aboutsummaryrefslogtreecommitdiff
path: root/fs/btrfs/ctree.h
diff options
context:
space:
mode:
authorLinus Torvalds <[email protected]>2021-08-31 09:41:22 -0700
committerLinus Torvalds <[email protected]>2021-08-31 09:41:22 -0700
commit87045e6546078dae215d1bd3b2bc82b3ada3ca77 (patch)
treef3d816b9834ca959514f6e399fb9f505871d2729 /fs/btrfs/ctree.h
parent9c849ce86e0fa93a218614eac562ace44053d7ce (diff)
parent0d977e0eba234e01a60bdde27314dc21374201b3 (diff)
Merge tag 'for-5.15-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs updates from David Sterba: "The highlights of this round are integrations with fs-verity and idmapped mounts, the rest is usual mix of minor improvements, speedups and cleanups. There are some patches outside of btrfs, namely updating some VFS interfaces, all straightforward and acked. Features: - fs-verity support, using standard ioctls, backward compatible with read-only limitation on inodes with previously enabled fs-verity - idmapped mount support - make mount with rescue=ibadroots more tolerant to partially damaged trees - allow raid0 on a single device and raid10 on two devices, degenerate cases but might be useful as an intermediate step during conversion to other profiles - zoned mode block group auto reclaim can be disabled via sysfs knob Performance improvements: - continue readahead of node siblings even if target node is in memory, could speed up full send (on sample test +11%) - batching of delayed items can speed up creating many files - fsync/tree-log speedups - avoid unnecessary work (gains +2% throughput, -2% run time on sample load) - reduced lock contention on renames (on dbench +4% throughput, up to -30% latency) Fixes: - various zoned mode fixes - preemptive flushing threshold tuning, avoid excessive work on almost full filesystems Core: - continued subpage support, preparation for implementing remaining features like compression and defragmentation; with some limitations, write is now enabled on 64K page systems with 4K sectors, still considered experimental - no readahead on compressed reads - inline extents disabled - disabled raid56 profile conversion and mount - improved flushing logic, fixing early ENOSPC on some workloads - inode flags have been internally split to read-only and read-write incompat bit parts, used by fs-verity - new tree items for fs-verity - descriptor item - Merkle tree item - inode operations extended to be namespace-aware - cleanups and refactoring Generic code changes: - fs: new export filemap_fdatawrite_wbc - fs: removed sync_inode - block: bio_trim argument type fixups - vfs: add namespace-aware lookup" * tag 'for-5.15-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (114 commits) btrfs: reset replace target device to allocation state on close btrfs: zoned: fix ordered extent boundary calculation btrfs: do not do preemptive flushing if the majority is global rsv btrfs: reduce the preemptive flushing threshold to 90% btrfs: tree-log: check btrfs_lookup_data_extent return value btrfs: avoid unnecessarily logging directories that had no changes btrfs: allow idmapped mount btrfs: handle ACLs on idmapped mounts btrfs: allow idmapped INO_LOOKUP_USER ioctl btrfs: allow idmapped SUBVOL_SETFLAGS ioctl btrfs: allow idmapped SET_RECEIVED_SUBVOL ioctls btrfs: relax restrictions for SNAP_DESTROY_V2 with subvolids btrfs: allow idmapped SNAP_DESTROY ioctls btrfs: allow idmapped SNAP_CREATE/SUBVOL_CREATE ioctls btrfs: check whether fsgid/fsuid are mapped during subvolume creation btrfs: allow idmapped permission inode op btrfs: allow idmapped setattr inode op btrfs: allow idmapped tmpfile inode op btrfs: allow idmapped symlink inode op btrfs: allow idmapped mkdir inode op ...
Diffstat (limited to 'fs/btrfs/ctree.h')
-rw-r--r--fs/btrfs/ctree.h94
1 files changed, 69 insertions, 25 deletions
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index e5e53e592d4f..f07c82fafa04 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -281,7 +281,8 @@ struct btrfs_super_block {
#define BTRFS_FEATURE_COMPAT_RO_SUPP \
(BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE | \
- BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID)
+ BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID | \
+ BTRFS_FEATURE_COMPAT_RO_VERITY)
#define BTRFS_FEATURE_COMPAT_RO_SAFE_SET 0ULL
#define BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR 0ULL
@@ -1012,8 +1013,6 @@ struct btrfs_fs_info {
u64 zoned;
};
- /* Max size to emit ZONE_APPEND write command */
- u64 max_zone_append_size;
struct mutex zoned_meta_io_lock;
spinlock_t treelog_bg_lock;
u64 treelog_bg;
@@ -1484,20 +1483,20 @@ do { \
/*
* Inode flags
*/
-#define BTRFS_INODE_NODATASUM (1 << 0)
-#define BTRFS_INODE_NODATACOW (1 << 1)
-#define BTRFS_INODE_READONLY (1 << 2)
-#define BTRFS_INODE_NOCOMPRESS (1 << 3)
-#define BTRFS_INODE_PREALLOC (1 << 4)
-#define BTRFS_INODE_SYNC (1 << 5)
-#define BTRFS_INODE_IMMUTABLE (1 << 6)
-#define BTRFS_INODE_APPEND (1 << 7)
-#define BTRFS_INODE_NODUMP (1 << 8)
-#define BTRFS_INODE_NOATIME (1 << 9)
-#define BTRFS_INODE_DIRSYNC (1 << 10)
-#define BTRFS_INODE_COMPRESS (1 << 11)
-
-#define BTRFS_INODE_ROOT_ITEM_INIT (1 << 31)
+#define BTRFS_INODE_NODATASUM (1U << 0)
+#define BTRFS_INODE_NODATACOW (1U << 1)
+#define BTRFS_INODE_READONLY (1U << 2)
+#define BTRFS_INODE_NOCOMPRESS (1U << 3)
+#define BTRFS_INODE_PREALLOC (1U << 4)
+#define BTRFS_INODE_SYNC (1U << 5)
+#define BTRFS_INODE_IMMUTABLE (1U << 6)
+#define BTRFS_INODE_APPEND (1U << 7)
+#define BTRFS_INODE_NODUMP (1U << 8)
+#define BTRFS_INODE_NOATIME (1U << 9)
+#define BTRFS_INODE_DIRSYNC (1U << 10)
+#define BTRFS_INODE_COMPRESS (1U << 11)
+
+#define BTRFS_INODE_ROOT_ITEM_INIT (1U << 31)
#define BTRFS_INODE_FLAG_MASK \
(BTRFS_INODE_NODATASUM | \
@@ -1514,6 +1513,10 @@ do { \
BTRFS_INODE_COMPRESS | \
BTRFS_INODE_ROOT_ITEM_INIT)
+#define BTRFS_INODE_RO_VERITY (1U << 0)
+
+#define BTRFS_INODE_RO_FLAG_MASK (BTRFS_INODE_RO_VERITY)
+
struct btrfs_map_token {
struct extent_buffer *eb;
char *kaddr;
@@ -2781,10 +2784,11 @@ enum btrfs_flush_state {
FLUSH_DELAYED_REFS = 4,
FLUSH_DELALLOC = 5,
FLUSH_DELALLOC_WAIT = 6,
- ALLOC_CHUNK = 7,
- ALLOC_CHUNK_FORCE = 8,
- RUN_DELAYED_IPUTS = 9,
- COMMIT_TRANS = 10,
+ FLUSH_DELALLOC_FULL = 7,
+ ALLOC_CHUNK = 8,
+ ALLOC_CHUNK_FORCE = 9,
+ RUN_DELAYED_IPUTS = 10,
+ COMMIT_TRANS = 11,
};
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
@@ -2901,10 +2905,13 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans,
return btrfs_insert_empty_items(trans, root, path, key, &data_size, 1);
}
-int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path);
int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path,
u64 time_seq);
+
+int btrfs_search_backwards(struct btrfs_root *root, struct btrfs_key *key,
+ struct btrfs_path *path);
+
static inline int btrfs_next_old_item(struct btrfs_root *root,
struct btrfs_path *p, u64 time_seq)
{
@@ -2913,6 +2920,18 @@ static inline int btrfs_next_old_item(struct btrfs_root *root,
return btrfs_next_old_leaf(root, p, time_seq);
return 0;
}
+
+/*
+ * Search the tree again to find a leaf with greater keys.
+ *
+ * Returns 0 if it found something or 1 if there are no greater leaves.
+ * Returns < 0 on error.
+ */
+static inline int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path)
+{
+ return btrfs_next_old_leaf(root, path, 0);
+}
+
static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p)
{
return btrfs_next_old_item(root, p, 0);
@@ -3145,7 +3164,8 @@ int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
struct extent_state **cached_state);
int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
struct btrfs_root *new_root,
- struct btrfs_root *parent_root);
+ struct btrfs_root *parent_root,
+ struct user_namespace *mnt_userns);
void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
unsigned *bits);
void btrfs_clear_delalloc_extent(struct inode *inode,
@@ -3194,10 +3214,10 @@ int btrfs_prealloc_file_range_trans(struct inode *inode,
int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page,
u64 start, u64 end, int *page_started, unsigned long *nr_written,
struct writeback_control *wbc);
-int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end);
+int btrfs_writepage_cow_fixup(struct page *page);
void btrfs_writepage_endio_finish_ordered(struct btrfs_inode *inode,
struct page *page, u64 start,
- u64 end, int uptodate);
+ u64 end, bool uptodate);
extern const struct dentry_operations btrfs_dentry_operations;
extern const struct iomap_ops btrfs_dio_iomap_ops;
extern const struct iomap_dio_ops btrfs_dio_ops;
@@ -3779,6 +3799,30 @@ static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info)
return signal_pending(current);
}
+/* verity.c */
+#ifdef CONFIG_FS_VERITY
+
+extern const struct fsverity_operations btrfs_verityops;
+int btrfs_drop_verity_items(struct btrfs_inode *inode);
+
+BTRFS_SETGET_FUNCS(verity_descriptor_encryption, struct btrfs_verity_descriptor_item,
+ encryption, 8);
+BTRFS_SETGET_FUNCS(verity_descriptor_size, struct btrfs_verity_descriptor_item,
+ size, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_verity_descriptor_encryption,
+ struct btrfs_verity_descriptor_item, encryption, 8);
+BTRFS_SETGET_STACK_FUNCS(stack_verity_descriptor_size,
+ struct btrfs_verity_descriptor_item, size, 64);
+
+#else
+
+static inline int btrfs_drop_verity_items(struct btrfs_inode *inode)
+{
+ return 0;
+}
+
+#endif
+
/* Sanity test specific functions */
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
void btrfs_test_destroy_inode(struct inode *inode);