inode->i_mapping, - pos, pos + len - 1); - if (ret) - return ret; + range_dirty = filemap_range_needs_writeback(inode->i_mapping, + pos, pos + len - 1); while ((ret = iomap_iter(&iter, ops)) > 0) - iter.processed = iomap_zero_iter(&iter, did_zero); + iter.processed = iomap_zero_iter(&iter, did_zero, &range_dirty); return ret; } EXPORT_SYMBOL_GPL(iomap_zero_range); From 6f634eb080161baa4811a39f5ec07923ede092bc Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Tue, 27 Aug 2024 10:42:07 +0200 Subject: [PATCH 15/22] filemap: fix htmldoc warning for mapping_align_index() Stephen reported that there is a kernel build warning due to a missing description of a parameter in mapping_align_index(). Add the missing index parameter in the comment description. Signed-off-by: Pankaj Raghav Link: https://lore.kernel.org/r/20240827084206.106347-2-kernel@pankajraghav.com Fixes: ab95d23bab22 ("filemap: allocate mapping_min_order folios in the page cache") Reported-by: Stephen Rothwell Signed-off-by: Christian Brauner --- include/linux/pagemap.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 55b254d951da..6c0dde447c98 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -470,6 +470,7 @@ mapping_min_folio_nrpages(struct address_space *mapping) /** * mapping_align_index() - Align index for this mapping. * @mapping: The address_space. + * @index: The page index. * * The index of a folio must be naturally aligned. If you are adding a * new folio to the page cache and need to know what index to give it, From b1daf3f8475fa2a4ffc1668043de738241f95d1d Mon Sep 17 00:00:00 2001 From: Dennis Lam Date: Sun, 8 Sep 2024 13:28:42 -0400 Subject: [PATCH 16/22] docs:filesystems: fix spelling and grammar mistakes in iomap design page Signed-off-by: Dennis Lam Link: https://lore.kernel.org/r/20240908172841.9616-2-dennis.lamerice@gmail.com Signed-off-by: Christian Brauner --- Documentation/filesystems/iomap/design.rst | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/filesystems/iomap/design.rst b/Documentation/filesystems/iomap/design.rst index f8ee3427bc1a..e2d34085dd0e 100644 --- a/Documentation/filesystems/iomap/design.rst +++ b/Documentation/filesystems/iomap/design.rst @@ -142,9 +142,9 @@ Definitions * **pure overwrite**: A write operation that does not require any metadata or zeroing operations to perform during either submission or completion. - This implies that the fileystem must have already allocated space + This implies that the filesystem must have already allocated space on disk as ``IOMAP_MAPPED`` and the filesystem must not place any - constaints on IO alignment or size. + constraints on IO alignment or size. The only constraints on I/O alignment are device level (minimum I/O size and alignment, typically sector size). @@ -426,7 +426,7 @@ iomap is concerned: The exact locking requirements are specific to the filesystem; for certain operations, some of these locks can be elided. -All further mention of locking are *recommendations*, not mandates. +All further mentions of locking are *recommendations*, not mandates. Each filesystem author must figure out the locking for themself. Bugs and Limitations From 7a9d43eace888a0ee6095035997bb138425844d3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Sep 2024 07:39:03 +0300 Subject: [PATCH 17/22] iomap: handle a post-direct I/O invalidate race in iomap_write_delalloc_release When direct I/O completions invalidates the page cache it holds neither the i_rwsem nor the invalidate_lock so it can be racing with iomap_write_delalloc_release. If the search for the end of the region that contains data returns the start offset we hit such a race and just need to look for the end of the newly created hole instead. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240910043949.3481298-2-hch@lst.de Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index de47698a029a..db7a3ff92e61 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1242,7 +1242,15 @@ static int iomap_write_delalloc_release(struct inode *inode, error = data_end; goto out_unlock; } - WARN_ON_ONCE(data_end <= start_byte); + + /* + * If we race with post-direct I/O invalidation of the page cache, + * there might be no data left at start_byte. + */ + if (data_end == start_byte) + continue; + + WARN_ON_ONCE(data_end < start_byte); WARN_ON_ONCE(data_end > scan_end_byte); error = iomap_write_delalloc_scan(inode, &punch_start_byte, From b53fdb215d13f8e9c29541434bf2d14dac8bcbdc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Sep 2024 07:39:04 +0300 Subject: [PATCH 18/22] iomap: improve shared block detection in iomap_unshare_iter Currently iomap_unshare_iter relies on the IOMAP_F_SHARED flag to detect blocks to unshare. This is reasonable, but IOMAP_F_SHARED is also useful for the file system to do internal book keeping for out of place writes. XFS used to that, until it got removed in commit 72a048c1056a ("xfs: only set IOMAP_F_SHARED when providing a srcmap to a write") because unshare for incorrectly unshare such blocks. Add an extra safeguard by checking the explicitly provided srcmap instead of the fallback to the iomap for valid data, as that catches the case where we'd just copy from the same place we'd write to easily, allowing to reinstate setting IOMAP_F_SHARED for all XFS writes that go to the COW fork. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240910043949.3481298-3-hch@lst.de Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index db7a3ff92e61..a00b213967e5 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1338,16 +1338,25 @@ EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc); static loff_t iomap_unshare_iter(struct iomap_iter *iter) { struct iomap *iomap = &iter->iomap; - const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); loff_t written = 0; - /* don't bother with blocks that are not shared to start with */ + /* Don't bother with blocks that are not shared to start with. */ if (!(iomap->flags & IOMAP_F_SHARED)) return length; - /* don't bother with holes or unwritten extents */ - if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) + + /* + * Don't bother with holes or unwritten extents. + * + * Note that we use srcmap directly instead of iomap_iter_srcmap as + * unsharing requires providing a separate source map, and the presence + * of one is a good indicator that unsharing is needed, unlike + * IOMAP_F_SHARED which can be set for any data that goes into the COW + * fork for XFS. + */ + if (iter->srcmap.type == IOMAP_HOLE || + iter->srcmap.type == IOMAP_UNWRITTEN) return length; do { From 11596dc3dfae572cc267dda2dc4dab9ae34668f3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Sep 2024 07:39:05 +0300 Subject: [PATCH 19/22] iomap: pass flags to iomap_file_buffered_write_punch_delalloc To fix short write error handling, We'll need to figure out what operation iomap_file_buffered_write_punch_delalloc is called for. Pass the flags argument on to it, and reorder the argument list to match that of ->iomap_end so that the compiler only has to add the new punch argument to the end of it instead of reshuffling the registers. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240910043949.3481298-4-hch@lst.de Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 11 +++++------ fs/xfs/xfs_iomap.c | 5 +++-- include/linux/iomap.h | 10 ++++++---- 3 files changed, 14 insertions(+), 12 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index a00b213967e5..363c8e6f7952 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -23,7 +23,6 @@ #define IOEND_BATCH_SIZE 4096 -typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length); /* * Structure allocated for each folio to track per-block uptodate, dirty state * and I/O completions. @@ -1200,8 +1199,8 @@ static int iomap_write_delalloc_scan(struct inode *inode, * require sprinkling this code with magic "+ 1" and "- 1" arithmetic and expose * the code to subtle off-by-one bugs.... */ -static int iomap_write_delalloc_release(struct inode *inode, - loff_t start_byte, loff_t end_byte, iomap_punch_t punch) +static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, + loff_t end_byte, unsigned flags, iomap_punch_t punch) { loff_t punch_start_byte = start_byte; loff_t scan_end_byte = min(i_size_read(inode), end_byte); @@ -1301,8 +1300,8 @@ out_unlock: * internal filesystem allocation lock */ int iomap_file_buffered_write_punch_delalloc(struct inode *inode, - struct iomap *iomap, loff_t pos, loff_t length, - ssize_t written, iomap_punch_t punch) + loff_t pos, loff_t length, ssize_t written, unsigned flags, + struct iomap *iomap, iomap_punch_t punch) { loff_t start_byte; loff_t end_byte; @@ -1330,7 +1329,7 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode, if (start_byte >= end_byte) return 0; - return iomap_write_delalloc_release(inode, start_byte, end_byte, + return iomap_write_delalloc_release(inode, start_byte, end_byte, flags, punch); } EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 72c981e3dc92..47b5c8358825 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1231,8 +1231,9 @@ xfs_buffered_write_iomap_end( struct xfs_mount *mp = XFS_M(inode->i_sb); int error; - error = iomap_file_buffered_write_punch_delalloc(inode, iomap, offset, - length, written, &xfs_buffered_write_delalloc_punch); + error = iomap_file_buffered_write_punch_delalloc(inode, offset, length, + written, flags, iomap, + &xfs_buffered_write_delalloc_punch); if (error && !xfs_is_shutdown(mp)) { xfs_alert(mp, "%s: unable to clean up ino 0x%llx", __func__, XFS_I(inode)->i_ino); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index f792b37f7627..52626906ff35 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -258,10 +258,6 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops, void *private); -int iomap_file_buffered_write_punch_delalloc(struct inode *inode, - struct iomap *iomap, loff_t pos, loff_t length, ssize_t written, - int (*punch)(struct inode *inode, loff_t pos, loff_t length)); - 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); @@ -277,6 +273,12 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); + +typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length); +int iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos, + loff_t length, ssize_t written, unsigned flag, + struct iomap *iomap, iomap_punch_t punch); + int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, const struct iomap_ops *ops); loff_t iomap_seek_hole(struct inode *inode, loff_t offset, From 492f53758fad4fde3e9a98696780f8b53f87cdae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Sep 2024 07:39:06 +0300 Subject: [PATCH 20/22] iomap: pass the iomap to the punch callback XFS will need to look at the flags in the iomap structure, so pass it down all the way to the callback. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240910043949.3481298-5-hch@lst.de Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 25 +++++++++++++------------ fs/xfs/xfs_iomap.c | 3 ++- include/linux/iomap.h | 3 ++- 3 files changed, 17 insertions(+), 14 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 363c8e6f7952..87c996657a52 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1048,7 +1048,7 @@ EXPORT_SYMBOL_GPL(iomap_file_buffered_write); static int iomap_write_delalloc_ifs_punch(struct inode *inode, struct folio *folio, loff_t start_byte, loff_t end_byte, - iomap_punch_t punch) + struct iomap *iomap, iomap_punch_t punch) { unsigned int first_blk, last_blk, i; loff_t last_byte; @@ -1073,7 +1073,7 @@ static int iomap_write_delalloc_ifs_punch(struct inode *inode, for (i = first_blk; i <= last_blk; i++) { if (!ifs_block_is_dirty(folio, ifs, i)) { ret = punch(inode, folio_pos(folio) + (i << blkbits), - 1 << blkbits); + 1 << blkbits, iomap); if (ret) return ret; } @@ -1085,7 +1085,7 @@ static int iomap_write_delalloc_ifs_punch(struct inode *inode, static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, - iomap_punch_t punch) + struct iomap *iomap, iomap_punch_t punch) { int ret = 0; @@ -1095,14 +1095,14 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, /* if dirty, punch up to offset */ if (start_byte > *punch_start_byte) { ret = punch(inode, *punch_start_byte, - start_byte - *punch_start_byte); + start_byte - *punch_start_byte, iomap); if (ret) return ret; } /* Punch non-dirty blocks within folio */ - ret = iomap_write_delalloc_ifs_punch(inode, folio, start_byte, - end_byte, punch); + ret = iomap_write_delalloc_ifs_punch(inode, folio, start_byte, end_byte, + iomap, punch); if (ret) return ret; @@ -1135,7 +1135,7 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, */ static int iomap_write_delalloc_scan(struct inode *inode, loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, - iomap_punch_t punch) + struct iomap *iomap, iomap_punch_t punch) { while (start_byte < end_byte) { struct folio *folio; @@ -1151,7 +1151,7 @@ static int iomap_write_delalloc_scan(struct inode *inode, } ret = iomap_write_delalloc_punch(inode, folio, punch_start_byte, - start_byte, end_byte, punch); + start_byte, end_byte, iomap, punch); if (ret) { folio_unlock(folio); folio_put(folio); @@ -1200,7 +1200,8 @@ static int iomap_write_delalloc_scan(struct inode *inode, * the code to subtle off-by-one bugs.... */ static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, - loff_t end_byte, unsigned flags, iomap_punch_t punch) + loff_t end_byte, unsigned flags, struct iomap *iomap, + iomap_punch_t punch) { loff_t punch_start_byte = start_byte; loff_t scan_end_byte = min(i_size_read(inode), end_byte); @@ -1253,7 +1254,7 @@ static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, WARN_ON_ONCE(data_end > scan_end_byte); error = iomap_write_delalloc_scan(inode, &punch_start_byte, - start_byte, data_end, punch); + start_byte, data_end, iomap, punch); if (error) goto out_unlock; @@ -1263,7 +1264,7 @@ static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, if (punch_start_byte < end_byte) error = punch(inode, punch_start_byte, - end_byte - punch_start_byte); + end_byte - punch_start_byte, iomap); out_unlock: filemap_invalidate_unlock(inode->i_mapping); return error; @@ -1330,7 +1331,7 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode, return 0; return iomap_write_delalloc_release(inode, start_byte, end_byte, flags, - punch); + iomap, punch); } EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 47b5c8358825..695e5bee776f 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1212,7 +1212,8 @@ static int xfs_buffered_write_delalloc_punch( struct inode *inode, loff_t offset, - loff_t length) + loff_t length, + struct iomap *iomap) { xfs_bmap_punch_delalloc_range(XFS_I(inode), offset, offset + length); return 0; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 52626906ff35..ec2eab94f00a 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -274,7 +274,8 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); -typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length); +typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, + struct iomap *iomap); int iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos, loff_t length, ssize_t written, unsigned flag, struct iomap *iomap, iomap_punch_t punch); From 4bceb9ba05aca23652567fb5f899cc7fcb12c8d0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Sep 2024 07:39:07 +0300 Subject: [PATCH 21/22] iomap: remove the iomap_file_buffered_write_punch_delalloc return value iomap_file_buffered_write_punch_delalloc can only return errors if either the ->punch callback returned an error, or if someone changed the API of mapping_seek_hole_data to return a negative error code that is not -ENXIO. As the only instance of ->punch never returns an error, an such an error would be fatal anyway remove the entire error propagation and don't return an error code from iomap_file_buffered_write_punch_delalloc. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240910043949.3481298-6-hch@lst.de Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 82 +++++++++++++++--------------------------- fs/xfs/xfs_iomap.c | 17 ++------- include/linux/iomap.h | 4 +-- 3 files changed, 33 insertions(+), 70 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 87c996657a52..b02545f8036e 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1046,7 +1046,7 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i, } EXPORT_SYMBOL_GPL(iomap_file_buffered_write); -static int iomap_write_delalloc_ifs_punch(struct inode *inode, +static void iomap_write_delalloc_ifs_punch(struct inode *inode, struct folio *folio, loff_t start_byte, loff_t end_byte, struct iomap *iomap, iomap_punch_t punch) { @@ -1054,7 +1054,6 @@ static int iomap_write_delalloc_ifs_punch(struct inode *inode, loff_t last_byte; u8 blkbits = inode->i_blkbits; struct iomap_folio_state *ifs; - int ret = 0; /* * When we have per-block dirty tracking, there can be @@ -1064,47 +1063,35 @@ static int iomap_write_delalloc_ifs_punch(struct inode *inode, */ ifs = folio->private; if (!ifs) - return ret; + return; last_byte = min_t(loff_t, end_byte - 1, folio_pos(folio) + folio_size(folio) - 1); first_blk = offset_in_folio(folio, start_byte) >> blkbits; last_blk = offset_in_folio(folio, last_byte) >> blkbits; for (i = first_blk; i <= last_blk; i++) { - if (!ifs_block_is_dirty(folio, ifs, i)) { - ret = punch(inode, folio_pos(folio) + (i << blkbits), + if (!ifs_block_is_dirty(folio, ifs, i)) + punch(inode, folio_pos(folio) + (i << blkbits), 1 << blkbits, iomap); - if (ret) - return ret; - } } - - return ret; } - -static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, +static void iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, struct iomap *iomap, iomap_punch_t punch) { - int ret = 0; - if (!folio_test_dirty(folio)) - return ret; + return; /* if dirty, punch up to offset */ if (start_byte > *punch_start_byte) { - ret = punch(inode, *punch_start_byte, - start_byte - *punch_start_byte, iomap); - if (ret) - return ret; + punch(inode, *punch_start_byte, start_byte - *punch_start_byte, + iomap); } /* Punch non-dirty blocks within folio */ - ret = iomap_write_delalloc_ifs_punch(inode, folio, start_byte, end_byte, + iomap_write_delalloc_ifs_punch(inode, folio, start_byte, end_byte, iomap, punch); - if (ret) - return ret; /* * Make sure the next punch start is correctly bound to @@ -1112,8 +1099,6 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, */ *punch_start_byte = min_t(loff_t, end_byte, folio_pos(folio) + folio_size(folio)); - - return ret; } /* @@ -1133,13 +1118,12 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, * This function uses [start_byte, end_byte) intervals (i.e. open ended) to * simplify range iterations. */ -static int iomap_write_delalloc_scan(struct inode *inode, +static void iomap_write_delalloc_scan(struct inode *inode, loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, struct iomap *iomap, iomap_punch_t punch) { while (start_byte < end_byte) { struct folio *folio; - int ret; /* grab locked page */ folio = filemap_lock_folio(inode->i_mapping, @@ -1150,20 +1134,14 @@ static int iomap_write_delalloc_scan(struct inode *inode, continue; } - ret = iomap_write_delalloc_punch(inode, folio, punch_start_byte, + iomap_write_delalloc_punch(inode, folio, punch_start_byte, start_byte, end_byte, iomap, punch); - if (ret) { - folio_unlock(folio); - folio_put(folio); - return ret; - } /* move offset to start of next folio in range */ start_byte = folio_next_index(folio) << PAGE_SHIFT; folio_unlock(folio); folio_put(folio); } - return 0; } /* @@ -1199,13 +1177,12 @@ static int iomap_write_delalloc_scan(struct inode *inode, * require sprinkling this code with magic "+ 1" and "- 1" arithmetic and expose * the code to subtle off-by-one bugs.... */ -static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, +static void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, loff_t end_byte, unsigned flags, struct iomap *iomap, iomap_punch_t punch) { loff_t punch_start_byte = start_byte; loff_t scan_end_byte = min(i_size_read(inode), end_byte); - int error = 0; /* * Lock the mapping to avoid races with page faults re-instantiating @@ -1222,13 +1199,15 @@ static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, /* * If there is no more data to scan, all that is left is to * punch out the remaining range. + * + * Note that mapping_seek_hole_data is only supposed to return + * either an offset or -ENXIO, so WARN on any other error as + * that would be an API change without updating the callers. */ if (start_byte == -ENXIO || start_byte == scan_end_byte) break; - if (start_byte < 0) { - error = start_byte; + if (WARN_ON_ONCE(start_byte < 0)) goto out_unlock; - } WARN_ON_ONCE(start_byte < punch_start_byte); WARN_ON_ONCE(start_byte > scan_end_byte); @@ -1238,10 +1217,8 @@ static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, */ data_end = mapping_seek_hole_data(inode->i_mapping, start_byte, scan_end_byte, SEEK_HOLE); - if (data_end < 0) { - error = data_end; + if (WARN_ON_ONCE(data_end < 0)) goto out_unlock; - } /* * If we race with post-direct I/O invalidation of the page cache, @@ -1253,21 +1230,18 @@ static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, WARN_ON_ONCE(data_end < start_byte); WARN_ON_ONCE(data_end > scan_end_byte); - error = iomap_write_delalloc_scan(inode, &punch_start_byte, - start_byte, data_end, iomap, punch); - if (error) - goto out_unlock; + iomap_write_delalloc_scan(inode, &punch_start_byte, start_byte, + data_end, iomap, punch); /* The next data search starts at the end of this one. */ start_byte = data_end; } if (punch_start_byte < end_byte) - error = punch(inode, punch_start_byte, - end_byte - punch_start_byte, iomap); + punch(inode, punch_start_byte, end_byte - punch_start_byte, + iomap); out_unlock: filemap_invalidate_unlock(inode->i_mapping); - return error; } /* @@ -1300,7 +1274,7 @@ out_unlock: * ->punch * internal filesystem allocation lock */ -int iomap_file_buffered_write_punch_delalloc(struct inode *inode, +void iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos, loff_t length, ssize_t written, unsigned flags, struct iomap *iomap, iomap_punch_t punch) { @@ -1309,11 +1283,11 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode, unsigned int blocksize = i_blocksize(inode); if (iomap->type != IOMAP_DELALLOC) - return 0; + return; /* If we didn't reserve the blocks, we're not allowed to punch them. */ if (!(iomap->flags & IOMAP_F_NEW)) - return 0; + return; /* * start_byte refers to the first unused block after a short write. If @@ -1328,10 +1302,10 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode, /* Nothing to do if we've written the entire delalloc extent */ if (start_byte >= end_byte) - return 0; + return; - return iomap_write_delalloc_release(inode, start_byte, end_byte, flags, - iomap, punch); + iomap_write_delalloc_release(inode, start_byte, end_byte, flags, iomap, + punch); } EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 695e5bee776f..1e11f48814c0 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1208,7 +1208,7 @@ out_unlock: return error; } -static int +static void xfs_buffered_write_delalloc_punch( struct inode *inode, loff_t offset, @@ -1216,7 +1216,6 @@ xfs_buffered_write_delalloc_punch( struct iomap *iomap) { xfs_bmap_punch_delalloc_range(XFS_I(inode), offset, offset + length); - return 0; } static int @@ -1228,18 +1227,8 @@ xfs_buffered_write_iomap_end( unsigned flags, struct iomap *iomap) { - - struct xfs_mount *mp = XFS_M(inode->i_sb); - int error; - - error = iomap_file_buffered_write_punch_delalloc(inode, offset, length, - written, flags, iomap, - &xfs_buffered_write_delalloc_punch); - if (error && !xfs_is_shutdown(mp)) { - xfs_alert(mp, "%s: unable to clean up ino 0x%llx", - __func__, XFS_I(inode)->i_ino); - return error; - } + iomap_file_buffered_write_punch_delalloc(inode, offset, length, written, + flags, iomap, &xfs_buffered_write_delalloc_punch); return 0; } diff --git a/include/linux/iomap.h b/include/linux/iomap.h index ec2eab94f00a..4ad12a3c8bae 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -274,9 +274,9 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); -typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, +typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, struct iomap *iomap); -int iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos, +void iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos, loff_t length, ssize_t written, unsigned flag, struct iomap *iomap, iomap_punch_t punch); From 71fdfcdd0dc8344ce6a7887b4675c7700efeffa6 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Tue, 20 Aug 2024 18:13:29 +0200 Subject: [PATCH 22/22] Documentation: iomap: fix a typo Change voidw -> void. Signed-off-by: Pankaj Raghav Link: https://lore.kernel.org/r/20240820161329.1293718-1-kernel@pankajraghav.com Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- Documentation/filesystems/iomap/design.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/filesystems/iomap/design.rst b/Documentation/filesystems/iomap/design.rst index e2d34085dd0e..df18a757604a 100644 --- a/Documentation/filesystems/iomap/design.rst +++ b/Documentation/filesystems/iomap/design.rst @@ -165,7 +165,7 @@ structure below: u16 flags; struct block_device *bdev; struct dax_device *dax_dev; - voidw *inline_data; + void *inline_data; void *private; const struct iomap_folio_ops *folio_ops; u64 validity_cookie;