From b430b7751286b3acff2d324553c8cec4f1e87764 Mon Sep 17 00:00:00 2001 From: Justin Maggard Date: Mon, 30 Oct 2017 15:29:10 -0700 Subject: [PATCH 1/5] btrfs: Fix quota reservation leak on preallocated files Commit c6887cd11149 ("Btrfs: don't do nocow check unless we have to") changed the behavior of __btrfs_buffered_write() so that it first tries to get a data space reservation, and then skips the relatively expensive nocow check if the reservation succeeded. If we have quotas enabled, the data space reservation also includes a quota reservation. But in the rewrite case, the space has already been accounted for in qgroups. So btrfs_check_data_free_space() increases the quota reservation, but it never gets decreased when the data actually gets written and overwrites the pre-existing data. So we're left with both the qgroup and qgroup reservation accounting for the same space. This commit adds the missing btrfs_qgroup_free_data() call in the case of BTRFS_ORDERED_PREALLOC extents. Fixes: c6887cd11149 ("Btrfs: don't do nocow check unless we have to") Signed-off-by: Justin Maggard Reviewed-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/inode.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 993061f83067..e1a7f3cb5be9 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3005,6 +3005,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) compress_type = ordered_extent->compress_type; if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) { BUG_ON(compress_type); + btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset, + ordered_extent->len); ret = btrfs_mark_extent_written(trans, BTRFS_I(inode), ordered_extent->file_offset, ordered_extent->file_offset + From 692826b2738101549f032a761a9191636e83be4e Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Tue, 21 Nov 2017 13:58:49 -0500 Subject: [PATCH 2/5] btrfs: handle errors while updating refcounts in update_ref_for_cow Since commit fb235dc06fa (btrfs: qgroup: Move half of the qgroup accounting time out of commit trans) the assumption that btrfs_add_delayed_{data,tree}_ref can only return 0 or -ENOMEM has been false. The qgroup operations call into btrfs_search_slot and friends and can now return the full spectrum of error codes. Fortunately, the fix here is easy since update_ref_for_cow failing is already handled so we just need to bail early with the error code. Fixes: fb235dc06fa (btrfs: qgroup: Move half of the qgroup accounting ...) Cc: # v4.11+ Signed-off-by: Jeff Mahoney Reviewed-by: Edmund Nadolski Reviewed-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/ctree.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 531e0a8645b0..1e74cf826532 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1032,14 +1032,17 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) { ret = btrfs_inc_ref(trans, root, buf, 1); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) { ret = btrfs_dec_ref(trans, root, buf, 0); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; ret = btrfs_inc_ref(trans, root, cow, 1); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; } new_flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF; } else { @@ -1049,7 +1052,8 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; } if (new_flags != 0) { int level = btrfs_header_level(buf); @@ -1068,9 +1072,11 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; ret = btrfs_dec_ref(trans, root, buf, 1); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; } clean_tree_block(fs_info, buf); *last_ref = 1; From e19182c0fff451e3744c1107d98f072e7ca377a0 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 4 Dec 2017 13:11:45 -0500 Subject: [PATCH 3/5] btrfs: fix missing error return in btrfs_drop_snapshot If btrfs_del_root fails in btrfs_drop_snapshot, we'll pick up the error but then return 0 anyway due to mixing err and ret. Fixes: 79787eaab4612 ("btrfs: replace many BUG_ONs with proper error handling") Cc: # v3.4+ Signed-off-by: Jeff Mahoney Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 784d41e95ed9..16e46ee3cd16 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -9220,6 +9220,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, ret = btrfs_del_root(trans, fs_info, &root->root_key); if (ret) { btrfs_abort_transaction(trans, ret); + err = ret; goto out_end_trans; } From 1b9e619c5bc8235cfba3dc4ced2fb0e3554a05d4 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 5 Dec 2017 22:54:02 -0800 Subject: [PATCH 4/5] Btrfs: disable FUA if mounted with nobarrier I was seeing disk flushes still happening when I mounted a Btrfs filesystem with nobarrier for testing. This is because we use FUA to write out the first super block, and on devices without FUA support, the block layer translates FUA to a flush. Even on devices supporting true FUA, using FUA when we asked for no barriers is surprising. Fixes: 387125fc722a8ed ("Btrfs: fix barrier flushes") Signed-off-by: Omar Sandoval Reviewed-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 10a2a579cc7f..a8ecccfc36de 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3231,6 +3231,7 @@ static int write_dev_supers(struct btrfs_device *device, int errors = 0; u32 crc; u64 bytenr; + int op_flags; if (max_mirrors == 0) max_mirrors = BTRFS_SUPER_MIRROR_MAX; @@ -3273,13 +3274,10 @@ static int write_dev_supers(struct btrfs_device *device, * we fua the first super. The others we allow * to go down lazy. */ - if (i == 0) { - ret = btrfsic_submit_bh(REQ_OP_WRITE, - REQ_SYNC | REQ_FUA | REQ_META | REQ_PRIO, bh); - } else { - ret = btrfsic_submit_bh(REQ_OP_WRITE, - REQ_SYNC | REQ_META | REQ_PRIO, bh); - } + op_flags = REQ_SYNC | REQ_META | REQ_PRIO; + if (i == 0 && !btrfs_test_opt(device->fs_info, NOBARRIER)) + op_flags |= REQ_FUA; + ret = btrfsic_submit_bh(REQ_OP_WRITE, op_flags, bh); if (ret) errors++; } From c8bcbfbd239ed60a6562964b58034ac8a25f4c31 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Fri, 1 Dec 2017 11:19:42 +0200 Subject: [PATCH 5/5] btrfs: Fix possible off-by-one in btrfs_search_path_in_tree The name char array passed to btrfs_search_path_in_tree is of size BTRFS_INO_LOOKUP_PATH_MAX (4080). So the actual accessible char indexes are in the range of [0, 4079]. Currently the code uses the define but this represents an off-by-one. Implications: Size of btrfs_ioctl_ino_lookup_args is 4096, so the new byte will be written to extra space, not some padding that could be provided by the allocator. btrfs-progs store the arguments on stack, but kernel does own copy of the ioctl buffer and the off-by-one overwrite does not affect userspace, but the ending 0 might be lost. Kernel ioctl buffer is allocated dynamically so we're overwriting somebody else's memory, and the ioctl is privileged if args.objectid is not 256. Which is in most cases, but resolving a subvolume stored in another directory will trigger that path. Before this patch the buffer was one byte larger, but then the -1 was not added. Fixes: ac8e9819d71f907 ("Btrfs: add search and inode lookup ioctls") Signed-off-by: Nikolay Borisov Reviewed-by: David Sterba [ added implications ] Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index fd172a93d11a..1a508fff7afe 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2206,7 +2206,7 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, if (!path) return -ENOMEM; - ptr = &name[BTRFS_INO_LOOKUP_PATH_MAX]; + ptr = &name[BTRFS_INO_LOOKUP_PATH_MAX - 1]; key.objectid = tree_id; key.type = BTRFS_ROOT_ITEM_KEY;