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>

6 files changed, 17 insertions, 6 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index e4bf2c4..9702f4c 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3666,7 +3666,9 @@ xfs_bmap_btalloc(
 	else if (mp->m_dalign)
 		stripe_align = mp->m_dalign;
 
-	if (xfs_alloc_is_userdata(ap->datatype))
+	if (ap->flags & XFS_BMAPI_COWFORK)
+		align = xfs_get_cowextsz_hint(ap->ip);
+	else if (xfs_alloc_is_userdata(ap->datatype))
 		align = xfs_get_extsz_hint(ap->ip);
 	if (unlikely(align)) {
 		error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
@@ -4192,7 +4194,10 @@ xfs_bmapi_reserve_delalloc(
 		alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff);
 
 	/* Figure out the extent size, adjust alen */
-	extsz = xfs_get_extsz_hint(ip);
+	if (whichfork == XFS_COW_FORK)
+		extsz = xfs_get_cowextsz_hint(ip);
+	else
+		extsz = xfs_get_extsz_hint(ip);
 	if (extsz) {
 		error = xfs_bmap_extsize_align(mp, got, prev, extsz, rt, eof,
 					       1, 0, &aoff, &alen);
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 777fa97..5e04ea2 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -901,7 +901,8 @@ typedef struct xfs_dinode {
 	__be64		di_changecount;	/* number of attribute changes */
 	__be64		di_lsn;		/* flush sequence */
 	__be64		di_flags2;	/* more random flags */
-	__u8		di_pad2[16];	/* more padding for future expansion */
+	__be32		di_cowextsize;	/* basic cow extent size for file */
+	__u8		di_pad2[12];	/* more padding for future expansion */
 
 	/* fields only written to during inode creation */
 	xfs_timestamp_t	di_crtime;	/* time created */
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 3d1efe5..b72dc82 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -278,7 +278,8 @@ typedef struct xfs_bstat {
 #define	bs_projid	bs_projid_lo	/* (previously just bs_projid)	*/
 	__u16		bs_forkoff;	/* inode fork offset in bytes	*/
 	__u16		bs_projid_hi;	/* higher part of project id	*/
-	unsigned char	bs_pad[10];	/* pad space, unused		*/
+	unsigned char	bs_pad[6];	/* pad space, unused		*/
+	__u32		bs_cowextsize;	/* cow extent size		*/
 	__u32		bs_dmevmask;	/* DMIG event mask		*/
 	__u16		bs_dmstate;	/* DMIG state info		*/
 	__u16		bs_aextents;	/* attribute number of extents	*/
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 4b9769e..a3e8038 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -256,6 +256,7 @@ xfs_inode_from_disk(
 		to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec);
 		to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec);
 		to->di_flags2 = be64_to_cpu(from->di_flags2);
+		to->di_cowextsize = be32_to_cpu(from->di_cowextsize);
 	}
 }
 
@@ -305,7 +306,7 @@ xfs_inode_to_disk(
 		to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
 		to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
 		to->di_flags2 = cpu_to_be64(from->di_flags2);
-
+		to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
 		to->di_ino = cpu_to_be64(ip->i_ino);
 		to->di_lsn = cpu_to_be64(lsn);
 		memset(to->di_pad2, 0, sizeof(to->di_pad2));
@@ -357,6 +358,7 @@ xfs_log_dinode_to_disk(
 		to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
 		to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
 		to->di_flags2 = cpu_to_be64(from->di_flags2);
+		to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
 		to->di_ino = cpu_to_be64(from->di_ino);
 		to->di_lsn = cpu_to_be64(from->di_lsn);
 		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 7c4dd32..62d9d46 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -47,6 +47,7 @@ struct xfs_icdinode {
 	__uint16_t	di_flags;	/* random flags, XFS_DIFLAG_... */
 
 	__uint64_t	di_flags2;	/* more random flags */
+	__uint32_t	di_cowextsize;	/* basic cow extent size for file */
 
 	xfs_ictimestamp_t di_crtime;	/* time created */
 };
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 5dd7c2e..364ce6f 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -423,7 +423,8 @@ struct xfs_log_dinode {
 	__uint64_t	di_changecount;	/* number of attribute changes */
 	xfs_lsn_t	di_lsn;		/* flush sequence */
 	__uint64_t	di_flags2;	/* more random flags */
-	__uint8_t	di_pad2[16];	/* more padding for future expansion */
+	__uint32_t	di_cowextsize;	/* basic cow extent size for file */
+	__uint8_t	di_pad2[12];	/* more padding for future expansion */
 
 	/* fields only written to during inode creation */
 	xfs_ictimestamp_t di_crtime;	/* time created */