From a8fd1f71749387c9a1053a83ff1c16287499a4e7 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Thu, 15 Feb 2018 22:59:47 -0500 Subject: btrfs: use kvzalloc to allocate btrfs_fs_info The srcu_struct in btrfs_fs_info scales in size with NR_CPUS. On kernels built with NR_CPUS=8192, this can result in kmalloc failures that prevent mounting. There is work in progress to try to resolve this for every user of srcu_struct but using kvzalloc will work around the failures until that is complete. As an example with NR_CPUS=512 on x86_64: the overall size of subvol_srcu is 3460 bytes, fs_info is 6496. Signed-off-by: Jeff Mahoney Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 2 +- fs/btrfs/super.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 1a462ab85c49..0f521ba5f2f9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2974,7 +2974,7 @@ static inline void free_fs_info(struct btrfs_fs_info *fs_info) kfree(fs_info->super_copy); kfree(fs_info->super_for_commit); security_free_mnt_opts(&fs_info->security_opts); - kfree(fs_info); + kvfree(fs_info); } /* tree mod log functions from ctree.c */ diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 6e71a2a78363..4b817947e00f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1545,7 +1545,7 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, * it for searching for existing supers, so this lets us do that and * then open_ctree will properly initialize everything later. */ - fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL); + fs_info = kvzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL); if (!fs_info) { error = -ENOMEM; goto error_sec_opts; -- cgit v1.2.3 From ac01f26a27f10aace4bb89fd2c2c05a60c251832 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 8 Jan 2018 10:59:43 +0200 Subject: btrfs: handle failure of add_pending_csums add_pending_csums was added as part of the new data=ordered implementation in e6dcd2dc9c48 ("Btrfs: New data=ordered implementation"). Even back then it called the btrfs_csum_file_blocks which can fail but it never bothered handling the failure. In ENOMEM situation this could lead to the filesystem failing to write the checksums for a particular extent and not detect this. On read this could lead to the filesystem erroring out due to crc mismatch. Fix it by propagating failure from add_pending_csums and handling them. Signed-off-by: Nikolay Borisov Reviewed-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 29b491328f4e..8f7d41fcfbff 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2042,12 +2042,15 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans, struct inode *inode, struct list_head *list) { struct btrfs_ordered_sum *sum; + int ret; list_for_each_entry(sum, list, list) { trans->adding_csums = true; - btrfs_csum_file_blocks(trans, + ret = btrfs_csum_file_blocks(trans, BTRFS_I(inode)->root->fs_info->csum_root, sum); trans->adding_csums = false; + if (ret) + return ret; } return 0; } @@ -3061,7 +3064,11 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) goto out; } - add_pending_csums(trans, inode, &ordered_extent->list); + ret = add_pending_csums(trans, inode, &ordered_extent->list); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } btrfs_ordered_update_i_size(inode, 0, ordered_extent); ret = btrfs_update_inode_fallback(trans, root, inode); -- cgit v1.2.3 From 765f3cebff0023d05d724374db8b63c01e07c499 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 31 Jan 2018 17:14:02 +0200 Subject: btrfs: Handle btrfs_set_extent_delalloc failure in relocate_file_extent_cluster Essentially duplicate the error handling from the above block which handles the !PageUptodate(page) case and additionally clear EXTENT_BOUNDARY. Signed-off-by: Nikolay Borisov Reviewed-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/relocation.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index f0c3f00e97cb..cd2298d185dd 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3268,8 +3268,22 @@ static int relocate_file_extent_cluster(struct inode *inode, nr++; } - btrfs_set_extent_delalloc(inode, page_start, page_end, 0, NULL, - 0); + ret = btrfs_set_extent_delalloc(inode, page_start, page_end, 0, + NULL, 0); + if (ret) { + unlock_page(page); + put_page(page); + btrfs_delalloc_release_metadata(BTRFS_I(inode), + PAGE_SIZE); + btrfs_delalloc_release_extents(BTRFS_I(inode), + PAGE_SIZE); + + clear_extent_bits(&BTRFS_I(inode)->io_tree, + page_start, page_end, + EXTENT_LOCKED | EXTENT_BOUNDARY); + goto out; + + } set_page_dirty(page); unlock_extent(&BTRFS_I(inode)->io_tree, -- cgit v1.2.3 From 92e222df7b8f05c565009c7383321b593eca488b Mon Sep 17 00:00:00 2001 From: Hans van Kranenburg Date: Mon, 5 Feb 2018 17:45:11 +0100 Subject: btrfs: alloc_chunk: fix DUP stripe size handling In case of using DUP, we search for enough unallocated disk space on a device to hold two stripes. The devices_info[ndevs-1].max_avail that holds the amount of unallocated space found is directly assigned to stripe_size, while it's actually twice the stripe size. Later on in the code, an unconditional division of stripe_size by dev_stripes corrects the value, but in the meantime there's a check to see if the stripe_size does not exceed max_chunk_size. Since during this check stripe_size is twice the amount as intended, the check will reduce the stripe_size to max_chunk_size if the actual correct to be used stripe_size is more than half the amount of max_chunk_size. The unconditional division later tries to correct stripe_size, but will actually make sure we can't allocate more than half the max_chunk_size. Fix this by moving the division by dev_stripes before the max chunk size check, so it always contains the right value, instead of putting a duct tape division in further on to get it fixed again. Since in all other cases than DUP, dev_stripes is 1, this change only affects DUP. Other attempts in the past were made to fix this: * 37db63a400 "Btrfs: fix max chunk size check in chunk allocator" tried to fix the same problem, but still resulted in part of the code acting on a wrongly doubled stripe_size value. * 86db25785a "Btrfs: fix max chunk size on raid5/6" unintentionally broke this fix again. The real problem was already introduced with the rest of the code in 73c5de0051. The user visible result however will be that the max chunk size for DUP will suddenly double, while it's actually acting according to the limits in the code again like it was 5 years ago. Reported-by: Naohiro Aota Link: https://www.spinics.net/lists/linux-btrfs/msg69752.html Fixes: 73c5de0051 ("btrfs: quasi-round-robin for chunk allocation") Fixes: 86db25785a ("Btrfs: fix max chunk size on raid5/6") Signed-off-by: Hans van Kranenburg Reviewed-by: David Sterba [ update comment ] Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2ceb924ca0d6..b2d05c6b1c56 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4829,10 +4829,13 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, ndevs = min(ndevs, devs_max); /* - * the primary goal is to maximize the number of stripes, so use as many - * devices as possible, even if the stripes are not maximum sized. + * The primary goal is to maximize the number of stripes, so use as + * many devices as possible, even if the stripes are not maximum sized. + * + * The DUP profile stores more than one stripe per device, the + * max_avail is the total size so we have to adjust. */ - stripe_size = devices_info[ndevs-1].max_avail; + stripe_size = div_u64(devices_info[ndevs - 1].max_avail, dev_stripes); num_stripes = ndevs * dev_stripes; /* @@ -4867,8 +4870,6 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, stripe_size = devices_info[ndevs-1].max_avail; } - stripe_size = div_u64(stripe_size, dev_stripes); - /* align to BTRFS_STRIPE_LEN */ stripe_size = round_down(stripe_size, BTRFS_STRIPE_LEN); -- cgit v1.2.3 From 3c181c12c431fe33b669410d663beb9cceefcd1b Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 22 Feb 2018 21:58:42 +0800 Subject: btrfs: use proper endianness accessors for super_copy The fs_info::super_copy is a byte copy of the on-disk structure and all members must use the accessor macros/functions to obtain the right value. This was missing in update_super_roots and in sysfs readers. Moving between opposite endianness hosts will report bogus numbers in sysfs, and mount may fail as the root will not be restored correctly. If the filesystem is always used on a same endian host, this will not be a problem. Fix this by using the btrfs_set_super...() functions to set fs_info::super_copy values, and for the sysfs, use the cached fs_info::nodesize/sectorsize values. CC: stable@vger.kernel.org Fixes: df93589a17378 ("btrfs: export more from FS_INFO to sysfs") Signed-off-by: Anand Jain Reviewed-by: Liu Bo Reviewed-by: David Sterba [ update changelog ] Signed-off-by: David Sterba --- fs/btrfs/sysfs.c | 8 +++----- fs/btrfs/transaction.c | 20 ++++++++++++-------- 2 files changed, 15 insertions(+), 13 deletions(-) diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index a8bafed931f4..d11c70bff5a9 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -423,7 +423,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->nodesize); + return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->nodesize); } BTRFS_ATTR(, nodesize, btrfs_nodesize_show); @@ -433,8 +433,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return snprintf(buf, PAGE_SIZE, "%u\n", - fs_info->super_copy->sectorsize); + return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show); @@ -444,8 +443,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return snprintf(buf, PAGE_SIZE, "%u\n", - fs_info->super_copy->sectorsize); + return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 04f07144b45c..9220f004001c 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1722,19 +1722,23 @@ static void update_super_roots(struct btrfs_fs_info *fs_info) super = fs_info->super_copy; + /* update latest btrfs_super_block::chunk_root refs */ root_item = &fs_info->chunk_root->root_item; - super->chunk_root = root_item->bytenr; - super->chunk_root_generation = root_item->generation; - super->chunk_root_level = root_item->level; + btrfs_set_super_chunk_root(super, root_item->bytenr); + btrfs_set_super_chunk_root_generation(super, root_item->generation); + btrfs_set_super_chunk_root_level(super, root_item->level); + /* update latest btrfs_super_block::root refs */ root_item = &fs_info->tree_root->root_item; - super->root = root_item->bytenr; - super->generation = root_item->generation; - super->root_level = root_item->level; + btrfs_set_super_root(super, root_item->bytenr); + btrfs_set_super_generation(super, root_item->generation); + btrfs_set_super_root_level(super, root_item->level); + if (btrfs_test_opt(fs_info, SPACE_CACHE)) - super->cache_generation = root_item->generation; + btrfs_set_super_cache_generation(super, root_item->generation); if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags)) - super->uuid_tree_generation = root_item->generation; + btrfs_set_super_uuid_tree_generation(super, + root_item->generation); } int btrfs_transaction_in_commit(struct btrfs_fs_info *info) -- cgit v1.2.3 From d4dfc0f4d39475ccbbac947880b5464a74c30b99 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 6 Feb 2018 20:39:20 +0000 Subject: Btrfs: send, fix issuing write op when processing hole in no data mode When doing an incremental send of a filesystem with the no-holes feature enabled, we end up issuing a write operation when using the no data mode send flag, instead of issuing an update extent operation. Fix this by issuing the update extent operation instead. Trivial reproducer: $ mkfs.btrfs -f -O no-holes /dev/sdc $ mkfs.btrfs -f /dev/sdd $ mount /dev/sdc /mnt/sdc $ mount /dev/sdd /mnt/sdd $ xfs_io -f -c "pwrite -S 0xab 0 32K" /mnt/sdc/foobar $ btrfs subvolume snapshot -r /mnt/sdc /mnt/sdc/snap1 $ xfs_io -c "fpunch 8K 8K" /mnt/sdc/foobar $ btrfs subvolume snapshot -r /mnt/sdc /mnt/sdc/snap2 $ btrfs send /mnt/sdc/snap1 | btrfs receive /mnt/sdd $ btrfs send --no-data -p /mnt/sdc/snap1 /mnt/sdc/snap2 \ | btrfs receive -vv /mnt/sdd Before this change the output of the second receive command is: receiving snapshot snap2 uuid=f6922049-8c22-e544-9ff9-fc6755918447... utimes write foobar, offset 8192, len 8192 utimes foobar BTRFS_IOC_SET_RECEIVED_SUBVOL uuid=f6922049-8c22-e544-9ff9-... After this change it is: receiving snapshot snap2 uuid=564d36a3-ebc8-7343-aec9-bf6fda278e64... utimes update_extent foobar: offset=8192, len=8192 utimes foobar BTRFS_IOC_SET_RECEIVED_SUBVOL uuid=564d36a3-ebc8-7343-aec9-bf6fda278e64... Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/send.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index f306c608dc28..484e2af793de 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5005,6 +5005,9 @@ static int send_hole(struct send_ctx *sctx, u64 end) u64 len; int ret = 0; + if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA) + return send_update_extent(sctx, offset, end - offset); + p = fs_path_alloc(); if (!p) return -ENOMEM; -- cgit v1.2.3 From 9a6509c4daa91400b52a5fd541a5521c649a8fea Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 28 Feb 2018 15:55:40 +0000 Subject: Btrfs: fix log replay failure after linking special file and fsync If in the same transaction we rename a special file (fifo, character/block device or symbolic link), create a hard link for it having its old name then sync the log, we will end up with a log that can not be replayed and at when attempting to replay it, an EEXIST error is returned and mounting the filesystem fails. Example scenario: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt $ mkdir /mnt/testdir $ mkfifo /mnt/testdir/foo # Make sure everything done so far is durably persisted. $ sync # Create some unrelated file and fsync it, this is just to create a log # tree. The file must be in the same directory as our special file. $ touch /mnt/testdir/f1 $ xfs_io -c "fsync" /mnt/testdir/f1 # Rename our special file and then create a hard link with its old name. $ mv /mnt/testdir/foo /mnt/testdir/bar $ ln /mnt/testdir/bar /mnt/testdir/foo # Create some other unrelated file and fsync it, this is just to persist # the log tree which was modified by the previous rename and link # operations. Alternatively we could have modified file f1 and fsync it. $ touch /mnt/f2 $ xfs_io -c "fsync" /mnt/f2 $ mount /dev/sdc /mnt mount: mount /dev/sdc on /mnt failed: File exists This happens because when both the log tree and the subvolume's tree have an entry in the directory "testdir" with the same name, that is, there is one key (258 INODE_REF 257) in the subvolume tree and another one in the log tree (where 258 is the inode number of our special file and 257 is the inode for directory "testdir"). Only the data of those two keys differs, in the subvolume tree the index field for inode reference has a value of 3 while the log tree it has a value of 5. Because the same key exists in both trees, but have different index, the log replay fails with an -EEXIST error when attempting to replay the inode reference from the log tree. Fix this by setting the last_unlink_trans field of the inode (our special file) to the current transaction id when a hard link is created, as this forces logging the parent directory inode, solving the conflict at log replay time. A new generic test case for fstests was also submitted. Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 61f20c367aaf..f7a18751314a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5851,7 +5851,7 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans, * this will force the logging code to walk the dentry chain * up for the file */ - if (S_ISREG(inode->vfs_inode.i_mode)) + if (!S_ISDIR(inode->vfs_inode.i_mode)) inode->last_unlink_trans = trans->transid; /* -- cgit v1.2.3 From 1f250e929a9c9332fd6ea34da684afee73837cfe Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 28 Feb 2018 15:56:10 +0000 Subject: Btrfs: fix log replay failure after unlink and link combination If we have a file with 2 (or more) hard links in the same directory, remove one of the hard links, create a new file (or link an existing file) in the same directory with the name of the removed hard link, and then finally fsync the new file, we end up with a log that fails to replay, causing a mount failure. Example: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt $ mkdir /mnt/testdir $ touch /mnt/testdir/foo $ ln /mnt/testdir/foo /mnt/testdir/bar $ sync $ unlink /mnt/testdir/bar $ touch /mnt/testdir/bar $ xfs_io -c "fsync" /mnt/testdir/bar $ mount /dev/sdb /mnt mount: mount(2) failed: /mnt: No such file or directory When replaying the log, for that example, we also see the following in dmesg/syslog: [71813.671307] BTRFS info (device dm-0): failed to delete reference to bar, inode 258 parent 257 [71813.674204] ------------[ cut here ]------------ [71813.675694] BTRFS: Transaction aborted (error -2) [71813.677236] WARNING: CPU: 1 PID: 13231 at fs/btrfs/inode.c:4128 __btrfs_unlink_inode+0x17b/0x355 [btrfs] [71813.679669] Modules linked in: btrfs xfs f2fs dm_flakey dm_mod dax ghash_clmulni_intel ppdev pcbc aesni_intel aes_x86_64 crypto_simd cryptd glue_helper evdev psmouse i2c_piix4 parport_pc i2c_core pcspkr sg serio_raw parport button sunrpc loop autofs4 ext4 crc16 mbcache jbd2 zstd_decompress zstd_compress xxhash raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c crc32c_generic raid1 raid0 multipath linear md_mod ata_generic sd_mod virtio_scsi ata_piix libata virtio_pci virtio_ring crc32c_intel floppy virtio e1000 scsi_mod [last unloaded: btrfs] [71813.679669] CPU: 1 PID: 13231 Comm: mount Tainted: G W 4.15.0-rc9-btrfs-next-56+ #1 [71813.679669] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.2-0-g5f4c7b1-prebuilt.qemu-project.org 04/01/2014 [71813.679669] RIP: 0010:__btrfs_unlink_inode+0x17b/0x355 [btrfs] [71813.679669] RSP: 0018:ffffc90001cef738 EFLAGS: 00010286 [71813.679669] RAX: 0000000000000025 RBX: ffff880217ce4708 RCX: 0000000000000001 [71813.679669] RDX: 0000000000000000 RSI: ffffffff81c14bae RDI: 00000000ffffffff [71813.679669] RBP: ffffc90001cef7c0 R08: 0000000000000001 R09: 0000000000000001 [71813.679669] R10: ffffc90001cef5e0 R11: ffffffff8343f007 R12: ffff880217d474c8 [71813.679669] R13: 00000000fffffffe R14: ffff88021ccf1548 R15: 0000000000000101 [71813.679669] FS: 00007f7cee84c480(0000) GS:ffff88023fc80000(0000) knlGS:0000000000000000 [71813.679669] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [71813.679669] CR2: 00007f7cedc1abf9 CR3: 00000002354b4003 CR4: 00000000001606e0 [71813.679669] Call Trace: [71813.679669] btrfs_unlink_inode+0x17/0x41 [btrfs] [71813.679669] drop_one_dir_item+0xfa/0x131 [btrfs] [71813.679669] add_inode_ref+0x71e/0x851 [btrfs] [71813.679669] ? __lock_is_held+0x39/0x71 [71813.679669] ? replay_one_buffer+0x53/0x53a [btrfs] [71813.679669] replay_one_buffer+0x4a4/0x53a [btrfs] [71813.679669] ? rcu_read_unlock+0x3a/0x57 [71813.679669] ? __lock_is_held+0x39/0x71 [71813.679669] walk_up_log_tree+0x101/0x1d2 [btrfs] [71813.679669] walk_log_tree+0xad/0x188 [btrfs] [71813.679669] btrfs_recover_log_trees+0x1fa/0x31e [btrfs] [71813.679669] ? replay_one_extent+0x544/0x544 [btrfs] [71813.679669] open_ctree+0x1cf6/0x2209 [btrfs] [71813.679669] btrfs_mount_root+0x368/0x482 [btrfs] [71813.679669] ? trace_hardirqs_on_caller+0x14c/0x1a6 [71813.679669] ? __lockdep_init_map+0x176/0x1c2 [71813.679669] ? mount_fs+0x64/0x10b [71813.679669] mount_fs+0x64/0x10b [71813.679669] vfs_kern_mount+0x68/0xce [71813.679669] btrfs_mount+0x13e/0x772 [btrfs] [71813.679669] ? trace_hardirqs_on_caller+0x14c/0x1a6 [71813.679669] ? __lockdep_init_map+0x176/0x1c2 [71813.679669] ? mount_fs+0x64/0x10b [71813.679669] mount_fs+0x64/0x10b [71813.679669] vfs_kern_mount+0x68/0xce [71813.679669] do_mount+0x6e5/0x973 [71813.679669] ? memdup_user+0x3e/0x5c [71813.679669] SyS_mount+0x72/0x98 [71813.679669] entry_SYSCALL_64_fastpath+0x1e/0x8b [71813.679669] RIP: 0033:0x7f7cedf150ba [71813.679669] RSP: 002b:00007ffca71da688 EFLAGS: 00000206 [71813.679669] Code: 7f a0 e8 51 0c fd ff 48 8b 43 50 f0 0f ba a8 30 2c 00 00 02 72 17 41 83 fd fb 74 11 44 89 ee 48 c7 c7 7d 11 7f a0 e8 38 f5 8d e0 <0f> ff 44 89 e9 ba 20 10 00 00 eb 4d 48 8b 4d b0 48 8b 75 88 4c [71813.679669] ---[ end trace 83bd473fc5b4663b ]--- [71813.854764] BTRFS: error (device dm-0) in __btrfs_unlink_inode:4128: errno=-2 No such entry [71813.886994] BTRFS: error (device dm-0) in btrfs_replay_log:2307: errno=-2 No such entry (Failed to recover log tree) [71813.903357] BTRFS error (device dm-0): cleaner transaction attach returned -30 [71814.128078] BTRFS error (device dm-0): open_ctree failed This happens because the log has inode reference items for both inode 258 (the first file we created) and inode 259 (the second file created), and when processing the reference item for inode 258, we replace the corresponding item in the subvolume tree (which has two names, "foo" and "bar") witht he one in the log (which only has one name, "foo") without removing the corresponding dir index keys from the parent directory. Later, when processing the inode reference item for inode 259, which has a name of "bar" associated to it, we notice that dir index entries exist for that name and for a different inode, so we attempt to unlink that name, which fails because the inode reference item for inode 258 no longer has the name "bar" associated to it, making a call to btrfs_unlink_inode() fail with a -ENOENT error. Fix this by unlinking all the names in an inode reference item from a subvolume tree that are not present in the inode reference item found in the log tree, before overwriting it with the item from the log tree. Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 5 ++- fs/btrfs/inode-item.c | 44 ++++++++++++-------- fs/btrfs/tree-log.c | 112 ++++++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 139 insertions(+), 22 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0f521ba5f2f9..da308774b8a4 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3095,7 +3095,10 @@ btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans, u64 inode_objectid, u64 ref_objectid, int ins_len, int cow); -int btrfs_find_name_in_ext_backref(struct btrfs_path *path, +int btrfs_find_name_in_backref(struct extent_buffer *leaf, int slot, + const char *name, + int name_len, struct btrfs_inode_ref **ref_ret); +int btrfs_find_name_in_ext_backref(struct extent_buffer *leaf, int slot, u64 ref_objectid, const char *name, int name_len, struct btrfs_inode_extref **extref_ret); diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 39c968f80157..65e1a76bf755 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -22,10 +22,10 @@ #include "transaction.h" #include "print-tree.h" -static int find_name_in_backref(struct btrfs_path *path, const char *name, - int name_len, struct btrfs_inode_ref **ref_ret) +int btrfs_find_name_in_backref(struct extent_buffer *leaf, int slot, + const char *name, + int name_len, struct btrfs_inode_ref **ref_ret) { - struct extent_buffer *leaf; struct btrfs_inode_ref *ref; unsigned long ptr; unsigned long name_ptr; @@ -33,9 +33,8 @@ static int find_name_in_backref(struct btrfs_path *path, const char *name, u32 cur_offset = 0; int len; - leaf = path->nodes[0]; - item_size = btrfs_item_size_nr(leaf, path->slots[0]); - ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); + item_size = btrfs_item_size_nr(leaf, slot); + ptr = btrfs_item_ptr_offset(leaf, slot); while (cur_offset < item_size) { ref = (struct btrfs_inode_ref *)(ptr + cur_offset); len = btrfs_inode_ref_name_len(leaf, ref); @@ -44,18 +43,19 @@ static int find_name_in_backref(struct btrfs_path *path, const char *name, if (len != name_len) continue; if (memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0) { - *ref_ret = ref; + if (ref_ret) + *ref_ret = ref; return 1; } } return 0; } -int btrfs_find_name_in_ext_backref(struct btrfs_path *path, u64 ref_objectid, +int btrfs_find_name_in_ext_backref(struct extent_buffer *leaf, int slot, + u64 ref_objectid, const char *name, int name_len, struct btrfs_inode_extref **extref_ret) { - struct extent_buffer *leaf; struct btrfs_inode_extref *extref; unsigned long ptr; unsigned long name_ptr; @@ -63,9 +63,8 @@ int btrfs_find_name_in_ext_backref(struct btrfs_path *path, u64 ref_objectid, u32 cur_offset = 0; int ref_name_len; - leaf = path->nodes[0]; - item_size = btrfs_item_size_nr(leaf, path->slots[0]); - ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); + item_size = btrfs_item_size_nr(leaf, slot); + ptr = btrfs_item_ptr_offset(leaf, slot); /* * Search all extended backrefs in this item. We're only @@ -113,7 +112,9 @@ btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans, return ERR_PTR(ret); if (ret > 0) return NULL; - if (!btrfs_find_name_in_ext_backref(path, ref_objectid, name, name_len, &extref)) + if (!btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0], + ref_objectid, name, name_len, + &extref)) return NULL; return extref; } @@ -155,7 +156,8 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, * This should always succeed so error here will make the FS * readonly. */ - if (!btrfs_find_name_in_ext_backref(path, ref_objectid, + if (!btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0], + ref_objectid, name, name_len, &extref)) { btrfs_handle_fs_error(root->fs_info, -ENOENT, NULL); ret = -EROFS; @@ -225,7 +227,8 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, } else if (ret < 0) { goto out; } - if (!find_name_in_backref(path, name, name_len, &ref)) { + if (!btrfs_find_name_in_backref(path->nodes[0], path->slots[0], + name, name_len, &ref)) { ret = -ENOENT; search_ext_refs = 1; goto out; @@ -293,7 +296,9 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, ret = btrfs_insert_empty_item(trans, root, path, &key, ins_len); if (ret == -EEXIST) { - if (btrfs_find_name_in_ext_backref(path, ref_objectid, + if (btrfs_find_name_in_ext_backref(path->nodes[0], + path->slots[0], + ref_objectid, name, name_len, NULL)) goto out; @@ -351,7 +356,8 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, if (ret == -EEXIST) { u32 old_size; - if (find_name_in_backref(path, name, name_len, &ref)) + if (btrfs_find_name_in_backref(path->nodes[0], path->slots[0], + name, name_len, &ref)) goto out; old_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]); @@ -365,7 +371,9 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, ret = 0; } else if (ret < 0) { if (ret == -EOVERFLOW) { - if (find_name_in_backref(path, name, name_len, &ref)) + if (btrfs_find_name_in_backref(path->nodes[0], + path->slots[0], + name, name_len, &ref)) ret = -EEXIST; else ret = -EMLINK; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index f7a18751314a..4c50f823949c 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -966,7 +966,9 @@ static noinline int backref_in_log(struct btrfs_root *log, ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); if (key->type == BTRFS_INODE_EXTREF_KEY) { - if (btrfs_find_name_in_ext_backref(path, ref_objectid, + if (btrfs_find_name_in_ext_backref(path->nodes[0], + path->slots[0], + ref_objectid, name, namelen, NULL)) match = 1; @@ -1190,7 +1192,8 @@ static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, read_extent_buffer(eb, *name, (unsigned long)&extref->name, *namelen); - *index = btrfs_inode_extref_index(eb, extref); + if (index) + *index = btrfs_inode_extref_index(eb, extref); if (parent_objectid) *parent_objectid = btrfs_inode_extref_parent(eb, extref); @@ -1211,11 +1214,101 @@ static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, read_extent_buffer(eb, *name, (unsigned long)(ref + 1), *namelen); - *index = btrfs_inode_ref_index(eb, ref); + if (index) + *index = btrfs_inode_ref_index(eb, ref); return 0; } +/* + * Take an inode reference item from the log tree and iterate all names from the + * inode reference item in the subvolume tree with the same key (if it exists). + * For any name that is not in the inode reference item from the log tree, do a + * proper unlink of that name (that is, remove its entry from the inode + * reference item and both dir index keys). + */ +static int unlink_old_inode_refs(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct btrfs_path *path, + struct btrfs_inode *inode, + struct extent_buffer *log_eb, + int log_slot, + struct btrfs_key *key) +{ + int ret; + unsigned long ref_ptr; + unsigned long ref_end; + struct extent_buffer *eb; + +again: + btrfs_release_path(path); + ret = btrfs_search_slot(NULL, root, key, path, 0, 0); + if (ret > 0) { + ret = 0; + goto out; + } + if (ret < 0) + goto out; + + eb = path->nodes[0]; + ref_ptr = btrfs_item_ptr_offset(eb, path->slots[0]); + ref_end = ref_ptr + btrfs_item_size_nr(eb, path->slots[0]); + while (ref_ptr < ref_end) { + char *name = NULL; + int namelen; + u64 parent_id; + + if (key->type == BTRFS_INODE_EXTREF_KEY) { + ret = extref_get_fields(eb, ref_ptr, &namelen, &name, + NULL, &parent_id); + } else { + parent_id = key->offset; + ret = ref_get_fields(eb, ref_ptr, &namelen, &name, + NULL); + } + if (ret) + goto out; + + if (key->type == BTRFS_INODE_EXTREF_KEY) + ret = btrfs_find_name_in_ext_backref(log_eb, log_slot, + parent_id, name, + namelen, NULL); + else + ret = btrfs_find_name_in_backref(log_eb, log_slot, name, + namelen, NULL); + + if (!ret) { + struct inode *dir; + + btrfs_release_path(path); + dir = read_one_inode(root, parent_id); + if (!dir) { + ret = -ENOENT; + kfree(name); + goto out; + } + ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir), + inode, name, namelen); + kfree(name); + iput(dir); + if (ret) + goto out; + goto again; + } + + kfree(name); + ref_ptr += namelen; + if (key->type == BTRFS_INODE_EXTREF_KEY) + ref_ptr += sizeof(struct btrfs_inode_extref); + else + ref_ptr += sizeof(struct btrfs_inode_ref); + } + ret = 0; + out: + btrfs_release_path(path); + return ret; +} + /* * replay one inode back reference item found in the log tree. * eb, slot and key refer to the buffer and key found in the log tree. @@ -1344,6 +1437,19 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, } } + /* + * Before we overwrite the inode reference item in the subvolume tree + * with the item from the log tree, we must unlink all names from the + * parent directory that are in the subvolume's tree inode reference + * item, otherwise we end up with an inconsistent subvolume tree where + * dir index entries exist for a name but there is no inode reference + * item with the same name. + */ + ret = unlink_old_inode_refs(trans, root, path, BTRFS_I(inode), eb, slot, + key); + if (ret) + goto out; + /* finally write the back reference in the inode */ ret = overwrite_item(trans, root, path, eb, slot, key); out: -- cgit v1.2.3