From f7f9a0c8736d418af8d981000ea68ea43b395da4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 15 Jul 2023 23:03:52 -0400 Subject: [PATCH 01/10] iov_iter: Map the page later in copy_page_from_iter_atomic() Remove a couple of calls to kunmap_atomic() in the rare error cases. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Kent Overstreet Reviewed-by: Darrick J. Wong --- lib/iov_iter.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/lib/iov_iter.c b/lib/iov_iter.c index e4dc809d1075..db58af778291 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -569,20 +569,20 @@ EXPORT_SYMBOL(iov_iter_zero); size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i) { - char *kaddr = kmap_atomic(page), *p = kaddr + offset; - if (!page_copy_sane(page, offset, bytes)) { - kunmap_atomic(kaddr); + char *p; + + if (!page_copy_sane(page, offset, bytes)) return 0; - } - if (WARN_ON_ONCE(!i->data_source)) { - kunmap_atomic(kaddr); + if (WARN_ON_ONCE(!i->data_source)) return 0; - } + + p = kmap_atomic(page) + offset; iterate_and_advance(i, bytes, base, len, off, copyin(p + off, base, len), memcpy_from_iter(i, p + off, base, len) ) - kunmap_atomic(kaddr); + kunmap_atomic(p); + return bytes; } EXPORT_SYMBOL(copy_page_from_iter_atomic); From 908a1ad89466c1febf20bfe0037b84fc66f8a3f8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 6 Jun 2023 16:43:32 -0400 Subject: [PATCH 02/10] iov_iter: Handle compound highmem pages in copy_page_from_iter_atomic() copy_page_from_iter_atomic() already handles !highmem compound pages correctly, but if we are passed a highmem compound page, each base page needs to be mapped & unmapped individually. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Kent Overstreet Reviewed-by: Darrick J. Wong Tested-by: Kent Overstreet --- lib/iov_iter.c | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) diff --git a/lib/iov_iter.c b/lib/iov_iter.c index db58af778291..eb3dffb24aae 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -566,24 +566,37 @@ size_t iov_iter_zero(size_t bytes, struct iov_iter *i) } EXPORT_SYMBOL(iov_iter_zero); -size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t bytes, - struct iov_iter *i) +size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, + size_t bytes, struct iov_iter *i) { - char *p; + size_t n, copied = 0; if (!page_copy_sane(page, offset, bytes)) return 0; if (WARN_ON_ONCE(!i->data_source)) return 0; - p = kmap_atomic(page) + offset; - iterate_and_advance(i, bytes, base, len, off, - copyin(p + off, base, len), - memcpy_from_iter(i, p + off, base, len) - ) - kunmap_atomic(p); + do { + char *p; - return bytes; + n = bytes - copied; + if (PageHighMem(page)) { + page += offset / PAGE_SIZE; + offset %= PAGE_SIZE; + n = min_t(size_t, n, PAGE_SIZE - offset); + } + + p = kmap_atomic(page) + offset; + iterate_and_advance(i, n, base, len, off, + copyin(p + off, base, len), + memcpy_from_iter(i, p + off, base, len) + ) + kunmap_atomic(p); + copied += n; + offset += n; + } while (PageHighMem(page) && copied != bytes && n > 0); + + return copied; } EXPORT_SYMBOL(copy_page_from_iter_atomic); From 1b0306981e0f1e5a9ad3d08b9c88bfe21b68e3b9 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 9 Jul 2023 18:17:33 -0400 Subject: [PATCH 03/10] iov_iter: Add copy_folio_from_iter_atomic() Add a folio wrapper around copy_page_from_iter_atomic(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Darrick J. Wong --- include/linux/uio.h | 9 ++++++++- lib/iov_iter.c | 2 +- 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/include/linux/uio.h b/include/linux/uio.h index ff81e5ccaef2..42bce38a8e87 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -163,7 +163,7 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) return ret; } -size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, +size_t copy_page_from_iter_atomic(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); void iov_iter_advance(struct iov_iter *i, size_t bytes); void iov_iter_revert(struct iov_iter *i, size_t bytes); @@ -184,6 +184,13 @@ static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, { return copy_page_to_iter(&folio->page, offset, bytes, i); } + +static inline size_t copy_folio_from_iter_atomic(struct folio *folio, + size_t offset, size_t bytes, struct iov_iter *i) +{ + return copy_page_from_iter_atomic(&folio->page, offset, bytes, i); +} + size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index eb3dffb24aae..424737045b97 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -566,7 +566,7 @@ size_t iov_iter_zero(size_t bytes, struct iov_iter *i) } EXPORT_SYMBOL(iov_iter_zero); -size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, +size_t copy_page_from_iter_atomic(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t n, copied = 0; From a221ab717c43147f728d93513923ba3528f861bf Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Jun 2023 18:09:11 -0400 Subject: [PATCH 04/10] iomap: Remove large folio handling in iomap_invalidate_folio() We do not need to release the iomap_page in iomap_invalidate_folio() to allow the folio to be split. The splitting code will call ->release_folio() if there is still per-fs private data attached to the folio. At that point, we will check if the folio is still dirty and decline to release the iomap_page. It is possible to trigger the warning in perfectly legitimate circumstances (eg if a disk read fails, we do a partial write to the folio, then we truncate the folio), which will cause those writes to be lost. Fixes: 60d8231089f0 ("iomap: Support large folios in invalidatepage") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- fs/iomap/buffered-io.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index aa8967cca1a3..7d2f70708f37 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -508,11 +508,6 @@ void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len) WARN_ON_ONCE(folio_test_writeback(folio)); folio_cancel_dirty(folio); iomap_page_release(folio); - } else if (folio_test_large(folio)) { - /* Must release the iop so the page can be split */ - WARN_ON_ONCE(!folio_test_uptodate(folio) && - folio_test_dirty(folio)); - iomap_page_release(folio); } } EXPORT_SYMBOL_GPL(iomap_invalidate_folio); From 32b29cc9db455f69ac792c637aea11493bfaf1bc Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Jun 2023 16:33:20 -0400 Subject: [PATCH 05/10] doc: Correct the description of ->release_folio The filesystem ->release_folio method is called under more circumstances now than when the documentation was written. The second sentence describing the interpretation of the return value is the wrong polarity (false indicates failure, not success). And the third sentence is also wrong (the kernel calls try_to_free_buffers() instead). So replace the entire paragraph with a detailed description of what the state of the folio may be, the meaning of the gfp parameter, why the method is being called and what the filesystem is expected to do. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- Documentation/filesystems/locking.rst | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index ed148919e11a..ca3d24becbf5 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -374,10 +374,17 @@ invalidate_lock before invalidating page cache in truncate / hole punch path (and thus calling into ->invalidate_folio) to block races between page cache invalidation and page cache filling functions (fault, read, ...). -->release_folio() is called when the kernel is about to try to drop the -buffers from the folio in preparation for freeing it. It returns false to -indicate that the buffers are (or may be) freeable. If ->release_folio is -NULL, the kernel assumes that the fs has no private interest in the buffers. +->release_folio() is called when the MM wants to make a change to the +folio that would invalidate the filesystem's private data. For example, +it may be about to be removed from the address_space or split. The folio +is locked and not under writeback. It may be dirty. The gfp parameter +is not usually used for allocation, but rather to indicate what the +filesystem may do to attempt to free the private data. The filesystem may +return false to indicate that the folio's private data cannot be freed. +If it returns true, it should have already removed the private data from +the folio. If a filesystem does not provide a ->release_folio method, +the pagecache will assume that private data is buffer_heads and call +try_to_free_buffers(). ->free_folio() is called when the kernel has dropped the folio from the page cache. From 7a8eb01b078f6280089347feee02aebda0024880 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Jun 2023 18:07:48 -0400 Subject: [PATCH 06/10] iomap: Remove unnecessary test from iomap_release_folio() The check for the folio being under writeback is unnecessary; the caller has checked this and the folio is locked, so the folio cannot be under writeback at this point. The comment is somewhat misleading in that it talks about one specific situation in which we can see a dirty folio. There are others, so change the comment to explain why we can't release the iomap_page. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 7d2f70708f37..cc640576f9f7 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -483,12 +483,11 @@ bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags) folio_size(folio)); /* - * mm accommodates an old ext3 case where clean folios might - * not have had the dirty bit cleared. Thus, it can send actual - * dirty folios to ->release_folio() via shrink_active_list(); - * skip those here. + * If the folio is dirty, we refuse to release our metadata because + * it may be partially dirty. Once we track per-block dirty state, + * we can release the metadata if every block is dirty. */ - if (folio_test_dirty(folio) || folio_test_writeback(folio)) + if (folio_test_dirty(folio)) return false; iomap_page_release(folio); return true; From ffc143db63eeea7c8a27deb3c56d090a220a1ace Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 26 May 2023 16:43:23 -0400 Subject: [PATCH 07/10] filemap: Add fgf_t typedef Similarly to gfp_t, define fgf_t as its own type to prevent various misuses and confusion. Leave the flags as FGP_* for now to reduce the size of this patch; they will be converted to FGF_* later. Move the documentation to the definition of the type insted of burying it in the __filemap_get_folio() documentation. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Kent Overstreet --- fs/btrfs/file.c | 6 +++--- fs/f2fs/compress.c | 2 +- fs/f2fs/f2fs.h | 2 +- fs/iomap/buffered-io.c | 2 +- include/linux/pagemap.h | 48 +++++++++++++++++++++++++++++++---------- mm/filemap.c | 19 ++-------------- mm/folio-compat.c | 2 +- 7 files changed, 46 insertions(+), 35 deletions(-) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index fd03e689a6be..3876fae90fc3 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -876,9 +876,9 @@ static int prepare_uptodate_page(struct inode *inode, return 0; } -static unsigned int get_prepare_fgp_flags(bool nowait) +static fgf_t get_prepare_fgp_flags(bool nowait) { - unsigned int fgp_flags = FGP_LOCK | FGP_ACCESSED | FGP_CREAT; + fgf_t fgp_flags = FGP_LOCK | FGP_ACCESSED | FGP_CREAT; if (nowait) fgp_flags |= FGP_NOWAIT; @@ -910,7 +910,7 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages, int i; unsigned long index = pos >> PAGE_SHIFT; gfp_t mask = get_prepare_gfp_flags(inode, nowait); - unsigned int fgp_flags = get_prepare_fgp_flags(nowait); + fgf_t fgp_flags = get_prepare_fgp_flags(nowait); int err = 0; int faili; diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 236d890f560b..0f7df9c11af3 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -1045,7 +1045,7 @@ static int prepare_compress_overwrite(struct compress_ctx *cc, struct address_space *mapping = cc->inode->i_mapping; struct page *page; sector_t last_block_in_bio; - unsigned fgp_flag = FGP_LOCK | FGP_WRITE | FGP_CREAT; + fgf_t fgp_flag = FGP_LOCK | FGP_WRITE | FGP_CREAT; pgoff_t start_idx = start_idx_of_cluster(cc); int i, ret; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index c7cb2177b252..c275ff2753c2 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2736,7 +2736,7 @@ static inline struct page *f2fs_grab_cache_page(struct address_space *mapping, static inline struct page *f2fs_pagecache_get_page( struct address_space *mapping, pgoff_t index, - int fgp_flags, gfp_t gfp_mask) + fgf_t fgp_flags, gfp_t gfp_mask) { if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) return NULL; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index cc640576f9f7..94a6ae05e03b 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -467,7 +467,7 @@ EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate); */ struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos) { - unsigned fgp = FGP_WRITEBEGIN | FGP_NOFS; + fgf_t fgp = FGP_WRITEBEGIN | FGP_NOFS; if (iter->flags & IOMAP_NOWAIT) fgp |= FGP_NOWAIT; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 716953ee1ebd..911201fc41fc 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -501,22 +501,48 @@ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); -#define FGP_ACCESSED 0x00000001 -#define FGP_LOCK 0x00000002 -#define FGP_CREAT 0x00000004 -#define FGP_WRITE 0x00000008 -#define FGP_NOFS 0x00000010 -#define FGP_NOWAIT 0x00000020 -#define FGP_FOR_MMAP 0x00000040 -#define FGP_STABLE 0x00000080 +/** + * typedef fgf_t - Flags for getting folios from the page cache. + * + * Most users of the page cache will not need to use these flags; + * there are convenience functions such as filemap_get_folio() and + * filemap_lock_folio(). For users which need more control over exactly + * what is done with the folios, these flags to __filemap_get_folio() + * are available. + * + * * %FGP_ACCESSED - The folio will be marked accessed. + * * %FGP_LOCK - The folio is returned locked. + * * %FGP_CREAT - If no folio is present then a new folio is allocated, + * added to the page cache and the VM's LRU list. The folio is + * returned locked. + * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the + * folio is already in cache. If the folio was allocated, unlock it + * before returning so the caller can do the same dance. + * * %FGP_WRITE - The folio will be written to by the caller. + * * %FGP_NOFS - __GFP_FS will get cleared in gfp. + * * %FGP_NOWAIT - Don't block on the folio lock. + * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) + * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin() + * implementation. + */ +typedef unsigned int __bitwise fgf_t; + +#define FGP_ACCESSED ((__force fgf_t)0x00000001) +#define FGP_LOCK ((__force fgf_t)0x00000002) +#define FGP_CREAT ((__force fgf_t)0x00000004) +#define FGP_WRITE ((__force fgf_t)0x00000008) +#define FGP_NOFS ((__force fgf_t)0x00000010) +#define FGP_NOWAIT ((__force fgf_t)0x00000020) +#define FGP_FOR_MMAP ((__force fgf_t)0x00000040) +#define FGP_STABLE ((__force fgf_t)0x00000080) #define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) void *filemap_get_entry(struct address_space *mapping, pgoff_t index); struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, - int fgp_flags, gfp_t gfp); + fgf_t fgp_flags, gfp_t gfp); struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, - int fgp_flags, gfp_t gfp); + fgf_t fgp_flags, gfp_t gfp); /** * filemap_get_folio - Find and get a folio. @@ -590,7 +616,7 @@ static inline struct page *find_get_page(struct address_space *mapping, } static inline struct page *find_get_page_flags(struct address_space *mapping, - pgoff_t offset, int fgp_flags) + pgoff_t offset, fgf_t fgp_flags) { return pagecache_get_page(mapping, offset, fgp_flags, 0); } diff --git a/mm/filemap.c b/mm/filemap.c index 9e44a49bbd74..8a669fecfd1c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1855,30 +1855,15 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index) * * Looks up the page cache entry at @mapping & @index. * - * @fgp_flags can be zero or more of these flags: - * - * * %FGP_ACCESSED - The folio will be marked accessed. - * * %FGP_LOCK - The folio is returned locked. - * * %FGP_CREAT - If no page is present then a new page is allocated using - * @gfp and added to the page cache and the VM's LRU list. - * The page is returned locked and with an increased refcount. - * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the - * page is already in cache. If the page was allocated, unlock it before - * returning so the caller can do the same dance. - * * %FGP_WRITE - The page will be written to by the caller. - * * %FGP_NOFS - __GFP_FS will get cleared in gfp. - * * %FGP_NOWAIT - Don't get blocked by page lock. - * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) - * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * - * If there is a page cache page, it is returned with an increased refcount. + * If this function returns a folio, it is returned with an increased refcount. * * Return: The found folio or an ERR_PTR() otherwise. */ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, - int fgp_flags, gfp_t gfp) + fgf_t fgp_flags, gfp_t gfp) { struct folio *folio; diff --git a/mm/folio-compat.c b/mm/folio-compat.c index c6f056c20503..10c3247542cb 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -92,7 +92,7 @@ EXPORT_SYMBOL(add_to_page_cache_lru); noinline struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, - int fgp_flags, gfp_t gfp) + fgf_t fgp_flags, gfp_t gfp) { struct folio *folio; From 4f66170119107f1452d2438ba4606e105e9e3afe Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 19 May 2023 16:10:37 -0400 Subject: [PATCH 08/10] filemap: Allow __filemap_get_folio to allocate large folios Allow callers of __filemap_get_folio() to specify a preferred folio order in the FGP flags. This is only honoured in the FGP_CREATE path; if there is already a folio in the page cache that covers the index, we will return it, no matter what its order is. No create-around is attempted; we will only create folios which start at the specified index. Unmodified callers will continue to allocate order 0 folios. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- include/linux/pagemap.h | 34 ++++++++++++++++++++++++++++++ mm/filemap.c | 46 +++++++++++++++++++++++++++++------------ mm/readahead.c | 13 ------------ 3 files changed, 67 insertions(+), 26 deletions(-) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 911201fc41fc..d87840acbfb2 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -470,6 +470,19 @@ static inline void *detach_page_private(struct page *page) return folio_detach_private(page_folio(page)); } +/* + * There are some parts of the kernel which assume that PMD entries + * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, + * limit the maximum allocation order to PMD size. I'm not aware of any + * assumptions about maximum order if THP are disabled, but 8 seems like + * a good order (that's 1MB if you're using 4kB pages) + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER +#else +#define MAX_PAGECACHE_ORDER 8 +#endif + #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order); #else @@ -535,9 +548,30 @@ typedef unsigned int __bitwise fgf_t; #define FGP_NOWAIT ((__force fgf_t)0x00000020) #define FGP_FOR_MMAP ((__force fgf_t)0x00000040) #define FGP_STABLE ((__force fgf_t)0x00000080) +#define FGF_GET_ORDER(fgf) (((__force unsigned)fgf) >> 26) /* top 6 bits */ #define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) +/** + * fgf_set_order - Encode a length in the fgf_t flags. + * @size: The suggested size of the folio to create. + * + * The caller of __filemap_get_folio() can use this to suggest a preferred + * size for the folio that is created. If there is already a folio at + * the index, it will be returned, no matter what its size. If a folio + * is freshly created, it may be of a different size than requested + * due to alignment constraints, memory pressure, or the presence of + * other folios at nearby indices. + */ +static inline fgf_t fgf_set_order(size_t size) +{ + unsigned int shift = ilog2(size); + + if (shift <= PAGE_SHIFT) + return 0; + return (__force fgf_t)((shift - PAGE_SHIFT) << 26); +} + void *filemap_get_entry(struct address_space *mapping, pgoff_t index); struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp); diff --git a/mm/filemap.c b/mm/filemap.c index 8a669fecfd1c..baafbf324c9f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1905,7 +1905,9 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, folio_wait_stable(folio); no_page: if (!folio && (fgp_flags & FGP_CREAT)) { + unsigned order = FGF_GET_ORDER(fgp_flags); int err; + if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) @@ -1914,26 +1916,44 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, gfp &= ~GFP_KERNEL; gfp |= GFP_NOWAIT | __GFP_NOWARN; } - - folio = filemap_alloc_folio(gfp, 0); - if (!folio) - return ERR_PTR(-ENOMEM); - if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; - /* Init accessed so avoid atomic mark_page_accessed later */ - if (fgp_flags & FGP_ACCESSED) - __folio_set_referenced(folio); + if (!mapping_large_folio_support(mapping)) + order = 0; + if (order > MAX_PAGECACHE_ORDER) + order = MAX_PAGECACHE_ORDER; + /* If we're not aligned, allocate a smaller folio */ + if (index & ((1UL << order) - 1)) + order = __ffs(index); - err = filemap_add_folio(mapping, folio, index, gfp); - if (unlikely(err)) { + do { + gfp_t alloc_gfp = gfp; + + err = -ENOMEM; + if (order == 1) + order = 0; + if (order > 0) + alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN; + folio = filemap_alloc_folio(alloc_gfp, order); + if (!folio) + continue; + + /* Init accessed so avoid atomic mark_page_accessed later */ + if (fgp_flags & FGP_ACCESSED) + __folio_set_referenced(folio); + + err = filemap_add_folio(mapping, folio, index, gfp); + if (!err) + break; folio_put(folio); folio = NULL; - if (err == -EEXIST) - goto repeat; - } + } while (order-- > 0); + if (err == -EEXIST) + goto repeat; + if (err) + return ERR_PTR(err); /* * filemap_add_folio locks the page, and for mmap * we expect an unlocked page. diff --git a/mm/readahead.c b/mm/readahead.c index a9c999aa19af..e815c114de21 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -461,19 +461,6 @@ static int try_context_readahead(struct address_space *mapping, return 1; } -/* - * There are some parts of the kernel which assume that PMD entries - * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, - * limit the maximum allocation order to PMD size. I'm not aware of any - * assumptions about maximum order if THP are disabled, but 8 seems like - * a good order (that's 1MB if you're using 4kB pages) - */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER -#else -#define MAX_PAGECACHE_ORDER 8 -#endif - static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, pgoff_t mark, unsigned int order, gfp_t gfp) { From d6bb59a9444d218dc60dee3b45fd93c0d4f5e123 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 19 May 2023 16:18:05 -0400 Subject: [PATCH 09/10] iomap: Create large folios in the buffered write path Use the size of the write as a hint for the size of the folio to create. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- fs/gfs2/bmap.c | 2 +- fs/iomap/buffered-io.c | 6 ++++-- include/linux/iomap.h | 2 +- 3 files changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 8d611fbcf0bd..521d1e00a0ff 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -971,7 +971,7 @@ gfs2_iomap_get_folio(struct iomap_iter *iter, loff_t pos, unsigned len) if (status) return ERR_PTR(status); - folio = iomap_get_folio(iter, pos); + folio = iomap_get_folio(iter, pos, len); if (IS_ERR(folio)) gfs2_trans_end(sdp); return folio; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 94a6ae05e03b..00e0e94c953e 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -461,16 +461,18 @@ EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate); * iomap_get_folio - get a folio reference for writing * @iter: iteration structure * @pos: start offset of write + * @len: Suggested size of folio to create. * * Returns a locked reference to the folio at @pos, or an error pointer if the * folio could not be obtained. */ -struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos) +struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len) { fgf_t fgp = FGP_WRITEBEGIN | FGP_NOFS; if (iter->flags & IOMAP_NOWAIT) fgp |= FGP_NOWAIT; + fgp |= fgf_set_order(len); return __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT, fgp, mapping_gfp_mask(iter->inode->i_mapping)); @@ -597,7 +599,7 @@ static struct folio *__iomap_get_folio(struct iomap_iter *iter, loff_t pos, if (folio_ops && folio_ops->get_folio) return folio_ops->get_folio(iter, pos, len); else - return iomap_get_folio(iter, pos); + return iomap_get_folio(iter, pos, len); } static void __iomap_put_folio(struct iomap_iter *iter, loff_t pos, size_t ret, diff --git a/include/linux/iomap.h b/include/linux/iomap.h index e2b836c2e119..80facb9c9e5b 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -261,7 +261,7 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode, 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); -struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos); +struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len); bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags); void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, From 5d8edfb900d55db7dbf2dbf325bfb9fdb863ec72 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 20 May 2023 12:13:20 -0400 Subject: [PATCH 10/10] iomap: Copy larger chunks from userspace If we have a large folio, we can copy in larger chunks than PAGE_SIZE. Start at the maximum page cache size and shrink by half every time we hit the "we are short on memory" problem. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 00e0e94c953e..608cd2e5a7c9 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -769,6 +769,7 @@ static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) { loff_t length = iomap_length(iter); + size_t chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; loff_t pos = iter->pos; ssize_t written = 0; long status = 0; @@ -777,15 +778,12 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) do { struct folio *folio; - struct page *page; - unsigned long offset; /* Offset into pagecache page */ - unsigned long bytes; /* Bytes to write to page */ + size_t offset; /* Offset into folio */ + size_t bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ - offset = offset_in_page(pos); - bytes = min_t(unsigned long, PAGE_SIZE - offset, - iov_iter_count(i)); -again: + offset = pos & (chunk - 1); + bytes = min(chunk - offset, iov_iter_count(i)); status = balance_dirty_pages_ratelimited_flags(mapping, bdp_flags); if (unlikely(status)) @@ -815,12 +813,14 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) if (iter->iomap.flags & IOMAP_F_STALE) break; - page = folio_file_page(folio, pos >> PAGE_SHIFT); + offset = offset_in_folio(folio, pos); + if (bytes > folio_size(folio) - offset) + bytes = folio_size(folio) - offset; + if (mapping_writably_mapped(mapping)) - flush_dcache_page(page); - - copied = copy_page_from_iter_atomic(page, offset, bytes, i); + flush_dcache_folio(folio); + copied = copy_folio_from_iter_atomic(folio, offset, bytes, i); status = iomap_write_end(iter, pos, bytes, copied, folio); if (unlikely(copied != status)) @@ -836,11 +836,13 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) */ if (copied) bytes = copied; - goto again; + if (chunk > PAGE_SIZE) + chunk /= 2; + } else { + pos += status; + written += status; + length -= status; } - pos += status; - written += status; - length -= status; } while (iov_iter_count(i) && length); if (status == -EAGAIN) {