Btrfs: add basic DIO read/write support
This provides basic DIO support for reading and writing. It does not do the
work to recover from mismatching checksums, that will come later. A few design
changes have been made from Jim's code (sorry Jim!)
1) Use the generic direct-io code. Jim originally re-wrote all the generic DIO
code in order to account for all of BTRFS's oddities, but thanks to that work it
seems like the best bet is to just ignore compression and such and just opt to
fallback on buffered IO.
2) Fallback on buffered IO for compressed or inline extents. Jim's code did
it's own buffering to make dio with compressed extents work. Now we just
fallback onto normal buffered IO.
3) Use ordered extents for the writes so that all of the
lock_extent()
lookup_ordered()
type checks continue to work.
4) Do the lock_extent() lookup_ordered() loop in readpage so we don't race with
DIO writes.
I've tested this with fsx and everything works great. This patch depends on my
dio and filemap.c patches to work. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 21aead3..a562a25 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -149,13 +149,14 @@
}
-int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode,
- struct bio *bio, u32 *dst)
+static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
+ struct inode *inode, struct bio *bio,
+ u64 logical_offset, u32 *dst, int dio)
{
u32 sum;
struct bio_vec *bvec = bio->bi_io_vec;
int bio_index = 0;
- u64 offset;
+ u64 offset = 0;
u64 item_start_offset = 0;
u64 item_last_offset = 0;
u64 disk_bytenr;
@@ -174,8 +175,11 @@
WARN_ON(bio->bi_vcnt <= 0);
disk_bytenr = (u64)bio->bi_sector << 9;
+ if (dio)
+ offset = logical_offset;
while (bio_index < bio->bi_vcnt) {
- offset = page_offset(bvec->bv_page) + bvec->bv_offset;
+ if (!dio)
+ offset = page_offset(bvec->bv_page) + bvec->bv_offset;
ret = btrfs_find_ordered_sum(inode, offset, disk_bytenr, &sum);
if (ret == 0)
goto found;
@@ -238,6 +242,7 @@
else
set_state_private(io_tree, offset, sum);
disk_bytenr += bvec->bv_len;
+ offset += bvec->bv_len;
bio_index++;
bvec++;
}
@@ -245,6 +250,18 @@
return 0;
}
+int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode,
+ struct bio *bio, u32 *dst)
+{
+ return __btrfs_lookup_bio_sums(root, inode, bio, 0, dst, 0);
+}
+
+int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode,
+ struct bio *bio, u64 offset, u32 *dst)
+{
+ return __btrfs_lookup_bio_sums(root, inode, bio, offset, dst, 1);
+}
+
int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
struct list_head *list)
{