diff options
Diffstat (limited to 'fs/iomap/buffered-io.c')
| -rw-r--r-- | fs/iomap/buffered-io.c | 1067 |
1 files changed, 567 insertions, 500 deletions
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 093c4515b22a..d303e6c8900c 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Red Hat, Inc. - * Copyright (C) 2016-2019 Christoph Hellwig. + * Copyright (C) 2016-2023 Christoph Hellwig. */ #include <linux/module.h> #include <linux/compiler.h> @@ -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. @@ -95,6 +94,44 @@ static inline bool ifs_block_is_dirty(struct folio *folio, return test_bit(block + blks_per_folio, ifs->state); } +static unsigned ifs_find_dirty_range(struct folio *folio, + struct iomap_folio_state *ifs, u64 *range_start, u64 range_end) +{ + struct inode *inode = folio->mapping->host; + unsigned start_blk = + offset_in_folio(folio, *range_start) >> inode->i_blkbits; + unsigned end_blk = min_not_zero( + offset_in_folio(folio, range_end) >> inode->i_blkbits, + i_blocks_per_folio(inode, folio)); + unsigned nblks = 1; + + while (!ifs_block_is_dirty(folio, ifs, start_blk)) + if (++start_blk == end_blk) + return 0; + + while (start_blk + nblks < end_blk) { + if (!ifs_block_is_dirty(folio, ifs, start_blk + nblks)) + break; + nblks++; + } + + *range_start = folio_pos(folio) + (start_blk << inode->i_blkbits); + return nblks << inode->i_blkbits; +} + +static unsigned iomap_find_dirty_range(struct folio *folio, u64 *range_start, + u64 range_end) +{ + struct iomap_folio_state *ifs = folio->private; + + if (*range_start >= range_end) + return 0; + + if (ifs) + return ifs_find_dirty_range(folio, ifs, range_start, range_end); + return range_end - *range_start; +} + static void ifs_clear_range_dirty(struct folio *folio, struct iomap_folio_state *ifs, size_t off, size_t len) { @@ -203,6 +240,7 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, unsigned block_size = (1 << block_bits); size_t poff = offset_in_folio(folio, *pos); size_t plen = min_t(loff_t, folio_size(folio) - poff, length); + size_t orig_plen = plen; unsigned first = poff >> block_bits; unsigned last = (poff + plen - 1) >> block_bits; @@ -239,7 +277,7 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, * handle both halves separately so that we properly zero data in the * page cache for blocks that are entirely outside of i_size. */ - if (orig_pos <= isize && orig_pos + length > isize) { + if (orig_pos <= isize && orig_pos + orig_plen > isize) { unsigned end = offset_in_folio(folio, isize - 1) >> block_bits; if (first <= end && last > end) @@ -268,8 +306,6 @@ static void iomap_finish_folio_read(struct folio *folio, size_t off, spin_unlock_irqrestore(&ifs->state_lock, flags); } - if (error) - folio_set_error(folio); if (finished) folio_end_read(folio, uptodate); } @@ -405,6 +441,24 @@ done: return pos - orig_pos + plen; } +static loff_t iomap_read_folio_iter(const struct iomap_iter *iter, + struct iomap_readpage_ctx *ctx) +{ + struct folio *folio = ctx->cur_folio; + size_t offset = offset_in_folio(folio, iter->pos); + loff_t length = min_t(loff_t, folio_size(folio) - offset, + iomap_length(iter)); + loff_t done, ret; + + for (done = 0; done < length; done += ret) { + ret = iomap_readpage_iter(iter, ctx, done); + if (ret <= 0) + return ret; + } + + return done; +} + int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops) { struct iomap_iter iter = { @@ -420,10 +474,7 @@ int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops) trace_iomap_readpage(iter.inode, 1); while ((ret = iomap_iter(&iter, ops)) > 0) - iter.processed = iomap_readpage_iter(&iter, &ctx, 0); - - if (ret < 0) - folio_set_error(folio); + iter.processed = iomap_read_folio_iter(&iter, &ctx); if (ctx.bio) { submit_bio(ctx.bio); @@ -659,7 +710,6 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos, if (folio_test_uptodate(folio)) return 0; - folio_clear_error(folio); do { iomap_adjust_read_range(iter->inode, folio, &block_start, @@ -786,12 +836,11 @@ static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, out_unlock: __iomap_put_folio(iter, pos, 0, folio); - iomap_write_failed(iter->inode, pos, len); return status; } -static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len, +static bool __iomap_write_end(struct inode *inode, loff_t pos, size_t len, size_t copied, struct folio *folio) { flush_dcache_folio(folio); @@ -808,14 +857,14 @@ static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len, * redo the whole thing. */ if (unlikely(copied < len && !folio_test_uptodate(folio))) - return 0; + return false; iomap_set_range_uptodate(folio, offset_in_folio(folio, pos), len); iomap_set_range_dirty(folio, offset_in_folio(folio, pos), copied); filemap_dirty_folio(inode->i_mapping, folio); - return copied; + return true; } -static size_t iomap_write_end_inline(const struct iomap_iter *iter, +static void iomap_write_end_inline(const struct iomap_iter *iter, struct folio *folio, loff_t pos, size_t copied) { const struct iomap *iomap = &iter->iomap; @@ -830,59 +879,51 @@ static size_t iomap_write_end_inline(const struct iomap_iter *iter, kunmap_local(addr); mark_inode_dirty(iter->inode); - return copied; } -/* 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, +/* + * Returns true if all copied bytes have been written to the pagecache, + * otherwise return false. + */ +static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, size_t copied, struct folio *folio) { const struct iomap *srcmap = iomap_iter_srcmap(iter); - loff_t old_size = iter->inode->i_size; - size_t ret; if (srcmap->type == IOMAP_INLINE) { - 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, &folio->page, NULL); - } else { - ret = __iomap_write_end(iter->inode, pos, len, copied, folio); + iomap_write_end_inline(iter, folio, pos, copied); + return true; } - /* - * Update the in-memory inode size after copying the data into the page - * cache. It's up to the file system to write the updated size to disk, - * preferably after I/O completion so that no stale data is exposed. - */ - if (pos + ret > old_size) { - i_size_write(iter->inode, pos + ret); - iter->iomap.flags |= IOMAP_F_SIZE_CHANGED; + if (srcmap->flags & IOMAP_F_BUFFER_HEAD) { + size_t bh_written; + + bh_written = block_write_end(NULL, iter->inode->i_mapping, pos, + len, copied, folio, NULL); + WARN_ON_ONCE(bh_written != copied && bh_written != 0); + return bh_written == copied; } - __iomap_put_folio(iter, pos, ret, folio); - if (old_size < pos) - pagecache_isize_extended(iter->inode, old_size, pos); - if (ret < len) - iomap_write_failed(iter->inode, pos + ret, len - ret); - return ret; + return __iomap_write_end(iter->inode, pos, len, copied, folio); } 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; + ssize_t total_written = 0; long status = 0; struct address_space *mapping = iter->inode->i_mapping; + size_t chunk = mapping_max_folio_size(mapping); unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0; do { struct folio *folio; + loff_t old_size; size_t offset; /* Offset into folio */ size_t bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ + size_t written; /* Bytes have been written */ bytes = iov_iter_count(i); retry: @@ -912,8 +953,10 @@ retry: } status = iomap_write_begin(iter, pos, bytes, &folio); - if (unlikely(status)) + if (unlikely(status)) { + iomap_write_failed(iter->inode, pos, bytes); break; + } if (iter->iomap.flags & IOMAP_F_STALE) break; @@ -925,19 +968,37 @@ retry: flush_dcache_folio(folio); copied = copy_folio_from_iter_atomic(folio, offset, bytes, i); - status = iomap_write_end(iter, pos, bytes, copied, folio); + written = iomap_write_end(iter, pos, bytes, copied, folio) ? + copied : 0; + + /* + * Update the in-memory inode size after copying the data into + * the page cache. It's up to the file system to write the + * updated size to disk, preferably after I/O completion so that + * no stale data is exposed. Only once that's done can we + * unlock and release the folio. + */ + old_size = iter->inode->i_size; + if (pos + written > old_size) { + i_size_write(iter->inode, pos + written); + iter->iomap.flags |= IOMAP_F_SIZE_CHANGED; + } + __iomap_put_folio(iter, pos, written, folio); - if (unlikely(copied != status)) - iov_iter_revert(i, copied - status); + if (old_size < pos) + pagecache_isize_extended(iter->inode, old_size, pos); cond_resched(); - if (unlikely(status == 0)) { + if (unlikely(written == 0)) { /* * A short copy made iomap_write_end() reject the * thing entirely. Might be memory poisoning * halfway through, might be a race with munmap, * might be severe memory pressure. */ + iomap_write_failed(iter->inode, pos, bytes); + iov_iter_revert(i, copied); + if (chunk > PAGE_SIZE) chunk /= 2; if (copied) { @@ -945,28 +1006,29 @@ retry: goto retry; } } else { - pos += status; - written += status; - length -= status; + pos += written; + total_written += written; + length -= written; } } while (iov_iter_count(i) && length); if (status == -EAGAIN) { - iov_iter_revert(i, written); + iov_iter_revert(i, total_written); return -EAGAIN; } - return written ? written : status; + return total_written ? total_written : status; } 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; @@ -984,15 +1046,14 @@ 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, - iomap_punch_t punch) + struct iomap *iomap, iomap_punch_t punch) { unsigned int first_blk, last_blk, i; 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 @@ -1002,47 +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), - 1 << blkbits); - if (ret) - return ret; - } + if (!ifs_block_is_dirty(folio, ifs, i)) + punch(inode, folio_pos(folio) + (i << blkbits), + 1 << blkbits, iomap); } - - 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, - iomap_punch_t punch) + 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); - 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, punch); - if (ret) - return ret; + iomap_write_delalloc_ifs_punch(inode, folio, start_byte, end_byte, + iomap, punch); /* * Make sure the next punch start is correctly bound to @@ -1050,8 +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; } /* @@ -1071,13 +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, - iomap_punch_t punch) + 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, @@ -1088,27 +1134,47 @@ static int iomap_write_delalloc_scan(struct inode *inode, continue; } - ret = iomap_write_delalloc_punch(inode, folio, punch_start_byte, - start_byte, end_byte, punch); - if (ret) { - folio_unlock(folio); - folio_put(folio); - return ret; - } + iomap_write_delalloc_punch(inode, folio, punch_start_byte, + start_byte, end_byte, iomap, punch); /* move offset to start of next folio in range */ - start_byte = folio_next_index(folio) << PAGE_SHIFT; + start_byte = folio_pos(folio) + folio_size(folio); folio_unlock(folio); folio_put(folio); } - return 0; } /* + * When a short write occurs, the filesystem might need to use ->iomap_end + * to remove space reservations created in ->iomap_begin. + * + * For filesystems that use delayed allocation, there can be dirty pages over + * the delalloc extent outside the range of a short write but still within the + * delalloc extent allocated for this iomap if the write raced with page + * faults. + * * Punch out all the delalloc blocks in the range given except for those that * have dirty data still pending in the page cache - those are going to be * written and so must still retain the delalloc backing for writeback. * + * The punch() callback *must* only punch delalloc extents in the range passed + * to it. It must skip over all other types of extents in the range and leave + * them completely unchanged. It must do this punch atomically with respect to + * other extent modifications. + * + * The punch() callback may be called with a folio locked to prevent writeback + * extent allocation racing at the edge of the range we are currently punching. + * The locked folio may or may not cover the range being punched, so it is not + * safe for the punch() callback to lock folios itself. + * + * Lock order is: + * + * inode->i_rwsem (shared or exclusive) + * inode->i_mapping->invalidate_lock (exclusive) + * folio_lock() + * ->punch + * internal filesystem allocation lock + * * As we are scanning the page cache for data, we don't need to reimplement the * wheel - mapping_seek_hole_data() does exactly what we need to identify the * start and end of data ranges correctly even for sub-folio block sizes. This @@ -1137,20 +1203,21 @@ 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) +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 - * folios and dirtying them via ->page_mkwrite whilst we walk the - * cache and perform delalloc extent removal. Failing to do this can - * leave dirty pages with no space reservation in the cache. + * The caller must hold invalidate_lock to avoid races with page faults + * re-instantiating folios and dirtying them via ->page_mkwrite whilst + * we walk the cache and perform delalloc extent removal. Failing to do + * this can leave dirty pages with no space reservation in the cache. */ - filemap_invalidate_lock(inode->i_mapping); + lockdep_assert_held_write(&inode->i_mapping->invalidate_lock); + while (start_byte < scan_end_byte) { loff_t data_end; @@ -1159,13 +1226,15 @@ static int iomap_write_delalloc_release(struct inode *inode, /* * 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; - goto out_unlock; - } + if (WARN_ON_ONCE(start_byte < 0)) + return; WARN_ON_ONCE(start_byte < punch_start_byte); WARN_ON_ONCE(start_byte > scan_end_byte); @@ -1175,108 +1244,40 @@ static int iomap_write_delalloc_release(struct inode *inode, */ data_end = mapping_seek_hole_data(inode->i_mapping, start_byte, scan_end_byte, SEEK_HOLE); - if (data_end < 0) { - error = data_end; - goto out_unlock; - } - WARN_ON_ONCE(data_end <= start_byte); + if (WARN_ON_ONCE(data_end < 0)) + return; + + /* + * 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, - start_byte, data_end, 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); -out_unlock: - filemap_invalidate_unlock(inode->i_mapping); - return error; + punch(inode, punch_start_byte, end_byte - punch_start_byte, + iomap); } - -/* - * When a short write occurs, the filesystem may need to remove reserved space - * that was allocated in ->iomap_begin from it's ->iomap_end method. For - * filesystems that use delayed allocation, we need to punch out delalloc - * extents from the range that are not dirty in the page cache. As the write can - * race with page faults, there can be dirty pages over the delalloc extent - * outside the range of a short write but still within the delalloc extent - * allocated for this iomap. - * - * This function uses [start_byte, end_byte) intervals (i.e. open ended) to - * simplify range iterations. - * - * The punch() callback *must* only punch delalloc extents in the range passed - * to it. It must skip over all other types of extents in the range and leave - * them completely unchanged. It must do this punch atomically with respect to - * other extent modifications. - * - * The punch() callback may be called with a folio locked to prevent writeback - * extent allocation racing at the edge of the range we are currently punching. - * The locked folio may or may not cover the range being punched, so it is not - * safe for the punch() callback to lock folios itself. - * - * Lock order is: - * - * inode->i_rwsem (shared or exclusive) - * inode->i_mapping->invalidate_lock (exclusive) - * folio_lock() - * ->punch - * 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 start_byte; - loff_t end_byte; - unsigned int blocksize = i_blocksize(inode); - - if (iomap->type != IOMAP_DELALLOC) - return 0; - - /* If we didn't reserve the blocks, we're not allowed to punch them. */ - if (!(iomap->flags & IOMAP_F_NEW)) - return 0; - - /* - * start_byte refers to the first unused block after a short write. If - * nothing was written, round offset down to point at the first block in - * the range. - */ - if (unlikely(!written)) - start_byte = round_down(pos, blocksize); - else - start_byte = round_up(pos + written, blocksize); - end_byte = round_up(pos + length, blocksize); - - /* Nothing to do if we've written the entire delalloc extent */ - if (start_byte >= end_byte) - return 0; - - return iomap_write_delalloc_release(inode, start_byte, end_byte, - punch); -} -EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc); +EXPORT_SYMBOL_GPL(iomap_write_delalloc_release); 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 */ - 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) + if (!iomap_want_unshare_iter(iter)) return length; do { @@ -1284,6 +1285,7 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) int status; size_t offset; size_t bytes = min_t(u64, SIZE_MAX, length); + bool ret; status = iomap_write_begin(iter, pos, bytes, &folio); if (unlikely(status)) @@ -1295,8 +1297,9 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) if (bytes > folio_size(folio) - offset) bytes = folio_size(folio) - offset; - bytes = iomap_write_end(iter, pos, bytes, bytes, folio); - if (WARN_ON_ONCE(bytes == 0)) + ret = iomap_write_end(iter, pos, bytes, bytes, folio); + __iomap_put_folio(iter, pos, bytes, folio); + if (WARN_ON_ONCE(!ret)) return -EIO; cond_resched(); @@ -1318,33 +1321,47 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, struct iomap_iter iter = { .inode = inode, .pos = pos, - .len = len, .flags = IOMAP_WRITE | IOMAP_UNSHARE, }; + loff_t size = i_size_read(inode); int ret; + if (pos < 0 || pos >= size) + return 0; + + iter.len = min(len, size - pos); while ((ret = iomap_iter(&iter, ops)) > 0) iter.processed = iomap_unshare_iter(&iter); return ret; } EXPORT_SYMBOL_GPL(iomap_file_unshare); +/* + * 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) { - 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) - return length; - do { struct folio *folio; int status; size_t offset; size_t bytes = min_t(u64, SIZE_MAX, length); + bool ret; status = iomap_write_begin(iter, pos, bytes, &folio); if (status) @@ -1352,6 +1369,8 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) if (iter->iomap.flags & IOMAP_F_STALE) break; + /* warn about zeroing folios beyond eof that won't write back */ + WARN_ON_ONCE(folio_pos(folio) > iter->inode->i_size); offset = offset_in_folio(folio, pos); if (bytes > folio_size(folio) - offset) bytes = folio_size(folio) - offset; @@ -1359,8 +1378,9 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) 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)) + ret = iomap_write_end(iter, pos, bytes, bytes, folio); + __iomap_put_folio(iter, pos, bytes, folio); + if (WARN_ON_ONCE(!ret)) return -EIO; pos += bytes; @@ -1383,10 +1403,58 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, .len = len, .flags = IOMAP_ZERO, }; + struct address_space *mapping = inode->i_mapping; + unsigned int blocksize = i_blocksize(inode); + unsigned int off = pos & (blocksize - 1); + loff_t plen = min_t(loff_t, len, blocksize - off); int ret; + bool range_dirty; + + /* + * Zero range can skip mappings that are zero on disk so long as + * pagecache is clean. If pagecache was dirty prior to zero range, the + * mapping converts on writeback completion and so must be zeroed. + * + * The simplest way to deal with this across a range is to flush + * pagecache and process the updated mappings. To avoid excessive + * flushing on partial eof zeroing, special case it to zero the + * unaligned start portion if already dirty in pagecache. + */ + if (off && + filemap_range_needs_writeback(mapping, pos, pos + plen - 1)) { + iter.len = plen; + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.processed = iomap_zero_iter(&iter, did_zero); + + iter.len = len - (iter.pos - pos); + if (ret || !iter.len) + return ret; + } + + /* + * To avoid an unconditional flush, check pagecache state and only flush + * if dirty and the fs returns a mapping that might convert on + * writeback. + */ + range_dirty = filemap_range_needs_writeback(inode->i_mapping, + iter.pos, iter.pos + iter.len - 1); + while ((ret = iomap_iter(&iter, ops)) > 0) { + const struct iomap *srcmap = iomap_iter_srcmap(&iter); + + if (srcmap->type == IOMAP_HOLE || + srcmap->type == IOMAP_UNWRITTEN) { + loff_t proc = iomap_length(&iter); + + if (range_dirty) { + range_dirty = false; + proc = iomap_zero_iter_flush_and_stale(&iter); + } + iter.processed = proc; + continue; + } - while ((ret = iomap_iter(&iter, ops)) > 0) iter.processed = iomap_zero_iter(&iter, did_zero); + } return ret; } EXPORT_SYMBOL_GPL(iomap_zero_range); @@ -1454,15 +1522,10 @@ out_unlock: EXPORT_SYMBOL_GPL(iomap_page_mkwrite); static void iomap_finish_folio_write(struct inode *inode, struct folio *folio, - size_t len, int error) + size_t len) { struct iomap_folio_state *ifs = folio->private; - if (error) { - folio_set_error(folio); - mapping_set_error(inode->i_mapping, error); - } - WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !ifs); WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) <= 0); @@ -1479,40 +1542,27 @@ static u32 iomap_finish_ioend(struct iomap_ioend *ioend, int error) { struct inode *inode = ioend->io_inode; - struct bio *bio = &ioend->io_inline_bio; - struct bio *last = ioend->io_bio, *next; - u64 start = bio->bi_iter.bi_sector; - loff_t offset = ioend->io_offset; - bool quiet = bio_flagged(bio, BIO_QUIET); + struct bio *bio = &ioend->io_bio; + struct folio_iter fi; u32 folio_count = 0; - for (bio = &ioend->io_inline_bio; bio; bio = next) { - struct folio_iter fi; - - /* - * For the last bio, bi_private points to the ioend, so we - * need to explicitly end the iteration here. - */ - if (bio == last) - next = NULL; - else - next = bio->bi_private; - - /* 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); - folio_count++; + if (error) { + mapping_set_error(inode->i_mapping, error); + if (!bio_flagged(bio, BIO_QUIET)) { + pr_err_ratelimited( +"%s: writeback error on inode %lu, offset %lld, sector %llu", + inode->i_sb->s_id, inode->i_ino, + ioend->io_offset, ioend->io_sector); } - bio_put(bio); } - /* The ioend has been freed by bio_put() */ - if (unlikely(error && !quiet)) { - printk_ratelimited(KERN_ERR -"%s: writeback error on inode %lu, offset %lld, sector %llu", - inode->i_sb->s_id, inode->i_ino, offset, start); + /* 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); + folio_count++; } + + bio_put(bio); /* frees the ioend */ return folio_count; } @@ -1553,7 +1603,9 @@ EXPORT_SYMBOL_GPL(iomap_finish_ioends); static bool iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next) { - if (ioend->io_bio->bi_status != next->io_bio->bi_status) + if (ioend->io_bio.bi_status != next->io_bio.bi_status) + return false; + if (next->io_flags & IOMAP_F_BOUNDARY) return false; if ((ioend->io_flags & IOMAP_F_SHARED) ^ (next->io_flags & IOMAP_F_SHARED)) @@ -1618,47 +1670,46 @@ EXPORT_SYMBOL_GPL(iomap_sort_ioends); static void iomap_writepage_end_bio(struct bio *bio) { - struct iomap_ioend *ioend = bio->bi_private; - - iomap_finish_ioend(ioend, blk_status_to_errno(bio->bi_status)); + iomap_finish_ioend(iomap_ioend_from_bio(bio), + blk_status_to_errno(bio->bi_status)); } /* * Submit the final bio for an ioend. * * If @error is non-zero, it means that we have a situation where some part of - * the submission process has failed after we've marked pages for writeback - * and unlocked them. In this situation, we need to fail the bio instead of - * submitting it. This typically only happens on a filesystem shutdown. + * the submission process has failed after we've marked pages for writeback. + * We cannot cancel ioend directly in that case, so call the bio end I/O handler + * with the error status here to run the normal I/O completion handler to clear + * the writeback bit and let the file system proess the errors. */ -static int -iomap_submit_ioend(struct iomap_writepage_ctx *wpc, struct iomap_ioend *ioend, - int error) +static int iomap_submit_ioend(struct iomap_writepage_ctx *wpc, int error) { - ioend->io_bio->bi_private = ioend; - ioend->io_bio->bi_end_io = iomap_writepage_end_bio; + if (!wpc->ioend) + return error; + /* + * Let the file systems prepare the I/O submission and hook in an I/O + * comletion handler. This also needs to happen in case after a + * failure happened so that the file system end I/O handler gets called + * to clean up. + */ if (wpc->ops->prepare_ioend) - error = wpc->ops->prepare_ioend(ioend, error); + error = wpc->ops->prepare_ioend(wpc->ioend, error); + if (error) { - /* - * If we're failing the IO now, just mark the ioend with an - * error and finish it. This will run IO completion immediately - * as there is only one reference to the ioend at this point in - * time. - */ - ioend->io_bio->bi_status = errno_to_blk_status(error); - bio_endio(ioend->io_bio); - return error; + wpc->ioend->io_bio.bi_status = errno_to_blk_status(error); + bio_endio(&wpc->ioend->io_bio); + } else { + submit_bio(&wpc->ioend->io_bio); } - submit_bio(ioend->io_bio); - return 0; + wpc->ioend = NULL; + return error; } -static struct iomap_ioend * -iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc, - loff_t offset, sector_t sector, struct writeback_control *wbc) +static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc, + struct writeback_control *wbc, struct inode *inode, loff_t pos) { struct iomap_ioend *ioend; struct bio *bio; @@ -1666,63 +1717,46 @@ iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc, bio = bio_alloc_bioset(wpc->iomap.bdev, BIO_MAX_VECS, REQ_OP_WRITE | wbc_to_write_flags(wbc), GFP_NOFS, &iomap_ioend_bioset); - bio->bi_iter.bi_sector = sector; + bio->bi_iter.bi_sector = iomap_sector(&wpc->iomap, pos); + bio->bi_end_io = iomap_writepage_end_bio; wbc_init_bio(wbc, bio); + bio->bi_write_hint = inode->i_write_hint; - ioend = container_of(bio, struct iomap_ioend, io_inline_bio); + ioend = iomap_ioend_from_bio(bio); INIT_LIST_HEAD(&ioend->io_list); ioend->io_type = wpc->iomap.type; ioend->io_flags = wpc->iomap.flags; + if (pos > wpc->iomap.offset) + wpc->iomap.flags &= ~IOMAP_F_BOUNDARY; ioend->io_inode = inode; ioend->io_size = 0; - ioend->io_folios = 0; - ioend->io_offset = offset; - ioend->io_bio = bio; - ioend->io_sector = sector; - return ioend; -} - -/* - * Allocate a new bio, and chain the old bio to the new one. - * - * Note that we have to perform the chaining in this unintuitive order - * so that the bi_private linkage is set up in the right direction for the - * traversal in iomap_finish_ioend(). - */ -static struct bio * -iomap_chain_bio(struct bio *prev) -{ - struct bio *new; + ioend->io_offset = pos; + ioend->io_sector = bio->bi_iter.bi_sector; - new = bio_alloc(prev->bi_bdev, BIO_MAX_VECS, prev->bi_opf, GFP_NOFS); - bio_clone_blkg_association(new, prev); - new->bi_iter.bi_sector = bio_end_sector(prev); - - bio_chain(prev, new); - bio_get(prev); /* for iomap_finish_ioend */ - submit_bio(prev); - return new; + wpc->nr_folios = 0; + return ioend; } -static bool -iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset, - sector_t sector) +static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos) { + if (wpc->iomap.offset == pos && (wpc->iomap.flags & IOMAP_F_BOUNDARY)) + return false; if ((wpc->iomap.flags & IOMAP_F_SHARED) != (wpc->ioend->io_flags & IOMAP_F_SHARED)) return false; if (wpc->iomap.type != wpc->ioend->io_type) return false; - if (offset != wpc->ioend->io_offset + wpc->ioend->io_size) + if (pos != wpc->ioend->io_offset + wpc->ioend->io_size) return false; - if (sector != bio_end_sector(wpc->ioend->io_bio)) + if (iomap_sector(&wpc->iomap, pos) != + bio_end_sector(&wpc->ioend->io_bio)) return false; /* * Limit ioend bio chain lengths to minimise IO completion latency. This * also prevents long tight loops ending page writeback on all the * folios in the ioend. */ - if (wpc->ioend->io_folios >= IOEND_BATCH_SIZE) + if (wpc->nr_folios >= IOEND_BATCH_SIZE) return false; return true; } @@ -1730,255 +1764,280 @@ iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset, /* * Test to see if we have an existing ioend structure that we could append to * first; otherwise finish off the current ioend and start another. + * + * If a new ioend is created and cached, the old ioend is submitted to the block + * layer instantly. Batching optimisations are provided by higher level block + * plugging. + * + * At the end of a writeback pass, there will be a cached ioend remaining on the + * writepage context that the caller will need to submit. */ -static void -iomap_add_to_ioend(struct inode *inode, loff_t pos, struct folio *folio, - struct iomap_folio_state *ifs, struct iomap_writepage_ctx *wpc, - struct writeback_control *wbc, struct list_head *iolist) +static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, + struct writeback_control *wbc, struct folio *folio, + struct inode *inode, loff_t pos, loff_t end_pos, + unsigned len) { - sector_t sector = iomap_sector(&wpc->iomap, pos); - unsigned len = i_blocksize(inode); + struct iomap_folio_state *ifs = folio->private; size_t poff = offset_in_folio(folio, pos); + int error; - 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, pos, sector, wbc); + if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos)) { +new_ioend: + error = iomap_submit_ioend(wpc, 0); + if (error) + return error; + wpc->ioend = iomap_alloc_ioend(wpc, wbc, inode, pos); } - if (!bio_add_folio(wpc->ioend->io_bio, folio, len, poff)) { - wpc->ioend->io_bio = iomap_chain_bio(wpc->ioend->io_bio); - bio_add_folio_nofail(wpc->ioend->io_bio, folio, len, poff); - } + if (!bio_add_folio(&wpc->ioend->io_bio, folio, len, poff)) + goto new_ioend; if (ifs) atomic_add(len, &ifs->write_bytes_pending); + + /* + * Clamp io_offset and io_size to the incore EOF so that ondisk + * file size updates in the ioend completion are byte-accurate. + * This avoids recovering files with zeroed tail regions when + * writeback races with appending writes: + * + * Thread 1: Thread 2: + * ------------ ----------- + * write [A, A+B] + * update inode size to A+B + * submit I/O [A, A+BS] + * write [A+B, A+B+C] + * update inode size to A+B+C + * <I/O completes, updates disk size to min(A+B+C, A+BS)> + * <power failure> + * + * After reboot: + * 1) with A+B+C < A+BS, the file has zero padding in range + * [A+B, A+B+C] + * + * |< Block Size (BS) >| + * |DDDDDDDDDDDD0000000000000| + * ^ ^ ^ + * A A+B A+B+C + * (EOF) + * + * 2) with A+B+C > A+BS, the file has zero padding in range + * [A+B, A+BS] + * + * |< Block Size (BS) >|< Block Size (BS) >| + * |DDDDDDDDDDDD0000000000000|00000000000000000000000000| + * ^ ^ ^ ^ + * A A+B A+BS A+B+C + * (EOF) + * + * D = Valid Data + * 0 = Zero Padding + * + * Note that this defeats the ability to chain the ioends of + * appending writes. + */ wpc->ioend->io_size += len; - wbc_account_cgroup_owner(wbc, &folio->page, len); + if (wpc->ioend->io_offset + wpc->ioend->io_size > end_pos) + wpc->ioend->io_size = end_pos - wpc->ioend->io_offset; + + wbc_account_cgroup_owner(wbc, folio, len); + return 0; } -/* - * We implement an immediate ioend submission policy here to avoid needing to - * chain multiple ioends and hence nest mempool allocations which can violate - * the forward progress guarantees we need to provide. The current ioend we're - * adding blocks to is cached in the writepage context, and if the new block - * doesn't append to the cached ioend, it will create a new ioend and cache that - * instead. - * - * If a new ioend is created and cached, the old ioend is returned and queued - * locally for submission once the entire page is processed or an error has been - * detected. While ioends are submitted immediately after they are completed, - * batching optimisations are provided by higher level block plugging. - * - * At the end of a writeback pass, there will be a cached ioend remaining on the - * writepage context that the caller will need to submit. - */ -static int -iomap_writepage_map(struct iomap_writepage_ctx *wpc, - struct writeback_control *wbc, struct inode *inode, - struct folio *folio, u64 end_pos) +static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, + struct writeback_control *wbc, struct folio *folio, + struct inode *inode, u64 pos, u64 end_pos, + unsigned dirty_len, unsigned *count) { - struct iomap_folio_state *ifs = folio->private; - struct iomap_ioend *ioend, *next; - unsigned len = i_blocksize(inode); - 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(end_pos <= pos); - - if (!ifs && nblocks > 1) { - ifs = ifs_alloc(inode, folio, 0); - iomap_set_range_dirty(folio, 0, end_pos - pos); - } - - WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) != 0); + int error; - /* - * 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; i < nblocks && pos < end_pos; i++, pos += len) { - if (ifs && !ifs_block_is_dirty(folio, ifs, i)) - continue; + do { + unsigned map_len; - error = wpc->ops->map_blocks(wpc, inode, pos); + error = wpc->ops->map_blocks(wpc, inode, pos, dirty_len); if (error) break; - trace_iomap_writepage_map(inode, &wpc->iomap); - if (WARN_ON_ONCE(wpc->iomap.type == IOMAP_INLINE)) - continue; - if (wpc->iomap.type == IOMAP_HOLE) - continue; - iomap_add_to_ioend(inode, pos, folio, ifs, wpc, wbc, - &submit_list); - count++; - } - if (count) - wpc->ioend->io_folios++; + trace_iomap_writepage_map(inode, pos, dirty_len, &wpc->iomap); - WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list)); - WARN_ON_ONCE(!folio_test_locked(folio)); - WARN_ON_ONCE(folio_test_writeback(folio)); - WARN_ON_ONCE(folio_test_dirty(folio)); + map_len = min_t(u64, dirty_len, + wpc->iomap.offset + wpc->iomap.length - pos); + WARN_ON_ONCE(!folio->private && map_len < dirty_len); + + switch (wpc->iomap.type) { + case IOMAP_INLINE: + WARN_ON_ONCE(1); + error = -EIO; + break; + case IOMAP_HOLE: + break; + default: + error = iomap_add_to_ioend(wpc, wbc, folio, inode, pos, + end_pos, map_len); + if (!error) + (*count)++; + break; + } + dirty_len -= map_len; + pos += map_len; + } while (dirty_len && !error); /* * We cannot cancel the ioend directly here on error. We may have * already set other pages under writeback and hence we have to run I/O * completion to mark the error state of the pages under writeback * appropriately. + * + * Just let the file system know what portion of the folio failed to + * map. */ - if (unlikely(error)) { - /* - * Let the filesystem know what portion of the current page - * failed to map. If the page hasn't been added to ioend, it - * won't be affected by I/O completion and we must unlock it - * now. - */ - if (wpc->ops->discard_folio) - wpc->ops->discard_folio(folio, pos); - if (!count) { - folio_unlock(folio); - goto done; - } - } - - /* - * We can have dirty bits set past end of file in page_mkwrite path - * while mapping the last partial folio. Hence it's better to clear - * all the dirty bits in the folio here. - */ - iomap_clear_range_dirty(folio, 0, folio_size(folio)); - folio_start_writeback(folio); - folio_unlock(folio); - - /* - * Preserve the original error if there was one; catch - * submission errors here and propagate into subsequent ioend - * submissions. - */ - list_for_each_entry_safe(ioend, next, &submit_list, io_list) { - int error2; - - list_del_init(&ioend->io_list); - error2 = iomap_submit_ioend(wpc, ioend, error); - if (error2 && !error) - error = error2; - } - - /* - * We can end up here with no error and nothing to write only if we race - * with a partial page truncate on a sub-page block sized filesystem. - */ - if (!count) - folio_end_writeback(folio); -done: - mapping_set_error(inode->i_mapping, error); + if (error && wpc->ops->discard_folio) + wpc->ops->discard_folio(folio, pos); return error; } /* - * Write out a dirty page. + * Check interaction of the folio with the file end. * - * For delalloc space on the page, we need to allocate space and flush it. - * For unwritten space on the page, we need to start the conversion to - * regular allocated space. + * If the folio is entirely beyond i_size, return false. If it straddles + * i_size, adjust end_pos and zero all data beyond i_size. */ -static int iomap_do_writepage(struct folio *folio, - struct writeback_control *wbc, void *data) +static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode, + u64 *end_pos) { - struct iomap_writepage_ctx *wpc = data; - struct inode *inode = folio->mapping->host; - u64 end_pos, isize; - - trace_iomap_writepage(inode, folio_pos(folio), folio_size(folio)); - - /* - * 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 - * allow reclaim from kswapd as the stack usage there is relatively low. - * - * This should never happen except in the case of a VM regression so - * warn about it. - */ - if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == - PF_MEMALLOC)) - goto redirty; + u64 isize = i_size_read(inode); - /* - * Is this folio beyond the end of the file? - * - * 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> | - * ----------------------------------------------------- - * | Page ... | Page N-2 | Page N-1 | Page N | | - * ^--------------------------------^----------|-------- - * | desired writeback range | see 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. - * ------------------------------------------------------- - * | file mapping | <EOF> | - * ------------------------------------------------------- - * | Page ... | Page N-2 | Page N-1 | Page N | Beyond | - * ^--------------------------------^-----------|--------- - * | | Straddles | - * ---------------------------------^-----------|--------| - */ + if (*end_pos > isize) { 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 truncate operation that's in progress. We've - * cleaned this page and truncate will finish things off for - * us. + * If the folio is entirely ouside of i_size, skip it. + * + * This can happen due to a truncate operation that is in + * progress and in that case truncate will finish it off once + * we've dropped the folio lock. * - * Note that the end_index is unsigned long. If the given - * offset is greater than 16TB on a 32-bit system then if we - * checked if the page is fully outside i_size with - * "if (page->index >= end_index + 1)", "end_index + 1" would - * overflow and evaluate to 0. Hence this page would be + * Note that the pgoff_t used for end_index is an unsigned long. + * If the given offset is greater than 16TB on a 32-bit system, + * then if we checked if the folio is fully outside i_size with + * "if (folio->index >= end_index + 1)", "end_index + 1" would + * overflow and evaluate to 0. Hence this folio would be * redirtied and written out repeatedly, which would result in * an infinite loop; the user program performing this operation * would hang. Instead, we can detect this situation by - * checking if the page is totally beyond i_size or if its + * checking if the folio is totally beyond i_size or if its * offset is just equal to the EOF. */ if (folio->index > end_index || (folio->index == end_index && poff == 0)) - goto unlock; + return false; /* - * The page straddles i_size. It must be zeroed out on each - * and every writepage invocation because it may be mmapped. - * "A file is mapped in multiples of the page size. For a file - * that is not a multiple of the page size, the remaining - * memory is zeroed when mapped, and writes to that region are - * not written out to the file." + * The folio straddles i_size. + * + * It must be zeroed out on each and every writepage invocation + * because it may be mmapped: + * + * A file is mapped in multiples of the page size. For a + * file that is not a multiple of the page size, the + * remaining memory is zeroed when mapped, and writes to that + * region are not written out to the file. + * + * Also adjust the end_pos to the end of file and skip writeback + * for all blocks entirely beyond i_size. */ folio_zero_segment(folio, poff, folio_size(folio)); - end_pos = isize; + *end_pos = isize; } - return iomap_writepage_map(wpc, wbc, inode, folio, end_pos); + return true; +} + +static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, + struct writeback_control *wbc, struct folio *folio) +{ + struct iomap_folio_state *ifs = folio->private; + struct inode *inode = folio->mapping->host; + u64 pos = folio_pos(folio); + u64 end_pos = pos + folio_size(folio); + u64 end_aligned = 0; + unsigned count = 0; + int error = 0; + u32 rlen; + + WARN_ON_ONCE(!folio_test_locked(folio)); + WARN_ON_ONCE(folio_test_dirty(folio)); + WARN_ON_ONCE(folio_test_writeback(folio)); + + trace_iomap_writepage(inode, pos, folio_size(folio)); -redirty: - folio_redirty_for_writepage(wbc, folio); -unlock: + if (!iomap_writepage_handle_eof(folio, inode, &end_pos)) { + folio_unlock(folio); + return 0; + } + WARN_ON_ONCE(end_pos <= pos); + + if (i_blocks_per_folio(inode, folio) > 1) { + if (!ifs) { + ifs = ifs_alloc(inode, folio, 0); + iomap_set_range_dirty(folio, 0, end_pos - pos); + } + + /* + * Keep the I/O completion handler from clearing the writeback + * bit until we have submitted all blocks by adding a bias to + * ifs->write_bytes_pending, which is dropped after submitting + * all blocks. + */ + WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending) != 0); + atomic_inc(&ifs->write_bytes_pending); + } + + /* + * Set the writeback bit ASAP, as the I/O completion for the single + * block per folio case happen hit as soon as we're submitting the bio. + */ + folio_start_writeback(folio); + + /* + * Walk through the folio to find dirty areas to write back. + */ + end_aligned = round_up(end_pos, i_blocksize(inode)); + while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) { + error = iomap_writepage_map_blocks(wpc, wbc, folio, inode, + pos, end_pos, rlen, &count); + if (error) + break; + pos += rlen; + } + + if (count) + wpc->nr_folios++; + + /* + * We can have dirty bits set past end of file in page_mkwrite path + * while mapping the last partial folio. Hence it's better to clear + * all the dirty bits in the folio here. + */ + iomap_clear_range_dirty(folio, 0, folio_size(folio)); + + /* + * Usually the writeback bit is cleared by the I/O completion handler. + * But we may end up either not actually writing any blocks, or (when + * there are multiple blocks in a folio) all I/O might have finished + * already at this point. In that case we need to clear the writeback + * bit ourselves right after unlocking the page. + */ folio_unlock(folio); - return 0; + if (ifs) { + if (atomic_dec_and_test(&ifs->write_bytes_pending)) + folio_end_writeback(folio); + } else { + if (!count) + folio_end_writeback(folio); + } + mapping_set_error(inode->i_mapping, error); + return error; } int @@ -1986,20 +2045,28 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc, struct iomap_writepage_ctx *wpc, const struct iomap_writeback_ops *ops) { - int ret; + struct folio *folio = NULL; + int error; + + /* + * Writeback from reclaim context should never happen except in the case + * of a VM regression so warn about it and refuse to write the data. + */ + if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC | PF_KSWAPD)) == + PF_MEMALLOC)) + return -EIO; wpc->ops = ops; - ret = write_cache_pages(mapping, wbc, iomap_do_writepage, wpc); - if (!wpc->ioend) - return ret; - return iomap_submit_ioend(wpc, wpc->ioend, ret); + while ((folio = writeback_iter(mapping, wbc, folio, &error))) + error = iomap_writepage_map(wpc, wbc, folio); + return iomap_submit_ioend(wpc, error); } 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_inline_bio), + offsetof(struct iomap_ioend, io_bio), BIOSET_NEED_BVECS); } -fs_initcall(iomap_init); +fs_initcall(iomap_buffered_init); |