From 13ef954445df4fd1d7c003a500ec5ce49573e14b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 15 Oct 2019 08:43:42 -0700 Subject: iomap: Allow forcing of waiting for running DIO in iomap_dio_rw() Filesystems do not support doing IO as asynchronous in some cases. For example in case of unaligned writes or in case file size needs to be extended (e.g. for ext4). Instead of forcing filesystem to wait for AIO in such cases, add argument to iomap_dio_rw() which makes the function wait for IO completion. This also results in executing iomap_dio_complete() inline in iomap_dio_rw() providing its return value to the caller as for ordinary sync IO. Signed-off-by: Jan Kara Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 7aa5d6117936..76b14cb729dc 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -195,7 +195,8 @@ struct iomap_dio_ops { }; ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, - const struct iomap_ops *ops, const struct iomap_dio_ops *dops); + const struct iomap_ops *ops, const struct iomap_dio_ops *dops, + bool wait_for_completion); int iomap_dio_iopoll(struct kiocb *kiocb, bool spin); #ifdef CONFIG_SWAP -- cgit From 7684e2c4384d5d1f884b01ab8bff2369e4db0bff Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 17 Oct 2019 13:12:01 -0700 Subject: iomap: iomap that extends beyond EOF should be marked dirty When doing a direct IO that spans the current EOF, and there are written blocks beyond EOF that extend beyond the current write, the only metadata update that needs to be done is a file size extension. However, we don't mark such iomaps as IOMAP_F_DIRTY to indicate that there is IO completion metadata updates required, and hence we may fail to correctly sync file size extensions made in IO completion when O_DSYNC writes are being used and the hardware supports FUA. Hence when setting IOMAP_F_DIRTY, we need to also take into account whether the iomap spans the current EOF. If it does, then we need to mark it dirty so that IO completion will call generic_write_sync() to flush the inode size update to stable storage correctly. Fixes: 3460cac1ca76 ("iomap: Use FUA for pure data O_DSYNC DIO writes") Signed-off-by: Dave Chinner Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong [darrick: removed the ext4 part; they'll handle it separately] Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_iomap.c | 7 +++++++ include/linux/iomap.h | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index f780e223b118..32993c2acbd9 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1049,6 +1049,13 @@ xfs_file_iomap_begin( trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap); out_finish: + /* + * Writes that span EOF might trigger an IO size update on completion, + * so consider them to be dirty for the purposes of O_DSYNC even if + * there is no other metadata changes pending or have been made here. + */ + if ((flags & IOMAP_WRITE) && offset + length > i_size_read(inode)) + iomap->flags |= IOMAP_F_DIRTY; return xfs_bmbt_to_iomap(ip, iomap, &imap, shared); out_found: diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 76b14cb729dc..4b25ad6b5edd 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -32,6 +32,8 @@ struct vm_fault; * * IOMAP_F_DIRTY indicates the inode has uncommitted metadata needed to access * written data and requires fdatasync to commit them to persistent storage. + * This needs to take into account metadata changes that *may* be made at IO + * completion, such as file size updates from direct IO. */ #define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */ #define IOMAP_F_DIRTY 0x02 /* uncommitted metadata */ -- cgit From 598ecfbaa742aca0dcdbbea25681406f95cc0b63 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 17 Oct 2019 13:12:15 -0700 Subject: iomap: lift the xfs writeback code to iomap Take the xfs writeback code and move it to fs/iomap. A new structure with three methods is added as the abstraction from the generic writeback code to the file system. These methods are used to map blocks, submit an ioend, and cancel a page that encountered an error before it was added to an ioend. Signed-off-by: Christoph Hellwig [darrick: rename ->submit_ioend to ->prepare_ioend to clarify what it does] Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/iomap/buffered-io.c | 551 +++++++++++++++++++++++++++++++++++++++++- fs/iomap/trace.h | 1 + fs/xfs/xfs_aops.c | 639 +++++-------------------------------------------- fs/xfs/xfs_aops.h | 17 -- fs/xfs/xfs_super.c | 11 +- fs/xfs/xfs_trace.h | 39 --- include/linux/iomap.h | 59 +++++ 7 files changed, 669 insertions(+), 648 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 55e514899b8c..41e1828a0bb3 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) 2016-2018 Christoph Hellwig. + * Copyright (C) 2016-2019 Christoph Hellwig. */ #include #include @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -20,6 +21,8 @@ #include "../internal.h" +static struct bio_set iomap_ioend_bioset; + static struct iomap_page * iomap_page_create(struct inode *inode, struct page *page) { @@ -1088,3 +1091,549 @@ out_unlock: return block_page_mkwrite_return(ret); } EXPORT_SYMBOL_GPL(iomap_page_mkwrite); + +static void +iomap_finish_page_writeback(struct inode *inode, struct bio_vec *bvec, + int error) +{ + struct iomap_page *iop = to_iomap_page(bvec->bv_page); + + if (error) { + SetPageError(bvec->bv_page); + mapping_set_error(inode->i_mapping, -EIO); + } + + WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop); + WARN_ON_ONCE(iop && atomic_read(&iop->write_count) <= 0); + + if (!iop || atomic_dec_and_test(&iop->write_count)) + end_page_writeback(bvec->bv_page); +} + +/* + * 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. + */ +static void +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; + 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; + + /* + * 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 each page on bio, ending page IO on them */ + bio_for_each_segment_all(bv, bio, iter_all) + iomap_finish_page_writeback(inode, bv, error); + bio_put(bio); + } + + if (unlikely(error && !quiet)) { + printk_ratelimited(KERN_ERR + "%s: writeback error on sector %llu", + inode->i_sb->s_id, start); + } +} + +void +iomap_finish_ioends(struct iomap_ioend *ioend, int error) +{ + struct list_head tmp; + + list_replace_init(&ioend->io_list, &tmp); + iomap_finish_ioend(ioend, error); + + while (!list_empty(&tmp)) { + ioend = list_first_entry(&tmp, struct iomap_ioend, io_list); + list_del_init(&ioend->io_list); + iomap_finish_ioend(ioend, error); + } +} +EXPORT_SYMBOL_GPL(iomap_finish_ioends); + +/* + * We can merge two adjacent ioends if they have the same set of work to do. + */ +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) + return false; + if ((ioend->io_flags & IOMAP_F_SHARED) ^ + (next->io_flags & IOMAP_F_SHARED)) + return false; + if ((ioend->io_type == IOMAP_UNWRITTEN) ^ + (next->io_type == IOMAP_UNWRITTEN)) + return false; + if (ioend->io_offset + ioend->io_size != next->io_offset) + return false; + return true; +} + +void +iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends, + void (*merge_private)(struct iomap_ioend *ioend, + struct iomap_ioend *next)) +{ + struct iomap_ioend *next; + + INIT_LIST_HEAD(&ioend->io_list); + + while ((next = list_first_entry_or_null(more_ioends, struct iomap_ioend, + io_list))) { + if (!iomap_ioend_can_merge(ioend, next)) + break; + list_move_tail(&next->io_list, &ioend->io_list); + ioend->io_size += next->io_size; + if (next->io_private && merge_private) + merge_private(ioend, next); + } +} +EXPORT_SYMBOL_GPL(iomap_ioend_try_merge); + +static int +iomap_ioend_compare(void *priv, struct list_head *a, struct list_head *b) +{ + struct iomap_ioend *ia, *ib; + + ia = container_of(a, struct iomap_ioend, io_list); + ib = container_of(b, struct iomap_ioend, io_list); + if (ia->io_offset < ib->io_offset) + return -1; + else if (ia->io_offset > ib->io_offset) + return 1; + return 0; +} + +void +iomap_sort_ioends(struct list_head *ioend_list) +{ + list_sort(NULL, ioend_list, iomap_ioend_compare); +} +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)); +} + +/* + * 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 have marked paged 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. + */ +static int +iomap_submit_ioend(struct iomap_writepage_ctx *wpc, struct iomap_ioend *ioend, + int error) +{ + ioend->io_bio->bi_private = ioend; + ioend->io_bio->bi_end_io = iomap_writepage_end_bio; + + if (wpc->ops->prepare_ioend) + error = wpc->ops->prepare_ioend(ioend, error); + if (error) { + /* + * If we are 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; + } + + submit_bio(ioend->io_bio); + return 0; +} + +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) +{ + struct iomap_ioend *ioend; + struct bio *bio; + + bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &iomap_ioend_bioset); + bio_set_dev(bio, wpc->iomap.bdev); + bio->bi_iter.bi_sector = sector; + bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); + bio->bi_write_hint = inode->i_write_hint; + wbc_init_bio(wbc, bio); + + ioend = container_of(bio, struct iomap_ioend, io_inline_bio); + INIT_LIST_HEAD(&ioend->io_list); + ioend->io_type = wpc->iomap.type; + ioend->io_flags = wpc->iomap.flags; + ioend->io_inode = inode; + ioend->io_size = 0; + ioend->io_offset = offset; + ioend->io_private = NULL; + ioend->io_bio = bio; + return ioend; +} + +/* + * Allocate a new bio, and chain the old bio to the new one. + * + * Note that we have to do 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; + + new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES); + bio_copy_dev(new, prev);/* also copies over blkcg information */ + new->bi_iter.bi_sector = bio_end_sector(prev); + new->bi_opf = prev->bi_opf; + new->bi_write_hint = prev->bi_write_hint; + + bio_chain(prev, new); + bio_get(prev); /* for iomap_finish_ioend */ + submit_bio(prev); + return new; +} + +static bool +iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset, + sector_t sector) +{ + 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) + return false; + if (sector != bio_end_sector(wpc->ioend->io_bio)) + 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. + */ +static void +iomap_add_to_ioend(struct inode *inode, loff_t offset, struct page *page, + 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); + unsigned len = i_blocksize(inode); + unsigned poff = offset & (PAGE_SIZE - 1); + bool merged, same_page = false; + + if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, offset, sector)) { + if (wpc->ioend) + list_add(&wpc->ioend->io_list, iolist); + wpc->ioend = iomap_alloc_ioend(inode, wpc, offset, sector, wbc); + } + + merged = __bio_try_merge_page(wpc->ioend->io_bio, page, len, poff, + &same_page); + if (iop && !same_page) + atomic_inc(&iop->write_count); + + if (!merged) { + if (bio_full(wpc->ioend->io_bio, len)) { + wpc->ioend->io_bio = + iomap_chain_bio(wpc->ioend->io_bio); + } + bio_add_page(wpc->ioend->io_bio, page, len, poff); + } + + wpc->ioend->io_size += len; + wbc_account_cgroup_owner(wbc, page, len); +} + +/* + * We implement an immediate ioend submission policy here to avoid needing to + * chain multiple ioends and hence nest mempool allocations which can violate + * forward progress guarantees we need to provide. The current ioend we are + * adding blocks to is cached on the writepage context, and if the new block + * does not 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 page *page, u64 end_offset) +{ + struct iomap_page *iop = to_iomap_page(page); + struct iomap_ioend *ioend, *next; + unsigned len = i_blocksize(inode); + u64 file_offset; /* file offset of page */ + int error = 0, count = 0, i; + LIST_HEAD(submit_list); + + WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop); + WARN_ON_ONCE(iop && atomic_read(&iop->write_count) != 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. + */ + for (i = 0, file_offset = page_offset(page); + i < (PAGE_SIZE >> inode->i_blkbits) && file_offset < end_offset; + i++, file_offset += len) { + if (iop && !test_bit(i, iop->uptodate)) + continue; + + error = wpc->ops->map_blocks(wpc, inode, file_offset); + if (error) + break; + if (wpc->iomap.type == IOMAP_HOLE) + continue; + iomap_add_to_ioend(inode, file_offset, page, 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)); + + /* + * 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. + */ + if (unlikely(error)) { + if (!count) { + /* + * If the current page hasn't been added to ioend, it + * won't be affected by I/O completions and we must + * discard and unlock it right here. + */ + if (wpc->ops->discard_page) + wpc->ops->discard_page(page); + ClearPageUptodate(page); + unlock_page(page); + goto done; + } + + /* + * If the page was not fully cleaned, we need to ensure that the + * higher layers come back to it correctly. That means we need + * to keep the page dirty, and for WB_SYNC_ALL writeback we need + * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed + * so another attempt to write this page in this writeback sweep + * will be made. + */ + set_page_writeback_keepwrite(page); + } else { + clear_page_dirty_for_io(page); + set_page_writeback(page); + } + + unlock_page(page); + + /* + * Preserve the original error if there was one, otherwise 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) + end_page_writeback(page); +done: + mapping_set_error(page->mapping, error); + return error; +} + +/* + * Write out a dirty page. + * + * 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. + */ +static int +iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data) +{ + struct iomap_writepage_ctx *wpc = data; + struct inode *inode = page->mapping->host; + pgoff_t end_index; + u64 end_offset; + loff_t offset; + + trace_iomap_writepage(inode, page, 0, 0); + + /* + * Refuse to write the page out if we are 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; + + /* + * Given that we do not allow direct reclaim to call us, we should + * never be called in a recursive filesystem reclaim context. + */ + if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS)) + goto redirty; + + /* + * Is this page 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. + * ----------------------------------------------------- + * | file mapping | | + * ----------------------------------------------------- + * | Page ... | Page N-2 | Page N-1 | Page N | | + * ^--------------------------------^----------|-------- + * | 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 { + /* + * Check whether the page to write out is beyond or straddles + * i_size or not. + * ------------------------------------------------------- + * | file mapping | | + * ------------------------------------------------------- + * | Page ... | Page N-2 | Page N-1 | Page N | Beyond | + * ^--------------------------------^-----------|--------- + * | | Straddles | + * ---------------------------------^-----------|--------| + */ + unsigned offset_into_page = offset & (PAGE_SIZE - 1); + + /* + * Skip the page if it is fully outside i_size, e.g. due to a + * truncate operation that is in progress. We must redirty the + * page so that reclaim stops reclaiming it. Otherwise + * iomap_vm_releasepage() is called on it and gets confused. + * + * Note that the end_index is unsigned long, it would overflow + * if the given offset is greater than 16TB on 32-bit system + * and if we do check the page is fully outside i_size or not + * via "if (page->index >= end_index + 1)" as "end_index + 1" + * will be evaluated to 0. Hence this page will be redirtied + * and be written out repeatedly which would result in an + * infinite loop, the user program that perform this operation + * will hang. Instead, we can verify this situation by checking + * if the page to write is totally beyond the i_size or if it's + * offset is just equal to the EOF. + */ + if (page->index > end_index || + (page->index == end_index && offset_into_page == 0)) + goto redirty; + + /* + * 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." + */ + zero_user_segment(page, offset_into_page, PAGE_SIZE); + + /* Adjust the end_offset to the end of file */ + end_offset = offset; + } + + return iomap_writepage_map(wpc, wbc, inode, page, end_offset); + +redirty: + redirty_page_for_writepage(wbc, page); + unlock_page(page); + return 0; +} + +int +iomap_writepage(struct page *page, struct writeback_control *wbc, + struct iomap_writepage_ctx *wpc, + const struct iomap_writeback_ops *ops) +{ + int ret; + + wpc->ops = ops; + ret = iomap_do_writepage(page, wbc, wpc); + if (!wpc->ioend) + return ret; + return iomap_submit_ioend(wpc, wpc->ioend, ret); +} +EXPORT_SYMBOL_GPL(iomap_writepage); + +int +iomap_writepages(struct address_space *mapping, struct writeback_control *wbc, + struct iomap_writepage_ctx *wpc, + const struct iomap_writeback_ops *ops) +{ + int ret; + + 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); +} +EXPORT_SYMBOL_GPL(iomap_writepages); + +static int __init iomap_init(void) +{ + return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE), + offsetof(struct iomap_ioend, io_inline_bio), + BIOSET_NEED_BVECS); +} +fs_initcall(iomap_init); diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h index 63a98ad01b0f..4ca1aa2f3f6e 100644 --- a/fs/iomap/trace.h +++ b/fs/iomap/trace.h @@ -76,6 +76,7 @@ DEFINE_EVENT(iomap_page_class, name, \ TP_PROTO(struct inode *inode, struct page *page, unsigned long off, \ unsigned int len), \ TP_ARGS(inode, page, off, len)) +DEFINE_PAGE_EVENT(iomap_writepage); DEFINE_PAGE_EVENT(iomap_releasepage); DEFINE_PAGE_EVENT(iomap_invalidatepage); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index f08563e2bd9f..5936507c6f50 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -18,16 +18,18 @@ #include "xfs_bmap_util.h" #include "xfs_reflink.h" -/* - * structure owned by writepages passed to individual writepage calls - */ struct xfs_writepage_ctx { - struct iomap iomap; + struct iomap_writepage_ctx ctx; unsigned int data_seq; unsigned int cow_seq; - struct xfs_ioend *ioend; }; +static inline struct xfs_writepage_ctx * +XFS_WPC(struct iomap_writepage_ctx *ctx) +{ + return container_of(ctx, struct xfs_writepage_ctx, ctx); +} + struct block_device * xfs_find_bdev_for_inode( struct inode *inode) @@ -54,87 +56,10 @@ xfs_find_daxdev_for_inode( return mp->m_ddev_targp->bt_daxdev; } -static void -xfs_finish_page_writeback( - struct inode *inode, - struct bio_vec *bvec, - int error) -{ - struct iomap_page *iop = to_iomap_page(bvec->bv_page); - - if (error) { - SetPageError(bvec->bv_page); - mapping_set_error(inode->i_mapping, -EIO); - } - - ASSERT(iop || i_blocksize(inode) == PAGE_SIZE); - ASSERT(!iop || atomic_read(&iop->write_count) > 0); - - if (!iop || atomic_dec_and_test(&iop->write_count)) - end_page_writeback(bvec->bv_page); -} - -/* - * 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. - */ -STATIC void -xfs_destroy_ioend( - struct xfs_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; - bool quiet = bio_flagged(bio, BIO_QUIET); - - for (bio = &ioend->io_inline_bio; bio; bio = next) { - struct bio_vec *bvec; - struct bvec_iter_all iter_all; - - /* - * 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 each page on bio, ending page IO on them */ - bio_for_each_segment_all(bvec, bio, iter_all) - xfs_finish_page_writeback(inode, bvec, error); - bio_put(bio); - } - - if (unlikely(error && !quiet)) { - xfs_err_ratelimited(XFS_I(inode)->i_mount, - "writeback error on sector %llu", start); - } -} - -static void -xfs_destroy_ioends( - struct xfs_ioend *ioend, - int error) -{ - struct list_head tmp; - - list_replace_init(&ioend->io_list, &tmp); - xfs_destroy_ioend(ioend, error); - while ((ioend = list_first_entry_or_null(&tmp, struct xfs_ioend, - io_list))) { - list_del_init(&ioend->io_list); - xfs_destroy_ioend(ioend, error); - } -} - /* * Fast and loose check if this write could update the on-disk inode size. */ -static inline bool xfs_ioend_is_append(struct xfs_ioend *ioend) +static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend) { return ioend->io_offset + ioend->io_size > XFS_I(ioend->io_inode)->i_d.di_size; @@ -142,7 +67,7 @@ static inline bool xfs_ioend_is_append(struct xfs_ioend *ioend) STATIC int xfs_setfilesize_trans_alloc( - struct xfs_ioend *ioend) + struct iomap_ioend *ioend) { struct xfs_mount *mp = XFS_I(ioend->io_inode)->i_mount; struct xfs_trans *tp; @@ -215,7 +140,7 @@ xfs_setfilesize( STATIC int xfs_setfilesize_ioend( - struct xfs_ioend *ioend, + struct iomap_ioend *ioend, int error) { struct xfs_inode *ip = XFS_I(ioend->io_inode); @@ -243,7 +168,7 @@ xfs_setfilesize_ioend( */ STATIC void xfs_end_ioend( - struct xfs_ioend *ioend) + struct iomap_ioend *ioend) { struct xfs_inode *ip = XFS_I(ioend->io_inode); xfs_off_t offset = ioend->io_offset; @@ -289,31 +214,10 @@ xfs_end_ioend( done: if (ioend->io_private) error = xfs_setfilesize_ioend(ioend, error); - xfs_destroy_ioends(ioend, error); + iomap_finish_ioends(ioend, error); memalloc_nofs_restore(nofs_flag); } -/* - * We can merge two adjacent ioends if they have the same set of work to do. - */ -static bool -xfs_ioend_can_merge( - struct xfs_ioend *ioend, - struct xfs_ioend *next) -{ - if (ioend->io_bio->bi_status != next->io_bio->bi_status) - return false; - if ((ioend->io_flags & IOMAP_F_SHARED) ^ - (next->io_flags & IOMAP_F_SHARED)) - return false; - if ((ioend->io_type == IOMAP_UNWRITTEN) ^ - (next->io_type == IOMAP_UNWRITTEN)) - return false; - if (ioend->io_offset + ioend->io_size != next->io_offset) - return false; - return true; -} - /* * If the to be merged ioend has a preallocated transaction for file * size updates we need to ensure the ioend it is merged into also @@ -322,8 +226,8 @@ xfs_ioend_can_merge( */ static void xfs_ioend_merge_private( - struct xfs_ioend *ioend, - struct xfs_ioend *next) + struct iomap_ioend *ioend, + struct iomap_ioend *next) { if (!ioend->io_private) { ioend->io_private = next->io_private; @@ -333,53 +237,6 @@ xfs_ioend_merge_private( } } -/* Try to merge adjacent completions. */ -STATIC void -xfs_ioend_try_merge( - struct xfs_ioend *ioend, - struct list_head *more_ioends) -{ - struct xfs_ioend *next; - - INIT_LIST_HEAD(&ioend->io_list); - - while ((next = list_first_entry_or_null(more_ioends, struct xfs_ioend, - io_list))) { - if (!xfs_ioend_can_merge(ioend, next)) - break; - list_move_tail(&next->io_list, &ioend->io_list); - ioend->io_size += next->io_size; - if (next->io_private) - xfs_ioend_merge_private(ioend, next); - } -} - -/* list_sort compare function for ioends */ -static int -xfs_ioend_compare( - void *priv, - struct list_head *a, - struct list_head *b) -{ - struct xfs_ioend *ia; - struct xfs_ioend *ib; - - ia = container_of(a, struct xfs_ioend, io_list); - ib = container_of(b, struct xfs_ioend, io_list); - if (ia->io_offset < ib->io_offset) - return -1; - else if (ia->io_offset > ib->io_offset) - return 1; - return 0; -} - -static void -xfs_sort_ioends( - struct list_head *ioend_list) -{ - list_sort(NULL, ioend_list, xfs_ioend_compare); -} - /* Finish all pending io completions. */ void xfs_end_io( @@ -387,7 +244,7 @@ xfs_end_io( { struct xfs_inode *ip = container_of(work, struct xfs_inode, i_ioend_work); - struct xfs_ioend *ioend; + struct iomap_ioend *ioend; struct list_head tmp; unsigned long flags; @@ -395,16 +252,16 @@ xfs_end_io( list_replace_init(&ip->i_ioend_list, &tmp); spin_unlock_irqrestore(&ip->i_ioend_lock, flags); - xfs_sort_ioends(&tmp); - while ((ioend = list_first_entry_or_null(&tmp, struct xfs_ioend, + iomap_sort_ioends(&tmp); + while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend, io_list))) { list_del_init(&ioend->io_list); - xfs_ioend_try_merge(ioend, &tmp); + iomap_ioend_try_merge(ioend, &tmp, xfs_ioend_merge_private); xfs_end_ioend(ioend); } } -static inline bool xfs_ioend_needs_workqueue(struct xfs_ioend *ioend) +static inline bool xfs_ioend_needs_workqueue(struct iomap_ioend *ioend) { return ioend->io_private || ioend->io_type == IOMAP_UNWRITTEN || @@ -415,20 +272,18 @@ STATIC void xfs_end_bio( struct bio *bio) { - struct xfs_ioend *ioend = bio->bi_private; + struct iomap_ioend *ioend = bio->bi_private; struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_mount *mp = ip->i_mount; unsigned long flags; - if (xfs_ioend_needs_workqueue(ioend)) { - spin_lock_irqsave(&ip->i_ioend_lock, flags); - if (list_empty(&ip->i_ioend_list)) - WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, - &ip->i_ioend_work)); - list_add_tail(&ioend->io_list, &ip->i_ioend_list); - spin_unlock_irqrestore(&ip->i_ioend_lock, flags); - } else - xfs_destroy_ioend(ioend, blk_status_to_errno(bio->bi_status)); + ASSERT(xfs_ioend_needs_workqueue(ioend)); + + spin_lock_irqsave(&ip->i_ioend_lock, flags); + if (list_empty(&ip->i_ioend_list)) + WARN_ON_ONCE(!queue_work(ip->i_mount->m_unwritten_workqueue, + &ip->i_ioend_work)); + list_add_tail(&ioend->io_list, &ip->i_ioend_list); + spin_unlock_irqrestore(&ip->i_ioend_lock, flags); } /* @@ -437,7 +292,7 @@ xfs_end_bio( */ static bool xfs_imap_valid( - struct xfs_writepage_ctx *wpc, + struct iomap_writepage_ctx *wpc, struct xfs_inode *ip, loff_t offset) { @@ -459,10 +314,10 @@ xfs_imap_valid( * checked (and found nothing at this offset) could have added * overlapping blocks. */ - if (wpc->data_seq != READ_ONCE(ip->i_df.if_seq)) + if (XFS_WPC(wpc)->data_seq != READ_ONCE(ip->i_df.if_seq)) return false; if (xfs_inode_has_cow_data(ip) && - wpc->cow_seq != READ_ONCE(ip->i_cowfp->if_seq)) + XFS_WPC(wpc)->cow_seq != READ_ONCE(ip->i_cowfp->if_seq)) return false; return true; } @@ -477,12 +332,18 @@ xfs_imap_valid( */ static int xfs_convert_blocks( - struct xfs_writepage_ctx *wpc, + struct iomap_writepage_ctx *wpc, struct xfs_inode *ip, int whichfork, loff_t offset) { int error; + unsigned *seq; + + if (whichfork == XFS_COW_FORK) + seq = &XFS_WPC(wpc)->cow_seq; + else + seq = &XFS_WPC(wpc)->data_seq; /* * Attempt to allocate whatever delalloc extent currently backs offset @@ -492,8 +353,7 @@ xfs_convert_blocks( */ do { error = xfs_bmapi_convert_delalloc(ip, whichfork, offset, - &wpc->iomap, whichfork == XFS_COW_FORK ? - &wpc->cow_seq : &wpc->data_seq); + &wpc->iomap, seq); if (error) return error; } while (wpc->iomap.offset + wpc->iomap.length <= offset); @@ -501,9 +361,9 @@ xfs_convert_blocks( return 0; } -STATIC int +static int xfs_map_blocks( - struct xfs_writepage_ctx *wpc, + struct iomap_writepage_ctx *wpc, struct inode *inode, loff_t offset) { @@ -559,7 +419,7 @@ retry: xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap)) cow_fsb = imap.br_startoff; if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) { - wpc->cow_seq = READ_ONCE(ip->i_cowfp->if_seq); + XFS_WPC(wpc)->cow_seq = READ_ONCE(ip->i_cowfp->if_seq); xfs_iunlock(ip, XFS_ILOCK_SHARED); whichfork = XFS_COW_FORK; @@ -582,7 +442,7 @@ retry: */ if (!xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap)) imap.br_startoff = end_fsb; /* fake a hole past EOF */ - wpc->data_seq = READ_ONCE(ip->i_df.if_seq); + XFS_WPC(wpc)->data_seq = READ_ONCE(ip->i_df.if_seq); xfs_iunlock(ip, XFS_ILOCK_SHARED); /* landed in a hole or beyond EOF? */ @@ -645,24 +505,9 @@ allocate_blocks: return 0; } -/* - * Submit the bio for an ioend. We are passed an ioend with a bio attached to - * it, and we submit that bio. The ioend may be used for multiple bio - * submissions, so we only want to allocate an append transaction for the ioend - * once. In the case of multiple bio submission, each bio will take an IO - * reference to the ioend to ensure that the ioend completion is only done once - * all bios have been submitted and the ioend is really done. - * - * If @status is non-zero, it means that we have a situation where some part of - * the submission process has failed after we have marked paged for writeback - * and unlocked them. In this situation, we need to fail the bio and ioend - * rather than submit it to IO. This typically only happens on a filesystem - * shutdown. - */ -STATIC int -xfs_submit_ioend( - struct writeback_control *wbc, - struct xfs_ioend *ioend, +static int +xfs_prepare_ioend( + struct iomap_ioend *ioend, int status) { unsigned int nofs_flag; @@ -690,137 +535,9 @@ xfs_submit_ioend( memalloc_nofs_restore(nofs_flag); - ioend->io_bio->bi_private = ioend; - ioend->io_bio->bi_end_io = xfs_end_bio; - - /* - * If we are 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. - */ - if (status) { - ioend->io_bio->bi_status = errno_to_blk_status(status); - bio_endio(ioend->io_bio); - return status; - } - - submit_bio(ioend->io_bio); - return 0; -} - -static struct xfs_ioend * -xfs_alloc_ioend( - struct inode *inode, - struct xfs_writepage_ctx *wpc, - xfs_off_t offset, - sector_t sector, - struct writeback_control *wbc) -{ - struct xfs_ioend *ioend; - struct bio *bio; - - bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &xfs_ioend_bioset); - bio_set_dev(bio, wpc->iomap.bdev); - bio->bi_iter.bi_sector = sector; - bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); - bio->bi_write_hint = inode->i_write_hint; - wbc_init_bio(wbc, bio); - - ioend = container_of(bio, struct xfs_ioend, io_inline_bio); - INIT_LIST_HEAD(&ioend->io_list); - ioend->io_type = wpc->iomap.type; - ioend->io_flags = wpc->iomap.flags; - ioend->io_inode = inode; - ioend->io_size = 0; - ioend->io_offset = offset; - ioend->io_private = NULL; - ioend->io_bio = bio; - return ioend; -} - -/* - * Allocate a new bio, and chain the old bio to the new one. - * - * Note that we have to do perform the chaining in this unintuitive order - * so that the bi_private linkage is set up in the right direction for the - * traversal in xfs_destroy_ioend(). - */ -static struct bio * -xfs_chain_bio( - struct bio *prev) -{ - struct bio *new; - - new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES); - bio_copy_dev(new, prev);/* also copies over blkcg information */ - new->bi_iter.bi_sector = bio_end_sector(prev); - new->bi_opf = prev->bi_opf; - new->bi_write_hint = prev->bi_write_hint; - - bio_chain(prev, new); - bio_get(prev); /* for xfs_destroy_ioend */ - submit_bio(prev); - return new; -} - -static bool -xfs_can_add_to_ioend( - struct xfs_writepage_ctx *wpc, - xfs_off_t offset, - sector_t sector) -{ - 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) - return false; - if (sector != bio_end_sector(wpc->ioend->io_bio)) - 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. - */ -STATIC void -xfs_add_to_ioend( - struct inode *inode, - xfs_off_t offset, - struct page *page, - struct iomap_page *iop, - struct xfs_writepage_ctx *wpc, - struct writeback_control *wbc, - struct list_head *iolist) -{ - sector_t sector = iomap_sector(&wpc->iomap, offset); - unsigned len = i_blocksize(inode); - unsigned poff = offset & (PAGE_SIZE - 1); - bool merged, same_page = false; - - if (!wpc->ioend || !xfs_can_add_to_ioend(wpc, offset, sector)) { - if (wpc->ioend) - list_add(&wpc->ioend->io_list, iolist); - wpc->ioend = xfs_alloc_ioend(inode, wpc, offset, sector, wbc); - } - - merged = __bio_try_merge_page(wpc->ioend->io_bio, page, len, poff, - &same_page); - - if (iop && !same_page) - atomic_inc(&iop->write_count); - - if (!merged) { - if (bio_full(wpc->ioend->io_bio, len)) - wpc->ioend->io_bio = xfs_chain_bio(wpc->ioend->io_bio); - bio_add_page(wpc->ioend->io_bio, page, len, poff); - } - - wpc->ioend->io_size += len; - wbc_account_cgroup_owner(wbc, page, len); + if (xfs_ioend_needs_workqueue(ioend)) + ioend->io_bio->bi_end_io = xfs_end_bio; + return status; } /* @@ -834,8 +551,8 @@ xfs_add_to_ioend( * transaction as there is no space left for block reservation (typically why we * see a ENOSPC in writeback). */ -STATIC void -xfs_aops_discard_page( +static void +xfs_discard_page( struct page *page) { struct inode *inode = page->mapping->host; @@ -860,243 +577,11 @@ out_invalidate: iomap_invalidatepage(page, 0, PAGE_SIZE); } -/* - * We implement an immediate ioend submission policy here to avoid needing to - * chain multiple ioends and hence nest mempool allocations which can violate - * forward progress guarantees we need to provide. The current ioend we are - * adding blocks to is cached on the writepage context, and if the new block - * does not 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 -xfs_writepage_map( - struct xfs_writepage_ctx *wpc, - struct writeback_control *wbc, - struct inode *inode, - struct page *page, - uint64_t end_offset) -{ - LIST_HEAD(submit_list); - struct iomap_page *iop = to_iomap_page(page); - unsigned len = i_blocksize(inode); - struct xfs_ioend *ioend, *next; - uint64_t file_offset; /* file offset of page */ - int error = 0, count = 0, i; - - ASSERT(iop || i_blocksize(inode) == PAGE_SIZE); - ASSERT(!iop || atomic_read(&iop->write_count) == 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. - */ - for (i = 0, file_offset = page_offset(page); - i < (PAGE_SIZE >> inode->i_blkbits) && file_offset < end_offset; - i++, file_offset += len) { - if (iop && !test_bit(i, iop->uptodate)) - continue; - - error = xfs_map_blocks(wpc, inode, file_offset); - if (error) - break; - if (wpc->iomap.type == IOMAP_HOLE) - continue; - xfs_add_to_ioend(inode, file_offset, page, iop, wpc, wbc, - &submit_list); - count++; - } - - ASSERT(wpc->ioend || list_empty(&submit_list)); - ASSERT(PageLocked(page)); - ASSERT(!PageWriteback(page)); - - /* - * On error, we have to fail the ioend here because we may have set - * pages under writeback, we have to make sure we run IO completion to - * mark the error state of the IO appropriately, so we can't cancel the - * ioend directly here. That means we have to mark this page as under - * writeback if we included any blocks from it in the ioend chain so - * that completion treats it correctly. - * - * If we didn't include the page in the ioend, the on error we can - * simply discard and unlock it as there are no other users of the page - * now. The caller will still need to trigger submission of outstanding - * ioends on the writepage context so they are treated correctly on - * error. - */ - if (unlikely(error)) { - if (!count) { - xfs_aops_discard_page(page); - ClearPageUptodate(page); - unlock_page(page); - goto done; - } - - /* - * If the page was not fully cleaned, we need to ensure that the - * higher layers come back to it correctly. That means we need - * to keep the page dirty, and for WB_SYNC_ALL writeback we need - * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed - * so another attempt to write this page in this writeback sweep - * will be made. - */ - set_page_writeback_keepwrite(page); - } else { - clear_page_dirty_for_io(page); - set_page_writeback(page); - } - - unlock_page(page); - - /* - * Preserve the original error if there was one, otherwise 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 = xfs_submit_ioend(wbc, 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) - end_page_writeback(page); -done: - mapping_set_error(page->mapping, error); - return error; -} - -/* - * Write out a dirty page. - * - * 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. - */ -STATIC int -xfs_do_writepage( - struct page *page, - struct writeback_control *wbc, - void *data) -{ - struct xfs_writepage_ctx *wpc = data; - struct inode *inode = page->mapping->host; - loff_t offset; - uint64_t end_offset; - pgoff_t end_index; - - trace_xfs_writepage(inode, page, 0, 0); - - /* - * Refuse to write the page out if we are 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; - - /* - * Given that we do not allow direct reclaim to call us, we should - * never be called while in a filesystem transaction. - */ - if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS)) - goto redirty; - - /* - * Is this page 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. - * ----------------------------------------------------- - * | file mapping | | - * ----------------------------------------------------- - * | Page ... | Page N-2 | Page N-1 | Page N | | - * ^--------------------------------^----------|-------- - * | desired writeback range | see else | - * ---------------------------------^------------------| - */ - offset = i_size_read(inode); - end_index = offset >> PAGE_SHIFT; - if (page->index < end_index) - end_offset = (xfs_off_t)(page->index + 1) << PAGE_SHIFT; - else { - /* - * Check whether the page to write out is beyond or straddles - * i_size or not. - * ------------------------------------------------------- - * | file mapping | | - * ------------------------------------------------------- - * | Page ... | Page N-2 | Page N-1 | Page N | Beyond | - * ^--------------------------------^-----------|--------- - * | | Straddles | - * ---------------------------------^-----------|--------| - */ - unsigned offset_into_page = offset & (PAGE_SIZE - 1); - - /* - * Skip the page if it is fully outside i_size, e.g. due to a - * truncate operation that is in progress. We must redirty the - * page so that reclaim stops reclaiming it. Otherwise - * xfs_vm_releasepage() is called on it and gets confused. - * - * Note that the end_index is unsigned long, it would overflow - * if the given offset is greater than 16TB on 32-bit system - * and if we do check the page is fully outside i_size or not - * via "if (page->index >= end_index + 1)" as "end_index + 1" - * will be evaluated to 0. Hence this page will be redirtied - * and be written out repeatedly which would result in an - * infinite loop, the user program that perform this operation - * will hang. Instead, we can verify this situation by checking - * if the page to write is totally beyond the i_size or if it's - * offset is just equal to the EOF. - */ - if (page->index > end_index || - (page->index == end_index && offset_into_page == 0)) - goto redirty; - - /* - * 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." - */ - zero_user_segment(page, offset_into_page, PAGE_SIZE); - - /* Adjust the end_offset to the end of file */ - end_offset = offset; - } - - return xfs_writepage_map(wpc, wbc, inode, page, end_offset); - -redirty: - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return 0; -} +static const struct iomap_writeback_ops xfs_writeback_ops = { + .map_blocks = xfs_map_blocks, + .prepare_ioend = xfs_prepare_ioend, + .discard_page = xfs_discard_page, +}; STATIC int xfs_vm_writepage( @@ -1104,12 +589,8 @@ xfs_vm_writepage( struct writeback_control *wbc) { struct xfs_writepage_ctx wpc = { }; - int ret; - ret = xfs_do_writepage(page, wbc, &wpc); - if (wpc.ioend) - ret = xfs_submit_ioend(wbc, wpc.ioend, ret); - return ret; + return iomap_writepage(page, wbc, &wpc.ctx, &xfs_writeback_ops); } STATIC int @@ -1118,13 +599,9 @@ xfs_vm_writepages( struct writeback_control *wbc) { struct xfs_writepage_ctx wpc = { }; - int ret; xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED); - ret = write_cache_pages(mapping, wbc, xfs_do_writepage, &wpc); - if (wpc.ioend) - ret = xfs_submit_ioend(wbc, wpc.ioend, ret); - return ret; + return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops); } STATIC int diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index 4a0226cdad4f..687b11f34fa2 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -6,23 +6,6 @@ #ifndef __XFS_AOPS_H__ #define __XFS_AOPS_H__ -extern struct bio_set xfs_ioend_bioset; - -/* - * Structure for buffered I/O completions. - */ -struct xfs_ioend { - struct list_head io_list; /* next ioend in chain */ - u16 io_type; - u16 io_flags; /* IOMAP_F_* */ - struct inode *io_inode; /* file being written to */ - size_t io_size; /* size of the extent */ - xfs_off_t io_offset; /* offset in the file */ - void *io_private; /* file system private data */ - struct bio *io_bio; /* bio being built */ - struct bio io_inline_bio; /* MUST BE LAST! */ -}; - extern const struct address_space_operations xfs_address_space_operations; extern const struct address_space_operations xfs_dax_aops; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 8d1df9f8be07..0a8cf6b87a21 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -40,7 +40,6 @@ #include static const struct super_operations xfs_super_operations; -struct bio_set xfs_ioend_bioset; static struct kset *xfs_kset; /* top-level xfs sysfs dir */ #ifdef DEBUG @@ -1853,15 +1852,10 @@ MODULE_ALIAS_FS("xfs"); STATIC int __init xfs_init_zones(void) { - if (bioset_init(&xfs_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE), - offsetof(struct xfs_ioend, io_inline_bio), - BIOSET_NEED_BVECS)) - goto out; - xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t), "xfs_log_ticket"); if (!xfs_log_ticket_zone) - goto out_free_ioend_bioset; + goto out; xfs_bmap_free_item_zone = kmem_zone_init( sizeof(struct xfs_extent_free_item), @@ -1996,8 +1990,6 @@ xfs_init_zones(void) kmem_zone_destroy(xfs_bmap_free_item_zone); out_destroy_log_ticket_zone: kmem_zone_destroy(xfs_log_ticket_zone); - out_free_ioend_bioset: - bioset_exit(&xfs_ioend_bioset); out: return -ENOMEM; } @@ -2028,7 +2020,6 @@ xfs_destroy_zones(void) kmem_zone_destroy(xfs_btree_cur_zone); kmem_zone_destroy(xfs_bmap_free_item_zone); kmem_zone_destroy(xfs_log_ticket_zone); - bioset_exit(&xfs_ioend_bioset); } STATIC int __init diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index eae4b29c174e..cbb23d7a3554 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -1158,45 +1158,6 @@ DEFINE_RW_EVENT(xfs_file_buffered_write); DEFINE_RW_EVENT(xfs_file_direct_write); DEFINE_RW_EVENT(xfs_file_dax_write); -DECLARE_EVENT_CLASS(xfs_page_class, - TP_PROTO(struct inode *inode, struct page *page, unsigned long off, - unsigned int len), - TP_ARGS(inode, page, off, len), - TP_STRUCT__entry( - __field(dev_t, dev) - __field(xfs_ino_t, ino) - __field(pgoff_t, pgoff) - __field(loff_t, size) - __field(unsigned long, offset) - __field(unsigned int, length) - ), - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = XFS_I(inode)->i_ino; - __entry->pgoff = page_offset(page); - __entry->size = i_size_read(inode); - __entry->offset = off; - __entry->length = len; - ), - TP_printk("dev %d:%d ino 0x%llx pgoff 0x%lx size 0x%llx offset %lx " - "length %x", - MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->ino, - __entry->pgoff, - __entry->size, - __entry->offset, - __entry->length) -) - -#define DEFINE_PAGE_EVENT(name) \ -DEFINE_EVENT(xfs_page_class, name, \ - TP_PROTO(struct inode *inode, struct page *page, unsigned long off, \ - unsigned int len), \ - TP_ARGS(inode, page, off, len)) -DEFINE_PAGE_EVENT(xfs_writepage); -DEFINE_PAGE_EVENT(xfs_releasepage); -DEFINE_PAGE_EVENT(xfs_invalidatepage); - DECLARE_EVENT_CLASS(xfs_imap_class, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count, int whichfork, struct xfs_bmbt_irec *irec), diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 4b25ad6b5edd..6e00bb843c7f 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -4,6 +4,7 @@ #include #include +#include #include #include #include @@ -12,6 +13,7 @@ struct address_space; struct fiemap_extent_info; struct inode; +struct iomap_writepage_ctx; struct iov_iter; struct kiocb; struct page; @@ -185,6 +187,63 @@ loff_t iomap_seek_data(struct inode *inode, loff_t offset, sector_t iomap_bmap(struct address_space *mapping, sector_t bno, const struct iomap_ops *ops); +/* + * Structure for writeback I/O completions. + */ +struct iomap_ioend { + struct list_head io_list; /* next ioend in chain */ + u16 io_type; + u16 io_flags; /* IOMAP_F_* */ + struct inode *io_inode; /* file being written to */ + size_t io_size; /* size of the extent */ + loff_t io_offset; /* offset in the file */ + void *io_private; /* file system private data */ + struct bio *io_bio; /* bio being built */ + struct bio io_inline_bio; /* MUST BE LAST! */ +}; + +struct iomap_writeback_ops { + /* + * Required, maps the blocks so that writeback can be performed on + * the range starting at offset. + */ + int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode, + loff_t offset); + + /* + * Optional, allows the file systems to perform actions just before + * submitting the bio and/or override the bio end_io handler for complex + * operations like copy on write extent manipulation or unwritten extent + * conversions. + */ + int (*prepare_ioend)(struct iomap_ioend *ioend, int status); + + /* + * Optional, allows the file system to discard state on a page where + * we failed to submit any I/O. + */ + void (*discard_page)(struct page *page); +}; + +struct iomap_writepage_ctx { + struct iomap iomap; + struct iomap_ioend *ioend; + const struct iomap_writeback_ops *ops; +}; + +void iomap_finish_ioends(struct iomap_ioend *ioend, int error); +void iomap_ioend_try_merge(struct iomap_ioend *ioend, + struct list_head *more_ioends, + void (*merge_private)(struct iomap_ioend *ioend, + struct iomap_ioend *next)); +void iomap_sort_ioends(struct list_head *ioend_list); +int iomap_writepage(struct page *page, struct writeback_control *wbc, + struct iomap_writepage_ctx *wpc, + const struct iomap_writeback_ops *ops); +int iomap_writepages(struct address_space *mapping, + struct writeback_control *wbc, struct iomap_writepage_ctx *wpc, + const struct iomap_writeback_ops *ops); + /* * Flags for direct I/O ->end_io: */ -- cgit From ab08b01ec0a205d9c98e712eb504c850a51e6fdb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 17 Oct 2019 13:12:19 -0700 Subject: iomap: move struct iomap_page out of iomap.h Now that all the writepage code is in the iomap code there is no need to keep this structure public. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Carlos Maiolino Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 17 +++++++++++++++++ include/linux/iomap.h | 17 ----------------- 2 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 901c1a799238..b5ff54fddf1f 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -21,6 +21,23 @@ #include "../internal.h" +/* + * Structure allocated for each page when block size < PAGE_SIZE to track + * sub-page uptodate status and I/O completions. + */ +struct iomap_page { + atomic_t read_count; + atomic_t write_count; + DECLARE_BITMAP(uptodate, PAGE_SIZE / 512); +}; + +static inline struct iomap_page *to_iomap_page(struct page *page) +{ + if (page_has_private(page)) + return (struct iomap_page *)page_private(page); + return NULL; +} + static struct bio_set iomap_ioend_bioset; static struct iomap_page * diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 6e00bb843c7f..0f741eebf3a7 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -136,23 +136,6 @@ loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, const struct iomap_ops *ops, void *data, iomap_actor_t actor); -/* - * Structure allocate for each page when block size < PAGE_SIZE to track - * sub-page uptodate status and I/O completions. - */ -struct iomap_page { - atomic_t read_count; - atomic_t write_count; - DECLARE_BITMAP(uptodate, PAGE_SIZE / 512); -}; - -static inline struct iomap_page *to_iomap_page(struct page *page) -{ - if (page_has_private(page)) - return (struct iomap_page *)page_private(page); - return NULL; -} - ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); int iomap_readpage(struct page *page, const struct iomap_ops *ops); -- cgit From 65a60e8687c1c8f69aae3e77eafbf4a54b9f99e7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 18 Oct 2019 16:40:17 -0700 Subject: iomap: better document the IOMAP_F_* flags The documentation for IOMAP_F_* is a bit disorganized, and doesn't mention the fact that most flags are set by the file system and consumed by the iomap core, while IOMAP_F_SIZE_CHANGED is set by the core and consumed by the file system. Signed-off-by: Christoph Hellwig Reviewed-by: Allison Collins Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 0f741eebf3a7..8016700e6121 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -30,23 +30,38 @@ struct vm_fault; #define IOMAP_INLINE 0x05 /* data inline in the inode */ /* - * Flags for all iomap mappings: + * Flags reported by the file system from iomap_begin: + * + * IOMAP_F_NEW indicates that the blocks have been newly allocated and need + * zeroing for areas that no data is copied to. * * IOMAP_F_DIRTY indicates the inode has uncommitted metadata needed to access * written data and requires fdatasync to commit them to persistent storage. * This needs to take into account metadata changes that *may* be made at IO * completion, such as file size updates from direct IO. + * + * IOMAP_F_SHARED indicates that the blocks are shared, and will need to be + * unshared as part a write. + * + * IOMAP_F_MERGED indicates that the iomap contains the merge of multiple block + * mappings. + * + * IOMAP_F_BUFFER_HEAD indicates that the file system requires the use of + * buffer heads for this mapping. */ -#define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */ -#define IOMAP_F_DIRTY 0x02 /* uncommitted metadata */ -#define IOMAP_F_BUFFER_HEAD 0x04 /* file system requires buffer heads */ -#define IOMAP_F_SIZE_CHANGED 0x08 /* file size has changed */ +#define IOMAP_F_NEW 0x01 +#define IOMAP_F_DIRTY 0x02 +#define IOMAP_F_SHARED 0x04 +#define IOMAP_F_MERGED 0x08 +#define IOMAP_F_BUFFER_HEAD 0x10 /* - * Flags that only need to be reported for IOMAP_REPORT requests: + * Flags set by the core iomap code during operations: + * + * IOMAP_F_SIZE_CHANGED indicates to the iomap_end method that the file size + * has changed as the result of this write operation. */ -#define IOMAP_F_MERGED 0x10 /* contains multiple blocks/extents */ -#define IOMAP_F_SHARED 0x20 /* block shared with another file */ +#define IOMAP_F_SIZE_CHANGED 0x100 /* * Flags from 0x1000 up are for file system specific usage: -- cgit From 3590c4d8979bcc364e2ded95ab3966b4e436b7bf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 18 Oct 2019 16:41:34 -0700 Subject: iomap: ignore non-shared or non-data blocks in xfs_file_dirty xfs_file_dirty is used to unshare reflink blocks. Rename the function to xfs_file_unshare to better document that purpose, and skip iomaps that are not shared and don't need zeroing. This will allow to simplify the caller. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 15 +++++++++++---- fs/xfs/xfs_reflink.c | 2 +- include/linux/iomap.h | 2 +- 3 files changed, 13 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 8f9b54db3811..30df87ac8349 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -887,12 +887,19 @@ __iomap_read_page(struct inode *inode, loff_t offset) } static loff_t -iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data, +iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct iomap *iomap) { long status = 0; ssize_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 (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN) + return length; + do { struct page *page, *rpage; unsigned long offset; /* Offset into pagecache page */ @@ -932,14 +939,14 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data, } int -iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, +iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops) { loff_t ret; while (len) { ret = iomap_apply(inode, pos, len, IOMAP_WRITE, ops, NULL, - iomap_dirty_actor); + iomap_unshare_actor); if (ret <= 0) return ret; pos += ret; @@ -948,7 +955,7 @@ iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, return 0; } -EXPORT_SYMBOL_GPL(iomap_file_dirty); +EXPORT_SYMBOL_GPL(iomap_file_unshare); static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset, unsigned bytes, struct iomap *iomap) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 0f08153b4994..a9634110c783 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1442,7 +1442,7 @@ xfs_reflink_dirty_extents( flen = XFS_FSB_TO_B(mp, rlen); if (fpos + flen > isize) flen = isize - fpos; - error = iomap_file_dirty(VFS_I(ip), fpos, flen, + error = iomap_file_unshare(VFS_I(ip), fpos, flen, &xfs_iomap_ops); xfs_ilock(ip, XFS_ILOCK_EXCL); if (error) diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 8016700e6121..1623851ade90 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -168,7 +168,7 @@ int iomap_migrate_page(struct address_space *mapping, struct page *newpage, #else #define iomap_migrate_page NULL #endif -int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, +int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); -- cgit From eb81cf9d0e18d438e27339e0d1a49d3ac8644674 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 18 Oct 2019 16:43:08 -0700 Subject: iomap: renumber IOMAP_HOLE to 0 Instead of keeping a separate unnamed state for uninitialized iomaps, renumber IOMAP_HOLE to zero so that an uninitialized iomap is treated as a hole. Suggested-by: Darrick J. Wong Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 1623851ade90..53e6e2275d3d 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -23,11 +23,11 @@ struct vm_fault; /* * Types of block ranges for iomap mappings: */ -#define IOMAP_HOLE 0x01 /* no blocks allocated, need allocation */ -#define IOMAP_DELALLOC 0x02 /* delayed allocation blocks */ -#define IOMAP_MAPPED 0x03 /* blocks allocated at @addr */ -#define IOMAP_UNWRITTEN 0x04 /* blocks allocated at @addr in unwritten state */ -#define IOMAP_INLINE 0x05 /* data inline in the inode */ +#define IOMAP_HOLE 0 /* no blocks allocated, need allocation */ +#define IOMAP_DELALLOC 1 /* delayed allocation blocks */ +#define IOMAP_MAPPED 2 /* blocks allocated at @addr */ +#define IOMAP_UNWRITTEN 3 /* blocks allocated at @addr in unwritten state */ +#define IOMAP_INLINE 4 /* data inline in the inode */ /* * Flags reported by the file system from iomap_begin: -- cgit From c039b99792726346ad46ff17c5a5bcb77a5edac4 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Fri, 18 Oct 2019 16:44:10 -0700 Subject: iomap: use a srcmap for a read-modify-write I/O The srcmap is used to identify where the read is to be performed from. It is passed to ->iomap_begin, which can fill it in if we need to read data for partially written blocks from a different location than the write target. The srcmap is only supported for buffered writes so far. Signed-off-by: Goldwyn Rodrigues [hch: merged two patches, removed the IOMAP_F_COW flag, use iomap as srcmap if not set, adjust length down to srcmap end as well] Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Acked-by: Goldwyn Rodrigues --- fs/dax.c | 13 ++++++---- fs/ext2/inode.c | 2 +- fs/ext4/inode.c | 2 +- fs/gfs2/bmap.c | 3 ++- fs/iomap/apply.c | 25 ++++++++++++++----- fs/iomap/buffered-io.c | 65 +++++++++++++++++++++++++++----------------------- fs/iomap/direct-io.c | 2 +- fs/iomap/fiemap.c | 4 ++-- fs/iomap/seek.c | 4 ++-- fs/iomap/swapfile.c | 3 ++- fs/xfs/xfs_iomap.c | 9 ++++--- include/linux/iomap.h | 5 ++-- 12 files changed, 82 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/fs/dax.c b/fs/dax.c index 6bf81f931de3..68eef98cd9c4 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1090,7 +1090,7 @@ EXPORT_SYMBOL_GPL(__dax_zero_page_range); static loff_t dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap) + struct iomap *iomap, struct iomap *srcmap) { struct block_device *bdev = iomap->bdev; struct dax_device *dax_dev = iomap->dax_dev; @@ -1247,7 +1247,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, struct inode *inode = mapping->host; unsigned long vaddr = vmf->address; loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT; - struct iomap iomap = { 0 }; + struct iomap iomap = { .type = IOMAP_HOLE }; + struct iomap srcmap = { .type = IOMAP_HOLE }; unsigned flags = IOMAP_FAULT; int error, major = 0; bool write = vmf->flags & FAULT_FLAG_WRITE; @@ -1292,7 +1293,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, * the file system block size to be equal the page size, which means * that we never have to deal with more than a single extent here. */ - error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap); + error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap, &srcmap); if (iomap_errp) *iomap_errp = error; if (error) { @@ -1471,7 +1472,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT; struct inode *inode = mapping->host; vm_fault_t result = VM_FAULT_FALLBACK; - struct iomap iomap = { 0 }; + struct iomap iomap = { .type = IOMAP_HOLE }; + struct iomap srcmap = { .type = IOMAP_HOLE }; pgoff_t max_pgoff; void *entry; loff_t pos; @@ -1546,7 +1548,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, * to look up our filesystem block. */ pos = (loff_t)xas.xa_index << PAGE_SHIFT; - error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap); + error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap, + &srcmap); if (error) goto unlock_entry; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 7004ce581a32..467c13ff6b40 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -801,7 +801,7 @@ int ext2_get_block(struct inode *inode, sector_t iblock, #ifdef CONFIG_FS_DAX static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length, - unsigned flags, struct iomap *iomap) + unsigned flags, struct iomap *iomap, struct iomap *srcmap) { unsigned int blkbits = inode->i_blkbits; unsigned long first_block = offset >> blkbits; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 516faa280ced..abaaf7d96ca4 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3407,7 +3407,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode) } static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, - unsigned flags, struct iomap *iomap) + unsigned flags, struct iomap *iomap, struct iomap *srcmap) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned int blkbits = inode->i_blkbits; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index f63df54a08c6..516103248272 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1149,7 +1149,8 @@ static inline bool gfs2_iomap_need_write_lock(unsigned flags) } static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, - unsigned flags, struct iomap *iomap) + unsigned flags, struct iomap *iomap, + struct iomap *srcmap) { struct gfs2_inode *ip = GFS2_I(inode); struct metapath mp = { .mp_aheight = 1, }; diff --git a/fs/iomap/apply.c b/fs/iomap/apply.c index 54c02aecf3cd..484dd8eda861 100644 --- a/fs/iomap/apply.c +++ b/fs/iomap/apply.c @@ -23,8 +23,10 @@ loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, const struct iomap_ops *ops, void *data, iomap_actor_t actor) { - struct iomap iomap = { 0 }; + struct iomap iomap = { .type = IOMAP_HOLE }; + struct iomap srcmap = { .type = IOMAP_HOLE }; loff_t written = 0, ret; + u64 end; /* * Need to map a range from start position for length bytes. This can @@ -38,7 +40,7 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, * expose transient stale data. If the reserve fails, we can safely * back out at this point as there is nothing to undo. */ - ret = ops->iomap_begin(inode, pos, length, flags, &iomap); + ret = ops->iomap_begin(inode, pos, length, flags, &iomap, &srcmap); if (ret) return ret; if (WARN_ON(iomap.offset > pos)) @@ -50,15 +52,26 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, * Cut down the length to the one actually provided by the filesystem, * as it might not be able to give us the whole size that we requested. */ - if (iomap.offset + iomap.length < pos + length) - length = iomap.offset + iomap.length - pos; + end = iomap.offset + iomap.length; + if (srcmap.type != IOMAP_HOLE) + end = min(end, srcmap.offset + srcmap.length); + if (pos + length > end) + length = end - pos; /* - * Now that we have guaranteed that the space allocation will succeed. + * Now that we have guaranteed that the space allocation will succeed, * we can do the copy-in page by page without having to worry about * failures exposing transient data. + * + * To support COW operations, we read in data for partially blocks from + * the srcmap if the file system filled it in. In that case we the + * length needs to be limited to the earlier of the ends of the iomaps. + * If the file system did not provide a srcmap we pass in the normal + * iomap into the actors so that they don't need to have special + * handling for the two cases. */ - written = actor(inode, pos, length, data, &iomap); + written = actor(inode, pos, length, data, &iomap, + srcmap.type != IOMAP_HOLE ? &srcmap : &iomap); /* * Now the data has been copied, commit the range we've copied. This diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index b61076823544..c62e807956b6 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -234,7 +234,7 @@ static inline bool iomap_block_needs_zeroing(struct inode *inode, static loff_t iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap) + struct iomap *iomap, struct iomap *srcmap) { struct iomap_readpage_ctx *ctx = data; struct page *page = ctx->cur_page; @@ -382,7 +382,7 @@ iomap_next_page(struct inode *inode, struct list_head *pages, loff_t pos, static loff_t iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { struct iomap_readpage_ctx *ctx = data; loff_t done, ret; @@ -402,7 +402,7 @@ iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length, ctx->cur_page_in_bio = false; } ret = iomap_readpage_actor(inode, pos + done, length - done, - ctx, iomap); + ctx, iomap, srcmap); } return done; @@ -582,7 +582,7 @@ iomap_read_page_sync(loff_t block_start, struct page *page, unsigned poff, static int __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags, - struct page *page, struct iomap *iomap) + struct page *page, struct iomap *srcmap) { struct iomap_page *iop = iomap_page_create(inode, page); loff_t block_size = i_blocksize(inode); @@ -605,7 +605,7 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags, (to <= poff || to >= poff + plen)) continue; - if (iomap_block_needs_zeroing(inode, iomap, block_start)) { + if (iomap_block_needs_zeroing(inode, srcmap, block_start)) { if (WARN_ON_ONCE(flags & IOMAP_WRITE_F_UNSHARE)) return -EIO; zero_user_segments(page, poff, from, to, poff + plen); @@ -614,7 +614,7 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags, } status = iomap_read_page_sync(block_start, page, poff, plen, - iomap); + srcmap); if (status) return status; } while ((block_start += plen) < block_end); @@ -624,13 +624,15 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags, static int iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, - struct page **pagep, struct iomap *iomap) + struct page **pagep, struct iomap *iomap, struct iomap *srcmap) { const struct iomap_page_ops *page_ops = iomap->page_ops; struct page *page; int status = 0; BUG_ON(pos + len > iomap->offset + iomap->length); + if (srcmap != iomap) + BUG_ON(pos + len > srcmap->offset + srcmap->length); if (fatal_signal_pending(current)) return -EINTR; @@ -648,13 +650,13 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, goto out_no_page; } - if (iomap->type == IOMAP_INLINE) - iomap_read_inline_data(inode, page, iomap); + if (srcmap->type == IOMAP_INLINE) + iomap_read_inline_data(inode, page, srcmap); else if (iomap->flags & IOMAP_F_BUFFER_HEAD) - status = __block_write_begin_int(page, pos, len, NULL, iomap); + status = __block_write_begin_int(page, pos, len, NULL, srcmap); else status = __iomap_write_begin(inode, pos, len, flags, page, - iomap); + srcmap); if (unlikely(status)) goto out_unlock; @@ -740,16 +742,16 @@ iomap_write_end_inline(struct inode *inode, struct page *page, } static int -iomap_write_end(struct inode *inode, loff_t pos, unsigned len, - unsigned copied, struct page *page, struct iomap *iomap) +iomap_write_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, + struct page *page, struct iomap *iomap, struct iomap *srcmap) { const struct iomap_page_ops *page_ops = iomap->page_ops; loff_t old_size = inode->i_size; int ret; - if (iomap->type == IOMAP_INLINE) { + if (srcmap->type == IOMAP_INLINE) { ret = iomap_write_end_inline(inode, page, iomap, pos, copied); - } else if (iomap->flags & IOMAP_F_BUFFER_HEAD) { + } else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) { ret = block_write_end(NULL, inode->i_mapping, pos, len, copied, page, NULL); } else { @@ -780,7 +782,7 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len, static loff_t iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap) + struct iomap *iomap, struct iomap *srcmap) { struct iov_iter *i = data; long status = 0; @@ -814,7 +816,8 @@ again: break; } - status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap); + status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, + srcmap); if (unlikely(status)) break; @@ -825,8 +828,8 @@ again: flush_dcache_page(page); - status = iomap_write_end(inode, pos, bytes, copied, page, - iomap); + status = iomap_write_end(inode, pos, bytes, copied, page, iomap, + srcmap); if (unlikely(status < 0)) break; copied = status; @@ -879,7 +882,7 @@ EXPORT_SYMBOL_GPL(iomap_file_buffered_write); static loff_t iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap) + struct iomap *iomap, struct iomap *srcmap) { long status = 0; ssize_t written = 0; @@ -888,7 +891,7 @@ iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data, if (!(iomap->flags & IOMAP_F_SHARED)) return length; /* don't bother with holes or unwritten extents */ - if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN) + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) return length; do { @@ -897,11 +900,12 @@ iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct page *page; status = iomap_write_begin(inode, pos, bytes, - IOMAP_WRITE_F_UNSHARE, &page, iomap); + IOMAP_WRITE_F_UNSHARE, &page, iomap, srcmap); if (unlikely(status)) return status; - status = iomap_write_end(inode, pos, bytes, bytes, page, iomap); + status = iomap_write_end(inode, pos, bytes, bytes, page, iomap, + srcmap); if (unlikely(status <= 0)) { if (WARN_ON_ONCE(status == 0)) return -EIO; @@ -940,19 +944,19 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, EXPORT_SYMBOL_GPL(iomap_file_unshare); static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset, - unsigned bytes, struct iomap *iomap) + unsigned bytes, struct iomap *iomap, struct iomap *srcmap) { struct page *page; int status; - status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap); + status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, srcmap); if (status) return status; zero_user(page, offset, bytes); mark_page_accessed(page); - return iomap_write_end(inode, pos, bytes, bytes, page, iomap); + return iomap_write_end(inode, pos, bytes, bytes, page, iomap, srcmap); } static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes, @@ -964,14 +968,14 @@ static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes, static loff_t iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { bool *did_zero = data; loff_t written = 0; int status; /* already zeroed? we're done. */ - if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN) + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) return count; do { @@ -983,7 +987,8 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count, if (IS_DAX(inode)) status = iomap_dax_zero(pos, offset, bytes, iomap); else - status = iomap_zero(inode, pos, offset, bytes, iomap); + status = iomap_zero(inode, pos, offset, bytes, iomap, + srcmap); if (status < 0) return status; @@ -1033,7 +1038,7 @@ EXPORT_SYMBOL_GPL(iomap_truncate_page); static loff_t iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { struct page *page = data; int ret; diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index da124cee1783..49bf9780e3ed 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -358,7 +358,7 @@ iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length, static loff_t iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { struct iomap_dio *dio = data; diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c index f26fdd36e383..690ef2d7c6c8 100644 --- a/fs/iomap/fiemap.c +++ b/fs/iomap/fiemap.c @@ -44,7 +44,7 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi, static loff_t iomap_fiemap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap) + struct iomap *iomap, struct iomap *srcmap) { struct fiemap_ctx *ctx = data; loff_t ret = length; @@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(iomap_fiemap); static loff_t iomap_bmap_actor(struct inode *inode, loff_t pos, loff_t length, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { sector_t *bno = data, addr; diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c index c04bad4b2b43..89f61d93c0bc 100644 --- a/fs/iomap/seek.c +++ b/fs/iomap/seek.c @@ -119,7 +119,7 @@ out: static loff_t iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { switch (iomap->type) { case IOMAP_UNWRITTEN: @@ -165,7 +165,7 @@ EXPORT_SYMBOL_GPL(iomap_seek_hole); static loff_t iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { switch (iomap->type) { case IOMAP_HOLE: diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c index 152a230f668d..a648dbf6991e 100644 --- a/fs/iomap/swapfile.c +++ b/fs/iomap/swapfile.c @@ -76,7 +76,8 @@ static int iomap_swapfile_add_extent(struct iomap_swapfile_info *isi) * distinction between written and unwritten extents. */ static loff_t iomap_swapfile_activate_actor(struct inode *inode, loff_t pos, - loff_t count, void *data, struct iomap *iomap) + loff_t count, void *data, struct iomap *iomap, + struct iomap *srcmap) { struct iomap_swapfile_info *isi = data; int error; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index f7b8b1329ddd..95719e161286 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -928,7 +928,8 @@ xfs_file_iomap_begin( loff_t offset, loff_t length, unsigned flags, - struct iomap *iomap) + struct iomap *iomap, + struct iomap *srcmap) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; @@ -1161,7 +1162,8 @@ xfs_seek_iomap_begin( loff_t offset, loff_t length, unsigned flags, - struct iomap *iomap) + struct iomap *iomap, + struct iomap *srcmap) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; @@ -1247,7 +1249,8 @@ xfs_xattr_iomap_begin( loff_t offset, loff_t length, unsigned flags, - struct iomap *iomap) + struct iomap *iomap, + struct iomap *srcmap) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 53e6e2275d3d..8b09463dae0d 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -129,7 +129,8 @@ struct iomap_ops { * The actual length is returned in iomap->length. */ int (*iomap_begin)(struct inode *inode, loff_t pos, loff_t length, - unsigned flags, struct iomap *iomap); + unsigned flags, struct iomap *iomap, + struct iomap *srcmap); /* * Commit and/or unreserve space previous allocated using iomap_begin. @@ -145,7 +146,7 @@ struct iomap_ops { * Main iomap iterator function. */ typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len, - void *data, struct iomap *iomap); + void *data, struct iomap *iomap, struct iomap *srcmap); loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, const struct iomap_ops *ops, void *data, -- cgit