[PATCH RESEND x3 v9 6/9] btrfs: support different disk extent size for delalloc

[Omar Sandoval <osandov@osandov.com>]

From: Omar Sandoval <osandov@fb.com>

Currently, we always reserve the same extent size in the file and extent
size on disk for delalloc because the former is the worst case for the
latter. For RWF_ENCODED writes, we know the exact size of the extent on
disk, which may be less than or greater than (for bookends) the size in
the file. Add a disk_num_bytes parameter to
btrfs_delalloc_reserve_metadata() so that we can reserve the correct
amount of csum bytes. No functional change.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
---
 fs/btrfs/ctree.h          |  3 ++-
 fs/btrfs/delalloc-space.c | 18 ++++++++++--------
 fs/btrfs/file.c           |  3 ++-
 fs/btrfs/inode.c          |  2 +-
 fs/btrfs/relocation.c     |  4 ++--
 5 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index dd37ec16f22a..86856889188d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2796,7 +2796,8 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root,
 				      struct btrfs_block_rsv *rsv);
 void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);
 
-int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
+int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
+				    u64 disk_num_bytes);
 u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
 int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
 				   u64 start, u64 end);
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 2059d1504149..143650004991 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -267,11 +267,11 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 }
 
 static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
-				    u64 num_bytes, u64 *meta_reserve,
-				    u64 *qgroup_reserve)
+				    u64 num_bytes, u64 disk_num_bytes,
+				    u64 *meta_reserve, u64 *qgroup_reserve)
 {
 	u64 nr_extents = count_max_extents(num_bytes);
-	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, num_bytes);
+	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes);
 	u64 inode_update = btrfs_calc_metadata_size(fs_info, 1);
 
 	*meta_reserve = btrfs_calc_insert_metadata_size(fs_info,
@@ -285,7 +285,8 @@ static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
 	*qgroup_reserve = nr_extents * fs_info->nodesize;
 }
 
-int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
+int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
+				    u64 disk_num_bytes)
 {
 	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -315,6 +316,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	}
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
+	disk_num_bytes = ALIGN(disk_num_bytes, fs_info->sectorsize);
 
 	/*
 	 * We always want to do it this way, every other way is wrong and ends
@@ -326,8 +328,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	 * everything out and try again, which is bad.  This way we just
 	 * over-reserve slightly, and clean up the mess when we are done.
 	 */
-	calc_inode_reservations(fs_info, num_bytes, &meta_reserve,
-				&qgroup_reserve);
+	calc_inode_reservations(fs_info, num_bytes, disk_num_bytes,
+				&meta_reserve, &qgroup_reserve);
 	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true);
 	if (ret)
 		return ret;
@@ -346,7 +348,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	spin_lock(&inode->lock);
 	nr_extents = count_max_extents(num_bytes);
 	btrfs_mod_outstanding_extents(inode, nr_extents);
-	inode->csum_bytes += num_bytes;
+	inode->csum_bytes += disk_num_bytes;
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
 	spin_unlock(&inode->lock);
 
@@ -451,7 +453,7 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode,
 	ret = btrfs_check_data_free_space(inode, reserved, start, len);
 	if (ret < 0)
 		return ret;
-	ret = btrfs_delalloc_reserve_metadata(inode, len);
+	ret = btrfs_delalloc_reserve_metadata(inode, len, len);
 	if (ret < 0)
 		btrfs_free_reserved_data_space(inode, *reserved, start, len);
 	return ret;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 28a05ba47060..4e13c481b21e 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1730,7 +1730,8 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
 					 fs_info->sectorsize);
 		WARN_ON(reserve_bytes == 0);
 		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
-				reserve_bytes);
+						      reserve_bytes,
+						      reserve_bytes);
 		if (ret) {
 			if (!only_release_metadata)
 				btrfs_free_reserved_data_space(BTRFS_I(inode),
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f59ad09abb61..fcf685fd4eff 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4898,7 +4898,7 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
 			goto out;
 		}
 	}
-	ret = btrfs_delalloc_reserve_metadata(inode, blocksize);
+	ret = btrfs_delalloc_reserve_metadata(inode, blocksize, blocksize);
 	if (ret < 0) {
 		if (!only_release_metadata)
 			btrfs_free_reserved_data_space(inode, data_reserved,
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 420a89869889..173d426ece30 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2922,8 +2922,8 @@ static int relocate_file_extent_cluster(struct inode *inode,
 	index = (cluster->start - offset) >> PAGE_SHIFT;
 	last_index = (cluster->end - offset) >> PAGE_SHIFT;
 	while (index <= last_index) {
-		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
-				PAGE_SIZE);
+		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), PAGE_SIZE,
+						      PAGE_SIZE);
 		if (ret)
 			goto out;
 
-- 
2.32.0