diff options
Diffstat (limited to 'fs/iomap')
| -rw-r--r-- | fs/iomap/Makefile | 6 | ||||
| -rw-r--r-- | fs/iomap/buffered-io.c | 559 | ||||
| -rw-r--r-- | fs/iomap/direct-io.c | 5 | ||||
| -rw-r--r-- | fs/iomap/fiemap.c | 3 | ||||
| -rw-r--r-- | fs/iomap/internal.h | 1 | ||||
| -rw-r--r-- | fs/iomap/ioend.c | 220 | ||||
| -rw-r--r-- | fs/iomap/iter.c | 1 | ||||
| -rw-r--r-- | fs/iomap/seek.c | 4 | ||||
| -rw-r--r-- | fs/iomap/swapfile.c | 3 | ||||
| -rw-r--r-- | fs/iomap/trace.c | 1 | ||||
| -rw-r--r-- | fs/iomap/trace.h | 4 |
11 files changed, 403 insertions, 404 deletions
diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile index 69e8ebb41302..f7e1c8534c46 100644 --- a/fs/iomap/Makefile +++ b/fs/iomap/Makefile @@ -9,9 +9,9 @@ ccflags-y += -I $(src) # needed for trace events obj-$(CONFIG_FS_IOMAP) += iomap.o iomap-y += trace.o \ - iter.o -iomap-$(CONFIG_BLOCK) += buffered-io.o \ - direct-io.o \ + iter.o \ + buffered-io.o +iomap-$(CONFIG_BLOCK) += direct-io.o \ ioend.o \ fiemap.o \ seek.o diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 3729391a18f3..fd827398afd2 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -3,20 +3,11 @@ * Copyright (C) 2010 Red Hat, Inc. * Copyright (C) 2016-2023 Christoph Hellwig. */ -#include <linux/module.h> -#include <linux/compiler.h> -#include <linux/fs.h> #include <linux/iomap.h> -#include <linux/pagemap.h> -#include <linux/uio.h> #include <linux/buffer_head.h> -#include <linux/dax.h> #include <linux/writeback.h> #include <linux/swap.h> -#include <linux/bio.h> -#include <linux/sched/signal.h> #include <linux/migrate.h> -#include "internal.h" #include "trace.h" #include "../internal.h" @@ -71,6 +62,9 @@ static void iomap_set_range_uptodate(struct folio *folio, size_t off, unsigned long flags; bool uptodate = true; + if (folio_test_uptodate(folio)) + return; + if (ifs) { spin_lock_irqsave(&ifs->state_lock, flags); uptodate = ifs_set_range_uptodate(folio, ifs, off, len); @@ -284,6 +278,46 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, *lenp = plen; } +static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter, + loff_t pos) +{ + const struct iomap *srcmap = iomap_iter_srcmap(iter); + + return srcmap->type != IOMAP_MAPPED || + (srcmap->flags & IOMAP_F_NEW) || + pos >= i_size_read(iter->inode); +} + +/** + * iomap_read_inline_data - copy inline data into the page cache + * @iter: iteration structure + * @folio: folio to copy to + * + * 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 folio *folio) +{ + const struct iomap *iomap = iomap_iter_srcmap(iter); + size_t size = i_size_read(iter->inode) - iomap->offset; + size_t offset = offset_in_folio(folio, iomap->offset); + + if (folio_test_uptodate(folio)) + return 0; + + if (WARN_ON_ONCE(size > iomap->length)) + return -EIO; + if (offset > 0) + ifs_alloc(iter->inode, folio, iter->flags); + + folio_fill_tail(folio, offset, iomap->inline_data, size); + iomap_set_range_uptodate(folio, offset, folio_size(folio) - offset); + return 0; +} + +#ifdef CONFIG_BLOCK static void iomap_finish_folio_read(struct folio *folio, size_t off, size_t len, int error) { @@ -323,45 +357,6 @@ struct iomap_readpage_ctx { struct readahead_control *rac; }; -/** - * iomap_read_inline_data - copy inline data into the page cache - * @iter: iteration structure - * @folio: folio to copy to - * - * 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 folio *folio) -{ - const struct iomap *iomap = iomap_iter_srcmap(iter); - size_t size = i_size_read(iter->inode) - iomap->offset; - size_t offset = offset_in_folio(folio, iomap->offset); - - if (folio_test_uptodate(folio)) - return 0; - - if (WARN_ON_ONCE(size > iomap->length)) - return -EIO; - if (offset > 0) - ifs_alloc(iter->inode, folio, iter->flags); - - folio_fill_tail(folio, offset, iomap->inline_data, size); - iomap_set_range_uptodate(folio, offset, folio_size(folio) - offset); - return 0; -} - -static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter, - loff_t pos) -{ - const struct iomap *srcmap = iomap_iter_srcmap(iter); - - return srcmap->type != IOMAP_MAPPED || - (srcmap->flags & IOMAP_F_NEW) || - pos >= i_size_read(iter->inode); -} - static int iomap_readpage_iter(struct iomap_iter *iter, struct iomap_readpage_ctx *ctx) { @@ -554,6 +549,27 @@ void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops) } EXPORT_SYMBOL_GPL(iomap_readahead); +static int iomap_read_folio_range(const struct iomap_iter *iter, + struct folio *folio, loff_t pos, size_t len) +{ + const struct iomap *srcmap = iomap_iter_srcmap(iter); + struct bio_vec bvec; + struct bio bio; + + bio_init(&bio, srcmap->bdev, &bvec, 1, REQ_OP_READ); + bio.bi_iter.bi_sector = iomap_sector(srcmap, pos); + bio_add_folio_nofail(&bio, folio, len, offset_in_folio(folio, pos)); + return submit_bio_wait(&bio); +} +#else +static int iomap_read_folio_range(const struct iomap_iter *iter, + struct folio *folio, loff_t pos, size_t len) +{ + WARN_ON_ONCE(1); + return -EIO; +} +#endif /* CONFIG_BLOCK */ + /* * iomap_is_partially_uptodate checks whether blocks within a folio are * uptodate or not. @@ -667,22 +683,10 @@ iomap_write_failed(struct inode *inode, loff_t pos, unsigned len) pos + len - 1); } -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; - - bio_init(&bio, iomap->bdev, &bvec, 1, REQ_OP_READ); - bio.bi_iter.bi_sector = iomap_sector(iomap, block_start); - bio_add_folio_nofail(&bio, folio, plen, poff); - return submit_bio_wait(&bio); -} - -static int __iomap_write_begin(const struct iomap_iter *iter, size_t len, +static int __iomap_write_begin(const struct iomap_iter *iter, + const struct iomap_write_ops *write_ops, size_t len, struct folio *folio) { - const struct iomap *srcmap = iomap_iter_srcmap(iter); struct iomap_folio_state *ifs; loff_t pos = iter->pos; loff_t block_size = i_blocksize(iter->inode); @@ -731,8 +735,12 @@ static int __iomap_write_begin(const struct iomap_iter *iter, size_t len, if (iter->flags & IOMAP_NOWAIT) return -EAGAIN; - status = iomap_read_folio_sync(block_start, folio, - poff, plen, srcmap); + if (write_ops && write_ops->read_folio_range) + status = write_ops->read_folio_range(iter, + folio, block_start, plen); + else + status = iomap_read_folio_range(iter, + folio, block_start, plen); if (status) return status; } @@ -742,28 +750,27 @@ static int __iomap_write_begin(const struct iomap_iter *iter, size_t len, return 0; } -static struct folio *__iomap_get_folio(struct iomap_iter *iter, size_t len) +static struct folio *__iomap_get_folio(struct iomap_iter *iter, + const struct iomap_write_ops *write_ops, size_t len) { - const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops; loff_t pos = iter->pos; if (!mapping_large_folio_support(iter->inode->i_mapping)) len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos)); - if (folio_ops && folio_ops->get_folio) - return folio_ops->get_folio(iter, pos, len); - else - return iomap_get_folio(iter, pos, len); + if (write_ops && write_ops->get_folio) + return write_ops->get_folio(iter, pos, len); + return iomap_get_folio(iter, pos, len); } -static void __iomap_put_folio(struct iomap_iter *iter, size_t ret, +static void __iomap_put_folio(struct iomap_iter *iter, + const struct iomap_write_ops *write_ops, size_t ret, struct folio *folio) { - const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops; loff_t pos = iter->pos; - if (folio_ops && folio_ops->put_folio) { - folio_ops->put_folio(iter->inode, pos, ret, folio); + if (write_ops && write_ops->put_folio) { + write_ops->put_folio(iter->inode, pos, ret, folio); } else { folio_unlock(folio); folio_put(folio); @@ -800,10 +807,10 @@ static int iomap_write_begin_inline(const struct iomap_iter *iter, * offset, and length. Callers can optionally pass a max length *plen, * otherwise init to zero. */ -static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop, +static int iomap_write_begin(struct iomap_iter *iter, + const struct iomap_write_ops *write_ops, struct folio **foliop, size_t *poffset, u64 *plen) { - const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops; const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; u64 len = min_t(u64, SIZE_MAX, iomap_length(iter)); @@ -818,7 +825,7 @@ static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop, if (fatal_signal_pending(current)) return -EINTR; - folio = __iomap_get_folio(iter, len); + folio = __iomap_get_folio(iter, write_ops, len); if (IS_ERR(folio)) return PTR_ERR(folio); @@ -832,8 +839,8 @@ static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop, * could do the wrong thing here (zero a page range incorrectly or fail * to zero) and corrupt data. */ - if (folio_ops && folio_ops->iomap_valid) { - bool iomap_valid = folio_ops->iomap_valid(iter->inode, + if (write_ops && write_ops->iomap_valid) { + bool iomap_valid = write_ops->iomap_valid(iter->inode, &iter->iomap); if (!iomap_valid) { iter->iomap.flags |= IOMAP_F_STALE; @@ -849,7 +856,7 @@ static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop, else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) status = __block_write_begin_int(folio, pos, len, NULL, srcmap); else - status = __iomap_write_begin(iter, len, folio); + status = __iomap_write_begin(iter, write_ops, len, folio); if (unlikely(status)) goto out_unlock; @@ -859,8 +866,7 @@ static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop, return 0; out_unlock: - __iomap_put_folio(iter, 0, folio); - + __iomap_put_folio(iter, write_ops, 0, folio); return status; } @@ -923,8 +929,7 @@ static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied, 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); + bh_written = block_write_end(pos, len, copied, folio); WARN_ON_ONCE(bh_written != copied && bh_written != 0); return bh_written == copied; } @@ -932,7 +937,8 @@ static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied, return __iomap_write_end(iter->inode, pos, len, copied, folio); } -static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) +static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i, + const struct iomap_write_ops *write_ops) { ssize_t total_written = 0; int status = 0; @@ -976,7 +982,8 @@ retry: break; } - status = iomap_write_begin(iter, &folio, &offset, &bytes); + status = iomap_write_begin(iter, write_ops, &folio, &offset, + &bytes); if (unlikely(status)) { iomap_write_failed(iter->inode, iter->pos, bytes); break; @@ -1005,7 +1012,7 @@ retry: i_size_write(iter->inode, pos + written); iter->iomap.flags |= IOMAP_F_SIZE_CHANGED; } - __iomap_put_folio(iter, written, folio); + __iomap_put_folio(iter, write_ops, written, folio); if (old_size < pos) pagecache_isize_extended(iter->inode, old_size, pos); @@ -1038,7 +1045,8 @@ retry: ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i, - const struct iomap_ops *ops, void *private) + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops, void *private) { struct iomap_iter iter = { .inode = iocb->ki_filp->f_mapping->host, @@ -1055,7 +1063,7 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i, iter.flags |= IOMAP_DONTCACHE; while ((ret = iomap_iter(&iter, ops)) > 0) - iter.status = iomap_write_iter(&iter, i); + iter.status = iomap_write_iter(&iter, i, write_ops); if (unlikely(iter.pos == iocb->ki_pos)) return ret; @@ -1289,7 +1297,8 @@ void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, } EXPORT_SYMBOL_GPL(iomap_write_delalloc_release); -static int iomap_unshare_iter(struct iomap_iter *iter) +static int iomap_unshare_iter(struct iomap_iter *iter, + const struct iomap_write_ops *write_ops) { struct iomap *iomap = &iter->iomap; u64 bytes = iomap_length(iter); @@ -1304,14 +1313,15 @@ static int iomap_unshare_iter(struct iomap_iter *iter) bool ret; bytes = min_t(u64, SIZE_MAX, bytes); - status = iomap_write_begin(iter, &folio, &offset, &bytes); + status = iomap_write_begin(iter, write_ops, &folio, &offset, + &bytes); if (unlikely(status)) return status; if (iomap->flags & IOMAP_F_STALE) break; ret = iomap_write_end(iter, bytes, bytes, folio); - __iomap_put_folio(iter, bytes, folio); + __iomap_put_folio(iter, write_ops, bytes, folio); if (WARN_ON_ONCE(!ret)) return -EIO; @@ -1329,7 +1339,8 @@ static int iomap_unshare_iter(struct iomap_iter *iter) int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, - const struct iomap_ops *ops) + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops) { struct iomap_iter iter = { .inode = inode, @@ -1344,7 +1355,7 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, iter.len = min(len, size - pos); while ((ret = iomap_iter(&iter, ops)) > 0) - iter.status = iomap_unshare_iter(&iter); + iter.status = iomap_unshare_iter(&iter, write_ops); return ret; } EXPORT_SYMBOL_GPL(iomap_file_unshare); @@ -1363,7 +1374,8 @@ static inline int iomap_zero_iter_flush_and_stale(struct iomap_iter *i) return filemap_write_and_wait_range(mapping, i->pos, end); } -static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) +static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero, + const struct iomap_write_ops *write_ops) { u64 bytes = iomap_length(iter); int status; @@ -1374,7 +1386,8 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) bool ret; bytes = min_t(u64, SIZE_MAX, bytes); - status = iomap_write_begin(iter, &folio, &offset, &bytes); + status = iomap_write_begin(iter, write_ops, &folio, &offset, + &bytes); if (status) return status; if (iter->iomap.flags & IOMAP_F_STALE) @@ -1387,7 +1400,7 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) folio_mark_accessed(folio); ret = iomap_write_end(iter, bytes, bytes, folio); - __iomap_put_folio(iter, bytes, folio); + __iomap_put_folio(iter, write_ops, bytes, folio); if (WARN_ON_ONCE(!ret)) return -EIO; @@ -1403,7 +1416,8 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, - const struct iomap_ops *ops, void *private) + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops, void *private) { struct iomap_iter iter = { .inode = inode, @@ -1433,7 +1447,8 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, filemap_range_needs_writeback(mapping, pos, pos + plen - 1)) { iter.len = plen; while ((ret = iomap_iter(&iter, ops)) > 0) - iter.status = iomap_zero_iter(&iter, did_zero); + iter.status = iomap_zero_iter(&iter, did_zero, + write_ops); iter.len = len - (iter.pos - pos); if (ret || !iter.len) @@ -1464,7 +1479,7 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, continue; } - iter.status = iomap_zero_iter(&iter, did_zero); + iter.status = iomap_zero_iter(&iter, did_zero, write_ops); } return ret; } @@ -1472,7 +1487,8 @@ EXPORT_SYMBOL_GPL(iomap_zero_range); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, - const struct iomap_ops *ops, void *private) + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops, void *private) { unsigned int blocksize = i_blocksize(inode); unsigned int off = pos & (blocksize - 1); @@ -1481,7 +1497,7 @@ iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, if (!off) return 0; return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops, - private); + write_ops, private); } EXPORT_SYMBOL_GPL(iomap_truncate_page); @@ -1535,280 +1551,54 @@ out_unlock: } EXPORT_SYMBOL_GPL(iomap_page_mkwrite); -static void iomap_finish_folio_write(struct inode *inode, struct folio *folio, +void iomap_start_folio_write(struct inode *inode, struct folio *folio, size_t len) { struct iomap_folio_state *ifs = folio->private; WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !ifs); - WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) <= 0); - - if (!ifs || atomic_sub_and_test(len, &ifs->write_bytes_pending)) - folio_end_writeback(folio); -} - -/* - * We're now finished for good with this ioend structure. Update the page - * state, release holds on bios, and finally free up memory. Do not use the - * ioend after this. - */ -u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend) -{ - struct inode *inode = ioend->io_inode; - struct bio *bio = &ioend->io_bio; - struct folio_iter fi; - u32 folio_count = 0; - - if (ioend->io_error) { - mapping_set_error(inode->i_mapping, ioend->io_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); - } - } - - /* 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; -} - -static void iomap_writepage_end_bio(struct bio *bio) -{ - struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); - - ioend->io_error = blk_status_to_errno(bio->bi_status); - iomap_finish_ioend_buffered(ioend); -} - -/* - * Submit 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. - * 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, int error) -{ - 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->submit_ioend) { - error = wpc->ops->submit_ioend(wpc, error); - } else { - if (WARN_ON_ONCE(wpc->iomap.flags & IOMAP_F_ANON_WRITE)) - error = -EIO; - if (!error) - submit_bio(&wpc->ioend->io_bio); - } - - if (error) { - wpc->ioend->io_bio.bi_status = errno_to_blk_status(error); - bio_endio(&wpc->ioend->io_bio); - } - - wpc->ioend = NULL; - return error; -} - -static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc, - struct writeback_control *wbc, struct inode *inode, loff_t pos, - u16 ioend_flags) -{ - struct bio *bio; - - 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 = iomap_sector(&wpc->iomap, pos); - bio->bi_end_io = iomap_writepage_end_bio; - bio->bi_write_hint = inode->i_write_hint; - wbc_init_bio(wbc, bio); - wpc->nr_folios = 0; - return iomap_init_ioend(inode, bio, pos, ioend_flags); -} - -static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos, - u16 ioend_flags) -{ - if (ioend_flags & IOMAP_IOEND_BOUNDARY) - return false; - if ((ioend_flags & IOMAP_IOEND_NOMERGE_FLAGS) != - (wpc->ioend->io_flags & IOMAP_IOEND_NOMERGE_FLAGS)) - return false; - if (pos != wpc->ioend->io_offset + wpc->ioend->io_size) - return false; - if (!(wpc->iomap.flags & IOMAP_F_ANON_WRITE) && - 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->nr_folios >= IOEND_BATCH_SIZE) - return false; - return true; + if (ifs) + atomic_add(len, &ifs->write_bytes_pending); } +EXPORT_SYMBOL_GPL(iomap_start_folio_write); -/* - * 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 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) +void iomap_finish_folio_write(struct inode *inode, struct folio *folio, + size_t len) { struct iomap_folio_state *ifs = folio->private; - size_t poff = offset_in_folio(folio, pos); - unsigned int ioend_flags = 0; - int error; - if (wpc->iomap.type == IOMAP_UNWRITTEN) - ioend_flags |= IOMAP_IOEND_UNWRITTEN; - if (wpc->iomap.flags & IOMAP_F_SHARED) - ioend_flags |= IOMAP_IOEND_SHARED; - if (folio_test_dropbehind(folio)) - ioend_flags |= IOMAP_IOEND_DONTCACHE; - if (pos == wpc->iomap.offset && (wpc->iomap.flags & IOMAP_F_BOUNDARY)) - ioend_flags |= IOMAP_IOEND_BOUNDARY; - - if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos, ioend_flags)) { -new_ioend: - error = iomap_submit_ioend(wpc, 0); - if (error) - return error; - wpc->ioend = iomap_alloc_ioend(wpc, wbc, inode, pos, - ioend_flags); - } - - 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; - if (wpc->ioend->io_offset + wpc->ioend->io_size > end_pos) - wpc->ioend->io_size = end_pos - wpc->ioend->io_offset; + WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !ifs); + WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) <= 0); - wbc_account_cgroup_owner(wbc, folio, len); - return 0; + if (!ifs || atomic_sub_and_test(len, &ifs->write_bytes_pending)) + folio_end_writeback(folio); } +EXPORT_SYMBOL_GPL(iomap_finish_folio_write); -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) +static int iomap_writeback_range(struct iomap_writepage_ctx *wpc, + struct folio *folio, u64 pos, u32 rlen, u64 end_pos, + bool *wb_pending) { - int error; - do { - unsigned map_len; - - error = wpc->ops->map_blocks(wpc, inode, pos, dirty_len); - if (error) - break; - trace_iomap_writepage_map(inode, pos, dirty_len, &wpc->iomap); + ssize_t ret; - map_len = min_t(u64, dirty_len, - wpc->iomap.offset + wpc->iomap.length - pos); - WARN_ON_ONCE(!folio->private && map_len < dirty_len); + ret = wpc->ops->writeback_range(wpc, folio, pos, rlen, end_pos); + if (WARN_ON_ONCE(ret == 0 || ret > rlen)) + return -EIO; + if (ret < 0) + return ret; + rlen -= ret; + pos += ret; - 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); + /* + * Holes are not be written back by ->writeback_range, so track + * if we did handle anything that is not a hole here. + */ + if (wpc->iomap.type != IOMAP_HOLE) + *wb_pending = true; + } while (rlen); - /* - * 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 (error && wpc->ops->discard_folio) - wpc->ops->discard_folio(folio, pos); - return error; + return 0; } /* @@ -1817,7 +1607,7 @@ static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, * 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 bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode, +static bool iomap_writeback_handle_eof(struct folio *folio, struct inode *inode, u64 *end_pos) { u64 isize = i_size_read(inode); @@ -1869,15 +1659,14 @@ static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode, return true; } -static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, - struct writeback_control *wbc, struct folio *folio) +int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio) { struct iomap_folio_state *ifs = folio->private; - struct inode *inode = folio->mapping->host; + struct inode *inode = wpc->inode; u64 pos = folio_pos(folio); u64 end_pos = pos + folio_size(folio); u64 end_aligned = 0; - unsigned count = 0; + bool wb_pending = false; int error = 0; u32 rlen; @@ -1885,12 +1674,10 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, WARN_ON_ONCE(folio_test_dirty(folio)); WARN_ON_ONCE(folio_test_writeback(folio)); - trace_iomap_writepage(inode, pos, folio_size(folio)); + trace_iomap_writeback_folio(inode, pos, folio_size(folio)); - if (!iomap_writepage_handle_eof(folio, inode, &end_pos)) { - folio_unlock(folio); + if (!iomap_writeback_handle_eof(folio, inode, &end_pos)) return 0; - } WARN_ON_ONCE(end_pos <= pos); if (i_blocks_per_folio(inode, folio) > 1) { @@ -1906,7 +1693,7 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, * all blocks. */ WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending) != 0); - atomic_inc(&ifs->write_bytes_pending); + iomap_start_folio_write(inode, folio, 1); } /* @@ -1920,14 +1707,14 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, */ 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); + error = iomap_writeback_range(wpc, folio, pos, rlen, end_pos, + &wb_pending); if (error) break; pos += rlen; } - if (count) + if (wb_pending) wpc->nr_folios++; /* @@ -1944,23 +1731,22 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, * already at this point. In that case we need to clear the writeback * bit ourselves right after unlocking the page. */ - folio_unlock(folio); if (ifs) { if (atomic_dec_and_test(&ifs->write_bytes_pending)) folio_end_writeback(folio); } else { - if (!count) + if (!wb_pending) folio_end_writeback(folio); } mapping_set_error(inode->i_mapping, error); return error; } +EXPORT_SYMBOL_GPL(iomap_writeback_folio); int -iomap_writepages(struct address_space *mapping, struct writeback_control *wbc, - struct iomap_writepage_ctx *wpc, - const struct iomap_writeback_ops *ops) +iomap_writepages(struct iomap_writepage_ctx *wpc) { + struct address_space *mapping = wpc->inode->i_mapping; struct folio *folio = NULL; int error; @@ -1972,9 +1758,22 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc, PF_MEMALLOC)) return -EIO; - wpc->ops = ops; - while ((folio = writeback_iter(mapping, wbc, folio, &error))) - error = iomap_writepage_map(wpc, wbc, folio); - return iomap_submit_ioend(wpc, error); + while ((folio = writeback_iter(mapping, wpc->wbc, folio, &error))) { + error = iomap_writeback_folio(wpc, folio); + folio_unlock(folio); + } + + /* + * 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. + * + * We cannot cancel the writeback directly in that case, so always call + * ->writeback_submit to run the I/O completion handler to clear the + * writeback bit and let the file system proess the errors. + */ + if (wpc->wb_ctx) + return wpc->ops->writeback_submit(wpc, error); + return error; } EXPORT_SYMBOL_GPL(iomap_writepages); diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 844261a31156..6f25d4cfea9f 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -3,14 +3,9 @@ * Copyright (C) 2010 Red Hat, Inc. * Copyright (c) 2016-2025 Christoph Hellwig. */ -#include <linux/module.h> -#include <linux/compiler.h> -#include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/pagemap.h> #include <linux/iomap.h> -#include <linux/backing-dev.h> -#include <linux/uio.h> #include <linux/task_io_accounting_ops.h> #include "internal.h" #include "trace.h" diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c index 80675c42e94e..d11dadff8286 100644 --- a/fs/iomap/fiemap.c +++ b/fs/iomap/fiemap.c @@ -2,9 +2,6 @@ /* * Copyright (c) 2016-2021 Christoph Hellwig. */ -#include <linux/module.h> -#include <linux/compiler.h> -#include <linux/fs.h> #include <linux/iomap.h> #include <linux/fiemap.h> #include <linux/pagemap.h> diff --git a/fs/iomap/internal.h b/fs/iomap/internal.h index f6992a3bf66a..d05cb3aed96e 100644 --- a/fs/iomap/internal.h +++ b/fs/iomap/internal.h @@ -4,7 +4,6 @@ #define IOEND_BATCH_SIZE 4096 -u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend); u32 iomap_finish_ioend_direct(struct iomap_ioend *ioend); #endif /* _IOMAP_INTERNAL_H */ diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c index 18894ebba6db..b49fa75eab26 100644 --- a/fs/iomap/ioend.c +++ b/fs/iomap/ioend.c @@ -1,10 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright (c) 2024-2025 Christoph Hellwig. + * Copyright (c) 2016-2025 Christoph Hellwig. */ #include <linux/iomap.h> #include <linux/list_sort.h> +#include <linux/pagemap.h> +#include <linux/writeback.h> #include "internal.h" +#include "trace.h" struct bio_set iomap_ioend_bioset; EXPORT_SYMBOL_GPL(iomap_ioend_bioset); @@ -28,6 +31,221 @@ struct iomap_ioend *iomap_init_ioend(struct inode *inode, } EXPORT_SYMBOL_GPL(iomap_init_ioend); +/* + * We're now finished for good with this ioend structure. Update the folio + * state, release holds on bios, and finally free up memory. Do not use the + * ioend after this. + */ +static u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend) +{ + struct inode *inode = ioend->io_inode; + struct bio *bio = &ioend->io_bio; + struct folio_iter fi; + u32 folio_count = 0; + + if (ioend->io_error) { + mapping_set_error(inode->i_mapping, ioend->io_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); + } + } + + /* 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; +} + +static void ioend_writeback_end_bio(struct bio *bio) +{ + struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); + + ioend->io_error = blk_status_to_errno(bio->bi_status); + iomap_finish_ioend_buffered(ioend); +} + +/* + * We cannot cancel the ioend directly in case of an error, so call the bio end + * I/O handler with the error status here to run the normal I/O completion + * handler. + */ +int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error) +{ + struct iomap_ioend *ioend = wpc->wb_ctx; + + if (!ioend->io_bio.bi_end_io) + ioend->io_bio.bi_end_io = ioend_writeback_end_bio; + + if (WARN_ON_ONCE(wpc->iomap.flags & IOMAP_F_ANON_WRITE)) + error = -EIO; + + if (error) { + ioend->io_bio.bi_status = errno_to_blk_status(error); + bio_endio(&ioend->io_bio); + return error; + } + + submit_bio(&ioend->io_bio); + return 0; +} +EXPORT_SYMBOL_GPL(iomap_ioend_writeback_submit); + +static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc, + loff_t pos, u16 ioend_flags) +{ + struct bio *bio; + + bio = bio_alloc_bioset(wpc->iomap.bdev, BIO_MAX_VECS, + REQ_OP_WRITE | wbc_to_write_flags(wpc->wbc), + GFP_NOFS, &iomap_ioend_bioset); + bio->bi_iter.bi_sector = iomap_sector(&wpc->iomap, pos); + bio->bi_write_hint = wpc->inode->i_write_hint; + wbc_init_bio(wpc->wbc, bio); + wpc->nr_folios = 0; + return iomap_init_ioend(wpc->inode, bio, pos, ioend_flags); +} + +static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos, + u16 ioend_flags) +{ + struct iomap_ioend *ioend = wpc->wb_ctx; + + if (ioend_flags & IOMAP_IOEND_BOUNDARY) + return false; + if ((ioend_flags & IOMAP_IOEND_NOMERGE_FLAGS) != + (ioend->io_flags & IOMAP_IOEND_NOMERGE_FLAGS)) + return false; + if (pos != ioend->io_offset + ioend->io_size) + return false; + if (!(wpc->iomap.flags & IOMAP_F_ANON_WRITE) && + iomap_sector(&wpc->iomap, pos) != bio_end_sector(&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->nr_folios >= IOEND_BATCH_SIZE) + return false; + return true; +} + +/* + * 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. + */ +ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio, + loff_t pos, loff_t end_pos, unsigned int dirty_len) +{ + struct iomap_ioend *ioend = wpc->wb_ctx; + size_t poff = offset_in_folio(folio, pos); + unsigned int ioend_flags = 0; + unsigned int map_len = min_t(u64, dirty_len, + wpc->iomap.offset + wpc->iomap.length - pos); + int error; + + trace_iomap_add_to_ioend(wpc->inode, pos, dirty_len, &wpc->iomap); + + WARN_ON_ONCE(!folio->private && map_len < dirty_len); + + switch (wpc->iomap.type) { + case IOMAP_INLINE: + WARN_ON_ONCE(1); + return -EIO; + case IOMAP_HOLE: + return map_len; + default: + break; + } + + if (wpc->iomap.type == IOMAP_UNWRITTEN) + ioend_flags |= IOMAP_IOEND_UNWRITTEN; + if (wpc->iomap.flags & IOMAP_F_SHARED) + ioend_flags |= IOMAP_IOEND_SHARED; + if (folio_test_dropbehind(folio)) + ioend_flags |= IOMAP_IOEND_DONTCACHE; + if (pos == wpc->iomap.offset && (wpc->iomap.flags & IOMAP_F_BOUNDARY)) + ioend_flags |= IOMAP_IOEND_BOUNDARY; + + if (!ioend || !iomap_can_add_to_ioend(wpc, pos, ioend_flags)) { +new_ioend: + if (ioend) { + error = wpc->ops->writeback_submit(wpc, 0); + if (error) + return error; + } + wpc->wb_ctx = ioend = iomap_alloc_ioend(wpc, pos, ioend_flags); + } + + if (!bio_add_folio(&ioend->io_bio, folio, map_len, poff)) + goto new_ioend; + + iomap_start_folio_write(wpc->inode, folio, map_len); + + /* + * 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. + */ + ioend->io_size += map_len; + if (ioend->io_offset + ioend->io_size > end_pos) + ioend->io_size = end_pos - ioend->io_offset; + + wbc_account_cgroup_owner(wpc->wbc, folio, map_len); + return map_len; +} +EXPORT_SYMBOL_GPL(iomap_add_to_ioend); + static u32 iomap_finish_ioend(struct iomap_ioend *ioend, int error) { if (ioend->io_parent) { diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c index 6ffc6a7b9ba5..cef77ca0c20b 100644 --- a/fs/iomap/iter.c +++ b/fs/iomap/iter.c @@ -3,7 +3,6 @@ * Copyright (C) 2010 Red Hat, Inc. * Copyright (c) 2016-2021 Christoph Hellwig. */ -#include <linux/fs.h> #include <linux/iomap.h> #include "trace.h" diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c index 04d7919636c1..56db2dd4b10d 100644 --- a/fs/iomap/seek.c +++ b/fs/iomap/seek.c @@ -3,12 +3,8 @@ * Copyright (C) 2017 Red Hat, Inc. * Copyright (c) 2018-2021 Christoph Hellwig. */ -#include <linux/module.h> -#include <linux/compiler.h> -#include <linux/fs.h> #include <linux/iomap.h> #include <linux/pagemap.h> -#include <linux/pagevec.h> static int iomap_seek_hole_iter(struct iomap_iter *iter, loff_t *hole_pos) diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c index c1a762c10ce4..0db77c449467 100644 --- a/fs/iomap/swapfile.c +++ b/fs/iomap/swapfile.c @@ -3,9 +3,6 @@ * Copyright (C) 2018 Oracle. All Rights Reserved. * Author: Darrick J. Wong <darrick.wong@oracle.com> */ -#include <linux/module.h> -#include <linux/compiler.h> -#include <linux/fs.h> #include <linux/iomap.h> #include <linux/swap.h> diff --git a/fs/iomap/trace.c b/fs/iomap/trace.c index 728d5443daf5..da217246b1a9 100644 --- a/fs/iomap/trace.c +++ b/fs/iomap/trace.c @@ -3,7 +3,6 @@ * Copyright (c) 2019 Christoph Hellwig */ #include <linux/iomap.h> -#include <linux/uio.h> /* * We include this last to have the helpers above available for the trace diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h index 455cc6f90be0..6ad66e6ba653 100644 --- a/fs/iomap/trace.h +++ b/fs/iomap/trace.h @@ -79,7 +79,7 @@ DECLARE_EVENT_CLASS(iomap_range_class, DEFINE_EVENT(iomap_range_class, name, \ TP_PROTO(struct inode *inode, loff_t off, u64 len),\ TP_ARGS(inode, off, len)) -DEFINE_RANGE_EVENT(iomap_writepage); +DEFINE_RANGE_EVENT(iomap_writeback_folio); DEFINE_RANGE_EVENT(iomap_release_folio); DEFINE_RANGE_EVENT(iomap_invalidate_folio); DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); @@ -169,7 +169,7 @@ DEFINE_EVENT(iomap_class, name, \ DEFINE_IOMAP_EVENT(iomap_iter_dstmap); DEFINE_IOMAP_EVENT(iomap_iter_srcmap); -TRACE_EVENT(iomap_writepage_map, +TRACE_EVENT(iomap_add_to_ioend, TP_PROTO(struct inode *inode, u64 pos, unsigned int dirty_len, struct iomap *iomap), TP_ARGS(inode, pos, dirty_len, iomap), |