aboutsummaryrefslogtreecommitdiffstats
path: root/fs/btrfs/ctree.h
diff options
context:
space:
mode:
authorOmar Sandoval <osandov@fb.com>2019-10-09 17:59:07 -0700
committerDavid Sterba <dsterba@suse.com>2022-03-14 13:13:51 +0100
commit1881fba89bd5dcd364d2e1bf561912a90a11c21a (patch)
tree8fc56bffbb8cbb23930418ff2b32165ada6ab944 /fs/btrfs/ctree.h
parentbtrfs: add definitions and documentation for encoded I/O ioctls (diff)
downloadlinux-dev-1881fba89bd5dcd364d2e1bf561912a90a11c21a.tar.xz
linux-dev-1881fba89bd5dcd364d2e1bf561912a90a11c21a.zip
btrfs: add BTRFS_IOC_ENCODED_READ ioctl
There are 4 main cases: 1. Inline extents: we copy the data straight out of the extent buffer. 2. Hole/preallocated extents: we fill in zeroes. 3. Regular, uncompressed extents: we read the sectors we need directly from disk. 4. Regular, compressed extents: we read the entire compressed extent from disk and indicate what subset of the decompressed extent is in the file. This initial implementation simplifies a few things that can be improved in the future: - Cases 1, 3, and 4 allocate temporary memory to read into before copying out to userspace. - We don't do read repair, because it turns out that read repair is currently broken for compressed data. - We hold the inode lock during the operation. Note that we don't need to hold the mmap lock. We may race with btrfs_page_mkwrite() and read the old data from before the page was dirtied: btrfs_page_mkwrite btrfs_encoded_read --------------------------------------------------- (enter) (enter) btrfs_wait_ordered_range lock_extent_bits btrfs_page_set_dirty unlock_extent_cached (exit) lock_extent_bits read extent (dirty page hasn't been flushed, so this is the old data) unlock_extent_cached (exit) we read the old data from before the page was dirtied. But, that's true even if we were to hold the mmap lock: btrfs_page_mkwrite btrfs_encoded_read ------------------------------------------------------------------- (enter) (enter) btrfs_inode_lock(BTRFS_ILOCK_MMAP) down_read(i_mmap_lock) (blocked) btrfs_wait_ordered_range lock_extent_bits read extent (page hasn't been dirtied, so this is the old data) unlock_extent_cached btrfs_inode_unlock(BTRFS_ILOCK_MMAP) down_read(i_mmap_lock) returns lock_extent_bits btrfs_page_set_dirty unlock_extent_cached In other words, this is inherently racy, so it's fine that we return the old data in this tiny window. Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'fs/btrfs/ctree.h')
-rw-r--r--fs/btrfs/ctree.h4
1 files changed, 4 insertions, 0 deletions
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 91b27d5eb8cf..22a3fef0a981 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -49,6 +49,7 @@ extern struct kmem_cache *btrfs_free_space_bitmap_cachep;
struct btrfs_ordered_sum;
struct btrfs_ref;
struct btrfs_bio;
+struct btrfs_ioctl_encoded_io_args;
#define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */
@@ -3305,6 +3306,9 @@ 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, bool uptodate);
+ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
+ struct btrfs_ioctl_encoded_io_args *encoded);
+
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;