From 1072c12d7d58b5512b6c05c2268f57d32f1ab76c Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 16 Apr 2020 14:46:11 -0700 Subject: block: add bio_for_each_bvec_all() An upcoming Btrfs fix needs to know the original size of a non-cloned bios. Rather than accessing the bvec table directly, let's add a bio_for_each_bvec_all() accessor. Reviewed-by: Johannes Thumshirn Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- include/linux/bio.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index a0ee494a6329..8e23f51ccfa4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -169,6 +169,14 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, #define bio_for_each_bvec(bvl, bio, iter) \ __bio_for_each_bvec(bvl, bio, iter, (bio)->bi_iter) +/* + * Iterate over all multi-page bvecs. Drivers shouldn't use this version for the + * same reasons as bio_for_each_segment_all(). + */ +#define bio_for_each_bvec_all(bvl, bio, i) \ + for (i = 0, bvl = bio_first_bvec_all(bio); \ + i < (bio)->bi_vcnt; i++, bvl++) \ + #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) static inline unsigned bio_segments(struct bio *bio) -- cgit v1.2.3 From 31344b2fcead3239c5b801016d9bae82506b92c2 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 11 May 2020 14:49:10 +0200 Subject: btrfs: remove more obsolete v0 extent ref declarations The extent references v0 have been superseded long time go, there are some unused declarations of access helpers. We can safely remove them now. The struct btrfs_extent_ref_v0 is not used anywhere, but struct btrfs_extent_item_v0 is still part of a backward compatibility check in relocation.c and thus not removed. Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 9 --------- include/uapi/linux/btrfs_tree.h | 9 --------- 2 files changed, 18 deletions(-) (limited to 'include') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0b78ab0213bb..86ec25250ac5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1648,9 +1648,6 @@ BTRFS_SETGET_FUNCS(extent_generation, struct btrfs_extent_item, generation, 64); BTRFS_SETGET_FUNCS(extent_flags, struct btrfs_extent_item, flags, 64); -BTRFS_SETGET_FUNCS(extent_refs_v0, struct btrfs_extent_item_v0, refs, 32); - - BTRFS_SETGET_FUNCS(tree_block_level, struct btrfs_tree_block_info, level, 8); static inline void btrfs_tree_block_key(struct extent_buffer *eb, @@ -1698,12 +1695,6 @@ static inline u32 btrfs_extent_inline_ref_size(int type) return 0; } -BTRFS_SETGET_FUNCS(ref_root_v0, struct btrfs_extent_ref_v0, root, 64); -BTRFS_SETGET_FUNCS(ref_generation_v0, struct btrfs_extent_ref_v0, - generation, 64); -BTRFS_SETGET_FUNCS(ref_objectid_v0, struct btrfs_extent_ref_v0, objectid, 64); -BTRFS_SETGET_FUNCS(ref_count_v0, struct btrfs_extent_ref_v0, count, 32); - /* struct btrfs_node */ BTRFS_SETGET_FUNCS(key_blockptr, struct btrfs_key_ptr, blockptr, 64); BTRFS_SETGET_FUNCS(key_generation, struct btrfs_key_ptr, generation, 64); diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 8e322e2c7e78..a3f3975df0de 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -519,15 +519,6 @@ struct btrfs_extent_inline_ref { __le64 offset; } __attribute__ ((__packed__)); -/* old style backrefs item */ -struct btrfs_extent_ref_v0 { - __le64 root; - __le64 generation; - __le64 objectid; - __le32 count; -} __attribute__ ((__packed__)); - - /* dev extents record free space on individual devices. The owner * field points back to the chunk allocation mapping tree that allocated * the extent. The chunk tree uuid field is a way to double check the owner -- cgit v1.2.3 From e289f03ea79bbc6574b78ac25682555423a91cbb Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 18 May 2020 12:14:50 +0100 Subject: btrfs: fix corrupt log due to concurrent fsync of inodes with shared extents When we have extents shared amongst different inodes in the same subvolume, if we fsync them in parallel we can end up with checksum items in the log tree that represent ranges which overlap. For example, consider we have inodes A and B, both sharing an extent that covers the logical range from X to X + 64KiB: 1) Task A starts an fsync on inode A; 2) Task B starts an fsync on inode B; 3) Task A calls btrfs_csum_file_blocks(), and the first search in the log tree, through btrfs_lookup_csum(), returns -EFBIG because it finds an existing checksum item that covers the range from X - 64KiB to X; 4) Task A checks that the checksum item has not reached the maximum possible size (MAX_CSUM_ITEMS) and then releases the search path before it does another path search for insertion (through a direct call to btrfs_search_slot()); 5) As soon as task A releases the path and before it does the search for insertion, task B calls btrfs_csum_file_blocks() and gets -EFBIG too, because there is an existing checksum item that has an end offset that matches the start offset (X) of the checksum range we want to log; 6) Task B releases the path; 7) Task A does the path search for insertion (through btrfs_search_slot()) and then verifies that the checksum item that ends at offset X still exists and extends its size to insert the checksums for the range from X to X + 64KiB; 8) Task A releases the path and returns from btrfs_csum_file_blocks(), having inserted the checksums into an existing checksum item that got its size extended. At this point we have one checksum item in the log tree that covers the logical range from X - 64KiB to X + 64KiB; 9) Task B now does a search for insertion using btrfs_search_slot() too, but it finds that the previous checksum item no longer ends at the offset X, it now ends at an of offset X + 64KiB, so it leaves that item untouched. Then it releases the path and calls btrfs_insert_empty_item() that inserts a checksum item with a key offset corresponding to X and a size for inserting a single checksum (4 bytes in case of crc32c). Subsequent iterations end up extending this new checksum item so that it contains the checksums for the range from X to X + 64KiB. So after task B returns from btrfs_csum_file_blocks() we end up with two checksum items in the log tree that have overlapping ranges, one for the range from X - 64KiB to X + 64KiB, and another for the range from X to X + 64KiB. Having checksum items that represent ranges which overlap, regardless of being in the log tree or in the chekcsums tree, can lead to problems where checksums for a file range end up not being found. This type of problem has happened a few times in the past and the following commits fixed them and explain in detail why having checksum items with overlapping ranges is problematic: 27b9a8122ff71a "Btrfs: fix csum tree corruption, duplicate and outdated checksums" b84b8390d6009c "Btrfs: fix file read corruption after extent cloning and fsync" 40e046acbd2f36 "Btrfs: fix missing data checksums after replaying a log tree" Since this specific instance of the problem can only happen when logging inodes, because it is the only case where concurrent attempts to insert checksums for the same range can happen, fix the issue by using an extent io tree as a range lock to serialize checksum insertion during inode logging. This issue could often be reproduced by the test case generic/457 from fstests. When it happens it produces the following trace: BTRFS critical (device dm-0): corrupt leaf: root=18446744073709551610 block=30625792 slot=42, csum end range (15020032) goes beyond the start range (15015936) of the next csum item BTRFS info (device dm-0): leaf 30625792 gen 7 total ptrs 49 free space 2402 owner 18446744073709551610 BTRFS info (device dm-0): refs 1 lock (w:0 r:0 bw:0 br:0 sw:0 sr:0) lock_owner 0 current 15884 item 0 key (18446744073709551606 128 13979648) itemoff 3991 itemsize 4 item 1 key (18446744073709551606 128 13983744) itemoff 3987 itemsize 4 item 2 key (18446744073709551606 128 13987840) itemoff 3983 itemsize 4 item 3 key (18446744073709551606 128 13991936) itemoff 3979 itemsize 4 item 4 key (18446744073709551606 128 13996032) itemoff 3975 itemsize 4 item 5 key (18446744073709551606 128 14000128) itemoff 3971 itemsize 4 (...) BTRFS error (device dm-0): block=30625792 write time tree block corruption detected ------------[ cut here ]------------ WARNING: CPU: 1 PID: 15884 at fs/btrfs/disk-io.c:539 btree_csum_one_bio+0x268/0x2d0 [btrfs] Modules linked in: btrfs dm_thin_pool ... CPU: 1 PID: 15884 Comm: fsx Tainted: G W 5.6.0-rc7-btrfs-next-58 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 RIP: 0010:btree_csum_one_bio+0x268/0x2d0 [btrfs] Code: c7 c7 ... RSP: 0018:ffffbb0109e6f8e0 EFLAGS: 00010296 RAX: 0000000000000000 RBX: ffffe1c0847b6080 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffffaa963988 RDI: 0000000000000001 RBP: ffff956a4f4d2000 R08: 0000000000000000 R09: 0000000000000001 R10: 0000000000000526 R11: 0000000000000000 R12: ffff956a5cd28bb0 R13: 0000000000000000 R14: ffff956a649c9388 R15: 000000011ed82000 FS: 00007fb419959e80(0000) GS:ffff956a7aa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000fe6d54 CR3: 0000000138696005 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: btree_submit_bio_hook+0x67/0xc0 [btrfs] submit_one_bio+0x31/0x50 [btrfs] btree_write_cache_pages+0x2db/0x4b0 [btrfs] ? __filemap_fdatawrite_range+0xb1/0x110 do_writepages+0x23/0x80 __filemap_fdatawrite_range+0xd2/0x110 btrfs_write_marked_extents+0x15e/0x180 [btrfs] btrfs_sync_log+0x206/0x10a0 [btrfs] ? kmem_cache_free+0x315/0x3b0 ? btrfs_log_inode+0x1e8/0xf90 [btrfs] ? __mutex_unlock_slowpath+0x45/0x2a0 ? lockref_put_or_lock+0x9/0x30 ? dput+0x2d/0x580 ? dput+0xb5/0x580 ? btrfs_sync_file+0x464/0x4d0 [btrfs] btrfs_sync_file+0x464/0x4d0 [btrfs] do_fsync+0x38/0x60 __x64_sys_fsync+0x10/0x20 do_syscall_64+0x5c/0x280 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fb41953a6d0 Code: 48 3d ... RSP: 002b:00007ffcc86bd218 EFLAGS: 00000246 ORIG_RAX: 000000000000004a RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007fb41953a6d0 RDX: 0000000000000009 RSI: 0000000000040000 RDI: 0000000000000003 RBP: 0000000000040000 R08: 0000000000000001 R09: 0000000000000009 R10: 0000000000000064 R11: 0000000000000246 R12: 0000556cf4b2c060 R13: 0000000000000100 R14: 0000000000000000 R15: 0000556cf322b420 irq event stamp: 0 hardirqs last enabled at (0): [<0000000000000000>] 0x0 hardirqs last disabled at (0): [] copy_process+0x74f/0x2020 softirqs last enabled at (0): [] copy_process+0x74f/0x2020 softirqs last disabled at (0): [<0000000000000000>] 0x0 ---[ end trace d543fc76f5ad7fd8 ]--- In that trace the tree checker detected the overlapping checksum items at the time when we triggered writeback for the log tree when syncing the log. Another trace that can happen is due to BUG_ON() when deleting checksum items while logging an inode: BTRFS critical (device dm-0): slot 81 key (18446744073709551606 128 13635584) new key (18446744073709551606 128 13635584) BTRFS info (device dm-0): leaf 30949376 gen 7 total ptrs 98 free space 8527 owner 18446744073709551610 BTRFS info (device dm-0): refs 4 lock (w:1 r:0 bw:0 br:0 sw:1 sr:0) lock_owner 13473 current 13473 item 0 key (257 1 0) itemoff 16123 itemsize 160 inode generation 7 size 262144 mode 100600 item 1 key (257 12 256) itemoff 16103 itemsize 20 item 2 key (257 108 0) itemoff 16050 itemsize 53 extent data disk bytenr 13631488 nr 4096 extent data offset 0 nr 131072 ram 131072 (...) ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.c:3153! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI CPU: 1 PID: 13473 Comm: fsx Not tainted 5.6.0-rc7-btrfs-next-58 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 RIP: 0010:btrfs_set_item_key_safe+0x1ea/0x270 [btrfs] Code: 0f b6 ... RSP: 0018:ffff95e3889179d0 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000051 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffffb7763988 RDI: 0000000000000001 RBP: fffffffffffffff6 R08: 0000000000000000 R09: 0000000000000001 R10: 00000000000009ef R11: 0000000000000000 R12: ffff8912a8ba5a08 R13: ffff95e388917a06 R14: ffff89138dcf68c8 R15: ffff95e388917ace FS: 00007fe587084e80(0000) GS:ffff8913baa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe587091000 CR3: 0000000126dac005 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: btrfs_del_csums+0x2f4/0x540 [btrfs] copy_items+0x4b5/0x560 [btrfs] btrfs_log_inode+0x910/0xf90 [btrfs] btrfs_log_inode_parent+0x2a0/0xe40 [btrfs] ? dget_parent+0x5/0x370 btrfs_log_dentry_safe+0x4a/0x70 [btrfs] btrfs_sync_file+0x42b/0x4d0 [btrfs] __x64_sys_msync+0x199/0x200 do_syscall_64+0x5c/0x280 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fe586c65760 Code: 00 f7 ... RSP: 002b:00007ffe250f98b8 EFLAGS: 00000246 ORIG_RAX: 000000000000001a RAX: ffffffffffffffda RBX: 00000000000040e1 RCX: 00007fe586c65760 RDX: 0000000000000004 RSI: 0000000000006b51 RDI: 00007fe58708b000 RBP: 0000000000006a70 R08: 0000000000000003 R09: 00007fe58700cb61 R10: 0000000000000100 R11: 0000000000000246 R12: 00000000000000e1 R13: 00007fe58708b000 R14: 0000000000006b51 R15: 0000558de021a420 Modules linked in: dm_log_writes ... ---[ end trace c92a7f447a8515f5 ]--- CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 3 +++ fs/btrfs/disk-io.c | 5 ++++- fs/btrfs/extent-io-tree.h | 1 + fs/btrfs/tree-log.c | 22 +++++++++++++++++++--- include/trace/events/btrfs.h | 1 + 5 files changed, 28 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 5afeb17a3f1a..30ce7039bc27 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1167,6 +1167,9 @@ struct btrfs_root { /* Record pairs of swapped blocks for qgroup */ struct btrfs_qgroup_swapped_blocks swapped_blocks; + /* Used only by log trees, when logging csum items */ + struct extent_io_tree log_csum_range; + #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS u64 alloc_bytenr; #endif diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f2f2864f5978..f8ec2d8606fd 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1133,9 +1133,12 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, root->log_transid = 0; root->log_transid_committed = -1; root->last_log_commit = 0; - if (!dummy) + if (!dummy) { extent_io_tree_init(fs_info, &root->dirty_log_pages, IO_TREE_ROOT_DIRTY_LOG_PAGES, NULL); + extent_io_tree_init(fs_info, &root->log_csum_range, + IO_TREE_LOG_CSUM_RANGE, NULL); + } memset(&root->root_key, 0, sizeof(root->root_key)); memset(&root->root_item, 0, sizeof(root->root_item)); diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h index b4a7bad3e82e..b6561455b3c4 100644 --- a/fs/btrfs/extent-io-tree.h +++ b/fs/btrfs/extent-io-tree.h @@ -44,6 +44,7 @@ enum { IO_TREE_TRANS_DIRTY_PAGES, IO_TREE_ROOT_DIRTY_LOG_PAGES, IO_TREE_INODE_FILE_EXTENT, + IO_TREE_LOG_CSUM_RANGE, IO_TREE_SELFTEST, }; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 67fa7087f707..920cee312f4e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3290,6 +3290,7 @@ static void free_log_tree(struct btrfs_trans_handle *trans, clear_extent_bits(&log->dirty_log_pages, 0, (u64)-1, EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT); + extent_io_tree_release(&log->log_csum_range); btrfs_put_root(log); } @@ -3903,8 +3904,20 @@ static int log_csums(struct btrfs_trans_handle *trans, struct btrfs_root *log_root, struct btrfs_ordered_sum *sums) { + const u64 lock_end = sums->bytenr + sums->len - 1; + struct extent_state *cached_state = NULL; int ret; + /* + * Serialize logging for checksums. This is to avoid racing with the + * same checksum being logged by another task that is logging another + * file which happens to refer to the same extent as well. Such races + * can leave checksum items in the log with overlapping ranges. + */ + ret = lock_extent_bits(&log_root->log_csum_range, sums->bytenr, + lock_end, &cached_state); + if (ret) + return ret; /* * Due to extent cloning, we might have logged a csum item that covers a * subrange of a cloned extent, and later we can end up logging a csum @@ -3915,10 +3928,13 @@ static int log_csums(struct btrfs_trans_handle *trans, * trim and adjust) any existing csum items in the log for this range. */ ret = btrfs_del_csums(trans, log_root, sums->bytenr, sums->len); - if (ret) - return ret; + if (!ret) + ret = btrfs_csum_file_blocks(trans, log_root, sums); - return btrfs_csum_file_blocks(trans, log_root, sums); + unlock_extent_cached(&log_root->log_csum_range, sums->bytenr, lock_end, + &cached_state); + + return ret; } static noinline int copy_items(struct btrfs_trans_handle *trans, diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index bcbc763b8814..360b0f9d2220 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -89,6 +89,7 @@ TRACE_DEFINE_ENUM(COMMIT_TRANS); { IO_TREE_TRANS_DIRTY_PAGES, "TRANS_DIRTY_PAGES" }, \ { IO_TREE_ROOT_DIRTY_LOG_PAGES, "ROOT_DIRTY_LOG_PAGES" }, \ { IO_TREE_INODE_FILE_EXTENT, "INODE_FILE_EXTENT" }, \ + { IO_TREE_LOG_CSUM_RANGE, "LOG_CSUM_RANGE" }, \ { IO_TREE_SELFTEST, "SELFTEST" }) #define BTRFS_GROUP_FLAGS \ -- cgit v1.2.3 From d85dc2e116fdce776280224ed2bee4c78e5e5af2 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Fri, 30 Aug 2019 12:09:24 -0500 Subject: fs: export generic_file_buffered_read() Export generic_file_buffered_read() to be used to supplement incomplete direct reads. Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Goldwyn Rodrigues Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/fs.h | 2 ++ mm/filemap.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 45cc10cdf6dd..366c533d30cd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3124,6 +3124,8 @@ extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t *count, unsigned int flags); +extern ssize_t generic_file_buffered_read(struct kiocb *iocb, + struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/mm/filemap.c b/mm/filemap.c index 23a051a7ef0f..ad82672a9941 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1991,7 +1991,7 @@ static void shrink_readahead_size_eio(struct file_ra_state *ra) * * total number of bytes copied, including those the were already @written * * negative error code if nothing was copied */ -static ssize_t generic_file_buffered_read(struct kiocb *iocb, +ssize_t generic_file_buffered_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t written) { struct file *filp = iocb->ki_filp; @@ -2243,6 +2243,7 @@ out: file_accessed(filp); return written ? written : error; } +EXPORT_SYMBOL_GPL(generic_file_buffered_read); /** * generic_file_read_iter - generic filesystem read routine -- cgit v1.2.3 From 8cecd0ba854799cda72d03a470e7de9eed3ed6c4 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Tue, 14 May 2019 18:54:27 -0500 Subject: iomap: add a filesystem hook for direct I/O bio submission This helps filesystems to perform tasks on the bio while submitting for I/O. This could be post-write operations such as data CRC or data replication for fs-handled RAID. Reviewed-by: Johannes Thumshirn Reviewed-by: Nikolay Borisov Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Goldwyn Rodrigues Signed-off-by: David Sterba --- fs/iomap/direct-io.c | 15 ++++++++++----- include/linux/iomap.h | 2 ++ 2 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 20dde5aadcdd..f88ba6e7f6af 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -59,7 +59,7 @@ int iomap_dio_iopoll(struct kiocb *kiocb, bool spin) EXPORT_SYMBOL_GPL(iomap_dio_iopoll); static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap, - struct bio *bio) + struct bio *bio, loff_t pos) { atomic_inc(&dio->ref); @@ -67,7 +67,12 @@ static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap, bio_set_polled(bio, dio->iocb); dio->submit.last_queue = bdev_get_queue(iomap->bdev); - dio->submit.cookie = submit_bio(bio); + if (dio->dops && dio->dops->submit_io) + dio->submit.cookie = dio->dops->submit_io( + file_inode(dio->iocb->ki_filp), + iomap, bio, pos); + else + dio->submit.cookie = submit_bio(bio); } static ssize_t iomap_dio_complete(struct iomap_dio *dio) @@ -191,7 +196,7 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos, get_page(page); __bio_add_page(bio, page, len, 0); bio_set_op_attrs(bio, REQ_OP_WRITE, flags); - iomap_dio_submit_bio(dio, iomap, bio); + iomap_dio_submit_bio(dio, iomap, bio, pos); } static loff_t @@ -299,11 +304,11 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, } dio->size += n; - pos += n; copied += n; nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES); - iomap_dio_submit_bio(dio, iomap, bio); + iomap_dio_submit_bio(dio, iomap, bio, pos); + pos += n; } while (nr_pages); /* diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 8b09463dae0d..5b4875344874 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -252,6 +252,8 @@ int iomap_writepages(struct address_space *mapping, struct iomap_dio_ops { int (*end_io)(struct kiocb *iocb, ssize_t size, int error, unsigned flags); + blk_qc_t (*submit_io)(struct inode *inode, struct iomap *iomap, + struct bio *bio, loff_t file_offset); }; ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, -- cgit v1.2.3 From b75b7ca7c27dfd61dba368f390b7d4dc20b3a8cb Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Mon, 25 Nov 2019 13:24:03 -0600 Subject: fs: remove dio_end_io() Since we removed the last user of dio_end_io(), remove the helper function dio_end_io(). Reviewed-by: Nikolay Borisov Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Goldwyn Rodrigues Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/direct-io.c | 19 ------------------- include/linux/fs.h | 2 -- 2 files changed, 21 deletions(-) (limited to 'include') diff --git a/fs/direct-io.c b/fs/direct-io.c index 00b4d15bb811..c44d60f375bc 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -386,25 +386,6 @@ static void dio_bio_end_io(struct bio *bio) spin_unlock_irqrestore(&dio->bio_lock, flags); } -/** - * dio_end_io - handle the end io action for the given bio - * @bio: The direct io bio thats being completed - * - * This is meant to be called by any filesystem that uses their own dio_submit_t - * so that the DIO specific endio actions are dealt with after the filesystem - * has done it's completion work. - */ -void dio_end_io(struct bio *bio) -{ - struct dio *dio = bio->bi_private; - - if (dio->is_async) - dio_bio_end_aio(bio); - else - dio_bio_end_io(bio); -} -EXPORT_SYMBOL_GPL(dio_end_io); - static inline void dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, struct block_device *bdev, diff --git a/include/linux/fs.h b/include/linux/fs.h index 366c533d30cd..e84623d5e173 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3187,8 +3187,6 @@ enum { DIO_SKIP_HOLES = 0x02, }; -void dio_end_io(struct bio *bio); - ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, -- cgit v1.2.3