diff options
Diffstat (limited to 'fs/iomap')
| -rw-r--r-- | fs/iomap/Makefile | 4 | ||||
| -rw-r--r-- | fs/iomap/buffered-io.c | 543 | ||||
| -rw-r--r-- | fs/iomap/direct-io.c | 1 |
3 files changed, 277 insertions, 271 deletions
diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile index 4143a3ff89db..fc070184b7fa 100644 --- a/fs/iomap/Makefile +++ b/fs/iomap/Makefile @@ -9,9 +9,9 @@ ccflags-y += -I $(srctree)/$(src) # needed for trace events obj-$(CONFIG_FS_IOMAP) += iomap.o iomap-y += trace.o \ - buffered-io.o \ + iter.o +iomap-$(CONFIG_BLOCK) += buffered-io.o \ direct-io.o \ fiemap.o \ - iter.o \ seek.o iomap-$(CONFIG_SWAP) += swapfile.o diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 71a36ae120ee..c938bbad075e 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -22,8 +22,8 @@ #include "../internal.h" /* - * Structure allocated for each page or THP when block size < page size - * to track sub-page uptodate status and I/O completions. + * Structure allocated for each folio when block size < folio size + * to track sub-folio uptodate status and I/O completions. */ struct iomap_page { atomic_t read_bytes_pending; @@ -32,27 +32,20 @@ struct iomap_page { unsigned long uptodate[]; }; -static inline struct iomap_page *to_iomap_page(struct page *page) +static inline struct iomap_page *to_iomap_page(struct folio *folio) { - /* - * per-block data is stored in the head page. Callers should - * not be dealing with tail pages, and if they are, they can - * call thp_head() first. - */ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - - if (page_has_private(page)) - return (struct iomap_page *)page_private(page); + if (folio_test_private(folio)) + return folio_get_private(folio); return NULL; } static struct bio_set iomap_ioend_bioset; static struct iomap_page * -iomap_page_create(struct inode *inode, struct page *page) +iomap_page_create(struct inode *inode, struct folio *folio) { - struct iomap_page *iop = to_iomap_page(page); - unsigned int nr_blocks = i_blocks_per_page(inode, page); + struct iomap_page *iop = to_iomap_page(folio); + unsigned int nr_blocks = i_blocks_per_folio(inode, folio); if (iop || nr_blocks <= 1) return iop; @@ -60,40 +53,40 @@ iomap_page_create(struct inode *inode, struct page *page) iop = kzalloc(struct_size(iop, uptodate, BITS_TO_LONGS(nr_blocks)), GFP_NOFS | __GFP_NOFAIL); spin_lock_init(&iop->uptodate_lock); - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) bitmap_fill(iop->uptodate, nr_blocks); - attach_page_private(page, iop); + folio_attach_private(folio, iop); return iop; } -static void -iomap_page_release(struct page *page) +static void iomap_page_release(struct folio *folio) { - struct iomap_page *iop = detach_page_private(page); - unsigned int nr_blocks = i_blocks_per_page(page->mapping->host, page); + struct iomap_page *iop = folio_detach_private(folio); + struct inode *inode = folio->mapping->host; + unsigned int nr_blocks = i_blocks_per_folio(inode, folio); if (!iop) return; WARN_ON_ONCE(atomic_read(&iop->read_bytes_pending)); WARN_ON_ONCE(atomic_read(&iop->write_bytes_pending)); WARN_ON_ONCE(bitmap_full(iop->uptodate, nr_blocks) != - PageUptodate(page)); + folio_test_uptodate(folio)); kfree(iop); } /* - * Calculate the range inside the page that we actually need to read. + * Calculate the range inside the folio that we actually need to read. */ -static void -iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop, - loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp) +static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, + loff_t *pos, loff_t length, size_t *offp, size_t *lenp) { + struct iomap_page *iop = to_iomap_page(folio); loff_t orig_pos = *pos; loff_t isize = i_size_read(inode); unsigned block_bits = inode->i_blkbits; unsigned block_size = (1 << block_bits); - unsigned poff = offset_in_page(*pos); - unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length); + size_t poff = offset_in_folio(folio, *pos); + size_t plen = min_t(loff_t, folio_size(folio) - poff, length); unsigned first = poff >> block_bits; unsigned last = (poff + plen - 1) >> block_bits; @@ -131,7 +124,7 @@ iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop, * page cache for blocks that are entirely outside of i_size. */ if (orig_pos <= isize && orig_pos + length > isize) { - unsigned end = offset_in_page(isize - 1) >> block_bits; + unsigned end = offset_in_folio(folio, isize - 1) >> block_bits; if (first <= end && last > end) plen -= (last - end) * block_size; @@ -141,66 +134,62 @@ iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop, *lenp = plen; } -static void -iomap_iop_set_range_uptodate(struct page *page, unsigned off, unsigned len) +static void iomap_iop_set_range_uptodate(struct folio *folio, + struct iomap_page *iop, size_t off, size_t len) { - struct iomap_page *iop = to_iomap_page(page); - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; unsigned first = off >> inode->i_blkbits; unsigned last = (off + len - 1) >> inode->i_blkbits; unsigned long flags; spin_lock_irqsave(&iop->uptodate_lock, flags); bitmap_set(iop->uptodate, first, last - first + 1); - if (bitmap_full(iop->uptodate, i_blocks_per_page(inode, page))) - SetPageUptodate(page); + if (bitmap_full(iop->uptodate, i_blocks_per_folio(inode, folio))) + folio_mark_uptodate(folio); spin_unlock_irqrestore(&iop->uptodate_lock, flags); } -static void -iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len) +static void iomap_set_range_uptodate(struct folio *folio, + struct iomap_page *iop, size_t off, size_t len) { - if (PageError(page)) + if (folio_test_error(folio)) return; - if (page_has_private(page)) - iomap_iop_set_range_uptodate(page, off, len); + if (iop) + iomap_iop_set_range_uptodate(folio, iop, off, len); else - SetPageUptodate(page); + folio_mark_uptodate(folio); } -static void -iomap_read_page_end_io(struct bio_vec *bvec, int error) +static void iomap_finish_folio_read(struct folio *folio, size_t offset, + size_t len, int error) { - struct page *page = bvec->bv_page; - struct iomap_page *iop = to_iomap_page(page); + struct iomap_page *iop = to_iomap_page(folio); if (unlikely(error)) { - ClearPageUptodate(page); - SetPageError(page); + folio_clear_uptodate(folio); + folio_set_error(folio); } else { - iomap_set_range_uptodate(page, bvec->bv_offset, bvec->bv_len); + iomap_set_range_uptodate(folio, iop, offset, len); } - if (!iop || atomic_sub_and_test(bvec->bv_len, &iop->read_bytes_pending)) - unlock_page(page); + if (!iop || atomic_sub_and_test(len, &iop->read_bytes_pending)) + folio_unlock(folio); } -static void -iomap_read_end_io(struct bio *bio) +static void iomap_read_end_io(struct bio *bio) { int error = blk_status_to_errno(bio->bi_status); - struct bio_vec *bvec; - struct bvec_iter_all iter_all; + struct folio_iter fi; - bio_for_each_segment_all(bvec, bio, iter_all) - iomap_read_page_end_io(bvec, error); + bio_for_each_folio_all(fi, bio) + iomap_finish_folio_read(fi.folio, fi.offset, fi.length, error); bio_put(bio); } struct iomap_readpage_ctx { - struct page *cur_page; - bool cur_page_in_bio; + struct folio *cur_folio; + bool cur_folio_in_bio; struct bio *bio; struct readahead_control *rac; }; @@ -208,21 +197,23 @@ struct iomap_readpage_ctx { /** * iomap_read_inline_data - copy inline data into the page cache * @iter: iteration structure - * @page: page to copy to + * @folio: folio to copy to * - * Copy the inline data in @iter into @page and zero out the rest of the page. + * Copy the inline data in @iter into @folio and zero out the rest of the folio. * Only a single IOMAP_INLINE extent is allowed at the end of each file. * Returns zero for success to complete the read, or the usual negative errno. */ static int iomap_read_inline_data(const struct iomap_iter *iter, - struct page *page) + struct folio *folio) { + struct iomap_page *iop; const struct iomap *iomap = iomap_iter_srcmap(iter); size_t size = i_size_read(iter->inode) - iomap->offset; size_t poff = offset_in_page(iomap->offset); + size_t offset = offset_in_folio(folio, iomap->offset); void *addr; - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) return 0; if (WARN_ON_ONCE(size > PAGE_SIZE - poff)) @@ -232,14 +223,16 @@ static int iomap_read_inline_data(const struct iomap_iter *iter, return -EIO; if (WARN_ON_ONCE(size > iomap->length)) return -EIO; - if (poff > 0) - iomap_page_create(iter->inode, page); + if (offset > 0) + iop = iomap_page_create(iter->inode, folio); + else + iop = to_iomap_page(folio); - addr = kmap_local_page(page) + poff; + addr = kmap_local_folio(folio, offset); memcpy(addr, iomap->inline_data, size); memset(addr + size, 0, PAGE_SIZE - poff - size); kunmap_local(addr); - iomap_set_range_uptodate(page, poff, PAGE_SIZE - poff); + iomap_set_range_uptodate(folio, iop, offset, PAGE_SIZE - poff); return 0; } @@ -259,36 +252,36 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter, const struct iomap *iomap = &iter->iomap; loff_t pos = iter->pos + offset; loff_t length = iomap_length(iter) - offset; - struct page *page = ctx->cur_page; + struct folio *folio = ctx->cur_folio; struct iomap_page *iop; loff_t orig_pos = pos; - unsigned poff, plen; + size_t poff, plen; sector_t sector; if (iomap->type == IOMAP_INLINE) - return iomap_read_inline_data(iter, page); + return iomap_read_inline_data(iter, folio); /* zero post-eof blocks as the page may be mapped */ - iop = iomap_page_create(iter->inode, page); - iomap_adjust_read_range(iter->inode, iop, &pos, length, &poff, &plen); + iop = iomap_page_create(iter->inode, folio); + iomap_adjust_read_range(iter->inode, folio, &pos, length, &poff, &plen); if (plen == 0) goto done; if (iomap_block_needs_zeroing(iter, pos)) { - zero_user(page, poff, plen); - iomap_set_range_uptodate(page, poff, plen); + folio_zero_range(folio, poff, plen); + iomap_set_range_uptodate(folio, iop, poff, plen); goto done; } - ctx->cur_page_in_bio = true; + ctx->cur_folio_in_bio = true; if (iop) atomic_add(plen, &iop->read_bytes_pending); sector = iomap_sector(iomap, pos); if (!ctx->bio || bio_end_sector(ctx->bio) != sector || - bio_add_page(ctx->bio, page, plen, poff) != plen) { - gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL); + !bio_add_folio(ctx->bio, folio, plen, poff)) { + gfp_t gfp = mapping_gfp_constraint(folio->mapping, GFP_KERNEL); gfp_t orig_gfp = gfp; unsigned int nr_vecs = DIV_ROUND_UP(length, PAGE_SIZE); @@ -311,8 +304,9 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter, ctx->bio->bi_iter.bi_sector = sector; bio_set_dev(ctx->bio, iomap->bdev); ctx->bio->bi_end_io = iomap_read_end_io; - __bio_add_page(ctx->bio, page, plen, poff); + bio_add_folio(ctx->bio, folio, plen, poff); } + done: /* * Move the caller beyond our range so that it keeps making progress. @@ -326,30 +320,31 @@ done: int iomap_readpage(struct page *page, const struct iomap_ops *ops) { + struct folio *folio = page_folio(page); struct iomap_iter iter = { - .inode = page->mapping->host, - .pos = page_offset(page), - .len = PAGE_SIZE, + .inode = folio->mapping->host, + .pos = folio_pos(folio), + .len = folio_size(folio), }; struct iomap_readpage_ctx ctx = { - .cur_page = page, + .cur_folio = folio, }; int ret; - trace_iomap_readpage(page->mapping->host, 1); + trace_iomap_readpage(iter.inode, 1); while ((ret = iomap_iter(&iter, ops)) > 0) iter.processed = iomap_readpage_iter(&iter, &ctx, 0); if (ret < 0) - SetPageError(page); + folio_set_error(folio); if (ctx.bio) { submit_bio(ctx.bio); - WARN_ON_ONCE(!ctx.cur_page_in_bio); + WARN_ON_ONCE(!ctx.cur_folio_in_bio); } else { - WARN_ON_ONCE(ctx.cur_page_in_bio); - unlock_page(page); + WARN_ON_ONCE(ctx.cur_folio_in_bio); + folio_unlock(folio); } /* @@ -368,15 +363,15 @@ static loff_t iomap_readahead_iter(const struct iomap_iter *iter, loff_t done, ret; for (done = 0; done < length; done += ret) { - if (ctx->cur_page && offset_in_page(iter->pos + done) == 0) { - if (!ctx->cur_page_in_bio) - unlock_page(ctx->cur_page); - put_page(ctx->cur_page); - ctx->cur_page = NULL; + if (ctx->cur_folio && + offset_in_folio(ctx->cur_folio, iter->pos + done) == 0) { + if (!ctx->cur_folio_in_bio) + folio_unlock(ctx->cur_folio); + ctx->cur_folio = NULL; } - if (!ctx->cur_page) { - ctx->cur_page = readahead_page(ctx->rac); - ctx->cur_page_in_bio = false; + if (!ctx->cur_folio) { + ctx->cur_folio = readahead_folio(ctx->rac); + ctx->cur_folio_in_bio = false; } ret = iomap_readpage_iter(iter, ctx, done); if (ret <= 0) @@ -419,10 +414,9 @@ void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops) if (ctx.bio) submit_bio(ctx.bio); - if (ctx.cur_page) { - if (!ctx.cur_page_in_bio) - unlock_page(ctx.cur_page); - put_page(ctx.cur_page); + if (ctx.cur_folio) { + if (!ctx.cur_folio_in_bio) + folio_unlock(ctx.cur_folio); } } EXPORT_SYMBOL_GPL(iomap_readahead); @@ -438,7 +432,8 @@ int iomap_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count) { - struct iomap_page *iop = to_iomap_page(page); + struct folio *folio = page_folio(page); + struct iomap_page *iop = to_iomap_page(folio); struct inode *inode = page->mapping->host; unsigned len, first, last; unsigned i; @@ -464,36 +459,49 @@ EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate); int iomap_releasepage(struct page *page, gfp_t gfp_mask) { - trace_iomap_releasepage(page->mapping->host, page_offset(page), - PAGE_SIZE); + struct folio *folio = page_folio(page); + + trace_iomap_releasepage(folio->mapping->host, folio_pos(folio), + folio_size(folio)); /* * mm accommodates an old ext3 case where clean pages might not have had * the dirty bit cleared. Thus, it can send actual dirty pages to * ->releasepage() via shrink_active_list(); skip those here. */ - if (PageDirty(page) || PageWriteback(page)) + if (folio_test_dirty(folio) || folio_test_writeback(folio)) return 0; - iomap_page_release(page); + iomap_page_release(folio); return 1; } EXPORT_SYMBOL_GPL(iomap_releasepage); -void -iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len) +void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len) { - trace_iomap_invalidatepage(page->mapping->host, offset, len); + trace_iomap_invalidatepage(folio->mapping->host, offset, len); /* - * If we're invalidating the entire page, clear the dirty state from it - * and release it to avoid unnecessary buildup of the LRU. + * If we're invalidating the entire folio, clear the dirty state + * from it and release it to avoid unnecessary buildup of the LRU. */ - if (offset == 0 && len == PAGE_SIZE) { - WARN_ON_ONCE(PageWriteback(page)); - cancel_dirty_page(page); - iomap_page_release(page); + if (offset == 0 && len == folio_size(folio)) { + 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); + +void iomap_invalidatepage(struct page *page, unsigned int offset, + unsigned int len) +{ + iomap_invalidate_folio(page_folio(page), offset, len); +} EXPORT_SYMBOL_GPL(iomap_invalidatepage); #ifdef CONFIG_MIGRATION @@ -501,19 +509,21 @@ int iomap_migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode) { + struct folio *folio = page_folio(page); + struct folio *newfolio = page_folio(newpage); int ret; - ret = migrate_page_move_mapping(mapping, newpage, page, 0); + ret = folio_migrate_mapping(mapping, newfolio, folio, 0); if (ret != MIGRATEPAGE_SUCCESS) return ret; - if (page_has_private(page)) - attach_page_private(newpage, detach_page_private(page)); + if (folio_test_private(folio)) + folio_attach_private(newfolio, folio_detach_private(folio)); if (mode != MIGRATE_SYNC_NO_COPY) - migrate_page_copy(newpage, page); + folio_migrate_copy(newfolio, folio); else - migrate_page_states(newpage, page); + folio_migrate_flags(newfolio, folio); return MIGRATEPAGE_SUCCESS; } EXPORT_SYMBOL_GPL(iomap_migrate_page); @@ -532,9 +542,8 @@ iomap_write_failed(struct inode *inode, loff_t pos, unsigned len) truncate_pagecache_range(inode, max(pos, i_size), pos + len); } -static int -iomap_read_page_sync(loff_t block_start, struct page *page, unsigned poff, - unsigned plen, const struct iomap *iomap) +static int iomap_read_folio_sync(loff_t block_start, struct folio *folio, + size_t poff, size_t plen, const struct iomap *iomap) { struct bio_vec bvec; struct bio bio; @@ -543,26 +552,27 @@ iomap_read_page_sync(loff_t block_start, struct page *page, unsigned poff, bio.bi_opf = REQ_OP_READ; bio.bi_iter.bi_sector = iomap_sector(iomap, block_start); bio_set_dev(&bio, iomap->bdev); - __bio_add_page(&bio, page, plen, poff); + bio_add_folio(&bio, folio, plen, poff); return submit_bio_wait(&bio); } static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos, - unsigned len, struct page *page) + size_t len, struct folio *folio) { const struct iomap *srcmap = iomap_iter_srcmap(iter); - struct iomap_page *iop = iomap_page_create(iter->inode, page); + struct iomap_page *iop = iomap_page_create(iter->inode, folio); loff_t block_size = i_blocksize(iter->inode); loff_t block_start = round_down(pos, block_size); loff_t block_end = round_up(pos + len, block_size); - unsigned from = offset_in_page(pos), to = from + len, poff, plen; + size_t from = offset_in_folio(folio, pos), to = from + len; + size_t poff, plen; - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) return 0; - ClearPageError(page); + folio_clear_error(folio); do { - iomap_adjust_read_range(iter->inode, iop, &block_start, + iomap_adjust_read_range(iter->inode, folio, &block_start, block_end - block_start, &poff, &plen); if (plen == 0) break; @@ -575,34 +585,35 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos, if (iomap_block_needs_zeroing(iter, block_start)) { if (WARN_ON_ONCE(iter->flags & IOMAP_UNSHARE)) return -EIO; - zero_user_segments(page, poff, from, to, poff + plen); + folio_zero_segments(folio, poff, from, to, poff + plen); } else { - int status = iomap_read_page_sync(block_start, page, + int status = iomap_read_folio_sync(block_start, folio, poff, plen, srcmap); if (status) return status; } - iomap_set_range_uptodate(page, poff, plen); + iomap_set_range_uptodate(folio, iop, poff, plen); } while ((block_start += plen) < block_end); return 0; } static int iomap_write_begin_inline(const struct iomap_iter *iter, - struct page *page) + struct folio *folio) { /* needs more work for the tailpacking case; disable for now */ if (WARN_ON_ONCE(iomap_iter_srcmap(iter)->offset != 0)) return -EIO; - return iomap_read_inline_data(iter, page); + return iomap_read_inline_data(iter, folio); } static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos, - unsigned len, struct page **pagep) + size_t len, struct folio **foliop) { const struct iomap_page_ops *page_ops = iter->iomap.page_ops; const struct iomap *srcmap = iomap_iter_srcmap(iter); - struct page *page; + struct folio *folio; + unsigned fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS; int status = 0; BUG_ON(pos + len > iter->iomap.offset + iter->iomap.length); @@ -612,35 +623,40 @@ static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos, if (fatal_signal_pending(current)) return -EINTR; + if (!mapping_large_folio_support(iter->inode->i_mapping)) + len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos)); + if (page_ops && page_ops->page_prepare) { status = page_ops->page_prepare(iter->inode, pos, len); if (status) return status; } - page = grab_cache_page_write_begin(iter->inode->i_mapping, - pos >> PAGE_SHIFT, AOP_FLAG_NOFS); - if (!page) { + folio = __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT, + fgp, mapping_gfp_mask(iter->inode->i_mapping)); + if (!folio) { status = -ENOMEM; goto out_no_page; } + if (pos + len > folio_pos(folio) + folio_size(folio)) + len = folio_pos(folio) + folio_size(folio) - pos; if (srcmap->type == IOMAP_INLINE) - status = iomap_write_begin_inline(iter, page); + status = iomap_write_begin_inline(iter, folio); else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) - status = __block_write_begin_int(page, pos, len, NULL, srcmap); + status = __block_write_begin_int(folio, pos, len, NULL, srcmap); else - status = __iomap_write_begin(iter, pos, len, page); + status = __iomap_write_begin(iter, pos, len, folio); if (unlikely(status)) goto out_unlock; - *pagep = page; + *foliop = folio; return 0; out_unlock: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); iomap_write_failed(iter->inode, pos, len); out_no_page: @@ -650,9 +666,10 @@ out_no_page: } static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len, - size_t copied, struct page *page) + size_t copied, struct folio *folio) { - flush_dcache_page(page); + struct iomap_page *iop = to_iomap_page(folio); + flush_dcache_folio(folio); /* * The blocks that were entirely written will now be uptodate, so we @@ -665,24 +682,24 @@ static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len, * non-uptodate page as a zero-length write, and force the caller to * redo the whole thing. */ - if (unlikely(copied < len && !PageUptodate(page))) + if (unlikely(copied < len && !folio_test_uptodate(folio))) return 0; - iomap_set_range_uptodate(page, offset_in_page(pos), len); - __set_page_dirty_nobuffers(page); + iomap_set_range_uptodate(folio, iop, offset_in_folio(folio, pos), len); + filemap_dirty_folio(inode->i_mapping, folio); return copied; } static size_t iomap_write_end_inline(const struct iomap_iter *iter, - struct page *page, loff_t pos, size_t copied) + struct folio *folio, loff_t pos, size_t copied) { const struct iomap *iomap = &iter->iomap; void *addr; - WARN_ON_ONCE(!PageUptodate(page)); + WARN_ON_ONCE(!folio_test_uptodate(folio)); BUG_ON(!iomap_inline_data_valid(iomap)); - flush_dcache_page(page); - addr = kmap_local_page(page) + pos; + flush_dcache_folio(folio); + addr = kmap_local_folio(folio, pos); memcpy(iomap_inline_data(iomap, pos), addr, copied); kunmap_local(addr); @@ -692,7 +709,7 @@ static size_t iomap_write_end_inline(const struct iomap_iter *iter, /* Returns the number of bytes copied. May be 0. Cannot be an errno. */ static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, - size_t copied, struct page *page) + size_t copied, struct folio *folio) { const struct iomap_page_ops *page_ops = iter->iomap.page_ops; const struct iomap *srcmap = iomap_iter_srcmap(iter); @@ -700,12 +717,12 @@ static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, size_t ret; if (srcmap->type == IOMAP_INLINE) { - ret = iomap_write_end_inline(iter, page, pos, copied); + ret = iomap_write_end_inline(iter, folio, pos, copied); } else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) { ret = block_write_end(NULL, iter->inode->i_mapping, pos, len, - copied, page, NULL); + copied, &folio->page, NULL); } else { - ret = __iomap_write_end(iter->inode, pos, len, copied, page); + ret = __iomap_write_end(iter->inode, pos, len, copied, folio); } /* @@ -717,13 +734,13 @@ static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, i_size_write(iter->inode, pos + ret); iter->iomap.flags |= IOMAP_F_SIZE_CHANGED; } - unlock_page(page); + folio_unlock(folio); if (old_size < pos) pagecache_isize_extended(iter->inode, old_size, pos); if (page_ops && page_ops->page_done) - page_ops->page_done(iter->inode, pos, ret, page); - put_page(page); + page_ops->page_done(iter->inode, pos, ret, &folio->page); + folio_put(folio); if (ret < len) iomap_write_failed(iter->inode, pos, len); @@ -738,6 +755,7 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) long status = 0; do { + struct folio *folio; struct page *page; unsigned long offset; /* Offset into pagecache page */ unsigned long bytes; /* Bytes to write to page */ @@ -761,16 +779,17 @@ again: break; } - status = iomap_write_begin(iter, pos, bytes, &page); + status = iomap_write_begin(iter, pos, bytes, &folio); if (unlikely(status)) break; + page = folio_file_page(folio, pos >> PAGE_SHIFT); if (mapping_writably_mapped(iter->inode->i_mapping)) flush_dcache_page(page); copied = copy_page_from_iter_atomic(page, offset, bytes, i); - status = iomap_write_end(iter, pos, bytes, copied, page); + status = iomap_write_end(iter, pos, bytes, copied, folio); if (unlikely(copied != status)) iov_iter_revert(i, copied - status); @@ -836,13 +855,13 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) do { unsigned long offset = offset_in_page(pos); unsigned long bytes = min_t(loff_t, PAGE_SIZE - offset, length); - struct page *page; + struct folio *folio; - status = iomap_write_begin(iter, pos, bytes, &page); + status = iomap_write_begin(iter, pos, bytes, &folio); if (unlikely(status)) return status; - status = iomap_write_end(iter, pos, bytes, bytes, page); + status = iomap_write_end(iter, pos, bytes, bytes, folio); if (WARN_ON_ONCE(status == 0)) return -EIO; @@ -876,26 +895,8 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, } EXPORT_SYMBOL_GPL(iomap_file_unshare); -static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length) -{ - struct page *page; - int status; - unsigned offset = offset_in_page(pos); - unsigned bytes = min_t(u64, PAGE_SIZE - offset, length); - - status = iomap_write_begin(iter, pos, bytes, &page); - if (status) - return status; - - zero_user(page, offset, bytes); - mark_page_accessed(page); - - return iomap_write_end(iter, pos, bytes, bytes, page); -} - static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) { - struct iomap *iomap = &iter->iomap; const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); @@ -906,14 +907,25 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) return length; do { - s64 bytes; + struct folio *folio; + int status; + size_t offset; + size_t bytes = min_t(u64, SIZE_MAX, length); - if (IS_DAX(iter->inode)) - bytes = dax_iomap_zero(pos, length, iomap); - else - bytes = __iomap_zero_iter(iter, pos, length); - if (bytes < 0) - return bytes; + status = iomap_write_begin(iter, pos, bytes, &folio); + if (status) + return status; + + offset = offset_in_folio(folio, pos); + if (bytes > folio_size(folio) - offset) + bytes = folio_size(folio) - offset; + + folio_zero_range(folio, offset, bytes); + folio_mark_accessed(folio); + + bytes = iomap_write_end(iter, pos, bytes, bytes, folio); + if (WARN_ON_ONCE(bytes == 0)) + return -EIO; pos += bytes; length -= bytes; @@ -957,21 +969,21 @@ iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, } EXPORT_SYMBOL_GPL(iomap_truncate_page); -static loff_t iomap_page_mkwrite_iter(struct iomap_iter *iter, - struct page *page) +static loff_t iomap_folio_mkwrite_iter(struct iomap_iter *iter, + struct folio *folio) { loff_t length = iomap_length(iter); int ret; if (iter->iomap.flags & IOMAP_F_BUFFER_HEAD) { - ret = __block_write_begin_int(page, iter->pos, length, NULL, + ret = __block_write_begin_int(folio, iter->pos, length, NULL, &iter->iomap); if (ret) return ret; - block_commit_write(page, 0, length); + block_commit_write(&folio->page, 0, length); } else { - WARN_ON_ONCE(!PageUptodate(page)); - set_page_dirty(page); + WARN_ON_ONCE(!folio_test_uptodate(folio)); + folio_mark_dirty(folio); } return length; @@ -983,44 +995,43 @@ vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops) .inode = file_inode(vmf->vma->vm_file), .flags = IOMAP_WRITE | IOMAP_FAULT, }; - struct page *page = vmf->page; + struct folio *folio = page_folio(vmf->page); ssize_t ret; - lock_page(page); - ret = page_mkwrite_check_truncate(page, iter.inode); + folio_lock(folio); + ret = folio_mkwrite_check_truncate(folio, iter.inode); if (ret < 0) goto out_unlock; - iter.pos = page_offset(page); + iter.pos = folio_pos(folio); iter.len = ret; while ((ret = iomap_iter(&iter, ops)) > 0) - iter.processed = iomap_page_mkwrite_iter(&iter, page); + iter.processed = iomap_folio_mkwrite_iter(&iter, folio); if (ret < 0) goto out_unlock; - wait_for_stable_page(page); + folio_wait_stable(folio); return VM_FAULT_LOCKED; out_unlock: - unlock_page(page); + folio_unlock(folio); return block_page_mkwrite_return(ret); } EXPORT_SYMBOL_GPL(iomap_page_mkwrite); -static void -iomap_finish_page_writeback(struct inode *inode, struct page *page, - int error, unsigned int len) +static void iomap_finish_folio_write(struct inode *inode, struct folio *folio, + size_t len, int error) { - struct iomap_page *iop = to_iomap_page(page); + struct iomap_page *iop = to_iomap_page(folio); if (error) { - SetPageError(page); + folio_set_error(folio); mapping_set_error(inode->i_mapping, error); } - WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop); + WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !iop); WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) <= 0); if (!iop || atomic_sub_and_test(len, &iop->write_bytes_pending)) - end_page_writeback(page); + folio_end_writeback(folio); } /* @@ -1039,8 +1050,7 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error) bool quiet = bio_flagged(bio, BIO_QUIET); for (bio = &ioend->io_inline_bio; bio; bio = next) { - struct bio_vec *bv; - struct bvec_iter_all iter_all; + struct folio_iter fi; /* * For the last bio, bi_private points to the ioend, so we @@ -1051,10 +1061,10 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error) else next = bio->bi_private; - /* walk each page on bio, ending page IO on them */ - bio_for_each_segment_all(bv, bio, iter_all) - iomap_finish_page_writeback(inode, bv->bv_page, error, - bv->bv_len); + /* walk all folios in bio, ending page IO on them */ + bio_for_each_folio_all(fi, bio) + iomap_finish_folio_write(inode, fi.folio, fi.length, + error); bio_put(bio); } /* The ioend has been freed by bio_put() */ @@ -1249,29 +1259,29 @@ iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset, * first; otherwise finish off the current ioend and start another. */ static void -iomap_add_to_ioend(struct inode *inode, loff_t offset, struct page *page, +iomap_add_to_ioend(struct inode *inode, loff_t pos, struct folio *folio, struct iomap_page *iop, struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct list_head *iolist) { - sector_t sector = iomap_sector(&wpc->iomap, offset); + sector_t sector = iomap_sector(&wpc->iomap, pos); unsigned len = i_blocksize(inode); - unsigned poff = offset & (PAGE_SIZE - 1); + size_t poff = offset_in_folio(folio, pos); - if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, offset, sector)) { + if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos, sector)) { if (wpc->ioend) list_add(&wpc->ioend->io_list, iolist); - wpc->ioend = iomap_alloc_ioend(inode, wpc, offset, sector, wbc); + wpc->ioend = iomap_alloc_ioend(inode, wpc, pos, sector, wbc); } - if (bio_add_page(wpc->ioend->io_bio, page, len, poff) != len) { + if (!bio_add_folio(wpc->ioend->io_bio, folio, len, poff)) { wpc->ioend->io_bio = iomap_chain_bio(wpc->ioend->io_bio); - __bio_add_page(wpc->ioend->io_bio, page, len, poff); + bio_add_folio(wpc->ioend->io_bio, folio, len, poff); } if (iop) atomic_add(len, &iop->write_bytes_pending); wpc->ioend->io_size += len; - wbc_account_cgroup_owner(wbc, page, len); + wbc_account_cgroup_owner(wbc, &folio->page, len); } /* @@ -1293,44 +1303,43 @@ iomap_add_to_ioend(struct inode *inode, loff_t offset, struct page *page, static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct inode *inode, - struct page *page, u64 end_offset) + struct folio *folio, u64 end_pos) { - struct iomap_page *iop = iomap_page_create(inode, page); + struct iomap_page *iop = iomap_page_create(inode, folio); struct iomap_ioend *ioend, *next; unsigned len = i_blocksize(inode); - u64 file_offset; /* file offset of page */ + unsigned nblocks = i_blocks_per_folio(inode, folio); + u64 pos = folio_pos(folio); int error = 0, count = 0, i; LIST_HEAD(submit_list); WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) != 0); /* - * Walk through the page to find areas to write back. If we run off the - * end of the current map or find the current map invalid, grab a new - * one. + * Walk through the folio to find areas to write back. If we + * run off the end of the current map or find the current map + * invalid, grab a new one. */ - for (i = 0, file_offset = page_offset(page); - i < (PAGE_SIZE >> inode->i_blkbits) && file_offset < end_offset; - i++, file_offset += len) { + for (i = 0; i < nblocks && pos < end_pos; i++, pos += len) { if (iop && !test_bit(i, iop->uptodate)) continue; - error = wpc->ops->map_blocks(wpc, inode, file_offset); + error = wpc->ops->map_blocks(wpc, inode, pos); if (error) break; if (WARN_ON_ONCE(wpc->iomap.type == IOMAP_INLINE)) continue; if (wpc->iomap.type == IOMAP_HOLE) continue; - iomap_add_to_ioend(inode, file_offset, page, iop, wpc, wbc, + iomap_add_to_ioend(inode, pos, folio, iop, wpc, wbc, &submit_list); count++; } WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list)); - WARN_ON_ONCE(!PageLocked(page)); - WARN_ON_ONCE(PageWriteback(page)); - WARN_ON_ONCE(PageDirty(page)); + WARN_ON_ONCE(!folio_test_locked(folio)); + WARN_ON_ONCE(folio_test_writeback(folio)); + WARN_ON_ONCE(folio_test_dirty(folio)); /* * We cannot cancel the ioend directly here on error. We may have @@ -1345,17 +1354,17 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, * won't be affected by I/O completion and we must unlock it * now. */ - if (wpc->ops->discard_page) - wpc->ops->discard_page(page, file_offset); + if (wpc->ops->discard_folio) + wpc->ops->discard_folio(folio, pos); if (!count) { - ClearPageUptodate(page); - unlock_page(page); + folio_clear_uptodate(folio); + folio_unlock(folio); goto done; } } - set_page_writeback(page); - unlock_page(page); + folio_start_writeback(folio); + folio_unlock(folio); /* * Preserve the original error if there was one; catch @@ -1376,9 +1385,9 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, * with a partial page truncate on a sub-page block sized filesystem. */ if (!count) - end_page_writeback(page); + folio_end_writeback(folio); done: - mapping_set_error(page->mapping, error); + mapping_set_error(folio->mapping, error); return error; } @@ -1392,16 +1401,15 @@ done: static int iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data) { + struct folio *folio = page_folio(page); struct iomap_writepage_ctx *wpc = data; - struct inode *inode = page->mapping->host; - pgoff_t end_index; - u64 end_offset; - loff_t offset; + struct inode *inode = folio->mapping->host; + u64 end_pos, isize; - trace_iomap_writepage(inode, page_offset(page), PAGE_SIZE); + trace_iomap_writepage(inode, folio_pos(folio), folio_size(folio)); /* - * Refuse to write the page out if we're called from reclaim context. + * Refuse to write the folio out if we're called from reclaim context. * * This avoids stack overflows when called from deeply used stacks in * random callers for direct reclaim or memcg reclaim. We explicitly @@ -1415,10 +1423,10 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data) goto redirty; /* - * Is this page beyond the end of the file? + * Is this folio beyond the end of the file? * - * The page index is less than the end_index, adjust the end_offset - * to the highest offset that this page should represent. + * The folio index is less than the end_index, adjust the end_pos + * to the highest offset that this folio should represent. * ----------------------------------------------------- * | file mapping | <EOF> | * ----------------------------------------------------- @@ -1427,11 +1435,9 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data) * | desired writeback range | see else | * ---------------------------------^------------------| */ - offset = i_size_read(inode); - end_index = offset >> PAGE_SHIFT; - if (page->index < end_index) - end_offset = (loff_t)(page->index + 1) << PAGE_SHIFT; - else { + isize = i_size_read(inode); + end_pos = folio_pos(folio) + folio_size(folio); + if (end_pos > isize) { /* * Check whether the page to write out is beyond or straddles * i_size or not. @@ -1443,7 +1449,8 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data) * | | Straddles | * ---------------------------------^-----------|--------| */ - unsigned offset_into_page = offset & (PAGE_SIZE - 1); + size_t poff = offset_in_folio(folio, isize); + pgoff_t end_index = isize >> PAGE_SHIFT; /* * Skip the page if it's fully outside i_size, e.g. due to a @@ -1462,8 +1469,8 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data) * checking if the page is totally beyond i_size or if its * offset is just equal to the EOF. */ - if (page->index > end_index || - (page->index == end_index && offset_into_page == 0)) + if (folio->index > end_index || + (folio->index == end_index && poff == 0)) goto redirty; /* @@ -1474,17 +1481,15 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data) * memory is zeroed when mapped, and writes to that region are * not written out to the file." */ - zero_user_segment(page, offset_into_page, PAGE_SIZE); - - /* Adjust the end_offset to the end of file */ - end_offset = offset; + folio_zero_segment(folio, poff, folio_size(folio)); + end_pos = isize; } - return iomap_writepage_map(wpc, wbc, inode, page, end_offset); + return iomap_writepage_map(wpc, wbc, inode, folio, end_pos); redirty: - redirty_page_for_writepage(wbc, page); - unlock_page(page); + folio_redirty_for_writepage(wbc, folio); + folio_unlock(folio); return 0; } diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index b4dc51063d36..03ea367df19a 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -6,6 +6,7 @@ #include <linux/module.h> #include <linux/compiler.h> #include <linux/fs.h> +#include <linux/pagemap.h> #include <linux/iomap.h> #include <linux/backing-dev.h> #include <linux/uio.h> |