From 38622010a6de3a62cc72688348548854ed82dcf5 Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Mon, 15 Aug 2022 13:54:28 -0700 Subject: btrfs: send: add support for fs-verity Preserve the fs-verity status of a btrfs file across send/recv. There is no facility for installing the Merkle tree contents directly on the receiving filesystem, so we package up the parameters used to enable verity found in the verity descriptor. This gives the receive side enough information to properly enable verity again. Note that this means that receive will have to re-compute the whole Merkle tree, similar to how compression worked before encoded_write. Since the file becomes read-only after verity is enabled, it is important that verity is added to the send stream after any file writes. Therefore, when we process a verity item, merely note that it happened, then actually create the command in the send stream during 'finish_inode_if_needed'. This also creates V3 of the send stream format, without any format changes besides adding the new commands and attributes. Signed-off-by: Boris Burkov Signed-off-by: David Sterba --- include/linux/fsverity.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 7af030fa3c36..40f14e5fed9d 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -22,6 +22,9 @@ */ #define FS_VERITY_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE +/* Arbitrary limit to bound the kmalloc() size. Can be changed. */ +#define FS_VERITY_MAX_DESCRIPTOR_SIZE 16384 + /* Verity operations for filesystems */ struct fsverity_operations { -- cgit v1.2.3 From 1c56ab991903dce60e905a08f431c0e6f79b9b9e Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 9 Aug 2022 13:02:18 +0800 Subject: btrfs: separate BLOCK_GROUP_TREE compat RO flag from EXTENT_TREE_V2 The problem of long mount time caused by block group item search is already known for some time, and the solution of block group tree has been proposed. There is really no need to bound this feature into extent tree v2, just introduce compat RO flag, BLOCK_GROUP_TREE, to correctly solve the problem. All the code handling block group root is already in the upstream kernel, thus this patch really only needs to introduce the new compat RO flag. This patch introduces one extra artificial limitation on block group tree feature, that free space cache v2 and no-holes feature must be enabled to use this new compat RO feature. This artificial requirement is mostly to reduce the test combinations, and can be a guideline for future features, to mostly rely on the latest default features. Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 7ada84e4a3ed..5655e89b962b 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -290,6 +290,12 @@ struct btrfs_ioctl_fs_info_args { #define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID (1ULL << 1) #define BTRFS_FEATURE_COMPAT_RO_VERITY (1ULL << 2) +/* + * Put all block group items into a dedicated block group tree, greatly + * reducing mount time for large filesystem due to better locality. + */ +#define BTRFS_FEATURE_COMPAT_RO_BLOCK_GROUP_TREE (1ULL << 3) + #define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF (1ULL << 0) #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (1ULL << 1) #define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS (1ULL << 2) -- cgit v1.2.3 From e71564c0438a1c0cffc5c8eb302ec5d849103b08 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 24 Aug 2022 09:14:06 +0800 Subject: btrfs: introduce BTRFS_QGROUP_STATUS_FLAGS_MASK for later expansion Currently we only have 3 qgroup flags: - BTRFS_QGROUP_STATUS_FLAG_ON - BTRFS_QGROUP_STATUS_FLAG_RESCAN - BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT These flags match the on-disk flags used in btrfs_qgroup_status. But we're going to introduce extra runtime flags which will not reach disks. So here we introduce a new mask, BTRFS_QGROUP_STATUS_FLAGS_MASK, to make sure only those flags can reach disks. Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs_tree.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 5f32a2a495dc..1f7a38ec6ac3 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -965,6 +965,10 @@ static inline __u16 btrfs_qgroup_level(__u64 qgroupid) */ #define BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT (1ULL << 2) +#define BTRFS_QGROUP_STATUS_FLAGS_MASK (BTRFS_QGROUP_STATUS_FLAG_ON | \ + BTRFS_QGROUP_STATUS_FLAG_RESCAN | \ + BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) + #define BTRFS_QGROUP_STATUS_VERSION 1 struct btrfs_qgroup_status_item { -- cgit v1.2.3 From 87c11705cc94d6b822551e88d8d4579fe0370051 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 9 Sep 2022 17:53:16 -0400 Subject: btrfs: convert the io_failure_tree to a plain rb_tree We still have this oddity of stashing the io_failure_record in the extent state for the io_failure_tree, which is leftover from when we used to stuff private pointers in extent_io_trees. However this doesn't make a lot of sense for the io failure records, we can simply use a normal rb_tree for this. This will allow us to further simplify the extent_io_tree code by removing the io_failure_rec pointer from the extent state. Convert the io_failure_tree to an rb tree + spinlock in the inode, and then use our rb tree simple helpers to insert and find failed records. This greatly cleans up this code and makes it easier to separate out the extent_io_tree code. Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 73df80d462dc..4db905311d67 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -84,7 +84,6 @@ struct raid56_bio_trace_info; EM( IO_TREE_FS_EXCLUDED_EXTENTS, "EXCLUDED_EXTENTS") \ EM( IO_TREE_BTREE_INODE_IO, "BTREE_INODE_IO") \ EM( IO_TREE_INODE_IO, "INODE_IO") \ - EM( IO_TREE_INODE_IO_FAILURE, "INODE_IO_FAILURE") \ EM( IO_TREE_RELOC_BLOCKS, "RELOC_BLOCKS") \ EM( IO_TREE_TRANS_DIRTY_PAGES, "TRANS_DIRTY_PAGES") \ EM( IO_TREE_ROOT_DIRTY_LOG_PAGES, "ROOT_DIRTY_LOG_PAGES") \ -- cgit v1.2.3 From bd86a532b26355695e87a6cf394d9c8bd24686c9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 7 Sep 2022 13:17:41 +0200 Subject: btrfs: stop tracking failed reads in the I/O tree There is a separate I/O failure tree to track the fail reads, so remove the extra EXTENT_DAMAGED bit in the I/O tree as it's set but never used. Reviewed-by: Josef Bacik Reviewed-by: Qu Wenruo Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 4db905311d67..ed50e81174bf 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -153,7 +153,6 @@ FLUSH_STATES { EXTENT_NODATASUM, "NODATASUM"}, \ { EXTENT_CLEAR_META_RESV, "CLEAR_META_RESV"}, \ { EXTENT_NEED_WAIT, "NEED_WAIT"}, \ - { EXTENT_DAMAGED, "DAMAGED"}, \ { EXTENT_NORESERVE, "NORESERVE"}, \ { EXTENT_QGROUP_RESERVED, "QGROUP_RESERVED"}, \ { EXTENT_CLEAR_DATA_RESV, "CLEAR_DATA_RESV"}, \ -- cgit v1.2.3