From a4553fefb59cb0336f543fa567170b47e90142a9 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Fri, 25 Sep 2015 14:43:01 +0800 Subject: Btrfs: consolidate btrfs_error() to btrfs_std_error() btrfs_error() and btrfs_std_error() does the same thing and calls _btrfs_std_error(), so consolidate them together. And the main motivation is that btrfs_error() is closely named with btrfs_err(), one handles error action the other is to log the error, so don't closely name them. Signed-off-by: Anand Jain Suggested-by: David Sterba Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 0adf5422fce9..f704d1c79739 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4806,7 +4806,7 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) /* update qgroup status and info */ err = btrfs_run_qgroups(trans, root->fs_info); if (err < 0) - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "failed to update qgroup status and info\n"); err = btrfs_end_transaction(trans, root); if (err && !ret) -- cgit v1.2.3 From ecaeb14b912a3be55530aeec4e81c7243f5ceb5d Mon Sep 17 00:00:00 2001 From: David Sterba Date: Thu, 8 Oct 2015 09:01:03 +0200 Subject: btrfs: switch message printers to _in_rcu variants Signed-off-by: David Sterba --- fs/btrfs/check-integrity.c | 4 ++-- fs/btrfs/dev-replace.c | 16 ++++++++-------- fs/btrfs/ioctl.c | 2 +- fs/btrfs/scrub.c | 14 +++++++------- fs/btrfs/volumes.c | 18 +++++++++--------- 5 files changed, 27 insertions(+), 27 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 541fbfaed276..3e20630db8aa 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -845,8 +845,8 @@ static int btrfsic_process_superblock_dev_mirror( superblock_tmp->never_written = 0; superblock_tmp->mirror_num = 1 + superblock_mirror_num; if (state->print_mask & BTRFSIC_PRINT_MASK_SUPERBLOCK_WRITE) - printk_in_rcu(KERN_INFO "New initial S-block (bdev %p, %s)" - " @%llu (%s/%llu/%d)\n", + btrfs_info_in_rcu(device->dev_root->fs_info, + "new initial S-block (bdev %p, %s) @%llu (%s/%llu/%d)", superblock_bdev, rcu_str_deref(device->name), dev_bytenr, dev_state->name, dev_bytenr, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index e54dd5905cee..ede1c1ad0baf 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -379,8 +379,8 @@ int btrfs_dev_replace_start(struct btrfs_root *root, if (ret) btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret); - printk_in_rcu(KERN_INFO - "BTRFS: dev_replace from %s (devid %llu) to %s started\n", + btrfs_info_in_rcu(root->fs_info, + "dev_replace from %s (devid %llu) to %s started", src_device->missing ? "" : rcu_str_deref(src_device->name), src_device->devid, @@ -523,8 +523,8 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, src_device, tgt_device); } else { - printk_in_rcu(KERN_ERR - "BTRFS: btrfs_scrub_dev(%s, %llu, %s) failed %d\n", + btrfs_err_in_rcu(root->fs_info, + "btrfs_scrub_dev(%s, %llu, %s) failed %d", src_device->missing ? "" : rcu_str_deref(src_device->name), src_device->devid, @@ -540,8 +540,8 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, return scrub_ret; } - printk_in_rcu(KERN_INFO - "BTRFS: dev_replace from %s (devid %llu) to %s finished\n", + btrfs_info_in_rcu(root->fs_info, + "dev_replace from %s (devid %llu) to %s finished", src_device->missing ? "" : rcu_str_deref(src_device->name), src_device->devid, @@ -809,8 +809,8 @@ static int btrfs_dev_replace_kthread(void *data) progress = status_args->status.progress_1000; kfree(status_args); progress = div_u64(progress, 10); - printk_in_rcu(KERN_INFO - "BTRFS: continuing dev_replace from %s (devid %llu) to %s @%u%%\n", + btrfs_info_in_rcu(fs_info, + "continuing dev_replace from %s (devid %llu) to %s @%u%%", dev_replace->srcdev->missing ? "" : rcu_str_deref(dev_replace->srcdev->name), dev_replace->srcdev->devid, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 0adf5422fce9..8e9105af723e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1579,7 +1579,7 @@ static noinline int btrfs_ioctl_resize(struct file *file, new_size = div_u64(new_size, root->sectorsize); new_size *= root->sectorsize; - printk_in_rcu(KERN_INFO "BTRFS: new size for %s is %llu\n", + btrfs_info_in_rcu(root->fs_info, "new size for %s is %llu", rcu_str_deref(device->name), new_size); if (new_size > old_size) { diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index a39f5d1144e8..26cfbb0b867c 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -580,9 +580,9 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, * hold all of the paths here */ for (i = 0; i < ipath->fspath->elem_cnt; ++i) - printk_in_rcu(KERN_WARNING "BTRFS: %s at logical %llu on dev " + btrfs_warn_in_rcu(fs_info, "%s at logical %llu on dev " "%s, sector %llu, root %llu, inode %llu, offset %llu, " - "length %llu, links %u (path: %s)\n", swarn->errstr, + "length %llu, links %u (path: %s)", swarn->errstr, swarn->logical, rcu_str_deref(swarn->dev->name), (unsigned long long)swarn->sector, root, inum, offset, min(isize - offset, (u64)PAGE_SIZE), nlink, @@ -592,9 +592,9 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, return 0; err: - printk_in_rcu(KERN_WARNING "BTRFS: %s at logical %llu on dev " + btrfs_warn_in_rcu(fs_info, "%s at logical %llu on dev " "%s, sector %llu, root %llu, inode %llu, offset %llu: path " - "resolving failed with ret=%d\n", swarn->errstr, + "resolving failed with ret=%d", swarn->errstr, swarn->logical, rcu_str_deref(swarn->dev->name), (unsigned long long)swarn->sector, root, inum, offset, ret); @@ -649,10 +649,10 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock) ret = tree_backref_for_extent(&ptr, eb, &found_key, ei, item_size, &ref_root, &ref_level); - printk_in_rcu(KERN_WARNING - "BTRFS: %s at logical %llu on dev %s, " + btrfs_warn_in_rcu(fs_info, + "%s at logical %llu on dev %s, " "sector %llu: metadata %s (level %d) in tree " - "%llu\n", errstr, swarn.logical, + "%llu", errstr, swarn.logical, rcu_str_deref(dev->name), (unsigned long long)swarn.sector, ref_level ? "node" : "leaf", diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6fc735869c18..b0dae14242e8 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6594,8 +6594,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, BUG_ON(!path); ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1); if (ret < 0) { - printk_in_rcu(KERN_WARNING "BTRFS: " - "error %d while searching for dev_stats item for device %s!\n", + btrfs_warn_in_rcu(dev_root->fs_info, + "error %d while searching for dev_stats item for device %s", ret, rcu_str_deref(device->name)); goto out; } @@ -6605,8 +6605,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, /* need to delete old one and insert a new one */ ret = btrfs_del_item(trans, dev_root, path); if (ret != 0) { - printk_in_rcu(KERN_WARNING "BTRFS: " - "delete too small dev_stats item for device %s failed %d!\n", + btrfs_warn_in_rcu(dev_root->fs_info, + "delete too small dev_stats item for device %s failed %d", rcu_str_deref(device->name), ret); goto out; } @@ -6619,9 +6619,9 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, ret = btrfs_insert_empty_item(trans, dev_root, path, &key, sizeof(*ptr)); if (ret < 0) { - printk_in_rcu(KERN_WARNING "BTRFS: " - "insert dev_stats item for device %s failed %d!\n", - rcu_str_deref(device->name), ret); + btrfs_warn_in_rcu(dev_root->fs_info, + "insert dev_stats item for device %s failed %d", + rcu_str_deref(device->name), ret); goto out; } } @@ -6695,8 +6695,8 @@ static void btrfs_dev_stat_print_on_load(struct btrfs_device *dev) if (i == BTRFS_DEV_STAT_VALUES_MAX) return; /* all values == 0, suppress message */ - printk_in_rcu(KERN_INFO "BTRFS: " - "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n", + btrfs_info_in_rcu(dev->dev_root->fs_info, + "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u", rcu_str_deref(dev->name), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS), -- cgit v1.2.3 From f14d104dbdb5044dac9acd0e983ffb60f706c746 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Thu, 8 Oct 2015 11:37:06 +0200 Subject: btrfs: switch more printks to our helpers Convert the simple cases, not all functions provide a way to reach the fs_info. Also skipped debugging messages (print-tree, integrity checker and pr_debug) and messages that are printed from possibly unfinished mount. Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 12 ++++++------ fs/btrfs/extent_io.c | 18 ++++++++++-------- fs/btrfs/ioctl.c | 6 +++--- fs/btrfs/root-tree.c | 5 +++-- fs/btrfs/send.c | 2 +- fs/btrfs/volumes.c | 3 ++- 6 files changed, 25 insertions(+), 21 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 72553cd9ed14..5bc94d2d5699 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2347,8 +2347,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, u64 bytenr = btrfs_super_log_root(disk_super); if (fs_devices->rw_devices == 0) { - printk(KERN_WARNING "BTRFS: log replay required " - "on RO media\n"); + btrfs_warn(fs_info, "log replay required on RO media"); return -EIO; } @@ -2363,12 +2362,12 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, log_tree_root->node = read_tree_block(tree_root, bytenr, fs_info->generation + 1); if (IS_ERR(log_tree_root->node)) { - printk(KERN_ERR "BTRFS: failed to read log tree\n"); + btrfs_warn(fs_info, "failed to read log tree"); ret = PTR_ERR(log_tree_root->node); kfree(log_tree_root); return ret; } else if (!extent_buffer_uptodate(log_tree_root->node)) { - printk(KERN_ERR "BTRFS: failed to read log tree\n"); + btrfs_err(fs_info, "failed to read log tree"); free_extent_buffer(log_tree_root->node); kfree(log_tree_root); return -EIO; @@ -3294,8 +3293,9 @@ static int write_dev_supers(struct btrfs_device *device, bh = __getblk(device->bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE); if (!bh) { - printk(KERN_ERR "BTRFS: couldn't get super " - "buffer head for bytenr %Lu\n", bytenr); + btrfs_err(device->dev_root->fs_info, + "couldn't get super buffer head for bytenr %llu", + bytenr); errors++; continue; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index bb318b4e5dd0..c7a33913188b 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5563,13 +5563,15 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, unsigned long src_i; if (src_offset + len > dst->len) { - printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move " - "len %lu dst len %lu\n", src_offset, len, dst->len); + btrfs_err(dst->fs_info, + "memmove bogus src_offset %lu move " + "len %lu dst len %lu", src_offset, len, dst->len); BUG_ON(1); } if (dst_offset + len > dst->len) { - printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move " - "len %lu dst len %lu\n", dst_offset, len, dst->len); + btrfs_err(dst->fs_info, + "memmove bogus dst_offset %lu move " + "len %lu dst len %lu", dst_offset, len, dst->len); BUG_ON(1); } @@ -5609,13 +5611,13 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, unsigned long src_i; if (src_offset + len > dst->len) { - printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move " - "len %lu len %lu\n", src_offset, len, dst->len); + btrfs_err(dst->fs_info, "memmove bogus src_offset %lu move " + "len %lu len %lu", src_offset, len, dst->len); BUG_ON(1); } if (dst_offset + len > dst->len) { - printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move " - "len %lu len %lu\n", dst_offset, len, dst->len); + btrfs_err(dst->fs_info, "memmove bogus dst_offset %lu move " + "len %lu len %lu", dst_offset, len, dst->len); BUG_ON(1); } if (dst_offset < src_offset) { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8e9105af723e..2e520c635709 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1342,7 +1342,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, break; if (btrfs_defrag_cancelled(root->fs_info)) { - printk(KERN_DEBUG "BTRFS: defrag_file cancelled\n"); + btrfs_debug(root->fs_info, "defrag_file cancelled"); ret = -EAGAIN; break; } @@ -2081,7 +2081,7 @@ static noinline int search_ioctl(struct inode *inode, key.offset = (u64)-1; root = btrfs_read_fs_root_no_name(info, &key); if (IS_ERR(root)) { - printk(KERN_ERR "BTRFS: could not find root %llu\n", + btrfs_err(info, "could not find root %llu", sk->tree_id); btrfs_free_path(path); return -ENOENT; @@ -2221,7 +2221,7 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, key.offset = (u64)-1; root = btrfs_read_fs_root_no_name(info, &key); if (IS_ERR(root)) { - printk(KERN_ERR "BTRFS: could not find root %llu\n", tree_id); + btrfs_err(info, "could not find root %llu", tree_id); ret = -ENOENT; goto out; } diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 360a728a639f..42267d37bb94 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -45,12 +45,13 @@ static void btrfs_read_root_item(struct extent_buffer *eb, int slot, if (!need_reset && btrfs_root_generation(item) != btrfs_root_generation_v2(item)) { if (btrfs_root_generation_v2(item) != 0) { - printk(KERN_WARNING "BTRFS: mismatching " + btrfs_warn(eb->fs_info, + "mismatching " "generation and generation_v2 " "found in root item. This root " "was probably mounted with an " "older kernel. Resetting all " - "new fields.\n"); + "new fields."); } need_reset = 1; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index aa72bfd28f7d..4ea07c8cd6c2 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -2562,7 +2562,7 @@ verbose_printk("btrfs: send_create_inode %llu\n", ino); } else if (S_ISSOCK(mode)) { cmd = BTRFS_SEND_C_MKSOCK; } else { - printk(KERN_WARNING "btrfs: unexpected inode type %o", + btrfs_warn(sctx->send_root->fs_info, "unexpected inode type %o", (int)(mode & S_IFMT)); ret = -ENOTSUPP; goto out; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 4f80986dbf3c..7ad310cc3efb 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2352,7 +2352,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) root->fs_info->fsid); if (kobject_rename(&root->fs_info->fs_devices->super_kobj, fsid_buf)) - pr_warn("BTRFS: sysfs: failed to create fsid for sprout\n"); + btrfs_warn(root->fs_info, + "sysfs: failed to create fsid for sprout"); } root->fs_info->num_tolerated_disk_barrier_failures = -- cgit v1.2.3 From 8039d87d9e473aeb740d4fdbd59b9d2f89b2ced9 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 13 Oct 2015 15:15:00 +0100 Subject: Btrfs: fix file corruption and data loss after cloning inline extents Currently the clone ioctl allows to clone an inline extent from one file to another that already has other (non-inlined) extents. This is a problem because btrfs is not designed to deal with files having inline and regular extents, if a file has an inline extent then it must be the only extent in the file and must start at file offset 0. Having a file with an inline extent followed by regular extents results in EIO errors when doing reads or writes against the first 4K of the file. Also, the clone ioctl allows one to lose data if the source file consists of a single inline extent, with a size of N bytes, and the destination file consists of a single inline extent with a size of M bytes, where we have M > N. In this case the clone operation removes the inline extent from the destination file and then copies the inline extent from the source file into the destination file - we lose the M - N bytes from the destination file, a read operation will get the value 0x00 for any bytes in the the range [N, M] (the destination inode's i_size remained as M, that's why we can read past N bytes). So fix this by not allowing such destructive operations to happen and return errno EOPNOTSUPP to user space. Currently the fstest btrfs/035 tests the data loss case but it totally ignores this - i.e. expects the operation to succeed and does not check the we got data loss. The following test case for fstests exercises all these cases that result in file corruption and data loss: seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter # real QA test starts here _need_to_be_root _supported_fs btrfs _supported_os Linux _require_scratch _require_cloner _require_btrfs_fs_feature "no_holes" _require_btrfs_mkfs_feature "no-holes" rm -f $seqres.full test_cloning_inline_extents() { local mkfs_opts=$1 local mount_opts=$2 _scratch_mkfs $mkfs_opts >>$seqres.full 2>&1 _scratch_mount $mount_opts # File bar, the source for all the following clone operations, consists # of a single inline extent (50 bytes). $XFS_IO_PROG -f -c "pwrite -S 0xbb 0 50" $SCRATCH_MNT/bar \ | _filter_xfs_io # Test cloning into a file with an extent (non-inlined) where the # destination offset overlaps that extent. It should not be possible to # clone the inline extent from file bar into this file. $XFS_IO_PROG -f -c "pwrite -S 0xaa 0K 16K" $SCRATCH_MNT/foo \ | _filter_xfs_io $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo # Doing IO against any range in the first 4K of the file should work. # Due to a past clone ioctl bug which allowed cloning the inline extent, # these operations resulted in EIO errors. echo "File foo data after clone operation:" # All bytes should have the value 0xaa (clone operation failed and did # not modify our file). od -t x1 $SCRATCH_MNT/foo $XFS_IO_PROG -c "pwrite -S 0xcc 0 100" $SCRATCH_MNT/foo | _filter_xfs_io # Test cloning the inline extent against a file which has a hole in its # first 4K followed by a non-inlined extent. It should not be possible # as well to clone the inline extent from file bar into this file. $XFS_IO_PROG -f -c "pwrite -S 0xdd 4K 12K" $SCRATCH_MNT/foo2 \ | _filter_xfs_io $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo2 # Doing IO against any range in the first 4K of the file should work. # Due to a past clone ioctl bug which allowed cloning the inline extent, # these operations resulted in EIO errors. echo "File foo2 data after clone operation:" # All bytes should have the value 0x00 (clone operation failed and did # not modify our file). od -t x1 $SCRATCH_MNT/foo2 $XFS_IO_PROG -c "pwrite -S 0xee 0 90" $SCRATCH_MNT/foo2 | _filter_xfs_io # Test cloning the inline extent against a file which has a size of zero # but has a prealloc extent. It should not be possible as well to clone # the inline extent from file bar into this file. $XFS_IO_PROG -f -c "falloc -k 0 1M" $SCRATCH_MNT/foo3 | _filter_xfs_io $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo3 # Doing IO against any range in the first 4K of the file should work. # Due to a past clone ioctl bug which allowed cloning the inline extent, # these operations resulted in EIO errors. echo "First 50 bytes of foo3 after clone operation:" # Should not be able to read any bytes, file has 0 bytes i_size (the # clone operation failed and did not modify our file). od -t x1 $SCRATCH_MNT/foo3 $XFS_IO_PROG -c "pwrite -S 0xff 0 90" $SCRATCH_MNT/foo3 | _filter_xfs_io # Test cloning the inline extent against a file which consists of a # single inline extent that has a size not greater than the size of # bar's inline extent (40 < 50). # It should be possible to do the extent cloning from bar to this file. $XFS_IO_PROG -f -c "pwrite -S 0x01 0 40" $SCRATCH_MNT/foo4 \ | _filter_xfs_io $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo4 # Doing IO against any range in the first 4K of the file should work. echo "File foo4 data after clone operation:" # Must match file bar's content. od -t x1 $SCRATCH_MNT/foo4 $XFS_IO_PROG -c "pwrite -S 0x02 0 90" $SCRATCH_MNT/foo4 | _filter_xfs_io # Test cloning the inline extent against a file which consists of a # single inline extent that has a size greater than the size of bar's # inline extent (60 > 50). # It should not be possible to clone the inline extent from file bar # into this file. $XFS_IO_PROG -f -c "pwrite -S 0x03 0 60" $SCRATCH_MNT/foo5 \ | _filter_xfs_io $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo5 # Reading the file should not fail. echo "File foo5 data after clone operation:" # Must have a size of 60 bytes, with all bytes having a value of 0x03 # (the clone operation failed and did not modify our file). od -t x1 $SCRATCH_MNT/foo5 # Test cloning the inline extent against a file which has no extents but # has a size greater than bar's inline extent (16K > 50). # It should not be possible to clone the inline extent from file bar # into this file. $XFS_IO_PROG -f -c "truncate 16K" $SCRATCH_MNT/foo6 | _filter_xfs_io $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo6 # Reading the file should not fail. echo "File foo6 data after clone operation:" # Must have a size of 16K, with all bytes having a value of 0x00 (the # clone operation failed and did not modify our file). od -t x1 $SCRATCH_MNT/foo6 # Test cloning the inline extent against a file which has no extents but # has a size not greater than bar's inline extent (30 < 50). # It should be possible to clone the inline extent from file bar into # this file. $XFS_IO_PROG -f -c "truncate 30" $SCRATCH_MNT/foo7 | _filter_xfs_io $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo7 # Reading the file should not fail. echo "File foo7 data after clone operation:" # Must have a size of 50 bytes, with all bytes having a value of 0xbb. od -t x1 $SCRATCH_MNT/foo7 # Test cloning the inline extent against a file which has a size not # greater than the size of bar's inline extent (20 < 50) but has # a prealloc extent that goes beyond the file's size. It should not be # possible to clone the inline extent from bar into this file. $XFS_IO_PROG -f -c "falloc -k 0 1M" \ -c "pwrite -S 0x88 0 20" \ $SCRATCH_MNT/foo8 | _filter_xfs_io $CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/bar $SCRATCH_MNT/foo8 echo "File foo8 data after clone operation:" # Must have a size of 20 bytes, with all bytes having a value of 0x88 # (the clone operation did not modify our file). od -t x1 $SCRATCH_MNT/foo8 _scratch_unmount } echo -e "\nTesting without compression and without the no-holes feature...\n" test_cloning_inline_extents echo -e "\nTesting with compression and without the no-holes feature...\n" test_cloning_inline_extents "" "-o compress" echo -e "\nTesting without compression and with the no-holes feature...\n" test_cloning_inline_extents "-O no-holes" "" echo -e "\nTesting with compression and with the no-holes feature...\n" test_cloning_inline_extents "-O no-holes" "-o compress" status=0 exit Cc: stable@vger.kernel.org Signed-off-by: Filipe Manana --- fs/btrfs/ioctl.c | 195 +++++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 152 insertions(+), 43 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 80342d3fa5d2..55a735ae1453 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3328,6 +3328,150 @@ static void clone_update_extent_map(struct inode *inode, &BTRFS_I(inode)->runtime_flags); } +/* + * Make sure we do not end up inserting an inline extent into a file that has + * already other (non-inline) extents. If a file has an inline extent it can + * not have any other extents and the (single) inline extent must start at the + * file offset 0. Failing to respect these rules will lead to file corruption, + * resulting in EIO errors on read/write operations, hitting BUG_ON's in mm, etc + * + * We can have extents that have been already written to disk or we can have + * dirty ranges still in delalloc, in which case the extent maps and items are + * created only when we run delalloc, and the delalloc ranges might fall outside + * the range we are currently locking in the inode's io tree. So we check the + * inode's i_size because of that (i_size updates are done while holding the + * i_mutex, which we are holding here). + * We also check to see if the inode has a size not greater than "datal" but has + * extents beyond it, due to an fallocate with FALLOC_FL_KEEP_SIZE (and we are + * protected against such concurrent fallocate calls by the i_mutex). + * + * If the file has no extents but a size greater than datal, do not allow the + * copy because we would need turn the inline extent into a non-inline one (even + * with NO_HOLES enabled). If we find our destination inode only has one inline + * extent, just overwrite it with the source inline extent if its size is less + * than the source extent's size, or we could copy the source inline extent's + * data into the destination inode's inline extent if the later is greater then + * the former. + */ +static int clone_copy_inline_extent(struct inode *src, + struct inode *dst, + struct btrfs_trans_handle *trans, + struct btrfs_path *path, + struct btrfs_key *new_key, + const u64 drop_start, + const u64 datal, + const u64 skip, + const u64 size, + char *inline_data) +{ + struct btrfs_root *root = BTRFS_I(dst)->root; + const u64 aligned_end = ALIGN(new_key->offset + datal, + root->sectorsize); + int ret; + struct btrfs_key key; + + if (new_key->offset > 0) + return -EOPNOTSUPP; + + key.objectid = btrfs_ino(dst); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = 0; + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) { + return ret; + } else if (ret > 0) { + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + return ret; + else if (ret > 0) + goto copy_inline_extent; + } + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + if (key.objectid == btrfs_ino(dst) && + key.type == BTRFS_EXTENT_DATA_KEY) { + ASSERT(key.offset > 0); + return -EOPNOTSUPP; + } + } else if (i_size_read(dst) <= datal) { + struct btrfs_file_extent_item *ei; + u64 ext_len; + + /* + * If the file size is <= datal, make sure there are no other + * extents following (can happen do to an fallocate call with + * the flag FALLOC_FL_KEEP_SIZE). + */ + ei = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + /* + * If it's an inline extent, it can not have other extents + * following it. + */ + if (btrfs_file_extent_type(path->nodes[0], ei) == + BTRFS_FILE_EXTENT_INLINE) + goto copy_inline_extent; + + ext_len = btrfs_file_extent_num_bytes(path->nodes[0], ei); + if (ext_len > aligned_end) + return -EOPNOTSUPP; + + ret = btrfs_next_item(root, path); + if (ret < 0) { + return ret; + } else if (ret == 0) { + btrfs_item_key_to_cpu(path->nodes[0], &key, + path->slots[0]); + if (key.objectid == btrfs_ino(dst) && + key.type == BTRFS_EXTENT_DATA_KEY) + return -EOPNOTSUPP; + } + } + +copy_inline_extent: + /* + * We have no extent items, or we have an extent at offset 0 which may + * or may not be inlined. All these cases are dealt the same way. + */ + if (i_size_read(dst) > datal) { + /* + * If the destination inode has an inline extent... + * This would require copying the data from the source inline + * extent into the beginning of the destination's inline extent. + * But this is really complex, both extents can be compressed + * or just one of them, which would require decompressing and + * re-compressing data (which could increase the new compressed + * size, not allowing the compressed data to fit anymore in an + * inline extent). + * So just don't support this case for now (it should be rare, + * we are not really saving space when cloning inline extents). + */ + return -EOPNOTSUPP; + } + + btrfs_release_path(path); + ret = btrfs_drop_extents(trans, root, dst, drop_start, aligned_end, 1); + if (ret) + return ret; + ret = btrfs_insert_empty_item(trans, root, path, new_key, size); + if (ret) + return ret; + + if (skip) { + const u32 start = btrfs_file_extent_calc_inline_size(0); + + memmove(inline_data + start, inline_data + start + skip, datal); + } + + write_extent_buffer(path->nodes[0], inline_data, + btrfs_item_ptr_offset(path->nodes[0], + path->slots[0]), + size); + inode_add_bytes(dst, datal); + + return 0; +} + /** * btrfs_clone() - clone a range from inode file to another * @@ -3594,21 +3738,6 @@ process_slot: } else if (type == BTRFS_FILE_EXTENT_INLINE) { u64 skip = 0; u64 trim = 0; - u64 aligned_end = 0; - - /* - * Don't copy an inline extent into an offset - * greater than zero. Having an inline extent - * at such an offset results in chaos as btrfs - * isn't prepared for such cases. Just skip - * this case for the same reasons as commented - * at btrfs_ioctl_clone(). - */ - if (last_dest_end > 0) { - ret = -EOPNOTSUPP; - btrfs_end_transaction(trans, root); - goto out; - } if (off > key.offset) { skip = off - key.offset; @@ -3626,42 +3755,22 @@ process_slot: size -= skip + trim; datal -= skip + trim; - aligned_end = ALIGN(new_key.offset + datal, - root->sectorsize); - ret = btrfs_drop_extents(trans, root, inode, - drop_start, - aligned_end, - 1); + ret = clone_copy_inline_extent(src, inode, + trans, path, + &new_key, + drop_start, + datal, + skip, size, buf); if (ret) { if (ret != -EOPNOTSUPP) btrfs_abort_transaction(trans, - root, ret); - btrfs_end_transaction(trans, root); - goto out; - } - - ret = btrfs_insert_empty_item(trans, root, path, - &new_key, size); - if (ret) { - btrfs_abort_transaction(trans, root, - ret); + root, + ret); btrfs_end_transaction(trans, root); goto out; } - - if (skip) { - u32 start = - btrfs_file_extent_calc_inline_size(0); - memmove(buf+start, buf+start+skip, - datal); - } - leaf = path->nodes[0]; slot = path->slots[0]; - write_extent_buffer(leaf, buf, - btrfs_item_ptr_offset(leaf, slot), - size); - inode_add_bytes(inode, datal); } /* If we have an implicit hole (NO_HOLES feature). */ -- cgit v1.2.3 From d7641a49a54f66e1a323d0de6b42caeee6d33aa5 Mon Sep 17 00:00:00 2001 From: Byongho Lee Date: Tue, 1 Sep 2015 23:10:57 +0900 Subject: btrfs: replace unnecessary list_for_each_entry_safe to list_for_each_entry There is no removing list element while iterating over list. So, replace list_for_each_entry_safe to list_for_each_entry. Reviewed-by: David Sterba Signed-off-by: Byongho Lee Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 0adf5422fce9..9181e640feab 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2699,7 +2699,6 @@ static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg) { struct btrfs_ioctl_fs_info_args *fi_args; struct btrfs_device *device; - struct btrfs_device *next; struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; int ret = 0; @@ -2711,7 +2710,7 @@ static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg) fi_args->num_devices = fs_devices->num_devices; memcpy(&fi_args->fsid, root->fs_info->fsid, sizeof(fi_args->fsid)); - list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) { + list_for_each_entry(device, &fs_devices->devices, dev_list) { if (device->devid > fi_args->max_id) fi_args->max_id = device->devid; } -- cgit v1.2.3 From df480633b891cf03301d87e56024a8ec3251da5b Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 8 Sep 2015 17:25:54 +0800 Subject: btrfs: extent-tree: Switch to new delalloc space reserve and release Use new __btrfs_delalloc_reserve_space() and __btrfs_delalloc_release_space() to reserve and release space for delalloc. Signed-off-by: Qu Wenruo Signed-off-by: Chris Mason --- fs/btrfs/file.c | 5 +++-- fs/btrfs/inode-map.c | 6 +++--- fs/btrfs/inode.c | 38 +++++++++++++++++++++++--------------- fs/btrfs/ioctl.c | 14 +++++++++----- 4 files changed, 38 insertions(+), 25 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 61fb78f1ea5c..29b3702fe10d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1608,7 +1608,7 @@ again: btrfs_delalloc_release_metadata(inode, release_bytes); else - btrfs_delalloc_release_space(inode, + __btrfs_delalloc_release_space(inode, pos, release_bytes); } @@ -1661,7 +1661,8 @@ again: btrfs_end_write_no_snapshoting(root); btrfs_delalloc_release_metadata(inode, release_bytes); } else { - btrfs_delalloc_release_space(inode, release_bytes); + __btrfs_delalloc_release_space(inode, pos, + release_bytes); } } diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index d4a582ac3f73..78bc09c552ab 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -488,17 +488,17 @@ again: /* Just to make sure we have enough space */ prealloc += 8 * PAGE_CACHE_SIZE; - ret = btrfs_delalloc_reserve_space(inode, prealloc); + ret = __btrfs_delalloc_reserve_space(inode, 0, prealloc); if (ret) goto out_put; ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc, prealloc, prealloc, &alloc_hint); if (ret) { - btrfs_delalloc_release_space(inode, prealloc); + __btrfs_delalloc_release_space(inode, 0, prealloc); goto out_put; } - btrfs_free_reserved_data_space(inode, prealloc); + __btrfs_free_reserved_data_space(inode, 0, prealloc); ret = btrfs_write_out_ino_cache(root, trans, path, inode); out_put: diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c21ed7b14691..a3942a70f97d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1769,7 +1769,8 @@ static void btrfs_clear_bit_hook(struct inode *inode, if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID && do_list && !(state->state & EXTENT_NORESERVE)) - btrfs_free_reserved_data_space(inode, len); + __btrfs_free_reserved_data_space(inode, state->start, + len); __percpu_counter_add(&root->fs_info->delalloc_bytes, -len, root->fs_info->delalloc_batch); @@ -1992,7 +1993,8 @@ again: goto again; } - ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE); + ret = __btrfs_delalloc_reserve_space(inode, page_start, + PAGE_CACHE_SIZE); if (ret) { mapping_set_error(page->mapping, ret); end_extent_writepage(page, ret, page_start, page_end); @@ -4638,14 +4640,17 @@ int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len, if ((offset & (blocksize - 1)) == 0 && (!len || ((len & (blocksize - 1)) == 0))) goto out; - ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE); + ret = __btrfs_delalloc_reserve_space(inode, + round_down(from, PAGE_CACHE_SIZE), PAGE_CACHE_SIZE); if (ret) goto out; again: page = find_or_create_page(mapping, index, mask); if (!page) { - btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE); + __btrfs_delalloc_release_space(inode, + round_down(from, PAGE_CACHE_SIZE), + PAGE_CACHE_SIZE); ret = -ENOMEM; goto out; } @@ -4713,7 +4718,8 @@ again: out_unlock: if (ret) - btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE); + __btrfs_delalloc_release_space(inode, page_start, + PAGE_CACHE_SIZE); unlock_page(page); page_cache_release(page); out: @@ -7644,7 +7650,7 @@ unlock: spin_unlock(&BTRFS_I(inode)->lock); } - btrfs_free_reserved_data_space(inode, len); + __btrfs_free_reserved_data_space(inode, start, len); WARN_ON(dio_data->reserve < len); dio_data->reserve -= len; current->journal_info = dio_data; @@ -8434,7 +8440,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, mutex_unlock(&inode->i_mutex); relock = true; } - ret = btrfs_delalloc_reserve_space(inode, count); + ret = __btrfs_delalloc_reserve_space(inode, offset, count); if (ret) goto out; dio_data.outstanding_extents = div64_u64(count + @@ -8463,11 +8469,11 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, current->journal_info = NULL; if (ret < 0 && ret != -EIOCBQUEUED) { if (dio_data.reserve) - btrfs_delalloc_release_space(inode, - dio_data.reserve); + __btrfs_delalloc_release_space(inode, offset, + dio_data.reserve); } else if (ret >= 0 && (size_t)ret < count) - btrfs_delalloc_release_space(inode, - count - (size_t)ret); + __btrfs_delalloc_release_space(inode, offset, + count - (size_t)ret); } out: if (wakeup) @@ -8675,7 +8681,11 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) u64 page_end; sb_start_pagefault(inode->i_sb); - ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE); + page_start = page_offset(page); + page_end = page_start + PAGE_CACHE_SIZE - 1; + + ret = __btrfs_delalloc_reserve_space(inode, page_start, + PAGE_CACHE_SIZE); if (!ret) { ret = file_update_time(vma->vm_file); reserved = 1; @@ -8694,8 +8704,6 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) again: lock_page(page); size = i_size_read(inode); - page_start = page_offset(page); - page_end = page_start + PAGE_CACHE_SIZE - 1; if ((page->mapping != inode->i_mapping) || (page_start >= size)) { @@ -8772,7 +8780,7 @@ out_unlock: } unlock_page(page); out: - btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE); + __btrfs_delalloc_release_space(inode, page_start, PAGE_CACHE_SIZE); out_noreserve: sb_end_pagefault(inode->i_sb); return ret; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 685df7e1b24e..70732e629b0f 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1119,8 +1119,9 @@ static int cluster_pages_for_defrag(struct inode *inode, page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); - ret = btrfs_delalloc_reserve_space(inode, - page_cnt << PAGE_CACHE_SHIFT); + ret = __btrfs_delalloc_reserve_space(inode, + start_index << PAGE_CACHE_SHIFT, + page_cnt << PAGE_CACHE_SHIFT); if (ret) return ret; i_done = 0; @@ -1209,8 +1210,9 @@ again: spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); - btrfs_delalloc_release_space(inode, - (page_cnt - i_done) << PAGE_CACHE_SHIFT); + __btrfs_delalloc_release_space(inode, + start_index << PAGE_CACHE_SHIFT, + (page_cnt - i_done) << PAGE_CACHE_SHIFT); } @@ -1235,7 +1237,9 @@ out: unlock_page(pages[i]); page_cache_release(pages[i]); } - btrfs_delalloc_release_space(inode, page_cnt << PAGE_CACHE_SHIFT); + __btrfs_delalloc_release_space(inode, + start_index << PAGE_CACHE_SHIFT, + page_cnt << PAGE_CACHE_SHIFT); return ret; } -- cgit v1.2.3 From 7cf5b97650f2ecefbd5afa2d58b61b289b6e3750 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 8 Sep 2015 17:25:55 +0800 Subject: btrfs: qgroup: Cleanup old inaccurate facilities Cleanup the old facilities which use old btrfs_qgroup_reserve() function call, replace them with the newer version, and remove the "__" prefix in them. Also, make btrfs_qgroup_reserve/free() functions private, as they are now only used inside qgroup codes. Now, the whole btrfs qgroup is swithed to use the new reserve facilities. Signed-off-by: Qu Wenruo Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 12 ++---- fs/btrfs/extent-tree.c | 109 +++++-------------------------------------------- fs/btrfs/file.c | 15 ++++--- fs/btrfs/inode-map.c | 6 +-- fs/btrfs/inode.c | 34 +++++++-------- fs/btrfs/ioctl.c | 6 +-- fs/btrfs/qgroup.c | 18 ++++---- fs/btrfs/qgroup.h | 8 ---- fs/btrfs/relocation.c | 8 ++-- 9 files changed, 60 insertions(+), 156 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0f1ade133111..0d0f5d2a534a 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3452,11 +3452,9 @@ enum btrfs_reserve_flush_enum { BTRFS_RESERVE_FLUSH_ALL, }; -int btrfs_check_data_free_space(struct inode *inode, u64 bytes, u64 write_bytes); -int __btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len); +int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len); int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes); -void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes); -void __btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len); +void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len); void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans, struct btrfs_root *root); void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans); @@ -3472,10 +3470,8 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root, u64 qgroup_reserved); int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes); void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes); -int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes); -int __btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len); -void btrfs_delalloc_release_space(struct inode *inode, u64 num_bytes); -void __btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len); +int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len); +void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len); void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type); struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_root *root, unsigned short type); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 8c8d8b386cad..3a23225e83f4 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3356,7 +3356,7 @@ again: num_pages *= 16; num_pages *= PAGE_CACHE_SIZE; - ret = __btrfs_check_data_free_space(inode, 0, num_pages); + ret = btrfs_check_data_free_space(inode, 0, num_pages); if (ret) goto out_put; @@ -3365,7 +3365,7 @@ again: &alloc_hint); if (!ret) dcs = BTRFS_DC_SETUP; - __btrfs_free_reserved_data_space(inode, 0, num_pages); + btrfs_free_reserved_data_space(inode, 0, num_pages); out_put: iput(inode); @@ -4033,28 +4033,12 @@ commit_trans: return ret; } -/* - * This will check the space that the inode allocates from to make sure we have - * enough space for bytes. - */ -int btrfs_check_data_free_space(struct inode *inode, u64 bytes, u64 write_bytes) -{ - struct btrfs_root *root = BTRFS_I(inode)->root; - int ret; - - ret = btrfs_alloc_data_chunk_ondemand(inode, bytes); - if (ret < 0) - return ret; - ret = btrfs_qgroup_reserve(root, write_bytes); - return ret; -} - /* * New check_data_free_space() with ability for precious data reservation * Will replace old btrfs_check_data_free_space(), but for patch split, * add a new function first and then replace it. */ -int __btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len) +int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len) { struct btrfs_root *root = BTRFS_I(inode)->root; int ret; @@ -4073,26 +4057,6 @@ int __btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len) return ret; } -/* - * Called if we need to clear a data reservation for this inode. - */ -void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes) -{ - struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_space_info *data_sinfo; - - /* make sure bytes are sectorsize aligned */ - bytes = ALIGN(bytes, root->sectorsize); - - data_sinfo = root->fs_info->data_sinfo; - spin_lock(&data_sinfo->lock); - WARN_ON(data_sinfo->bytes_may_use < bytes); - data_sinfo->bytes_may_use -= bytes; - trace_btrfs_space_reservation(root->fs_info, "space_info", - data_sinfo->flags, bytes, 0); - spin_unlock(&data_sinfo->lock); -} - /* * Called if we need to clear a data reservation for this inode * Normally in a error case. @@ -4100,7 +4064,7 @@ void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes) * This one will handle the per-indoe data rsv map for accurate reserved * space framework. */ -void __btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len) +void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len) { struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_space_info *data_sinfo; @@ -5715,7 +5679,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes) } /** - * __btrfs_delalloc_reserve_space - reserve data and metadata space for + * btrfs_delalloc_reserve_space - reserve data and metadata space for * delalloc * @inode: inode we're writing to * @start: start range we are writing to @@ -5739,53 +5703,21 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes) * Return 0 for success * Return <0 for error(-ENOSPC or -EQUOT) */ -int __btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len) +int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len) { int ret; - ret = __btrfs_check_data_free_space(inode, start, len); + ret = btrfs_check_data_free_space(inode, start, len); if (ret < 0) return ret; ret = btrfs_delalloc_reserve_metadata(inode, len); if (ret < 0) - __btrfs_free_reserved_data_space(inode, start, len); + btrfs_free_reserved_data_space(inode, start, len); return ret; } /** - * btrfs_delalloc_reserve_space - reserve data and metadata space for delalloc - * @inode: inode we're writing to - * @num_bytes: the number of bytes we want to allocate - * - * This will do the following things - * - * o reserve space in the data space info for num_bytes - * o reserve space in the metadata space info based on number of outstanding - * extents and how much csums will be needed - * o add to the inodes ->delalloc_bytes - * o add it to the fs_info's delalloc inodes list. - * - * This will return 0 for success and -ENOSPC if there is no space left. - */ -int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes) -{ - int ret; - - ret = btrfs_check_data_free_space(inode, num_bytes, num_bytes); - if (ret) - return ret; - - ret = btrfs_delalloc_reserve_metadata(inode, num_bytes); - if (ret) { - btrfs_free_reserved_data_space(inode, num_bytes); - return ret; - } - - return 0; -} - -/** - * __btrfs_delalloc_release_space - release data and metadata space for delalloc + * btrfs_delalloc_release_space - release data and metadata space for delalloc * @inode: inode we're releasing space for * @start: start position of the space already reserved * @len: the len of the space already reserved @@ -5799,29 +5731,10 @@ int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes) * list if there are no delalloc bytes left. * Also it will handle the qgroup reserved space. */ -void __btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len) +void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len) { btrfs_delalloc_release_metadata(inode, len); - __btrfs_free_reserved_data_space(inode, start, len); -} - -/** - * btrfs_delalloc_release_space - release data and metadata space for delalloc - * @inode: inode we're releasing space for - * @num_bytes: the number of bytes we want to free up - * - * This must be matched with a call to btrfs_delalloc_reserve_space. This is - * called in the case that we don't need the metadata AND data reservations - * anymore. So if there is an error or we insert an inline extent. - * - * This function will release the metadata space that was not used and will - * decrement ->delalloc_bytes and remove it from the fs_info delalloc_inodes - * list if there are no delalloc bytes left. - */ -void btrfs_delalloc_release_space(struct inode *inode, u64 num_bytes) -{ - btrfs_delalloc_release_metadata(inode, num_bytes); - btrfs_free_reserved_data_space(inode, num_bytes); + btrfs_free_reserved_data_space(inode, start, len); } static int update_block_group(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 29b3702fe10d..47785c8a7d39 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1529,7 +1529,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, goto reserve_metadata; } } - ret = __btrfs_check_data_free_space(inode, pos, write_bytes); + ret = btrfs_check_data_free_space(inode, pos, write_bytes); if (ret < 0) break; @@ -1537,8 +1537,8 @@ reserve_metadata: ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes); if (ret) { if (!only_release_metadata) - __btrfs_free_reserved_data_space(inode, pos, - write_bytes); + btrfs_free_reserved_data_space(inode, pos, + write_bytes); else btrfs_end_write_no_snapshoting(root); break; @@ -1608,7 +1608,7 @@ again: btrfs_delalloc_release_metadata(inode, release_bytes); else - __btrfs_delalloc_release_space(inode, pos, + btrfs_delalloc_release_space(inode, pos, release_bytes); } @@ -1661,8 +1661,7 @@ again: btrfs_end_write_no_snapshoting(root); btrfs_delalloc_release_metadata(inode, release_bytes); } else { - __btrfs_delalloc_release_space(inode, pos, - release_bytes); + btrfs_delalloc_release_space(inode, pos, release_bytes); } } @@ -2708,8 +2707,8 @@ static long btrfs_fallocate(struct file *file, int mode, out: mutex_unlock(&inode->i_mutex); /* Let go of our reservation. */ - __btrfs_free_reserved_data_space(inode, alloc_start, - alloc_end - alloc_start); + btrfs_free_reserved_data_space(inode, alloc_start, + alloc_end - alloc_start); return ret; } diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 78bc09c552ab..767a6056ac45 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -488,17 +488,17 @@ again: /* Just to make sure we have enough space */ prealloc += 8 * PAGE_CACHE_SIZE; - ret = __btrfs_delalloc_reserve_space(inode, 0, prealloc); + ret = btrfs_delalloc_reserve_space(inode, 0, prealloc); if (ret) goto out_put; ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc, prealloc, prealloc, &alloc_hint); if (ret) { - __btrfs_delalloc_release_space(inode, 0, prealloc); + btrfs_delalloc_release_space(inode, 0, prealloc); goto out_put; } - __btrfs_free_reserved_data_space(inode, 0, prealloc); + btrfs_free_reserved_data_space(inode, 0, prealloc); ret = btrfs_write_out_ino_cache(root, trans, path, inode); out_put: diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a3942a70f97d..a34e5a9c51cb 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1769,8 +1769,8 @@ static void btrfs_clear_bit_hook(struct inode *inode, if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID && do_list && !(state->state & EXTENT_NORESERVE)) - __btrfs_free_reserved_data_space(inode, state->start, - len); + btrfs_free_reserved_data_space(inode, state->start, + len); __percpu_counter_add(&root->fs_info->delalloc_bytes, -len, root->fs_info->delalloc_batch); @@ -1993,8 +1993,8 @@ again: goto again; } - ret = __btrfs_delalloc_reserve_space(inode, page_start, - PAGE_CACHE_SIZE); + ret = btrfs_delalloc_reserve_space(inode, page_start, + PAGE_CACHE_SIZE); if (ret) { mapping_set_error(page->mapping, ret); end_extent_writepage(page, ret, page_start, page_end); @@ -4640,7 +4640,7 @@ int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len, if ((offset & (blocksize - 1)) == 0 && (!len || ((len & (blocksize - 1)) == 0))) goto out; - ret = __btrfs_delalloc_reserve_space(inode, + ret = btrfs_delalloc_reserve_space(inode, round_down(from, PAGE_CACHE_SIZE), PAGE_CACHE_SIZE); if (ret) goto out; @@ -4648,7 +4648,7 @@ int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len, again: page = find_or_create_page(mapping, index, mask); if (!page) { - __btrfs_delalloc_release_space(inode, + btrfs_delalloc_release_space(inode, round_down(from, PAGE_CACHE_SIZE), PAGE_CACHE_SIZE); ret = -ENOMEM; @@ -4718,8 +4718,8 @@ again: out_unlock: if (ret) - __btrfs_delalloc_release_space(inode, page_start, - PAGE_CACHE_SIZE); + btrfs_delalloc_release_space(inode, page_start, + PAGE_CACHE_SIZE); unlock_page(page); page_cache_release(page); out: @@ -7650,7 +7650,7 @@ unlock: spin_unlock(&BTRFS_I(inode)->lock); } - __btrfs_free_reserved_data_space(inode, start, len); + btrfs_free_reserved_data_space(inode, start, len); WARN_ON(dio_data->reserve < len); dio_data->reserve -= len; current->journal_info = dio_data; @@ -8440,7 +8440,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, mutex_unlock(&inode->i_mutex); relock = true; } - ret = __btrfs_delalloc_reserve_space(inode, offset, count); + ret = btrfs_delalloc_reserve_space(inode, offset, count); if (ret) goto out; dio_data.outstanding_extents = div64_u64(count + @@ -8469,11 +8469,11 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, current->journal_info = NULL; if (ret < 0 && ret != -EIOCBQUEUED) { if (dio_data.reserve) - __btrfs_delalloc_release_space(inode, offset, - dio_data.reserve); + btrfs_delalloc_release_space(inode, offset, + dio_data.reserve); } else if (ret >= 0 && (size_t)ret < count) - __btrfs_delalloc_release_space(inode, offset, - count - (size_t)ret); + btrfs_delalloc_release_space(inode, offset, + count - (size_t)ret); } out: if (wakeup) @@ -8684,8 +8684,8 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) page_start = page_offset(page); page_end = page_start + PAGE_CACHE_SIZE - 1; - ret = __btrfs_delalloc_reserve_space(inode, page_start, - PAGE_CACHE_SIZE); + ret = btrfs_delalloc_reserve_space(inode, page_start, + PAGE_CACHE_SIZE); if (!ret) { ret = file_update_time(vma->vm_file); reserved = 1; @@ -8780,7 +8780,7 @@ out_unlock: } unlock_page(page); out: - __btrfs_delalloc_release_space(inode, page_start, PAGE_CACHE_SIZE); + btrfs_delalloc_release_space(inode, page_start, PAGE_CACHE_SIZE); out_noreserve: sb_end_pagefault(inode->i_sb); return ret; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 70732e629b0f..7ed033a84212 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1119,7 +1119,7 @@ static int cluster_pages_for_defrag(struct inode *inode, page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); - ret = __btrfs_delalloc_reserve_space(inode, + ret = btrfs_delalloc_reserve_space(inode, start_index << PAGE_CACHE_SHIFT, page_cnt << PAGE_CACHE_SHIFT); if (ret) @@ -1210,7 +1210,7 @@ again: spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); - __btrfs_delalloc_release_space(inode, + btrfs_delalloc_release_space(inode, start_index << PAGE_CACHE_SHIFT, (page_cnt - i_done) << PAGE_CACHE_SHIFT); } @@ -1237,7 +1237,7 @@ out: unlock_page(pages[i]); page_cache_release(pages[i]); } - __btrfs_delalloc_release_space(inode, + btrfs_delalloc_release_space(inode, start_index << PAGE_CACHE_SHIFT, page_cnt << PAGE_CACHE_SHIFT); return ret; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 897a49d71638..7d5339da01b8 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2035,7 +2035,7 @@ out: return ret; } -int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes) +static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes) { struct btrfs_root *quota_root; struct btrfs_qgroup *qgroup; @@ -2168,6 +2168,11 @@ out: spin_unlock(&fs_info->qgroup_lock); } +static inline void qgroup_free(struct btrfs_root *root, u64 num_bytes) +{ + return btrfs_qgroup_free_refroot(root->fs_info, root->objectid, + num_bytes); +} void assert_qgroups_uptodate(struct btrfs_trans_handle *trans) { if (list_empty(&trans->qgroup_ref_list) && !trans->delayed_ref_elem.seq) @@ -2517,7 +2522,7 @@ int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len) &changeset); if (ret < 0) goto cleanup; - ret = btrfs_qgroup_reserve(root, changeset.bytes_changed); + ret = qgroup_reserve(root, changeset.bytes_changed); if (ret < 0) goto cleanup; @@ -2553,8 +2558,7 @@ static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len, goto out; if (free) - btrfs_qgroup_free(BTRFS_I(inode)->root, - changeset.bytes_changed); + qgroup_free(BTRFS_I(inode)->root, changeset.bytes_changed); out: ulist_free(changeset.range_changed); return ret; @@ -2604,7 +2608,7 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes) return 0; BUG_ON(num_bytes != round_down(num_bytes, root->nodesize)); - ret = btrfs_qgroup_reserve(root, num_bytes); + ret = qgroup_reserve(root, num_bytes); if (ret < 0) return ret; atomic_add(num_bytes, &root->qgroup_meta_rsv); @@ -2621,7 +2625,7 @@ void btrfs_qgroup_free_meta_all(struct btrfs_root *root) reserved = atomic_xchg(&root->qgroup_meta_rsv, 0); if (reserved == 0) return; - btrfs_qgroup_free(root, reserved); + qgroup_free(root, reserved); } void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes) @@ -2632,5 +2636,5 @@ void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes) BUG_ON(num_bytes != round_down(num_bytes, root->nodesize)); WARN_ON(atomic_read(&root->qgroup_meta_rsv) < num_bytes); atomic_sub(num_bytes, &root->qgroup_meta_rsv); - btrfs_qgroup_free(root, num_bytes); + qgroup_free(root, num_bytes); } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 7d1c87cd3c78..adb03da3d298 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -71,15 +71,8 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans, int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid, struct btrfs_qgroup_inherit *inherit); -int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes); void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info, u64 ref_root, u64 num_bytes); -static inline void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes) -{ - return btrfs_qgroup_free_refroot(root->fs_info, root->objectid, - num_bytes); -} - /* * TODO: Add proper trace point for it, as btrfs_qgroup_free() is * called by everywhere, can't provide good trace for delayed ref case. @@ -89,7 +82,6 @@ static inline void btrfs_qgroup_free_delayed_ref(struct btrfs_fs_info *fs_info, { btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes); } - void assert_qgroups_uptodate(struct btrfs_trans_handle *trans); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 490c9e298c58..a7dc45622e90 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3034,8 +3034,8 @@ int prealloc_file_extent_cluster(struct inode *inode, BUG_ON(cluster->start != cluster->boundary[0]); mutex_lock(&inode->i_mutex); - ret = __btrfs_check_data_free_space(inode, cluster->start, - cluster->end + 1 - cluster->start); + ret = btrfs_check_data_free_space(inode, cluster->start, + cluster->end + 1 - cluster->start); if (ret) goto out; @@ -3056,8 +3056,8 @@ int prealloc_file_extent_cluster(struct inode *inode, break; nr++; } - __btrfs_free_reserved_data_space(inode, cluster->start, - cluster->end + 1 - cluster->start); + btrfs_free_reserved_data_space(inode, cluster->start, + cluster->end + 1 - cluster->start); out: mutex_unlock(&inode->i_mutex); return ret; -- cgit v1.2.3 From b06c4bf5c874a57254b197f53ddf588e7a24a2bf Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 23 Oct 2015 07:52:54 +0100 Subject: Btrfs: fix regression running delayed references when using qgroups MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the kernel 4.2 merge window we had a big changes to the implementation of delayed references and qgroups which made the no_quota field of delayed references not used anymore. More specifically the no_quota field is not used anymore as of: commit 0ed4792af0e8 ("btrfs: qgroup: Switch to new extent-oriented qgroup mechanism.") Leaving the no_quota field actually prevents delayed references from getting merged, which in turn cause the following BUG_ON(), at fs/btrfs/extent-tree.c, to be hit when qgroups are enabled: static int run_delayed_tree_ref(...) { (...) BUG_ON(node->ref_mod != 1); (...) } This happens on a scenario like the following: 1) Ref1 bytenr X, action = BTRFS_ADD_DELAYED_REF, no_quota = 1, added. 2) Ref2 bytenr X, action = BTRFS_DROP_DELAYED_REF, no_quota = 0, added. It's not merged with Ref1 because Ref1->no_quota != Ref2->no_quota. 3) Ref3 bytenr X, action = BTRFS_ADD_DELAYED_REF, no_quota = 1, added. It's not merged with the reference at the tail of the list of refs for bytenr X because the reference at the tail, Ref2 is incompatible due to Ref2->no_quota != Ref3->no_quota. 4) Ref4 bytenr X, action = BTRFS_DROP_DELAYED_REF, no_quota = 0, added. It's not merged with the reference at the tail of the list of refs for bytenr X because the reference at the tail, Ref3 is incompatible due to Ref3->no_quota != Ref4->no_quota. 5) We run delayed references, trigger merging of delayed references, through __btrfs_run_delayed_refs() -> btrfs_merge_delayed_refs(). 6) Ref1 and Ref3 are merged as Ref1->no_quota = Ref3->no_quota and all other conditions are satisfied too. So Ref1 gets a ref_mod value of 2. 7) Ref2 and Ref4 are merged as Ref2->no_quota = Ref4->no_quota and all other conditions are satisfied too. So Ref2 gets a ref_mod value of 2. 8) Ref1 and Ref2 aren't merged, because they have different values for their no_quota field. 9) Delayed reference Ref1 is picked for running (select_delayed_ref() always prefers references with an action == BTRFS_ADD_DELAYED_REF). So run_delayed_tree_ref() is called for Ref1 which triggers the BUG_ON because Ref1->red_mod != 1 (equals 2). So fix this by removing the no_quota field, as it's not used anymore as of commit 0ed4792af0e8 ("btrfs: qgroup: Switch to new extent-oriented qgroup mechanism."). The use of no_quota was also buggy in at least two places: 1) At delayed-refs.c:btrfs_add_delayed_tree_ref() - we were setting no_quota to 0 instead of 1 when the following condition was true: is_fstree(ref_root) || !fs_info->quota_enabled 2) At extent-tree.c:__btrfs_inc_extent_ref() - we were attempting to reset a node's no_quota when the condition "!is_fstree(root_objectid) || !root->fs_info->quota_enabled" was true but we did it only in an unused local stack variable, that is, we never reset the no_quota value in the node itself. This fixes the remainder of problems several people have been having when running delayed references, mostly while a balance is running in parallel, on a 4.2+ kernel. Very special thanks to Stéphane Lesimple for helping debugging this issue and testing this fix on his multi terabyte filesystem (which took more than one day to balance alone, plus fsck, etc). Also, this fixes deadlock issue when using the clone ioctl with qgroups enabled, as reported by Elias Probst in the mailing list. The deadlock happens because after calling btrfs_insert_empty_item we have our path holding a write lock on a leaf of the fs/subvol tree and then before releasing the path we called check_ref() which did backref walking, when qgroups are enabled, and tried to read lock the same leaf. The trace for this case is the following: INFO: task systemd-nspawn:6095 blocked for more than 120 seconds. (...) Call Trace: [] schedule+0x74/0x83 [] btrfs_tree_read_lock+0xc0/0xea [] ? wait_woken+0x74/0x74 [] btrfs_search_old_slot+0x51a/0x810 [] btrfs_next_old_leaf+0xdf/0x3ce [] ? ulist_add_merge+0x1b/0x127 [] __resolve_indirect_refs+0x62a/0x667 [] ? btrfs_clear_lock_blocking_rw+0x78/0xbe [] find_parent_nodes+0xaf3/0xfc6 [] __btrfs_find_all_roots+0x92/0xf0 [] btrfs_find_all_roots+0x45/0x65 [] ? btrfs_get_tree_mod_seq+0x2b/0x88 [] check_ref+0x64/0xc4 [] btrfs_clone+0x66e/0xb5d [] btrfs_ioctl_clone+0x48f/0x5bb [] ? native_sched_clock+0x28/0x77 [] btrfs_ioctl+0xabc/0x25cb (...) The problem goes away by eleminating check_ref(), which no longer is needed as its purpose was to get a value for the no_quota field of a delayed reference (this patch removes the no_quota field as mentioned earlier). Reported-by: Stéphane Lesimple Tested-by: Stéphane Lesimple Reported-by: Elias Probst Reported-by: Peter Becker Reported-by: Malte Schröder Reported-by: Derek Dongray Reported-by: Erkki Seppala Cc: stable@vger.kernel.org # 4.2+ Signed-off-by: Filipe Manana Reviewed-by: Qu Wenruo --- fs/btrfs/ctree.h | 4 ++-- fs/btrfs/delayed-ref.c | 28 +++++++---------------- fs/btrfs/delayed-ref.h | 7 ++---- fs/btrfs/extent-tree.c | 45 +++++++++++++----------------------- fs/btrfs/file.c | 10 ++++---- fs/btrfs/inode.c | 4 ++-- fs/btrfs/ioctl.c | 62 +------------------------------------------------- fs/btrfs/relocation.c | 16 ++++++------- fs/btrfs/tree-log.c | 2 +- 9 files changed, 44 insertions(+), 134 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index bc3c711e82f2..3fa3c3b7bb66 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3422,7 +3422,7 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, - u64 owner, u64 offset, int no_quota); + u64 owner, u64 offset); int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len, int delalloc); @@ -3435,7 +3435,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset, int no_quota); + u64 root_objectid, u64 owner, u64 offset); int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans, struct btrfs_root *root); diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 2f4158034c24..1c3588a70ce6 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -220,7 +220,7 @@ static bool merge_ref(struct btrfs_trans_handle *trans, if (seq && next->seq >= seq) goto next; - if (next->type != ref->type || next->no_quota != ref->no_quota) + if (next->type != ref->type) goto next; if ((ref->type == BTRFS_TREE_BLOCK_REF_KEY || @@ -405,8 +405,7 @@ add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans, exist = list_entry(href->ref_list.prev, struct btrfs_delayed_ref_node, list); /* No need to compare bytenr nor is_head */ - if (exist->type != ref->type || exist->no_quota != ref->no_quota || - exist->seq != ref->seq) + if (exist->type != ref->type || exist->seq != ref->seq) goto add_tail; if ((exist->type == BTRFS_TREE_BLOCK_REF_KEY || @@ -639,7 +638,7 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_head *head_ref, struct btrfs_delayed_ref_node *ref, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, - int action, int no_quota) + int action) { struct btrfs_delayed_tree_ref *full_ref; struct btrfs_delayed_ref_root *delayed_refs; @@ -661,7 +660,6 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info, ref->action = action; ref->is_head = 0; ref->in_tree = 1; - ref->no_quota = no_quota; ref->seq = seq; full_ref = btrfs_delayed_node_to_tree_ref(ref); @@ -694,7 +692,7 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_head *head_ref, struct btrfs_delayed_ref_node *ref, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, u64 owner, - u64 offset, int action, int no_quota) + u64 offset, int action) { struct btrfs_delayed_data_ref *full_ref; struct btrfs_delayed_ref_root *delayed_refs; @@ -717,7 +715,6 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info, ref->action = action; ref->is_head = 0; ref->in_tree = 1; - ref->no_quota = no_quota; ref->seq = seq; full_ref = btrfs_delayed_node_to_data_ref(ref); @@ -748,17 +745,13 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, int action, - struct btrfs_delayed_extent_op *extent_op, - int no_quota) + struct btrfs_delayed_extent_op *extent_op) { struct btrfs_delayed_tree_ref *ref; struct btrfs_delayed_ref_head *head_ref; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_qgroup_extent_record *record = NULL; - if (!is_fstree(ref_root) || !fs_info->quota_enabled) - no_quota = 0; - BUG_ON(extent_op && extent_op->is_data); ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS); if (!ref) @@ -787,8 +780,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, bytenr, num_bytes, action, 0); add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr, - num_bytes, parent, ref_root, level, action, - no_quota); + num_bytes, parent, ref_root, level, action); spin_unlock(&delayed_refs->lock); return 0; @@ -809,17 +801,13 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, u64 owner, u64 offset, int action, - struct btrfs_delayed_extent_op *extent_op, - int no_quota) + struct btrfs_delayed_extent_op *extent_op) { struct btrfs_delayed_data_ref *ref; struct btrfs_delayed_ref_head *head_ref; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_qgroup_extent_record *record = NULL; - if (!is_fstree(ref_root) || !fs_info->quota_enabled) - no_quota = 0; - BUG_ON(extent_op && !extent_op->is_data); ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS); if (!ref) @@ -855,7 +843,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr, num_bytes, parent, ref_root, owner, offset, - action, no_quota); + action); spin_unlock(&delayed_refs->lock); return 0; diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index d4c41e26101c..f9cf2345b864 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -68,7 +68,6 @@ struct btrfs_delayed_ref_node { unsigned int action:8; unsigned int type:8; - unsigned int no_quota:1; /* is this node still in the rbtree? */ unsigned int is_head:1; unsigned int in_tree:1; @@ -244,15 +243,13 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, int action, - struct btrfs_delayed_extent_op *extent_op, - int no_quota); + struct btrfs_delayed_extent_op *extent_op); int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, u64 owner, u64 offset, int action, - struct btrfs_delayed_extent_op *extent_op, - int no_quota); + struct btrfs_delayed_extent_op *extent_op); int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 ref_root, u64 bytenr, u64 num_bytes); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index c0f30f5d8a41..c1f8c7e27a6d 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -95,8 +95,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 parent, u64 root_objectid, u64 flags, struct btrfs_disk_key *key, - int level, struct btrfs_key *ins, - int no_quota); + int level, struct btrfs_key *ins); static int do_chunk_alloc(struct btrfs_trans_handle *trans, struct btrfs_root *extent_root, u64 flags, int force); @@ -2073,8 +2072,7 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset, - int no_quota) + u64 root_objectid, u64 owner, u64 offset) { int ret; struct btrfs_fs_info *fs_info = root->fs_info; @@ -2086,12 +2084,12 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr, num_bytes, parent, root_objectid, (int)owner, - BTRFS_ADD_DELAYED_REF, NULL, no_quota); + BTRFS_ADD_DELAYED_REF, NULL); } else { ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, num_bytes, parent, root_objectid, owner, offset, - BTRFS_ADD_DELAYED_REF, NULL, no_quota); + BTRFS_ADD_DELAYED_REF, NULL); } return ret; } @@ -2112,15 +2110,11 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, u64 num_bytes = node->num_bytes; u64 refs; int ret; - int no_quota = node->no_quota; path = btrfs_alloc_path(); if (!path) return -ENOMEM; - if (!is_fstree(root_objectid) || !root->fs_info->quota_enabled) - no_quota = 1; - path->reada = 1; path->leave_spinning = 1; /* this will setup the path even if it fails to insert the back ref */ @@ -2355,8 +2349,7 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, parent, ref_root, extent_op->flags_to_set, &extent_op->key, - ref->level, &ins, - node->no_quota); + ref->level, &ins); } else if (node->action == BTRFS_ADD_DELAYED_REF) { ret = __btrfs_inc_extent_ref(trans, root, node, parent, ref_root, @@ -3192,7 +3185,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, int level; int ret = 0; int (*process_func)(struct btrfs_trans_handle *, struct btrfs_root *, - u64, u64, u64, u64, u64, u64, int); + u64, u64, u64, u64, u64, u64); if (btrfs_test_is_dummy_root(root)) @@ -3233,15 +3226,14 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, key.offset -= btrfs_file_extent_offset(buf, fi); ret = process_func(trans, root, bytenr, num_bytes, parent, ref_root, key.objectid, - key.offset, 1); + key.offset); if (ret) goto fail; } else { bytenr = btrfs_node_blockptr(buf, i); num_bytes = root->nodesize; ret = process_func(trans, root, bytenr, num_bytes, - parent, ref_root, level - 1, 0, - 1); + parent, ref_root, level - 1, 0); if (ret) goto fail; } @@ -6431,7 +6423,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, int extent_slot = 0; int found_extent = 0; int num_to_del = 1; - int no_quota = node->no_quota; u32 item_size; u64 refs; u64 bytenr = node->bytenr; @@ -6440,9 +6431,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, bool skinny_metadata = btrfs_fs_incompat(root->fs_info, SKINNY_METADATA); - if (!info->quota_enabled || !is_fstree(root_objectid)) - no_quota = 1; - path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -6768,7 +6756,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, buf->start, buf->len, parent, root->root_key.objectid, btrfs_header_level(buf), - BTRFS_DROP_DELAYED_REF, NULL, 0); + BTRFS_DROP_DELAYED_REF, NULL); BUG_ON(ret); /* -ENOMEM */ } @@ -6816,7 +6804,7 @@ out: /* Can return -ENOMEM */ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, - u64 owner, u64 offset, int no_quota) + u64 owner, u64 offset) { int ret; struct btrfs_fs_info *fs_info = root->fs_info; @@ -6839,13 +6827,13 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr, num_bytes, parent, root_objectid, (int)owner, - BTRFS_DROP_DELAYED_REF, NULL, no_quota); + BTRFS_DROP_DELAYED_REF, NULL); } else { ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, num_bytes, parent, root_objectid, owner, offset, BTRFS_DROP_DELAYED_REF, - NULL, no_quota); + NULL); } return ret; } @@ -7690,8 +7678,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 parent, u64 root_objectid, u64 flags, struct btrfs_disk_key *key, - int level, struct btrfs_key *ins, - int no_quota) + int level, struct btrfs_key *ins) { int ret; struct btrfs_fs_info *fs_info = root->fs_info; @@ -7781,7 +7768,7 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, ret = btrfs_add_delayed_data_ref(root->fs_info, trans, ins->objectid, ins->offset, 0, root_objectid, owner, offset, - BTRFS_ADD_DELAYED_EXTENT, NULL, 0); + BTRFS_ADD_DELAYED_EXTENT, NULL); return ret; } @@ -7995,7 +7982,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, ins.objectid, ins.offset, parent, root_objectid, level, BTRFS_ADD_DELAYED_EXTENT, - extent_op, 0); + extent_op); if (ret) goto out_free_delayed; } @@ -8544,7 +8531,7 @@ skip: } } ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent, - root->root_key.objectid, level - 1, 0, 0); + root->root_key.objectid, level - 1, 0); BUG_ON(ret); /* -ENOMEM */ } btrfs_tree_unlock(next); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 12432057a12e..381be79f779a 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -847,7 +847,7 @@ next_slot: disk_bytenr, num_bytes, 0, root->root_key.objectid, new_key.objectid, - start - extent_offset, 1); + start - extent_offset); BUG_ON(ret); /* -ENOMEM */ } key.offset = start; @@ -925,7 +925,7 @@ delete_extent_item: disk_bytenr, num_bytes, 0, root->root_key.objectid, key.objectid, key.offset - - extent_offset, 0); + extent_offset); BUG_ON(ret); /* -ENOMEM */ inode_sub_bytes(inode, extent_end - key.offset); @@ -1204,7 +1204,7 @@ again: ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0, root->root_key.objectid, - ino, orig_offset, 1); + ino, orig_offset); BUG_ON(ret); /* -ENOMEM */ if (split == start) { @@ -1231,7 +1231,7 @@ again: del_nr++; ret = btrfs_free_extent(trans, root, bytenr, num_bytes, 0, root->root_key.objectid, - ino, orig_offset, 0); + ino, orig_offset); BUG_ON(ret); /* -ENOMEM */ } other_start = 0; @@ -1248,7 +1248,7 @@ again: del_nr++; ret = btrfs_free_extent(trans, root, bytenr, num_bytes, 0, root->root_key.objectid, - ino, orig_offset, 0); + ino, orig_offset); BUG_ON(ret); /* -ENOMEM */ } if (del_nr == 0) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a018e4707dac..6f030c299de8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2595,7 +2595,7 @@ again: ret = btrfs_inc_extent_ref(trans, root, new->bytenr, new->disk_len, 0, backref->root_id, backref->inum, - new->file_pos, 0); /* start - extent_offset */ + new->file_pos); /* start - extent_offset */ if (ret) { btrfs_abort_transaction(trans, root, ret); goto out_free_path; @@ -4541,7 +4541,7 @@ delete: ret = btrfs_free_extent(trans, root, extent_start, extent_num_bytes, 0, btrfs_header_owner(leaf), - ino, extent_offset, 0); + ino, extent_offset); BUG_ON(ret); if (btrfs_should_throttle_delayed_refs(trans, root)) btrfs_async_run_delayed_refs(root, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 7ed033a84212..4df0f2bd9af7 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3206,41 +3206,6 @@ out: return ret; } -/* Helper to check and see if this root currently has a ref on the given disk - * bytenr. If it does then we need to update the quota for this root. This - * doesn't do anything if quotas aren't enabled. - */ -static int check_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - u64 disko) -{ - struct seq_list tree_mod_seq_elem = SEQ_LIST_INIT(tree_mod_seq_elem); - struct ulist *roots; - struct ulist_iterator uiter; - struct ulist_node *root_node = NULL; - int ret; - - if (!root->fs_info->quota_enabled) - return 1; - - btrfs_get_tree_mod_seq(root->fs_info, &tree_mod_seq_elem); - ret = btrfs_find_all_roots(trans, root->fs_info, disko, - tree_mod_seq_elem.seq, &roots); - if (ret < 0) - goto out; - ret = 0; - ULIST_ITER_INIT(&uiter); - while ((root_node = ulist_next(roots, &uiter))) { - if (root_node->val == root->objectid) { - ret = 1; - break; - } - } - ulist_free(roots); -out: - btrfs_put_tree_mod_seq(root->fs_info, &tree_mod_seq_elem); - return ret; -} - static int clone_finish_inode_update(struct btrfs_trans_handle *trans, struct inode *inode, u64 endoff, @@ -3499,9 +3464,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode, u32 nritems; int slot; int ret; - int no_quota; const u64 len = olen_aligned; - u64 last_disko = 0; u64 last_dest_end = destoff; ret = -ENOMEM; @@ -3547,7 +3510,6 @@ static int btrfs_clone(struct inode *src, struct inode *inode, nritems = btrfs_header_nritems(path->nodes[0]); process_slot: - no_quota = 1; if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(BTRFS_I(src)->root, path); if (ret < 0) @@ -3699,35 +3661,13 @@ process_slot: btrfs_set_file_extent_num_bytes(leaf, extent, datal); - /* - * We need to look up the roots that point at - * this bytenr and see if the new root does. If - * it does not we need to make sure we update - * quotas appropriately. - */ - if (disko && root != BTRFS_I(src)->root && - disko != last_disko) { - no_quota = check_ref(trans, root, - disko); - if (no_quota < 0) { - btrfs_abort_transaction(trans, - root, - ret); - btrfs_end_transaction(trans, - root); - ret = no_quota; - goto out; - } - } - if (disko) { inode_add_bytes(inode, datal); ret = btrfs_inc_extent_ref(trans, root, disko, diskl, 0, root->root_key.objectid, btrfs_ino(inode), - new_key.offset - datao, - no_quota); + new_key.offset - datao); if (ret) { btrfs_abort_transaction(trans, root, diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index a7dc45622e90..b4ca5454ef1a 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1716,7 +1716,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans, ret = btrfs_inc_extent_ref(trans, root, new_bytenr, num_bytes, parent, btrfs_header_owner(leaf), - key.objectid, key.offset, 1); + key.objectid, key.offset); if (ret) { btrfs_abort_transaction(trans, root, ret); break; @@ -1724,7 +1724,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans, ret = btrfs_free_extent(trans, root, bytenr, num_bytes, parent, btrfs_header_owner(leaf), - key.objectid, key.offset, 1); + key.objectid, key.offset); if (ret) { btrfs_abort_transaction(trans, root, ret); break; @@ -1900,23 +1900,21 @@ again: ret = btrfs_inc_extent_ref(trans, src, old_bytenr, blocksize, path->nodes[level]->start, - src->root_key.objectid, level - 1, 0, - 1); + src->root_key.objectid, level - 1, 0); BUG_ON(ret); ret = btrfs_inc_extent_ref(trans, dest, new_bytenr, blocksize, 0, dest->root_key.objectid, level - 1, - 0, 1); + 0); BUG_ON(ret); ret = btrfs_free_extent(trans, src, new_bytenr, blocksize, path->nodes[level]->start, - src->root_key.objectid, level - 1, 0, - 1); + src->root_key.objectid, level - 1, 0); BUG_ON(ret); ret = btrfs_free_extent(trans, dest, old_bytenr, blocksize, 0, dest->root_key.objectid, level - 1, - 0, 1); + 0); BUG_ON(ret); btrfs_unlock_up_safe(path, 0); @@ -2745,7 +2743,7 @@ static int do_relocation(struct btrfs_trans_handle *trans, node->eb->start, blocksize, upper->eb->start, btrfs_header_owner(upper->eb), - node->level, 0, 1); + node->level, 0); BUG_ON(ret); ret = btrfs_drop_subtree(trans, root, eb, upper->eb); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 1fffe8845c09..323e12cc9d2f 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -693,7 +693,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, ret = btrfs_inc_extent_ref(trans, root, ins.objectid, ins.offset, 0, root->root_key.objectid, - key->objectid, offset, 0); + key->objectid, offset); if (ret) goto out; } else { -- cgit v1.2.3 From 849ef9286f30c88113906dc35f44a499c0cb385d Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 12 Oct 2015 16:55:54 +0200 Subject: btrfs: check unsupported filters in balance arguments We don't verify that all the balance filter arguments supplemented by the flags are actually known to the kernel. Thus we let it silently pass and do nothing. At the moment this means only the 'limit' filter, but we're going to add a few more soon so it's better to have that fixed. Also in older stable kernels so that it works with newer userspace tools. Cc: stable@vger.kernel.org # 3.16+ Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/ioctl.c | 5 +++++ fs/btrfs/volumes.h | 8 ++++++++ 2 files changed, 13 insertions(+) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 4df0f2bd9af7..7375cf2e6bbf 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4691,6 +4691,11 @@ locked: bctl->flags |= BTRFS_BALANCE_TYPE_MASK; } + if (bctl->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) { + ret = -EINVAL; + goto out_bargs; + } + do_balance: /* * Ownership of bctl and mutually_exclusive_operation_running diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 99c208f6718d..b8e64ea984f1 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -381,6 +381,14 @@ struct map_lookup { #define BTRFS_BALANCE_ARGS_VRANGE (1ULL << 4) #define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5) +#define BTRFS_BALANCE_ARGS_MASK \ + (BTRFS_BALANCE_ARGS_PROFILES | \ + BTRFS_BALANCE_ARGS_USAGE | \ + BTRFS_BALANCE_ARGS_DEVID | \ + BTRFS_BALANCE_ARGS_DRANGE | \ + BTRFS_BALANCE_ARGS_VRANGE | \ + BTRFS_BALANCE_ARGS_LIMIT) + /* * Profile changing flags. When SOFT is set we won't relocate chunk if * it already has the target profile (even though it may be -- cgit v1.2.3