xfs: create a separate cow extent size hint for the allocator

Create a per-inode extent size allocator hint for copy-on-write.  This
hint is separate from the existing extent size hint so that CoW can
take advantage of the fragmentation-reducing properties of extent size
hints without disabling delalloc for regular writes.

The extent size hint that's fed to the allocator during a copy on
write operation is the greater of the cowextsize and regular extsize
hint.

During reflink, if we're sharing the entire source file to the entire
destination file and the destination file doesn't already have a
cowextsize hint, propagate the source file's cowextsize hint to the
destination file.

Furthermore, zero the bulkstat buffer prior to setting the fields
so that we don't copy kernel memory contents into userspace.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>

1 files changed, 33 insertions, 0 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index f072f48b3c04..09640bdd3e44 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -78,6 +78,27 @@ xfs_get_extsz_hint(
 }
 
 /*
+ * Helper function to extract CoW extent size hint from inode.
+ * Between the extent size hint and the CoW extent size hint, we
+ * return the greater of the two.
+ */
+xfs_extlen_t
+xfs_get_cowextsz_hint(
+	struct xfs_inode	*ip)
+{
+	xfs_extlen_t		a, b;
+
+	a = 0;
+	if (ip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)
+		a = ip->i_d.di_cowextsize;
+	b = xfs_get_extsz_hint(ip);
+
+	if (a > b)
+		return a;
+	return b;
+}
+
+/*
  * These two are wrapper routines around the xfs_ilock() routine used to
  * centralize some grungy code.  They are used in places that wish to lock the
  * inode solely for reading the extents.  The reason these places can't just
@@ -652,6 +673,8 @@ _xfs_dic2xflags(
 	if (di_flags2 & XFS_DIFLAG2_ANY) {
 		if (di_flags2 & XFS_DIFLAG2_DAX)
 			flags |= FS_XFLAG_DAX;
+		if (di_flags2 & XFS_DIFLAG2_COWEXTSIZE)
+			flags |= FS_XFLAG_COWEXTSIZE;
 	}
 
 	if (has_attr)
@@ -835,6 +858,7 @@ xfs_ialloc(
 	if (ip->i_d.di_version == 3) {
 		inode->i_version = 1;
 		ip->i_d.di_flags2 = 0;
+		ip->i_d.di_cowextsize = 0;
 		ip->i_d.di_crtime.t_sec = (__int32_t)tv.tv_sec;
 		ip->i_d.di_crtime.t_nsec = (__int32_t)tv.tv_nsec;
 	}
@@ -897,6 +921,15 @@ xfs_ialloc(
 			ip->i_d.di_flags |= di_flags;
 			ip->i_d.di_flags2 |= di_flags2;
 		}
+		if (pip &&
+		    (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) &&
+		    pip->i_d.di_version == 3 &&
+		    ip->i_d.di_version == 3) {
+			if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
+				ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+				ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
+			}
+		}
 		/* FALLTHROUGH */
 	case S_IFLNK:
 		ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;