btrfs: reset last_reflink_trans after fsyncing inode

When an inode has a last_reflink_trans matching the current transaction,
we have to take special care when logging its checksums in order to
avoid getting checksum items with overlapping ranges in a log tree,
which could result in missing checksums after log replay (more on that
in the changelogs of commit 40e046acbd2f36 ("Btrfs: fix missing data
checksums after replaying a log tree") and commit e289f03ea79bbc ("btrfs:
fix corrupt log due to concurrent fsync of inodes with shared extents")).
We also need to make sure a full fsync will copy all old file extent
items it finds in modified leaves, because they might have been copied
from some other inode.

However once we fsync an inode, we don't need to keep paying the price of
that extra special care in future fsyncs done in the same transaction,
unless the inode is used for another reflink operation or the full sync
flag is set on it (truncate, failure to allocate extent maps for holes,
and other exceptional and infrequent cases).

So after we fsync an inode reset its last_unlink_trans to zero. In case
another reflink happens, we continue to update the last_reflink_trans of
the inode, just as before. Also set last_reflink_trans to the generation
of the last transaction that modified the inode whenever we need to set
the full sync flag on the inode, just like when we need to load an inode
from disk after eviction.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 5 insertions, 7 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 53f46d5c78c7..2e7143ff5523 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -418,7 +418,7 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 size,
 		goto out;
 	}
 
-	set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags);
+	btrfs_set_inode_full_sync(inode);
 out:
 	/*
 	 * Don't forget to free the reserved space, as for inlined extent
@@ -4911,8 +4911,7 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 						cur_offset + hole_size - 1, 0);
 			hole_em = alloc_extent_map();
 			if (!hole_em) {
-				set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-					&inode->runtime_flags);
+				btrfs_set_inode_full_sync(inode);
 				goto next;
 			}
 			hole_em->start = cur_offset;
@@ -6165,7 +6164,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	 * sync since it will be a full sync anyway and this will blow away the
 	 * old info in the log.
 	 */
-	set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
+	btrfs_set_inode_full_sync(BTRFS_I(inode));
 
 	key[0].objectid = objectid;
 	key[0].type = BTRFS_INODE_ITEM_KEY;
@@ -8767,7 +8766,7 @@ out:
 	 * extents beyond i_size to drop.
 	 */
 	if (control.extents_found > 0)
-		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
+		btrfs_set_inode_full_sync(BTRFS_I(inode));
 
 	return ret;
 }
@@ -9975,8 +9974,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 
 		em = alloc_extent_map();
 		if (!em) {
-			set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-				&BTRFS_I(inode)->runtime_flags);
+			btrfs_set_inode_full_sync(BTRFS_I(inode));
 			goto next;
 		}